#define PAGE_READONLY_EXEC _MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_RDONLY)
#define PAGE_KERNEL _MOD_PROT(pgprot_kernel, L_PTE_XN)
#define PAGE_KERNEL_EXEC pgprot_kernel
- #define PAGE_HYP _MOD_PROT(pgprot_kernel, L_PTE_HYP)
+ #define PAGE_HYP _MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_XN)
+ #define PAGE_HYP_EXEC _MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_RDONLY)
+ #define PAGE_HYP_RO _MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_RDONLY | L_PTE_XN)
#define PAGE_HYP_DEVICE _MOD_PROT(pgprot_hyp_device, L_PTE_HYP)
#define PAGE_S2 _MOD_PROT(pgprot_s2, L_PTE_S2_RDONLY)
#define PAGE_S2_DEVICE _MOD_PROT(pgprot_s2_device, L_PTE_S2_RDONLY)
#define pgd_offset_k(addr) pgd_offset(&init_mm, addr)
#define pmd_none(pmd) (!pmd_val(pmd))
-#define pmd_present(pmd) (pmd_val(pmd))
static inline pte_t *pmd_page_vaddr(pmd_t pmd)
{
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/kvm_host.h>
+ #include <linux/list.h>
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/fs.h>
if (ret)
goto out_fail_alloc;
- ret = create_hyp_mappings(kvm, kvm + 1);
+ ret = create_hyp_mappings(kvm, kvm + 1, PAGE_HYP);
if (ret)
goto out_free_stage2_pgd;
r = KVM_MAX_VCPUS;
break;
default:
- r = kvm_arch_dev_ioctl_check_extension(ext);
+ r = kvm_arch_dev_ioctl_check_extension(kvm, ext);
break;
}
return r;
if (err)
goto free_vcpu;
- err = create_hyp_mappings(vcpu, vcpu + 1);
+ err = create_hyp_mappings(vcpu, vcpu + 1, PAGE_HYP);
if (err)
goto vcpu_uninit;
kvm_timer_vcpu_terminate(vcpu);
kvm_vgic_vcpu_destroy(vcpu);
kvm_pmu_vcpu_destroy(vcpu);
+ kvm_vcpu_uninit(vcpu);
kmem_cache_free(kvm_vcpu_cache, vcpu);
}
/**
* need_new_vmid_gen - check that the VMID is still valid
- * @kvm: The VM's VMID to checkt
+ * @kvm: The VM's VMID to check
*
* return true if there is a new generation of VMIDs being used
*
* Enter the guest
*/
trace_kvm_entry(*vcpu_pc(vcpu));
- __kvm_guest_enter();
+ guest_enter_irqoff();
vcpu->mode = IN_GUEST_MODE;
ret = kvm_call_hyp(__kvm_vcpu_run, vcpu);
local_irq_enable();
/*
- * We do local_irq_enable() before calling kvm_guest_exit() so
+ * We do local_irq_enable() before calling guest_exit() so
* that if a timer interrupt hits while running the guest we
* account that tick as being spent in the guest. We enable
- * preemption after calling kvm_guest_exit() so that if we get
+ * preemption after calling guest_exit() so that if we get
* preempted we make sure ticks after that is not counted as
* guest time.
*/
- kvm_guest_exit();
+ guest_exit();
trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
/*
static void cpu_init_hyp_mode(void *dummy)
{
- phys_addr_t boot_pgd_ptr;
phys_addr_t pgd_ptr;
unsigned long hyp_stack_ptr;
unsigned long stack_page;
/* Switch from the HYP stub to our own HYP init vector */
__hyp_set_vectors(kvm_get_idmap_vector());
- boot_pgd_ptr = kvm_mmu_get_boot_httbr();
pgd_ptr = kvm_mmu_get_httbr();
stack_page = __this_cpu_read(kvm_arm_hyp_stack_page);
hyp_stack_ptr = stack_page + PAGE_SIZE;
vector_ptr = (unsigned long)kvm_ksym_ref(__kvm_hyp_vector);
- __cpu_init_hyp_mode(boot_pgd_ptr, pgd_ptr, hyp_stack_ptr, vector_ptr);
+ __cpu_init_hyp_mode(pgd_ptr, hyp_stack_ptr, vector_ptr);
__cpu_init_stage2();
kvm_arm_init_debug();
static void cpu_hyp_reset(void)
{
- phys_addr_t boot_pgd_ptr;
- phys_addr_t phys_idmap_start;
-
- if (!is_kernel_in_hyp_mode()) {
- boot_pgd_ptr = kvm_mmu_get_boot_httbr();
- phys_idmap_start = kvm_get_idmap_start();
-
- __cpu_reset_hyp_mode(boot_pgd_ptr, phys_idmap_start);
- }
+ if (!is_kernel_in_hyp_mode())
+ __cpu_reset_hyp_mode(hyp_default_vectors,
+ kvm_get_idmap_start());
}
static void _kvm_arch_hardware_enable(void *discard)
* Map the Hyp-code called directly from the host
*/
err = create_hyp_mappings(kvm_ksym_ref(__hyp_text_start),
- kvm_ksym_ref(__hyp_text_end));
+ kvm_ksym_ref(__hyp_text_end), PAGE_HYP_EXEC);
if (err) {
kvm_err("Cannot map world-switch code\n");
goto out_err;
}
err = create_hyp_mappings(kvm_ksym_ref(__start_rodata),
- kvm_ksym_ref(__end_rodata));
+ kvm_ksym_ref(__end_rodata), PAGE_HYP_RO);
if (err) {
kvm_err("Cannot map rodata section\n");
goto out_err;
*/
for_each_possible_cpu(cpu) {
char *stack_page = (char *)per_cpu(kvm_arm_hyp_stack_page, cpu);
- err = create_hyp_mappings(stack_page, stack_page + PAGE_SIZE);
+ err = create_hyp_mappings(stack_page, stack_page + PAGE_SIZE,
+ PAGE_HYP);
if (err) {
kvm_err("Cannot map hyp stack\n");
kvm_cpu_context_t *cpu_ctxt;
cpu_ctxt = per_cpu_ptr(kvm_host_cpu_state, cpu);
- err = create_hyp_mappings(cpu_ctxt, cpu_ctxt + 1);
+ err = create_hyp_mappings(cpu_ctxt, cpu_ctxt + 1, PAGE_HYP);
if (err) {
kvm_err("Cannot map host CPU state: %d\n", err);
}
}
- #ifndef CONFIG_HOTPLUG_CPU
- free_boot_hyp_pgd();
- #endif
-
/* set size of VMID supported by CPU */
kvm_vmid_bits = kvm_get_vmid_bits();
kvm_info("%d-bit VMID\n", kvm_vmid_bits);
#define ARM64_HAS_VIRT_HOST_EXTN 11
#define ARM64_WORKAROUND_CAVIUM_27456 12
#define ARM64_HAS_32BIT_EL0 13
+ #define ARM64_HYP_OFFSET_LOW 14
- #define ARM64_NCAPS 14
+ #define ARM64_NCAPS 15
#ifndef __ASSEMBLY__
void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
const char *info);
+void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps);
void check_local_cpu_errata(void);
+void __init enable_errata_workarounds(void);
void verify_local_cpu_errata(void);
void verify_local_cpu_capabilities(void);
*/
#define HVC_SET_VECTORS 1
+/*
+ * HVC_SOFT_RESTART - CPU soft reset, used by the cpu_soft_restart routine.
+ */
+#define HVC_SOFT_RESTART 2
+
#define BOOT_CPU_MODE_EL1 (0xe11)
#define BOOT_CPU_MODE_EL2 (0xe12)
static inline void verify_cpu_run_el(void) {}
#endif
+ /* The section containing the hypervisor idmap text */
+ extern char __hyp_idmap_text_start[];
+ extern char __hyp_idmap_text_end[];
+
/* The section containing the hypervisor text */
extern char __hyp_text_start[];
extern char __hyp_text_end[];
return is_kernel_in_hyp_mode();
}
+ static bool hyp_offset_low(const struct arm64_cpu_capabilities *entry,
+ int __unused)
+ {
+ phys_addr_t idmap_addr = virt_to_phys(__hyp_idmap_text_start);
+
+ /*
+ * Activate the lower HYP offset only if:
+ * - the idmap doesn't clash with it,
+ * - the kernel is not running at EL2.
+ */
+ return idmap_addr > GENMASK(VA_BITS - 2, 0) && !is_kernel_in_hyp_mode();
+ }
+
static const struct arm64_cpu_capabilities arm64_features[] = {
{
.desc = "GIC system register CPU interface",
.field_pos = ID_AA64PFR0_EL0_SHIFT,
.min_field_value = ID_AA64PFR0_EL0_32BIT_64BIT,
},
+ {
+ .desc = "Reduced HYP mapping offset",
+ .capability = ARM64_HYP_OFFSET_LOW,
+ .def_scope = SCOPE_SYSTEM,
+ .matches = hyp_offset_low,
+ },
{},
};
* Run through the enabled capabilities and enable() it on all active
* CPUs
*/
-static void __init
-enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
+void __init enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
{
for (; caps->matches; caps++)
if (caps->enable && cpus_have_cap(caps->capability))
/* Set the CPU feature capabilies */
setup_feature_capabilities();
+ enable_errata_workarounds();
setup_elf_hwcaps(arm64_elf_hwcaps);
if (system_supports_32bit_el0())
static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
{
u64 esr = read_sysreg_el2(esr);
- u8 ec = esr >> ESR_ELx_EC_SHIFT;
+ u8 ec = ESR_ELx_EC(esr);
u64 hpfar, far;
vcpu->arch.fault.esr_el2 = esr;
static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par)
{
- unsigned long str_va = (unsigned long)__hyp_panic_string;
+ unsigned long str_va;
- __hyp_do_panic(hyp_kern_va(str_va),
+ /*
+ * Force the panic string to be loaded from the literal pool,
+ * making sure it is a kernel address and not a PC-relative
+ * reference.
+ */
+ asm volatile("ldr %0, =__hyp_panic_string" : "=r" (str_va));
+
+ __hyp_do_panic(str_va,
spsr, elr,
read_sysreg(esr_el2), read_sysreg_el2(far),
read_sysreg(hpfar_el2), par,
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
#include <asm/kvm_book3s_asm.h>
#endif
+#include <asm/accounting.h>
+ #include <asm/hmi.h>
register struct paca_struct *local_paca asm("r13");
*/
u16 in_mce;
u8 hmi_event_available; /* HMI event is available */
+ /*
+ * Bitmap for sibling subcore status. See kvm/book3s_hv_ras.c for
+ * more details
+ */
+ struct sibling_subcore_state *sibling_subcore_state;
#endif
/* Stuff for accurate time accounting */
- u64 user_time; /* accumulated usermode TB ticks */
- u64 system_time; /* accumulated system TB ticks */
- u64 user_time_scaled; /* accumulated usermode SPURR ticks */
- u64 starttime; /* TB value snapshot */
- u64 starttime_user; /* TB value on exit to usermode */
- u64 startspurr; /* SPURR value snapshot */
- u64 utime_sspurr; /* ->user_time when ->startspurr set */
+ struct cpu_accounting_data accounting;
u64 stolen_time; /* TB ticks taken by hypervisor */
u64 dtl_ridx; /* read index in dispatch log */
struct dtl_entry *dtl_curr; /* pointer corresponding to dtl_ridx */
obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o
obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o
- obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o
+ obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o hmi.o
-obj64-$(CONFIG_RELOCATABLE) += reloc_64.o
obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o
obj-$(CONFIG_PPC64) += vdso64/
obj-$(CONFIG_ALTIVEC) += vecemu.o
obj-$(CONFIG_PPC_970_NAP) += idle_power4.o
-obj-$(CONFIG_PPC_P7_NAP) += idle_power7.o
+obj-$(CONFIG_PPC_P7_NAP) += idle_book3s.o
procfs-y := proc_powerpc.o
obj-$(CONFIG_PROC_FS) += $(procfs-y)
rtaspci-$(CONFIG_PPC64)-$(CONFIG_PCI) := rtas_pci.o
extra-$(CONFIG_8xx) := head_8xx.o
extra-y += vmlinux.lds
-obj-$(CONFIG_RELOCATABLE_PPC32) += reloc_32.o
+obj-$(CONFIG_RELOCATABLE) += reloc_$(CONFIG_WORD_SIZE).o
obj-$(CONFIG_PPC32) += entry_32.o setup_32.o
obj-$(CONFIG_PPC64) += dma-iommu.o iommu.o
beq 9f
cmpwi cr3,r13,2
-
- /*
- * Check if last bit of HSPGR0 is set. This indicates whether we are
- * waking up from winkle.
- */
GET_PACA(r13)
- clrldi r5,r13,63
- clrrdi r13,r13,1
- cmpwi cr4,r5,1
- mtspr SPRN_HSPRG0,r13
-
- lbz r0,PACA_THREAD_IDLE_STATE(r13)
- cmpwi cr2,r0,PNV_THREAD_NAP
- bgt cr2,8f /* Either sleep or Winkle */
-
- /* Waking up from nap should not cause hypervisor state loss */
- bgt cr3,.
+ bl pnv_restore_hyp_resource
- /* Waking up from nap */
li r0,PNV_THREAD_RUNNING
stb r0,PACA_THREAD_IDLE_STATE(r13) /* Clear thread state */
/* Return SRR1 from power7_nap() */
mfspr r3,SPRN_SRR1
- beq cr3,2f
- b power7_wakeup_noloss
-2: b power7_wakeup_loss
-
- /* Fast Sleep wakeup on PowerNV */
-8: GET_PACA(r13)
- b power7_wakeup_tb_loss
+ blt cr3,2f
+ b pnv_wakeup_loss
+2: b pnv_wakeup_noloss
9:
END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
EXCEPTION_PROLOG_0(PACA_EXGEN)
b h_doorbell_hv
+ . = 0xea0
+hv_virt_irq_trampoline:
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
+ b h_virt_irq_hv
+
/* We need to deal with the Altivec unavailable exception
* here which is at 0xf20, thus in the middle of the
* prolog code of the PerformanceMonitor one. A little
MASKABLE_EXCEPTION_HV_OOL(0xe82, h_doorbell)
KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe82)
+ MASKABLE_EXCEPTION_HV_OOL(0xea2, h_virt_irq)
+ KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xea2)
+
/* moved from 0xf00 */
STD_EXCEPTION_PSERIES_OOL(0xf00, performance_monitor)
KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf00)
BEGIN_FTR_SECTION
cmpwi r3,0xe80
beq h_doorbell_common
+ cmpwi r3,0xea0
+ beq h_virt_irq_common
+ cmpwi r3,0xe60
+ beq hmi_exception_common
FTR_SECTION_ELSE
cmpwi r3,0xa00
beq doorbell_super_common
#else
STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, unknown_exception)
#endif
+ STD_EXCEPTION_COMMON_ASYNC(0xea0, h_virt_irq, do_IRQ)
STD_EXCEPTION_COMMON_ASYNC(0xf00, performance_monitor, performance_monitor_exception)
STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, instruction_breakpoint_exception)
STD_EXCEPTION_COMMON(0x1502, denorm, unknown_exception)
#else
STD_EXCEPTION_COMMON(0x1700, altivec_assist, unknown_exception)
#endif
-#ifdef CONFIG_CBE_RAS
- STD_EXCEPTION_COMMON(0x1200, cbe_system_error, cbe_system_error_exception)
- STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, cbe_maintenance_exception)
- STD_EXCEPTION_COMMON(0x1800, cbe_thermal, cbe_thermal_exception)
-#endif /* CONFIG_CBE_RAS */
/*
* Relocation-on interrupts: A subset of the interrupts can be delivered
EXCEPTION_PROLOG_0(PACA_EXGEN)
b h_doorbell_relon_hv
+ . = 0x4ea0
+h_virt_irq_relon_trampoline:
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
+ b h_virt_irq_relon_hv
+
. = 0x4f00
performance_monitor_relon_pseries_trampoline:
SET_SCRATCH0(r13)
bl vsx_unavailable_exception
b ret_from_except
- STD_EXCEPTION_COMMON(0xf60, facility_unavailable, facility_unavailable_exception)
- STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, facility_unavailable_exception)
-
/* Equivalents to the above handlers for relocation-on interrupt vectors */
STD_RELON_EXCEPTION_HV_OOL(0xe40, emulation_assist)
MASKABLE_RELON_EXCEPTION_HV_OOL(0xe80, h_doorbell)
+ MASKABLE_RELON_EXCEPTION_HV_OOL(0xea0, h_virt_irq)
STD_RELON_EXCEPTION_PSERIES_OOL(0xf00, performance_monitor)
STD_RELON_EXCEPTION_PSERIES_OOL(0xf20, altivec_unavailable)
. = 0x8000
#endif /* defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) */
+ STD_EXCEPTION_COMMON(0xf60, facility_unavailable, facility_unavailable_exception)
+ STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, facility_unavailable_exception)
+
+#ifdef CONFIG_CBE_RAS
+ STD_EXCEPTION_COMMON(0x1200, cbe_system_error, cbe_system_error_exception)
+ STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, cbe_maintenance_exception)
+ STD_EXCEPTION_COMMON(0x1800, cbe_thermal, cbe_thermal_exception)
+#endif /* CONFIG_CBE_RAS */
+
.globl hmi_exception_early
hmi_exception_early:
- EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0xe60)
+ EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST, 0xe62)
mr r10,r1 /* Save r1 */
ld r1,PACAEMERGSP(r13) /* Use emergency stack */
subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */
GET_PACA(r13)
ld r1,PACAR1(r13)
li r3,PNV_THREAD_NAP
- b power7_enter_nap_mode
+ b pnv_enter_arch207_idle_mode
4:
#endif
/*
lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */
mtlr r10
-BEGIN_MMU_FTR_SECTION
- b 2f
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_RADIX)
andi. r10,r12,MSR_RI /* check for unrecoverable exception */
+BEGIN_MMU_FTR_SECTION
beq- 2f
+FTR_SECTION_ELSE
+ b 2f
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX)
.machine push
.machine "power4"
--- /dev/null
- bl opal_rm_handle_hmi; \
+/*
+ * This file contains idle entry/exit functions for POWER7,
+ * POWER8 and POWER9 CPUs.
+ *
+ * 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.
+ */
+
+#include <linux/threads.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/ppc-opcode.h>
+#include <asm/hw_irq.h>
+#include <asm/kvm_book3s_asm.h>
+#include <asm/opal.h>
+#include <asm/cpuidle.h>
+#include <asm/book3s/64/mmu-hash.h>
+#include <asm/mmu.h>
+
+#undef DEBUG
+
+/*
+ * Use unused space in the interrupt stack to save and restore
+ * registers for winkle support.
+ */
+#define _SDR1 GPR3
+#define _RPR GPR4
+#define _SPURR GPR5
+#define _PURR GPR6
+#define _TSCR GPR7
+#define _DSCR GPR8
+#define _AMOR GPR9
+#define _WORT GPR10
+#define _WORC GPR11
+#define _PTCR GPR12
+
+#define PSSCR_HV_TEMPLATE PSSCR_ESL | PSSCR_EC | \
+ PSSCR_PSLL_MASK | PSSCR_TR_MASK | \
+ PSSCR_MTL_MASK
+
+/* Idle state entry routines */
+
+#define IDLE_STATE_ENTER_SEQ(IDLE_INST) \
+ /* Magic NAP/SLEEP/WINKLE mode enter sequence */ \
+ std r0,0(r1); \
+ ptesync; \
+ ld r0,0(r1); \
+1: cmp cr0,r0,r0; \
+ bne 1b; \
+ IDLE_INST; \
+ b .
+
+ .text
+
+/*
+ * Used by threads before entering deep idle states. Saves SPRs
+ * in interrupt stack frame
+ */
+save_sprs_to_stack:
+ /*
+ * Note all register i.e per-core, per-subcore or per-thread is saved
+ * here since any thread in the core might wake up first
+ */
+BEGIN_FTR_SECTION
+ mfspr r3,SPRN_PTCR
+ std r3,_PTCR(r1)
+ /*
+ * Note - SDR1 is dropped in Power ISA v3. Hence not restoring
+ * SDR1 here
+ */
+FTR_SECTION_ELSE
+ mfspr r3,SPRN_SDR1
+ std r3,_SDR1(r1)
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
+ mfspr r3,SPRN_RPR
+ std r3,_RPR(r1)
+ mfspr r3,SPRN_SPURR
+ std r3,_SPURR(r1)
+ mfspr r3,SPRN_PURR
+ std r3,_PURR(r1)
+ mfspr r3,SPRN_TSCR
+ std r3,_TSCR(r1)
+ mfspr r3,SPRN_DSCR
+ std r3,_DSCR(r1)
+ mfspr r3,SPRN_AMOR
+ std r3,_AMOR(r1)
+ mfspr r3,SPRN_WORT
+ std r3,_WORT(r1)
+ mfspr r3,SPRN_WORC
+ std r3,_WORC(r1)
+
+ blr
+
+/*
+ * Used by threads when the lock bit of core_idle_state is set.
+ * Threads will spin in HMT_LOW until the lock bit is cleared.
+ * r14 - pointer to core_idle_state
+ * r15 - used to load contents of core_idle_state
+ */
+
+core_idle_lock_held:
+ HMT_LOW
+3: lwz r15,0(r14)
+ andi. r15,r15,PNV_CORE_IDLE_LOCK_BIT
+ bne 3b
+ HMT_MEDIUM
+ lwarx r15,0,r14
+ blr
+
+/*
+ * Pass requested state in r3:
+ * r3 - PNV_THREAD_NAP/SLEEP/WINKLE in POWER8
+ * - Requested STOP state in POWER9
+ *
+ * To check IRQ_HAPPENED in r4
+ * 0 - don't check
+ * 1 - check
+ *
+ * Address to 'rfid' to in r5
+ */
+_GLOBAL(pnv_powersave_common)
+ /* Use r3 to pass state nap/sleep/winkle */
+ /* NAP is a state loss, we create a regs frame on the
+ * stack, fill it up with the state we care about and
+ * stick a pointer to it in PACAR1. We really only
+ * need to save PC, some CR bits and the NV GPRs,
+ * but for now an interrupt frame will do.
+ */
+ mflr r0
+ std r0,16(r1)
+ stdu r1,-INT_FRAME_SIZE(r1)
+ std r0,_LINK(r1)
+ std r0,_NIP(r1)
+
+ /* Hard disable interrupts */
+ mfmsr r9
+ rldicl r9,r9,48,1
+ rotldi r9,r9,16
+ mtmsrd r9,1 /* hard-disable interrupts */
+
+ /* Check if something happened while soft-disabled */
+ lbz r0,PACAIRQHAPPENED(r13)
+ andi. r0,r0,~PACA_IRQ_HARD_DIS@l
+ beq 1f
+ cmpwi cr0,r4,0
+ beq 1f
+ addi r1,r1,INT_FRAME_SIZE
+ ld r0,16(r1)
+ li r3,0 /* Return 0 (no nap) */
+ mtlr r0
+ blr
+
+1: /* We mark irqs hard disabled as this is the state we'll
+ * be in when returning and we need to tell arch_local_irq_restore()
+ * about it
+ */
+ li r0,PACA_IRQ_HARD_DIS
+ stb r0,PACAIRQHAPPENED(r13)
+
+ /* We haven't lost state ... yet */
+ li r0,0
+ stb r0,PACA_NAPSTATELOST(r13)
+
+ /* Continue saving state */
+ SAVE_GPR(2, r1)
+ SAVE_NVGPRS(r1)
+ mfcr r4
+ std r4,_CCR(r1)
+ std r9,_MSR(r1)
+ std r1,PACAR1(r13)
+
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ /* Tell KVM we're entering idle */
+ li r4,KVM_HWTHREAD_IN_IDLE
+ stb r4,HSTATE_HWTHREAD_STATE(r13)
+#endif
+
+ /*
+ * Go to real mode to do the nap, as required by the architecture.
+ * Also, we need to be in real mode before setting hwthread_state,
+ * because as soon as we do that, another thread can switch
+ * the MMU context to the guest.
+ */
+ LOAD_REG_IMMEDIATE(r7, MSR_IDLE)
+ li r6, MSR_RI
+ andc r6, r9, r6
+ mtmsrd r6, 1 /* clear RI before setting SRR0/1 */
+ mtspr SPRN_SRR0, r5
+ mtspr SPRN_SRR1, r7
+ rfid
+
+ .globl pnv_enter_arch207_idle_mode
+pnv_enter_arch207_idle_mode:
+ stb r3,PACA_THREAD_IDLE_STATE(r13)
+ cmpwi cr3,r3,PNV_THREAD_SLEEP
+ bge cr3,2f
+ IDLE_STATE_ENTER_SEQ(PPC_NAP)
+ /* No return */
+2:
+ /* Sleep or winkle */
+ lbz r7,PACA_THREAD_MASK(r13)
+ ld r14,PACA_CORE_IDLE_STATE_PTR(r13)
+lwarx_loop1:
+ lwarx r15,0,r14
+
+ andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT
+ bnel core_idle_lock_held
+
+ andc r15,r15,r7 /* Clear thread bit */
+
+ andi. r15,r15,PNV_CORE_IDLE_THREAD_BITS
+
+/*
+ * If cr0 = 0, then current thread is the last thread of the core entering
+ * sleep. Last thread needs to execute the hardware bug workaround code if
+ * required by the platform.
+ * Make the workaround call unconditionally here. The below branch call is
+ * patched out when the idle states are discovered if the platform does not
+ * require it.
+ */
+.global pnv_fastsleep_workaround_at_entry
+pnv_fastsleep_workaround_at_entry:
+ beq fastsleep_workaround_at_entry
+
+ stwcx. r15,0,r14
+ bne- lwarx_loop1
+ isync
+
+common_enter: /* common code for all the threads entering sleep or winkle */
+ bgt cr3,enter_winkle
+ IDLE_STATE_ENTER_SEQ(PPC_SLEEP)
+
+fastsleep_workaround_at_entry:
+ ori r15,r15,PNV_CORE_IDLE_LOCK_BIT
+ stwcx. r15,0,r14
+ bne- lwarx_loop1
+ isync
+
+ /* Fast sleep workaround */
+ li r3,1
+ li r4,1
+ bl opal_rm_config_cpu_idle_state
+
+ /* Clear Lock bit */
+ li r0,0
+ lwsync
+ stw r0,0(r14)
+ b common_enter
+
+enter_winkle:
+ bl save_sprs_to_stack
+
+ IDLE_STATE_ENTER_SEQ(PPC_WINKLE)
+
+/*
+ * r3 - requested stop state
+ */
+power_enter_stop:
+/*
+ * Check if the requested state is a deep idle state.
+ */
+ LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
+ ld r4,ADDROFF(pnv_first_deep_stop_state)(r5)
+ cmpd r3,r4
+ bge 2f
+ IDLE_STATE_ENTER_SEQ(PPC_STOP)
+2:
+/*
+ * Entering deep idle state.
+ * Clear thread bit in PACA_CORE_IDLE_STATE, save SPRs to
+ * stack and enter stop
+ */
+ lbz r7,PACA_THREAD_MASK(r13)
+ ld r14,PACA_CORE_IDLE_STATE_PTR(r13)
+
+lwarx_loop_stop:
+ lwarx r15,0,r14
+ andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT
+ bnel core_idle_lock_held
+ andc r15,r15,r7 /* Clear thread bit */
+
+ stwcx. r15,0,r14
+ bne- lwarx_loop_stop
+ isync
+
+ bl save_sprs_to_stack
+
+ IDLE_STATE_ENTER_SEQ(PPC_STOP)
+
+_GLOBAL(power7_idle)
+ /* Now check if user or arch enabled NAP mode */
+ LOAD_REG_ADDRBASE(r3,powersave_nap)
+ lwz r4,ADDROFF(powersave_nap)(r3)
+ cmpwi 0,r4,0
+ beqlr
+ li r3, 1
+ /* fall through */
+
+_GLOBAL(power7_nap)
+ mr r4,r3
+ li r3,PNV_THREAD_NAP
+ LOAD_REG_ADDR(r5, pnv_enter_arch207_idle_mode)
+ b pnv_powersave_common
+ /* No return */
+
+_GLOBAL(power7_sleep)
+ li r3,PNV_THREAD_SLEEP
+ li r4,1
+ LOAD_REG_ADDR(r5, pnv_enter_arch207_idle_mode)
+ b pnv_powersave_common
+ /* No return */
+
+_GLOBAL(power7_winkle)
+ li r3,PNV_THREAD_WINKLE
+ li r4,1
+ LOAD_REG_ADDR(r5, pnv_enter_arch207_idle_mode)
+ b pnv_powersave_common
+ /* No return */
+
+#define CHECK_HMI_INTERRUPT \
+ mfspr r0,SPRN_SRR1; \
+BEGIN_FTR_SECTION_NESTED(66); \
+ rlwinm r0,r0,45-31,0xf; /* extract wake reason field (P8) */ \
+FTR_SECTION_ELSE_NESTED(66); \
+ rlwinm r0,r0,45-31,0xe; /* P7 wake reason field is 3 bits */ \
+ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_ARCH_207S, 66); \
+ cmpwi r0,0xa; /* Hypervisor maintenance ? */ \
+ bne 20f; \
+ /* Invoke opal call to handle hmi */ \
+ ld r2,PACATOC(r13); \
+ ld r1,PACAR1(r13); \
+ std r3,ORIG_GPR3(r1); /* Save original r3 */ \
++ li r3,0; /* NULL argument */ \
++ bl hmi_exception_realmode; \
++ nop; \
+ ld r3,ORIG_GPR3(r1); /* Restore original r3 */ \
+20: nop;
+
+
+/*
+ * r3 - requested stop state
+ */
+_GLOBAL(power9_idle_stop)
+ LOAD_REG_IMMEDIATE(r4, PSSCR_HV_TEMPLATE)
+ or r4,r4,r3
+ mtspr SPRN_PSSCR, r4
+ li r4, 1
+ LOAD_REG_ADDR(r5,power_enter_stop)
+ b pnv_powersave_common
+ /* No return */
+/*
+ * Called from reset vector. Check whether we have woken up with
+ * hypervisor state loss. If yes, restore hypervisor state and return
+ * back to reset vector.
+ *
+ * r13 - Contents of HSPRG0
+ * cr3 - set to gt if waking up with partial/complete hypervisor state loss
+ */
+_GLOBAL(pnv_restore_hyp_resource)
+ ld r2,PACATOC(r13);
+BEGIN_FTR_SECTION
+ /*
+ * POWER ISA 3. Use PSSCR to determine if we
+ * are waking up from deep idle state
+ */
+ LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
+ ld r4,ADDROFF(pnv_first_deep_stop_state)(r5)
+
+ mfspr r5,SPRN_PSSCR
+ /*
+ * 0-3 bits correspond to Power-Saving Level Status
+ * which indicates the idle state we are waking up from
+ */
+ rldicl r5,r5,4,60
+ cmpd cr4,r5,r4
+ bge cr4,pnv_wakeup_tb_loss
+ /*
+ * Waking up without hypervisor state loss. Return to
+ * reset vector
+ */
+ blr
+
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+
+ /*
+ * POWER ISA 2.07 or less.
+ * Check if last bit of HSPGR0 is set. This indicates whether we are
+ * waking up from winkle.
+ */
+ clrldi r5,r13,63
+ clrrdi r13,r13,1
+ cmpwi cr4,r5,1
+ mtspr SPRN_HSPRG0,r13
+
+ lbz r0,PACA_THREAD_IDLE_STATE(r13)
+ cmpwi cr2,r0,PNV_THREAD_NAP
+ bgt cr2,pnv_wakeup_tb_loss /* Either sleep or Winkle */
+
+ /*
+ * We fall through here if PACA_THREAD_IDLE_STATE shows we are waking
+ * up from nap. At this stage CR3 shouldn't contains 'gt' since that
+ * indicates we are waking with hypervisor state loss from nap.
+ */
+ bgt cr3,.
+
+ blr /* Return back to System Reset vector from where
+ pnv_restore_hyp_resource was invoked */
+
+/*
+ * Called if waking up from idle state which can cause either partial or
+ * complete hyp state loss.
+ * In POWER8, called if waking up from fastsleep or winkle
+ * In POWER9, called if waking up from stop state >= pnv_first_deep_stop_state
+ *
+ * r13 - PACA
+ * cr3 - gt if waking up with partial/complete hypervisor state loss
+ * cr4 - eq if waking up from complete hypervisor state loss.
+ */
+_GLOBAL(pnv_wakeup_tb_loss)
+ ld r1,PACAR1(r13)
+ /*
+ * Before entering any idle state, the NVGPRs are saved in the stack
+ * and they are restored before switching to the process context. Hence
+ * until they are restored, they are free to be used.
+ *
+ * Save SRR1 and LR in NVGPRs as they might be clobbered in
+ * opal_call() (called in CHECK_HMI_INTERRUPT). SRR1 is required
+ * to determine the wakeup reason if we branch to kvm_start_guest. LR
+ * is required to return back to reset vector after hypervisor state
+ * restore is complete.
+ */
+ mflr r17
+ mfspr r16,SPRN_SRR1
+BEGIN_FTR_SECTION
+ CHECK_HMI_INTERRUPT
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
+
+ lbz r7,PACA_THREAD_MASK(r13)
+ ld r14,PACA_CORE_IDLE_STATE_PTR(r13)
+lwarx_loop2:
+ lwarx r15,0,r14
+ andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT
+ /*
+ * Lock bit is set in one of the 2 cases-
+ * a. In the sleep/winkle enter path, the last thread is executing
+ * fastsleep workaround code.
+ * b. In the wake up path, another thread is executing fastsleep
+ * workaround undo code or resyncing timebase or restoring context
+ * In either case loop until the lock bit is cleared.
+ */
+ bnel core_idle_lock_held
+
+ cmpwi cr2,r15,0
+
+ /*
+ * At this stage
+ * cr2 - eq if first thread to wakeup in core
+ * cr3- gt if waking up with partial/complete hypervisor state loss
+ * cr4 - eq if waking up from complete hypervisor state loss.
+ */
+
+ ori r15,r15,PNV_CORE_IDLE_LOCK_BIT
+ stwcx. r15,0,r14
+ bne- lwarx_loop2
+ isync
+
+BEGIN_FTR_SECTION
+ lbz r4,PACA_SUBCORE_SIBLING_MASK(r13)
+ and r4,r4,r15
+ cmpwi r4,0 /* Check if first in subcore */
+
+ or r15,r15,r7 /* Set thread bit */
+ beq first_thread_in_subcore
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
+
+ or r15,r15,r7 /* Set thread bit */
+ beq cr2,first_thread_in_core
+
+ /* Not first thread in core or subcore to wake up */
+ b clear_lock
+
+first_thread_in_subcore:
+ /*
+ * If waking up from sleep, subcore state is not lost. Hence
+ * skip subcore state restore
+ */
+ bne cr4,subcore_state_restored
+
+ /* Restore per-subcore state */
+ ld r4,_SDR1(r1)
+ mtspr SPRN_SDR1,r4
+
+ ld r4,_RPR(r1)
+ mtspr SPRN_RPR,r4
+ ld r4,_AMOR(r1)
+ mtspr SPRN_AMOR,r4
+
+subcore_state_restored:
+ /*
+ * Check if the thread is also the first thread in the core. If not,
+ * skip to clear_lock.
+ */
+ bne cr2,clear_lock
+
+first_thread_in_core:
+
+ /*
+ * First thread in the core waking up from any state which can cause
+ * partial or complete hypervisor state loss. It needs to
+ * call the fastsleep workaround code if the platform requires it.
+ * Call it unconditionally here. The below branch instruction will
+ * be patched out if the platform does not have fastsleep or does not
+ * require the workaround. Patching will be performed during the
+ * discovery of idle-states.
+ */
+.global pnv_fastsleep_workaround_at_exit
+pnv_fastsleep_workaround_at_exit:
+ b fastsleep_workaround_at_exit
+
+timebase_resync:
+ /*
+ * Use cr3 which indicates that we are waking up with atleast partial
+ * hypervisor state loss to determine if TIMEBASE RESYNC is needed.
+ */
+ ble cr3,clear_lock
+ /* Time base re-sync */
+ bl opal_rm_resync_timebase;
+ /*
+ * If waking up from sleep, per core state is not lost, skip to
+ * clear_lock.
+ */
+ bne cr4,clear_lock
+
+ /*
+ * First thread in the core to wake up and its waking up with
+ * complete hypervisor state loss. Restore per core hypervisor
+ * state.
+ */
+BEGIN_FTR_SECTION
+ ld r4,_PTCR(r1)
+ mtspr SPRN_PTCR,r4
+ ld r4,_RPR(r1)
+ mtspr SPRN_RPR,r4
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+
+ ld r4,_TSCR(r1)
+ mtspr SPRN_TSCR,r4
+ ld r4,_WORC(r1)
+ mtspr SPRN_WORC,r4
+
+clear_lock:
+ andi. r15,r15,PNV_CORE_IDLE_THREAD_BITS
+ lwsync
+ stw r15,0(r14)
+
+common_exit:
+ /*
+ * Common to all threads.
+ *
+ * If waking up from sleep, hypervisor state is not lost. Hence
+ * skip hypervisor state restore.
+ */
+ bne cr4,hypervisor_state_restored
+
+ /* Waking up from winkle */
+
+BEGIN_MMU_FTR_SECTION
+ b no_segments
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_RADIX)
+ /* Restore SLB from PACA */
+ ld r8,PACA_SLBSHADOWPTR(r13)
+
+ .rept SLB_NUM_BOLTED
+ li r3, SLBSHADOW_SAVEAREA
+ LDX_BE r5, r8, r3
+ addi r3, r3, 8
+ LDX_BE r6, r8, r3
+ andis. r7,r5,SLB_ESID_V@h
+ beq 1f
+ slbmte r6,r5
+1: addi r8,r8,16
+ .endr
+no_segments:
+
+ /* Restore per thread state */
+
+ ld r4,_SPURR(r1)
+ mtspr SPRN_SPURR,r4
+ ld r4,_PURR(r1)
+ mtspr SPRN_PURR,r4
+ ld r4,_DSCR(r1)
+ mtspr SPRN_DSCR,r4
+ ld r4,_WORT(r1)
+ mtspr SPRN_WORT,r4
+
+ /* Call cur_cpu_spec->cpu_restore() */
+ LOAD_REG_ADDR(r4, cur_cpu_spec)
+ ld r4,0(r4)
+ ld r12,CPU_SPEC_RESTORE(r4)
+#ifdef PPC64_ELF_ABI_v1
+ ld r12,0(r12)
+#endif
+ mtctr r12
+ bctrl
+
+hypervisor_state_restored:
+
+ mtspr SPRN_SRR1,r16
+ mtlr r17
+ blr /* Return back to System Reset vector from where
+ pnv_restore_hyp_resource was invoked */
+
+fastsleep_workaround_at_exit:
+ li r3,1
+ li r4,0
+ bl opal_rm_config_cpu_idle_state
+ b timebase_resync
+
+/*
+ * R3 here contains the value that will be returned to the caller
+ * of power7_nap.
+ */
+_GLOBAL(pnv_wakeup_loss)
+ ld r1,PACAR1(r13)
+BEGIN_FTR_SECTION
+ CHECK_HMI_INTERRUPT
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
+ REST_NVGPRS(r1)
+ REST_GPR(2, r1)
+ ld r6,_CCR(r1)
+ ld r4,_MSR(r1)
+ ld r5,_NIP(r1)
+ addi r1,r1,INT_FRAME_SIZE
+ mtcr r6
+ mtspr SPRN_SRR1,r4
+ mtspr SPRN_SRR0,r5
+ rfid
+
+/*
+ * R3 here contains the value that will be returned to the caller
+ * of power7_nap.
+ */
+_GLOBAL(pnv_wakeup_noloss)
+ lbz r0,PACA_NAPSTATELOST(r13)
+ cmpwi r0,0
+ bne pnv_wakeup_loss
+BEGIN_FTR_SECTION
+ CHECK_HMI_INTERRUPT
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
+ ld r1,PACAR1(r13)
+ ld r6,_CCR(r1)
+ ld r4,_MSR(r1)
+ ld r5,_NIP(r1)
+ addi r1,r1,INT_FRAME_SIZE
+ mtcr r6
+ mtspr SPRN_SRR1,r4
+ mtspr SPRN_SRR0,r5
+ rfid
#include <asm/switch_to.h>
#include <asm/tm.h>
#include <asm/debug.h>
+#include <asm/asm-prototypes.h>
+ #include <asm/hmi.h>
#include <sysdev/fsl_pci.h>
#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
{
__this_cpu_inc(irq_stat.hmi_exceptions);
+ wait_for_subcore_guest_exit();
+
if (ppc_md.hmi_exception_early)
ppc_md.hmi_exception_early(regs);
+ wait_for_tb_resync();
+
return 0;
}
[FSCR_TM_LG] = "TM",
[FSCR_EBB_LG] = "EBB",
[FSCR_TAR_LG] = "TAR",
+ [FSCR_LM_LG] = "LM",
};
char *facility = "unknown";
u64 value;
rd = (instword >> 21) & 0x1f;
current->thread.dscr = regs->gpr[rd];
current->thread.dscr_inherit = 1;
- mtspr(SPRN_FSCR, value | FSCR_DSCR);
+ current->thread.fscr |= FSCR_DSCR;
+ mtspr(SPRN_FSCR, current->thread.fscr);
}
/* Read from DSCR (mfspr RT, 0x03) */
emulate_single_step(regs);
}
return;
+ } else if ((status == FSCR_LM_LG) && cpu_has_feature(CPU_FTR_ARCH_300)) {
+ /*
+ * This process has touched LM, so turn it on forever
+ * for this process
+ */
+ current->thread.fscr |= FSCR_LM;
+ mtspr(SPRN_FSCR, current->thread.fscr);
+ return;
}
if ((status < ARRAY_SIZE(facility_strings)) &&
#include <asm/kvm_book3s_asm.h>
#include <asm/book3s/64/mmu-hash.h>
#include <asm/tm.h>
+ #include <asm/opal.h>
#define VCPU_GPRS_TM(reg) (((reg) * ULONG_SIZE) + VCPU_GPR_TM)
lwsync
std r0, HSTATE_KVM_VCORE(r13)
+ /*
+ * All secondaries exiting guest will fall through this path.
+ * Before proceeding, just check for HMI interrupt and
+ * invoke opal hmi handler. By now we are sure that the
+ * primary thread on this core/subcore has already made partition
+ * switch/TB resync and we are good to call opal hmi handler.
+ */
+ cmpwi r12, BOOK3S_INTERRUPT_HMI
+ bne kvm_no_guest
+
+ li r3,0 /* NULL argument */
+ bl hmi_exception_realmode
/*
* At this point we have finished executing in the guest.
* We need to wait for hwthread_req to become zero, since
cmpwi r3, 0
bne 54f
/*
- * We jump to power7_wakeup_loss, which will return to the caller
+ * We jump to pnv_wakeup_loss, which will return to the caller
* of power7_nap in the powernv cpu offline loop. The value we
* put in r3 becomes the return value for power7_nap.
*/
rlwimi r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
mtspr SPRN_LPCR, r4
li r3, 0
- b power7_wakeup_loss
+ b pnv_wakeup_loss
53: HMT_LOW
ld r5, HSTATE_KVM_VCORE(r13)
* whole-core mode, so we need to nap.
*/
kvm_unsplit_nap:
+ /*
+ * When secondaries are napping in kvm_unsplit_nap() with
+ * hwthread_req = 1, HMI goes ignored even though subcores are
+ * already exited the guest. Hence HMI keeps waking up secondaries
+ * from nap in a loop and secondaries always go back to nap since
+ * no vcore is assigned to them. This makes impossible for primary
+ * thread to get hold of secondary threads resulting into a soft
+ * lockup in KVM path.
