From 6ccbd29ade0d159ee1be398dc9defaae567c253d Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:02 +0200 Subject: KVM: SVM: nested: Don't allocate VMCB structures on stack Do not allocate a vmcb_control_area and a vmcb_save_area on the stack, as these structures will become larger with future extenstions of SVM and thus the svm_set_nested_state() function will become a too large stack frame. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-2-joro@8bytes.org --- arch/x86/kvm/svm/nested.c | 47 +++++++++++++++++++++++++++++++++-------------- 1 file changed, 33 insertions(+), 14 deletions(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index fb68467e6049..28036629abf8 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1060,10 +1060,14 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, struct vmcb *hsave = svm->nested.hsave; struct vmcb __user *user_vmcb = (struct vmcb __user *) &user_kvm_nested_state->data.svm[0]; - struct vmcb_control_area ctl; - struct vmcb_save_area save; + struct vmcb_control_area *ctl; + struct vmcb_save_area *save; + int ret; u32 cr0; + BUILD_BUG_ON(sizeof(struct vmcb_control_area) + sizeof(struct vmcb_save_area) > + KVM_STATE_NESTED_SVM_VMCB_SIZE); + if (kvm_state->format != KVM_STATE_NESTED_FORMAT_SVM) return -EINVAL; @@ -1095,13 +1099,22 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, return -EINVAL; if (kvm_state->size < sizeof(*kvm_state) + KVM_STATE_NESTED_SVM_VMCB_SIZE) return -EINVAL; - if (copy_from_user(&ctl, &user_vmcb->control, sizeof(ctl))) - return -EFAULT; - if (copy_from_user(&save, &user_vmcb->save, sizeof(save))) - return -EFAULT; - if (!nested_vmcb_check_controls(&ctl)) - return -EINVAL; + ret = -ENOMEM; + ctl = kzalloc(sizeof(*ctl), GFP_KERNEL); + save = kzalloc(sizeof(*save), GFP_KERNEL); + if (!ctl || !save) + goto out_free; + + ret = -EFAULT; + if (copy_from_user(ctl, &user_vmcb->control, sizeof(*ctl))) + goto out_free; + if (copy_from_user(save, &user_vmcb->save, sizeof(*save))) + goto out_free; + + ret = -EINVAL; + if (!nested_vmcb_check_controls(ctl)) + goto out_free; /* * Processor state contains L2 state. Check that it is @@ -1109,15 +1122,15 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, */ cr0 = kvm_read_cr0(vcpu); if (((cr0 & X86_CR0_CD) == 0) && (cr0 & X86_CR0_NW)) - return -EINVAL; + goto out_free; /* * Validate host state saved from before VMRUN (see * nested_svm_check_permissions). * TODO: validate reserved bits for all saved state. */ - if (!(save.cr0 & X86_CR0_PG)) - return -EINVAL; + if (!(save->cr0 & X86_CR0_PG)) + goto out_free; /* * All checks done, we can enter guest mode. L1 control fields @@ -1126,15 +1139,21 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, * contains saved L1 state. */ copy_vmcb_control_area(&hsave->control, &svm->vmcb->control); - hsave->save = save; + hsave->save = *save; svm->nested.vmcb = kvm_state->hdr.svm.vmcb_pa; - load_nested_vmcb_control(svm, &ctl); + load_nested_vmcb_control(svm, ctl); nested_prepare_vmcb_control(svm); out_set_gif: svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET)); - return 0; + + ret = 0; +out_free: + kfree(save); + kfree(ctl); + + return ret; } struct kvm_x86_nested_ops svm_nested_ops = { -- cgit v1.2.3-58-ga151 From d07f46f9f51afc7fc9f021eae19eba3c2e7870ac Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 7 Sep 2020 15:15:03 +0200 Subject: KVM: SVM: Add GHCB definitions Extend the vmcb_safe_area with SEV-ES fields and add a new 'struct ghcb' which will be used for guest-hypervisor communication. Signed-off-by: Tom Lendacky Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-3-joro@8bytes.org --- arch/x86/include/asm/svm.h | 51 ++++++++++++++++++++++++++++++++++++++++++++-- arch/x86/kvm/svm/svm.c | 2 ++ 2 files changed, 51 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 8a1f5382a4ea..acac55d6f941 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -200,13 +200,60 @@ struct __attribute__ ((__packed__)) vmcb_save_area { u64 br_to; u64 last_excp_from; u64 last_excp_to; + + /* + * The following part of the save area is valid only for + * SEV-ES guests when referenced through the GHCB. + */ + u8 reserved_7[104]; + u64 reserved_8; /* rax already available at 0x01f8 */ + u64 rcx; + u64 rdx; + u64 rbx; + u64 reserved_9; /* rsp already available at 0x01d8 */ + u64 rbp; + u64 rsi; + u64 rdi; + u64 r8; + u64 r9; + u64 r10; + u64 r11; + u64 r12; + u64 r13; + u64 r14; + u64 r15; + u8 reserved_10[16]; + u64 sw_exit_code; + u64 sw_exit_info_1; + u64 sw_exit_info_2; + u64 sw_scratch; + u8 reserved_11[56]; + u64 xcr0; + u8 