* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-udf-2.6:
udf: Fix regression in UDF anchor block detection
# subdirectories here. Add them in the ".gitignore" file
# in that subdirectory instead.
#
+# NOTE! Please use 'git-ls-files -i --exclude-standard'
+# command after changing this file, to see if there are
+# any tracked files which get ignored after the change.
+#
# Normal rules
#
.*
*.lst
*.symtypes
*.order
+*.elf
+*.bin
+*.gz
#
# Top-level generic files
#
tags
TAGS
-vmlinux*
-!vmlinux.lds.S
-!vmlinux.lds.h
+vmlinux
System.map
Module.markers
Module.symvers
!.gitignore
+!.mailmap
#
# Generated include files
runs an instance of gdb against the vmlinux file which contains
the symbols (not boot image such as bzImage, zImage, uImage...).
In gdb the developer specifies the connection parameters and
- connects to kgdb. Depending on which kgdb I/O modules exist in
- the kernel for a given architecture, it may be possible to debug
- the test machine's kernel with the development machine using a
- rs232 or ethernet connection.
+ connects to kgdb. The type of connection a developer makes with
+ gdb depends on the availability of kgdb I/O modules compiled as
+ builtin's or kernel modules in the test machine's kernel.
</para>
</chapter>
<chapter id="CompilingAKernel">
</para>
<para>
IMPORTANT NOTE: Using this option with kgdb over the console
- (kgdboc) or kgdb over ethernet (kgdboe) is not supported.
+ (kgdboc) is not supported.
</para>
</sect1>
</chapter>
(gdb) target remote /dev/ttyS0
</programlisting>
<para>
- Example (kgdb to a terminal server):
+ Example (kgdb to a terminal server on tcp port 2012):
</para>
<programlisting>
% gdb ./vmlinux
- (gdb) target remote udp:192.168.2.2:6443
- </programlisting>
- <para>
- Example (kgdb over ethernet):
- </para>
- <programlisting>
- % gdb ./vmlinux
- (gdb) target remote udp:192.168.2.2:6443
+ (gdb) target remote 192.168.2.2:2012
</programlisting>
<para>
Once connected, you can debug a kernel the way you would debug an
VERSION = 2
PATCHLEVEL = 6
SUBLEVEL = 26
-EXTRAVERSION = -rc7
+EXTRAVERSION = -rc8
NAME = Rotary Wombat
# *DOCUMENTATION*
}
/* helper function */
-static void __fill_code_cplbtab(struct cplb_tab *t, int i, u32 a_start, u32 a_end)
+static void __init
+__fill_code_cplbtab(struct cplb_tab *t, int i, u32 a_start, u32 a_end)
{
if (cplb_data[i].psize) {
fill_cplbtab(t,
}
}
-static void __fill_data_cplbtab(struct cplb_tab *t, int i, u32 a_start, u32 a_end)
+static void __init
+__fill_data_cplbtab(struct cplb_tab *t, int i, u32 a_start, u32 a_end)
{
if (cplb_data[i].psize) {
fill_cplbtab(t,
};
static struct irq_desc bad_irq_desc = {
+ .status = IRQ_DISABLED,
.chip = &bad_chip,
.handle_irq = handle_bad_irq,
.depth = 1,
+ .lock = __SPIN_LOCK_UNLOCKED(irq_desc->lock),
+#ifdef CONFIG_SMP
+ .affinity = CPU_MASK_ALL
+#endif
};
int show_interrupts(struct seq_file *p, void *v)
if (!iosapic_kmalloc_ok && list_empty(&free_rte_list)) {
rte = alloc_bootmem(sizeof(struct iosapic_rte_info) *
NR_PREALLOCATE_RTE_ENTRIES);
- if (!rte)
- return NULL;
for (i = 0; i < NR_PREALLOCATE_RTE_ENTRIES; i++, rte++)
list_add(&rte->rte_list, &free_rte_list);
}
cpu_init(); /* initialize the bootstrap CPU */
mmu_context_init(); /* initialize context_id bitmap */
- check_sal_cache_flush();
-
#ifdef CONFIG_ACPI
acpi_boot_init();
#endif
ia64_mca_init();
platform_setup(cmdline_p);
+ check_sal_cache_flush();
paging_init();
}
int cpu;
char optstr[64];
- if (count > sizeof(optstr))
+ if (count == 0 || count > sizeof(optstr))
return -EINVAL;
if (copy_from_user(optstr, user, count))
return -EFAULT;
config KVM_CLOCK
bool "KVM paravirtualized clock"
select PARAVIRT
+ select PARAVIRT_CLOCK
depends on !(X86_VISWS || X86_VOYAGER)
help
Turning on this option will allow you to run a paravirtualized clock
over full virtualization. However, when run without a hypervisor
the kernel is theoretically slower and slightly larger.
+config PARAVIRT_CLOCK
+ bool
+ default n
+
endif
config MEMTEST_BOOTPARAM
obj-$(CONFIG_KVM_GUEST) += kvm.o
obj-$(CONFIG_KVM_CLOCK) += kvmclock.o
obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o
+obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o
obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o
#include <linux/clocksource.h>
#include <linux/kvm_para.h>
+#include <asm/pvclock.h>
#include <asm/arch_hooks.h>
#include <asm/msr.h>
#include <asm/apic.h>
early_param("no-kvmclock", parse_no_kvmclock);
/* The hypervisor will put information about time periodically here */
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct kvm_vcpu_time_info, hv_clock);
-#define get_clock(cpu, field) per_cpu(hv_clock, cpu).field
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct pvclock_vcpu_time_info, hv_clock);
+static struct pvclock_wall_clock wall_clock;
-static inline u64 kvm_get_delta(u64 last_tsc)
-{
- int cpu = smp_processor_id();
- u64 delta = native_read_tsc() - last_tsc;
- return (delta * get_clock(cpu, tsc_to_system_mul)) >> KVM_SCALE;
-}
-
-static struct kvm_wall_clock wall_clock;
-static cycle_t kvm_clock_read(void);
/*
* The wallclock is the time of day when we booted. Since then, some time may
* have elapsed since the hypervisor wrote the data. So we try to account for
*/
static unsigned long kvm_get_wallclock(void)
{
- u32 wc_sec, wc_nsec;
- u64 delta;
+ struct pvclock_vcpu_time_info *vcpu_time;
struct timespec ts;
- int version, nsec;
int low, high;
low = (int)__pa(&wall_clock);
high = ((u64)__pa(&wall_clock) >> 32);
+ native_write_msr(MSR_KVM_WALL_CLOCK, low, high);
- delta = kvm_clock_read();
+ vcpu_time = &get_cpu_var(hv_clock);
+ pvclock_read_wallclock(&wall_clock, vcpu_time, &ts);
+ put_cpu_var(hv_clock);
- native_write_msr(MSR_KVM_WALL_CLOCK, low, high);
- do {
- version = wall_clock.wc_version;
- rmb();
- wc_sec = wall_clock.wc_sec;
- wc_nsec = wall_clock.wc_nsec;
- rmb();
- } while ((wall_clock.wc_version != version) || (version & 1));
-
- delta = kvm_clock_read() - delta;
- delta += wc_nsec;
- nsec = do_div(delta, NSEC_PER_SEC);
- set_normalized_timespec(&ts, wc_sec + delta, nsec);
- /*
- * Of all mechanisms of time adjustment I've tested, this one
- * was the champion!
