* 'x86-vdso-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-tip:
x86-64: Rework vsyscall emulation and add vsyscall= parameter
x86-64: Wire up getcpu syscall
x86: Remove unnecessary compile flag tweaks for vsyscall code
x86-64: Add vsyscall:emulate_vsyscall trace event
x86-64: Add user_64bit_mode paravirt op
x86-64, xen: Enable the vvar mapping
x86-64: Work around gold bug 13023
x86-64: Move the "user" vsyscall segment out of the data segment.
x86-64: Pad vDSO to a page boundary
See also Documentation/power/pm.txt, pci=noacpi
+ acpi_rsdp= [ACPI,EFI,KEXEC]
+ Pass the RSDP address to the kernel, mostly used
+ on machines running EFI runtime service to boot the
+ second kernel for kdump.
+
acpi_apic_instance= [ACPI, IOAPIC]
Format: <int>
2: use 2nd APIC table, if available
/proc/<pid>/coredump_filter.
See also Documentation/filesystems/proc.txt.
+ cpuidle.off=1 [CPU_IDLE]
+ disable the cpuidle sub-system
+
cpcihp_generic= [HW,PCI] Generic port I/O CompactPCI driver
Format:
<first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>]
for all guests.
Default is 1 (enabled) if in 64bit or 32bit-PAE mode
- kvm-intel.bypass_guest_pf=
- [KVM,Intel] Disables bypassing of guest page faults
- on Intel chips. Default is 1 (enabled)
-
kvm-intel.ept= [KVM,Intel] Disable extended page tables
(virtualized MMU) support on capable Intel chips.
Default is 1 (enabled)
no-kvmapf [X86,KVM] Disable paravirtualized asynchronous page
fault handling.
+ no-steal-acc [X86,KVM] Disable paravirtualized steal time accounting.
+ steal time is computed, but won't influence scheduler
+ behaviour
+
nolapic [X86-32,APIC] Do not enable or use the local APIC.
nolapic_timer [X86-32,APIC] Do not use the local APIC timer.
See Documentation/sound/oss/oss-parameters.txt
panic= [KNL] Kernel behaviour on panic: delay <timeout>
- seconds before rebooting
+ timeout > 0: seconds before rebooting
+ timeout = 0: wait forever
+ timeout < 0: reboot immediately
Format: <timeout>
parkbd.port= [HW] Parallel port number the keyboard adapter is
[HW,MOUSE] Controls Logitech smartscroll autorepeat.
0 = disabled, 1 = enabled (default).
+ pstore.backend= Specify the name of the pstore backend to use
+
pt. [PARIDE]
See Documentation/blockdev/paride.txt.
ro [KNL] Mount root device read-only on boot
root= [KNL] Root filesystem
+ See name_to_dev_t comment in init/do_mounts.c.
rootdelay= [KNL] Delay (in seconds) to pause before attempting to
mount the root filesystem
<port#>,<js1>,<js2>,<js3>,<js4>,<js5>,<js6>,<js7>
See also Documentation/input/joystick-parport.txt
+ udbg-immortal [PPC] When debugging early kernel crashes that
+ happen after console_init() and before a proper
+ console driver takes over, this boot options might
+ help "seeing" what's going on.
+
uhash_entries= [KNL,NET]
Set number of hash buckets for UDP/UDP-Lite connections
unknown_nmi_panic
[X86] Cause panic on unknown NMI.
+ usbcore.authorized_default=
+ [USB] Default USB device authorization:
+ (default -1 = authorized except for wireless USB,
+ 0 = not authorized, 1 = authorized)
+
usbcore.autosuspend=
[USB] The autosuspend time delay (in seconds) used
for newly-detected USB devices (default 2). This
vmpoff= [KNL,S390] Perform z/VM CP command after power off.
Format: <command>
+ vsyscall= [X86-64]
+ Controls the behavior of vsyscalls (i.e. calls to
+ fixed addresses of 0xffffffffff600x00 from legacy
+ code). Most statically-linked binaries and older
+ versions of glibc use these calls. Because these
+ functions are at fixed addresses, they make nice
+ targets for exploits that can control RIP.
+
+ emulate [default] Vsyscalls turn into traps and are
+ emulated reasonably safely.
+
+ native Vsyscalls are native syscall instructions.
