Commit 8c5e14f4 authored by Paolo Bonzini's avatar Paolo Bonzini

Merge tag 'kvmarm-for-v4.21' of...

Merge tag 'kvmarm-for-v4.21' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm updates for 4.21

- Large PUD support for HugeTLB
- Single-stepping fixes
- Improved tracing
- Various timer and vgic fixups
parents 51324119 8c33df1a
......@@ -23,6 +23,10 @@
#define ARM_EXIT_WITH_ABORT_BIT 31
#define ARM_EXCEPTION_CODE(x) ((x) & ~(1U << ARM_EXIT_WITH_ABORT_BIT))
#define ARM_EXCEPTION_IS_TRAP(x) \
(ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_PREF_ABORT || \
ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_DATA_ABORT || \
ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_HVC)
#define ARM_ABORT_PENDING(x) !!((x) & (1U << ARM_EXIT_WITH_ABORT_BIT))
#define ARM_EXCEPTION_RESET 0
......
......@@ -296,11 +296,6 @@ static inline void kvm_arm_init_debug(void) {}
static inline void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) {}
static inline void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) {}
static inline void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) {}
static inline bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu,
struct kvm_run *run)
{
return false;
}
int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
struct kvm_device_attr *attr);
......
......@@ -82,6 +82,67 @@ void kvm_clear_hyp_idmap(void);
#define kvm_mk_pud(pmdp) __pud(__pa(pmdp) | PMD_TYPE_TABLE)
#define kvm_mk_pgd(pudp) ({ BUILD_BUG(); 0; })
#define kvm_pfn_pte(pfn, prot) pfn_pte(pfn, prot)
#define kvm_pfn_pmd(pfn, prot) pfn_pmd(pfn, prot)
#define kvm_pfn_pud(pfn, prot) (__pud(0))
#define kvm_pud_pfn(pud) ({ WARN_ON(1); 0; })
#define kvm_pmd_mkhuge(pmd) pmd_mkhuge(pmd)
/* No support for pud hugepages */
#define kvm_pud_mkhuge(pud) ( {WARN_ON(1); pud; })
/*
* The following kvm_*pud*() functions are provided strictly to allow
* sharing code with arm64. They should never be called in practice.
*/
static inline void kvm_set_s2pud_readonly(pud_t *pud)
{
WARN_ON(1);
}
static inline bool kvm_s2pud_readonly(pud_t *pud)
{
WARN_ON(1);
return false;
}
static inline void kvm_set_pud(pud_t *pud, pud_t new_pud)
{
WARN_ON(1);
}
static inline pud_t kvm_s2pud_mkwrite(pud_t pud)
{
WARN_ON(1);
return pud;
}
static inline pud_t kvm_s2pud_mkexec(pud_t pud)
{
WARN_ON(1);
return pud;
}
static inline bool kvm_s2pud_exec(pud_t *pud)
{
WARN_ON(1);
return false;
}
static inline pud_t kvm_s2pud_mkyoung(pud_t pud)
{
BUG();
return pud;
}
static inline bool kvm_s2pud_young(pud_t pud)
{
WARN_ON(1);
return false;
}
static inline pte_t kvm_s2pte_mkwrite(pte_t pte)
{
pte_val(pte) |= L_PTE_S2_RDWR;
......
......@@ -68,4 +68,12 @@ stage2_pmd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
#define stage2_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp)
#define stage2_pud_table_empty(kvm, pudp) false
static inline bool kvm_stage2_has_pud(struct kvm *kvm)
{
return false;
}
#define S2_PMD_MASK PMD_MASK
#define S2_PMD_SIZE PMD_SIZE
#endif /* __ARM_S2_PGTABLE_H_ */
......@@ -602,8 +602,8 @@ static int emulate_cp15(struct kvm_vcpu *vcpu,
}
} else {
/* If access function fails, it should complain. */
kvm_err("Unsupported guest CP15 access at: %08lx\n",
*vcpu_pc(vcpu));
kvm_err("Unsupported guest CP15 access at: %08lx [%08lx]\n",
*vcpu_pc(vcpu), *vcpu_cpsr(vcpu));
print_cp_instr(params);
kvm_inject_undefined(vcpu);
}
......
......@@ -104,7 +104,7 @@
TCR_EL2_ORGN0_MASK | TCR_EL2_IRGN0_MASK | TCR_EL2_T0SZ_MASK)
/* VTCR_EL2 Registers bits */
#define VTCR_EL2_RES1 (1 << 31)
#define VTCR_EL2_RES1 (1U << 31)
#define VTCR_EL2_HD (1 << 22)
#define VTCR_EL2_HA (1 << 21)
#define VTCR_EL2_PS_SHIFT TCR_EL2_PS_SHIFT
......@@ -320,10 +320,6 @@
#define PAR_TO_HPFAR(par) \
(((par) & GENMASK_ULL(PHYS_MASK_SHIFT - 1, 12)) >> 8)
#define kvm_arm_exception_type \
{0, "IRQ" }, \
{1, "TRAP" }
#define ECN(x) { ESR_ELx_EC_##x, #x }
#define kvm_arm_exception_class \
......
......@@ -25,6 +25,7 @@
#define ARM_EXIT_WITH_SERROR_BIT 31
#define ARM_EXCEPTION_CODE(x) ((x) & ~(1U << ARM_EXIT_WITH_SERROR_BIT))
#define ARM_EXCEPTION_IS_TRAP(x) (ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_TRAP)
#define ARM_SERROR_PENDING(x) !!((x) & (1U << ARM_EXIT_WITH_SERROR_BIT))
#define ARM_EXCEPTION_IRQ 0
......@@ -34,6 +35,12 @@
/* The hyp-stub will return this for any kvm_call_hyp() call */
#define ARM_EXCEPTION_HYP_GONE HVC_STUB_ERR
#define kvm_arm_exception_type \
{ARM_EXCEPTION_IRQ, "IRQ" }, \
{ARM_EXCEPTION_EL1_SERROR, "SERROR" }, \
{ARM_EXCEPTION_TRAP, "TRAP" }, \
{ARM_EXCEPTION_HYP_GONE, "HYP_GONE" }
#ifndef __ASSEMBLY__
#include <linux/mm.h>
......
......@@ -24,6 +24,7 @@
#include <linux/kvm_host.h>
#include <asm/debug-monitors.h>
#include <asm/esr.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_hyp.h>
......@@ -147,14 +148,6 @@ static inline bool kvm_condition_valid(const struct kvm_vcpu *vcpu)
return true;
}
static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr)
{
if (vcpu_mode_is_32bit(vcpu))
kvm_skip_instr32(vcpu, is_wide_instr);
else
*vcpu_pc(vcpu) += 4;
}
static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
{
*vcpu_cpsr(vcpu) |= PSR_AA32_T_BIT;
......@@ -424,4 +417,30 @@ static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
return data; /* Leave LE untouched */
}
static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr)
{
if (vcpu_mode_is_32bit(vcpu))
kvm_skip_instr32(vcpu, is_wide_instr);
else
*vcpu_pc(vcpu) += 4;
/* advance the singlestep state machine */
*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
}
/*
* Skip an instruction which has been emulated at hyp while most guest sysregs
* are live.
