From ea9c3652f5aec45a36b3e1c9a21ecfcc0ffd77b0 Mon Sep 17 00:00:00 2001 From: Stefano Stabellini Date: Tue, 4 Jun 2013 11:06:30 +0000 Subject: arm64/xen: use XEN_IO_PROTO_ABI_ARM on ARM64 Signed-off-by: Stefano Stabellini Acked-by: Ian Campbell --- include/xen/interface/io/protocols.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/xen/interface/io/protocols.h b/include/xen/interface/io/protocols.h index 0eafaf254fff..056744b4b05e 100644 --- a/include/xen/interface/io/protocols.h +++ b/include/xen/interface/io/protocols.h @@ -15,7 +15,7 @@ # define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_IA64 #elif defined(__powerpc64__) # define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_POWERPC64 -#elif defined(__arm__) +#elif defined(__arm__) || defined(__aarch64__) # define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_ARM #else # error arch fixup needed here -- cgit v1.2.3 From 7c8c5e6a9101ea57a1c2c9faff0917e79251a21e Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 10 Dec 2012 16:15:34 +0000 Subject: arm64: KVM: system register handling Provide 64bit system register handling, modeled after the cp15 handling for ARM. Reviewed-by: Christopher Covington Reviewed-by: Catalin Marinas Signed-off-by: Marc Zyngier --- arch/arm64/include/asm/kvm_coproc.h | 51 +++ arch/arm64/include/uapi/asm/kvm.h | 29 ++ arch/arm64/kvm/sys_regs.c | 883 ++++++++++++++++++++++++++++++++++++ arch/arm64/kvm/sys_regs.h | 138 ++++++ include/uapi/linux/kvm.h | 1 + 5 files changed, 1102 insertions(+) create mode 100644 arch/arm64/include/asm/kvm_coproc.h create mode 100644 arch/arm64/kvm/sys_regs.c create mode 100644 arch/arm64/kvm/sys_regs.h (limited to 'include') diff --git a/arch/arm64/include/asm/kvm_coproc.h b/arch/arm64/include/asm/kvm_coproc.h new file mode 100644 index 000000000000..9b4477acb554 --- /dev/null +++ b/arch/arm64/include/asm/kvm_coproc.h @@ -0,0 +1,51 @@ +/* + * Copyright (C) 2012,2013 - ARM Ltd + * Author: Marc Zyngier + * + * Derived from arch/arm/include/asm/kvm_coproc.h + * Copyright (C) 2012 Rusty Russell IBM Corporation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#ifndef __ARM64_KVM_COPROC_H__ +#define __ARM64_KVM_COPROC_H__ + +#include + +void kvm_reset_sys_regs(struct kvm_vcpu *vcpu); + +struct kvm_sys_reg_table { + const struct sys_reg_desc *table; + size_t num; +}; + +struct kvm_sys_reg_target_table { + struct kvm_sys_reg_table table64; +}; + +void kvm_register_target_sys_reg_table(unsigned int target, + struct kvm_sys_reg_target_table *table); + +int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run); + +#define kvm_coproc_table_init kvm_sys_reg_table_init +void kvm_sys_reg_table_init(void); + +struct kvm_one_reg; +int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); +int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); +int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); +unsigned long kvm_arm_num_sys_reg_descs(struct kvm_vcpu *vcpu); + +#endif /* __ARM64_KVM_COPROC_H__ */ diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 4e64570a20c9..ebac919dc0ca 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -92,6 +92,35 @@ struct kvm_sync_regs { struct kvm_arch_memory_slot { }; +/* If you need to interpret the index values, here is the key: */ +#define KVM_REG_ARM_COPROC_MASK 0x000000000FFF0000 +#define KVM_REG_ARM_COPROC_SHIFT 16 + +/* Normal registers are mapped as coprocessor 16. */ +#define KVM_REG_ARM_CORE (0x0010 << KVM_REG_ARM_COPROC_SHIFT) +#define KVM_REG_ARM_CORE_REG(name) (offsetof(struct kvm_regs, name) / sizeof(__u32)) + +/* Some registers need more space to represent values. */ +#define KVM_REG_ARM_DEMUX (0x0011 << KVM_REG_ARM_COPROC_SHIFT) +#define KVM_REG_ARM_DEMUX_ID_MASK 0x000000000000FF00 +#define KVM_REG_ARM_DEMUX_ID_SHIFT 8 +#define KVM_REG_ARM_DEMUX_ID_CCSIDR (0x00 << KVM_REG_ARM_DEMUX_ID_SHIFT) +#define KVM_REG_ARM_DEMUX_VAL_MASK 0x00000000000000FF +#define KVM_REG_ARM_DEMUX_VAL_SHIFT 0 + +/* AArch64 system registers */ +#define KVM_REG_ARM64_SYSREG (0x0013 << KVM_REG_ARM_COPROC_SHIFT) +#define KVM_REG_ARM64_SYSREG_OP0_MASK 0x000000000000c000 +#define KVM_REG_ARM64_SYSREG_OP0_SHIFT 14 +#define KVM_REG_ARM64_SYSREG_OP1_MASK 0x0000000000003800 +#define KVM_REG_ARM64_SYSREG_OP1_SHIFT 11 +#define KVM_REG_ARM64_SYSREG_CRN_MASK 0x0000000000000780 +#define KVM_REG_ARM64_SYSREG_CRN_SHIFT 7 +#define KVM_REG_ARM64_SYSREG_CRM_MASK 0x0000000000000078 +#define KVM_REG_ARM64_SYSREG_CRM_SHIFT 3 +#define KVM_REG_ARM64_SYSREG_OP2_MASK 0x0000000000000007 +#define KVM_REG_ARM64_SYSREG_OP2_SHIFT 0 + /* KVM_IRQ_LINE irq field index values */ #define KVM_ARM_IRQ_TYPE_SHIFT 24 #define KVM_ARM_IRQ_TYPE_MASK 0xff diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c new file mode 100644 index 000000000000..52fff0ae3442 --- /dev/null +++ b/arch/arm64/kvm/sys_regs.c @@ -0,0 +1,883 @@ +/* + * Copyright (C) 2012,2013 - ARM Ltd + * Author: Marc Zyngier + * + * Derived from arch/arm/kvm/coproc.c: + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Authors: Rusty Russell + * Christoffer Dall + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "sys_regs.h" + +/* + * All of this file is extremly similar to the ARM coproc.c, but the + * types are different. My gut feeling is that it should be pretty + * easy to merge, but that would be an ABI breakage -- again. VFP + * would