- */
- return ts.tv_sec + 1;
+ return ts.tv_sec;
}
static int kvm_set_wallclock(unsigned long now)
{
- return 0;
+ return -1;
}
-/*
- * This is our read_clock function. The host puts an tsc timestamp each time
- * it updates a new time. Without the tsc adjustment, we can have a situation
- * in which a vcpu starts to run earlier (smaller system_time), but probes
- * time later (compared to another vcpu), leading to backwards time
- */
static cycle_t kvm_clock_read(void)
{
- u64 last_tsc, now;
- int cpu;
+ struct pvclock_vcpu_time_info *src;
+ cycle_t ret;
- preempt_disable();
- cpu = smp_processor_id();
-
- last_tsc = get_clock(cpu, tsc_timestamp);
- now = get_clock(cpu, system_time);
-
- now += kvm_get_delta(last_tsc);
- preempt_enable();
-
- return now;
+ src = &get_cpu_var(hv_clock);
+ ret = pvclock_clocksource_read(src);
+ put_cpu_var(hv_clock);
+ return ret;
}
+
static struct clocksource kvm_clock = {
.name = "kvm-clock",
.read = kvm_clock_read,
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
-static int kvm_register_clock(void)
+static int kvm_register_clock(char *txt)
{
int cpu = smp_processor_id();
int low, high;
low = (int)__pa(&per_cpu(hv_clock, cpu)) | 1;
high = ((u64)__pa(&per_cpu(hv_clock, cpu)) >> 32);
-
+ printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n",
+ cpu, high, low, txt);
return native_write_msr_safe(MSR_KVM_SYSTEM_TIME, low, high);
}
* Now that the first cpu already had this clocksource initialized,
* we shouldn't fail.
*/
- WARN_ON(kvm_register_clock());
+ WARN_ON(kvm_register_clock("secondary cpu clock"));
/* ok, done with our trickery, call native */
setup_secondary_APIC_clock();
}
#endif
+#ifdef CONFIG_SMP
+void __init kvm_smp_prepare_boot_cpu(void)
+{
+ WARN_ON(kvm_register_clock("primary cpu clock"));
+ native_smp_prepare_boot_cpu();
+}
+#endif
+
/*
* After the clock is registered, the host will keep writing to the
* registered memory location. If the guest happens to shutdown, this memory
return;
if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
- if (kvm_register_clock())
+ if (kvm_register_clock("boot clock"))
return;
pv_time_ops.get_wallclock = kvm_get_wallclock;
pv_time_ops.set_wallclock = kvm_set_wallclock;
pv_time_ops.sched_clock = kvm_clock_read;
#ifdef CONFIG_X86_LOCAL_APIC
pv_apic_ops.setup_secondary_clock = kvm_setup_secondary_clock;
+#endif
+#ifdef CONFIG_SMP
+ smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
#endif
machine_ops.shutdown = kvm_shutdown;
#ifdef CONFIG_KEXEC
--- /dev/null
+/* paravirtual clock -- common code used by kvm/xen
+
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 2 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+*/
+
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <asm/pvclock.h>
+
+/*
+ * These are perodically updated
+ * xen: magic shared_info page
+ * kvm: gpa registered via msr
+ * and then copied here.
+ */
+struct pvclock_shadow_time {
+ u64 tsc_timestamp; /* TSC at last update of time vals. */
+ u64 system_timestamp; /* Time, in nanosecs, since boot. */
+ u32 tsc_to_nsec_mul;
+ int tsc_shift;
+ u32 version;
+};
+
+/*
+ * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
+ * yielding a 64-bit result.
+ */
+static inline u64 scale_delta(u64 delta, u32 mul_frac, int shift)
+{
+ u64 product;
+#ifdef __i386__
+ u32 tmp1, tmp2;
+#endif
+
+ if (shift < 0)
+ delta >>= -shift;
+ else
+ delta <<= shift;
+
+#ifdef __i386__
+ __asm__ (
+ "mul %5 ; "
+ "mov %4,%%eax ; "
+ "mov %%edx,%4 ; "
+ "mul %5 ; "
+ "xor %5,%5 ; "
+ "add %4,%%eax ; "
+ "adc %5,%%edx ; "
+ : "=A" (product), "=r" (tmp1), "=r" (tmp2)
+ : "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) );
+#elif __x86_64__
+ __asm__ (
+ "mul %%rdx ; shrd $32,%%rdx,%%rax"
+ : "=a" (product) : "0" (delta), "d" ((u64)mul_frac) );
+#else
+#error implement me!
+#endif
+
+ return product;
+}
+
+static u64 pvclock_get_nsec_offset(struct pvclock_shadow_time *shadow)
+{
+ u64 delta = native_read_tsc() - shadow->tsc_timestamp;
+ return scale_delta(delta, shadow->tsc_to_nsec_mul, shadow->tsc_shift);
+}
+
+/*
+ * Reads a consistent set of time-base values from hypervisor,
+ * into a shadow data area.
+ */
+static unsigned pvclock_get_time_values(struct pvclock_shadow_time *dst,
+ struct pvclock_vcpu_time_info *src)
+{
+ do {
+ dst->version = src->version;
+ rmb(); /* fetch version before data */
+ dst->tsc_timestamp = src->tsc_timestamp;
+ dst->system_timestamp = src->system_time;
+ dst->tsc_to_nsec_mul = src->tsc_to_system_mul;
+ dst->tsc_shift = src->tsc_shift;
+ rmb(); /* test version after fetching data */
+ } while ((src->version & 1) || (dst->version != src->version));
+
+ return dst->version;
+}
+
+cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
+{
+ struct pvclock_shadow_time shadow;
+ unsigned version;
+ cycle_t ret, offset;
+
+ do {
+ version = pvclock_get_time_values(&shadow, src);
+ barrier();
+ offset = pvclock_get_nsec_offset(&shadow);
+ ret = shadow.system_timestamp + offset;
+ barrier();
+ } while (version != src->version);
+
+ return ret;
+}
+
+void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
+ struct pvclock_vcpu_time_info *vcpu_time,
+ struct timespec *ts)
+{
+ u32 version;
+ u64 delta;
+ struct timespec now;
+
+ /* get wallclock at system boot */
+ do {
+ version = wall_clock->version;
+ rmb(); /* fetch version before time */
+ now.tv_sec = wall_clock->sec;
+ now.tv_nsec = wall_clock->nsec;
+ rmb(); /* fetch time before checking version */
+ } while ((wall_clock->version & 1) || (version != wall_clock->version));
+
+ delta = pvclock_clocksource_read(vcpu_time); /* time since system boot */
+ delta += now.tv_sec * (u64)NSEC_PER_SEC + now.tv_nsec;
+
+ now.tv_nsec = do_div(delta, NSEC_PER_SEC);
+ now.tv_sec = delta;
+
+ set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
+}
atomic_inc(&pt->pending);
smp_mb__after_atomic_inc();
- if (vcpu0 && waitqueue_active(&vcpu0->wq)) {
- vcpu0->arch.mp_state = KVM_MP_STATE_RUNNABLE;
- wake_up_interruptible(&vcpu0->wq);
+ if (vcpu0) {
+ set_bit(KVM_REQ_PENDING_TIMER, &vcpu0->requests);
+ if (waitqueue_active(&vcpu0->wq)) {
+ vcpu0->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+ wake_up_interruptible(&vcpu0->wq);
+ }
}
pt->timer.expires = ktime_add_ns(pt->timer.expires, pt->period);
wait_queue_head_t *q = &apic->vcpu->wq;
atomic_inc(&apic->timer.pending);
+ set_bit(KVM_REQ_PENDING_TIMER, &apic->vcpu->requests);
if (waitqueue_active(q)) {
apic->vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
wake_up_interruptible(q);
rmap_remove(kvm, spte);
--kvm->stat.lpages;
set_shadow_pte(spte, shadow_trap_nonpresent_pte);
+ spte = NULL;
write_protected = 1;
}
spte = rmap_next(kvm, rmapp, spte);
struct kvm_mmu_page *shadow;
spte |= PT_WRITABLE_MASK;
- if (user_fault) {
- mmu_unshadow(vcpu->kvm, gfn);
- goto unshadowed;
- }
shadow = kvm_mmu_lookup_page(vcpu->kvm, gfn);
if (shadow ||
}
}
-unshadowed:
-
if (pte_access & ACC_WRITE_MASK)
mark_page_dirty(vcpu->kvm, gfn);
u64 *spte,
const void *new)
{
- if ((sp->role.level != PT_PAGE_TABLE_LEVEL)
- && !vcpu->arch.update_pte.largepage) {
- ++vcpu->kvm->stat.mmu_pde_zapped;
- return;
- }
+ if (sp->role.level != PT_PAGE_TABLE_LEVEL) {
+ if (!vcpu->arch.update_pte.largepage ||
+ sp->role.glevels == PT32_ROOT_LEVEL) {
+ ++vcpu->kvm->stat.mmu_pde_zapped;
+ return;
+ }
+ }
++vcpu->kvm->stat.mmu_pte_updated;
if (sp->role.glevels == PT32_ROOT_LEVEL)
load_transition_efer(vmx);
}
-static void vmx_load_host_state(struct vcpu_vmx *vmx)
+static void __vmx_load_host_state(struct vcpu_vmx *vmx)
{
unsigned long flags;
reload_host_efer(vmx);
}
+static void vmx_load_host_state(struct vcpu_vmx *vmx)
+{
+ preempt_disable();
+ __vmx_load_host_state(vmx);
+ preempt_enable();
+}
+
/*
* Switches to specified vcpu, until a matching vcpu_put(), but assumes
* vcpu mutex is already taken.