*/
static inline void __hyp_text __kvm_skip_instr(struct kvm_vcpu *vcpu)
{
*vcpu_pc(vcpu) = read_sysreg_el2(elr);
vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(spsr);
kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
write_sysreg_el2(vcpu->arch.ctxt.gp_regs.regs.pstate, spsr);
write_sysreg_el2(*vcpu_pc(vcpu), elr);
}
#endif /* __ARM64_KVM_EMULATE_H__ */
......@@ -319,7 +319,7 @@ struct kvm_vcpu_arch {
*/
#define __vcpu_sys_reg(v,r) ((v)->arch.ctxt.sys_regs[(r)])
u64 vcpu_read_sys_reg(struct kvm_vcpu *vcpu, int reg);
u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg);
void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg);
/*
......@@ -445,7 +445,6 @@ void kvm_arm_init_debug(void);
void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
void kvm_arm_clear_debug(struct kvm_vcpu *vcpu);
void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu);
bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu, struct kvm_run *run);
int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
struct kvm_device_attr *attr);
int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
......
......@@ -184,6 +184,17 @@ void kvm_clear_hyp_idmap(void);
#define kvm_mk_pgd(pudp) \
__pgd(__phys_to_pgd_val(__pa(pudp)) | PUD_TYPE_TABLE)
#define kvm_set_pud(pudp, pud) set_pud(pudp, pud)
#define kvm_pfn_pte(pfn, prot) pfn_pte(pfn, prot)
#define kvm_pfn_pmd(pfn, prot) pfn_pmd(pfn, prot)
#define kvm_pfn_pud(pfn, prot) pfn_pud(pfn, prot)
#define kvm_pud_pfn(pud) pud_pfn(pud)
#define kvm_pmd_mkhuge(pmd) pmd_mkhuge(pmd)
#define kvm_pud_mkhuge(pud) pud_mkhuge(pud)
static inline pte_t kvm_s2pte_mkwrite(pte_t pte)
{
pte_val(pte) |= PTE_S2_RDWR;
......@@ -196,6 +207,12 @@ static inline pmd_t kvm_s2pmd_mkwrite(pmd_t pmd)
return pmd;
}
static inline pud_t kvm_s2pud_mkwrite(pud_t pud)
{
pud_val(pud) |= PUD_S2_RDWR;
return pud;
}
static inline pte_t kvm_s2pte_mkexec(pte_t pte)
{
pte_val(pte) &= ~PTE_S2_XN;
......@@ -208,6 +225,12 @@ static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd)
return pmd;
}
static inline pud_t kvm_s2pud_mkexec(pud_t pud)
{
pud_val(pud) &= ~PUD_S2_XN;
return pud;
}
static inline void kvm_set_s2pte_readonly(pte_t *ptep)
{
pteval_t old_pteval, pteval;
......@@ -246,6 +269,31 @@ static inline bool kvm_s2pmd_exec(pmd_t *pmdp)
return !(READ_ONCE(pmd_val(*pmdp)) & PMD_S2_XN);
}
static inline void kvm_set_s2pud_readonly(pud_t *pudp)
{
kvm_set_s2pte_readonly((pte_t *)pudp);
}
static inline bool kvm_s2pud_readonly(pud_t *pudp)
{
return kvm_s2pte_readonly((pte_t *)pudp);
}
static inline bool kvm_s2pud_exec(pud_t *pudp)
{
return !(READ_ONCE(pud_val(*pudp)) & PUD_S2_XN);
}
static inline pud_t kvm_s2pud_mkyoung(pud_t pud)
{
return pud_mkyoung(pud);
}
static inline bool kvm_s2pud_young(pud_t pud)
{
return pud_young(pud);
}
#define hyp_pte_table_empty(ptep) kvm_page_empty(ptep)
#ifdef __PAGETABLE_PMD_FOLDED
......
......@@ -193,6 +193,10 @@
#define PMD_S2_RDWR (_AT(pmdval_t, 3) << 6) /* HAP[2:1] */
#define PMD_S2_XN (_AT(pmdval_t, 2) << 53) /* XN[1:0] */
#define PUD_S2_RDONLY (_AT(pudval_t, 1) << 6) /* HAP[2:1] */
#define PUD_S2_RDWR (_AT(pudval_t, 3) << 6) /* HAP[2:1] */
#define PUD_S2_XN (_AT(pudval_t, 2) << 53) /* XN[1:0] */
/*
* Memory Attribute override for Stage-2 (MemAttr[3:0])
*/
......
......@@ -314,6 +314,11 @@ static inline pte_t pud_pte(pud_t pud)
return __pte(pud_val(pud));
}
static inline pud_t pte_pud(pte_t pte)
{
return __pud(pte_val(pte));
}
static inline pmd_t pud_pmd(pud_t pud)
{
return __pmd(pud_val(pud));
......@@ -381,8 +386,12 @@ static inline int pmd_protnone(pmd_t pmd)
#define pfn_pmd(pfn,prot) __pmd(__phys_to_pmd_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
#define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot)
#define pud_young(pud) pte_young(pud_pte(pud))
#define pud_mkyoung(pud) pte_pud(pte_mkyoung(pud_pte(pud)))
#define pud_write(pud) pte_write(pud_pte(pud))
#define pud_mkhuge(pud) (__pud(pud_val(pud) & ~PUD_TABLE_BIT))
#define __pud_to_phys(pud) __pte_to_phys(pud_pte(pud))
#define __phys_to_pud_val(phys) __phys_to_pte_val(phys)
#define pud_pfn(pud) ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT)
......
......@@ -30,16 +30,14 @@
#define pt_levels_pgdir_shift(lvls) ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - (lvls))
/*
* The hardware supports concatenation of up to 16 tables at stage2 entry level
* and we use the feature whenever possible.
* The hardware supports concatenation of up to 16 tables at stage2 entry
* level and we use the feature whenever possible, which means we resolve 4
* additional bits of address at the entry level.
*
* Now, the minimum number of bits resolved at any level is (PAGE_SHIFT - 3).
* On arm64, the smallest PAGE_SIZE supported is 4k, which means
* (PAGE_SHIFT - 3) > 4 holds for all page sizes.
* This implies, the total number of page table levels at stage2 expected
* by the hardware is actually the number of levels required for (IPA_SHIFT - 4)
* in normal translations(e.g, stage1), since we cannot have another level in
* the range (IPA_SHIFT, IPA_SHIFT - 4).
* This implies, the total number of page table levels required for
* IPA_SHIFT at stage2 expected by the hardware can be calculated using
* the same logic used for the (non-collapsable) stage1 page tables but for
* (IPA_SHIFT - 4).
*/
#define stage2_pgtable_levels(ipa) ARM64_HW_PGTABLE_LEVELS((ipa) - 4)
#define kvm_stage2_levels(kvm) VTCR_EL2_LVLS(kvm->arch.vtcr)
......
