* 'x86-vdso-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86-64, vdso: Do not allocate memory for the vDSO
clocksource: Change __ARCH_HAS_CLOCKSOURCE_DATA to a CONFIG option
x86, vdso: Drop now wrong comment
Document the vDSO and add a reference parser
ia64: Replace clocksource.fsys_mmio with generic arch data
x86-64: Move vread_tsc and vread_hpet into the vDSO
clocksource: Replace vread with generic arch data
x86-64: Add --no-undefined to vDSO build
x86-64: Allow alternative patching in the vDSO
x86: Make alternative instruction pointers relative
x86-64: Improve vsyscall emulation CS and RIP handling
x86-64: Emulate legacy vsyscalls
x86-64: Fill unused parts of the vsyscall page with 0xcc
x86-64: Remove vsyscall number 3 (venosys)
x86-64: Map the HPET NX
x86-64: Remove kernel.vsyscall64 sysctl
x86-64: Give vvars their own page
x86-64: Document some of entry_64.S
x86-64: Fix alignment of jiffies variable
bool
default y
+ config ARCH_CLOCKSOURCE_DATA
+ def_bool y
+
config SCHED_OMIT_FRAME_POINTER
bool
default y
source "drivers/pcmcia/Kconfig"
-config DMAR
- bool "Support for DMA Remapping Devices (EXPERIMENTAL)"
- depends on IA64_GENERIC && ACPI && EXPERIMENTAL
- help
- DMA remapping (DMAR) devices support enables independent address
- translations for Direct Memory Access (DMA) from devices.
- These DMA remapping devices are reported via ACPI tables
- and include PCI device scope covered by these DMA
- remapping devices.
-
-config DMAR_DEFAULT_ON
- def_bool y
- prompt "Enable DMA Remapping Devices by default"
- depends on DMAR
- help
- Selecting this option will enable a DMAR device at boot time if
- one is found. If this option is not selected, DMAR support can
- be enabled by passing intel_iommu=on to the kernel. It is
- recommended you say N here while the DMAR code remains
- experimental.
-
endmenu
endif
config IOMMU_HELPER
def_bool (IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB || IA64_GENERIC || SWIOTLB)
-
-config IOMMU_API
- def_bool (DMAR)
select HAVE_UNSTABLE_SCHED_CLOCK
select HAVE_IDE
select HAVE_OPROFILE
+ select HAVE_PCSPKR_PLATFORM
select HAVE_PERF_EVENTS
select HAVE_IRQ_WORK
select HAVE_IOREMAP_PROT
select IRQ_FORCED_THREADING
select USE_GENERIC_SMP_HELPERS if SMP
select HAVE_BPF_JIT if (X86_64 && NET)
+ select CLKEVT_I8253
config INSTRUCTION_DECODER
def_bool (KPROBES || PERF_EVENTS)
config GENERIC_CLOCKEVENTS
def_bool y
+ config ARCH_CLOCKSOURCE_DATA
+ def_bool y
+ depends on X86_64
+
config GENERIC_CLOCKEVENTS_BROADCAST
def_bool y
depends on X86_64 || (X86_32 && X86_LOCAL_APIC)
Calgary anyway, pass 'iommu=calgary' on the kernel command line.
If unsure, say Y.
-config AMD_IOMMU
- bool "AMD IOMMU support"
- select SWIOTLB
- select PCI_MSI
- select PCI_IOV
- depends on X86_64 && PCI && ACPI
- ---help---
- With this option you can enable support for AMD IOMMU hardware in
- your system. An IOMMU is a hardware component which provides
- remapping of DMA memory accesses from devices. With an AMD IOMMU you
- can isolate the the DMA memory of different devices and protect the
- system from misbehaving device drivers or hardware.
-
- You can find out if your system has an AMD IOMMU if you look into
- your BIOS for an option to enable it or if you have an IVRS ACPI
- table.
-
-config AMD_IOMMU_STATS
- bool "Export AMD IOMMU statistics to debugfs"
- depends on AMD_IOMMU
- select DEBUG_FS
- ---help---
- This option enables code in the AMD IOMMU driver to collect various
- statistics about whats happening in the driver and exports that
- information to userspace via debugfs.