static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
{
- vmx_load_host_state(to_vmx(vcpu));
+ __vmx_load_host_state(to_vmx(vcpu));
}
static void vmx_fpu_activate(struct kvm_vcpu *vcpu)
switch (msr_index) {
#ifdef CONFIG_X86_64
case MSR_EFER:
+ vmx_load_host_state(vmx);
ret = kvm_set_msr_common(vcpu, msr_index, data);
- if (vmx->host_state.loaded) {
- reload_host_efer(vmx);
- load_transition_efer(vmx);
- }
break;
case MSR_FS_BASE:
vmcs_writel(GUEST_FS_BASE, data);
guest_write_tsc(data);
break;
default:
+ vmx_load_host_state(vmx);
msr = find_msr_entry(vmx, msr_index);
if (msr) {
msr->data = data;
- if (vmx->host_state.loaded)
- load_msrs(vmx->guest_msrs, vmx->save_nmsrs);
break;
}
ret = kvm_set_msr_common(vcpu, msr_index, data);
static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
{
static int version;
- struct kvm_wall_clock wc;
- struct timespec wc_ts;
+ struct pvclock_wall_clock wc;
+ struct timespec now, sys, boot;
if (!wall_clock)
return;
kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
- wc_ts = current_kernel_time();
- wc.wc_sec = wc_ts.tv_sec;
- wc.wc_nsec = wc_ts.tv_nsec;
- wc.wc_version = version;
+ /*
+ * The guest calculates current wall clock time by adding
+ * system time (updated by kvm_write_guest_time below) to the
+ * wall clock specified here. guest system time equals host
+ * system time for us, thus we must fill in host boot time here.
+ */
+ now = current_kernel_time();
+ ktime_get_ts(&sys);
+ boot = ns_to_timespec(timespec_to_ns(&now) - timespec_to_ns(&sys));
+
+ wc.sec = boot.tv_sec;
+ wc.nsec = boot.tv_nsec;
+ wc.version = version;
kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc));
kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
}
+static uint32_t div_frac(uint32_t dividend, uint32_t divisor)
+{
+ uint32_t quotient, remainder;
+
+ /* Don't try to replace with do_div(), this one calculates
+ * "(dividend << 32) / divisor" */
+ __asm__ ( "divl %4"
+ : "=a" (quotient), "=d" (remainder)
+ : "0" (0), "1" (dividend), "r" (divisor) );
+ return quotient;
+}
+
+static void kvm_set_time_scale(uint32_t tsc_khz, struct pvclock_vcpu_time_info *hv_clock)
+{
+ uint64_t nsecs = 1000000000LL;
+ int32_t shift = 0;
+ uint64_t tps64;
+ uint32_t tps32;
+
+ tps64 = tsc_khz * 1000LL;
+ while (tps64 > nsecs*2) {
+ tps64 >>= 1;
+ shift--;
+ }
+
+ tps32 = (uint32_t)tps64;
+ while (tps32 <= (uint32_t)nsecs) {
+ tps32 <<= 1;
+ shift++;
+ }
+
+ hv_clock->tsc_shift = shift;
+ hv_clock->tsc_to_system_mul = div_frac(nsecs, tps32);
+
+ pr_debug("%s: tsc_khz %u, tsc_shift %d, tsc_mul %u\n",
+ __FUNCTION__, tsc_khz, hv_clock->tsc_shift,
+ hv_clock->tsc_to_system_mul);
+}
+
static void kvm_write_guest_time(struct kvm_vcpu *v)
{
struct timespec ts;
if ((!vcpu->time_page))
return;
+ if (unlikely(vcpu->hv_clock_tsc_khz != tsc_khz)) {
+ kvm_set_time_scale(tsc_khz, &vcpu->hv_clock);
+ vcpu->hv_clock_tsc_khz = tsc_khz;
+ }
+
/* Keep irq disabled to prevent changes to the clock */
local_irq_save(flags);
kvm_get_msr(v, MSR_IA32_TIME_STAMP_COUNTER,
/*
* The interface expects us to write an even number signaling that the
* update is finished. Since the guest won't see the intermediate
- * state, we just write "2" at the end
+ * state, we just increase by 2 at the end.