......@@ -236,24 +236,3 @@ void kvm_arm_clear_debug(struct kvm_vcpu *vcpu)
}
}
}
/*
* After successfully emulating an instruction, we might want to
* return to user space with a KVM_EXIT_DEBUG. We can only do this
* once the emulation is complete, though, so for userspace emulations
* we have to wait until we have re-entered KVM before calling this
* helper.
*
* Return true (and set exit_reason) to return to userspace or false
* if no further action is required.
*/
bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
run->exit_reason = KVM_EXIT_DEBUG;
run->debug.arch.hsr = ESR_ELx_EC_SOFTSTP_LOW << ESR_ELx_EC_SHIFT;
return true;
}
return false;
}
......@@ -229,13 +229,6 @@ static int handle_trap_exceptions(struct kvm_vcpu *vcpu, struct kvm_run *run)
handled = exit_handler(vcpu, run);
}
/*
* kvm_arm_handle_step_debug() sets the exit_reason on the kvm_run
* structure if we need to return to userspace.
*/
if (handled > 0 && kvm_arm_handle_step_debug(vcpu, run))
handled = 0;
return handled;
}
......@@ -269,12 +262,7 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
case ARM_EXCEPTION_IRQ:
return 1;
case ARM_EXCEPTION_EL1_SERROR:
/* We may still need to return for single-step */
if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS)
&& kvm_arm_handle_step_debug(vcpu, run))
return 0;
else
return 1;
return 1;
case ARM_EXCEPTION_TRAP:
return handle_trap_exceptions(vcpu, run);
case ARM_EXCEPTION_HYP_GONE:
......
......@@ -305,33 +305,6 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
return true;
}
/* Skip an instruction which has been emulated. Returns true if
* execution can continue or false if we need to exit hyp mode because
* single-step was in effect.
*/
static bool __hyp_text __skip_instr(struct kvm_vcpu *vcpu)
{
*vcpu_pc(vcpu) = read_sysreg_el2(elr);
if (vcpu_mode_is_32bit(vcpu)) {
vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(spsr);
kvm_skip_instr32(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
write_sysreg_el2(vcpu->arch.ctxt.gp_regs.regs.pstate, spsr);
} else {
*vcpu_pc(vcpu) += 4;
}
write_sysreg_el2(*vcpu_pc(vcpu), elr);
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
vcpu->arch.fault.esr_el2 =
(ESR_ELx_EC_SOFTSTP_LOW << ESR_ELx_EC_SHIFT) | 0x22;
return false;
} else {
return true;
}
}
static bool __hyp_text __hyp_switch_fpsimd(struct kvm_vcpu *vcpu)
{
struct user_fpsimd_state *host_fpsimd = vcpu->arch.host_fpsimd_state;
......@@ -420,20 +393,12 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
if (valid) {
int ret = __vgic_v2_perform_cpuif_access(vcpu);
if (ret == 1 && __skip_instr(vcpu))
if (ret == 1)
return true;
if (ret == -1) {
/* Promote an illegal access to an
* SError. If we would be returning
* due to single-step clear the SS
* bit so handle_exit knows what to
* do after dealing with the error.
*/
if (!__skip_instr(vcpu))
*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
/* Promote an illegal access to an SError.*/
if (ret == -1)
*exit_code = ARM_EXCEPTION_EL1_SERROR;
}
goto exit;
}
......@@ -444,7 +409,7 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) {
int ret = __vgic_v3_perform_cpuif_access(vcpu);
if (ret == 1 && __skip_instr(vcpu))
if (ret == 1)
return true;
}
......
......@@ -41,7 +41,7 @@ static bool __hyp_text __is_be(struct kvm_vcpu *vcpu)
* Returns:
* 1: GICV access successfully performed
* 0: Not a GICV access
* -1: Illegal GICV access
* -1: Illegal GICV access successfully performed
*/
int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
{
......@@ -61,12 +61,16 @@ int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
return 0;
/* Reject anything but a 32bit access */
if (kvm_vcpu_dabt_get_as(vcpu) != sizeof(u32))
if (kvm_vcpu_dabt_get_as(vcpu) != sizeof(u32)) {
__kvm_skip_instr(vcpu);
return -1;
}
/* Not aligned? Don't bother */
if (fault_ipa & 3)
if (fault_ipa & 3) {
__kvm_skip_instr(vcpu);
return -1;
}
rd = kvm_vcpu_dabt_get_rd(vcpu);
addr = hyp_symbol_addr(kvm_vgic_global_state)->vcpu_hyp_va;
......@@ -88,5 +92,7 @@ int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
vcpu_set_reg(vcpu, rd, data);
}
__kvm_skip_instr(vcpu);
return 1;
}
......@@ -76,7 +76,7 @@ static bool write_to_read_only(struct kvm_vcpu *vcpu,
return false;
}
u64 vcpu_read_sys_reg(struct kvm_vcpu *vcpu, int reg)
u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
{
if (!vcpu->arch.sysregs_loaded_on_cpu)
goto immediate_read;
......@@ -1850,6 +1850,8 @@ static void perform_access(struct kvm_vcpu *vcpu,
struct sys_reg_params *params,
const struct sys_reg_desc *r)
{
trace_kvm_sys_access(*vcpu_pc(vcpu), params, r);
/*
* Not having an accessor means that we have configured a trap
* that we don't know how to handle. This certainly qualifies
......@@ -1912,8 +1914,8 @@ static void unhandled_cp_access(struct kvm_vcpu *vcpu,
WARN_ON(1);
}
kvm_err("Unsupported guest CP%d access at: %08lx\n",
cp, *vcpu_pc(vcpu));
kvm_err("Unsupported guest CP%d access at: %08lx [%08lx]\n",
cp, *vcpu_pc(vcpu), *vcpu_cpsr(vcpu));
print_sys_reg_instr(params);
kvm_inject_undefined(vcpu);
}
......@@ -2063,8 +2065,8 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu,
if (likely(r)) {
perform_access(vcpu, params, r);
} else {
kvm_err("Unsupported guest sys_reg access at: %lx\n",
*vcpu_pc(vcpu));
kvm_err("Unsupported guest sys_reg access at: %lx [%08lx]\n",
*vcpu_pc(vcpu), *vcpu_cpsr(vcpu));
print_sys_reg_instr(params);
kvm_inject_undefined(vcpu);
}
......
......@@ -35,6 +35,9 @@ struct sys_reg_params {
};
struct sys_reg_desc {
/* Sysreg string for debug */
const char *name;
/* MRS/MSR instruction which accesses it. */
u8 Op0;
u8 Op1;
......@@ -130,6 +133,7 @@ const struct sys_reg_desc *find_reg_by_id(u64 id,
#define Op2(_x) .Op2 = _x
#define SYS_DESC(reg) \
.name = #reg, \
Op0(sys_reg_Op0(reg)), Op1(sys_reg_Op1(reg)), \
CRn(sys_reg_CRn(reg)), CRm(sys_reg_CRm(reg)), \
Op2(sys_reg_Op2(reg))
......
