diff options
Diffstat (limited to '')
106 files changed, 1930 insertions, 1757 deletions
diff --git a/arch/alpha/include/asm/elf.h b/arch/alpha/include/asm/elf.h index 4d7c46f50382..50c82187e60e 100644 --- a/arch/alpha/include/asm/elf.h +++ b/arch/alpha/include/asm/elf.h @@ -74,7 +74,7 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG]; /* * This is used to ensure we don't load something for the wrong architecture. */ -#define elf_check_arch(x) ((x)->e_machine == EM_ALPHA) +#define elf_check_arch(x) (((x)->e_machine == EM_ALPHA) && !((x)->e_flags & EF_ALPHA_32BIT)) /* * These are used to set parameters in the core dumps. @@ -137,10 +137,6 @@ extern int dump_elf_task(elf_greg_t *dest, struct task_struct *task); : amask (AMASK_CIX) ? "ev6" : "ev67"); \ }) -#define SET_PERSONALITY(EX) \ - set_personality(((EX).e_flags & EF_ALPHA_32BIT) \ - ? PER_LINUX_32BIT : PER_LINUX) - extern int alpha_l1i_cacheshape; extern int alpha_l1d_cacheshape; extern int alpha_l2_cacheshape; diff --git a/arch/alpha/include/asm/hwrpb.h b/arch/alpha/include/asm/hwrpb.h index fc76f36265ad..db831cf8de10 100644 --- a/arch/alpha/include/asm/hwrpb.h +++ b/arch/alpha/include/asm/hwrpb.h @@ -135,7 +135,7 @@ struct crb_struct { /* virtual->physical map */ unsigned long map_entries; unsigned long map_pages; - struct vf_map_struct map[1]; + struct vf_map_struct map[]; }; struct memclust_struct { diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h index 635f0a5f5bbd..02e8817a8921 100644 --- a/arch/alpha/include/asm/pgtable.h +++ b/arch/alpha/include/asm/pgtable.h @@ -360,7 +360,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) extern void paging_init(void); -/* We have our own get_unmapped_area to cope with ADDR_LIMIT_32BIT. */ +/* We have our own get_unmapped_area */ #define HAVE_ARCH_UNMAPPED_AREA #endif /* _ALPHA_PGTABLE_H */ diff --git a/arch/alpha/include/asm/processor.h b/arch/alpha/include/asm/processor.h index 55bb1c09fd39..5dce5518a211 100644 --- a/arch/alpha/include/asm/processor.h +++ b/arch/alpha/include/asm/processor.h @@ -8,23 +8,19 @@ #ifndef __ASM_ALPHA_PROCESSOR_H #define __ASM_ALPHA_PROCESSOR_H -#include <linux/personality.h> /* for ADDR_LIMIT_32BIT */ - /* * We have a 42-bit user address space: 4TB user VM... */ #define TASK_SIZE (0x40000000000UL) -#define STACK_TOP \ - (current->personality & ADDR_LIMIT_32BIT ? 0x80000000 : 0x00120000000UL) +#define STACK_TOP (0x00120000000UL) #define STACK_TOP_MAX 0x00120000000UL /* This decides where the kernel will search for a free chunk of vm * space during mmap's. */ -#define TASK_UNMAPPED_BASE \ - ((current->personality & ADDR_LIMIT_32BIT) ? 0x40000000 : TASK_SIZE / 2) +#define TASK_UNMAPPED_BASE (TASK_SIZE / 2) /* This is dead. Everything has been moved to thread_info. */ struct thread_struct { }; diff --git a/arch/alpha/include/uapi/asm/ptrace.h b/arch/alpha/include/uapi/asm/ptrace.h index 5ca45934fcbb..72ed913a910f 100644 --- a/arch/alpha/include/uapi/asm/ptrace.h +++ b/arch/alpha/include/uapi/asm/ptrace.h @@ -42,6 +42,8 @@ struct pt_regs { unsigned long trap_a0; unsigned long trap_a1; unsigned long trap_a2; +/* This makes the stack 16-byte aligned as GCC expects */ + unsigned long __pad0; /* These are saved by PAL-code: */ unsigned long ps; unsigned long pc; diff --git a/arch/alpha/kernel/asm-offsets.c b/arch/alpha/kernel/asm-offsets.c index 4cfeae42c79a..e9dad60b147f 100644 --- a/arch/alpha/kernel/asm-offsets.c +++ b/arch/alpha/kernel/asm-offsets.c @@ -19,9 +19,13 @@ static void __used foo(void) DEFINE(TI_STATUS, offsetof(struct thread_info, status)); BLANK(); + DEFINE(SP_OFF, offsetof(struct pt_regs, ps)); DEFINE(SIZEOF_PT_REGS, sizeof(struct pt_regs)); BLANK(); + DEFINE(SWITCH_STACK_SIZE, sizeof(struct switch_stack)); + BLANK(); + DEFINE(HAE_CACHE, offsetof(struct alpha_machine_vector, hae_cache)); DEFINE(HAE_REG, offsetof(struct alpha_machine_vector, hae_register)); } diff --git a/arch/alpha/kernel/entry.S b/arch/alpha/kernel/entry.S index dd26062d75b3..f4d41b4538c2 100644 --- a/arch/alpha/kernel/entry.S +++ b/arch/alpha/kernel/entry.S @@ -15,10 +15,6 @@ .set noat .cfi_sections .debug_frame -/* Stack offsets. */ -#define SP_OFF 184 -#define SWITCH_STACK_SIZE 64 - .macro CFI_START_OSF_FRAME func .align 4 .globl \func @@ -198,8 +194,8 @@ CFI_END_OSF_FRAME entArith CFI_START_OSF_FRAME entMM SAVE_ALL /* save $9 - $15 so the inline exception code can manipulate them. */ - subq $sp, 56, $sp - .cfi_adjust_cfa_offset 56 + subq $sp, 64, $sp + .cfi_adjust_cfa_offset 64 stq $9, 0($sp) stq $10, 8($sp) stq $11, 16($sp) @@ -214,7 +210,7 @@ CFI_START_OSF_FRAME entMM .cfi_rel_offset $13, 32 .cfi_rel_offset $14, 40 .cfi_rel_offset $15, 48 - addq $sp, 56, $19 + addq $sp, 64, $19 /* handle the fault */ lda $8, 0x3fff bic $sp, $8, $8 @@ -227,7 +223,7 @@ CFI_START_OSF_FRAME entMM ldq $13, 32($sp) ldq $14, 40($sp) ldq $15, 48($sp) - addq $sp, 56, $sp + addq $sp, 64, $sp .cfi_restore $9 .cfi_restore $10 .cfi_restore $11 @@ -235,7 +231,7 @@ CFI_START_OSF_FRAME entMM .cfi_restore $13 .cfi_restore $14 .cfi_restore $15 - .cfi_adjust_cfa_offset -56 + .cfi_adjust_cfa_offset -64 /* finish up the syscall as normal. */ br ret_from_sys_call CFI_END_OSF_FRAME entMM @@ -382,8 +378,8 @@ entUnaUser: .cfi_restore $0 .cfi_adjust_cfa_offset -256 SAVE_ALL /* setup normal kernel stack */ - lda $sp, -56($sp) - .cfi_adjust_cfa_offset 56 + lda $sp, -64($sp) + .cfi_adjust_cfa_offset 64 stq $9, 0($sp) stq $10, 8($sp) stq $11, 16($sp) @@ -399,7 +395,7 @@ entUnaUser: .cfi_rel_offset $14, 40 .cfi_rel_offset $15, 48 lda $8, 0x3fff - addq $sp, 56, $19 + addq $sp, 64, $19 bic $sp, $8, $8 jsr $26, do_entUnaUser ldq $9, 0($sp) @@ -409,7 +405,7 @@ entUnaUser: ldq $13, 32($sp) ldq $14, 40($sp) ldq $15, 48($sp) - lda $sp, 56($sp) + lda $sp, 64($sp) .cfi_restore $9 .cfi_restore $10 .cfi_restore $11 @@ -417,7 +413,7 @@ entUnaUser: .cfi_restore $13 .cfi_restore $14 .cfi_restore $15 - .cfi_adjust_cfa_offset -56 + .cfi_adjust_cfa_offset -64 br ret_from_sys_call CFI_END_OSF_FRAME entUna diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 86185021f75a..a08e8edef1a4 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -1210,8 +1210,7 @@ SYSCALL_DEFINE1(old_adjtimex, struct timex32 __user *, txc_p) return ret; } -/* Get an address range which is currently unmapped. Similar to the - generic version except that we know how to honor ADDR_LIMIT_32BIT. */ +/* Get an address range which is currently unmapped. */ static unsigned long arch_get_unmapped_area_1(unsigned long addr, unsigned long len, @@ -1230,13 +1229,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { - unsigned long limit; - - /* "32 bit" actually means 31 bit, since pointers sign extend. */ - if (current->personality & ADDR_LIMIT_32BIT) - limit = 0x80000000; - else - limit = TASK_SIZE; + unsigned long limit = TASK_SIZE; if (len > limit) return -ENOMEM; diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c index 681f56089d9c..dc91de50f906 100644 --- a/arch/alpha/kernel/pci_iommu.c +++ b/arch/alpha/kernel/pci_iommu.c @@ -13,6 +13,7 @@ #include <linux/log2.h> #include <linux/dma-map-ops.h> #include <linux/iommu-helper.h> +#include <linux/string_choices.h> #include <asm/io.h> #include <asm/hwrpb.h> @@ -212,7 +213,7 @@ static int pci_dac_dma_supported(struct pci_dev *dev, u64 mask) /* If both conditions above are met, we are fine. */ DBGA("pci_dac_dma_supported %s from %ps\n", - ok ? "yes" : "no", __builtin_return_address(0)); + str_yes_no(ok), __builtin_return_address(0)); return ok; } diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index a9a38c80c4a7..7004397937cf 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -649,7 +649,7 @@ s_reg_to_mem (unsigned long s_reg) static int unauser_reg_offsets[32] = { R(r0), R(r1), R(r2), R(r3), R(r4), R(r5), R(r6), R(r7), R(r8), /* r9 ... r15 are stored in front of regs. */ - -56, -48, -40, -32, -24, -16, -8, + -64, -56, -48, -40, -32, -24, -16, /* padding at -8 */ R(r16), R(r17), R(r18), R(r19), R(r20), R(r21), R(r22), R(r23), R(r24), R(r25), R(r26), R(r27), R(r28), R(gp), diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index 8c9850437e67..a9816bbc9f34 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -78,8 +78,8 @@ __load_new_mm_context(struct mm_struct *next_mm) /* Macro for exception fixup code to access integer registers. */ #define dpf_reg(r) \ - (((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-16 : \ - (r) <= 18 ? (r)+10 : (r)-10]) + (((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-17 : \ + (r) <= 18 ? (r)+11 : (r)-10]) asmlinkage void do_page_fault(unsigned long address, unsigned long mmcsr, diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index fcdd0ed3eca8..940343beb3d4 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -225,7 +225,6 @@ config ARM64 select HAVE_FUNCTION_ERROR_INJECTION select HAVE_FUNCTION_GRAPH_FREGS select HAVE_FUNCTION_GRAPH_TRACER - select HAVE_FUNCTION_GRAPH_RETVAL select HAVE_GCC_PLUGINS select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && \ HW_PERF_EVENTS && HAVE_PERF_EVENTS_NMI diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 358c68565bfd..2b25d671365f 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -48,7 +48,11 @@ KBUILD_CFLAGS += $(CC_FLAGS_NO_FPU) \ KBUILD_CFLAGS += $(call cc-disable-warning, psabi) KBUILD_AFLAGS += $(compat_vdso) +ifeq ($(call test-ge, $(CONFIG_RUSTC_VERSION), 108500),y) +KBUILD_RUSTFLAGS += --target=aarch64-unknown-none-softfloat +else KBUILD_RUSTFLAGS += --target=aarch64-unknown-none -Ctarget-feature="-neon" +endif KBUILD_CFLAGS += $(call cc-option,-mabi=lp64) KBUILD_AFLAGS += $(call cc-option,-mabi=lp64) diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 47f2cf408eed..78ec1ef2cfe8 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -605,48 +605,6 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu) __cpacr_to_cptr_set(clr, set));\ } while (0) -static __always_inline void kvm_write_cptr_el2(u64 val) -{ - if (has_vhe() || has_hvhe()) - write_sysreg(val, cpacr_el1); - else - write_sysreg(val, cptr_el2); -} - -/* Resets the value of cptr_el2 when returning to the host. */ -static __always_inline void __kvm_reset_cptr_el2(struct kvm *kvm) -{ - u64 val; - - if (has_vhe()) { - val = (CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN); - if (cpus_have_final_cap(ARM64_SME)) - val |= CPACR_EL1_SMEN_EL1EN; - } else if (has_hvhe()) { - val = CPACR_EL1_FPEN; - - if (!kvm_has_sve(kvm) || !guest_owns_fp_regs()) - val |= CPACR_EL1_ZEN; - if (cpus_have_final_cap(ARM64_SME)) - val |= CPACR_EL1_SMEN; - } else { - val = CPTR_NVHE_EL2_RES1; - - if (kvm_has_sve(kvm) && guest_owns_fp_regs()) - val |= CPTR_EL2_TZ; - if (!cpus_have_final_cap(ARM64_SME)) - val |= CPTR_EL2_TSM; - } - - kvm_write_cptr_el2(val); -} - -#ifdef __KVM_NVHE_HYPERVISOR__ -#define kvm_reset_cptr_el2(v) __kvm_reset_cptr_el2(kern_hyp_va((v)->kvm)) -#else -#define kvm_reset_cptr_el2(v) __kvm_reset_cptr_el2((v)->kvm) -#endif - /* * Returns a 'sanitised' view of CPTR_EL2, translating from nVHE to the VHE * format if E2H isn't set. diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 7cfa024de4e3..3a7ec98ef123 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -100,7 +100,7 @@ static inline void push_hyp_memcache(struct kvm_hyp_memcache *mc, static inline void *pop_hyp_memcache(struct kvm_hyp_memcache *mc, void *(*to_va)(phys_addr_t phys)) { - phys_addr_t *p = to_va(mc->head); + phys_addr_t *p = to_va(mc->head & PAGE_MASK); if (!mc->nr_pages) return NULL; @@ -615,8 +615,6 @@ struct cpu_sve_state { struct kvm_host_data { #define KVM_HOST_DATA_FLAG_HAS_SPE 0 #define KVM_HOST_DATA_FLAG_HAS_TRBE 1 -#define KVM_HOST_DATA_FLAG_HOST_SVE_ENABLED 2 -#define KVM_HOST_DATA_FLAG_HOST_SME_ENABLED 3 #define KVM_HOST_DATA_FLAG_TRBE_ENABLED 4 #define KVM_HOST_DATA_FLAG_EL1_TRACING_CONFIGURED 5 unsigned long flags; @@ -624,23 +622,13 @@ struct kvm_host_data { struct kvm_cpu_context host_ctxt; /* - * All pointers in this union are hyp VA. + * Hyp VA. * sve_state is only used in pKVM and if system_supports_sve(). */ - union { - struct user_fpsimd_state *fpsimd_state; - struct cpu_sve_state *sve_state; - }; - - union { - /* HYP VA pointer to the host storage for FPMR */ - u64 *fpmr_ptr; - /* - * Used by pKVM only, as it needs to provide storage - * for the host - */ - u64 fpmr; - }; + struct cpu_sve_state *sve_state; + + /* Used by pKVM only. */ + u64 fpmr; /* Ownership of the FP regs */ enum { diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c index d9c9218fa1fd..309942b06c5b 100644 --- a/arch/arm64/kernel/cacheinfo.c +++ b/arch/arm64/kernel/cacheinfo.c @@ -101,16 +101,18 @@ int populate_cache_leaves(unsigned int cpu) unsigned int level, idx; enum cache_type type; struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); - struct cacheinfo *this_leaf = this_cpu_ci->info_list; + struct cacheinfo *infos = this_cpu_ci->info_list; for (idx = 0, level = 1; level <= this_cpu_ci->num_levels && - idx < this_cpu_ci->num_leaves; idx++, level++) { + idx < this_cpu_ci->num_leaves; level++) { type = get_cache_type(level); if (type == CACHE_TYPE_SEPARATE) { - ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level); - ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level); + if (idx + 1 >= this_cpu_ci->num_leaves) + break; + ci_leaf_init(&infos[idx++], CACHE_TYPE_DATA, level); + ci_leaf_init(&infos[idx++], CACHE_TYPE_INST, level); } else { - ci_leaf_init(this_leaf++, type, level); + ci_leaf_init(&infos[idx++], type, level); } } return 0; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 4eb7c6698ae4..d561cf3b8ac7 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -3091,6 +3091,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR0_EL1, TS, FLAGM, CAP_HWCAP, KERNEL_HWCAP_FLAGM), HWCAP_CAP(ID_AA64ISAR0_EL1, TS, FLAGM2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2), HWCAP_CAP(ID_AA64ISAR0_EL1, RNDR, IMP, CAP_HWCAP, KERNEL_HWCAP_RNG), + HWCAP_CAP(ID_AA64ISAR3_EL1, FPRCVT, IMP, CAP_HWCAP, KERNEL_HWCAP_FPRCVT), HWCAP_CAP(ID_AA64PFR0_EL1, FP, IMP, CAP_HWCAP, KERNEL_HWCAP_FP), HWCAP_CAP(ID_AA64PFR0_EL1, FP, FP16, CAP_HWCAP, KERNEL_HWCAP_FPHP), HWCAP_CAP(ID_AA64PFR0_EL1, AdvSIMD, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMD), @@ -3180,8 +3181,6 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA), HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4), HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2), - HWCAP_CAP(ID_AA64SMFR0_EL1, SF8MM8, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8MM8), - HWCAP_CAP(ID_AA64SMFR0_EL1, SF8MM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8MM4), HWCAP_CAP(ID_AA64SMFR0_EL1, SBitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SBITPERM), HWCAP_CAP(ID_AA64SMFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_AES), HWCAP_CAP(ID_AA64SMFR0_EL1, SFEXPA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SFEXPA), @@ -3192,6 +3191,8 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64FPFR0_EL1, F8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_F8FMA), HWCAP_CAP(ID_AA64FPFR0_EL1, F8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_F8DP4), HWCAP_CAP(ID_AA64FPFR0_EL1, F8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8DP2), + HWCAP_CAP(ID_AA64FPFR0_EL1, F8MM8, IMP, CAP_HWCAP, KERNEL_HWCAP_F8MM8), + HWCAP_CAP(ID_AA64FPFR0_EL1, F8MM4, IMP, CAP_HWCAP, KERNEL_HWCAP_F8MM4), HWCAP_CAP(ID_AA64FPFR0_EL1, F8E4M3, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E4M3), HWCAP_CAP(ID_AA64FPFR0_EL1, F8E5M2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E5M2), #ifdef CONFIG_ARM64_POE diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 2b601d88762d..8370d55f0353 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1695,31 +1695,6 @@ void fpsimd_signal_preserve_current_state(void) } /* - * Called by KVM when entering the guest. - */ -void fpsimd_kvm_prepare(void) -{ - if (!system_supports_sve()) - return; - - /* - * KVM does not save host SVE state since we can only enter - * the guest from a syscall so the ABI means that only the - * non-saved SVE state needs to be saved. If we have left - * SVE enabled for performance reasons then update the task - * state to be FPSIMD only. - */ - get_cpu_fpsimd_context(); - - if (test_and_clear_thread_flag(TIF_SVE)) { - sve_to_fpsimd(current); - current->thread.fp_type = FP_STATE_FPSIMD; - } - - put_cpu_fpsimd_context(); -} - -/* * Associate current's FPSIMD context with this cpu * The caller must have ownership of the cpu FPSIMD context before calling * this function. diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 1a2c72f3e7f8..cb180684d10d 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -194,12 +194,19 @@ static void amu_fie_setup(const struct cpumask *cpus) int cpu; /* We are already set since the last insmod of cpufreq driver */ - if (unlikely(cpumask_subset(cpus, amu_fie_cpus))) + if (cpumask_available(amu_fie_cpus) && + unlikely(cpumask_subset(cpus, amu_fie_cpus))) return; - for_each_cpu(cpu, cpus) { + for_each_cpu(cpu, cpus) if (!freq_counters_valid(cpu)) return; + + if (!cpumask_available(amu_fie_cpus) && + !zalloc_cpumask_var(&amu_fie_cpus, GFP_KERNEL)) { + WARN_ONCE(1, "Failed to allocate FIE cpumask for CPUs[%*pbl]\n", + cpumask_pr_args(cpus)); + return; } cpumask_or(amu_fie_cpus, amu_fie_cpus, cpus); @@ -237,17 +244,8 @@ static struct notifier_block init_amu_fie_notifier = { static int __init init_amu_fie(void) { - int ret; - - if (!zalloc_cpumask_var(&amu_fie_cpus, GFP_KERNEL)) - return -ENOMEM; - - ret = cpufreq_register_notifier(&init_amu_fie_notifier, + return cpufreq_register_notifier(&init_amu_fie_notifier, CPUFREQ_POLICY_NOTIFIER); - if (ret) - free_cpumask_var(amu_fie_cpus); - - return ret; } core_initcall(init_amu_fie); diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S index 4ec32e86a8da..47ad6944f9f0 100644 --- a/arch/arm64/kernel/vdso/vdso.lds.S +++ b/arch/arm64/kernel/vdso/vdso.lds.S @@ -41,6 +41,7 @@ SECTIONS */ /DISCARD/ : { *(.note.GNU-stack .note.gnu.property) + *(.ARM.attributes) } .note : { *(.note.*) } :text :note diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index f84c71f04d9e..e73326bd3ff7 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -162,6 +162,7 @@ SECTIONS /DISCARD/ : { *(.interp .dynamic) *(.dynsym .dynstr .hash .gnu.hash) + *(.ARM.attributes) } . = KIMAGE_VADDR; diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index d3d243366536..70802e4c91cf 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -447,21 +447,19 @@ static void kvm_timer_update_status(struct arch_timer_context *ctx, bool level) static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level, struct arch_timer_context *timer_ctx) { - int ret; - kvm_timer_update_status(timer_ctx, new_level); timer_ctx->irq.level = new_level; trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_irq(timer_ctx), timer_ctx->irq.level); - if (!userspace_irqchip(vcpu->kvm)) { - ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu, - timer_irq(timer_ctx), - timer_ctx->irq.level, - timer_ctx); - WARN_ON(ret); - } + if (userspace_irqchip(vcpu->kvm)) + return; + + kvm_vgic_inject_irq(vcpu->kvm, vcpu, + timer_irq(timer_ctx), + timer_ctx->irq.level, + timer_ctx); } /* Only called for a fully emulated timer */ @@ -471,10 +469,8 @@ static void timer_emulate(struct arch_timer_context *ctx) trace_kvm_timer_emulate(ctx, should_fire); - if (should_fire != ctx->irq.level) { + if (should_fire != ctx->irq.level) kvm_timer_update_irq(ctx->vcpu, should_fire, ctx); - return; - } kvm_timer_update_status(ctx, should_fire); @@ -761,21 +757,6 @@ static void kvm_timer_vcpu_load_nested_switch(struct kvm_vcpu *vcpu, timer_irq(map->direct_ptimer), &arch_timer_irq_ops); WARN_ON_ONCE(ret); - - /* - * The virtual offset behaviour is "interesting", as it - * always applies when HCR_EL2.E2H==0, but only when - * accessed from EL1 when HCR_EL2.E2H==1. So make sure we - * track E2H when putting the HV timer in "direct" mode. - */ - if (map->direct_vtimer == vcpu_hvtimer(vcpu)) { - struct arch_timer_offset *offs = &map->direct_vtimer->offset; - - if (vcpu_el2_e2h_is_set(vcpu)) - offs->vcpu_offset = NULL; - else - offs->vcpu_offset = &__vcpu_sys_reg(vcpu, CNTVOFF_EL2); - } } } @@ -976,31 +957,21 @@ void kvm_timer_sync_nested(struct kvm_vcpu *vcpu) * which allows trapping of the timer registers even with NV2. * Still, this is still worse than FEAT_NV on its own. Meh. */ - if (!vcpu_el2_e2h_is_set(vcpu)) { - if (cpus_have_final_cap(ARM64_HAS_ECV)) - return; - - /* - * A non-VHE guest hypervisor doesn't have any direct access - * to its timers: the EL2 registers trap (and the HW is - * fully emulated), while the EL0 registers access memory - * despite the access being notionally direct. Boo. - * - * We update the hardware timer registers with the - * latest value written by the guest to the VNCR page - * and let the hardware take care of the rest. - */ - write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTV_CTL_EL0), SYS_CNTV_CTL); - write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTV_CVAL_EL0), SYS_CNTV_CVAL); - write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTP_CTL_EL0), SYS_CNTP_CTL); - write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTP_CVAL_EL0), SYS_CNTP_CVAL); - } else { + if (!cpus_have_final_cap(ARM64_HAS_ECV)) { /* * For a VHE guest hypervisor, the EL2 state is directly - * stored in the host EL1 timers, while the emulated EL0 + * stored in the host EL1 timers, while the emulated EL1 * state is stored in the VNCR page. The latter could have * been updated behind our back, and we must reset the * emulation of the timers. + * + * A non-VHE guest hypervisor doesn't have any direct access + * to its timers: the EL2 registers trap despite being + * notionally direct (we use the EL1 HW, as for VHE), while + * the EL1 registers access memory. + * + * In both cases, process the emulated timers on each guest + * exit. Boo. */ struct timer_map map; get_timer_map(vcpu, &map); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 646e806c6ca6..b8e55a441282 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -2290,6 +2290,19 @@ static int __init init_subsystems(void) break; case -ENODEV: case -ENXIO: + /* + * No VGIC? No pKVM for you. + * + * Protected mode assumes that VGICv3 is present, so no point + * in trying to hobble along if vgic initialization fails. + */ + if (is_protected_kvm_enabled()) + goto out; + + /* + * Otherwise, userspace could choose to implement a GIC for its + * guest on non-cooperative hardware. + */ vgic_present = false; err = 0; break; @@ -2400,6 +2413,13 @@ static void kvm_hyp_init_symbols(void) kvm_nvhe_sym(id_aa64smfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64SMFR0_EL1); kvm_nvhe_sym(__icache_flags) = __icache_flags; kvm_nvhe_sym(kvm_arm_vmid_bits) = kvm_arm_vmid_bits; + + /* + * Flush entire BSS since part of its data containing init symbols is read + * while the MMU is off. + */ + kvm_flush_dcache_to_poc(kvm_ksym_ref(__hyp_bss_start), + kvm_ksym_ref(__hyp_bss_end) - kvm_ksym_ref(__hyp_bss_start)); } static int __init kvm_hyp_init_protection(u32 hyp_va_bits) @@ -2461,14 +2481,6 @@ static void finalize_init_hyp_mode(void) per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state = kern_hyp_va(sve_state); } - } else { - for_each_possible_cpu(cpu) { - struct user_fpsimd_state *fpsimd_state; - - fpsimd_state = &per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->host_ctxt.fp_regs; - per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->fpsimd_state = - kern_hyp_va(fpsimd_state); - } } } diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 4d3d1a2eb157..7f6e43d25691 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -54,50 +54,18 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) if (!system_supports_fpsimd()) return; - fpsimd_kvm_prepare(); - /* - * We will check TIF_FOREIGN_FPSTATE just before entering the - * guest in kvm_arch_vcpu_ctxflush_fp() and override this to - * FP_STATE_FREE if the flag set. + * Ensure that any host FPSIMD/SVE/SME state is saved and unbound such + * that the host kernel is responsible for restoring this state upon + * return to userspace, and the hyp code doesn't need to save anything. + * + * When the host may use SME, fpsimd_save_and_flush_cpu_state() ensures + * that PSTATE.