*/
- vcpu->hv_clock.version = 2;
+ vcpu->hv_clock.version += 2;
shared_kaddr = kmap_atomic(vcpu->time_page, KM_USER0);
memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
- sizeof(vcpu->hv_clock));
+ sizeof(vcpu->hv_clock));
kunmap_atomic(shared_kaddr, KM_USER0);
/* ...but clean it before doing the actual write */
vcpu->arch.time_offset = data & ~(PAGE_MASK | 1);
- vcpu->arch.hv_clock.tsc_to_system_mul =
- clocksource_khz2mult(tsc_khz, 22);
- vcpu->arch.hv_clock.tsc_shift = 22;
-
down_read(¤t->mm->mmap_sem);
vcpu->arch.time_page =
gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);
if (vcpu->requests) {
if (test_and_clear_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests))
__kvm_migrate_timers(vcpu);
+ if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
+ kvm_x86_ops->tlb_flush(vcpu);
if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS,
&vcpu->requests)) {
kvm_run->exit_reason = KVM_EXIT_TPR_ACCESS;
}
}
+ clear_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests);
kvm_inject_pending_timer_irqs(vcpu);
preempt_disable();
local_irq_disable();
- if (need_resched()) {
+ if (vcpu->requests || need_resched()) {
local_irq_enable();
preempt_enable();
r = 1;
goto out;
}
- if (vcpu->requests)
- if (test_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests)) {
- local_irq_enable();
- preempt_enable();
- r = 1;
- goto out;
- }
-
if (signal_pending(current)) {
local_irq_enable();
preempt_enable();
kvm_guest_enter();
- if (vcpu->requests)
- if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
- kvm_x86_ops->tlb_flush(vcpu);
KVMTRACE_0D(VMENTRY, vcpu, entryexit);
kvm_x86_ops->run(vcpu, kvm_run);
config XEN
bool "Xen guest support"
select PARAVIRT
+ select PARAVIRT_CLOCK
depends on X86_32
- depends on X86_CMPXCHG && X86_TSC && !(X86_VISWS || X86_VOYAGER)
+ depends on X86_CMPXCHG && X86_TSC && X86_PAE && !(X86_VISWS || X86_VOYAGER)
help
This is the Linux Xen port. Enabling this will allow the
kernel to boot in a paravirtualized environment under the
static __init void xen_pagetable_setup_start(pgd_t *base)
{
pgd_t *xen_pgd = (pgd_t *)xen_start_info->pt_base;
+ int i;
/* special set_pte for pagetable initialization */
pv_mmu_ops.set_pte = xen_set_pte_init;
init_mm.pgd = base;
/*
- * copy top-level of Xen-supplied pagetable into place. For
- * !PAE we can use this as-is, but for PAE it is a stand-in
- * while we copy the pmd pages.
+ * copy top-level of Xen-supplied pagetable into place. This
+ * is a stand-in while we copy the pmd pages.
*/
memcpy(base, xen_pgd, PTRS_PER_PGD * sizeof(pgd_t));
- if (PTRS_PER_PMD > 1) {
- int i;
- /*
- * For PAE, need to allocate new pmds, rather than
- * share Xen's, since Xen doesn't like pmd's being
- * shared between address spaces.
- */
- for (i = 0; i < PTRS_PER_PGD; i++) {
- if (pgd_val_ma(xen_pgd[i]) & _PAGE_PRESENT) {
- pmd_t *pmd = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE);
+ /*
+ * For PAE, need to allocate new pmds, rather than
+ * share Xen's, since Xen doesn't like pmd's being
+ * shared between address spaces.
+ */
+ for (i = 0; i < PTRS_PER_PGD; i++) {
+ if (pgd_val_ma(xen_pgd[i]) & _PAGE_PRESENT) {
+ pmd_t *pmd = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE);
- memcpy(pmd, (void *)pgd_page_vaddr(xen_pgd[i]),
- PAGE_SIZE);
+ memcpy(pmd, (void *)pgd_page_vaddr(xen_pgd[i]),
+ PAGE_SIZE);
- make_lowmem_page_readonly(pmd);
+ make_lowmem_page_readonly(pmd);
- set_pgd(&base[i], __pgd(1 + __pa(pmd)));
- } else
- pgd_clear(&base[i]);
- }
+ set_pgd(&base[i], __pgd(1 + __pa(pmd)));
+ } else
+ pgd_clear(&base[i]);
}
/* make sure zero_page is mapped RO so we can use it in pagetables */
/* Actually pin the pagetable down, but we can't set PG_pinned
yet because the page structures don't exist yet. */
- {
- unsigned level;
-
-#ifdef CONFIG_X86_PAE
- level = MMUEXT_PIN_L3_TABLE;
-#else
- level = MMUEXT_PIN_L2_TABLE;
-#endif
-
- pin_pagetable_pfn(level, PFN_DOWN(__pa(base)));
- }
+ pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(base)));
}
/* This is called once we have the cpu_possible_map */
.make_pte = xen_make_pte,
.make_pgd = xen_make_pgd,
-#ifdef CONFIG_X86_PAE
.set_pte_atomic = xen_set_pte_atomic,
.set_pte_present = xen_set_pte_at,
.set_pud = xen_set_pud,
.make_pmd = xen_make_pmd,
.pmd_val = xen_pmd_val,
-#endif /* PAE */
.activate_mm = xen_activate_mm,
.dup_mmap = xen_dup_mmap,
{
return pte_mfn_to_pfn(pmd.pmd);
}
-#ifdef CONFIG_X86_PAE
+
void xen_set_pud(pud_t *ptr, pud_t val)
{
struct multicall_space mcs;
pmd = pte_pfn_to_mfn(pmd);
return native_make_pmd(pmd);
}
-#else /* !PAE */
-void xen_set_pte(pte_t *ptep, pte_t pte)
-{
- *ptep = pte;
-}
-#endif /* CONFIG_X86_PAE */
/*
(Yet another) pagetable walker. This one is intended for pinning a
read-only, and can be pinned. */
void xen_pgd_pin(pgd_t *pgd)
{
- unsigned level;
-
xen_mc_batch();
if (pgd_walk(pgd, pin_page, TASK_SIZE)) {
xen_mc_batch();
}
-#ifdef CONFIG_X86_PAE
- level = MMUEXT_PIN_L3_TABLE;
-#else
- level = MMUEXT_PIN_L2_TABLE;
-#endif
-
- xen_do_pin(level, PFN_DOWN(__pa(pgd)));
-
+ xen_do_pin(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(pgd)));
xen_mc_issue(0);
}
void xen_pgd_pin(pgd_t *pgd);
//void xen_pgd_unpin(pgd_t *pgd);
-#ifdef CONFIG_X86_PAE
-unsigned long long xen_pte_val(pte_t);
-unsigned long long xen_pmd_val(pmd_t);
-unsigned long long xen_pgd_val(pgd_t);
+pteval_t xen_pte_val(pte_t);
+pmdval_t xen_pmd_val(pmd_t);
+pgdval_t xen_pgd_val(pgd_t);
-pte_t xen_make_pte(unsigned long long);
-pmd_t xen_make_pmd(unsigned long long);
-pgd_t xen_make_pgd(unsigned long long);
+pte_t xen_make_pte(pteval_t);
+pmd_t xen_make_pmd(pmdval_t);
+pgd_t xen_make_pgd(pgdval_t);
void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pteval);
void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
void xen_pmd_clear(pmd_t *pmdp);
-
-#else
-unsigned long xen_pte_val(pte_t);
-unsigned long xen_pmd_val(pmd_t);
-unsigned long xen_pgd_val(pgd_t);
-
-pte_t xen_make_pte(unsigned long);
-pmd_t xen_make_pmd(unsigned long);
-pgd_t xen_make_pgd(unsigned long);
-#endif
-
#endif /* _XEN_MMU_H */
#include <linux/kernel_stat.h>
#include <linux/math64.h>
+#include <asm/pvclock.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
static cycle_t xen_clocksource_read(void);
-/* These are perodically updated in shared_info, and then copied here. */
-struct shadow_time_info {
- u64 tsc_timestamp; /* TSC at last update of time vals. */
- u64 system_timestamp; /* Time, in nanosecs, since boot. */
- u32 tsc_to_nsec_mul;
- int tsc_shift;
- u32 version;
-};
-
-static DEFINE_PER_CPU(struct shadow_time_info, shadow_time);
-
/* runstate info updated by Xen */
static DEFINE_PER_CPU(struct vcpu_runstate_info, runstate);
unsigned long xen_cpu_khz(void)
{
u64 xen_khz = 1000000ULL << 32;
- const struct vcpu_time_info *info =
+ const struct pvclock_vcpu_time_info *info =
&HYPERVISOR_shared_info->vcpu_info[0].time;
do_div(xen_khz, info->tsc_to_system_mul);
return xen_khz;
}
-/*
- * Reads a consistent set of time-base values from Xen, into a shadow data
- * area.