+ This is a little bit faster than trapping
+ and makes a few dynamic recompilers work
+ better than they would in emulation mode.
+ It also makes exploits much easier to write.
+
+ none Vsyscalls don't work at all. This makes
+ them quite hard to use for exploits but
+ might break your system.
+
vt.cur_default= [VT] Default cursor shape.
Format: 0xCCBBAA, where AA, BB, and CC are the same as
the parameters of the <Esc>[?A;B;Cc escape sequence;
* Vectors 0 ... 31 : system traps and exceptions - hardcoded events
* Vectors 32 ... 127 : device interrupts
* Vector 128 : legacy int80 syscall interface
- * 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
*
#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
#include <asm/desc_defs.h>
#include <asm/kmap_types.h>
+ #include <asm/pgtable_types.h>
struct page;
struct thread_struct;
struct pv_info {
unsigned int kernel_rpl;
int shared_kernel_pmd;
+
+ #ifdef CONFIG_X86_64
+ u16 extra_user_64bit_cs; /* __USER_CS if none */
+ #endif
+
int paravirt_enabled;
const char *name;
};
struct pv_time_ops {
unsigned long long (*sched_clock)(void);
+ unsigned long long (*steal_clock)(int cpu);
unsigned long (*get_tsc_khz)(void);
};
CFLAGS_REMOVE_early_printk.o = -pg
endif
- #
- # vsyscalls (which work on the user stack) should have
- # no stack-protector checks:
- #
- nostackp := $(call cc-option, -fno-stack-protector)
- CFLAGS_vsyscall_64.o := $(PROFILING) -g0 $(nostackp)
- CFLAGS_hpet.o := $(nostackp)
- CFLAGS_paravirt.o := $(nostackp)
- GCOV_PROFILE_vsyscall_64.o := n
- GCOV_PROFILE_hpet.o := n
- GCOV_PROFILE_tsc.o := n
- GCOV_PROFILE_paravirt.o := n
-
obj-y := process_$(BITS).o signal.o entry_$(BITS).o
obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
obj-y += time.o ioport.o ldt.o dumpstack.o
obj-$(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
.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 */
__native_flush_tlb_single(addr);
}
+struct jump_label_key paravirt_steal_enabled;
+struct jump_label_key paravirt_steal_rq_enabled;
+
+static u64 native_steal_clock(int cpu)
+{
+ return 0;
+}
+
/* These are in entry.S */
extern void native_iret(void);
extern void native_irq_enable_sysexit(void);
.paravirt_enabled = 0,
.kernel_rpl = 0,
.shared_kernel_pmd = 1, /* Only used when CONFIG_X86_PAE is set */
+
+ #ifdef CONFIG_X86_64
+ .extra_user_64bit_cs = __USER_CS,
+ #endif
};
struct pv_init_ops pv_init_ops = {
struct pv_time_ops pv_time_ops = {
.sched_clock = native_sched_clock,
+ .steal_clock = native_steal_clock,
};
struct pv_irq_ops pv_irq_ops = {
#include <asm/stacktrace.h>
#include <asm/processor.h>
#include <asm/debugreg.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
#include <asm/system.h>
#include <asm/traps.h>
#include <asm/desc.h>
set_bit(SYSCALL_VECTOR, used_vectors);
#endif
- #ifdef CONFIG_X86_64
- BUG_ON(test_bit(VSYSCALL_EMU_VECTOR, used_vectors));
- set_system_intr_gate(VSYSCALL_EMU_VECTOR, &emulate_vsyscall);
- set_bit(VSYSCALL_EMU_VECTOR, used_vectors);
- #endif
-
/*
* Should be a barrier for any external CPU state:
*/
* but for now it's good enough to assume that long
* mode only uses well known segments or kernel.
*/
- return (!user_mode(regs)) || (regs->cs == __USER_CS);
+ return (!user_mode(regs) || user_64bit_mode(regs));
#endif
case 0x60:
/* 0x64 thru 0x67 are valid prefixes in all modes. */
if (is_errata100(regs, address))
return;
+ #ifdef CONFIG_X86_64
+ /*
+ * Instruction fetch faults in the vsyscall page might need
+ * emulation.