......@@ -3,6 +3,7 @@
#define _TRACE_ARM64_KVM_H
#include <linux/tracepoint.h>
#include "sys_regs.h"
#undef TRACE_SYSTEM
#define TRACE_SYSTEM kvm
......@@ -152,6 +153,40 @@ TRACE_EVENT(kvm_handle_sys_reg,
TP_printk("HSR 0x%08lx", __entry->hsr)
);
TRACE_EVENT(kvm_sys_access,
TP_PROTO(unsigned long vcpu_pc, struct sys_reg_params *params, const struct sys_reg_desc *reg),
TP_ARGS(vcpu_pc, params, reg),
TP_STRUCT__entry(
__field(unsigned long, vcpu_pc)
__field(bool, is_write)
__field(const char *, name)
__field(u8, Op0)
__field(u8, Op1)
__field(u8, CRn)
__field(u8, CRm)
__field(u8, Op2)
),
TP_fast_assign(
__entry->vcpu_pc = vcpu_pc;
__entry->is_write = params->is_write;
__entry->name = reg->name;
__entry->Op0 = reg->Op0;
__entry->Op0 = reg->Op0;
__entry->Op1 = reg->Op1;
__entry->CRn = reg->CRn;
__entry->CRm = reg->CRm;
__entry->Op2 = reg->Op2;
),
TP_printk("PC: %lx %s (%d,%d,%d,%d,%d) %s",
__entry->vcpu_pc, __entry->name ?: "UNKN",
__entry->Op0, __entry->Op1, __entry->CRn,
__entry->CRm, __entry->Op2,
__entry->is_write ? "write" : "read")
);
TRACE_EVENT(kvm_set_guest_debug,
TP_PROTO(struct kvm_vcpu *vcpu, __u32 guest_debug),
TP_ARGS(vcpu, guest_debug),
......
......@@ -21,7 +21,6 @@
#include <linux/clocksource.h>
#include <linux/hrtimer.h>
#include <linux/workqueue.h>
struct arch_timer_context {
/* Registers: control register, timer value */
......@@ -52,9 +51,6 @@ struct arch_timer_cpu {
/* Background timer used when the guest is not running */
struct hrtimer bg_timer;
/* Work queued with the above timer expires */
struct work_struct expired;
/* Physical timer emulation */
struct hrtimer phys_timer;
......
......@@ -70,11 +70,9 @@ static void soft_timer_start(struct hrtimer *hrt, u64 ns)
HRTIMER_MODE_ABS);
}
static void soft_timer_cancel(struct hrtimer *hrt, struct work_struct *work)
static void soft_timer_cancel(struct hrtimer *hrt)
{
hrtimer_cancel(hrt);
if (work)
cancel_work_sync(work);
}
static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id)
......@@ -102,23 +100,6 @@ static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id)
return IRQ_HANDLED;
}
/*
* Work function for handling the backup timer that we schedule when a vcpu is
* no longer running, but had a timer programmed to fire in the future.
*/
static void kvm_timer_inject_irq_work(struct work_struct *work)
{
struct kvm_vcpu *vcpu;
vcpu = container_of(work, struct kvm_vcpu, arch.timer_cpu.expired);
/*
* If the vcpu is blocked we want to wake it up so that it will see
* the timer has expired when entering the guest.
*/
kvm_vcpu_wake_up(vcpu);
}
static u64 kvm_timer_compute_delta(struct arch_timer_context *timer_ctx)
{
u64 cval, now;
......@@ -188,7 +169,7 @@ static enum hrtimer_restart kvm_bg_timer_expire(struct hrtimer *hrt)
return HRTIMER_RESTART;
}
schedule_work(&timer->expired);
kvm_vcpu_wake_up(vcpu);
return HRTIMER_NORESTART;
}
......@@ -300,7 +281,7 @@ static void phys_timer_emulate(struct kvm_vcpu *vcpu)
* then we also don't need a soft timer.
*/
if (kvm_timer_should_fire(ptimer) || !kvm_timer_irq_can_fire(ptimer)) {
soft_timer_cancel(&timer->phys_timer, NULL);
soft_timer_cancel(&timer->phys_timer);
return;
}
......@@ -426,7 +407,7 @@ void kvm_timer_unschedule(struct kvm_vcpu *vcpu)
vtimer_restore_state(vcpu);
soft_timer_cancel(&timer->bg_timer, &timer->expired);
soft_timer_cancel(&timer->bg_timer);
}
static void set_cntvoff(u64 cntvoff)
......@@ -544,7 +525,7 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
* In any case, we re-schedule the hrtimer for the physical timer when
* coming back to the VCPU thread in kvm_timer_vcpu_load().
*/
soft_timer_cancel(&timer->phys_timer, NULL);
soft_timer_cancel(&timer->phys_timer);
/*
* The kernel may decide to run userspace after calling vcpu_put, so
......@@ -637,7 +618,6 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
update_vtimer_cntvoff(vcpu, kvm_phys_timer_read());
vcpu_ptimer(vcpu)->cntvoff = 0;
INIT_WORK(&timer->expired, kvm_timer_inject_irq_work);
hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
timer->bg_timer.function = kvm_bg_timer_expire;
......@@ -792,11 +772,8 @@ int kvm_timer_hyp_init(bool has_gic)
void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu)
{
struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
soft_timer_cancel(&timer->bg_timer, &timer->expired);
soft_timer_cancel(&timer->phys_timer, NULL);
kvm_vgic_unmap_phys_irq(vcpu, vtimer->irq.irq);
soft_timer_cancel(&timer->bg_timer);
}
static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu)
......
......@@ -66,7 +66,7 @@ static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_arm_running_vcpu);
static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1);
static u32 kvm_next_vmid;
static unsigned int kvm_vmid_bits __read_mostly;
static DEFINE_RWLOCK(kvm_vmid_lock);
static DEFINE_SPINLOCK(kvm_vmid_lock);
static bool vgic_present;
......@@ -484,7 +484,9 @@ void force_vm_exit(const cpumask_t *mask)
*/
static bool need_new_vmid_gen(struct kvm *kvm)
{
return unlikely(kvm->arch.vmid_gen != atomic64_read(&kvm_vmid_gen));
u64 current_vmid_gen = atomic64_read(&kvm_vmid_gen);
smp_rmb(); /* Orders read of kvm_vmid_gen and kvm->arch.vmid */
return unlikely(READ_ONCE(kvm->arch.vmid_gen) != current_vmid_gen);
}
/**
......@@ -499,16 +501,11 @@ static void update_vttbr(struct kvm *kvm)
{
phys_addr_t pgd_phys;
u64 vmid, cnp = kvm_cpu_has_cnp() ? VTTBR_CNP_BIT : 0;
bool new_gen;
read_lock(&kvm_vmid_lock);
new_gen = need_new_vmid_gen(kvm);
read_unlock(&kvm_vmid_lock);
if (!new_gen)
if (!need_new_vmid_gen(kvm))
return;
write_lock(&kvm_vmid_lock);
spin_lock(&kvm_vmid_lock);
/*
* We need to re-check the vmid_gen here to ensure that if another vcpu
......@@ -516,7 +513,7 @@ static void update_vttbr(struct kvm *kvm)
* use the same vmid.