- If unsure, say N.
-
# need this always selected by IOMMU for the VIA workaround
config SWIOTLB
def_bool y if X86_64
config IOMMU_HELPER
def_bool (CALGARY_IOMMU || GART_IOMMU || SWIOTLB || AMD_IOMMU)
-config IOMMU_API
- def_bool (AMD_IOMMU || DMAR)
-
config MAXSMP
bool "Enable Maximum number of SMP Processors and NUMA Nodes"
depends on X86_64 && SMP && DEBUG_KERNEL && EXPERIMENTAL
config AMD_NUMA
def_bool y
prompt "Old style AMD Opteron NUMA detection"
- depends on NUMA && PCI
+ depends on X86_64 && NUMA && PCI
---help---
Enable AMD NUMA node topology detection. You should say Y here if
you have a multi processor AMD system. This uses an old method to
You should say N unless you know you need this.
-config DMAR
- bool "Support for DMA Remapping Devices (EXPERIMENTAL)"
- depends on PCI_MSI && ACPI && EXPERIMENTAL
- help
- DMA remapping (DMAR) devices support enables independent address
- translations for Direct Memory Access (DMA) from devices.
- These DMA remapping devices are reported via ACPI tables
- and include PCI device scope covered by these DMA
- remapping devices.
-
-config DMAR_DEFAULT_ON
- def_bool y
- prompt "Enable DMA Remapping Devices by default"
- depends on DMAR
- help
- Selecting this option will enable a DMAR device at boot time if
- one is found. If this option is not selected, DMAR support can
- be enabled by passing intel_iommu=on to the kernel. It is
- recommended you say N here while the DMAR code remains
- experimental.
-
-config DMAR_BROKEN_GFX_WA
- bool "Workaround broken graphics drivers (going away soon)"
- depends on DMAR && BROKEN
- ---help---
- Current Graphics drivers tend to use physical address
- for DMA and avoid using DMA APIs. Setting this config
- option permits the IOMMU driver to set a unity map for
- all the OS-visible memory. Hence the driver can continue
- to use physical addresses for DMA, at least until this
- option is removed in the 2.6.32 kernel.
-
-config DMAR_FLOPPY_WA
- def_bool y
- depends on DMAR
- ---help---
- Floppy disk drivers are known to bypass DMA API calls
- thereby failing to work when IOMMU is enabled. This
- workaround will setup a 1:1 mapping for the first
- 16MiB to make floppy (an ISA device) work.
-
-config INTR_REMAP
- bool "Support for Interrupt Remapping (EXPERIMENTAL)"
- depends on X86_64 && X86_IO_APIC && PCI_MSI && ACPI && EXPERIMENTAL
- ---help---
- Supports Interrupt remapping for IO-APIC and MSI devices.
- To use x2apic mode in the CPU's which support x2APIC enhancements or
- to support platforms with CPU's having > 8 bit APIC ID, say Y.
-
source "drivers/pci/pcie/Kconfig"
source "drivers/pci/Kconfig"
* Vectors 0 ... 31 : system traps and exceptions - hardcoded events
* Vectors 32 ... 127 : device interrupts
* Vector 128 : legacy int80 syscall interface
- * Vectors 129 ... INVALIDATE_TLB_VECTOR_START-1 : device interrupts
+ * Vector 204 : legacy x86_64 vsyscall emulation
+ * Vectors 129 ... INVALIDATE_TLB_VECTOR_START-1 except 204 : device interrupts
* Vectors INVALIDATE_TLB_VECTOR_START ... 255 : special interrupts
*
* 64-bit x86 has per CPU IDT tables, 32-bit has one shared IDT table.
#ifdef CONFIG_X86_32
# define SYSCALL_VECTOR 0x80
#endif
+ #ifdef CONFIG_X86_64
+ # define VSYSCALL_EMU_VECTOR 0xcc
+ #endif
/*
* Vectors 0x30-0x3f are used for ISA interrupts.