{SM,ZA} == {0,0}. */ - *host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED; - *host_data_ptr(fpsimd_state) = kern_hyp_va(¤t->thread.uw.fpsimd_state); - *host_data_ptr(fpmr_ptr) = kern_hyp_va(¤t->thread.uw.fpmr); - - host_data_clear_flag(HOST_SVE_ENABLED); - if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) - host_data_set_flag(HOST_SVE_ENABLED); - - if (system_supports_sme()) { - host_data_clear_flag(HOST_SME_ENABLED); - if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN) - host_data_set_flag(HOST_SME_ENABLED); - - /* - * If PSTATE.SM is enabled then save any pending FP - * state and disable PSTATE.SM. If we leave PSTATE.SM - * enabled and the guest does not enable SME via - * CPACR_EL1.SMEN then operations that should be valid - * may generate SME traps from EL1 to EL1 which we - * can't intercept and which would confuse the guest. - * - * Do the same for PSTATE.ZA in the case where there - * is state in the registers which has not already - * been saved, this is very unlikely to happen. - */ - if (read_sysreg_s(SYS_SVCR) & (SVCR_SM_MASK | SVCR_ZA_MASK)) { - *host_data_ptr(fp_owner) = FP_STATE_FREE; - fpsimd_save_and_flush_cpu_state(); - } - } + fpsimd_save_and_flush_cpu_state(); + *host_data_ptr(fp_owner) = FP_STATE_FREE; - /* - * If normal guests gain SME support, maintain this behavior for pKVM - * guests, which don't support SME. - */ - WARN_ON(is_protected_kvm_enabled() && system_supports_sme() && - read_sysreg_s(SYS_SVCR)); + WARN_ON_ONCE(system_supports_sme() && read_sysreg_s(SYS_SVCR)); } /* @@ -162,52 +130,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) local_irq_save(flags); - /* - * If we have VHE then the Hyp code will reset CPACR_EL1 to - * the default value and we need to reenable SME. - */ - if (has_vhe() && system_supports_sme()) { - /* Also restore EL0 state seen on entry */ - if (host_data_test_flag(HOST_SME_ENABLED)) - sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_SMEN); - else - sysreg_clear_set(CPACR_EL1, - CPACR_EL1_SMEN_EL0EN, - CPACR_EL1_SMEN_EL1EN); - isb(); - } - if (guest_owns_fp_regs()) { - if (vcpu_has_sve(vcpu)) { - u64 zcr = read_sysreg_el1(SYS_ZCR); - - /* - * If the vCPU is in the hyp context then ZCR_EL1 is - * loaded with its vEL2 counterpart. - */ - __vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr; - - /* - * Restore the VL that was saved when bound to the CPU, - * which is the maximum VL for the guest. Because the - * layout of the data when saving the sve state depends - * on the VL, we need to use a consistent (i.e., the - * maximum) VL. - * Note that this means that at guest exit ZCR_EL1 is - * not necessarily the same as on guest entry. - * - * ZCR_EL2 holds the guest hypervisor's VL when running - * a nested guest, which could be smaller than the - * max for the vCPU. Similar to above, we first need to - * switch to a VL consistent with the layout of the - * vCPU's SVE state. KVM support for NV implies VHE, so - * using the ZCR_EL1 alias is safe. - */ - if (!has_vhe() || (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))) - sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, - SYS_ZCR_EL1); - } - /* * Flush (save and invalidate) the fpsimd/sve state so that if * the host tries to use fpsimd/sve, it's not using stale data @@ -219,18 +142,6 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) * when needed. */ fpsimd_save_and_flush_cpu_state(); - } else if (has_vhe() && system_supports_sve()) { - /* - * The FPSIMD/SVE state in the CPU has not been touched, and we - * have SVE (and VHE): CPACR_EL1 (alias CPTR_EL2) has been - * reset by kvm_reset_cptr_el2() in the Hyp code, disabling SVE - * for EL0. To avoid spurious traps, restore the trap state - * seen by kvm_arch_vcpu_load_fp(): - */ - if (host_data_test_flag(HOST_SVE_ENABLED)) - sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_ZEN_EL0EN); - else - sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0); } local_irq_restore(flags); diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index 4433a234aa9b..9f4e8d68ab50 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -44,6 +44,11 @@ alternative_if ARM64_HAS_RAS_EXTN alternative_else_nop_endif mrs x1, isr_el1 cbz x1, 1f + + // Ensure that __guest_enter() always provides a context + // synchronization event so that callers don't need ISBs for anything + // that would usually be synchonized by the ERET. + isb mov x0, #ARM_EXCEPTION_IRQ ret diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index f838a45665f2..23bbe28eaaf9 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -326,7 +326,7 @@ static inline bool __populate_fault_info(struct kvm_vcpu *vcpu) return __get_fault_info(vcpu->arch.fault.esr_el2, &vcpu->arch.fault); } -static bool kvm_hyp_handle_mops(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_mops(struct kvm_vcpu *vcpu, u64 *exit_code) { *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); arm64_mops_reset_regs(vcpu_gp_regs(vcpu), vcpu->arch.fault.esr_el2); @@ -375,7 +375,87 @@ static inline void __hyp_sve_save_host(void) true); } -static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu); +static inline void fpsimd_lazy_switch_to_guest(struct kvm_vcpu *vcpu) +{ + u64 zcr_el1, zcr_el2; + + if (!guest_owns_fp_regs()) + return; + + if (vcpu_has_sve(vcpu)) { + /* A guest hypervisor may restrict the effective max VL. */ + if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) + zcr_el2 = __vcpu_sys_reg(vcpu, ZCR_EL2); + else + zcr_el2 = vcpu_sve_max_vq(vcpu) - 1; + + write_sysreg_el2(zcr_el2, SYS_ZCR); + + zcr_el1 = __vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)); + write_sysreg_el1(zcr_el1, SYS_ZCR); + } +} + +static inline void fpsimd_lazy_switch_to_host(struct kvm_vcpu *vcpu) +{ + u64 zcr_el1, zcr_el2; + + if (!guest_owns_fp_regs()) + return; + + /* + * When the guest owns the FP regs, we know that guest+hyp traps for + * any FPSIMD/SVE/SME features exposed to the guest have been disabled + * by either fpsimd_lazy_switch_to_guest() or kvm_hyp_handle_fpsimd() + * prior to __guest_entry(). As __guest_entry() guarantees a context + * synchronization event, we don't need an ISB here to avoid taking + * traps for anything that was exposed to the guest. + */ + if (vcpu_has_sve(vcpu)) { + zcr_el1 = read_sysreg_el1(SYS_ZCR); + __vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr_el1; + + /* + * The guest's state is always saved using the guest's max VL. + * Ensure that the host has the guest's max VL active such that + * the host can save the guest's state lazily, but don't + * artificially restrict the host to the guest's max VL. + */ + if (has_vhe()) { + zcr_el2 = vcpu_sve_max_vq(vcpu) - 1; + write_sysreg_el2(zcr_el2, SYS_ZCR); + } else { + zcr_el2 = sve_vq_from_vl(kvm_host_sve_max_vl) - 1; + write_sysreg_el2(zcr_el2, SYS_ZCR); + + zcr_el1 = vcpu_sve_max_vq(vcpu) - 1; + write_sysreg_el1(zcr_el1, SYS_ZCR); + } + } +} + +static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu) +{ + /* + * Non-protected kvm relies on the host restoring its sve state. + * Protected kvm restores the host's sve state as not to reveal that + * fpsimd was used by a guest nor leak upper sve bits. + */ + if (system_supports_sve()) { + __hyp_sve_save_host(); + + /* Re-enable SVE traps if not supported for the guest vcpu. */ + if (!vcpu_has_sve(vcpu)) + cpacr_clear_set(CPACR_EL1_ZEN, 0); + + } else { + __fpsimd_save_state(host_data_ptr(host_ctxt.fp_regs)); + } + + if (kvm_has_fpmr(kern_hyp_va(vcpu->kvm))) + *host_data_ptr(fpmr) = read_sysreg_s(SYS_FPMR); +} + /* * We trap the first access to the FP/SIMD to save the host context and @@ -383,7 +463,7 @@ static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu); * If FP/SIMD is not implemented, handle the trap and inject an undefined * instruction exception to the guest. Similarly for trapped SVE accesses. */ -static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) { bool sve_guest; u8 esr_ec; @@ -425,7 +505,7 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) isb(); /* Write out the host state if it's in the registers */ - if (host_owns_fp_regs()) + if (is_protected_kvm_enabled() && host_owns_fp_regs()) kvm_hyp_save_fpsimd_host(vcpu); /* Restore the guest state */ @@ -501,9 +581,22 @@ static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu) return true; } +/* Open-coded version of timer_get_offset() to allow for kern_hyp_va() */ +static inline u64 hyp_timer_get_offset(struct arch_timer_context *ctxt) +{ + u64 offset = 0; + + if (ctxt->offset.vm_offset) + offset += *kern_hyp_va(ctxt->offset.vm_offset); + if (ctxt->offset.vcpu_offset) + offset += *kern_hyp_va(ctxt->offset.vcpu_offset); + + return offset; +} + static inline u64 compute_counter_value(struct arch_timer_context *ctxt) { - return arch_timer_read_cntpct_el0() - timer_get_offset(ctxt); + return arch_timer_read_cntpct_el0() - hyp_timer_get_offset(ctxt); } static bool kvm_handle_cntxct(struct kvm_vcpu *vcpu) @@ -587,7 +680,7 @@ static bool handle_ampere1_tcr(struct kvm_vcpu *vcpu) return true; } -static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) { if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) && handle_tx2_tvm(vcpu)) @@ -607,7 +700,7 @@ static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) return false; } -static bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code) { if (static_branch_unlikely(&vgic_v3_cpuif_trap) && __vgic_v3_perform_cpuif_access(vcpu) == 1) @@ -616,19 +709,18 @@ static bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code) return false; } -static bool kvm_hyp_handle_memory_fault(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_memory_fault(struct kvm_vcpu *vcpu, + u64 *exit_code) { if (!__populate_fault_info(vcpu)) return true; return false; } -static bool kvm_hyp_handle_iabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) - __alias(kvm_hyp_handle_memory_fault); -static bool kvm_hyp_handle_watchpt_low(struct kvm_vcpu *vcpu, u64 *exit_code) - __alias(kvm_hyp_handle_memory_fault); +#define kvm_hyp_handle_iabt_low kvm_hyp_handle_memory_fault +#define kvm_hyp_handle_watchpt_low kvm_hyp_handle_memory_fault -static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) { if (kvm_hyp_handle_memory_fault(vcpu, exit_code)) return true; @@ -658,23 +750,16 @@ static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) typedef bool (*exit_handler_fn)(struct kvm_vcpu *, u64 *); -static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu); - -static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code); - /* * Allow the hypervisor to handle the exit with an exit handler if it has one. * * Returns true if the hypervisor handled the exit, and control should go back * to the guest, or false if it hasn't. */ -static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code, + const exit_handler_fn *handlers) { - const exit_handler_fn *handlers = kvm_get_exit_handler_array(vcpu); - exit_handler_fn fn; - - fn = handlers[kvm_vcpu_trap_get_class(vcpu)]; - + exit_handler_fn fn = handlers[kvm_vcpu_trap_get_class(vcpu)]; if (fn) return fn(vcpu, exit_code); @@ -704,20 +789,9 @@ static inline void synchronize_vcpu_pstate(struct kvm_vcpu *vcpu, u64 *exit_code * the guest, false when we should restore the host state and return to the * main run loop. */ -static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool __fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code, + const exit_handler_fn *handlers) { - /* - * Save PSTATE early so that we can evaluate the vcpu mode - * early on. - */ - synchronize_vcpu_pstate(vcpu, exit_code); - - /* - * Check whether we want to repaint the state one way or - * another. - */ - early_exit_filter(vcpu, exit_code); - if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR); @@ -747,7 +821,7 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) goto exit; /* Check if there's an exit handler and allow it to handle the exit. */ - if (kvm_hyp_handle_exit(vcpu, exit_code)) + if (kvm_hyp_handle_exit(vcpu, exit_code, handlers)) goto guest; exit: /* Return to the host kernel and handle the exit */ diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 5c134520e180..2c37680d954c 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -5,6 +5,7 @@ */ #include <hyp/adjust_pc.h> +#include <hyp/switch.h> #include <asm/pgtable-types.h> #include <asm/kvm_asm.h> @@ -83,7 +84,7 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu) if (system_supports_sve()) __hyp_sve_restore_host(); else - __fpsimd_restore_state(*host_data_ptr(fpsimd_state)); + __fpsimd_restore_state(host_data_ptr(host_ctxt.fp_regs)); if (has_fpmr) write_sysreg_s(*host_data_ptr(fpmr), SYS_FPMR); @@ -91,11 +92,34 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu) *host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED; } +static void flush_debug_state(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu; + + hyp_vcpu->vcpu.arch.debug_owner = host_vcpu->arch.debug_owner; + + if (kvm_guest_owns_debug_regs(&hyp_vcpu->vcpu)) + hyp_vcpu->vcpu.arch.vcpu_debug_state = host_vcpu->arch.vcpu_debug_state; + else if (kvm_host_owns_debug_regs(&hyp_vcpu->vcpu)) + hyp_vcpu->vcpu.arch.external_debug_state = host_vcpu->arch.external_debug_state; +} + +static void sync_debug_state(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu; + + if (kvm_guest_owns_debug_regs(&hyp_vcpu->vcpu)) + host_vcpu->arch.vcpu_debug_state = hyp_vcpu->vcpu.arch.vcpu_debug_state; + else if (kvm_host_owns_debug_regs(&hyp_vcpu->vcpu)) + host_vcpu->arch.external_debug_state = hyp_vcpu->vcpu.arch.external_debug_state; +} + static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu) { struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu; fpsimd_sve_flush(); + flush_debug_state(hyp_vcpu); hyp_vcpu->vcpu.arch.ctxt = host_vcpu->arch.ctxt; @@ -123,6 +147,7 @@ static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu) unsigned int i; fpsimd_sve_sync(&hyp_vcpu->vcpu); + sync_debug_state(hyp_vcpu); host_vcpu->arch.ctxt = hyp_vcpu->vcpu.arch.ctxt; @@ -200,8 +225,12 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt) sync_hyp_vcpu(hyp_vcpu); } else { + struct kvm_vcpu *vcpu = kern_hyp_va(host_vcpu); + /* The host is fully trusted, run its vCPU directly. */ - ret = __kvm_vcpu_run(kern_hyp_va(host_vcpu)); + fpsimd_lazy_switch_to_guest(vcpu); + ret = __kvm_vcpu_run(vcpu); + fpsimd_lazy_switch_to_host(vcpu); } out: cpu_reg(host_ctxt, 1) = ret; @@ -651,12 +680,6 @@ void handle_trap(struct kvm_cpu_context *host_ctxt) case ESR_ELx_EC_SMC64: handle_host_smc(host_ctxt); break; - case ESR_ELx_EC_SVE: - cpacr_clear_set(0, CPACR_EL1_ZEN); - isb(); - sve_cond_update_zcr_vq(sve_vq_from_vl(kvm_host_sve_max_vl) - 1, - SYS_ZCR_EL2); - break; case ESR_ELx_EC_IABT_LOW: case ESR_ELx_EC_DABT_LOW: handle_host_mem_abort(host_ctxt); diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 7ad7b133b81a..19c3c631708c 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -943,10 +943,10 @@ static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ip ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level); if (ret) return ret; - if (level != KVM_PGTABLE_LAST_LEVEL) - return -E2BIG; if (!kvm_pte_valid(pte)) return -ENOENT; + if (level != KVM_PGTABLE_LAST_LEVEL) + return -E2BIG; state = guest_get_page_state(pte, ipa); if (state != PKVM_PAGE_SHARED_BORROWED) @@ -998,63 +998,73 @@ unlock: return ret; } -int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot) +static void assert_host_shared_guest(struct pkvm_hyp_vm *vm, u64 ipa) { - struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); - u64 ipa = hyp_pfn_to_phys(gfn); u64 phys; int ret; - if (prot & ~KVM_PGTABLE_PROT_RWX) - return -EINVAL; + if (!IS_ENABLED(CONFIG_NVHE_EL2_DEBUG)) + return; host_lock_component(); guest_lock_component(vm); ret = __check_host_shared_guest(vm, &phys, ipa); - if (!ret) - ret = kvm_pgtable_stage2_relax_perms(&vm->pgt, ipa, prot, 0); guest_unlock_component(vm); host_unlock_component(); - return ret; + WARN_ON(ret && ret != -ENOENT); } -int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *vm) +int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot) { + struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); u64 ipa = hyp_pfn_to_phys(gfn); - u64 phys; int ret; - host_lock_component(); - guest_lock_component(vm); + if (pkvm_hyp_vm_is_protected(vm)) + return -EPERM; - ret = __check_host_shared_guest(vm, &phys, ipa); - if (!ret) - ret = kvm_pgtable_stage2_wrprotect(&vm->pgt, ipa, PAGE_SIZE); + if (prot & ~KVM_PGTABLE_PROT_RWX) + return -EINVAL; + assert_host_shared_guest(vm, ipa); + guest_lock_component(vm); + ret = kvm_pgtable_stage2_relax_perms(&vm->pgt, ipa, prot, 0); guest_unlock_component(vm); - host_unlock_component(); return ret; } -int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm) +int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *vm) { u64 ipa = hyp_pfn_to_phys(gfn); - u64 phys; int ret; - host_lock_component(); + if (pkvm_hyp_vm_is_protected(vm)) + return -EPERM; + + assert_host_shared_guest(vm, ipa); guest_lock_component(vm); + ret = kvm_pgtable_stage2_wrprotect(&vm->pgt, ipa, PAGE_SIZE); + guest_unlock_component(vm); - ret = __check_host_shared_guest(vm, &phys, ipa); - if (!ret) - ret = kvm_pgtable_stage2_test_clear_young(&vm->pgt, ipa, PAGE_SIZE, mkold); + return ret; +} + +int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm) +{ + u64 ipa = hyp_pfn_to_phys(gfn); + int ret; + + if (pkvm_hyp_vm_is_protected(vm)) + return -EPERM; + assert_host_shared_guest(vm, ipa); + guest_lock_component(vm); + ret = kvm_pgtable_stage2_test_clear_young(&vm->pgt, ipa, PAGE_SIZE, mkold); guest_unlock_component(vm); - host_unlock_component(); return ret; } @@ -1063,18 +1073,14 @@ int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu) { struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); u64 ipa = hyp_pfn_to_phys(gfn); - u64 phys; - int ret; - - host_lock_component(); - guest_lock_component(vm); - ret = __check_host_shared_guest(vm, &phys, ipa); - if (!ret) - kvm_pgtable_stage2_mkyoung(&vm->pgt, ipa, 0); + if (pkvm_hyp_vm_is_protected(vm)) + return -EPERM; + assert_host_shared_guest(vm, ipa); + guest_lock_component(vm); + kvm_pgtable_stage2_mkyoung(&vm->pgt, ipa, 0); guest_unlock_component(vm); - host_unlock_component(); - return ret; + return 0; } diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 6c846d033d24..7d2ba6ef0261 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -39,6 +39,9 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu) { u64 val = CPTR_EL2_TAM; /* Same bit irrespective of E2H */ + if (!guest_owns_fp_regs()) + __activate_traps_fpsimd32(vcpu); + if (has_hvhe()) { val |= CPACR_EL1_TTA; @@ -47,6 +50,8 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu) if (vcpu_has_sve(vcpu)) val |= CPACR_EL1_ZEN; } + + write_sysreg(val, cpacr_el1); } else { val |= CPTR_EL2_TTA | CPTR_NVHE_EL2_RES1; @@ -61,12 +66,32 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu) if (!guest_owns_fp_regs()) val |= CPTR_EL2_TFP; + + write_sysreg(val, cptr_el2); } +} - if (!guest_owns_fp_regs()) - __activate_traps_fpsimd32(vcpu); +static void __deactivate_cptr_traps(struct kvm_vcpu *vcpu) +{ + if (has_hvhe()) { + u64 val = CPACR_EL1_FPEN; + + if (cpus_have_final_cap(ARM64_SVE)) + val |= CPACR_EL1_ZEN; + if (cpus_have_final_cap(ARM64_SME)) + val |= CPACR_EL1_SMEN; - kvm_write_cptr_el2(val); + write_sysreg(val, cpacr_el1); + } else { + u64 val = CPTR_NVHE_EL2_RES1; + + if (!cpus_have_final_cap(ARM64_SVE)) + val |= CPTR_EL2_TZ; + if (!cpus_have_final_cap(ARM64_SME)) + val |= CPTR_EL2_TSM; + + write_sysreg(val, cptr_el2); + } } static void __activate_traps(struct kvm_vcpu *vcpu) @@ -119,7 +144,7 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2); - kvm_reset_cptr_el2(vcpu); + __deactivate_cptr_traps(vcpu); write_sysreg(__kvm_hyp_host_vector, vbar_el2); } @@ -192,34 +217,6 @@ static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code) kvm_handle_pvm_sysreg(vcpu, exit_code)); } -static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu) -{ - /* - * Non-protected kvm relies on the host restoring its sve state. - * Protected kvm restores the host's sve state as not to reveal that - * fpsimd was used by a guest nor leak upper sve bits. - */ - if (unlikely(is_protected_kvm_enabled() && system_supports_sve())) { - __hyp_sve_save_host(); - - /* Re-enable SVE traps if not supported for the guest vcpu. */ - if (!vcpu_has_sve(vcpu)) - cpacr_clear_set(CPACR_EL1_ZEN, 0); - - } else { - __fpsimd_save_state(*host_data_ptr(fpsimd_state)); - } - - if (kvm_has_fpmr(kern_hyp_va(vcpu->kvm))) { - u64 val = read_sysreg_s(SYS_FPMR); - - if (unlikely(is_protected_kvm_enabled())) - *host_data_ptr(fpmr) = val; - else - **host_data_ptr(fpmr_ptr) = val; - } -} - static const exit_handler_fn hyp_exit_handlers[] = { [0 ... ESR_ELx_EC_MAX] = NULL, [ESR_ELx_EC_CP15_32] = kvm_hyp_handle_cp15_32, @@ -251,19 +248,21 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu) return hyp_exit_handlers; } -/* - * Some guests (e.g., protected VMs) are not be allowed to run in AArch32. - * The ARMv8 architecture does not give the hypervisor a mechanism to prevent a - * guest from dropping to AArch32 EL0 if implemented by the CPU. If the - * hypervisor spots a guest in such a state ensure it is handled, and don't - * trust the host to spot or fix it. The check below is based on the one in - * kvm_arch_vcpu_ioctl_run(). - * - * Returns false if the guest ran in AArch32 when it shouldn't have, and - * thus should exit to the host, or true if a the guest run loop can continue. - */ -static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) { + const exit_handler_fn *handlers = kvm_get_exit_handler_array(vcpu); + + synchronize_vcpu_pstate(vcpu, exit_code); + + /* + * Some guests (e.g., protected VMs) are not be allowed to run in + * AArch32. The ARMv8 architecture does not give the hypervisor a + * mechanism to prevent a guest from dropping to AArch32 EL0 if + * implemented by the CPU. If the hypervisor spots a guest in such a + * state ensure it is handled, and don't trust the host to spot or fix + * it. The check below is based on the one in + * kvm_arch_vcpu_ioctl_run(). + */ if (unlikely(vcpu_is_protected(vcpu) && vcpu_mode_is_32bit(vcpu))) { /* * As we have caught the guest red-handed, decide that it isn't @@ -276,6 +275,8 @@ static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) *exit_code &= BIT(ARM_EXIT_WITH_SERROR_BIT); *exit_code |= ARM_EXCEPTION_IL; } + + return __fixup_guest_exit(vcpu, exit_code, handlers); } /* Switch to the guest for legacy non-VHE systems */ diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index b5b9dbaf1fdd..647737d6e8d0 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -136,6 +136,16 @@ write: write_sysreg(val, cpacr_el1); } +static void __deactivate_cptr_traps(struct kvm_vcpu *vcpu) +{ + u64 val = CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN; + + if (cpus_have_final_cap(ARM64_SME)) + val |= CPACR_EL1_SMEN_EL1EN; + + write_sysreg(val, cpacr_el1); +} + static void __activate_traps(struct kvm_vcpu *vcpu) { u64 val; @@ -207,7 +217,7 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) */ asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT)); - kvm_reset_cptr_el2(vcpu); + __deactivate_cptr_traps(vcpu); if (!arm64_kernel_unmapped_at_el0()) host_vectors = __this_cpu_read(this_cpu_vector); @@ -413,14 +423,6 @@ static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code) return true; } -static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu) -{ - __fpsimd_save_state(*host_data_ptr(fpsimd_state)); - - if (kvm_has_fpmr(vcpu->kvm)) - **host_data_ptr(fpmr_ptr) = read_sysreg_s(SYS_FPMR); -} - static bool kvm_hyp_handle_tlbi_el2(struct kvm_vcpu *vcpu, u64 *exit_code) { int ret = -EINVAL; @@ -538,13 +540,10 @@ static const exit_handler_fn hyp_exit_handlers[] = { [ESR_ELx_EC_MOPS] = kvm_hyp_handle_mops, }; -static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu) +static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) { - return hyp_exit_handlers; -} + synchronize_vcpu_pstate(vcpu, exit_code); -static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) -{ /* * If we were in HYP context on entry, adjust the PSTATE view * so that the usual helpers work correctly. @@ -564,6 +563,8 @@ static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) *vcpu_cpsr(vcpu) &= ~(PSR_MODE_MASK | PSR_MODE32_BIT); *vcpu_cpsr(vcpu) |= mode; } + + return __fixup_guest_exit(vcpu, exit_code, hyp_exit_handlers); } /* Switch to the guest for VHE systems running in EL2 */ @@ -578,6 +579,8 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) sysreg_save_host_state_vhe(host_ctxt); + fpsimd_lazy_switch_to_guest(vcpu); + /* * Note that ARM erratum 1165522 requires us to configure both stage 1 * and stage 2 translation for the guest context before we clear @@ -602,6 +605,8 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) __deactivate_traps(vcpu); + fpsimd_lazy_switch_to_host(vcpu); + sysreg_restore_host_state_vhe(host_ctxt); if (guest_owns_fp_regs()) diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index 33d2ace68665..0c9387d2f507 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -67,26 +67,27 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu) if (!tmp) return -ENOMEM; + swap(kvm->arch.nested_mmus, tmp); + /* * If we went through a realocation, adjust the MMU back-pointers in * the previously initialised kvm_pgtable structures. */ if (kvm->arch.nested_mmus != tmp) for (int i = 0; i < kvm->arch.nested_mmus_size; i++) - tmp[i].pgt->mmu = &tmp[i]; + kvm->arch.nested_mmus[i].pgt->mmu = &kvm->arch.nested_mmus[i]; for (int i = kvm->arch.nested_mmus_size; !ret && i < num_mmus; i++) - ret = init_nested_s2_mmu(kvm, &tmp[i]); + ret = init_nested_s2_mmu(kvm, &kvm->arch.nested_mmus[i]); if (ret) { for (int i = kvm->arch.nested_mmus_size; i < num_mmus; i++) - kvm_free_stage2_pgd(&tmp[i]); + kvm_free_stage2_pgd(&kvm->arch.nested_mmus[i]); return ret; } kvm->arch.nested_mmus_size = num_mmus; - kvm->arch.nested_mmus = tmp; return 0; } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index f6cd1ea7fb55..82430c1e1dd0 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1452,6 +1452,16 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu, return true; } +static bool access_hv_timer(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (!vcpu_el2_e2h_is_set(vcpu)) + return undef_access(vcpu, p, r); + + return access_arch_timer(vcpu, p, r); +} + static s64 kvm_arm64_ftr_safe_value(u32 id, const struct arm64_ftr_bits *ftrp, s64 new, s64 cur) { @@ -3103,9 +3113,9 @@ static const struct sys_reg_desc sys_reg_descs[] = { EL2_REG(CNTHP_CTL_EL2, access_arch_timer, reset_val, 0), EL2_REG(CNTHP_CVAL_EL2, access_arch_timer, reset_val, 0), - { SYS_DESC(SYS_CNTHV_TVAL_EL2), access_arch_timer }, - EL2_REG(CNTHV_CTL_EL2, access_arch_timer, reset_val, 0), - EL2_REG(CNTHV_CVAL_EL2, access_arch_timer, reset_val, 0), + { SYS_DESC(SYS_CNTHV_TVAL_EL2), access_hv_timer }, + EL2_REG(CNTHV_CTL_EL2, access_hv_timer, reset_val, 0), + EL2_REG(CNTHV_CVAL_EL2, access_hv_timer, reset_val, 0), { SYS_DESC(SYS_CNTKCTL_EL12), access_cntkctl_el12 }, diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index bc7e22ab5d81..775461cf2d2d 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -34,9 +34,9 @@ * * CPU Interface: * - * - kvm_vgic_vcpu_init(): initialization of static data that - * doesn't depend on any sizing information or emulation type. No - * allocation is allowed there. + * - kvm_vgic_vcpu_init(): initialization of static data that doesn't depend + * on any sizing information. Private interrupts are allocated if not + * already allocated at vgic-creation time. */ /* EARLY INIT */ @@ -58,6 +58,8 @@ void kvm_vgic_early_init(struct kvm *kvm) /* CREATION */ +static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type); + /** * kvm_vgic_create: triggered by the instantiation of the VGIC device by * user space, either through the legacy KVM_CREATE_IRQCHIP ioctl (v2 only) @@ -112,6 +114,22 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) goto out_unlock; } + kvm_for_each_vcpu(i, vcpu, kvm) { + ret = vgic_allocate_private_irqs_locked(vcpu, type); + if (ret) + break; + } + + if (ret) { + kvm_for_each_vcpu(i, vcpu, kvm) { + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + kfree(vgic_cpu->private_irqs); + vgic_cpu->private_irqs = NULL; + } + + goto out_unlock; + } + kvm->arch.vgic.in_kernel = true; kvm->arch.vgic.vgic_model = type; @@ -180,7 +198,7 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis) return 0; } -static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu) +static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; int i; @@ -218,17 +236,28 @@ static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu) /* PPIs */ irq->config = VGIC_CONFIG_LEVEL; } + + switch (type) { + case KVM_DEV_TYPE_ARM_VGIC_V3: + irq->group = 1; + irq->mpidr = kvm_vcpu_get_mpidr_aff(vcpu); + break; + case KVM_DEV_TYPE_ARM_VGIC_V2: + irq->group = 0; + irq->targets = BIT(vcpu->vcpu_id); + break; + } } return 0; } -static int vgic_allocate_private_irqs(struct kvm_vcpu *vcpu) +static int vgic_allocate_private_irqs(struct kvm_vcpu *vcpu, u32 type) { int ret; mutex_lock(&vcpu->kvm->arch.config_lock); - ret = vgic_allocate_private_irqs_locked(vcpu); + ret = vgic_allocate_private_irqs_locked(vcpu, type); mutex_unlock(&vcpu->kvm->arch.config_lock); return ret; @@ -258,7 +287,7 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) if (!irqchip_in_kernel(vcpu->kvm)) return 0; - ret = vgic_allocate_private_irqs(vcpu); + ret = vgic_allocate_private_irqs(vcpu, dist->vgic_model); if (ret) return ret; @@ -295,7 +324,7 @@ int vgic_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; - int ret = 0, i; + int ret = 0; unsigned long idx; lockdep_assert_held(&kvm->arch.config_lock); @@ -315,35 +344,6 @@ int vgic_init(struct kvm *kvm) if (ret) goto out; - /* Initialize groups on CPUs created before the VGIC type was known */ - kvm_for_each_vcpu(idx, vcpu, kvm) { - ret = vgic_allocate_private_irqs_locked(vcpu); - if (ret) - goto out; - - for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) { - struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, i); - - switch (dist->vgic_model) { - case KVM_DEV_TYPE_ARM_VGIC_V3: - irq->group = 1; - irq->mpidr = kvm_vcpu_get_mpidr_aff(vcpu); - break; - case KVM_DEV_TYPE_ARM_VGIC_V2: - irq->group = 0; - irq->targets = 1U << idx; - break; - default: - ret = -EINVAL; - } - - vgic_put_irq(kvm, irq); - - if (ret) - goto out; - } - } - /* * If we have GICv4.1 enabled, unconditionally request enable the * v4 support so that we get HW-accelerated vSGIs. Otherwise, only diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c index 19c67ed1a21f..18543b603c77 100644 --- a/arch/arm64/mm/trans_pgd.c +++ b/arch/arm64/mm/trans_pgd.c @@ -162,6 +162,13 @@ static int copy_p4d(struct trans_pgd_info *info, pgd_t *dst_pgdp, unsigned long next; unsigned long addr = start; + if (pgd_none(READ_ONCE(*dst_pgdp))) { + dst_p4dp = trans_alloc(info); + if (!dst_p4dp) + return -ENOMEM; + pgd_populate(NULL, dst_pgdp, dst_p4dp); + } + dst_p4dp = p4d_offset(dst_pgdp, start); src_p4dp = p4d_offset(src_pgdp, start); do { diff --git a/arch/loongarch/include/asm/cpu-info.h b/arch/loongarch/include/asm/cpu-info.h index 35e0a230a484..7f5bc0ad9d50 100644 --- a/arch/loongarch/include/asm/cpu-info.h +++ b/arch/loongarch/include/asm/cpu-info.h @@ -76,27 +76,6 @@ extern const char *__cpu_full_name[]; #define cpu_family_string() __cpu_family[raw_smp_processor_id()] #define cpu_full_name_string() __cpu_full_name[raw_smp_processor_id()] -struct seq_file; -struct notifier_block; - -extern int register_proc_cpuinfo_notifier(struct notifier_block *nb); -extern int proc_cpuinfo_notifier_call_chain(unsigned long val, void *v); - -#define proc_cpuinfo_notifier(fn, pri) \ -({ \ - static struct notifier_block fn##_nb = { \ - .notifier_call = fn, \ - .priority = pri \ - }; \ - \ - register_proc_cpuinfo_notifier(&fn##_nb); \ -}) - -struct proc_cpuinfo_notifier_args { - struct seq_file *m; - unsigned long n; -}; - static inline bool cpus_are_siblings(int cpua, int cpub) { struct cpuinfo_loongarch *infoa = &cpu_data[cpua]; diff --git a/arch/loongarch/include/asm/smp.h b/arch/loongarch/include/asm/smp.h index 3383c9d24e94..b87d1d5e5890 100644 --- a/arch/loongarch/include/asm/smp.h +++ b/arch/loongarch/include/asm/smp.h @@ -77,6 +77,8 @@ extern int __cpu_logical_map[NR_CPUS]; #define SMP_IRQ_WORK BIT(ACTION_IRQ_WORK) #define SMP_CLEAR_VECTOR BIT(ACTION_CLEAR_VECTOR) +struct seq_file; + struct secondary_data { unsigned long stack; unsigned long thread_info; diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S index 86d5d90ebefe..4f0912141781 100644 --- a/arch/loongarch/kernel/genex.S +++ b/arch/loongarch/kernel/genex.S @@ -18,16 +18,19 @@ .align 5 SYM_FUNC_START(__arch_cpu_idle) - /* start of rollback region */ - LONG_L t0, tp, TI_FLAGS - nop - andi t0, t0, _TIF_NEED_RESCHED - bnez t0, 1f - nop - nop - nop + /* start of idle interrupt region */ + ori t0, zero, CSR_CRMD_IE + /* idle instruction needs irq enabled */ + csrxchg t0, t0, LOONGARCH_CSR_CRMD + /* + * If an interrupt lands here; between enabling interrupts above and + * going idle on the next instruction, we must *NOT* go idle since the + * interrupt could have set TIF_NEED_RESCHED or caused an timer to need + * reprogramming. Fall through -- see handle_vint() below -- and have + * the idle loop take care of things. + */ idle 0 - /* end of rollback region */ + /* end of idle interrupt region */ 1: jr ra SYM_FUNC_END(__arch_cpu_idle) @@ -35,11 +38,10 @@ SYM_CODE_START(handle_vint) UNWIND_HINT_UNDEFINED BACKUP_T0T1 SAVE_ALL - la_abs t1, __arch_cpu_idle + la_abs t1, 1b LONG_L t0, sp, PT_ERA - /* 32 byte rollback region */ - ori t0, t0, 0x1f - xori t0, t0, 0x1f + /* 3 instructions idle interrupt region */ + ori t0, t0, 0b1100 bne t0, t1, 1f LONG_S t0, sp, PT_ERA 1: move a0, sp diff --git a/arch/loongarch/kernel/idle.c b/arch/loongarch/kernel/idle.c index 0b5dd2faeb90..54b247d8cdb6 100644 --- a/arch/loongarch/kernel/idle.c +++ b/arch/loongarch/kernel/idle.c @@ -11,7 +11,6 @@ void __cpuidle arch_cpu_idle(void) { - raw_local_irq_enable(); - __arch_cpu_idle(); /* idle instruction needs irq enabled */ + __arch_cpu_idle(); raw_local_irq_disable(); } diff --git a/arch/loongarch/kernel/proc.c b/arch/loongarch/kernel/proc.c index 6ce46d92f1f1..cea30768ae92 100644 --- a/arch/loongarch/kernel/proc.c +++ b/arch/loongarch/kernel/proc.c @@ -13,28 +13,12 @@ #include <asm/processor.h> #include <asm/time.h> -/* - * No lock; only written during early bootup by CPU 0. - */ -static RAW_NOTIFIER_HEAD(proc_cpuinfo_chain); - -int __ref register_proc_cpuinfo_notifier(struct notifier_block *nb) -{ - return raw_notifier_chain_register(&proc_cpuinfo_chain, nb); -} - -int proc_cpuinfo_notifier_call_chain(unsigned long val, void *v) -{ - return raw_notifier_call_chain(&proc_cpuinfo_chain, val, v); -} - static int show_cpuinfo(struct seq_file *m, void *v) { unsigned long n = (unsigned long) v - 1; unsigned int isa = cpu_data[n].isa_level; unsigned int version = cpu_data[n].processor_id & 0xff; unsigned int fp_version = cpu_data[n].fpu_vers; - struct proc_cpuinfo_notifier_args proc_cpuinfo_notifier_args; #ifdef CONFIG_SMP if (!cpu_online(n)) @@ -91,20 +75,13 @@ static int show_cpuinfo(struct seq_file *m, void *v) if (cpu_has_lbt_mips) seq_printf(m, " lbt_mips"); seq_printf(m, "\n"); - seq_printf(m, "Hardware Watchpoint\t: %s", - cpu_has_watch ? "yes, " : "no\n"); + seq_printf(m, "Hardware Watchpoint\t: %s", str_yes_no(cpu_has_watch)); if (cpu_has_watch) { - seq_printf(m, "iwatch count: %d, dwatch count: %d\n", + seq_printf(m, ", iwatch count: %d, dwatch count: %d", cpu_data[n].watch_ireg_count, cpu_data[n].watch_dreg_count); } - proc_cpuinfo_notifier_args.m = m; - proc_cpuinfo_notifier_args.n = n; - - raw_notifier_call_chain(&proc_cpuinfo_chain, 0, - &proc_cpuinfo_notifier_args); - - seq_printf(m, "\n"); + seq_printf(m, "\n\n"); return 0; } diff --git a/arch/loongarch/kernel/reset.c b/arch/loongarch/kernel/reset.c index 1ef8c6383535..de8fa5a8a825 100644 --- a/arch/loongarch/kernel/reset.c +++ b/arch/loongarch/kernel/reset.c @@ -33,7 +33,7 @@ void machine_halt(void) console_flush_on_panic(CONSOLE_FLUSH_PENDING); while (true) { - __arch_cpu_idle(); + __asm__ __volatile__("idle 0" : : : "memory"); } } @@ -53,7 +53,7 @@ void machine_power_off(void) #endif while (true) { - __arch_cpu_idle(); + __asm__ __volatile__("idle 0" : : : "memory"); } } @@ -74,6 +74,6 @@ void machine_restart(char *command) acpi_reboot(); while (true) { - __arch_cpu_idle(); + __asm__ __volatile__("idle 0" : : : "memory"); } } diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c index bf9268bf26d5..f6d3242b9234 100644 --- a/arch/loongarch/kvm/main.c +++ b/arch/loongarch/kvm/main.c @@ -303,9 +303,9 @@ int kvm_arch_enable_virtualization_cpu(void) * TOE=0: Trap on Exception. * TIT=0: Trap on Timer. */ - if (env & CSR_GCFG_GCIP_ALL) + if (env & CSR_GCFG_GCIP_SECURE) gcfg |= CSR_GCFG_GCI_SECURE; - if (env & CSR_GCFG_MATC_ROOT) + if (env & CSR_GCFG_MATP_ROOT) gcfg |= CSR_GCFG_MATC_ROOT; write_csr_gcfg(gcfg); diff --git a/arch/loongarch/kvm/switch.S b/arch/loongarch/kvm/switch.S index 0c292f818492..1be185e94807 100644 --- a/arch/loongarch/kvm/switch.S +++ b/arch/loongarch/kvm/switch.S @@ -85,7 +85,7 @@ * Guest CRMD comes from separate GCSR_CRMD register */ ori t0, zero, CSR_PRMD_PIE - csrxchg t0, t0, LOONGARCH_CSR_PRMD + csrwr t0, LOONGARCH_CSR_PRMD /* Set PVM bit to setup ertn to guest context */ ori t0, zero, CSR_GSTAT_PVM diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c index fb72095c8077..20f941af3e9e 100644 --- a/arch/loongarch/kvm/vcpu.c +++ b/arch/loongarch/kvm/vcpu.c @@ -1548,9 +1548,6 @@ static int _kvm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) /* Restore timer state regardless */ kvm_restore_timer(vcpu); - - /* Control guest page CCA attribute */ - change_csr_gcfg(CSR_GCFG_MATC_MASK, CSR_GCFG_MATC_ROOT); kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); /* Restore hardware PMU CSRs */ diff --git a/arch/loongarch/lib/csum.c b/arch/loongarch/lib/csum.c index a5e84b403c3b..df309ae4045d 100644 --- a/arch/loongarch/lib/csum.c +++ b/arch/loongarch/lib/csum.c @@ -25,7 +25,7 @@ unsigned int __no_sanitize_address do_csum(const unsigned char *buff, int len) const u64 *ptr; u64 data, sum64 = 0; - if (unlikely(len == 0)) + if (unlikely(len <= 0)) return 0; offset = (unsigned long)buff & 7; diff --git a/arch/loongarch/mm/pageattr.c b/arch/loongarch/mm/pageattr.c index bf8678248444..99165903908a 100644 --- a/arch/loongarch/mm/pageattr.c +++ b/arch/loongarch/mm/pageattr.c @@ -3,6 +3,7 @@ * Copyright (C) 2024 Loongson Technology Corporation Limited */ +#include <linux/memblock.h> #include <linux/pagewalk.h> #include <linux/pgtable.h> #include <asm/set_memory.h> @@ -167,7 +168,7 @@ bool kernel_page_present(struct page *page) unsigned long addr = (unsigned long)page_address(page); if (addr < vm_map_base) - return true; + return memblock_is_memory(__pa(addr)); pgd = pgd_offset_k(addr); if (pgd_none(pgdp_get(pgd))) diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h index 4a2b40ce39e0..85fa9962266a 100644 --- a/arch/mips/include/asm/ptrace.h +++ b/arch/mips/include/asm/ptrace.h @@ -27,8 +27,8 @@ */ struct pt_regs { #ifdef CONFIG_32BIT - /* Pad bytes for argument save space on the stack. */ - unsigned long pad0[8]; + /* Saved syscall stack arguments; entries 0-3 unused. */ + unsigned long args[8]; #endif /* Saved main processor registers. */ diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h index ebdf4d910af2..056aa1b713e2 100644 --- a/arch/mips/include/asm/syscall.h +++ b/arch/mips/include/asm/syscall.h @@ -57,37 +57,21 @@ static inline void mips_syscall_update_nr(struct task_struct *task, static inline void mips_get_syscall_arg(unsigned long *arg, struct task_struct *task, struct pt_regs *regs, unsigned int n) { - unsigned long usp __maybe_unused = regs->regs[29]; - +#ifdef CONFIG_32BIT switch (n) { case 0: case 1: case 2: case 3: *arg = regs->regs[4 + n]; - - return; - -#ifdef CONFIG_32BIT - case 4: case 5: case 6: case 7: - get_user(*arg, (int *)usp + n); return; -#endif - -#ifdef CONFIG_64BIT case 4: case 5: case 6: case 7: -#ifdef CONFIG_MIPS32_O32 - if (test_tsk_thread_flag(task, TIF_32BIT_REGS)) - get_user(*arg, (int *)usp + n); - else -#endif - *arg = regs->regs[4 + n]; - + *arg = regs->args[n]; return; -#endif - - default: - BUG(); } - - unreachable(); +#else + *arg = regs->regs[4 + n]; + if ((IS_ENABLED(CONFIG_MIPS32_O32) && + test_tsk_thread_flag(task, TIF_32BIT_REGS))) + *arg = (unsigned int)*arg; +#endif } static inline long syscall_get_error(struct task_struct *task, diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c index cb1045ebab06..b910ec54a3a1 100644 --- a/arch/mips/kernel/asm-offsets.c +++ b/arch/mips/kernel/asm-offsets.c @@ -27,6 +27,12 @@ void output_ptreg_defines(void); void output_ptreg_defines(void) { COMMENT("MIPS pt_regs offsets."); +#ifdef CONFIG_32BIT + OFFSET(PT_ARG4, pt_regs, args[4]); + OFFSET(PT_ARG5, pt_regs, args[5]); + OFFSET(PT_ARG6, pt_regs, args[6]); + OFFSET(PT_ARG7, pt_regs, args[7]); +#endif OFFSET(PT_R0, pt_regs, regs[0]); OFFSET(PT_R1, pt_regs, regs[1]); OFFSET(PT_R2, pt_regs, regs[2]); diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index 2c604717e630..4947a4f39e37 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -64,10 +64,10 @@ load_a6: user_lw(t7, 24(t0)) # argument #7 from usp load_a7: user_lw(t8, 28(t0)) # argument #8 from usp loads_done: - sw t5, 16(sp) # argument #5 to ksp - sw t6, 20(sp) # argument #6 to ksp - sw t7, 24(sp) # argument #7 to ksp - sw t8, 28(sp) # argument #8 to ksp + sw t5, PT_ARG4(sp) # argument #5 to ksp + sw t6, PT_ARG5(sp) # argument #6 to ksp + sw t7, PT_ARG6(sp) # argument #7 to ksp + sw t8, PT_ARG7(sp) # argument #8 to ksp .set pop .section __ex_table,"a" diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index 1aa0cb097c9c..7b9a5ea9cad9 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -75,7 +75,7 @@ static void fsl_msi_print_chip(struct irq_data *irqd, struct seq_file *p) srs = (hwirq >> msi_data->srs_shift) & MSI_SRS_MASK; cascade_virq = msi_data->cascade_array[srs]->virq; - seq_printf(p, " fsl-msi-%d", cascade_virq); + seq_printf(p, "fsl-msi-%d", cascade_virq); } diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index d6beec5292a0..44f01a4bc810 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -740,7 +740,6 @@ CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y -CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 8cfbfb10bba8..8bcd37edd3c9 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -725,7 +725,6 @@ CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y -CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_USER=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index bcbaa069de96..853b2326a171 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -62,7 +62,6 @@ CONFIG_ZFCP=y # CONFIG_INOTIFY_USER is not set # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set -CONFIG_LSM="yama,loadpin,safesetid,integrity" # CONFIG_ZLIB_DFLTCC is not set CONFIG_XZ_DEC_MICROLZMA=y CONFIG_PRINTK_TIME=y diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index d5125296ade2..a5ca0a947691 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -53,7 +53,11 @@ static __always_inline bool arch_test_bit(unsigned long nr, const volatile unsig unsigned long mask; int cc; - if (__builtin_constant_p(nr)) { + /* + * With CONFIG_PROFILE_ALL_BRANCHES enabled gcc fails to + * handle __builtin_constant_p() in some cases. + */ + if (!IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && __builtin_constant_p(nr)) { addr = (const volatile unsigned char *)ptr; addr += (nr ^ (BITS_PER_LONG - BITS_PER_BYTE)) / BITS_PER_BYTE; mask = 1UL << (nr & (BITS_PER_BYTE - 1)); diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h index 13f51a6a5bb1..4e73ef46d4b2 100644 --- a/arch/s390/include/asm/gmap.h +++ b/arch/s390/include/asm/gmap.h @@ -23,7 +23,6 @@ /** * struct gmap_struct - guest address space * @list: list head for the mm->context gmap list - * @crst_list: list of all crst tables used in the guest address space * @mm: pointer to the parent mm_struct * @guest_to_host: radix tree with guest to host address translation * @host_to_guest: radix tree with pointer to segment table entries @@ -35,7 +34,6 @@ * @guest_handle: protected virtual machine handle for the ultravisor * @host_to_rmap: radix tree with gmap_rmap lists * @children: list of shadow gmap structures - * @pt_list: list of all page tables used in the shadow guest address space * @shadow_lock: spinlock to protect the shadow gmap list * @parent: pointer to the parent gmap for shadow guest address spaces * @orig_asce: ASCE for which the shadow page table has been created @@ -45,7 +43,6 @@ */ struct gmap { struct list_head list; - struct list_head crst_list; struct mm_struct *mm; struct radix_tree_root guest_to_host; struct radix_tree_root host_to_guest; @@ -61,7 +58,6 @@ struct gmap { /* Additional data for shadow guest address spaces */ struct radix_tree_root host_to_rmap; struct list_head children; - struct list_head pt_list; spinlock_t shadow_lock; struct gmap *parent; unsigned long orig_asce; @@ -106,23 +102,21 @@ struct gmap *gmap_create(struct mm_struct *mm, unsigned long limit); void gmap_remove(struct gmap *gmap); struct gmap *gmap_get(struct gmap *gmap); void gmap_put(struct gmap *gmap); +void gmap_free(struct gmap *gmap); +struct gmap *gmap_alloc(unsigned long limit); int gmap_map_segment(struct gmap *gmap, unsigned long from, unsigned long to, unsigned long len); int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len); unsigned long __gmap_translate(struct gmap *, unsigned long gaddr); -unsigned long gmap_translate(struct gmap *, unsigned long gaddr); int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr); -int gmap_fault(struct gmap *, unsigned long gaddr, unsigned int fault_flags); void gmap_discard(struct gmap *, unsigned long from, unsigned long to); void __gmap_zap(struct gmap *, unsigned long gaddr); void gmap_unlink(struct mm_struct *, unsigned long *table, unsigned long vmaddr); int gmap_read_table(struct gmap *gmap, unsigned long gaddr, unsigned long *val); -struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, - int edat_level); -int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level); +void gmap_unshadow(struct gmap *sg); int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t, int fake); int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t, @@ -131,24 +125,22 @@ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt, int fake); int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt, int fake); -int gmap_shadow_pgt_lookup(struct gmap *sg, unsigned long saddr, - unsigned long *pgt, int *dat_protection, int *fake); int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte); void gmap_register_pte_notifier(struct gmap_notifier *); void gmap_unregister_pte_notifier(struct gmap_notifier *); -int gmap_mprotect_notify(struct gmap *, unsigned long start, - unsigned long len, int prot); +int gmap_protect_one(struct gmap *gmap, unsigned long gaddr, int prot, unsigned long bits); void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4], unsigned long gaddr, unsigned long vmaddr); int s390_disable_cow_sharing(void); -void s390_unlist_old_asce(struct gmap *gmap); int s390_replace_asce(struct gmap *gmap); void s390_uv_destroy_pfns(unsigned long count, unsigned long *pfns); int __s390_uv_destroy_range(struct mm_struct *mm, unsigned long start, unsigned long end, bool interruptible); +int kvm_s390_wiggle_split_folio(struct mm_struct *mm, struct folio *folio, bool split); +unsigned long *gmap_table_walk(struct gmap *gmap, unsigned long gaddr, int level); /** * s390_uv_destroy_range - Destroy a range of pages in the given mm. diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 97c7c8127543..9a367866cab0 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -30,6 +30,8 @@ #define KVM_S390_ESCA_CPU_SLOTS 248 #define KVM_MAX_VCPUS 255 +#define KVM_INTERNAL_MEM_SLOTS 1 + /* * These seem to be used for allocating ->chip in the routing table, which we * don't use. 1 is as small as we can get to reduce the needed memory. If we @@ -931,12 +933,14 @@ struct sie_page2 { u8 reserved928[0x1000 - 0x928]; /* 0x0928 */ }; +struct vsie_page; + 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 vsie_page *pages[KVM_MAX_VCPUS]; }; struct kvm_s390_gisa_iam { diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index a3b51056a177..3ca5af4cfe43 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -420,9 +420,10 @@ void setup_protection_map(void); #define PGSTE_HC_BIT 0x0020000000000000UL #define PGSTE_GR_BIT 0x0004000000000000UL #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 */ +#define PGSTE_ST2_MASK 0x0000ffff00000000UL +#define PGSTE_UC_BIT 0x0000000000008000UL /* user dirty (migration) */ +#define PGSTE_IN_BIT 0x0000000000004000UL /* IPTE notify bit */ +#define PGSTE_VSIE_BIT 0x0000000000002000UL /* ref'd in a shadow table */ /* Guest Page State used for virtualization */ #define _PGSTE_GPS_ZERO 0x0000000080000000UL @@ -2007,4 +2008,18 @@ extern void s390_reset_cmma(struct mm_struct *mm); #define pmd_pgtable(pmd) \ ((pgtable_t)__va(pmd_val(pmd) & -sizeof(pte_t)*PTRS_PER_PTE)) +static inline unsigned long gmap_pgste_get_pgt_addr(unsigned long *pgt) +{ + unsigned long *pgstes, res; + + pgstes = pgt + _PAGE_ENTRIES; + + res = (pgstes[0] & PGSTE_ST2_MASK) << 16; + res |= pgstes[1] & PGSTE_ST2_MASK; + res |= (pgstes[2] & PGSTE_ST2_MASK) >> 16; + res |= (pgstes[3] & PGSTE_ST2_MASK) >> 32; + + return res; +} + #endif /* _S390_PAGE_H */ diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index dc332609f2c3..b11f5b6d0bd1 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -628,12 +628,12 @@ static inline int is_prot_virt_host(void) } int uv_pin_shared(unsigned long