+ *
+ * Let us check if HMI is pending and handle it before we go to nap.
+ */
+ cmpwi r12, BOOK3S_INTERRUPT_HMI
+ bne 55f
+ li r3, 0 /* NULL argument */
+ bl hmi_exception_realmode
+ 55:
/*
* Ensure that secondary doesn't nap when it has
* its vcore pointer set.
mtspr SPRN_DPDES, r8
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+ /* Mark the subcore state as inside guest */
+ bl kvmppc_subcore_enter_guest
+ nop
+ ld r5, HSTATE_KVM_VCORE(r13)
+ ld r4, HSTATE_KVM_VCPU(r13)
li r0,1
stb r0,VCORE_IN_GUEST(r5) /* signal secondaries to continue */
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
BEGIN_FTR_SECTION
- b skip_tm
- END_FTR_SECTION_IFCLR(CPU_FTR_TM)
-
- /* Turn on TM/FP/VSX/VMX so we can restore them. */
- mfmsr r5
- li r6, MSR_TM >> 32
- sldi r6, r6, 32
- or r5, r5, r6
- ori r5, r5, MSR_FP
- oris r5, r5, (MSR_VEC | MSR_VSX)@h
- mtmsrd r5
-
- /*
- * The user may change these outside of a transaction, so they must
- * always be context switched.
- */
- ld r5, VCPU_TFHAR(r4)
- ld r6, VCPU_TFIAR(r4)
- ld r7, VCPU_TEXASR(r4)
- mtspr SPRN_TFHAR, r5
- mtspr SPRN_TFIAR, r6
- mtspr SPRN_TEXASR, r7
-
- ld r5, VCPU_MSR(r4)
- rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
- beq skip_tm /* TM not active in guest */
-
- /* Make sure the failure summary is set, otherwise we'll program check
- * when we trechkpt. It's possible that this might have been not set
- * on a kvmppc_set_one_reg() call but we shouldn't let this crash the
- * host.
- */
- oris r7, r7, (TEXASR_FS)@h
- mtspr SPRN_TEXASR, r7
-
- /*
- * We need to load up the checkpointed state for the guest.
- * We need to do this early as it will blow away any GPRs, VSRs and
- * some SPRs.
- */
-
- mr r31, r4
- addi r3, r31, VCPU_FPRS_TM
- bl load_fp_state
- addi r3, r31, VCPU_VRS_TM
- bl load_vr_state
- mr r4, r31
- lwz r7, VCPU_VRSAVE_TM(r4)
- mtspr SPRN_VRSAVE, r7
-
- ld r5, VCPU_LR_TM(r4)
- lwz r6, VCPU_CR_TM(r4)
- ld r7, VCPU_CTR_TM(r4)
- ld r8, VCPU_AMR_TM(r4)
- ld r9, VCPU_TAR_TM(r4)
- mtlr r5
- mtcr r6
- mtctr r7
- mtspr SPRN_AMR, r8
- mtspr SPRN_TAR, r9
-
- /*
- * Load up PPR and DSCR values but don't put them in the actual SPRs
- * till the last moment to avoid running with userspace PPR and DSCR for
- * too long.
- */
- ld r29, VCPU_DSCR_TM(r4)
- ld r30, VCPU_PPR_TM(r4)
-
- std r2, PACATMSCRATCH(r13) /* Save TOC */
-
- /* Clear the MSR RI since r1, r13 are all going to be foobar. */
- li r5, 0
- mtmsrd r5, 1
-
- /* Load GPRs r0-r28 */
- reg = 0
- .rept 29
- ld reg, VCPU_GPRS_TM(reg)(r31)
- reg = reg + 1
- .endr
-
- mtspr SPRN_DSCR, r29
- mtspr SPRN_PPR, r30
-
- /* Load final GPRs */
- ld 29, VCPU_GPRS_TM(29)(r31)
- ld 30, VCPU_GPRS_TM(30)(r31)
- ld 31, VCPU_GPRS_TM(31)(r31)
-
- /* TM checkpointed state is now setup. All GPRs are now volatile. */
- TRECHKPT
-
- /* Now let's get back the state we need. */
- HMT_MEDIUM
- GET_PACA(r13)
- ld r29, HSTATE_DSCR(r13)
- mtspr SPRN_DSCR, r29
- ld r4, HSTATE_KVM_VCPU(r13)
- ld r1, HSTATE_HOST_R1(r13)
- ld r2, PACATMSCRATCH(r13)
-
- /* Set the MSR RI since we have our registers back. */
- li r5, MSR_RI
- mtmsrd r5, 1
- skip_tm:
+ bl kvmppc_restore_tm
+ END_FTR_SECTION_IFSET(CPU_FTR_TM)
#endif
/* Load guest PMU registers */
/* Skip next section on POWER7 */
b 8f
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
- /* Turn on TM so we can access TFHAR/TFIAR/TEXASR */
- mfmsr r8
- li r0, 1
- rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG
- mtmsrd r8
-
/* Load up POWER8-specific registers */
ld r5, VCPU_IAMR(r4)
lwz r6, VCPU_PSPB(r4)
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
BEGIN_FTR_SECTION
- b 2f
- END_FTR_SECTION_IFCLR(CPU_FTR_TM)
- /* Turn on TM. */
- mfmsr r8
- li r0, 1
- rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG
- mtmsrd r8
-
- ld r5, VCPU_MSR(r9)
- rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
- beq 1f /* TM not active in guest. */
-
- li r3, TM_CAUSE_KVM_RESCHED
-
- /* Clear the MSR RI since r1, r13 are all going to be foobar. */
- li r5, 0
- mtmsrd r5, 1
-
- /* All GPRs are volatile at this point. */
- TRECLAIM(R3)
-
- /* Temporarily store r13 and r9 so we have some regs to play with */
- SET_SCRATCH0(r13)
- GET_PACA(r13)
- std r9, PACATMSCRATCH(r13)
- ld r9, HSTATE_KVM_VCPU(r13)
-
- /* Get a few more GPRs free. */
- std r29, VCPU_GPRS_TM(29)(r9)
- std r30, VCPU_GPRS_TM(30)(r9)
- std r31, VCPU_GPRS_TM(31)(r9)
-
- /* Save away PPR and DSCR soon so don't run with user values. */
- mfspr r31, SPRN_PPR
- HMT_MEDIUM
- mfspr r30, SPRN_DSCR
- ld r29, HSTATE_DSCR(r13)
- mtspr SPRN_DSCR, r29
-
- /* Save all but r9, r13 & r29-r31 */
- reg = 0
- .rept 29
- .if (reg != 9) && (reg != 13)
- std reg, VCPU_GPRS_TM(reg)(r9)
- .endif
- reg = reg + 1
- .endr
- /* ... now save r13 */
- GET_SCRATCH0(r4)
- std r4, VCPU_GPRS_TM(13)(r9)
- /* ... and save r9 */
- ld r4, PACATMSCRATCH(r13)
- std r4, VCPU_GPRS_TM(9)(r9)
-
- /* Reload stack pointer and TOC. */
- ld r1, HSTATE_HOST_R1(r13)
- ld r2, PACATOC(r13)
-
- /* Set MSR RI now we have r1 and r13 back. */
- li r5, MSR_RI
- mtmsrd r5, 1
-
- /* Save away checkpinted SPRs. */
- std r31, VCPU_PPR_TM(r9)
- std r30, VCPU_DSCR_TM(r9)
- mflr r5
- mfcr r6
- mfctr r7
- mfspr r8, SPRN_AMR
- mfspr r10, SPRN_TAR
- std r5, VCPU_LR_TM(r9)
- stw r6, VCPU_CR_TM(r9)
- std r7, VCPU_CTR_TM(r9)
- std r8, VCPU_AMR_TM(r9)
- std r10, VCPU_TAR_TM(r9)
-
- /* Restore r12 as trap number. */
- lwz r12, VCPU_TRAP(r9)
-
- /* Save FP/VSX. */
- addi r3, r9, VCPU_FPRS_TM
- bl store_fp_state
- addi r3, r9, VCPU_VRS_TM
- bl store_vr_state
- mfspr r6, SPRN_VRSAVE
- stw r6, VCPU_VRSAVE_TM(r9)
- 1:
- /*
- * We need to save these SPRs after the treclaim so that the software
- * error code is recorded correctly in the TEXASR. Also the user may
- * change these outside of a transaction, so they must always be
- * context switched.
- */
- mfspr r5, SPRN_TFHAR
- mfspr r6, SPRN_TFIAR
- mfspr r7, SPRN_TEXASR
- std r5, VCPU_TFHAR(r9)
- std r6, VCPU_TFIAR(r9)
- std r7, VCPU_TEXASR(r9)
- 2:
+ bl kvmppc_save_tm
+ END_FTR_SECTION_IFSET(CPU_FTR_TM)
#endif
/* Increment yield count if they have a VPA */
mtspr SPRN_DPDES, r8
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+ /* If HMI, call kvmppc_realmode_hmi_handler() */
+ cmpwi r12, BOOK3S_INTERRUPT_HMI
+ bne 27f
+ bl kvmppc_realmode_hmi_handler
+ nop
+ li r12, BOOK3S_INTERRUPT_HMI
+ /*
+ * At this point kvmppc_realmode_hmi_handler would have resync-ed
+ * the TB. Hence it is not required to subtract guest timebase
+ * offset from timebase. So, skip it.
+ *
+ * Also, do not call kvmppc_subcore_exit_guest() because it has
+ * been invoked as part of kvmppc_realmode_hmi_handler().
+ */
+ b 30f
+
+ 27:
/* Subtract timebase offset from timebase */
ld r8,VCORE_TB_OFFSET(r5)
cmpdi r8,0
addis r8,r8,0x100 /* if so, increment upper 40 bits */
mtspr SPRN_TBU40,r8
+ 17: bl kvmppc_subcore_exit_guest
+ nop
+ 30: ld r5,HSTATE_KVM_VCORE(r13)
+ ld r4,VCORE_KVM(r5) /* pointer to struct kvm */
+
/* Reset PCR */
- 17: ld r0, VCORE_PCR(r5)
+ ld r0, VCORE_PCR(r5)
cmpdi r0, 0
beq 18f
li r0, 0
/* save FP state */
bl kvmppc_save_fp
+ #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ BEGIN_FTR_SECTION
+ ld r9, HSTATE_KVM_VCPU(r13)
+ bl kvmppc_save_tm
+ END_FTR_SECTION_IFSET(CPU_FTR_TM)
+ #endif
+
/*
* Set DEC to the smaller of DEC and HDEC, so that we wake
* no later than the end of our timeslice (HDEC interrupts
bl kvmhv_accumulate_time
#endif
+ #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ BEGIN_FTR_SECTION
+ bl kvmppc_restore_tm
+ END_FTR_SECTION_IFSET(CPU_FTR_TM)
+ #endif
+
/* load up FP state */
bl kvmppc_load_fp
cmpwi r6, 3 /* hypervisor doorbell? */
beq 3f
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+ cmpwi r6, 0xa /* Hypervisor maintenance ? */
+ beq 4f
li r3, 1 /* anything else, return 1 */
0: blr
li r3, -1
blr
+ /* Woken up due to Hypervisor maintenance interrupt */
+ 4: li r12, BOOK3S_INTERRUPT_HMI
+ li r3, 1
+ blr
+
/*
* Determine what sort of external interrupt is pending (if any).
* Returns:
mr r4,r31
blr
+ #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /*
+ * Save transactional state and TM-related registers.
+ * Called with r9 pointing to the vcpu struct.
+ * This can modify all checkpointed registers, but
+ * restores r1, r2 and r9 (vcpu pointer) before exit.
+ */
+ kvmppc_save_tm:
+ mflr r0
+ std r0, PPC_LR_STKOFF(r1)
+
+ /* Turn on TM. */
+ mfmsr r8
+ li r0, 1
+ rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG
+ mtmsrd r8
+
+ ld r5, VCPU_MSR(r9)
+ rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
+ beq 1f /* TM not active in guest. */
+
+ std r1, HSTATE_HOST_R1(r13)
+ li r3, TM_CAUSE_KVM_RESCHED
+
+ /* Clear the MSR RI since r1, r13 are all going to be foobar. */
+ li r5, 0
+ mtmsrd r5, 1
+
+ /* All GPRs are volatile at this point. */
+ TRECLAIM(R3)
+
+ /* Temporarily store r13 and r9 so we have some regs to play with */
+ SET_SCRATCH0(r13)
+ GET_PACA(r13)
+ std r9, PACATMSCRATCH(r13)
+ ld r9, HSTATE_KVM_VCPU(r13)
+
+ /* Get a few more GPRs free. */
+ std r29, VCPU_GPRS_TM(29)(r9)
+ std r30, VCPU_GPRS_TM(30)(r9)
+ std r31, VCPU_GPRS_TM(31)(r9)
+
+ /* Save away PPR and DSCR soon so don't run with user values. */
+ mfspr r31, SPRN_PPR
+ HMT_MEDIUM
+ mfspr r30, SPRN_DSCR
+ ld r29, HSTATE_DSCR(r13)
+ mtspr SPRN_DSCR, r29
+
+ /* Save all but r9, r13 & r29-r31 */
+ reg = 0
+ .rept 29
+ .if (reg != 9) && (reg != 13)
+ std reg, VCPU_GPRS_TM(reg)(r9)
+ .endif
+ reg = reg + 1
+ .endr
+ /* ... now save r13 */
+ GET_SCRATCH0(r4)
+ std r4, VCPU_GPRS_TM(13)(r9)
+ /* ... and save r9 */
+ ld r4, PACATMSCRATCH(r13)
+ std r4, VCPU_GPRS_TM(9)(r9)
+
+ /* Reload stack pointer and TOC. */
+ ld r1, HSTATE_HOST_R1(r13)
+ ld r2, PACATOC(r13)
+
+ /* Set MSR RI now we have r1 and r13 back. */
+ li r5, MSR_RI
+ mtmsrd r5, 1
+
+ /* Save away checkpinted SPRs. */
+ std r31, VCPU_PPR_TM(r9)
+ std r30, VCPU_DSCR_TM(r9)
+ mflr r5
+ mfcr r6
+ mfctr r7
+ mfspr r8, SPRN_AMR
+ mfspr r10, SPRN_TAR
+ std r5, VCPU_LR_TM(r9)
+ stw r6, VCPU_CR_TM(r9)
+ std r7, VCPU_CTR_TM(r9)
+ std r8, VCPU_AMR_TM(r9)
+ std r10, VCPU_TAR_TM(r9)
+
+ /* Restore r12 as trap number. */
+ lwz r12, VCPU_TRAP(r9)
+
+ /* Save FP/VSX. */
+ addi r3, r9, VCPU_FPRS_TM
+ bl store_fp_state
+ addi r3, r9, VCPU_VRS_TM
+ bl store_vr_state
+ mfspr r6, SPRN_VRSAVE
+ stw r6, VCPU_VRSAVE_TM(r9)
+ 1:
+ /*
+ * We need to save these SPRs after the treclaim so that the software
+ * error code is recorded correctly in the TEXASR. Also the user may
+ * change these outside of a transaction, so they must always be
+ * context switched.
+ */
+ mfspr r5, SPRN_TFHAR
+ mfspr r6, SPRN_TFIAR
+ mfspr r7, SPRN_TEXASR
+ std r5, VCPU_TFHAR(r9)
+ std r6, VCPU_TFIAR(r9)
+ std r7, VCPU_TEXASR(r9)
+
+ ld r0, PPC_LR_STKOFF(r1)
+ mtlr r0
+ blr
+
+ /*
+ * Restore transactional state and TM-related registers.
+ * Called with r4 pointing to the vcpu struct.
+ * This potentially modifies all checkpointed registers.
+ * It restores r1, r2, r4 from the PACA.
+ */
+ kvmppc_restore_tm:
+ mflr r0
+ std r0, PPC_LR_STKOFF(r1)
+
+ /* Turn on TM/FP/VSX/VMX so we can restore them. */
+ mfmsr r5
+ li r6, MSR_TM >> 32
+ sldi r6, r6, 32
+ or r5, r5, r6
+ ori r5, r5, MSR_FP
+ oris r5, r5, (MSR_VEC | MSR_VSX)@h
+ mtmsrd r5
+
+ /*
+ * The user may change these outside of a transaction, so they must
+ * always be context switched.
+ */
+ ld r5, VCPU_TFHAR(r4)
+ ld r6, VCPU_TFIAR(r4)
+ ld r7, VCPU_TEXASR(r4)
+ mtspr SPRN_TFHAR, r5
+ mtspr SPRN_TFIAR, r6
+ mtspr SPRN_TEXASR, r7
+
+ ld r5, VCPU_MSR(r4)
+ rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
+ beqlr /* TM not active in guest */
+ std r1, HSTATE_HOST_R1(r13)
+
+ /* Make sure the failure summary is set, otherwise we'll program check
+ * when we trechkpt. It's possible that this might have been not set
+ * on a kvmppc_set_one_reg() call but we shouldn't let this crash the
+ * host.
+ */
+ oris r7, r7, (TEXASR_FS)@h
+ mtspr SPRN_TEXASR, r7
+
+ /*
+ * We need to load up the checkpointed state for the guest.
+ * We need to do this early as it will blow away any GPRs, VSRs and
+ * some SPRs.
+ */
+
+ mr r31, r4
+ addi r3, r31, VCPU_FPRS_TM
+ bl load_fp_state
+ addi r3, r31, VCPU_VRS_TM
+ bl load_vr_state
+ mr r4, r31
+ lwz r7, VCPU_VRSAVE_TM(r4)
+ mtspr SPRN_VRSAVE, r7
+
+ ld r5, VCPU_LR_TM(r4)
+ lwz r6, VCPU_CR_TM(r4)
+ ld r7, VCPU_CTR_TM(r4)
+ ld r8, VCPU_AMR_TM(r4)
+ ld r9, VCPU_TAR_TM(r4)
+ mtlr r5
+ mtcr r6
+ mtctr r7
+ mtspr SPRN_AMR, r8
+ mtspr SPRN_TAR, r9
+
+ /*
+ * Load up PPR and DSCR values but don't put them in the actual SPRs
+ * till the last moment to avoid running with userspace PPR and DSCR for
+ * too long.
+ */
+ ld r29, VCPU_DSCR_TM(r4)
+ ld r30, VCPU_PPR_TM(r4)
+
+ std r2, PACATMSCRATCH(r13) /* Save TOC */
+
+ /* Clear the MSR RI since r1, r13 are all going to be foobar. */
+ li r5, 0
+ mtmsrd r5, 1
+
+ /* Load GPRs r0-r28 */
+ reg = 0
+ .rept 29
+ ld reg, VCPU_GPRS_TM(reg)(r31)
+ reg = reg + 1
+ .endr
+
+ mtspr SPRN_DSCR, r29
+ mtspr SPRN_PPR, r30
+
+ /* Load final GPRs */
+ ld 29, VCPU_GPRS_TM(29)(r31)
+ ld 30, VCPU_GPRS_TM(30)(r31)
+ ld 31, VCPU_GPRS_TM(31)(r31)
+
+ /* TM checkpointed state is now setup. All GPRs are now volatile. */
+ TRECHKPT
+
+ /* Now let's get back the state we need. */
+ HMT_MEDIUM
+ GET_PACA(r13)
+ ld r29, HSTATE_DSCR(r13)
+ mtspr SPRN_DSCR, r29
+ ld r4, HSTATE_KVM_VCPU(r13)
+ ld r1, HSTATE_HOST_R1(r13)
+ ld r2, PACATMSCRATCH(r13)
+
+ /* Set the MSR RI since we have our registers back. */
+ li r5, MSR_RI
+ mtmsrd r5, 1
+
+ ld r0, PPC_LR_STKOFF(r1)
+ mtlr r0
+ blr
+ #endif
+
/*
* We come here if we get any exception or interrupt while we are
* executing host real mode code while in guest MMU context.
#include <asm/mmu_context.h>
#include <asm/switch_to.h>
#include <asm/firmware.h>
-#include <asm/hvcall.h>
+#include <asm/setup.h>
#include <linux/gfp.h>
#include <linux/sched.h>
#include <linux/vmalloc.h>
/* We get here with MSR.EE=1 */
trace_kvm_exit(exit_nr, vcpu);
- kvm_guest_exit();
+ guest_exit();
switch (exit_nr) {
case BOOK3S_INTERRUPT_INST_STORAGE:
int emul;
program_interrupt:
- flags = vcpu->arch.shadow_srr1 & 0x1f0000ull;
+ /*
+ * shadow_srr1 only contains valid flags if we came here via
+ * a program exception. The other exceptions (emulation assist,
+ * FP unavailable, etc.) do not provide flags in SRR1, so use
+ * an illegal-instruction exception when injecting a program
+ * interrupt into the guest.
+ */
+ if (exit_nr == BOOK3S_INTERRUPT_PROGRAM)
+ flags = vcpu->arch.shadow_srr1 & 0x1f0000ull;
+ else
+ flags = SRR1_PROGILL;
emul = kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst);
if (emul != EMULATE_DONE) {
kvmppc_clear_debug(vcpu);
- /* No need for kvm_guest_exit. It's done in handle_exit.
+ /* No need for guest_exit. It's done in handle_exit.
We also get here with interrupts enabled. */
/* Make sure we save the guest FPU/Altivec/VSX state */
if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
spin_lock(&kvm_global_user_count_lock);
if (++kvm_global_user_count == 1)
- pSeries_disable_reloc_on_exc();
+ pseries_disable_reloc_on_exc();
spin_unlock(&kvm_global_user_count_lock);
}
return 0;
spin_lock(&kvm_global_user_count_lock);
BUG_ON(kvm_global_user_count == 0);
if (--kvm_global_user_count == 0)
- pSeries_enable_reloc_on_exc();
+ pseries_enable_reloc_on_exc();
spin_unlock(&kvm_global_user_count_lock);
}
}
#define OPAL_CALL(name, token) \
_GLOBAL_TOC(name); \
mflr r0; \
- std r0,16(r1); \
+ std r0,PPC_LR_STKOFF(r1); \
li r0,token; \
OPAL_BRANCH(opal_tracepoint_entry) \
mfcr r12; \
stw r12,8(r1); \
- std r1,PACAR1(r13); \
li r11,0; \
mfmsr r12; \
ori r11,r11,MSR_EE; \
FIXUP_ENDIAN
ld r2,PACATOC(r13);
lwz r4,8(r1);
- ld r5,16(r1);
+ ld r5,PPC_LR_STKOFF(r1);
ld r6,PACASAVEDMSR(r13);
mtspr SPRN_SRR0,r5;
mtspr SPRN_SRR1,r6;
mfcr r12
std r11,16(r1)
stw r12,8(r1)
- std r1,PACAR1(r13)
li r11,0
mfmsr r12
ori r11,r11,MSR_EE
blr
#endif
-/*
- * Make opal call in realmode. This is a generic function to be called
- * from realmode. It handles endianness.
- *
- * r13 - paca pointer
- * r1 - stack pointer
- * r0 - opal token
- */
-_GLOBAL(opal_call_realmode)
- mflr r12
- std r12,PPC_LR_STKOFF(r1)
- ld r2,PACATOC(r13)
- /* Set opal return address */
- LOAD_REG_ADDR(r12,return_from_opal_call)
- mtlr r12
-
- mfmsr r12
-#ifdef __LITTLE_ENDIAN__
- /* Handle endian-ness */
- li r11,MSR_LE
- andc r12,r12,r11
-#endif
- mtspr SPRN_HSRR1,r12
- LOAD_REG_ADDR(r11,opal)
- ld r12,8(r11)
- ld r2,0(r11)
- mtspr SPRN_HSRR0,r12
+#define OPAL_CALL_REAL(name, token) \
+ _GLOBAL_TOC(name); \
+ mflr r0; \
+ std r0,PPC_LR_STKOFF(r1); \
+ li r0,token; \
+ mfcr r12; \
+ stw r12,8(r1); \
+ \
+ /* Set opal return address */ \
+ LOAD_REG_ADDR(r11, opal_return_realmode); \
+ mtlr r11; \
+ mfmsr r12; \
+ li r11,MSR_LE; \
+ andc r12,r12,r11; \
+ mtspr SPRN_HSRR1,r12; \
+ LOAD_REG_ADDR(r11,opal); \
+ ld r12,8(r11); \
+ ld r2,0(r11); \
+ mtspr SPRN_HSRR0,r12; \
hrfid
-return_from_opal_call:
-#ifdef __LITTLE_ENDIAN__
+opal_return_realmode:
FIXUP_ENDIAN
-#endif
+ ld r2,PACATOC(r13);
+ lwz r11,8(r1);
ld r12,PPC_LR_STKOFF(r1)
+ mtcr r11;
mtlr r12
blr
+
OPAL_CALL(opal_invalid_call, OPAL_INVALID_CALL);
OPAL_CALL(opal_console_write, OPAL_CONSOLE_WRITE);
OPAL_CALL(opal_console_read, OPAL_CONSOLE_READ);
OPAL_CALL(opal_manage_flash, OPAL_FLASH_MANAGE);
OPAL_CALL(opal_update_flash, OPAL_FLASH_UPDATE);
OPAL_CALL(opal_resync_timebase, OPAL_RESYNC_TIMEBASE);
+OPAL_CALL_REAL(opal_rm_resync_timebase, OPAL_RESYNC_TIMEBASE);
OPAL_CALL(opal_check_token, OPAL_CHECK_TOKEN);
OPAL_CALL(opal_dump_init, OPAL_DUMP_INIT);
OPAL_CALL(opal_dump_info, OPAL_DUMP_INFO);
OPAL_CALL(opal_dump_read, OPAL_DUMP_READ);
OPAL_CALL(opal_dump_ack, OPAL_DUMP_ACK);
OPAL_CALL(opal_get_msg, OPAL_GET_MSG);
+OPAL_CALL(opal_write_oppanel_async, OPAL_WRITE_OPPANEL_ASYNC);
OPAL_CALL(opal_check_completion, OPAL_CHECK_ASYNC_COMPLETION);
OPAL_CALL(opal_dump_resend_notification, OPAL_DUMP_RESEND);
OPAL_CALL(opal_sync_host_reboot, OPAL_SYNC_HOST_REBOOT);
OPAL_CALL(opal_get_param, OPAL_GET_PARAM);
OPAL_CALL(opal_set_param, OPAL_SET_PARAM);
OPAL_CALL(opal_handle_hmi, OPAL_HANDLE_HMI);
+OPAL_CALL_REAL(opal_rm_handle_hmi, OPAL_HANDLE_HMI);
OPAL_CALL(opal_config_cpu_idle_state, OPAL_CONFIG_CPU_IDLE_STATE);
+OPAL_CALL_REAL(opal_rm_config_cpu_idle_state, OPAL_CONFIG_CPU_IDLE_STATE);
OPAL_CALL(opal_slw_set_reg, OPAL_SLW_SET_REG);
OPAL_CALL(opal_register_dump_region, OPAL_REGISTER_DUMP_REGION);
OPAL_CALL(opal_unregister_dump_region, OPAL_UNREGISTER_DUMP_REGION);
OPAL_CALL(opal_leds_get_ind, OPAL_LEDS_GET_INDICATOR);
OPAL_CALL(opal_leds_set_ind, OPAL_LEDS_SET_INDICATOR);
OPAL_CALL(opal_console_flush, OPAL_CONSOLE_FLUSH);
+OPAL_CALL(opal_get_device_tree, OPAL_GET_DEVICE_TREE);
+OPAL_CALL(opal_pci_get_presence_state, OPAL_PCI_GET_PRESENCE_STATE);
+OPAL_CALL(opal_pci_get_power_state, OPAL_PCI_GET_POWER_STATE);
+OPAL_CALL(opal_pci_set_power_state, OPAL_PCI_SET_POWER_STATE);
+OPAL_CALL(opal_int_get_xirr, OPAL_INT_GET_XIRR);
+OPAL_CALL(opal_int_set_cppr, OPAL_INT_SET_CPPR);
+OPAL_CALL(opal_int_eoi, OPAL_INT_EOI);
+OPAL_CALL(opal_int_set_mfrr, OPAL_INT_SET_MFRR);
+OPAL_CALL(opal_pci_tce_kill, OPAL_PCI_TCE_KILL);
+OPAL_CALL_REAL(opal_rm_pci_tce_kill, OPAL_PCI_TCE_KILL);
diag_stat_inc(DIAG_STAT_X010);
asm volatile(
"0: diag %0,%1,0x10\n"
- "1:\n"
+ "1: nopr %%r7\n"
EX_TABLE(0b, 1b)
EX_TABLE(1b, 1b)
: : "a" (start_addr), "a" (end_addr));
extern int diag210(struct diag210 *addr);
+ /* bit is set in flags, when physical cpu info is included in diag 204 data */
+ #define DIAG204_LPAR_PHYS_FLG 0x80
+ #define DIAG204_LPAR_NAME_LEN 8 /* lpar name len in diag 204 data */
+ #define DIAG204_CPU_NAME_LEN 16 /* type name len of cpus in diag224 name table */
+
+ /* diag 204 subcodes */
+ enum diag204_sc {
+ DIAG204_SUBC_STIB4 = 4,
+ DIAG204_SUBC_RSI = 5,
+ DIAG204_SUBC_STIB6 = 6,
+ DIAG204_SUBC_STIB7 = 7
+ };
+
+ /* The two available diag 204 data formats */
+ enum diag204_format {
+ DIAG204_INFO_SIMPLE = 0,
+ DIAG204_INFO_EXT = 0x00010000
+ };
+
+ enum diag204_cpu_flags {
+ DIAG204_CPU_ONLINE = 0x20,
+ DIAG204_CPU_CAPPED = 0x40,
+ };
+
+ struct diag204_info_blk_hdr {
+ __u8 npar;
+ __u8 flags;
+ __u16 tslice;
+ __u16 phys_cpus;
+ __u16 this_part;
+ __u64 curtod;
+ } __packed;
+
+ struct diag204_x_info_blk_hdr {
+ __u8 npar;
+ __u8 flags;
+ __u16 tslice;
+ __u16 phys_cpus;
+ __u16 this_part;
+ __u64 curtod1;
+ __u64 curtod2;
+ char reserved[40];
+ } __packed;
+
+ struct diag204_part_hdr {
+ __u8 pn;
+ __u8 cpus;
+ char reserved[6];
+ char part_name[DIAG204_LPAR_NAME_LEN];
+ } __packed;
+
+ struct diag204_x_part_hdr {
+ __u8 pn;
+ __u8 cpus;
+ __u8 rcpus;
+ __u8 pflag;
+ __u32 mlu;
+ char part_name[DIAG204_LPAR_NAME_LEN];
+ char lpc_name[8];
+ char os_name[8];
+ __u64 online_cs;
+ __u64 online_es;
+ __u8 upid;
+ __u8 reserved:3;
+ __u8 mtid:5;
+ char reserved1[2];
+ __u32 group_mlu;
+ char group_name[8];
+ char hardware_group_name[8];
+ char reserved2[24];
+ } __packed;
+
+ struct diag204_cpu_info {
+ __u16 cpu_addr;
+ char reserved1[2];
+ __u8 ctidx;
+ __u8 cflag;
+ __u16 weight;
+ __u64 acc_time;
+ __u64 lp_time;
+ } __packed;
+
+ struct diag204_x_cpu_info {
+ __u16 cpu_addr;
+ char reserved1[2];
+ __u8 ctidx;
+ __u8 cflag;
+ __u16 weight;
+ __u64 acc_time;
+ __u64 lp_time;
+ __u16 min_weight;
+ __u16 cur_weight;
+ __u16 max_weight;
+ char reseved2[2];
+ __u64 online_time;
+ __u64 wait_time;
+ __u32 pma_weight;
+ __u32 polar_weight;
+ __u32 cpu_type_cap;
+ __u32 group_cpu_type_cap;
+ char reserved3[32];
+ } __packed;
+
+ struct diag204_phys_hdr {
+ char reserved1[1];
+ __u8 cpus;
+ char reserved2[6];
+ char mgm_name[8];
+ } __packed;
+
+ struct diag204_x_phys_hdr {
+ char reserved1[1];
+ __u8 cpus;
+ char reserved2[6];
+ char mgm_name[8];
+ char reserved3[80];
+ } __packed;
+
+ struct diag204_phys_cpu {
+ __u16 cpu_addr;
+ char reserved1[2];
+ __u8 ctidx;
+ char reserved2[3];
+ __u64 mgm_time;
+ char reserved3[8];
+ } __packed;
+
+ struct diag204_x_phys_cpu {
+ __u16 cpu_addr;
+ char reserved1[2];
+ __u8 ctidx;
+ char reserved2[1];
+ __u16 weight;
+ __u64 mgm_time;
+ char reserved3[80];
+ } __packed;
+
+ struct diag204_x_part_block {
+ struct diag204_x_part_hdr hdr;
+ struct diag204_x_cpu_info cpus[];
+ } __packed;
+
+ struct diag204_x_phys_block {
+ struct diag204_x_phys_hdr hdr;
+ struct diag204_x_phys_cpu cpus[];
+ } __packed;
+
+ int diag204(unsigned long subcode, unsigned long size, void *addr);
+ int diag224(void *ptr);
#endif /* _ASM_S390_DIAG_H */
/* s390-specific vcpu->requests bit members */
#define KVM_REQ_ENABLE_IBS 8
#define KVM_REQ_DISABLE_IBS 9
+ #define KVM_REQ_ICPT_OPEREXC 10
#define SIGP_CTRL_C 0x80
#define SIGP_CTRL_SCN_MASK 0x3f
__u64 cputm; /* 0x0028 */
__u64 ckc; /* 0x0030 */
__u64 epoch; /* 0x0038 */
- __u8 reserved40[4]; /* 0x0040 */
+ __u32 svcc; /* 0x0040 */
#define LCTL_CR0 0x8000
#define LCTL_CR6 0x0200
#define LCTL_CR9 0x0040
#define LCTL_CR14 0x0002
__u16 lctl; /* 0x0044 */
__s16 icpua; /* 0x0046 */
+ #define ICTL_OPEREXC 0x80000000
#define ICTL_PINT 0x20000000
#define ICTL_LPSW 0x00400000
#define ICTL_STCTL 0x00040000
#define ICPT_INST 0x04
#define ICPT_PROGI 0x08
#define ICPT_INSTPROGI 0x0C
+ #define ICPT_EXTINT 0x14
+ #define ICPT_VALIDITY 0x20
+ #define ICPT_STOP 0x28
#define ICPT_OPEREXC 0x2C
#define ICPT_PARTEXEC 0x38
#define ICPT_IOINST 0x40
__u32 scaol; /* 0x0064 */
__u8 reserved68[4]; /* 0x0068 */
__u32 todpr; /* 0x006c */
- __u8 reserved70[32]; /* 0x0070 */
+ __u8 reserved70[16]; /* 0x0070 */
+ __u64 mso; /* 0x0080 */
+ __u64 msl; /* 0x0088 */
psw_t gpsw; /* 0x0090 */
__u64 gg14; /* 0x00a0 */
__u64 gg15; /* 0x00a8 */
__u8 reserved1e6[2]; /* 0x01e6 */
__u64 itdba; /* 0x01e8 */
__u64 riccbd; /* 0x01f0 */
- __u8 reserved1f8[8]; /* 0x01f8 */
+ __u64 gvrd; /* 0x01f8 */
} __attribute__((packed));
struct kvm_s390_itdb {
u32 exit_stop_request;
u32 exit_validity;
u32 exit_instruction;
+ u32 exit_pei;
u32 halt_successful_poll;
u32 halt_attempted_poll;
u32 halt_poll_invalid;
u32 instruction_stctg;
u32 exit_program_interruption;
u32 exit_instr_and_program;
+ u32 exit_operation_exception;
u32 deliver_external_call;
u32 deliver_emergency_signal;
u32 deliver_service_signal;
u32 instruction_stsi;
u32 instruction_stfl;
u32 instruction_tprot;
+ u32 instruction_sie;
u32 instruction_essa;
+ u32 instruction_sthyi;
u32 instruction_sigp_sense;
u32 instruction_sigp_sense_running;
u32 instruction_sigp_external_call;
struct kvm_vcpu_arch {
struct kvm_s390_sie_block *sie_block;
+ /* if vsie is active, currently executed shadow sie control block */
+ struct kvm_s390_sie_block *vsie_block;
unsigned int host_acrs[NUM_ACRS];
struct fpu host_fpregs;
struct kvm_s390_local_interrupt local_int;
struct hrtimer ckc_timer;
struct kvm_s390_pgm_info pgm;
struct gmap *gmap;
+ /* backup location for the currently enabled gmap when scheduled out */
+ struct gmap *enabled_gmap;
struct kvm_guestdbg_info_arch guestdbg;
unsigned long pfault_token;
unsigned long pfault_select;
u8 reserved900[0x1000 - 0x900]; /* 0x0900 */
} __packed;
+ struct kvm_s390_vsie {
+ struct mutex mutex;
+ struct radix_tree_root addr_to_page;
+ int page_count;
+ int next;
+ struct page *pages[KVM_MAX_VCPUS];
+ };
+
struct kvm_arch{
void *sca;
int use_esca;
int user_cpu_state_ctrl;
int user_sigp;
int user_stsi;
+ int user_instr0;
struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS];
wait_queue_head_t ipte_wq;
int ipte_lock_count;
struct mutex ipte_mutex;
+ struct ratelimit_state sthyi_limit;
spinlock_t start_stop_lock;
struct sie_page2 *sie_page2;
struct kvm_s390_cpu_model model;
struct kvm_s390_crypto crypto;
+ struct kvm_s390_vsie vsie;
u64 epoch;
+ /* subset of available cpu features enabled by user space */
+ DECLARE_BITMAP(cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS);
};
#define KVM_HVA_ERR_BAD (-1UL)
typedef struct {
cpumask_t cpu_attach_mask;
- atomic_t attach_count;
+ atomic_t flush_count;
unsigned int flush_mm;
- spinlock_t list_lock;
+ spinlock_t pgtable_lock;
struct list_head pgtable_list;
+ spinlock_t gmap_lock;
struct list_head gmap_list;
unsigned long asce;
unsigned long asce_limit;
unsigned int use_skey:1;
} mm_context_t;
- #define INIT_MM_CONTEXT(name) \
- .context.list_lock = __SPIN_LOCK_UNLOCKED(name.context.list_lock), \
- .context.pgtable_list = LIST_HEAD_INIT(name.context.pgtable_list), \
+ #define INIT_MM_CONTEXT(name) \
+ .context.pgtable_lock = \
+ __SPIN_LOCK_UNLOCKED(name.context.pgtable_lock), \
+ .context.pgtable_list = LIST_HEAD_INIT(name.context.pgtable_list), \
+ .context.gmap_lock = __SPIN_LOCK_UNLOCKED(name.context.gmap_lock), \
.context.gmap_list = LIST_HEAD_INIT(name.context.gmap_list),
static inline int tprot(unsigned long addr)
static inline int init_new_context(struct task_struct *tsk,
struct mm_struct *mm)
{
- spin_lock_init(&mm->context.list_lock);
+ spin_lock_init(&mm->context.pgtable_lock);
INIT_LIST_HEAD(&mm->context.pgtable_list);
+ spin_lock_init(&mm->context.gmap_lock);
INIT_LIST_HEAD(&mm->context.gmap_list);
cpumask_clear(&mm->context.cpu_attach_mask);
- atomic_set(&mm->context.attach_count, 0);
+ atomic_set(&mm->context.flush_count, 0);
mm->context.flush_mm = 0;
#ifdef CONFIG_PGSTE
mm->context.alloc_pgste = page_table_allocate_pgste;
S390_lowcore.user_asce = next->context.asce;
if (prev == next)
return;
- if (MACHINE_HAS_TLB_LC)
- cpumask_set_cpu(cpu, &next->context.cpu_attach_mask);
+ cpumask_set_cpu(cpu, &next->context.cpu_attach_mask);
+ cpumask_set_cpu(cpu, mm_cpumask(next));
/* Clear old ASCE by loading the kernel ASCE. */
__ctl_load(S390_lowcore.kernel_asce, 1, 1);
__ctl_load(S390_lowcore.kernel_asce, 7, 7);
- atomic_inc(&next->context.attach_count);
- atomic_dec(&prev->context.attach_count);
- if (MACHINE_HAS_TLB_LC)
- cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
+ cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
}
#define finish_arch_post_lock_switch finish_arch_post_lock_switch
load_kernel_asce();
if (mm) {
preempt_disable();
- while (atomic_read(&mm->context.attach_count) >> 16)
+ while (atomic_read(&mm->context.flush_count))
cpu_relax();
- cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
if (mm->context.flush_mm)
__tlb_flush_mm(mm);
preempt_enable();
struct mm_struct *next)
{
switch_mm(prev, next, current);
- cpumask_set_cpu(smp_processor_id(), mm_cpumask(next));
set_user_asce(next);
}
#define HPAGE_SIZE (1UL << HPAGE_SHIFT)
#define HPAGE_MASK (~(HPAGE_SIZE - 1))
#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT)
+#define HUGE_MAX_HSTATE 2
#define ARCH_HAS_SETCLEAR_HUGE_PTE
#define ARCH_HAS_HUGE_PTE_TYPE
#include <asm/setup.h>
#ifndef __ASSEMBLY__
+void __storage_key_init_range(unsigned long start, unsigned long end);
+
static inline void storage_key_init_range(unsigned long start, unsigned long end)
{
-#if PAGE_DEFAULT_KEY
- __storage_key_init_range(start, end);
-#endif
+ if (PAGE_DEFAULT_KEY)
+ __storage_key_init_range(start, end);
}
#define clear_page(page) memset((page), 0, PAGE_SIZE)
static inline int page_reset_referenced(unsigned long addr)
{
- unsigned int ipm;
+ int cc;
asm volatile(
" rrbe 0,%1\n"
" ipm %0\n"
- : "=d" (ipm) : "a" (addr) : "cc");
- return !!(ipm & 0x20000000);
+ " srl %0,28\n"
+ : "=d" (cc) : "a" (addr) : "cc");
+ return cc;
}
/* Bits int the storage key */
#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
#define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT)
#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
+ #define pfn_to_virt(pfn) __va((pfn) << PAGE_SHIFT)
+ #define page_to_virt(page) pfn_to_virt(page_to_pfn(page))
#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | \
VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
#include <linux/mm_types.h>
#include <linux/page-flags.h>
#include <linux/radix-tree.h>
+#include <linux/atomic.h>
#include <asm/bug.h>
#include <asm/page.h>
-extern pgd_t swapper_pg_dir[] __attribute__ ((aligned (4096)));
+extern pgd_t swapper_pg_dir[];
extern void paging_init(void);
extern void vmem_map_init(void);
+pmd_t *vmem_pmd_alloc(void);
+pte_t *vmem_pte_alloc(void);
+
+enum {
+ PG_DIRECT_MAP_4K = 0,
+ PG_DIRECT_MAP_1M,
+ PG_DIRECT_MAP_2G,
+ PG_DIRECT_MAP_MAX
+};
+
+extern atomic_long_t direct_pages_count[PG_DIRECT_MAP_MAX];
+
+static inline void update_page_count(int level, long count)
+{
+ if (IS_ENABLED(CONFIG_PROC_FS))
+ atomic_long_add(count, &direct_pages_count[level]);
+}
+
+struct seq_file;
+void arch_report_meminfo(struct seq_file *m);
/*
* The S390 doesn't have any external MMU info: the kernel page
* swap .11..ttttt.0
* prot-none, clean, old .11.xx0000.1
* prot-none, clean, young .11.xx0001.1
- * prot-none, dirty, old .10.xx0010.1
- * prot-none, dirty, young .10.xx0011.1
+ * prot-none, dirty, old .11.xx0010.1
+ * prot-none, dirty, young .11.xx0011.1
* read-only, clean, old .11.xx0100.1
* read-only, clean, young .01.xx0101.1
* read-only, dirty, old .11.xx0110.1
/* Bits in the region table entry */
#define _REGION_ENTRY_ORIGIN ~0xfffUL/* region/segment table origin */
#define _REGION_ENTRY_PROTECT 0x200 /* region protection bit */
+ #define _REGION_ENTRY_OFFSET 0xc0 /* region table offset */
#define _REGION_ENTRY_INVALID 0x20 /* invalid region table entry */
#define _REGION_ENTRY_TYPE_MASK 0x0c /* region/segment table type mask */
#define _REGION_ENTRY_TYPE_R1 0x0c /* region first table type */
#define _REGION3_ENTRY (_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_LENGTH)
#define _REGION3_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INVALID)
-#define _REGION3_ENTRY_LARGE 0x400 /* RTTE-format control, large page */
-#define _REGION3_ENTRY_RO 0x200 /* page protection bit */
+#define _REGION3_ENTRY_ORIGIN_LARGE ~0x7fffffffUL /* large page address */
+#define _REGION3_ENTRY_ORIGIN ~0x7ffUL/* region third table origin */
+
+#define _REGION3_ENTRY_DIRTY 0x2000 /* SW region dirty bit */
+#define _REGION3_ENTRY_YOUNG 0x1000 /* SW region young bit */
+#define _REGION3_ENTRY_LARGE 0x0400 /* RTTE-format control, large page */
+#define _REGION3_ENTRY_READ 0x0002 /* SW region read bit */
+#define _REGION3_ENTRY_WRITE 0x0001 /* SW region write bit */
+
+#ifdef CONFIG_MEM_SOFT_DIRTY
+#define _REGION3_ENTRY_SOFT_DIRTY 0x4000 /* SW region soft dirty bit */
+#else
+#define _REGION3_ENTRY_SOFT_DIRTY 0x0000 /* SW region soft dirty bit */
+#endif
+
+#define _REGION_ENTRY_BITS 0xfffffffffffff227UL
+#define _REGION_ENTRY_BITS_LARGE 0xffffffff8000fe27UL
/* Bits in the segment table entry */
#define _SEGMENT_ENTRY_BITS 0xfffffffffffffe33UL
#define _SEGMENT_ENTRY_DIRTY 0x2000 /* SW segment dirty bit */
#define _SEGMENT_ENTRY_YOUNG 0x1000 /* SW segment young bit */
#define _SEGMENT_ENTRY_LARGE 0x0400 /* STE-format control, large page */
-#define _SEGMENT_ENTRY_READ 0x0002 /* SW segment read bit */
-#define _SEGMENT_ENTRY_WRITE 0x0001 /* SW segment write bit */
+#define _SEGMENT_ENTRY_WRITE 0x0002 /* SW segment write bit */
+#define _SEGMENT_ENTRY_READ 0x0001 /* SW segment read bit */
#ifdef CONFIG_MEM_SOFT_DIRTY
#define _SEGMENT_ENTRY_SOFT_DIRTY 0x4000 /* SW segment soft dirty bit */
#endif
/*
- * Segment table entry encoding (R = read-only, I = invalid, y = young bit):
- * dy..R...I...rw
+ * Segment table and region3 table entry encoding
+ * (R = read-only, I = invalid, y = young bit):
+ * dy..R...I...wr
* prot-none, clean, old 00..1...1...00
* prot-none, clean, young 01..1...1...00
* prot-none, dirty, old 10..1...1...00
* prot-none, dirty, young 11..1...1...00
- * read-only, clean, old 00..1...1...10
- * read-only, clean, young 01..1...0...10
- * read-only, dirty, old 10..1...1...10
- * read-only, dirty, young 11..1...0...10
+ * read-only, clean, old 00..1...1...01
+ * read-only, clean, young 01..1...0...01
+ * read-only, dirty, old 10..1...1...01
+ * read-only, dirty, young 11..1...0...01
* read-write, clean, old 00..1...1...11
* read-write, clean, young 01..1...0...11
* read-write, dirty, old 10..0...1...11
#define PGSTE_GC_BIT 0x0002000000000000UL
#define PGSTE_UC_BIT 0x0000800000000000UL /* user dirty (migration) */
#define PGSTE_IN_BIT 0x0000400000000000UL /* IPTE notify bit */
+ #define PGSTE_VSIE_BIT 0x0000200000000000UL /* ref'd in a shadow table */
/* Guest Page State used for virtualization */
#define _PGSTE_GPS_ZERO 0x0000000080000000UL
/*
* Page protection definitions.
