xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
انشعاب 0
کد مسائل تقاضاهای واکشی Actions Packages پروژه‌ها انتشارها دانشنامه فعالیت

Merge branch 'linus' into x86/urgent

فهرست منبع 
Merge reason: Merge upstream commits to avoid conflicts in upcoming patches.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Ingo Molnar
2011-03-18 10:38:53 +01:00
والد 1eda75c131 016aa2ed1c
کامیت 8dd8997d2c
549فایلهای تغییر یافته به همراه21085 افزوده شده و 13382 حذف شده
دانلود پرونده وصله دانلود فایل تغییرات diff Expand all files Collapse all files

5
arch/x86/kernel/Makefile
مشاهده پرونده

@@ -66,9 +66,9 @@ obj-$(CONFIG_PCI) += early-quirks.o
apm-y := apm_32.o
obj-$(CONFIG_APM) += apm.o
obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_SMP) += smpboot.o tsc_sync.o
obj-$(CONFIG_SMP) += smpboot.o
obj-$(CONFIG_SMP) += tsc_sync.o
obj-$(CONFIG_SMP) += setup_percpu.o
obj-$(CONFIG_X86_64_SMP) += tsc_sync.o
obj-$(CONFIG_X86_TRAMPOLINE) += trampoline_$(BITS).o
obj-$(CONFIG_X86_MPPARSE) += mpparse.o
obj-y += apic/
@@ -109,6 +109,7 @@ obj-$(CONFIG_MICROCODE) += microcode.o
obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o
obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o
obj-$(CONFIG_OF) += devicetree.o
###
# 64 bit specific files

8
arch/x86/kernel/acpi/boot.c
مشاهده پرونده

@@ -595,14 +595,8 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
nid = acpi_get_node(handle);
if (nid == -1 || !node_online(nid))
return;
#ifdef CONFIG_X86_64
apicid_to_node[physid] = nid;
set_apicid_to_node(physid, nid);
numa_set_node(cpu, nid);
#else /* CONFIG_X86_32 */
apicid_2_node[physid] = nid;
cpu_to_node_map[cpu] = nid;
#endif
#endif
}

58
arch/x86/kernel/apb_timer.c
مشاهده پرونده

@@ -508,64 +508,12 @@ static int apbt_next_event(unsigned long delta,
return 0;
}
/*
* APB timer clock is not in sync with pclk on Langwell, which translates to
* unreliable read value caused by sampling error. the error does not add up
* overtime and only happens when sampling a 0 as a 1 by mistake. so the time
* would go backwards. the following code is trying to prevent time traveling
* backwards. little bit paranoid.
*/
static cycle_t apbt_read_clocksource(struct clocksource *cs)
{
unsigned long t0, t1, t2;
static unsigned long last_read;
unsigned long current_count;
bad_count:
t1 = apbt_readl(phy_cs_timer_id,
APBTMR_N_CURRENT_VALUE);
t2 = apbt_readl(phy_cs_timer_id,
APBTMR_N_CURRENT_VALUE);
if (unlikely(t1 < t2)) {
pr_debug("APBT: read current count error %lx:%lx:%lx\n",
t1, t2, t2 - t1);
goto bad_count;
}
/*
* check against cached last read, makes sure time does not go back.
* it could be a normal rollover but we will do tripple check anyway
*/
if (unlikely(t2 > last_read)) {
/* check if we have a normal rollover */
unsigned long raw_intr_status =
apbt_readl_reg(APBTMRS_RAW_INT_STATUS);
/*
* cs timer interrupt is masked but raw intr bit is set if
* rollover occurs. then we read EOI reg to clear it.
*/
if (raw_intr_status & (1 << phy_cs_timer_id)) {
apbt_readl(phy_cs_timer_id, APBTMR_N_EOI);
goto out;
}
pr_debug("APB CS going back %lx:%lx:%lx ",
t2, last_read, t2 - last_read);
bad_count_x3:
pr_debug("triple check enforced\n");
t0 = apbt_readl(phy_cs_timer_id,
APBTMR_N_CURRENT_VALUE);
udelay(1);
t1 = apbt_readl(phy_cs_timer_id,
APBTMR_N_CURRENT_VALUE);
udelay(1);
t2 = apbt_readl(phy_cs_timer_id,
APBTMR_N_CURRENT_VALUE);
if ((t2 > t1) || (t1 > t0)) {
printk(KERN_ERR "Error: APB CS tripple check failed\n");
goto bad_count_x3;
}
}
out:
last_read = t2;
return (cycle_t)~t2;
current_count = apbt_readl(phy_cs_timer_id, APBTMR_N_CURRENT_VALUE);
return (cycle_t)~current_count;
}
static int apbt_clocksource_register(void)

33
arch/x86/kernel/aperture_64.c
مشاهده پرونده

@@ -13,7 +13,7 @@
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/memblock.h>
#include <linux/mmzone.h>
#include <linux/pci_ids.h>
#include <linux/pci.h>
@@ -57,7 +57,7 @@ static void __init insert_aperture_resource(u32 aper_base, u32 aper_size)
static u32 __init allocate_aperture(void)
{
u32 aper_size;
void *p;
unsigned long addr;
/* aper_size should <= 1G */
if (fallback_aper_order > 5)
@@ -83,27 +83,26 @@ static u32 __init allocate_aperture(void)
* so don't use 512M below as gart iommu, leave the space for kernel
* code for safe
*/
p = __alloc_bootmem_nopanic(aper_size, aper_size, 512ULL<<20);
addr = memblock_find_in_range(0, 1ULL<<32, aper_size, 512ULL<<20);
if (addr == MEMBLOCK_ERROR || addr + aper_size > 0xffffffff) {
printk(KERN_ERR
"Cannot allocate aperture memory hole (%lx,%uK)\n",
addr, aper_size>>10);
return 0;
}
memblock_x86_reserve_range(addr, addr + aper_size, "aperture64");
/*
* Kmemleak should not scan this block as it may not be mapped via the
* kernel direct mapping.
*/
kmemleak_ignore(p);
if (!p || __pa(p)+aper_size > 0xffffffff) {
printk(KERN_ERR
"Cannot allocate aperture memory hole (%p,%uK)\n",
p, aper_size>>10);
if (p)
free_bootmem(__pa(p), aper_size);
return 0;
}
kmemleak_ignore(phys_to_virt(addr));
printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n",
aper_size >> 10, __pa(p));
insert_aperture_resource((u32)__pa(p), aper_size);
register_nosave_region((u32)__pa(p) >> PAGE_SHIFT,
(u32)__pa(p+aper_size) >> PAGE_SHIFT);
aper_size >> 10, addr);
insert_aperture_resource((u32)addr, aper_size);
register_nosave_region(addr >> PAGE_SHIFT,
(addr+aper_size) >> PAGE_SHIFT);
return (u32)__pa(p);
return (u32)addr;
}

150
arch/x86/kernel/apic/apic.c
مشاهده پرونده

@@ -43,6 +43,7 @@
#include <asm/i8259.h>
#include <asm/proto.h>
#include <asm/apic.h>
#include <asm/io_apic.h>
#include <asm/desc.h>
#include <asm/hpet.h>
#include <asm/idle.h>
@@ -78,12 +79,21 @@ EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
#ifdef CONFIG_X86_32
/*
* On x86_32, the mapping between cpu and logical apicid may vary
* depending on apic in use. The following early percpu variable is
* 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);
/*
* Knob to control our willingness to enable the local APIC.
*
* +1=force-enable
*/
static int force_enable_local_apic;
static int force_enable_local_apic __initdata;
/*
* APIC command line parameters
*/
@@ -153,7 +163,7 @@ early_param("nox2apic", setup_nox2apic);
unsigned long mp_lapic_addr;
int disable_apic;
/* Disable local APIC timer from the kernel commandline or via dmi quirk */
static int disable_apic_timer __cpuinitdata;
static int disable_apic_timer __initdata;
/* Local APIC timer works in C2 */
int local_apic_timer_c2_ok;
EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
@@ -177,29 +187,8 @@ static struct resource lapic_resource = {
static unsigned int calibration_result;
static int lapic_next_event(unsigned long delta,
struct clock_event_device *evt);
static void lapic_timer_setup(enum clock_event_mode mode,
struct clock_event_device *evt);
static void lapic_timer_broadcast(const struct cpumask *mask);
static void apic_pm_activate(void);
/*
* The local apic timer can be used for any function which is CPU local.
*/
static struct clock_event_device lapic_clockevent = {
.name = "lapic",
.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT
| CLOCK_EVT_FEAT_C3STOP | CLOCK_EVT_FEAT_DUMMY,
.shift = 32,
.set_mode = lapic_timer_setup,
.set_next_event = lapic_next_event,
.broadcast = lapic_timer_broadcast,
.rating = 100,
.irq = -1,
};
static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
static unsigned long apic_phys;
/*
@@ -238,7 +227,7 @@ static int modern_apic(void)
* right after this call apic become NOOP driven
* so apic->write/read doesn't do anything
*/
void apic_disable(void)
static void __init apic_disable(void)
{
pr_info("APIC: switched to apic NOOP\n");
apic = &apic_noop;
@@ -282,23 +271,6 @@ u64 native_apic_icr_read(void)
return icr1 | ((u64)icr2 << 32);
}
/**
* enable_NMI_through_LVT0 - enable NMI through local vector table 0
*/
void __cpuinit enable_NMI_through_LVT0(void)
{
unsigned int v;
/* unmask and set to NMI */
v = APIC_DM_NMI;
/* Level triggered for 82489DX (32bit mode) */
if (!lapic_is_integrated())
v |= APIC_LVT_LEVEL_TRIGGER;
apic_write(APIC_LVT0, v);
}
#ifdef CONFIG_X86_32
/**
* get_physical_broadcast - Get number of physical broadcast IDs
@@ -508,6 +480,23 @@ static void lapic_timer_broadcast(const struct cpumask *mask)
#endif
}
/*
* The local apic timer can be used for any function which is CPU local.
*/
static struct clock_event_device lapic_clockevent = {
.name = "lapic",
.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT
| CLOCK_EVT_FEAT_C3STOP | CLOCK_EVT_FEAT_DUMMY,
.shift = 32,
.set_mode = lapic_timer_setup,
.set_next_event = lapic_next_event,
.broadcast = lapic_timer_broadcast,
.rating = 100,
.irq = -1,
};
static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
/*
* Setup the local APIC timer for this CPU. Copy the initialized values
* of the boot CPU and register the clock event in the framework.
@@ -1209,7 +1198,7 @@ void __cpuinit setup_local_APIC(void)
rdtscll(tsc);
if (disable_apic) {
arch_disable_smp_support();
disable_ioapic_support();
return;
}
@@ -1237,6 +1226,19 @@ void __cpuinit setup_local_APIC(void)
*/
apic->init_apic_ldr();
#ifdef CONFIG_X86_32
/*
* APIC LDR is initialized. If logical_apicid mapping was
* initialized during get_smp_config(), make sure it matches the
* actual value.
*/
i = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
WARN_ON(i != BAD_APICID && i != logical_smp_processor_id());
/* always use the value from LDR */
early_per_cpu(x86_cpu_to_logical_apicid, cpu) =
logical_smp_processor_id();
#endif
/*
* Set Task Priority to 'accept all'. We never change this
* later on.
@@ -1448,7 +1450,7 @@ int __init enable_IR(void)
void __init enable_IR_x2apic(void)
{
unsigned long flags;
struct IO_APIC_route_entry **ioapic_entries = NULL;
struct IO_APIC_route_entry **ioapic_entries;
int ret, x2apic_enabled = 0;
int dmar_table_init_ret;
@@ -1537,7 +1539,7 @@ static int __init detect_init_APIC(void)
}
#else
static int apic_verify(void)
static int __init apic_verify(void)
{
u32 features, h, l;
@@ -1562,7 +1564,7 @@ static int apic_verify(void)
return 0;
}
int apic_force_enable(void)
int __init apic_force_enable(unsigned long addr)
{
u32 h, l;
@@ -1578,7 +1580,7 @@ int apic_force_enable(void)
if (!(l & MSR_IA32_APICBASE_ENABLE)) {
pr_info("Local APIC disabled by BIOS -- reenabling.\n");
l &= ~MSR_IA32_APICBASE_BASE;
l |= MSR_IA32_APICBASE_ENABLE | APIC_DEFAULT_PHYS_BASE;
l |= MSR_IA32_APICBASE_ENABLE | addr;
wrmsr(MSR_IA32_APICBASE, l, h);
enabled_via_apicbase = 1;
}
@@ -1619,7 +1621,7 @@ static int __init detect_init_APIC(void)
"you can enable it with \"lapic\"\n");
return -1;
}
if (apic_force_enable())
if (apic_force_enable(APIC_DEFAULT_PHYS_BASE))
return -1;
} else {
if (apic_verify())
@@ -1930,17 +1932,6 @@ void __cpuinit generic_processor_info(int apicid, int version)
{
int cpu;
/*
* Validate version
*/
if (version == 0x0) {
pr_warning("BIOS bug, APIC version is 0 for CPU#%d! "
"fixing up to 0x10. (tell your hw vendor)\n",
version);
version = 0x10;
}
apic_version[apicid] = version;
if (num_processors >= nr_cpu_ids) {
int max = nr_cpu_ids;
int thiscpu = max + disabled_cpus;
@@ -1954,22 +1945,34 @@ void __cpuinit generic_processor_info(int apicid, int version)
}
num_processors++;
cpu = cpumask_next_zero(-1, cpu_present_mask);
if (version != apic_version[boot_cpu_physical_apicid])
WARN_ONCE(1,
"ACPI: apic version mismatch, bootcpu: %x cpu %d: %x\n",
apic_version[boot_cpu_physical_apicid], cpu, version);
physid_set(apicid, phys_cpu_present_map);
if (apicid == boot_cpu_physical_apicid) {
/*
* x86_bios_cpu_apicid is required to have processors listed
* in same order as logical cpu numbers. Hence the first
* entry is BSP, and so on.
* boot_cpu_init() already hold bit 0 in cpu_present_mask
* for BSP.
*/
cpu = 0;
} else
cpu = cpumask_next_zero(-1, cpu_present_mask);
/*
* Validate version
*/
if (version == 0x0) {
pr_warning("BIOS bug: APIC version is 0 for CPU %d/0x%x, fixing up to 0x10\n",
cpu, apicid);
version = 0x10;
}
apic_version[apicid] = version;
if (version != apic_version[boot_cpu_physical_apicid]) {
pr_warning("BIOS bug: APIC version mismatch, boot CPU: %x, CPU %d: version %x\n",
apic_version[boot_cpu_physical_apicid], cpu, version);
}
physid_set(apicid, phys_cpu_present_map);
if (apicid > max_physical_apicid)
max_physical_apicid = apicid;
@@ -1977,7 +1980,10 @@ void __cpuinit generic_processor_info(int apicid, int version)
early_per_cpu(x86_cpu_to_apicid, cpu) = apicid;
early_per_cpu(x86_bios_cpu_apicid, cpu) = apicid;
#endif
#ifdef CONFIG_X86_32
early_per_cpu(x86_cpu_to_logical_apicid, cpu) =
apic->x86_32_early_logical_apicid(cpu);
#endif
set_cpu_possible(cpu, true);
set_cpu_present(cpu, true);
}
@@ -1998,10 +2004,14 @@ void default_init_apic_ldr(void)
}
#ifdef CONFIG_X86_32
int default_apicid_to_node(int logical_apicid)
int default_x86_32_numa_cpu_node(int cpu)
{
#ifdef CONFIG_SMP
return apicid_2_node[hard_smp_processor_id()];
#ifdef CONFIG_NUMA
int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
if (apicid != BAD_APICID)
return __apicid_to_node[apicid];
return NUMA_NO_NODE;
#else
return 0;
#endif

4
arch/x86/kernel/apic/apic_flat_64.c
مشاهده پرونده

@@ -185,8 +185,6 @@ struct apic apic_flat = {
.ioapic_phys_id_map = NULL,
.setup_apic_routing = NULL,
.multi_timer_check = NULL,
.apicid_to_node = NULL,
.cpu_to_logical_apicid = NULL,
.cpu_present_to_apicid = default_cpu_present_to_apicid,
.apicid_to_cpu_present = NULL,
.setup_portio_remap = NULL,
@@ -337,8 +335,6 @@ struct apic apic_physflat = {
.ioapic_phys_id_map = NULL,
.setup_apic_routing = NULL,
.multi_timer_check = NULL,
.apicid_to_node = NULL,
.cpu_to_logical_apicid = NULL,
.cpu_present_to_apicid = default_cpu_present_to_apicid,
.apicid_to_cpu_present = NULL,
.setup_portio_remap = NULL,

26
arch/x86/kernel/apic/apic_noop.c
مشاهده پرونده

@@ -54,11 +54,6 @@ static u64 noop_apic_icr_read(void)
return 0;
}
static int noop_cpu_to_logical_apicid(int cpu)
{
return 0;
}
static int noop_phys_pkg_id(int cpuid_apic, int index_msb)
{
return 0;
@@ -113,12 +108,6 @@ static void noop_vector_allocation_domain(int cpu, struct cpumask *retmask)
cpumask_set_cpu(cpu, retmask);
}
int noop_apicid_to_node(int logical_apicid)
{
/* we're always on node 0 */
return 0;
}
static u32 noop_apic_read(u32 reg)
{
WARN_ON_ONCE((cpu_has_apic && !disable_apic));
@@ -130,6 +119,14 @@ static void noop_apic_write(u32 reg, u32 v)
WARN_ON_ONCE(cpu_has_apic && !disable_apic);
}
#ifdef CONFIG_X86_32
static int noop_x86_32_numa_cpu_node(int cpu)
{
/* we're always on node 0 */
return 0;
}
#endif
struct apic apic_noop = {
.name = "noop",
.probe = noop_probe,
@@ -153,9 +150,7 @@ struct apic apic_noop = {
.ioapic_phys_id_map = default_ioapic_phys_id_map,
.setup_apic_routing = NULL,
.multi_timer_check = NULL,
.apicid_to_node = noop_apicid_to_node,
.cpu_to_logical_apicid = noop_cpu_to_logical_apicid,
.cpu_present_to_apicid = default_cpu_present_to_apicid,
.apicid_to_cpu_present = physid_set_mask_of_physid,
@@ -197,4 +192,9 @@ struct apic apic_noop = {
.icr_write = noop_apic_icr_write,
.wait_icr_idle = noop_apic_wait_icr_idle,
.safe_wait_icr_idle = noop_safe_apic_wait_icr_idle,
#ifdef CONFIG_X86_32
.x86_32_early_logical_apicid = noop_x86_32_early_logical_apicid,
.x86_32_numa_cpu_node = noop_x86_32_numa_cpu_node,
#endif
};

34
arch/x86/kernel/apic/bigsmp_32.c
مشاهده پرونده

@@ -45,6 +45,12 @@ static unsigned long bigsmp_check_apicid_present(int bit)
return 1;
}
static int bigsmp_early_logical_apicid(int cpu)
{
/* on bigsmp, logical apicid is the same as physical */
return early_per_cpu(x86_cpu_to_apicid, cpu);
}
static inline unsigned long calculate_ldr(int cpu)
{
unsigned long val, id;
@@ -80,11 +86,6 @@ static void bigsmp_setup_apic_routing(void)
nr_ioapics);
}
static int bigsmp_apicid_to_node(int logical_apicid)
{
return apicid_2_node[hard_smp_processor_id()];
}
static int bigsmp_cpu_present_to_apicid(int mps_cpu)
{
if (mps_cpu < nr_cpu_ids)
@@ -93,14 +94,6 @@ static int bigsmp_cpu_present_to_apicid(int mps_cpu)
return BAD_APICID;
}
/* Mapping from cpu number to logical apicid */
static inline int bigsmp_cpu_to_logical_apicid(int cpu)
{
if (cpu >= nr_cpu_ids)
return BAD_APICID;
return cpu_physical_id(cpu);
}
static void bigsmp_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap)
{
/* For clustered we don't have a good way to do this yet - hack */
@@ -115,7 +108,11 @@ static int bigsmp_check_phys_apicid_present(int phys_apicid)
/* As we are using single CPU as destination, pick only one CPU here */
static unsigned int bigsmp_cpu_mask_to_apicid(const struct cpumask *cpumask)
{
return bigsmp_cpu_to_logical_apicid(cpumask_first(cpumask));
int cpu = cpumask_first(cpumask);
if (cpu < nr_cpu_ids)
return cpu_physical_id(cpu);
return BAD_APICID;
}
static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
@@ -129,9 +126,9 @@ static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
*/
for_each_cpu_and(cpu, cpumask, andmask) {
if (cpumask_test_cpu(cpu, cpu_online_mask))
break;
return cpu_physical_id(cpu);
}
return bigsmp_cpu_to_logical_apicid(cpu);
return BAD_APICID;
}
static int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb)
@@ -219,8 +216,6 @@ struct apic apic_bigsmp = {
.ioapic_phys_id_map = bigsmp_ioapic_phys_id_map,
.setup_apic_routing = bigsmp_setup_apic_routing,
.multi_timer_check = NULL,
.apicid_to_node = bigsmp_apicid_to_node,
.cpu_to_logical_apicid = bigsmp_cpu_to_logical_apicid,
.cpu_present_to_apicid = bigsmp_cpu_present_to_apicid,
.apicid_to_cpu_present = physid_set_mask_of_physid,
.setup_portio_remap = NULL,
@@ -256,4 +251,7 @@ struct apic apic_bigsmp = {
.icr_write = native_apic_icr_write,
.wait_icr_idle = native_apic_wait_icr_idle,
.safe_wait_icr_idle = native_safe_apic_wait_icr_idle,
.x86_32_early_logical_apicid = bigsmp_early_logical_apicid,
.x86_32_numa_cpu_node = default_x86_32_numa_cpu_node,
};