*/
if (!need_new_vmid_gen(kvm)) {
write_unlock(&kvm_vmid_lock);
spin_unlock(&kvm_vmid_lock);
return;
}
......@@ -539,7 +536,6 @@ static void update_vttbr(struct kvm *kvm)
kvm_call_hyp(__kvm_flush_vm_context);
}
kvm->arch.vmid_gen = atomic64_read(&kvm_vmid_gen);
kvm->arch.vmid = kvm_next_vmid;
kvm_next_vmid++;
kvm_next_vmid &= (1 << kvm_vmid_bits) - 1;
......@@ -550,7 +546,10 @@ static void update_vttbr(struct kvm *kvm)
vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK(kvm_vmid_bits);
kvm->arch.vttbr = kvm_phys_to_vttbr(pgd_phys) | vmid | cnp;
write_unlock(&kvm_vmid_lock);
smp_wmb();
WRITE_ONCE(kvm->arch.vmid_gen, atomic64_read(&kvm_vmid_gen));
spin_unlock(&kvm_vmid_lock);
}
static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
......@@ -674,8 +673,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
ret = kvm_handle_mmio_return(vcpu, vcpu->run);
if (ret)
return ret;
if (kvm_arm_handle_step_debug(vcpu, vcpu->run))
return 0;
}
if (run->immediate_exit)
......
......@@ -1012,8 +1012,10 @@ int __hyp_text __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu)
esr = kvm_vcpu_get_hsr(vcpu);
if (vcpu_mode_is_32bit(vcpu)) {
if (!kvm_condition_valid(vcpu))
if (!kvm_condition_valid(vcpu)) {
__kvm_skip_instr(vcpu);
return 1;
}
sysreg = esr_cp15_to_sysreg(esr);
} else {
......@@ -1123,6 +1125,8 @@ int __hyp_text __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu)
rt = kvm_vcpu_sys_get_rt(vcpu);
fn(vcpu, vmcr, rt);
__kvm_skip_instr(vcpu);
return 1;
}
......
......@@ -117,6 +117,12 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
vcpu_set_reg(vcpu, vcpu->arch.mmio_decode.rt, data);
}
/*
* The MMIO instruction is emulated and should not be re-executed
* in the guest.
*/
kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
return 0;
}
......@@ -144,11 +150,6 @@ static int decode_hsr(struct kvm_vcpu *vcpu, bool *is_write, int *len)
vcpu->arch.mmio_decode.sign_extend = sign_extend;
vcpu->arch.mmio_decode.rt = rt;
/*
* The MMIO instruction is emulated and should not be re-executed
* in the guest.
*/
kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
return 0;
}
......
......@@ -115,6 +115,25 @@ static void stage2_dissolve_pmd(struct kvm *kvm, phys_addr_t addr, pmd_t *pmd)
put_page(virt_to_page(pmd));
}
/**
* stage2_dissolve_pud() - clear and flush huge PUD entry
* @kvm: pointer to kvm structure.
* @addr: IPA
* @pud: pud pointer for IPA
*
* Function clears a PUD entry, flushes addr 1st and 2nd stage TLBs. Marks all
* pages in the range dirty.
*/
static void stage2_dissolve_pud(struct kvm *kvm, phys_addr_t addr, pud_t *pudp)
{
if (!stage2_pud_huge(kvm, *pudp))
return;
stage2_pud_clear(kvm, pudp);
kvm_tlb_flush_vmid_ipa(kvm, addr);
put_page(virt_to_page(pudp));
}
static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
int min, int max)
{
......@@ -607,7 +626,7 @@ static void create_hyp_pte_mappings(pmd_t *pmd, unsigned long start,
addr = start;
do {
pte = pte_offset_kernel(pmd, addr);
kvm_set_pte(pte, pfn_pte(pfn, prot));
kvm_set_pte(pte, kvm_pfn_pte(pfn, prot));
get_page(virt_to_page(pte));
pfn++;
} while (addr += PAGE_SIZE, addr != end);
......@@ -1022,7 +1041,7 @@ static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
pmd_t *pmd;
pud = stage2_get_pud(kvm, cache, addr);
if (!pud)
if (!pud || stage2_pud_huge(kvm, *pud))
return NULL;
if (stage2_pud_none(kvm, *pud)) {
......@@ -1083,29 +1102,103 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
return 0;
}
static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr)
static int stage2_set_pud_huge(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
phys_addr_t addr, const pud_t *new_pudp)
{
pud_t *pudp, old_pud;
pudp = stage2_get_pud(kvm, cache, addr);
VM_BUG_ON(!pudp);
old_pud = *pudp;
/*
* A large number of vcpus faulting on the same stage 2 entry,
* can lead to a refault due to the
* stage2_pud_clear()/tlb_flush(). Skip updating the page
* tables if there is no change.
*/
if (pud_val(old_pud) == pud_val(*new_pudp))
return 0;
if (stage2_pud_present(kvm, old_pud)) {
stage2_pud_clear(kvm, pudp);
kvm_tlb_flush_vmid_ipa(kvm, addr);
} else {
get_page(virt_to_page(pudp));
}
kvm_set_pud(pudp, *new_pudp);
return 0;
}
/*
* stage2_get_leaf_entry - walk the stage2 VM page tables and return
* true if a valid and present leaf-entry is found. A pointer to the
* leaf-entry is returned in the appropriate level variable - pudpp,
* pmdpp, ptepp.
*/
static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr,
pud_t **pudpp, pmd_t **pmdpp, pte_t **ptepp)
{
pud_t *pudp;
pmd_t *pmdp;
pte_t *ptep;
pmdp = stage2_get_pmd(kvm, NULL, addr);
*pudpp = NULL;
*pmdpp = NULL;
*ptepp = NULL;
pudp = stage2_get_pud(kvm, NULL, addr);
if (!pudp || stage2_pud_none(kvm, *pudp) || !stage2_pud_present(kvm, *pudp))
return false;
if (stage2_pud_huge(kvm, *pudp)) {
*pudpp = pudp;
return true;
}
pmdp = stage2_pmd_offset(kvm, pudp, addr);
if (!pmdp || pmd_none(*pmdp) || !pmd_present(*pmdp))
return false;
if (pmd_thp_or_huge(*pmdp))
return kvm_s2pmd_exec(pmdp);
if (pmd_thp_or_huge(*pmdp)) {
*pmdpp = pmdp;
return true;
}
ptep = pte_offset_kernel(pmdp, addr);
if (!ptep || pte_none(*ptep) || !pte_present(*ptep))
return false;
return kvm_s2pte_exec(ptep);
*ptepp = ptep;
return true;
}
static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr)
{
pud_t *pudp;
pmd_t *pmdp;
pte_t *ptep;
bool found;
found = stage2_get_leaf_entry(kvm, addr, &pudp, &pmdp, &ptep);
if (!found)
return false;
if (pudp)
return kvm_s2pud_exec(pudp);
else if (pmdp)
return kvm_s2pmd_exec(pmdp);
else
return kvm_s2pte_exec(ptep);
}
static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
phys_addr_t addr, const pte_t *new_pte,
unsigned long flags)
{
pud_t *pud;
pmd_t *pmd;
pte_t *pte, old_pte;
bool iomap = flags & KVM_S2PTE_FLAG_IS_IOMAP;
......@@ -1114,7 +1207,31 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
VM_BUG_ON(logging_active && !cache);
/* Create stage-2 page table mapping - Levels 0 and 1 */
pmd = stage2_get_pmd(kvm, cache, addr);
pud = stage2_get_pud(kvm, cache, addr);
if (!pud) {
/*
* Ignore calls from kvm_set_spte_hva for unallocated
* address ranges.