*/
-#define PAGE_NONE __pgprot(_PAGE_PRESENT | _PAGE_INVALID)
+#define PAGE_NONE __pgprot(_PAGE_PRESENT | _PAGE_INVALID | _PAGE_PROTECT)
#define PAGE_READ __pgprot(_PAGE_PRESENT | _PAGE_READ | \
_PAGE_INVALID | _PAGE_PROTECT)
#define PAGE_WRITE __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \
_SEGMENT_ENTRY_READ)
#define SEGMENT_WRITE __pgprot(_SEGMENT_ENTRY_READ | \
_SEGMENT_ENTRY_WRITE)
+#define SEGMENT_KERNEL __pgprot(_SEGMENT_ENTRY | \
+ _SEGMENT_ENTRY_LARGE | \
+ _SEGMENT_ENTRY_READ | \
+ _SEGMENT_ENTRY_WRITE | \
+ _SEGMENT_ENTRY_YOUNG | \
+ _SEGMENT_ENTRY_DIRTY)
+#define SEGMENT_KERNEL_RO __pgprot(_SEGMENT_ENTRY | \
+ _SEGMENT_ENTRY_LARGE | \
+ _SEGMENT_ENTRY_READ | \
+ _SEGMENT_ENTRY_YOUNG | \
+ _SEGMENT_ENTRY_PROTECT)
+
+/*
+ * Region3 entry (large page) protection definitions.
+ */
+
+#define REGION3_KERNEL __pgprot(_REGION_ENTRY_TYPE_R3 | \
+ _REGION3_ENTRY_LARGE | \
+ _REGION3_ENTRY_READ | \
+ _REGION3_ENTRY_WRITE | \
+ _REGION3_ENTRY_YOUNG | \
+ _REGION3_ENTRY_DIRTY)
+#define REGION3_KERNEL_RO __pgprot(_REGION_ENTRY_TYPE_R3 | \
+ _REGION3_ENTRY_LARGE | \
+ _REGION3_ENTRY_READ | \
+ _REGION3_ENTRY_YOUNG | \
+ _REGION_ENTRY_PROTECT)
static inline int mm_has_pgste(struct mm_struct *mm)
{
return 0;
}
+static inline void csp(unsigned int *ptr, unsigned int old, unsigned int new)
+{
+ register unsigned long reg2 asm("2") = old;
+ register unsigned long reg3 asm("3") = new;
+ unsigned long address = (unsigned long)ptr | 1;
+
+ asm volatile(
+ " csp %0,%3"
+ : "+d" (reg2), "+m" (*ptr)
+ : "d" (reg3), "d" (address)
+ : "cc");
+}
+
+static inline void cspg(unsigned long *ptr, unsigned long old, unsigned long new)
+{
+ register unsigned long reg2 asm("2") = old;
+ register unsigned long reg3 asm("3") = new;
+ unsigned long address = (unsigned long)ptr | 1;
+
+ asm volatile(
+ " .insn rre,0xb98a0000,%0,%3"
+ : "+d" (reg2), "+m" (*ptr)
+ : "d" (reg3), "d" (address)
+ : "cc");
+}
+
+#define CRDTE_DTT_PAGE 0x00UL
+#define CRDTE_DTT_SEGMENT 0x10UL
+#define CRDTE_DTT_REGION3 0x14UL
+#define CRDTE_DTT_REGION2 0x18UL
+#define CRDTE_DTT_REGION1 0x1cUL
+
+static inline void crdte(unsigned long old, unsigned long new,
+ unsigned long table, unsigned long dtt,
+ unsigned long address, unsigned long asce)
+{
+ register unsigned long reg2 asm("2") = old;
+ register unsigned long reg3 asm("3") = new;
+ register unsigned long reg4 asm("4") = table | dtt;
+ register unsigned long reg5 asm("5") = address;
+
+ asm volatile(".insn rrf,0xb98f0000,%0,%2,%4,0"
+ : "+d" (reg2)
+ : "d" (reg3), "d" (reg4), "d" (reg5), "a" (asce)
+ : "memory", "cc");
+}
+
/*
* pgd/pmd/pte query functions
*/
{
if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3)
return 0;
- return (pud_val(pud) & _REGION_ENTRY_INVALID) != 0UL;
+ return pud_val(pud) == _REGION3_ENTRY_EMPTY;
}
static inline int pud_large(pud_t pud)
return !!(pud_val(pud) & _REGION3_ENTRY_LARGE);
}
+static inline unsigned long pud_pfn(pud_t pud)
+{
+ unsigned long origin_mask;
+
+ origin_mask = _REGION3_ENTRY_ORIGIN;
+ if (pud_large(pud))
+ origin_mask = _REGION3_ENTRY_ORIGIN_LARGE;
+ return (pud_val(pud) & origin_mask) >> PAGE_SHIFT;
+}
+
+static inline int pmd_large(pmd_t pmd)
+{
+ return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) != 0;
+}
+
+static inline int pmd_bad(pmd_t pmd)
+{
+ if (pmd_large(pmd))
+ return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS_LARGE) != 0;
+ return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0;
+}
+
static inline int pud_bad(pud_t pud)
{
- /*
- * With dynamic page table levels the pud can be a region table
- * entry or a segment table entry. Check for the bit that are
- * invalid for either table entry.
- */
- unsigned long mask =
- ~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INVALID &
- ~_REGION_ENTRY_TYPE_MASK & ~_REGION_ENTRY_LENGTH;
- return (pud_val(pud) & mask) != 0;
+ if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3)
+ return pmd_bad(__pmd(pud_val(pud)));
+ if (pud_large(pud))
+ return (pud_val(pud) & ~_REGION_ENTRY_BITS_LARGE) != 0;
+ return (pud_val(pud) & ~_REGION_ENTRY_BITS) != 0;
}
static inline int pmd_present(pmd_t pmd)
return pmd_val(pmd) == _SEGMENT_ENTRY_INVALID;
}
-static inline int pmd_large(pmd_t pmd)
-{
- return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) != 0;
-}
-
static inline unsigned long pmd_pfn(pmd_t pmd)
{
unsigned long origin_mask;
return (pmd_val(pmd) & origin_mask) >> PAGE_SHIFT;
}
-static inline int pmd_bad(pmd_t pmd)
-{
- if (pmd_large(pmd))
- return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS_LARGE) != 0;
- return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0;
-}
-
#define __HAVE_ARCH_PMD_WRITE
static inline int pmd_write(pmd_t pmd)
{
void ptep_set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t entry);
void ptep_set_notify(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
- void ptep_notify(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+ void ptep_notify(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, unsigned long bits);
+ int ptep_force_prot(struct mm_struct *mm, unsigned long gaddr,
+ pte_t *ptep, int prot, unsigned long bit);
void ptep_zap_unused(struct mm_struct *mm, unsigned long addr,
pte_t *ptep , int reset);
void ptep_zap_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+ int ptep_shadow_pte(struct mm_struct *mm, unsigned long saddr,
+ pte_t *sptep, pte_t *tptep, pte_t pte);
+ void ptep_unshadow_pte(struct mm_struct *mm, unsigned long saddr, pte_t *ptep);
bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long address);
int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
unsigned char key, bool nq);
- unsigned char get_guest_storage_key(struct mm_struct *mm, unsigned long addr);
+ int cond_set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
+ unsigned char key, unsigned char *oldkey,
+ bool nq, bool mr, bool mc);
+ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr);
+ int get_guest_storage_key(struct mm_struct *mm, unsigned long addr,
+ unsigned char *key);
/*
* Certain architectures need to do special things when PTEs
#define pte_page(x) pfn_to_page(pte_pfn(x))
#define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd))
+#define pud_page(pud) pfn_to_page(pud_pfn(pud))
/* Find an entry in the lowest level page table.. */
#define pte_offset(pmd, addr) ((pte_t *) pmd_deref(*(pmd)) + pte_index(addr))
#define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address)
#define pte_unmap(pte) do { } while (0)
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)
-static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot)
-{
- /*
- * pgprot is PAGE_NONE, PAGE_READ, or PAGE_WRITE (see __Pxxx / __Sxxx)
- * Convert to segment table entry format.
- */
- if (pgprot_val(pgprot) == pgprot_val(PAGE_NONE))
- return pgprot_val(SEGMENT_NONE);
- if (pgprot_val(pgprot) == pgprot_val(PAGE_READ))
- return pgprot_val(SEGMENT_READ);
- return pgprot_val(SEGMENT_WRITE);
-}
-
static inline pmd_t pmd_wrprotect(pmd_t pmd)
{
pmd_val(pmd) &= ~_SEGMENT_ENTRY_WRITE;
return pmd;
}
+static inline pud_t pud_wrprotect(pud_t pud)
+{
+ pud_val(pud) &= ~_REGION3_ENTRY_WRITE;
+ pud_val(pud) |= _REGION_ENTRY_PROTECT;
+ return pud;
+}
+
+static inline pud_t pud_mkwrite(pud_t pud)
+{
+ pud_val(pud) |= _REGION3_ENTRY_WRITE;
+ if (pud_large(pud) && !(pud_val(pud) & _REGION3_ENTRY_DIRTY))
+ return pud;
+ pud_val(pud) &= ~_REGION_ENTRY_PROTECT;
+ return pud;
+}
+
+static inline pud_t pud_mkclean(pud_t pud)
+{
+ if (pud_large(pud)) {
+ pud_val(pud) &= ~_REGION3_ENTRY_DIRTY;
+ pud_val(pud) |= _REGION_ENTRY_PROTECT;
+ }
+ return pud;
+}
+
+static inline pud_t pud_mkdirty(pud_t pud)
+{
+ if (pud_large(pud)) {
+ pud_val(pud) |= _REGION3_ENTRY_DIRTY |
+ _REGION3_ENTRY_SOFT_DIRTY;
+ if (pud_val(pud) & _REGION3_ENTRY_WRITE)
+ pud_val(pud) &= ~_REGION_ENTRY_PROTECT;
+ }
+ return pud;
+}
+
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)
+static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot)
+{
+ /*
+ * pgprot is PAGE_NONE, PAGE_READ, or PAGE_WRITE (see __Pxxx / __Sxxx)
+ * Convert to segment table entry format.
+ */
+ if (pgprot_val(pgprot) == pgprot_val(PAGE_NONE))
+ return pgprot_val(SEGMENT_NONE);
+ if (pgprot_val(pgprot) == pgprot_val(PAGE_READ))
+ return pgprot_val(SEGMENT_READ);
+ return pgprot_val(SEGMENT_WRITE);
+}
+
static inline pmd_t pmd_mkyoung(pmd_t pmd)
{
if (pmd_large(pmd)) {
static inline void __pmdp_csp(pmd_t *pmdp)
{
- register unsigned long reg2 asm("2") = pmd_val(*pmdp);
- register unsigned long reg3 asm("3") = pmd_val(*pmdp) |
- _SEGMENT_ENTRY_INVALID;
- register unsigned long reg4 asm("4") = ((unsigned long) pmdp) + 5;
-
- asm volatile(
- " csp %1,%3"
- : "=m" (*pmdp)
- : "d" (reg2), "d" (reg3), "d" (reg4), "m" (*pmdp) : "cc");
+ csp((unsigned int *)pmdp + 1, pmd_val(*pmdp),
+ pmd_val(*pmdp) | _SEGMENT_ENTRY_INVALID);
}
static inline void __pmdp_idte(unsigned long address, pmd_t *pmdp)
: "cc" );
}
+static inline void __pudp_idte(unsigned long address, pud_t *pudp)
+{
+ unsigned long r3o;
+
+ r3o = (unsigned long) pudp - pud_index(address) * sizeof(pud_t);
+ r3o |= _ASCE_TYPE_REGION3;
+ asm volatile(
+ " .insn rrf,0xb98e0000,%2,%3,0,0"
+ : "=m" (*pudp)
+ : "m" (*pudp), "a" (r3o), "a" ((address & PUD_MASK))
+ : "cc");
+}
+
static inline void __pmdp_idte_local(unsigned long address, pmd_t *pmdp)
{
unsigned long sto;
: "cc" );
}
+static inline void __pudp_idte_local(unsigned long address, pud_t *pudp)
+{
+ unsigned long r3o;
+
+ r3o = (unsigned long) pudp - pud_index(address) * sizeof(pud_t);
+ r3o |= _ASCE_TYPE_REGION3;
+ asm volatile(
+ " .insn rrf,0xb98e0000,%2,%3,0,1"
+ : "=m" (*pudp)
+ : "m" (*pudp), "a" (r3o), "a" ((address & PUD_MASK))
+ : "cc");
+}
+
pmd_t pmdp_xchg_direct(struct mm_struct *, unsigned long, pmd_t *, pmd_t);
pmd_t pmdp_xchg_lazy(struct mm_struct *, unsigned long, pmd_t *, pmd_t);
+pud_t pudp_xchg_direct(struct mm_struct *, unsigned long, pud_t *, pud_t);
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
asm volatile("stidp %0" : "=Q" (*ptr));
}
-extern void s390_adjust_jiffies(void);
+void s390_adjust_jiffies(void);
+void s390_update_cpu_mhz(void);
+void cpu_detect_mhz_feature(void);
+
extern const struct seq_operations cpuinfo_op;
extern int sysctl_ieee_emulation_warnings;
extern void execve_tail(void);
unsigned long ksp; /* kernel stack pointer */
mm_segment_t mm_segment;
unsigned long gmap_addr; /* address of last gmap fault. */
+ unsigned int gmap_write_flag; /* gmap fault write indication */
+ unsigned int gmap_int_code; /* int code of last gmap fault */
unsigned int gmap_pfault; /* signal of a pending guest pfault */
struct per_regs per_user; /* User specified PER registers */
struct per_event per_event; /* Cause of the last PER trap */
#define cpu_relax_lowlatency() barrier()
+#define ECAG_CACHE_ATTRIBUTE 0
+#define ECAG_CPU_ATTRIBUTE 1
+
+static inline unsigned long __ecag(unsigned int asi, unsigned char parm)
+{
+ unsigned long val;
+
+ asm volatile(".insn rsy,0xeb000000004c,%0,0,0(%1)" /* ecag */
+ : "=d" (val) : "a" (asi << 8 | parm));
+ return val;
+}
+
static inline void psw_set_key(unsigned int key)
{
asm volatile("spka 0(%0)" : : "d" (key));
}
EXPORT_SYMBOL(diag14);
-static inline int __diag204(unsigned long subcode, unsigned long size, void *addr)
++static inline int __diag204(unsigned long *subcode, unsigned long size, void *addr)
+ {
- register unsigned long _subcode asm("0") = subcode;
++ register unsigned long _subcode asm("0") = *subcode;
+ register unsigned long _size asm("1") = size;
+
+ asm volatile(
+ " diag %2,%0,0x204\n"
- "0:\n"
++ "0: nopr %%r7\n"
+ EX_TABLE(0b,0b)
+ : "+d" (_subcode), "+d" (_size) : "d" (addr) : "memory");
- if (_subcode)
- return -1;
++ *subcode = _subcode;
+ return _size;
+ }
+
+ int diag204(unsigned long subcode, unsigned long size, void *addr)
+ {
+ diag_stat_inc(DIAG_STAT_X204);
- return __diag204(subcode, size, addr);
++ size = __diag204(&subcode, size, addr);
++ if (subcode)
++ return -1;
++ return size;
+ }
+ EXPORT_SYMBOL(diag204);
+
/*
* Diagnose 210: Get information about a virtual device
*/
return ccode;
}
EXPORT_SYMBOL(diag210);
+
+ int diag224(void *ptr)
+ {
+ int rc = -EOPNOTSUPP;
+
+ diag_stat_inc(DIAG_STAT_X224);
+ asm volatile(
+ " diag %1,%2,0x224\n"
+ "0: lhi %0,0x0\n"
+ "1:\n"
+ EX_TABLE(0b,1b)
+ : "+d" (rc) :"d" (0), "d" (ptr) : "memory");
+ return rc;
+ }
+ EXPORT_SYMBOL(diag224);
static int handle_partial_execution(struct kvm_vcpu *vcpu)
{
+ vcpu->stat.exit_pei++;
+
if (vcpu->arch.sie_block->ipa == 0xb254) /* MVPG */
return handle_mvpg_pei(vcpu);
if (vcpu->arch.sie_block->ipa >> 8 == 0xae) /* SIGP */
return -EOPNOTSUPP;
}
+ static int handle_operexc(struct kvm_vcpu *vcpu)
+ {
+ vcpu->stat.exit_operation_exception++;
+ trace_kvm_s390_handle_operexc(vcpu, vcpu->arch.sie_block->ipa,
+ vcpu->arch.sie_block->ipb);
+
+ if (vcpu->arch.sie_block->ipa == 0xb256 &&
+ test_kvm_facility(vcpu->kvm, 74))
+ return handle_sthyi(vcpu);
+
+ if (vcpu->arch.sie_block->ipa == 0 && vcpu->kvm->arch.user_instr0)
+ return -EOPNOTSUPP;
+
+ return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
+ }
+
int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)
{
+ int rc, per_rc = 0;
+
if (kvm_is_ucontrol(vcpu->kvm))
return -EOPNOTSUPP;
case 0x18:
return handle_noop(vcpu);
case 0x04:
- return handle_instruction(vcpu);
+ rc = handle_instruction(vcpu);
+ break;
case 0x08:
return handle_prog(vcpu);
case 0x14:
return handle_validity(vcpu);
case 0x28:
return handle_stop(vcpu);
+ case 0x2c:
+ rc = handle_operexc(vcpu);
+ break;
case 0x38:
- return handle_partial_execution(vcpu);
+ rc = handle_partial_execution(vcpu);
+ break;
default:
return -EOPNOTSUPP;
}
+
+ /* process PER, also if the instrution is processed in user space */
+ if (vcpu->arch.sie_block->icptstatus & 0x02 &&
+ (!rc || rc == -EOPNOTSUPP))
+ per_rc = kvm_s390_handle_per_ifetch_icpt(vcpu);
+ return per_rc ? per_rc : rc;
}
#include <linux/init.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
+ #include <linux/mman.h>
#include <linux/module.h>
#include <linux/random.h>
#include <linux/slab.h>
#include <linux/timer.h>
#include <linux/vmalloc.h>
+ #include <linux/bitmap.h>
#include <asm/asm-offsets.h>
#include <asm/lowcore.h>
-#include <asm/etr.h>
+#include <asm/stp.h>
#include <asm/pgtable.h>
#include <asm/gmap.h>
#include <asm/nmi.h>
#include <asm/switch_to.h>
#include <asm/isc.h>
#include <asm/sclp.h>
-#include <asm/etr.h>
+ #include <asm/cpacf.h>
++#include <asm/timex.h>
#include "kvm-s390.h"
#include "gaccess.h"
{ "exit_external_request", VCPU_STAT(exit_external_request) },
{ "exit_external_interrupt", VCPU_STAT(exit_external_interrupt) },
{ "exit_instruction", VCPU_STAT(exit_instruction) },
+ { "exit_pei", VCPU_STAT(exit_pei) },
{ "exit_program_interruption", VCPU_STAT(exit_program_interruption) },
{ "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) },
+ { "exit_operation_exception", VCPU_STAT(exit_operation_exception) },
{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) },
{ "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) },
{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
+ { "instruction_sthyi", VCPU_STAT(instruction_sthyi) },
+ { "instruction_sie", VCPU_STAT(instruction_sie) },
{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
{ "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) },
{ "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) },
{ NULL }
};
+ /* allow nested virtualization in KVM (if enabled by user space) */
+ static int nested;
+ module_param(nested, int, S_IRUGO);
+ MODULE_PARM_DESC(nested, "Nested virtualization support");
+
/* upper facilities limit for kvm */
unsigned long kvm_s390_fac_list_mask[16] = {
0xffe6000000000000UL,
return ARRAY_SIZE(kvm_s390_fac_list_mask);
}
+ /* available cpu features supported by kvm */
+ static DECLARE_BITMAP(kvm_s390_available_cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS);
+ /* available subfunctions indicated via query / "test bit" */
+ static struct kvm_s390_vm_cpu_subfunc kvm_s390_available_subfunc;
+
static struct gmap_notifier gmap_notifier;
+ static struct gmap_notifier vsie_gmap_notifier;
debug_info_t *kvm_s390_dbf;
/* Section: not file related */
return 0;
}
- static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address);
+ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
+ unsigned long end);
/*
* This callback is executed during stop_machine(). All CPUs are therefore
vcpu->arch.sie_block->epoch -= *delta;
if (vcpu->arch.cputm_enabled)
vcpu->arch.cputm_start += *delta;
+ if (vcpu->arch.vsie_block)
+ vcpu->arch.vsie_block->epoch -= *delta;
}
}
return NOTIFY_OK;
int kvm_arch_hardware_setup(void)
{
gmap_notifier.notifier_call = kvm_gmap_notifier;
- gmap_register_ipte_notifier(&gmap_notifier);
+ gmap_register_pte_notifier(&gmap_notifier);
+ vsie_gmap_notifier.notifier_call = kvm_s390_vsie_gmap_notifier;
+ gmap_register_pte_notifier(&vsie_gmap_notifier);
atomic_notifier_chain_register(&s390_epoch_delta_notifier,
&kvm_clock_notifier);
return 0;
void kvm_arch_hardware_unsetup(void)
{
- gmap_unregister_ipte_notifier(&gmap_notifier);
+ gmap_unregister_pte_notifier(&gmap_notifier);
+ gmap_unregister_pte_notifier(&vsie_gmap_notifier);
atomic_notifier_chain_unregister(&s390_epoch_delta_notifier,
&kvm_clock_notifier);
}
- etr_ptff(kvm_s390_available_subfunc.ptff, ETR_PTFF_QAF);
+ static void allow_cpu_feat(unsigned long nr)
+ {
+ set_bit_inv(nr, kvm_s390_available_cpu_feat);
+ }
+
+ static inline int plo_test_bit(unsigned char nr)
+ {
+ register unsigned long r0 asm("0") = (unsigned long) nr | 0x100;
+ int cc = 3; /* subfunction not available */
+
+ asm volatile(
+ /* Parameter registers are ignored for "test bit" */
+ " plo 0,0,0,0(0)\n"
+ " ipm %0\n"
+ " srl %0,28\n"
+ : "=d" (cc)
+ : "d" (r0)
+ : "cc");
+ return cc == 0;
+ }
+
+ static void kvm_s390_cpu_feat_init(void)
+ {
+ int i;
+
+ for (i = 0; i < 256; ++i) {
+ if (plo_test_bit(i))
+ kvm_s390_available_subfunc.plo[i >> 3] |= 0x80 >> (i & 7);
+ }
+
+ if (test_facility(28)) /* TOD-clock steering */
++ ptff(kvm_s390_available_subfunc.ptff,
++ sizeof(kvm_s390_available_subfunc.ptff),
++ PTFF_QAF);
+
+ if (test_facility(17)) { /* MSA */
+ __cpacf_query(CPACF_KMAC, kvm_s390_available_subfunc.kmac);
+ __cpacf_query(CPACF_KMC, kvm_s390_available_subfunc.kmc);
+ __cpacf_query(CPACF_KM, kvm_s390_available_subfunc.km);
+ __cpacf_query(CPACF_KIMD, kvm_s390_available_subfunc.kimd);
+ __cpacf_query(CPACF_KLMD, kvm_s390_available_subfunc.klmd);
+ }
+ if (test_facility(76)) /* MSA3 */
+ __cpacf_query(CPACF_PCKMO, kvm_s390_available_subfunc.pckmo);
+ if (test_facility(77)) { /* MSA4 */
+ __cpacf_query(CPACF_KMCTR, kvm_s390_available_subfunc.kmctr);
+ __cpacf_query(CPACF_KMF, kvm_s390_available_subfunc.kmf);
+ __cpacf_query(CPACF_KMO, kvm_s390_available_subfunc.kmo);
+ __cpacf_query(CPACF_PCC, kvm_s390_available_subfunc.pcc);
+ }
+ if (test_facility(57)) /* MSA5 */
+ __cpacf_query(CPACF_PPNO, kvm_s390_available_subfunc.ppno);
+
+ if (MACHINE_HAS_ESOP)
+ allow_cpu_feat(KVM_S390_VM_CPU_FEAT_ESOP);
+ /*
+ * We need SIE support, ESOP (PROT_READ protection for gmap_shadow),
+ * 64bit SCAO (SCA passthrough) and IDTE (for gmap_shadow unshadowing).
+ */
+ if (!sclp.has_sief2 || !MACHINE_HAS_ESOP || !sclp.has_64bscao ||
+ !test_facility(3) || !nested)
+ return;
+ allow_cpu_feat(KVM_S390_VM_CPU_FEAT_SIEF2);
+ if (sclp.has_64bscao)
+ allow_cpu_feat(KVM_S390_VM_CPU_FEAT_64BSCAO);
+ if (sclp.has_siif)
+ allow_cpu_feat(KVM_S390_VM_CPU_FEAT_SIIF);
+ if (sclp.has_gpere)
+ allow_cpu_feat(KVM_S390_VM_CPU_FEAT_GPERE);
+ if (sclp.has_gsls)
+ allow_cpu_feat(KVM_S390_VM_CPU_FEAT_GSLS);
+ if (sclp.has_ib)
+ allow_cpu_feat(KVM_S390_VM_CPU_FEAT_IB);
+ if (sclp.has_cei)
+ allow_cpu_feat(KVM_S390_VM_CPU_FEAT_CEI);
+ if (sclp.has_ibs)
+ allow_cpu_feat(KVM_S390_VM_CPU_FEAT_IBS);
+ /*
+ * KVM_S390_VM_CPU_FEAT_SKEY: Wrong shadow of PTE.I bits will make
+ * all skey handling functions read/set the skey from the PGSTE
+ * instead of the real storage key.
+ *
+ * KVM_S390_VM_CPU_FEAT_CMMA: Wrong shadow of PTE.I bits will make
+ * pages being detected as preserved although they are resident.
+ *
+ * KVM_S390_VM_CPU_FEAT_PFMFI: Wrong shadow of PTE.I bits will
+ * have the same effect as for KVM_S390_VM_CPU_FEAT_SKEY.
+ *
+ * For KVM_S390_VM_CPU_FEAT_SKEY, KVM_S390_VM_CPU_FEAT_CMMA and
+ * KVM_S390_VM_CPU_FEAT_PFMFI, all PTE.I and PGSTE bits have to be
+ * correctly shadowed. We can do that for the PGSTE but not for PTE.I.
+ *
+ * KVM_S390_VM_CPU_FEAT_SIGPIF: Wrong SCB addresses in the SCA. We
+ * cannot easily shadow the SCA because of the ipte lock.
+ */
+ }
+
int kvm_arch_init(void *opaque)
{
kvm_s390_dbf = debug_register("kvm-trace", 32, 1, 7 * sizeof(long));
return -ENOMEM;
}
+ kvm_s390_cpu_feat_init();
+
/* Register floating interrupt controller interface. */
return kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC);
}
case KVM_CAP_S390_USER_STSI:
case KVM_CAP_S390_SKEYS:
case KVM_CAP_S390_IRQ_STATE:
+ case KVM_CAP_S390_USER_INSTR0:
r = 1;
break;
case KVM_CAP_S390_MEM_OP:
break;
case KVM_CAP_NR_VCPUS:
case KVM_CAP_MAX_VCPUS:
- r = sclp.has_esca ? KVM_S390_ESCA_CPU_SLOTS
- : KVM_S390_BSCA_CPU_SLOTS;
+ r = KVM_S390_BSCA_CPU_SLOTS;
+ if (sclp.has_esca && sclp.has_64bscao)
+ r = KVM_S390_ESCA_CPU_SLOTS;
break;
case KVM_CAP_NR_MEMSLOTS:
r = KVM_USER_MEM_SLOTS;
return r;
}
+ static void icpt_operexc_on_all_vcpus(struct kvm *kvm)
+ {
+ unsigned int i;
+ struct kvm_vcpu *vcpu;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ kvm_s390_sync_request(KVM_REQ_ICPT_OPEREXC, vcpu);
+ }
+ }
+
static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
{
int r;
break;
case KVM_CAP_S390_VECTOR_REGISTERS:
mutex_lock(&kvm->lock);
- if (atomic_read(&kvm->online_vcpus)) {
+ if (kvm->created_vcpus) {
r = -EBUSY;
} else if (MACHINE_HAS_VX) {
set_kvm_facility(kvm->arch.model.fac_mask, 129);
case KVM_CAP_S390_RI:
r = -EINVAL;
mutex_lock(&kvm->lock);
- if (atomic_read(&kvm->online_vcpus)) {
+ if (kvm->created_vcpus) {
r = -EBUSY;
} else if (test_facility(64)) {
set_kvm_facility(kvm->arch.model.fac_mask, 64);
kvm->arch.user_stsi = 1;
r = 0;
break;
+ case KVM_CAP_S390_USER_INSTR0:
+ VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_INSTR0");
+ kvm->arch.user_instr0 = 1;
+ icpt_operexc_on_all_vcpus(kvm);
+ r = 0;
+ break;
default:
r = -EINVAL;
break;
unsigned int idx;
switch (attr->attr) {
case KVM_S390_VM_MEM_ENABLE_CMMA:
- /* enable CMMA only for z10 and later (EDAT_1) */
- ret = -EINVAL;
- if (!MACHINE_IS_LPAR || !MACHINE_HAS_EDAT1)
+ ret = -ENXIO;
+ if (!sclp.has_cmma)
break;
ret = -EBUSY;
VM_EVENT(kvm, 3, "%s", "ENABLE: CMMA support");
mutex_lock(&kvm->lock);
- if (atomic_read(&kvm->online_vcpus) == 0) {
+ if (!kvm->created_vcpus) {
kvm->arch.use_cmma = 1;
ret = 0;
}
mutex_unlock(&kvm->lock);
break;
case KVM_S390_VM_MEM_CLR_CMMA:
+ ret = -ENXIO;
+ if (!sclp.has_cmma)
+ break;
ret = -EINVAL;
if (!kvm->arch.use_cmma)
break;
if (!new_limit)
return -EINVAL;
- /* gmap_alloc takes last usable address */
+ /* gmap_create takes last usable address */
if (new_limit != KVM_S390_NO_MEM_LIMIT)
new_limit -= 1;
ret = -EBUSY;
mutex_lock(&kvm->lock);
- if (atomic_read(&kvm->online_vcpus) == 0) {
- /* gmap_alloc will round the limit up */
- struct gmap *new = gmap_alloc(current->mm, new_limit);
+ if (!kvm->created_vcpus) {
+ /* gmap_create will round the limit up */
+ struct gmap *new = gmap_create(current->mm, new_limit);
if (!new) {
ret = -ENOMEM;
} else {
- gmap_free(kvm->arch.gmap);
+ gmap_remove(kvm->arch.gmap);
new->private = kvm;
kvm->arch.gmap = new;
ret = 0;
int ret = 0;
mutex_lock(&kvm->lock);
- if (atomic_read(&kvm->online_vcpus)) {
+ if (kvm->created_vcpus) {
ret = -EBUSY;
goto out;
}
kvm->arch.model.cpuid = proc->cpuid;
lowest_ibc = sclp.ibc >> 16 & 0xfff;
unblocked_ibc = sclp.ibc & 0xfff;
- if (lowest_ibc) {
+ if (lowest_ibc && proc->ibc) {
if (proc->ibc > unblocked_ibc)
kvm->arch.model.ibc = unblocked_ibc;
else if (proc->ibc < lowest_ibc)
return ret;
}
+ static int kvm_s390_set_processor_feat(struct kvm *kvm,
+ struct kvm_device_attr *attr)
+ {
+ struct kvm_s390_vm_cpu_feat data;
+ int ret = -EBUSY;
+
+ if (copy_from_user(&data, (void __user *)attr->addr, sizeof(data)))
+ return -EFAULT;
+ if (!bitmap_subset((unsigned long *) data.feat,
+ kvm_s390_available_cpu_feat,
+ KVM_S390_VM_CPU_FEAT_NR_BITS))
+ return -EINVAL;
+
+ mutex_lock(&kvm->lock);
+ if (!atomic_read(&kvm->online_vcpus)) {
+ bitmap_copy(kvm->arch.cpu_feat, (unsigned long *) data.feat,
+ KVM_S390_VM_CPU_FEAT_NR_BITS);
+ ret = 0;
+ }
+ mutex_unlock(&kvm->lock);
+ return ret;
+ }
+
+ static int kvm_s390_set_processor_subfunc(struct kvm *kvm,
+ struct kvm_device_attr *attr)
+ {
+ /*
+ * Once supported by kernel + hw, we have to store the subfunctions
+ * in kvm->arch and remember that user space configured them.
+ */
+ return -ENXIO;
+ }
+
static int kvm_s390_set_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
{
int ret = -ENXIO;
case KVM_S390_VM_CPU_PROCESSOR:
ret = kvm_s390_set_processor(kvm, attr);
break;
+ case KVM_S390_VM_CPU_PROCESSOR_FEAT:
+ ret = kvm_s390_set_processor_feat(kvm, attr);
+ break;
+ case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC:
+ ret = kvm_s390_set_processor_subfunc(kvm, attr);
+ break;
}
return ret;
}
return ret;
}
+ static int kvm_s390_get_processor_feat(struct kvm *kvm,
+ struct kvm_device_attr *attr)
+ {
+ struct kvm_s390_vm_cpu_feat data;
+
+ bitmap_copy((unsigned long *) data.feat, kvm->arch.cpu_feat,
+ KVM_S390_VM_CPU_FEAT_NR_BITS);
+ if (copy_to_user((void __user *)attr->addr, &data, sizeof(data)))
+ return -EFAULT;
+ return 0;
+ }
+
+ static int kvm_s390_get_machine_feat(struct kvm *kvm,
+ struct kvm_device_attr *attr)
+ {
+ struct kvm_s390_vm_cpu_feat data;
+
+ bitmap_copy((unsigned long *) data.feat,
+ kvm_s390_available_cpu_feat,
+ KVM_S390_VM_CPU_FEAT_NR_BITS);
+ if (copy_to_user((void __user *)attr->addr, &data, sizeof(data)))
+ return -EFAULT;
+ return 0;
+ }
+
+ static int kvm_s390_get_processor_subfunc(struct kvm *kvm,
+ struct kvm_device_attr *attr)
+ {
+ /*
+ * Once we can actually configure subfunctions (kernel + hw support),
+ * we have to check if they were already set by user space, if so copy
+ * them from kvm->arch.