35
arch/x86/kernel/apic/es7000_32.c
مشاهده پرونده

@@ -460,6 +460,12 @@ static unsigned long es7000_check_apicid_present(int bit)
return physid_isset(bit, phys_cpu_present_map);
}
static int es7000_early_logical_apicid(int cpu)
{
/* on es7000, logical apicid is the same as physical */
return early_per_cpu(x86_bios_cpu_apicid, cpu);
}
static unsigned long calculate_ldr(int cpu)
{
unsigned long id = per_cpu(x86_bios_cpu_apicid, cpu);
@@ -504,12 +510,11 @@ static void es7000_setup_apic_routing(void)
nr_ioapics, cpumask_bits(es7000_target_cpus())[0]);
}
static int es7000_apicid_to_node(int logical_apicid)
static int es7000_numa_cpu_node(int cpu)
{
return 0;
}
static int es7000_cpu_present_to_apicid(int mps_cpu)
{
if (!mps_cpu)
@@ -528,18 +533,6 @@ static void es7000_apicid_to_cpu_present(int phys_apicid, physid_mask_t *retmap)
++cpu_id;
}
/* Mapping from cpu number to logical apicid */
static int es7000_cpu_to_logical_apicid(int cpu)
{
#ifdef CONFIG_SMP
if (cpu >= nr_cpu_ids)
return BAD_APICID;
return cpu_2_logical_apicid[cpu];
#else
return logical_smp_processor_id();
#endif
}
static void es7000_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap)
{
/* For clustered we don't have a good way to do this yet - hack */
@@ -561,7 +554,7 @@ static unsigned int es7000_cpu_mask_to_apicid(const struct cpumask *cpumask)
* The cpus in the mask must all be on the apic cluster.
*/
for_each_cpu(cpu, cpumask) {
int new_apicid = es7000_cpu_to_logical_apicid(cpu);
int new_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) {
WARN(1, "Not a valid mask!");
@@ -578,7 +571,7 @@ static unsigned int
es7000_cpu_mask_to_apicid_and(const struct cpumask *inmask,
const struct cpumask *andmask)
{
int apicid = es7000_cpu_to_logical_apicid(0);
int apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0);
cpumask_var_t cpumask;
if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC))
@@ -655,8 +648,6 @@ struct apic __refdata apic_es7000_cluster = {
.ioapic_phys_id_map = es7000_ioapic_phys_id_map,
.setup_apic_routing = es7000_setup_apic_routing,
.multi_timer_check = NULL,
.apicid_to_node = es7000_apicid_to_node,
.cpu_to_logical_apicid = es7000_cpu_to_logical_apicid,
.cpu_present_to_apicid = es7000_cpu_present_to_apicid,
.apicid_to_cpu_present = es7000_apicid_to_cpu_present,
.setup_portio_remap = NULL,
@@ -695,6 +686,9 @@ struct apic __refdata apic_es7000_cluster = {
.icr_write = native_apic_icr_write,
.wait_icr_idle = native_apic_wait_icr_idle,
.safe_wait_icr_idle = native_safe_apic_wait_icr_idle,
.x86_32_early_logical_apicid = es7000_early_logical_apicid,
.x86_32_numa_cpu_node = es7000_numa_cpu_node,
};
struct apic __refdata apic_es7000 = {
@@ -720,8 +714,6 @@ struct apic __refdata apic_es7000 = {
.ioapic_phys_id_map = es7000_ioapic_phys_id_map,
.setup_apic_routing = es7000_setup_apic_routing,
.multi_timer_check = NULL,
.apicid_to_node = es7000_apicid_to_node,
.cpu_to_logical_apicid = es7000_cpu_to_logical_apicid,
.cpu_present_to_apicid = es7000_cpu_present_to_apicid,
.apicid_to_cpu_present = es7000_apicid_to_cpu_present,
.setup_portio_remap = NULL,
@@ -758,4 +750,7 @@ struct apic __refdata apic_es7000 = {
.icr_write = native_apic_icr_write,
.wait_icr_idle = native_apic_wait_icr_idle,
.safe_wait_icr_idle = native_safe_apic_wait_icr_idle,
.x86_32_early_logical_apicid = es7000_early_logical_apicid,
.x86_32_numa_cpu_node = es7000_numa_cpu_node,
};

1
arch/x86/kernel/apic/hw_nmi.c
مشاهده پرونده

@@ -83,7 +83,6 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
arch_spin_lock(&lock);
printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
show_regs(regs);
dump_stack();
arch_spin_unlock(&lock);
cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
return NOTIFY_STOP;

392
arch/x86/kernel/apic/io_apic.c
مشاهده پرونده

@@ -108,7 +108,10 @@ DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
int skip_ioapic_setup;
void arch_disable_smp_support(void)
/**
* disable_ioapic_support() - disables ioapic support at runtime
*/
void disable_ioapic_support(void)
{
#ifdef CONFIG_PCI
noioapicquirk = 1;
@@ -120,11 +123,14 @@ void arch_disable_smp_support(void)
static int __init parse_noapic(char *str)
{
/* disable IO-APIC */
arch_disable_smp_support();
disable_ioapic_support();
return 0;
}
early_param("noapic", parse_noapic);
static int io_apic_setup_irq_pin_once(unsigned int irq, int node,
struct io_apic_irq_attr *attr);
/* Will be called in mpparse/acpi/sfi codes for saving IRQ info */
void mp_save_irq(struct mpc_intsrc *m)
{
@@ -181,7 +187,7 @@ int __init arch_early_irq_init(void)
irq_reserve_irqs(0, legacy_pic->nr_legacy_irqs);
for (i = 0; i < count; i++) {
set_irq_chip_data(i, &cfg[i]);
irq_set_chip_data(i, &cfg[i]);
zalloc_cpumask_var_node(&cfg[i].domain, GFP_KERNEL, node);
zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_KERNEL, node);
/*
@@ -200,7 +206,7 @@ int __init arch_early_irq_init(void)
#ifdef CONFIG_SPARSE_IRQ
static struct irq_cfg *irq_cfg(unsigned int irq)
{
return get_irq_chip_data(irq);
return irq_get_chip_data(irq);
}
static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node)
@@ -226,7 +232,7 @@ static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg)
{
if (!cfg)
return;
set_irq_chip_data(at, NULL);
irq_set_chip_data(at, NULL);
free_cpumask_var(cfg->domain);
free_cpumask_var(cfg->old_domain);
kfree(cfg);
@@ -256,14 +262,14 @@ static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node)
if (res < 0) {
if (res != -EEXIST)
return NULL;
cfg = get_irq_chip_data(at);
cfg = irq_get_chip_data(at);
if (cfg)
return cfg;
}
cfg = alloc_irq_cfg(at, node);
if (cfg)
set_irq_chip_data(at, cfg);
irq_set_chip_data(at, cfg);
else
irq_free_desc(at);
return cfg;
@@ -818,7 +824,7 @@ static int EISA_ELCR(unsigned int irq)
#define default_MCA_trigger(idx) (1)
#define default_MCA_polarity(idx) default_ISA_polarity(idx)
static int MPBIOS_polarity(int idx)
static int irq_polarity(int idx)
{
int bus = mp_irqs[idx].srcbus;
int polarity;
@@ -860,7 +866,7 @@ static int MPBIOS_polarity(int idx)
return polarity;
}
static int MPBIOS_trigger(int idx)
static int irq_trigger(int idx)
{
int bus = mp_irqs[idx].srcbus;
int trigger;
@@ -932,16 +938,6 @@ static int MPBIOS_trigger(int idx)
return trigger;
}
static inline int irq_polarity(int idx)
{
return MPBIOS_polarity(idx);
}
static inline int irq_trigger(int idx)
{
return MPBIOS_trigger(idx);
}
static int pin_2_irq(int idx, int apic, int pin)
{
int irq;
@@ -1189,7 +1185,7 @@ void __setup_vector_irq(int cpu)
raw_spin_lock(&vector_lock);
/* Mark the inuse vectors */
for_each_active_irq(irq) {
cfg = get_irq_chip_data(irq);
cfg = irq_get_chip_data(irq);
if (!cfg)
continue;
/*
@@ -1220,10 +1216,6 @@ void __setup_vector_irq(int cpu)
static struct irq_chip ioapic_chip;
static struct irq_chip ir_ioapic_chip;
#define IOAPIC_AUTO -1
#define IOAPIC_EDGE 0
#define IOAPIC_LEVEL 1
#ifdef CONFIG_X86_32
static inline int IO_APIC_irq_trigger(int irq)
{
@@ -1248,35 +1240,31 @@ static inline int IO_APIC_irq_trigger(int irq)
}
#endif
static void ioapic_register_intr(unsigned int irq, unsigned long trigger)
static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg,
unsigned long trigger)
{
struct irq_chip *chip = &ioapic_chip;
irq_flow_handler_t hdl;
bool fasteoi;
if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
trigger == IOAPIC_LEVEL)
trigger == IOAPIC_LEVEL) {
irq_set_status_flags(irq, IRQ_LEVEL);
else
fasteoi = true;
} else {
irq_clear_status_flags(irq, IRQ_LEVEL);
if (irq_remapped(get_irq_chip_data(irq))) {
irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
if (trigger)
set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
handle_fasteoi_irq,
"fasteoi");
else
set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
handle_edge_irq, "edge");
return;
fasteoi = false;
}
if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
trigger == IOAPIC_LEVEL)
set_irq_chip_and_handler_name(irq, &ioapic_chip,
handle_fasteoi_irq,
"fasteoi");
else
set_irq_chip_and_handler_name(irq, &ioapic_chip,
handle_edge_irq, "edge");
if (irq_remapped(cfg)) {
irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
chip = &ir_ioapic_chip;
fasteoi = trigger != 0;
}
hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq;
irq_set_chip_and_handler_name(irq, chip, hdl,
fasteoi ? "fasteoi" : "edge");
}
static int setup_ioapic_entry(int apic_id, int irq,
@@ -1374,7 +1362,7 @@ static void setup_ioapic_irq(int apic_id, int pin, unsigned int irq,
return;
}
ioapic_register_intr(irq, trigger);
ioapic_register_intr(irq, cfg, trigger);
if (irq < legacy_pic->nr_legacy_irqs)
legacy_pic->mask(irq);
@@ -1385,33 +1373,26 @@ static struct {
DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1);
} mp_ioapic_routing[MAX_IO_APICS];
static void __init setup_IO_APIC_irqs(void)
static bool __init io_apic_pin_not_connected(int idx, int apic_id, int pin)
{
int apic_id, pin, idx, irq, notcon = 0;
int node = cpu_to_node(0);
struct irq_cfg *cfg;
if (idx != -1)
return false;
apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
apic_printk(APIC_VERBOSE, KERN_DEBUG " apic %d pin %d not connected\n",
mp_ioapics[apic_id].apicid, pin);
return true;
}
static void __init __io_apic_setup_irqs(unsigned int apic_id)
{
int idx, node = cpu_to_node(0);
struct io_apic_irq_attr attr;
unsigned int pin, irq;
for (apic_id = 0; apic_id < nr_ioapics; apic_id++)
for (pin = 0; pin < nr_ioapic_registers[apic_id]; pin++) {
idx = find_irq_entry(apic_id, pin, mp_INT);
if (idx == -1) {
if (!notcon) {
notcon = 1;
apic_printk(APIC_VERBOSE,
KERN_DEBUG " %d-%d",
mp_ioapics[apic_id].apicid, pin);
} else
apic_printk(APIC_VERBOSE, " %d-%d",
mp_ioapics[apic_id].apicid, pin);
if (io_apic_pin_not_connected(idx, apic_id, pin))
continue;
}
if (notcon) {
apic_printk(APIC_VERBOSE,
" (apicid-pin) not connected\n");
notcon = 0;
}
irq = pin_2_irq(idx, apic_id, pin);
@@ -1423,25 +1404,24 @@ static void __init setup_IO_APIC_irqs(void)
* installed and if it returns 1:
*/
if (apic->multi_timer_check &&
apic->multi_timer_check(apic_id, irq))
apic->multi_timer_check(apic_id, irq))
continue;
cfg = alloc_irq_and_cfg_at(irq, node);
if (!cfg)
continue;
set_io_apic_irq_attr(&attr, apic_id, pin, irq_trigger(idx),
irq_polarity(idx));
add_pin_to_irq_node(cfg, node, apic_id, pin);
/*
* don't mark it in pin_programmed, so later acpi could
* set it correctly when irq < 16
*/
setup_ioapic_irq(apic_id, pin, irq, cfg, irq_trigger(idx),
irq_polarity(idx));
io_apic_setup_irq_pin(irq, node, &attr);
}
}
if (notcon)
apic_printk(APIC_VERBOSE,
" (apicid-pin) not connected\n");
static void __init setup_IO_APIC_irqs(void)
{
unsigned int apic_id;
apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
for (apic_id = 0; apic_id < nr_ioapics; apic_id++)
__io_apic_setup_irqs(apic_id);
}
/*
@@ -1452,7 +1432,7 @@ static void __init setup_IO_APIC_irqs(void)
void setup_IO_APIC_irq_extra(u32 gsi)
{
int apic_id = 0, pin, idx, irq, node = cpu_to_node(0);
struct irq_cfg *cfg;
struct io_apic_irq_attr attr;
/*
* Convert 'gsi' to 'ioapic.pin'.
@@ -1472,21 +1452,10 @@ void setup_IO_APIC_irq_extra(u32 gsi)
if (apic_id == 0 || irq < NR_IRQS_LEGACY)
return;
cfg = alloc_irq_and_cfg_at(irq, node);
if (!cfg)
return;
set_io_apic_irq_attr(&attr, apic_id, pin, irq_trigger(idx),
irq_polarity(idx));
add_pin_to_irq_node(cfg, node, apic_id, pin);
if (test_bit(pin, mp_ioapic_routing[apic_id].pin_programmed)) {
pr_debug("Pin %d-%d already programmed\n",
mp_ioapics[apic_id].apicid, pin);
return;
}
set_bit(pin, mp_ioapic_routing[apic_id].pin_programmed);
setup_ioapic_irq(apic_id, pin, irq, cfg,
irq_trigger(idx), irq_polarity(idx));
io_apic_setup_irq_pin_once(irq, node, &attr);
}
/*
@@ -1518,7 +1487,8 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic_id, unsigned int pin,
* The timer IRQ doesn't have to know that behind the
* scene we may have a 8259A-master in AEOI mode ...
*/
set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq,
"edge");
/*
* Add it to the IO-APIC irq-routing table:
@@ -1625,7 +1595,7 @@ __apicdebuginit(void) print_IO_APIC(void)
for_each_active_irq(irq) {
struct irq_pin_list *entry;
cfg = get_irq_chip_data(irq);
cfg = irq_get_chip_data(irq);
if (!cfg)
continue;
entry = cfg->irq_2_pin;
@@ -2391,7 +2361,7 @@ static void irq_complete_move(struct irq_cfg *cfg)
void irq_force_complete_move(int irq)
{
struct irq_cfg *cfg = get_irq_chip_data(irq);
struct irq_cfg *cfg = irq_get_chip_data(irq);
if (!cfg)
return;
@@ -2405,7 +2375,7 @@ static inline void irq_complete_move(struct irq_cfg *cfg) { }
static void ack_apic_edge(struct irq_data *data)
{
irq_complete_move(data->chip_data);
move_native_irq(data->irq);
irq_move_irq(data);
ack_APIC_irq();
}
@@ -2462,7 +2432,7 @@ static void ack_apic_level(struct irq_data *data)
irq_complete_move(cfg);
#ifdef CONFIG_GENERIC_PENDING_IRQ
/* If we are moving the irq we need to mask it */
if (unlikely(irq_to_desc(irq)->status & IRQ_MOVE_PENDING)) {
if (unlikely(irqd_is_setaffinity_pending(data))) {
do_unmask_irq = 1;
mask_ioapic(cfg);
}
@@ -2551,7 +2521,7 @@ static void ack_apic_level(struct irq_data *data)
* and you can go talk to the chipset vendor about it.
*/
if (!io_apic_level_ack_pending(cfg))
move_masked_irq(irq);
irq_move_masked_irq(data);
unmask_ioapic(cfg);
}
}
@@ -2614,7 +2584,7 @@ static inline void init_IO_APIC_traps(void)
* 0x80, because int 0x80 is hm, kind of importantish. ;)
*/
for_each_active_irq(irq) {
cfg = get_irq_chip_data(irq);
cfg = irq_get_chip_data(irq);
if (IO_APIC_IRQ(irq) && cfg && !cfg->vector) {
/*
* Hmm.. We don't have an entry for this,
@@ -2625,7 +2595,7 @@ static inline void init_IO_APIC_traps(void)
legacy_pic->make_irq(irq);
else
/* Strange. Oh, well.. */
set_irq_chip(irq, &no_irq_chip);
irq_set_chip(irq, &no_irq_chip);
}
}
}
@@ -2665,7 +2635,7 @@ static struct irq_chip lapic_chip __read_mostly = {
static void lapic_register_intr(int irq)
{
irq_clear_status_flags(irq, IRQ_LEVEL);
set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
irq_set_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
"edge");
}
@@ -2749,7 +2719,7 @@ int timer_through_8259 __initdata;
*/
static inline void __init check_timer(void)
{
struct irq_cfg *cfg = get_irq_chip_data(0);
struct irq_cfg *cfg = irq_get_chip_data(0);
int node = cpu_to_node(0);
int apic1, pin1, apic2, pin2;
unsigned long flags;
@@ -3060,7 +3030,7 @@ unsigned int create_irq_nr(unsigned int from, int node)
raw_spin_unlock_irqrestore(&vector_lock, flags);
if (ret) {
set_irq_chip_data(irq, cfg);
irq_set_chip_data(irq, cfg);
irq_clear_status_flags(irq, IRQ_NOREQUEST);
} else {
free_irq_at(irq, cfg);
@@ -3085,7 +3055,7 @@ int create_irq(void)
void destroy_irq(unsigned int irq)
{
struct irq_cfg *cfg = get_irq_chip_data(irq);
struct irq_cfg *cfg = irq_get_chip_data(irq);
unsigned long flags;
irq_set_status_flags(irq, IRQ_NOREQUEST|IRQ_NOPROBE);
@@ -3119,7 +3089,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus());
if (irq_remapped(get_irq_chip_data(irq))) {
if (irq_remapped(cfg)) {
struct irte irte;
int ir_index;
u16 sub_handle;
@@ -3291,6 +3261,7 @@ static int msi_alloc_irte(struct pci_dev *dev, int irq, int nvec)
static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
{
struct irq_chip *chip = &msi_chip;
struct msi_msg msg;
int ret;
@@ -3298,14 +3269,15 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
if (ret < 0)
return ret;
set_irq_msi(irq, msidesc);
irq_set_msi_desc(irq, msidesc);
write_msi_msg(irq, &msg);
if (irq_remapped(get_irq_chip_data(irq))) {
if (irq_remapped(irq_get_chip_data(irq))) {
irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
set_irq_chip_and_handler_name(irq, &msi_ir_chip, handle_edge_irq, "edge");
} else
set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge");
chip = &msi_ir_chip;
}
irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
dev_printk(KERN_DEBUG, &dev->dev, "irq %d for MSI/MSI-X\n", irq);
@@ -3423,8 +3395,8 @@ int arch_setup_dmar_msi(unsigned int irq)
if (ret < 0)
return ret;
dmar_msi_write(irq, &msg);
set_irq_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
"edge");
irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
"edge");
return 0;
}
#endif
@@ -3482,6 +3454,7 @@ static struct irq_chip hpet_msi_type = {
int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
{
struct irq_chip *chip = &hpet_msi_type;
struct msi_msg msg;
int ret;
@@ -3501,15 +3474,12 @@ int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
if (ret < 0)
return ret;
hpet_msi_write(get_irq_data(irq), &msg);
hpet_msi_write(irq_get_handler_data(irq), &msg);
irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
if (irq_remapped(get_irq_chip_data(irq)))
set_irq_chip_and_handler_name(irq, &ir_hpet_msi_type,
handle_edge_irq, "edge");
else
set_irq_chip_and_handler_name(irq, &hpet_msi_type,
handle_edge_irq, "edge");
if (irq_remapped(irq_get_chip_data(irq)))
chip = &ir_hpet_msi_type;
irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
return 0;
}
#endif
@@ -3596,7 +3566,7 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
write_ht_irq_msg(irq, &msg);
set_irq_chip_and_handler_name(irq, &ht_irq_chip,
irq_set_chip_and_handler_name(irq, &ht_irq_chip,
handle_edge_irq, "edge");
dev_printk(KERN_DEBUG, &dev->dev, "irq %d for HT\n", irq);
@@ -3605,7 +3575,40 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
}
#endif /* CONFIG_HT_IRQ */
int __init io_apic_get_redir_entries (int ioapic)
int
io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr)
{
struct irq_cfg *cfg = alloc_irq_and_cfg_at(irq, node);
int ret;
if (!cfg)
return -EINVAL;
ret = __add_pin_to_irq_node(cfg, node, attr->ioapic, attr->ioapic_pin);
if (!ret)
setup_ioapic_irq(attr->ioapic, attr->ioapic_pin, irq, cfg,
attr->trigger, attr->polarity);
return ret;
}
static int io_apic_setup_irq_pin_once(unsigned int irq, int node,
struct io_apic_irq_attr *attr)
{
unsigned int id = attr->ioapic, pin = attr->ioapic_pin;
int ret;
/* Avoid redundant programming */
if (test_bit(pin, mp_ioapic_routing[id].pin_programmed)) {
pr_debug("Pin %d-%d already programmed\n",
mp_ioapics[id].apicid, pin);
return 0;
}
ret = io_apic_setup_irq_pin(irq, node, attr);
if (!ret)
set_bit(pin, mp_ioapic_routing[id].pin_programmed);
return ret;
}
static int __init io_apic_get_redir_entries(int ioapic)
{
union IO_APIC_reg_01 reg_01;
unsigned long flags;
@@ -3659,96 +3662,24 @@ int __init arch_probe_nr_irqs(void)
}
#endif
static int __io_apic_set_pci_routing(struct device *dev, int irq,
struct io_apic_irq_attr *irq_attr)
int io_apic_set_pci_routing(struct device *dev, int irq,
struct io_apic_irq_attr *irq_attr)
{
struct irq_cfg *cfg;
int node;
int ioapic, pin;
int trigger, polarity;
ioapic = irq_attr->ioapic;
if (!IO_APIC_IRQ(irq)) {
apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n",
ioapic);
irq_attr->ioapic);
return -EINVAL;
}
if (dev)
node = dev_to_node(dev);
else
node = cpu_to_node(0);
node = dev ? dev_to_node(dev) : cpu_to_node(0);
cfg = alloc_irq_and_cfg_at(irq, node);
if (!cfg)
return 0;
pin = irq_attr->ioapic_pin;
trigger = irq_attr->trigger;
polarity = irq_attr->polarity;
/*
* IRQs < 16 are already in the irq_2_pin[] map
*/
if (irq >= legacy_pic->nr_legacy_irqs) {
if (__add_pin_to_irq_node(cfg, node, ioapic, pin)) {
printk(KERN_INFO "can not add pin %d for irq %d\n",
pin, irq);
return 0;
}
}
setup_ioapic_irq(ioapic, pin, irq, cfg, trigger, polarity);
return 0;
}
int io_apic_set_pci_routing(struct device *dev, int irq,
struct io_apic_irq_attr *irq_attr)
{
int ioapic, pin;
/*
* Avoid pin reprogramming. PRTs typically include entries
* with redundant pin->gsi mappings (but unique PCI devices);
* we only program the IOAPIC on the first.
*/
ioapic = irq_attr->ioapic;
pin = irq_attr->ioapic_pin;
if (test_bit(pin, mp_ioapic_routing[ioapic].pin_programmed)) {
pr_debug("Pin %d-%d already programmed\n",
mp_ioapics[ioapic].apicid, pin);
return 0;
}
set_bit(pin, mp_ioapic_routing[ioapic].pin_programmed);
return __io_apic_set_pci_routing(dev, irq, irq_attr);
}
u8 __init io_apic_unique_id(u8 id)
{
#ifdef CONFIG_X86_32
if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
!APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
return io_apic_get_unique_id(nr_ioapics, id);
else
return id;
#else
int i;
DECLARE_BITMAP(used, 256);
bitmap_zero(used, 256);
for (i = 0; i < nr_ioapics; i++) {
struct mpc_ioapic *ia = &mp_ioapics[i];
__set_bit(ia->apicid, used);
}
if (!test_bit(id, used))
return id;
return find_first_zero_bit(used, 256);
#endif
return io_apic_setup_irq_pin_once(irq, node, irq_attr);
}
#ifdef CONFIG_X86_32
int __init io_apic_get_unique_id(int ioapic, int apic_id)
static int __init io_apic_get_unique_id(int ioapic, int apic_id)
{
union IO_APIC_reg_00 reg_00;
static physid_mask_t apic_id_map = PHYSID_MASK_NONE;
@@ -3821,9 +3752,33 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id)
return apic_id;
}
static u8 __init io_apic_unique_id(u8 id)
{
if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
!APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
return io_apic_get_unique_id(nr_ioapics, id);
else
return id;
}
#else
static u8 __init io_apic_unique_id(u8 id)
{
int i;
DECLARE_BITMAP(used, 256);
bitmap_zero(used, 256);
for (i = 0; i < nr_ioapics; i++) {
struct mpc_ioapic *ia = &mp_ioapics[i];
__set_bit(ia->apicid, used);
}
if (!test_bit(id, used))
return id;
return find_first_zero_bit(used, 256);
}
#endif
int __init io_apic_get_version(int ioapic)
static int __init io_apic_get_version(int ioapic)
{
union IO_APIC_reg_01 reg_01;
unsigned long flags;
@@ -3868,8 +3823,8 @@ int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity)
void __init setup_ioapic_dest(void)
{
int pin, ioapic, irq, irq_entry;
struct irq_desc *desc;
const struct cpumask *mask;
struct irq_data *idata;
if (skip_ioapic_setup == 1)
return;
@@ -3884,21 +3839,20 @@ void __init setup_ioapic_dest(void)
if ((ioapic > 0) && (irq > 16))
continue;
desc = irq_to_desc(irq);
idata = irq_get_irq_data(irq);
/*
* Honour affinities which have been set in early boot
*/
if (desc->status &
(IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
mask = desc->irq_data.affinity;
if (!irqd_can_balance(idata) || irqd_affinity_was_set(idata))
mask = idata->affinity;
else
mask = apic->target_cpus();
if (intr_remapping_enabled)
ir_ioapic_set_affinity(&desc->irq_data, mask, false);
ir_ioapic_set_affinity(idata, mask, false);
else
ioapic_set_affinity(&desc->irq_data, mask, false);
ioapic_set_affinity(idata, mask, false);
}
}
@@ -4026,7 +3980,7 @@ int mp_find_ioapic_pin(int ioapic, u32 gsi)
return gsi - mp_gsi_routing[ioapic].gsi_base;
}
static int bad_ioapic(unsigned long address)
static __init int bad_ioapic(unsigned long address)
{
if (nr_ioapics >= MAX_IO_APICS) {
printk(KERN_WARNING "WARING: Max # of I/O APICs (%d) exceeded "
@@ -4086,20 +4040,16 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
/* Enable IOAPIC early just for system timer */
void __init pre_init_apic_IRQ0(void)
{
struct irq_cfg *cfg;
struct io_apic_irq_attr attr = { 0, 0, 0, 0 };
printk(KERN_INFO "Early APIC setup for system timer0\n");
#ifndef CONFIG_SMP
physid_set_mask_of_physid(boot_cpu_physical_apicid,
&phys_cpu_present_map);
#endif
/* Make sure the irq descriptor is set up */
cfg = alloc_irq_and_cfg_at(0, 0);
setup_local_APIC();
add_pin_to_irq_node(cfg, 0, 0, 0);
set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
setup_ioapic_irq(0, 0, 0, cfg, 0, 0);
io_apic_setup_irq_pin(0, 0, &attr);
irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq,
"edge");
}

12
arch/x86/kernel/apic/ipi.c
مشاهده پرونده

@@ -56,6 +56,8 @@ void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask,
local_irq_restore(flags);
}
#ifdef CONFIG_X86_32
void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
int vector)
{
@@ -71,8 +73,8 @@ void default_send_IPI_mask_sequence_logical(const struct cpumask *mask,
local_irq_save(flags);
for_each_cpu(query_cpu, mask)
__default_send_IPI_dest_field(
apic->cpu_to_logical_apicid(query_cpu), vector,
apic->dest_logical);
early_per_cpu(x86_cpu_to_logical_apicid, query_cpu),
vector, apic->dest_logical);
local_irq_restore(flags);
}
@@ -90,14 +92,12 @@ void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask,
if (query_cpu == this_cpu)
continue;
__default_send_IPI_dest_field(
apic->cpu_to_logical_apicid(query_cpu), vector,
apic->dest_logical);
early_per_cpu(x86_cpu_to_logical_apicid, query_cpu),
vector, apic->dest_logical);
}
local_irq_restore(flags);
}
#ifdef CONFIG_X86_32
/*
* This is only used on smaller machines.
*/

21
arch/x86/kernel/apic/numaq_32.c
مشاهده پرونده

@@ -373,13 +373,6 @@ static inline void numaq_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask
return physids_promote(0xFUL, retmap);
}
static inline int numaq_cpu_to_logical_apicid(int cpu)
{
if (cpu >= nr_cpu_ids)
return BAD_APICID;
return cpu_2_logical_apicid[cpu];
}
/*
* Supporting over 60 cpus on NUMA-Q requires a locality-dependent
* cpu to APIC ID relation to properly interact with the intelligent
@@ -398,6 +391,15 @@ static inline int numaq_apicid_to_node(int logical_apicid)
return logical_apicid >> 4;
}
static int numaq_numa_cpu_node(int cpu)
{
int logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
if (logical_apicid != BAD_APICID)
return numaq_apicid_to_node(logical_apicid);
return NUMA_NO_NODE;
}
static void numaq_apicid_to_cpu_present(int logical_apicid, physid_mask_t *retmap)
{
int node = numaq_apicid_to_node(logical_apicid);
@@ -508,8 +510,6 @@ struct apic __refdata apic_numaq = {
.ioapic_phys_id_map = numaq_ioapic_phys_id_map,
.setup_apic_routing = numaq_setup_apic_routing,
.multi_timer_check = numaq_multi_timer_check,
.apicid_to_node = numaq_apicid_to_node,
.cpu_to_logical_apicid = numaq_cpu_to_logical_apicid,
.cpu_present_to_apicid = numaq_cpu_present_to_apicid,
.apicid_to_cpu_present = numaq_apicid_to_cpu_present,
.setup_portio_remap = numaq_setup_portio_remap,
@@ -547,4 +547,7 @@ struct apic __refdata apic_numaq = {
.icr_write = native_apic_icr_write,
.wait_icr_idle = native_apic_wait_icr_idle,
.safe_wait_icr_idle = native_safe_apic_wait_icr_idle,
.x86_32_early_logical_apicid = noop_x86_32_early_logical_apicid,
.x86_32_numa_cpu_node = numaq_numa_cpu_node,
};

10
arch/x86/kernel/apic/probe_32.c
مشاهده پرونده

@@ -77,6 +77,11 @@ void __init default_setup_apic_routing(void)
apic->setup_apic_routing();
}
static int default_x86_32_early_logical_apicid(int cpu)
{
return 1 << cpu;
}
static void setup_apic_flat_routing(void)
{
#ifdef CONFIG_X86_IO_APIC
@@ -130,8 +135,6 @@ struct apic apic_default = {
.ioapic_phys_id_map = default_ioapic_phys_id_map,
.setup_apic_routing = setup_apic_flat_routing,
.multi_timer_check = NULL,
.apicid_to_node = default_apicid_to_node,
.cpu_to_logical_apicid = default_cpu_to_logical_apicid,
.cpu_present_to_apicid = default_cpu_present_to_apicid,
.apicid_to_cpu_present = physid_set_mask_of_physid,
.setup_portio_remap = NULL,
@@ -167,6 +170,9 @@ struct apic apic_default = {
.icr_write = native_apic_icr_write,
.wait_icr_idle = native_apic_wait_icr_idle,
.safe_wait_icr_idle = native_safe_apic_wait_icr_idle,
.x86_32_early_logical_apicid = default_x86_32_early_logical_apicid,
.x86_32_numa_cpu_node = default_x86_32_numa_cpu_node,
};
extern struct apic apic_numaq;

47
arch/x86/kernel/apic/summit_32.c
مشاهده پرونده

@@ -194,11 +194,10 @@ static unsigned long summit_check_apicid_present(int bit)
return 1;
}
static void summit_init_apic_ldr(void)
static int summit_early_logical_apicid(int cpu)
{
unsigned long val, id;
int count = 0;
u8 my_id = (u8)hard_smp_processor_id();
u8 my_id = early_per_cpu(x86_cpu_to_apicid, cpu);
u8 my_cluster = APIC_CLUSTER(my_id);
#ifdef CONFIG_SMP
u8 lid;
@@ -206,7 +205,7 @@ static void summit_init_apic_ldr(void)
/* Create logical APIC IDs by counting CPUs already in cluster. */
for (count = 0, i = nr_cpu_ids; --i >= 0; ) {
lid = cpu_2_logical_apicid[i];
lid = early_per_cpu(x86_cpu_to_logical_apicid, i);
if (lid != BAD_APICID && APIC_CLUSTER(lid) == my_cluster)
++count;
}
@@ -214,7 +213,15 @@ static void summit_init_apic_ldr(void)
/* We only have a 4 wide bitmap in cluster mode. If a deranged
* BIOS puts 5 CPUs in one APIC cluster, we're hosed. */
BUG_ON(count >= XAPIC_DEST_CPUS_SHIFT);
id = my_cluster | (1UL << count);
return my_cluster | (1UL << count);
}
static void summit_init_apic_ldr(void)
{
int cpu = smp_processor_id();
unsigned long id = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
unsigned long val;
apic_write(APIC_DFR, SUMMIT_APIC_DFR_VALUE);
val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
val |= SET_APIC_LOGICAL_ID(id);
@@ -232,27 +239,6 @@ static void summit_setup_apic_routing(void)
nr_ioapics);
}
static int summit_apicid_to_node(int logical_apicid)
{
#ifdef CONFIG_SMP
return apicid_2_node[hard_smp_processor_id()];
#else
return 0;
#endif
}
/* Mapping from cpu number to logical apicid */
static inline int summit_cpu_to_logical_apicid(int cpu)
{
#ifdef CONFIG_SMP
if (cpu >= nr_cpu_ids)
return BAD_APICID;
return cpu_2_logical_apicid[cpu];
#else
return logical_smp_processor_id();
#endif
}
static int summit_cpu_present_to_apicid(int mps_cpu)
{
if (mps_cpu < nr_cpu_ids)
@@ -286,7 +272,7 @@ static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask)
* The cpus in the mask must all be on the apic cluster.
*/
for_each_cpu(cpu, cpumask) {
int new_apicid = summit_cpu_to_logical_apicid(cpu);
int new_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) {
printk("%s: Not a valid mask!\n", __func__);
@@ -301,7 +287,7 @@ static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask)
static unsigned int summit_cpu_mask_to_apicid_and(const struct cpumask *inmask,
const struct cpumask *andmask)
{
int apicid = summit_cpu_to_logical_apicid(0);
int apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0);
cpumask_var_t cpumask;
if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC))
@@ -528,8 +514,6 @@ struct apic apic_summit = {
.ioapic_phys_id_map = summit_ioapic_phys_id_map,
.setup_apic_routing = summit_setup_apic_routing,
.multi_timer_check = NULL,
.apicid_to_node = summit_apicid_to_node,
.cpu_to_logical_apicid = summit_cpu_to_logical_apicid,
.cpu_present_to_apicid = summit_cpu_present_to_apicid,
.apicid_to_cpu_present = summit_apicid_to_cpu_present,
.setup_portio_remap = NULL,
@@ -565,4 +549,7 @@ struct apic apic_summit = {
.icr_write = native_apic_icr_write,
.wait_icr_idle = native_apic_wait_icr_idle,
.safe_wait_icr_idle = native_safe_apic_wait_icr_idle,
.x86_32_early_logical_apicid = summit_early_logical_apicid,
.x86_32_numa_cpu_node = default_x86_32_numa_cpu_node,
};

2
arch/x86/kernel/apic/x2apic_cluster.c
مشاهده پرونده

@@ -206,8 +206,6 @@ struct apic apic_x2apic_cluster = {
.ioapic_phys_id_map = NULL,
.setup_apic_routing = NULL,
.multi_timer_check = NULL,
.apicid_to_node = NULL,
.cpu_to_logical_apicid = NULL,
.cpu_present_to_apicid = default_cpu_present_to_apicid,
.apicid_to_cpu_present = NULL,
.setup_portio_remap = NULL,

2
arch/x86/kernel/apic/x2apic_phys.c
مشاهده پرونده

@@ -195,8 +195,6 @@ struct apic apic_x2apic_phys = {
.ioapic_phys_id_map = NULL,
.setup_apic_routing = NULL,
.multi_timer_check = NULL,
.apicid_to_node = NULL,
.cpu_to_logical_apicid = NULL,
.cpu_present_to_apicid = default_cpu_present_to_apicid,
.apicid_to_cpu_present = NULL,
.setup_portio_remap = NULL,

2
arch/x86/kernel/apic/x2apic_uv_x.c
مشاهده پرونده

@@ -338,8 +338,6 @@ struct apic __refdata apic_x2apic_uv_x = {
.ioapic_phys_id_map = NULL,
.setup_apic_routing = NULL,
.multi_timer_check = NULL,
.apicid_to_node = NULL,
.cpu_to_logical_apicid = NULL,
.cpu_present_to_apicid = default_cpu_present_to_apicid,
.apicid_to_cpu_present = NULL,
.setup_portio_remap = NULL,

65
arch/x86/kernel/asm-offsets.c
مشاهده پرونده

@@ -1,5 +1,70 @@
/*
* Generate definitions needed by assembly language modules.
* This code generates raw asm output which is post-processed to extract
* and format the required data.
*/
#define COMPILE_OFFSETS
#include <linux/crypto.h>
#include <linux/sched.h>
#include <linux/stddef.h>
#include <linux/hardirq.h>
#include <linux/suspend.h>
#include <linux/kbuild.h>
#include <asm/processor.h>
#include <asm/thread_info.h>
#include <asm/sigframe.h>
#include <asm/bootparam.h>
#include <asm/suspend.h>
#ifdef CONFIG_XEN
#include <xen/interface/xen.h>
#endif
#ifdef CONFIG_X86_32
# include "asm-offsets_32.c"
#else
# include "asm-offsets_64.c"
#endif
void common(void) {
BLANK();
OFFSET(TI_flags, thread_info, flags);
OFFSET(TI_status, thread_info, status);
OFFSET(TI_addr_limit, thread_info, addr_limit);
OFFSET(TI_preempt_count, thread_info, preempt_count);
BLANK();
OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
BLANK();
OFFSET(pbe_address, pbe, address);
OFFSET(pbe_orig_address, pbe, orig_address);
OFFSET(pbe_next, pbe, next);
#ifdef CONFIG_PARAVIRT
BLANK();
OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops);
OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops);
OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);
#endif
#ifdef CONFIG_XEN
BLANK();
OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending);
#endif
BLANK();
OFFSET(BP_scratch, boot_params, scratch);
OFFSET(BP_loadflags, boot_params, hdr.loadflags);
OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
OFFSET(BP_version, boot_params, hdr.version);
OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
}

69
arch/x86/kernel/asm-offsets_32.c
مشاهده پرونده

@@ -1,26 +1,4 @@
/*
* Generate definitions needed by assembly language modules.
* This code generates raw asm output which is post-processed
* to extract and format the required data.
*/
#include <linux/crypto.h>
#include <linux/sched.h>
#include <linux/signal.h>
#include <linux/personality.h>
#include <linux/suspend.h>
#include <linux/kbuild.h>
#include <asm/ucontext.h>
#include <asm/sigframe.h>
#include <asm/pgtable.h>
#include <asm/fixmap.h>
#include <asm/processor.h>
#include <asm/thread_info.h>
#include <asm/bootparam.h>
#include <asm/elf.h>
#include <asm/suspend.h>
#include <xen/interface/xen.h>
#include <linux/lguest.h>
#include "../../../drivers/lguest/lg.h"
@@ -51,21 +29,10 @@ void foo(void)
OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id);
BLANK();
OFFSET(TI_task, thread_info, task);
OFFSET(TI_exec_domain, thread_info, exec_domain);
OFFSET(TI_flags, thread_info, flags);
OFFSET(TI_status, thread_info, status);
OFFSET(TI_preempt_count, thread_info, preempt_count);
OFFSET(TI_addr_limit, thread_info, addr_limit);
OFFSET(TI_restart_block, thread_info, restart_block);
OFFSET(TI_sysenter_return, thread_info, sysenter_return);
OFFSET(TI_cpu, thread_info, cpu);
BLANK();
OFFSET(GDS_size, desc_ptr, size);
OFFSET(GDS_address, desc_ptr, address);
BLANK();
OFFSET(PT_EBX, pt_regs, bx);
OFFSET(PT_ECX, pt_regs, cx);
OFFSET(PT_EDX, pt_regs, dx);
@@ -85,42 +52,13 @@ void foo(void)
OFFSET(PT_OLDSS, pt_regs, ss);
BLANK();
OFFSET(EXEC_DOMAIN_handler, exec_domain, handler);
OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe, uc.uc_mcontext);
BLANK();
OFFSET(pbe_address, pbe, address);
OFFSET(pbe_orig_address, pbe, orig_address);
OFFSET(pbe_next, pbe, next);
/* Offset from the sysenter stack to tss.sp0 */
DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) -
sizeof(struct tss_struct));
DEFINE(PAGE_SIZE_asm, PAGE_SIZE);
DEFINE(PAGE_SHIFT_asm, PAGE_SHIFT);
DEFINE(THREAD_SIZE_asm, THREAD_SIZE);
OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
#ifdef CONFIG_PARAVIRT
BLANK();
OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops);
OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops);
OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
#endif
#ifdef CONFIG_XEN
BLANK();
OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending);
#endif
#if defined(CONFIG_LGUEST) || defined(CONFIG_LGUEST_GUEST) || defined(CONFIG_LGUEST_MODULE)
BLANK();
OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled);
@@ -139,11 +77,4 @@ void foo(void)
OFFSET(LGUEST_PAGES_regs_errcode, lguest_pages, regs.errcode);
OFFSET(LGUEST_PAGES_regs, lguest_pages, regs);
#endif
BLANK();
OFFSET(BP_scratch, boot_params, scratch);
OFFSET(BP_loadflags, boot_params, hdr.loadflags);
OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
OFFSET(BP_version, boot_params, hdr.version);
OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
}

90
arch/x86/kernel/asm-offsets_64.c
مشاهده پرونده

@@ -1,27 +1,4 @@
/*
* Generate definitions needed by assembly language modules.
* This code generates raw asm output which is post-processed to extract
* and format the required data.
*/
#define COMPILE_OFFSETS
#include <linux/crypto.h>
#include <linux/sched.h>
#include <linux/stddef.h>
#include <linux/errno.h>
#include <linux/hardirq.h>
#include <linux/suspend.h>
#include <linux/kbuild.h>
#include <asm/processor.h>
#include <asm/segment.h>
#include <asm/thread_info.h>
#include <asm/ia32.h>
#include <asm/bootparam.h>
#include <asm/suspend.h>
#include <xen/interface/xen.h>
#include <asm/sigframe.h>
#define __NO_STUBS 1
#undef __SYSCALL
@@ -33,41 +10,19 @@ static char syscalls[] = {
int main(void)
{
#define ENTRY(entry) DEFINE(tsk_ ## entry, offsetof(struct task_struct, entry))
ENTRY(state);
ENTRY(flags);
ENTRY(pid);
BLANK();
#undef ENTRY
#define ENTRY(entry) DEFINE(TI_ ## entry, offsetof(struct thread_info, entry))
ENTRY(flags);
ENTRY(addr_limit);
ENTRY(preempt_count);
ENTRY(status);
#ifdef CONFIG_IA32_EMULATION
ENTRY(sysenter_return);
#endif
BLANK();
#undef ENTRY
#ifdef CONFIG_PARAVIRT
BLANK();
OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops);
OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops);
OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
OFFSET(PV_IRQ_adjust_exception_frame, pv_irq_ops, adjust_exception_frame);
OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
OFFSET(PV_CPU_usergs_sysret32, pv_cpu_ops, usergs_sysret32);
OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64);
OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs);
OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);
BLANK();
#endif
#ifdef CONFIG_IA32_EMULATION
#define ENTRY(entry) DEFINE(IA32_SIGCONTEXT_ ## entry, offsetof(struct sigcontext_ia32, entry))
OFFSET(TI_sysenter_return, thread_info, sysenter_return);
BLANK();
#define ENTRY(entry) OFFSET(IA32_SIGCONTEXT_ ## entry, sigcontext_ia32, entry)
ENTRY(ax);
ENTRY(bx);
ENTRY(cx);
@@ -79,15 +34,12 @@ int main(void)
ENTRY(ip);
BLANK();
#undef ENTRY
DEFINE(IA32_RT_SIGFRAME_sigcontext,
offsetof (struct rt_sigframe_ia32, uc.uc_mcontext));
OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
BLANK();
#endif
DEFINE(pbe_address, offsetof(struct pbe, address));
DEFINE(pbe_orig_address, offsetof(struct pbe, orig_address));
DEFINE(pbe_next, offsetof(struct pbe, next));
BLANK();
#define ENTRY(entry) DEFINE(pt_regs_ ## entry, offsetof(struct pt_regs, entry))
#define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry)
ENTRY(bx);
ENTRY(bx);
ENTRY(cx);
@@ -107,7 +59,8 @@ int main(void)
ENTRY(flags);
BLANK();
#undef ENTRY
#define ENTRY(entry) DEFINE(saved_context_ ## entry, offsetof(struct saved_context, entry))
#define ENTRY(entry) OFFSET(saved_context_ ## entry, saved_context, entry)
ENTRY(cr0);
ENTRY(cr2);
ENTRY(cr3);
@@ -115,26 +68,11 @@ int main(void)
ENTRY(cr8);
BLANK();
#undef ENTRY
DEFINE(TSS_ist, offsetof(struct tss_struct, x86_tss.ist));
BLANK();
DEFINE(crypto_tfm_ctx_offset, offsetof(struct crypto_tfm, __crt_ctx));
OFFSET(TSS_ist, tss_struct, x86_tss.ist);
BLANK();
DEFINE(__NR_syscall_max, sizeof(syscalls) - 1);
BLANK();
OFFSET(BP_scratch, boot_params, scratch);
OFFSET(BP_loadflags, boot_params, hdr.loadflags);
OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
OFFSET(BP_version, boot_params, hdr.version);
OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
BLANK();
DEFINE(PAGE_SIZE_asm, PAGE_SIZE);
#ifdef CONFIG_XEN
BLANK();
OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending);
#undef ENTRY
#endif
return 0;
}

51
arch/x86/kernel/cpu/amd.c
مشاهده پرونده

@@ -233,18 +233,22 @@ static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c)
}
#endif
#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
#ifdef CONFIG_NUMA
/*
* To workaround broken NUMA config. Read the comment in
* srat_detect_node().
*/
static int __cpuinit nearby_node(int apicid)
{
int i, node;
for (i = apicid - 1; i >= 0; i--) {
node = apicid_to_node[i];
node = __apicid_to_node[i];
if (node != NUMA_NO_NODE && node_online(node))
return node;
}
for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) {
node = apicid_to_node[i];
node = __apicid_to_node[i];
if (node != NUMA_NO_NODE && node_online(node))
return node;
}
@@ -338,31 +342,40 @@ EXPORT_SYMBOL_GPL(amd_get_nb_id);
static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
{
#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
#ifdef CONFIG_NUMA
int cpu = smp_processor_id();
int node;
unsigned apicid = c->apicid;
node = per_cpu(cpu_llc_id, cpu);
node = numa_cpu_node(cpu);
if (node == NUMA_NO_NODE)
node = per_cpu(cpu_llc_id, cpu);
if (apicid_to_node[apicid] != NUMA_NO_NODE)
node = apicid_to_node[apicid];
if (!node_online(node)) {
/* Two possibilities here:
- The CPU is missing memory and no node was created.
In that case try picking one from a nearby CPU
- The APIC IDs differ from the HyperTransport node IDs
which the K8 northbridge parsing fills in.
Assume they are all increased by a constant offset,
but in the same order as the HT nodeids.
If that doesn't result in a usable node fall back to the
path for the previous case. */
/*
* Two possibilities here:
*
* - The CPU is missing memory and no node was created. In
* that case try picking one from a nearby CPU.
*
* - The APIC IDs differ from the HyperTransport node IDs
* which the K8 northbridge parsing fills in. Assume
* they are all increased by a constant offset, but in
* the same order as the HT nodeids. If that doesn't
* result in a usable node fall back to the path for the
* previous case.
*
* This workaround operates directly on the mapping between
* APIC ID and NUMA node, assuming certain relationship
* between APIC ID, HT node ID and NUMA topology. As going
* through CPU mapping may alter the outcome, directly
* access __apicid_to_node[].
*/
int ht_nodeid = c->initial_apicid;
if (ht_nodeid >= 0 &&
apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
node = apicid_to_node[ht_nodeid];
__apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
node = __apicid_to_node[ht_nodeid];
/* Pick a nearby node */
if (!node_online(node))
node = nearby_node(apicid);

6
arch/x86/kernel/cpu/common.c
مشاهده پرونده

@@ -675,7 +675,7 @@ void __init early_cpu_init(void)
const struct cpu_dev *const *cdev;
int count = 0;
#ifdef PROCESSOR_SELECT
#ifdef CONFIG_PROCESSOR_SELECT
printk(KERN_INFO "KERNEL supported cpus:\n");
#endif
@@ -687,7 +687,7 @@ void __init early_cpu_init(void)
cpu_devs[count] = cpudev;
count++;
#ifdef PROCESSOR_SELECT
#ifdef CONFIG_PROCESSOR_SELECT
{
unsigned int j;
@@ -869,7 +869,7 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
select_idle_routine(c);
#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
#ifdef CONFIG_NUMA
numa_add_cpu(smp_processor_id());
#endif
}

5
arch/x86/kernel/cpu/intel.c
مشاهده پرونده

@@ -276,14 +276,13 @@ static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c)
static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
{
#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
#ifdef CONFIG_NUMA
unsigned node;
int cpu = smp_processor_id();
int apicid = cpu_has_apic ? hard_smp_processor_id() : c->apicid;
/* Don't do the funky fallback heuristics the AMD version employs
for now. */
node = apicid_to_node[apicid];
node = numa_cpu_node(cpu);
if (node == NUMA_NO_NODE || !node_online(node)) {
/* reuse the value from init_cpu_to_node() */
node = cpu_to_node(cpu);

4
arch/x86/kernel/cpu/intel_cacheinfo.c
مشاهده پرونده

@@ -768,11 +768,11 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
struct cpuinfo_x86 *c = &cpu_data(cpu);
if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) {
for_each_cpu(i, c->llc_shared_map) {
for_each_cpu(i, cpu_llc_shared_mask(cpu)) {
if (!per_cpu(ici_cpuid4_info, i))
continue;
this_leaf = CPUID4_INFO_IDX(i, index);
for_each_cpu(sibling, c->llc_shared_map) {
for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) {
if (!cpu_online(sibling))
continue;
set_bit(sibling, this_leaf->shared_cpu_map);

7
arch/x86/kernel/cpu/mcheck/mce_amd.c
مشاهده پرونده

@@ -527,15 +527,12 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
int i, err = 0;
struct threshold_bank *b = NULL;
char name[32];
#ifdef CONFIG_SMP
struct cpuinfo_x86 *c = &cpu_data(cpu);
#endif
sprintf(name, "threshold_bank%i", bank);
#ifdef CONFIG_SMP
if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) { /* symlink */
i = cpumask_first(c->llc_shared_map);
i = cpumask_first(cpu_llc_shared_mask(cpu));
/* first core not up yet */
if (cpu_data(i).cpu_core_id)
@@ -555,7 +552,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
if (err)
goto out;
cpumask_copy(b->cpus, c->llc_shared_map);
cpumask_copy(b->cpus, cpu_llc_shared_mask(cpu));
per_cpu(threshold_banks, cpu)[bank] = b;
goto out;

170
arch/x86/kernel/cpu/perf_event.c
مشاهده پرونده

@@ -30,6 +30,7 @@
#include <asm/stacktrace.h>
#include <asm/nmi.h>
#include <asm/compat.h>
#include <asm/smp.h>
#if 0
#undef wrmsrl
@@ -93,6 +94,8 @@ struct amd_nb {
struct event_constraint event_constraints[X86_PMC_IDX_MAX];
};
struct intel_percore;
#define MAX_LBR_ENTRIES 16
struct cpu_hw_events {
@@ -127,6 +130,13 @@ struct cpu_hw_events {
struct perf_branch_stack lbr_stack;
struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES];
/*
* Intel percore register state.
* Coordinate shared resources between HT threads.
*/
int percore_used; /* Used by this CPU? */
struct intel_percore *per_core;
/*
* AMD specific bits
*/
@@ -166,8 +176,10 @@ struct cpu_hw_events {
/*
* Constraint on the Event code + UMask
*/
#define PEBS_EVENT_CONSTRAINT(c, n) \
#define INTEL_UEVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
#define PEBS_EVENT_CONSTRAINT(c, n) \
INTEL_UEVENT_CONSTRAINT(c, n)
#define EVENT_CONSTRAINT_END \
EVENT_CONSTRAINT(0, 0, 0)
@@ -175,6 +187,28 @@ struct cpu_hw_events {
#define for_each_event_constraint(e, c) \
for ((e) = (c); (e)->weight; (e)++)
/*
* Extra registers for specific events.
* Some events need large masks and require external MSRs.
* Define a mapping to these extra registers.
*/
struct extra_reg {
unsigned int event;
unsigned int msr;
u64 config_mask;
u64 valid_mask;
};
#define EVENT_EXTRA_REG(e, ms, m, vm) { \
.event = (e), \
.msr = (ms), \
.config_mask = (m), \
.valid_mask = (vm), \
}
#define INTEL_EVENT_EXTRA_REG(event, msr, vm) \
EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm)
#define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0)
union perf_capabilities {
struct {
u64 lbr_format : 6;
@@ -219,6 +253,7 @@ struct x86_pmu {
void (*put_event_constraints)(struct cpu_hw_events *cpuc,
struct perf_event *event);
struct event_constraint *event_constraints;
struct event_constraint *percore_constraints;
void (*quirks)(void);
int perfctr_second_write;
@@ -247,6 +282,11 @@ struct x86_pmu {
*/
unsigned long lbr_tos, lbr_from, lbr_to; /* MSR base regs */
int lbr_nr; /* hardware stack size */
/*
* Extra registers for events
*/
struct extra_reg *extra_regs;
};
static struct x86_pmu x86_pmu __read_mostly;
@@ -271,6 +311,10 @@ static u64 __read_mostly hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX];
static u64 __read_mostly hw_cache_extra_regs
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX];
/*
* Propagate event elapsed time into the generic event.
@@ -298,7 +342,7 @@ x86_perf_event_update(struct perf_event *event)
*/
again:
prev_raw_count = local64_read(&hwc->prev_count);
rdmsrl(hwc->event_base + idx, new_raw_count);
rdmsrl(hwc->event_base, new_raw_count);
if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
new_raw_count) != prev_raw_count)
@@ -321,6 +365,49 @@ again:
return new_raw_count;
}
/* using X86_FEATURE_PERFCTR_CORE to later implement ALTERNATIVE() here */
static inline int x86_pmu_addr_offset(int index)
{
if (boot_cpu_has(X86_FEATURE_PERFCTR_CORE))
return index << 1;
return index;
}
static inline unsigned int x86_pmu_config_addr(int index)
{
return x86_pmu.eventsel + x86_pmu_addr_offset(index);
}
static inline unsigned int x86_pmu_event_addr(int index)
{
return x86_pmu.perfctr + x86_pmu_addr_offset(index);
}
/*
* Find and validate any extra registers to set up.
*/
static int x86_pmu_extra_regs(u64 config, struct perf_event *event)
{
struct extra_reg *er;
event->hw.extra_reg = 0;
event->hw.extra_config = 0;
if (!x86_pmu.extra_regs)
return 0;
for (er = x86_pmu.extra_regs; er->msr; er++) {
if (er->event != (config & er->config_mask))
continue;
if (event->attr.config1 & ~er->valid_mask)
return -EINVAL;
event->hw.extra_reg = er->msr;
event->hw.extra_config = event->attr.config1;
break;
}
return 0;
}
static atomic_t active_events;
static DEFINE_MUTEX(pmc_reserve_mutex);
@@ -331,12 +418,12 @@ static bool reserve_pmc_hardware(void)
int i;
for (i = 0; i < x86_pmu.num_counters; i++) {
if (!reserve_perfctr_nmi(x86_pmu.perfctr + i))
if (!reserve_perfctr_nmi(x86_pmu_event_addr(i)))
goto perfctr_fail;
}
for (i = 0; i < x86_pmu.num_counters; i++) {
if (!reserve_evntsel_nmi(x86_pmu.eventsel + i))
if (!reserve_evntsel_nmi(x86_pmu_config_addr(i)))
goto eventsel_fail;
}
@@ -344,13 +431,13 @@ static bool reserve_pmc_hardware(void)
eventsel_fail:
for (i--; i >= 0; i--)
release_evntsel_nmi(x86_pmu.eventsel + i);
release_evntsel_nmi(x86_pmu_config_addr(i));
i = x86_pmu.num_counters;
perfctr_fail:
for (i--; i >= 0; i--)
release_perfctr_nmi(x86_pmu.perfctr + i);
release_perfctr_nmi(x86_pmu_event_addr(i));
return false;
}
@@ -360,8 +447,8 @@ static void release_pmc_hardware(void)
int i;
for (i = 0; i < x86_pmu.num_counters; i++) {
release_perfctr_nmi(x86_pmu.perfctr + i);
release_evntsel_nmi(x86_pmu.eventsel + i);
release_perfctr_nmi(x86_pmu_event_addr(i));
release_evntsel_nmi(x86_pmu_config_addr(i));
}
}
@@ -382,7 +469,7 @@ static bool check_hw_exists(void)
* complain and bail.
*/
for (i = 0; i < x86_pmu.num_counters; i++) {
reg = x86_pmu.eventsel + i;
reg = x86_pmu_config_addr(i);
ret = rdmsrl_safe(reg, &val);
if (ret)
goto msr_fail;
@@ -407,8 +494,8 @@ static bool check_hw_exists(void)
* that don't trap on the MSR access and always return 0s.
*/
val = 0xabcdUL;
ret = checking_wrmsrl(x86_pmu.perfctr, val);
ret |= rdmsrl_safe(x86_pmu.perfctr, &val_new);
ret = checking_wrmsrl(x86_pmu_event_addr(0), val);
ret |= rdmsrl_safe(x86_pmu_event_addr(0), &val_new);
if (ret || val != val_new)
goto msr_fail;
@@ -442,8 +529,9 @@ static inline int x86_pmu_initialized(void)
}
static inline int
set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr)
set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event)
{
struct perf_event_attr *attr = &event->attr;
unsigned int cache_type, cache_op, cache_result;
u64 config, val;
@@ -470,8 +558,8 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr)
return -EINVAL;
hwc->config |= val;
return 0;
attr->config1 = hw_cache_extra_regs[cache_type][cache_op][cache_result];
return x86_pmu_extra_regs(val, event);
}
static int x86_setup_perfctr(struct perf_event *event)
@@ -496,10 +584,10 @@ static int x86_setup_perfctr(struct perf_event *event)
}
if (attr->type == PERF_TYPE_RAW)
return 0;
return x86_pmu_extra_regs(event->attr.config, event);
if (attr->type == PERF_TYPE_HW_CACHE)
return set_ext_hw_attr(hwc, attr);
return set_ext_hw_attr(hwc, event);
if (attr->config >= x86_pmu.max_events)
return -EINVAL;
@@ -617,11 +705,11 @@ static void x86_pmu_disable_all(void)
if (!test_bit(idx, cpuc->active_mask))
continue;
rdmsrl(x86_pmu.eventsel + idx, val);
rdmsrl(x86_pmu_config_addr(idx), val);
if (!(val & ARCH_PERFMON_EVENTSEL_ENABLE))
continue;
val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
wrmsrl(x86_pmu.eventsel + idx, val);
wrmsrl(x86_pmu_config_addr(idx), val);
}
}
@@ -642,21 +730,26 @@ static void x86_pmu_disable(struct pmu *pmu)
x86_pmu.disable_all();
}
static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
u64 enable_mask)
{
if (hwc->extra_reg)
wrmsrl(hwc->extra_reg, hwc->extra_config);
wrmsrl(hwc->config_base, hwc->config | enable_mask);
}
static void x86_pmu_enable_all(int added)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
int idx;
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
struct perf_event *event = cpuc->events[idx];
u64 val;
struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
if (!test_bit(idx, cpuc->active_mask))
continue;
val = event->hw.config;
val |= ARCH_PERFMON_EVENTSEL_ENABLE;
wrmsrl(x86_pmu.eventsel + idx, val);
__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
}
}
@@ -821,15 +914,10 @@ static inline void x86_assign_hw_event(struct perf_event *event,
hwc->event_base = 0;
} else if (hwc->idx >= X86_PMC_IDX_FIXED) {
hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
/*
* We set it so that event_base + idx in wrmsr/rdmsr maps to
* MSR_ARCH_PERFMON_FIXED_CTR0 ... CTR2:
*/
hwc->event_base =
MSR_ARCH_PERFMON_FIXED_CTR0 - X86_PMC_IDX_FIXED;
hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0;
} else {
hwc->config_base = x86_pmu.eventsel;
hwc->event_base = x86_pmu.perfctr;
hwc->config_base = x86_pmu_config_addr(hwc->idx);
hwc->event_base = x86_pmu_event_addr(hwc->idx);
}
}
@@ -915,17 +1003,11 @@ static void x86_pmu_enable(struct pmu *pmu)
x86_pmu.enable_all(added);
}
static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
u64 enable_mask)
{
wrmsrl(hwc->config_base + hwc->idx, hwc->config | enable_mask);
}
static inline void x86_pmu_disable_event(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
wrmsrl(hwc->config_base + hwc->idx, hwc->config);
wrmsrl(hwc->config_base, hwc->config);
}
static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
@@ -978,7 +1060,7 @@ x86_perf_event_set_period(struct perf_event *event)
*/
local64_set(&hwc->prev_count, (u64)-left);
wrmsrl(hwc->event_base + idx, (u64)(-left) & x86_pmu.cntval_mask);
wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
/*
* Due to erratum on certan cpu we need
@@ -986,7 +1068,7 @@ x86_perf_event_set_period(struct perf_event *event)
* is updated properly
*/
if (x86_pmu.perfctr_second_write) {
wrmsrl(hwc->event_base + idx,
wrmsrl(hwc->event_base,
(u64)(-left) & x86_pmu.cntval_mask);
}
@@ -1113,8 +1195,8 @@ void perf_event_print_debug(void)
pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask);
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
rdmsrl(x86_pmu.eventsel + idx, pmc_ctrl);
rdmsrl(x86_pmu.perfctr + idx, pmc_count);
rdmsrl(x86_pmu_config_addr(idx), pmc_ctrl);
rdmsrl(x86_pmu_event_addr(idx), pmc_count);
prev_left = per_cpu(pmc_prev_left[idx], cpu);
@@ -1389,7 +1471,7 @@ static void __init pmu_check_apic(void)
pr_info("no hardware sampling interrupt available.\n");
}
int __init init_hw_perf_events(void)
static int __init init_hw_perf_events(void)
{
struct event_constraint *c;
int err;
@@ -1608,7 +1690,7 @@ out:
return ret;
}
int x86_pmu_event_init(struct perf_event *event)
static int x86_pmu_event_init(struct perf_event *event)
{
struct pmu *tmp;
int err;