*/
return 0;
}
/*
* While dirty page logging - dissolve huge PUD, then continue
* on to allocate page.
*/
if (logging_active)
stage2_dissolve_pud(kvm, addr, pud);
if (stage2_pud_none(kvm, *pud)) {
if (!cache)
return 0; /* ignore calls from kvm_set_spte_hva */
pmd = mmu_memory_cache_alloc(cache);
stage2_pud_populate(kvm, pud, pmd);
get_page(virt_to_page(pud));
}
pmd = stage2_pmd_offset(kvm, pud, addr);
if (!pmd) {
/*
* Ignore calls from kvm_set_spte_hva for unallocated
......@@ -1182,6 +1299,11 @@ static int stage2_pmdp_test_and_clear_young(pmd_t *pmd)
return stage2_ptep_test_and_clear_young((pte_t *)pmd);
}
static int stage2_pudp_test_and_clear_young(pud_t *pud)
{
return stage2_ptep_test_and_clear_young((pte_t *)pud);
}
/**
* kvm_phys_addr_ioremap - map a device range to guest IPA
*
......@@ -1202,7 +1324,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
pfn = __phys_to_pfn(pa);
for (addr = guest_ipa; addr < end; addr += PAGE_SIZE) {
pte_t pte = pfn_pte(pfn, PAGE_S2_DEVICE);
pte_t pte = kvm_pfn_pte(pfn, PAGE_S2_DEVICE);
if (writable)
pte = kvm_s2pte_mkwrite(pte);
......@@ -1234,7 +1356,7 @@ static bool transparent_hugepage_adjust(kvm_pfn_t *pfnp, phys_addr_t *ipap)
struct page *page = pfn_to_page(pfn);
/*
* PageTransCompoungMap() returns true for THP and
* PageTransCompoundMap() returns true for THP and
* hugetlbfs. Make sure the adjustment is done only for THP
* pages.
*/
......@@ -1347,9 +1469,12 @@ static void stage2_wp_puds(struct kvm *kvm, pgd_t *pgd,
do {
next = stage2_pud_addr_end(kvm, addr, end);
if (!stage2_pud_none(kvm, *pud)) {
/* TODO:PUD not supported, revisit later if supported */
BUG_ON(stage2_pud_huge(kvm, *pud));
stage2_wp_pmds(kvm, pud, addr, next);
if (stage2_pud_huge(kvm, *pud)) {
if (!kvm_s2pud_readonly(pud))
kvm_set_s2pud_readonly(pud);
} else {
stage2_wp_pmds(kvm, pud, addr, next);
}
}
} while (pud++, addr = next, addr != end);
}
......@@ -1392,7 +1517,7 @@ static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
*
* Called to start logging dirty pages after memory region
* KVM_MEM_LOG_DIRTY_PAGES operation is called. After this function returns
* all present PMD and PTEs are write protected in the memory region.
* all present PUD, PMD and PTEs are write protected in the memory region.
* Afterwards read of dirty page log can be called.
*
* Acquires kvm_mmu_lock. Called with kvm->slots_lock mutex acquired,
......@@ -1470,12 +1595,70 @@ static void kvm_send_hwpoison_signal(unsigned long address,
send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb, current);
}
static bool fault_supports_stage2_pmd_mappings(struct kvm_memory_slot *memslot,
unsigned long hva)
{
gpa_t gpa_start, gpa_end;
hva_t uaddr_start, uaddr_end;
size_t size;
size = memslot->npages * PAGE_SIZE;
gpa_start = memslot->base_gfn << PAGE_SHIFT;
gpa_end = gpa_start + size;
uaddr_start = memslot->userspace_addr;
uaddr_end = uaddr_start + size;
/*
* Pages belonging to memslots that don't have the same alignment
* within a PMD for userspace and IPA cannot be mapped with stage-2
* PMD entries, because we'll end up mapping the wrong pages.
*
* Consider a layout like the following:
*
* memslot->userspace_addr:
* +-----+--------------------+--------------------+---+
* |abcde|fgh Stage-1 PMD | Stage-1 PMD tv|xyz|
* +-----+--------------------+--------------------+---+
*
* memslot->base_gfn << PAGE_SIZE:
* +---+--------------------+--------------------+-----+
* |abc|def Stage-2 PMD | Stage-2 PMD |tvxyz|
* +---+--------------------+--------------------+-----+
*
* If we create those stage-2 PMDs, we'll end up with this incorrect
* mapping:
* d -> f
* e -> g
* f -> h
*/
if ((gpa_start & ~S2_PMD_MASK) != (uaddr_start & ~S2_PMD_MASK))
return false;
/*
* Next, let's make sure we're not trying to map anything not covered
* by the memslot. This means we have to prohibit PMD size mappings
* for the beginning and end of a non-PMD aligned and non-PMD sized
* memory slot (illustrated by the head and tail parts of the
* userspace view above containing pages 'abcde' and 'xyz',
* respectively).
*
* Note that it doesn't matter if we do the check using the
* userspace_addr or the base_gfn, as both are equally aligned (per
* the check above) and equally sized.
*/
return (hva & S2_PMD_MASK) >= uaddr_start &&
(hva & S2_PMD_MASK) + S2_PMD_SIZE <= uaddr_end;
}
static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
struct kvm_memory_slot *memslot, unsigned long hva,
unsigned long fault_status)
{
int ret;
bool write_fault, exec_fault, writable, hugetlb = false, force_pte = false;
bool write_fault, writable, force_pte = false;
bool exec_fault, needs_exec;
unsigned long mmu_seq;
gfn_t gfn = fault_ipa >> PAGE_SHIFT;
struct kvm *kvm = vcpu->kvm;
......@@ -1484,7 +1667,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
kvm_pfn_t pfn;
pgprot_t mem_type = PAGE_S2;
bool logging_active = memslot_is_logging(memslot);
unsigned long flags = 0;
unsigned long vma_pagesize, flags = 0;
write_fault = kvm_is_write_fault(vcpu);
exec_fault = kvm_vcpu_trap_is_iabt(vcpu);
......@@ -1495,6 +1678,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
return -EFAULT;
}
if (!fault_supports_stage2_pmd_mappings(memslot, hva))
force_pte = true;
if (logging_active)
force_pte = true;
/* Let's check if we will get back a huge page backed by hugetlbfs */
down_read(&current->mm->mmap_sem);
vma = find_vma_intersection(current->mm, hva, hva + 1);
......@@ -1504,22 +1693,15 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
return -EFAULT;
}
if (vma_kernel_pagesize(vma) == PMD_SIZE && !logging_active) {
hugetlb = true;
gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT;
} else {
/*
* Pages belonging to memslots that don't have the same
* alignment for userspace and IPA cannot be mapped using
* block descriptors even if the pages belong to a THP for
* the process, because the stage-2 block descriptor will
* cover more than a single THP and we loose atomicity for
* unmapping, updates, and splits of the THP or other pages
* in the stage-2 block range.