- */
-static unsigned get_time_values_from_xen(void)
-{
- struct vcpu_time_info *src;
- struct shadow_time_info *dst;
-
- /* src is shared memory with the hypervisor, so we need to
- make sure we get a consistent snapshot, even in the face of
- being preempted. */
- src = &__get_cpu_var(xen_vcpu)->time;
- dst = &__get_cpu_var(shadow_time);
-
- do {
- dst->version = src->version;
- rmb(); /* fetch version before data */
- dst->tsc_timestamp = src->tsc_timestamp;
- dst->system_timestamp = src->system_time;
- dst->tsc_to_nsec_mul = src->tsc_to_system_mul;
- dst->tsc_shift = src->tsc_shift;
- rmb(); /* test version after fetching data */
- } while ((src->version & 1) | (dst->version ^ src->version));
-
- return dst->version;
-}
-
-/*
- * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
- * yielding a 64-bit result.
- */
-static inline u64 scale_delta(u64 delta, u32 mul_frac, int shift)
-{
- u64 product;
-#ifdef __i386__
- u32 tmp1, tmp2;
-#endif
-
- if (shift < 0)
- delta >>= -shift;
- else
- delta <<= shift;
-
-#ifdef __i386__
- __asm__ (
- "mul %5 ; "
- "mov %4,%%eax ; "
- "mov %%edx,%4 ; "
- "mul %5 ; "
- "xor %5,%5 ; "
- "add %4,%%eax ; "
- "adc %5,%%edx ; "
- : "=A" (product), "=r" (tmp1), "=r" (tmp2)
- : "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) );
-#elif __x86_64__
- __asm__ (
- "mul %%rdx ; shrd $32,%%rdx,%%rax"
- : "=a" (product) : "0" (delta), "d" ((u64)mul_frac) );
-#else
-#error implement me!
-#endif
-
- return product;
-}
-
-static u64 get_nsec_offset(struct shadow_time_info *shadow)
-{
- u64 now, delta;
- now = native_read_tsc();
- delta = now - shadow->tsc_timestamp;
- return scale_delta(delta, shadow->tsc_to_nsec_mul, shadow->tsc_shift);
-}
-
static cycle_t xen_clocksource_read(void)
{
- struct shadow_time_info *shadow = &get_cpu_var(shadow_time);
+ struct pvclock_vcpu_time_info *src;
cycle_t ret;
- unsigned version;
-
- do {
- version = get_time_values_from_xen();
- barrier();
- ret = shadow->system_timestamp + get_nsec_offset(shadow);
- barrier();
- } while (version != __get_cpu_var(xen_vcpu)->time.version);
-
- put_cpu_var(shadow_time);
+ src = &get_cpu_var(xen_vcpu)->time;
+ ret = pvclock_clocksource_read(src);
+ put_cpu_var(xen_vcpu);
return ret;
}
static void xen_read_wallclock(struct timespec *ts)
{
- const struct shared_info *s = HYPERVISOR_shared_info;
- u32 version;
- u64 delta;
- struct timespec now;
-
- /* get wallclock at system boot */
- do {
- version = s->wc_version;
- rmb(); /* fetch version before time */
- now.tv_sec = s->wc_sec;
- now.tv_nsec = s->wc_nsec;
- rmb(); /* fetch time before checking version */
- } while ((s->wc_version & 1) | (version ^ s->wc_version));
+ struct shared_info *s = HYPERVISOR_shared_info;
+ struct pvclock_wall_clock *wall_clock = &(s->wc);
+ struct pvclock_vcpu_time_info *vcpu_time;
- delta = xen_clocksource_read(); /* time since system boot */
- delta += now.tv_sec * (u64)NSEC_PER_SEC + now.tv_nsec;
-
- now.tv_nsec = do_div(delta, NSEC_PER_SEC);
- now.tv_sec = delta;
-
- set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
+ vcpu_time = &get_cpu_var(xen_vcpu)->time;
+ pvclock_read_wallclock(wall_clock, vcpu_time, ts);
+ put_cpu_var(xen_vcpu);
}
unsigned long xen_get_wallclock(void)
struct timespec ts;
xen_read_wallclock(&ts);
-
return ts.tv_sec;
}
{
int cpu = smp_processor_id();
- get_time_values_from_xen();
-
clocksource_register(&xen_clocksource);
if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL) == 0) {
ELFNOTE(Xen, XEN_ELFNOTE_ENTRY, .long startup_xen)
ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, .long hypercall_page)
ELFNOTE(Xen, XEN_ELFNOTE_FEATURES, .asciz "!writable_page_tables|pae_pgdir_above_4gb")
-#ifdef CONFIG_X86_PAE
ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE, .asciz "yes")
-#else
- ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE, .asciz "no")
-#endif
ELFNOTE(Xen, XEN_ELFNOTE_LOADER, .asciz "generic")
#endif /*CONFIG_XEN */
pci_restore_state(dev->pdev);
if (pci_enable_device(dev->pdev))
return -1;
+ pci_set_master(dev->pdev);
pci_write_config_byte(dev->pdev, LBB, dev_priv->saveLBB);
obj-$(CONFIG_I6300ESB_WDT) += i6300esb.o
obj-$(CONFIG_ITCO_WDT) += iTCO_wdt.o iTCO_vendor_support.o
obj-$(CONFIG_IT8712F_WDT) += it8712f_wdt.o
-CFLAGS_hpwdt.o += -O
obj-$(CONFIG_HP_WATCHDOG) += hpwdt.o
obj-$(CONFIG_SC1200_WDT) += sc1200wdt.o
obj-$(CONFIG_SCx200_WDT) += scx200_wdt.o
struct gendisk *disk;
int ret;
int part;
+ int perm = 0;
- ret = devcgroup_inode_permission(bdev->bd_inode, file->f_mode);
+ if (file->f_mode & FMODE_READ)
+ perm |= MAY_READ;
+ if (file->f_mode & FMODE_WRITE)
+ perm |= MAY_WRITE;
+ /*
+ * hooks: /n/, see "layering violations".
+ */
+ ret = devcgroup_inode_permission(bdev->bd_inode, perm);
if (ret != 0)
return ret;
#include <linux/syscalls.h>
#include <linux/string.h>
#include <linux/mm.h>
+#include <linux/fdtable.h>
#include <linux/fs.h>
#include <linux/fsnotify.h>
#include <linux/slab.h>
/*
* Release the dentry's inode, using the filesystem
* d_iput() operation if defined.
- * Called with dcache_lock and per dentry lock held, drops both.
*/
static void dentry_iput(struct dentry * dentry)
+ __releases(dentry->d_lock)
+ __releases(dcache_lock)
{
struct inode *inode = dentry->d_inode;
if (inode) {
* d_kill - kill dentry and return parent
* @dentry: dentry to kill
*
- * Called with dcache_lock and d_lock, releases both. The dentry must
- * already be unhashed and removed from the LRU.
+ * The dentry must already be unhashed and removed from the LRU.
*
* If this is the root of the dentry tree, return NULL.