paddr); -int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb); -int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr); int uv_destroy_folio(struct folio *folio); int uv_destroy_pte(pte_t pte); int uv_convert_from_secure_pte(pte_t pte); -int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr); +int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb); +int uv_convert_from_secure(unsigned long paddr); +int uv_convert_from_secure_folio(struct folio *folio); void setup_uv(void); diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 6f9654a191ad..9f05df2da2f7 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -19,19 +19,6 @@ #include <asm/sections.h> #include <asm/uv.h> -#if !IS_ENABLED(CONFIG_KVM) -unsigned long __gmap_translate(struct gmap *gmap, unsigned long gaddr) -{ - return 0; -} - -int gmap_fault(struct gmap *gmap, unsigned long gaddr, - unsigned int fault_flags) -{ - return 0; -} -#endif - /* the bootdata_preserved fields come from ones in arch/s390/boot/uv.c */ int __bootdata_preserved(prot_virt_guest); EXPORT_SYMBOL(prot_virt_guest); @@ -159,6 +146,7 @@ int uv_destroy_folio(struct folio *folio) folio_put(folio); return rc; } +EXPORT_SYMBOL(uv_destroy_folio); /* * The present PTE still indirectly holds a folio reference through the mapping. @@ -175,7 +163,7 @@ int uv_destroy_pte(pte_t pte) * * @paddr: Absolute host address of page to be exported */ -static int uv_convert_from_secure(unsigned long paddr) +int uv_convert_from_secure(unsigned long paddr) { struct uv_cb_cfs uvcb = { .header.cmd = UVC_CMD_CONV_FROM_SEC_STOR, @@ -187,11 +175,12 @@ static int uv_convert_from_secure(unsigned long paddr) return -EINVAL; return 0; } +EXPORT_SYMBOL_GPL(uv_convert_from_secure); /* * The caller must already hold a reference to the folio. */ -static int uv_convert_from_secure_folio(struct folio *folio) +int uv_convert_from_secure_folio(struct folio *folio) { int rc; @@ -206,6 +195,7 @@ static int uv_convert_from_secure_folio(struct folio *folio) folio_put(folio); return rc; } +EXPORT_SYMBOL_GPL(uv_convert_from_secure_folio); /* * The present PTE still indirectly holds a folio reference through the mapping. @@ -237,13 +227,33 @@ static int expected_folio_refs(struct folio *folio) return res; } -static int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb) +/** + * make_folio_secure() - make a folio secure + * @folio: the folio to make secure + * @uvcb: the uvcb that describes the UVC to be used + * + * The folio @folio will be made secure if possible, @uvcb will be passed + * as-is to the UVC. + * + * Return: 0 on success; + * -EBUSY if the folio is in writeback or has too many references; + * -E2BIG if the folio is large; + * -EAGAIN if the UVC needs to be attempted again; + * -ENXIO if the address is not mapped; + * -EINVAL if the UVC failed for other reasons. + * + * Context: The caller must hold exactly one extra reference on the folio + * (it's the same logic as split_folio()) + */ +int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb) { int expected, cc = 0; + if (folio_test_large(folio)) + return -E2BIG; if (folio_test_writeback(folio)) - return -EAGAIN; - expected = expected_folio_refs(folio); + return -EBUSY; + expected = expected_folio_refs(folio) + 1; if (!folio_ref_freeze(folio, expected)) return -EBUSY; set_bit(PG_arch_1, &folio->flags); @@ -267,251 +277,7 @@ static int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb) return -EAGAIN; return uvcb->rc == 0x10a ? -ENXIO : -EINVAL; } - -/** - * should_export_before_import - Determine whether an export is needed - * before an import-like operation - * @uvcb: the Ultravisor control block of the UVC to be performed - * @mm: the mm of the process - * - * Returns whether an export is needed before every import-like operation. - * This is needed for shared pages, which don't trigger a secure storage - * exception when accessed from a different guest. - * - * Although considered as one, the Unpin Page UVC is not an actual import, - * so it is not affected. - * - * No export is needed also when there is only one protected VM, because the - * page cannot belong to the wrong VM in that case (there is no "other VM" - * it can belong to). - * - * Return: true if an export is needed before every import, otherwise false. - */ -static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_struct *mm) -{ - /* - * The misc feature indicates, among other things, that importing a - * shared page from a different protected VM will automatically also - * transfer its ownership. - */ - if (uv_has_feature(BIT_UV_FEAT_MISC)) - return false; - if (uvcb->cmd == UVC_CMD_UNPIN_PAGE_SHARED) - return false; - return atomic_read(&mm->context.protected_count) > 1; -} - -/* - * Drain LRU caches: the local one on first invocation and the ones of all - * CPUs on successive invocations. Returns "true" on the first invocation. - */ -static bool drain_lru(bool *drain_lru_called) -{ - /* - * If we have tried a local drain and the folio refcount - * still does not match our expected safe value, try with a - * system wide drain. This is needed if the pagevecs holding - * the page are on a different CPU. - */ - if (*drain_lru_called) { - lru_add_drain_all(); - /* We give up here, don't retry immediately. */ - return false; - } - /* - * We are here if the folio refcount does not match the - * expected safe value. The main culprits are usually - * pagevecs. With lru_add_drain() we drain the pagevecs - * on the local CPU so that hopefully the refcount will - * reach the expected safe value. - */ - lru_add_drain(); - *drain_lru_called = true; - /* The caller should try again immediately */ - return true; -} - -/* - * Requests the Ultravisor to make a page accessible to a guest. - * If it's brought in the first time, it will be cleared. If - * it has been exported before, it will be decrypted and integrity - * checked. - */ -int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb) -{ - struct vm_area_struct *vma; - bool drain_lru_called = false; - spinlock_t *ptelock; - unsigned long uaddr; - struct folio *folio; - pte_t *ptep; - int rc; - -again: - rc = -EFAULT; - mmap_read_lock(gmap->mm); - - uaddr = __gmap_translate(gmap, gaddr); - if (IS_ERR_VALUE(uaddr)) - goto out; - vma = vma_lookup(gmap->mm, uaddr); - if (!vma) - goto out; - /* - * Secure pages cannot be huge and userspace should not combine both. - * In case userspace does it anyway this will result in an -EFAULT for - * the unpack. The guest is thus never reaching secure mode. If - * userspace is playing dirty tricky with mapping huge pages later - * on this will result in a segmentation fault. - */ - if (is_vm_hugetlb_page(vma)) - goto out; - - rc = -ENXIO; - ptep = get_locked_pte(gmap->mm, uaddr, &ptelock); - if (!ptep) - goto out; - if (pte_present(*ptep) && !(pte_val(*ptep) & _PAGE_INVALID) && pte_write(*ptep)) { - folio = page_folio(pte_page(*ptep)); - rc = -EAGAIN; - if (folio_test_large(folio)) { - rc = -E2BIG; - } else if (folio_trylock(folio)) { - if (should_export_before_import(uvcb, gmap->mm)) - uv_convert_from_secure(PFN_PHYS(folio_pfn(folio))); - rc = make_folio_secure(folio, uvcb); - folio_unlock(folio); - } - - /* - * Once we drop the PTL, the folio may get unmapped and - * freed immediately. We need a temporary reference. - */ - if (rc == -EAGAIN || rc == -E2BIG) - folio_get(folio); - } - pte_unmap_unlock(ptep, ptelock); -out: - mmap_read_unlock(gmap->mm); - - switch (rc) { - case -E2BIG: - folio_lock(folio); - rc = split_folio(folio); - folio_unlock(folio); - folio_put(folio); - - switch (rc) { - case 0: - /* Splitting succeeded, try again immediately. */ - goto again; - case -EAGAIN: - /* Additional folio references. */ - if (drain_lru(&drain_lru_called)) - goto again; - return -EAGAIN; - case -EBUSY: - /* Unexpected race. */ - return -EAGAIN; - } - WARN_ON_ONCE(1); - return -ENXIO; - case -EAGAIN: - /* - * If we are here because the UVC returned busy or partial - * completion, this is just a useless check, but it is safe. - */ - folio_wait_writeback(folio); - folio_put(folio); - return -EAGAIN; - case -EBUSY: - /* Additional folio references. */ - if (drain_lru(&drain_lru_called)) - goto again; - return -EAGAIN; - case -ENXIO: - if (gmap_fault(gmap, gaddr, FAULT_FLAG_WRITE)) - return -EFAULT; - return -EAGAIN; - } - return rc; -} -EXPORT_SYMBOL_GPL(gmap_make_secure); - -int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr) -{ - struct uv_cb_cts uvcb = { - .header.cmd = UVC_CMD_CONV_TO_SEC_STOR, - .header.len = sizeof(uvcb), - .guest_handle = gmap->guest_handle, - .gaddr = gaddr, - }; - - return gmap_make_secure(gmap, gaddr, &uvcb); -} -EXPORT_SYMBOL_GPL(gmap_convert_to_secure); - -/** - * gmap_destroy_page - Destroy a guest page. - * @gmap: the gmap of the guest - * @gaddr: the guest address to destroy - * - * An attempt will be made to destroy the given guest page. If the attempt - * fails, an attempt is made to export the page. If both attempts fail, an - * appropriate error is returned. - */ -int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr) -{ - struct vm_area_struct *vma; - struct folio_walk fw; - unsigned long uaddr; - struct folio *folio; - int rc; - - rc = -EFAULT; - mmap_read_lock(gmap->mm); - - uaddr = __gmap_translate(gmap, gaddr); - if (IS_ERR_VALUE(uaddr)) - goto out; - vma = vma_lookup(gmap->mm, uaddr); - if (!vma) - goto out; - /* - * Huge pages should not be able to become secure - */ - if (is_vm_hugetlb_page(vma)) - goto out; - - rc = 0; - folio = folio_walk_start(&fw, vma, uaddr, 0); - if (!folio) - goto out; - /* - * See gmap_make_secure(): large folios cannot be secure. Small - * folio implies FW_LEVEL_PTE. - */ - if (folio_test_large(folio) || !pte_write(fw.pte)) - goto out_walk_end; - rc = uv_destroy_folio(folio); - /* - * Fault handlers can race; it is possible that two CPUs will fault - * on the same secure page. One CPU can destroy the page, reboot, - * re-enter secure mode and import it, while the second CPU was - * stuck at the beginning of the handler. At some point the second - * CPU will be able to progress, and it will not be able to destroy - * the page. In that case we do not want to terminate the process, - * we instead try to export the page. - */ - if (rc) - rc = uv_convert_from_secure_folio(folio); -out_walk_end: - folio_walk_end(&fw, vma); -out: - mmap_read_unlock(gmap->mm); - return rc; -} -EXPORT_SYMBOL_GPL(gmap_destroy_page); +EXPORT_SYMBOL_GPL(make_folio_secure); /* * To be called with the folio locked or with an extra reference! This will diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile index 02217fb4ae10..f0ffe874adc2 100644 --- a/arch/s390/kvm/Makefile +++ b/arch/s390/kvm/Makefile @@ -8,7 +8,7 @@ include $(srctree)/virt/kvm/Makefile.kvm ccflags-y := -Ivirt/kvm -Iarch/s390/kvm kvm-y += kvm-s390.o intercept.o interrupt.o priv.o sigp.o -kvm-y += diag.o gaccess.o guestdbg.o vsie.o pv.o +kvm-y += diag.o gaccess.o guestdbg.o vsie.o pv.o gmap.o gmap-vsie.o kvm-$(CONFIG_VFIO_PCI_ZDEV_KVM) += pci.o obj-$(CONFIG_KVM) += kvm.o diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 9816b0060fbe..f6fded15633a 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -16,6 +16,7 @@ #include <asm/gmap.h> #include <asm/dat-bits.h> #include "kvm-s390.h" +#include "gmap.h" #include "gaccess.h" /* @@ -1393,6 +1394,44 @@ shadow_pgt: } /** + * shadow_pgt_lookup() - 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_lock in read. + */ +static int shadow_pgt_lookup(struct gmap *sg, unsigned long saddr, unsigned long *pgt, + int *dat_protection, int *fake) +{ + unsigned long pt_index; + unsigned long *table; + struct page *page; + int rc; + + 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); + pt_index = gmap_pgste_get_pgt_addr(page_to_virt(page)); + *pgt = pt_index & ~GMAP_SHADOW_FAKE_TABLE; + *dat_protection = !!(*table & _SEGMENT_ENTRY_PROTECT); + *fake = !!(pt_index & GMAP_SHADOW_FAKE_TABLE); + rc = 0; + } else { + rc = -EAGAIN; + } + spin_unlock(&sg->guest_table_lock); + return rc; +} + +/** * kvm_s390_shadow_fault - handle fault on a shadow page table * @vcpu: virtual cpu * @sg: pointer to the shadow guest address space structure @@ -1415,6 +1454,9 @@ int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg, int dat_protection, fake; int rc; + if (KVM_BUG_ON(!gmap_is_shadow(sg), vcpu->kvm)) + return -EFAULT; + mmap_read_lock(sg->mm); /* * We don't want any guest-2 tables to change - so the parent @@ -1423,7 +1465,7 @@ int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg, */ ipte_lock(vcpu->kvm); - rc = gmap_shadow_pgt_lookup(sg, saddr, &pgt, &dat_protection, &fake); + rc = shadow_pgt_lookup(sg, saddr, &pgt, &dat_protection, &fake); if (rc) rc = kvm_s390_shadow_tables(sg, saddr, &pgt, &dat_protection, &fake); diff --git a/arch/s390/kvm/gmap-vsie.c b/arch/s390/kvm/gmap-vsie.c new file mode 100644 index 000000000000..a6d1dbb04c97 --- /dev/null +++ b/arch/s390/kvm/gmap-vsie.c @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Guest memory management for KVM/s390 nested VMs. + * + * Copyright IBM Corp. 2008, 2020, 2024 + * + * Author(s): Claudio Imbrenda <imbrenda@linux.ibm.com> + * Martin Schwidefsky <schwidefsky@de.ibm.com> + * David Hildenbrand <david@redhat.com> + * Janosch Frank <frankja@linux.vnet.ibm.com> + */ + +#include <linux/compiler.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/pgtable.h> +#include <linux/pagemap.h> +#include <linux/mman.h> + +#include <asm/lowcore.h> +#include <asm/gmap.h> +#include <asm/uv.h> + +#include "kvm-s390.h" +#include "gmap.h" + +/** + * 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 + * + * Context: Called with parent->shadow_lock held + */ +static struct gmap *gmap_find_shadow(struct gmap *parent, unsigned long asce, int edat_level) +{ + struct gmap *sg; + + lockdep_assert_held(&parent->shadow_lock); + list_for_each_entry(sg, &parent->children, list) { + if (!gmap_shadow_valid(sg, asce, edat_level)) + continue; + if (!sg->initialized) + return ERR_PTR(-EAGAIN); + refcount_inc(&sg->ref_count); + return sg; + } + return NULL; +} + +/** + * 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; + + if (KVM_BUG_ON(parent->mm->context.allow_gmap_hpage_1m, (struct kvm *)parent->private) || + KVM_BUG_ON(gmap_is_shadow(parent), (struct kvm *)parent->private)) + return ERR_PTR(-EFAULT); + 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->private = parent->private; + 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; + } + } + } + refcount_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 */ + mmap_read_lock(parent->mm); + rc = __kvm_s390_mprotect_many(parent, asce & _ASCE_ORIGIN, + ((asce & _ASCE_TABLE_LENGTH) + 1), + PROT_READ, GMAP_NOTIFY_SHADOW); + mmap_read_unlock(parent->mm); + 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; +} diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c new file mode 100644 index 000000000000..02adf151d4de --- /dev/null +++ b/arch/s390/kvm/gmap.c @@ -0,0 +1,212 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Guest memory management for KVM/s390 + * + * Copyright IBM Corp. 2008, 2020, 2024 + * + * Author(s): Claudio Imbrenda <imbrenda@linux.ibm.com> + * Martin Schwidefsky <schwidefsky@de.ibm.com> + * David Hildenbrand <david@redhat.com> + * Janosch Frank <frankja@linux.vnet.ibm.com> + */ + +#include <linux/compiler.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/pgtable.h> +#include <linux/pagemap.h> + +#include <asm/lowcore.h> +#include <asm/gmap.h> +#include <asm/uv.h> + +#include "gmap.h" + +/** + * should_export_before_import - Determine whether an export is needed + * before an import-like operation + * @uvcb: the Ultravisor control block of the UVC to be performed + * @mm: the mm of the process + * + * Returns whether an export is needed before every import-like operation. + * This is needed for shared pages, which don't trigger a secure storage + * exception when accessed from a different guest. + * + * Although considered as one, the Unpin Page UVC is not an actual import, + * so it is not affected. + * + * No export is needed also when there is only one protected VM, because the + * page cannot belong to the wrong VM in that case (there is no "other VM" + * it can belong to). + * + * Return: true if an export is needed before every import, otherwise false. + */ +static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_struct *mm) +{ + /* + * The misc feature indicates, among other things, that importing a + * shared page from a different protected VM will automatically also + * transfer its ownership. + */ + if (uv_has_feature(BIT_UV_FEAT_MISC)) + return false; + if (uvcb->cmd == UVC_CMD_UNPIN_PAGE_SHARED) + return false; + return atomic_read(&mm->context.protected_count) > 1; +} + +static int __gmap_make_secure(struct gmap *gmap, struct page *page, void *uvcb) +{ + struct folio *folio = page_folio(page); + int rc; + + /* + * Secure pages cannot be huge and userspace should not combine both. + * In case userspace does it anyway this will result in an -EFAULT for + * the unpack. The guest is thus never reaching secure mode. + * If userspace plays dirty tricks and decides to map huge pages at a + * later point in time, it will receive a segmentation fault or + * KVM_RUN will return -EFAULT. + */ + if (folio_test_hugetlb(folio)) + return -EFAULT; + if (folio_test_large(folio)) { + mmap_read_unlock(gmap->mm); + rc = kvm_s390_wiggle_split_folio(gmap->mm, folio, true); + mmap_read_lock(gmap->mm); + if (rc) + return rc; + folio = page_folio(page); + } + + if (!folio_trylock(folio)) + return -EAGAIN; + if (should_export_before_import(uvcb, gmap->mm)) + uv_convert_from_secure(folio_to_phys(folio)); + rc = make_folio_secure(folio, uvcb); + folio_unlock(folio); + + /* + * In theory a race is possible and the folio might have become + * large again before the folio_trylock() above. In that case, no + * action is performed and -EAGAIN is returned; the callers will + * have to try again later. + * In most cases this implies running the VM again, getting the same + * exception again, and make another attempt in this function. + * This is expected to happen extremely rarely. + */ + if (rc == -E2BIG) + return -EAGAIN; + /* The folio has too many references, try to shake some off */ + if (rc == -EBUSY) { + mmap_read_unlock(gmap->mm); + kvm_s390_wiggle_split_folio(gmap->mm, folio, false); + mmap_read_lock(gmap->mm); + return -EAGAIN; + } + + return rc; +} + +/** + * gmap_make_secure() - make one guest page secure + * @gmap: the guest gmap + * @gaddr: the guest address that needs to be made secure + * @uvcb: the UVCB specifying which operation needs to be performed + * + * Context: needs to be called with kvm->srcu held. + * Return: 0 on success, < 0 in case of error (see __gmap_make_secure()). + */ +int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb) +{ + struct kvm *kvm = gmap->private; + struct page *page; + int rc = 0; + + lockdep_assert_held(&kvm->srcu); + + page = gfn_to_page(kvm, gpa_to_gfn(gaddr)); + mmap_read_lock(gmap->mm); + if (page) + rc = __gmap_make_secure(gmap, page, uvcb); + kvm_release_page_clean(page); + mmap_read_unlock(gmap->mm); + + return rc; +} + +int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr) +{ + struct uv_cb_cts uvcb = { + .header.cmd = UVC_CMD_CONV_TO_SEC_STOR, + .header.len = sizeof(uvcb), + .guest_handle = gmap->guest_handle, + .gaddr = gaddr, + }; + + return gmap_make_secure(gmap, gaddr, &uvcb); +} + +/** + * __gmap_destroy_page() - Destroy a guest page. + * @gmap: the gmap of the guest + * @page: the page to destroy + * + * An attempt will be made to destroy the given guest page. If the attempt + * fails, an attempt is made to export the page. If both attempts fail, an + * appropriate error is returned. + * + * Context: must be called holding the mm lock for gmap->mm + */ +static int __gmap_destroy_page(struct gmap *gmap, struct page *page) +{ + struct folio *folio = page_folio(page); + int rc; + + /* + * See gmap_make_secure(): large folios cannot be secure. Small + * folio implies FW_LEVEL_PTE. + */ + if (folio_test_large(folio)) + return -EFAULT; + + rc = uv_destroy_folio(folio); + /* + * Fault handlers can race; it is possible that two CPUs will fault + * on the same secure page. One CPU can destroy the page, reboot, + * re-enter secure mode and import it, while the second CPU was + * stuck at the beginning of the handler. At some point the second + * CPU will be able to progress, and it will not be able to destroy + * the page. In that case we do not want to terminate the process, + * we instead try to export the page. + */ + if (rc) + rc = uv_convert_from_secure_folio(folio); + + return rc; +} + +/** + * gmap_destroy_page() - Destroy a guest page. + * @gmap: the gmap of the guest + * @gaddr: the guest address to destroy + * + * An attempt will be made to destroy the given guest page. If the attempt + * fails, an attempt is made to export the page. If both attempts fail, an + * appropriate error is returned. + * + * Context: may sleep. + */ +int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr) +{ + struct page *page; + int rc = 0; + + mmap_read_lock(gmap->mm); + page = gfn_to_page(gmap->private, gpa_to_gfn(gaddr)); + if (page) + rc = __gmap_destroy_page(gmap, page); + kvm_release_page_clean(page); + mmap_read_unlock(gmap->mm); + return rc; +} diff --git a/arch/s390/kvm/gmap.h b/arch/s390/kvm/gmap.h new file mode 100644 index 000000000000..c8f031c9ea5f --- /dev/null +++ b/arch/s390/kvm/gmap.