also need to be abstracted. + */ + +/* 3 bits per cache level, as per CLIDR, but non-existent caches always 0 */ +static u32 cache_levels; + +/* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */ +#define CSSELR_MAX 12 + +/* Which cache CCSIDR represents depends on CSSELR value. */ +static u32 get_ccsidr(u32 csselr) +{ + u32 ccsidr; + + /* Make sure noone else changes CSSELR during this! */ + local_irq_disable(); + /* Put value into CSSELR */ + asm volatile("msr csselr_el1, %x0" : : "r" (csselr)); + isb(); + /* Read result out of CCSIDR */ + asm volatile("mrs %0, ccsidr_el1" : "=r" (ccsidr)); + local_irq_enable(); + + return ccsidr; +} + +static void do_dc_cisw(u32 val) +{ + asm volatile("dc cisw, %x0" : : "r" (val)); + dsb(); +} + +static void do_dc_csw(u32 val) +{ + asm volatile("dc csw, %x0" : : "r" (val)); + dsb(); +} + +/* See note at ARM ARM B1.14.4 */ +static bool access_dcsw(struct kvm_vcpu *vcpu, + const struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + unsigned long val; + int cpu; + + if (!p->is_write) + return read_from_write_only(vcpu, p); + + cpu = get_cpu(); + + cpumask_setall(&vcpu->arch.require_dcache_flush); + cpumask_clear_cpu(cpu, &vcpu->arch.require_dcache_flush); + + /* If we were already preempted, take the long way around */ + if (cpu != vcpu->arch.last_pcpu) { + flush_cache_all(); + goto done; + } + + val = *vcpu_reg(vcpu, p->Rt); + + switch (p->CRm) { + case 6: /* Upgrade DCISW to DCCISW, as per HCR.SWIO */ + case 14: /* DCCISW */ + do_dc_cisw(val); + break; + + case 10: /* DCCSW */ + do_dc_csw(val); + break; + } + +done: + put_cpu(); + + return true; +} + +/* + * We could trap ID_DFR0 and tell the guest we don't support performance + * monitoring. Unfortunately the patch to make the kernel check ID_DFR0 was + * NAKed, so it will read the PMCR anyway. + * + * Therefore we tell the guest we have 0 counters. Unfortunately, we + * must always support PMCCNTR (the cycle counter): we just RAZ/WI for + * all PM registers, which doesn't crash the guest kernel at least. + */ +static bool pm_fake(struct kvm_vcpu *vcpu, + const struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) + return ignore_write(vcpu, p); + else + return read_zero(vcpu, p); +} + +static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) +{ + u64 amair; + + asm volatile("mrs %0, amair_el1\n" : "=r" (amair)); + vcpu_sys_reg(vcpu, AMAIR_EL1) = amair; +} + +static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) +{ + /* + * Simply map the vcpu_id into the Aff0 field of the MPIDR. + */ + vcpu_sys_reg(vcpu, MPIDR_EL1) = (1UL << 31) | (vcpu->vcpu_id & 0xff); +} + +/* + * Architected system registers. + * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2 + */ +static const struct sys_reg_desc sys_reg_descs[] = { + /* DC ISW */ + { Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b0110), Op2(0b010), + access_dcsw }, + /* DC CSW */ + { Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b1010), Op2(0b010), + access_dcsw }, + /* DC CISW */ + { Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b010), + access_dcsw }, + + /* MPIDR_EL1 */ + { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0000), Op2(0b101), + NULL, reset_mpidr, MPIDR_EL1 }, + /* SCTLR_EL1 */ + { Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000), + NULL, reset_val, SCTLR_EL1, 0x00C50078 }, + /* CPACR_EL1 */ + { Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b010), + NULL, reset_val, CPACR_EL1, 0 }, + /* TTBR0_EL1 */ + { Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b000), + NULL, reset_unknown, TTBR0_EL1 }, + /* TTBR1_EL1 */ + { Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b001), + NULL, reset_unknown, TTBR1_EL1 }, + /* TCR_EL1 */ + { Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b010), + NULL, reset_val, TCR_EL1, 0 }, + + /* AFSR0_EL1 */ + { Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b000), + NULL, reset_unknown, AFSR0_EL1 }, + /* AFSR1_EL1 */ + { Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b001), + NULL, reset_unknown, AFSR1_EL1 }, + /* ESR_EL1 */ + { Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0010), Op2(0b000), + NULL, reset_unknown, ESR_EL1 }, + /* FAR_EL1 */ + { Op0(0b11), Op1(0b000), CRn(0b0110), CRm(0b0000), Op2(0b000), + NULL, reset_unknown, FAR_EL1 }, + + /* PMINTENSET_EL1 */ + { Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b001), + pm_fake }, + /* PMINTENCLR_EL1 */ + { Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b010), + pm_fake }, + + /* MAIR_EL1 */ + { Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0010), Op2(0b000), + NULL, reset_unknown, MAIR_EL1 }, + /* AMAIR_EL1 */ + { Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0011), Op2(0b000), + NULL, reset_amair_el1, AMAIR_EL1 }, + + /* VBAR_EL1 */ + { Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b0000), Op2(0b000), + NULL, reset_val, VBAR_EL1, 0 }, + /* CONTEXTIDR_EL1 */ + { Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b001), + NULL, reset_val, CONTEXTIDR_EL1, 0 }, + /* TPIDR_EL1 */ + { Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b100), + NULL, reset_unknown, TPIDR_EL1 }, + + /* CNTKCTL_EL1 */ + { Op0(0b11), Op1(0b000), CRn(0b1110), CRm(0b0001), Op2(0b000), + NULL, reset_val, CNTKCTL_EL1, 0}, + + /* CSSELR_EL1 */ + { Op0(0b11), Op1(0b010), CRn(0b0000), CRm(0b0000), Op2(0b000), + NULL, reset_unknown, CSSELR_EL1 }, + + /* PMCR_EL0 */ + { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b000), + pm_fake }, + /* PMCNTENSET_EL0 */ + { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b001), + pm_fake }, + /* PMCNTENCLR_EL0 */ + { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b010), + pm_fake }, + /* PMOVSCLR_EL0 */ + { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b011), + pm_fake }, + /* PMSWINC_EL0 */ + { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b100), + pm_fake }, + /* PMSELR_EL0 */ + { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b101), + pm_fake }, + /* PMCEID0_EL0 */ + { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b110), + pm_fake }, + /* PMCEID1_EL0 */ + { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b111), + pm_fake }, + /* PMCCNTR_EL0 */ + { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b000), + pm_fake }, + /* PMXEVTYPER_EL0 */ + { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b001), + pm_fake }, + /* PMXEVCNTR_EL0 */ + { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b010), + pm_fake }, + /* PMUSERENR_EL0 */ + { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b000), + pm_fake }, + /* PMOVSSET_EL0 */ + { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b011), + pm_fake }, + + /* TPIDR_EL0 */ + { Op0(0b11), Op1(0b011), CRn(0b1101), CRm(0b0000), Op2(0b010), + NULL, reset_unknown, TPIDR_EL0 }, + /* TPIDRRO_EL0 */ + { Op0(0b11), Op1(0b011), CRn(0b1101), CRm(0b0000), Op2(0b011), + NULL, reset_unknown, TPIDRRO_EL0 }, +}; + +/* Target specific emulation tables */ +static struct kvm_sys_reg_target_table *target_tables[KVM_ARM_NUM_TARGETS]; + +void kvm_register_target_sys_reg_table(unsigned int target, + struct kvm_sys_reg_target_table *table) +{ + target_tables[target] = table; +} + +/* Get specific register table for this target. */ +static const struct sys_reg_desc *get_target_table(unsigned target, size_t *num) +{ + struct kvm_sys_reg_target_table *table; + + table = target_tables[target]; + *num = table->table64.num; + return table->table64.table; +} + +static const struct sys_reg_desc *find_reg(const struct sys_reg_params *params, + const struct sys_reg_desc table[], + unsigned int num) +{ + unsigned int i; + + for (i = 0; i < num; i++) { + const struct sys_reg_desc *r = &table[i]; + + if (params->Op0 != r->Op0) + continue; + if (params->Op1 != r->Op1) + continue; + if (params->CRn != r->CRn) + continue; + if (params->CRm != r->CRm) + continue; + if (params->Op2 != r->Op2) + continue; + + return r; + } + return NULL; +} + +static int emulate_sys_reg(struct kvm_vcpu *vcpu, + const struct sys_reg_params *params) +{ + size_t num; + const struct sys_reg_desc *table, *r; + + table = get_target_table(vcpu->arch.target, &num); + + /* Search target-specific then generic table. */ + r = find_reg(params, table, num); + if (!r) + r = find_reg(params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); + + if (likely(r)) { + /* + * Not having an accessor means that we have + * configured a trap that we don't know how to + * handle. This certainly qualifies as a gross bug + * that should be fixed right away. + */ + BUG_ON(!r->access); + + if (likely(r->access(vcpu, params, r))) { + /* Skip instruction, since it was emulated */ + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + return 1; + } + /* If access function fails, it should complain. */ + } else { + kvm_err("Unsupported guest sys_reg access at: %lx\n", + *vcpu_pc(vcpu)); + print_sys_reg_instr(params); + } + kvm_inject_undefined(vcpu); + return 1; +} + +static void reset_sys_reg_descs(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *table, size_t num) +{ + unsigned long i; + + for (i = 0; i < num; i++) + if (table[i].reset) + table[i].reset(vcpu, &table[i]); +} + +/** + * kvm_handle_sys_reg -- handles a mrs/msr trap on a guest sys_reg access + * @vcpu: The VCPU pointer + * @run: The kvm_run struct + */ +int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + struct sys_reg_params params; + unsigned long esr = kvm_vcpu_get_hsr(vcpu); + + params.Op0 = (esr >> 20) & 3; + params.Op1 = (esr >> 14) & 0x7; + params.CRn = (esr >> 10) & 0xf; + params.CRm = (esr >> 1) & 0xf; + params.Op2 = (esr >> 17) & 0x7; + params.Rt = (esr >> 5) & 0x1f; + params.is_write = !(esr & 1); + + return emulate_sys_reg(vcpu, ¶ms); +} + +/****************************************************************************** + * Userspace API + *****************************************************************************/ + +static bool index_to_params(u64 id, struct sys_reg_params *params) +{ + switch (id & KVM_REG_SIZE_MASK) { + case KVM_REG_SIZE_U64: + /* Any unused index bits means it's not valid. */ + if (id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK + | KVM_REG_ARM_COPROC_MASK + | KVM_REG_ARM64_SYSREG_OP0_MASK + | KVM_REG_ARM64_SYSREG_OP1_MASK + | KVM_REG_ARM64_SYSREG_CRN_MASK + | KVM_REG_ARM64_SYSREG_CRM_MASK + | KVM_REG_ARM64_SYSREG_OP2_MASK)) + return false; + params->Op0 = ((id & KVM_REG_ARM64_SYSREG_OP0_MASK) + >> KVM_REG_ARM64_SYSREG_OP0_SHIFT); + params->Op1 = ((id & KVM_REG_ARM64_SYSREG_OP1_MASK) + >> KVM_REG_ARM64_SYSREG_OP1_SHIFT); + params->CRn = ((id & KVM_REG_ARM64_SYSREG_CRN_MASK) + >> KVM_REG_ARM64_SYSREG_CRN_SHIFT); + params->CRm = ((id & KVM_REG_ARM64_SYSREG_CRM_MASK) + >> KVM_REG_ARM64_SYSREG_CRM_SHIFT); + params->Op2 = ((id & KVM_REG_ARM64_SYSREG_OP2_MASK) + >> KVM_REG_ARM64_SYSREG_OP2_SHIFT); + return true; + default: + return false; + } +} + +/* Decode an index value, and find the sys_reg_desc entry. */ +static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu, + u64 id) +{ + size_t num; + const struct sys_reg_desc *table, *r; + struct sys_reg_params params; + + /* We only do sys_reg for now. */ + if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM64_SYSREG) + return NULL; + + if (!index_to_params(id, ¶ms)) + return NULL; + + table = get_target_table(vcpu->arch.target, &num); + r = find_reg(¶ms, table, num); + if (!r) + r = find_reg(¶ms, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); + + /* Not saved in the sys_reg array? */ + if (r && !r->reg) + r = NULL; + + return r; +} + +/* + * These are the invariant sys_reg registers: we let the guest see the + * host versions of these, so they're part of the guest state. + * + * A future CPU may provide a mechanism to present different values to + * the guest, or a future kvm may trap them. + */ + +#define FUNCTION_INVARIANT(reg) \ + static void get_##reg(struct kvm_vcpu *v, \ + const struct sys_reg_desc *r) \ + { \ + u64 val; \ + \ + asm volatile("mrs %0, " __stringify(reg) "\n" \ + : "=r" (val)); \ + ((struct sys_reg_desc *)r)->val = val; \ + } + +FUNCTION_INVARIANT(midr_el1) +FUNCTION_INVARIANT(ctr_el0) +FUNCTION_INVARIANT(revidr_el1) +FUNCTION_INVARIANT(id_pfr0_el1) +FUNCTION_INVARIANT(id_pfr1_el1) +FUNCTION_INVARIANT(id_dfr0_el1) +FUNCTION_INVARIANT(id_afr0_el1) +FUNCTION_INVARIANT(id_mmfr0_el1) +FUNCTION_INVARIANT(id_mmfr1_el1) +FUNCTION_INVARIANT(id_mmfr2_el1) +FUNCTION_INVARIANT(id_mmfr3_el1) +FUNCTION_INVARIANT(id_isar0_el1) +FUNCTION_INVARIANT(id_isar1_el1) +FUNCTION_INVARIANT(id_isar2_el1) +FUNCTION_INVARIANT(id_isar3_el1) +FUNCTION_INVARIANT(id_isar4_el1) +FUNCTION_INVARIANT(id_isar5_el1) +FUNCTION_INVARIANT(clidr_el1) +FUNCTION_INVARIANT(aidr_el1) + +/* ->val is filled in by kvm_sys_reg_table_init() */ +static struct sys_reg_desc invariant_sys_regs[] = { + { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0000), Op2(0b000), + NULL, get_midr_el1 }, + { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0000), Op2(0b110), + NULL, get_revidr_el1 }, + { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b000), + NULL, get_id_pfr0_el1 }, + { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b001), + NULL, get_id_pfr1_el1 }, + { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b010), + NULL, get_id_dfr0_el1 }, + { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b011), + NULL, get_id_afr0_el1 }, + { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b100), + NULL, get_id_mmfr0_el1 }, + { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b101), + NULL, get_id_mmfr1_el1 }, + { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b110), + NULL, get_id_mmfr2_el1 }, + { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b111), + NULL, get_id_mmfr3_el1 }, + { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b000), + NULL, get_id_isar0_el1 }, + { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b001), + NULL, get_id_isar1_el1 }, + { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b010), + NULL, get_id_isar2_el1 }, + { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b011), + NULL, get_id_isar3_el1 }, + { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b100), + NULL, get_id_isar4_el1 }, + { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b101), + NULL, get_id_isar5_el1 }, + { Op0(0b11), Op1(0b001), CRn(0b0000), CRm(0b0000), Op2(0b001), + NULL, get_clidr_el1 }, + { Op0(0b11), Op1(0b001), CRn(0b0000), CRm(0b0000), Op2(0b111), + NULL, get_aidr_el1 }, + { Op0(0b11), Op1(0b011), CRn(0b0000), CRm(0b0000), Op2(0b001), + NULL, get_ctr_el0 }, +}; + +static int reg_from_user(void *val, const void __user *uaddr, u64 id) +{ + /* This Just Works because we are little endian. */ + if (copy_from_user(val, uaddr, KVM_REG_SIZE(id)) != 0) + return -EFAULT; + return 0; +} + +static int reg_to_user(void __user *uaddr, const void *val, u64 id) +{ + /* This Just Works because we are little endian. */ + if (copy_to_user(uaddr, val, KVM_REG_SIZE(id)) != 0) + return -EFAULT; + return 0; +} + +static int get_invariant_sys_reg(u64 id, void __user *uaddr) +{ + struct sys_reg_params params; + const struct sys_reg_desc *r; + + if (!index_to_params(id, ¶ms)) + return -ENOENT; + + r = find_reg(¶ms, invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs)); + if (!r) + return -ENOENT; + + return reg_to_user(uaddr, &r->val, id); +} + +static int set_invariant_sys_reg(u64 id, void __user *uaddr) +{ + struct sys_reg_params params; + const struct sys_reg_desc *r; + int err; + u64 val = 0; /* Make sure high bits are 0 for 32-bit regs */ + + if (!index_to_params(id, ¶ms)) + return -ENOENT; + r = find_reg(¶ms, invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs)); + if (!r) + return -ENOENT; + + err = reg_from_user(&val, uaddr, id); + if (err) + return err; + + /* This is what we mean by invariant: you can't change it. */ + if (r->val != val) + return -EINVAL; + + return 0; +} + +static bool is_valid_cache(u32 val) +{ + u32 level, ctype; + + if (val >= CSSELR_MAX) + return -ENOENT; + + /* Bottom bit is Instruction or Data bit. Next 3 bits are level. */ + level = (val >> 1); + ctype = (cache_levels >> (level * 3)) & 7; + + switch (ctype) { + case 0: /* No cache */ + return false; + case 1: /* Instruction cache only */ + return (val & 1); + case 2: /* Data cache only */ + case 4: /* Unified cache */ + return !