*/
static struct dentry *d_kill(struct dentry *dentry)
+ __releases(dentry->d_lock)
+ __releases(dcache_lock)
{
struct dentry *parent;
* Try to prune ancestors as well. This is necessary to prevent
* quadratic behavior of shrink_dcache_parent(), but is also expected
* to be beneficial in reducing dentry cache fragmentation.
- *
- * Called with dcache_lock, drops it and then regains.
- * Called with dentry->d_lock held, drops it.
*/
static void prune_one_dentry(struct dentry * dentry)
+ __releases(dentry->d_lock)
+ __releases(dcache_lock)
+ __acquires(dcache_lock)
{
__d_drop(dentry);
dentry = d_kill(dentry);
*
* Note: If ever the locking in lock_rename() changes, then please
* remember to update this too...
- *
- * On return, dcache_lock will have been unlocked.
*/
static struct dentry *__d_unalias(struct dentry *dentry, struct dentry *alias)
+ __releases(dcache_lock)
{
struct mutex *m1 = NULL, *m2 = NULL;
struct dentry *ret;
shouldnt_be_hashed:
spin_unlock(&dcache_lock);
BUG();
- goto shouldnt_be_hashed;
}
-static int prepend(char **buffer, int *buflen, const char *str,
- int namelen)
+static int prepend(char **buffer, int *buflen, const char *str, int namelen)
{
*buflen -= namelen;
if (*buflen < 0)
return 0;
}
+static int prepend_name(char **buffer, int *buflen, struct qstr *name)
+{
+ return prepend(buffer, buflen, name->name, name->len);
+}
+
/**
- * d_path - return the path of a dentry
+ * __d_path - return the path of a dentry
* @path: the dentry/vfsmount to report
* @root: root vfsmnt/dentry (may be modified by this function)
* @buffer: buffer to return value in
{
struct dentry *dentry = path->dentry;
struct vfsmount *vfsmnt = path->mnt;
- char * end = buffer+buflen;
- char * retval;
+ char *end = buffer + buflen;
+ char *retval;
+ spin_lock(&vfsmount_lock);
prepend(&end, &buflen, "\0", 1);
if (!IS_ROOT(dentry) && d_unhashed(dentry) &&
(prepend(&end, &buflen, " (deleted)", 10) != 0))
break;
if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) {
/* Global root? */
- spin_lock(&vfsmount_lock);
if (vfsmnt->mnt_parent == vfsmnt) {
- spin_unlock(&vfsmount_lock);
goto global_root;
}
dentry = vfsmnt->mnt_mountpoint;
vfsmnt = vfsmnt->mnt_parent;
- spin_unlock(&vfsmount_lock);
continue;
}
parent = dentry->d_parent;
prefetch(parent);
- if ((prepend(&end, &buflen, dentry->d_name.name,
- dentry->d_name.len) != 0) ||
+ if ((prepend_name(&end, &buflen, &dentry->d_name) != 0) ||
(prepend(&end, &buflen, "/", 1) != 0))
goto Elong;
retval = end;
dentry = parent;
}
+out:
+ spin_unlock(&vfsmount_lock);
return retval;
global_root:
retval += 1; /* hit the slash */
- if (prepend(&retval, &buflen, dentry->d_name.name,
- dentry->d_name.len) != 0)
+ if (prepend_name(&retval, &buflen, &dentry->d_name) != 0)
goto Elong;
root->mnt = vfsmnt;
root->dentry = dentry;
- return retval;
+ goto out;
+
Elong:
- return ERR_PTR(-ENAMETOOLONG);
+ retval = ERR_PTR(-ENAMETOOLONG);
+ goto out;
}
/**
*
* Returns the buffer or an error code if the path was too long.
*
- * "buflen" should be positive. Caller holds the dcache_lock.
+ * "buflen" should be positive.
*/
-char *d_path(struct path *path, char *buf, int buflen)
+char *d_path(const struct path *path, char *buf, int buflen)
{
char *res;
struct path root;
retval = end-1;
*retval = '/';
- for (;;) {
- struct dentry *parent;
- if (IS_ROOT(dentry))
- break;
+ while (!IS_ROOT(dentry)) {
+ struct dentry *parent = dentry->d_parent;
- parent = dentry->d_parent;
prefetch(parent);
-
- if ((prepend(&end, &buflen, dentry->d_name.name,
- dentry->d_name.len) != 0) ||
+ if ((prepend_name(&end, &buflen, &dentry->d_name) != 0) ||
(prepend(&end, &buflen, "/", 1) != 0))
goto Elong;
error = -ENOENT;
/* Has the current directory has been unlinked? */
spin_lock(&dcache_lock);
- if (pwd.dentry->d_parent == pwd.dentry || !d_unhashed(pwd.dentry)) {
+ if (IS_ROOT(pwd.dentry) || !d_unhashed(pwd.dentry)) {
unsigned long len;
struct path tmp = root;
char * cwd;
}
-static inline unsigned int zero_metapath_length(const struct metapath *mp,
- unsigned height)
+static inline unsigned int metapath_branch_start(const struct metapath *mp)
{
- unsigned int i;
- for (i = 0; i < height - 1; i++) {
- if (mp->mp_list[i] != 0)
- return i;
- }
- return height;
+ if (mp->mp_list[0] == 0)
+ return 2;
+ return 1;
}
/**
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct buffer_head *dibh = mp->mp_bh[0];
u64 bn, dblock = 0;
- unsigned n, i, blks, alloced = 0, iblks = 0, zmpl = 0;
+ unsigned n, i, blks, alloced = 0, iblks = 0, branch_start = 0;
unsigned dblks = 0;
unsigned ptrs_per_blk;
const unsigned end_of_metadata = height - 1;
/* Building up tree height */
state = ALLOC_GROW_HEIGHT;
iblks = height - ip->i_height;
- zmpl = zero_metapath_length(mp, height);
- iblks -= zmpl;
- iblks += height;
+ branch_start = metapath_branch_start(mp);
+ iblks += (height - branch_start);
}
}
sizeof(struct gfs2_meta_header));
*ptr = zero_bn;
state = ALLOC_GROW_DEPTH;
- for(i = zmpl; i < height; i++) {
+ for(i = branch_start; i < height; i++) {
if (mp->mp_bh[i] == NULL)
break;
brelse(mp->mp_bh[i]);
mp->mp_bh[i] = NULL;
}
- i = zmpl;
+ i = branch_start;
}
if (n == 0)
break;
depending on architecture. I've experimented with several ways
of writing this section such as using an else before the goto
but this one seems to be the fastest. */
- while ((unsigned char *)plong < end - 1) {
+ while ((unsigned char *)plong < end - sizeof(unsigned long)) {
prefetch(plong + 1);
if (((*plong) & LBITMASK) != lskipval)
break;
/* insert into file's list */
fl->fl_next = *pos;
*pos = fl;
-
- if (fl->fl_ops && fl->fl_ops->fl_insert)
- fl->fl_ops->fl_insert(fl);
}
/*
fl->fl_fasync = NULL;