+ */
+ return -ENXIO;
+ }
+
+ static int kvm_s390_get_machine_subfunc(struct kvm *kvm,
+ struct kvm_device_attr *attr)
+ {
+ if (copy_to_user((void __user *)attr->addr, &kvm_s390_available_subfunc,
+ sizeof(struct kvm_s390_vm_cpu_subfunc)))
+ return -EFAULT;
+ return 0;
+ }
static int kvm_s390_get_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
{
int ret = -ENXIO;
case KVM_S390_VM_CPU_MACHINE:
ret = kvm_s390_get_machine(kvm, attr);
break;
+ case KVM_S390_VM_CPU_PROCESSOR_FEAT:
+ ret = kvm_s390_get_processor_feat(kvm, attr);
+ break;
+ case KVM_S390_VM_CPU_MACHINE_FEAT:
+ ret = kvm_s390_get_machine_feat(kvm, attr);
+ break;
+ case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC:
+ ret = kvm_s390_get_processor_subfunc(kvm, attr);
+ break;
+ case KVM_S390_VM_CPU_MACHINE_SUBFUNC:
+ ret = kvm_s390_get_machine_subfunc(kvm, attr);
+ break;
}
return ret;
}
switch (attr->attr) {
case KVM_S390_VM_MEM_ENABLE_CMMA:
case KVM_S390_VM_MEM_CLR_CMMA:
+ ret = sclp.has_cmma ? 0 : -ENXIO;
+ break;
case KVM_S390_VM_MEM_LIMIT_SIZE:
ret = 0;
break;
switch (attr->attr) {
case KVM_S390_VM_CPU_PROCESSOR:
case KVM_S390_VM_CPU_MACHINE:
+ case KVM_S390_VM_CPU_PROCESSOR_FEAT:
+ case KVM_S390_VM_CPU_MACHINE_FEAT:
+ case KVM_S390_VM_CPU_MACHINE_SUBFUNC:
ret = 0;
break;
+ /* configuring subfunctions is not supported yet */
+ case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC:
default:
ret = -ENXIO;
break;
{
uint8_t *keys;
uint64_t hva;
- unsigned long curkey;
int i, r = 0;
if (args->flags != 0)
if (!keys)
return -ENOMEM;
+ down_read(¤t->mm->mmap_sem);
for (i = 0; i < args->count; i++) {
hva = gfn_to_hva(kvm, args->start_gfn + i);
if (kvm_is_error_hva(hva)) {
r = -EFAULT;
- goto out;
+ break;
}
- curkey = get_guest_storage_key(current->mm, hva);
- if (IS_ERR_VALUE(curkey)) {
- r = curkey;
- goto out;
- }
- keys[i] = curkey;
+ r = get_guest_storage_key(current->mm, hva, &keys[i]);
+ if (r)
+ break;
+ }
+ up_read(¤t->mm->mmap_sem);
+
+ if (!r) {
+ r = copy_to_user((uint8_t __user *)args->skeydata_addr, keys,
+ sizeof(uint8_t) * args->count);
+ if (r)
+ r = -EFAULT;
}
- r = copy_to_user((uint8_t __user *)args->skeydata_addr, keys,
- sizeof(uint8_t) * args->count);
- if (r)
- r = -EFAULT;
- out:
kvfree(keys);
return r;
}
if (r)
goto out;
+ down_read(¤t->mm->mmap_sem);
for (i = 0; i < args->count; i++) {
hva = gfn_to_hva(kvm, args->start_gfn + i);
if (kvm_is_error_hva(hva)) {
r = -EFAULT;
- goto out;
+ break;
}
/* Lowest order bit is reserved */
if (keys[i] & 0x01) {
r = -EINVAL;
- goto out;
+ break;
}
- r = set_guest_storage_key(current->mm, hva,
- (unsigned long)keys[i], 0);
+ r = set_guest_storage_key(current->mm, hva, keys[i], 0);
if (r)
- goto out;
+ break;
}
+ up_read(¤t->mm->mmap_sem);
out:
kvfree(keys);
return r;
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
+ gfp_t alloc_flags = GFP_KERNEL;
int i, rc;
char debug_name[16];
static unsigned long sca_offset;
rc = -ENOMEM;
+ ratelimit_state_init(&kvm->arch.sthyi_limit, 5 * HZ, 500);
+
kvm->arch.use_esca = 0; /* start with basic SCA */
+ if (!sclp.has_64bscao)
+ alloc_flags |= GFP_DMA;
rwlock_init(&kvm->arch.sca_lock);
- kvm->arch.sca = (struct bsca_block *) get_zeroed_page(GFP_KERNEL);
+ kvm->arch.sca = (struct bsca_block *) get_zeroed_page(alloc_flags);
if (!kvm->arch.sca)
goto out_err;
spin_lock(&kvm_lock);
memcpy(kvm->arch.model.fac_list, kvm->arch.model.fac_mask,
S390_ARCH_FAC_LIST_SIZE_BYTE);
+ set_kvm_facility(kvm->arch.model.fac_mask, 74);
+ set_kvm_facility(kvm->arch.model.fac_list, 74);
+
kvm->arch.model.cpuid = kvm_s390_get_initial_cpuid();
kvm->arch.model.ibc = sclp.ibc & 0x0fff;
else
kvm->arch.mem_limit = min_t(unsigned long, TASK_MAX_SIZE,
sclp.hamax + 1);
- kvm->arch.gmap = gmap_alloc(current->mm, kvm->arch.mem_limit - 1);
+ kvm->arch.gmap = gmap_create(current->mm, kvm->arch.mem_limit - 1);
if (!kvm->arch.gmap)
goto out_err;
kvm->arch.gmap->private = kvm;
kvm->arch.epoch = 0;
spin_lock_init(&kvm->arch.start_stop_lock);
+ kvm_s390_vsie_init(kvm);
KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid);
return 0;
sca_del_vcpu(vcpu);
if (kvm_is_ucontrol(vcpu->kvm))
- gmap_free(vcpu->arch.gmap);
+ gmap_remove(vcpu->arch.gmap);
if (vcpu->kvm->arch.use_cmma)
kvm_s390_vcpu_unsetup_cmma(vcpu);
debug_unregister(kvm->arch.dbf);
free_page((unsigned long)kvm->arch.sie_page2);
if (!kvm_is_ucontrol(kvm))
- gmap_free(kvm->arch.gmap);
+ gmap_remove(kvm->arch.gmap);
kvm_s390_destroy_adapters(kvm);
kvm_s390_clear_float_irqs(kvm);
+ kvm_s390_vsie_destroy(kvm);
KVM_EVENT(3, "vm 0x%pK destroyed", kvm);
}
/* Section: vcpu related */
static int __kvm_ucontrol_vcpu_init(struct kvm_vcpu *vcpu)
{
- vcpu->arch.gmap = gmap_alloc(current->mm, -1UL);
+ vcpu->arch.gmap = gmap_create(current->mm, -1UL);
if (!vcpu->arch.gmap)
return -ENOMEM;
vcpu->arch.gmap->private = vcpu->kvm;
if (id < KVM_S390_BSCA_CPU_SLOTS)
return true;
- if (!sclp.has_esca)
+ if (!sclp.has_esca || !sclp.has_64bscao)
return false;
mutex_lock(&kvm->lock);
save_access_regs(vcpu->arch.host_acrs);
restore_access_regs(vcpu->run->s.regs.acrs);
- gmap_enable(vcpu->arch.gmap);
+ gmap_enable(vcpu->arch.enabled_gmap);
atomic_or(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
__start_cpu_timer_accounting(vcpu);
if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
__stop_cpu_timer_accounting(vcpu);
atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
- gmap_disable(vcpu->arch.gmap);
+ vcpu->arch.enabled_gmap = gmap_get_enabled();
+ gmap_disable(vcpu->arch.enabled_gmap);
/* Save guest register state */
save_fpu_regs();
vcpu->arch.gmap = vcpu->kvm->arch.gmap;
sca_add_vcpu(vcpu);
}
-
+ if (test_kvm_facility(vcpu->kvm, 74) || vcpu->kvm->arch.user_instr0)
+ vcpu->arch.sie_block->ictl |= ICTL_OPEREXC;
+ /* make vcpu_load load the right gmap on the first trigger */
+ vcpu->arch.enabled_gmap = vcpu->arch.gmap;
}
static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
kvm_s390_vcpu_setup_model(vcpu);
- vcpu->arch.sie_block->ecb = 0x02;
+ /* pgste_set_pte has special handling for !MACHINE_HAS_ESOP */
+ if (MACHINE_HAS_ESOP)
+ vcpu->arch.sie_block->ecb |= 0x02;
if (test_kvm_facility(vcpu->kvm, 9))
vcpu->arch.sie_block->ecb |= 0x04;
- if (test_kvm_facility(vcpu->kvm, 50) && test_kvm_facility(vcpu->kvm, 73))
+ if (test_kvm_facility(vcpu->kvm, 73))
vcpu->arch.sie_block->ecb |= 0x10;
- if (test_kvm_facility(vcpu->kvm, 8))
+ if (test_kvm_facility(vcpu->kvm, 8) && sclp.has_pfmfi)
vcpu->arch.sie_block->ecb2 |= 0x08;
- vcpu->arch.sie_block->eca = 0xC1002000U;
+ vcpu->arch.sie_block->eca = 0x1002000U;
+ if (sclp.has_cei)
+ vcpu->arch.sie_block->eca |= 0x80000000U;
+ if (sclp.has_ib)
+ vcpu->arch.sie_block->eca |= 0x40000000U;
if (sclp.has_siif)
vcpu->arch.sie_block->eca |= 1;
if (sclp.has_sigpif)
vcpu->arch.sie_block = &sie_page->sie_block;
vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;
+ /* the real guest size will always be smaller than msl */
+ vcpu->arch.sie_block->mso = 0;
+ vcpu->arch.sie_block->msl = sclp.hamax;
+
vcpu->arch.sie_block->icpua = id;
spin_lock_init(&vcpu->arch.local_int.lock);
vcpu->arch.local_int.float_int = &kvm->arch.float_int;
kvm_s390_vcpu_request(vcpu);
}
- static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address)
+ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
+ unsigned long end)
{
- int i;
struct kvm *kvm = gmap->private;
struct kvm_vcpu *vcpu;
+ unsigned long prefix;
+ int i;
+ if (gmap_is_shadow(gmap))
+ return;
+ if (start >= 1UL << 31)
+ /* We are only interested in prefix pages */
+ return;
kvm_for_each_vcpu(i, vcpu, kvm) {
/* match against both prefix pages */
- if (kvm_s390_get_prefix(vcpu) == (address & ~0x1000UL)) {
- VCPU_EVENT(vcpu, 2, "gmap notifier for %lx", address);
+ prefix = kvm_s390_get_prefix(vcpu);
+ if (prefix <= end && start <= prefix + 2*PAGE_SIZE - 1) {
+ VCPU_EVENT(vcpu, 2, "gmap notifier for %lx-%lx",
+ start, end);
kvm_s390_sync_request(KVM_REQ_MMU_RELOAD, vcpu);
}
}
if (dbg->control & ~VALID_GUESTDBG_FLAGS)
return -EINVAL;
+ if (!sclp.has_gpere)
+ return -EINVAL;
if (dbg->control & KVM_GUESTDBG_ENABLE) {
vcpu->guest_debug = dbg->control;
return 0;
/*
* We use MMU_RELOAD just to re-arm the ipte notifier for the
- * guest prefix page. gmap_ipte_notify will wait on the ptl lock.
+ * guest prefix page. gmap_mprotect_notify will wait on the ptl lock.
* This ensures that the ipte instruction for this request has
* already finished. We might race against a second unmapper that
* wants to set the blocking bit. Lets just retry the request loop.
*/
if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) {
int rc;
- rc = gmap_ipte_notify(vcpu->arch.gmap,
- kvm_s390_get_prefix(vcpu),
- PAGE_SIZE * 2);
+ rc = gmap_mprotect_notify(vcpu->arch.gmap,
+ kvm_s390_get_prefix(vcpu),
+ PAGE_SIZE * 2, PROT_WRITE);
if (rc)
return rc;
goto retry;
goto retry;
}
+ if (kvm_check_request(KVM_REQ_ICPT_OPEREXC, vcpu)) {
+ vcpu->arch.sie_block->ictl |= ICTL_OPEREXC;
+ goto retry;
+ }
+
/* nothing to do, just clear the request */
clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
* guest_enter and guest_exit should be no uaccess.
*/
local_irq_disable();
- __kvm_guest_enter();
+ guest_enter_irqoff();
__disable_cpu_timer_accounting(vcpu);
local_irq_enable();
exit_reason = sie64a(vcpu->arch.sie_block,
vcpu->run->s.regs.gprs);
local_irq_disable();
__enable_cpu_timer_accounting(vcpu);
- __kvm_guest_exit();
+ guest_exit_irqoff();
local_irq_enable();
vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
static void __enable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
{
+ if (!sclp.has_ibs)
+ return;
kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu);
kvm_s390_sync_request(KVM_REQ_ENABLE_IBS, vcpu);
}
(struct gmap *) S390_lowcore.gmap : NULL;
if (gmap) {
current->thread.gmap_addr = address;
+ current->thread.gmap_write_flag = !!(flags & FAULT_FLAG_WRITE);
+ current->thread.gmap_int_code = regs->int_code & 0xffff;
address = __gmap_translate(gmap, address);
if (address == -EFAULT) {
fault = VM_FAULT_BADMAP;
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
/* No reason to continue if interrupted by SIGKILL. */
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
fault = VM_FAULT_SIGNAL;
diag_stat_inc(DIAG_STAT_X258);
asm volatile(
" diag %0,0,0x258\n"
- "0:\n"
+ "0: nopr %%r7\n"
EX_TABLE(0b,0b)
: : "a" (&refbk), "m" (refbk) : "cc");
}
#include <asm/gmap.h>
#include <asm/tlb.h>
+ #define GMAP_SHADOW_FAKE_TABLE 1ULL
+
/**
- * gmap_alloc - allocate a guest address space
+ * gmap_alloc - allocate and initialize a guest address space
* @mm: pointer to the parent mm_struct
* @limit: maximum address of the gmap address space
*
* Returns a guest address space structure.
*/
- struct gmap *gmap_alloc(struct mm_struct *mm, unsigned long limit)
+ static struct gmap *gmap_alloc(unsigned long limit)
{
struct gmap *gmap;
struct page *page;
if (!gmap)
goto out;
INIT_LIST_HEAD(&gmap->crst_list);
+ INIT_LIST_HEAD(&gmap->children);
+ INIT_LIST_HEAD(&gmap->pt_list);
INIT_RADIX_TREE(&gmap->guest_to_host, GFP_KERNEL);
INIT_RADIX_TREE(&gmap->host_to_guest, GFP_ATOMIC);
+ INIT_RADIX_TREE(&gmap->host_to_rmap, GFP_ATOMIC);
spin_lock_init(&gmap->guest_table_lock);
- gmap->mm = mm;
+ spin_lock_init(&gmap->shadow_lock);
+ atomic_set(&gmap->ref_count, 1);
page = alloc_pages(GFP_KERNEL, 2);
if (!page)
goto out_free;
gmap->asce = atype | _ASCE_TABLE_LENGTH |
_ASCE_USER_BITS | __pa(table);
gmap->asce_end = limit;
- down_write(&mm->mmap_sem);
- list_add(&gmap->list, &mm->context.gmap_list);
- up_write(&mm->mmap_sem);
return gmap;
out_free:
out:
return NULL;
}
- EXPORT_SYMBOL_GPL(gmap_alloc);
+
+ /**
+ * gmap_create - create a guest address space
+ * @mm: pointer to the parent mm_struct
+ * @limit: maximum size of the gmap address space
+ *
+ * Returns a guest address space structure.
+ */
+ struct gmap *gmap_create(struct mm_struct *mm, unsigned long limit)
+ {
+ struct gmap *gmap;
+
+ gmap = gmap_alloc(limit);
+ if (!gmap)
+ return NULL;
+ gmap->mm = mm;
+ spin_lock(&mm->context.gmap_lock);
+ list_add_rcu(&gmap->list, &mm->context.gmap_list);
+ spin_unlock(&mm->context.gmap_lock);
+ return gmap;
+ }
+ EXPORT_SYMBOL_GPL(gmap_create);
static void gmap_flush_tlb(struct gmap *gmap)
{
if (MACHINE_HAS_IDTE)
- __tlb_flush_asce(gmap->mm, gmap->asce);
+ __tlb_flush_idte(gmap->asce);
else
__tlb_flush_global();
}
} while (nr > 0);
}
+ static void gmap_rmap_radix_tree_free(struct radix_tree_root *root)
+ {
+ struct gmap_rmap *rmap, *rnext, *head;
+ struct radix_tree_iter iter;
+ unsigned long indices[16];
+ unsigned long index;
+ void **slot;
+ int i, nr;
+
+ /* A radix tree is freed by deleting all of its entries */
+ index = 0;
+ do {
+ nr = 0;
+ radix_tree_for_each_slot(slot, root, &iter, index) {
+ indices[nr] = iter.index;
+ if (++nr == 16)
+ break;
+ }
+ for (i = 0; i < nr; i++) {
+ index = indices[i];
+ head = radix_tree_delete(root, index);
+ gmap_for_each_rmap_safe(rmap, rnext, head)
+ kfree(rmap);
+ }
+ } while (nr > 0);
+ }
+
/**
* gmap_free - free a guest address space
* @gmap: pointer to the guest address space structure
+ *
+ * No locks required. There are no references to this gmap anymore.
*/
- void gmap_free(struct gmap *gmap)
+ static void gmap_free(struct gmap *gmap)
{
struct page *page, *next;
- /* Flush tlb. */
- if (MACHINE_HAS_IDTE)
- __tlb_flush_idte(gmap->asce);
- else
- __tlb_flush_global();
-
+ /* Flush tlb of all gmaps (if not already done for shadows) */
+ if (!(gmap_is_shadow(gmap) && gmap->removed))
+ gmap_flush_tlb(gmap);
/* Free all segment & region tables. */
list_for_each_entry_safe(page, next, &gmap->crst_list, lru)
__free_pages(page, 2);
gmap_radix_tree_free(&gmap->guest_to_host);
gmap_radix_tree_free(&gmap->host_to_guest);
- down_write(&gmap->mm->mmap_sem);
- list_del(&gmap->list);
- up_write(&gmap->mm->mmap_sem);
+
+ /* Free additional data for a shadow gmap */
+ if (gmap_is_shadow(gmap)) {
+ /* Free all page tables. */
+ list_for_each_entry_safe(page, next, &gmap->pt_list, lru)
+ page_table_free_pgste(page);
+ gmap_rmap_radix_tree_free(&gmap->host_to_rmap);
+ /* Release reference to the parent */
+ gmap_put(gmap->parent);
+ }
+
kfree(gmap);
}
- EXPORT_SYMBOL_GPL(gmap_free);
+
+ /**
+ * gmap_get - increase reference counter for guest address space
+ * @gmap: pointer to the guest address space structure
+ *
+ * Returns the gmap pointer
+ */
+ struct gmap *gmap_get(struct gmap *gmap)
+ {
+ atomic_inc(&gmap->ref_count);
+ return gmap;
+ }
+ EXPORT_SYMBOL_GPL(gmap_get);
+
+ /**
+ * gmap_put - decrease reference counter for guest address space
+ * @gmap: pointer to the guest address space structure
+ *
+ * If the reference counter reaches zero the guest address space is freed.
+ */
+ void gmap_put(struct gmap *gmap)
+ {
+ if (atomic_dec_return(&gmap->ref_count) == 0)
+ gmap_free(gmap);
+ }
+ EXPORT_SYMBOL_GPL(gmap_put);
+
+ /**
+ * gmap_remove - remove a guest address space but do not free it yet
+ * @gmap: pointer to the guest address space structure
+ */
+ void gmap_remove(struct gmap *gmap)
+ {
+ struct gmap *sg, *next;
+
+ /* Remove all shadow gmaps linked to this gmap */
+ if (!list_empty(&gmap->children)) {
+ spin_lock(&gmap->shadow_lock);
+ list_for_each_entry_safe(sg, next, &gmap->children, list) {
+ list_del(&sg->list);
+ gmap_put(sg);
+ }
+ spin_unlock(&gmap->shadow_lock);
+ }
+ /* Remove gmap from the pre-mm list */
+ spin_lock(&gmap->mm->context.gmap_lock);
+ list_del_rcu(&gmap->list);
+ spin_unlock(&gmap->mm->context.gmap_lock);
+ synchronize_rcu();
+ /* Put reference */
+ gmap_put(gmap);
+ }
+ EXPORT_SYMBOL_GPL(gmap_remove);
/**
* gmap_enable - switch primary space to the guest address space
}
EXPORT_SYMBOL_GPL(gmap_disable);
+ /**
+ * gmap_get_enabled - get a pointer to the currently enabled gmap
+ *
+ * Returns a pointer to the currently enabled gmap. 0 if none is enabled.
+ */
+ struct gmap *gmap_get_enabled(void)
+ {
+ return (struct gmap *) S390_lowcore.gmap;
+ }
+ EXPORT_SYMBOL_GPL(gmap_get_enabled);
+
/*
* gmap_alloc_table is assumed to be called with mmap_sem held
*/
return -ENOMEM;
new = (unsigned long *) page_to_phys(page);
crst_table_init(new, init);
- spin_lock(&gmap->mm->page_table_lock);
+ spin_lock(&gmap->guest_table_lock);
if (*table & _REGION_ENTRY_INVALID) {
list_add(&page->lru, &gmap->crst_list);
*table = (unsigned long) new | _REGION_ENTRY_LENGTH |
page->index = gaddr;
page = NULL;
}
- spin_unlock(&gmap->mm->page_table_lock);
+ spin_unlock(&gmap->guest_table_lock);
if (page)
__free_pages(page, 2);
return 0;
unsigned long *entry;
int flush = 0;
+ BUG_ON(gmap_is_shadow(gmap));
spin_lock(&gmap->guest_table_lock);
entry = radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT);
if (entry) {
unsigned long off;
int flush;
+ BUG_ON(gmap_is_shadow(gmap));
if ((to | len) & (PMD_SIZE - 1))
return -EINVAL;
if (len == 0 || to + len < to)
unsigned long off;
int flush;
+ BUG_ON(gmap_is_shadow(gmap));
if ((from | to | len) & (PMD_SIZE - 1))
return -EINVAL;
if (len == 0 || from + len < from || to + len < to ||
* This function does not establish potentially missing page table entries.
* The mmap_sem of the mm that belongs to the address space must be held
* when this function gets called.
+ *
+ * Note: Can also be called for shadow gmaps.
*/
unsigned long __gmap_translate(struct gmap *gmap, unsigned long gaddr)
{
vmaddr = (unsigned long)
radix_tree_lookup(&gmap->guest_to_host, gaddr >> PMD_SHIFT);
+ /* Note: guest_to_host is empty for a shadow gmap */
return vmaddr ? (vmaddr | (gaddr & ~PMD_MASK)) : -EFAULT;
}
EXPORT_SYMBOL_GPL(__gmap_translate);
struct gmap *gmap;
int flush;
- list_for_each_entry(gmap, &mm->context.gmap_list, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
flush = __gmap_unlink_by_vmaddr(gmap, vmaddr);
if (flush)
gmap_flush_tlb(gmap);
}
+ rcu_read_unlock();
}
/**
pmd_t *pmd;
int rc;
+ BUG_ON(gmap_is_shadow(gmap));
/* Create higher level tables in the gmap page table */
table = gmap->table;
if ((gmap->asce & _ASCE_TYPE_MASK) >= _ASCE_TYPE_REGION1) {
VM_BUG_ON(pgd_none(*pgd));
pud = pud_offset(pgd, vmaddr);
VM_BUG_ON(pud_none(*pud));
+ /* large puds cannot yet be handled */
+ if (pud_large(*pud))
+ return -EFAULT;
pmd = pmd_offset(pud, vmaddr);
VM_BUG_ON(pmd_none(*pmd));
/* large pmds cannot yet be handled */
static DEFINE_SPINLOCK(gmap_notifier_lock);
/**
- * gmap_register_ipte_notifier - register a pte invalidation callback
+ * gmap_register_pte_notifier - register a pte invalidation callback
* @nb: pointer to the gmap notifier block
*/
- void gmap_register_ipte_notifier(struct gmap_notifier *nb)
+ void gmap_register_pte_notifier(struct gmap_notifier *nb)
{
spin_lock(&gmap_notifier_lock);
- list_add(&nb->list, &gmap_notifier_list);
+ list_add_rcu(&nb->list, &gmap_notifier_list);
spin_unlock(&gmap_notifier_lock);
}
- EXPORT_SYMBOL_GPL(gmap_register_ipte_notifier);
+ EXPORT_SYMBOL_GPL(gmap_register_pte_notifier);
/**
- * gmap_unregister_ipte_notifier - remove a pte invalidation callback
+ * gmap_unregister_pte_notifier - remove a pte invalidation callback
* @nb: pointer to the gmap notifier block
*/
- void gmap_unregister_ipte_notifier(struct gmap_notifier *nb)
+ void gmap_unregister_pte_notifier(struct gmap_notifier *nb)
{
spin_lock(&gmap_notifier_lock);
- list_del_init(&nb->list);
+ list_del_rcu(&nb->list);
spin_unlock(&gmap_notifier_lock);
+ synchronize_rcu();
+ }
+ EXPORT_SYMBOL_GPL(gmap_unregister_pte_notifier);
+
+ /**
+ * gmap_call_notifier - call all registered invalidation callbacks
+ * @gmap: pointer to guest mapping meta data structure
+ * @start: start virtual address in the guest address space
+ * @end: end virtual address in the guest address space
+ */
+ static void gmap_call_notifier(struct gmap *gmap, unsigned long start,
+ unsigned long end)
+ {
+ struct gmap_notifier *nb;
+
+ list_for_each_entry(nb, &gmap_notifier_list, list)
+ nb->notifier_call(gmap, start, end);
+ }
+
+ /**
+ * gmap_table_walk - walk the gmap page tables
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: virtual address in the guest address space
+ * @level: page table level to stop at
+ *
+ * Returns a table entry pointer for the given guest address and @level
+ * @level=0 : returns a pointer to a page table table entry (or NULL)
+ * @level=1 : returns a pointer to a segment table entry (or NULL)
+ * @level=2 : returns a pointer to a region-3 table entry (or NULL)
+ * @level=3 : returns a pointer to a region-2 table entry (or NULL)
+ * @level=4 : returns a pointer to a region-1 table entry (or NULL)
+ *
+ * Returns NULL if the gmap page tables could not be walked to the
+ * requested level.
+ *
+ * Note: Can also be called for shadow gmaps.
+ */
+ static inline unsigned long *gmap_table_walk(struct gmap *gmap,
+ unsigned long gaddr, int level)
+ {
+ unsigned long *table;
+
+ if ((gmap->asce & _ASCE_TYPE_MASK) + 4 < (level * 4))
+ return NULL;
+ if (gmap_is_shadow(gmap) && gmap->removed)
+ return NULL;
+ if (gaddr & (-1UL << (31 + ((gmap->asce & _ASCE_TYPE_MASK) >> 2)*11)))
+ return NULL;
+ table = gmap->table;
+ switch (gmap->asce & _ASCE_TYPE_MASK) {
+ case _ASCE_TYPE_REGION1:
+ table += (gaddr >> 53) & 0x7ff;
+ if (level == 4)
+ break;
+ if (*table & _REGION_ENTRY_INVALID)
+ return NULL;
+ table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+ /* Fallthrough */
+ case _ASCE_TYPE_REGION2:
+ table += (gaddr >> 42) & 0x7ff;
+ if (level == 3)
+ break;
+ if (*table & _REGION_ENTRY_INVALID)
+ return NULL;
+ table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+ /* Fallthrough */
+ case _ASCE_TYPE_REGION3:
+ table += (gaddr >> 31) & 0x7ff;
+ if (level == 2)
+ break;
+ if (*table & _REGION_ENTRY_INVALID)
+ return NULL;
+ table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+ /* Fallthrough */
+ case _ASCE_TYPE_SEGMENT:
+ table += (gaddr >> 20) & 0x7ff;
+ if (level == 1)
+ break;
+ if (*table & _REGION_ENTRY_INVALID)
+ return NULL;
+ table = (unsigned long *)(*table & _SEGMENT_ENTRY_ORIGIN);
+ table += (gaddr >> 12) & 0xff;
+ }
+ return table;
+ }
+
+ /**
+ * gmap_pte_op_walk - walk the gmap page table, get the page table lock
+ * and return the pte pointer
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: virtual address in the guest address space
+ * @ptl: pointer to the spinlock pointer
+ *
+ * Returns a pointer to the locked pte for a guest address, or NULL
+ *
+ * Note: Can also be called for shadow gmaps.
+ */
+ static pte_t *gmap_pte_op_walk(struct gmap *gmap, unsigned long gaddr,
+ spinlock_t **ptl)
+ {
+ unsigned long *table;
+
+ if (gmap_is_shadow(gmap))
+ spin_lock(&gmap->guest_table_lock);
+ /* Walk the gmap page table, lock and get pte pointer */
+ table = gmap_table_walk(gmap, gaddr, 1); /* get segment pointer */
+ if (!table || *table & _SEGMENT_ENTRY_INVALID) {
+ if (gmap_is_shadow(gmap))
+ spin_unlock(&gmap->guest_table_lock);
+ return NULL;
+ }
+ if (gmap_is_shadow(gmap)) {
+ *ptl = &gmap->guest_table_lock;
+ return pte_offset_map((pmd_t *) table, gaddr);
+ }
+ return pte_alloc_map_lock(gmap->mm, (pmd_t *) table, gaddr, ptl);
+ }
+
+ /**
+ * gmap_pte_op_fixup - force a page in and connect the gmap page table
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: virtual address in the guest address space
+ * @vmaddr: address in the host process address space
+ * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
+ *
+ * Returns 0 if the caller can retry __gmap_translate (might fail again),
+ * -ENOMEM if out of memory and -EFAULT if anything goes wrong while fixing
+ * up or connecting the gmap page table.
+ */
+ static int gmap_pte_op_fixup(struct gmap *gmap, unsigned long gaddr,
+ unsigned long vmaddr, int prot)
+ {
+ struct mm_struct *mm = gmap->mm;
+ unsigned int fault_flags;
+ bool unlocked = false;
+
+ BUG_ON(gmap_is_shadow(gmap));
+ fault_flags = (prot == PROT_WRITE) ? FAULT_FLAG_WRITE : 0;
+ if (fixup_user_fault(current, mm, vmaddr, fault_flags, &unlocked))
+ return -EFAULT;
+ if (unlocked)
+ /* lost mmap_sem, caller has to retry __gmap_translate */
+ return 0;
+ /* Connect the page tables */
+ return __gmap_link(gmap, gaddr, vmaddr);
}
- EXPORT_SYMBOL_GPL(gmap_unregister_ipte_notifier);
/**
- * gmap_ipte_notify - mark a range of ptes for invalidation notification
+ * gmap_pte_op_end - release the page table lock
+ * @ptl: pointer to the spinlock pointer
+ */
+ static void gmap_pte_op_end(spinlock_t *ptl)
+ {
+ spin_unlock(ptl);
+ }
+
+ /*
+ * gmap_protect_range - remove access rights to memory and set pgste bits
* @gmap: pointer to guest mapping meta data structure
* @gaddr: virtual address in the guest address space
* @len: size of area
+ * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
+ * @bits: pgste notification bits to set
+ *
+ * Returns 0 if successfully protected, -ENOMEM if out of memory and
+ * -EFAULT if gaddr is invalid (or mapping for shadows is missing).
+ *
+ * Called with sg->mm->mmap_sem in read.
*
- * Returns 0 if for each page in the given range a gmap mapping exists and
- * the invalidation notification could be set. If the gmap mapping is missing
- * for one or more pages -EFAULT is returned. If no memory could be allocated
- * -ENOMEM is returned. This function establishes missing page table entries.
+ * Note: Can also be called for shadow gmaps.
*/
- int gmap_ipte_notify(struct gmap *gmap, unsigned long gaddr, unsigned long len)
+ static int gmap_protect_range(struct gmap *gmap, unsigned long gaddr,
+ unsigned long len, int prot, unsigned long bits)
{
- unsigned long addr;
+ unsigned long vmaddr;
spinlock_t *ptl;
pte_t *ptep;
- bool unlocked;
- int rc = 0;
+ int rc;
+
+ while (len) {
+ rc = -EAGAIN;
+ ptep = gmap_pte_op_walk(gmap, gaddr, &ptl);
+ if (ptep) {
+ rc = ptep_force_prot(gmap->mm, gaddr, ptep, prot, bits);
+ gmap_pte_op_end(ptl);
+ }
+ if (rc) {
+ vmaddr = __gmap_translate(gmap, gaddr);
+ if (IS_ERR_VALUE(vmaddr))
+ return vmaddr;
+ rc = gmap_pte_op_fixup(gmap, gaddr, vmaddr, prot);
+ if (rc)
+ return rc;
+ continue;
+ }
+ gaddr += PAGE_SIZE;
+ len -= PAGE_SIZE;
+ }
+ return 0;
+ }
- if ((gaddr & ~PAGE_MASK) || (len & ~PAGE_MASK))
+ /**
+ * gmap_mprotect_notify - change access rights for a range of ptes and
+ * call the notifier if any pte changes again
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: virtual address in the guest address space
+ * @len: size of area
+ * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
+ *
+ * Returns 0 if for each page in the given range a gmap mapping exists,
+ * the new access rights could be set and the notifier could be armed.
+ * If the gmap mapping is missing for one or more pages -EFAULT is
+ * returned. If no memory could be allocated -ENOMEM is returned.
+ * This function establishes missing page table entries.
+ */
+ int gmap_mprotect_notify(struct gmap *gmap, unsigned long gaddr,
+ unsigned long len, int prot)
+ {
+ int rc;
+
+ if ((gaddr & ~PAGE_MASK) || (len & ~PAGE_MASK) || gmap_is_shadow(gmap))
+ return -EINVAL;
+ if (!MACHINE_HAS_ESOP && prot == PROT_READ)
return -EINVAL;
down_read(&gmap->mm->mmap_sem);
- while (len) {
- unlocked = false;
- /* Convert gmap address and connect the page tables */
- addr = __gmap_translate(gmap, gaddr);
- if (IS_ERR_VALUE(addr)) {
- rc = addr;
- break;
+ rc = gmap_protect_range(gmap, gaddr, len, prot, PGSTE_IN_BIT);
+ up_read(&gmap->mm->mmap_sem);
+ return rc;
+ }
+ EXPORT_SYMBOL_GPL(gmap_mprotect_notify);
+
+ /**
+ * gmap_read_table - get an unsigned long value from a guest page table using
+ * absolute addressing, without marking the page referenced.
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: virtual address in the guest address space
+ * @val: pointer to the unsigned long value to return
+ *
+ * Returns 0 if the value was read, -ENOMEM if out of memory and -EFAULT
+ * if reading using the virtual address failed.
+ *
+ * Called with gmap->mm->mmap_sem in read.
+ */
+ int gmap_read_table(struct gmap *gmap, unsigned long gaddr, unsigned long *val)
+ {
+ unsigned long address, vmaddr;
+ spinlock_t *ptl;
+ pte_t *ptep, pte;
+ int rc;
+
+ while (1) {
+ rc = -EAGAIN;
+ ptep = gmap_pte_op_walk(gmap, gaddr, &ptl);
+ if (ptep) {
+ pte = *ptep;
+ if (pte_present(pte) && (pte_val(pte) & _PAGE_READ)) {
+ address = pte_val(pte) & PAGE_MASK;
+ address += gaddr & ~PAGE_MASK;
+ *val = *(unsigned long *) address;
+ pte_val(*ptep) |= _PAGE_YOUNG;
+ /* Do *NOT* clear the _PAGE_INVALID bit! */
+ rc = 0;
+ }
+ gmap_pte_op_end(ptl);
}
- /* Get the page mapped */
- if (fixup_user_fault(current, gmap->mm, addr, FAULT_FLAG_WRITE,
- &unlocked)) {
- rc = -EFAULT;
+ if (!rc)
+ break;
+ vmaddr = __gmap_translate(gmap, gaddr);
+ if (IS_ERR_VALUE(vmaddr)) {
+ rc = vmaddr;
break;
}
- /* While trying to map mmap_sem got unlocked. Let us retry */
- if (unlocked)
- continue;
- rc = __gmap_link(gmap, gaddr, addr);
+ rc = gmap_pte_op_fixup(gmap, gaddr, vmaddr, PROT_READ);
if (rc)
break;
- /* Walk the process page table, lock and get pte pointer */
- ptep = get_locked_pte(gmap->mm, addr, &ptl);
- VM_BUG_ON(!ptep);
- /* Set notification bit in the pgste of the pte */
- if ((pte_val(*ptep) & (_PAGE_INVALID | _PAGE_PROTECT)) == 0) {
- ptep_set_notify(gmap->mm, addr, ptep);
- gaddr += PAGE_SIZE;
- len -= PAGE_SIZE;
- }
- pte_unmap_unlock(ptep, ptl);
}
- up_read(&gmap->mm->mmap_sem);
return rc;
}
- EXPORT_SYMBOL_GPL(gmap_ipte_notify);
+ EXPORT_SYMBOL_GPL(gmap_read_table);
/**
- * ptep_notify - call all invalidation callbacks for a specific pte.
- * @mm: pointer to the process mm_struct
- * @addr: virtual address in the process address space
- * @pte: pointer to the page table entry
+ * gmap_insert_rmap - add a rmap to the host_to_rmap radix tree
+ * @sg: pointer to the shadow guest address space structure
+ * @vmaddr: vm address associated with the rmap
+ * @rmap: pointer to the rmap structure
*
- * This function is assumed to be called with the page table lock held
- * for the pte to notify.
+ * Called with the sg->guest_table_lock
*/
- void ptep_notify(struct mm_struct *mm, unsigned long vmaddr, pte_t *pte)
+ static inline void gmap_insert_rmap(struct gmap *sg, unsigned long vmaddr,
+ struct gmap_rmap *rmap)
{
- unsigned long offset, gaddr;
- unsigned long *table;
- struct gmap_notifier *nb;
- struct gmap *gmap;
+ void **slot;
- offset = ((unsigned long) pte) & (255 * sizeof(pte_t));
- offset = offset * (4096 / sizeof(pte_t));
- spin_lock(&gmap_notifier_lock);
- list_for_each_entry(gmap, &mm->context.gmap_list, list) {
- table = radix_tree_lookup(&gmap->host_to_guest,
- vmaddr >> PMD_SHIFT);
- if (!table)
+ BUG_ON(!gmap_is_shadow(sg));
+ slot = radix_tree_lookup_slot(&sg->host_to_rmap, vmaddr >> PAGE_SHIFT);
+ if (slot) {
+ rmap->next = radix_tree_deref_slot_protected(slot,
+ &sg->guest_table_lock);
+ radix_tree_replace_slot(slot, rmap);
+ } else {
+ rmap->next = NULL;
+ radix_tree_insert(&sg->host_to_rmap, vmaddr >> PAGE_SHIFT,
+ rmap);
+ }
+ }
+
+ /**
+ * gmap_protect_rmap - modify access rights to memory and create an rmap
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: rmap address in the shadow gmap
+ * @paddr: address in the parent guest address space
+ * @len: length of the memory area to protect
+ * @prot: indicates access rights: none, read-only or read-write
+ *
+ * Returns 0 if successfully protected and the rmap was created, -ENOMEM
+ * if out of memory and -EFAULT if paddr is invalid.
+ */
+ static int gmap_protect_rmap(struct gmap *sg, unsigned long raddr,
+ unsigned long paddr, unsigned long len, int prot)
+ {
+ struct gmap *parent;
+ struct gmap_rmap *rmap;
+ unsigned long vmaddr;
+ spinlock_t *ptl;
+ pte_t *ptep;
+ int rc;
+
+ BUG_ON(!gmap_is_shadow(sg));
+ parent = sg->parent;
+ while (len) {
+ vmaddr = __gmap_translate(parent, paddr);
+ if (IS_ERR_VALUE(vmaddr))
+ return vmaddr;
+ rmap = kzalloc(sizeof(*rmap), GFP_KERNEL);
+ if (!rmap)
+ return -ENOMEM;
+ rmap->raddr = raddr;
+ rc = radix_tree_preload(GFP_KERNEL);
+ if (rc) {
+ kfree(rmap);
+ return rc;
+ }
+ rc = -EAGAIN;
+ ptep = gmap_pte_op_walk(parent, paddr, &ptl);
+ if (ptep) {
+ spin_lock(&sg->guest_table_lock);
+ rc = ptep_force_prot(parent->mm, paddr, ptep, prot,
+ PGSTE_VSIE_BIT);
+ if (!rc)
+ gmap_insert_rmap(sg, vmaddr, rmap);
+ spin_unlock(&sg->guest_table_lock);
+ gmap_pte_op_end(ptl);
+ }
+ radix_tree_preload_end();
+ if (rc) {
+ kfree(rmap);
+ rc = gmap_pte_op_fixup(parent, paddr, vmaddr, prot);
+ if (rc)
+ return rc;
continue;
- gaddr = __gmap_segment_gaddr(table) + offset;
- list_for_each_entry(nb, &gmap_notifier_list, list)
- nb->notifier_call(gmap, gaddr);
+ }
+ paddr += PAGE_SIZE;
+ len -= PAGE_SIZE;
}
- spin_unlock(&gmap_notifier_lock);
+ return 0;
+ }
+
+ #define _SHADOW_RMAP_MASK 0x7
+ #define _SHADOW_RMAP_REGION1 0x5
+ #define _SHADOW_RMAP_REGION2 0x4
+ #define _SHADOW_RMAP_REGION3 0x3
+ #define _SHADOW_RMAP_SEGMENT 0x2
+ #define _SHADOW_RMAP_PGTABLE 0x1
+
+ /**
+ * gmap_idte_one - invalidate a single region or segment table entry
+ * @asce: region or segment table *origin* + table-type bits
+ * @vaddr: virtual address to identify the table entry to flush
+ *
+ * The invalid bit of a single region or segment table entry is set
+ * and the associated TLB entries depending on the entry are flushed.
+ * The table-type of the @asce identifies the portion of the @vaddr
+ * that is used as the invalidation index.