#define UV_BAU_MESSAGE 0xf5
-/*
- * Self IPI vector for machine checks
- */
-#define MCE_SELF_VECTOR 0xf4
-
/* Xen vector callback to receive events in a HVM domain */
#define XEN_HVM_EVTCHN_CALLBACK 0xf3
nostackp := $(call cc-option, -fno-stack-protector)
CFLAGS_vsyscall_64.o := $(PROFILING) -g0 $(nostackp)
CFLAGS_hpet.o := $(nostackp)
- CFLAGS_vread_tsc_64.o := $(nostackp)
CFLAGS_paravirt.o := $(nostackp)
GCOV_PROFILE_vsyscall_64.o := n
GCOV_PROFILE_hpet.o := n
GCOV_PROFILE_tsc.o := n
- GCOV_PROFILE_vread_tsc_64.o := n
GCOV_PROFILE_paravirt.o := n
- # vread_tsc_64 is hot and should be fully optimized:
- CFLAGS_REMOVE_vread_tsc_64.o = -pg -fno-optimize-sibling-calls
-
obj-y := process_$(BITS).o signal.o entry_$(BITS).o
obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
obj-y += time.o ioport.o ldt.o dumpstack.o
obj-y += probe_roms.o
obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o
obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o
- obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o vread_tsc_64.o
+ obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o
+ obj-$(CONFIG_X86_64) += vsyscall_emu_64.o
obj-y += bootflag.o e820.o
obj-y += pci-dma.o quirks.o topology.o kdebugfs.o
obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o
obj-$(CONFIG_GART_IOMMU) += amd_gart_64.o aperture_64.o
obj-$(CONFIG_CALGARY_IOMMU) += pci-calgary_64.o tce_64.o
- obj-$(CONFIG_AMD_IOMMU) += amd_iommu_init.o amd_iommu.o
obj-$(CONFIG_PCI_MMCONFIG) += mmconf-fam10h_64.o
obj-y += vsmp_64.o
/*
* entry.S contains the system-call and fault low-level handling routines.
*
+ * Some of this is documented in Documentation/x86/entry_64.txt
+ *
* NOTE: This code handles signal-recognition, which happens every time
* after an interrupt and after each system call.
*
.endm
/* save partial stack frame */
- .pushsection .kprobes.text, "ax"
-ENTRY(save_args)
- XCPT_FRAME
+ .macro SAVE_ARGS_IRQ
cld
- /*
- * start from rbp in pt_regs and jump over
- * return address.
- */
- movq_cfi rdi, RDI+8-RBP
- movq_cfi rsi, RSI+8-RBP
- movq_cfi rdx, RDX+8-RBP
- movq_cfi rcx, RCX+8-RBP
- movq_cfi rax, RAX+8-RBP
- movq_cfi r8, R8+8-RBP
- movq_cfi r9, R9+8-RBP
- movq_cfi r10, R10+8-RBP
- movq_cfi r11, R11+8-RBP
-
- leaq -RBP+8(%rsp),%rdi /* arg1 for handler */
- movq_cfi rbp, 8 /* push %rbp */
- leaq 8(%rsp), %rbp /* mov %rsp, %ebp */
+ /* start from rbp in pt_regs and jump over */
+ movq_cfi rdi, RDI-RBP
+ movq_cfi rsi, RSI-RBP
+ movq_cfi rdx, RDX-RBP
+ movq_cfi rcx, RCX-RBP
+ movq_cfi rax, RAX-RBP
+ movq_cfi r8, R8-RBP
+ movq_cfi r9, R9-RBP
+ movq_cfi r10, R10-RBP
+ movq_cfi r11, R11-RBP
+
+ /* Save rbp so that we can unwind from get_irq_regs() */
+ movq_cfi rbp, 0
+
+ /* Save previous stack value */
+ movq %rsp, %rsi
+
+ leaq -RBP(%rsp),%rdi /* arg1 for handler */
testl $3, CS(%rdi)
je 1f
SWAPGS
*/
1: incl PER_CPU_VAR(irq_count)
jne 2f
- popq_cfi %rax /* move return address... */
mov PER_CPU_VAR(irq_stack_ptr),%rsp
EMPTY_FRAME 0
- pushq_cfi %rbp /* backlink for unwinder */
- pushq_cfi %rax /* ... to the new stack */
- /*