}
- if (fl->fl_ops && fl->fl_ops->fl_remove)
- fl->fl_ops->fl_remove(fl);
-
if (fl->fl_nspid) {
put_pid(fl->fl_nspid);
fl->fl_nspid = NULL;
int result;
/* make sure the stuff we saved doesn't go away */
- dget(save.dentry);
- mntget(save.mnt);
+ path_get(&save);
result = __link_path_walk(name, nd);
if (result == -ESTALE) {
/* nd->path had been dropped */
nd->path = save;
- dget(nd->path.dentry);
- mntget(nd->path.mnt);
+ path_get(&nd->path);
nd->flags |= LOOKUP_REVAL;
result = __link_path_walk(name, nd);
}
nd->flags = flags;
nd->depth = 0;
- nd->path.mnt = mntget(mnt);
- nd->path.dentry = dget(dentry);
+ nd->path.dentry = dentry;
+ nd->path.mnt = mnt;
+ path_get(&nd->path);
retval = path_walk(name, nd);
if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry &&
{
struct nameidata nd;
void *cookie;
+ int res;
nd.depth = 0;
cookie = dentry->d_inode->i_op->follow_link(dentry, &nd);
- if (!IS_ERR(cookie)) {
- int res = vfs_readlink(dentry, buffer, buflen, nd_get_link(&nd));
- if (dentry->d_inode->i_op->put_link)
- dentry->d_inode->i_op->put_link(dentry, &nd, cookie);
- cookie = ERR_PTR(res);
- }
- return PTR_ERR(cookie);
+ if (IS_ERR(cookie))
+ return PTR_ERR(cookie);
+
+ res = vfs_readlink(dentry, buffer, buflen, nd_get_link(&nd));
+ if (dentry->d_inode->i_op->put_link)
+ dentry->d_inode->i_op->put_link(dentry, &nd, cookie);
+ return res;
}
int vfs_follow_link(struct nameidata *nd, const char *link)
void free_write_pipe(struct file *f)
{
free_pipe_info(f->f_dentry->d_inode);
- dput(f->f_path.dentry);
- mntput(f->f_path.mnt);
+ path_put(&f->f_path);
put_filp(f);
}
return ERR_PTR(-ENFILE);
/* Grab pipe from the writer */
- f->f_path.mnt = mntget(wrf->f_path.mnt);
- f->f_path.dentry = dget(wrf->f_path.dentry);
+ f->f_path = wrf->f_path;
+ path_get(&wrf->f_path);
f->f_mapping = wrf->f_path.dentry->d_inode->i_mapping;
f->f_pos = 0;
err_fdr:
put_unused_fd(fdr);
err_read_pipe:
- dput(fr->f_dentry);
- mntput(fr->f_vfsmnt);
+ path_put(&fr->f_path);
put_filp(fr);
err_write_pipe:
free_write_pipe(fw);
#endif
-static bool nsec_special(long nsec)
-{
- return nsec == UTIME_OMIT || nsec == UTIME_NOW;
-}
-
static bool nsec_valid(long nsec)
{
- if (nsec_special(nsec))
+ if (nsec == UTIME_OMIT || nsec == UTIME_NOW)
return true;
return nsec >= 0 && nsec <= 999999999;
if (error)
goto dput_and_out;
- /* Don't worry, the checks are done in inode_change_ok() */
+ if (times && times[0].tv_nsec == UTIME_NOW &&
+ times[1].tv_nsec == UTIME_NOW)
+ times = NULL;
+
+ /* In most cases, the checks are done in inode_change_ok() */
newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME;
if (times) {
error = -EPERM;
newattrs.ia_mtime.tv_nsec = times[1].tv_nsec;
newattrs.ia_valid |= ATTR_MTIME_SET;
}
- }
- /*
- * If times is NULL or both times are either UTIME_OMIT or
- * UTIME_NOW, then need to check permissions, because
- * inode_change_ok() won't do it.
- */
- if (!times || (nsec_special(times[0].tv_nsec) &&
- nsec_special(times[1].tv_nsec))) {
+ /*
+ * For the UTIME_OMIT/UTIME_NOW and UTIME_NOW/UTIME_OMIT
+ * cases, we need to make an extra check that is not done by
+ * inode_change_ok().
+ */
+ if (((times[0].tv_nsec == UTIME_NOW &&
+ times[1].tv_nsec == UTIME_OMIT)
+ ||
+ (times[0].tv_nsec == UTIME_OMIT &&
+ times[1].tv_nsec == UTIME_NOW))
+ && !is_owner_or_cap(inode))
+ goto mnt_drop_write_and_out;
+ } else {
+
+ /*
+ * If times is NULL (or both times are UTIME_NOW),
+ * then we need to check permissions, because
+ * inode_change_ok() won't do it.
+ */
error = -EACCES;
if (IS_IMMUTABLE(inode))
goto mnt_drop_write_and_out;
if (!is_owner_or_cap(inode)) {
- if (f) {
- if (!(f->f_mode & FMODE_WRITE))
- goto mnt_drop_write_and_out;
- } else {
- error = vfs_permission(&nd, MAY_WRITE);
- if (error)
- goto mnt_drop_write_and_out;
- }
+ error = permission(inode, MAY_WRITE, NULL);
+ if (error)
+ goto mnt_drop_write_and_out;
}
}
mutex_lock(&inode->i_mutex);
if (utimes) {
if (copy_from_user(&tstimes, utimes, sizeof(tstimes)))
return -EFAULT;
- if ((tstimes[0].tv_nsec == UTIME_OMIT ||
- tstimes[0].tv_nsec == UTIME_NOW) &&
- tstimes[0].tv_sec != 0)
- return -EINVAL;
- if ((tstimes[1].tv_nsec == UTIME_OMIT ||
- tstimes[1].tv_nsec == UTIME_NOW) &&
- tstimes[1].tv_sec != 0)
- return -EINVAL;
/* Nothing to do, we must not even check the path. */
if (tstimes[0].tv_nsec == UTIME_OMIT &&
#define __get_cpu_var(var) per_cpu_var(var)
#define __raw_get_cpu_var(var) per_cpu_var(var)
+#define PER_CPU_ATTRIBUTES
+
#endif /* SMP */
#define DECLARE_PER_CPU(type, name) extern __typeof__(type) per_cpu_var(name)
#include <linux/kvm_para.h>
#include <linux/kvm_types.h>
+#include <asm/pvclock-abi.h>
#include <asm/desc.h>
#define KVM_MAX_VCPUS 16
struct x86_emulate_ctxt emulate_ctxt;
gpa_t time;
- struct kvm_vcpu_time_info hv_clock;
+ struct pvclock_vcpu_time_info hv_clock;
+ unsigned int hv_clock_tsc_khz;
unsigned int time_offset;
struct page *time_page;
};
#ifdef __KERNEL__
#include <asm/processor.h>
-/* xen binary-compatible interface. See xen headers for details */
-struct kvm_vcpu_time_info {
- uint32_t version;
- uint32_t pad0;
- uint64_t tsc_timestamp;
- uint64_t system_time;
- uint32_t tsc_to_system_mul;
- int8_t tsc_shift;
- int8_t pad[3];
-} __attribute__((__packed__)); /* 32 bytes */
-
-struct kvm_wall_clock {
- uint32_t wc_version;
- uint32_t wc_sec;
- uint32_t wc_nsec;
-} __attribute__((__packed__));
-
-
extern void kvmclock_init(void);
--- /dev/null
+#ifndef _ASM_X86_PVCLOCK_ABI_H_
+#define _ASM_X86_PVCLOCK_ABI_H_
+#ifndef __ASSEMBLY__
+
+/*
+ * These structs MUST NOT be changed.
+ * They are the ABI between hypervisor and guest OS.
+ * Both Xen and KVM are using this.