+ */
+ static inline void gmap_idte_one(unsigned long asce, unsigned long vaddr)
+ {
+ asm volatile(
+ " .insn rrf,0xb98e0000,%0,%1,0,0"
+ : : "a" (asce), "a" (vaddr) : "cc", "memory");
+ }
+
+ /**
+ * gmap_unshadow_page - remove a page from a shadow page table
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: rmap address in the shadow guest address space
+ *
+ * Called with the sg->guest_table_lock
+ */
+ static void gmap_unshadow_page(struct gmap *sg, unsigned long raddr)
+ {
+ unsigned long *table;
+
+ BUG_ON(!gmap_is_shadow(sg));
+ table = gmap_table_walk(sg, raddr, 0); /* get page table pointer */
+ if (!table || *table & _PAGE_INVALID)
+ return;
+ gmap_call_notifier(sg, raddr, raddr + (1UL << 12) - 1);
+ ptep_unshadow_pte(sg->mm, raddr, (pte_t *) table);
+ }
+
+ /**
+ * __gmap_unshadow_pgt - remove all entries from a shadow page table
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: rmap address in the shadow guest address space
+ * @pgt: pointer to the start of a shadow page table
+ *
+ * Called with the sg->guest_table_lock
+ */
+ static void __gmap_unshadow_pgt(struct gmap *sg, unsigned long raddr,
+ unsigned long *pgt)
+ {
+ int i;
+
+ BUG_ON(!gmap_is_shadow(sg));
+ for (i = 0; i < 256; i++, raddr += 1UL << 12)
+ pgt[i] = _PAGE_INVALID;
+ }
+
+ /**
+ * gmap_unshadow_pgt - remove a shadow page table from a segment entry
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: address in the shadow guest address space
+ *
+ * Called with the sg->guest_table_lock
+ */
+ static void gmap_unshadow_pgt(struct gmap *sg, unsigned long raddr)
+ {
+ unsigned long sto, *ste, *pgt;
+ struct page *page;
+
+ BUG_ON(!gmap_is_shadow(sg));
+ ste = gmap_table_walk(sg, raddr, 1); /* get segment pointer */
+ if (!ste || !(*ste & _SEGMENT_ENTRY_ORIGIN))
+ return;
+ gmap_call_notifier(sg, raddr, raddr + (1UL << 20) - 1);
+ sto = (unsigned long) (ste - ((raddr >> 20) & 0x7ff));
+ gmap_idte_one(sto | _ASCE_TYPE_SEGMENT, raddr);
+ pgt = (unsigned long *)(*ste & _SEGMENT_ENTRY_ORIGIN);
+ *ste = _SEGMENT_ENTRY_EMPTY;
+ __gmap_unshadow_pgt(sg, raddr, pgt);
+ /* Free page table */
+ page = pfn_to_page(__pa(pgt) >> PAGE_SHIFT);
+ list_del(&page->lru);
+ page_table_free_pgste(page);
+ }
+
+ /**
+ * __gmap_unshadow_sgt - remove all entries from a shadow segment table
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: rmap address in the shadow guest address space
+ * @sgt: pointer to the start of a shadow segment table
+ *
+ * Called with the sg->guest_table_lock
+ */
+ static void __gmap_unshadow_sgt(struct gmap *sg, unsigned long raddr,
+ unsigned long *sgt)
+ {
+ unsigned long asce, *pgt;
+ struct page *page;
+ int i;
+
+ BUG_ON(!gmap_is_shadow(sg));
+ asce = (unsigned long) sgt | _ASCE_TYPE_SEGMENT;
+ for (i = 0; i < 2048; i++, raddr += 1UL << 20) {
+ if (!(sgt[i] & _SEGMENT_ENTRY_ORIGIN))
+ continue;
+ pgt = (unsigned long *)(sgt[i] & _REGION_ENTRY_ORIGIN);
+ sgt[i] = _SEGMENT_ENTRY_EMPTY;
+ __gmap_unshadow_pgt(sg, raddr, pgt);
+ /* Free page table */
+ page = pfn_to_page(__pa(pgt) >> PAGE_SHIFT);
+ list_del(&page->lru);
+ page_table_free_pgste(page);
+ }
+ }
+
+ /**
+ * gmap_unshadow_sgt - remove a shadow segment table from a region-3 entry
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: rmap address in the shadow guest address space
+ *
+ * Called with the shadow->guest_table_lock
+ */
+ static void gmap_unshadow_sgt(struct gmap *sg, unsigned long raddr)
+ {
+ unsigned long r3o, *r3e, *sgt;
+ struct page *page;
+
+ BUG_ON(!gmap_is_shadow(sg));
+ r3e = gmap_table_walk(sg, raddr, 2); /* get region-3 pointer */
+ if (!r3e || !(*r3e & _REGION_ENTRY_ORIGIN))
+ return;
+ gmap_call_notifier(sg, raddr, raddr + (1UL << 31) - 1);
+ r3o = (unsigned long) (r3e - ((raddr >> 31) & 0x7ff));
+ gmap_idte_one(r3o | _ASCE_TYPE_REGION3, raddr);
+ sgt = (unsigned long *)(*r3e & _REGION_ENTRY_ORIGIN);
+ *r3e = _REGION3_ENTRY_EMPTY;
+ __gmap_unshadow_sgt(sg, raddr, sgt);
+ /* Free segment table */
+ page = pfn_to_page(__pa(sgt) >> PAGE_SHIFT);
+ list_del(&page->lru);
+ __free_pages(page, 2);
+ }
+
+ /**
+ * __gmap_unshadow_r3t - remove all entries from a shadow region-3 table
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: address in the shadow guest address space
+ * @r3t: pointer to the start of a shadow region-3 table
+ *
+ * Called with the sg->guest_table_lock
+ */
+ static void __gmap_unshadow_r3t(struct gmap *sg, unsigned long raddr,
+ unsigned long *r3t)
+ {
+ unsigned long asce, *sgt;
+ struct page *page;
+ int i;
+
+ BUG_ON(!gmap_is_shadow(sg));
+ asce = (unsigned long) r3t | _ASCE_TYPE_REGION3;
+ for (i = 0; i < 2048; i++, raddr += 1UL << 31) {
+ if (!(r3t[i] & _REGION_ENTRY_ORIGIN))
+ continue;
+ sgt = (unsigned long *)(r3t[i] & _REGION_ENTRY_ORIGIN);
+ r3t[i] = _REGION3_ENTRY_EMPTY;
+ __gmap_unshadow_sgt(sg, raddr, sgt);
+ /* Free segment table */
+ page = pfn_to_page(__pa(sgt) >> PAGE_SHIFT);
+ list_del(&page->lru);
+ __free_pages(page, 2);
+ }
+ }
+
+ /**
+ * gmap_unshadow_r3t - remove a shadow region-3 table from a region-2 entry
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: rmap address in the shadow guest address space
+ *
+ * Called with the sg->guest_table_lock
+ */
+ static void gmap_unshadow_r3t(struct gmap *sg, unsigned long raddr)
+ {
+ unsigned long r2o, *r2e, *r3t;
+ struct page *page;
+
+ BUG_ON(!gmap_is_shadow(sg));
+ r2e = gmap_table_walk(sg, raddr, 3); /* get region-2 pointer */
+ if (!r2e || !(*r2e & _REGION_ENTRY_ORIGIN))
+ return;
+ gmap_call_notifier(sg, raddr, raddr + (1UL << 42) - 1);
+ r2o = (unsigned long) (r2e - ((raddr >> 42) & 0x7ff));
+ gmap_idte_one(r2o | _ASCE_TYPE_REGION2, raddr);
+ r3t = (unsigned long *)(*r2e & _REGION_ENTRY_ORIGIN);
+ *r2e = _REGION2_ENTRY_EMPTY;
+ __gmap_unshadow_r3t(sg, raddr, r3t);
+ /* Free region 3 table */
+ page = pfn_to_page(__pa(r3t) >> PAGE_SHIFT);
+ list_del(&page->lru);
+ __free_pages(page, 2);
+ }
+
+ /**
+ * __gmap_unshadow_r2t - remove all entries from a shadow region-2 table
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: rmap address in the shadow guest address space
+ * @r2t: pointer to the start of a shadow region-2 table
+ *
+ * Called with the sg->guest_table_lock
+ */
+ static void __gmap_unshadow_r2t(struct gmap *sg, unsigned long raddr,
+ unsigned long *r2t)
+ {
+ unsigned long asce, *r3t;
+ struct page *page;
+ int i;
+
+ BUG_ON(!gmap_is_shadow(sg));
+ asce = (unsigned long) r2t | _ASCE_TYPE_REGION2;
+ for (i = 0; i < 2048; i++, raddr += 1UL << 42) {
+ if (!(r2t[i] & _REGION_ENTRY_ORIGIN))
+ continue;
+ r3t = (unsigned long *)(r2t[i] & _REGION_ENTRY_ORIGIN);
+ r2t[i] = _REGION2_ENTRY_EMPTY;
+ __gmap_unshadow_r3t(sg, raddr, r3t);
+ /* Free region 3 table */
+ page = pfn_to_page(__pa(r3t) >> PAGE_SHIFT);
+ list_del(&page->lru);
+ __free_pages(page, 2);
+ }
+ }
+
+ /**
+ * gmap_unshadow_r2t - remove a shadow region-2 table from a region-1 entry
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: rmap address in the shadow guest address space
+ *
+ * Called with the sg->guest_table_lock
+ */
+ static void gmap_unshadow_r2t(struct gmap *sg, unsigned long raddr)
+ {
+ unsigned long r1o, *r1e, *r2t;
+ struct page *page;
+
+ BUG_ON(!gmap_is_shadow(sg));
+ r1e = gmap_table_walk(sg, raddr, 4); /* get region-1 pointer */
+ if (!r1e || !(*r1e & _REGION_ENTRY_ORIGIN))
+ return;
+ gmap_call_notifier(sg, raddr, raddr + (1UL << 53) - 1);
+ r1o = (unsigned long) (r1e - ((raddr >> 53) & 0x7ff));
+ gmap_idte_one(r1o | _ASCE_TYPE_REGION1, raddr);
+ r2t = (unsigned long *)(*r1e & _REGION_ENTRY_ORIGIN);
+ *r1e = _REGION1_ENTRY_EMPTY;
+ __gmap_unshadow_r2t(sg, raddr, r2t);
+ /* Free region 2 table */
+ page = pfn_to_page(__pa(r2t) >> PAGE_SHIFT);
+ list_del(&page->lru);
+ __free_pages(page, 2);
+ }
+
+ /**
+ * __gmap_unshadow_r1t - remove all entries from a shadow region-1 table
+ * @sg: pointer to the shadow guest address space structure
+ * @raddr: rmap address in the shadow guest address space
+ * @r1t: pointer to the start of a shadow region-1 table
+ *
+ * Called with the shadow->guest_table_lock
+ */
+ static void __gmap_unshadow_r1t(struct gmap *sg, unsigned long raddr,
+ unsigned long *r1t)
+ {
+ unsigned long asce, *r2t;
+ struct page *page;
+ int i;
+
+ BUG_ON(!gmap_is_shadow(sg));
+ asce = (unsigned long) r1t | _ASCE_TYPE_REGION1;
+ for (i = 0; i < 2048; i++, raddr += 1UL << 53) {
+ if (!(r1t[i] & _REGION_ENTRY_ORIGIN))
+ continue;
+ r2t = (unsigned long *)(r1t[i] & _REGION_ENTRY_ORIGIN);
+ __gmap_unshadow_r2t(sg, raddr, r2t);
+ /* Clear entry and flush translation r1t -> r2t */
+ gmap_idte_one(asce, raddr);
+ r1t[i] = _REGION1_ENTRY_EMPTY;
+ /* Free region 2 table */
+ page = pfn_to_page(__pa(r2t) >> PAGE_SHIFT);
+ list_del(&page->lru);
+ __free_pages(page, 2);
+ }
+ }
+
+ /**
+ * gmap_unshadow - remove a shadow page table completely
+ * @sg: pointer to the shadow guest address space structure
+ *
+ * Called with sg->guest_table_lock
+ */
+ static void gmap_unshadow(struct gmap *sg)
+ {
+ unsigned long *table;
+
+ BUG_ON(!gmap_is_shadow(sg));
+ if (sg->removed)
+ return;
+ sg->removed = 1;
+ gmap_call_notifier(sg, 0, -1UL);
+ gmap_flush_tlb(sg);
+ table = (unsigned long *)(sg->asce & _ASCE_ORIGIN);
+ switch (sg->asce & _ASCE_TYPE_MASK) {
+ case _ASCE_TYPE_REGION1:
+ __gmap_unshadow_r1t(sg, 0, table);
+ break;
+ case _ASCE_TYPE_REGION2:
+ __gmap_unshadow_r2t(sg, 0, table);
+ break;
+ case _ASCE_TYPE_REGION3:
+ __gmap_unshadow_r3t(sg, 0, table);
+ break;
+ case _ASCE_TYPE_SEGMENT:
+ __gmap_unshadow_sgt(sg, 0, table);
+ break;
+ }
+ }
+
+ /**
+ * gmap_find_shadow - find a specific asce in the list of shadow tables
+ * @parent: pointer to the parent gmap
+ * @asce: ASCE for which the shadow table is created
+ * @edat_level: edat level to be used for the shadow translation
+ *
+ * Returns the pointer to a gmap if a shadow table with the given asce is
+ * already available, ERR_PTR(-EAGAIN) if another one is just being created,
+ * otherwise NULL
+ */
+ static struct gmap *gmap_find_shadow(struct gmap *parent, unsigned long asce,
+ int edat_level)
+ {
+ struct gmap *sg;
+
+ list_for_each_entry(sg, &parent->children, list) {
+ if (sg->orig_asce != asce || sg->edat_level != edat_level ||
+ sg->removed)
+ continue;
+ if (!sg->initialized)
+ return ERR_PTR(-EAGAIN);
+ atomic_inc(&sg->ref_count);
+ return sg;
+ }
+ return NULL;
+ }
+
+ /**
+ * gmap_shadow_valid - check if a shadow guest address space matches the
+ * given properties and is still valid
+ * @sg: pointer to the shadow guest address space structure
+ * @asce: ASCE for which the shadow table is requested
+ * @edat_level: edat level to be used for the shadow translation
+ *
+ * Returns 1 if the gmap shadow is still valid and matches the given
+ * properties, the caller can continue using it. Returns 0 otherwise, the
+ * caller has to request a new shadow gmap in this case.
+ *
+ */
+ int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level)
+ {
+ if (sg->removed)
+ return 0;
+ return sg->orig_asce == asce && sg->edat_level == edat_level;
+ }
+ EXPORT_SYMBOL_GPL(gmap_shadow_valid);
+
+ /**
+ * gmap_shadow - create/find a shadow guest address space
+ * @parent: pointer to the parent gmap
+ * @asce: ASCE for which the shadow table is created
+ * @edat_level: edat level to be used for the shadow translation
+ *
+ * The pages of the top level page table referred by the asce parameter
+ * will be set to read-only and marked in the PGSTEs of the kvm process.
+ * The shadow table will be removed automatically on any change to the
+ * PTE mapping for the source table.
+ *
+ * Returns a guest address space structure, ERR_PTR(-ENOMEM) if out of memory,
+ * ERR_PTR(-EAGAIN) if the caller has to retry and ERR_PTR(-EFAULT) if the
+ * parent gmap table could not be protected.
+ */
+ struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce,
+ int edat_level)
+ {
+ struct gmap *sg, *new;
+ unsigned long limit;
+ int rc;
+
+ BUG_ON(gmap_is_shadow(parent));
+ spin_lock(&parent->shadow_lock);
+ sg = gmap_find_shadow(parent, asce, edat_level);
+ spin_unlock(&parent->shadow_lock);
+ if (sg)
+ return sg;
+ /* Create a new shadow gmap */
+ limit = -1UL >> (33 - (((asce & _ASCE_TYPE_MASK) >> 2) * 11));
+ if (asce & _ASCE_REAL_SPACE)
+ limit = -1UL;
+ new = gmap_alloc(limit);
+ if (!new)
+ return ERR_PTR(-ENOMEM);
+ new->mm = parent->mm;
+ new->parent = gmap_get(parent);
+ new->orig_asce = asce;
+ new->edat_level = edat_level;
+ new->initialized = false;
+ spin_lock(&parent->shadow_lock);
+ /* Recheck if another CPU created the same shadow */
+ sg = gmap_find_shadow(parent, asce, edat_level);
+ if (sg) {
+ spin_unlock(&parent->shadow_lock);
+ gmap_free(new);
+ return sg;
+ }
+ if (asce & _ASCE_REAL_SPACE) {
+ /* only allow one real-space gmap shadow */
+ list_for_each_entry(sg, &parent->children, list) {
+ if (sg->orig_asce & _ASCE_REAL_SPACE) {
+ spin_lock(&sg->guest_table_lock);
+ gmap_unshadow(sg);
+ spin_unlock(&sg->guest_table_lock);
+ list_del(&sg->list);
+ gmap_put(sg);
+ break;
+ }
+ }
+ }
+ atomic_set(&new->ref_count, 2);
+ list_add(&new->list, &parent->children);
+ if (asce & _ASCE_REAL_SPACE) {
+ /* nothing to protect, return right away */
+ new->initialized = true;
+ spin_unlock(&parent->shadow_lock);
+ return new;
+ }
+ spin_unlock(&parent->shadow_lock);
+ /* protect after insertion, so it will get properly invalidated */
+ down_read(&parent->mm->mmap_sem);
+ rc = gmap_protect_range(parent, asce & _ASCE_ORIGIN,
+ ((asce & _ASCE_TABLE_LENGTH) + 1) * 4096,
+ PROT_READ, PGSTE_VSIE_BIT);
+ up_read(&parent->mm->mmap_sem);
+ spin_lock(&parent->shadow_lock);
+ new->initialized = true;
+ if (rc) {
+ list_del(&new->list);
+ gmap_free(new);
+ new = ERR_PTR(rc);
+ }
+ spin_unlock(&parent->shadow_lock);
+ return new;
+ }
+ EXPORT_SYMBOL_GPL(gmap_shadow);
+
+ /**
+ * gmap_shadow_r2t - create an empty shadow region 2 table
+ * @sg: pointer to the shadow guest address space structure
+ * @saddr: faulting address in the shadow gmap
+ * @r2t: parent gmap address of the region 2 table to get shadowed
+ * @fake: r2t references contiguous guest memory block, not a r2t
+ *
+ * The r2t parameter specifies the address of the source table. The
+ * four pages of the source table are made read-only in the parent gmap
+ * address space. A write to the source table area @r2t will automatically
+ * remove the shadow r2 table and all of its decendents.
+ *
+ * Returns 0 if successfully shadowed or already shadowed, -EAGAIN if the
+ * shadow table structure is incomplete, -ENOMEM if out of memory and
+ * -EFAULT if an address in the parent gmap could not be resolved.
+ *
+ * Called with sg->mm->mmap_sem in read.
+ */
+ int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t,
+ int fake)
+ {
+ unsigned long raddr, origin, offset, len;
+ unsigned long *s_r2t, *table;
+ struct page *page;
+ int rc;
+
+ BUG_ON(!gmap_is_shadow(sg));
+ /* Allocate a shadow region second table */
+ page = alloc_pages(GFP_KERNEL, 2);
+ if (!page)
+ return -ENOMEM;
+ page->index = r2t & _REGION_ENTRY_ORIGIN;
+ if (fake)
+ page->index |= GMAP_SHADOW_FAKE_TABLE;
+ s_r2t = (unsigned long *) page_to_phys(page);
+ /* Install shadow region second table */
+ spin_lock(&sg->guest_table_lock);
+ table = gmap_table_walk(sg, saddr, 4); /* get region-1 pointer */
+ if (!table) {
+ rc = -EAGAIN; /* Race with unshadow */
+ goto out_free;
+ }
+ if (!(*table & _REGION_ENTRY_INVALID)) {
+ rc = 0; /* Already established */
+ goto out_free;
+ } else if (*table & _REGION_ENTRY_ORIGIN) {
+ rc = -EAGAIN; /* Race with shadow */
+ goto out_free;
+ }
+ crst_table_init(s_r2t, _REGION2_ENTRY_EMPTY);
+ /* mark as invalid as long as the parent table is not protected */
+ *table = (unsigned long) s_r2t | _REGION_ENTRY_LENGTH |
+ _REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_INVALID;
+ if (sg->edat_level >= 1)
+ *table |= (r2t & _REGION_ENTRY_PROTECT);
+ list_add(&page->lru, &sg->crst_list);
+ if (fake) {
+ /* nothing to protect for fake tables */
+ *table &= ~_REGION_ENTRY_INVALID;
+ spin_unlock(&sg->guest_table_lock);
+ return 0;
+ }
+ spin_unlock(&sg->guest_table_lock);
+ /* Make r2t read-only in parent gmap page table */
+ raddr = (saddr & 0xffe0000000000000UL) | _SHADOW_RMAP_REGION1;
+ origin = r2t & _REGION_ENTRY_ORIGIN;
+ offset = ((r2t & _REGION_ENTRY_OFFSET) >> 6) * 4096;
+ len = ((r2t & _REGION_ENTRY_LENGTH) + 1) * 4096 - offset;
+ rc = gmap_protect_rmap(sg, raddr, origin + offset, len, PROT_READ);
+ spin_lock(&sg->guest_table_lock);
+ if (!rc) {
+ table = gmap_table_walk(sg, saddr, 4);
+ if (!table || (*table & _REGION_ENTRY_ORIGIN) !=
+ (unsigned long) s_r2t)
+ rc = -EAGAIN; /* Race with unshadow */
+ else
+ *table &= ~_REGION_ENTRY_INVALID;
+ } else {
+ gmap_unshadow_r2t(sg, raddr);
+ }
+ spin_unlock(&sg->guest_table_lock);
+ return rc;
+ out_free:
+ spin_unlock(&sg->guest_table_lock);
+ __free_pages(page, 2);
+ return rc;
+ }
+ EXPORT_SYMBOL_GPL(gmap_shadow_r2t);
+
+ /**
+ * gmap_shadow_r3t - create a shadow region 3 table
+ * @sg: pointer to the shadow guest address space structure
+ * @saddr: faulting address in the shadow gmap
+ * @r3t: parent gmap address of the region 3 table to get shadowed
+ * @fake: r3t references contiguous guest memory block, not a r3t
+ *
+ * Returns 0 if successfully shadowed or already shadowed, -EAGAIN if the
+ * shadow table structure is incomplete, -ENOMEM if out of memory and
+ * -EFAULT if an address in the parent gmap could not be resolved.
+ *
+ * Called with sg->mm->mmap_sem in read.
+ */
+ int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t,
+ int fake)
+ {
+ unsigned long raddr, origin, offset, len;
+ unsigned long *s_r3t, *table;
+ struct page *page;
+ int rc;
+
+ BUG_ON(!gmap_is_shadow(sg));
+ /* Allocate a shadow region second table */
+ page = alloc_pages(GFP_KERNEL, 2);
+ if (!page)
+ return -ENOMEM;
+ page->index = r3t & _REGION_ENTRY_ORIGIN;
+ if (fake)
+ page->index |= GMAP_SHADOW_FAKE_TABLE;
+ s_r3t = (unsigned long *) page_to_phys(page);
+ /* Install shadow region second table */
+ spin_lock(&sg->guest_table_lock);
+ table = gmap_table_walk(sg, saddr, 3); /* get region-2 pointer */
+ if (!table) {
+ rc = -EAGAIN; /* Race with unshadow */
+ goto out_free;
+ }
+ if (!(*table & _REGION_ENTRY_INVALID)) {
+ rc = 0; /* Already established */
+ goto out_free;
+ } else if (*table & _REGION_ENTRY_ORIGIN) {
+ rc = -EAGAIN; /* Race with shadow */
+ }
+ crst_table_init(s_r3t, _REGION3_ENTRY_EMPTY);
+ /* mark as invalid as long as the parent table is not protected */
+ *table = (unsigned long) s_r3t | _REGION_ENTRY_LENGTH |
+ _REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_INVALID;
+ if (sg->edat_level >= 1)
+ *table |= (r3t & _REGION_ENTRY_PROTECT);
+ list_add(&page->lru, &sg->crst_list);
+ if (fake) {
+ /* nothing to protect for fake tables */
+ *table &= ~_REGION_ENTRY_INVALID;
+ spin_unlock(&sg->guest_table_lock);
+ return 0;
+ }
+ spin_unlock(&sg->guest_table_lock);
+ /* Make r3t read-only in parent gmap page table */
+ raddr = (saddr & 0xfffffc0000000000UL) | _SHADOW_RMAP_REGION2;
+ origin = r3t & _REGION_ENTRY_ORIGIN;
+ offset = ((r3t & _REGION_ENTRY_OFFSET) >> 6) * 4096;
+ len = ((r3t & _REGION_ENTRY_LENGTH) + 1) * 4096 - offset;
+ rc = gmap_protect_rmap(sg, raddr, origin + offset, len, PROT_READ);
+ spin_lock(&sg->guest_table_lock);
+ if (!rc) {
+ table = gmap_table_walk(sg, saddr, 3);
+ if (!table || (*table & _REGION_ENTRY_ORIGIN) !=
+ (unsigned long) s_r3t)
+ rc = -EAGAIN; /* Race with unshadow */
+ else
+ *table &= ~_REGION_ENTRY_INVALID;
+ } else {
+ gmap_unshadow_r3t(sg, raddr);
+ }
+ spin_unlock(&sg->guest_table_lock);
+ return rc;
+ out_free:
+ spin_unlock(&sg->guest_table_lock);
+ __free_pages(page, 2);
+ return rc;
+ }
+ EXPORT_SYMBOL_GPL(gmap_shadow_r3t);
+
+ /**
+ * gmap_shadow_sgt - create a shadow segment table
+ * @sg: pointer to the shadow guest address space structure
+ * @saddr: faulting address in the shadow gmap
+ * @sgt: parent gmap address of the segment table to get shadowed
+ * @fake: sgt references contiguous guest memory block, not a sgt
+ *
+ * Returns: 0 if successfully shadowed or already shadowed, -EAGAIN if the
+ * shadow table structure is incomplete, -ENOMEM if out of memory and
+ * -EFAULT if an address in the parent gmap could not be resolved.
+ *
+ * Called with sg->mm->mmap_sem in read.
+ */
+ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt,
+ int fake)
+ {
+ unsigned long raddr, origin, offset, len;
+ unsigned long *s_sgt, *table;
+ struct page *page;
+ int rc;
+
+ BUG_ON(!gmap_is_shadow(sg) || (sgt & _REGION3_ENTRY_LARGE));
+ /* Allocate a shadow segment table */
+ page = alloc_pages(GFP_KERNEL, 2);
+ if (!page)
+ return -ENOMEM;
+ page->index = sgt & _REGION_ENTRY_ORIGIN;
+ if (fake)
+ page->index |= GMAP_SHADOW_FAKE_TABLE;
+ s_sgt = (unsigned long *) page_to_phys(page);
+ /* Install shadow region second table */
+ spin_lock(&sg->guest_table_lock);
+ table = gmap_table_walk(sg, saddr, 2); /* get region-3 pointer */
+ if (!table) {
+ rc = -EAGAIN; /* Race with unshadow */
+ goto out_free;
+ }
+ if (!(*table & _REGION_ENTRY_INVALID)) {
+ rc = 0; /* Already established */
+ goto out_free;
+ } else if (*table & _REGION_ENTRY_ORIGIN) {
+ rc = -EAGAIN; /* Race with shadow */
+ goto out_free;
+ }
+ crst_table_init(s_sgt, _SEGMENT_ENTRY_EMPTY);
+ /* mark as invalid as long as the parent table is not protected */
+ *table = (unsigned long) s_sgt | _REGION_ENTRY_LENGTH |
+ _REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INVALID;
+ if (sg->edat_level >= 1)
+ *table |= sgt & _REGION_ENTRY_PROTECT;
+ list_add(&page->lru, &sg->crst_list);
+ if (fake) {
+ /* nothing to protect for fake tables */
+ *table &= ~_REGION_ENTRY_INVALID;
+ spin_unlock(&sg->guest_table_lock);
+ return 0;
+ }
+ spin_unlock(&sg->guest_table_lock);
+ /* Make sgt read-only in parent gmap page table */
+ raddr = (saddr & 0xffffffff80000000UL) | _SHADOW_RMAP_REGION3;
+ origin = sgt & _REGION_ENTRY_ORIGIN;
+ offset = ((sgt & _REGION_ENTRY_OFFSET) >> 6) * 4096;
+ len = ((sgt & _REGION_ENTRY_LENGTH) + 1) * 4096 - offset;
+ rc = gmap_protect_rmap(sg, raddr, origin + offset, len, PROT_READ);
+ spin_lock(&sg->guest_table_lock);
+ if (!rc) {
+ table = gmap_table_walk(sg, saddr, 2);
+ if (!table || (*table & _REGION_ENTRY_ORIGIN) !=
+ (unsigned long) s_sgt)
+ rc = -EAGAIN; /* Race with unshadow */
+ else
+ *table &= ~_REGION_ENTRY_INVALID;
+ } else {
+ gmap_unshadow_sgt(sg, raddr);
+ }
+ spin_unlock(&sg->guest_table_lock);
+ return rc;
+ out_free:
+ spin_unlock(&sg->guest_table_lock);
+ __free_pages(page, 2);
+ return rc;
+ }
+ EXPORT_SYMBOL_GPL(gmap_shadow_sgt);
+
+ /**
+ * gmap_shadow_lookup_pgtable - find a shadow page table
+ * @sg: pointer to the shadow guest address space structure
+ * @saddr: the address in the shadow aguest address space
+ * @pgt: parent gmap address of the page table to get shadowed
+ * @dat_protection: if the pgtable is marked as protected by dat
+ * @fake: pgt references contiguous guest memory block, not a pgtable
+ *
+ * Returns 0 if the shadow page table was found and -EAGAIN if the page
+ * table was not found.
+ *
+ * Called with sg->mm->mmap_sem in read.
+ */
+ int gmap_shadow_pgt_lookup(struct gmap *sg, unsigned long saddr,
+ unsigned long *pgt, int *dat_protection,
+ int *fake)
+ {
+ unsigned long *table;
+ struct page *page;
+ int rc;
+
+ BUG_ON(!gmap_is_shadow(sg));
+ spin_lock(&sg->guest_table_lock);
+ table = gmap_table_walk(sg, saddr, 1); /* get segment pointer */
+ if (table && !(*table & _SEGMENT_ENTRY_INVALID)) {
+ /* Shadow page tables are full pages (pte+pgste) */
+ page = pfn_to_page(*table >> PAGE_SHIFT);
+ *pgt = page->index & ~GMAP_SHADOW_FAKE_TABLE;
+ *dat_protection = !!(*table & _SEGMENT_ENTRY_PROTECT);
+ *fake = !!(page->index & GMAP_SHADOW_FAKE_TABLE);
+ rc = 0;
+ } else {
+ rc = -EAGAIN;
+ }
+ spin_unlock(&sg->guest_table_lock);
+ return rc;
+
+ }
+ EXPORT_SYMBOL_GPL(gmap_shadow_pgt_lookup);
+
+ /**
+ * gmap_shadow_pgt - instantiate a shadow page table
+ * @sg: pointer to the shadow guest address space structure
+ * @saddr: faulting address in the shadow gmap
+ * @pgt: parent gmap address of the page table to get shadowed
+ * @fake: pgt references contiguous guest memory block, not a pgtable
+ *
+ * Returns 0 if successfully shadowed or already shadowed, -EAGAIN if the
+ * shadow table structure is incomplete, -ENOMEM if out of memory,
+ * -EFAULT if an address in the parent gmap could not be resolved and
+ *
+ * Called with gmap->mm->mmap_sem in read
+ */
+ int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt,
+ int fake)
+ {
+ unsigned long raddr, origin;
+ unsigned long *s_pgt, *table;
+ struct page *page;
+ int rc;
+
+ BUG_ON(!gmap_is_shadow(sg) || (pgt & _SEGMENT_ENTRY_LARGE));
+ /* Allocate a shadow page table */
+ page = page_table_alloc_pgste(sg->mm);
+ if (!page)
+ return -ENOMEM;
+ page->index = pgt & _SEGMENT_ENTRY_ORIGIN;
+ if (fake)
+ page->index |= GMAP_SHADOW_FAKE_TABLE;
+ s_pgt = (unsigned long *) page_to_phys(page);
+ /* Install shadow page table */
+ spin_lock(&sg->guest_table_lock);
+ table = gmap_table_walk(sg, saddr, 1); /* get segment pointer */
+ if (!table) {
+ rc = -EAGAIN; /* Race with unshadow */
+ goto out_free;
+ }
+ if (!(*table & _SEGMENT_ENTRY_INVALID)) {
+ rc = 0; /* Already established */
+ goto out_free;
+ } else if (*table & _SEGMENT_ENTRY_ORIGIN) {
+ rc = -EAGAIN; /* Race with shadow */
+ goto out_free;
+ }
+ /* mark as invalid as long as the parent table is not protected */
+ *table = (unsigned long) s_pgt | _SEGMENT_ENTRY |
+ (pgt & _SEGMENT_ENTRY_PROTECT) | _SEGMENT_ENTRY_INVALID;
+ list_add(&page->lru, &sg->pt_list);
+ if (fake) {
+ /* nothing to protect for fake tables */
+ *table &= ~_SEGMENT_ENTRY_INVALID;
+ spin_unlock(&sg->guest_table_lock);
+ return 0;
+ }
+ spin_unlock(&sg->guest_table_lock);
+ /* Make pgt read-only in parent gmap page table (not the pgste) */
+ raddr = (saddr & 0xfffffffffff00000UL) | _SHADOW_RMAP_SEGMENT;
+ origin = pgt & _SEGMENT_ENTRY_ORIGIN & PAGE_MASK;
+ rc = gmap_protect_rmap(sg, raddr, origin, PAGE_SIZE, PROT_READ);
+ spin_lock(&sg->guest_table_lock);
+ if (!rc) {
+ table = gmap_table_walk(sg, saddr, 1);
+ if (!table || (*table & _SEGMENT_ENTRY_ORIGIN) !=
+ (unsigned long) s_pgt)
+ rc = -EAGAIN; /* Race with unshadow */
+ else
+ *table &= ~_SEGMENT_ENTRY_INVALID;
+ } else {
+ gmap_unshadow_pgt(sg, raddr);
+ }
+ spin_unlock(&sg->guest_table_lock);
+ return rc;
+ out_free:
+ spin_unlock(&sg->guest_table_lock);
+ page_table_free_pgste(page);
+ return rc;
+
+ }
+ EXPORT_SYMBOL_GPL(gmap_shadow_pgt);
+
+ /**
+ * gmap_shadow_page - create a shadow page mapping
+ * @sg: pointer to the shadow guest address space structure
+ * @saddr: faulting address in the shadow gmap
+ * @pte: pte in parent gmap address space to get shadowed
+ *
+ * Returns 0 if successfully shadowed or already shadowed, -EAGAIN if the
+ * shadow table structure is incomplete, -ENOMEM if out of memory and
+ * -EFAULT if an address in the parent gmap could not be resolved.
+ *
+ * Called with sg->mm->mmap_sem in read.
+ */
+ int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte)
+ {
+ struct gmap *parent;
+ struct gmap_rmap *rmap;
+ unsigned long vmaddr, paddr;
+ spinlock_t *ptl;
+ pte_t *sptep, *tptep;
+ int prot;
+ int rc;
+
+ BUG_ON(!gmap_is_shadow(sg));
+ parent = sg->parent;
+ prot = (pte_val(pte) & _PAGE_PROTECT) ? PROT_READ : PROT_WRITE;
+
+ rmap = kzalloc(sizeof(*rmap), GFP_KERNEL);
+ if (!rmap)
+ return -ENOMEM;
+ rmap->raddr = (saddr & PAGE_MASK) | _SHADOW_RMAP_PGTABLE;
+
+ while (1) {
+ paddr = pte_val(pte) & PAGE_MASK;
+ vmaddr = __gmap_translate(parent, paddr);
+ if (IS_ERR_VALUE(vmaddr)) {
+ rc = vmaddr;
+ break;
+ }
+ rc = radix_tree_preload(GFP_KERNEL);
+ if (rc)
+ break;
+ rc = -EAGAIN;
+ sptep = gmap_pte_op_walk(parent, paddr, &ptl);
+ if (sptep) {
+ spin_lock(&sg->guest_table_lock);
+ /* Get page table pointer */
+ tptep = (pte_t *) gmap_table_walk(sg, saddr, 0);
+ if (!tptep) {
+ spin_unlock(&sg->guest_table_lock);
+ gmap_pte_op_end(ptl);
+ radix_tree_preload_end();
+ break;
+ }
+ rc = ptep_shadow_pte(sg->mm, saddr, sptep, tptep, pte);
+ if (rc > 0) {
+ /* Success and a new mapping */
+ gmap_insert_rmap(sg, vmaddr, rmap);
+ rmap = NULL;
+ rc = 0;
+ }
+ gmap_pte_op_end(ptl);
+ spin_unlock(&sg->guest_table_lock);
+ }
+ radix_tree_preload_end();
+ if (!rc)
+ break;
+ rc = gmap_pte_op_fixup(parent, paddr, vmaddr, prot);
+ if (rc)
+ break;
+ }
+ kfree(rmap);
+ return rc;
+ }
+ EXPORT_SYMBOL_GPL(gmap_shadow_page);
+
+ /**
+ * gmap_shadow_notify - handle notifications for shadow gmap
+ *
+ * Called with sg->parent->shadow_lock.
+ */
+ static void gmap_shadow_notify(struct gmap *sg, unsigned long vmaddr,
+ unsigned long offset, pte_t *pte)
+ {
+ struct gmap_rmap *rmap, *rnext, *head;
+ unsigned long gaddr, start, end, bits, raddr;
+ unsigned long *table;
+
+ BUG_ON(!gmap_is_shadow(sg));
+ spin_lock(&sg->parent->guest_table_lock);
+ table = radix_tree_lookup(&sg->parent->host_to_guest,
+ vmaddr >> PMD_SHIFT);
+ gaddr = table ? __gmap_segment_gaddr(table) + offset : 0;
+ spin_unlock(&sg->parent->guest_table_lock);
+ if (!table)
+ return;
+
+ spin_lock(&sg->guest_table_lock);
+ if (sg->removed) {
+ spin_unlock(&sg->guest_table_lock);
+ return;
+ }
+ /* Check for top level table */
+ start = sg->orig_asce & _ASCE_ORIGIN;
+ end = start + ((sg->orig_asce & _ASCE_TABLE_LENGTH) + 1) * 4096;
+ if (!(sg->orig_asce & _ASCE_REAL_SPACE) && gaddr >= start &&
+ gaddr < end) {
+ /* The complete shadow table has to go */
+ gmap_unshadow(sg);
+ spin_unlock(&sg->guest_table_lock);
+ list_del(&sg->list);
+ gmap_put(sg);
+ return;
+ }
+ /* Remove the page table tree from on specific entry */
+ head = radix_tree_delete(&sg->host_to_rmap, vmaddr >> 12);
+ gmap_for_each_rmap_safe(rmap, rnext, head) {
+ bits = rmap->raddr & _SHADOW_RMAP_MASK;
+ raddr = rmap->raddr ^ bits;
+ switch (bits) {
+ case _SHADOW_RMAP_REGION1:
+ gmap_unshadow_r2t(sg, raddr);
+ break;
+ case _SHADOW_RMAP_REGION2:
+ gmap_unshadow_r3t(sg, raddr);
+ break;
+ case _SHADOW_RMAP_REGION3:
+ gmap_unshadow_sgt(sg, raddr);
+ break;
+ case _SHADOW_RMAP_SEGMENT:
+ gmap_unshadow_pgt(sg, raddr);
+ break;
+ case _SHADOW_RMAP_PGTABLE:
+ gmap_unshadow_page(sg, raddr);
+ break;
+ }
+ kfree(rmap);
+ }
+ spin_unlock(&sg->guest_table_lock);
+ }
+
+ /**
+ * ptep_notify - call all invalidation callbacks for a specific pte.
+ * @mm: pointer to the process mm_struct
+ * @addr: virtual address in the process address space
+ * @pte: pointer to the page table entry
+ * @bits: bits from the pgste that caused the notify call
+ *
+ * This function is assumed to be called with the page table lock held
+ * for the pte to notify.
+ */
+ void ptep_notify(struct mm_struct *mm, unsigned long vmaddr,
+ pte_t *pte, unsigned long bits)
+ {
+ unsigned long offset, gaddr;
+ unsigned long *table;
+ struct gmap *gmap, *sg, *next;
+
+ offset = ((unsigned long) pte) & (255 * sizeof(pte_t));
+ offset = offset * (4096 / sizeof(pte_t));
+ rcu_read_lock();
+ list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
+ if (!list_empty(&gmap->children) && (bits & PGSTE_VSIE_BIT)) {
+ spin_lock(&gmap->shadow_lock);
+ list_for_each_entry_safe(sg, next,
+ &gmap->children, list)
+ gmap_shadow_notify(sg, vmaddr, offset, pte);
+ spin_unlock(&gmap->shadow_lock);
+ }
+ if (!(bits & PGSTE_IN_BIT))
+ continue;
+ spin_lock(&gmap->guest_table_lock);
+ table = radix_tree_lookup(&gmap->host_to_guest,
+ vmaddr >> PMD_SHIFT);
+ if (table)
+ gaddr = __gmap_segment_gaddr(table) + offset;
+ spin_unlock(&gmap->guest_table_lock);
+ if (table)
+ gmap_call_notifier(gmap, gaddr, gaddr + PAGE_SIZE - 1);
+ }
+ rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(ptep_notify);
return new;
}
+ #ifdef CONFIG_PGSTE
+
+ struct page *page_table_alloc_pgste(struct mm_struct *mm)
+ {
+ struct page *page;
+ unsigned long *table;
+
+ page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
+ if (page) {
+ table = (unsigned long *) page_to_phys(page);
+ clear_table(table, _PAGE_INVALID, PAGE_SIZE/2);
+ clear_table(table + PTRS_PER_PTE, 0, PAGE_SIZE/2);
+ }
+ return page;
+ }
+
+ void page_table_free_pgste(struct page *page)
+ {
+ __free_page(page);
+ }
+
+ #endif /* CONFIG_PGSTE */
+
/*
* page table entry allocation/free routines.
*/
/* Try to get a fragment of a 4K page as a 2K page table */
if (!mm_alloc_pgste(mm)) {
table = NULL;
- spin_lock_bh(&mm->context.list_lock);
+ spin_lock_bh(&mm->context.pgtable_lock);
if (!list_empty(&mm->context.pgtable_list)) {
page = list_first_entry(&mm->context.pgtable_list,
struct page, lru);
list_del(&page->lru);
}
}
- spin_unlock_bh(&mm->context.list_lock);
+ spin_unlock_bh(&mm->context.pgtable_lock);
if (table)
return table;
}
/* Allocate a fresh page */
- page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
+ page = alloc_page(GFP_KERNEL);
if (!page)
return NULL;
if (!pgtable_page_ctor(page)) {
/* Return the first 2K fragment of the page */
atomic_set(&page->_mapcount, 1);
clear_table(table, _PAGE_INVALID, PAGE_SIZE);
- spin_lock_bh(&mm->context.list_lock);
+ spin_lock_bh(&mm->context.pgtable_lock);
list_add(&page->lru, &mm->context.pgtable_list);
- spin_unlock_bh(&mm->context.list_lock);
+ spin_unlock_bh(&mm->context.pgtable_lock);
}
return table;
}
if (!mm_alloc_pgste(mm)) {
/* Free 2K page table fragment of a 4K page */
bit = (__pa(table) & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t));
- spin_lock_bh(&mm->context.list_lock);
+ spin_lock_bh(&mm->context.pgtable_lock);
mask = atomic_xor_bits(&page->_mapcount, 1U << bit);
if (mask & 3)
list_add(&page->lru, &mm->context.pgtable_list);
else
list_del(&page->lru);
- spin_unlock_bh(&mm->context.list_lock);
+ spin_unlock_bh(&mm->context.pgtable_lock);
if (mask != 0)
return;
}
return;
}
bit = (__pa(table) & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t));
- spin_lock_bh(&mm->context.list_lock);
+ spin_lock_bh(&mm->context.pgtable_lock);
mask = atomic_xor_bits(&page->_mapcount, 0x11U << bit);
if (mask & 3)
list_add_tail(&page->lru, &mm->context.pgtable_list);
else
list_del(&page->lru);
- spin_unlock_bh(&mm->context.list_lock);
+ spin_unlock_bh(&mm->context.pgtable_lock);
table = (unsigned long *) (__pa(table) | (1U << bit));
tlb_remove_table(tlb, table);
}
static inline pte_t ptep_flush_direct(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
- int active, count;
pte_t old;
old = *ptep;
if (unlikely(pte_val(old) & _PAGE_INVALID))
return old;
- active = (mm == current->active_mm) ? 1 : 0;
- count = atomic_add_return(0x10000, &mm->context.attach_count);
- if (MACHINE_HAS_TLB_LC && (count & 0xffff) <= active &&
+ atomic_inc(&mm->context.flush_count);
+ if (MACHINE_HAS_TLB_LC &&
cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
__ptep_ipte_local(addr, ptep);
else
__ptep_ipte(addr, ptep);
- atomic_sub(0x10000, &mm->context.attach_count);
+ atomic_dec(&mm->context.flush_count);
return old;
}
static inline pte_t ptep_flush_lazy(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
- int active, count;
pte_t old;
old = *ptep;
if (unlikely(pte_val(old) & _PAGE_INVALID))
return old;
- active = (mm == current->active_mm) ? 1 : 0;
- count = atomic_add_return(0x10000, &mm->context.attach_count);
- if ((count & 0xffff) <= active) {
+ atomic_inc(&mm->context.flush_count);
+ if (cpumask_equal(&mm->context.cpu_attach_mask,
+ cpumask_of(smp_processor_id()))) {
pte_val(*ptep) |= _PAGE_INVALID;
mm->context.flush_mm = 1;
} else
__ptep_ipte(addr, ptep);
- atomic_sub(0x10000, &mm->context.attach_count);
+ atomic_dec(&mm->context.flush_count);
return old;
}
#ifdef CONFIG_PGSTE
unsigned long old;
- preempt_disable();
asm(
" lg %0,%2\n"
"0: lgr %1,%0\n"
: "=Q" (ptep[PTRS_PER_PTE])
: "d" (pgste_val(pgste)), "Q" (ptep[PTRS_PER_PTE])
: "cc", "memory");
- preempt_enable();
#endif
}
return pgste;
}
- static inline pgste_t pgste_ipte_notify(struct mm_struct *mm,
- unsigned long addr,
- pte_t *ptep, pgste_t pgste)
+ static inline pgste_t pgste_pte_notify(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep, pgste_t pgste)
{
#ifdef CONFIG_PGSTE
- if (pgste_val(pgste) & PGSTE_IN_BIT) {
- pgste_val(pgste) &= ~PGSTE_IN_BIT;
- ptep_notify(mm, addr, ptep);
+ unsigned long bits;
+
+ bits = pgste_val(pgste) & (PGSTE_IN_BIT | PGSTE_VSIE_BIT);
+ if (bits) {
+ pgste_val(pgste) ^= bits;
+ ptep_notify(mm, addr, ptep, bits);
}
#endif
return pgste;
if (mm_has_pgste(mm)) {
pgste = pgste_get_lock(ptep);
- pgste = pgste_ipte_notify(mm, addr, ptep, pgste);
+ pgste = pgste_pte_notify(mm, addr, ptep, pgste);
}
return pgste;
}
pgste_t pgste;
pte_t old;
+ preempt_disable();
pgste = ptep_xchg_start(mm, addr, ptep);
old = ptep_flush_direct(mm, addr, ptep);
ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
+ preempt_enable();
return old;
}
EXPORT_SYMBOL(ptep_xchg_direct);
pgste_t pgste;
pte_t old;
+ preempt_disable();
pgste = ptep_xchg_start(mm, addr, ptep);
old = ptep_flush_lazy(mm, addr, ptep);
ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
+ preempt_enable();
return old;
}
EXPORT_SYMBOL(ptep_xchg_lazy);
pgste_t pgste;
pte_t old;
+ preempt_disable();
pgste = ptep_xchg_start(mm, addr, ptep);
old = ptep_flush_lazy(mm, addr, ptep);
if (mm_has_pgste(mm)) {
} else {
*ptep = pte;
}
+ preempt_enable();
}
EXPORT_SYMBOL(ptep_modify_prot_commit);
static inline pmd_t pmdp_flush_direct(struct mm_struct *mm,
unsigned long addr, pmd_t *pmdp)
{
- int active, count;
pmd_t old;
old = *pmdp;
__pmdp_csp(pmdp);
return old;
}
- active = (mm == current->active_mm) ? 1 : 0;
- count = atomic_add_return(0x10000, &mm->context.attach_count);
- if (MACHINE_HAS_TLB_LC && (count & 0xffff) <= active &&
+ atomic_inc(&mm->context.flush_count);
+ if (MACHINE_HAS_TLB_LC &&
cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
__pmdp_idte_local(addr, pmdp);
else
__pmdp_idte(addr, pmdp);
- atomic_sub(0x10000, &mm->context.attach_count);
+ atomic_dec(&mm->context.flush_count);
return old;
}
static inline pmd_t pmdp_flush_lazy(struct mm_struct *mm,
unsigned long addr, pmd_t *pmdp)
{
- int active, count;
pmd_t old;
old = *pmdp;
if (pmd_val(old) & _SEGMENT_ENTRY_INVALID)
return old;
- active = (mm == current->active_mm) ? 1 : 0;
- count = atomic_add_return(0x10000, &mm->context.attach_count);
- if ((count & 0xffff) <= active) {
+ atomic_inc(&mm->context.flush_count);
+ if (cpumask_equal(&mm->context.cpu_attach_mask,
+ cpumask_of(smp_processor_id()))) {
pmd_val(*pmdp) |= _SEGMENT_ENTRY_INVALID;
mm->context.flush_mm = 1;
} else if (MACHINE_HAS_IDTE)
__pmdp_idte(addr, pmdp);
else
__pmdp_csp(pmdp);
- atomic_sub(0x10000, &mm->context.attach_count);
+ atomic_dec(&mm->context.flush_count);
return old;
}
{
pmd_t old;
+ preempt_disable();
old = pmdp_flush_direct(mm, addr, pmdp);
*pmdp = new;
+ preempt_enable();
return old;
}
EXPORT_SYMBOL(pmdp_xchg_direct);
{
pmd_t old;
+ preempt_disable();
old = pmdp_flush_lazy(mm, addr, pmdp);
*pmdp = new;
+ preempt_enable();
return old;
}
EXPORT_SYMBOL(pmdp_xchg_lazy);
+static inline pud_t pudp_flush_direct(struct mm_struct *mm,
+ unsigned long addr, pud_t *pudp)
+{
+ pud_t old;
+
+ old = *pudp;
+ if (pud_val(old) & _REGION_ENTRY_INVALID)
+ return old;
+ if (!MACHINE_HAS_IDTE) {
+ /*
+ * Invalid bit position is the same for pmd and pud, so we can
+ * re-use _pmd_csp() here
+ */
+ __pmdp_csp((pmd_t *) pudp);
+ return old;
+ }
+ atomic_inc(&mm->context.flush_count);
+ if (MACHINE_HAS_TLB_LC &&
+ cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
+ __pudp_idte_local(addr, pudp);
+ else
+ __pudp_idte(addr, pudp);
+ atomic_dec(&mm->context.flush_count);
+ return old;
+}
+
+pud_t pudp_xchg_direct(struct mm_struct *mm, unsigned long addr,
+ pud_t *pudp, pud_t new)
+{
+ pud_t old;
+
+ preempt_disable();
+ old = pudp_flush_direct(mm, addr, pudp);
+ *pudp = new;
+ preempt_enable();
+ return old;
+}
+EXPORT_SYMBOL(pudp_xchg_direct);
+
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
pgtable_t pgtable)
pgste_t pgste;
/* the mm_has_pgste() check is done in set_pte_at() */
+ preempt_disable();
pgste = pgste_get_lock(ptep);
pgste_val(pgste) &= ~_PGSTE_GPS_ZERO;
pgste_set_key(ptep, pgste, entry, mm);
pgste = pgste_set_pte(ptep, pgste, entry);
pgste_set_unlock(ptep, pgste);
+ preempt_enable();
}
void ptep_set_notify(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
{
pgste_t pgste;
+ preempt_disable();
pgste = pgste_get_lock(ptep);
pgste_val(pgste) |= PGSTE_IN_BIT;
pgste_set_unlock(ptep, pgste);
+ preempt_enable();
}
+ /**
+ * ptep_force_prot - change access rights of a locked pte
+ * @mm: pointer to the process mm_struct
+ * @addr: virtual address in the guest address space
+ * @ptep: pointer to the page table entry
+ * @prot: indicates guest access rights: PROT_NONE, PROT_READ or PROT_WRITE
+ * @bit: pgste bit to set (e.g. for notification)
+ *
+ * Returns 0 if the access rights were changed and -EAGAIN if the current
+ * and requested access rights are incompatible.