*/
if ((memslot->userspace_addr & ~PMD_MASK) !=
((memslot->base_gfn << PAGE_SHIFT) & ~PMD_MASK))
force_pte = true;
vma_pagesize = vma_kernel_pagesize(vma);
/*
* PUD level may not exist for a VM but PMD is guaranteed to
* exist.
*/
if ((vma_pagesize == PMD_SIZE ||
(vma_pagesize == PUD_SIZE && kvm_stage2_has_pud(kvm))) &&
!force_pte) {
gfn = (fault_ipa & huge_page_mask(hstate_vma(vma))) >> PAGE_SHIFT;
}
up_read(&current->mm->mmap_sem);
......@@ -1558,7 +1740,6 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
* should not be mapped with huge pages (it introduces churn
* and performance degradation), so force a pte mapping.
*/
force_pte = true;
flags |= KVM_S2_FLAG_LOGGING_ACTIVE;
/*
......@@ -1573,50 +1754,69 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
if (mmu_notifier_retry(kvm, mmu_seq))
goto out_unlock;
if (!hugetlb && !force_pte)
hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa);
if (vma_pagesize == PAGE_SIZE && !force_pte) {
/*
* Only PMD_SIZE transparent hugepages(THP) are
* currently supported. This code will need to be
* updated to support other THP sizes.
*/
if (transparent_hugepage_adjust(&pfn, &fault_ipa))
vma_pagesize = PMD_SIZE;
}
if (writable)
kvm_set_pfn_dirty(pfn);
if (hugetlb) {
pmd_t new_pmd = pfn_pmd(pfn, mem_type);
new_pmd = pmd_mkhuge(new_pmd);
if (writable) {
new_pmd = kvm_s2pmd_mkwrite(new_pmd);
kvm_set_pfn_dirty(pfn);
}
if (fault_status != FSC_PERM)
clean_dcache_guest_page(pfn, vma_pagesize);
if (exec_fault)
invalidate_icache_guest_page(pfn, vma_pagesize);
if (fault_status != FSC_PERM)
clean_dcache_guest_page(pfn, PMD_SIZE);
/*
* If we took an execution fault we have made the
* icache/dcache coherent above and should now let the s2
* mapping be executable.
*
* Write faults (!exec_fault && FSC_PERM) are orthogonal to
* execute permissions, and we preserve whatever we have.
*/
needs_exec = exec_fault ||
(fault_status == FSC_PERM && stage2_is_exec(kvm, fault_ipa));
if (exec_fault) {
if (vma_pagesize == PUD_SIZE) {
pud_t new_pud = kvm_pfn_pud(pfn, mem_type);
new_pud = kvm_pud_mkhuge(new_pud);
if (writable)
new_pud = kvm_s2pud_mkwrite(new_pud);
if (needs_exec)
new_pud = kvm_s2pud_mkexec(new_pud);
ret = stage2_set_pud_huge(kvm, memcache, fault_ipa, &new_pud);
} else if (vma_pagesize == PMD_SIZE) {
pmd_t new_pmd = kvm_pfn_pmd(pfn, mem_type);
new_pmd = kvm_pmd_mkhuge(new_pmd);
if (writable)
new_pmd = kvm_s2pmd_mkwrite(new_pmd);
if (needs_exec)
new_pmd = kvm_s2pmd_mkexec(new_pmd);
invalidate_icache_guest_page(pfn, PMD_SIZE);
} else if (fault_status == FSC_PERM) {
/* Preserve execute if XN was already cleared */
if (stage2_is_exec(kvm, fault_ipa))
new_pmd = kvm_s2pmd_mkexec(new_pmd);
}
ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
} else {
pte_t new_pte = pfn_pte(pfn, mem_type);
pte_t new_pte = kvm_pfn_pte(pfn, mem_type);
if (writable) {
new_pte = kvm_s2pte_mkwrite(new_pte);
kvm_set_pfn_dirty(pfn);
mark_page_dirty(kvm, gfn);
}
if (fault_status != FSC_PERM)
clean_dcache_guest_page(pfn, PAGE_SIZE);
if (exec_fault) {
if (needs_exec)
new_pte = kvm_s2pte_mkexec(new_pte);
invalidate_icache_guest_page(pfn, PAGE_SIZE);
} else if (fault_status == FSC_PERM) {
/* Preserve execute if XN was already cleared */
if (stage2_is_exec(kvm, fault_ipa))
new_pte = kvm_s2pte_mkexec(new_pte);
}
ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, flags);
}
......@@ -1637,6 +1837,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
*/
static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
{
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
kvm_pfn_t pfn;
......@@ -1646,24 +1847,23 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
spin_lock(&vcpu->kvm->mmu_lock);
pmd = stage2_get_pmd(vcpu->kvm, NULL, fault_ipa);
if (!pmd || pmd_none(*pmd)) /* Nothing there */
if (!stage2_get_leaf_entry(vcpu->kvm, fault_ipa, &pud, &pmd, &pte))
goto out;
if (pmd_thp_or_huge(*pmd)) { /* THP, HugeTLB */
if (pud) { /* HugeTLB */
*pud = kvm_s2pud_mkyoung(*pud);
pfn = kvm_pud_pfn(*pud);
pfn_valid = true;
} else if (pmd) { /* THP, HugeTLB */
*pmd = pmd_mkyoung(*pmd);
pfn = pmd_pfn(*pmd);
pfn_valid = true;
goto out;
} else {
*pte = pte_mkyoung(*pte); /* Just a page... */
pfn = pte_pfn(*pte);
pfn_valid = true;
}
pte = pte_offset_kernel(pmd, fault_ipa);
if (pte_none(*pte)) /* Nothing there either */
goto out;
*pte = pte_mkyoung(*pte); /* Just a page... */
pfn = pte_pfn(*pte);
pfn_valid = true;
out:
spin_unlock(&vcpu->kvm->mmu_lock);
if (pfn_valid)
......@@ -1865,48 +2065,44 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
* just like a translation fault and clean the cache to the PoC.