+ */
+ if (unlikely((error_code & PF_INSTR) &&
+ ((address & ~0xfff) == VSYSCALL_START))) {
+ if (emulate_vsyscall(regs, address))
+ return;
+ }
+ #endif
+
if (unlikely(show_unhandled_signals))
show_signal_msg(regs, error_code, address, tsk);
if (unlikely(error_code & PF_RSVD))
pgtable_bad(regs, error_code, address);
- perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
/*
* If we're in an interrupt, have no user context or are running
if (flags & FAULT_FLAG_ALLOW_RETRY) {
if (fault & VM_FAULT_MAJOR) {
tsk->maj_flt++;
- perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
regs, address);
} else {
tsk->min_flt++;
- perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
regs, address);
}
if (fault & VM_FAULT_RETRY) {
struct mmuext_op *op;
struct multicall_space mcs = xen_mc_entry(sizeof(*op));
+ trace_xen_cpu_set_ldt(addr, entries);
+
op = mcs.args;
op->cmd = MMUEXT_SET_LDT;
op->arg1.linear_addr = (unsigned long)addr;
xmaddr_t mach_lp = arbitrary_virt_to_machine(&dt[entrynum]);
u64 entry = *(u64 *)ptr;
+ trace_xen_cpu_write_ldt_entry(dt, entrynum, entry);
+
preempt_disable();
xen_mc_flush();
unsigned long p = (unsigned long)&dt[entrynum];
unsigned long start, end;
+ trace_xen_cpu_write_idt_entry(dt, entrynum, g);
+
preempt_disable();
start = __this_cpu_read(idt_desc.address);
static DEFINE_SPINLOCK(lock);
static struct trap_info traps[257];
+ trace_xen_cpu_load_idt(desc);
+
spin_lock(&lock);
__get_cpu_var(idt_desc) = *desc;
static void xen_write_gdt_entry(struct desc_struct *dt, int entry,
const void *desc, int type)
{
+ trace_xen_cpu_write_gdt_entry(dt, entry, desc, type);
+
preempt_disable();
switch (type) {
static void __init xen_write_gdt_entry_boot(struct desc_struct *dt, int entry,
const void *desc, int type)
{
+ trace_xen_cpu_write_gdt_entry(dt, entry, desc, type);
+
switch (type) {
case DESC_LDT:
case DESC_TSS:
static void xen_load_sp0(struct tss_struct *tss,
struct thread_struct *thread)
{
- struct multicall_space mcs = xen_mc_entry(0);
+ struct multicall_space mcs;
+
+ mcs = xen_mc_entry(0);
MULTI_stack_switch(mcs.mc, __KERNEL_DS, thread->sp0);
xen_mc_issue(PARAVIRT_LAZY_CPU);
}
.paravirt_enabled = 1,
.shared_kernel_pmd = 0,
+ #ifdef CONFIG_X86_64
+ .extra_user_64bit_cs = FLAT_USER_CS64,
+ #endif
+
.name = "Xen",
};
if (pci_xen)
x86_init.pci.arch_init = pci_xen_init;
} else {
+ const struct dom0_vga_console_info *info =
+ (void *)((char *)xen_start_info +
+ xen_start_info->console.dom0.info_off);
+
+ xen_init_vga(info, xen_start_info->console.dom0.info_size);
+ xen_start_info->console.domU.mfn = 0;
+ xen_start_info->console.domU.evtchn = 0;
+
/* Make sure ACS will be enabled */
pci_request_acs();
}
#include <linux/memblock.h>
#include <linux/seq_file.h>
+#include <trace/events/xen.h>
+
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/fixmap.h>
struct multicall_space mcs;
struct mmu_update *u;
+ trace_xen_mmu_set_domain_pte(ptep, pteval, domid);
+
mcs = xen_mc_entry(sizeof(*u));
u = mcs.args;
*u = *update;
}
+static void xen_extend_mmuext_op(const struct mmuext_op *op)
+{
+ struct multicall_space mcs;
+ struct mmuext_op *u;
+
+ mcs = xen_mc_extend_args(__HYPERVISOR_mmuext_op, sizeof(*u));
+
+ if (mcs.mc != NULL) {
+ mcs.mc->args[1]++;
+ } else {
+ mcs = __xen_mc_entry(sizeof(*u));
+ MULTI_mmuext_op(mcs.mc, mcs.args, 1, NULL, DOMID_SELF);
+ }
+
+ u = mcs.args;
+ *u = *op;
+}
+
static void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val)