(val & 1); + case 3: /* Separate instruction and data caches */ + return true; + default: /* Reserved: we can't know instruction or data. */ + return false; + } +} + +static int demux_c15_get(u64 id, void __user *uaddr) +{ + u32 val; + u32 __user *uval = uaddr; + + /* Fail if we have unknown bits set. */ + if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK + | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1))) + return -ENOENT; + + switch (id & KVM_REG_ARM_DEMUX_ID_MASK) { + case KVM_REG_ARM_DEMUX_ID_CCSIDR: + if (KVM_REG_SIZE(id) != 4) + return -ENOENT; + val = (id & KVM_REG_ARM_DEMUX_VAL_MASK) + >> KVM_REG_ARM_DEMUX_VAL_SHIFT; + if (!is_valid_cache(val)) + return -ENOENT; + + return put_user(get_ccsidr(val), uval); + default: + return -ENOENT; + } +} + +static int demux_c15_set(u64 id, void __user *uaddr) +{ + u32 val, newval; + u32 __user *uval = uaddr; + + /* Fail if we have unknown bits set. */ + if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK + | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1))) + return -ENOENT; + + switch (id & KVM_REG_ARM_DEMUX_ID_MASK) { + case KVM_REG_ARM_DEMUX_ID_CCSIDR: + if (KVM_REG_SIZE(id) != 4) + return -ENOENT; + val = (id & KVM_REG_ARM_DEMUX_VAL_MASK) + >> KVM_REG_ARM_DEMUX_VAL_SHIFT; + if (!is_valid_cache(val)) + return -ENOENT; + + if (get_user(newval, uval)) + return -EFAULT; + + /* This is also invariant: you can't change it. */ + if (newval != get_ccsidr(val)) + return -EINVAL; + return 0; + default: + return -ENOENT; + } +} + +int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + const struct sys_reg_desc *r; + void __user *uaddr = (void __user *)(unsigned long)reg->addr; + + if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX) + return demux_c15_get(reg->id, uaddr); + + if (KVM_REG_SIZE(reg->id) != sizeof(__u64)) + return -ENOENT; + + r = index_to_sys_reg_desc(vcpu, reg->id); + if (!r) + return get_invariant_sys_reg(reg->id, uaddr); + + return reg_to_user(uaddr, &vcpu_sys_reg(vcpu, r->reg), reg->id); +} + +int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + const struct sys_reg_desc *r; + void __user *uaddr = (void __user *)(unsigned long)reg->addr; + + if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX) + return demux_c15_set(reg->id, uaddr); + + if (KVM_REG_SIZE(reg->id) != sizeof(__u64)) + return -ENOENT; + + r = index_to_sys_reg_desc(vcpu, reg->id); + if (!r) + return set_invariant_sys_reg(reg->id, uaddr); + + return reg_from_user(&vcpu_sys_reg(vcpu, r->reg), uaddr, reg->id); +} + +static unsigned int num_demux_regs(void) +{ + unsigned int i, count = 0; + + for (i = 0; i < CSSELR_MAX; i++) + if (is_valid_cache(i)) + count++; + + return count; +} + +static int write_demux_regids(u64 __user *uindices) +{ + u64 val = KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX; + unsigned int i; + + val |= KVM_REG_ARM_DEMUX_ID_CCSIDR; + for (i = 0; i < CSSELR_MAX; i++) { + if (!is_valid_cache(i)) + continue; + if (put_user(val | i, uindices)) + return -EFAULT; + uindices++; + } + return 0; +} + +static u64 sys_reg_to_index(const struct sys_reg_desc *reg) +{ + return (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | + KVM_REG_ARM64_SYSREG | + (reg->Op0 << KVM_REG_ARM64_SYSREG_OP0_SHIFT) | + (reg->Op1 << KVM_REG_ARM64_SYSREG_OP1_SHIFT) | + (reg->CRn << KVM_REG_ARM64_SYSREG_CRN_SHIFT) | + (reg->CRm << KVM_REG_ARM64_SYSREG_CRM_SHIFT) | + (reg->Op2 << KVM_REG_ARM64_SYSREG_OP2_SHIFT)); +} + +static bool copy_reg_to_user(const struct sys_reg_desc *reg, u64 __user **uind) +{ + if (!*uind) + return true; + + if (put_user(sys_reg_to_index(reg), *uind)) + return false; + + (*uind)++; + return true; +} + +/* Assumed ordered tables, see kvm_sys_reg_table_init. */ +static int walk_sys_regs(struct kvm_vcpu *vcpu, u64 __user *uind) +{ + const struct sys_reg_desc *i1, *i2, *end1, *end2; + unsigned int total = 0; + size_t num; + + /* We check for duplicates here, to allow arch-specific overrides. */ + i1 = get_target_table(vcpu->arch.target, &num); + end1 = i1 + num; + i2 = sys_reg_descs; + end2 = sys_reg_descs + ARRAY_SIZE(sys_reg_descs); + + BUG_ON(i1 == end1 || i2 == end2); + + /* Walk carefully, as both tables may refer to the same register. */ + while (i1 || i2) { + int cmp = cmp_sys_reg(i1, i2); + /* target-specific overrides generic entry. */ + if (cmp <= 0) { + /* Ignore registers we trap but don't save. */ + if (i1->reg) { + if (!copy_reg_to_user(i1, &uind)) + return -EFAULT; + total++; + } + } else { + /* Ignore registers we trap but don't save. */ + if (i2->reg) { + if (!copy_reg_to_user(i2, &uind)) + return -EFAULT; + total++; + } + } + + if (cmp <= 0 && ++i1 == end1) + i1 = NULL; + if (cmp >= 0 && ++i2 == end2) + i2 = NULL; + } + return total; +} + +unsigned long kvm_arm_num_sys_reg_descs(struct kvm_vcpu *vcpu) +{ + return ARRAY_SIZE(invariant_sys_regs) + + num_demux_regs() + + walk_sys_regs(vcpu, (u64 __user *)NULL); +} + +int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) +{ + unsigned int i; + int err; + + /* Then give them all the invariant