- * We entered an interrupt context - irqs are off:
- */
-2: TRACE_IRQS_OFF
- ret
- CFI_ENDPROC
-END(save_args)
- .popsection
+
+2: /* Store previous stack value */
+ pushq %rsi
+ /* We entered an interrupt context - irqs are off: */
+ TRACE_IRQS_OFF
+ .endm
ENTRY(save_rest)
PARTIAL_FRAME 1 REST_SKIP+8
* and short:
*/
ENABLE_INTERRUPTS(CLBR_NONE)
- SAVE_ARGS 8,1
+ SAVE_ARGS 8,0
movq %rax,ORIG_RAX-ARGOFFSET(%rsp)
movq %rcx,RIP-ARGOFFSET(%rsp)
CFI_REL_OFFSET rip,RIP-ARGOFFSET
TRACE_IRQS_ON
movq RIP-ARGOFFSET(%rsp),%rcx
CFI_REGISTER rip,rcx
- RESTORE_ARGS 0,-ARG_SKIP,1
+ RESTORE_ARGS 1,-ARG_SKIP,0
/*CFI_REGISTER rflags,r11*/
movq PER_CPU_VAR(old_rsp), %rsp
USERGS_SYSRET64
/* reserve pt_regs for scratch regs and rbp */
subq $ORIG_RAX-RBP, %rsp
CFI_ADJUST_CFA_OFFSET ORIG_RAX-RBP
- call save_args
+ SAVE_ARGS_IRQ
PARTIAL_FRAME 0
call \func
.endm
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
decl PER_CPU_VAR(irq_count)
- leaveq
- CFI_RESTORE rbp
+ /* Restore saved previous stack */
+ popq %rsi
+ leaq 16(%rsi), %rsp
+
CFI_DEF_CFA_REGISTER rsp
- CFI_ADJUST_CFA_OFFSET -8
+ CFI_ADJUST_CFA_OFFSET -16
- /* we did not save rbx, restore only from ARGOFFSET */
- addq $8, %rsp
- CFI_ADJUST_CFA_OFFSET -8
exit_intr:
GET_THREAD_INFO(%rcx)
testl $3,CS-ARGOFFSET(%rsp)
*/
TRACE_IRQS_IRETQ
restore_args:
- RESTORE_ARGS 0,8,0
+ RESTORE_ARGS 1,8,1
irq_return:
INTERRUPT_RETURN
apicinterrupt THERMAL_APIC_VECTOR \
thermal_interrupt smp_thermal_interrupt
-#ifdef CONFIG_X86_MCE
-apicinterrupt MCE_SELF_VECTOR \
- mce_self_interrupt smp_mce_self_interrupt
-#endif
-
#ifdef CONFIG_SMP
apicinterrupt CALL_FUNCTION_SINGLE_VECTOR \
call_function_single_interrupt smp_call_function_single_interrupt
zeroentry coprocessor_error do_coprocessor_error
errorentry alignment_check do_alignment_check
zeroentry simd_coprocessor_error do_simd_coprocessor_error
+ zeroentry emulate_vsyscall do_emulate_vsyscall
+
/* Reload gs selector with exception handling */
/* edi: new selector */
#include <linux/sysdev.h>
#include <linux/delay.h>
#include <linux/errno.h>
+#include <linux/i8253.h>
#include <linux/slab.h>
#include <linux/hpet.h>
#include <linux/init.h>
#include <linux/io.h>
#include <asm/fixmap.h>
-#include <asm/i8253.h>
#include <asm/hpet.h>
+#include <asm/time.h>
#define HPET_MASK CLOCKSOURCE_MASK(32)
{
hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE);
#ifdef CONFIG_X86_64
- __set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VSYSCALL_NOCACHE);
+ __set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VVAR_NOCACHE);
#endif
}
return (cycle_t)hpet_readl(HPET_COUNTER);
}
- #ifdef CONFIG_X86_64
- static cycle_t __vsyscall_fn vread_hpet(void)
- {
- return readl((const void __iomem *)fix_to_virt(VSYSCALL_HPET) + 0xf0);
- }
- #endif
-
static struct clocksource clocksource_hpet = {
.name = "hpet",
.rating = 250,
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
.resume = hpet_resume_counter,
#ifdef CONFIG_X86_64
- .vread = vread_hpet,
+ .archdata = { .vclock_mode = VCLOCK_HPET },
#endif
};
* This has the effect of treating non-periodic like periodic.