{
struct mmu_update u;
static void xen_set_pmd(pmd_t *ptr, pmd_t val)
{
+ trace_xen_mmu_set_pmd(ptr, val);
+
/* If page is not pinned, we can just update the entry
directly */
if (!xen_page_pinned(ptr)) {
return true;
}
-static void xen_set_pte(pte_t *ptep, pte_t pteval)
+static inline void __xen_set_pte(pte_t *ptep, pte_t pteval)
{
if (!xen_batched_set_pte(ptep, pteval))
native_set_pte(ptep, pteval);
}
+static void xen_set_pte(pte_t *ptep, pte_t pteval)
+{
+ trace_xen_mmu_set_pte(ptep, pteval);
+ __xen_set_pte(ptep, pteval);
+}
+
static void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pteval)
{
- xen_set_pte(ptep, pteval);
+ trace_xen_mmu_set_pte_at(mm, addr, ptep, pteval);
+ __xen_set_pte(ptep, pteval);
}
pte_t xen_ptep_modify_prot_start(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
/* Just return the pte as-is. We preserve the bits on commit */
+ trace_xen_mmu_ptep_modify_prot_start(mm, addr, ptep, *ptep);
return *ptep;
}
{
struct mmu_update u;
+ trace_xen_mmu_ptep_modify_prot_commit(mm, addr, ptep, pte);
xen_mc_batch();
u.ptr = virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;
static void xen_set_pud(pud_t *ptr, pud_t val)
{
+ trace_xen_mmu_set_pud(ptr, val);
+
/* If page is not pinned, we can just update the entry
directly */
if (!xen_page_pinned(ptr)) {
#ifdef CONFIG_X86_PAE
static void xen_set_pte_atomic(pte_t *ptep, pte_t pte)
{
+ trace_xen_mmu_set_pte_atomic(ptep, pte);
set_64bit((u64 *)ptep, native_pte_val(pte));
}
static void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
{
+ trace_xen_mmu_pte_clear(mm, addr, ptep);
if (!xen_batched_set_pte(ptep, native_make_pte(0)))
native_pte_clear(mm, addr, ptep);
}
static void xen_pmd_clear(pmd_t *pmdp)
{
+ trace_xen_mmu_pmd_clear(pmdp);
set_pmd(pmdp, __pmd(0));
}
#endif /* CONFIG_X86_PAE */
{
pgd_t *user_ptr = xen_get_user_pgd(ptr);
+ trace_xen_mmu_set_pgd(ptr, user_ptr, val);
+
/* If page is not pinned, we can just update the entry
directly */
if (!xen_page_pinned(ptr)) {
static void xen_do_pin(unsigned level, unsigned long pfn)
{
- struct mmuext_op *op;
- struct multicall_space mcs;
+ struct mmuext_op op;
- mcs = __xen_mc_entry(sizeof(*op));
- op = mcs.args;
- op->cmd = level;
- op->arg1.mfn = pfn_to_mfn(pfn);
- MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+ op.cmd = level;
+ op.arg1.mfn = pfn_to_mfn(pfn);
+
+ xen_extend_mmuext_op(&op);
}
static int xen_pin_page(struct mm_struct *mm, struct page *page,
read-only, and can be pinned. */
static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
{
+ trace_xen_mmu_pgd_pin(mm, pgd);
+
xen_mc_batch();
if (__xen_pgd_walk(mm, pgd, xen_pin_page, USER_LIMIT)) {
/* Release a pagetables pages back as normal RW */
static void __xen_pgd_unpin(struct mm_struct *mm, pgd_t *pgd)
{
+ trace_xen_mmu_pgd_unpin(mm, pgd);
+
xen_mc_batch();
xen_do_pin(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
struct mmuext_op *op;
struct multicall_space mcs;
+ trace_xen_mmu_flush_tlb(0);
+
preempt_disable();
mcs = xen_mc_entry(sizeof(*op));
struct mmuext_op *op;
struct multicall_space mcs;
+ trace_xen_mmu_flush_tlb_single(addr);
+
preempt_disable();
mcs = xen_mc_entry(sizeof(*op));
} *args;
struct multicall_space mcs;
+ trace_xen_mmu_flush_tlb_others(cpus, mm, va);
+
if (cpumask_empty(cpus))
return; /* nothing to do */
static void __xen_write_cr3(bool kernel, unsigned long cr3)
{
- struct mmuext_op *op;