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * KVM guest address space mapping code + * + * Copyright IBM Corp. 2007, 2016, 2025 + * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> + * Claudio Imbrenda <imbrenda@linux.ibm.com> + */ + +#ifndef ARCH_KVM_S390_GMAP_H +#define ARCH_KVM_S390_GMAP_H + +#define GMAP_SHADOW_FAKE_TABLE 1ULL + +int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb); +int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr); +int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr); +struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, int edat_level); + +/** + * 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. + * + */ +static inline 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; +} + +#endif diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 5bbaadf75dc6..610dd44a948b 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -21,6 +21,7 @@ #include "gaccess.h" #include "trace.h" #include "trace-s390.h" +#include "gmap.h" u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu) { @@ -367,7 +368,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu) reg2, &srcaddr, GACC_FETCH, 0); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); - rc = gmap_fault(vcpu->arch.gmap, srcaddr, 0); + rc = kvm_s390_handle_dat_fault(vcpu, srcaddr, 0); if (rc != 0) return rc; @@ -376,7 +377,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu) reg1, &dstaddr, GACC_STORE, 0); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); - rc = gmap_fault(vcpu->arch.gmap, dstaddr, FAULT_FLAG_WRITE); + rc = kvm_s390_handle_dat_fault(vcpu, dstaddr, FOLL_WRITE); if (rc != 0) return rc; @@ -549,7 +550,7 @@ static int handle_pv_uvc(struct kvm_vcpu *vcpu) * If the unpin did not succeed, the guest will exit again for the UVC * and we will retry the unpin. */ - if (rc == -EINVAL) + if (rc == -EINVAL || rc == -ENXIO) return 0; /* * If we got -EAGAIN here, we simply return it. It will eventually diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index d4f031e086fc..07ff0e10cb7f 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -2893,7 +2893,8 @@ int kvm_set_routing_entry(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) { - u64 uaddr; + u64 uaddr_s, uaddr_i; + int idx; switch (ue->type) { /* we store the userspace addresses instead of the guest addresses */ @@ -2901,14 +2902,16 @@ int kvm_set_routing_entry(struct kvm *kvm, if (kvm_is_ucontrol(kvm)) return -EINVAL; e->set = set_adapter_int; - uaddr = gmap_translate(kvm->arch.gmap, ue->u.adapter.summary_addr); - if (uaddr == -EFAULT) - return -EFAULT; - e->adapter.summary_addr = uaddr; - uaddr = gmap_translate(kvm->arch.gmap, ue->u.adapter.ind_addr); - if (uaddr == -EFAULT) + + idx = srcu_read_lock(&kvm->srcu); + uaddr_s = gpa_to_hva(kvm, ue->u.adapter.summary_addr); + uaddr_i = gpa_to_hva(kvm, ue->u.adapter.ind_addr); + srcu_read_unlock(&kvm->srcu, idx); + + if (kvm_is_error_hva(uaddr_s) || kvm_is_error_hva(uaddr_i)) return -EFAULT; - e->adapter.ind_addr = uaddr; + e->adapter.summary_addr = uaddr_s; + e->adapter.ind_addr = uaddr_i; e->adapter.summary_offset = ue->u.adapter.summary_offset; e->adapter.ind_offset = ue->u.adapter.ind_offset; e->adapter.adapter_id = ue->u.adapter.adapter_id; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index d8080c27d45b..ebecb96bacce 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -50,6 +50,7 @@ #include "kvm-s390.h" #include "gaccess.h" #include "pci.h" +#include "gmap.h" #define CREATE_TRACE_POINTS #include "trace.h" @@ -3428,8 +3429,20 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) VM_EVENT(kvm, 3, "vm created with type %lu", type); if (type & KVM_VM_S390_UCONTROL) { + struct kvm_userspace_memory_region2 fake_memslot = { + .slot = KVM_S390_UCONTROL_MEMSLOT, + .guest_phys_addr = 0, + .userspace_addr = 0, + .memory_size = ALIGN_DOWN(TASK_SIZE, _SEGMENT_SIZE), + .flags = 0, + }; + kvm->arch.gmap = NULL; kvm->arch.mem_limit = KVM_S390_NO_MEM_LIMIT; + /* one flat fake memslot covering the whole address-space */ + mutex_lock(&kvm->slots_lock); + KVM_BUG_ON(kvm_set_internal_memslot(kvm, &fake_memslot), kvm); + mutex_unlock(&kvm->slots_lock); } else { if (sclp.hamax == U64_MAX) kvm->arch.mem_limit = TASK_SIZE_MAX; @@ -4498,6 +4511,75 @@ static bool ibs_enabled(struct kvm_vcpu *vcpu) return kvm_s390_test_cpuflags(vcpu, CPUSTAT_IBS); } +static int __kvm_s390_fixup_fault_sync(struct gmap *gmap, gpa_t gaddr, unsigned int flags) +{ + struct kvm *kvm = gmap->private; + gfn_t gfn = gpa_to_gfn(gaddr); + bool unlocked; + hva_t vmaddr; + gpa_t tmp; + int rc; + + if (kvm_is_ucontrol(kvm)) { + tmp = __gmap_translate(gmap, gaddr); + gfn = gpa_to_gfn(tmp); + } + + vmaddr = gfn_to_hva(kvm, gfn); + rc = fixup_user_fault(gmap->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked); + if (!rc) + rc = __gmap_link(gmap, gaddr, vmaddr); + return rc; +} + +/** + * __kvm_s390_mprotect_many() - Apply specified protection to guest pages + * @gmap: the gmap of the guest + * @gpa: the starting guest address + * @npages: how many pages to protect + * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE + * @bits: pgste notification bits to set + * + * Returns: 0 in case of success, < 0 in case of error - see gmap_protect_one() + * + * Context: kvm->srcu and gmap->mm need to be held in read mode + */ +int __kvm_s390_mprotect_many(struct gmap *gmap, gpa_t gpa, u8 npages, unsigned int prot, + unsigned long bits) +{ + unsigned int fault_flag = (prot & PROT_WRITE) ? FAULT_FLAG_WRITE : 0; + gpa_t end = gpa + npages * PAGE_SIZE; + int rc; + + for (; gpa < end; gpa = ALIGN(gpa + 1, rc)) { + rc = gmap_protect_one(gmap, gpa, prot, bits); + if (rc == -EAGAIN) { + __kvm_s390_fixup_fault_sync(gmap, gpa, fault_flag); + rc = gmap_protect_one(gmap, gpa, prot, bits); + } + if (rc < 0) + return rc; + } + + return 0; +} + +static int kvm_s390_mprotect_notify_prefix(struct kvm_vcpu *vcpu) +{ + gpa_t gaddr = kvm_s390_get_prefix(vcpu); + int idx, rc; + + idx = srcu_read_lock(&vcpu->kvm->srcu); + mmap_read_lock(vcpu->arch.gmap->mm); + + rc = __kvm_s390_mprotect_many(vcpu->arch.gmap, gaddr, 2, PROT_WRITE, GMAP_NOTIFY_MPROT); + + mmap_read_unlock(vcpu->arch.gmap->mm); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + + return rc; +} + static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu) { retry: @@ -4513,9 +4595,8 @@ retry: */ if (kvm_check_request(KVM_REQ_REFRESH_GUEST_PREFIX, vcpu)) { int rc; - rc = gmap_mprotect_notify(vcpu->arch.gmap, - kvm_s390_get_prefix(vcpu), - PAGE_SIZE * 2, PROT_WRITE); + + rc = kvm_s390_mprotect_notify_prefix(vcpu); if (rc) { kvm_make_request(KVM_REQ_REFRESH_GUEST_PREFIX, vcpu); return rc; @@ -4766,11 +4847,111 @@ static int vcpu_post_run_addressing_exception(struct kvm_vcpu *vcpu) return kvm_s390_inject_prog_irq(vcpu, &pgm_info); } +static void kvm_s390_assert_primary_as(struct kvm_vcpu *vcpu) +{ + KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm, + "Unexpected program interrupt 0x%x, TEID 0x%016lx", + current->thread.gmap_int_code, current->thread.gmap_teid.val); +} + +/* + * __kvm_s390_handle_dat_fault() - handle a dat fault for the gmap of a vcpu + * @vcpu: the vCPU whose gmap is to be fixed up + * @gfn: the guest frame number used for memslots (including fake memslots) + * @gaddr: the gmap address, does not have to match @gfn for ucontrol gmaps + * @flags: FOLL_* flags + * + * Return: 0 on success, < 0 in case of error. + * Context: The mm lock must not be held before calling. May sleep. + */ +int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, unsigned int flags) +{ + struct kvm_memory_slot *slot; + unsigned int fault_flags; + bool writable, unlocked; + unsigned long vmaddr; + struct page *page; + kvm_pfn_t pfn; + int rc; + + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + if (!slot || slot->flags & KVM_MEMSLOT_INVALID) + return vcpu_post_run_addressing_exception(vcpu); + + fault_flags = flags & FOLL_WRITE ? FAULT_FLAG_WRITE : 0; + if (vcpu->arch.gmap->pfault_enabled) + flags |= FOLL_NOWAIT; + vmaddr = __gfn_to_hva_memslot(slot, gfn); + +try_again: + pfn = __kvm_faultin_pfn(slot, gfn, flags, &writable, &page); + + /* Access outside memory, inject addressing exception */ + if (is_noslot_pfn(pfn)) + return vcpu_post_run_addressing_exception(vcpu); + /* Signal pending: try again */ + if (pfn == KVM_PFN_ERR_SIGPENDING) + return -EAGAIN; + + /* Needs I/O, try to setup async pfault (only possible with FOLL_NOWAIT) */ + if (pfn == KVM_PFN_ERR_NEEDS_IO) { + trace_kvm_s390_major_guest_pfault(vcpu); + if (kvm_arch_setup_async_pf(vcpu)) + return 0; + vcpu->stat.pfault_sync++; + /* Could not setup async pfault, try again synchronously */ + flags &= ~FOLL_NOWAIT; + goto try_again; + } + /* Any other error */ + if (is_error_pfn(pfn)) + return -EFAULT; + + /* Success */ + mmap_read_lock(vcpu->arch.gmap->mm); + /* Mark the userspace PTEs as young and/or dirty, to avoid page fault loops */ + rc = fixup_user_fault(vcpu->arch.gmap->mm, vmaddr, fault_flags, &unlocked); + if (!rc) + rc = __gmap_link(vcpu->arch.gmap, gaddr, vmaddr); + scoped_guard(spinlock, &vcpu->kvm->mmu_lock) { + kvm_release_faultin_page(vcpu->kvm, page, false, writable); + } + mmap_read_unlock(vcpu->arch.gmap->mm); + return rc; +} + +static int vcpu_dat_fault_handler(struct kvm_vcpu *vcpu, unsigned long gaddr, unsigned int flags) +{ + unsigned long gaddr_tmp; + gfn_t gfn; + + gfn = gpa_to_gfn(gaddr); + if (kvm_is_ucontrol(vcpu->kvm)) { + /* + * This translates the per-vCPU guest address into a + * fake guest address, which can then be used with the + * fake memslots that are identity mapping userspace. + * This allows ucontrol VMs to use the normal fault + * resolution path, like normal VMs. + */ + mmap_read_lock(vcpu->arch.gmap->mm); + gaddr_tmp = __gmap_translate(vcpu->arch.gmap, gaddr); + mmap_read_unlock(vcpu->arch.gmap->mm); + if (gaddr_tmp == -EFAULT) { + vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL; + vcpu->run->s390_ucontrol.trans_exc_code = gaddr; + vcpu->run->s390_ucontrol.pgm_code = PGM_SEGMENT_TRANSLATION; + return -EREMOTE; + } + gfn = gpa_to_gfn(gaddr_tmp); + } + return __kvm_s390_handle_dat_fault(vcpu, gfn, gaddr, flags); +} + static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) { unsigned int flags = 0; unsigned long gaddr; - int rc = 0; gaddr = current->thread.gmap_teid.addr * PAGE_SIZE; if (kvm_s390_cur_gmap_fault_is_write()) @@ -4781,9 +4962,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) vcpu->stat.exit_null++; break; case PGM_NON_SECURE_STORAGE_ACCESS: - KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm, - "Unexpected program interrupt 0x%x, TEID 0x%016lx", - current->thread.gmap_int_code, current->thread.gmap_teid.val); + kvm_s390_assert_primary_as(vcpu); /* * This is normal operation; a page belonging to a protected * guest has not been imported yet. Try to import the page into @@ -4794,9 +4973,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) break; case PGM_SECURE_STORAGE_ACCESS: case PGM_SECURE_STORAGE_VIOLATION: - KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm, - "Unexpected program interrupt 0x%x, TEID 0x%016lx", - current->thread.gmap_int_code, current->thread.gmap_teid.val); + kvm_s390_assert_primary_as(vcpu); /* * This can happen after a reboot with asynchronous teardown; * the new guest (normal or protected) will run on top of the @@ -4825,40 +5002,15 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) case PGM_REGION_FIRST_TRANS: case PGM_REGION_SECOND_TRANS: case PGM_REGION_THIRD_TRANS: - KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm, - "Unexpected program interrupt 0x%x, TEID 0x%016lx", - current->thread.gmap_int_code, current->thread.gmap_teid.val); - if (vcpu->arch.gmap->pfault_enabled) { - rc = gmap_fault(vcpu->arch.gmap, gaddr, flags | FAULT_FLAG_RETRY_NOWAIT); - if (rc == -EFAULT) - return vcpu_post_run_addressing_exception(vcpu); - if (rc == -EAGAIN) { - trace_kvm_s390_major_guest_pfault(vcpu); - if (kvm_arch_setup_async_pf(vcpu)) - return 0; - vcpu->stat.pfault_sync++; - } else { - return rc; - } - } - rc = gmap_fault(vcpu->arch.gmap, gaddr, flags); - if (rc == -EFAULT) { - if (kvm_is_ucontrol(vcpu->kvm)) { - vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL; - vcpu->run->s390_ucontrol.trans_exc_code = gaddr; - vcpu->run->s390_ucontrol.pgm_code = 0x10; - return -EREMOTE; - } - return vcpu_post_run_addressing_exception(vcpu); - } - break; + kvm_s390_assert_primary_as(vcpu); + return vcpu_dat_fault_handler(vcpu, gaddr, flags); default: KVM_BUG(1, vcpu->kvm, "Unexpected program interrupt 0x%x, TEID 0x%016lx", current->thread.gmap_int_code, current->thread.gmap_teid.val); send_sig(SIGSEGV, current, 0); break; } - return rc; + return 0; } static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) @@ -5737,7 +5889,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, } #endif case KVM_S390_VCPU_FAULT: { - r = gmap_fault(vcpu->arch.gmap, arg, 0); + idx = srcu_read_lock(&vcpu->kvm->srcu); + r = vcpu_dat_fault_handler(vcpu, arg, 0); + srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } case KVM_ENABLE_CAP: @@ -5853,7 +6007,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, { gpa_t size; - if (kvm_is_ucontrol(kvm)) + if (kvm_is_ucontrol(kvm) && new->id < KVM_USER_MEM_SLOTS) return -EINVAL; /* When we are protected, we should not change the memory slots */ @@ -5905,6 +6059,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, { int rc = 0; + if (kvm_is_ucontrol(kvm)) + return; + switch (change) { case KVM_MR_DELETE: rc = gmap_unmap_segment(kvm->arch.gmap, old->base_gfn * PAGE_SIZE, diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 597d7a71deeb..8d3bbb2dd8d2 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -20,6 +20,8 @@ #include <asm/processor.h> #include <asm/sclp.h> +#define KVM_S390_UCONTROL_MEMSLOT (KVM_USER_MEM_SLOTS + 0) + static inline void kvm_s390_fpu_store(struct kvm_run *run) { fpu_stfpc(&run->s.regs.fpc); @@ -279,6 +281,15 @@ static inline u32 kvm_s390_get_gisa_desc(struct kvm *kvm) return gd; } +static inline hva_t gpa_to_hva(struct kvm *kvm, gpa_t gpa) +{ + hva_t hva = gfn_to_hva(kvm, gpa_to_gfn(gpa)); + + if (!kvm_is_error_hva(hva)) + hva |= offset_in_page(gpa); + return hva; +} + /* implemented in pv.c */ int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc); int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc); @@ -408,6 +419,14 @@ void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu); void kvm_s390_set_cpu_timer(struct kvm_vcpu *vcpu, __u64 cputm); __u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu); int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rc, u16 *rrc); +int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, unsigned int flags); +int __kvm_s390_mprotect_many(struct gmap *gmap, gpa_t gpa, u8 npages, unsigned int prot, + unsigned long bits); + +static inline int kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gpa_t gaddr, unsigned int flags) +{ + return __kvm_s390_handle_dat_fault(vcpu, gpa_to_gfn(gaddr), gaddr, flags); +} /* implemented in diag.c */ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu); diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 75e81ba26d04..22c012aa5206 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -17,6 +17,7 @@ #include <linux/sched/mm.h> #include <linux/mmu_notifier.h> #include "kvm-s390.h" +#include "gmap.h" bool kvm_s390_pv_is_protected(struct kvm *kvm) { @@ -638,10 +639,28 @@ static int unpack_one(struct kvm *kvm, unsigned long addr, u64 tweak, .tweak[1] = offset, }; int ret = gmap_make_secure(kvm->arch.gmap, addr, &uvcb); + unsigned long vmaddr; + bool unlocked; *rc = uvcb.header.rc; *rrc = uvcb.header.rrc; + if (ret == -ENXIO) { + mmap_read_lock(kvm->mm); + vmaddr = gfn_to_hva(kvm, gpa_to_gfn(addr)); + if (kvm_is_error_hva(vmaddr)) { + ret = -EFAULT; + } else { + ret = fixup_user_fault(kvm->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked); + if (!ret) + ret = __gmap_link(kvm->arch.gmap, addr, vmaddr); + } + mmap_read_unlock(kvm->mm); + if (!ret) + return -EAGAIN; + return ret; + } + if (ret && ret != -EAGAIN) KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: failed addr %llx with rc %x rrc %x", uvcb.gaddr, *rc, *rrc); @@ -660,6 +679,8 @@ int kvm_s390_pv_unpack(struct kvm *kvm, unsigned long addr, unsigned long size, KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: start addr %lx size %lx", addr, size); + guard(srcu)(&kvm->srcu); + while (offset < size) { ret = unpack_one(kvm, addr, tweak, offset, rc, rrc); if (ret == -EAGAIN) { diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index a687695d8f68..a78df3a4f353 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -13,6 +13,7 @@ #include <linux/bitmap.h> #include <linux/sched/signal.h> #include <linux/io.h> +#include <linux/mman.h> #include <asm/gmap.h> #include <asm/mmu_context.h> @@ -22,6 +23,11 @@ #include <asm/facility.h> #include "kvm-s390.h" #include "gaccess.h" +#include "gmap.h" + +enum vsie_page_flags { + VSIE_PAGE_IN_USE = 0, +}; struct vsie_page { struct kvm_s390_sie_block scb_s; /* 0x0000 */ @@ -46,7 +52,18 @@ struct vsie_page { gpa_t gvrd_gpa; /* 0x0240 */ gpa_t riccbd_gpa; /* 0x0248 */ gpa_t sdnx_gpa; /* 0x0250 */ - __u8 reserved[0x0700 - 0x0258]; /* 0x0258 */ + /* + * guest address of the original SCB. Remains set for free vsie + * pages, so we can properly look them up in our addr_to_page + * radix tree. + */ + gpa_t scb_gpa; /* 0x0258 */ + /* + * Flags: must be set/cleared atomically after the vsie page can be + * looked up by other CPUs. + */ + unsigned long flags; /* 0x0260 */ + __u8 reserved[0x0700 - 0x0268]; /* 0x0268 */ struct kvm_s390_crypto_cb crycb; /* 0x0700 */ __u8 fac[S390_ARCH_FAC_LIST_SIZE_BYTE]; /* 0x0800 */ }; @@ -584,7 +601,6 @@ void kvm_s390_vsie_gmap_notifier(struct gmap *gmap, unsigned long start, struct kvm *kvm = gmap->private; struct vsie_page *cur; unsigned long prefix; - struct page *page; int i; if (!gmap_is_shadow(gmap)) @@ -594,10 +610,9 @@ void kvm_s390_vsie_gmap_notifier(struct gmap *gmap, unsigned long start, * therefore we can safely reference them all the time. */ for (i = 0; i < kvm->arch.vsie.page_count; i++) { - page = READ_ONCE(kvm->arch.vsie.pages[i]); - if (!page) + cur = READ_ONCE(kvm->arch.vsie.pages[i]); + if (!cur) continue; - cur = page_to_virt(page); if (READ_ONCE(cur->gmap) != gmap) continue; prefix = cur->scb_s.prefix << GUEST_PREFIX_SHIFT; @@ -1345,6 +1360,20 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) return rc; } +/* Try getting a given vsie page, returning "true" on success. */ +static inline bool try_get_vsie_page(struct vsie_page *vsie_page) +{ + if (test_bit(VSIE_PAGE_IN_USE, &vsie_page->flags)) + return false; + return !test_and_set_bit(VSIE_PAGE_IN_USE, &vsie_page->flags); +} + +/* Put a vsie page acquired through get_vsie_page / try_get_vsie_page. */ +static void put_vsie_page(struct vsie_page *vsie_page) +{ + clear_bit(VSIE_PAGE_IN_USE, &vsie_page->flags); +} + /* * Get or create a vsie page for a scb address. * @@ -1355,16 +1384,21 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr) { struct vsie_page *vsie_page; - struct page *page; int nr_vcpus; rcu_read_lock(); - page = radix_tree_lookup(&kvm->arch.vsie.addr_to_page, addr >> 9); + vsie_page = radix_tree_lookup(&kvm->arch.vsie.addr_to_page, addr >> 9); rcu_read_unlock(); - if (page) { - if (page_ref_inc_return(page) == 2) - return page_to_virt(page); - page_ref_dec(page); + if (vsie_page) { + if (try_get_vsie_page(vsie_page)) { + if (vsie_page->scb_gpa == addr) + return vsie_page; + /* + * We raced with someone reusing + putting this vsie + * page before we grabbed it. + */ + put_vsie_page(vsie_page); + } } /* @@ -1375,36 +1409,40 @@ static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr) mutex_lock(&kvm->arch.vsie.mutex); if (kvm->arch.vsie.page_count < nr_vcpus) { - page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO | GFP_DMA); - if (!page) { + vsie_page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO | GFP_DMA); + if (!vsie_page) { mutex_unlock(&kvm->arch.vsie.mutex); return ERR_PTR(-ENOMEM); } - page_ref_inc(page); - kvm->arch.vsie.pages[kvm->arch.vsie.page_count] = page; + __set_bit(VSIE_PAGE_IN_USE, &vsie_page->flags); + kvm->arch.vsie.pages[kvm->arch.vsie.page_count] = vsie_page; kvm->arch.vsie.page_count++; } else { /* reuse an existing entry that belongs to nobody */ while (true) { - page = kvm->arch.vsie.pages[kvm->arch.vsie.next]; - if (page_ref_inc_return(page) == 2) + vsie_page = kvm->arch.vsie.pages[kvm->arch.vsie.next]; + if (try_get_vsie_page(vsie_page)) break; - page_ref_dec(page); kvm->arch.vsie.next++; kvm->arch.vsie.next %= nr_vcpus; } - radix_tree_delete(&kvm->arch.vsie.addr_to_page, page->index >> 9); + if (vsie_page->scb_gpa != ULONG_MAX) + radix_tree_delete(&kvm->arch.vsie.addr_to_page, + vsie_page->scb_gpa >> 9); } - page->index = addr; - /* double use of the same address */ - if (radix_tree_insert(&kvm->arch.vsie.addr_to_page, addr >> 9, page)) { - page_ref_dec(page); + /* Mark it as invalid until it resides in the tree. */ + vsie_page->scb_gpa = ULONG_MAX; + + /* Double use of the same address or allocation failure. */ + if (radix_tree_insert(&kvm->arch.vsie.addr_to_page, addr >> 9, + vsie_page)) { + put_vsie_page(vsie_page); mutex_unlock(&kvm->arch.vsie.mutex); return NULL; } + vsie_page->scb_gpa = addr; mutex_unlock(&kvm->arch.vsie.mutex); - vsie_page = page_to_virt(page); memset(&vsie_page->scb_s, 0, sizeof(struct kvm_s390_sie_block)); release_gmap_shadow(vsie_page); vsie_page->fault_addr = 0; @@ -1412,14 +1450,6 @@ static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr) return vsie_page; } -/* put a vsie page acquired via get_vsie_page */ -static void put_vsie_page(struct kvm *kvm, struct vsie_page *vsie_page) -{ - struct page *page = pfn_to_page(__pa(vsie_page) >> PAGE_SHIFT); - - page_ref_dec(page); -} - int kvm_s390_handle_vsie(struct kvm_vcpu *vcpu) { struct vsie_page *vsie_page; @@ -1470,7 +1500,7 @@ out_unshadow: out_unpin_scb: unpin_scb(vcpu, vsie_page, scb_addr); out_put: - put_vsie_page(vcpu->kvm, vsie_page); + put_vsie_page(vsie_page); return rc < 0 ? rc : 0; } @@ -1486,18 +1516,18 @@ void kvm_s390_vsie_init(struct kvm *kvm) void kvm_s390_vsie_destroy(struct kvm *kvm) { struct vsie_page *vsie_page; - struct page *page; int i; mutex_lock(&kvm->arch.vsie.mutex); for (i = 0; i < kvm->arch.vsie.page_count; i++) { - page = kvm->arch.vsie.pages[i]; + vsie_page = kvm->arch.vsie.pages[i]; kvm->arch.vsie.pages[i] = NULL; - vsie_page = page_to_virt(page); release_gmap_shadow(vsie_page); /* free the radix tree entry */ - radix_tree_delete(&kvm->arch.vsie.addr_to_page, page->index >> 9); - __free_page(page); + if (vsie_page->scb_gpa != ULONG_MAX) + radix_tree_delete(&kvm->arch.vsie.addr_to_page, + vsie_page->scb_gpa >> 9); + free_page((unsigned long)vsie_page); } kvm->arch.vsie.page_count = 0; mutex_unlock(&kvm->arch.vsie.mutex); diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 16b8a36c56de..94d927785800 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -24,6 +24,16 @@ #include <asm/page.h> #include <asm/tlb.h> +/* + * The address is saved in a radix tree directly; NULL would be ambiguous, + * since 0 is a valid address, and NULL is returned when nothing was found. + * The lower bits are ignored by all users of the macro, so it can be used + * to distinguish a valid address 0 from a NULL. + */ +#define VALID_GADDR_FLAG 1 +#define IS_GADDR_VALID(gaddr) ((gaddr) & VALID_GADDR_FLAG) +#define MAKE_VALID_GADDR(gaddr) (((gaddr) & HPAGE_MASK) | VALID_GADDR_FLAG) + #define GMAP_SHADOW_FAKE_TABLE 1ULL static struct page *gmap_alloc_crst(void) @@ -43,7 +53,7 @@ static struct page *gmap_alloc_crst(void) * * Returns a guest address space structure. */ -static struct gmap *gmap_alloc(unsigned long limit) +struct gmap *gmap_alloc(unsigned long limit) { struct gmap *gmap; struct page *page; @@ -70,9 +80,7 @@ static struct gmap *gmap_alloc(unsigned long limit) gmap = kzalloc(sizeof(struct gmap), GFP_KERNEL_ACCOUNT); 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_ACCOUNT); INIT_RADIX_TREE(&gmap->host_to_guest, GFP_ATOMIC | __GFP_ACCOUNT); INIT_RADIX_TREE(&gmap->host_to_rmap, GFP_ATOMIC | __GFP_ACCOUNT); @@ -82,8 +90,6 @@ static struct gmap *gmap_alloc(unsigned long limit) page = gmap_alloc_crst(); if (!page) goto out_free; - page->index = 0; - list_add(&page->lru, &gmap->crst_list); table = page_to_virt(page); crst_table_init(table, etype); gmap->table = table; @@ -97,6 +103,7 @@ out_free: out: return NULL; } +EXPORT_SYMBOL_GPL(gmap_alloc); /** * gmap_create - create a guest address space @@ -185,32 +192,46 @@ static void gmap_rmap_radix_tree_free(struct radix_tree_root *root) } while (nr > 0); } +static void gmap_free_crst(unsigned long *table, bool free_ptes) +{ + bool is_segment = (table[0] & _SEGMENT_ENTRY_TYPE_MASK) == 0; + int i; + + if (is_segment) { + if (!free_ptes) + goto out; + for (i = 0; i < _CRST_ENTRIES; i++) + if (!(table[i] & _SEGMENT_ENTRY_INVALID)) + page_table_free_pgste(page_ptdesc(phys_to_page(table[i]))); + } else { + for (i = 0; i < _CRST_ENTRIES; i++) + if (!(table[i] & _REGION_ENTRY_INVALID)) + gmap_free_crst(__va(table[i] & PAGE_MASK), free_ptes); + } + +out: + free_pages((unsigned long)table, CRST_ALLOC_ORDER); +} + /** * 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. */ -static void gmap_free(struct gmap *gmap) +void gmap_free(struct gmap *gmap) { - struct page *page, *next; - /* 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, CRST_ALLOC_ORDER); + gmap_free_crst(gmap->table, gmap_is_shadow(gmap)); + gmap_radix_tree_free(&gmap->guest_to_host); gmap_radix_tree_free(&gmap->host_to_guest); /* Free additional data for a shadow gmap */ if (gmap_is_shadow(gmap)) { - struct ptdesc *ptdesc, *n; - - /* Free all page tables. */ - list_for_each_entry_safe(ptdesc, n, &gmap->pt_list, pt_list) - page_table_free_pgste(ptdesc); gmap_rmap_radix_tree_free(&gmap->host_to_rmap); /* Release reference to the parent */ gmap_put(gmap->parent); @@ -218,6 +239,7 @@ static void gmap_free(struct gmap *gmap) kfree(gmap); } +EXPORT_SYMBOL_GPL(gmap_free); /** * gmap_get - increase reference counter for guest address space @@ -298,10 +320,8 @@ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table, crst_table_init(new, init); spin_lock(&gmap->guest_table_lock); if (*table & _REGION_ENTRY_INVALID) { - list_add(&page->lru, &gmap->crst_list); *table = __pa(new) | _REGION_ENTRY_LENGTH | (*table & _REGION_ENTRY_TYPE_MASK); - page->index = gaddr; page = NULL; } spin_unlock(&gmap->guest_table_lock); @@ -310,21 +330,23 @@ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table, return 0; } -/** - * __gmap_segment_gaddr - find virtual address from segment pointer - * @entry: pointer to a segment table entry in the guest address space - * - * Returns the virtual address in the guest address space for the segment - */ -static unsigned long __gmap_segment_gaddr(unsigned long *entry) +static unsigned long host_to_guest_lookup(struct gmap *gmap, unsigned long vmaddr) { - struct page *page; - unsigned long offset; + return (unsigned long)radix_tree_lookup(&gmap->host_to_guest, vmaddr >> PMD_SHIFT); +} - offset = (unsigned long) entry / sizeof(unsigned long); - offset = (offset & (PTRS_PER_PMD - 1)) * PMD_SIZE; - page = pmd_pgtable_page((pmd_t *) entry); - return page->index + offset; +static unsigned long host_to_guest_delete(struct gmap *gmap, unsigned long vmaddr) +{ + return (unsigned long)radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT); +} + +static pmd_t *host_to_guest_pmd_delete(struct gmap *gmap, unsigned long vmaddr, + unsigned long *gaddr) +{ + *gaddr = host_to_guest_delete(gmap, vmaddr); + if (IS_GADDR_VALID(*gaddr)) + return (pmd_t *)gmap_table_walk(gmap, *gaddr, 1); + return NULL; } /** @@ -336,16 +358,19 @@ static unsigned long __gmap_segment_gaddr(unsigned long *entry) */ static int __gmap_unlink_by_vmaddr(struct gmap *gmap, unsigned long vmaddr) { - unsigned long *entry; + unsigned long gaddr; int flush = 0; + pmd_t *pmdp; 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) { - flush = (*entry != _SEGMENT_ENTRY_EMPTY); - *entry = _SEGMENT_ENTRY_EMPTY; + + pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr); + if (pmdp) { + flush = (pmd_val(*pmdp) != _SEGMENT_ENTRY_EMPTY); + *pmdp = __pmd(_SEGMENT_ENTRY_EMPTY); } + spin_unlock(&gmap->guest_table_lock); return flush; } @@ -464,26 +489,6 @@ unsigned long __gmap_translate(struct gmap *gmap, unsigned long gaddr) EXPORT_SYMBOL_GPL(__gmap_translate); /** - * gmap_translate - translate a guest address to a user space address - * @gmap: pointer to guest mapping meta data structure - * @gaddr: guest address - * - * Returns user space address which corresponds to the guest address or - * -EFAULT if no such mapping exists. - * This function does not establish potentially missing page table entries. - */ -unsigned long gmap_translate(struct gmap *gmap, unsigned long gaddr) -{ - unsigned long rc; - - mmap_read_lock(gmap->mm); - rc = __gmap_translate(gmap, gaddr); - mmap_read_unlock(gmap->mm); - return rc; -} -EXPORT_SYMBOL_GPL(gmap_translate); - -/** * gmap_unlink - disconnect a page table from the gmap shadow tables * @mm: pointer to the parent mm_struct * @table: pointer to the host page table @@ -582,7 +587,8 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) spin_lock(&gmap->guest_table_lock); if (*table == _SEGMENT_ENTRY_EMPTY) { rc = radix_tree_insert(&gmap->host_to_guest, - vmaddr >> PMD_SHIFT, table); + vmaddr >> PMD_SHIFT, + (void *)MAKE_VALID_GADDR(gaddr)); if (!rc) { if (pmd_leaf(*pmd)) { *table = (pmd_val(*pmd) & @@ -605,130 +611,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) radix_tree_preload_end(); return rc; } - -/** - * fixup_user_fault_nowait - manually resolve a user page fault without waiting - * @mm: mm_struct of target mm - * @address: user address - * @fault_flags:flags to pass down to handle_mm_fault() - * @unlocked: did we unlock the mmap_lock while retrying - * - * This function behaves similarly to fixup_user_fault(), but it guarantees - * that the fault will be resolved without waiting. The function might drop - * and re-acquire the mm lock, in which case @unlocked will be set to true. - * - * The guarantee is that the fault is handled without waiting, but the - * function itself might sleep, due to the lock. - * - * Context: Needs to be called with mm->mmap_lock held in read mode, and will - * return with the lock held in read mode; @unlocked will indicate whether - * the lock has been dropped and re-acquired. This is the same behaviour as - * fixup_user_fault(). - * - * Return: 0 on success, -EAGAIN if the fault cannot be resolved without - * waiting, -EFAULT if the fault cannot be resolved, -ENOMEM if out of - * memory. - */ -static int fixup_user_fault_nowait(struct mm_struct *mm, unsigned long address, - unsigned int fault_flags, bool *unlocked) -{ - struct vm_area_struct *vma; - unsigned int test_flags; - vm_fault_t fault; - int rc; - - fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT; - test_flags = fault_flags & FAULT_FLAG_WRITE ? VM_WRITE : VM_READ; - - vma = find_vma(mm, address); - if (unlikely(!vma || address < vma->vm_start)) - return -EFAULT; - if (unlikely(!(vma->vm_flags & test_flags))) - return -EFAULT; - - fault = handle_mm_fault(vma, address, fault_flags, NULL); - /* the mm lock has been dropped, take it again */ - if (fault & VM_FAULT_COMPLETED) { - *unlocked = true; - mmap_read_lock(mm); - return 0; - } - /* the mm lock has not been dropped */ - if (fault & VM_FAULT_ERROR) { - rc = vm_fault_to_errno(fault, 0); - BUG_ON(!rc); - return rc; - } - /* the mm lock has not been dropped because of FAULT_FLAG_RETRY_NOWAIT */ - if (fault & VM_FAULT_RETRY) - return -EAGAIN; - /* nothing needed to be done and the mm lock has not been dropped */ - return 0; -} - -/** - * __gmap_fault - resolve a fault on a guest address - * @gmap: pointer to guest mapping meta data structure - * @gaddr: guest address - * @fault_flags: flags to pass down to handle_mm_fault() - * - * Context: Needs to be called with mm->mmap_lock held in read mode. Might - * drop and re-acquire the lock. Will always return with the lock held. - */ -static int __gmap_fault(struct gmap *gmap, unsigned long gaddr, unsigned int fault_flags) -{ - unsigned long vmaddr; - bool unlocked; - int rc = 0; - -retry: - unlocked = false; - - vmaddr = __gmap_translate(gmap, gaddr); - if (IS_ERR_VALUE(vmaddr)) - return vmaddr; - - if (fault_flags & FAULT_FLAG_RETRY_NOWAIT) - rc = fixup_user_fault_nowait(gmap->mm, vmaddr, fault_flags, &unlocked); - else - rc = fixup_user_fault(gmap->mm, vmaddr, fault_flags, &unlocked); - if (rc) - return rc; - /* - * In the case that fixup_user_fault unlocked the mmap_lock during - * fault-in, redo __gmap_translate() to avoid racing with a - * map/unmap_segment. - * In particular, __gmap_translate(), fixup_user_fault{,_nowait}(), - * and __gmap_link() must all be called atomically in one go; if the - * lock had been dropped in between, a retry is needed. - */ - if (unlocked) - goto retry; - - return __gmap_link(gmap, gaddr, vmaddr); -} - -/** - * gmap_fault - resolve a fault on a guest address - * @gmap: pointer to guest mapping meta data structure - * @gaddr: guest address - * @fault_flags: flags to pass down to handle_mm_fault() - * - * Returns 0 on success, -ENOMEM for out of memory conditions, -EFAULT if the - * vm address is already mapped to a different guest segment, and -EAGAIN if - * FAULT_FLAG_RETRY_NOWAIT was specified and the fault could not be processed - * immediately. - */ -int gmap_fault(struct gmap *gmap, unsigned long gaddr, unsigned int fault_flags) -{ - int rc; - - mmap_read_lock(gmap->mm); - rc = __gmap_fault(gmap, gaddr, fault_flags); - mmap_read_unlock(gmap->mm); - return rc; -} -EXPORT_SYMBOL_GPL(gmap_fault); +EXPORT_SYMBOL(__gmap_link); /* * this function is assumed to be called with mmap_lock held @@ -853,8 +736,7 @@ static void gmap_call_notifier(struct gmap *gmap, unsigned long start, * * 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 *gmap_table_walk(struct gmap *gmap, unsigned long gaddr, int level) { const int asce_type = gmap->asce & _ASCE_TYPE_MASK; unsigned long *table = gmap->table; @@ -905,6 +787,7 @@ static inline unsigned long *gmap_table_walk(struct gmap *gmap, } return table; } +EXPORT_SYMBOL(gmap_table_walk); /** * gmap_pte_op_walk - walk the gmap page table, get the page table lock @@ -1101,86 +984,40 @@ static int gmap_protect_pte(struct gmap *gmap, unsigned long gaddr, * @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). + * Returns: + * PAGE_SIZE if a small page was successfully protected; + * HPAGE_SIZE if a large page was successfully protected; + * -ENOMEM if out of memory; + * -EFAULT if gaddr is invalid (or mapping for shadows is missing); + * -EAGAIN if the guest mapping is missing and should be fixed by the caller. * - * Called with sg->mm->mmap_lock in read. + * Context: Called with sg->mm->mmap_lock in read. */ -static int gmap_protect_range(struct gmap *gmap, unsigned long gaddr, - unsigned long len, int prot, unsigned long bits) +int gmap_protect_one(struct gmap *gmap, unsigned long gaddr, int prot, unsigned long bits) { - unsigned long vmaddr, dist; pmd_t *pmdp; - int rc; + int rc = 0; BUG_ON(gmap_is_shadow(gmap)); - while (len) { - rc = -EAGAIN; - pmdp = gmap_pmd_op_walk(gmap, gaddr); - if (pmdp) { - if (!pmd_leaf(*pmdp)) { - rc = gmap_protect_pte(gmap, gaddr, pmdp, prot, - bits); - if (!rc) { - len -= PAGE_SIZE; - gaddr += PAGE_SIZE; - } - } else { - rc = gmap_protect_pmd(gmap, gaddr, pmdp, prot, - bits); - if (!rc) { - dist = HPAGE_SIZE - (gaddr & ~HPAGE_MASK); - len = len < dist ? 0 : len - dist; - gaddr = (gaddr & HPAGE_MASK) + HPAGE_SIZE; - } - } - gmap_pmd_op_end(gmap, pmdp); - } - if (rc) { - if (rc == -EINVAL) - return rc; - /* -EAGAIN, fixup of userspace mm and gmap */ - 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; - } - } - return 0; -} + pmdp = gmap_pmd_op_walk(gmap, gaddr); + if (!pmdp) + return -EAGAIN; -/** - * 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 (!pmd_leaf(*pmdp)) { + rc = gmap_protect_pte(gmap, gaddr, pmdp, prot, bits); + if (!rc) + rc = PAGE_SIZE; + } else { + rc = gmap_protect_pmd(gmap, gaddr, pmdp, prot, bits); + if (!rc) + rc = HPAGE_SIZE; + } + gmap_pmd_op_end(gmap, pmdp); - if ((gaddr & ~PAGE_MASK) || (len & ~PAGE_MASK) || gmap_is_shadow(gmap)) - return -EINVAL; - if (!MACHINE_HAS_ESOP && prot == PROT_READ) - return -EINVAL; - mmap_read_lock(gmap->mm); - rc = gmap_protect_range(gmap, gaddr, len, prot, GMAP_NOTIFY_MPROT); - mmap_read_unlock(gmap->mm); return rc; } -EXPORT_SYMBOL_GPL(gmap_mprotect_notify); +EXPORT_SYMBOL_GPL(gmap_protect_one); /** * gmap_read_table - get an unsigned long value from a guest page table using @@ -1414,7 +1251,6 @@ static void gmap_unshadow_pgt(struct gmap *sg, unsigned long raddr) __gmap_unshadow_pgt(sg, raddr, __va(pgt)); /* Free page table */ ptdesc = page_ptdesc(phys_to_page(pgt)); - list_del(&ptdesc->pt_list); page_table_free_pgste(ptdesc); } @@ -1442,7 +1278,6 @@ static void __gmap_unshadow_sgt(struct gmap *sg, unsigned long raddr, __gmap_unshadow_pgt(sg, raddr, __va(pgt)); /* Free page table */ ptdesc = page_ptdesc(phys_to_page(pgt)); - list_del(&ptdesc->pt_list); page_table_free_pgste(ptdesc); } } @@ -1472,7 +1307,6 @@ static void gmap_unshadow_sgt(struct gmap *sg, unsigned long raddr) __gmap_unshadow_sgt(sg, raddr, __va(sgt)); /* Free segment table */ page = phys_to_page(sgt); - list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } @@ -1500,7 +1334,6 @@ static void __gmap_unshadow_r3t(struct gmap *sg, unsigned long raddr, __gmap_unshadow_sgt(sg, raddr, __va(sgt)); /* Free segment table */ page = phys_to_page(sgt); - list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } } @@ -1530,7 +1363,6 @@ static void gmap_unshadow_r3t(struct gmap *sg, unsigned long raddr) __gmap_unshadow_r3t(sg, raddr, __va(r3t)); /* Free region 3 table */ page = phys_to_page(r3t); - list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } @@ -1558,7 +1390,6 @@ static void __gmap_unshadow_r2t(struct gmap *sg, unsigned long raddr, __gmap_unshadow_r3t(sg, raddr, __va(r3t)); /* Free region 3 table */ page = phys_to_page(r3t); - list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } } @@ -1588,7 +1419,6 @@ static void gmap_unshadow_r2t(struct gmap *sg, unsigned long raddr) __gmap_unshadow_r2t(sg, raddr, __va(r2t)); /* Free region 2 table */ page = phys_to_page(r2t); - list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } @@ -1620,7 +1450,6 @@ static void __gmap_unshadow_r1t(struct gmap *sg, unsigned long raddr, r1t[i] = _REGION1_ENTRY_EMPTY; /* Free region 2 table */ page = phys_to_page(r2t); - list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } } @@ -1631,7 +1460,7 @@ static void __gmap_unshadow_r1t(struct gmap *sg, unsigned long raddr, * * Called with sg->guest_table_lock */ -static void gmap_unshadow(struct gmap *sg) +void gmap_unshadow(struct gmap *sg) { unsigned long *table; @@ -1657,143 +1486,7 @@ static void gmap_unshadow(struct gmap *sg) 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); - refcount_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(parent->mm->context.allow_gmap_hpage_1m); - 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->private = parent->private; - 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; - } - } - } - refcount_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 */ - mmap_read_lock(parent->mm); - rc = gmap_protect_range(parent, asce & _ASCE_ORIGIN, - ((asce & _ASCE_TABLE_LENGTH) + 1) * PAGE_SIZE, - PROT_READ, GMAP_NOTIFY_SHADOW); - mmap_read_unlock(parent->mm); - 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); +EXPORT_SYMBOL(gmap_unshadow); /** * gmap_shadow_r2t - create an empty shadow region 2 table @@ -1827,9 +1520,6 @@ int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t, page = gmap_alloc_crst(); if (!page) return -ENOMEM; - page->index = r2t & _REGION_ENTRY_ORIGIN; - if (fake) - page->index |= GMAP_SHADOW_FAKE_TABLE; s_r2t = page_to_phys(page); /* Install shadow region second table */ spin_lock(&sg->guest_table_lock); @@ -1851,7 +1541,6 @@ int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t, _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; @@ -1911,9 +1600,6 @@ int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t, page = gmap_alloc_crst(); if (!page) return -ENOMEM; - page->index = r3t & _REGION_ENTRY_ORIGIN; - if (fake) - page->index |= GMAP_SHADOW_FAKE_TABLE; s_r3t = page_to_phys(page); /* Install shadow region second table */ spin_lock(&sg->guest_table_lock); @@ -1935,7 +1621,6 @@ int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t, _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; @@ -1995,9 +1680,6 @@ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt, page = gmap_alloc_crst(); if (!page) return -ENOMEM; - page->index = sgt & _REGION_ENTRY_ORIGIN; - if (fake) - page->index |= GMAP_SHADOW_FAKE_TABLE; s_sgt = page_to_phys(page); /* Install shadow region second table */ spin_lock(&sg->guest_table_lock); @@ -2019,7 +1701,6 @@ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt, _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; @@ -2052,45 +1733,22 @@ out_free: } EXPORT_SYMBOL_GPL(gmap_shadow_sgt); -/** - * gmap_shadow_pgt_lookup - 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_lock in read. - */ -int gmap_shadow_pgt_lookup(struct gmap *sg, unsigned long saddr, - unsigned long *pgt, int *dat_protection, - int *fake) +static void gmap_pgste_set_pgt_addr(struct ptdesc *ptdesc, unsigned long pgt_addr) { - unsigned long *table; - struct page *page; - int rc; + unsigned long *pgstes = page_to_virt(ptdesc_page(ptdesc)); - 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; + pgstes += _PAGE_ENTRIES; + + pgstes[0] &= ~PGSTE_ST2_MASK; + pgstes[1] &= ~PGSTE_ST2_MASK; + pgstes[2] &= ~PGSTE_ST2_MASK; + pgstes[3] &= ~PGSTE_ST2_MASK; + pgstes[0] |= (pgt_addr >> 16) & PGSTE_ST2_MASK; + pgstes[1] |= pgt_addr & PGSTE_ST2_MASK; + pgstes[2] |= (pgt_addr << 16) & PGSTE_ST2_MASK; + pgstes[3] |= (pgt_addr << 32) & PGSTE_ST2_MASK; } -EXPORT_SYMBOL_GPL(gmap_shadow_pgt_lookup); /** * gmap_shadow_pgt - instantiate a shadow page table @@ -2119,9 +1777,10 @@ int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt, ptdesc = page_table_alloc_pgste(sg->mm); if (!ptdesc) return -ENOMEM; - ptdesc->pt_index = pgt & _SEGMENT_ENTRY_ORIGIN; + origin = pgt & _SEGMENT_ENTRY_ORIGIN; if (fake) - ptdesc->pt_index |= GMAP_SHADOW_FAKE_TABLE; + origin |= GMAP_SHADOW_FAKE_TABLE; + gmap_pgste_set_pgt_addr(ptdesc, origin); s_pgt = page_to_phys(ptdesc_page(ptdesc)); /* Install shadow page table */ spin_lock(&sg->guest_table_lock); @@ -2140,7 +1799,6 @@ int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt, /* 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(&ptdesc->pt_list, &sg->pt_list); if (fake) { /* nothing to protect for fake tables */ *table &= ~_SEGMENT_ENTRY_INVALID; @@ -2318,7 +1976,6 @@ void ptep_notify(struct mm_struct *mm, unsigned long vmaddr, pte_t *pte, unsigned long bits) { unsigned long offset, gaddr = 0; - unsigned long *table; struct gmap *gmap, *sg, *next; offset = ((unsigned long) pte) & (255 * sizeof(pte_t)); @@ -2326,12 +1983,9 @@ void ptep_notify(struct mm_struct *mm, unsigned long vmaddr, rcu_read_lock(); list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) { 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; + gaddr = host_to_guest_lookup(gmap, vmaddr) + offset; spin_unlock(&gmap->guest_table_lock); - if (!table) + if (!IS_GADDR_VALID(gaddr)) continue; if (!list_empty(&gmap->children) && (bits & PGSTE_VSIE_BIT)) { @@ -2391,10 +2045,8 @@ static void gmap_pmdp_clear(struct mm_struct *mm, unsigned long vmaddr, rcu_read_lock(); list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) { spin_lock(&gmap->guest_table_lock); - pmdp = (pmd_t *)radix_tree_delete(&gmap->host_to_guest, - vmaddr >> PMD_SHIFT); + pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr); if (pmdp) { - gaddr = __gmap_segment_gaddr((unsigned long *)pmdp); pmdp_notify_gmap(gmap, pmdp, gaddr); WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE | _SEGMENT_ENTRY_GMAP_UC | @@ -2438,28 +2090,25 @@ EXPORT_SYMBOL_GPL(gmap_pmdp_csp); */ void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr) { - unsigned long *entry, gaddr; + unsigned long gaddr; struct gmap *gmap; pmd_t *pmdp; rcu_read_lock(); list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) { spin_lock(&gmap->guest_table_lock); - entry = radix_tree_delete(&gmap->host_to_guest, - vmaddr >> PMD_SHIFT); - if (entry) { - pmdp = (pmd_t *)entry; - gaddr = __gmap_segment_gaddr(entry); + pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr); + if (pmdp) { pmdp_notify_gmap(gmap, pmdp, gaddr); - WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE | - _SEGMENT_ENTRY_GMAP_UC | - _SEGMENT_ENTRY)); + WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE | + _SEGMENT_ENTRY_GMAP_UC | + _SEGMENT_ENTRY)); if (MACHINE_HAS_TLB_GUEST) __pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE, gmap->asce, IDTE_LOCAL); else if (MACHINE_HAS_IDTE) __pmdp_idte(gaddr, pmdp, 0, 0, IDTE_LOCAL); - *entry = _SEGMENT_ENTRY_EMPTY; + *pmdp = __pmd(_SEGMENT_ENTRY_EMPTY); } spin_unlock(&gmap->guest_table_lock); } @@ -2474,22 +2123,19 @@ EXPORT_SYMBOL_GPL(gmap_pmdp_idte_local); */ void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr) { - unsigned long *entry, gaddr; + unsigned long gaddr; struct gmap *gmap; pmd_t *pmdp; rcu_read_lock(); list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) { spin_lock(&gmap->guest_table_lock); - entry = radix_tree_delete(&gmap->host_to_guest, - vmaddr >> PMD_SHIFT); - if (entry) { - pmdp = (pmd_t *)entry; - gaddr = __gmap_segment_gaddr(entry); + pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr); + if (pmdp) { pmdp_notify_gmap(gmap, pmdp, gaddr); - WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE | - _SEGMENT_ENTRY_GMAP_UC | - _SEGMENT_ENTRY)); + WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE | + _SEGMENT_ENTRY_GMAP_UC | + _SEGMENT_ENTRY)); if (MACHINE_HAS_TLB_GUEST) __pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE, gmap->asce, IDTE_GLOBAL); @@ -2497,7 +2143,7 @@ void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr) __pmdp_idte(gaddr, pmdp, 0, 0, IDTE_GLOBAL); else __pmdp_csp(pmdp); - *entry = _SEGMENT_ENTRY_EMPTY; + *pmdp = __pmd(_SEGMENT_ENTRY_EMPTY); } spin_unlock(&gmap->guest_table_lock); } @@ -2943,49 +2589,6 @@ int __s390_uv_destroy_range(struct mm_struct *mm, unsigned long start, EXPORT_SYMBOL_GPL(__s390_uv_destroy_range); /** - * s390_unlist_old_asce - Remove the topmost level of page tables from the - * list of page tables of the gmap. - * @gmap: the gmap whose table is to be removed - * - * On s390x, KVM keeps a list of all pages containing the page tables of the - * gmap (the CRST list). This list is used at tear down time to free all - * pages that are now not needed anymore. - * - * This function removes the topmost page of the tree (the one pointed to by - * the ASCE) from the CRST list. - * - * This means that it will not be freed when the VM is torn down, and needs - * to be handled separately by the caller, unless a leak is actually - * intended. Notice that this function will only remove the page from the - * list, the page will still be used as a top level page table (and ASCE). - */ -void s390_unlist_old_asce(struct gmap *gmap) -{ - struct page *old; - - old = virt_to_page(gmap->table); - spin_lock(&gmap->guest_table_lock); - list_del(&old->lru); - /* - * Sometimes the topmost page might need to be "removed" multiple - * times, for example if the VM is rebooted into secure mode several - * times concurrently, or if s390_replace_asce fails after calling - * s390_remove_old_asce and is attempted again later. In that case - * the old asce has been removed from the list, and therefore it - * will not be freed when the VM terminates, but the ASCE is still - * in use and still pointed to. - * A subsequent call to replace_asce will follow the pointer and try - * to remove the same page from the list again. - * Therefore it's necessary that the page of the ASCE has valid - * pointers, so list_del can work (and do nothing) without - * dereferencing stale or invalid pointers. - */ - INIT_LIST_HEAD(&old->lru); - spin_unlock(&gmap->guest_table_lock); -} -EXPORT_SYMBOL_GPL(s390_unlist_old_asce); - -/** * s390_replace_asce - Try to replace the current ASCE of a gmap with a copy * @gmap: the gmap whose ASCE needs to be replaced * @@ -3004,8 +2607,6 @@ int s390_replace_asce(struct gmap *gmap) struct page *page; void *table; - s390_unlist_old_asce(gmap); - /* Replacing segment type ASCEs would cause serious issues */ if ((gmap->asce & _ASCE_TYPE_MASK) == _ASCE_TYPE_SEGMENT) return -EINVAL; @@ -3013,19 +2614,9 @@ int s390_replace_asce(struct gmap *gmap) page = gmap_alloc_crst(); if (!page) return -ENOMEM; - page->index = 0; table = page_to_virt(page); memcpy(table, gmap->table, 1UL << (CRST_ALLOC_ORDER + PAGE_SHIFT)); - /* - * The caller has to deal with the old ASCE, but here we make sure - * the new one is properly added to the CRST list, so that - * it will be freed when the VM is torn down. - */ - spin_lock(&gmap->guest_table_lock); - list_add(&page->lru, &gmap->crst_list); - spin_unlock(&gmap->guest_table_lock); - /* Set new table origin while preserving existing ASCE control bits */ asce = (gmap->asce & ~_ASCE_ORIGIN) | __pa(table); WRITE_ONCE(gmap->asce, asce); @@ -3035,3 +2626,31 @@ int s390_replace_asce(struct gmap *gmap) return 0; } EXPORT_SYMBOL_GPL(s390_replace_asce); + +/** + * kvm_s390_wiggle_split_folio() - try to drain extra references to a folio and optionally split + * @mm: the mm containing the folio to work on + * @folio: the folio + * @split: whether to split a large folio + * + * Context: Must be called while holding an extra reference to the folio; + * the mm lock should not be held. + */ +int kvm_s390_wiggle_split_folio(struct mm_struct *mm, struct folio *folio, bool split) +{ + int rc; + + lockdep_assert_not_held(&mm->mmap_lock); + folio_wait_writeback(folio); + lru_add_drain_all(); + if (split) { + folio_lock(folio); + rc = split_folio(folio); + folio_unlock(folio); + + if (rc != -EBUSY) + return rc; + } + return -EAGAIN; +} +EXPORT_SYMBOL_GPL(kvm_s390_wiggle_split_folio); diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index cd2fef79ad2c..30387a6e98ff 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -176,8 +176,6 @@ unsigned long *page_table_alloc(struct mm_struct *mm) } table = ptdesc_to_virt(ptdesc); __arch_set_page_dat(table, 1); - /* pt_list is used by gmap only */ - INIT_LIST_HEAD(&ptdesc->pt_list); memset64((u64 *)table, _PAGE_INVALID, PTRS_PER_PTE); memset64((u64 *)table + PTRS_PER_PTE, 0, PTRS_PER_PTE); return table; diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index 857afbc4828f..39a481ec4a40 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -331,6 +331,17 @@ error: return rc; } +static bool zpci_bus_is_isolated_vf(struct zpci_bus *zbus, struct zpci_dev *zdev) +{ + struct pci_dev *pdev; + + pdev = zpci_iov_find_parent_pf(zbus, zdev); + if (!pdev) + return true; + pci_dev_put(pdev); + return false; +} + int zpci_bus_device_register(struct zpci_dev *zdev, struct pci_ops *ops) { bool topo_is_tid = zdev->tid_avail; @@ -345,6 +356,15 @@ int zpci_bus_device_register(struct zpci_dev *zdev, struct pci_ops *ops) topo = topo_is_tid ? zdev->tid : zdev->pchid; zbus = zpci_bus_get(topo, topo_is_tid); + /* + * An isolated VF gets its own domain/bus even if there exists + * a matching domain/bus already + */ + if (zbus && zpci_bus_is_isolated_vf(zbus, zdev)) { + zpci_bus_put(zbus); + zbus = NULL; + } + if (!zbus) { zbus = zpci_bus_alloc(topo, topo_is_tid); if (!zbus) diff --git a/arch/s390/pci/pci_iov.c b/arch/s390/pci/pci_iov.c index ead062bf2b41..191e56a623f6 100644 --- a/arch/s390/pci/pci_iov.c +++ b/arch/s390/pci/pci_iov.c @@ -60,18 +60,35 @@ static int zpci_iov_link_virtfn(struct pci_dev *pdev, struct pci_dev *virtfn, in return 0; } -int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn) +/** + * zpci_iov_find_parent_pf - Find the parent PF, if any, of the given function + * @zbus: The bus that the PCI function is on, or would be added on + * @zdev: The PCI function + * + * Finds the parent PF, if it exists and is configured, of the given PCI function + * and increments its refcount. Th PF is searched for on the provided bus so the + * caller has to ensure that this is the correct bus to search. This function may + * be used before adding the PCI function to a zbus. + * + * Return: Pointer to the struct pci_dev of the parent PF or NULL if it not + * found. If the function is not a VF or has no RequesterID information, + * NULL is returned as well. + */ +struct pci_dev *zpci_iov_find_parent_pf(struct zpci_bus *zbus, struct zpci_dev *zdev) { - int i, cand_devfn; - struct zpci_dev *zdev; + int i, vfid, devfn, cand_devfn; struct pci_dev *pdev; - int vfid = vfn - 1; /* Linux' vfid's start at 0 vfn at 1*/ - int rc = 0; if (!zbus->multifunction) - return 0; - - /* If the parent PF for the given VF is also configured in the + return NULL; + /* Non-VFs and VFs without RID available don't have a parent */ + if (!zdev->vfn || !zdev->rid_available) + return NULL; + /* Linux vfid starts at 0 vfn at 1 */ + vfid = zdev->vfn - 1; + devfn = zdev->rid & ZPCI_RID_MASK_DEVFN; + /* + * If the parent PF for the given VF is also configured in the * instance, it must be on the same zbus. * We can then identify the parent PF by checking what * devfn the VF would have if it belonged to that PF using the PF's @@ -85,15 +102,26 @@ int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn if (!pdev) continue; cand_devfn = pci_iov_virtfn_devfn(pdev, vfid); - if (cand_devfn == virtfn->devfn) { - rc = zpci_iov_link_virtfn(pdev, virtfn, vfid); - /* balance pci_get_slot() */ - pci_dev_put(pdev); - break; - } + if (cand_devfn == devfn) + return pdev; /* balance pci_get_slot() */ pci_dev_put(pdev); } } + return NULL; +} + +int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn) +{ + struct zpci_dev *zdev = to_zpci(virtfn); + struct pci_dev *pdev_pf; + int rc = 0; + + pdev_pf = zpci_iov_find_parent_pf(zbus, zdev); + if (pdev_pf) { + /* Linux' vfids start at 0 while zdev->vfn starts at 1 */ + rc = zpci_iov_link_virtfn(pdev_pf, virtfn, zdev->vfn - 1); + pci_dev_put(pdev_pf); + } return rc; } diff --git a/arch/s390/pci/pci_iov.h b/arch/s390/pci/pci_iov.h index e3fa4e77fc86..d2c2793eb0f3 100644 --- a/arch/s390/pci/pci_iov.h +++ b/arch/s390/pci/pci_iov.h @@ -19,6 +19,8 @@ void zpci_iov_map_resources(struct pci_dev *pdev); int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn); +struct pci_dev *zpci_iov_find_parent_pf(struct zpci_bus *zbus, struct zpci_dev *zdev); + #else /* CONFIG_PCI_IOV */ static inline void zpci_iov_remove_virtfn(struct pci_dev *pdev, int vfn) {} @@ -28,5 +30,10 @@ static inline int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *v { return 0; } + +static inline struct pci_dev *zpci_iov_find_parent_pf(struct zpci_bus *zbus, struct zpci_dev *zdev) +{ + return NULL; +} #endif /* CONFIG_PCI_IOV */ #endif /* __S390_PCI_IOV_h */ diff --git a/arch/um/drivers/virt-pci.c b/arch/um/drivers/virt-pci.c index 744e7f31e8ef..dd5580f975cc 100644 --- a/arch/um/drivers/virt-pci.c +++ b/arch/um/drivers/virt-pci.c @@ -25,8 +25,10 @@ #define MAX_IRQ_MSG_SIZE (sizeof(struct virtio_pcidev_msg) + sizeof(u32)) #define NUM_IRQ_MSGS 10 -#define HANDLE_NO_FREE(ptr) ((void *)((unsigned long)(ptr) | 1)) -#define HANDLE_IS_NO_FREE(ptr) ((unsigned long)(ptr) & 1) +struct um_pci_message_buffer { + struct virtio_pcidev_msg hdr; + u8 data[8]; +}; struct um_pci_device { struct virtio_device *vdev; @@ -36,6 +38,11 @@ struct um_pci_device { struct virtqueue *cmd_vq, *irq_vq; +#define UM_PCI_WRITE_BUFS 20 + struct um_pci_message_buffer bufs[UM_PCI_WRITE_BUFS + 1]; + void *extra_ptrs[UM_PCI_WRITE_BUFS + 1]; + DECLARE_BITMAP(used_bufs, UM_PCI_WRITE_BUFS); + #define UM_PCI_STAT_WAITING 0 unsigned long status; @@ -61,12 +68,40 @@ static unsigned long um_pci_msi_used[BITS_TO_LONGS(MAX_MSI_VECTORS)]; static unsigned int um_pci_max_delay_us = 40000; module_param_named(max_delay_us, um_pci_max_delay_us, uint, 0644); -struct um_pci_message_buffer { - struct virtio_pcidev_msg hdr; - u8 data[8]; -}; +static int um_pci_get_buf(struct um_pci_device *dev, bool *posted) +{ + int i; + + for (i = 0; i < UM_PCI_WRITE_BUFS; i++) { + if (!test_and_set_bit(i, dev->used_bufs)) + return i; + } -static struct um_pci_message_buffer __percpu *um_pci_msg_bufs; + *posted = false; + return UM_PCI_WRITE_BUFS; +} + +static void um_pci_free_buf(struct um_pci_device *dev, void *buf) +{ + int i; + + if (buf == &dev->bufs[UM_PCI_WRITE_BUFS]) { + kfree(dev->extra_ptrs[UM_PCI_WRITE_BUFS]); + dev->extra_ptrs[UM_PCI_WRITE_BUFS] = NULL; + return; + } + + for (i = 0; i < UM_PCI_WRITE_BUFS; i++) { + if (buf == &dev->bufs[i]) { + kfree(dev->extra_ptrs[i]); + dev->extra_ptrs[i] = NULL; + WARN_ON(!test_and_clear_bit(i, dev->used_bufs)); + return; + } + } + + WARN_ON(1); +} static int um_pci_send_cmd(struct um_pci_device *dev, struct virtio_pcidev_msg *cmd, @@ -82,7 +117,9 @@ static int um_pci_send_cmd(struct um_pci_device *dev, }; struct um_pci_message_buffer *buf; int delay_count = 0; + bool bounce_out; int ret, len; + int buf_idx; bool posted; if (WARN_ON(cmd_size < sizeof(*cmd) || cmd_size > sizeof(*buf))) @@ -101,26 +138,28 @@ static int um_pci_send_cmd(struct um_pci_device *dev, break; } - buf = get_cpu_var(um_pci_msg_bufs); - if (buf) - memcpy(buf, cmd, cmd_size); + bounce_out = !posted && cmd_size <= sizeof(*cmd) && + out && out_size <= sizeof(buf->data); - if (posted) { - u8 *ncmd = kmalloc(cmd_size + extra_size, GFP_ATOMIC); - - if (ncmd) { - memcpy(ncmd, cmd, cmd_size); - if (extra) - memcpy(ncmd + cmd_size, extra, extra_size); - cmd = (void *)ncmd; - cmd_size += extra_size; - extra = NULL; - extra_size = 0; - } else { - /* try without allocating memory */ - posted = false; - cmd = (void *)buf; + buf_idx = um_pci_get_buf(dev, &posted); + buf = &dev->bufs[buf_idx]; + memcpy(buf, cmd, cmd_size); + + if (posted && extra && extra_size > sizeof(buf) - cmd_size) { + dev->extra_ptrs[buf_idx] = kmemdup(extra, extra_size, + GFP_ATOMIC); + + if (!dev->extra_ptrs[buf_idx]) { + um_pci_free_buf(dev, buf); + return -ENOMEM; } + extra = dev->extra_ptrs[buf_idx]; + } else if (extra && extra_size <= sizeof(buf) - cmd_size) { + memcpy((u8 *)buf + cmd_size, extra, extra_size); + cmd_size += extra_size; + extra_size = 0; + extra = NULL; + cmd = (void *)buf; } else { cmd = (void *)buf; } @@ -128,39 +167,40 @@ static int um_pci_send_cmd(struct um_pci_device *dev, sg_init_one(&out_sg, cmd, cmd_size); if (extra) sg_init_one(&extra_sg, extra, extra_size); - if (out) + /* allow stack for small buffers */ + if (bounce_out) + sg_init_one(&in_sg, buf->data, out_size); + else if (out) sg_init_one(&in_sg, out, out_size); /* add to internal virtio queue */ ret = virtqueue_add_sgs(dev->cmd_vq, sgs_list, extra ? 2 : 1, out ? 1 : 0, - posted ? cmd : HANDLE_NO_FREE(cmd), - GFP_ATOMIC); + cmd, GFP_ATOMIC); if (ret) { - if (posted) - kfree(cmd); - goto out; + um_pci_free_buf(dev, buf); + return ret; } if (posted) { virtqueue_kick(dev->cmd_vq); - ret = 0; - goto out; + return 0; } /* kick and poll for getting a response on the queue */ set_bit(UM_PCI_STAT_WAITING, &dev->status); virtqueue_kick(dev->cmd_vq); + ret = 0; while (1) { void *completed = virtqueue_get_buf(dev->cmd_vq, &len); - if (completed == HANDLE_NO_FREE(cmd)) + if (completed == buf) break; - if (completed && !HANDLE_IS_NO_FREE(completed)) - kfree(completed); + if (completed) + um_pci_free_buf(dev, completed); if (WARN_ONCE(virtqueue_is_broken(dev->cmd_vq) || ++delay_count > um_pci_max_delay_us, @@ -172,8 +212,11 @@ static int um_pci_send_cmd(struct um_pci_device *dev, } clear_bit(UM_PCI_STAT_WAITING, &dev->status); -out: - put_cpu_var(um_pci_msg_bufs); + if (bounce_out) + memcpy(out, buf->data, out_size); + + um_pci_free_buf(dev, buf); + return ret; } @@ -187,20 +230,13 @@ static unsigned long um_pci_cfgspace_read(void *priv, unsigned int offset, .size = size, .addr = offset, }; - /* buf->data is maximum size - we may only use parts of it */ - struct um_pci_message_buffer *buf; - u8 *data; - unsigned long ret = ULONG_MAX; - size_t bytes = sizeof(buf->data); + /* max 8, we might not use it all */ + u8 data[8]; if (!dev) return ULONG_MAX; - buf = get_cpu_var(um_pci_msg_bufs); - data = buf->data; - - if (buf) - memset(data, 0xff, bytes); + memset(data, 0xff, sizeof(data)); switch (size) { case 1: @@ -212,34 +248,26 @@ static unsigned long um_pci_cfgspace_read(void *priv, unsigned int offset, break; default: WARN(1, "invalid config space read size %d\n", size); - goto out; + return ULONG_MAX; } - if (um_pci_send_cmd(dev, &hdr, sizeof(hdr), NULL, 0, data, bytes)) - goto out; + if (um_pci_send_cmd(dev, &hdr, sizeof(hdr), NULL, 0, data, size)) + return ULONG_MAX; switch (size) { case 1: - ret = data[0]; - break; + return data[0]; case 2: - ret = le16_to_cpup((void *)data); - break; + return le16_to_cpup((void *)data); case 4: - ret = le32_to_cpup((void *)data); - break; + return le32_to_cpup((void *)data); #ifdef CONFIG_64BIT case 8: - ret = le64_to_cpup((void *)data); - break; + return le64_to_cpup((void *)data); #endif default: - break; + return ULONG_MAX; } - -out: - put_cpu_var(um_pci_msg_bufs); - return ret; } static void um_pci_cfgspace_write(void *priv, unsigned int offset, int size, @@ -312,13 +340,8 @@ static void um_pci_bar_copy_from(void *priv, void *buffer, static unsigned long um_pci_bar_read(void *priv, unsigned int offset, int size) { - /* buf->data is maximum size - we may only use parts of it */ - struct um_pci_message_buffer *buf; - u8 *data; - unsigned long ret = ULONG_MAX; - - buf = get_cpu_var(um_pci_msg_bufs); - data = buf->data; + /* 8 is maximum size - we may only use parts of it */ + u8 data[8]; switch (size) { case 1: @@ -330,33 +353,25 @@ static unsigned long um_pci_bar_read(void *priv, unsigned int offset, break; default: WARN(1, "invalid config space read size %d\n", size); - goto out; + return ULONG_MAX; } um_pci_bar_copy_from(priv, data, offset, size); switch (size) { case 1: - ret = data[0]; - break; + return data[0]; case 2: - ret = le16_to_cpup((void *)data); - break; + return le16_to_cpup((void *)data); case 4: - ret = le32_to_cpup((void *)data); - break; + return le32_to_cpup((void *)data); #ifdef CONFIG_64BIT case 8: - ret = le64_to_cpup((void *)data); - break; + return le64_to_cpup((void *)data); #endif default: - break; + return ULONG_MAX; } - -out: - put_cpu_var(um_pci_msg_bufs); - return ret; } static void um_pci_bar_copy_to(void *priv, unsigned int offset, @@ -523,11 +538,8 @@ static void um_pci_cmd_vq_cb(struct virtqueue *vq) if (test_bit(UM_PCI_STAT_WAITING, &dev->status)) return; - while ((cmd = virtqueue_get_buf(vq, &len))) { - if (WARN_ON(HANDLE_IS_NO_FREE(cmd))) - continue; - kfree(cmd); - } + while ((cmd = virtqueue_get_buf(vq, &len))) + um_pci_free_buf(dev, cmd); } static void um_pci_irq_vq_cb(struct virtqueue *vq) @@ -1006,10 +1018,6 @@ static int __init um_pci_init(void) "No virtio device ID configured for PCI - no PCI support\n")) return 0; - um_pci_msg_bufs = alloc_percpu(struct um_pci_message_buffer); - if (!um_pci_msg_bufs) - return -ENOMEM; - bridge = pci_alloc_host_bridge(0); if (!bridge) { err = -ENOMEM; @@ -1070,7 +1078,6 @@ free: pci_free_resource_list(&bridge->windows); pci_free_host_bridge(bridge); } - free_percpu(um_pci_msg_bufs); return err; } module_init(um_pci_init); @@ -1082,6 +1089,5 @@ static void __exit um_pci_exit(void) irq_domain_remove(um_pci_inner_domain); pci_free_resource_list(&bridge->windows); pci_free_host_bridge(bridge); - free_percpu(um_pci_msg_bufs); } module_exit(um_pci_exit); diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c index 65df43fa9be5..ad8d78fb1d9a 100644 --- a/arch/um/drivers/virtio_uml.c +++ b/arch/um/drivers/virtio_uml.c @@ -52,7 +52,7 @@ struct virtio_uml_device { struct platform_device *pdev; struct virtio_uml_platform_data *pdata; - spinlock_t sock_lock; + raw_spinlock_t sock_lock; int sock, req_fd, irq; u64 features; u64 protocol_features; @@ -246,7 +246,7 @@ static int vhost_user_send(struct virtio_uml_device *vu_dev, if (request_ack) msg->header.flags |= VHOST_USER_FLAG_NEED_REPLY; - spin_lock_irqsave(&vu_dev->sock_lock, flags); + raw_spin_lock_irqsave(&vu_dev->sock_lock, flags); rc = full_sendmsg_fds(vu_dev->sock, msg, size, fds, num_fds); if (rc < 0) goto out; @@ -266,7 +266,7 @@ static int vhost_user_send(struct virtio_uml_device *vu_dev, } out: - spin_unlock_irqrestore(&vu_dev->sock_lock, flags); + raw_spin_unlock_irqrestore(&vu_dev->sock_lock, flags); return rc; } @@ -1239,7 +1239,7 @@ static int virtio_uml_probe(struct platform_device *pdev) goto error_free; vu_dev->sock = rc; - spin_lock_init(&vu_dev->sock_lock); + raw_spin_lock_init(&vu_dev->sock_lock); rc = vhost_user_init(vu_dev); if (rc) diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c index 338450741aac..a4991746f5ea 100644 --- a/arch/um/kernel/irq.c +++ b/arch/um/kernel/irq.c @@ -52,7 +52,7 @@ struct irq_entry { bool sigio_workaround; }; -static DEFINE_SPINLOCK(irq_lock); +static DEFINE_RAW_SPINLOCK(irq_lock); static LIST_HEAD(active_fds); static DECLARE_BITMAP(irqs_allocated, UM_LAST_SIGNAL_IRQ); static bool irqs_suspended; @@ -257,7 +257,7 @@ static struct irq_entry *get_irq_entry_by_fd(int fd) return NULL; } -static void free_irq_entry(struct irq_entry *to_free, bool remove) +static void remove_irq_entry(struct irq_entry *to_free, bool remove) { if (!to_free) return; @@ -265,7 +265,6 @@ static void free_irq_entry(struct irq_entry *to_free, bool remove) if (remove) os_del_epoll_fd(to_free->fd); list_del(&to_free->list); - kfree(to_free); } static bool update_irq_entry(struct irq_entry *entry) @@ -286,17 +285,19 @@ static bool update_irq_entry(struct irq_entry *entry) return false; } -static void update_or_free_irq_entry(struct irq_entry *entry) +static struct irq_entry *update_or_remove_irq_entry(struct irq_entry *entry) { - if (!update_irq_entry(entry)) - free_irq_entry(entry, false); + if (update_irq_entry(entry)) + return NULL; + remove_irq_entry(entry, false); + return entry; } static int activate_fd(int irq, int fd, enum um_irq_type type, void *dev_id, void (*timetravel_handler)(int, int, void *, struct time_travel_event *)) { - struct irq_entry *irq_entry; + struct irq_entry *irq_entry, *to_free = NULL; int err, events = os_event_mask(type); unsigned long flags; @@ -304,9 +305,10 @@ static int activate_fd(int irq, int fd, enum um_irq_type type, void *dev_id, if (err < 0) goto out; - spin_lock_irqsave(&irq_lock, flags); + raw_spin_lock_irqsave(&irq_lock, flags); irq_entry = get_irq_entry_by_fd(fd); if (irq_entry) { +already: /* cannot register the same FD twice with the same type */ if (WARN_ON(irq_entry->reg[type].events)) { err = -EALREADY; @@ -316,11 +318,22 @@ static int activate_fd(int irq, int fd, enum um_irq_type type, void *dev_id, /* temporarily disable to avoid IRQ-side locking */ os_del_epoll_fd(fd); } else { - irq_entry = kzalloc(sizeof(*irq_entry), GFP_ATOMIC); - if (!irq_entry) { - err = -ENOMEM; - goto out_unlock; + struct irq_entry *new; + + /* don't restore interrupts */ + raw_spin_unlock(&irq_lock); + new = kzalloc(sizeof(*irq_entry), GFP_ATOMIC); + if (!new) { + local_irq_restore(flags); + return -ENOMEM; } + raw_spin_lock(&irq_lock); + irq_entry = get_irq_entry_by_fd(fd); + if (irq_entry) { + to_free = new; + goto already; + } + irq_entry = new; irq_entry->fd = fd; list_add_tail(&irq_entry->list, &active_fds); maybe_sigio_broken(fd); @@ -339,12 +352,11 @@ static int activate_fd(int irq, int fd, enum um_irq_type type, void *dev_id, #endif WARN_ON(!update_irq_entry(irq_entry)); - spin_unlock_irqrestore(&irq_lock, flags); - - return 0; + err = 0; out_unlock: - spin_unlock_irqrestore(&irq_lock, flags); + raw_spin_unlock_irqrestore(&irq_lock, flags); out: + kfree(to_free); return err; } @@ -358,19 +370,20 @@ void free_irq_by_fd(int fd) struct irq_entry *to_free; unsigned long flags; - spin_lock_irqsave(&irq_lock, flags); + raw_spin_lock_irqsave(&irq_lock, flags); to_free = get_irq_entry_by_fd(fd); - free_irq_entry(to_free, true); - spin_unlock_irqrestore(&irq_lock, flags); + remove_irq_entry(to_free, true); + raw_spin_unlock_irqrestore(&irq_lock, flags); + kfree(to_free); } EXPORT_SYMBOL(free_irq_by_fd); static void free_irq_by_irq_and_dev(unsigned int irq, void *dev) { - struct irq_entry *entry; + struct irq_entry *entry, *to_free = NULL; unsigned long flags; - spin_lock_irqsave(&irq_lock, flags); + raw_spin_lock_irqsave(&irq_lock, flags); list_for_each_entry(entry, &active_fds, list) { enum um_irq_type i; @@ -386,12 +399,13 @@ static void free_irq_by_irq_and_dev(unsigned int irq, void *dev) os_del_epoll_fd(entry->fd); reg->events = 0; - update_or_free_irq_entry(entry); + to_free = update_or_remove_irq_entry(entry); goto out; } } out: - spin_unlock_irqrestore(&irq_lock, flags); + raw_spin_unlock_irqrestore(&irq_lock, flags); + kfree(to_free); } void deactivate_fd(int fd, int irqnum) @@ -402,7 +416,7 @@ void deactivate_fd(int fd, int irqnum) os_del_epoll_fd(fd); - spin_lock_irqsave(&irq_lock, flags); + raw_spin_lock_irqsave(&irq_lock, flags); entry = get_irq_entry_by_fd(fd); if (!entry) goto out; @@ -414,9 +428,10 @@ void deactivate_fd(int fd, int irqnum) entry->reg[i].events = 0; } - update_or_free_irq_entry(entry); + entry = update_or_remove_irq_entry(entry); out: - spin_unlock_irqrestore(&irq_lock, flags); + raw_spin_unlock_irqrestore(&irq_lock, flags); + kfree(entry); ignore_sigio_fd(fd); } @@ -546,7 +561,7 @@ void um_irqs_suspend(void) irqs_suspended = true; - spin_lock_irqsave(&irq_lock, flags); + raw_spin_lock_irqsave(&irq_lock, flags); list_for_each_entry(entry, &active_fds, list) { enum um_irq_type t; bool clear = true; @@ -579,7 +594,7 @@ void um_irqs_suspend(void) !__ignore_sigio_fd(entry->fd); } } - spin_unlock_irqrestore(&irq_lock, flags); + raw_spin_unlock_irqrestore(&irq_lock, flags); } void um_irqs_resume(void) @@ -588,7 +603,7 @@ void um_irqs_resume(void) unsigned long flags; - spin_lock_irqsave(&irq_lock, flags); + raw_spin_lock_irqsave(&irq_lock, flags); list_for_each_entry(entry, &active_fds, list) { if (entry->suspended) { int err = os_set_fd_async(entry->fd); @@ -602,7 +617,7 @@ void um_irqs_resume(void) } } } - spin_unlock_irqrestore(&irq_lock, flags); + raw_spin_unlock_irqrestore(&irq_lock, flags); irqs_suspended = false; send_sigio_to_self(); @@ -613,7 +628,7 @@ static int normal_irq_set_wake(struct irq_data *d, unsigned int on) struct irq_entry *entry; unsigned long flags; - spin_lock_irqsave(&irq_lock, flags); + raw_spin_lock_irqsave(&irq_lock, flags); list_for_each_entry(entry, &active_fds, list) { enum um_irq_type t; @@ -628,7 +643,7 @@ static int normal_irq_set_wake(struct irq_data *d, unsigned int on) } } unlock: - spin_unlock_irqrestore(&irq_lock, flags); + raw_spin_unlock_irqrestore(&irq_lock, flags); return 0; } #else diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index e5a2d4d897e0..0cd6fad3d908 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -191,7 +191,15 @@ void initial_thread_cb(void (*proc)(void *), void *arg) int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - memcpy(dst, src, arch_task_struct_size); + /* init_task is not dynamically sized (missing FPU state) */ + if (unlikely(src == &init_task)) { + memcpy(dst, src, sizeof(init_task)); + memset((void *)dst + sizeof(init_task), 0, + arch_task_struct_size - sizeof(init_task)); + } else { + memcpy(dst, src, arch_task_struct_size); + } + return 0; } diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index f683cfc9e51a..e2f8f156402f 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -181,6 +181,10 @@ extern char __syscall_stub_start[]; static int stub_exe_fd; +#ifndef CLOSE_RANGE_CLOEXEC +#define CLOSE_RANGE_CLOEXEC (1U << 2) +#endif + static int userspace_tramp(void *stack) { char *const argv[] = { "uml-userspace", NULL }; @@ -202,8 +206,12 @@ static int userspace_tramp(void *stack) init_data.stub_data_fd = phys_mapping(uml_to_phys(stack), &offset); init_data.stub_data_offset = MMAP_OFFSET(offset); - /* Set CLOEXEC on all FDs and then unset on all memory related FDs */ - close_range(0, ~0U, CLOSE_RANGE_CLOEXEC); + /* + * Avoid leaking unneeded FDs to the stub by setting CLOEXEC on all FDs + * and then unsetting it on all memory related FDs. + * This is not strictly necessary from a safety perspective. + */ + syscall(__NR_close_range, 0, ~0U, CLOSE_RANGE_CLOEXEC); fcntl(init_data.stub_data_fd, F_SETFD, 0); for (iomem = iomem_regions; iomem; iomem = iomem->next) @@ -224,7 +232,9 @@ static int userspace_tramp(void *stack) if (ret != sizeof(init_data)) exit(4); - execveat(stub_exe_fd, "", argv, NULL, AT_EMPTY_PATH); + /* Raw execveat for compatibility with older libc versions */ + syscall(__NR_execveat, stub_exe_fd, (unsigned long)"", + (unsigned long)argv, NULL, AT_EMPTY_PATH); exit(5); } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 87198d957e2f..be2c311f5118 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2599,7 +2599,8 @@ config MITIGATION_IBPB_ENTRY depends on CPU_SUP_AMD && X86_64 default y help - Compile the kernel with support for the retbleed=ibpb mitigation. + Compile the kernel with support for the retbleed=ibpb and + spec_rstack_overflow={ibpb,ibpb-vmexit} mitigations. config MITIGATION_IBRS_ENTRY bool "Enable IBRS on kernel entry" diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index f2051644de94..606c74f27459 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -25,6 +25,7 @@ targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \ # avoid errors with '-march=i386', and future flags may depend on the target to # be valid. KBUILD_CFLAGS := -m$(BITS) -O2 $(CLANG_FLAGS) +KBUILD_CFLAGS += -std=gnu11 KBUILD_CFLAGS += -fno-strict-aliasing -fPIE KBUILD_CFLAGS += -Wundef KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7601196d1d18..e86333eee266 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4905,20 +4905,22 @@ static inline bool intel_pmu_broken_perf_cap(void) static void update_pmu_cap(struct x86_hybrid_pmu *pmu) { - unsigned int sub_bitmaps, eax, ebx, ecx, edx; + unsigned int cntr, fixed_cntr, ecx, edx; + union cpuid35_eax eax; + union cpuid35_ebx ebx; - cpuid(ARCH_PERFMON_EXT_LEAF, &sub_bitmaps, &ebx, &ecx, &edx); + cpuid(ARCH_PERFMON_EXT_LEAF, &eax.full, &ebx.full, &ecx, &edx); - if (ebx & ARCH_PERFMON_EXT_UMASK2) + if (ebx.split.umask2) pmu->config_mask |= ARCH_PERFMON_EVENTSEL_UMASK2; - if (ebx & ARCH_PERFMON_EXT_EQ) + if (ebx.split.eq) pmu->config_mask |= ARCH_PERFMON_EVENTSEL_EQ; - if (sub_bitmaps & ARCH_PERFMON_NUM_COUNTER_LEAF_BIT) { + if (eax.split.cntr_subleaf) { cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_NUM_COUNTER_LEAF, - &eax, &ebx, &ecx, &edx); - pmu->cntr_mask64 = eax; - pmu->fixed_cntr_mask64 = ebx; + &cntr, &fixed_cntr, &ecx, &edx); + pmu->cntr_mask64 = cntr; + pmu->fixed_cntr_mask64 = fixed_cntr; } if (!intel_pmu_broken_perf_cap()) { @@ -4941,11 +4943,6 @@ static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu) else pmu->intel_ctrl &= ~(1ULL << GLOBAL_CTRL_EN_PERF_METRICS); - if (pmu->intel_cap.pebs_output_pt_available) - pmu->pmu.capabilities |= PERF_PMU_CAP_AUX_OUTPUT; - else - pmu->pmu.capabilities &= ~PERF_PMU_CAP_AUX_OUTPUT; - intel_pmu_check_event_constraints(pmu->event_constraints, pmu->cntr_mask64, pmu->fixed_cntr_mask64, @@ -5023,9 +5020,6 @@ static bool init_hybrid_pmu(int cpu) pr_info("%s PMU driver: ", pmu->name); - if (pmu->intel_cap.pebs_output_pt_available) - pr_cont("PEBS-via-PT "); - pr_cont("\n"); x86_pmu_show_pmu_cap(&pmu->pmu); @@ -5048,8 +5042,11 @@ static void intel_pmu_cpu_starting(int cpu) init_debug_store_on_cpu(cpu); /* - * Deal with CPUs that don't clear their LBRs on power-up. + * Deal with CPUs that don't clear their LBRs on power-up, and that may + * even boot with LBRs enabled. */ + if (!static_cpu_has(X86_FEATURE_ARCH_LBR) && x86_pmu.lbr_nr) + msr_clear_bit(MSR_IA32_DEBUGCTLMSR, DEBUGCTLMSR_LBR_BIT); intel_pmu_lbr_reset(); cpuc->lbr_sel = NULL; @@ -6370,11 +6367,9 @@ static __always_inline int intel_pmu_init_hybrid(enum hybrid_pmu_type pmus) pmu->intel_cap.capabilities = x86_pmu.intel_cap.capabilities; if (pmu->pmu_type & hybrid_small_tiny) { pmu->intel_cap.perf_metrics = 0; - pmu->intel_cap.pebs_output_pt_available = 1; pmu->mid_ack = true; } else if (pmu->pmu_type & hybrid_big) { pmu->intel_cap.perf_metrics = 1; - pmu->intel_cap.pebs_output_pt_available = 0; pmu->late_ack = true; } } diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index ba74e1198328..c2e2eae7309c 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -2578,7 +2578,15 @@ void __init intel_ds_init(void) } pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual); - if (!is_hybrid() && x86_pmu.intel_cap.pebs_output_pt_available) { + /* + * The PEBS-via-PT is not supported on hybrid platforms, + * because not all CPUs of a hybrid machine support it. + * The global x86_pmu.intel_cap, which only contains the + * common capabilities, is used to check the availability + * of the feature. The per-PMU pebs_output_pt_available + * in a hybrid machine should be ignored. + */ + if (x86_pmu.intel_cap.pebs_output_pt_available) { pr_cont("PEBS-via-PT, "); x86_get_pmu(smp_processor_id())->capabilities |= PERF_PMU_CAP_AUX_OUTPUT; } diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index d3bb3865c1b1..4952faf03e82 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -370,6 +370,10 @@ static int rapl_pmu_event_init(struct perf_event *event) unsigned int rapl_pmu_idx; struct rapl_pmus *rapl_pmus; + /* only look at RAPL events */ + if (event->attr.type != event->pmu->type) + return -ENOENT; + /* unsupported modes and filters */ if (event->attr.sample_period) /* no sampling */ return -EINVAL; @@ -387,10 +391,6 @@ static int rapl_pmu_event_init(struct perf_event *event) rapl_pmus_scope = rapl_pmus->pmu.scope; if (rapl_pmus_scope == PERF_PMU_SCOPE_PKG || rapl_pmus_scope == PERF_PMU_SCOPE_DIE) { - /* only look at RAPL package events */ - if (event->attr.type != rapl_pmus_pkg->pmu.type) - return -ENOENT; - cfg = array_index_nospec((long)cfg, NR_RAPL_PKG_DOMAINS + 1); if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1) return -EINVAL; @@ -398,10 +398,6 @@ static int rapl_pmu_event_init(struct perf_event *event) bit = cfg - 1; event->hw.event_base = rapl_model->rapl_pkg_msrs[bit].msr; } else if (rapl_pmus_scope == PERF_PMU_SCOPE_CORE) { - /* only look at RAPL core events */ - if (event->attr.type != rapl_pmus_core->pmu.type) - return -ENOENT; - cfg = array_index_nospec((long)cfg, NR_RAPL_CORE_DOMAINS + 1); if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1) return -EINVAL; diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index c35550581da0..823c0434bbad 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -48,6 +48,7 @@ KVM_X86_OP(set_idt) KVM_X86_OP(get_gdt) KVM_X86_OP(set_gdt) KVM_X86_OP(sync_dirty_debug_regs) +KVM_X86_OP(set_dr6) KVM_X86_OP(set_dr7) KVM_X86_OP(cache_reg) KVM_X86_OP(get_rflags) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index b15cde0a9b5c..0b7af5902ff7 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1696,6 +1696,7 @@ struct kvm_x86_ops { void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu); + void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value); void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value); void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 9a71880eec07..72765b2fe0d8 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -395,7 +395,8 @@ #define MSR_IA32_PASID_VALID BIT_ULL(31) /* DEBUGCTLMSR bits (others vary by model): */ -#define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */ +#define DEBUGCTLMSR_LBR_BIT 0 /* last branch recording */ +#define DEBUGCTLMSR_LBR (1UL << DEBUGCTLMSR_LBR_BIT) #define DEBUGCTLMSR_BTF_SHIFT 1 #define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */ #define DEBUGCTLMSR_BUS_LOCK_DETECT (1UL << 2) diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 1ac79f361645..0ba8d20f2d1d 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -188,11 +188,33 @@ union cpuid10_edx { * detection/enumeration details: */ #define ARCH_PERFMON_EXT_LEAF 0x00000023 -#define ARCH_PERFMON_EXT_UMASK2 0x1 -#define ARCH_PERFMON_EXT_EQ 0x2 -#define ARCH_PERFMON_NUM_COUNTER_LEAF_BIT 0x1 #define ARCH_PERFMON_NUM_COUNTER_LEAF 0x1 +union cpuid35_eax { + struct { + unsigned int leaf0:1; + /* Counters Sub-Leaf */ + unsigned int cntr_subleaf:1; + /* Auto Counter Reload Sub-Leaf */ + unsigned int acr_subleaf:1; + /* Events Sub-Leaf */ + unsigned int events_subleaf:1; + unsigned int reserved:28; + } split; + unsigned int full; +}; + +union cpuid35_ebx { + struct { + /* UnitMask2 Supported */ + unsigned int umask2:1; + /* EQ-bit Supported */ + unsigned int eq:1; + unsigned int reserved:30; + } split; + unsigned int full; +}; + /* * Intel Architectural LBR CPUID detection/enumeration details: */ diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 5d9685f92e5c..1581246491b5 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -531,6 +531,7 @@ static inline void __init snp_secure_tsc_init(void) { } #ifdef CONFIG_KVM_AMD_SEV bool snp_probe_rmptable_info(void); +int snp_rmptable_init(void); int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level); void snp_dump_hva_rmpentry(unsigned long address); int psmash(u64 pfn); @@ -541,6 +542,7 @@ void kdump_sev_callback(void); void snp_fixup_e820_tables(void); #else static inline bool snp_probe_rmptable_info(void) { return false; } +static inline int snp_rmptable_init(void) { return -ENOSYS; } static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; } static inline void snp_dump_hva_rmpentry(unsigned long address) {} static inline int psmash(u64 pfn) { return -ENODEV; } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 5a505aa65489..a5d0998d7604 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1115,6 +1115,8 @@ do_cmd_auto: case RETBLEED_MITIGATION_IBPB: setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); + setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); + mitigate_smt = true; /* * IBPB on entry already obviates the need for @@ -1124,9 +1126,6 @@ do_cmd_auto: setup_clear_cpu_cap(X86_FEATURE_UNRET); setup_clear_cpu_cap(X86_FEATURE_RETHUNK); - setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); - mitigate_smt = true; - /* * There is no need for RSB filling: entry_ibpb() ensures * all predictions, including the RSB, are invalidated, @@ -2646,6 +2645,7 @@ static void __init srso_select_mitigation(void) if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) { if (has_microcode) { setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); + setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); srso_mitigation = SRSO_MITIGATION_IBPB; /* @@ -2655,6 +2655,13 @@ static void __init srso_select_mitigation(void) */ setup_clear_cpu_cap(X86_FEATURE_UNRET); setup_clear_cpu_cap(X86_FEATURE_RETHUNK); + + /* + * There is no need for RSB filling: entry_ibpb() ensures + * all predictions, including the RSB, are invalidated, + * regardless of IBPB implementation. + */ + setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT); } } else { pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n"); @@ -2663,8 +2670,8 @@ static void __init srso_select_mitigation(void) ibpb_on_vmexit: case SRSO_CMD_IBPB_ON_VMEXIT: - if (IS_ENABLED(CONFIG_MITIGATION_SRSO)) { - if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) { + if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) { + if (has_microcode) { setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT; @@ -2676,8 +2683,8 @@ ibpb_on_vmexit: setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT); } } else { - pr_err("WARNING: kernel not compiled with MITIGATION_SRSO.\n"); - } + pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n"); + } break; default: break; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 2cbb3874ad39..8eb3a88707f2 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -1180,7 +1180,7 @@ void kvm_set_cpu_caps(void) SYNTHESIZED_F(SBPB), SYNTHESIZED_F(IBPB_BRTYPE), SYNTHESIZED_F(SRSO_NO), - SYNTHESIZED_F(SRSO_USER_KERNEL_NO), + F(SRSO_USER_KERNEL_NO), ); kvm_cpu_cap_init(CPUID_8000_0022_EAX, diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 6a6dd5a84f22..6ebeb6cea6c0 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -2226,6 +2226,9 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) u32 vector; bool all_cpus; + if (!lapic_in_kernel(vcpu)) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + if (hc->code == HVCALL_SEND_IPI) { if (!hc->fast) { if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi, @@ -2852,7 +2855,8 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, ent->eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED; ent->eax |= HV_X64_APIC_ACCESS_RECOMMENDED; ent->eax |= HV_X64_RELAXED_TIMING_RECOMMENDED; - ent->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED; + if (!vcpu || lapic_in_kernel(vcpu)) + ent->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED; ent->eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED; if (evmcs_ver) ent->eax |= HV_X64_ENLIGHTENED_VMCS_RECOMMENDED; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index a45ae60e84ab..d4ac4a1f8b81 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5540,7 +5540,7 @@ void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0, union kvm_mmu_page_role root_role; /* NPT requires CR0.PG=1. */ - WARN_ON_ONCE(cpu_role.base.direct); + WARN_ON_ONCE(cpu_role.base.direct || !cpu_role.base.guest_mode); root_role = cpu_role.base; root_role.level = kvm_mmu_get_tdp_level(vcpu); @@ -7120,6 +7120,19 @@ static void mmu_destroy_caches(void) kmem_cache_destroy(mmu_page_header_cache); } +static void kvm_wake_nx_recovery_thread(struct kvm *kvm) +{ + /* + * The NX recovery thread is spawned on-demand at the first KVM_RUN and + * may not be valid even though the VM is globally visible. Do nothing, + * as such a VM can't have any possible NX huge pages. + */ + struct vhost_task *nx_thread = READ_ONCE(kvm->arch.nx_huge_page_recovery_thread); + + if (nx_thread) + vhost_task_wake(nx_thread); +} + static int get_nx_huge_pages(char *buffer, const struct kernel_param *kp) { if (nx_hugepage_mitigation_hard_disabled) @@ -7180,7 +7193,7 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) kvm_mmu_zap_all_fast(kvm); mutex_unlock(&kvm->slots_lock); - vhost_task_wake(kvm->arch.nx_huge_page_recovery_thread); + kvm_wake_nx_recovery_thread(kvm); } mutex_unlock(&kvm_lock); } @@ -7315,7 +7328,7 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) - vhost_task_wake(kvm->arch.nx_huge_page_recovery_thread); + kvm_wake_nx_recovery_thread(kvm); mutex_unlock(&kvm_lock); } @@ -7451,14 +7464,20 @@ static void kvm_mmu_start_lpage_recovery(struct once *once) { struct kvm_arch *ka = container_of(once, struct kvm_arch, nx_once); struct kvm *kvm = container_of(ka, struct kvm, arch); + struct vhost_task *nx_thread; kvm->arch.nx_huge_page_last = get_jiffies_64(); - kvm->arch.nx_huge_page_recovery_thread = vhost_task_create( - kvm_nx_huge_page_recovery_worker, kvm_nx_huge_page_recovery_worker_kill, - kvm, "kvm-nx-lpage-recovery"); + nx_thread = vhost_task_create(kvm_nx_huge_page_recovery_worker, + kvm_nx_huge_page_recovery_worker_kill, + kvm, "kvm-nx-lpage-recovery"); - if (kvm->arch.nx_huge_page_recovery_thread) - vhost_task_start(kvm->arch.nx_huge_page_recovery_thread); + if (!nx_thread) + return; + + vhost_task_start(nx_thread); + + /* Make the task visible only once it is fully started. */ + WRITE_ONCE(kvm->arch.nx_huge_page_recovery_thread, nx_thread); } int kvm_mmu_post_init_vm(struct kvm *kvm) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index d77b094d9a4d..04c375bf1ac2 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -646,6 +646,11 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, u32 pause_count12; u32 pause_thresh12; + nested_svm_transition_tlb_flush(vcpu); + + /* Enter Guest-Mode */ + enter_guest_mode(vcpu); + /* * Filled at exit: exit_code, exit_code_hi, exit_info_1, exit_info_2, * exit_int_info, exit_int_info_err, next_rip, insn_len, insn_bytes. @@ -762,11 +767,6 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, } } - nested_svm_transition_tlb_flush(vcpu); - - /* Enter Guest-Mode */ - enter_guest_mode(vcpu); - /* * Merge guest and host intercepts - must be called with vcpu in * guest-mode to take effect. diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index a2a794c32050..0dbb25442ec1 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2972,6 +2972,16 @@ void __init sev_hardware_setup(void) WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_FLUSHBYASID))) goto out; + /* + * The kernel's initcall infrastructure lacks the ability to express + * dependencies between initcalls, whereas the modules infrastructure + * automatically handles dependencies via symbol loading. Ensure the + * PSP SEV driver is initialized before proceeding if KVM is built-in, + * as the dependency isn't handled by the initcall infrastructure. + */ + if (IS_BUILTIN(CONFIG_KVM_AMD) && sev_module_init()) + goto out; + /* Retrieve SEV CPUID information */ cpuid(0x8000001f, &eax, &ebx, &ecx, &edx); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 7640a84e554a..a713c803a3a3 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1991,11 +1991,11 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd) svm->asid = sd->next_asid++; } -static void svm_set_dr6(struct vcpu_svm *svm, unsigned long value) +static void svm_set_dr6(struct kvm_vcpu *vcpu, unsigned long value) { - struct vmcb *vmcb = svm->vmcb; + struct vmcb *vmcb = to_svm(vcpu)->vmcb; - if (svm->vcpu.arch.guest_state_protected) + if (vcpu->arch.guest_state_protected) return; if (unlikely(value != vmcb->save.dr6)) { @@ -4247,10 +4247,8 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, * Run with all-zero DR6 unless needed, so that we can get the exact cause * of a #DB. */ - if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) - svm_set_dr6(svm, vcpu->arch.dr6); - else - svm_set_dr6(svm, DR6_ACTIVE_LOW); + if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))) + svm_set_dr6(vcpu, DR6_ACTIVE_LOW); clgi(); kvm_load_guest_xsave_state(vcpu); @@ -5043,6 +5041,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .set_idt = svm_set_idt, .get_gdt = svm_get_gdt, .set_gdt = svm_set_gdt, + .set_dr6 = svm_set_dr6, .set_dr7 = svm_set_dr7, .sync_dirty_debug_regs = svm_sync_dirty_debug_regs, .cache_reg = svm_cache_reg, diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c index 2427f918e763..43ee9ed11291 100644 --- a/arch/x86/kvm/vmx/main.c +++ b/arch/x86/kvm/vmx/main.c @@ -61,6 +61,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .set_idt = vmx_set_idt, .get_gdt = vmx_get_gdt, .set_gdt = vmx_set_gdt, + .set_dr6 = vmx_set_dr6, .set_dr7 = vmx_set_dr7, .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs, .cache_reg = vmx_cache_reg, diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index f72835e85b6d..6c56d5235f0f 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -5648,6 +5648,12 @@ void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) set_debugreg(DR6_RESERVED, 6); } +void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val) +{ + lockdep_assert_irqs_disabled(); + set_debugreg(vcpu->arch.dr6, 6); +} + void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) { vmcs_writel(GUEST_DR7, val); @@ -7417,10 +7423,6 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) vmx->loaded_vmcs->host_state.cr4 = cr4; } - /* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */ - if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) - set_debugreg(vcpu->arch.dr6, 6); - /* When single-stepping over STI and MOV SS, we must clear the * corresponding interruptibility bits in the guest state. Otherwise * vmentry fails as it then expects bit 14 (BS) in pending debug diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h index ce3295a67c04..430773a5ef8e 100644 --- a/arch/x86/kvm/vmx/x86_ops.h +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -73,6 +73,7 @@ void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); +void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val); void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val); void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu); void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6d4a6734b2d6..02159c967d29 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10961,6 +10961,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) set_debugreg(vcpu->arch.eff_db[1], 1); set_debugreg(vcpu->arch.eff_db[2], 2); set_debugreg(vcpu->arch.eff_db[3], 3); + /* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */ + if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) + kvm_x86_call(set_dr6)(vcpu, vcpu->arch.dr6); } else if (unlikely(hw_breakpoint_active())) { set_debugreg(0, 7); } @@ -12741,6 +12744,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) "does not run without ignore_msrs=1, please report it to kvm@vger.kernel.org.\n"); } + once_init(&kvm->arch.nx_once); return 0; out_uninit_mmu: @@ -12750,12 +12754,6 @@ out: return ret; } -int kvm_arch_post_init_vm(struct kvm *kvm) -{ - once_init(&kvm->arch.nx_once); - return 0; -} - static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) { vcpu_load(vcpu); diff --git a/arch/x86/um/os-Linux/registers.c b/arch/x86/um/os-Linux/registers.c index 76eaeb93928c..eb1cdadc8a61 100644 --- a/arch/x86/um/os-Linux/registers.c +++ b/arch/x86/um/os-Linux/registers.c @@ -18,6 +18,7 @@ #include <registers.h> #include <sys/mman.h> +static unsigned long ptrace_regset; unsigned long host_fp_size; int get_fp_registers(int pid, unsigned long *regs) @@ -27,7 +28,7 @@ int get_fp_registers(int pid, unsigned long *regs) .iov_len = host_fp_size, }; - if (ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov) < 0) + if (ptrace(PTRACE_GETREGSET, pid, ptrace_regset, &iov) < 0) return -errno; return 0; } @@ -39,7 +40,7 @@ int put_fp_registers(int pid, unsigned long *regs) .iov_len = host_fp_size, }; - if (ptrace(PTRACE_SETREGSET, pid, NT_X86_XSTATE, &iov) < 0) + if (ptrace(PTRACE_SETREGSET, pid, ptrace_regset, &iov) < 0) return -errno; return 0; } @@ -58,9 +59,23 @@ int arch_init_registers(int pid) return -ENOMEM; /* GDB has x86_xsave_length, which uses x86_cpuid_count */ - ret = ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov); + ptrace_regset = NT_X86_XSTATE; + ret = ptrace(PTRACE_GETREGSET, pid, ptrace_regset, &iov); if (ret) ret = -errno; + + if (ret == -ENODEV) { +#ifdef CONFIG_X86_32 + ptrace_regset = NT_PRXFPREG; +#else + ptrace_regset = NT_PRFPREG; +#endif + iov.iov_len = 2 * 1024 * 1024; + ret = ptrace(PTRACE_GETREGSET, pid, ptrace_regset, &iov); + if (ret) + ret = -errno; + } + munmap(iov.iov_base, 2 * 1024 * 1024); host_fp_size = iov.iov_len; diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c index 75087e85b6fd..2934e170b0fe 100644 --- a/arch/x86/um/signal.c +++ b/arch/x86/um/signal.c @@ -187,7 +187,12 @@ static int copy_sc_to_user(struct sigcontext __user *to, * Put magic/size values for userspace. We do not bother to verify them * later on, however, userspace needs them should it try to read the * XSTATE data. And ptrace does not fill in these parts. + * + * Skip this if we do not have an XSTATE frame. */ + if (host_fp_size <= sizeof(to_fp64->fpstate)) + return 0; + BUILD_BUG_ON(sizeof(int) != FP_XSTATE_MAGIC2_SIZE); #ifdef CONFIG_X86_32 __put_user(offsetof(struct _fpstate_32, _fxsr_env) + @@ -367,11 +372,13 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, int err = 0, sig = ksig->sig; unsigned long fp_to; - frame = (struct rt_sigframe __user *) - round_down(stack_top - sizeof(struct rt_sigframe), 16); + frame = (void __user *)stack_top - sizeof(struct rt_sigframe); /* Add required space for math frame */ - frame = (struct rt_sigframe __user *)((unsigned long)frame - math_size); + frame = (void __user *)((unsigned long)frame - math_size); + + /* ABI requires 16 byte boundary alignment */ + frame = (void __user *)round_down((unsigned long)frame, 16); /* Subtract 128 for a red zone and 8 for proper alignment */ frame = (struct rt_sigframe __user *) ((unsigned long) frame - 128 - 8); diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c index 1dcc027ec77e..42e74a5a7d78 100644 --- a/arch/x86/virt/svm/sev.c +++ b/arch/x86/virt/svm/sev.c @@ -505,19 +505,19 @@ static bool __init setup_rmptable(void) * described in the SNP_INIT_EX firmware command description in the SNP * firmware ABI spec. */ -static int __init snp_rmptable_init(void) +int __init snp_rmptable_init(void) { unsigned int i; u64 val; - if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) - return 0; + if (WARN_ON_ONCE(!cc_platform_has(CC_ATTR_HOST_SEV_SNP))) + return -ENOSYS; - if (!amd_iommu_snp_en) - goto nosnp; + if (WARN_ON_ONCE(!amd_iommu_snp_en)) + return -ENOSYS; if (!setup_rmptable()) - goto nosnp; + return -ENOSYS; /* * Check if SEV-SNP is already enabled, this can happen in case of @@ -530,7 +530,7 @@ static int __init snp_rmptable_init(void) /* Zero out the RMP bookkeeping area */ if (!clear_rmptable_bookkeeping()) { free_rmp_segment_table(); - goto nosnp; + return -ENOSYS; } /* Zero out the RMP entries */ @@ -562,17 +562,8 @@ skip_enable: crash_kexec_post_notifiers = true; return 0; - -nosnp: - cc_platform_clear(CC_ATTR_HOST_SEV_SNP); - return -ENOSYS; } -/* - * This must be called after the IOMMU has been initialized. - */ -device_initcall(snp_rmptable_init); - static void set_rmp_segment_info(unsigned int segment_shift) { rmp_segment_shift = segment_shift; diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 2c70cd35e72c..d078de2c952b 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -111,6 +111,51 @@ static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss; */ static DEFINE_SPINLOCK(xen_reservation_lock); +/* Protected by xen_reservation_lock. */ +#define MIN_CONTIG_ORDER 9 /* 2MB */ +static unsigned int discontig_frames_order = MIN_CONTIG_ORDER; +static unsigned long discontig_frames_early[1UL << MIN_CONTIG_ORDER] __initdata; +static unsigned long *discontig_frames __refdata = discontig_frames_early; +static bool discontig_frames_dyn; + +static int alloc_discontig_frames(unsigned int order) +{ + unsigned long *new_array, *old_array; + unsigned int old_order; + unsigned long flags; + + BUG_ON(order < MIN_CONTIG_ORDER); + BUILD_BUG_ON(sizeof(discontig_frames_early) != PAGE_SIZE); + + new_array = (unsigned long *)__get_free_pages(GFP_KERNEL, + order - MIN_CONTIG_ORDER); + if (!new_array) + return -ENOMEM; + + spin_lock_irqsave(&xen_reservation_lock, flags); + + old_order = discontig_frames_order; + + if (order > discontig_frames_order || !discontig_frames_dyn) { + if (!discontig_frames_dyn) + old_array = NULL; + else + old_array = discontig_frames; + + discontig_frames = new_array; + discontig_frames_order = order; + discontig_frames_dyn = true; + } else { + old_array = new_array; + } + + spin_unlock_irqrestore(&xen_reservation_lock, flags); + + free_pages((unsigned long)old_array, old_order - MIN_CONTIG_ORDER); + + return 0; +} + /* * Note about cr3 (pagetable base) values: * @@ -814,6 +859,9 @@ static void __init xen_after_bootmem(void) SetPagePinned(virt_to_page(level3_user_vsyscall)); #endif xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP); + + if (alloc_discontig_frames(MIN_CONTIG_ORDER)) + BUG(); } static void xen_unpin_page(struct mm_struct *mm, struct page *page, @@ -2203,10 +2251,6 @@ void __init xen_init_mmu_ops(void) memset(dummy_mapping, 0xff, PAGE_SIZE); } -/* Protected by xen_reservation_lock. */ -#define MAX_CONTIG_ORDER 9 /* 2MB */ -static unsigned long discontig_frames[1<<MAX_CONTIG_ORDER]; - #define VOID_PTE (mfn_pte(0, __pgprot(0))) static void xen_zap_pfn_range(unsigned long vaddr, unsigned int order, unsigned long *in_frames, @@ -2323,18 +2367,25 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, unsigned int address_bits, dma_addr_t *dma_handle) { - unsigned long *in_frames = discontig_frames, out_frame; + unsigned long *in_frames, out_frame; unsigned long flags; int success; unsigned long vstart = (unsigned long)phys_to_virt(pstart); - if (unlikely(order > MAX_CONTIG_ORDER)) - return -ENOMEM; + if (unlikely(order > discontig_frames_order)) { + if (!discontig_frames_dyn) + return -ENOMEM; + + if (alloc_discontig_frames(order)) + return -ENOMEM; + } memset((void *) vstart, 0, PAGE_SIZE << order); spin_lock_irqsave(&xen_reservation_lock, flags); + in_frames = discontig_frames; + /* 1. Zap current PTEs, remembering MFNs. */ xen_zap_pfn_range(vstart, order, in_frames, NULL); @@ -2358,12 +2409,12 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) { - unsigned long *out_frames = discontig_frames, in_frame; + unsigned long *out_frames, in_frame; unsigned long flags; int success; unsigned long vstart; - if (unlikely(order > MAX_CONTIG_ORDER)) + if (unlikely(order > discontig_frames_order)) return; vstart = (unsigned long)phys_to_virt(pstart); @@ -2371,6 +2422,8 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) spin_lock_irqsave(&xen_reservation_lock, flags); + out_frames = discontig_frames; + /* 1. Find start MFN of contiguous extent. */ in_frame = virt_to_mfn((void *)vstart); diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 9252652afe59..894edf8d6d62 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -100,9 +100,6 @@ SYM_FUNC_START(xen_hypercall_hvm) push %r10 push %r9 push %r8 -#ifdef CONFIG_FRAME_POINTER - pushq $0 /* Dummy push for stack alignment. */ -#endif #endif /* Set the vendor specific function. */ call __xen_hypercall_setfunc @@ -117,11 +114,8 @@ SYM_FUNC_START(xen_hypercall_hvm) pop %ebx pop %eax #else - lea xen_hypercall_amd(%rip), %rbx - cmp %rax, %rbx -#ifdef CONFIG_FRAME_POINTER - pop %rax /* Dummy pop. */ -#endif + lea xen_hypercall_amd(%rip), %rcx + cmp %rax, %rcx pop %r8 pop %r9 pop %r10 @@ -132,6 +126,7 @@ SYM_FUNC_START(xen_hypercall_hvm) pop %rcx pop %rax #endif + FRAME_END /* Use correct hypercall function. */ jz xen_hypercall_amd jmp xen_hypercall_intel |