registers' indices. */ + for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++) { + if (put_user(sys_reg_to_index(&invariant_sys_regs[i]), uindices)) + return -EFAULT; + uindices++; + } + + err = walk_sys_regs(vcpu, uindices); + if (err < 0) + return err; + uindices += err; + + return write_demux_regids(uindices); +} + +void kvm_sys_reg_table_init(void) +{ + unsigned int i; + struct sys_reg_desc clidr; + + /* Make sure tables are unique and in order. */ + for (i = 1; i < ARRAY_SIZE(sys_reg_descs); i++) + BUG_ON(cmp_sys_reg(&sys_reg_descs[i-1], &sys_reg_descs[i]) >= 0); + + /* We abuse the reset function to overwrite the table itself. */ + for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++) + invariant_sys_regs[i].reset(NULL, &invariant_sys_regs[i]); + + /* + * CLIDR format is awkward, so clean it up. See ARM B4.1.20: + * + * If software reads the Cache Type fields from Ctype1 + * upwards, once it has seen a value of 0b000, no caches + * exist at further-out levels of the hierarchy. So, for + * example, if Ctype3 is the first Cache Type field with a + * value of 0b000, the values of Ctype4 to Ctype7 must be + * ignored. + */ + get_clidr_el1(NULL, &clidr); /* Ugly... */ + cache_levels = clidr.val; + for (i = 0; i < 7; i++) + if (((cache_levels >> (i*3)) & 7) == 0) + break; + /* Clear all higher bits. */ + cache_levels &= (1 << (i*3))-1; +} + +/** + * kvm_reset_sys_regs - sets system registers to reset value + * @vcpu: The VCPU pointer + * + * This function finds the right table above and sets the registers on the + * virtual CPU struct to their architecturally defined reset values. + */ +void kvm_reset_sys_regs(struct kvm_vcpu *vcpu) +{ + size_t num; + const struct sys_reg_desc *table; + + /* Catch someone adding a register without putting in reset entry. */ + memset(&vcpu->arch.ctxt.sys_regs, 0x42, sizeof(vcpu->arch.ctxt.sys_regs)); + + /* Generic chip reset first (so target could override). */ + reset_sys_reg_descs(vcpu, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); + + table = get_target_table(vcpu->arch.target, &num); + reset_sys_reg_descs(vcpu, table, num); + + for (num = 1; num < NR_SYS_REGS; num++) + if (vcpu_sys_reg(vcpu, num) == 0x4242424242424242) + panic("Didn't reset vcpu_sys_reg(%zi)", num); +} diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h new file mode 100644 index 000000000000..d50d3722998e --- /dev/null +++ b/arch/arm64/kvm/sys_regs.h @@ -0,0 +1,138 @@ +/* + * Copyright (C) 2012,2013 - ARM Ltd + * Author: Marc Zyngier + * + * Derived from arch/arm/kvm/coproc.h + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Authors: Christoffer Dall + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#ifndef __ARM64_KVM_SYS_REGS_LOCAL_H__ +#define __ARM64_KVM_SYS_REGS_LOCAL_H__ + +struct sys_reg_params { + u8 Op0; + u8 Op1; + u8 CRn; + u8 CRm; + u8 Op2; + u8 Rt; + bool is_write; +}; + +struct sys_reg_desc { + /* MRS/MSR instruction which accesses it. */ + u8 Op0; + u8 Op1; + u8 CRn; + u8 CRm; + u8 Op2; + + /* Trapped access from guest, if non-NULL. */ + bool (*access)(struct kvm_vcpu *, + const struct sys_reg_params *, + const struct sys_reg_desc *); + + /* Initialization for vcpu. */ + void (*reset)(struct kvm_vcpu *, const struct sys_reg_desc *); + + /* Index into sys_reg[], or 0 if we don't need to save it. */ + int reg; + + /* Value (usually reset value) */ + u64 val; +}; + +static inline void print_sys_reg_instr(const struct sys_reg_params *p) +{ + /* Look, we even formatted it for you to paste into the table! */ + kvm_pr_unimpl(" { Op0(%2u), Op1(%2u), CRn(%2u), CRm(%2u), Op2(%2u), func_%s },\n", + p->Op0, p->Op1, p->CRn, p->CRm, p->Op2, p->is_write ? "write" : "read"); +} + +static inline bool ignore_write(struct kvm_vcpu *vcpu, + const struct sys_reg_params *p) +{ + return true; +} + +static inline bool read_zero(struct kvm_vcpu *vcpu, + const struct sys_reg_params *p) +{ + *vcpu_reg(vcpu, p->Rt) = 0; + return true; +} + +static inline bool write_to_read_only(struct kvm_vcpu *vcpu, + const struct sys_reg_params *params) +{ + kvm_debug("sys_reg write to read-only register at: %lx\n", + *vcpu_pc(vcpu)); + print_sys_reg_instr(params); + return false; +} + +static inline bool read_from_write_only(struct kvm_vcpu *vcpu, + const struct sys_reg_params *params) +{ + kvm_debug("sys_reg read to write-only register at: %lx\n", + *vcpu_pc(vcpu)); + print_sys_reg_instr(params); + return false; +} + +/* Reset functions */ +static inline void reset_unknown(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *r) +{ + BUG_ON(!r->reg); + BUG_ON(r->reg >= NR_SYS_REGS); + vcpu_sys_reg(vcpu, r->reg) = 0x1de7ec7edbadc0deULL; +} + +static inline void reset_val(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) +{ + BUG_ON(!r->reg); + BUG_ON(r->reg >= NR_SYS_REGS); + vcpu_sys_reg(vcpu, r->reg) = r->val; +} + +static inline int cmp_sys_reg(const struct sys_reg_desc *i1, + const struct sys_reg_desc *i2) +{ + BUG_ON(i1 == i2); + if (!i1) + return 1; + else if (!i2) + return -1; + if (i1->Op0 != i2->Op0) + return i1->Op0 - i2->Op0; + if (i1->Op1 != i2->Op1) + return i1->Op1 - i2->Op1; + if (i1->CRn != i2->CRn) + return i1->CRn - i2->CRn; + if (i1->CRm != i2->CRm) + return i1->CRm - i2->CRm; + return i1->Op2 - i2->Op2; +} + + +#define Op0(_x) .Op0 = _x +#define Op1(_x) .Op1 = _x +#define CRn(_x) .CRn = _x +#define CRm(_x) .CRm = _x +#define Op2(_x) .Op2 = _x + +#endif /* __ARM64_KVM_SYS_REGS_LOCAL_H__ */ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index a5c86fc34a37..2d1bcb891468 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -783,6 +783,7 @@ struct kvm_dirty_tlb { #define KVM_REG_IA64 0x3000000000000000ULL #define KVM_REG_ARM 0x4000000000000000ULL #define KVM_REG_S390 0x5000000000000000ULL +#define KVM_REG_ARM64 0x6000000000000000ULL #define KVM_REG_SIZE_SHIFT 52 #define KVM_REG_SIZE_MASK 0x00f0000000000000ULL -- cgit v1.2.3 From 0d854a60b1d7d39a37b25dd28f63cfa0df637b91 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 7 Feb 2013 10:46:46 +0000 Subject: arm64: KVM: enable initialization of a 32bit vcpu Wire the init of a 32bit vcpu by allowing 32bit modes in pstate, and providing sensible defaults out of reset state. This feature is of course conditioned by the presence of 32bit capability on the physical CPU, and is checked by the KVM_CAP_ARM_EL1_32BIT capability. Reviewed-by: Catalin Marinas Signed-off-by: Marc Zyngier --- arch/arm64/include/asm/kvm_host.h | 2 +- arch/arm64/include/uapi/asm/kvm.h | 1 + arch/arm64/kvm/guest.c | 6 ++++++ arch/arm64/kvm/reset.c | 26 +++++++++++++++++++++++++- include/uapi/linux/kvm.h | 1 + 5 files changed, 34 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 3f5830b3ca3f..644d73956864 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -34,7 +34,7 @@ #include #include -#define KVM_VCPU_MAX_FEATURES 1 +#define KVM_VCPU_MAX_FEATURES 2 /* We don't currently support large pages. */ #define KVM_HPAGE_GFN_SHIFT(x) 0 diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 5b1110c49df5..5031f4263937 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -75,6 +75,7 @@ struct kvm_regs { #define KVM_VGIC_V2_CPU_SIZE 0x2000 #define KVM_ARM_VCPU_POWER_OFF 0 /* CPU is started in OFF state */ +#define KVM_ARM_VCPU_EL1_32BIT 1 /* CPU running a 32bit VM */ struct kvm_vcpu_init { __u32 target; diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 3d7518a7ebaa..2c3ff67a8ecb 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -99,6 +99,12 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) if (off == KVM_REG_ARM_CORE_REG(regs.pstate)) { u32 mode = (*(u32 *)valp) & COMPAT_PSR_MODE_MASK; switch (mode) { + case COMPAT_PSR_MODE_USR: + case COMPAT_PSR_MODE_FIQ: + case COMPAT_PSR_MODE_IRQ: + case COMPAT_PSR_MODE_SVC: + case COMPAT_PSR_MODE_ABT: + case COMPAT_PSR_MODE_UND: case PSR_MODE_EL0t: case PSR_MODE_EL1t: case PSR_MODE_EL1h: diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 766150ac76ed..70a7816535cd 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -38,16 +38,32 @@ static const struct kvm_regs default_regs_reset = { PSR_F_BIT | PSR_D_BIT), }; +static const struct kvm_regs default_regs_reset32 = { + .regs.pstate = (COMPAT_PSR_MODE_SVC | COMPAT_PSR_A_BIT | + COMPAT_PSR_I_BIT | COMPAT_PSR_F_BIT), +}; + static const struct kvm_irq_level default_vtimer_irq = { .irq = 27, .level = 1, }; +static bool cpu_has_32bit_el1(void) +{ + u64 pfr0; + + pfr0 = read_cpuid(ID_AA64PFR0_EL1); + return !!(pfr0 & 0x20); +} + int kvm_arch_dev_ioctl_check_extension(long ext) { int r; switch (ext) { + case KVM_CAP_ARM_EL1_32BIT: + r = cpu_has_32bit_el1(); + break; default: r = 0; } @@ -70,7 +86,15 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) switch (vcpu->arch.target) { default: - cpu_reset = &default_regs_reset; + if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) { + if (!cpu_has_32bit_el1()) + return -EINVAL; + cpu_reset = &default_regs_reset32; + vcpu->arch.hcr_el2 &= ~HCR_RW; + } else { + cpu_reset = &default_regs_reset; + } + cpu_vtimer_irq = &default_vtimer_irq; break; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 2d1bcb891468..aac27640bec2 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -666,6 +666,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_IRQ_MPIC 90 #define KVM_CAP_PPC_RTAS 91 #define KVM_CAP_IRQ_XICS 92 +#define KVM_CAP_ARM_EL1_32BIT 93 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 3212b535f200c85b5a67cbfaea18431da71b5c72 Mon Sep 17 00:00:00 2001 From: Steve Capper Date: Tue, 23 Apr 2013 12:35:02 +0100 Subject: mm: hugetlb: Copy huge_pmd_share from x86 to mm. Under x86, multiple puds can be made to reference the same bank of huge pmds provided that they represent a full PUD_SIZE of shared huge memory that is aligned to a PUD_SIZE boundary. The code to share pmds does not require any architecture specific knowledge other than the fact that pmds can be indexed, thus can be beneficial to some other architectures. This patch copies the huge pmd sharing (and unsharing) logic from x86/ to mm/ and introduces a new config option to activate it: CONFIG_ARCH_WANTS_HUGE_PMD_SHARE Signed-off-by: Steve Capper Acked-by: Catalin Marinas Acked-by: Andrew Morton --- include/linux/hugetlb.h | 4 ++ mm/hugetlb.c | 122 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 126 insertions(+) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 6b4890fa57e7..981546ad231c 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -69,6 +69,10 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); int dequeue_hwpoisoned_huge_page(struct page *page); void copy_huge_page(struct page *dst, struct page *src); +#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud); +#endif + extern unsigned long hugepages_treat_as_movable; extern const unsigned long hugetlb_zero, hugetlb_infinity; extern int sysctl_hugetlb_shm_group; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f8feeeca6686..b0bfb292350e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3169,6 +3169,128 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed) hugetlb_acct_memory(h, -(chg - freed)); } +#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +static unsigned long page_table_shareable(struct vm_area_struct *svma, + struct vm_area_struct *vma, + unsigned long addr, pgoff_t idx) +{ + unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) + + svma->vm_start; + unsigned long sbase = saddr & PUD_MASK; + unsigned long s_end = sbase + PUD_SIZE; + + /* Allow segments to share if only one is marked locked */ + unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED; + unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED; + + /* + * match the virtual addresses, permission and the alignment of the + * page table page. + */ + if (pmd_index(addr) != pmd_index(saddr) || + vm_flags != svm_flags || + sbase < svma->vm_start || svma->vm_end < s_end) + return 0; + + return saddr; +} + +static int vma_shareable(struct vm_area_struct *vma, unsigned long addr) +{ + unsigned long base = addr & PUD_MASK; + unsigned long end = base + PUD_SIZE; + + /* + * check on proper vm_flags and page table alignment + */ + if (vma->vm_flags & VM_MAYSHARE && + vma->vm_start <= base && end <= vma->vm_end) + return 1; + return 0; +} + +/* + * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() + * and returns the corresponding pte. While this is not necessary for the + * !shared pmd case because we can allocate the pmd later as well, it makes the + * code much cleaner. pmd allocation is essential for the shared case because + * pud has to be populated inside the same i_mmap_mutex section - otherwise + * racing tasks could either miss the sharing (see huge_pte_offset) or select a + * bad pmd for sharing. + */ +pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) +{ + struct vm_area_struct *vma = find_vma(mm, addr); + struct address_space *mapping = vma->vm_file->f_mapping; + pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + + vma->vm_pgoff; + struct vm_area_struct *svma; + unsigned long saddr; + pte_t *spte = NULL; + pte_t *pte; + + if (!vma_shareable(vma, addr)) + return (pte_t *)pmd_alloc(mm, pud, addr); + + mutex_lock(&mapping->i_mmap_mutex); + vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { + if (svma == vma) + continue; + + saddr = page_table_shareable(svma, vma, addr, idx); + if (saddr) { + spte = huge_pte_offset(svma->vm_mm, saddr); + if (spte) { + get_page(virt_to_page(spte)); + break; + } + } + } + + if (!spte) + goto out; + + spin_lock(&mm->page_table_lock); + if (pud_none(*pud)) + pud_populate(mm, pud, + (pmd_t *)((unsigned long)spte & PAGE_MASK)); + else + put_page(virt_to_page(spte)); + spin_unlock(&mm->page_table_lock); +out: + pte = (pte_t *)pmd_alloc(mm, pud, addr); + mutex_unlock(&mapping->i_mmap_mutex); + return pte; +} + +/* + * unmap huge page backed by shared pte. + * + * Hugetlb pte page is ref counted at the time of mapping. If pte is shared + * indicated by page_count > 1, unmap is achieved by clearing pud and + * decrementing the ref count. If count == 1, the pte page is not shared. + * + * called with vma->vm_mm->page_table_lock held. + * + * returns: 1 successfully unmapped a shared pte page + * 0 the underlying pte page is not shared, or it is the last user + */ +int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) +{ + pgd_t *pgd = pgd_offset(mm, *addr); + pud_t *pud = pud_offset(pgd, *addr); + + BUG_ON(page_count(virt_to_page(ptep)) == 0); + if (page_count(virt_to_page(ptep)) == 1) + return 0; + + pud_clear(pud); + put_page(virt_to_page(ptep)); + *addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE; + return 1; +} +#endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ + #ifdef CONFIG_MEMORY_FAILURE /* Should be called in hugetlb_lock */ -- cgit v1.2.3 From dfa5e237e935bc6712c9ac2f52a5469a0df85bcf Mon Sep 17 00:00:00 2001 From: Steve Capper Date: Tue, 7 May 2013 14:46:03 +0100 Subject: mm: thp: Correct the HPAGE_PMD_ORDER check. All Transparent Huge Pages are allocated by the buddy allocator. A compile time check is in place that fails when the order of a transparent huge page is too large to be allocated by the buddy allocator. Unfortunately that compile time check passes when: HPAGE_PMD_ORDER == MAX_ORDER ( which is incorrect as the buddy allocator can only allocate memory of order strictly less than MAX_ORDER. ) This patch updates the compile time check to fail in the above case. Signed-off-by: Steve Capper Acked-by: Catalin Marinas Acked-by: Andrew Morton --- include/linux/huge_mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 528454c2caa9..26ee56c80dc7 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -123,7 +123,7 @@ extern void __split_huge_page_pmd(struct vm_area_struct *vma, } while (0) extern void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address, pmd_t *pmd); -#if HPAGE_PMD_ORDER > MAX_ORDER +#if HPAGE_PMD_ORDER >= MAX_ORDER #error "hugepages can't be allocated by the buddy allocator" #endif extern int hugepage_madvise(struct vm_area_struct *vma, -- cgit v1.2.3