- struct multicall_space mcs;
+ struct mmuext_op op;
unsigned long mfn;
+ trace_xen_mmu_write_cr3(kernel, cr3);
+
if (cr3)
mfn = pfn_to_mfn(PFN_DOWN(cr3));
else
WARN_ON(mfn == 0 && kernel);
- mcs = __xen_mc_entry(sizeof(*op));
-
- op = mcs.args;
- op->cmd = kernel ? MMUEXT_NEW_BASEPTR : MMUEXT_NEW_USER_BASEPTR;
- op->arg1.mfn = mfn;
+ op.cmd = kernel ? MMUEXT_NEW_BASEPTR : MMUEXT_NEW_USER_BASEPTR;
+ op.arg1.mfn = mfn;
- MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+ xen_extend_mmuext_op(&op);
if (kernel) {
percpu_write(xen_cr3, cr3);
make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
}
+static inline void __pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
+{
+ struct multicall_space mcs;
+ struct mmuext_op *op;
+
+ mcs = __xen_mc_entry(sizeof(*op));
+ op = mcs.args;
+ op->cmd = cmd;
+ op->arg1.mfn = pfn_to_mfn(pfn);
+
+ MULTI_mmuext_op(mcs.mc, mcs.args, 1, NULL, DOMID_SELF);
+}
+
+static inline void __set_pfn_prot(unsigned long pfn, pgprot_t prot)
+{
+ struct multicall_space mcs;
+ unsigned long addr = (unsigned long)__va(pfn << PAGE_SHIFT);
+
+ mcs = __xen_mc_entry(0);
+ MULTI_update_va_mapping(mcs.mc, (unsigned long)addr,
+ pfn_pte(pfn, prot), 0);
+}
+
/* This needs to make sure the new pte page is pinned iff its being
attached to a pinned pagetable. */
-static void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, unsigned level)
+static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,
+ unsigned level)
{
- struct page *page = pfn_to_page(pfn);
+ bool pinned = PagePinned(virt_to_page(mm->pgd));
+
+ trace_xen_mmu_alloc_ptpage(mm, pfn, level, pinned);
+
+ if (pinned) {
+ struct page *page = pfn_to_page(pfn);
- if (PagePinned(virt_to_page(mm->pgd))) {
SetPagePinned(page);
if (!PageHighMem(page)) {
- make_lowmem_page_readonly(__va(PFN_PHYS((unsigned long)pfn)));
+ xen_mc_batch();
+
+ __set_pfn_prot(pfn, PAGE_KERNEL_RO);
+
if (level == PT_PTE && USE_SPLIT_PTLOCKS)
- pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
+ __pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
+
+ xen_mc_issue(PARAVIRT_LAZY_MMU);
} else {
/* make sure there are no stray mappings of
this page */
}
/* This should never happen until we're OK to use struct page */
-static void xen_release_ptpage(unsigned long pfn, unsigned level)
+static inline void xen_release_ptpage(unsigned long pfn, unsigned level)
{
struct page *page = pfn_to_page(pfn);
+ bool pinned = PagePinned(page);
- if (PagePinned(page)) {
+ trace_xen_mmu_release_ptpage(pfn, level, pinned);
+
+ if (pinned) {
if (!PageHighMem(page)) {
+ xen_mc_batch();
+
if (level == PT_PTE && USE_SPLIT_PTLOCKS)
- pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
- make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
+ __pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
+
+ __set_pfn_prot(pfn, PAGE_KERNEL);
+
+ xen_mc_issue(PARAVIRT_LAZY_MMU);
}
ClearPagePinned(page);
}
# endif
#else
case VSYSCALL_LAST_PAGE ... VSYSCALL_FIRST_PAGE:
+ case VVAR_PAGE:
#endif
case FIX_TEXT_POKE0:
case FIX_TEXT_POKE1:
#ifdef CONFIG_X86_64
/* Replicate changes to map the vsyscall page into the user
pagetable vsyscall mapping. */
- if (idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) {
+ if ((idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) ||
+ idx == VVAR_PAGE) {
unsigned long vaddr = __fix_to_virt(idx);
set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte);
}