*/
clean_dcache_guest_page(pfn, PAGE_SIZE);
stage2_pte = pfn_pte(pfn, PAGE_S2);
stage2_pte = kvm_pfn_pte(pfn, PAGE_S2);
handle_hva_to_gpa(kvm, hva, end, &kvm_set_spte_handler, &stage2_pte);
}
static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
{
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
WARN_ON(size != PAGE_SIZE && size != PMD_SIZE);
pmd = stage2_get_pmd(kvm, NULL, gpa);
if (!pmd || pmd_none(*pmd)) /* Nothing there */
WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
if (!stage2_get_leaf_entry(kvm, gpa, &pud, &pmd, &pte))
return 0;
if (pmd_thp_or_huge(*pmd)) /* THP, HugeTLB */
if (pud)
return stage2_pudp_test_and_clear_young(pud);
else if (pmd)
return stage2_pmdp_test_and_clear_young(pmd);
pte = pte_offset_kernel(pmd, gpa);
if (pte_none(*pte))
return 0;
return stage2_ptep_test_and_clear_young(pte);
else
return stage2_ptep_test_and_clear_young(pte);
}
static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
{
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
WARN_ON(size != PAGE_SIZE && size != PMD_SIZE);
pmd = stage2_get_pmd(kvm, NULL, gpa);
if (!pmd || pmd_none(*pmd)) /* Nothing there */
WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
if (!stage2_get_leaf_entry(kvm, gpa, &pud, &pmd, &pte))
return 0;
if (pmd_thp_or_huge(*pmd)) /* THP, HugeTLB */
if (pud)
return kvm_s2pud_young(*pud);
else if (pmd)
return pmd_young(*pmd);
pte = pte_offset_kernel(pmd, gpa);
if (!pte_none(*pte)) /* Just a page... */
else
return pte_young(*pte);
return 0;
}
int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
......
......@@ -26,25 +26,25 @@ TRACE_EVENT(kvm_entry,
);
TRACE_EVENT(kvm_exit,
TP_PROTO(int idx, unsigned int exit_reason, unsigned long vcpu_pc),
TP_ARGS(idx, exit_reason, vcpu_pc),
TP_PROTO(int ret, unsigned int esr_ec, unsigned long vcpu_pc),
TP_ARGS(ret, esr_ec, vcpu_pc),
TP_STRUCT__entry(
__field( int, idx )
__field( unsigned int, exit_reason )
__field( int, ret )
__field( unsigned int, esr_ec )
__field( unsigned long, vcpu_pc )
),
TP_fast_assign(
__entry->idx = idx;
__entry->exit_reason = exit_reason;
__entry->ret = ARM_EXCEPTION_CODE(ret);
__entry->esr_ec = ARM_EXCEPTION_IS_TRAP(ret) ? esr_ec : 0;
__entry->vcpu_pc = vcpu_pc;
),
TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%08lx",
__print_symbolic(__entry->idx, kvm_arm_exception_type),
__entry->exit_reason,
__print_symbolic(__entry->exit_reason, kvm_arm_exception_class),
__print_symbolic(__entry->ret, kvm_arm_exception_type),
__entry->esr_ec,
__print_symbolic(__entry->esr_ec, kvm_arm_exception_class),
__entry->vcpu_pc)
);
......
......@@ -313,36 +313,30 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
spin_lock_irqsave(&irq->irq_lock, flags);
/*
* If this virtual IRQ was written into a list register, we
* have to make sure the CPU that runs the VCPU thread has
* synced back the LR state to the struct vgic_irq.
*
* As long as the conditions below are true, we know the VCPU thread
* may be on its way back from the guest (we kicked the VCPU thread in
* vgic_change_active_prepare) and still has to sync back this IRQ,
* so we release and re-acquire the spin_lock to let the other thread
* sync back the IRQ.
*
* When accessing VGIC state from user space, requester_vcpu is
* NULL, which is fine, because we guarantee that no VCPUs are running
* when accessing VGIC state from user space so irq->vcpu->cpu is
* always -1.
*/
while (irq->vcpu && /* IRQ may have state in an LR somewhere */
irq->vcpu != requester_vcpu && /* Current thread is not the VCPU thread */
irq->vcpu->cpu != -1) /* VCPU thread is running */
cond_resched_lock(&irq->irq_lock);
if (irq->hw) {
vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu);
} else {
u32 model = vcpu->kvm->arch.vgic.vgic_model;
u8 active_source;
irq->active = active;
/*
* The GICv2 architecture indicates that the source CPUID for
* an SGI should be provided during an EOI which implies that
* the active state is stored somewhere, but at the same time
* this state is not architecturally exposed anywhere and we
* have no way of knowing the right source.
*
* This may lead to a VCPU not being able to receive
* additional instances of a particular SGI after migration
* for a GICv2 VM on some GIC implementations. Oh well.
*/
active_source = (requester_vcpu) ? requester_vcpu->vcpu_id : 0;
if (model == KVM_DEV_TYPE_ARM_VGIC_V2 &&
active && vgic_irq_is_sgi(irq->intid))
irq->active_source = requester_vcpu->vcpu_id;
irq->active_source = active_source;
}
if (irq->active)
......@@ -368,14 +362,16 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
*/
static void vgic_change_active_prepare(struct kvm_vcpu *vcpu, u32 intid)
{
if (intid > VGIC_NR_PRIVATE_IRQS)
if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 ||
intid > VGIC_NR_PRIVATE_IRQS)
kvm_arm_halt_guest(vcpu->kvm);
}
/* See vgic_change_active_prepare */
static void vgic_change_active_finish(struct kvm_vcpu *vcpu, u32 intid)
{
if (intid > VGIC_NR_PRIVATE_IRQS)
if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 ||
intid > VGIC_NR_PRIVATE_IRQS)
kvm_arm_resume_guest(vcpu->kvm);
}
......
......@@ -103,13 +103,13 @@ struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
{
/* SGIs and PPIs */
if (intid <= VGIC_MAX_PRIVATE) {
intid = array_index_nospec(intid, VGIC_MAX_PRIVATE);
intid = array_index_nospec(intid, VGIC_MAX_PRIVATE + 1);
return &vcpu->arch.vgic_cpu.private_irqs[intid];
}
/* SPIs */
if (intid <= VGIC_MAX_SPI) {
intid = array_index_nospec(intid, VGIC_MAX_SPI);
if (intid < (kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS)) {
intid = array_index_nospec(intid, kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS);
return &kvm->arch.vgic.spis[intid - VGIC_NR_PRIVATE_IRQS];
}
......@@ -908,6 +908,7 @@ int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
struct vgic_irq *irq;
bool pending = false;
unsigned long flags;
struct vgic_vmcr vmcr;
if (!vcpu->kvm->arch.vgic.enabled)
return false;
......@@ -915,11 +916,15 @@ int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
if (vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last)
return true;
vgic_get_vmcr(vcpu, &vmcr);
spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags);
list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
spin_lock(&irq->irq_lock);
pending = irq_is_pending(irq) && irq->enabled;
pending = irq_is_pending(irq) && irq->enabled &&
!irq->active &&
irq->priority < vmcr.pmr;
spin_unlock(&irq->irq_lock);
if (pending)
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment