summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/acpi/boot.c5
-rw-r--r--arch/x86/kernel/acpi/cstate.c1
-rw-r--r--arch/x86/kernel/amd_gart_64.c11
-rw-r--r--arch/x86/kernel/apic/apic.c13
-rw-r--r--arch/x86/kernel/apic/apic_numachip.c3
-rw-r--r--arch/x86/kernel/apic/io_apic.c159
-rw-r--r--arch/x86/kernel/apic/x2apic_cluster.c2
-rw-r--r--arch/x86/kernel/apic/x2apic_phys.c2
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c7
-rw-r--r--arch/x86/kernel/apm_32.c1
-rw-r--r--arch/x86/kernel/asm-offsets_64.c6
-rw-r--r--arch/x86/kernel/cpu/common.c2
-rw-r--r--arch/x86/kernel/cpu/mcheck/p5.c1
-rw-r--r--arch/x86/kernel/cpu/mcheck/therm_throt.c1
-rw-r--r--arch/x86/kernel/cpu/mcheck/winchip.c1
-rw-r--r--arch/x86/kernel/cpu/mtrr/generic.c1
-rw-r--r--arch/x86/kernel/cpu/mtrr/if.c10
-rw-r--r--arch/x86/kernel/cpu/perf_event.c21
-rw-r--r--arch/x86/kernel/cpu/perf_event.h1
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd.c18
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c36
-rw-r--r--arch/x86/kernel/cpu/perf_event_p4.c13
-rw-r--r--arch/x86/kernel/cpu/perf_event_p6.c19
-rw-r--r--arch/x86/kernel/cpuid.c1
-rw-r--r--arch/x86/kernel/dumpstack.c9
-rw-r--r--arch/x86/kernel/entry_64.S44
-rw-r--r--arch/x86/kernel/i8259.c1
-rw-r--r--arch/x86/kernel/irq.c7
-rw-r--r--arch/x86/kernel/irqinit.c3
-rw-r--r--arch/x86/kernel/kdebugfs.c9
-rw-r--r--arch/x86/kernel/kgdb.c61
-rw-r--r--arch/x86/kernel/kvmclock.c15
-rw-r--r--arch/x86/kernel/ldt.c1
-rw-r--r--arch/x86/kernel/machine_kexec_32.c1
-rw-r--r--arch/x86/kernel/mca_32.c1
-rw-r--r--arch/x86/kernel/module.c1
-rw-r--r--arch/x86/kernel/msr.c1
-rw-r--r--arch/x86/kernel/paravirt.c1
-rw-r--r--arch/x86/kernel/pci-calgary_64.c10
-rw-r--r--arch/x86/kernel/pci-dma.c3
-rw-r--r--arch/x86/kernel/pci-nommu.c6
-rw-r--r--arch/x86/kernel/pci-swiotlb.c17
-rw-r--r--arch/x86/kernel/process.c125
-rw-r--r--arch/x86/kernel/process_32.c60
-rw-r--r--arch/x86/kernel/process_64.c136
-rw-r--r--arch/x86/kernel/ptrace.c103
-rw-r--r--arch/x86/kernel/setup.c12
-rw-r--r--arch/x86/kernel/signal.c140
-rw-r--r--arch/x86/kernel/smpboot.c10
-rw-r--r--arch/x86/kernel/sys_x86_64.c6
-rw-r--r--arch/x86/kernel/syscall_64.c8
-rw-r--r--arch/x86/kernel/tboot.c9
-rw-r--r--arch/x86/kernel/tce_64.c1
-rw-r--r--arch/x86/kernel/tls.c5
-rw-r--r--arch/x86/kernel/traps.c134
-rw-r--r--arch/x86/kernel/tsc.c14
-rw-r--r--arch/x86/kernel/vm86_32.c2
-rw-r--r--arch/x86/kernel/vsyscall_64.c27
-rw-r--r--arch/x86/kernel/x86_init.c5
59 files changed, 892 insertions, 431 deletions
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 406ed77216d..a415b1f4436 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -239,7 +239,7 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
* to not preallocating memory for all NR_CPUS
* when we use CPU hotplug.
*/
- if (!cpu_has_x2apic && (apic_id >= 0xff) && enabled)
+ if (!apic->apic_id_valid(apic_id) && enabled)
printk(KERN_WARNING PREFIX "x2apic entry ignored\n");
else
acpi_register_lapic(apic_id, enabled);
@@ -642,6 +642,7 @@ static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu)
kfree(buffer.pointer);
buffer.length = ACPI_ALLOCATE_BUFFER;
buffer.pointer = NULL;
+ lapic = NULL;
if (!alloc_cpumask_var(&tmp_map, GFP_KERNEL))
goto out;
@@ -650,7 +651,7 @@ static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu)
goto free_tmp_map;
cpumask_copy(tmp_map, cpu_present_mask);
- acpi_register_lapic(physid, lapic->lapic_flags & ACPI_MADT_ENABLED);
+ acpi_register_lapic(physid, ACPI_MADT_ENABLED);
/*
* If mp_register_lapic successfully generates a new logical cpu
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index f50e7fb2a20..d2b7f27781b 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -14,6 +14,7 @@
#include <acpi/processor.h>
#include <asm/acpi.h>
#include <asm/mwait.h>
+#include <asm/special_insns.h>
/*
* Initialize bm_flags based on the CPU cache properties
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index b1e7c7f7a0a..e66311200cb 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -477,7 +477,7 @@ error:
/* allocate and map a coherent mapping */
static void *
gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
- gfp_t flag)
+ gfp_t flag, struct dma_attrs *attrs)
{
dma_addr_t paddr;
unsigned long align_mask;
@@ -500,7 +500,8 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
}
__free_pages(page, get_order(size));
} else
- return dma_generic_alloc_coherent(dev, size, dma_addr, flag);
+ return dma_generic_alloc_coherent(dev, size, dma_addr, flag,
+ attrs);
return NULL;
}
@@ -508,7 +509,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
/* free a coherent mapping */
static void
gart_free_coherent(struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_addr)
+ dma_addr_t dma_addr, struct dma_attrs *attrs)
{
gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, NULL);
free_pages((unsigned long)vaddr, get_order(size));
@@ -700,8 +701,8 @@ static struct dma_map_ops gart_dma_ops = {
.unmap_sg = gart_unmap_sg,
.map_page = gart_map_page,
.unmap_page = gart_unmap_page,
- .alloc_coherent = gart_alloc_coherent,
- .free_coherent = gart_free_coherent,
+ .alloc = gart_alloc_coherent,
+ .free = gart_free_coherent,
.mapping_error = gart_mapping_error,
};
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 2eec05b6d1b..11544d8f1e9 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -383,20 +383,25 @@ static inline int eilvt_entry_is_changeable(unsigned int old, unsigned int new)
static unsigned int reserve_eilvt_offset(int offset, unsigned int new)
{
- unsigned int rsvd; /* 0: uninitialized */
+ unsigned int rsvd, vector;
if (offset >= APIC_EILVT_NR_MAX)
return ~0;
- rsvd = atomic_read(&eilvt_offsets[offset]) & ~APIC_EILVT_MASKED;
+ rsvd = atomic_read(&eilvt_offsets[offset]);
do {
- if (rsvd &&
- !eilvt_entry_is_changeable(rsvd, new))
+ vector = rsvd & ~APIC_EILVT_MASKED; /* 0: unassigned */
+ if (vector && !eilvt_entry_is_changeable(vector, new))
/* may not change if vectors are different */
return rsvd;
rsvd = atomic_cmpxchg(&eilvt_offsets[offset], rsvd, new);
} while (rsvd != new);
+ rsvd &= ~APIC_EILVT_MASKED;
+ if (rsvd && rsvd != vector)
+ pr_info("LVT offset %d assigned for vector 0x%02x\n",
+ offset, rsvd);
+
return new;
}
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index d9ea5f331ac..899803e0321 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -229,11 +229,10 @@ static int __init numachip_system_init(void)
}
early_initcall(numachip_system_init);
-static int __cpuinit numachip_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+static int numachip_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
{
if (!strncmp(oem_id, "NUMASC", 6)) {
numachip_system = 1;
- setup_force_cpu_cap(X86_FEATURE_X2APIC);
return 1;
}
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 6d10a66fc5a..e88300d8e80 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -64,9 +64,28 @@
#include <asm/apic.h>
#define __apicdebuginit(type) static type __init
+
#define for_each_irq_pin(entry, head) \
for (entry = head; entry; entry = entry->next)
+static void __init __ioapic_init_mappings(void);
+
+static unsigned int __io_apic_read (unsigned int apic, unsigned int reg);
+static void __io_apic_write (unsigned int apic, unsigned int reg, unsigned int val);
+static void __io_apic_modify(unsigned int apic, unsigned int reg, unsigned int val);
+
+static struct io_apic_ops io_apic_ops = {
+ .init = __ioapic_init_mappings,
+ .read = __io_apic_read,
+ .write = __io_apic_write,
+ .modify = __io_apic_modify,
+};
+
+void __init set_io_apic_ops(const struct io_apic_ops *ops)
+{
+ io_apic_ops = *ops;
+}
+
/*
* Is the SiS APIC rmw bug present ?
* -1 = don't know, 0 = no, 1 = yes
@@ -294,6 +313,22 @@ static void free_irq_at(unsigned int at, struct irq_cfg *cfg)
irq_free_desc(at);
}
+static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
+{
+ return io_apic_ops.read(apic, reg);
+}
+
+static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
+{
+ io_apic_ops.write(apic, reg, value);
+}
+
+static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
+{
+ io_apic_ops.modify(apic, reg, value);
+}
+
+
struct io_apic {
unsigned int index;
unsigned int unused[3];
@@ -314,16 +349,17 @@ static inline void io_apic_eoi(unsigned int apic, unsigned int vector)
writel(vector, &io_apic->eoi);
}
-static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
+static unsigned int __io_apic_read(unsigned int apic, unsigned int reg)
{
struct io_apic __iomem *io_apic = io_apic_base(apic);
writel(reg, &io_apic->index);
return readl(&io_apic->data);
}
-static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
+static void __io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
{
struct io_apic __iomem *io_apic = io_apic_base(apic);
+
writel(reg, &io_apic->index);
writel(value, &io_apic->data);
}
@@ -334,7 +370,7 @@ static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned i
*
* Older SiS APIC requires we rewrite the index register
*/
-static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
+static void __io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
{
struct io_apic __iomem *io_apic = io_apic_base(apic);
@@ -377,6 +413,7 @@ static struct IO_APIC_route_entry __ioapic_read_entry(int apic, int pin)
eu.w1 = io_apic_read(apic, 0x10 + 2 * pin);
eu.w2 = io_apic_read(apic, 0x11 + 2 * pin);
+
return eu.entry;
}
@@ -384,9 +421,11 @@ static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin)
{
union entry_union eu;
unsigned long flags;
+
raw_spin_lock_irqsave(&ioapic_lock, flags);
eu.entry = __ioapic_read_entry(apic, pin);
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+
return eu.entry;
}
@@ -396,8 +435,7 @@ static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin)
* the interrupt, and we need to make sure the entry is fully populated
* before that happens.
*/
-static void
-__ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
+static void __ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
{
union entry_union eu = {{0, 0}};
@@ -409,6 +447,7 @@ __ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
{
unsigned long flags;
+
raw_spin_lock_irqsave(&ioapic_lock, flags);
__ioapic_write_entry(apic, pin, e);
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
@@ -435,8 +474,7 @@ static void ioapic_mask_entry(int apic, int pin)
* shared ISA-space IRQs, so we have to support them. We are super
* fast in the common case, and fast for shared ISA-space IRQs.
*/
-static int
-__add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
+static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
{
struct irq_pin_list **last, *entry;
@@ -521,6 +559,7 @@ static void io_apic_sync(struct irq_pin_list *entry)
* a dummy read from the IO-APIC
*/
struct io_apic __iomem *io_apic;
+
io_apic = io_apic_base(entry->apic);
readl(&io_apic->data);
}
@@ -2512,21 +2551,73 @@ static void ack_apic_edge(struct irq_data *data)
atomic_t irq_mis_count;
-static void ack_apic_level(struct irq_data *data)
-{
- struct irq_cfg *cfg = data->chip_data;
- int i, do_unmask_irq = 0, irq = data->irq;
- unsigned long v;
-
- irq_complete_move(cfg);
#ifdef CONFIG_GENERIC_PENDING_IRQ
+static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg)
+{
/* If we are moving the irq we need to mask it */
if (unlikely(irqd_is_setaffinity_pending(data))) {
- do_unmask_irq = 1;
mask_ioapic(cfg);
+ return true;
}
+ return false;
+}
+
+static inline void ioapic_irqd_unmask(struct irq_data *data,
+ struct irq_cfg *cfg, bool masked)
+{
+ if (unlikely(masked)) {
+ /* Only migrate the irq if the ack has been received.
+ *
+ * On rare occasions the broadcast level triggered ack gets
+ * delayed going to ioapics, and if we reprogram the
+ * vector while Remote IRR is still set the irq will never
+ * fire again.
+ *
+ * To prevent this scenario we read the Remote IRR bit
+ * of the ioapic. This has two effects.
+ * - On any sane system the read of the ioapic will
+ * flush writes (and acks) going to the ioapic from
+ * this cpu.
+ * - We get to see if the ACK has actually been delivered.
+ *
+ * Based on failed experiments of reprogramming the
+ * ioapic entry from outside of irq context starting
+ * with masking the ioapic entry and then polling until
+ * Remote IRR was clear before reprogramming the
+ * ioapic I don't trust the Remote IRR bit to be
+ * completey accurate.
+ *
+ * However there appears to be no other way to plug
+ * this race, so if the Remote IRR bit is not
+ * accurate and is causing problems then it is a hardware bug
+ * and you can go talk to the chipset vendor about it.
+ */
+ if (!io_apic_level_ack_pending(cfg))
+ irq_move_masked_irq(data);
+ unmask_ioapic(cfg);
+ }
+}
+#else
+static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg)
+{
+ return false;
+}
+static inline void ioapic_irqd_unmask(struct irq_data *data,
+ struct irq_cfg *cfg, bool masked)
+{
+}
#endif
+static void ack_apic_level(struct irq_data *data)
+{
+ struct irq_cfg *cfg = data->chip_data;
+ int i, irq = data->irq;
+ unsigned long v;
+ bool masked;
+
+ irq_complete_move(cfg);
+ masked = ioapic_irqd_mask(data, cfg);
+
/*
* It appears there is an erratum which affects at least version 0x11
* of I/O APIC (that's the 82093AA and cores integrated into various
@@ -2581,38 +2672,7 @@ static void ack_apic_level(struct irq_data *data)
eoi_ioapic_irq(irq, cfg);
}
- /* Now we can move and renable the irq */
- if (unlikely(do_unmask_irq)) {
- /* Only migrate the irq if the ack has been received.
- *
- * On rare occasions the broadcast level triggered ack gets
- * delayed going to ioapics, and if we reprogram the
- * vector while Remote IRR is still set the irq will never
- * fire again.
- *
- * To prevent this scenario we read the Remote IRR bit
- * of the ioapic. This has two effects.
- * - On any sane system the read of the ioapic will
- * flush writes (and acks) going to the ioapic from
- * this cpu.
- * - We get to see if the ACK has actually been delivered.
- *
- * Based on failed experiments of reprogramming the
- * ioapic entry from outside of irq context starting
- * with masking the ioapic entry and then polling until
- * Remote IRR was clear before reprogramming the
- * ioapic I don't trust the Remote IRR bit to be
- * completey accurate.
- *
- * However there appears to be no other way to plug
- * this race, so if the Remote IRR bit is not
- * accurate and is causing problems then it is a hardware bug
- * and you can go talk to the chipset vendor about it.
- */
- if (!io_apic_level_ack_pending(cfg))
- irq_move_masked_irq(data);
- unmask_ioapic(cfg);
- }
+ ioapic_irqd_unmask(data, cfg, masked);
}
#ifdef CONFIG_IRQ_REMAP
@@ -3873,6 +3933,11 @@ static struct resource * __init ioapic_setup_resources(int nr_ioapics)
void __init ioapic_and_gsi_init(void)
{
+ io_apic_ops.init();
+}
+
+static void __init __ioapic_init_mappings(void)
+{
unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
struct resource *ioapic_res;
int i;
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 9193713060a..48f3103b3c9 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -213,7 +213,7 @@ static struct apic apic_x2apic_cluster = {
.name = "cluster x2apic",
.probe = x2apic_cluster_probe,
.acpi_madt_oem_check = x2apic_acpi_madt_oem_check,
- .apic_id_valid = default_apic_id_valid,
+ .apic_id_valid = x2apic_apic_id_valid,
.apic_id_registered = x2apic_apic_id_registered,
.irq_delivery_mode = dest_LowestPrio,
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index bcd1db6eaca..8a778db45e3 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -119,7 +119,7 @@ static struct apic apic_x2apic_phys = {
.name = "physical x2apic",
.probe = x2apic_phys_probe,
.acpi_madt_oem_check = x2apic_acpi_madt_oem_check,
- .apic_id_valid = default_apic_id_valid,
+ .apic_id_valid = x2apic_apic_id_valid,
.apic_id_registered = x2apic_apic_id_registered,
.irq_delivery_mode = dest_Fixed,
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index fc477142585..87bfa69e216 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -266,6 +266,11 @@ static void uv_send_IPI_all(int vector)
uv_send_IPI_mask(cpu_online_mask, vector);
}
+static int uv_apic_id_valid(int apicid)
+{
+ return 1;
+}
+
static int uv_apic_id_registered(void)
{
return 1;
@@ -351,7 +356,7 @@ static struct apic __refdata apic_x2apic_uv_x = {
.name = "UV large system",
.probe = uv_probe,
.acpi_madt_oem_check = uv_acpi_madt_oem_check,
- .apic_id_valid = default_apic_id_valid,
+ .apic_id_valid = uv_apic_id_valid,
.apic_id_registered = uv_apic_id_registered,
.irq_delivery_mode = dest_Fixed,
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 5d56931a15b..459e78cbf61 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -231,7 +231,6 @@
#include <linux/syscore_ops.h>
#include <linux/i8253.h>
-#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/desc.h>
#include <asm/olpc.h>
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 834e897b1e2..1b4754f82ba 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -1,6 +1,12 @@
#include <asm/ia32.h>
#define __SYSCALL_64(nr, sym, compat) [nr] = 1,
+#define __SYSCALL_COMMON(nr, sym, compat) [nr] = 1,
+#ifdef CONFIG_X86_X32_ABI
+# define __SYSCALL_X32(nr, sym, compat) [nr] = 1,
+#else
+# define __SYSCALL_X32(nr, sym, compat) /* nothing */
+#endif
static char syscalls_64[] = {
#include <asm/syscalls_64.h>
};
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index e49477444ff..67e258362a3 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -999,7 +999,7 @@ void __cpuinit print_cpu_info(struct cpuinfo_x86 *c)
else
printk(KERN_CONT "\n");
- __print_cpu_msr();
+ print_cpu_msr(c);
}
void __cpuinit print_cpu_msr(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c
index 5c0e6533d9b..2d5454cd2c4 100644
--- a/arch/x86/kernel/cpu/mcheck/p5.c
+++ b/arch/x86/kernel/cpu/mcheck/p5.c
@@ -9,7 +9,6 @@
#include <linux/smp.h>
#include <asm/processor.h>
-#include <asm/system.h>
#include <asm/mce.h>
#include <asm/msr.h>
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 67bb17a37a0..47a1870279a 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -25,7 +25,6 @@
#include <linux/cpu.h>
#include <asm/processor.h>
-#include <asm/system.h>
#include <asm/apic.h>
#include <asm/idle.h>
#include <asm/mce.h>
diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c
index 54060f56597..2d7998fb628 100644
--- a/arch/x86/kernel/cpu/mcheck/winchip.c
+++ b/arch/x86/kernel/cpu/mcheck/winchip.c
@@ -8,7 +8,6 @@
#include <linux/init.h>
#include <asm/processor.h>
-#include <asm/system.h>
#include <asm/mce.h>
#include <asm/msr.h>
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 97b26356e9e..75772ae6c65 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -12,7 +12,6 @@
#include <asm/processor-flags.h>
#include <asm/cpufeature.h>
#include <asm/tlbflush.h>
-#include <asm/system.h>
#include <asm/mtrr.h>
#include <asm/msr.h>
#include <asm/pat.h>
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index 79289632cb2..a041e094b8b 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -167,6 +167,7 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
{
int err = 0;
mtrr_type type;
+ unsigned long base;
unsigned long size;
struct mtrr_sentry sentry;
struct mtrr_gentry gentry;
@@ -267,14 +268,14 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
#endif
if (gentry.regnum >= num_var_ranges)
return -EINVAL;
- mtrr_if->get(gentry.regnum, &gentry.base, &size, &type);
+ mtrr_if->get(gentry.regnum, &base, &size, &type);
/* Hide entries that go above 4GB */
- if (gentry.base + size - 1 >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT))
+ if (base + size - 1 >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT))
|| size >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT)))
gentry.base = gentry.size = gentry.type = 0;
else {
- gentry.base <<= PAGE_SHIFT;
+ gentry.base = base << PAGE_SHIFT;
gentry.size = size << PAGE_SHIFT;
gentry.type = type;
}
@@ -321,11 +322,12 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
#endif
if (gentry.regnum >= num_var_ranges)
return -EINVAL;
- mtrr_if->get(gentry.regnum, &gentry.base, &size, &type);
+ mtrr_if->get(gentry.regnum, &base, &size, &type);
/* Hide entries that would overflow */
if (size != (__typeof__(gentry.size))size)
gentry.base = gentry.size = gentry.type = 0;
else {
+ gentry.base = base;
gentry.size = size;
gentry.type = type;
}
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index fa2900c0e39..bb8e03407e1 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -29,7 +29,6 @@
#include <asm/apic.h>
#include <asm/stacktrace.h>
#include <asm/nmi.h>
-#include <asm/compat.h>
#include <asm/smp.h>
#include <asm/alternative.h>
#include <asm/timer.h>
@@ -1314,6 +1313,11 @@ static void __init pmu_check_apic(void)
pr_info("no hardware sampling interrupt available.\n");
}
+static struct attribute_group x86_pmu_format_group = {
+ .name = "format",
+ .attrs = NULL,
+};
+
static int __init init_hw_perf_events(void)
{
struct x86_pmu_quirk *quirk;
@@ -1388,6 +1392,7 @@ static int __init init_hw_perf_events(void)
}
x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
+ x86_pmu_format_group.attrs = x86_pmu.format_attrs;
pr_info("... version: %d\n", x86_pmu.version);
pr_info("... bit width: %d\n", x86_pmu.cntval_bits);
@@ -1616,6 +1621,9 @@ static int x86_pmu_event_idx(struct perf_event *event)
{
int idx = event->hw.idx;
+ if (!x86_pmu.attr_rdpmc)
+ return 0;
+
if (x86_pmu.num_counters_fixed && idx >= X86_PMC_IDX_FIXED) {
idx -= X86_PMC_IDX_FIXED;
idx |= 1 << 30;
@@ -1668,6 +1676,7 @@ static struct attribute_group x86_pmu_attr_group = {
static const struct attribute_group *x86_pmu_attr_groups[] = {
&x86_pmu_attr_group,
+ &x86_pmu_format_group,
NULL,
};
@@ -1699,14 +1708,19 @@ static struct pmu pmu = {
.flush_branch_stack = x86_pmu_flush_branch_stack,
};
-void perf_update_user_clock(struct perf_event_mmap_page *userpg, u64 now)
+void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
{
+ userpg->cap_usr_time = 0;
+ userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc;
+ userpg->pmc_width = x86_pmu.cntval_bits;
+
if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
return;
if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
return;
+ userpg->cap_usr_time = 1;
userpg->time_mult = this_cpu_read(cyc2ns);
userpg->time_shift = CYC2NS_SCALE_FACTOR;
userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
@@ -1748,6 +1762,9 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
}
#ifdef CONFIG_COMPAT
+
+#include <asm/compat.h>
+
static inline int
perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
{
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 8484e77c211..6638aaf5449 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -339,6 +339,7 @@ struct x86_pmu {
* sysfs attrs
*/
int attr_rdpmc;
+ struct attribute **format_attrs;
/*
* CPU Hotplug hooks
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index dd002faff7a..95e7fe1c5f0 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -404,6 +404,21 @@ static void amd_pmu_cpu_dead(int cpu)
}
}
+PMU_FORMAT_ATTR(event, "config:0-7,32-35");
+PMU_FORMAT_ATTR(umask, "config:8-15" );
+PMU_FORMAT_ATTR(edge, "config:18" );
+PMU_FORMAT_ATTR(inv, "config:23" );
+PMU_FORMAT_ATTR(cmask, "config:24-31" );
+
+static struct attribute *amd_format_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_cmask.attr,
+ NULL,
+};
+
static __initconst const struct x86_pmu amd_pmu = {
.name = "AMD",
.handle_irq = x86_pmu_handle_irq,
@@ -426,6 +441,8 @@ static __initconst const struct x86_pmu amd_pmu = {
.get_event_constraints = amd_get_event_constraints,
.put_event_constraints = amd_put_event_constraints,
+ .format_attrs = amd_format_attr,
+
.cpu_prepare = amd_pmu_cpu_prepare,
.cpu_starting = amd_pmu_cpu_starting,
.cpu_dead = amd_pmu_cpu_dead,
@@ -596,6 +613,7 @@ static __initconst const struct x86_pmu amd_pmu_f15h = {
.cpu_dead = amd_pmu_cpu_dead,
#endif
.cpu_starting = amd_pmu_cpu_starting,
+ .format_attrs = amd_format_attr,
};
__init int amd_pmu_init(void)
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 6a84e7f28f0..26b3e2fef10 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1431,6 +1431,24 @@ static void core_pmu_enable_all(int added)
}
}
+PMU_FORMAT_ATTR(event, "config:0-7" );
+PMU_FORMAT_ATTR(umask, "config:8-15" );
+PMU_FORMAT_ATTR(edge, "config:18" );
+PMU_FORMAT_ATTR(pc, "config:19" );
+PMU_FORMAT_ATTR(any, "config:21" ); /* v3 + */
+PMU_FORMAT_ATTR(inv, "config:23" );
+PMU_FORMAT_ATTR(cmask, "config:24-31" );
+
+static struct attribute *intel_arch_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_pc.attr,
+ &format_attr_inv.attr,
+ &format_attr_cmask.attr,
+ NULL,
+};
+
static __initconst const struct x86_pmu core_pmu = {
.name = "core",
.handle_irq = x86_pmu_handle_irq,
@@ -1455,6 +1473,7 @@ static __initconst const struct x86_pmu core_pmu = {
.put_event_constraints = intel_put_event_constraints,
.event_constraints = intel_core_event_constraints,
.guest_get_msrs = core_guest_get_msrs,
+ .format_attrs = intel_arch_formats_attr,
};
struct intel_shared_regs *allocate_shared_regs(int cpu)
@@ -1553,6 +1572,21 @@ static void intel_pmu_flush_branch_stack(void)
intel_pmu_lbr_reset();
}
+PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
+
+static struct attribute *intel_arch3_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_pc.attr,
+ &format_attr_any.attr,
+ &format_attr_inv.attr,
+ &format_attr_cmask.attr,
+
+ &format_attr_offcore_rsp.attr, /* XXX do NHM/WSM + SNB breakout */
+ NULL,
+};
+
static __initconst const struct x86_pmu intel_pmu = {
.name = "Intel",
.handle_irq = intel_pmu_handle_irq,
@@ -1576,6 +1610,8 @@ static __initconst const struct x86_pmu intel_pmu = {
.get_event_constraints = intel_get_event_constraints,
.put_event_constraints = intel_put_event_constraints,
+ .format_attrs = intel_arch3_formats_attr,
+
.cpu_prepare = intel_pmu_cpu_prepare,
.cpu_starting = intel_pmu_cpu_starting,
.cpu_dying = intel_pmu_cpu_dying,
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index ef484d9d0a2..a2dfacfd710 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -1271,6 +1271,17 @@ done:
return num ? -EINVAL : 0;
}
+PMU_FORMAT_ATTR(cccr, "config:0-31" );
+PMU_FORMAT_ATTR(escr, "config:32-62");
+PMU_FORMAT_ATTR(ht, "config:63" );
+
+static struct attribute *intel_p4_formats_attr[] = {
+ &format_attr_cccr.attr,
+ &format_attr_escr.attr,
+ &format_attr_ht.attr,
+ NULL,
+};
+
static __initconst const struct x86_pmu p4_pmu = {
.name = "Netburst P4/Xeon",
.handle_irq = p4_pmu_handle_irq,
@@ -1305,6 +1316,8 @@ static __initconst const struct x86_pmu p4_pmu = {
* the former idea is taken from OProfile code
*/
.perfctr_second_write = 1,
+
+ .format_attrs = intel_p4_formats_attr,
};
__init int p4_pmu_init(void)
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index c7181befecd..32bcfc7dd23 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -87,6 +87,23 @@ static void p6_pmu_enable_event(struct perf_event *event)
(void)checking_wrmsrl(hwc->config_base, val);
}
+PMU_FORMAT_ATTR(event, "config:0-7" );
+PMU_FORMAT_ATTR(umask, "config:8-15" );
+PMU_FORMAT_ATTR(edge, "config:18" );
+PMU_FORMAT_ATTR(pc, "config:19" );
+PMU_FORMAT_ATTR(inv, "config:23" );
+PMU_FORMAT_ATTR(cmask, "config:24-31" );
+
+static struct attribute *intel_p6_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_pc.attr,
+ &format_attr_inv.attr,
+ &format_attr_cmask.attr,
+ NULL,
+};
+
static __initconst const struct x86_pmu p6_pmu = {
.name = "p6",
.handle_irq = x86_pmu_handle_irq,
@@ -115,6 +132,8 @@ static __initconst const struct x86_pmu p6_pmu = {
.cntval_mask = (1ULL << 32) - 1,
.get_event_constraints = x86_get_event_constraints,
.event_constraints = p6_event_constraints,
+
+ .format_attrs = intel_p6_formats_attr,
};
__init int p6_pmu_init(void)
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index a524353d93f..39472dd2323 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -43,7 +43,6 @@
#include <asm/processor.h>
#include <asm/msr.h>
-#include <asm/system.h>
static struct class *cpuid_class;
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 4025fe4f928..1b81839b6c8 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -37,13 +37,16 @@ print_ftrace_graph_addr(unsigned long addr, void *data,
const struct stacktrace_ops *ops,
struct thread_info *tinfo, int *graph)
{
- struct task_struct *task = tinfo->task;
+ struct task_struct *task;
unsigned long ret_addr;
- int index = task->curr_ret_stack;
+ int index;
if (addr != (unsigned long)return_to_handler)
return;
+ task = tinfo->task;
+ index = task->curr_ret_stack;
+
if (!task->ret_stack || index < *graph)
return;
@@ -265,7 +268,7 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err)
#endif
printk("\n");
if (notify_die(DIE_OOPS, str, regs, err,
- current->thread.trap_no, SIGSEGV) == NOTIFY_STOP)
+ current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP)
return 1;
show_registers(regs);
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 734ebd1d3ca..cdc79b5cfcd 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -481,7 +481,12 @@ GLOBAL(system_call_after_swapgs)
testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
jnz tracesys
system_call_fastpath:
+#if __SYSCALL_MASK == ~0
cmpq $__NR_syscall_max,%rax
+#else
+ andl $__SYSCALL_MASK,%eax
+ cmpl $__NR_syscall_max,%eax
+#endif
ja badsys
movq %r10,%rcx
call *sys_call_table(,%rax,8) # XXX: rip relative
@@ -595,7 +600,12 @@ tracesys:
*/
LOAD_ARGS ARGOFFSET, 1
RESTORE_REST
+#if __SYSCALL_MASK == ~0
cmpq $__NR_syscall_max,%rax
+#else
+ andl $__SYSCALL_MASK,%eax
+ cmpl $__NR_syscall_max,%eax
+#endif
ja int_ret_from_sys_call /* RAX(%rsp) set to -ENOSYS above */
movq %r10,%rcx /* fixup for C */
call *sys_call_table(,%rax,8)
@@ -735,6 +745,40 @@ ENTRY(stub_rt_sigreturn)
CFI_ENDPROC
END(stub_rt_sigreturn)
+#ifdef CONFIG_X86_X32_ABI
+ PTREGSCALL stub_x32_sigaltstack, sys32_sigaltstack, %rdx
+
+ENTRY(stub_x32_rt_sigreturn)
+ CFI_STARTPROC
+ addq $8, %rsp
+ PARTIAL_FRAME 0
+ SAVE_REST
+ movq %rsp,%rdi
+ FIXUP_TOP_OF_STACK %r11
+ call sys32_x32_rt_sigreturn
+ movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer
+ RESTORE_REST
+ jmp int_ret_from_sys_call
+ CFI_ENDPROC
+END(stub_x32_rt_sigreturn)
+
+ENTRY(stub_x32_execve)
+ CFI_STARTPROC
+ addq $8, %rsp
+ PARTIAL_FRAME 0
+ SAVE_REST
+ FIXUP_TOP_OF_STACK %r11
+ movq %rsp, %rcx
+ call sys32_execve
+ RESTORE_TOP_OF_STACK %r11
+ movq %rax,RAX(%rsp)
+ RESTORE_REST
+ jmp int_ret_from_sys_call
+ CFI_ENDPROC
+END(stub_x32_execve)
+
+#endif
+
/*
* Build the entry stubs and pointer table with some assembler magic.
* We pack 7 stubs into a single 32-byte chunk, which will fit in a
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 610485223bd..36d1853e91a 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -15,7 +15,6 @@
#include <linux/delay.h>
#include <linux/atomic.h>
-#include <asm/system.h>
#include <asm/timer.h>
#include <asm/hw_irq.h>
#include <asm/pgtable.h>
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 7943e0c21bd..3dafc6003b7 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -282,8 +282,13 @@ void fixup_irqs(void)
else if (!(warned++))
set_affinity = 0;
+ /*
+ * We unmask if the irq was not marked masked by the
+ * core code. That respects the lazy irq disable
+ * behaviour.
+ */
if (!irqd_can_move_in_process_context(data) &&
- !irqd_irq_disabled(data) && chip->irq_unmask)
+ !irqd_irq_masked(data) && chip->irq_unmask)
chip->irq_unmask(data);
raw_spin_unlock(&desc->lock);
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 43e2b1cff0a..252981afd6c 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -16,7 +16,6 @@
#include <linux/delay.h>
#include <linux/atomic.h>
-#include <asm/system.h>
#include <asm/timer.h>
#include <asm/hw_irq.h>
#include <asm/pgtable.h>
@@ -61,7 +60,7 @@ static irqreturn_t math_error_irq(int cpl, void *dev_id)
outb(0, 0xF0);
if (ignore_fpu_irq || !boot_cpu_data.hard_math)
return IRQ_NONE;
- math_error(get_irq_regs(), 0, 16);
+ math_error(get_irq_regs(), 0, X86_TRAP_MF);
return IRQ_HANDLED;
}
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index 90fcf62854b..1d5d31ea686 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -68,16 +68,9 @@ static ssize_t setup_data_read(struct file *file, char __user *user_buf,
return count;
}
-static int setup_data_open(struct inode *inode, struct file *file)
-{
- file->private_data = inode->i_private;
-
- return 0;
-}
-
static const struct file_operations fops_setup_data = {
.read = setup_data_read,
- .open = setup_data_open,
+ .open = simple_open,
.llseek = default_llseek,
};
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index fdc37b3d0ce..8bfb6146f75 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -43,10 +43,11 @@
#include <linux/smp.h>
#include <linux/nmi.h>
#include <linux/hw_breakpoint.h>
+#include <linux/uaccess.h>
+#include <linux/memory.h>
#include <asm/debugreg.h>
#include <asm/apicdef.h>
-#include <asm/system.h>
#include <asm/apic.h>
#include <asm/nmi.h>
@@ -742,6 +743,64 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip)
regs->ip = ip;
}
+int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
+{
+ int err;
+ char opc[BREAK_INSTR_SIZE];
+
+ bpt->type = BP_BREAKPOINT;
+ err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
+ BREAK_INSTR_SIZE);
+ if (err)
+ return err;
+ err = probe_kernel_write((char *)bpt->bpt_addr,
+ arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE);
+#ifdef CONFIG_DEBUG_RODATA
+ if (!err)
+ return err;
+ /*
+ * It is safe to call text_poke() because normal kernel execution
+ * is stopped on all cores, so long as the text_mutex is not locked.
+ */
+ if (mutex_is_locked(&text_mutex))
+ return -EBUSY;
+ text_poke((void *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr,
+ BREAK_INSTR_SIZE);
+ err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE);
+ if (err)
+ return err;
+ if (memcmp(opc, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE))
+ return -EINVAL;
+ bpt->type = BP_POKE_BREAKPOINT;
+#endif /* CONFIG_DEBUG_RODATA */
+ return err;
+}
+
+int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
+{
+#ifdef CONFIG_DEBUG_RODATA
+ int err;
+ char opc[BREAK_INSTR_SIZE];
+
+ if (bpt->type != BP_POKE_BREAKPOINT)
+ goto knl_write;
+ /*
+ * It is safe to call text_poke() because normal kernel execution
+ * is stopped on all cores, so long as the text_mutex is not locked.
+ */
+ if (mutex_is_locked(&text_mutex))
+ goto knl_write;
+ text_poke((void *)bpt->bpt_addr, bpt->saved_instr, BREAK_INSTR_SIZE);
+ err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE);
+ if (err || memcmp(opc, bpt->saved_instr, BREAK_INSTR_SIZE))
+ goto knl_write;
+ return err;
+knl_write:
+#endif /* CONFIG_DEBUG_RODATA */
+ return probe_kernel_write((char *)bpt->bpt_addr,
+ (char *)bpt->saved_instr, BREAK_INSTR_SIZE);
+}
+
struct kgdb_arch arch_kgdb_ops = {
/* Breakpoint instruction: */
.gdb_bpt_instr = { 0xcc },
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 44842d756b2..f8492da65bf 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -136,6 +136,15 @@ int kvm_register_clock(char *txt)
return ret;
}
+static void kvm_save_sched_clock_state(void)
+{
+}
+
+static void kvm_restore_sched_clock_state(void)
+{
+ kvm_register_clock("primary cpu clock, resume");
+}
+
#ifdef CONFIG_X86_LOCAL_APIC
static void __cpuinit kvm_setup_secondary_clock(void)
{
@@ -144,8 +153,6 @@ static void __cpuinit kvm_setup_secondary_clock(void)
* we shouldn't fail.
*/
WARN_ON(kvm_register_clock("secondary cpu clock"));
- /* ok, done with our trickery, call native */
- setup_secondary_APIC_clock();
}
#endif
@@ -194,9 +201,11 @@ void __init kvmclock_init(void)
x86_platform.get_wallclock = kvm_get_wallclock;
x86_platform.set_wallclock = kvm_set_wallclock;
#ifdef CONFIG_X86_LOCAL_APIC
- x86_cpuinit.setup_percpu_clockev =
+ x86_cpuinit.early_percpu_clock_init =
kvm_setup_secondary_clock;
#endif
+ x86_platform.save_sched_clock_state = kvm_save_sched_clock_state;
+ x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state;
machine_ops.shutdown = kvm_shutdown;
#ifdef CONFIG_KEXEC
machine_ops.crash_shutdown = kvm_crash_shutdown;
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index ea697263b37..ebc98739892 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -15,7 +15,6 @@
#include <linux/vmalloc.h>
#include <linux/uaccess.h>
-#include <asm/system.h>
#include <asm/ldt.h>
#include <asm/desc.h>
#include <asm/mmu_context.h>
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index a3fa43ba5d3..5b19e4d78b0 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -23,7 +23,6 @@
#include <asm/apic.h>
#include <asm/cpufeature.h>
#include <asm/desc.h>
-#include <asm/system.h>
#include <asm/cacheflush.h>
#include <asm/debugreg.h>
diff --git a/arch/x86/kernel/mca_32.c b/arch/x86/kernel/mca_32.c
index 177183cbb6a..7eb1e2b9782 100644
--- a/arch/x86/kernel/mca_32.c
+++ b/arch/x86/kernel/mca_32.c
@@ -43,7 +43,6 @@
#include <linux/mca.h>
#include <linux/kprobes.h>
#include <linux/slab.h>
-#include <asm/system.h>
#include <asm/io.h>
#include <linux/proc_fs.h>
#include <linux/mman.h>
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 925179f871d..f21fd94ac89 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -26,7 +26,6 @@
#include <linux/gfp.h>
#include <linux/jump_label.h>
-#include <asm/system.h>
#include <asm/page.h>
#include <asm/pgtable.h>
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 96356762a51..eb113693f04 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -40,7 +40,6 @@
#include <asm/processor.h>
#include <asm/msr.h>
-#include <asm/system.h>
static struct class *msr_class;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 9c57c02e54f..ab137605e69 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -38,6 +38,7 @@
#include <asm/apic.h>
#include <asm/tlbflush.h>
#include <asm/timer.h>
+#include <asm/special_insns.h>
/* nop stub */
void _paravirt_nop(void)
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 726494b5834..d0b2fb9ccbb 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -42,7 +42,6 @@
#include <asm/calgary.h>
#include <asm/tce.h>
#include <asm/pci-direct.h>
-#include <asm/system.h>
#include <asm/dma.h>
#include <asm/rio.h>
#include <asm/bios_ebda.h>
@@ -431,7 +430,7 @@ static void calgary_unmap_page(struct device *dev, dma_addr_t dma_addr,
}
static void* calgary_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t flag)
+ dma_addr_t *dma_handle, gfp_t flag, struct dma_attrs *attrs)
{
void *ret = NULL;
dma_addr_t mapping;
@@ -464,7 +463,8 @@ error:
}
static void calgary_free_coherent(struct device *dev, size_t size,
- void *vaddr, dma_addr_t dma_handle)
+ void *vaddr, dma_addr_t dma_handle,
+ struct dma_attrs *attrs)
{
unsigned int npages;
struct iommu_table *tbl = find_iommu_table(dev);
@@ -477,8 +477,8 @@ static void calgary_free_coherent(struct device *dev, size_t size,
}
static struct dma_map_ops calgary_dma_ops = {
- .alloc_coherent = calgary_alloc_coherent,
- .free_coherent = calgary_free_coherent,
+ .alloc = calgary_alloc_coherent,
+ .free = calgary_free_coherent,
.map_sg = calgary_map_sg,
.unmap_sg = calgary_unmap_sg,
.map_page = calgary_map_page,
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 28e5e06fcba..3003250ac51 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -96,7 +96,8 @@ void __init pci_iommu_alloc(void)
}
}
void *dma_generic_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_addr, gfp_t flag)
+ dma_addr_t *dma_addr, gfp_t flag,
+ struct dma_attrs *attrs)
{
unsigned long dma_mask;
struct page *page;
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index 3af4af810c0..f96050685b4 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -75,7 +75,7 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
}
static void nommu_free_coherent(struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_addr)
+ dma_addr_t dma_addr, struct dma_attrs *attrs)
{
free_pages((unsigned long)vaddr, get_order(size));
}
@@ -96,8 +96,8 @@ static void nommu_sync_sg_for_device(struct device *dev,
}
struct dma_map_ops nommu_dma_ops = {
- .alloc_coherent = dma_generic_alloc_coherent,
- .free_coherent = nommu_free_coherent,
+ .alloc = dma_generic_alloc_coherent,
+ .free = nommu_free_coherent,
.map_sg = nommu_map_sg,
.map_page = nommu_map_page,
.sync_single_for_device = nommu_sync_single_for_device,
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 8f972cbddef..6c483ba98b9 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -15,21 +15,30 @@
int swiotlb __read_mostly;
static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
- dma_addr_t *dma_handle, gfp_t flags)
+ dma_addr_t *dma_handle, gfp_t flags,
+ struct dma_attrs *attrs)
{
void *vaddr;
- vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags);
+ vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags,
+ attrs);
if (vaddr)
return vaddr;
return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags);
}
+static void x86_swiotlb_free_coherent(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_addr,
+ struct dma_attrs *attrs)
+{
+ swiotlb_free_coherent(dev, size, vaddr, dma_addr);
+}
+
static struct dma_map_ops swiotlb_dma_ops = {
.mapping_error = swiotlb_dma_mapping_error,
- .alloc_coherent = x86_swiotlb_alloc_coherent,
- .free_coherent = swiotlb_free_coherent,
+ .alloc = x86_swiotlb_alloc_coherent,
+ .free = x86_swiotlb_free_coherent,
.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
.sync_single_for_device = swiotlb_sync_single_for_device,
.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 14baf78d5a1..1d92a5ab6e8 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -12,10 +12,12 @@
#include <linux/user-return-notifier.h>
#include <linux/dmi.h>
#include <linux/utsname.h>
+#include <linux/stackprotector.h>
+#include <linux/tick.h>
+#include <linux/cpuidle.h>
#include <trace/events/power.h>
#include <linux/hw_breakpoint.h>
#include <asm/cpu.h>
-#include <asm/system.h>
#include <asm/apic.h>
#include <asm/syscalls.h>
#include <asm/idle.h>
@@ -23,6 +25,24 @@
#include <asm/i387.h>
#include <asm/fpu-internal.h>
#include <asm/debugreg.h>
+#include <asm/nmi.h>
+
+#ifdef CONFIG_X86_64
+static DEFINE_PER_CPU(unsigned char, is_idle);
+static ATOMIC_NOTIFIER_HEAD(idle_notifier);
+
+void idle_notifier_register(struct notifier_block *n)
+{
+ atomic_notifier_chain_register(&idle_notifier, n);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_register);
+
+void idle_notifier_unregister(struct notifier_block *n)
+{
+ atomic_notifier_chain_unregister(&idle_notifier, n);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_unregister);
+#endif
struct kmem_cache *task_xstate_cachep;
EXPORT_SYMBOL_GPL(task_xstate_cachep);
@@ -342,36 +362,105 @@ void (*pm_idle)(void);
EXPORT_SYMBOL(pm_idle);
#endif
-#ifdef CONFIG_X86_32
-/*
- * This halt magic was a workaround for ancient floppy DMA
- * wreckage. It should be safe to remove.
- */
-static int hlt_counter;
-void disable_hlt(void)
+static inline int hlt_use_halt(void)
{
- hlt_counter++;
+ return 1;
}
-EXPORT_SYMBOL(disable_hlt);
-void enable_hlt(void)
+#ifndef CONFIG_SMP
+static inline void play_dead(void)
{
- hlt_counter--;
+ BUG();
}
-EXPORT_SYMBOL(enable_hlt);
+#endif
-static inline int hlt_use_halt(void)
+#ifdef CONFIG_X86_64
+void enter_idle(void)
{
- return (!hlt_counter && boot_cpu_data.hlt_works_ok);
+ percpu_write(is_idle, 1);
+ atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
}
-#else
-static inline int hlt_use_halt(void)
+
+static void __exit_idle(void)
{
- return 1;
+ if (x86_test_and_clear_bit_percpu(0, is_idle) == 0)
+ return;
+ atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
+}
+
+/* Called from interrupts to signify idle end */
+void exit_idle(void)
+{
+ /* idle loop has pid 0 */
+ if (current->pid)
+ return;
+ __exit_idle();
}
#endif
/*
+ * The idle thread. There's no useful work to be
+ * done, so just try to conserve power and have a
+ * low exit latency (ie sit in a loop waiting for
+ * somebody to say that they'd like to reschedule)
+ */
+void cpu_idle(void)
+{
+ /*
+ * If we're the non-boot CPU, nothing set the stack canary up
+ * for us. CPU0 already has it initialized but no harm in
+ * doing it again. This is a good place for updating it, as
+ * we wont ever return from this function (so the invalid
+ * canaries already on the stack wont ever trigger).
+ */
+ boot_init_stack_canary();
+ current_thread_info()->status |= TS_POLLING;
+
+ while (1) {
+ tick_nohz_idle_enter();
+
+ while (!need_resched()) {
+ rmb();
+
+ if (cpu_is_offline(smp_processor_id()))
+ play_dead();
+
+ /*
+ * Idle routines should keep interrupts disabled
+ * from here on, until they go to idle.
+ * Otherwise, idle callbacks can misfire.
+ */
+ local_touch_nmi();
+ local_irq_disable();
+
+ enter_idle();
+
+ /* Don't trace irqs off for idle */
+ stop_critical_timings();
+
+ /* enter_idle() needs rcu for notifiers */
+ rcu_idle_enter();
+
+ if (cpuidle_idle_call())
+ pm_idle();
+
+ rcu_idle_exit();
+ start_critical_timings();
+
+ /* In many cases the interrupt that ended idle
+ has already called exit_idle. But some idle
+ loops can be woken up without interrupt. */
+ __exit_idle();
+ }
+
+ tick_nohz_idle_exit();
+ preempt_enable_no_resched();
+ schedule();
+ preempt_disable();
+ }
+}
+
+/*
* We use this if we don't have any better
* idle routine..
*/
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 9d7d4842bfa..ae6847303e2 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -9,7 +9,6 @@
* This file handles the architecture-dependent parts of process handling..
*/
-#include <linux/stackprotector.h>
#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/sched.h>
@@ -31,17 +30,14 @@
#include <linux/kallsyms.h>
#include <linux/ptrace.h>
#include <linux/personality.h>
-#include <linux/tick.h>
#include <linux/percpu.h>
#include <linux/prctl.h>
#include <linux/ftrace.h>
#include <linux/uaccess.h>
#include <linux/io.h>
#include <linux/kdebug.h>
-#include <linux/cpuidle.h>
#include <asm/pgtable.h>
-#include <asm/system.h>
#include <asm/ldt.h>
#include <asm/processor.h>
#include <asm/i387.h>
@@ -58,7 +54,7 @@
#include <asm/idle.h>
#include <asm/syscalls.h>
#include <asm/debugreg.h>
-#include <asm/nmi.h>
+#include <asm/switch_to.h>
asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
@@ -70,60 +66,6 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
return ((unsigned long *)tsk->thread.sp)[3];
}
-#ifndef CONFIG_SMP
-static inline void play_dead(void)
-{
- BUG();
-}
-#endif
-
-/*
- * The idle thread. There's no useful work to be
- * done, so just try to conserve power and have a
- * low exit latency (ie sit in a loop waiting for
- * somebody to say that they'd like to reschedule)
- */
-void cpu_idle(void)
-{
- int cpu = smp_processor_id();
-
- /*
- * If we're the non-boot CPU, nothing set the stack canary up
- * for us. CPU0 already has it initialized but no harm in
- * doing it again. This is a good place for updating it, as
- * we wont ever return from this function (so the invalid
- * canaries already on the stack wont ever trigger).
- */
- boot_init_stack_canary();
-
- current_thread_info()->status |= TS_POLLING;
-
- /* endless idle loop with no priority at all */
- while (1) {
- tick_nohz_idle_enter();
- rcu_idle_enter();
- while (!need_resched()) {
-
- check_pgt_cache();
- rmb();
-
- if (cpu_is_offline(cpu))
- play_dead();
-
- local_touch_nmi();
- local_irq_disable();
- /* Don't trace irqs off for idle */
- stop_critical_timings();
- if (cpuidle_idle_call())
- pm_idle();
- start_critical_timings();
- }
- rcu_idle_exit();
- tick_nohz_idle_exit();
- schedule_preempt_disabled();
- }
-}
-
void __show_regs(struct pt_regs *regs, int all)
{
unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 292da13fc5a..733ca39f367 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -14,7 +14,6 @@
* This file handles the architecture-dependent parts of process handling..
*/
-#include <linux/stackprotector.h>
#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/sched.h>
@@ -32,15 +31,12 @@
#include <linux/notifier.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
-#include <linux/tick.h>
#include <linux/prctl.h>
#include <linux/uaccess.h>
#include <linux/io.h>
#include <linux/ftrace.h>
-#include <linux/cpuidle.h>
#include <asm/pgtable.h>
-#include <asm/system.h>
#include <asm/processor.h>
#include <asm/i387.h>
#include <asm/fpu-internal.h>
@@ -52,114 +48,11 @@
#include <asm/idle.h>
#include <asm/syscalls.h>
#include <asm/debugreg.h>
-#include <asm/nmi.h>
+#include <asm/switch_to.h>
asmlinkage extern void ret_from_fork(void);
DEFINE_PER_CPU(unsigned long, old_rsp);
-static DEFINE_PER_CPU(unsigned char, is_idle);
-
-static ATOMIC_NOTIFIER_HEAD(idle_notifier);
-
-void idle_notifier_register(struct notifier_block *n)
-{
- atomic_notifier_chain_register(&idle_notifier, n);
-}
-EXPORT_SYMBOL_GPL(idle_notifier_register);
-
-void idle_notifier_unregister(struct notifier_block *n)
-{
- atomic_notifier_chain_unregister(&idle_notifier, n);
-}
-EXPORT_SYMBOL_GPL(idle_notifier_unregister);
-
-void enter_idle(void)
-{
- percpu_write(is_idle, 1);
- atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
-}
-
-static void __exit_idle(void)
-{
- if (x86_test_and_clear_bit_percpu(0, is_idle) == 0)
- return;
- atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
-}
-
-/* Called from interrupts to signify idle end */
-void exit_idle(void)
-{
- /* idle loop has pid 0 */
- if (current->pid)
- return;
- __exit_idle();
-}
-
-#ifndef CONFIG_SMP
-static inline void play_dead(void)
-{
- BUG();
-}
-#endif
-
-/*
- * The idle thread. There's no useful work to be
- * done, so just try to conserve power and have a
- * low exit latency (ie sit in a loop waiting for
- * somebody to say that they'd like to reschedule)
- */
-void cpu_idle(void)
-{
- current_thread_info()->status |= TS_POLLING;
-
- /*
- * If we're the non-boot CPU, nothing set the stack canary up
- * for us. CPU0 already has it initialized but no harm in
- * doing it again. This is a good place for updating it, as
- * we wont ever return from this function (so the invalid
- * canaries already on the stack wont ever trigger).
- */
- boot_init_stack_canary();
-
- /* endless idle loop with no priority at all */
- while (1) {
- tick_nohz_idle_enter();
- while (!need_resched()) {
-
- rmb();
-
- if (cpu_is_offline(smp_processor_id()))
- play_dead();
- /*
- * Idle routines should keep interrupts disabled
- * from here on, until they go to idle.
- * Otherwise, idle callbacks can misfire.
- */
- local_touch_nmi();
- local_irq_disable();
- enter_idle();
- /* Don't trace irqs off for idle */
- stop_critical_timings();
-
- /* enter_idle() needs rcu for notifiers */
- rcu_idle_enter();
-
- if (cpuidle_idle_call())
- pm_idle();
-
- rcu_idle_exit();
- start_critical_timings();
-
- /* In many cases the interrupt that ended idle
- has already called exit_idle. But some idle
- loops can be woken up without interrupt. */
- __exit_idle();
- }
-
- tick_nohz_idle_exit();
- schedule_preempt_disabled();
- }
-}
/* Prints also some state that isn't saved in the pt_regs */
void __show_regs(struct pt_regs *regs, int all)
@@ -365,7 +258,9 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp)
{
start_thread_common(regs, new_ip, new_sp,
- __USER32_CS, __USER32_DS, __USER32_DS);
+ test_thread_flag(TIF_X32)
+ ? __USER_CS : __USER32_CS,
+ __USER_DS, __USER_DS);
}
#endif
@@ -488,6 +383,8 @@ void set_personality_64bit(void)
/* Make sure to be in 64bit mode */
clear_thread_flag(TIF_IA32);
+ clear_thread_flag(TIF_ADDR32);
+ clear_thread_flag(TIF_X32);
/* Ensure the corresponding mm is not marked. */
if (current->mm)
@@ -500,20 +397,31 @@ void set_personality_64bit(void)
current->personality &= ~READ_IMPLIES_EXEC;
}
-void set_personality_ia32(void)
+void set_personality_ia32(bool x32)
{
/* inherit personality from parent */
/* Make sure to be in 32bit mode */
- set_thread_flag(TIF_IA32);
- current->personality |= force_personality32;
+ set_thread_flag(TIF_ADDR32);
/* Mark the associated mm as containing 32-bit tasks. */
if (current->mm)
current->mm->context.ia32_compat = 1;
- /* Prepare the first "return" to user space */
- current_thread_info()->status |= TS_COMPAT;
+ if (x32) {
+ clear_thread_flag(TIF_IA32);
+ set_thread_flag(TIF_X32);
+ current->personality &= ~READ_IMPLIES_EXEC;
+ /* is_compat_task() uses the presence of the x32
+ syscall bit flag to determine compat status */
+ current_thread_info()->status &= ~TS_COMPAT;
+ } else {
+ set_thread_flag(TIF_IA32);
+ clear_thread_flag(TIF_X32);
+ current->personality |= force_personality32;
+ /* Prepare the first "return" to user space */
+ current_thread_info()->status |= TS_COMPAT;
+ }
}
unsigned long get_wchan(struct task_struct *p)
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 78f05e438be..685845cf16e 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -24,7 +24,6 @@
#include <asm/uaccess.h>
#include <asm/pgtable.h>
-#include <asm/system.h>
#include <asm/processor.h>
#include <asm/i387.h>
#include <asm/fpu-internal.h>
@@ -34,6 +33,7 @@
#include <asm/prctl.h>
#include <asm/proto.h>
#include <asm/hw_breakpoint.h>
+#include <asm/traps.h>
#include "tls.h"
@@ -1131,6 +1131,100 @@ static int genregs32_set(struct task_struct *target,
return ret;
}
+#ifdef CONFIG_X86_X32_ABI
+static long x32_arch_ptrace(struct task_struct *child,
+ compat_long_t request, compat_ulong_t caddr,
+ compat_ulong_t cdata)
+{
+ unsigned long addr = caddr;
+ unsigned long data = cdata;
+ void __user *datap = compat_ptr(data);
+ int ret;
+
+ switch (request) {
+ /* Read 32bits at location addr in the USER area. Only allow
+ to return the lower 32bits of segment and debug registers. */
+ case PTRACE_PEEKUSR: {
+ u32 tmp;
+
+ ret = -EIO;
+ if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user) ||
+ addr < offsetof(struct user_regs_struct, cs))
+ break;
+
+ tmp = 0; /* Default return condition */
+ if (addr < sizeof(struct user_regs_struct))
+ tmp = getreg(child, addr);
+ else if (addr >= offsetof(struct user, u_debugreg[0]) &&
+ addr <= offsetof(struct user, u_debugreg[7])) {
+ addr -= offsetof(struct user, u_debugreg[0]);
+ tmp = ptrace_get_debugreg(child, addr / sizeof(data));
+ }
+ ret = put_user(tmp, (__u32 __user *)datap);
+ break;
+ }
+
+ /* Write the word at location addr in the USER area. Only allow
+ to update segment and debug registers with the upper 32bits
+ zero-extended. */
+ case PTRACE_POKEUSR:
+ ret = -EIO;
+ if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user) ||
+ addr < offsetof(struct user_regs_struct, cs))
+ break;
+
+ if (addr < sizeof(struct user_regs_struct))
+ ret = putreg(child, addr, data);
+ else if (addr >= offsetof(struct user, u_debugreg[0]) &&
+ addr <= offsetof(struct user, u_debugreg[7])) {
+ addr -= offsetof(struct user, u_debugreg[0]);
+ ret = ptrace_set_debugreg(child,
+ addr / sizeof(data), data);
+ }
+ break;
+
+ case PTRACE_GETREGS: /* Get all gp regs from the child. */
+ return copy_regset_to_user(child,
+ task_user_regset_view(current),
+ REGSET_GENERAL,
+ 0, sizeof(struct user_regs_struct),
+ datap);
+
+ case PTRACE_SETREGS: /* Set all gp regs in the child. */
+ return copy_regset_from_user(child,
+ task_user_regset_view(current),
+ REGSET_GENERAL,
+ 0, sizeof(struct user_regs_struct),
+ datap);
+
+ case PTRACE_GETFPREGS: /* Get the child FPU state. */
+ return copy_regset_to_user(child,
+ task_user_regset_view(current),
+ REGSET_FP,
+ 0, sizeof(struct user_i387_struct),
+ datap);
+
+ case PTRACE_SETFPREGS: /* Set the child FPU state. */
+ return copy_regset_from_user(child,
+ task_user_regset_view(current),
+ REGSET_FP,
+ 0, sizeof(struct user_i387_struct),
+ datap);
+
+ /* normal 64bit interface to access TLS data.
+ Works just like arch_prctl, except that the arguments
+ are reversed. */
+ case PTRACE_ARCH_PRCTL:
+ return do_arch_prctl(child, data, addr);
+
+ default:
+ return compat_ptrace_request(child, request, addr, data);
+ }
+
+ return ret;
+}
+#endif
+
long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
compat_ulong_t caddr, compat_ulong_t cdata)
{
@@ -1140,6 +1234,11 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
int ret;
__u32 val;
+#ifdef CONFIG_X86_X32_ABI
+ if (!is_ia32_task())
+ return x32_arch_ptrace(child, request, caddr, cdata);
+#endif
+
switch (request) {
case PTRACE_PEEKUSR:
ret = getreg32(child, addr, &val);
@@ -1327,7 +1426,7 @@ static void fill_sigtrap_info(struct task_struct *tsk,
int error_code, int si_code,
struct siginfo *info)
{
- tsk->thread.trap_no = 1;
+ tsk->thread.trap_nr = X86_TRAP_DB;
tsk->thread.error_code = error_code;
memset(info, 0, sizeof(*info));
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 88638883176..1a290156205 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -90,7 +90,6 @@
#include <asm/processor.h>
#include <asm/bugs.h>
-#include <asm/system.h>
#include <asm/vsyscall.h>
#include <asm/cpu.h>
#include <asm/desc.h>
@@ -509,15 +508,6 @@ static void __init memblock_x86_reserve_range_setup_data(void)
#ifdef CONFIG_KEXEC
-static inline unsigned long long get_total_mem(void)
-{
- unsigned long long total;
-
- total = max_pfn - min_low_pfn;
-
- return total << PAGE_SHIFT;
-}
-
/*
* Keep the crash kernel below this limit. On 32 bits earlier kernels
* would limit the kernel to the low 512 MiB due to mapping restrictions.
@@ -536,7 +526,7 @@ static void __init reserve_crashkernel(void)
unsigned long long crash_size, crash_base;
int ret;
- total_mem = get_total_mem();
+ total_mem = memblock_phys_mem_size();
ret = parse_crashkernel(boot_command_line, total_mem,
&crash_size, &crash_base);
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 25edcfc9ba5..115eac43148 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -10,10 +10,8 @@
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/kernel.h>
-#include <linux/signal.h>
#include <linux/errno.h>
#include <linux/wait.h>
-#include <linux/ptrace.h>
#include <linux/tracehook.h>
#include <linux/unistd.h>
#include <linux/stddef.h>
@@ -27,10 +25,12 @@
#include <asm/fpu-internal.h>
#include <asm/vdso.h>
#include <asm/mce.h>
+#include <asm/sighandling.h>
#ifdef CONFIG_X86_64
#include <asm/proto.h>
#include <asm/ia32_unistd.h>
+#include <asm/sys_ia32.h>
#endif /* CONFIG_X86_64 */
#include <asm/syscall.h>
@@ -38,13 +38,6 @@
#include <asm/sigframe.h>
-#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
-
-#define __FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_OF | \
- X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \
- X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \
- X86_EFLAGS_CF)
-
#ifdef CONFIG_X86_32
# define FIX_EFLAGS (__FIX_EFLAGS | X86_EFLAGS_RF)
#else
@@ -69,9 +62,8 @@
regs->seg = GET_SEG(seg) | 3; \
} while (0)
-static int
-restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
- unsigned long *pax)
+int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
+ unsigned long *pax)
{
void __user *buf;
unsigned int tmpflags;
@@ -126,9 +118,8 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
return err;
}
-static int
-setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
- struct pt_regs *regs, unsigned long mask)
+int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
+ struct pt_regs *regs, unsigned long mask)
{
int err = 0;
@@ -160,7 +151,7 @@ setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
put_user_ex(regs->r15, &sc->r15);
#endif /* CONFIG_X86_64 */
- put_user_ex(current->thread.trap_no, &sc->trapno);
+ put_user_ex(current->thread.trap_nr, &sc->trapno);
put_user_ex(current->thread.error_code, &sc->err);
put_user_ex(regs->ip, &sc->ip);
#ifdef CONFIG_X86_32
@@ -643,6 +634,16 @@ static int signr_convert(int sig)
#define is_ia32 0
#endif /* CONFIG_IA32_EMULATION */
+#ifdef CONFIG_X86_X32_ABI
+#define is_x32 test_thread_flag(TIF_X32)
+
+static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
+ siginfo_t *info, compat_sigset_t *set,
+ struct pt_regs *regs);
+#else /* !CONFIG_X86_X32_ABI */
+#define is_x32 0
+#endif /* CONFIG_X86_X32_ABI */
+
int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
sigset_t *set, struct pt_regs *regs);
int ia32_setup_frame(int sig, struct k_sigaction *ka,
@@ -667,8 +668,14 @@ setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
ret = ia32_setup_rt_frame(usig, ka, info, set, regs);
else
ret = ia32_setup_frame(usig, ka, set, regs);
- } else
+#ifdef CONFIG_X86_X32_ABI
+ } else if (is_x32) {
+ ret = x32_setup_rt_frame(usig, ka, info,
+ (compat_sigset_t *)set, regs);
+#endif
+ } else {
ret = __setup_rt_frame(sig, ka, info, set, regs);
+ }
if (ret) {
force_sigsegv(sig, current);
@@ -851,3 +858,102 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
force_sig(SIGSEGV, me);
}
+
+#ifdef CONFIG_X86_X32_ABI
+static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
+ siginfo_t *info, compat_sigset_t *set,
+ struct pt_regs *regs)
+{
+ struct rt_sigframe_x32 __user *frame;
+ void __user *restorer;
+ int err = 0;
+ void __user *fpstate = NULL;
+
+ frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
+
+ if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+ return -EFAULT;
+
+ if (ka->sa.sa_flags & SA_SIGINFO) {
+ if (copy_siginfo_to_user32(&frame->info, info))
+ return -EFAULT;
+ }
+
+ put_user_try {
+ /* Create the ucontext. */
+ if (cpu_has_xsave)
+ put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
+ else
+ put_user_ex(0, &frame->uc.uc_flags);
+ put_user_ex(0, &frame->uc.uc_link);
+ put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+ put_user_ex(sas_ss_flags(regs->sp),
+ &frame->uc.uc_stack.ss_flags);
+ put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
+ put_user_ex(0, &frame->uc.uc__pad0);
+ err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
+ regs, set->sig[0]);
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+
+ if (ka->sa.sa_flags & SA_RESTORER) {
+ restorer = ka->sa.sa_restorer;
+ } else {
+ /* could use a vstub here */
+ restorer = NULL;
+ err |= -EFAULT;
+ }
+ put_user_ex(restorer, &frame->pretcode);
+ } put_user_catch(err);
+
+ if (err)
+ return -EFAULT;
+
+ /* Set up registers for signal handler */
+ regs->sp = (unsigned long) frame;
+ regs->ip = (unsigned long) ka->sa.sa_handler;
+
+ /* We use the x32 calling convention here... */
+ regs->di = sig;
+ regs->si = (unsigned long) &frame->info;
+ regs->dx = (unsigned long) &frame->uc;
+
+ loadsegment(ds, __USER_DS);
+ loadsegment(es, __USER_DS);
+
+ regs->cs = __USER_CS;
+ regs->ss = __USER_DS;
+
+ return 0;
+}
+
+asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs)
+{
+ struct rt_sigframe_x32 __user *frame;
+ sigset_t set;
+ unsigned long ax;
+ struct pt_regs tregs;
+
+ frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8);
+
+ if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
+ goto badframe;
+ if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+ goto badframe;
+
+ sigdelsetmask(&set, ~_BLOCKABLE);
+ set_current_blocked(&set);
+
+ if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax))
+ goto badframe;
+
+ tregs = *regs;
+ if (sys32_sigaltstack(&frame->uc.uc_stack, NULL, &tregs) == -EFAULT)
+ goto badframe;
+
+ return ax;
+
+badframe:
+ signal_fault(regs, frame, "x32 rt_sigreturn");
+ return 0;
+}
+#endif
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index e578a79a309..6e1e406038c 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -50,6 +50,7 @@
#include <linux/tboot.h>
#include <linux/stackprotector.h>
#include <linux/gfp.h>
+#include <linux/cpuidle.h>
#include <asm/acpi.h>
#include <asm/desc.h>
@@ -219,14 +220,9 @@ static void __cpuinit smp_callin(void)
* Update loops_per_jiffy in cpu_data. Previous call to
* smp_store_cpu_info() stored a value that is close but not as
* accurate as the value just calculated.
- *
- * Need to enable IRQs because it can take longer and then
- * the NMI watchdog might kill us.
*/
- local_irq_enable();
calibrate_delay();
cpu_data(cpuid).loops_per_jiffy = loops_per_jiffy;
- local_irq_disable();
pr_debug("Stack at about %p\n", &cpuid);
/*
@@ -255,6 +251,7 @@ notrace static void __cpuinit start_secondary(void *unused)
* most necessary things.
*/
cpu_init();
+ x86_cpuinit.early_percpu_clock_init();
preempt_disable();
smp_callin();
@@ -1408,7 +1405,8 @@ void native_play_dead(void)
tboot_shutdown(TB_SHUTDOWN_WFS);
mwait_play_dead(); /* Only returns on failure */
- hlt_play_dead();
+ if (cpuidle_play_dead())
+ hlt_play_dead();
}
#else /* ... !CONFIG_HOTPLUG_CPU */
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index ef59642ff1b..b4d3c3927dd 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -98,7 +98,7 @@ out:
static void find_start_end(unsigned long flags, unsigned long *begin,
unsigned long *end)
{
- if (!test_thread_flag(TIF_IA32) && (flags & MAP_32BIT)) {
+ if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT)) {
unsigned long new_begin;
/* This is usually used needed to map code in small
model, so it needs to be in the first 31bit. Limit
@@ -144,7 +144,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
(!vma || addr + len <= vma->vm_start))
return addr;
}
- if (((flags & MAP_32BIT) || test_thread_flag(TIF_IA32))
+ if (((flags & MAP_32BIT) || test_thread_flag(TIF_ADDR32))
&& len <= mm->cached_hole_size) {
mm->cached_hole_size = 0;
mm->free_area_cache = begin;
@@ -205,7 +205,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
return addr;
/* for MAP_32BIT mappings we force the legact mmap base */
- if (!test_thread_flag(TIF_IA32) && (flags & MAP_32BIT))
+ if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT))
goto bottomup;
/* requesting a specific address */
diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/kernel/syscall_64.c
index 7ac7943be02..5c7f8c20da7 100644
--- a/arch/x86/kernel/syscall_64.c
+++ b/arch/x86/kernel/syscall_64.c
@@ -5,6 +5,14 @@
#include <linux/cache.h>
#include <asm/asm-offsets.h>
+#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
+
+#ifdef CONFIG_X86_X32_ABI
+# define __SYSCALL_X32(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
+#else
+# define __SYSCALL_X32(nr, sym, compat) /* nothing */
+#endif
+
#define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ;
#include <asm/syscalls_64.h>
#undef __SYSCALL_64
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index e2410e27f97..6410744ac5c 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -272,7 +272,7 @@ static void tboot_copy_fadt(const struct acpi_table_fadt *fadt)
offsetof(struct acpi_table_facs, firmware_waking_vector);
}
-void tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control)
+static int tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control)
{
static u32 acpi_shutdown_map[ACPI_S_STATE_COUNT] = {
/* S0,1,2: */ -1, -1, -1,
@@ -281,7 +281,7 @@ void tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control)
/* S5: */ TB_SHUTDOWN_S5 };
if (!tboot_enabled())
- return;
+ return 0;
tboot_copy_fadt(&acpi_gbl_FADT);
tboot->acpi_sinfo.pm1a_cnt_val = pm1a_control;
@@ -292,10 +292,11 @@ void tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control)
if (sleep_state >= ACPI_S_STATE_COUNT ||
acpi_shutdown_map[sleep_state] == -1) {
pr_warning("unsupported sleep state 0x%x\n", sleep_state);
- return;
+ return -1;
}
tboot_shutdown(acpi_shutdown_map[sleep_state]);
+ return 0;
}
static atomic_t ap_wfs_count;
@@ -345,6 +346,8 @@ static __init int tboot_late_init(void)
atomic_set(&ap_wfs_count, 0);
register_hotcpu_notifier(&tboot_cpu_notifier);
+
+ acpi_os_set_prepare_sleep(&tboot_sleep);
return 0;
}
diff --git a/arch/x86/kernel/tce_64.c b/arch/x86/kernel/tce_64.c
index 9e540fee700..ab40954e113 100644
--- a/arch/x86/kernel/tce_64.c
+++ b/arch/x86/kernel/tce_64.c
@@ -34,6 +34,7 @@
#include <asm/tce.h>
#include <asm/calgary.h>
#include <asm/proto.h>
+#include <asm/cacheflush.h>
/* flush a tce at 'tceaddr' to main memory */
static inline void flush_tce(void* tceaddr)
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 6bb7b8579e7..9d9d2f9e77a 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -6,7 +6,6 @@
#include <asm/uaccess.h>
#include <asm/desc.h>
-#include <asm/system.h>
#include <asm/ldt.h>
#include <asm/processor.h>
#include <asm/proto.h>
@@ -163,7 +162,7 @@ int regset_tls_get(struct task_struct *target, const struct user_regset *regset,
{
const struct desc_struct *tls;
- if (pos > GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
+ if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
(pos % sizeof(struct user_desc)) != 0 ||
(count % sizeof(struct user_desc)) != 0)
return -EINVAL;
@@ -198,7 +197,7 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset,
struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES];
const struct user_desc *info;
- if (pos > GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
+ if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
(pos % sizeof(struct user_desc)) != 0 ||
(count % sizeof(struct user_desc)) != 0)
return -EINVAL;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index ec61d4c1b93..ff9281f1602 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -50,7 +50,6 @@
#include <asm/processor.h>
#include <asm/debugreg.h>
#include <linux/atomic.h>
-#include <asm/system.h>
#include <asm/traps.h>
#include <asm/desc.h>
#include <asm/i387.h>
@@ -120,7 +119,7 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
* traps 0, 1, 3, 4, and 5 should be forwarded to vm86.
* On nmi (interrupt 2), do_trap should not be called.
*/
- if (trapnr < 6)
+ if (trapnr < X86_TRAP_UD)
goto vm86_trap;
goto trap_signal;
}
@@ -133,7 +132,7 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
trap_signal:
#endif
/*
- * We want error_code and trap_no set for userspace faults and
+ * We want error_code and trap_nr set for userspace faults and
* kernelspace faults which result in die(), but not
* kernelspace faults which are fixed up. die() gives the
* process no chance to handle the signal and notice the
@@ -142,7 +141,7 @@ trap_signal:
* delivered, faults. See also do_general_protection below.
*/
tsk->thread.error_code = error_code;
- tsk->thread.trap_no = trapnr;
+ tsk->thread.trap_nr = trapnr;
#ifdef CONFIG_X86_64
if (show_unhandled_signals && unhandled_signal(tsk, signr) &&
@@ -165,7 +164,7 @@ trap_signal:
kernel_trap:
if (!fixup_exception(regs)) {
tsk->thread.error_code = error_code;
- tsk->thread.trap_no = trapnr;
+ tsk->thread.trap_nr = trapnr;
die(str, regs, error_code);
}
return;
@@ -204,27 +203,31 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \
do_trap(trapnr, signr, str, regs, error_code, &info); \
}
-DO_ERROR_INFO(0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->ip)
-DO_ERROR(4, SIGSEGV, "overflow", overflow)
-DO_ERROR(5, SIGSEGV, "bounds", bounds)
-DO_ERROR_INFO(6, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->ip)
-DO_ERROR(9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun)
-DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS)
-DO_ERROR(11, SIGBUS, "segment not present", segment_not_present)
+DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV,
+ regs->ip)
+DO_ERROR(X86_TRAP_OF, SIGSEGV, "overflow", overflow)
+DO_ERROR(X86_TRAP_BR, SIGSEGV, "bounds", bounds)
+DO_ERROR_INFO(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN,
+ regs->ip)
+DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun",
+ coprocessor_segment_overrun)
+DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS)
+DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present)
#ifdef CONFIG_X86_32
-DO_ERROR(12, SIGBUS, "stack segment", stack_segment)
+DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment)
#endif
-DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0)
+DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check,
+ BUS_ADRALN, 0)
#ifdef CONFIG_X86_64
/* Runs on IST stack */
dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code)
{
if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
- 12, SIGBUS) == NOTIFY_STOP)
+ X86_TRAP_SS, SIGBUS) == NOTIFY_STOP)
return;
preempt_conditional_sti(regs);
- do_trap(12, SIGBUS, "stack segment", regs, error_code, NULL);
+ do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
preempt_conditional_cli(regs);
}
@@ -234,10 +237,10 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
struct task_struct *tsk = current;
/* Return not checked because double check cannot be ignored */
- notify_die(DIE_TRAP, str, regs, error_code, 8, SIGSEGV);
+ notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
tsk->thread.error_code = error_code;
- tsk->thread.trap_no = 8;
+ tsk->thread.trap_nr = X86_TRAP_DF;
/*
* This is always a kernel trap and never fixable (and thus must
@@ -265,7 +268,7 @@ do_general_protection(struct pt_regs *regs, long error_code)
goto gp_in_kernel;
tsk->thread.error_code = error_code;
- tsk->thread.trap_no = 13;
+ tsk->thread.trap_nr = X86_TRAP_GP;
if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
printk_ratelimit()) {
@@ -292,9 +295,9 @@ gp_in_kernel:
return;
tsk->thread.error_code = error_code;
- tsk->thread.trap_no = 13;
- if (notify_die(DIE_GPF, "general protection fault", regs,
- error_code, 13, SIGSEGV) == NOTIFY_STOP)
+ tsk->thread.trap_nr = X86_TRAP_GP;
+ if (notify_die(DIE_GPF, "general protection fault", regs, error_code,
+ X86_TRAP_GP, SIGSEGV) == NOTIFY_STOP)
return;
die("general protection fault", regs, error_code);
}
@@ -303,13 +306,13 @@ gp_in_kernel:
dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code)
{
#ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
- if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP)
- == NOTIFY_STOP)
+ if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
+ SIGTRAP) == NOTIFY_STOP)
return;
#endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */
- if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP)
- == NOTIFY_STOP)
+ if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
+ SIGTRAP) == NOTIFY_STOP)
return;
/*
@@ -318,7 +321,7 @@ dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code)
*/
debug_stack_usage_inc();
preempt_conditional_sti(regs);
- do_trap(3, SIGTRAP, "int3", regs, error_code, NULL);
+ do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
preempt_conditional_cli(regs);
debug_stack_usage_dec();
}
@@ -423,8 +426,8 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
preempt_conditional_sti(regs);
if (regs->flags & X86_VM_MASK) {
- handle_vm86_trap((struct kernel_vm86_regs *) regs,
- error_code, 1);
+ handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code,
+ X86_TRAP_DB);
preempt_conditional_cli(regs);
debug_stack_usage_dec();
return;
@@ -461,7 +464,8 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr)
struct task_struct *task = current;
siginfo_t info;
unsigned short err;
- char *str = (trapnr == 16) ? "fpu exception" : "simd exception";
+ char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" :
+ "simd exception";
if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, SIGFPE) == NOTIFY_STOP)
return;
@@ -471,7 +475,7 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr)
{
if (!fixup_exception(regs)) {
task->thread.error_code = error_code;
- task->thread.trap_no = trapnr;
+ task->thread.trap_nr = trapnr;
die(str, regs, error_code);
}
return;
@@ -481,12 +485,12 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr)
* Save the info for the exception handler and clear the error.
*/
save_init_fpu(task);
- task->thread.trap_no = trapnr;
+ task->thread.trap_nr = trapnr;
task->thread.error_code = error_code;
info.si_signo = SIGFPE;
info.si_errno = 0;
info.si_addr = (void __user *)regs->ip;
- if (trapnr == 16) {
+ if (trapnr == X86_TRAP_MF) {
unsigned short cwd, swd;
/*
* (~cwd & swd) will mask out exceptions that are not set to unmasked
@@ -530,10 +534,11 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr)
info.si_code = FPE_FLTRES;
} else {
/*
- * If we're using IRQ 13, or supposedly even some trap 16
- * implementations, it's possible we get a spurious trap...
+ * If we're using IRQ 13, or supposedly even some trap
+ * X86_TRAP_MF implementations, it's possible
+ * we get a spurious trap, which is not an error.
*/
- return; /* Spurious trap, no error */
+ return;
}
force_sig_info(SIGFPE, &info, task);
}
@@ -544,13 +549,13 @@ dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code)
ignore_fpu_irq = 1;
#endif
- math_error(regs, error_code, 16);
+ math_error(regs, error_code, X86_TRAP_MF);
}
dotraplinkage void
do_simd_coprocessor_error(struct pt_regs *regs, long error_code)
{
- math_error(regs, error_code, 19);
+ math_error(regs, error_code, X86_TRAP_XF);
}
dotraplinkage void
@@ -644,20 +649,21 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
info.si_errno = 0;
info.si_code = ILL_BADSTK;
info.si_addr = NULL;
- if (notify_die(DIE_TRAP, "iret exception",
- regs, error_code, 32, SIGILL) == NOTIFY_STOP)
+ if (notify_die(DIE_TRAP, "iret exception", regs, error_code,
+ X86_TRAP_IRET, SIGILL) == NOTIFY_STOP)
return;
- do_trap(32, SIGILL, "iret exception", regs, error_code, &info);
+ do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code,
+ &info);
}
#endif
/* Set of traps needed for early debugging. */
void __init early_trap_init(void)
{
- set_intr_gate_ist(1, &debug, DEBUG_STACK);
+ set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK);
/* int3 can be called from all */
- set_system_intr_gate_ist(3, &int3, DEBUG_STACK);
- set_intr_gate(14, &page_fault);
+ set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK);
+ set_intr_gate(X86_TRAP_PF, &page_fault);
load_idt(&idt_descr);
}
@@ -673,30 +679,30 @@ void __init trap_init(void)
early_iounmap(p, 4);
#endif
- set_intr_gate(0, &divide_error);
- set_intr_gate_ist(2, &nmi, NMI_STACK);
+ set_intr_gate(X86_TRAP_DE, &divide_error);
+ set_intr_gate_ist(X86_TRAP_NMI, &nmi, NMI_STACK);
/* int4 can be called from all */
- set_system_intr_gate(4, &overflow);
- set_intr_gate(5, &bounds);
- set_intr_gate(6, &invalid_op);
- set_intr_gate(7, &device_not_available);
+ set_system_intr_gate(X86_TRAP_OF, &overflow);
+ set_intr_gate(X86_TRAP_BR, &bounds);
+ set_intr_gate(X86_TRAP_UD, &invalid_op);
+ set_intr_gate(X86_TRAP_NM, &device_not_available);
#ifdef CONFIG_X86_32
- set_task_gate(8, GDT_ENTRY_DOUBLEFAULT_TSS);
+ set_task_gate(X86_TRAP_DF, GDT_ENTRY_DOUBLEFAULT_TSS);
#else
- set_intr_gate_ist(8, &double_fault, DOUBLEFAULT_STACK);
+ set_intr_gate_ist(X86_TRAP_DF, &double_fault, DOUBLEFAULT_STACK);
#endif
- set_intr_gate(9, &coprocessor_segment_overrun);
- set_intr_gate(10, &invalid_TSS);
- set_intr_gate(11, &segment_not_present);
- set_intr_gate_ist(12, &stack_segment, STACKFAULT_STACK);
- set_intr_gate(13, &general_protection);
- set_intr_gate(15, &spurious_interrupt_bug);
- set_intr_gate(16, &coprocessor_error);
- set_intr_gate(17, &alignment_check);
+ set_intr_gate(X86_TRAP_OLD_MF, &coprocessor_segment_overrun);
+ set_intr_gate(X86_TRAP_TS, &invalid_TSS);
+ set_intr_gate(X86_TRAP_NP, &segment_not_present);
+ set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK);
+ set_intr_gate(X86_TRAP_GP, &general_protection);
+ set_intr_gate(X86_TRAP_SPURIOUS, &spurious_interrupt_bug);
+ set_intr_gate(X86_TRAP_MF, &coprocessor_error);
+ set_intr_gate(X86_TRAP_AC, &alignment_check);
#ifdef CONFIG_X86_MCE
- set_intr_gate_ist(18, &machine_check, MCE_STACK);
+ set_intr_gate_ist(X86_TRAP_MC, &machine_check, MCE_STACK);
#endif
- set_intr_gate(19, &simd_coprocessor_error);
+ set_intr_gate(X86_TRAP_XF, &simd_coprocessor_error);
/* Reserve all the builtin and the syscall vector: */
for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++)
@@ -721,7 +727,7 @@ void __init trap_init(void)
#ifdef CONFIG_X86_64
memcpy(&nmi_idt_table, &idt_table, IDT_ENTRIES * 16);
- set_nmi_gate(1, &debug);
- set_nmi_gate(3, &int3);
+ set_nmi_gate(X86_TRAP_DB, &debug);
+ set_nmi_gate(X86_TRAP_BP, &int3);
#endif
}
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 183c5925a9f..fc0a147e372 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -630,7 +630,7 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
static unsigned long long cyc2ns_suspend;
-void save_sched_clock_state(void)
+void tsc_save_sched_clock_state(void)
{
if (!sched_clock_stable)
return;
@@ -646,7 +646,7 @@ void save_sched_clock_state(void)
* that sched_clock() continues from the point where it was left off during
* suspend.
*/
-void restore_sched_clock_state(void)
+void tsc_restore_sched_clock_state(void)
{
unsigned long long offset;
unsigned long flags;
@@ -933,6 +933,16 @@ static int __init init_tsc_clocksource(void)
clocksource_tsc.rating = 0;
clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
}
+
+ /*
+ * Trust the results of the earlier calibration on systems
+ * exporting a reliable TSC.
+ */
+ if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) {
+ clocksource_register_khz(&clocksource_tsc, tsc_khz);
+ return 0;
+ }
+
schedule_delayed_work(&tsc_irqwork, 0);
return 0;
}
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 328cb37bb82..255f58ae71e 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -569,7 +569,7 @@ int handle_vm86_trap(struct kernel_vm86_regs *regs, long error_code, int trapno)
}
if (trapno != 1)
return 1; /* we let this handle by the calling routine */
- current->thread.trap_no = trapno;
+ current->thread.trap_nr = trapno;
current->thread.error_code = error_code;
force_sig(SIGTRAP, current);
return 0;
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index b07ba939356..f386dc49f98 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -52,10 +52,7 @@
#include "vsyscall_trace.h"
DEFINE_VVAR(int, vgetcpu_mode);
-DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data) =
-{
- .lock = __SEQLOCK_UNLOCKED(__vsyscall_gtod_data.lock),
-};
+DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data);
static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE;
@@ -80,20 +77,15 @@ early_param("vsyscall", vsyscall_setup);
void update_vsyscall_tz(void)
{
- unsigned long flags;
-
- write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags);
- /* sys_tz has changed */
vsyscall_gtod_data.sys_tz = sys_tz;
- write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
}
void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
struct clocksource *clock, u32 mult)
{
- unsigned long flags;
+ struct timespec monotonic;
- write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags);
+ write_seqcount_begin(&vsyscall_gtod_data.seq);
/* copy vsyscall data */
vsyscall_gtod_data.clock.vclock_mode = clock->archdata.vclock_mode;
@@ -101,12 +93,19 @@ void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
vsyscall_gtod_data.clock.mask = clock->mask;
vsyscall_gtod_data.clock.mult = mult;
vsyscall_gtod_data.clock.shift = clock->shift;
+
vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec;
vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec;
- vsyscall_gtod_data.wall_to_monotonic = *wtm;
+
+ monotonic = timespec_add(*wall_time, *wtm);
+ vsyscall_gtod_data.monotonic_time_sec = monotonic.tv_sec;
+ vsyscall_gtod_data.monotonic_time_nsec = monotonic.tv_nsec;
+
vsyscall_gtod_data.wall_time_coarse = __current_kernel_time();
+ vsyscall_gtod_data.monotonic_time_coarse =
+ timespec_add(vsyscall_gtod_data.wall_time_coarse, *wtm);
- write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
+ write_seqcount_end(&vsyscall_gtod_data.seq);
}
static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
@@ -153,7 +152,7 @@ static bool write_ok_or_segv(unsigned long ptr, size_t size)
thread->error_code = 6; /* user fault, no page, write */
thread->cr2 = ptr;
- thread->trap_no = 14;
+ thread->trap_nr = X86_TRAP_PF;
memset(&info, 0, sizeof(info));
info.si_signo = SIGSEGV;
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 947a06ccc67..e9f265fd79a 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -91,6 +91,7 @@ struct x86_init_ops x86_init __initdata = {
};
struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = {
+ .early_percpu_clock_init = x86_init_noop,
.setup_percpu_clockev = setup_secondary_APIC_clock,
.fixup_cpu_id = x86_default_fixup_cpu_id,
};
@@ -107,7 +108,9 @@ struct x86_platform_ops x86_platform = {
.is_untracked_pat_range = is_ISA_range,
.nmi_init = default_nmi_init,
.get_nmi_reason = default_get_nmi_reason,
- .i8042_detect = default_i8042_detect
+ .i8042_detect = default_i8042_detect,
+ .save_sched_clock_state = tsc_save_sched_clock_state,
+ .restore_sched_clock_state = tsc_restore_sched_clock_state,
};
EXPORT_SYMBOL_GPL(x86_platform);