*/
if ((devp->hd_flags & (HPET_IE | HPET_PERIODIC)) == HPET_IE) {
- unsigned long m, t;
+ unsigned long m, t, mc, base, k;
+ struct hpet __iomem *hpet = devp->hd_hpet;
+ struct hpets *hpetp = devp->hd_hpets;
t = devp->hd_ireqfreq;
m = read_counter(&devp->hd_timer->hpet_compare);
- write_counter(t + m, &devp->hd_timer->hpet_compare);
+ mc = read_counter(&hpet->hpet_mc);
+ /* The time for the next interrupt would logically be t + m,
+ * however, if we are very unlucky and the interrupt is delayed
+ * for longer than t then we will completely miss the next
+ * interrupt if we set t + m and an application will hang.
+ * Therefore we need to make a more complex computation assuming
+ * that there exists a k for which the following is true:
+ * k * t + base < mc + delta
+ * (k + 1) * t + base > mc + delta
+ * where t is the interval in hpet ticks for the given freq,
+ * base is the theoretical start value 0 < base < t,
+ * mc is the main counter value at the time of the interrupt,
+ * delta is the time it takes to write the a value to the
+ * comparator.
+ * k may then be computed as (mc - base + delta) / t .
+ */
+ base = mc % t;
+ k = (mc - base + hpetp->hp_delta) / t;
+ write_counter(t * (k + 1) + base,
+ &devp->hd_timer->hpet_compare);
}
if (devp->hd_flags & HPET_SHARED_IRQ)
#ifdef CONFIG_IA64
if (!hpet_clocksource) {
hpet_mctr = (void __iomem *)&hpetp->hp_hpet->hpet_mc;
- CLKSRC_FSYS_MMIO_SET(clocksource_hpet.fsys_mmio, hpet_mctr);
+ clocksource_hpet.archdata.fsys_mmio = hpet_mctr;
clocksource_register_hz(&clocksource_hpet, hpetp->hp_tick_freq);
hpetp->hp_clocksource = &clocksource_hpet;
hpet_clocksource = &clocksource_hpet;
typedef u64 cycle_t;
struct clocksource;
+ #ifdef CONFIG_ARCH_CLOCKSOURCE_DATA
+ #include <asm/clocksource.h>
+ #endif
+
/**
* struct cyclecounter - hardware abstraction for a free running counter
* Provides completely state-free accessors to the underlying hardware.
* @shift: cycle to nanosecond divisor (power of two)
* @max_idle_ns: max idle time permitted by the clocksource (nsecs)
* @flags: flags describing special properties
- * @vread: vsyscall based read
+ * @archdata: arch-specific data
* @suspend: suspend function for the clocksource, if necessary
* @resume: resume function for the clocksource, if necessary
*/
u32 shift;
u64 max_idle_ns;
- #ifdef CONFIG_IA64
- void *fsys_mmio; /* used by fsyscall asm code */
- #define CLKSRC_FSYS_MMIO_SET(mmio, addr) ((mmio) = (addr))
- #else
- #define CLKSRC_FSYS_MMIO_SET(mmio, addr) do { } while (0)
+ #ifdef CONFIG_ARCH_CLOCKSOURCE_DATA
+ struct arch_clocksource_data archdata;
#endif
+
const char *name;
struct list_head list;
int rating;
- cycle_t (*vread)(void);
int (*enable)(struct clocksource *cs);
void (*disable)(struct clocksource *cs);
unsigned long flags;
#ifdef CONFIG_CLOCKSOURCE_WATCHDOG
/* Watchdog related data, used by the framework */
struct list_head wd_list;
+ cycle_t cs_last;
cycle_t wd_last;
#endif
} ____cacheline_aligned;