+ */
+ int ptep_force_prot(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, int prot, unsigned long bit)
+ {
+ pte_t entry;
+ pgste_t pgste;
+ int pte_i, pte_p;
+
+ pgste = pgste_get_lock(ptep);
+ entry = *ptep;
+ /* Check pte entry after all locks have been acquired */
+ pte_i = pte_val(entry) & _PAGE_INVALID;
+ pte_p = pte_val(entry) & _PAGE_PROTECT;
+ if ((pte_i && (prot != PROT_NONE)) ||
+ (pte_p && (prot & PROT_WRITE))) {
+ pgste_set_unlock(ptep, pgste);
+ return -EAGAIN;
+ }
+ /* Change access rights and set pgste bit */
+ if (prot == PROT_NONE && !pte_i) {
+ ptep_flush_direct(mm, addr, ptep);
+ pgste = pgste_update_all(entry, pgste, mm);
+ pte_val(entry) |= _PAGE_INVALID;
+ }
+ if (prot == PROT_READ && !pte_p) {
+ ptep_flush_direct(mm, addr, ptep);
+ pte_val(entry) &= ~_PAGE_INVALID;
+ pte_val(entry) |= _PAGE_PROTECT;
+ }
+ pgste_val(pgste) |= bit;
+ pgste = pgste_set_pte(ptep, pgste, entry);
+ pgste_set_unlock(ptep, pgste);
+ return 0;
+ }
+
+ int ptep_shadow_pte(struct mm_struct *mm, unsigned long saddr,
+ pte_t *sptep, pte_t *tptep, pte_t pte)
+ {
+ pgste_t spgste, tpgste;
+ pte_t spte, tpte;
+ int rc = -EAGAIN;
+
+ if (!(pte_val(*tptep) & _PAGE_INVALID))
+ return 0; /* already shadowed */
+ spgste = pgste_get_lock(sptep);
+ spte = *sptep;
+ if (!(pte_val(spte) & _PAGE_INVALID) &&
+ !((pte_val(spte) & _PAGE_PROTECT) &&
+ !(pte_val(pte) & _PAGE_PROTECT))) {
+ pgste_val(spgste) |= PGSTE_VSIE_BIT;
+ tpgste = pgste_get_lock(tptep);
+ pte_val(tpte) = (pte_val(spte) & PAGE_MASK) |
+ (pte_val(pte) & _PAGE_PROTECT);
+ /* don't touch the storage key - it belongs to parent pgste */
+ tpgste = pgste_set_pte(tptep, tpgste, tpte);
+ pgste_set_unlock(tptep, tpgste);
+ rc = 1;
+ }
+ pgste_set_unlock(sptep, spgste);
+ return rc;
+ }
+
+ void ptep_unshadow_pte(struct mm_struct *mm, unsigned long saddr, pte_t *ptep)
+ {
+ pgste_t pgste;
+
+ pgste = pgste_get_lock(ptep);
+ /* notifier is called by the caller */
+ ptep_flush_direct(mm, saddr, ptep);
+ /* don't touch the storage key - it belongs to parent pgste */
+ pgste = pgste_set_pte(ptep, pgste, __pte(_PAGE_INVALID));
+ pgste_set_unlock(ptep, pgste);
+ }
+
static void ptep_zap_swap_entry(struct mm_struct *mm, swp_entry_t entry)
{
if (!non_swap_entry(entry))
pte_t pte;
/* Zap unused and logically-zero pages */
+ preempt_disable();
pgste = pgste_get_lock(ptep);
pgstev = pgste_val(pgste);
pte = *ptep;
- if (pte_swap(pte) &&
+ if (!reset && pte_swap(pte) &&
((pgstev & _PGSTE_GPS_USAGE_MASK) == _PGSTE_GPS_USAGE_UNUSED ||
(pgstev & _PGSTE_GPS_ZERO))) {
ptep_zap_swap_entry(mm, pte_to_swp_entry(pte));
if (reset)
pgste_val(pgste) &= ~_PGSTE_GPS_USAGE_MASK;
pgste_set_unlock(ptep, pgste);
+ preempt_enable();
}
void ptep_zap_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
pgste_t pgste;
/* Clear storage key */
+ preempt_disable();
pgste = pgste_get_lock(ptep);
pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT |
PGSTE_GR_BIT | PGSTE_GC_BIT);
if (!(ptev & _PAGE_INVALID) && (ptev & _PAGE_WRITE))
page_set_storage_key(ptev & PAGE_MASK, PAGE_DEFAULT_KEY, 1);
pgste_set_unlock(ptep, pgste);
+ preempt_enable();
}
/*
pgste_val(pgste) &= ~PGSTE_UC_BIT;
pte = *ptep;
if (dirty && (pte_val(pte) & _PAGE_PRESENT)) {
- pgste = pgste_ipte_notify(mm, addr, ptep, pgste);
+ pgste = pgste_pte_notify(mm, addr, ptep, pgste);
__ptep_ipte(addr, ptep);
if (MACHINE_HAS_ESOP || !(pte_val(pte) & _PAGE_WRITE))
pte_val(pte) |= _PAGE_PROTECT;
pgste_t old, new;
pte_t *ptep;
- down_read(&mm->mmap_sem);
ptep = get_locked_pte(mm, addr, &ptl);
- if (unlikely(!ptep)) {
- up_read(&mm->mmap_sem);
+ if (unlikely(!ptep))
return -EFAULT;
- }
new = old = pgste_get_lock(ptep);
pgste_val(new) &= ~(PGSTE_GR_BIT | PGSTE_GC_BIT |
pgste_set_unlock(ptep, new);
pte_unmap_unlock(ptep, ptl);
- up_read(&mm->mmap_sem);
return 0;
}
EXPORT_SYMBOL(set_guest_storage_key);
- unsigned char get_guest_storage_key(struct mm_struct *mm, unsigned long addr)
+ /**
+ * Conditionally set a guest storage key (handling csske).
+ * oldkey will be updated when either mr or mc is set and a pointer is given.
+ *
+ * Returns 0 if a guests storage key update wasn't necessary, 1 if the guest
+ * storage key was updated and -EFAULT on access errors.
+ */
+ int cond_set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
+ unsigned char key, unsigned char *oldkey,
+ bool nq, bool mr, bool mc)
+ {
+ unsigned char tmp, mask = _PAGE_ACC_BITS | _PAGE_FP_BIT;
+ int rc;
+
+ /* we can drop the pgste lock between getting and setting the key */
+ if (mr | mc) {
+ rc = get_guest_storage_key(current->mm, addr, &tmp);
+ if (rc)
+ return rc;
+ if (oldkey)
+ *oldkey = tmp;
+ if (!mr)
+ mask |= _PAGE_REFERENCED;
+ if (!mc)
+ mask |= _PAGE_CHANGED;
+ if (!((tmp ^ key) & mask))
+ return 0;
+ }
+ rc = set_guest_storage_key(current->mm, addr, key, nq);
+ return rc < 0 ? rc : 1;
+ }
+ EXPORT_SYMBOL(cond_set_guest_storage_key);
+
+ /**
+ * Reset a guest reference bit (rrbe), returning the reference and changed bit.
+ *
+ * Returns < 0 in case of error, otherwise the cc to be reported to the guest.
+ */
+ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr)
{
- unsigned char key;
spinlock_t *ptl;
- pgste_t pgste;
+ pgste_t old, new;
pte_t *ptep;
+ int cc = 0;
- down_read(&mm->mmap_sem);
ptep = get_locked_pte(mm, addr, &ptl);
- if (unlikely(!ptep)) {
- up_read(&mm->mmap_sem);
+ if (unlikely(!ptep))
return -EFAULT;
- }
- pgste = pgste_get_lock(ptep);
- if (pte_val(*ptep) & _PAGE_INVALID) {
- key = (pgste_val(pgste) & PGSTE_ACC_BITS) >> 56;
- key |= (pgste_val(pgste) & PGSTE_FP_BIT) >> 56;
- key |= (pgste_val(pgste) & PGSTE_GR_BIT) >> 48;
- key |= (pgste_val(pgste) & PGSTE_GC_BIT) >> 48;
- } else {
- key = page_get_storage_key(pte_val(*ptep) & PAGE_MASK);
+ new = old = pgste_get_lock(ptep);
+ /* Reset guest reference bit only */
+ pgste_val(new) &= ~PGSTE_GR_BIT;
- /* Reflect guest's logical view, not physical */
- if (pgste_val(pgste) & PGSTE_GR_BIT)
- key |= _PAGE_REFERENCED;
- if (pgste_val(pgste) & PGSTE_GC_BIT)
- key |= _PAGE_CHANGED;
+ if (!(pte_val(*ptep) & _PAGE_INVALID)) {
+ cc = page_reset_referenced(pte_val(*ptep) & PAGE_MASK);
+ /* Merge real referenced bit into host-set */
+ pgste_val(new) |= ((unsigned long) cc << 53) & PGSTE_HR_BIT;
}
+ /* Reflect guest's logical view, not physical */
+ cc |= (pgste_val(old) & (PGSTE_GR_BIT | PGSTE_GC_BIT)) >> 49;
+ /* Changing the guest storage key is considered a change of the page */
+ if ((pgste_val(new) ^ pgste_val(old)) & PGSTE_GR_BIT)
+ pgste_val(new) |= PGSTE_UC_BIT;
+
+ pgste_set_unlock(ptep, new);
+ pte_unmap_unlock(ptep, ptl);
+ return 0;
+ }
+ EXPORT_SYMBOL(reset_guest_reference_bit);
+
+ int get_guest_storage_key(struct mm_struct *mm, unsigned long addr,
+ unsigned char *key)
+ {
+ spinlock_t *ptl;
+ pgste_t pgste;
+ pte_t *ptep;
+ ptep = get_locked_pte(mm, addr, &ptl);
+ if (unlikely(!ptep))
+ return -EFAULT;
+
+ pgste = pgste_get_lock(ptep);
+ *key = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56;
+ if (!(pte_val(*ptep) & _PAGE_INVALID))
+ *key = page_get_storage_key(pte_val(*ptep) & PAGE_MASK);
+ /* Reflect guest's logical view, not physical */
+ *key |= (pgste_val(pgste) & (PGSTE_GR_BIT | PGSTE_GC_BIT)) >> 48;
pgste_set_unlock(ptep, pgste);
pte_unmap_unlock(ptep, ptl);
- up_read(&mm->mmap_sem);
- return key;
+ return 0;
}
EXPORT_SYMBOL(get_guest_storage_key);
#endif
#include <linux/irqbypass.h>
#include <linux/hyperv.h>
+#include <asm/apic.h>
#include <asm/pvclock-abi.h>
#include <asm/desc.h>
#include <asm/mtrr.h>
#include <asm/asm.h>
#include <asm/kvm_page_track.h>
- #define KVM_MAX_VCPUS 255
- #define KVM_SOFT_MAX_VCPUS 160
+ #define KVM_MAX_VCPUS 288
+ #define KVM_SOFT_MAX_VCPUS 240
+ #define KVM_MAX_VCPU_ID 1023
#define KVM_USER_MEM_SLOTS 509
/* memory slots that are not exposed to userspace */
#define KVM_PRIVATE_MEM_SLOTS 3
u64 mcg_cap;
u64 mcg_status;
u64 mcg_ctl;
+ u64 mcg_ext_ctl;
u64 *mce_banks;
/* Cache MMIO info */
struct kvm_apic_map {
struct rcu_head rcu;
u8 mode;
- struct kvm_lapic *phys_map[256];
- /* first index is cluster id second is cpu id in a cluster */
- struct kvm_lapic *logical_map[16][16];
+ u32 max_apic_id;
+ union {
+ struct kvm_lapic *xapic_flat_map[8];
+ struct kvm_lapic *xapic_cluster_map[16][4];
+ };
+ struct kvm_lapic *phys_map[];
};
/* Hyper-V emulation context */
u32 ldr_mode;
struct page *avic_logical_id_table_page;
struct page *avic_physical_id_table_page;
+
+ bool x2apic_format;
+ bool x2apic_broadcast_quirk_disabled;
};
struct kvm_vm_stat {
int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq,
uint32_t guest_irq, bool set);
void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu);
+
+ int (*set_hv_timer)(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc);
+ void (*cancel_hv_timer)(struct kvm_vcpu *vcpu);
+
+ void (*setup_mce)(struct kvm_vcpu *vcpu);
};
struct kvm_arch_async_pf {
void kvm_mmu_init_vm(struct kvm *kvm);
void kvm_mmu_uninit_vm(struct kvm *kvm);
void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
- u64 dirty_mask, u64 nx_mask, u64 x_mask);
+ u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask);
void kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
extern u8 kvm_tsc_scaling_ratio_frac_bits;
/* maximum allowed value of TSC scaling ratio */
extern u64 kvm_max_tsc_scaling_ratio;
+ /* 1ull << kvm_tsc_scaling_ratio_frac_bits */
+ extern u64 kvm_default_tsc_scaling_ratio;
+
+ extern u64 kvm_mce_cap_supported;
enum emulation_result {
EMULATE_DONE, /* no further processing */
bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq,
struct kvm_vcpu **dest_vcpu);
- void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
+ void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
struct kvm_lapic_irq *irq);
static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
+static inline int kvm_cpu_get_apicid(int mps_cpu)
+{
+#ifdef CONFIG_X86_LOCAL_APIC
+ return __default_cpu_present_to_apicid(mps_cpu);
+#else
+ WARN_ON_ONCE(1);
+ return BAD_APICID;
+#endif
+}
+
#endif /* _ASM_X86_KVM_HOST_H */
#include <linux/list.h>
#include <linux/kvm_host.h>
-#include <linux/module.h>
+#include <linux/moduleparam.h>
#include <linux/pci.h>
#include <linux/stat.h>
- #include <linux/dmar.h>
#include <linux/iommu.h>
- #include <linux/intel-iommu.h>
#include "assigned-dev.h"
static bool allow_unsafe_assigned_interrupts;
#include <linux/smp.h>
#include <linux/hrtimer.h>
#include <linux/io.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/math64.h>
#include <linux/slab.h>
#include <asm/processor.h>
(LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \
APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER)
- /* The logical map is definitely wrong if we have multiple
- * modes at the same time. (Physical map is always right.)
- */
- static inline bool kvm_apic_logical_map_valid(struct kvm_apic_map *map)
- {
- return !(map->mode & (map->mode - 1));
+ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map,
+ u32 dest_id, struct kvm_lapic ***cluster, u16 *mask) {
+ switch (map->mode) {
+ case KVM_APIC_MODE_X2APIC: {
+ u32 offset = (dest_id >> 16) * 16;
+ u32 max_apic_id = map->max_apic_id;
+
+ if (offset <= max_apic_id) {
+ u8 cluster_size = min(max_apic_id - offset + 1, 16U);
+
+ *cluster = &map->phys_map[offset];
+ *mask = dest_id & (0xffff >> (16 - cluster_size));
+ } else {
+ *mask = 0;
+ }
+
+ return true;
+ }
+ case KVM_APIC_MODE_XAPIC_FLAT:
+ *cluster = map->xapic_flat_map;
+ *mask = dest_id & 0xff;
+ return true;
+ case KVM_APIC_MODE_XAPIC_CLUSTER:
+ *cluster = map->xapic_cluster_map[dest_id >> 4];
+ *mask = dest_id & 0xf;
+ return true;
+ default:
+ /* Not optimized. */
+ return false;
+ }
}
- static inline void
- apic_logical_id(struct kvm_apic_map *map, u32 dest_id, u16 *cid, u16 *lid)
+ static void kvm_apic_map_free(struct rcu_head *rcu)
{
- unsigned lid_bits;
+ struct kvm_apic_map *map = container_of(rcu, struct kvm_apic_map, rcu);
- BUILD_BUG_ON(KVM_APIC_MODE_XAPIC_CLUSTER != 4);
- BUILD_BUG_ON(KVM_APIC_MODE_XAPIC_FLAT != 8);
- BUILD_BUG_ON(KVM_APIC_MODE_X2APIC != 16);
- lid_bits = map->mode;
-
- *cid = dest_id >> lid_bits;
- *lid = dest_id & ((1 << lid_bits) - 1);
+ kvfree(map);
}
static void recalculate_apic_map(struct kvm *kvm)
struct kvm_apic_map *new, *old = NULL;
struct kvm_vcpu *vcpu;
int i;
-
- new = kzalloc(sizeof(struct kvm_apic_map), GFP_KERNEL);
+ u32 max_id = 255;
mutex_lock(&kvm->arch.apic_map_lock);
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ if (kvm_apic_present(vcpu))
+ max_id = max(max_id, kvm_apic_id(vcpu->arch.apic));
+
+ new = kvm_kvzalloc(sizeof(struct kvm_apic_map) +
+ sizeof(struct kvm_lapic *) * ((u64)max_id + 1));
+
if (!new)
goto out;
+ new->max_apic_id = max_id;
+
kvm_for_each_vcpu(i, vcpu, kvm) {
struct kvm_lapic *apic = vcpu->arch.apic;
- u16 cid, lid;
+ struct kvm_lapic **cluster;
+ u16 mask;
u32 ldr, aid;
if (!kvm_apic_present(vcpu))
aid = kvm_apic_id(apic);
ldr = kvm_lapic_get_reg(apic, APIC_LDR);
- if (aid < ARRAY_SIZE(new->phys_map))
+ if (aid <= new->max_apic_id)
new->phys_map[aid] = apic;
if (apic_x2apic_mode(apic)) {
new->mode |= KVM_APIC_MODE_XAPIC_CLUSTER;
}
- if (!kvm_apic_logical_map_valid(new))
+ if (!kvm_apic_map_get_logical_dest(new, ldr, &cluster, &mask))
continue;
- apic_logical_id(new, ldr, &cid, &lid);
-
- if (lid && cid < ARRAY_SIZE(new->logical_map))
- new->logical_map[cid][ffs(lid) - 1] = apic;
+ if (mask)
+ cluster[ffs(mask) - 1] = apic;
}
out:
old = rcu_dereference_protected(kvm->arch.apic_map,
mutex_unlock(&kvm->arch.apic_map_lock);
if (old)
- kfree_rcu(old, rcu);
+ call_rcu(&old->rcu, kvm_apic_map_free);
kvm_make_scan_ioapic_request(kvm);
}
}
}
- static inline void kvm_apic_set_id(struct kvm_lapic *apic, u8 id)
+ static inline void kvm_apic_set_xapic_id(struct kvm_lapic *apic, u8 id)
{
kvm_lapic_set_reg(apic, APIC_ID, id << 24);
recalculate_apic_map(apic->vcpu->kvm);
recalculate_apic_map(apic->vcpu->kvm);
}
- static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u8 id)
+ static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id)
{
u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf));
- kvm_lapic_set_reg(apic, APIC_ID, id << 24);
+ kvm_lapic_set_reg(apic, APIC_ID, id);
kvm_lapic_set_reg(apic, APIC_LDR, ldr);
recalculate_apic_map(apic->vcpu->kvm);
}
}
}
- /* KVM APIC implementation has two quirks
- * - dest always begins at 0 while xAPIC MDA has offset 24,
- * - IOxAPIC messages have to be delivered (directly) to x2APIC.
+ /* The KVM local APIC implementation has two quirks:
+ *
+ * - the xAPIC MDA stores the destination at bits 24-31, while this
+ * is not true of struct kvm_lapic_irq's dest_id field. This is
+ * just a quirk in the API and is not problematic.
+ *
+ * - in-kernel IOAPIC messages have to be delivered directly to
+ * x2APIC, because the kernel does not support interrupt remapping.
+ * In order to support broadcast without interrupt remapping, x2APIC
+ * rewrites the destination of non-IPI messages from APIC_BROADCAST
+ * to X2APIC_BROADCAST.
+ *
+ * The broadcast quirk can be disabled with KVM_CAP_X2APIC_API. This is
+ * important when userspace wants to use x2APIC-format MSIs, because
+ * APIC_BROADCAST (0xff) is a legal route for "cluster 0, CPUs 0-7".
*/
- static u32 kvm_apic_mda(unsigned int dest_id, struct kvm_lapic *source,
- struct kvm_lapic *target)
+ static u32 kvm_apic_mda(struct kvm_vcpu *vcpu, unsigned int dest_id,
+ struct kvm_lapic *source, struct kvm_lapic *target)
{
bool ipi = source != NULL;
bool x2apic_mda = apic_x2apic_mode(ipi ? source : target);
- if (!ipi && dest_id == APIC_BROADCAST && x2apic_mda)
+ if (!vcpu->kvm->arch.x2apic_broadcast_quirk_disabled &&
+ !ipi && dest_id == APIC_BROADCAST && x2apic_mda)
return X2APIC_BROADCAST;
return x2apic_mda ? dest_id : SET_APIC_DEST_FIELD(dest_id);
int short_hand, unsigned int dest, int dest_mode)
{
struct kvm_lapic *target = vcpu->arch.apic;
- u32 mda = kvm_apic_mda(dest, source, target);
+ u32 mda = kvm_apic_mda(vcpu, dest, source, target);
apic_debug("target %p, source %p, dest 0x%x, "
"dest_mode 0x%x, short_hand 0x%x\n",
}
}
- bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
- struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map)
+ static bool kvm_apic_is_broadcast_dest(struct kvm *kvm, struct kvm_lapic **src,
+ struct kvm_lapic_irq *irq, struct kvm_apic_map *map)
{
- struct kvm_apic_map *map;
- unsigned long bitmap = 1;
- struct kvm_lapic **dst;
- int i;
- bool ret, x2apic_ipi;
+ if (kvm->arch.x2apic_broadcast_quirk_disabled) {
+ if ((irq->dest_id == APIC_BROADCAST &&
+ map->mode != KVM_APIC_MODE_X2APIC))
+ return true;
+ if (irq->dest_id == X2APIC_BROADCAST)
+ return true;
+ } else {
+ bool x2apic_ipi = src && *src && apic_x2apic_mode(*src);
+ if (irq->dest_id == (x2apic_ipi ?
+ X2APIC_BROADCAST : APIC_BROADCAST))
+ return true;
+ }
- *r = -1;
+ return false;
+ }
- if (irq->shorthand == APIC_DEST_SELF) {
- *r = kvm_apic_set_irq(src->vcpu, irq, dest_map);
- return true;
- }
+ /* Return true if the interrupt can be handled by using *bitmap as index mask
+ * for valid destinations in *dst array.
+ * Return false if kvm_apic_map_get_dest_lapic did nothing useful.
+ * Note: we may have zero kvm_lapic destinations when we return true, which
+ * means that the interrupt should be dropped. In this case, *bitmap would be
+ * zero and *dst undefined.
+ */
+ static inline bool kvm_apic_map_get_dest_lapic(struct kvm *kvm,
+ struct kvm_lapic **src, struct kvm_lapic_irq *irq,
+ struct kvm_apic_map *map, struct kvm_lapic ***dst,
+ unsigned long *bitmap)
+ {
+ int i, lowest;
- if (irq->shorthand)
+ if (irq->shorthand == APIC_DEST_SELF && src) {
+ *dst = src;
+ *bitmap = 1;
+ return true;
+ } else if (irq->shorthand)
return false;
- x2apic_ipi = src && apic_x2apic_mode(src);
- if (irq->dest_id == (x2apic_ipi ? X2APIC_BROADCAST : APIC_BROADCAST))
+ if (!map || kvm_apic_is_broadcast_dest(kvm, src, irq, map))
return false;
- ret = true;
- rcu_read_lock();
- map = rcu_dereference(kvm->arch.apic_map);
-
- if (!map) {
- ret = false;
- goto out;
+ if (irq->dest_mode == APIC_DEST_PHYSICAL) {
+ if (irq->dest_id > map->max_apic_id) {
+ *bitmap = 0;
+ } else {
+ *dst = &map->phys_map[irq->dest_id];
+ *bitmap = 1;
+ }
+ return true;
}
- if (irq->dest_mode == APIC_DEST_PHYSICAL) {
- if (irq->dest_id >= ARRAY_SIZE(map->phys_map))
- goto out;
+ *bitmap = 0;
+ if (!kvm_apic_map_get_logical_dest(map, irq->dest_id, dst,
+ (u16 *)bitmap))
+ return false;
- dst = &map->phys_map[irq->dest_id];
- } else {
- u16 cid;
+ if (!kvm_lowest_prio_delivery(irq))
+ return true;
- if (!kvm_apic_logical_map_valid(map)) {
- ret = false;
- goto out;
+ if (!kvm_vector_hashing_enabled()) {
+ lowest = -1;
+ for_each_set_bit(i, bitmap, 16) {
+ if (!(*dst)[i])
+ continue;
+ if (lowest < 0)
+ lowest = i;
+ else if (kvm_apic_compare_prio((*dst)[i]->vcpu,
+ (*dst)[lowest]->vcpu) < 0)
+ lowest = i;
}
+ } else {
+ if (!*bitmap)
+ return true;
- apic_logical_id(map, irq->dest_id, &cid, (u16 *)&bitmap);
+ lowest = kvm_vector_to_index(irq->vector, hweight16(*bitmap),
+ bitmap, 16);
- if (cid >= ARRAY_SIZE(map->logical_map))
- goto out;
+ if (!(*dst)[lowest]) {
+ kvm_apic_disabled_lapic_found(kvm);
+ *bitmap = 0;
+ return true;
+ }
+ }
- dst = map->logical_map[cid];
+ *bitmap = (lowest >= 0) ? 1 << lowest : 0;
- if (!kvm_lowest_prio_delivery(irq))
- goto set_irq;
+ return true;
+ }
- if (!kvm_vector_hashing_enabled()) {
- int l = -1;
- for_each_set_bit(i, &bitmap, 16) {
- if (!dst[i])
- continue;
- if (l < 0)
- l = i;
- else if (kvm_apic_compare_prio(dst[i]->vcpu,
- dst[l]->vcpu) < 0)
- l = i;
- }
- bitmap = (l >= 0) ? 1 << l : 0;
- } else {
- int idx;
- unsigned int dest_vcpus;
+ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
+ struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map)
+ {
+ struct kvm_apic_map *map;
+ unsigned long bitmap;
+ struct kvm_lapic **dst = NULL;
+ int i;
+ bool ret;
- dest_vcpus = hweight16(bitmap);
- if (dest_vcpus == 0)
- goto out;
+ *r = -1;
- idx = kvm_vector_to_index(irq->vector,
- dest_vcpus, &bitmap, 16);
+ if (irq->shorthand == APIC_DEST_SELF) {
+ *r = kvm_apic_set_irq(src->vcpu, irq, dest_map);
+ return true;
+ }
- if (!dst[idx]) {
- kvm_apic_disabled_lapic_found(kvm);
- goto out;
- }
+ rcu_read_lock();
+ map = rcu_dereference(kvm->arch.apic_map);
- bitmap = (idx >= 0) ? 1 << idx : 0;
+ ret = kvm_apic_map_get_dest_lapic(kvm, &src, irq, map, &dst, &bitmap);
+ if (ret)
+ for_each_set_bit(i, &bitmap, 16) {
+ if (!dst[i])
+ continue;
+ if (*r < 0)
+ *r = 0;
+ *r += kvm_apic_set_irq(dst[i]->vcpu, irq, dest_map);
}
- }
- set_irq:
- for_each_set_bit(i, &bitmap, 16) {
- if (!dst[i])
- continue;
- if (*r < 0)
- *r = 0;
- *r += kvm_apic_set_irq(dst[i]->vcpu, irq, dest_map);
- }
- out:
rcu_read_unlock();
return ret;
}
struct kvm_vcpu **dest_vcpu)
{
struct kvm_apic_map *map;
+ unsigned long bitmap;
+ struct kvm_lapic **dst = NULL;
bool ret = false;
- struct kvm_lapic *dst = NULL;
if (irq->shorthand)
return false;
rcu_read_lock();
map = rcu_dereference(kvm->arch.apic_map);
- if (!map)
- goto out;
-
- if (irq->dest_mode == APIC_DEST_PHYSICAL) {
- if (irq->dest_id == 0xFF)
- goto out;
-
- if (irq->dest_id >= ARRAY_SIZE(map->phys_map))
- goto out;
-
- dst = map->phys_map[irq->dest_id];
- if (dst && kvm_apic_present(dst->vcpu))
- *dest_vcpu = dst->vcpu;
- else
- goto out;
- } else {
- u16 cid;
- unsigned long bitmap = 1;
- int i, r = 0;
-
- if (!kvm_apic_logical_map_valid(map))
- goto out;
-
- apic_logical_id(map, irq->dest_id, &cid, (u16 *)&bitmap);
-
- if (cid >= ARRAY_SIZE(map->logical_map))
- goto out;
-
- if (kvm_vector_hashing_enabled() &&
- kvm_lowest_prio_delivery(irq)) {
- int idx;
- unsigned int dest_vcpus;
+ if (kvm_apic_map_get_dest_lapic(kvm, NULL, irq, map, &dst, &bitmap) &&
+ hweight16(bitmap) == 1) {
+ unsigned long i = find_first_bit(&bitmap, 16);
- dest_vcpus = hweight16(bitmap);
- if (dest_vcpus == 0)
- goto out;
-
- idx = kvm_vector_to_index(irq->vector, dest_vcpus,
- &bitmap, 16);
-
- dst = map->logical_map[cid][idx];
- if (!dst) {
- kvm_apic_disabled_lapic_found(kvm);
- goto out;
- }
-
- *dest_vcpu = dst->vcpu;
- } else {
- for_each_set_bit(i, &bitmap, 16) {
- dst = map->logical_map[cid][i];
- if (++r == 2)
- goto out;
- }
-
- if (dst && kvm_apic_present(dst->vcpu))
- *dest_vcpu = dst->vcpu;
- else
- goto out;
+ if (dst[i]) {
+ *dest_vcpu = dst[i]->vcpu;
+ ret = true;
}
}
- ret = true;
- out:
rcu_read_unlock();
return ret;
}
return 0;
switch (offset) {
- case APIC_ID:
- if (apic_x2apic_mode(apic))
- val = kvm_apic_id(apic);
- else
- val = kvm_apic_id(apic) << 24;
- break;
case APIC_ARBPRI:
apic_debug("Access APIC ARBPRI register which is for P6\n");
break;
/* __delay is delay_tsc whenever the hardware has TSC, thus always. */
if (guest_tsc < tsc_deadline)
- __delay(tsc_deadline - guest_tsc);
+ __delay(min(tsc_deadline - guest_tsc,
+ nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
}
+ static void start_sw_tscdeadline(struct kvm_lapic *apic)
+ {
+ u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline;
+ u64 ns = 0;
+ ktime_t expire;
+ struct kvm_vcpu *vcpu = apic->vcpu;
+ unsigned long this_tsc_khz = vcpu->arch.virtual_tsc_khz;
+ unsigned long flags;
+ ktime_t now;
+
+ if (unlikely(!tscdeadline || !this_tsc_khz))
+ return;
+
+ local_irq_save(flags);
+
+ now = apic->lapic_timer.timer.base->get_time();
+ guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
+ if (likely(tscdeadline > guest_tsc)) {
+ ns = (tscdeadline - guest_tsc) * 1000000ULL;
+ do_div(ns, this_tsc_khz);
+ expire = ktime_add_ns(now, ns);
+ expire = ktime_sub_ns(expire, lapic_timer_advance_ns);
+ hrtimer_start(&apic->lapic_timer.timer,
+ expire, HRTIMER_MODE_ABS_PINNED);
+ } else
+ apic_timer_expired(apic);
+
+ local_irq_restore(flags);
+ }
+
+ bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu)
+ {
+ return vcpu->arch.apic->lapic_timer.hv_timer_in_use;
+ }
+ EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use);
+
+ static void cancel_hv_tscdeadline(struct kvm_lapic *apic)
+ {
+ kvm_x86_ops->cancel_hv_timer(apic->vcpu);
+ apic->lapic_timer.hv_timer_in_use = false;
+ }
+
+ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu)
+ {
+ struct kvm_lapic *apic = vcpu->arch.apic;
+
+ WARN_ON(!apic->lapic_timer.hv_timer_in_use);
+ WARN_ON(swait_active(&vcpu->wq));
+ cancel_hv_tscdeadline(apic);
+ apic_timer_expired(apic);
+ }
+ EXPORT_SYMBOL_GPL(kvm_lapic_expired_hv_timer);
+
+ static bool start_hv_tscdeadline(struct kvm_lapic *apic)
+ {
+ u64 tscdeadline = apic->lapic_timer.tscdeadline;
+
+ if (atomic_read(&apic->lapic_timer.pending) ||
+ kvm_x86_ops->set_hv_timer(apic->vcpu, tscdeadline)) {
+ if (apic->lapic_timer.hv_timer_in_use)
+ cancel_hv_tscdeadline(apic);
+ } else {
+ apic->lapic_timer.hv_timer_in_use = true;
+ hrtimer_cancel(&apic->lapic_timer.timer);
+
+ /* In case the sw timer triggered in the window */
+ if (atomic_read(&apic->lapic_timer.pending))
+ cancel_hv_tscdeadline(apic);
+ }
+ trace_kvm_hv_timer_state(apic->vcpu->vcpu_id,
+ apic->lapic_timer.hv_timer_in_use);
+ return apic->lapic_timer.hv_timer_in_use;
+ }
+
+ void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu)
+ {
+ struct kvm_lapic *apic = vcpu->arch.apic;
+
+ WARN_ON(apic->lapic_timer.hv_timer_in_use);
+
+ if (apic_lvtt_tscdeadline(apic))
+ start_hv_tscdeadline(apic);
+ }
+ EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_hv_timer);
+
+ void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu)
+ {
+ struct kvm_lapic *apic = vcpu->arch.apic;
+
+ /* Possibly the TSC deadline timer is not enabled yet */
+ if (!apic->lapic_timer.hv_timer_in_use)
+ return;
+
+ cancel_hv_tscdeadline(apic);
+
+ if (atomic_read(&apic->lapic_timer.pending))
+ return;
+
+ start_sw_tscdeadline(apic);
+ }
+ EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer);
+
static void start_apic_timer(struct kvm_lapic *apic)
{
ktime_t now;
ktime_to_ns(ktime_add_ns(now,
apic->lapic_timer.period)));
} else if (apic_lvtt_tscdeadline(apic)) {
- /* lapic timer in tsc deadline mode */
- u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline;
- u64 ns = 0;
- ktime_t expire;
- struct kvm_vcpu *vcpu = apic->vcpu;
- unsigned long this_tsc_khz = vcpu->arch.virtual_tsc_khz;
- unsigned long flags;
-
- if (unlikely(!tscdeadline || !this_tsc_khz))
- return;
-
- local_irq_save(flags);
-
- now = apic->lapic_timer.timer.base->get_time();
- guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
- if (likely(tscdeadline > guest_tsc)) {
- ns = (tscdeadline - guest_tsc) * 1000000ULL;
- do_div(ns, this_tsc_khz);
- expire = ktime_add_ns(now, ns);
- expire = ktime_sub_ns(expire, lapic_timer_advance_ns);
- hrtimer_start(&apic->lapic_timer.timer,
- expire, HRTIMER_MODE_ABS_PINNED);
- } else
- apic_timer_expired(apic);
-
- local_irq_restore(flags);
+ if (!(kvm_x86_ops->set_hv_timer && start_hv_tscdeadline(apic)))
+ start_sw_tscdeadline(apic);
}
}
switch (reg) {
case APIC_ID: /* Local APIC ID */
if (!apic_x2apic_mode(apic))
- kvm_apic_set_id(apic, val >> 24);
+ kvm_apic_set_xapic_id(apic, val >> 24);
else
ret = 1;
break;
/* update jump label if enable bit changes */
if ((old_value ^ value) & MSR_IA32_APICBASE_ENABLE) {
- if (value & MSR_IA32_APICBASE_ENABLE)
+ if (value & MSR_IA32_APICBASE_ENABLE) {
+ kvm_apic_set_xapic_id(apic, vcpu->vcpu_id);
static_key_slow_dec_deferred(&apic_hw_disabled);
- else
+ } else
static_key_slow_inc(&apic_hw_disabled.key);
recalculate_apic_map(vcpu->kvm);
}
/* Stop the timer in case it's a reset to an active apic */
hrtimer_cancel(&apic->lapic_timer.timer);
- if (!init_event)
- kvm_apic_set_id(apic, vcpu->vcpu_id);
+ if (!init_event) {
+ kvm_lapic_set_base(vcpu, APIC_DEFAULT_PHYS_BASE |
+ MSR_IA32_APICBASE_ENABLE);
+ kvm_apic_set_xapic_id(apic, vcpu->vcpu_id);
+ }
kvm_apic_set_version(apic->vcpu);
for (i = 0; i < KVM_APIC_LVT_NUM; i++)
* thinking that APIC satet has changed.
*/
vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE;
- kvm_lapic_set_base(vcpu,
- APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE);
-
static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */
kvm_lapic_reset(vcpu, false);
kvm_iodevice_init(&apic->dev, &apic_mmio_ops);
return vector;
}
- void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
- struct kvm_lapic_state *s)
+ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
+ struct kvm_lapic_state *s, bool set)
+ {
+ if (apic_x2apic_mode(vcpu->arch.apic)) {
+ u32 *id = (u32 *)(s->regs + APIC_ID);
+
+ if (vcpu->kvm->arch.x2apic_format) {
+ if (*id != vcpu->vcpu_id)
+ return -EINVAL;
+ } else {
+ if (set)
+ *id >>= 24;
+ else
+ *id <<= 24;
+ }
+ }
+
+ return 0;
+ }
+
+ int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
+ {
+ memcpy(s->regs, vcpu->arch.apic->regs, sizeof(*s));
+ return kvm_apic_state_fixup(vcpu, s, false);
+ }
+
+ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
{
struct kvm_lapic *apic = vcpu->arch.apic;
+ int r;
+
kvm_lapic_set_base(vcpu, vcpu->arch.apic_base);
/* set SPIV separately to get count of SW disabled APICs right */
apic_set_spiv(apic, *((u32 *)(s->regs + APIC_SPIV)));
+
+ r = kvm_apic_state_fixup(vcpu, s, true);
+ if (r)
+ return r;
memcpy(vcpu->arch.apic->regs, s->regs, sizeof *s);
- /* call kvm_apic_set_id() to put apic into apic_map */
- kvm_apic_set_id(apic, kvm_apic_id(apic));
+
+ recalculate_apic_map(vcpu->kvm);
kvm_apic_set_version(vcpu);
apic_update_ppr(apic);
kvm_rtc_eoi_tracking_restore_one(vcpu);
vcpu->arch.apic_arb_prio = 0;
+
+ return 0;
}
void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu)
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/highmem.h>
-#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/export.h>
#include <linux/swap.h>
#include <linux/hugetlb.h>
#include <linux/compiler.h>
static u64 __read_mostly shadow_accessed_mask;
static u64 __read_mostly shadow_dirty_mask;
static u64 __read_mostly shadow_mmio_mask;
+ static u64 __read_mostly shadow_present_mask;
static void mmu_spte_set(u64 *sptep, u64 spte);
static void mmu_free_roots(struct kvm_vcpu *vcpu);
}
void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
- u64 dirty_mask, u64 nx_mask, u64 x_mask)
+ u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask)
{
shadow_user_mask = user_mask;
shadow_accessed_mask = accessed_mask;
shadow_dirty_mask = dirty_mask;
shadow_nx_mask = nx_mask;
shadow_x_mask = x_mask;
+ shadow_present_mask = p_mask;
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
static int is_shadow_present_pte(u64 pte)
{
- return pte & PT_PRESENT_MASK && !is_mmio_spte(pte);
+ return (pte & 0xFFFFFFFFull) && !is_mmio_spte(pte);
}
static int is_large_pte(u64 pte)
}
/* Rules for using mmu_spte_update:
- * Update the state bits, it means the mapped pfn is not changged.
+ * Update the state bits, it means the mapped pfn is not changed.
*
* Whenever we overwrite a writable spte with a read-only one we
* should flush remote TLBs. Otherwise rmap_write_protect
{
u64 spte;
- BUILD_BUG_ON(VMX_EPT_READABLE_MASK != PT_PRESENT_MASK ||
- VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);
+ BUILD_BUG_ON(VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);
- spte = __pa(sp->spt) | PT_PRESENT_MASK | PT_WRITABLE_MASK |
+ spte = __pa(sp->spt) | shadow_present_mask | PT_WRITABLE_MASK |
shadow_user_mask | shadow_x_mask | shadow_accessed_mask;
mmu_spte_set(sptep, spte);
gfn_t gfn, kvm_pfn_t pfn, bool speculative,
bool can_unsync, bool host_writable)
{
- u64 spte;
+ u64 spte = 0;
int ret = 0;
if (set_mmio_spte(vcpu, sptep, gfn, pfn, pte_access))
return 0;
- spte = PT_PRESENT_MASK;
+ /*
+ * For the EPT case, shadow_present_mask is 0 if hardware
+ * supports exec-only page table entries. In that case,
+ * ACC_USER_MASK and shadow_user_mask are used to represent
+ * read access. See FNAME(gpte_access) in paging_tmpl.h.