175
arch/x86/kernel/cpu/perf_event_amd.c
مشاهده پرونده

@@ -127,6 +127,11 @@ static int amd_pmu_hw_config(struct perf_event *event)
/*
* AMD64 events are detected based on their event codes.
*/
static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc)
{
return ((hwc->config >> 24) & 0x0f00) | (hwc->config & 0x00ff);
}
static inline int amd_is_nb_event(struct hw_perf_event *hwc)
{
return (hwc->config & 0xe0) == 0xe0;
@@ -385,13 +390,181 @@ static __initconst const struct x86_pmu amd_pmu = {
.cpu_dead = amd_pmu_cpu_dead,
};
/* AMD Family 15h */
#define AMD_EVENT_TYPE_MASK 0x000000F0ULL
#define AMD_EVENT_FP 0x00000000ULL ... 0x00000010ULL
#define AMD_EVENT_LS 0x00000020ULL ... 0x00000030ULL
#define AMD_EVENT_DC 0x00000040ULL ... 0x00000050ULL
#define AMD_EVENT_CU 0x00000060ULL ... 0x00000070ULL
#define AMD_EVENT_IC_DE 0x00000080ULL ... 0x00000090ULL
#define AMD_EVENT_EX_LS 0x000000C0ULL
#define AMD_EVENT_DE 0x000000D0ULL
#define AMD_EVENT_NB 0x000000E0ULL ... 0x000000F0ULL
/*
* AMD family 15h event code/PMC mappings:
*
* type = event_code & 0x0F0:
*
* 0x000 FP PERF_CTL[5:3]
* 0x010 FP PERF_CTL[5:3]
* 0x020 LS PERF_CTL[5:0]
* 0x030 LS PERF_CTL[5:0]
* 0x040 DC PERF_CTL[5:0]
* 0x050 DC PERF_CTL[5:0]
* 0x060 CU PERF_CTL[2:0]
* 0x070 CU PERF_CTL[2:0]
* 0x080 IC/DE PERF_CTL[2:0]
* 0x090 IC/DE PERF_CTL[2:0]
* 0x0A0 ---
* 0x0B0 ---
* 0x0C0 EX/LS PERF_CTL[5:0]
* 0x0D0 DE PERF_CTL[2:0]
* 0x0E0 NB NB_PERF_CTL[3:0]
* 0x0F0 NB NB_PERF_CTL[3:0]
*
* Exceptions:
*
* 0x003 FP PERF_CTL[3]
* 0x00B FP PERF_CTL[3]
* 0x00D FP PERF_CTL[3]
* 0x023 DE PERF_CTL[2:0]
* 0x02D LS PERF_CTL[3]
* 0x02E LS PERF_CTL[3,0]
* 0x043 CU PERF_CTL[2:0]
* 0x045 CU PERF_CTL[2:0]
* 0x046 CU PERF_CTL[2:0]
* 0x054 CU PERF_CTL[2:0]
* 0x055 CU PERF_CTL[2:0]
* 0x08F IC PERF_CTL[0]
* 0x187 DE PERF_CTL[0]
* 0x188 DE PERF_CTL[0]
* 0x0DB EX PERF_CTL[5:0]
* 0x0DC LS PERF_CTL[5:0]
* 0x0DD LS PERF_CTL[5:0]
* 0x0DE LS PERF_CTL[5:0]
* 0x0DF LS PERF_CTL[5:0]
* 0x1D6 EX PERF_CTL[5:0]
* 0x1D8 EX PERF_CTL[5:0]
*/
static struct event_constraint amd_f15_PMC0 = EVENT_CONSTRAINT(0, 0x01, 0);
static struct event_constraint amd_f15_PMC20 = EVENT_CONSTRAINT(0, 0x07, 0);
static struct event_constraint amd_f15_PMC3 = EVENT_CONSTRAINT(0, 0x08, 0);
static struct event_constraint amd_f15_PMC30 = EVENT_CONSTRAINT(0, 0x09, 0);
static struct event_constraint amd_f15_PMC50 = EVENT_CONSTRAINT(0, 0x3F, 0);
static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0);
static struct event_constraint *
amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event)
{
unsigned int event_code = amd_get_event_code(&event->hw);
switch (event_code & AMD_EVENT_TYPE_MASK) {
case AMD_EVENT_FP:
switch (event_code) {
case 0x003:
case 0x00B:
case 0x00D:
return &amd_f15_PMC3;
default:
return &amd_f15_PMC53;
}
case AMD_EVENT_LS:
case AMD_EVENT_DC:
case AMD_EVENT_EX_LS:
switch (event_code) {
case 0x023:
case 0x043:
case 0x045:
case 0x046:
case 0x054:
case 0x055:
return &amd_f15_PMC20;
case 0x02D:
return &amd_f15_PMC3;
case 0x02E:
return &amd_f15_PMC30;
default:
return &amd_f15_PMC50;
}
case AMD_EVENT_CU:
case AMD_EVENT_IC_DE:
case AMD_EVENT_DE:
switch (event_code) {
case 0x08F:
case 0x187:
case 0x188:
return &amd_f15_PMC0;
case 0x0DB ... 0x0DF:
case 0x1D6:
case 0x1D8:
return &amd_f15_PMC50;
default:
return &amd_f15_PMC20;
}
case AMD_EVENT_NB:
/* not yet implemented */
return &emptyconstraint;
default:
return &emptyconstraint;
}
}
static __initconst const struct x86_pmu amd_pmu_f15h = {
.name = "AMD Family 15h",
.handle_irq = x86_pmu_handle_irq,
.disable_all = x86_pmu_disable_all,
.enable_all = x86_pmu_enable_all,
.enable = x86_pmu_enable_event,
.disable = x86_pmu_disable_event,
.hw_config = amd_pmu_hw_config,
.schedule_events = x86_schedule_events,
.eventsel = MSR_F15H_PERF_CTL,
.perfctr = MSR_F15H_PERF_CTR,
.event_map = amd_pmu_event_map,
.max_events = ARRAY_SIZE(amd_perfmon_event_map),
.num_counters = 6,
.cntval_bits = 48,
.cntval_mask = (1ULL << 48) - 1,
.apic = 1,
/* use highest bit to detect overflow */
.max_period = (1ULL << 47) - 1,
.get_event_constraints = amd_get_event_constraints_f15h,
/* nortbridge counters not yet implemented: */
#if 0
.put_event_constraints = amd_put_event_constraints,
.cpu_prepare = amd_pmu_cpu_prepare,
.cpu_starting = amd_pmu_cpu_starting,
.cpu_dead = amd_pmu_cpu_dead,
#endif
};
static __init int amd_pmu_init(void)
{
/* Performance-monitoring supported from K7 and later: */
if (boot_cpu_data.x86 < 6)
return -ENODEV;
x86_pmu = amd_pmu;
/*
* If core performance counter extensions exists, it must be
* family 15h, otherwise fail. See x86_pmu_addr_offset().
*/
switch (boot_cpu_data.x86) {
case 0x15:
if (!cpu_has_perfctr_core)
return -ENODEV;
x86_pmu = amd_pmu_f15h;
break;
default:
if (cpu_has_perfctr_core)
return -ENODEV;
x86_pmu = amd_pmu;
break;
}
/* Events are common for all AMDs */
memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,

417
arch/x86/kernel/cpu/perf_event_intel.c
مشاهده پرونده

@@ -1,5 +1,27 @@
#ifdef CONFIG_CPU_SUP_INTEL
#define MAX_EXTRA_REGS 2
/*
* Per register state.
*/
struct er_account {
int ref; /* reference count */
unsigned int extra_reg; /* extra MSR number */
u64 extra_config; /* extra MSR config */
};
/*
* Per core state
* This used to coordinate shared registers for HT threads.
*/
struct intel_percore {
raw_spinlock_t lock; /* protect structure */
struct er_account regs[MAX_EXTRA_REGS];
int refcnt; /* number of threads */
unsigned core_id;
};
/*
* Intel PerfMon, used on Core and later.
*/
@@ -64,6 +86,18 @@ static struct event_constraint intel_nehalem_event_constraints[] =
EVENT_CONSTRAINT_END
};
static struct extra_reg intel_nehalem_extra_regs[] =
{
INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff),
EVENT_EXTRA_END
};
static struct event_constraint intel_nehalem_percore_constraints[] =
{
INTEL_EVENT_CONSTRAINT(0xb7, 0),
EVENT_CONSTRAINT_END
};
static struct event_constraint intel_westmere_event_constraints[] =
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
@@ -76,6 +110,33 @@ static struct event_constraint intel_westmere_event_constraints[] =
EVENT_CONSTRAINT_END
};
static struct event_constraint intel_snb_event_constraints[] =
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
/* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */
INTEL_EVENT_CONSTRAINT(0xb7, 0x1), /* OFF_CORE_RESPONSE_0 */
INTEL_EVENT_CONSTRAINT(0xbb, 0x8), /* OFF_CORE_RESPONSE_1 */
INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
EVENT_CONSTRAINT_END
};
static struct extra_reg intel_westmere_extra_regs[] =
{
INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff),
INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff),
EVENT_EXTRA_END
};
static struct event_constraint intel_westmere_percore_constraints[] =
{
INTEL_EVENT_CONSTRAINT(0xb7, 0),
INTEL_EVENT_CONSTRAINT(0xbb, 0),
EVENT_CONSTRAINT_END
};
static struct event_constraint intel_gen_event_constraints[] =
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
@@ -89,6 +150,106 @@ static u64 intel_pmu_event_map(int hw_event)
return intel_perfmon_event_map[hw_event];
}
static __initconst const u64 snb_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] =
{
[ C(L1D) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0xf1d0, /* MEM_UOP_RETIRED.LOADS */
[ C(RESULT_MISS) ] = 0x0151, /* L1D.REPLACEMENT */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0xf2d0, /* MEM_UOP_RETIRED.STORES */
[ C(RESULT_MISS) ] = 0x0851, /* L1D.ALL_M_REPLACEMENT */
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x0,
[ C(RESULT_MISS) ] = 0x024e, /* HW_PRE_REQ.DL1_MISS */
},
},
[ C(L1I ) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x0,
[ C(RESULT_MISS) ] = 0x0280, /* ICACHE.MISSES */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = -1,
[ C(RESULT_MISS) ] = -1,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x0,
[ C(RESULT_MISS) ] = 0x0,
},
},
[ C(LL ) ] = {
/*
* TBD: Need Off-core Response Performance Monitoring support
*/
[ C(OP_READ) ] = {
/* OFFCORE_RESPONSE_0.ANY_DATA.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
/* OFFCORE_RESPONSE_1.ANY_DATA.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01bb,
},
[ C(OP_WRITE) ] = {
/* OFFCORE_RESPONSE_0.ANY_RFO.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
/* OFFCORE_RESPONSE_1.ANY_RFO.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01bb,
},
[ C(OP_PREFETCH) ] = {
/* OFFCORE_RESPONSE_0.PREFETCH.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
/* OFFCORE_RESPONSE_1.PREFETCH.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01bb,
},
},
[ C(DTLB) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_UOP_RETIRED.ALL_LOADS */
[ C(RESULT_MISS) ] = 0x0108, /* DTLB_LOAD_MISSES.CAUSES_A_WALK */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_UOP_RETIRED.ALL_STORES */
[ C(RESULT_MISS) ] = 0x0149, /* DTLB_STORE_MISSES.MISS_CAUSES_A_WALK */
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x0,
[ C(RESULT_MISS) ] = 0x0,
},
},
[ C(ITLB) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x1085, /* ITLB_MISSES.STLB_HIT */
[ C(RESULT_MISS) ] = 0x0185, /* ITLB_MISSES.CAUSES_A_WALK */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = -1,
[ C(RESULT_MISS) ] = -1,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = -1,
[ C(RESULT_MISS) ] = -1,
},
},
[ C(BPU ) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */
[ C(RESULT_MISS) ] = 0x00c5, /* BR_MISP_RETIRED.ALL_BRANCHES */
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = -1,
[ C(RESULT_MISS) ] = -1,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = -1,
[ C(RESULT_MISS) ] = -1,
},
},
};
static __initconst const u64 westmere_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -124,16 +285,26 @@ static __initconst const u64 westmere_hw_cache_event_ids
},
[ C(LL ) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS */
[ C(RESULT_MISS) ] = 0x0224, /* L2_RQSTS.LD_MISS */
/* OFFCORE_RESPONSE_0.ANY_DATA.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
/* OFFCORE_RESPONSE_1.ANY_DATA.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01bb,
},
/*
* Use RFO, not WRITEBACK, because a write miss would typically occur
* on RFO.
*/
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS */
[ C(RESULT_MISS) ] = 0x0824, /* L2_RQSTS.RFO_MISS */
/* OFFCORE_RESPONSE_1.ANY_RFO.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01bb,
/* OFFCORE_RESPONSE_0.ANY_RFO.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference */
[ C(RESULT_MISS) ] = 0x412e, /* LLC Misses */
/* OFFCORE_RESPONSE_0.PREFETCH.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
/* OFFCORE_RESPONSE_1.PREFETCH.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01bb,
},
},
[ C(DTLB) ] = {
@@ -180,6 +351,39 @@ static __initconst const u64 westmere_hw_cache_event_ids
},
};
/*
* OFFCORE_RESPONSE MSR bits (subset), See IA32 SDM Vol 3 30.6.1.3
*/
#define DMND_DATA_RD (1 << 0)
#define DMND_RFO (1 << 1)
#define DMND_WB (1 << 3)
#define PF_DATA_RD (1 << 4)
#define PF_DATA_RFO (1 << 5)
#define RESP_UNCORE_HIT (1 << 8)
#define RESP_MISS (0xf600) /* non uncore hit */
static __initconst const u64 nehalem_hw_cache_extra_regs
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] =
{
[ C(LL ) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = DMND_DATA_RD|RESP_UNCORE_HIT,
[ C(RESULT_MISS) ] = DMND_DATA_RD|RESP_MISS,
},
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = DMND_RFO|DMND_WB|RESP_UNCORE_HIT,
[ C(RESULT_MISS) ] = DMND_RFO|DMND_WB|RESP_MISS,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = PF_DATA_RD|PF_DATA_RFO|RESP_UNCORE_HIT,
[ C(RESULT_MISS) ] = PF_DATA_RD|PF_DATA_RFO|RESP_MISS,
},
}
};
static __initconst const u64 nehalem_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -215,16 +419,26 @@ static __initconst const u64 nehalem_hw_cache_event_ids
},
[ C(LL ) ] = {
[ C(OP_READ) ] = {
[ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS */
[ C(RESULT_MISS) ] = 0x0224, /* L2_RQSTS.LD_MISS */
/* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
/* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01b7,
},
/*
* Use RFO, not WRITEBACK, because a write miss would typically occur
* on RFO.
*/
[ C(OP_WRITE) ] = {
[ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS */
[ C(RESULT_MISS) ] = 0x0824, /* L2_RQSTS.RFO_MISS */
/* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
/* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_PREFETCH) ] = {
[ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference */
[ C(RESULT_MISS) ] = 0x412e, /* LLC Misses */
/* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
/* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01b7,
},
},
[ C(DTLB) ] = {
@@ -691,8 +905,8 @@ static void intel_pmu_reset(void)
printk("clearing PMU state on CPU#%d\n", smp_processor_id());
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
checking_wrmsrl(x86_pmu.eventsel + idx, 0ull);
checking_wrmsrl(x86_pmu.perfctr + idx, 0ull);
checking_wrmsrl(x86_pmu_config_addr(idx), 0ull);
checking_wrmsrl(x86_pmu_event_addr(idx), 0ull);
}
for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++)
checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
@@ -793,6 +1007,67 @@ intel_bts_constraints(struct perf_event *event)
return NULL;
}
static struct event_constraint *
intel_percore_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
unsigned int e = hwc->config & ARCH_PERFMON_EVENTSEL_EVENT;
struct event_constraint *c;
struct intel_percore *pc;
struct er_account *era;
int i;
int free_slot;
int found;
if (!x86_pmu.percore_constraints || hwc->extra_alloc)
return NULL;
for (c = x86_pmu.percore_constraints; c->cmask; c++) {
if (e != c->code)
continue;
/*
* Allocate resource per core.
*/
pc = cpuc->per_core;
if (!pc)
break;
c = &emptyconstraint;
raw_spin_lock(&pc->lock);
free_slot = -1;
found = 0;
for (i = 0; i < MAX_EXTRA_REGS; i++) {
era = &pc->regs[i];
if (era->ref > 0 && hwc->extra_reg == era->extra_reg) {
/* Allow sharing same config */
if (hwc->extra_config == era->extra_config) {
era->ref++;
cpuc->percore_used = 1;
hwc->extra_alloc = 1;
c = NULL;
}
/* else conflict */
found = 1;
break;
} else if (era->ref == 0 && free_slot == -1)
free_slot = i;
}
if (!found && free_slot != -1) {
era = &pc->regs[free_slot];
era->ref = 1;
era->extra_reg = hwc->extra_reg;
era->extra_config = hwc->extra_config;
cpuc->percore_used = 1;
hwc->extra_alloc = 1;
c = NULL;
}
raw_spin_unlock(&pc->lock);
return c;
}
return NULL;
}
static struct event_constraint *
intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
{
@@ -806,9 +1081,51 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event
if (c)
return c;
c = intel_percore_constraints(cpuc, event);
if (c)
return c;
return x86_get_event_constraints(cpuc, event);
}
static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
struct perf_event *event)
{
struct extra_reg *er;
struct intel_percore *pc;
struct er_account *era;
struct hw_perf_event *hwc = &event->hw;
int i, allref;
if (!cpuc->percore_used)
return;
for (er = x86_pmu.extra_regs; er->msr; er++) {
if (er->event != (hwc->config & er->config_mask))
continue;
pc = cpuc->per_core;
raw_spin_lock(&pc->lock);
for (i = 0; i < MAX_EXTRA_REGS; i++) {
era = &pc->regs[i];
if (era->ref > 0 &&
era->extra_config == hwc->extra_config &&
era->extra_reg == er->msr) {
era->ref--;
hwc->extra_alloc = 0;
break;
}
}
allref = 0;
for (i = 0; i < MAX_EXTRA_REGS; i++)
allref += pc->regs[i].ref;
if (allref == 0)
cpuc->percore_used = 0;
raw_spin_unlock(&pc->lock);
break;
}
}
static int intel_pmu_hw_config(struct perf_event *event)
{
int ret = x86_pmu_hw_config(event);
@@ -880,20 +1197,67 @@ static __initconst const struct x86_pmu core_pmu = {
*/
.max_period = (1ULL << 31) - 1,
.get_event_constraints = intel_get_event_constraints,
.put_event_constraints = intel_put_event_constraints,
.event_constraints = intel_core_event_constraints,
};
static int intel_pmu_cpu_prepare(int cpu)
{
struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
if (!cpu_has_ht_siblings())
return NOTIFY_OK;
cpuc->per_core = kzalloc_node(sizeof(struct intel_percore),
GFP_KERNEL, cpu_to_node(cpu));
if (!cpuc->per_core)
return NOTIFY_BAD;
raw_spin_lock_init(&cpuc->per_core->lock);
cpuc->per_core->core_id = -1;
return NOTIFY_OK;
}
static void intel_pmu_cpu_starting(int cpu)
{
struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
int core_id = topology_core_id(cpu);
int i;
init_debug_store_on_cpu(cpu);
/*
* Deal with CPUs that don't clear their LBRs on power-up.
*/
intel_pmu_lbr_reset();
if (!cpu_has_ht_siblings())
return;
for_each_cpu(i, topology_thread_cpumask(cpu)) {
struct intel_percore *pc = per_cpu(cpu_hw_events, i).per_core;
if (pc && pc->core_id == core_id) {
kfree(cpuc->per_core);
cpuc->per_core = pc;
break;
}
}
cpuc->per_core->core_id = core_id;
cpuc->per_core->refcnt++;
}
static void intel_pmu_cpu_dying(int cpu)
{
struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
struct intel_percore *pc = cpuc->per_core;
if (pc) {
if (pc->core_id == -1 || --pc->refcnt == 0)
kfree(pc);
cpuc->per_core = NULL;
}
fini_debug_store_on_cpu(cpu);
}
@@ -918,7 +1282,9 @@ static __initconst const struct x86_pmu intel_pmu = {
*/
.max_period = (1ULL << 31) - 1,
.get_event_constraints = intel_get_event_constraints,
.put_event_constraints = intel_put_event_constraints,
.cpu_prepare = intel_pmu_cpu_prepare,
.cpu_starting = intel_pmu_cpu_starting,
.cpu_dying = intel_pmu_cpu_dying,
};
@@ -1024,6 +1390,7 @@ static __init int intel_pmu_init(void)
intel_pmu_lbr_init_core();
x86_pmu.event_constraints = intel_core2_event_constraints;
x86_pmu.pebs_constraints = intel_core2_pebs_event_constraints;
pr_cont("Core2 events, ");
break;
@@ -1032,11 +1399,16 @@ static __init int intel_pmu_init(void)
case 46: /* 45 nm nehalem-ex, "Beckton" */
memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
sizeof(hw_cache_extra_regs));
intel_pmu_lbr_init_nhm();
x86_pmu.event_constraints = intel_nehalem_event_constraints;
x86_pmu.pebs_constraints = intel_nehalem_pebs_event_constraints;
x86_pmu.percore_constraints = intel_nehalem_percore_constraints;
x86_pmu.enable_all = intel_pmu_nhm_enable_all;
x86_pmu.extra_regs = intel_nehalem_extra_regs;
pr_cont("Nehalem events, ");
break;
@@ -1047,6 +1419,7 @@ static __init int intel_pmu_init(void)
intel_pmu_lbr_init_atom();
x86_pmu.event_constraints = intel_gen_event_constraints;
x86_pmu.pebs_constraints = intel_atom_pebs_event_constraints;
pr_cont("Atom events, ");
break;
@@ -1054,14 +1427,30 @@ static __init int intel_pmu_init(void)
case 44: /* 32 nm nehalem, "Gulftown" */
memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
sizeof(hw_cache_extra_regs));
intel_pmu_lbr_init_nhm();
x86_pmu.event_constraints = intel_westmere_event_constraints;
x86_pmu.percore_constraints = intel_westmere_percore_constraints;
x86_pmu.enable_all = intel_pmu_nhm_enable_all;
x86_pmu.pebs_constraints = intel_westmere_pebs_event_constraints;
x86_pmu.extra_regs = intel_westmere_extra_regs;
pr_cont("Westmere events, ");
break;
case 42: /* SandyBridge */
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
intel_pmu_lbr_init_nhm();
x86_pmu.event_constraints = intel_snb_event_constraints;
x86_pmu.pebs_constraints = intel_snb_pebs_events;
pr_cont("SandyBridge events, ");
break;
default:
/*
* default constraints for v2 and up

97
arch/x86/kernel/cpu/perf_event_intel_ds.c
مشاهده پرونده

@@ -361,30 +361,88 @@ static int intel_pmu_drain_bts_buffer(void)
/*
* PEBS
*/
static struct event_constraint intel_core_pebs_events[] = {
PEBS_EVENT_CONSTRAINT(0x00c0, 0x1), /* INSTR_RETIRED.ANY */
static struct event_constraint intel_core2_pebs_event_constraints[] = {
PEBS_EVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
PEBS_EVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */
PEBS_EVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
PEBS_EVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
PEBS_EVENT_CONSTRAINT(0x01cb, 0x1), /* MEM_LOAD_RETIRED.L1D_MISS */
PEBS_EVENT_CONSTRAINT(0x02cb, 0x1), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */
PEBS_EVENT_CONSTRAINT(0x04cb, 0x1), /* MEM_LOAD_RETIRED.L2_MISS */
PEBS_EVENT_CONSTRAINT(0x08cb, 0x1), /* MEM_LOAD_RETIRED.L2_LINE_MISS */
PEBS_EVENT_CONSTRAINT(0x10cb, 0x1), /* MEM_LOAD_RETIRED.DTLB_MISS */
INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */
EVENT_CONSTRAINT_END
};
static struct event_constraint intel_nehalem_pebs_events[] = {
PEBS_EVENT_CONSTRAINT(0x00c0, 0xf), /* INSTR_RETIRED.ANY */
PEBS_EVENT_CONSTRAINT(0xfec1, 0xf), /* X87_OPS_RETIRED.ANY */
PEBS_EVENT_CONSTRAINT(0x00c5, 0xf), /* BR_INST_RETIRED.MISPRED */
PEBS_EVENT_CONSTRAINT(0x1fc7, 0xf), /* SIMD_INST_RETURED.ANY */
PEBS_EVENT_CONSTRAINT(0x01cb, 0xf), /* MEM_LOAD_RETIRED.L1D_MISS */
PEBS_EVENT_CONSTRAINT(0x02cb, 0xf), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */
PEBS_EVENT_CONSTRAINT(0x04cb, 0xf), /* MEM_LOAD_RETIRED.L2_MISS */
PEBS_EVENT_CONSTRAINT(0x08cb, 0xf), /* MEM_LOAD_RETIRED.L2_LINE_MISS */
PEBS_EVENT_CONSTRAINT(0x10cb, 0xf), /* MEM_LOAD_RETIRED.DTLB_MISS */
static struct event_constraint intel_atom_pebs_event_constraints[] = {
PEBS_EVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
PEBS_EVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */
INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */
EVENT_CONSTRAINT_END
};
static struct event_constraint intel_nehalem_pebs_event_constraints[] = {
INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
PEBS_EVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INST_RETIRED.ANY */
INTEL_EVENT_CONSTRAINT(0xc2, 0xf), /* UOPS_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
PEBS_EVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */
INTEL_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */
PEBS_EVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
INTEL_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */
EVENT_CONSTRAINT_END
};
static struct event_constraint intel_westmere_pebs_event_constraints[] = {
INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
PEBS_EVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INSTR_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xc2, 0xf), /* UOPS_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */
PEBS_EVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
INTEL_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */
EVENT_CONSTRAINT_END
};
static struct event_constraint intel_snb_pebs_events[] = {
PEBS_EVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
PEBS_EVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
PEBS_EVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
PEBS_EVENT_CONSTRAINT(0x01c4, 0xf), /* BR_INST_RETIRED.CONDITIONAL */
PEBS_EVENT_CONSTRAINT(0x02c4, 0xf), /* BR_INST_RETIRED.NEAR_CALL */
PEBS_EVENT_CONSTRAINT(0x04c4, 0xf), /* BR_INST_RETIRED.ALL_BRANCHES */
PEBS_EVENT_CONSTRAINT(0x08c4, 0xf), /* BR_INST_RETIRED.NEAR_RETURN */
PEBS_EVENT_CONSTRAINT(0x10c4, 0xf), /* BR_INST_RETIRED.NOT_TAKEN */
PEBS_EVENT_CONSTRAINT(0x20c4, 0xf), /* BR_INST_RETIRED.NEAR_TAKEN */
PEBS_EVENT_CONSTRAINT(0x40c4, 0xf), /* BR_INST_RETIRED.FAR_BRANCH */
PEBS_EVENT_CONSTRAINT(0x01c5, 0xf), /* BR_MISP_RETIRED.CONDITIONAL */
PEBS_EVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */
PEBS_EVENT_CONSTRAINT(0x04c5, 0xf), /* BR_MISP_RETIRED.ALL_BRANCHES */
PEBS_EVENT_CONSTRAINT(0x10c5, 0xf), /* BR_MISP_RETIRED.NOT_TAKEN */
PEBS_EVENT_CONSTRAINT(0x20c5, 0xf), /* BR_MISP_RETIRED.TAKEN */
PEBS_EVENT_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
PEBS_EVENT_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORE */
PEBS_EVENT_CONSTRAINT(0x11d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_LOADS */
PEBS_EVENT_CONSTRAINT(0x12d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_STORES */
PEBS_EVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOP_RETIRED.LOCK_LOADS */
PEBS_EVENT_CONSTRAINT(0x22d0, 0xf), /* MEM_UOP_RETIRED.LOCK_STORES */
PEBS_EVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_LOADS */
PEBS_EVENT_CONSTRAINT(0x42d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_STORES */
PEBS_EVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOP_RETIRED.ANY_LOADS */
PEBS_EVENT_CONSTRAINT(0x82d0, 0xf), /* MEM_UOP_RETIRED.ANY_STORES */
PEBS_EVENT_CONSTRAINT(0x01d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L1_HIT */
PEBS_EVENT_CONSTRAINT(0x02d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L2_HIT */
PEBS_EVENT_CONSTRAINT(0x04d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.LLC_HIT */
PEBS_EVENT_CONSTRAINT(0x40d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.HIT_LFB */
PEBS_EVENT_CONSTRAINT(0x01d2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS */
PEBS_EVENT_CONSTRAINT(0x02d2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT */
PEBS_EVENT_CONSTRAINT(0x04d2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM */
PEBS_EVENT_CONSTRAINT(0x08d2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_NONE */
PEBS_EVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */
EVENT_CONSTRAINT_END
};
@@ -695,20 +753,17 @@ static void intel_ds_init(void)
printk(KERN_CONT "PEBS fmt0%c, ", pebs_type);
x86_pmu.pebs_record_size = sizeof(struct pebs_record_core);
x86_pmu.drain_pebs = intel_pmu_drain_pebs_core;
x86_pmu.pebs_constraints = intel_core_pebs_events;
break;
case 1:
printk(KERN_CONT "PEBS fmt1%c, ", pebs_type);
x86_pmu.pebs_record_size = sizeof(struct pebs_record_nhm);
x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
x86_pmu.pebs_constraints = intel_nehalem_pebs_events;
break;
default:
printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type);
x86_pmu.pebs = 0;
break;
}
}
}

8
arch/x86/kernel/cpu/perf_event_p4.c
مشاهده پرونده

@@ -764,9 +764,9 @@ static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
u64 v;
/* an official way for overflow indication */
rdmsrl(hwc->config_base + hwc->idx, v);
rdmsrl(hwc->config_base, v);
if (v & P4_CCCR_OVF) {
wrmsrl(hwc->config_base + hwc->idx, v & ~P4_CCCR_OVF);
wrmsrl(hwc->config_base, v & ~P4_CCCR_OVF);
return 1;
}
@@ -815,7 +815,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event)
* state we need to clear P4_CCCR_OVF, otherwise interrupt get
* asserted again and again
*/
(void)checking_wrmsrl(hwc->config_base + hwc->idx,
(void)checking_wrmsrl(hwc->config_base,
(u64)(p4_config_unpack_cccr(hwc->config)) &
~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED);
}
@@ -885,7 +885,7 @@ static void p4_pmu_enable_event(struct perf_event *event)
p4_pmu_enable_pebs(hwc->config);
(void)checking_wrmsrl(escr_addr, escr_conf);
(void)checking_wrmsrl(hwc->config_base + hwc->idx,
(void)checking_wrmsrl(hwc->config_base,
(cccr & ~P4_CCCR_RESERVED) | P4_CCCR_ENABLE);
}

4
arch/x86/kernel/cpu/perf_event_p6.c
مشاهده پرونده

@@ -68,7 +68,7 @@ p6_pmu_disable_event(struct perf_event *event)
if (cpuc->enabled)
val |= ARCH_PERFMON_EVENTSEL_ENABLE;
(void)checking_wrmsrl(hwc->config_base + hwc->idx, val);
(void)checking_wrmsrl(hwc->config_base, val);
}
static void p6_pmu_enable_event(struct perf_event *event)
@@ -81,7 +81,7 @@ static void p6_pmu_enable_event(struct perf_event *event)
if (cpuc->enabled)
val |= ARCH_PERFMON_EVENTSEL_ENABLE;
(void)checking_wrmsrl(hwc->config_base + hwc->idx, val);
(void)checking_wrmsrl(hwc->config_base, val);
}
static __initconst const struct x86_pmu p6_pmu = {

4
arch/x86/kernel/cpu/perfctr-watchdog.c
مشاهده پرونده

@@ -46,6 +46,8 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
/* returns the bit offset of the performance counter register */
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_AMD:
if (msr >= MSR_F15H_PERF_CTR)
return (msr - MSR_F15H_PERF_CTR) >> 1;
return msr - MSR_K7_PERFCTR0;
case X86_VENDOR_INTEL:
if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
@@ -70,6 +72,8 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
/* returns the bit offset of the event selection register */
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_AMD:
if (msr >= MSR_F15H_PERF_CTL)
return (msr - MSR_F15H_PERF_CTL) >> 1;
return msr - MSR_K7_EVNTSEL0;
case X86_VENDOR_INTEL:
if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))

441
arch/x86/kernel/devicetree.c Normal file
مشاهده پرونده

@@ -0,0 +1,441 @@
/*
* Architecture specific OF callbacks.
*/
#include <linux/bootmem.h>
#include <linux/io.h>
#include <linux/interrupt.h>
#include <linux/list.h>
#include <linux/of.h>
#include <linux/of_fdt.h>
#include <linux/of_address.h>
#include <linux/of_platform.h>
#include <linux/of_irq.h>
#include <linux/slab.h>
#include <linux/pci.h>
#include <linux/of_pci.h>
#include <asm/hpet.h>
#include <asm/irq_controller.h>
#include <asm/apic.h>
#include <asm/pci_x86.h>
__initdata u64 initial_dtb;
char __initdata cmd_line[COMMAND_LINE_SIZE];
static LIST_HEAD(irq_domains);
static DEFINE_RAW_SPINLOCK(big_irq_lock);
int __initdata of_ioapic;
#ifdef CONFIG_X86_IO_APIC
static void add_interrupt_host(struct irq_domain *ih)
{
unsigned long flags;
raw_spin_lock_irqsave(&big_irq_lock, flags);
list_add(&ih->l, &irq_domains);
raw_spin_unlock_irqrestore(&big_irq_lock, flags);
}
#endif
static struct irq_domain *get_ih_from_node(struct device_node *controller)
{
struct irq_domain *ih, *found = NULL;
unsigned long flags;
raw_spin_lock_irqsave(&big_irq_lock, flags);
list_for_each_entry(ih, &irq_domains, l) {
if (ih->controller == controller) {
found = ih;
break;
}
}
raw_spin_unlock_irqrestore(&big_irq_lock, flags);
return found;
}
unsigned int irq_create_of_mapping(struct device_node *controller,
const u32 *intspec, unsigned int intsize)
{
struct irq_domain *ih;
u32 virq, type;
int ret;
ih = get_ih_from_node(controller);
if (!ih)
return 0;
ret = ih->xlate(ih, intspec, intsize, &virq, &type);
if (ret)
return ret;
if (type == IRQ_TYPE_NONE)
return virq;
/* set the mask if it is different from current */
if (type == (irq_to_desc(virq)->status & IRQF_TRIGGER_MASK))
set_irq_type(virq, type);
return virq;
}
EXPORT_SYMBOL_GPL(irq_create_of_mapping);
unsigned long pci_address_to_pio(phys_addr_t address)
{
/*
* The ioport address can be directly used by inX / outX
*/
BUG_ON(address >= (1 << 16));
return (unsigned long)address;
}
EXPORT_SYMBOL_GPL(pci_address_to_pio);
void __init early_init_dt_scan_chosen_arch(unsigned long node)
{
BUG();
}
void __init early_init_dt_add_memory_arch(u64 base, u64 size)
{
BUG();
}
void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
{
return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS));
}
void __init add_dtb(u64 data)
{
initial_dtb = data + offsetof(struct setup_data, data);
}
/*
* CE4100 ids. Will be moved to machine_device_initcall() once we have it.
*/
static struct of_device_id __initdata ce4100_ids[] = {
{ .compatible = "intel,ce4100-cp", },
{ .compatible = "isa", },
{ .compatible = "pci", },
{},
};
static int __init add_bus_probe(void)
{
if (!of_have_populated_dt())
return 0;
return of_platform_bus_probe(NULL, ce4100_ids, NULL);
}
module_init(add_bus_probe);
#ifdef CONFIG_PCI
static int x86_of_pci_irq_enable(struct pci_dev *dev)
{
struct of_irq oirq;
u32 virq;
int ret;
u8 pin;
ret = pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
if (ret)
return ret;
if (!pin)
return 0;
ret = of_irq_map_pci(dev, &oirq);
if (ret)
return ret;
virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
oirq.size);
if (virq == 0)
return -EINVAL;
dev->irq = virq;
return 0;
}
static void x86_of_pci_irq_disable(struct pci_dev *dev)
{
}
void __cpuinit x86_of_pci_init(void)
{
struct device_node *np;
pcibios_enable_irq = x86_of_pci_irq_enable;
pcibios_disable_irq = x86_of_pci_irq_disable;
for_each_node_by_type(np, "pci") {
const void *prop;
struct pci_bus *bus;
unsigned int bus_min;
struct device_node *child;
prop = of_get_property(np, "bus-range", NULL);
if (!prop)
continue;
bus_min = be32_to_cpup(prop);
bus = pci_find_bus(0, bus_min);
if (!bus) {
printk(KERN_ERR "Can't find a node for bus %s.\n",
np->full_name);
continue;
}
if (bus->self)
bus->self->dev.of_node = np;
else
bus->dev.of_node = np;
for_each_child_of_node(np, child) {
struct pci_dev *dev;
u32 devfn;
prop = of_get_property(child, "reg", NULL);
if (!prop)
continue;
devfn = (be32_to_cpup(prop) >> 8) & 0xff;
dev = pci_get_slot(bus, devfn);
if (!dev)
continue;
dev->dev.of_node = child;
pci_dev_put(dev);
}
}
}
#endif
static void __init dtb_setup_hpet(void)
{
#ifdef CONFIG_HPET_TIMER
struct device_node *dn;
struct resource r;
int ret;
dn = of_find_compatible_node(NULL, NULL, "intel,ce4100-hpet");
if (!dn)
return;
ret = of_address_to_resource(dn, 0, &r);
if (ret) {
WARN_ON(1);
return;
}
hpet_address = r.start;
#endif
}
static void __init dtb_lapic_setup(void)
{
#ifdef CONFIG_X86_LOCAL_APIC
struct device_node *dn;
struct resource r;
int ret;
dn = of_find_compatible_node(NULL, NULL, "intel,ce4100-lapic");
if (!dn)
return;
ret = of_address_to_resource(dn, 0, &r);
if (WARN_ON(ret))
return;
/* Did the boot loader setup the local APIC ? */
if (!cpu_has_apic) {
if (apic_force_enable(r.start))
return;
}
smp_found_config = 1;
pic_mode = 1;
register_lapic_address(r.start);
generic_processor_info(boot_cpu_physical_apicid,
GET_APIC_VERSION(apic_read(APIC_LVR)));
#endif
}
#ifdef CONFIG_X86_IO_APIC
static unsigned int ioapic_id;
static void __init dtb_add_ioapic(struct device_node *dn)
{
struct resource r;
int ret;
ret = of_address_to_resource(dn, 0, &r);
if (ret) {
printk(KERN_ERR "Can't obtain address from node %s.\n",
dn->full_name);
return;
}
mp_register_ioapic(++ioapic_id, r.start, gsi_top);
}
static void __init dtb_ioapic_setup(void)
{
struct device_node *dn;
for_each_compatible_node(dn, NULL, "intel,ce4100-ioapic")
dtb_add_ioapic(dn);
if (nr_ioapics) {
of_ioapic = 1;
return;
}
printk(KERN_ERR "Error: No information about IO-APIC in OF.\n");
}
#else
static void __init dtb_ioapic_setup(void) {}
#endif
static void __init dtb_apic_setup(void)
{
dtb_lapic_setup();
dtb_ioapic_setup();
}
#ifdef CONFIG_OF_FLATTREE
static void __init x86_flattree_get_config(void)
{
u32 size, map_len;
void *new_dtb;
if (!initial_dtb)
return;
map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK),
(u64)sizeof(struct boot_param_header));
initial_boot_params = early_memremap(initial_dtb, map_len);
size = be32_to_cpu(initial_boot_params->totalsize);
if (map_len < size) {
early_iounmap(initial_boot_params, map_len);
initial_boot_params = early_memremap(initial_dtb, size);
map_len = size;
}
new_dtb = alloc_bootmem(size);
memcpy(new_dtb, initial_boot_params, size);
early_iounmap(initial_boot_params, map_len);
initial_boot_params = new_dtb;
/* root level address cells */
of_scan_flat_dt(early_init_dt_scan_root, NULL);
unflatten_device_tree();
}
#else
static inline void x86_flattree_get_config(void) { }
#endif
void __init x86_dtb_init(void)
{
x86_flattree_get_config();
if (!of_have_populated_dt())
return;
dtb_setup_hpet();
dtb_apic_setup();
}
#ifdef CONFIG_X86_IO_APIC
struct of_ioapic_type {
u32 out_type;
u32 trigger;
u32 polarity;
};
static struct of_ioapic_type of_ioapic_type[] =
{
{
.out_type = IRQ_TYPE_EDGE_RISING,
.trigger = IOAPIC_EDGE,
.polarity = 1,
},
{
.out_type = IRQ_TYPE_LEVEL_LOW,
.trigger = IOAPIC_LEVEL,
.polarity = 0,
},
{
.out_type = IRQ_TYPE_LEVEL_HIGH,
.trigger = IOAPIC_LEVEL,
.polarity = 1,
},
{
.out_type = IRQ_TYPE_EDGE_FALLING,
.trigger = IOAPIC_EDGE,
.polarity = 0,
},
};
static int ioapic_xlate(struct irq_domain *id, const u32 *intspec, u32 intsize,
u32 *out_hwirq, u32 *out_type)
{
struct io_apic_irq_attr attr;
struct of_ioapic_type *it;
u32 line, idx, type;
if (intsize < 2)
return -EINVAL;
line = *intspec;
idx = (u32) id->priv;
*out_hwirq = line + mp_gsi_routing[idx].gsi_base;
intspec++;
type = *intspec;
if (type >= ARRAY_SIZE(of_ioapic_type))
return -EINVAL;
it = of_ioapic_type + type;
*out_type = it->out_type;
set_io_apic_irq_attr(&attr, idx, line, it->trigger, it->polarity);
return io_apic_setup_irq_pin(*out_hwirq, cpu_to_node(0), &attr);
}
static void __init ioapic_add_ofnode(struct device_node *np)
{
struct resource r;
int i, ret;
ret = of_address_to_resource(np, 0, &r);
if (ret) {
printk(KERN_ERR "Failed to obtain address for %s\n",
np->full_name);
return;
}
for (i = 0; i < nr_ioapics; i++) {
if (r.start == mp_ioapics[i].apicaddr) {
struct irq_domain *id;
id = kzalloc(sizeof(*id), GFP_KERNEL);
BUG_ON(!id);
id->controller = np;
id->xlate = ioapic_xlate;
id->priv = (void *)i;
add_interrupt_host(id);
return;
}
}
printk(KERN_ERR "IOxAPIC at %s is not registered.\n", np->full_name);
}
void __init x86_add_irq_domains(void)
{
struct device_node *dp;
if (!of_have_populated_dt())
return;
for_each_node_with_property(dp, "interrupt-controller") {
if (of_device_is_compatible(dp, "intel,ce4100-ioapic"))
ioapic_add_ofnode(dp);
}
}
#else
void __init x86_add_irq_domains(void) { }
#endif

25
arch/x86/kernel/dumpstack.c
مشاهده پرونده

@@ -320,31 +320,6 @@ void die(const char *str, struct pt_regs *regs, long err)
oops_end(flags, regs, sig);
}
void notrace __kprobes
die_nmi(char *str, struct pt_regs *regs, int do_panic)
{
unsigned long flags;
if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP)
return;
/*
* We are in trouble anyway, lets at least try
* to get a message out.
*/
flags = oops_begin();
printk(KERN_EMERG "%s", str);
printk(" on CPU%d, ip %08lx, registers:\n",
smp_processor_id(), regs->ip);
show_registers(regs);
oops_end(flags, regs, 0);
if (do_panic || panic_on_oops)
panic("Non maskable interrupt");
nmi_exit();
local_irq_enable();
do_exit(SIGBUS);
}
static int __init oops_setup(char *s)
{
if (!s)

18
arch/x86/kernel/e820.c
مشاهده پرونده

@@ -667,21 +667,15 @@ __init void e820_setup_gap(void)
* boot_params.e820_map, others are passed via SETUP_E820_EXT node of
* linked list of struct setup_data, which is parsed here.
*/
void __init parse_e820_ext(struct setup_data *sdata, unsigned long pa_data)
void __init parse_e820_ext(struct setup_data *sdata)
{
u32 map_len;
int entries;
struct e820entry *extmap;
entries = sdata->len / sizeof(struct e820entry);
map_len = sdata->len + sizeof(struct setup_data);
if (map_len > PAGE_SIZE)
sdata = early_ioremap(pa_data, map_len);
extmap = (struct e820entry *)(sdata->data);
__append_e820_map(extmap, entries);
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
if (map_len > PAGE_SIZE)
early_iounmap(sdata, map_len);
printk(KERN_INFO "extended physical RAM map:\n");
e820_print_map("extended");
}
@@ -847,15 +841,21 @@ static int __init parse_memopt(char *p)
if (!p)
return -EINVAL;
#ifdef CONFIG_X86_32
if (!strcmp(p, "nopentium")) {
#ifdef CONFIG_X86_32
setup_clear_cpu_cap(X86_FEATURE_PSE);
return 0;
}
#else
printk(KERN_WARNING "mem=nopentium ignored! (only supported on x86_32)\n");
return -EINVAL;
#endif
}
userdef = 1;
mem_size = memparse(p, &p);
/* don't remove all of memory when handling "mem={invalid}" param */
if (mem_size == 0)
return -EINVAL;
e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
return 0;

11
arch/x86/kernel/entry_32.S
مشاهده پرونده

@@ -65,6 +65,8 @@
#define sysexit_audit syscall_exit_work
#endif
.section .entry.text, "ax"
/*
* We use macros for low-level operations which need to be overridden
* for paravirtualization. The following will never clobber any registers:
@@ -395,7 +397,7 @@ sysenter_past_esp:
* A tiny bit of offset fixup is necessary - 4*4 means the 4 words
* pushed above; +8 corresponds to copy_thread's esp0 setting.
*/
pushl_cfi ((TI_sysenter_return)-THREAD_SIZE_asm+8+4*4)(%esp)
pushl_cfi ((TI_sysenter_return)-THREAD_SIZE+8+4*4)(%esp)
CFI_REL_OFFSET eip, 0
pushl_cfi %eax
@@ -788,7 +790,7 @@ ENDPROC(ptregs_clone)
*/
.section .init.rodata,"a"
ENTRY(interrupt)
.text
.section .entry.text, "ax"
.p2align 5
.p2align CONFIG_X86_L1_CACHE_SHIFT
ENTRY(irq_entries_start)
@@ -807,7 +809,7 @@ vector=FIRST_EXTERNAL_VECTOR
.endif
.previous
.long 1b
.text
.section .entry.text, "ax"
vector=vector+1
.endif
.endr
@@ -1409,8 +1411,7 @@ END(general_protection)
#ifdef CONFIG_KVM_GUEST
ENTRY(async_page_fault)
RING0_EC_FRAME
pushl $do_async_page_fault
CFI_ADJUST_CFA_OFFSET 4
pushl_cfi $do_async_page_fault
jmp error_code
CFI_ENDPROC
END(apf_page_fault)

13
arch/x86/kernel/entry_64.S
مشاهده پرونده

@@ -61,6 +61,8 @@
#define __AUDIT_ARCH_LE 0x40000000
.code64
.section .entry.text, "ax"
#ifdef CONFIG_FUNCTION_TRACER
#ifdef CONFIG_DYNAMIC_FTRACE
ENTRY(mcount)
@@ -744,7 +746,7 @@ END(stub_rt_sigreturn)
*/
.section .init.rodata,"a"
ENTRY(interrupt)
.text
.section .entry.text
.p2align 5
.p2align CONFIG_X86_L1_CACHE_SHIFT
ENTRY(irq_entries_start)
@@ -763,7 +765,7 @@ vector=FIRST_EXTERNAL_VECTOR
.endif
.previous
.quad 1b
.text
.section .entry.text
vector=vector+1
.endif
.endr
@@ -975,9 +977,12 @@ apicinterrupt X86_PLATFORM_IPI_VECTOR \
x86_platform_ipi smp_x86_platform_ipi
#ifdef CONFIG_SMP
.irpc idx, "01234567"
.irp idx,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15, \
16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
.if NUM_INVALIDATE_TLB_VECTORS > \idx
apicinterrupt (INVALIDATE_TLB_VECTOR_START)+\idx \
invalidate_interrupt\idx smp_invalidate_interrupt
.endif
.endr
#endif
@@ -1248,7 +1253,7 @@ ENTRY(xen_do_hypervisor_callback) # do_hypervisor_callback(struct *pt_regs)
decl PER_CPU_VAR(irq_count)
jmp error_exit
CFI_ENDPROC
END(do_hypervisor_callback)
END(xen_do_hypervisor_callback)
/*
* Hypervisor uses this for application faults while it executes.

17
arch/x86/kernel/ftrace.c
مشاهده پرونده

@@ -437,18 +437,19 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
return;
}
trace.func = self_addr;
trace.depth = current->curr_ret_stack + 1;
/* Only trace if the calling function expects to */
if (!ftrace_graph_entry(&trace)) {
*parent = old;
return;
}
if (ftrace_push_return_trace(old, self_addr, &trace.depth,
frame_pointer) == -EBUSY) {
*parent = old;
return;
}
trace.func = self_addr;
/* Only trace if the calling function expects to */
if (!ftrace_graph_entry(&trace)) {
current->curr_ret_stack--;
*parent = old;
}
}
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */

10
arch/x86/kernel/head_32.S
مشاهده پرونده

@@ -73,7 +73,7 @@ MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT
*/
KERNEL_PAGES = LOWMEM_PAGES
INIT_MAP_SIZE = PAGE_TABLE_SIZE(KERNEL_PAGES) * PAGE_SIZE_asm
INIT_MAP_SIZE = PAGE_TABLE_SIZE(KERNEL_PAGES) * PAGE_SIZE
RESERVE_BRK(pagetables, INIT_MAP_SIZE)
/*
@@ -137,7 +137,7 @@ ENTRY(startup_32)
movsl
1:
#ifdef CONFIG_OLPC_OPENFIRMWARE
#ifdef CONFIG_OLPC
/* save OFW's pgdir table for later use when calling into OFW */
movl %cr3, %eax
movl %eax, pa(olpc_ofw_pgd)
@@ -623,7 +623,7 @@ ENTRY(initial_code)
* BSS section
*/
__PAGE_ALIGNED_BSS
.align PAGE_SIZE_asm
.align PAGE_SIZE
#ifdef CONFIG_X86_PAE
initial_pg_pmd:
.fill 1024*KPMDS,4,0
@@ -644,7 +644,7 @@ ENTRY(swapper_pg_dir)
#ifdef CONFIG_X86_PAE
__PAGE_ALIGNED_DATA
/* Page-aligned for the benefit of paravirt? */
.align PAGE_SIZE_asm
.align PAGE_SIZE
ENTRY(initial_page_table)
.long pa(initial_pg_pmd+PGD_IDENT_ATTR),0 /* low identity map */
# if KPMDS == 3
@@ -662,7 +662,7 @@ ENTRY(initial_page_table)
# else
# error "Kernel PMDs should be 1, 2 or 3"
# endif
.align PAGE_SIZE_asm /* needs to be page-sized too */
.align PAGE_SIZE /* needs to be page-sized too */
#endif
.data

2
arch/x86/kernel/hpet.c
مشاهده پرونده

@@ -503,7 +503,7 @@ static int hpet_assign_irq(struct hpet_dev *dev)
if (!irq)
return -EINVAL;
set_irq_data(irq, dev);
irq_set_handler_data(irq, dev);
if (hpet_setup_msi_irq(irq))
return -EINVAL;

2
arch/x86/kernel/i8259.c
مشاهده پرونده

@@ -112,7 +112,7 @@ static void make_8259A_irq(unsigned int irq)
{
disable_irq_nosync(irq);
io_apic_irqs &= ~(1<<irq);
set_irq_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq,
irq_set_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq,
i8259A_chip.name);
enable_irq(irq);
}

20
arch/x86/kernel/ioport.c
مشاهده پرونده

@@ -14,22 +14,9 @@
#include <linux/slab.h>
#include <linux/thread_info.h>
#include <linux/syscalls.h>
#include <linux/bitmap.h>
#include <asm/syscalls.h>
/* Set EXTENT bits starting at BASE in BITMAP to value TURN_ON. */
static void set_bitmap(unsigned long *bitmap, unsigned int base,
unsigned int extent, int new_value)
{
unsigned int i;
for (i = base; i < base + extent; i++) {
if (new_value)
__set_bit(i, bitmap);
else
__clear_bit(i, bitmap);
}
}
/*
* this changes the io permissions bitmap in the current task.
*/
@@ -69,7 +56,10 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
*/
tss = &per_cpu(init_tss, get_cpu());
set_bitmap(t->io_bitmap_ptr, from, num, !turn_on);
if (turn_on)
bitmap_clear(t->io_bitmap_ptr, from, num);
else
bitmap_set(t->io_bitmap_ptr, from, num);
/*
* Search for a (possibly new) maximum. This is simple and stupid,

91
arch/x86/kernel/irq.c
مشاهده پرونده

@@ -44,9 +44,9 @@ void ack_bad_irq(unsigned int irq)
#define irq_stats(x) (&per_cpu(irq_stat, x))
/*
* /proc/interrupts printing:
* /proc/interrupts printing for arch specific interrupts
*/
static int show_other_interrupts(struct seq_file *p, int prec)
int arch_show_interrupts(struct seq_file *p, int prec)
{
int j;
@@ -122,59 +122,6 @@ static int show_other_interrupts(struct seq_file *p, int prec)
return 0;
}
int show_interrupts(struct seq_file *p, void *v)
{
unsigned long flags, any_count = 0;
int i = *(loff_t *) v, j, prec;
struct irqaction *action;
struct irq_desc *desc;
if (i > nr_irqs)
return 0;
for (prec = 3, j = 1000; prec < 10 && j <= nr_irqs; ++prec)
j *= 10;
if (i == nr_irqs)
return show_other_interrupts(p, prec);
/* print header */
if (i == 0) {
seq_printf(p, "%*s", prec + 8, "");
for_each_online_cpu(j)
seq_printf(p, "CPU%-8d", j);
seq_putc(p, '\n');
}
desc = irq_to_desc(i);
if (!desc)
return 0;
raw_spin_lock_irqsave(&desc->lock, flags);
for_each_online_cpu(j)
any_count |= kstat_irqs_cpu(i, j);
action = desc->action;
if (!action && !any_count)
goto out;
seq_printf(p, "%*d: ", prec, i);
for_each_online_cpu(j)
seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
seq_printf(p, " %8s", desc->irq_data.chip->name);
seq_printf(p, "-%-8s", desc->name);
if (action) {
seq_printf(p, " %s", action->name);
while ((action = action->next) != NULL)
seq_printf(p, ", %s", action->name);
}
seq_putc(p, '\n');
out:
raw_spin_unlock_irqrestore(&desc->lock, flags);
return 0;
}
/*
* /proc/stat helpers
*/
@@ -276,15 +223,6 @@ void smp_x86_platform_ipi(struct pt_regs *regs)
EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq);
#ifdef CONFIG_OF
unsigned int irq_create_of_mapping(struct device_node *controller,
const u32 *intspec, unsigned int intsize)
{
return intspec[0];
}
EXPORT_SYMBOL_GPL(irq_create_of_mapping);
#endif
#ifdef CONFIG_HOTPLUG_CPU
/* A cpu has been removed from cpu_online_mask. Reset irq affinities. */
void fixup_irqs(void)
@@ -293,6 +231,7 @@ void fixup_irqs(void)
static int warned;
struct irq_desc *desc;
struct irq_data *data;
struct irq_chip *chip;
for_each_irq_desc(irq, desc) {
int break_affinity = 0;
@@ -307,10 +246,10 @@ void fixup_irqs(void)
/* interrupt's are disabled at this point */
raw_spin_lock(&desc->lock);
data = &desc->irq_data;
data = irq_desc_get_irq_data(desc);
affinity = data->affinity;
if (!irq_has_action(irq) ||
cpumask_equal(affinity, cpu_online_mask)) {
cpumask_subset(affinity, cpu_online_mask)) {
raw_spin_unlock(&desc->lock);
continue;
}
@@ -327,16 +266,17 @@ void fixup_irqs(void)
affinity = cpu_all_mask;
}
if (!(desc->status & IRQ_MOVE_PCNTXT) && data->chip->irq_mask)
data->chip->irq_mask(data);
chip = irq_data_get_irq_chip(data);
if (!irqd_can_move_in_process_context(data) && chip->irq_mask)
chip->irq_mask(data);
if (data->chip->irq_set_affinity)
data->chip->irq_set_affinity(data, affinity, true);
if (chip->irq_set_affinity)
chip->irq_set_affinity(data, affinity, true);
else if (!(warned++))
set_affinity = 0;
if (!(desc->status & IRQ_MOVE_PCNTXT) && data->chip->irq_unmask)
data->chip->irq_unmask(data);
if (!irqd_can_move_in_process_context(data) && chip->irq_unmask)
chip->irq_unmask(data);
raw_spin_unlock(&desc->lock);
@@ -368,10 +308,11 @@ void fixup_irqs(void)
irq = __this_cpu_read(vector_irq[vector]);
desc = irq_to_desc(irq);
data = &desc->irq_data;
data = irq_desc_get_irq_data(desc);
chip = irq_data_get_irq_chip(data);
raw_spin_lock(&desc->lock);
if (data->chip->irq_retrigger)
data->chip->irq_retrigger(data);
if (chip->irq_retrigger)
chip->irq_retrigger(data);
raw_spin_unlock(&desc->lock);
}
}

92
arch/x86/kernel/irqinit.c
مشاهده پرونده

@@ -25,6 +25,7 @@
#include <asm/setup.h>
#include <asm/i8259.h>
#include <asm/traps.h>
#include <asm/prom.h>
/*
* ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
@@ -71,6 +72,7 @@ static irqreturn_t math_error_irq(int cpl, void *dev_id)
static struct irqaction fpu_irq = {
.handler = math_error_irq,
.name = "fpu",
.flags = IRQF_NO_THREAD,
};
#endif
@@ -80,6 +82,7 @@ static struct irqaction fpu_irq = {
static struct irqaction irq2 = {
.handler = no_action,
.name = "cascade",
.flags = IRQF_NO_THREAD,
};
DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
@@ -110,13 +113,19 @@ void __init init_ISA_irqs(void)
legacy_pic->init(0);
for (i = 0; i < legacy_pic->nr_legacy_irqs; i++)
set_irq_chip_and_handler_name(i, chip, handle_level_irq, name);
irq_set_chip_and_handler_name(i, chip, handle_level_irq, name);
}
void __init init_IRQ(void)
{
int i;
/*
* We probably need a better place for this, but it works for
* now ...
*/
x86_add_irq_domains();
/*
* On cpu 0, Assign IRQ0_VECTOR..IRQ15_VECTOR's to IRQ 0..15.
* If these IRQ's are handled by legacy interrupt-controllers like PIC,
@@ -164,14 +173,77 @@ static void __init smp_intr_init(void)
alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
/* IPIs for invalidation */
alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
#define ALLOC_INVTLB_VEC(NR) \
alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+NR, \
invalidate_interrupt##NR)
switch (NUM_INVALIDATE_TLB_VECTORS) {
default:
ALLOC_INVTLB_VEC(31);
case 31:
ALLOC_INVTLB_VEC(30);
case 30:
ALLOC_INVTLB_VEC(29);
case 29:
ALLOC_INVTLB_VEC(28);
case 28:
ALLOC_INVTLB_VEC(27);
case 27:
ALLOC_INVTLB_VEC(26);
case 26:
ALLOC_INVTLB_VEC(25);
case 25:
ALLOC_INVTLB_VEC(24);
case 24:
ALLOC_INVTLB_VEC(23);
case 23:
ALLOC_INVTLB_VEC(22);
case 22:
ALLOC_INVTLB_VEC(21);
case 21:
ALLOC_INVTLB_VEC(20);
case 20:
ALLOC_INVTLB_VEC(19);
case 19:
ALLOC_INVTLB_VEC(18);
case 18:
ALLOC_INVTLB_VEC(17);
case 17:
ALLOC_INVTLB_VEC(16);
case 16:
ALLOC_INVTLB_VEC(15);
case 15:
ALLOC_INVTLB_VEC(14);
case 14:
ALLOC_INVTLB_VEC(13);
case 13:
ALLOC_INVTLB_VEC(12);
case 12:
ALLOC_INVTLB_VEC(11);
case 11:
ALLOC_INVTLB_VEC(10);
case 10:
ALLOC_INVTLB_VEC(9);
case 9:
ALLOC_INVTLB_VEC(8);
case 8:
ALLOC_INVTLB_VEC(7);
case 7:
ALLOC_INVTLB_VEC(6);
case 6:
ALLOC_INVTLB_VEC(5);
case 5:
ALLOC_INVTLB_VEC(4);
case 4:
ALLOC_INVTLB_VEC(3);
case 3:
ALLOC_INVTLB_VEC(2);
case 2:
ALLOC_INVTLB_VEC(1);
case 1:
ALLOC_INVTLB_VEC(0);
break;
}
/* IPI for generic function call */
alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
@@ -243,7 +315,7 @@ void __init native_init_IRQ(void)
set_intr_gate(i, interrupt[i-FIRST_EXTERNAL_VECTOR]);
}
if (!acpi_ioapic)
if (!acpi_ioapic && !of_ioapic)
setup_irq(2, &irq2);
#ifdef CONFIG_X86_32

9
arch/x86/kernel/kgdb.c
مشاهده پرونده

@@ -533,15 +533,6 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd)
}
return NOTIFY_DONE;
case DIE_NMIWATCHDOG:
if (atomic_read(&kgdb_active) != -1) {
/* KGDB CPU roundup: */
kgdb_nmicallback(raw_smp_processor_id(), regs);
return NOTIFY_STOP;
}
/* Enter debugger: */
break;
case DIE_DEBUG:
if (atomic_read(&kgdb_cpu_doing_single_step) != -1) {
if (user_mode(regs))

8
arch/x86/kernel/kprobes.c
مشاهده پرونده

@@ -1276,6 +1276,14 @@ static int __kprobes can_optimize(unsigned long paddr)
if (!kallsyms_lookup_size_offset(paddr, &size, &offset))
return 0;
/*
* Do not optimize in the entry code due to the unstable
* stack handling.
*/
if ((paddr >= (unsigned long )__entry_text_start) &&
(paddr < (unsigned long )__entry_text_end))
return 0;
/* Check there is enough space for a relative jump. */
if (size - offset < RELATIVEJUMP_SIZE)
return 0;

186
arch/x86/kernel/microcode_amd.c
مشاهده پرونده

@@ -66,7 +66,6 @@ struct microcode_amd {
unsigned int mpb[0];
};
#define UCODE_MAX_SIZE 2048
#define UCODE_CONTAINER_SECTION_HDR 8
#define UCODE_CONTAINER_HEADER_SIZE 12
@@ -77,20 +76,20 @@ static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
struct cpuinfo_x86 *c = &cpu_data(cpu);
u32 dummy;
memset(csig, 0, sizeof(*csig));
if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) {
pr_warning("microcode: CPU%d: AMD CPU family 0x%x not "
"supported\n", cpu, c->x86);
pr_warning("CPU%d: family %d not supported\n", cpu, c->x86);
return -1;
}
rdmsr(MSR_AMD64_PATCH_LEVEL, csig->rev, dummy);
pr_info("CPU%d: patch_level=0x%x\n", cpu, csig->rev);
pr_info("CPU%d: patch_level=0x%08x\n", cpu, csig->rev);
return 0;
}
static int get_matching_microcode(int cpu, void *mc, int rev)
static int get_matching_microcode(int cpu, struct microcode_header_amd *mc_hdr,
int rev)
{
struct microcode_header_amd *mc_header = mc;
unsigned int current_cpu_id;
u16 equiv_cpu_id = 0;
unsigned int i = 0;
@@ -109,17 +108,17 @@ static int get_matching_microcode(int cpu, void *mc, int rev)
if (!equiv_cpu_id)
return 0;
if (mc_header->processor_rev_id != equiv_cpu_id)
if (mc_hdr->processor_rev_id != equiv_cpu_id)
return 0;
/* ucode might be chipset specific -- currently we don't support this */
if (mc_header->nb_dev_id || mc_header->sb_dev_id) {
pr_err("CPU%d: loading of chipset specific code not yet supported\n",
if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) {
pr_err("CPU%d: chipset specific code not yet supported\n",
cpu);
return 0;
}
if (mc_header->patch_id <= rev)
if (mc_hdr->patch_id <= rev)
return 0;
return 1;
@@ -144,71 +143,93 @@ static int apply_microcode_amd(int cpu)
/* check current patch id and patch's id for match */
if (rev != mc_amd->hdr.patch_id) {
pr_err("CPU%d: update failed (for patch_level=0x%x)\n",
pr_err("CPU%d: update failed for patch_level=0x%08x\n",
cpu, mc_amd->hdr.patch_id);
return -1;
}
pr_info("CPU%d: updated (new patch_level=0x%x)\n", cpu, rev);
pr_info("CPU%d: new patch_level=0x%08x\n", cpu, rev);
uci->cpu_sig.rev = rev;
return 0;
}
static void *
get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size)
static unsigned int verify_ucode_size(int cpu, const u8 *buf, unsigned int size)
{
unsigned int total_size;
u8 section_hdr[UCODE_CONTAINER_SECTION_HDR];
void *mc;
struct cpuinfo_x86 *c = &cpu_data(cpu);
unsigned int max_size, actual_size;
get_ucode_data(section_hdr, buf, UCODE_CONTAINER_SECTION_HDR);
#define F1XH_MPB_MAX_SIZE 2048
#define F14H_MPB_MAX_SIZE 1824
#define F15H_MPB_MAX_SIZE 4096
if (section_hdr[0] != UCODE_UCODE_TYPE) {
pr_err("error: invalid type field in container file section header\n");
return NULL;
switch (c->x86) {
case 0x14:
max_size = F14H_MPB_MAX_SIZE;
break;
case 0x15:
max_size = F15H_MPB_MAX_SIZE;
break;
default:
max_size = F1XH_MPB_MAX_SIZE;
break;
}
total_size = (unsigned long) (section_hdr[4] + (section_hdr[5] << 8));
actual_size = buf[4] + (buf[5] << 8);
if (total_size > size || total_size > UCODE_MAX_SIZE) {
pr_err("error: size mismatch\n");
return NULL;
if (actual_size > size || actual_size > max_size) {
pr_err("section size mismatch\n");
return 0;
}
mc = vzalloc(UCODE_MAX_SIZE);
return actual_size;
}
static struct microcode_header_amd *
get_next_ucode(int cpu, const u8 *buf, unsigned int size, unsigned int *mc_size)
{
struct microcode_header_amd *mc = NULL;
unsigned int actual_size = 0;
if (buf[0] != UCODE_UCODE_TYPE) {
pr_err("invalid type field in container file section header\n");
goto out;
}
actual_size = verify_ucode_size(cpu, buf, size);
if (!actual_size)
goto out;
mc = vzalloc(actual_size);
if (!mc)
return NULL;
goto out;
get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR, total_size);
*mc_size = total_size + UCODE_CONTAINER_SECTION_HDR;
get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR, actual_size);
*mc_size = actual_size + UCODE_CONTAINER_SECTION_HDR;
out:
return mc;
}
static int install_equiv_cpu_table(const u8 *buf)
{
u8 *container_hdr[UCODE_CONTAINER_HEADER_SIZE];
unsigned int *buf_pos = (unsigned int *)container_hdr;
unsigned long size;
unsigned int *ibuf = (unsigned int *)buf;
unsigned int type = ibuf[1];
unsigned int size = ibuf[2];
get_ucode_data(&container_hdr, buf, UCODE_CONTAINER_HEADER_SIZE);
size = buf_pos[2];
if (buf_pos[1] != UCODE_EQUIV_CPU_TABLE_TYPE || !size) {
pr_err("error: invalid type field in container file section header\n");
return 0;
if (type != UCODE_EQUIV_CPU_TABLE_TYPE || !size) {
pr_err("empty section/"
"invalid type field in container file section header\n");
return -EINVAL;
}
equiv_cpu_table = vmalloc(size);
if (!equiv_cpu_table) {
pr_err("failed to allocate equivalent CPU table\n");
return 0;
return -ENOMEM;
}
buf += UCODE_CONTAINER_HEADER_SIZE;
get_ucode_data(equiv_cpu_table, buf, size);
get_ucode_data(equiv_cpu_table, buf + UCODE_CONTAINER_HEADER_SIZE, size);
return size + UCODE_CONTAINER_HEADER_SIZE; /* add header length */
}
@@ -223,16 +244,16 @@ static enum ucode_state
generic_load_microcode(int cpu, const u8 *data, size_t size)
{
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
struct microcode_header_amd *mc_hdr = NULL;
unsigned int mc_size, leftover;
int offset;
const u8 *ucode_ptr = data;
void *new_mc = NULL;
void *mc;
int new_rev = uci->cpu_sig.rev;
unsigned int leftover;
unsigned long offset;
unsigned int new_rev = uci->cpu_sig.rev;
enum ucode_state state = UCODE_OK;
offset = install_equiv_cpu_table(ucode_ptr);
if (!offset) {
if (offset < 0) {
pr_err("failed to create equivalent cpu table\n");
return UCODE_ERROR;
}
@@ -241,64 +262,65 @@ generic_load_microcode(int cpu, const u8 *data, size_t size)
leftover = size - offset;
while (leftover) {
unsigned int uninitialized_var(mc_size);
struct microcode_header_amd *mc_header;
mc = get_next_ucode(ucode_ptr, leftover, &mc_size);
if (!mc)
mc_hdr = get_next_ucode(cpu, ucode_ptr, leftover, &mc_size);
if (!mc_hdr)
break;
mc_header = (struct microcode_header_amd *)mc;
if (get_matching_microcode(cpu, mc, new_rev)) {
if (get_matching_microcode(cpu, mc_hdr, new_rev)) {
vfree(new_mc);
new_rev = mc_header->patch_id;
new_mc = mc;
new_rev = mc_hdr->patch_id;
new_mc = mc_hdr;
} else
vfree(mc);
vfree(mc_hdr);
ucode_ptr += mc_size;
leftover -= mc_size;
}
if (new_mc) {
if (!leftover) {
vfree(uci->mc);
uci->mc = new_mc;
pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
cpu, new_rev, uci->cpu_sig.rev);
} else {
vfree(new_mc);
state = UCODE_ERROR;
}
} else
if (!new_mc) {
state = UCODE_NFOUND;
goto free_table;
}
if (!leftover) {
vfree(uci->mc);
uci->mc = new_mc;
pr_debug("CPU%d update ucode (0x%08x -> 0x%08x)\n",
cpu, uci->cpu_sig.rev, new_rev);
} else {
vfree(new_mc);
state = UCODE_ERROR;
}
free_table:
free_equiv_cpu_table();
return state;
}
static enum ucode_state request_microcode_fw(int cpu, struct device *device)
static enum ucode_state request_microcode_amd(int cpu, struct device *device)
{
const char *fw_name = "amd-ucode/microcode_amd.bin";
const struct firmware *firmware;
enum ucode_state ret;
const struct firmware *fw;
enum ucode_state ret = UCODE_NFOUND;
if (request_firmware(&firmware, fw_name, device)) {
printk(KERN_ERR "microcode: failed to load file %s\n", fw_name);
return UCODE_NFOUND;
if (request_firmware(&fw, fw_name, device)) {
pr_err("failed to load file %s\n", fw_name);
goto out;
}
if (*(u32 *)firmware->data != UCODE_MAGIC) {
pr_err("invalid UCODE_MAGIC (0x%08x)\n",
*(u32 *)firmware->data);
return UCODE_ERROR;
ret = UCODE_ERROR;
if (*(u32 *)fw->data != UCODE_MAGIC) {
pr_err("invalid magic value (0x%08x)\n", *(u32 *)fw->data);
goto fw_release;
}
ret = generic_load_microcode(cpu, firmware->data, firmware->size);
ret = generic_load_microcode(cpu, fw->data, fw->size);
release_firmware(firmware);
fw_release:
release_firmware(fw);
out:
return ret;
}
@@ -319,7 +341,7 @@ static void microcode_fini_cpu_amd(int cpu)
static struct microcode_ops microcode_amd_ops = {
.request_microcode_user = request_microcode_user,
.request_microcode_fw = request_microcode_fw,
.request_microcode_fw = request_microcode_amd,
.collect_cpu_info = collect_cpu_info_amd,
.apply_microcode = apply_microcode_amd,
.microcode_fini_cpu = microcode_fini_cpu_amd,