+ *
+ * pvclock_vcpu_time_info holds the system time and the tsc timestamp
+ * of the last update. So the guest can use the tsc delta to get a
+ * more precise system time. There is one per virtual cpu.
+ *
+ * pvclock_wall_clock references the point in time when the system
+ * time was zero (usually boot time), thus the guest calculates the
+ * current wall clock by adding the system time.
+ *
+ * Protocol for the "version" fields is: hypervisor raises it (making
+ * it uneven) before it starts updating the fields and raises it again
+ * (making it even) when it is done. Thus the guest can make sure the
+ * time values it got are consistent by checking the version before
+ * and after reading them.
+ */
+
+struct pvclock_vcpu_time_info {
+ u32 version;
+ u32 pad0;
+ u64 tsc_timestamp;
+ u64 system_time;
+ u32 tsc_to_system_mul;
+ s8 tsc_shift;
+ u8 pad[3];
+} __attribute__((__packed__)); /* 32 bytes */
+
+struct pvclock_wall_clock {
+ u32 version;
+ u32 sec;
+ u32 nsec;
+} __attribute__((__packed__));
+
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_X86_PVCLOCK_ABI_H_ */
--- /dev/null
+#ifndef _ASM_X86_PVCLOCK_H_
+#define _ASM_X86_PVCLOCK_H_
+
+#include <linux/clocksource.h>
+#include <asm/pvclock-abi.h>
+
+/* some helper functions for xen and kvm pv clock sources */
+cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src);
+void pvclock_read_wallclock(struct pvclock_wall_clock *wall,
+ struct pvclock_vcpu_time_info *vcpu,
+ struct timespec *ts);
+
+#endif /* _ASM_X86_PVCLOCK_H_ */
return (pte_t) { .pte = x };
}
-#ifdef CONFIG_X86_PAE
#define pmd_val_ma(v) ((v).pmd)
#define pud_val_ma(v) ((v).pgd.pgd)
#define __pmd_ma(x) ((pmd_t) { (x) } )
-#else /* !X86_PAE */
-#define pmd_val_ma(v) ((v).pud.pgd.pgd)
-#endif /* CONFIG_X86_PAE */
#define pgd_val_ma(x) ((x).pgd)
extern int audit_update_lsm_rules(void);
/* Private API (for audit.c only) */
-extern int audit_filter_user(struct netlink_skb_parms *cb, int type);
+extern int audit_filter_user(struct netlink_skb_parms *cb);
extern int audit_filter_type(int type);
extern int audit_receive_filter(int type, int pid, int uid, int seq,
void *data, size_t datasz, uid_t loginuid,
extern char *dynamic_dname(struct dentry *, char *, int, const char *, ...);
extern char *__d_path(const struct path *path, struct path *root, char *, int);
-extern char *d_path(struct path *, char *, int);
+extern char *d_path(const struct path *, char *, int);
extern char *dentry_path(struct dentry *, char *, int);
/* Allocation counts.. */
typedef struct files_struct *fl_owner_t;
struct file_lock_operations {
- void (*fl_insert)(struct file_lock *); /* lock insertion callback */
- void (*fl_remove)(struct file_lock *); /* lock removal callback */
void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
void (*fl_release_private)(struct file_lock *);
};
#define KVM_REQ_REPORT_TPR_ACCESS 2
#define KVM_REQ_MMU_RELOAD 3
#define KVM_REQ_TRIPLE_FAULT 4
+#define KVM_REQ_PENDING_TIMER 5
struct kvm_vcpu;
extern struct kmem_cache *kvm_vcpu_cache;
#define __XEN_PUBLIC_XEN_H__
#include <asm/xen/interface.h>
+#include <asm/pvclock-abi.h>
/*
* XEN "SYSTEM CALLS" (a.k.a. HYPERCALLS).
uint8_t evtchn_upcall_mask;
unsigned long evtchn_pending_sel;
struct arch_vcpu_info arch;
- struct vcpu_time_info time;
+ struct pvclock_vcpu_time_info time;
}; /* 64 bytes (x86) */
/*
* Wallclock time: updated only by control software. Guests should base
* their gettimeofday() syscall on this wallclock-base value.
*/
- uint32_t wc_version; /* Version counter: see vcpu_time_info_t. */
- uint32_t wc_sec; /* Secs 00:00:00 UTC, Jan 1, 1970. */
- uint32_t wc_nsec; /* Nsecs 00:00:00 UTC, Jan 1, 1970. */
+ struct pvclock_wall_clock wc;
struct arch_shared_info arch;
if (!audit_enabled && msg_type != AUDIT_USER_AVC)
return 0;
- err = audit_filter_user(&NETLINK_CB(skb), msg_type);
+ err = audit_filter_user(&NETLINK_CB(skb));
if (err == 1) {
err = 0;
if (msg_type == AUDIT_USER_TTY) {
}
/* fallthrough */
case AUDIT_LIST:
- err = audit_receive_filter(nlh->nlmsg_type, NETLINK_CB(skb).pid,
+ err = audit_receive_filter(msg_type, NETLINK_CB(skb).pid,
uid, seq, data, nlmsg_len(nlh),
loginuid, sessionid, sid);
break;
}
/* fallthrough */
case AUDIT_LIST_RULES:
- err = audit_receive_filter(nlh->nlmsg_type, NETLINK_CB(skb).pid,
+ err = audit_receive_filter(msg_type, NETLINK_CB(skb).pid,
uid, seq, data, nlmsg_len(nlh),
loginuid, sessionid, sid);
break;
* @data: payload data
* @datasz: size of payload data
* @loginuid: loginuid of sender
+ * @sessionid: sessionid for netlink audit message
* @sid: SE Linux Security ID of sender
*/
int audit_receive_filter(int type, int pid, int uid, int seq, void *data,
return 1;
}
-int audit_filter_user(struct netlink_skb_parms *cb, int type)
+int audit_filter_user(struct netlink_skb_parms *cb)
{
enum audit_state state = AUDIT_DISABLED;
struct audit_entry *e;
return 1;
}
-void kgdb_console_write(struct console *co, const char *s, unsigned count)
+static void kgdb_console_write(struct console *co, const char *s,
+ unsigned count)
{
unsigned long flags;
}
}
-static int get_eoi_gsi(struct kvm_ioapic *ioapic, int vector)
+static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int gsi)
{
- int i;
-
- for (i = 0; i < IOAPIC_NUM_PINS; i++)
- if (ioapic->redirtbl[i].fields.vector == vector)
- return i;
- return -1;
-}
-
-void kvm_ioapic_update_eoi(struct kvm *kvm, int vector)
-{
- struct kvm_ioapic *ioapic = kvm->arch.vioapic;
union ioapic_redir_entry *ent;
- int gsi;
-
- gsi = get_eoi_gsi(ioapic, vector);
- if (gsi == -1) {
- printk(KERN_WARNING "Can't find redir item for %d EOI\n",
- vector);
- return;
- }
ent = &ioapic->redirtbl[gsi];
ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
ioapic_deliver(ioapic, gsi);
}
+void kvm_ioapic_update_eoi(struct kvm *kvm, int vector)
+{
+ struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+ int i;
+
+ for (i = 0; i < IOAPIC_NUM_PINS; i++)
+ if (ioapic->redirtbl[i].fields.vector == vector)
+ __kvm_ioapic_update_eoi(ioapic, i);
+}
+
static int ioapic_in_range(struct kvm_io_device *this, gpa_t addr)
{
struct kvm_ioapic *ioapic = (struct kvm_ioapic *)this->private;