+ */
+ spte |= shadow_present_mask;
if (!speculative)
spte |= shadow_accessed_mask;
MMU_WARN_ON(VALID_PAGE(root));
if (vcpu->arch.mmu.root_level == PT32E_ROOT_LEVEL) {
pdptr = vcpu->arch.mmu.get_pdptr(vcpu, i);
- if (!is_present_gpte(pdptr)) {
+ if (!(pdptr & PT_PRESENT_MASK)) {
vcpu->arch.mmu.pae_root[i] = 0;
continue;
}
* clearer.
*/
smap = cr4_smap && u && !uf && !ff;
- } else
- /* Not really needed: no U/S accesses on ept */
- u = 1;
+ }
fault = (ff && !x) || (uf && !u) || (wf && !w) ||
(smapf && smap);
/* enable / disable AVIC */
static int avic;
+#ifdef CONFIG_X86_LOCAL_APIC
module_param(avic, int, S_IRUGO);
+#endif
static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
static void svm_flush_tlb(struct kvm_vcpu *vcpu);
} else
kvm_disable_tdp();
- if (avic && (!npt_enabled || !boot_cpu_has(X86_FEATURE_AVIC)))
- avic = false;
-
- if (avic)
- pr_info("AVIC enabled\n");
+ if (avic) {
+ if (!npt_enabled ||
+ !boot_cpu_has(X86_FEATURE_AVIC) ||
+ !IS_ENABLED(CONFIG_X86_LOCAL_APIC))
+ avic = false;
+ else
+ pr_info("AVIC enabled\n");
+ }
return 0;
static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
{
u64 entry;
- int h_physical_id = __default_cpu_present_to_apicid(vcpu->cpu);
+ int h_physical_id = kvm_cpu_get_apicid(vcpu->cpu);
struct vcpu_svm *svm = to_svm(vcpu);
if (!kvm_vcpu_apicv_active(vcpu))
{
u64 entry;
/* ID = 0xff (broadcast), ID > 0xff (reserved) */
- int h_physical_id = __default_cpu_present_to_apicid(cpu);
+ int h_physical_id = kvm_cpu_get_apicid(cpu);
struct vcpu_svm *svm = to_svm(vcpu);
if (!kvm_vcpu_apicv_active(vcpu))
static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
{
/*
- * Any change of EFLAGS.VM is accompained by a reload of SS
+ * Any change of EFLAGS.VM is accompanied by a reload of SS
* (caused by either a task switch or an inter-privilege IRET),
* so we do not need to update the CPL here.
*/
if (avic_vcpu_is_running(vcpu))
wrmsrl(SVM_AVIC_DOORBELL,
- __default_cpu_present_to_apicid(vcpu->cpu));
+ kvm_cpu_get_apicid(vcpu->cpu));
else
kvm_vcpu_wake_up(vcpu);
}
static void svm_handle_external_intr(struct kvm_vcpu *vcpu)
{
local_irq_enable();
+ /*
+ * We must have an instruction with interrupts enabled, so
+ * the timer interrupt isn't delayed by the interrupt shadow.
+ */
+ asm("nop");
+ local_irq_disable();
}
static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu)
#define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL
+ /* Guest_tsc -> host_tsc conversion requires 64-bit division. */
+ static int __read_mostly cpu_preemption_timer_multi;
+ static bool __read_mostly enable_preemption_timer = 1;
+ #ifdef CONFIG_X86_64
+ module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO);
+ #endif
+
#define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD)
#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST (X86_CR0_WP | X86_CR0_NE)
#define KVM_VM_CR0_ALWAYS_ON \
/* The host-usable pointer to the above */
struct page *current_vmcs12_page;
struct vmcs12 *current_vmcs12;
+ /*
+ * Cache of the guest's VMCS, existing outside of guest memory.
+ * Loaded from guest memory during VMPTRLD. Flushed to guest
+ * memory during VMXOFF, VMCLEAR, VMPTRLD.
+ */
+ struct vmcs12 *cached_vmcs12;
struct vmcs *current_shadow_vmcs;
/*
* Indicates if the shadow vmcs must be updated with the
struct pi_desc *pi_desc;
bool pi_pending;
u16 posted_intr_nv;
- u64 msr_ia32_feature_control;
struct hrtimer preemption_timer;
bool preemption_timer_expired;
#define PML_ENTITY_NUM 512
struct page *pml_pg;
+ /* apic deadline value in host tsc */
+ u64 hv_deadline_tsc;
+
u64 current_tsc_ratio;
bool guest_pkru_valid;
u32 guest_pkru;
u32 host_pkru;
+
+ /*
+ * Only bits masked by msr_ia32_feature_control_valid_bits can be set in
+ * msr_ia32_feature_control. FEATURE_CONTROL_LOCKED is always included
+ * in msr_ia32_feature_control_valid_bits.
+ */
+ u64 msr_ia32_feature_control;
+ u64 msr_ia32_feature_control_valid_bits;
};
enum segment_cache_field {
static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
{
- return to_vmx(vcpu)->nested.current_vmcs12;
+ return to_vmx(vcpu)->nested.cached_vmcs12;
}
static struct page *nested_get_page(struct kvm_vcpu *vcpu, gpa_t addr)
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY;
}
+ /*
+ * Comment's format: document - errata name - stepping - processor name.
+ * Refer from
+ * https://www.virtualbox.org/svn/vbox/trunk/src/VBox/VMM/VMMR0/HMR0.cpp
+ */
+ static u32 vmx_preemption_cpu_tfms[] = {
+ /* 323344.pdf - BA86 - D0 - Xeon 7500 Series */
+ 0x000206E6,
+ /* 323056.pdf - AAX65 - C2 - Xeon L3406 */
+ /* 322814.pdf - AAT59 - C2 - i7-600, i5-500, i5-400 and i3-300 Mobile */
+ /* 322911.pdf - AAU65 - C2 - i5-600, i3-500 Desktop and Pentium G6950 */
+ 0x00020652,
+ /* 322911.pdf - AAU65 - K0 - i5-600, i3-500 Desktop and Pentium G6950 */
+ 0x00020655,
+ /* 322373.pdf - AAO95 - B1 - Xeon 3400 Series */
+ /* 322166.pdf - AAN92 - B1 - i7-800 and i5-700 Desktop */
+ /*
+ * 320767.pdf - AAP86 - B1 -
+ * i7-900 Mobile Extreme, i7-800 and i7-700 Mobile
+ */
+ 0x000106E5,
+ /* 321333.pdf - AAM126 - C0 - Xeon 3500 */
+ 0x000106A0,
+ /* 321333.pdf - AAM126 - C1 - Xeon 3500 */
+ 0x000106A1,
+ /* 320836.pdf - AAJ124 - C0 - i7-900 Desktop Extreme and i7-900 Desktop */
+ 0x000106A4,
+ /* 321333.pdf - AAM126 - D0 - Xeon 3500 */
+ /* 321324.pdf - AAK139 - D0 - Xeon 5500 */
+ /* 320836.pdf - AAJ124 - D0 - i7-900 Extreme and i7-900 Desktop */
+ 0x000106A5,
+ };
+
+ static inline bool cpu_has_broken_vmx_preemption_timer(void)
+ {
+ u32 eax = cpuid_eax(0x00000001), i;
+
+ /* Clear the reserved bits */
+ eax &= ~(0x3U << 14 | 0xfU << 28);
+ for (i = 0; i < ARRAY_SIZE(vmx_preemption_cpu_tfms); i++)
+ if (eax == vmx_preemption_cpu_tfms[i])
+ return true;
+
+ return false;
+ }
+
+ static inline bool cpu_has_vmx_preemption_timer(void)
+ {
+ return vmcs_config.pin_based_exec_ctrl &
+ PIN_BASED_VMX_PREEMPTION_TIMER;
+ }
+
static inline bool cpu_has_vmx_posted_intr(void)
{
return IS_ENABLED(CONFIG_X86_LOCAL_APIC) &&
__vmcs_writel(field, __vmcs_readl(field) | mask);
}
+ static inline void vm_entry_controls_reset_shadow(struct vcpu_vmx *vmx)
+ {
+ vmx->vm_entry_controls_shadow = vmcs_read32(VM_ENTRY_CONTROLS);
+ }
+
static inline void vm_entry_controls_init(struct vcpu_vmx *vmx, u32 val)
{
vmcs_write32(VM_ENTRY_CONTROLS, val);
vm_entry_controls_set(vmx, vm_entry_controls_get(vmx) & ~val);
}
+ static inline void vm_exit_controls_reset_shadow(struct vcpu_vmx *vmx)
+ {
+ vmx->vm_exit_controls_shadow = vmcs_read32(VM_EXIT_CONTROLS);
+ }
+
static inline void vm_exit_controls_init(struct vcpu_vmx *vmx, u32 val)
{
vmcs_write32(VM_EXIT_CONTROLS, val);
unsigned int dest;
if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP))
+ !irq_remapping_cap(IRQ_POSTING_CAP) ||
+ !kvm_vcpu_apicv_active(vcpu))
return;
do {
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
+ bool already_loaded = vmx->loaded_vmcs->cpu == cpu;
if (!vmm_exclusive)
kvm_cpu_vmxon(phys_addr);
- else if (vmx->loaded_vmcs->cpu != cpu)
+ else if (!already_loaded)
loaded_vmcs_clear(vmx->loaded_vmcs);
- if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) {
- per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs;
- vmcs_load(vmx->loaded_vmcs->vmcs);
- }
-
- if (vmx->loaded_vmcs->cpu != cpu) {
- struct desc_ptr *gdt = this_cpu_ptr(&host_gdt);
- unsigned long sysenter_esp;
-
- kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+ if (!already_loaded) {
local_irq_disable();
crash_disable_local_vmclear(cpu);
&per_cpu(loaded_vmcss_on_cpu, cpu));
crash_enable_local_vmclear(cpu);
local_irq_enable();
+ }
+
+ if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) {
+ per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs;
+ vmcs_load(vmx->loaded_vmcs->vmcs);
+ }
+
+ if (!already_loaded) {
+ struct desc_ptr *gdt = this_cpu_ptr(&host_gdt);
+ unsigned long sysenter_esp;
+
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
/*
* Linux uses per-cpu TSS and GDT, so set these when switching
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP))
+ !irq_remapping_cap(IRQ_POSTING_CAP) ||
+ !kvm_vcpu_apicv_active(vcpu))
return;
/* Set SN when the vCPU is preempted */
SECONDARY_EXEC_APIC_REGISTER_VIRT |
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
SECONDARY_EXEC_WBINVD_EXITING |
- SECONDARY_EXEC_XSAVES |
- SECONDARY_EXEC_PCOMMIT;
+ SECONDARY_EXEC_XSAVES;
if (enable_ept) {
/* nested EPT: emulate EPT also to L1 */
vmx->nested.nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT |
VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT |
VMX_EPT_INVEPT_BIT;
+ if (cpu_has_vmx_ept_execute_only())
+ vmx->nested.nested_vmx_ept_caps |=
+ VMX_EPT_EXECUTE_ONLY_BIT;
vmx->nested.nested_vmx_ept_caps &= vmx_capability.ept;
/*
* For nested guests, we don't do anything specific
return 0;
}
+ static inline bool vmx_feature_control_msr_valid(struct kvm_vcpu *vcpu,
+ uint64_t val)
+ {
+ uint64_t valid_bits = to_vmx(vcpu)->msr_ia32_feature_control_valid_bits;
+
+ return !(val & ~valid_bits);
+ }
+
/*
* Reads an msr value (of 'msr_index') into 'pdata'.
* Returns 0 on success, non-0 otherwise.
return 1;
msr_info->data = vmcs_read64(GUEST_BNDCFGS);
break;
- case MSR_IA32_FEATURE_CONTROL:
- if (!nested_vmx_allowed(vcpu))
+ case MSR_IA32_MCG_EXT_CTL:
+ if (!msr_info->host_initiated &&
+ !(to_vmx(vcpu)->msr_ia32_feature_control &
+ FEATURE_CONTROL_LMCE))
return 1;
- msr_info->data = to_vmx(vcpu)->nested.msr_ia32_feature_control;
+ msr_info->data = vcpu->arch.mcg_ext_ctl;
+ break;
+ case MSR_IA32_FEATURE_CONTROL:
+ msr_info->data = to_vmx(vcpu)->msr_ia32_feature_control;
break;
case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
if (!nested_vmx_allowed(vcpu))
case MSR_IA32_TSC_ADJUST:
ret = kvm_set_msr_common(vcpu, msr_info);
break;
+ case MSR_IA32_MCG_EXT_CTL:
+ if ((!msr_info->host_initiated &&
+ !(to_vmx(vcpu)->msr_ia32_feature_control &
+ FEATURE_CONTROL_LMCE)) ||
+ (data & ~MCG_EXT_CTL_LMCE_EN))
+ return 1;
+ vcpu->arch.mcg_ext_ctl = data;
+ break;
case MSR_IA32_FEATURE_CONTROL:
- if (!nested_vmx_allowed(vcpu) ||
- (to_vmx(vcpu)->nested.msr_ia32_feature_control &
+ if (!vmx_feature_control_msr_valid(vcpu, data) ||
+ (to_vmx(vcpu)->msr_ia32_feature_control &
FEATURE_CONTROL_LOCKED && !msr_info->host_initiated))
return 1;
- vmx->nested.msr_ia32_feature_control = data;
+ vmx->msr_ia32_feature_control = data;
if (msr_info->host_initiated && data == 0)
vmx_leave_nested(vcpu);
break;
SECONDARY_EXEC_SHADOW_VMCS |
SECONDARY_EXEC_XSAVES |
SECONDARY_EXEC_ENABLE_PML |
- SECONDARY_EXEC_PCOMMIT |
SECONDARY_EXEC_TSC_SCALING;
if (adjust_vmx_controls(min2, opt2,
MSR_IA32_VMX_PROCBASED_CTLS2,
vmx_capability.ept, vmx_capability.vpid);
}
- min = VM_EXIT_SAVE_DEBUG_CONTROLS;
+ min = VM_EXIT_SAVE_DEBUG_CONTROLS | VM_EXIT_ACK_INTR_ON_EXIT;
#ifdef CONFIG_X86_64
min |= VM_EXIT_HOST_ADDR_SPACE_SIZE;
#endif
opt = VM_EXIT_SAVE_IA32_PAT | VM_EXIT_LOAD_IA32_PAT |
- VM_EXIT_ACK_INTR_ON_EXIT | VM_EXIT_CLEAR_BNDCFGS;
+ VM_EXIT_CLEAR_BNDCFGS;
if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS,
&_vmexit_control) < 0)
return -EIO;
min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING;
- opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR;
+ opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR |
+ PIN_BASED_VMX_PREEMPTION_TIMER;
if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS,
&_pin_based_exec_control) < 0)
return -EIO;
+ if (cpu_has_broken_vmx_preemption_timer())
+ _pin_based_exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
if (!(_cpu_based_2nd_exec_control &
- SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) ||
- !(_vmexit_control & VM_EXIT_ACK_INTR_ON_EXIT))
+ SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY))
_pin_based_exec_control &= ~PIN_BASED_POSTED_INTR;
min = VM_ENTRY_LOAD_DEBUG_CONTROLS;
/*
* Some cpus support VM_ENTRY_(LOAD|SAVE)_IA32_PERF_GLOBAL_CTRL
- * but due to arrata below it can't be used. Workaround is to use
+ * but due to errata below it can't be used. Workaround is to use
* msr load mechanism to switch IA32_PERF_GLOBAL_CTRL.
*
* VM Exit May Incorrectly Clear IA32_PERF_GLOBAL_CTRL [34:32]
if (!kvm_vcpu_apicv_active(&vmx->vcpu))
pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR;
+ /* Enable the preemption timer dynamically */
+ pin_based_exec_ctrl &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
return pin_based_exec_ctrl;
}
if (!enable_pml)
exec_control &= ~SECONDARY_EXEC_ENABLE_PML;
- /* Currently, we allow L1 guest to directly run pcommit instruction. */
- exec_control &= ~SECONDARY_EXEC_PCOMMIT;
-
return exec_control;
}
/* Control */
vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, vmx_pin_based_exec_ctrl(vmx));
+ vmx->hv_deadline_tsc = -1;
vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, vmx_exec_control(vmx));
- if (cpu_has_secondary_exec_ctrls())
+ if (cpu_has_secondary_exec_ctrls()) {
vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
vmx_secondary_exec_control(vmx));
+ }
if (kvm_vcpu_apicv_active(&vmx->vcpu)) {
vmcs_write64(EOI_EXIT_BITMAP0, 0);
if (vmx_xsaves_supported())
vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP);
+ if (enable_pml) {
+ ASSERT(vmx->pml_pg);
+ vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
+ vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+ }
+
return 0;
}
gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
trace_kvm_page_fault(gpa, exit_qualification);
- /* It is a write fault? */
- error_code = exit_qualification & PFERR_WRITE_MASK;
+ /* it is a read fault? */
+ error_code = (exit_qualification << 2) & PFERR_USER_MASK;
+ /* it is a write fault? */
+ error_code |= exit_qualification & PFERR_WRITE_MASK;
/* It is a fetch fault? */
error_code |= (exit_qualification << 2) & PFERR_FETCH_MASK;
/* ept page table is present? */
- error_code |= (exit_qualification >> 3) & PFERR_PRESENT_MASK;
+ error_code |= (exit_qualification & 0x38) != 0;
vcpu->arch.exit_qualification = exit_qualification;
for (msr = 0x800; msr <= 0x8ff; msr++)
vmx_disable_intercept_msr_read_x2apic(msr);
- /* According SDM, in x2apic mode, the whole id reg is used. But in
- * KVM, it only use the highest eight bits. Need to intercept it */
- vmx_enable_intercept_msr_read_x2apic(0x802);
/* TMCCT */
vmx_enable_intercept_msr_read_x2apic(0x839);
/* TPR */
vmx_disable_intercept_msr_write_x2apic(0x83f);
if (enable_ept) {
- kvm_mmu_set_mask_ptes(0ull,
+ kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK,
(enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull,
(enable_ept_ad_bits) ? VMX_EPT_DIRTY_BIT : 0ull,
- 0ull, VMX_EPT_EXECUTABLE_MASK);
+ 0ull, VMX_EPT_EXECUTABLE_MASK,
+ cpu_has_vmx_ept_execute_only() ?
+ 0ull : VMX_EPT_READABLE_MASK);
ept_set_mmio_spte_mask();
kvm_enable_tdp();
} else
kvm_x86_ops->enable_log_dirty_pt_masked = NULL;
}
+ if (cpu_has_vmx_preemption_timer() && enable_preemption_timer) {
+ u64 vmx_msr;
+
+ rdmsrl(MSR_IA32_VMX_MISC, vmx_msr);
+ cpu_preemption_timer_multi =
+ vmx_msr & VMX_MISC_PREEMPTION_TIMER_RATE_MASK;
+ } else {
+ kvm_x86_ops->set_hv_timer = NULL;
+ kvm_x86_ops->cancel_hv_timer = NULL;
+ }
+
kvm_set_posted_intr_wakeup_handler(wakeup_handler);
+ kvm_mce_cap_supported |= MCG_LMCE_P;
+
return alloc_kvm_area();
out8:
/* Checks for #GP/#SS exceptions. */
exn = false;
- if (is_protmode(vcpu)) {
+ if (is_long_mode(vcpu)) {
+ /* Long mode: #GP(0)/#SS(0) if the memory address is in a
+ * non-canonical form. This is the only check on the memory
+ * destination for long mode!
+ */
+ exn = is_noncanonical_address(*ret);
+ } else if (is_protmode(vcpu)) {
/* Protected mode: apply checks for segment validity in the
* following order:
* - segment type check (#GP(0) may be thrown)
* execute-only code segment
*/
exn = ((s.type & 0xa) == 8);
- }
- if (exn) {
- kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
- return 1;
- }
- if (is_long_mode(vcpu)) {
- /* Long mode: #GP(0)/#SS(0) if the memory address is in a
- * non-canonical form. This is an only check for long mode.
- */
- exn = is_noncanonical_address(*ret);
- } else if (is_protmode(vcpu)) {
+ if (exn) {
+ kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
+ return 1;
+ }
/* Protected mode: #GP(0)/#SS(0) if the segment is unusable.
*/
exn = (s.unusable != 0);
return 1;
}
- if ((vmx->nested.msr_ia32_feature_control & VMXON_NEEDED_FEATURES)
+ if ((vmx->msr_ia32_feature_control & VMXON_NEEDED_FEATURES)
!= VMXON_NEEDED_FEATURES) {
kvm_inject_gp(vcpu, 0);
return 1;
}
+ vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL);
+ if (!vmx->nested.cached_vmcs12)
+ return -ENOMEM;
+
if (enable_shadow_vmcs) {
shadow_vmcs = alloc_vmcs();
- if (!shadow_vmcs)
+ if (!shadow_vmcs) {
+ kfree(vmx->nested.cached_vmcs12);
return -ENOMEM;
+ }
/* mark vmcs as shadow */
shadow_vmcs->revision_id |= (1u << 31);
/* init shadow vmcs */
vmcs_write64(VMCS_LINK_POINTER, -1ull);
}
vmx->nested.posted_intr_nv = -1;
+
+ /* Flush VMCS12 to guest memory */
+ memcpy(vmx->nested.current_vmcs12, vmx->nested.cached_vmcs12,
+ VMCS12_SIZE);
+
kunmap(vmx->nested.current_vmcs12_page);
nested_release_page(vmx->nested.current_vmcs12_page);
vmx->nested.current_vmptr = -1ull;
nested_release_vmcs12(vmx);
if (enable_shadow_vmcs)
free_vmcs(vmx->nested.current_shadow_vmcs);
+ kfree(vmx->nested.cached_vmcs12);
/* Unpin physical memory we referred to in current vmcs02 */
if (vmx->nested.apic_access_page) {
nested_release_page(vmx->nested.apic_access_page);
vmx->nested.current_vmptr = vmptr;
vmx->nested.current_vmcs12 = new_vmcs12;
vmx->nested.current_vmcs12_page = page;
+ /*
+ * Load VMCS12 from guest memory since it is not already
+ * cached.
+ */
+ memcpy(vmx->nested.cached_vmcs12,
+ vmx->nested.current_vmcs12, VMCS12_SIZE);
+
if (enable_shadow_vmcs) {
vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
SECONDARY_EXEC_SHADOW_VMCS);
return 1;
}
-static int handle_pcommit(struct kvm_vcpu *vcpu)
-{
- /* we never catch pcommit instruct for L1 guest. */
- WARN_ON(1);
- return 1;
-}
-
+ static int handle_preemption_timer(struct kvm_vcpu *vcpu)
+ {
+ kvm_lapic_expired_hv_timer(vcpu);
+ return 1;
+ }
+
/*
* The exit handlers return 1 if the exit was handled fully and guest execution
* may resume. Otherwise they set the kvm_run parameter to indicate what needs
[EXIT_REASON_XSAVES] = handle_xsaves,
[EXIT_REASON_XRSTORS] = handle_xrstors,
[EXIT_REASON_PML_FULL] = handle_pml_full,
- [EXIT_REASON_PCOMMIT] = handle_pcommit,
+ [EXIT_REASON_PREEMPTION_TIMER] = handle_preemption_timer,
};
static const int kvm_vmx_max_exit_handlers =
* the XSS exit bitmap in vmcs12.
*/
return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
- case EXIT_REASON_PCOMMIT:
- return nested_cpu_has2(vmcs12, SECONDARY_EXEC_PCOMMIT);
+ case EXIT_REASON_PREEMPTION_TIMER:
+ return false;
default:
return true;
}
*info2 = vmcs_read32(VM_EXIT_INTR_INFO);
}
-static int vmx_create_pml_buffer(struct vcpu_vmx *vmx)
-{
- struct page *pml_pg;
-
- pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO);
- if (!pml_pg)
- return -ENOMEM;
-
- vmx->pml_pg = pml_pg;
-
- vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
- vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
-
- return 0;
-}
-
static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx)
{
if (vmx->pml_pg) {
if ((vectoring_info & VECTORING_INFO_VALID_MASK) &&
(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
exit_reason != EXIT_REASON_EPT_VIOLATION &&
+ exit_reason != EXIT_REASON_PML_FULL &&
exit_reason != EXIT_REASON_TASK_SWITCH)) {
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
* the next L2->L1 exit.
*/
if (!is_guest_mode(vcpu) ||
- !nested_cpu_has2(vmx->nested.current_vmcs12,
+ !nested_cpu_has2(get_vmcs12(&vmx->vcpu),
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
vmcs_write64(APIC_ACCESS_ADDR, hpa);
}
"push %[sp]\n\t"
#endif
"pushf\n\t"
- "orl $0x200, (%%" _ASM_SP ")\n\t"
__ASM_SIZE(push) " $%c[cs]\n\t"
"call *%[entry]\n\t"
:
[ss]"i"(__KERNEL_DS),
[cs]"i"(__KERNEL_CS)
);
- } else
- local_irq_enable();
+ }
}
static bool vmx_has_high_real_mode_segbase(void)
msrs[i].host);
}
+ void vmx_arm_hv_timer(struct kvm_vcpu *vcpu)
+ {
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ u64 tscl;
+ u32 delta_tsc;
+
+ if (vmx->hv_deadline_tsc == -1)
+ return;
+
+ tscl = rdtsc();
+ if (vmx->hv_deadline_tsc > tscl)
+ /* sure to be 32 bit only because checked on set_hv_timer */
+ delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >>
+ cpu_preemption_timer_multi);
+ else
+ delta_tsc = 0;
+
+ vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, delta_tsc);
+ }
+
static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
atomic_switch_perf_msrs(vmx);
debugctlmsr = get_debugctlmsr();
+ vmx_arm_hv_timer(vcpu);
+
vmx->__launched = vmx->loaded_vmcs->launched;
asm(
/* Store host registers */
put_cpu();
}
+/*
+ * Ensure that the current vmcs of the logical processor is the
+ * vmcs01 of the vcpu before calling free_nested().
+ */
+static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ int r;
+
+ r = vcpu_load(vcpu);
+ BUG_ON(r);
+ vmx_load_vmcs01(vcpu);
+ free_nested(vmx);
+ vcpu_put(vcpu);
+}
+
static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
vmx_destroy_pml_buffer(vmx);
free_vpid(vmx->vpid);
leave_guest_mode(vcpu);
- vmx_load_vmcs01(vcpu);
- free_nested(vmx);
+ vmx_free_vcpu_nested(vcpu);
free_loaded_vmcs(vmx->loaded_vmcs);
kfree(vmx->guest_msrs);
kvm_vcpu_uninit(vcpu);
if (err)
goto free_vcpu;
+ err = -ENOMEM;
+
+ /*
+ * If PML is turned on, failure on enabling PML just results in failure
+ * of creating the vcpu, therefore we can simplify PML logic (by
+ * avoiding dealing with cases, such as enabling PML partially on vcpus
+ * for the guest, etc.
+ */
+ if (enable_pml) {
+ vmx->pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO);
+ if (!vmx->pml_pg)
+ goto uninit_vcpu;
+ }
+
vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx->guest_msrs[0])
> PAGE_SIZE);
- err = -ENOMEM;
- if (!vmx->guest_msrs) {
- goto uninit_vcpu;
- }
+ if (!vmx->guest_msrs)
+ goto free_pml;
vmx->loaded_vmcs = &vmx->vmcs01;
vmx->loaded_vmcs->vmcs = alloc_vmcs();
vmx->nested.current_vmptr = -1ull;
vmx->nested.current_vmcs12 = NULL;
- /*
- * If PML is turned on, failure on enabling PML just results in failure
- * of creating the vcpu, therefore we can simplify PML logic (by
- * avoiding dealing with cases, such as enabling PML partially on vcpus
- * for the guest, etc.
- */
- if (enable_pml) {
- err = vmx_create_pml_buffer(vmx);
- if (err)
- goto free_vmcs;
- }
-
+ vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED;
+
return &vmx->vcpu;
free_vmcs:
free_loaded_vmcs(vmx->loaded_vmcs);
free_msrs:
kfree(vmx->guest_msrs);
+free_pml:
+ vmx_destroy_pml_buffer(vmx);
uninit_vcpu:
kvm_vcpu_uninit(&vmx->vcpu);
free_vcpu:
if (cpu_has_secondary_exec_ctrls())
vmcs_set_secondary_exec_control(secondary_exec_ctl);
- if (static_cpu_has(X86_FEATURE_PCOMMIT) && nested) {
- if (guest_cpuid_has_pcommit(vcpu))
- vmx->nested.nested_vmx_secondary_ctls_high |=
- SECONDARY_EXEC_PCOMMIT;
- else
- vmx->nested.nested_vmx_secondary_ctls_high &=
- ~SECONDARY_EXEC_PCOMMIT;
- }
-
+
+ if (nested_vmx_allowed(vcpu))
+ to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |=
+ FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+ else
+ to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &=
+ ~FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
}
static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
vmcs_write64(VMCS_LINK_POINTER, -1ull);
exec_control = vmcs12->pin_based_vm_exec_control;
- exec_control |= vmcs_config.pin_based_exec_ctrl;
+
+ /* Preemption timer setting is only taken from vmcs01. */
exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+ exec_control |= vmcs_config.pin_based_exec_ctrl;
+ if (vmx->hv_deadline_tsc == -1)
+ exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+ /* Posted interrupts setting is only taken from vmcs12. */
if (nested_cpu_has_posted_intr(vmcs12)) {
/*
* Note that we use L0's vector here and in
exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
SECONDARY_EXEC_RDTSCP |
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
- SECONDARY_EXEC_APIC_REGISTER_VIRT |
- SECONDARY_EXEC_PCOMMIT);
+ SECONDARY_EXEC_APIC_REGISTER_VIRT);
if (nested_cpu_has(vmcs12,
CPU_BASED_ACTIVATE_SECONDARY_CONTROLS))
exec_control |= vmcs12->secondary_vm_exec_control;
vmcs12->vm_exit_intr_error_code,
KVM_ISA_VMX);
- vm_entry_controls_init(vmx, vmcs_read32(VM_ENTRY_CONTROLS));
- vm_exit_controls_init(vmx, vmcs_read32(VM_EXIT_CONTROLS));
+ vm_entry_controls_reset_shadow(vmx);
+ vm_exit_controls_reset_shadow(vmx);
vmx_segment_cache_clear(vmx);
/* if no vmcs02 cache requested, remove the one we used */
load_vmcs12_host_state(vcpu, vmcs12);
- /* Update TSC_OFFSET if TSC was changed while L2 ran */
+ /* Update any VMCS fields that might have changed while L2 ran */
vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);
+ if (vmx->hv_deadline_tsc == -1)
+ vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
+ PIN_BASED_VMX_PREEMPTION_TIMER);
+ else
+ vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
+ PIN_BASED_VMX_PREEMPTION_TIMER);
/* This is needed for same reason as it was needed in prepare_vmcs02 */
vmx->host_rsp = 0;
return X86EMUL_CONTINUE;
}
+ #ifdef CONFIG_X86_64
+ /* (a << shift) / divisor, return 1 if overflow otherwise 0 */
+ static inline int u64_shl_div_u64(u64 a, unsigned int shift,
+ u64 divisor, u64 *result)
+ {
+ u64 low = a << shift, high = a >> (64 - shift);
+
+ /* To avoid the overflow on divq */
+ if (high >= divisor)
+ return 1;
+
+ /* Low hold the result, high hold rem which is discarded */
+ asm("divq %2\n\t" : "=a" (low), "=d" (high) :
+ "rm" (divisor), "0" (low), "1" (high));
+ *result = low;
+
+ return 0;
+ }
+
+ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
+ {
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ u64 tscl = rdtsc();
+ u64 guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
+ u64 delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
+
+ /* Convert to host delta tsc if tsc scaling is enabled */
+ if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio &&
+ u64_shl_div_u64(delta_tsc,
+ kvm_tsc_scaling_ratio_frac_bits,
+ vcpu->arch.tsc_scaling_ratio,
+ &delta_tsc))
+ return -ERANGE;
+
+ /*
+ * If the delta tsc can't fit in the 32 bit after the multi shift,
+ * we can't use the preemption timer.
+ * It's possible that it fits on later vmentries, but checking
+ * on every vmentry is costly so we just use an hrtimer.
+ */
+ if (delta_tsc >> (cpu_preemption_timer_multi + 32))
+ return -ERANGE;
+
+ vmx->hv_deadline_tsc = tscl + delta_tsc;
+ vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
+ PIN_BASED_VMX_PREEMPTION_TIMER);
+ return 0;
+ }
+
+ static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)
+ {
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ vmx->hv_deadline_tsc = -1;
+ vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
+ PIN_BASED_VMX_PREEMPTION_TIMER);
+ }
+ #endif
+
static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
{
if (ple_gap)
* this case, return 1, otherwise, return 0.
*
*/
- static int vmx_pre_block(struct kvm_vcpu *vcpu)
+ static int pi_pre_block(struct kvm_vcpu *vcpu)
{
unsigned long flags;
unsigned int dest;
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP))
+ !irq_remapping_cap(IRQ_POSTING_CAP) ||
+ !kvm_vcpu_apicv_active(vcpu))
return 0;
vcpu->pre_pcpu = vcpu->cpu;
return 0;
}
- static void vmx_post_block(struct kvm_vcpu *vcpu)
+ static int vmx_pre_block(struct kvm_vcpu *vcpu)
+ {
+ if (pi_pre_block(vcpu))
+ return 1;
+
+ if (kvm_lapic_hv_timer_in_use(vcpu))
+ kvm_lapic_switch_to_sw_timer(vcpu);
+
+ return 0;
+ }
+
+ static void pi_post_block(struct kvm_vcpu *vcpu)
{
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
struct pi_desc old, new;
unsigned long flags;
if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP))
+ !irq_remapping_cap(IRQ_POSTING_CAP) ||
+ !kvm_vcpu_apicv_active(vcpu))
return;
do {
}
}
+ static void vmx_post_block(struct kvm_vcpu *vcpu)
+ {
+ if (kvm_x86_ops->set_hv_timer)
+ kvm_lapic_switch_to_hv_timer(vcpu);
+
+ pi_post_block(vcpu);
+ }
+
/*
* vmx_update_pi_irte - set IRTE for Posted-Interrupts
*
int idx, ret = -EINVAL;
if (!kvm_arch_has_assigned_device(kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP))
+ !irq_remapping_cap(IRQ_POSTING_CAP) ||
+ !kvm_vcpu_apicv_active(kvm->vcpus[0]))
return 0;
idx = srcu_read_lock(&kvm->irq_srcu);
* We will support full lowest-priority interrupt later.
*/
- kvm_set_msi_irq(e, &irq);
+ kvm_set_msi_irq(kvm, e, &irq);
if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) {
/*
* Make sure the IRTE is in remapped mode if
return ret;
}
+ static void vmx_setup_mce(struct kvm_vcpu *vcpu)
+ {
+ if (vcpu->arch.mcg_cap & MCG_LMCE_P)
+ to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |=
+ FEATURE_CONTROL_LMCE;
+ else
+ to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &=
+ ~FEATURE_CONTROL_LMCE;
+ }
+
static struct kvm_x86_ops vmx_x86_ops = {
.cpu_has_kvm_support = cpu_has_kvm_support,
.disabled_by_bios = vmx_disabled_by_bios,
.pmu_ops = &intel_pmu_ops,
.update_pi_irte = vmx_update_pi_irte,
+
+ #ifdef CONFIG_X86_64
+ .set_hv_timer = vmx_set_hv_timer,
+ .cancel_hv_timer = vmx_cancel_hv_timer,
+ #endif
+
+ .setup_mce = vmx_setup_mce,
};
static int __init vmx_init(void)
#include <linux/kvm.h>
#include <linux/fs.h>
#include <linux/vmalloc.h>
-#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/moduleparam.h>
#include <linux/mman.h>
#include <linux/highmem.h>
#include <linux/iommu.h>
#include <linux/irqbypass.h>
#include <trace/events/kvm.h>
-#define CREATE_TRACE_POINTS
-#include "trace.h"
-
#include <asm/debugreg.h>
#include <asm/msr.h>
#include <asm/desc.h>
#include <asm/div64.h>
#include <asm/irq_remapping.h>
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
#define MAX_IO_MSRS 256
#define KVM_MAX_MCE_BANKS 32
- #define KVM_MCE_CAP_SUPPORTED (MCG_CTL_P | MCG_SER_P)
+ u64 __read_mostly kvm_mce_cap_supported = MCG_CTL_P | MCG_SER_P;
+ EXPORT_SYMBOL_GPL(kvm_mce_cap_supported);
#define emul_to_vcpu(ctxt) \
container_of(ctxt, struct kvm_vcpu, arch.emulate_ctxt)
#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
+ #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \
+ KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK)
+
static void update_cr8_intercept(struct kvm_vcpu *vcpu);
static void process_nmi(struct kvm_vcpu *vcpu);
+ static void enter_smm(struct kvm_vcpu *vcpu);
static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
struct kvm_x86_ops *kvm_x86_ops __read_mostly;
EXPORT_SYMBOL_GPL(kvm_tsc_scaling_ratio_frac_bits);
u64 __read_mostly kvm_max_tsc_scaling_ratio;
EXPORT_SYMBOL_GPL(kvm_max_tsc_scaling_ratio);
- static u64 __read_mostly kvm_default_tsc_scaling_ratio;
+ u64 __read_mostly kvm_default_tsc_scaling_ratio;
+ EXPORT_SYMBOL_GPL(kvm_default_tsc_scaling_ratio);
/* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */
static u32 __read_mostly tsc_tolerance_ppm = 250;
goto out;
}
for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
- if (is_present_gpte(pdpte[i]) &&
+ if ((pdpte[i] & PT_PRESENT_MASK) &&
(pdpte[i] &
vcpu->arch.mmu.guest_rsvd_check.rsvd_bits_mask[0][2])) {
ret = 0;
MSR_IA32_MISC_ENABLE,
MSR_IA32_MCG_STATUS,
MSR_IA32_MCG_CTL,
+ MSR_IA32_MCG_EXT_CTL,
MSR_IA32_SMBASE,
};
int version;
int r;
struct pvclock_wall_clock wc;
- struct timespec boot;
+ struct timespec64 boot;
if (!wall_clock)
return;
* wall clock specified here. guest system time equals host
* system time for us, thus we must fill in host boot time here.