6
arch/x86/kernel/microcode_core.c
مشاهده پرونده

@@ -417,8 +417,10 @@ static int mc_sysdev_add(struct sys_device *sys_dev)
if (err)
return err;
if (microcode_init_cpu(cpu) == UCODE_ERROR)
err = -EINVAL;
if (microcode_init_cpu(cpu) == UCODE_ERROR) {
sysfs_remove_group(&sys_dev->kobj, &mc_attr_group);
return -EINVAL;
}
return err;
}

9
arch/x86/kernel/process.c
مشاهده پرونده

@@ -110,12 +110,9 @@ void show_regs_common(void)
init_utsname()->release,
(int)strcspn(init_utsname()->version, " "),
init_utsname()->version);
printk(KERN_CONT " ");
printk(KERN_CONT "%s %s", vendor, product);
if (board) {
printk(KERN_CONT "/");
printk(KERN_CONT "%s", board);
}
printk(KERN_CONT " %s %s", vendor, product);
if (board)
printk(KERN_CONT "/%s", board);
printk(KERN_CONT "\n");
}

3
arch/x86/kernel/rtc.c
مشاهده پرونده

@@ -6,6 +6,7 @@
#include <linux/acpi.h>
#include <linux/bcd.h>
#include <linux/pnp.h>
#include <linux/of.h>
#include <asm/vsyscall.h>
#include <asm/x86_init.h>
@@ -236,6 +237,8 @@ static __init int add_rtc_cmos(void)
}
}
#endif
if (of_have_populated_dt())
return 0;
platform_device_register(&rtc_device);
dev_info(&rtc_device.dev,

76
arch/x86/kernel/setup.c
مشاهده پرونده

@@ -113,6 +113,7 @@
#endif
#include <asm/mce.h>
#include <asm/alternative.h>
#include <asm/prom.h>
/*
* end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
@@ -293,10 +294,32 @@ static void __init init_gbpages(void)
else
direct_gbpages = 0;
}
static void __init cleanup_highmap_brk_end(void)
{
pud_t *pud;
pmd_t *pmd;
mmu_cr4_features = read_cr4();
/*
* _brk_end cannot change anymore, but it and _end may be
* located on different 2M pages. cleanup_highmap(), however,
* can only consider _end when it runs, so destroy any
* mappings beyond _brk_end here.
*/
pud = pud_offset(pgd_offset_k(_brk_end), _brk_end);
pmd = pmd_offset(pud, _brk_end - 1);
while (++pmd <= pmd_offset(pud, (unsigned long)_end - 1))
pmd_clear(pmd);
}
#else
static inline void init_gbpages(void)
{
}
static inline void cleanup_highmap_brk_end(void)
{
}
#endif
static void __init reserve_brk(void)
@@ -307,6 +330,8 @@ static void __init reserve_brk(void)
/* Mark brk area as locked down and no longer taking any
new allocations */
_brk_start = 0;
cleanup_highmap_brk_end();
}
#ifdef CONFIG_BLK_DEV_INITRD
@@ -429,16 +454,30 @@ static void __init parse_setup_data(void)
return;
pa_data = boot_params.hdr.setup_data;
while (pa_data) {
data = early_memremap(pa_data, PAGE_SIZE);
u32 data_len, map_len;
map_len = max(PAGE_SIZE - (pa_data & ~PAGE_MASK),
(u64)sizeof(struct setup_data));
data = early_memremap(pa_data, map_len);
data_len = data->len + sizeof(struct setup_data);
if (data_len > map_len) {
early_iounmap(data, map_len);
data = early_memremap(pa_data, data_len);
map_len = data_len;
}
switch (data->type) {
case SETUP_E820_EXT:
parse_e820_ext(data, pa_data);
parse_e820_ext(data);
break;
case SETUP_DTB:
add_dtb(pa_data);
break;
default:
break;
}
pa_data = data->next;
early_iounmap(data, PAGE_SIZE);
early_iounmap(data, map_len);
}
}
@@ -680,15 +719,6 @@ static int __init parse_reservelow(char *p)
early_param("reservelow", parse_reservelow);
static u64 __init get_max_mapped(void)
{
u64 end = max_pfn_mapped;
end <<= PAGE_SHIFT;
return end;
}
/*
* Determine if we were loaded by an EFI loader. If so, then we have also been
* passed the efi memmap, systab, etc., so we should use these data structures
@@ -704,8 +734,6 @@ static u64 __init get_max_mapped(void)
void __init setup_arch(char **cmdline_p)
{
int acpi = 0;
int amd = 0;
unsigned long flags;
#ifdef CONFIG_X86_32
@@ -984,19 +1012,7 @@ void __init setup_arch(char **cmdline_p)
early_acpi_boot_init();
#ifdef CONFIG_ACPI_NUMA
/*
* Parse SRAT to discover nodes.
*/
acpi = acpi_numa_init();
#endif
#ifdef CONFIG_AMD_NUMA
if (!acpi)
amd = !amd_numa_init(0, max_pfn);
#endif
initmem_init(0, max_pfn, acpi, amd);
initmem_init();
memblock_find_dma_reserve();
dma32_reserve_bootmem();
@@ -1029,8 +1045,8 @@ void __init setup_arch(char **cmdline_p)
* Read APIC and some other early information from ACPI tables.
*/
acpi_boot_init();
sfi_init();
x86_dtb_init();
/*
* get boot-time SMP configuration:
@@ -1040,9 +1056,7 @@ void __init setup_arch(char **cmdline_p)
prefill_possible_map();
#ifdef CONFIG_X86_64
init_cpu_to_node();
#endif
init_apic_mappings();
ioapic_and_gsi_init();
@@ -1066,6 +1080,8 @@ void __init setup_arch(char **cmdline_p)
#endif
x86_init.oem.banner();
x86_init.timers.wallclock_init();
mcheck_init();
local_irq_save(flags);

11
arch/x86/kernel/setup_percpu.c
مشاهده پرونده

@@ -225,10 +225,15 @@ void __init setup_per_cpu_areas(void)
per_cpu(x86_bios_cpu_apicid, cpu) =
early_per_cpu_map(x86_bios_cpu_apicid, cpu);
#endif
#ifdef CONFIG_X86_32
per_cpu(x86_cpu_to_logical_apicid, cpu) =
early_per_cpu_map(x86_cpu_to_logical_apicid, cpu);
#endif
#ifdef CONFIG_X86_64
per_cpu(irq_stack_ptr, cpu) =
per_cpu(irq_stack_union.irq_stack, cpu) +
IRQ_STACK_SIZE - 64;
#endif
#ifdef CONFIG_NUMA
per_cpu(x86_cpu_to_node_map, cpu) =
early_per_cpu_map(x86_cpu_to_node_map, cpu);
@@ -241,7 +246,6 @@ void __init setup_per_cpu_areas(void)
* So set them all (boot cpu and all APs).
*/
set_cpu_numa_node(cpu, early_cpu_to_node(cpu));
#endif
#endif
/*
* Up to this point, the boot CPU has been using .init.data
@@ -256,7 +260,10 @@ void __init setup_per_cpu_areas(void)
early_per_cpu_ptr(x86_cpu_to_apicid) = NULL;
early_per_cpu_ptr(x86_bios_cpu_apicid) = NULL;
#endif
#if defined(CONFIG_X86_64) && defined(CONFIG_NUMA)
#ifdef CONFIG_X86_32
early_per_cpu_ptr(x86_cpu_to_logical_apicid) = NULL;
#endif
#ifdef CONFIG_NUMA
early_per_cpu_ptr(x86_cpu_to_node_map) = NULL;
#endif

123
arch/x86/kernel/smpboot.c
مشاهده پرونده

@@ -64,6 +64,7 @@
#include <asm/mtrr.h>
#include <asm/mwait.h>
#include <asm/apic.h>
#include <asm/io_apic.h>
#include <asm/setup.h>
#include <asm/uv/uv.h>
#include <linux/mc146818rtc.h>
@@ -71,10 +72,6 @@
#include <asm/smpboot_hooks.h>
#include <asm/i8259.h>
#ifdef CONFIG_X86_32
u8 apicid_2_node[MAX_APICID];
#endif
/* State of each CPU */
DEFINE_PER_CPU(int, cpu_state) = { 0 };
@@ -130,68 +127,14 @@ EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
DEFINE_PER_CPU(cpumask_var_t, cpu_core_map);
EXPORT_PER_CPU_SYMBOL(cpu_core_map);
DEFINE_PER_CPU(cpumask_var_t, cpu_llc_shared_map);
/* Per CPU bogomips and other parameters */
DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
EXPORT_PER_CPU_SYMBOL(cpu_info);
atomic_t init_deasserted;
#if defined(CONFIG_NUMA) && defined(CONFIG_X86_32)
/* which node each logical CPU is on */
int cpu_to_node_map[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = 0 };
EXPORT_SYMBOL(cpu_to_node_map);
/* set up a mapping between cpu and node. */
static void map_cpu_to_node(int cpu, int node)
{
printk(KERN_INFO "Mapping cpu %d to node %d\n", cpu, node);
cpumask_set_cpu(cpu, node_to_cpumask_map[node]);
cpu_to_node_map[cpu] = node;
}
/* undo a mapping between cpu and node. */
static void unmap_cpu_to_node(int cpu)
{
int node;
printk(KERN_INFO "Unmapping cpu %d from all nodes\n", cpu);
for (node = 0; node < MAX_NUMNODES; node++)
cpumask_clear_cpu(cpu, node_to_cpumask_map[node]);
cpu_to_node_map[cpu] = 0;
}
#else /* !(CONFIG_NUMA && CONFIG_X86_32) */
#define map_cpu_to_node(cpu, node) ({})
#define unmap_cpu_to_node(cpu) ({})
#endif
#ifdef CONFIG_X86_32
static int boot_cpu_logical_apicid;
u8 cpu_2_logical_apicid[NR_CPUS] __read_mostly =
{ [0 ... NR_CPUS-1] = BAD_APICID };
static void map_cpu_to_logical_apicid(void)
{
int cpu = smp_processor_id();
int apicid = logical_smp_processor_id();
int node = apic->apicid_to_node(apicid);
if (!node_online(node))
node = first_online_node;
cpu_2_logical_apicid[cpu] = apicid;
map_cpu_to_node(cpu, node);
}
void numa_remove_cpu(int cpu)
{
cpu_2_logical_apicid[cpu] = BAD_APICID;
unmap_cpu_to_node(cpu);
}
#else
#define map_cpu_to_logical_apicid() do {} while (0)
#endif
/*
* Report back to the Boot Processor.
* Running on AP.
@@ -259,7 +202,6 @@ static void __cpuinit smp_callin(void)
apic->smp_callin_clear_local_apic();
setup_local_APIC();
end_local_APIC_setup();
map_cpu_to_logical_apicid();
/*
* Need to setup vector mappings before we enable interrupts.
@@ -355,23 +297,6 @@ notrace static void __cpuinit start_secondary(void *unused)
cpu_idle();
}
#ifdef CONFIG_CPUMASK_OFFSTACK
/* In this case, llc_shared_map is a pointer to a cpumask. */
static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst,
const struct cpuinfo_x86 *src)
{
struct cpumask *llc = dst->llc_shared_map;
*dst = *src;
dst->llc_shared_map = llc;
}
#else
static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst,
const struct cpuinfo_x86 *src)
{
*dst = *src;
}
#endif /* CONFIG_CPUMASK_OFFSTACK */
/*
* The bootstrap kernel entry code has set these up. Save them for
* a given CPU
@@ -381,7 +306,7 @@ void __cpuinit smp_store_cpu_info(int id)
{
struct cpuinfo_x86 *c = &cpu_data(id);
copy_cpuinfo_x86(c, &boot_cpu_data);
*c = boot_cpu_data;
c->cpu_index = id;
if (id != 0)
identify_secondary_cpu(c);
@@ -389,15 +314,12 @@ void __cpuinit smp_store_cpu_info(int id)
static void __cpuinit link_thread_siblings(int cpu1, int cpu2)
{
struct cpuinfo_x86 *c1 = &cpu_data(cpu1);
struct cpuinfo_x86 *c2 = &cpu_data(cpu2);
cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2));
cpumask_set_cpu(cpu2, cpu_sibling_mask(cpu1));
cpumask_set_cpu(cpu1, cpu_core_mask(cpu2));
cpumask_set_cpu(cpu2, cpu_core_mask(cpu1));
cpumask_set_cpu(cpu1, c2->llc_shared_map);
cpumask_set_cpu(cpu2, c1->llc_shared_map);
cpumask_set_cpu(cpu1, cpu_llc_shared_mask(cpu2));
cpumask_set_cpu(cpu2, cpu_llc_shared_mask(cpu1));
}
@@ -426,7 +348,7 @@ void __cpuinit set_cpu_sibling_map(int cpu)
cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
}
cpumask_set_cpu(cpu, c->llc_shared_map);
cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
if (__this_cpu_read(cpu_info.x86_max_cores) == 1) {
cpumask_copy(cpu_core_mask(cpu), cpu_sibling_mask(cpu));
@@ -437,8 +359,8 @@ void __cpuinit set_cpu_sibling_map(int cpu)
for_each_cpu(i, cpu_sibling_setup_mask) {
if (per_cpu(cpu_llc_id, cpu) != BAD_APICID &&
per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) {
cpumask_set_cpu(i, c->llc_shared_map);
cpumask_set_cpu(cpu, cpu_data(i).llc_shared_map);
cpumask_set_cpu(i, cpu_llc_shared_mask(cpu));
cpumask_set_cpu(cpu, cpu_llc_shared_mask(i));
}
if (c->phys_proc_id == cpu_data(i).phys_proc_id) {
cpumask_set_cpu(i, cpu_core_mask(cpu));
@@ -477,7 +399,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
!(cpu_has(c, X86_FEATURE_AMD_DCM)))
return cpu_core_mask(cpu);
else
return c->llc_shared_map;
return cpu_llc_shared_mask(cpu);
}
static void impress_friends(void)
@@ -946,6 +868,14 @@ int __cpuinit native_cpu_up(unsigned int cpu)
return 0;
}
/**
* arch_disable_smp_support() - disables SMP support for x86 at runtime
*/
void arch_disable_smp_support(void)
{
disable_ioapic_support();
}
/*
* Fall back to non SMP mode after errors.
*
@@ -961,7 +891,6 @@ static __init void disable_smp(void)
physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
else
physid_set_mask_of_physid(0, &phys_cpu_present_map);
map_cpu_to_logical_apicid();
cpumask_set_cpu(0, cpu_sibling_mask(0));
cpumask_set_cpu(0, cpu_core_mask(0));
}
@@ -1046,7 +975,7 @@ static int __init smp_sanity_check(unsigned max_cpus)
"(tell your hw vendor)\n");
}
smpboot_clear_io_apic();
arch_disable_smp_support();
disable_ioapic_support();
return -1;
}
@@ -1090,21 +1019,19 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
preempt_disable();
smp_cpu_index_default();
memcpy(__this_cpu_ptr(&cpu_info), &boot_cpu_data, sizeof(cpu_info));
cpumask_copy(cpu_callin_mask, cpumask_of(0));
mb();
/*
* Setup boot CPU information
*/
smp_store_cpu_info(0); /* Final full version of the data */
#ifdef CONFIG_X86_32
boot_cpu_logical_apicid = logical_smp_processor_id();
#endif
cpumask_copy(cpu_callin_mask, cpumask_of(0));
mb();
current_thread_info()->cpu = 0; /* needed? */
for_each_possible_cpu(i) {
zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
zalloc_cpumask_var(&cpu_data(i).llc_shared_map, GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
}
set_cpu_sibling_map(0);
@@ -1140,8 +1067,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
bsp_end_local_APIC_setup();
map_cpu_to_logical_apicid();
if (apic->setup_portio_remap)
apic->setup_portio_remap();

3
arch/x86/kernel/syscall_table_32.S
مشاهده پرونده

@@ -340,3 +340,6 @@ ENTRY(sys_call_table)
.long sys_fanotify_init
.long sys_fanotify_mark
.long sys_prlimit64 /* 340 */
.long sys_name_to_handle_at
.long sys_open_by_handle_at
.long sys_clock_adjtime

3
arch/x86/kernel/vmlinux.lds.S
مشاهده پرونده

@@ -105,6 +105,7 @@ SECTIONS
SCHED_TEXT
LOCK_TEXT
KPROBES_TEXT
ENTRY_TEXT
IRQENTRY_TEXT
*(.fixup)
*(.gnu.warning)
@@ -305,7 +306,7 @@ SECTIONS
}
#if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
PERCPU(THREAD_SIZE)
PERCPU(PAGE_SIZE)
#endif
. = ALIGN(PAGE_SIZE);

1
arch/x86/kernel/x8664_ksyms_64.c
مشاهده پرونده

@@ -52,6 +52,7 @@ extern void *__memcpy(void *, const void *, __kernel_size_t);
EXPORT_SYMBOL(memset);
EXPORT_SYMBOL(memcpy);
EXPORT_SYMBOL(__memcpy);
EXPORT_SYMBOL(memmove);
EXPORT_SYMBOL(empty_zero_page);
#ifndef CONFIG_PARAVIRT

1
arch/x86/kernel/x86_init.c
مشاهده پرونده

@@ -70,6 +70,7 @@ struct x86_init_ops x86_init __initdata = {
.setup_percpu_clockev = setup_boot_APIC_clock,
.tsc_pre_init = x86_init_noop,
.timer_init = hpet_time_init,
.wallclock_init = x86_init_noop,
},
.iommu = {