*/
- getboottime(&boot);
+ getboottime64(&boot);
if (kvm->arch.kvmclock_offset) {
- struct timespec ts = ns_to_timespec(kvm->arch.kvmclock_offset);
- boot = timespec_sub(boot, ts);
+ struct timespec64 ts = ns_to_timespec64(kvm->arch.kvmclock_offset);
+ boot = timespec64_sub(boot, ts);
}
- wc.sec = boot.tv_sec;
+ wc.sec = (u32)boot.tv_sec; /* overflow in 2106 guest time */
wc.nsec = boot.tv_nsec;
wc.version = version;
static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);
static unsigned long max_tsc_khz;
-static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
-{
- return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult,
- vcpu->arch.virtual_tsc_shift);
-}
-
static u32 adjust_tsc_khz(u32 khz, s32 ppm)
{
u64 v = (u64)khz * (1000000 + ppm);
case KVM_CAP_TSC_CONTROL:
r = kvm_has_tsc_control;
break;
+ case KVM_CAP_X2APIC_API:
+ r = KVM_X2APIC_API_VALID_FLAGS;
+ break;
default:
r = 0;
break;
break;
}
case KVM_X86_GET_MCE_CAP_SUPPORTED: {
- u64 mce_cap;
-
- mce_cap = KVM_MCE_CAP_SUPPORTED;
r = -EFAULT;
- if (copy_to_user(argp, &mce_cap, sizeof mce_cap))
+ if (copy_to_user(argp, &kvm_mce_cap_supported,
+ sizeof(kvm_mce_cap_supported)))
goto out;
r = 0;
break;
rdtsc() - vcpu->arch.last_host_tsc;
if (tsc_delta < 0)
mark_tsc_unstable("KVM discovered backwards TSC");
+
+ if (kvm_lapic_hv_timer_in_use(vcpu) &&
+ kvm_x86_ops->set_hv_timer(vcpu,
+ kvm_get_lapic_tscdeadline_msr(vcpu)))
+ kvm_lapic_switch_to_sw_timer(vcpu);
if (check_tsc_unstable()) {
u64 offset = kvm_compute_tsc_offset(vcpu,
vcpu->arch.last_guest_tsc);
if (vcpu->arch.apicv_active)
kvm_x86_ops->sync_pir_to_irr(vcpu);
- memcpy(s->regs, vcpu->arch.apic->regs, sizeof *s);
-
- return 0;
+ return kvm_apic_get_state(vcpu, s);
}
static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
struct kvm_lapic_state *s)
{
- kvm_apic_post_state_restore(vcpu, s);
+ int r;
+
+ r = kvm_apic_set_state(vcpu, s);
+ if (r)
+ return r;
update_cr8_intercept(vcpu);
return 0;
r = -EINVAL;
if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS)
goto out;
- if (mcg_cap & ~(KVM_MCE_CAP_SUPPORTED | 0xff | 0xff0000))
+ if (mcg_cap & ~(kvm_mce_cap_supported | 0xff | 0xff0000))
goto out;
r = 0;
vcpu->arch.mcg_cap = mcg_cap;
/* Init IA32_MCi_CTL to all 1s */
for (bank = 0; bank < bank_num; bank++)
vcpu->arch.mce_banks[bank*4] = ~(u64)0;
+
+ if (kvm_x86_ops->setup_mce)
+ kvm_x86_ops->setup_mce(vcpu);
out:
return r;
}
r = -EEXIST;
if (irqchip_in_kernel(kvm))
goto split_irqchip_unlock;
- if (atomic_read(&kvm->online_vcpus))
+ if (kvm->created_vcpus)
goto split_irqchip_unlock;
r = kvm_setup_empty_irq_routing(kvm);
if (r)
mutex_unlock(&kvm->lock);
break;
}
+ case KVM_CAP_X2APIC_API:
+ r = -EINVAL;
+ if (cap->args[0] & ~KVM_X2APIC_API_VALID_FLAGS)
+ break;
+
+ if (cap->args[0] & KVM_X2APIC_API_USE_32BIT_IDS)
+ kvm->arch.x2apic_format = true;
+ if (cap->args[0] & KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK)
+ kvm->arch.x2apic_broadcast_quirk_disabled = true;
+
+ r = 0;
+ break;
default:
r = -EINVAL;
break;
if (kvm->arch.vpic)
goto create_irqchip_unlock;
r = -EINVAL;
- if (atomic_read(&kvm->online_vcpus))
+ if (kvm->created_vcpus)
goto create_irqchip_unlock;
r = -ENOMEM;
vpic = kvm_create_pic(kvm);
sizeof(struct kvm_pit_config)))
goto out;
create_pit:
- mutex_lock(&kvm->slots_lock);
+ mutex_lock(&kvm->lock);
r = -EEXIST;
if (kvm->arch.vpit)
goto create_pit_unlock;
if (kvm->arch.vpit)
r = 0;
create_pit_unlock:
- mutex_unlock(&kvm->slots_lock);
+ mutex_unlock(&kvm->lock);
break;
case KVM_GET_IRQCHIP: {
/* 0: PIC master, 1: PIC slave, 2: IOAPIC */
case KVM_SET_BOOT_CPU_ID:
r = 0;
mutex_lock(&kvm->lock);
- if (atomic_read(&kvm->online_vcpus) != 0)
+ if (kvm->created_vcpus)
r = -EBUSY;
else
kvm->arch.bsp_vcpu_id = arg;
/* This is a good place to trace that we are exiting SMM. */
trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, false);
- if (unlikely(vcpu->arch.smi_pending)) {
- kvm_make_request(KVM_REQ_SMI, vcpu);
- vcpu->arch.smi_pending = 0;
- } else {
- /* Process a latched INIT, if any. */
- kvm_make_request(KVM_REQ_EVENT, vcpu);
- }
+ /* Process a latched INIT or SMI, if any. */
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
}
kvm_mmu_reset_context(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_fast_pio_out);
-static void tsc_bad(void *info)
+static int kvmclock_cpu_down_prep(unsigned int cpu)
{
__this_cpu_write(cpu_tsc_khz, 0);
+ return 0;
}
static void tsc_khz_changed(void *data)
.notifier_call = kvmclock_cpufreq_notifier
};
-static int kvmclock_cpu_notifier(struct notifier_block *nfb,
- unsigned long action, void *hcpu)
+static int kvmclock_cpu_online(unsigned int cpu)
{
- unsigned int cpu = (unsigned long)hcpu;
-
- switch (action) {
- case CPU_ONLINE:
- case CPU_DOWN_FAILED:
- smp_call_function_single(cpu, tsc_khz_changed, NULL, 1);
- break;
- case CPU_DOWN_PREPARE:
- smp_call_function_single(cpu, tsc_bad, NULL, 1);
- break;
- }
- return NOTIFY_OK;
+ tsc_khz_changed(NULL);
+ return 0;
}
-static struct notifier_block kvmclock_cpu_notifier_block = {
- .notifier_call = kvmclock_cpu_notifier,
- .priority = -INT_MAX
-};
-
static void kvm_timer_init(void)
{
int cpu;
max_tsc_khz = tsc_khz;
- cpu_notifier_register_begin();
if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
#ifdef CONFIG_CPU_FREQ
struct cpufreq_policy policy;
CPUFREQ_TRANSITION_NOTIFIER);
}
pr_debug("kvm: max_tsc_khz = %ld\n", max_tsc_khz);
- for_each_online_cpu(cpu)
- smp_call_function_single(cpu, tsc_khz_changed, NULL, 1);
-
- __register_hotcpu_notifier(&kvmclock_cpu_notifier_block);
- cpu_notifier_register_done();
+ cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "AP_X86_KVM_CLK_ONLINE",
+ kvmclock_cpu_online, kvmclock_cpu_down_prep);
}
static DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu);
kvm_x86_ops = ops;
kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
- PT_DIRTY_MASK, PT64_NX_MASK, 0);
-
+ PT_DIRTY_MASK, PT64_NX_MASK, 0,
+ PT_PRESENT_MASK);
kvm_timer_init();
perf_register_guest_info_callbacks(&kvm_guest_cbs);
if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block,
CPUFREQ_TRANSITION_NOTIFIER);
- unregister_hotcpu_notifier(&kvmclock_cpu_notifier_block);
+ cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE);
#ifdef CONFIG_X86_64
pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier);
#endif
}
/* try to inject new event if pending */
- if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) {
+ if (vcpu->arch.smi_pending && !is_smm(vcpu)) {
+ vcpu->arch.smi_pending = false;
+ enter_smm(vcpu);
+ } else if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) {
--vcpu->arch.nmi_pending;
vcpu->arch.nmi_injected = true;
kvm_x86_ops->set_nmi(vcpu);
kvm_x86_ops->set_irq(vcpu);
}
}
+
return 0;
}
#define put_smstate(type, buf, offset, val) \
*(type *)((buf) + (offset) - 0x7e00) = val
- static u32 process_smi_get_segment_flags(struct kvm_segment *seg)
+ static u32 enter_smm_get_segment_flags(struct kvm_segment *seg)
{
u32 flags = 0;
flags |= seg->g << 23;
return flags;
}
- static void process_smi_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n)
+ static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n)
{
struct kvm_segment seg;
int offset;
put_smstate(u32, buf, offset + 8, seg.base);
put_smstate(u32, buf, offset + 4, seg.limit);
- put_smstate(u32, buf, offset, process_smi_get_segment_flags(&seg));
+ put_smstate(u32, buf, offset, enter_smm_get_segment_flags(&seg));
}
#ifdef CONFIG_X86_64
- static void process_smi_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n)
+ static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n)
{
struct kvm_segment seg;
int offset;
kvm_get_segment(vcpu, &seg, n);
offset = 0x7e00 + n * 16;
- flags = process_smi_get_segment_flags(&seg) >> 8;
+ flags = enter_smm_get_segment_flags(&seg) >> 8;
put_smstate(u16, buf, offset, seg.selector);
put_smstate(u16, buf, offset + 2, flags);
put_smstate(u32, buf, offset + 4, seg.limit);
}
#endif
- static void process_smi_save_state_32(struct kvm_vcpu *vcpu, char *buf)
+ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf)
{
struct desc_ptr dt;
struct kvm_segment seg;
put_smstate(u32, buf, 0x7fc4, seg.selector);
put_smstate(u32, buf, 0x7f64, seg.base);
put_smstate(u32, buf, 0x7f60, seg.limit);
- put_smstate(u32, buf, 0x7f5c, process_smi_get_segment_flags(&seg));
+ put_smstate(u32, buf, 0x7f5c, enter_smm_get_segment_flags(&seg));
kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
put_smstate(u32, buf, 0x7fc0, seg.selector);
put_smstate(u32, buf, 0x7f80, seg.base);
put_smstate(u32, buf, 0x7f7c, seg.limit);
- put_smstate(u32, buf, 0x7f78, process_smi_get_segment_flags(&seg));
+ put_smstate(u32, buf, 0x7f78, enter_smm_get_segment_flags(&seg));
kvm_x86_ops->get_gdt(vcpu, &dt);
put_smstate(u32, buf, 0x7f74, dt.address);
put_smstate(u32, buf, 0x7f54, dt.size);
for (i = 0; i < 6; i++)
- process_smi_save_seg_32(vcpu, buf, i);
+ enter_smm_save_seg_32(vcpu, buf, i);
put_smstate(u32, buf, 0x7f14, kvm_read_cr4(vcpu));
put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase);
}
- static void process_smi_save_state_64(struct kvm_vcpu *vcpu, char *buf)
+ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
{
#ifdef CONFIG_X86_64
struct desc_ptr dt;
kvm_get_segment(vcpu, &seg, VCPU_SREG_TR);
put_smstate(u16, buf, 0x7e90, seg.selector);
- put_smstate(u16, buf, 0x7e92, process_smi_get_segment_flags(&seg) >> 8);
+ put_smstate(u16, buf, 0x7e92, enter_smm_get_segment_flags(&seg) >> 8);
put_smstate(u32, buf, 0x7e94, seg.limit);
put_smstate(u64, buf, 0x7e98, seg.base);
kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
put_smstate(u16, buf, 0x7e70, seg.selector);
- put_smstate(u16, buf, 0x7e72, process_smi_get_segment_flags(&seg) >> 8);
+ put_smstate(u16, buf, 0x7e72, enter_smm_get_segment_flags(&seg) >> 8);
put_smstate(u32, buf, 0x7e74, seg.limit);
put_smstate(u64, buf, 0x7e78, seg.base);
put_smstate(u64, buf, 0x7e68, dt.address);
for (i = 0; i < 6; i++)
- process_smi_save_seg_64(vcpu, buf, i);
+ enter_smm_save_seg_64(vcpu, buf, i);
#else
WARN_ON_ONCE(1);
#endif
}
- static void process_smi(struct kvm_vcpu *vcpu)
+ static void enter_smm(struct kvm_vcpu *vcpu)
{
struct kvm_segment cs, ds;
struct desc_ptr dt;
char buf[512];
u32 cr0;
- if (is_smm(vcpu)) {
- vcpu->arch.smi_pending = true;
- return;
- }
-
trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true);
vcpu->arch.hflags |= HF_SMM_MASK;
memset(buf, 0, 512);
if (guest_cpuid_has_longmode(vcpu))
- process_smi_save_state_64(vcpu, buf);
+ enter_smm_save_state_64(vcpu, buf);
else
- process_smi_save_state_32(vcpu, buf);
+ enter_smm_save_state_32(vcpu, buf);
kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf));
kvm_mmu_reset_context(vcpu);
}
+ static void process_smi(struct kvm_vcpu *vcpu)
+ {
+ vcpu->arch.smi_pending = true;
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+ }
+
void kvm_make_scan_ioapic_request(struct kvm *kvm)
{
kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
if (inject_pending_event(vcpu, req_int_win) != 0)
req_immediate_exit = true;
- /* enable NMI/IRQ window open exits if needed */
else {
+ /* Enable NMI/IRQ window open exits if needed.
+ *
+ * SMIs have two cases: 1) they can be nested, and
+ * then there is nothing to do here because RSM will
+ * cause a vmexit anyway; 2) or the SMI can be pending
+ * because inject_pending_event has completed the
+ * injection of an IRQ or NMI from the previous vmexit,
+ * and then we request an immediate exit to inject the SMI.
+ */
+ if (vcpu->arch.smi_pending && !is_smm(vcpu))
+ req_immediate_exit = true;
if (vcpu->arch.nmi_pending)
kvm_x86_ops->enable_nmi_window(vcpu);
if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
kvm_load_guest_xcr0(vcpu);
- if (req_immediate_exit)
+ if (req_immediate_exit) {
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
smp_send_reschedule(vcpu->cpu);
+ }
trace_kvm_entry(vcpu->vcpu_id);
wait_lapic_expire(vcpu);
- __kvm_guest_enter();
+ guest_enter_irqoff();
if (unlikely(vcpu->arch.switch_db_regs)) {
set_debugreg(0, 7);
++vcpu->stat.exits;
- /*
- * We must have an instruction between local_irq_enable() and
- * kvm_guest_exit(), so the timer interrupt isn't delayed by
- * the interrupt shadow. The stat.exits increment will do nicely.
- * But we need to prevent reordering, hence this barrier():
- */
- barrier();
-
- kvm_guest_exit();
+ guest_exit_irqoff();
+ local_irq_enable();
preempt_enable();
vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
{
vcpu->arch.hflags = 0;
+ vcpu->arch.smi_pending = 0;
atomic_set(&vcpu->arch.nmi_queued, 0);
vcpu->arch.nmi_pending = 0;
vcpu->arch.nmi_injected = false;
return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0;
}
- bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu)
- {
- return irqchip_in_kernel(vcpu->kvm) == lapic_in_kernel(vcpu);
- }
-
struct static_key kvm_no_apic_vcpu __read_mostly;
EXPORT_SYMBOL_GPL(kvm_no_apic_vcpu);
kfree(kvm->arch.vpic);
kfree(kvm->arch.vioapic);
kvm_free_vcpus(kvm);
- kfree(rcu_dereference_check(kvm->arch.apic_map, 1));
+ kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
kvm_mmu_uninit_vm(kvm);
}
/*
* When producer of consumer is unregistered, we change back to
* remapped mode, so we can re-use the current implementation
- * when the irq is masked/disabed or the consumer side (KVM
+ * when the irq is masked/disabled or the consumer side (KVM
* int this case doesn't want to receive the interrupts.
*/
ret = kvm_x86_ops->update_pi_irte(irqfd->kvm, prod->irq, irqfd->gsi, 0);
context_tracking_exit(CONTEXT_USER);
}
+/* Called with interrupts disabled. */
+static inline void user_enter_irqoff(void)
+{
+ if (context_tracking_is_enabled())
+ __context_tracking_enter(CONTEXT_USER);
+
+}
+static inline void user_exit_irqoff(void)
+{
+ if (context_tracking_is_enabled())
+ __context_tracking_exit(CONTEXT_USER);
+}
+
static inline enum ctx_state exception_enter(void)
{
enum ctx_state prev_ctx;
#else
static inline void user_enter(void) { }
static inline void user_exit(void) { }
+static inline void user_enter_irqoff(void) { }
+static inline void user_exit_irqoff(void) { }
static inline enum ctx_state exception_enter(void) { return 0; }
static inline void exception_exit(enum ctx_state prev_ctx) { }
static inline enum ctx_state ct_state(void) { return CONTEXT_DISABLED; }
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
- static inline void guest_enter(void)
+ /* must be called with irqs disabled */
+ static inline void guest_enter_irqoff(void)
{
if (vtime_accounting_cpu_enabled())
vtime_guest_enter(current);
if (context_tracking_is_enabled())
__context_tracking_enter(CONTEXT_GUEST);
+
+ /* KVM does not hold any references to rcu protected data when it
+ * switches CPU into a guest mode. In fact switching to a guest mode
+ * is very similar to exiting to userspace from rcu point of view. In
+ * addition CPU may stay in a guest mode for quite a long time (up to
+ * one time slice). Lets treat guest mode as quiescent state, just like
+ * we do with user-mode execution.
+ */
+ if (!context_tracking_cpu_is_enabled())
+ rcu_virt_note_context_switch(smp_processor_id());
}
- static inline void guest_exit(void)
+ static inline void guest_exit_irqoff(void)
{
if (context_tracking_is_enabled())
__context_tracking_exit(CONTEXT_GUEST);
}
#else
- static inline void guest_enter(void)
+ static inline void guest_enter_irqoff(void)
{
/*
* This is running in ioctl context so its safe
*/
vtime_account_system(current);
current->flags |= PF_VCPU;
+ rcu_virt_note_context_switch(smp_processor_id());
}
- static inline void guest_exit(void)
+ static inline void guest_exit_irqoff(void)
{
/* Flush the guest cputime we spent on the guest */
vtime_account_system(current);
}
#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */
+ static inline void guest_enter(void)
+ {
+ unsigned long flags;
+
+ local_irq_save(flags);
+ guest_enter_irqoff();
+ local_irq_restore(flags);
+ }
+
+ static inline void guest_exit(void)
+ {
+ unsigned long flags;
+
+ local_irq_save(flags);
+ guest_exit_irqoff();
+ local_irq_restore(flags);
+ }
+
#endif
#define GICR_WAKER_ProcessorSleep (1U << 1)
#define GICR_WAKER_ChildrenAsleep (1U << 2)
- #define GICR_PROPBASER_NonShareable (0U << 10)
- #define GICR_PROPBASER_InnerShareable (1U << 10)
- #define GICR_PROPBASER_OuterShareable (2U << 10)
- #define GICR_PROPBASER_SHAREABILITY_MASK (3UL << 10)
- #define GICR_PROPBASER_nCnB (0U << 7)
- #define GICR_PROPBASER_nC (1U << 7)
- #define GICR_PROPBASER_RaWt (2U << 7)
- #define GICR_PROPBASER_RaWb (3U << 7)
- #define GICR_PROPBASER_WaWt (4U << 7)
- #define GICR_PROPBASER_WaWb (5U << 7)
- #define GICR_PROPBASER_RaWaWt (6U << 7)
- #define GICR_PROPBASER_RaWaWb (7U << 7)
- #define GICR_PROPBASER_CACHEABILITY_MASK (7U << 7)
- #define GICR_PROPBASER_IDBITS_MASK (0x1f)
-
- #define GICR_PENDBASER_NonShareable (0U << 10)
- #define GICR_PENDBASER_InnerShareable (1U << 10)
- #define GICR_PENDBASER_OuterShareable (2U << 10)
- #define GICR_PENDBASER_SHAREABILITY_MASK (3UL << 10)
- #define GICR_PENDBASER_nCnB (0U << 7)
- #define GICR_PENDBASER_nC (1U << 7)
- #define GICR_PENDBASER_RaWt (2U << 7)
- #define GICR_PENDBASER_RaWb (3U << 7)
- #define GICR_PENDBASER_WaWt (4U << 7)
- #define GICR_PENDBASER_WaWb (5U << 7)
- #define GICR_PENDBASER_RaWaWt (6U << 7)
- #define GICR_PENDBASER_RaWaWb (7U << 7)
- #define GICR_PENDBASER_CACHEABILITY_MASK (7U << 7)
+ #define GIC_BASER_CACHE_nCnB 0ULL
+ #define GIC_BASER_CACHE_SameAsInner 0ULL
+ #define GIC_BASER_CACHE_nC 1ULL
+ #define GIC_BASER_CACHE_RaWt 2ULL
+ #define GIC_BASER_CACHE_RaWb 3ULL
+ #define GIC_BASER_CACHE_WaWt 4ULL
+ #define GIC_BASER_CACHE_WaWb 5ULL
+ #define GIC_BASER_CACHE_RaWaWt 6ULL
+ #define GIC_BASER_CACHE_RaWaWb 7ULL
+ #define GIC_BASER_CACHE_MASK 7ULL
+ #define GIC_BASER_NonShareable 0ULL
+ #define GIC_BASER_InnerShareable 1ULL
+ #define GIC_BASER_OuterShareable 2ULL
+ #define GIC_BASER_SHAREABILITY_MASK 3ULL
+
+ #define GIC_BASER_CACHEABILITY(reg, inner_outer, type) \
+ (GIC_BASER_CACHE_##type << reg##_##inner_outer##_CACHEABILITY_SHIFT)
+
+ #define GIC_BASER_SHAREABILITY(reg, type) \
+ (GIC_BASER_##type << reg##_SHAREABILITY_SHIFT)
+
+ #define GICR_PROPBASER_SHAREABILITY_SHIFT (10)
+ #define GICR_PROPBASER_INNER_CACHEABILITY_SHIFT (7)
+ #define GICR_PROPBASER_OUTER_CACHEABILITY_SHIFT (56)
+ #define GICR_PROPBASER_SHAREABILITY_MASK \
+ GIC_BASER_SHAREABILITY(GICR_PROPBASER, SHAREABILITY_MASK)
+ #define GICR_PROPBASER_INNER_CACHEABILITY_MASK \
+ GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, MASK)
+ #define GICR_PROPBASER_OUTER_CACHEABILITY_MASK \
+ GIC_BASER_CACHEABILITY(GICR_PROPBASER, OUTER, MASK)
+ #define GICR_PROPBASER_CACHEABILITY_MASK GICR_PROPBASER_INNER_CACHEABILITY_MASK
+
+ #define GICR_PROPBASER_InnerShareable \
+ GIC_BASER_SHAREABILITY(GICR_PROPBASER, InnerShareable)
+
+ #define GICR_PROPBASER_nCnB GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, nCnB)
+ #define GICR_PROPBASER_nC GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, nC)
+ #define GICR_PROPBASER_RaWt GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWt)
+ #define GICR_PROPBASER_RaWb GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWt)
+ #define GICR_PROPBASER_WaWt GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, WaWt)
+ #define GICR_PROPBASER_WaWb GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, WaWb)
+ #define GICR_PROPBASER_RaWaWt GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWaWt)
+ #define GICR_PROPBASER_RaWaWb GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWaWb)
+
+ #define GICR_PROPBASER_IDBITS_MASK (0x1f)
+
+ #define GICR_PENDBASER_SHAREABILITY_SHIFT (10)
+ #define GICR_PENDBASER_INNER_CACHEABILITY_SHIFT (7)
+ #define GICR_PENDBASER_OUTER_CACHEABILITY_SHIFT (56)
+ #define GICR_PENDBASER_SHAREABILITY_MASK \
+ GIC_BASER_SHAREABILITY(GICR_PENDBASER, SHAREABILITY_MASK)
+ #define GICR_PENDBASER_INNER_CACHEABILITY_MASK \
+ GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, MASK)
+ #define GICR_PENDBASER_OUTER_CACHEABILITY_MASK \
+ GIC_BASER_CACHEABILITY(GICR_PENDBASER, OUTER, MASK)
+ #define GICR_PENDBASER_CACHEABILITY_MASK GICR_PENDBASER_INNER_CACHEABILITY_MASK
+
+ #define GICR_PENDBASER_InnerShareable \
+ GIC_BASER_SHAREABILITY(GICR_PENDBASER, InnerShareable)
+
+ #define GICR_PENDBASER_nCnB GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, nCnB)
+ #define GICR_PENDBASER_nC GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, nC)
+ #define GICR_PENDBASER_RaWt GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWt)
+ #define GICR_PENDBASER_RaWb GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWt)
+ #define GICR_PENDBASER_WaWt GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, WaWt)
+ #define GICR_PENDBASER_WaWb GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, WaWb)
+ #define GICR_PENDBASER_RaWaWt GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWaWt)
+ #define GICR_PENDBASER_RaWaWb GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWaWb)
+
+ #define GICR_PENDBASER_PTZ BIT_ULL(62)
/*
* Re-Distributor registers, offsets from SGI_base
#define GITS_CWRITER 0x0088
#define GITS_CREADR 0x0090
#define GITS_BASER 0x0100
+ #define GITS_IDREGS_BASE 0xffd0
+ #define GITS_PIDR0 0xffe0
+ #define GITS_PIDR1 0xffe4
#define GITS_PIDR2 GICR_PIDR2
+ #define GITS_PIDR4 0xffd0
+ #define GITS_CIDR0 0xfff0
+ #define GITS_CIDR1 0xfff4
+ #define GITS_CIDR2 0xfff8
+ #define GITS_CIDR3 0xfffc
#define GITS_TRANSLATER 0x10040
#define GITS_CTLR_ENABLE (1U << 0)
#define GITS_CTLR_QUIESCENT (1U << 31)
+ #define GITS_TYPER_PLPIS (1UL << 0)
+ #define GITS_TYPER_IDBITS_SHIFT 8
#define GITS_TYPER_DEVBITS_SHIFT 13
#define GITS_TYPER_DEVBITS(r) ((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1)
#define GITS_TYPER_PTA (1UL << 19)
-
- #define GITS_CBASER_VALID (1UL << 63)
- #define GITS_CBASER_nCnB (0UL << 59)
- #define GITS_CBASER_nC (1UL << 59)
- #define GITS_CBASER_RaWt (2UL << 59)
- #define GITS_CBASER_RaWb (3UL << 59)
- #define GITS_CBASER_WaWt (4UL << 59)
- #define GITS_CBASER_WaWb (5UL << 59)
- #define GITS_CBASER_RaWaWt (6UL << 59)
- #define GITS_CBASER_RaWaWb (7UL << 59)
- #define GITS_CBASER_CACHEABILITY_MASK (7UL << 59)
- #define GITS_CBASER_NonShareable (0UL << 10)
- #define GITS_CBASER_InnerShareable (1UL << 10)
- #define GITS_CBASER_OuterShareable (2UL << 10)
- #define GITS_CBASER_SHAREABILITY_MASK (3UL << 10)
+ #define GITS_TYPER_HWCOLLCNT_SHIFT 24
+
+ #define GITS_CBASER_VALID (1UL << 63)
+ #define GITS_CBASER_SHAREABILITY_SHIFT (10)
+ #define GITS_CBASER_INNER_CACHEABILITY_SHIFT (59)
+ #define GITS_CBASER_OUTER_CACHEABILITY_SHIFT (53)
+ #define GITS_CBASER_SHAREABILITY_MASK \
+ GIC_BASER_SHAREABILITY(GITS_CBASER, SHAREABILITY_MASK)
+ #define GITS_CBASER_INNER_CACHEABILITY_MASK \
+ GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, MASK)
+ #define GITS_CBASER_OUTER_CACHEABILITY_MASK \
+ GIC_BASER_CACHEABILITY(GITS_CBASER, OUTER, MASK)
+ #define GITS_CBASER_CACHEABILITY_MASK GITS_CBASER_INNER_CACHEABILITY_MASK
+
+ #define GITS_CBASER_InnerShareable \
+ GIC_BASER_SHAREABILITY(GITS_CBASER, InnerShareable)
+
+ #define GITS_CBASER_nCnB GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, nCnB)
+ #define GITS_CBASER_nC GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, nC)
+ #define GITS_CBASER_RaWt GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWt)
+ #define GITS_CBASER_RaWb GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWt)
+ #define GITS_CBASER_WaWt GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, WaWt)
+ #define GITS_CBASER_WaWb GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, WaWb)
+ #define GITS_CBASER_RaWaWt GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWaWt)
+ #define GITS_CBASER_RaWaWb GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWaWb)
#define GITS_BASER_NR_REGS 8
- #define GITS_BASER_VALID (1UL << 63)
- #define GITS_BASER_INDIRECT (1UL << 62)
- #define GITS_BASER_nCnB (0UL << 59)
- #define GITS_BASER_nC (1UL << 59)
- #define GITS_BASER_RaWt (2UL << 59)
- #define GITS_BASER_RaWb (3UL << 59)
- #define GITS_BASER_WaWt (4UL << 59)
- #define GITS_BASER_WaWb (5UL << 59)
- #define GITS_BASER_RaWaWt (6UL << 59)
- #define GITS_BASER_RaWaWb (7UL << 59)
- #define GITS_BASER_CACHEABILITY_MASK (7UL << 59)
- #define GITS_BASER_TYPE_SHIFT (56)
+ #define GITS_BASER_VALID (1UL << 63)
+ #define GITS_BASER_INDIRECT (1ULL << 62)
+
+ #define GITS_BASER_INNER_CACHEABILITY_SHIFT (59)
+ #define GITS_BASER_OUTER_CACHEABILITY_SHIFT (53)
+ #define GITS_BASER_INNER_CACHEABILITY_MASK \
+ GIC_BASER_CACHEABILITY(GITS_BASER, INNER, MASK)
+ #define GITS_BASER_CACHEABILITY_MASK GITS_BASER_INNER_CACHEABILITY_MASK
+ #define GITS_BASER_OUTER_CACHEABILITY_MASK \
+ GIC_BASER_CACHEABILITY(GITS_BASER, OUTER, MASK)
+ #define GITS_BASER_SHAREABILITY_MASK \
+ GIC_BASER_SHAREABILITY(GITS_BASER, SHAREABILITY_MASK)
+
+ #define GITS_BASER_nCnB GIC_BASER_CACHEABILITY(GITS_BASER, INNER, nCnB)
+ #define GITS_BASER_nC GIC_BASER_CACHEABILITY(GITS_BASER, INNER, nC)
+ #define GITS_BASER_RaWt GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWt)
+ #define GITS_BASER_RaWb GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWt)
+ #define GITS_BASER_WaWt GIC_BASER_CACHEABILITY(GITS_BASER, INNER, WaWt)
+ #define GITS_BASER_WaWb GIC_BASER_CACHEABILITY(GITS_BASER, INNER, WaWb)
+ #define GITS_BASER_RaWaWt GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWaWt)
+ #define GITS_BASER_RaWaWb GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWaWb)
+
+ #define GITS_BASER_TYPE_SHIFT (56)
#define GITS_BASER_TYPE(r) (((r) >> GITS_BASER_TYPE_SHIFT) & 7)
- #define GITS_BASER_ENTRY_SIZE_SHIFT (48)
+ #define GITS_BASER_ENTRY_SIZE_SHIFT (48)
#define GITS_BASER_ENTRY_SIZE(r) ((((r) >> GITS_BASER_ENTRY_SIZE_SHIFT) & 0xff) + 1)
- #define GITS_BASER_NonShareable (0UL << 10)
- #define GITS_BASER_InnerShareable (1UL << 10)
- #define GITS_BASER_OuterShareable (2UL << 10)
#define GITS_BASER_SHAREABILITY_SHIFT (10)
- #define GITS_BASER_SHAREABILITY_MASK (3UL << GITS_BASER_SHAREABILITY_SHIFT)
+ #define GITS_BASER_InnerShareable \
+ GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable)
#define GITS_BASER_PAGE_SIZE_SHIFT (8)
#define GITS_BASER_PAGE_SIZE_4K (0UL << GITS_BASER_PAGE_SIZE_SHIFT)
#define GITS_BASER_PAGE_SIZE_16K (1UL << GITS_BASER_PAGE_SIZE_SHIFT)
#define GITS_BASER_PAGE_SIZE_64K (2UL << GITS_BASER_PAGE_SIZE_SHIFT)
#define GITS_BASER_PAGE_SIZE_MASK (3UL << GITS_BASER_PAGE_SIZE_SHIFT)
#define GITS_BASER_PAGES_MAX 256
+#define GITS_BASER_PAGES_SHIFT (0)
+ #define GITS_BASER_NR_PAGES(r) (((r) & 0xff) + 1)
#define GITS_BASER_TYPE_NONE 0
#define GITS_BASER_TYPE_DEVICE 1
#define GITS_BASER_TYPE_RESERVED6 6
#define GITS_BASER_TYPE_RESERVED7 7
+#define GITS_LVL1_ENTRY_SIZE (8UL)
+
/*
* ITS commands
*/
#define GITS_CMD_MAPD 0x08
#define GITS_CMD_MAPC 0x09
- #define GITS_CMD_MAPVI 0x0a
+ #define GITS_CMD_MAPTI 0x0a
+ /* older GIC documentation used MAPVI for this command */
+ #define GITS_CMD_MAPVI GITS_CMD_MAPTI
+ #define GITS_CMD_MAPI 0x0b
#define GITS_CMD_MOVI 0x01
#define GITS_CMD_DISCARD 0x0f
#define GITS_CMD_INV 0x0c
#define GITS_CMD_CLEAR 0x04
#define GITS_CMD_SYNC 0x05
+ /*
+ * ITS error numbers
+ */
+ #define E_ITS_MOVI_UNMAPPED_INTERRUPT 0x010107
+ #define E_ITS_MOVI_UNMAPPED_COLLECTION 0x010109
+ #define E_ITS_CLEAR_UNMAPPED_INTERRUPT 0x010507
+ #define E_ITS_MAPD_DEVICE_OOR 0x010801
+ #define E_ITS_MAPC_PROCNUM_OOR 0x010902
+ #define E_ITS_MAPC_COLLECTION_OOR 0x010903
+ #define E_ITS_MAPTI_UNMAPPED_DEVICE 0x010a04
+ #define E_ITS_MAPTI_PHYSICALID_OOR 0x010a06
+ #define E_ITS_INV_UNMAPPED_INTERRUPT 0x010c07
+ #define E_ITS_INVALL_UNMAPPED_COLLECTION 0x010d09
+ #define E_ITS_MOVALL_PROCNUM_OOR 0x010e01
+ #define E_ITS_DISCARD_UNMAPPED_INTERRUPT 0x010f07
+
/*
* CPU interface registers
*/
#define ICC_SGI1R_AFFINITY_1_SHIFT 16
#define ICC_SGI1R_AFFINITY_1_MASK (0xff << ICC_SGI1R_AFFINITY_1_SHIFT)
#define ICC_SGI1R_SGI_ID_SHIFT 24
-#define ICC_SGI1R_SGI_ID_MASK (0xff << ICC_SGI1R_SGI_ID_SHIFT)
+#define ICC_SGI1R_SGI_ID_MASK (0xfULL << ICC_SGI1R_SGI_ID_SHIFT)
#define ICC_SGI1R_AFFINITY_2_SHIFT 32
-#define ICC_SGI1R_AFFINITY_2_MASK (0xffULL << ICC_SGI1R_AFFINITY_1_SHIFT)
+#define ICC_SGI1R_AFFINITY_2_MASK (0xffULL << ICC_SGI1R_AFFINITY_2_SHIFT)
#define ICC_SGI1R_IRQ_ROUTING_MODE_BIT 40
#define ICC_SGI1R_AFFINITY_3_SHIFT 48
-#define ICC_SGI1R_AFFINITY_3_MASK (0xffULL << ICC_SGI1R_AFFINITY_1_SHIFT)
+#define ICC_SGI1R_AFFINITY_3_MASK (0xffULL << ICC_SGI1R_AFFINITY_3_SHIFT)
#include <asm/arch_gicv3.h>
spin_unlock(ptl);
ret = 0;
split_huge_pmd(vma, pmd, address);
+ if (pmd_trans_unstable(pmd))
+ ret = -EBUSY;
} else {
get_page(page);
spin_unlock(ptl);
ret = split_huge_page(page);
unlock_page(page);
put_page(page);
+ if (pmd_none(*pmd))
+ return no_page_table(vma, flags);
}
return ret ? ERR_PTR(ret) :
static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
unsigned long address, unsigned int *flags, int *nonblocking)
{
- struct mm_struct *mm = vma->vm_mm;
unsigned int fault_flags = 0;
int ret;
fault_flags |= FAULT_FLAG_TRIED;
}
- ret = handle_mm_fault(mm, vma, address, fault_flags);
+ ret = handle_mm_fault(vma, address, fault_flags);
if (ret & VM_FAULT_ERROR) {
if (ret & VM_FAULT_OOM)
return -ENOMEM;
if (!vma_permits_fault(vma, fault_flags))
return -EFAULT;
- ret = handle_mm_fault(mm, vma, address, fault_flags);
+ ret = handle_mm_fault(vma, address, fault_flags);
major |= ret & VM_FAULT_MAJOR;
if (ret & VM_FAULT_ERROR) {
if (ret & VM_FAULT_OOM)
}
return 0;
}
+ EXPORT_SYMBOL_GPL(fixup_user_fault);
static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
struct mm_struct *mm,
struct kvm_vcpu *vcpu0 = kvm_get_vcpu(kvm, 0);
int i;
+ INIT_LIST_HEAD(&dist->lpi_list_head);
+ spin_lock_init(&dist->lpi_list_lock);
+
dist->spis = kcalloc(nr_spis, sizeof(struct vgic_irq), GFP_KERNEL);
if (!dist->spis)
return -ENOMEM;
spin_lock_init(&irq->irq_lock);
irq->vcpu = NULL;
irq->target_vcpu = vcpu0;
+ kref_init(&irq->refcount);
if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2)
irq->targets = 0;
else
irq->vcpu = NULL;
irq->target_vcpu = vcpu;
irq->targets = 1U << vcpu->vcpu_id;
+ kref_init(&irq->refcount);
if (vgic_irq_is_sgi(i)) {
/* SGIs */
irq->enabled = 1;
if (ret)
goto out;
+ if (vgic_has_its(kvm))
+ dist->msis_require_devid = true;
+
kvm_for_each_vcpu(i, vcpu, kvm)
kvm_vgic_vcpu_init(vcpu);
dist->initialized = false;
kfree(dist->spis);
- kfree(dist->redist_iodevs);
dist->nr_spis = 0;
mutex_unlock(&kvm->lock);
/* GENERIC PROBE */
-static void vgic_init_maintenance_interrupt(void *info)
+static int vgic_init_cpu_starting(unsigned int cpu)
{
enable_percpu_irq(kvm_vgic_global_state.maint_irq, 0);
+ return 0;
}
-static int vgic_cpu_notify(struct notifier_block *self,
- unsigned long action, void *cpu)
-{
- switch (action) {
- case CPU_STARTING:
- case CPU_STARTING_FROZEN:
- vgic_init_maintenance_interrupt(NULL);
- break;
- case CPU_DYING:
- case CPU_DYING_FROZEN:
- disable_percpu_irq(kvm_vgic_global_state.maint_irq);
- break;
- }
- return NOTIFY_OK;
+static int vgic_init_cpu_dying(unsigned int cpu)
+{
+ disable_percpu_irq(kvm_vgic_global_state.maint_irq);
+ return 0;
}
-static struct notifier_block vgic_cpu_nb = {
- .notifier_call = vgic_cpu_notify,
-};
-
static irqreturn_t vgic_maintenance_handler(int irq, void *data)
{
/*
return ret;
}
- ret = __register_cpu_notifier(&vgic_cpu_nb);
+ ret = cpuhp_setup_state(CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING,
+ "AP_KVM_ARM_VGIC_INIT_STARTING",
+ vgic_init_cpu_starting, vgic_init_cpu_dying);
if (ret) {
kvm_err("Cannot register vgic CPU notifier\n");
goto out_free_irq;
}
- on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1);
-
kvm_info("vgic interrupt IRQ%d\n", kvm_vgic_global_state.maint_irq);
return 0;
put_cpu();
return 0;
}
+EXPORT_SYMBOL_GPL(vcpu_load);
void vcpu_put(struct kvm_vcpu *vcpu)
{
preempt_enable();
mutex_unlock(&vcpu->mutex);
}
+EXPORT_SYMBOL_GPL(vcpu_put);
static void ack_flush(void *_completed)
{
return true;
}
+ static int hva_to_pfn_remapped(struct vm_area_struct *vma,
+ unsigned long addr, bool *async,
+ bool write_fault, kvm_pfn_t *p_pfn)
+ {
+ unsigned long pfn;
+ int r;
+
+ r = follow_pfn(vma, addr, &pfn);
+ if (r) {
+ /*
+ * get_user_pages fails for VM_IO and VM_PFNMAP vmas and does
+ * not call the fault handler, so do it here.
+ */
+ bool unlocked = false;
+ r = fixup_user_fault(current, current->mm, addr,
+ (write_fault ? FAULT_FLAG_WRITE : 0),
+ &unlocked);
+ if (unlocked)
+ return -EAGAIN;
+ if (r)
+ return r;
+
+ r = follow_pfn(vma, addr, &pfn);
+ if (r)
+ return r;
+
+ }
+
+
+ /*
+ * Get a reference here because callers of *hva_to_pfn* and
+ * *gfn_to_pfn* ultimately call kvm_release_pfn_clean on the
+ * returned pfn. This is only needed if the VMA has VM_MIXEDMAP
+ * set, but the kvm_get_pfn/kvm_release_pfn_clean pair will
+ * simply do nothing for reserved pfns.
+ *
+ * Whoever called remap_pfn_range is also going to call e.g.
+ * unmap_mapping_range before the underlying pages are freed,
+ * causing a call to our MMU notifier.
+ */
+ kvm_get_pfn(pfn);
+
+ *p_pfn = pfn;
+ return 0;
+ }
+
/*
* Pin guest page in memory and return its pfn.
* @addr: host virtual address which maps memory to the guest
{
struct vm_area_struct *vma;
kvm_pfn_t pfn = 0;
- int npages;
+ int npages, r;
/* we can do it either atomically or asynchronously, not both */
BUG_ON(atomic && async);
goto exit;
}
+ retry:
vma = find_vma_intersection(current->mm, addr, addr + 1);
if (vma == NULL)
pfn = KVM_PFN_ERR_FAULT;
- else if ((vma->vm_flags & VM_PFNMAP)) {
- pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) +
- vma->vm_pgoff;
- BUG_ON(!kvm_is_reserved_pfn(pfn));
+ else if (vma->vm_flags & (VM_IO | VM_PFNMAP)) {
+ r = hva_to_pfn_remapped(vma, addr, async, write_fault, &pfn);
+ if (r == -EAGAIN)
+ goto retry;
+ if (r < 0)
+ pfn = KVM_PFN_ERR_FAULT;
} else {
if (async && vma_is_valid(vma, write_fault))
*async = true;
if (id >= KVM_MAX_VCPU_ID)
return -EINVAL;
+ mutex_lock(&kvm->lock);
+ if (kvm->created_vcpus == KVM_MAX_VCPUS) {
+ mutex_unlock(&kvm->lock);
+ return -EINVAL;
+ }
+
+ kvm->created_vcpus++;
+ mutex_unlock(&kvm->lock);
+
vcpu = kvm_arch_vcpu_create(kvm, id);
- if (IS_ERR(vcpu))
- return PTR_ERR(vcpu);
+ if (IS_ERR(vcpu)) {
+ r = PTR_ERR(vcpu);
+ goto vcpu_decrement;
+ }
preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops);
goto vcpu_destroy;
mutex_lock(&kvm->lock);
- if (!kvm_vcpu_compatible(vcpu)) {
- r = -EINVAL;
- goto unlock_vcpu_destroy;
- }
- if (atomic_read(&kvm->online_vcpus) == KVM_MAX_VCPUS) {
- r = -EINVAL;
- goto unlock_vcpu_destroy;
- }
if (kvm_get_vcpu_by_id(kvm, id)) {
r = -EEXIST;
goto unlock_vcpu_destroy;
mutex_unlock(&kvm->lock);
vcpu_destroy:
kvm_arch_vcpu_destroy(vcpu);
+ vcpu_decrement:
+ mutex_lock(&kvm->lock);
+ kvm->created_vcpus--;
+ mutex_unlock(&kvm->lock);
return r;
}
if (copy_from_user(&routing, argp, sizeof(routing)))
goto out;
r = -EINVAL;
- if (routing.nr >= KVM_MAX_IRQ_ROUTES)
+ if (routing.nr > KVM_MAX_IRQ_ROUTES)
goto out;
if (routing.flags)
goto out;
{
int r;
struct kvm *kvm;
+ struct file *file;
kvm = kvm_create_vm(type);
if (IS_ERR(kvm))
return r;
}
#endif
- r = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR | O_CLOEXEC);
+ r = get_unused_fd_flags(O_CLOEXEC);
if (r < 0) {
kvm_put_kvm(kvm);
return r;
}
+ file = anon_inode_getfile("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
+ if (IS_ERR(file)) {
+ put_unused_fd(r);
+ kvm_put_kvm(kvm);
+ return PTR_ERR(file);
+ }
if (kvm_create_vm_debugfs(kvm, r) < 0) {
- kvm_put_kvm(kvm);
+ put_unused_fd(r);
+ fput(file);
return -ENOMEM;
}
+ fd_install(r, file);
return r;
}
}
}
-static void hardware_enable(void)
+static int kvm_starting_cpu(unsigned int cpu)
{
raw_spin_lock(&kvm_count_lock);
if (kvm_usage_count)
hardware_enable_nolock(NULL);
raw_spin_unlock(&kvm_count_lock);
+ return 0;
}
static void hardware_disable_nolock(void *junk)
kvm_arch_hardware_disable();
}
-static void hardware_disable(void)
+static int kvm_dying_cpu(unsigned int cpu)
{
raw_spin_lock(&kvm_count_lock);
if (kvm_usage_count)
hardware_disable_nolock(NULL);
raw_spin_unlock(&kvm_count_lock);
+ return 0;
}
static void hardware_disable_all_nolock(void)
return r;
}
-static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
- void *v)
-{
- val &= ~CPU_TASKS_FROZEN;
- switch (val) {
- case CPU_DYING:
- hardware_disable();
- break;
- case CPU_STARTING:
- hardware_enable();
- break;
- }
- return NOTIFY_OK;
-}
-
static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
void *v)
{
return r;
}
-static struct notifier_block kvm_cpu_notifier = {
- .notifier_call = kvm_cpu_hotplug,
-};
-
+ struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
+ gpa_t addr)
+ {
+ struct kvm_io_bus *bus;
+ int dev_idx, srcu_idx;
+ struct kvm_io_device *iodev = NULL;
+
+ srcu_idx = srcu_read_lock(&kvm->srcu);
+
+ bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
+
+ dev_idx = kvm_io_bus_get_first_dev(bus, addr, 1);
+ if (dev_idx < 0)
+ goto out_unlock;
+
+ iodev = bus->range[dev_idx].dev;
+
+ out_unlock:
+ srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+ return iodev;
+ }
+ EXPORT_SYMBOL_GPL(kvm_io_bus_get_dev);
+
static int kvm_debugfs_open(struct inode *inode, struct file *file,
int (*get)(void *, u64 *), int (*set)(void *, u64),
const char *fmt)
goto out_free_1;
}
- r = register_cpu_notifier(&kvm_cpu_notifier);
+ r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "AP_KVM_STARTING",
+ kvm_starting_cpu, kvm_dying_cpu);
if (r)
goto out_free_2;
register_reboot_notifier(&kvm_reboot_notifier);
kmem_cache_destroy(kvm_vcpu_cache);
out_free_3:
unregister_reboot_notifier(&kvm_reboot_notifier);
- unregister_cpu_notifier(&kvm_cpu_notifier);
+ cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING);
out_free_2:
out_free_1:
kvm_arch_hardware_unsetup();
kvm_async_pf_deinit();
unregister_syscore_ops(&kvm_syscore_ops);
unregister_reboot_notifier(&kvm_reboot_notifier);
- unregister_cpu_notifier(&kvm_cpu_notifier);
+ cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING);
on_each_cpu(hardware_disable_nolock, NULL, 1);
kvm_arch_hardware_unsetup();
kvm_arch_exit();