valid_bitmap[16]; + u64 x87_state_gpa; }; +struct ghcb { + struct vmcb_save_area save; + u8 reserved_save[2048 - sizeof(struct vmcb_save_area)]; + + u8 shared_buffer[2032]; + + u8 reserved_1[10]; + u16 protocol_version; /* negotiated SEV-ES/GHCB protocol version */ + u32 ghcb_usage; +} __packed; + + +#define EXPECTED_VMCB_SAVE_AREA_SIZE 1032 +#define EXPECTED_VMCB_CONTROL_AREA_SIZE 256 +#define EXPECTED_GHCB_SIZE PAGE_SIZE static inline void __unused_size_checks(void) { - BUILD_BUG_ON(sizeof(struct vmcb_save_area) != 0x298); - BUILD_BUG_ON(sizeof(struct vmcb_control_area) != 256); + BUILD_BUG_ON(sizeof(struct vmcb_save_area) != EXPECTED_VMCB_SAVE_AREA_SIZE); + BUILD_BUG_ON(sizeof(struct vmcb_control_area) != EXPECTED_VMCB_CONTROL_AREA_SIZE); + BUILD_BUG_ON(sizeof(struct ghcb) != EXPECTED_GHCB_SIZE); } struct __attribute__ ((__packed__)) vmcb { diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 0194336b64a4..1db4fdcb4906 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4164,6 +4164,8 @@ static struct kvm_x86_init_ops svm_init_ops __initdata = { static int __init svm_init(void) { + __unused_size_checks(); + return kvm_init(&svm_init_ops, sizeof(struct vcpu_svm), __alignof__(struct vcpu_svm), THIS_MODULE); } -- cgit v1.2.3-58-ga151 From 3702c2f4eed2188440f65ecdfc89165106fe565d Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:04 +0200 Subject: KVM: SVM: Add GHCB Accessor functions Building a correct GHCB for the hypervisor requires setting valid bits in the GHCB. Simplify that process by providing accessor functions to set values and to update the valid bitmap and to check the valid bitmap in KVM. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-4-joro@8bytes.org --- arch/x86/include/asm/svm.h | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index acac55d6f941..06e52585aed3 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -345,4 +345,47 @@ struct __attribute__ ((__packed__)) vmcb { #define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP) +/* GHCB Accessor functions */ + +#define GHCB_BITMAP_IDX(field) \ + (offsetof(struct vmcb_save_area, field) / sizeof(u64)) + +#define DEFINE_GHCB_ACCESSORS(field) \ + static inline bool ghcb_##field##_is_valid(const struct ghcb *ghcb) \ + { \ + return test_bit(GHCB_BITMAP_IDX(field), \ + (unsigned long *)&ghcb->save.valid_bitmap); \ + } \ + \ + static inline void ghcb_set_##field(struct ghcb *ghcb, u64 value) \ + { \ + __set_bit(GHCB_BITMAP_IDX(field), \ + (unsigned long *)&ghcb->save.valid_bitmap); \ + ghcb->save.field = value; \ + } + +DEFINE_GHCB_ACCESSORS(cpl) +DEFINE_GHCB_ACCESSORS(rip) +DEFINE_GHCB_ACCESSORS(rsp) +DEFINE_GHCB_ACCESSORS(rax) +DEFINE_GHCB_ACCESSORS(rcx) +DEFINE_GHCB_ACCESSORS(rdx) +DEFINE_GHCB_ACCESSORS(rbx) +DEFINE_GHCB_ACCESSORS(rbp) +DEFINE_GHCB_ACCESSORS(rsi) +DEFINE_GHCB_ACCESSORS(rdi) +DEFINE_GHCB_ACCESSORS(r8) +DEFINE_GHCB_ACCESSORS(r9) +DEFINE_GHCB_ACCESSORS(r10) +DEFINE_GHCB_ACCESSORS(r11) +DEFINE_GHCB_ACCESSORS(r12) +DEFINE_GHCB_ACCESSORS(r13) +DEFINE_GHCB_ACCESSORS(r14) +DEFINE_GHCB_ACCESSORS(r15) +DEFINE_GHCB_ACCESSORS(sw_exit_code) +DEFINE_GHCB_ACCESSORS(sw_exit_info_1) +DEFINE_GHCB_ACCESSORS(sw_exit_info_2) +DEFINE_GHCB_ACCESSORS(sw_scratch) +DEFINE_GHCB_ACCESSORS(xcr0) + #endif -- cgit v1.2.3-58-ga151 From 976bc5e2aceedef13e0ba1f0e6e372a22164aa0c Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 7 Sep 2020 15:15:05 +0200 Subject: KVM: SVM: Use __packed shorthand Use the shorthand to make it more readable. No functional changes. Signed-off-by: Borislav Petkov Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-5-joro@8bytes.org --- arch/x86/include/asm/svm.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 06e52585aed3..cf13f9e78585 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -150,14 +150,14 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define SVM_NESTED_CTL_NP_ENABLE BIT(0) #define SVM_NESTED_CTL_SEV_ENABLE BIT(1) -struct __attribute__ ((__packed__)) vmcb_seg { +struct vmcb_seg { u16 selector; u16 attrib; u32 limit; u64 base; -}; +} __packed; -struct __attribute__ ((__packed__)) vmcb_save_area { +struct vmcb_save_area { struct vmcb_seg es; struct vmcb_seg cs; struct vmcb_seg ss; @@ -231,7 +231,7 @@ struct __attribute__ ((__packed__)) vmcb_save_area { u64 xcr0; u8 valid_bitmap[16]; u64 x87_state_gpa; -}; +} __packed; struct ghcb { struct vmcb_save_area save; @@ -256,11 +256,11 @@ static inline void __unused_size_checks(void) BUILD_BUG_ON(sizeof(struct ghcb) != EXPECTED_GHCB_SIZE); } -struct __attribute__ ((__packed__)) vmcb { +struct vmcb { struct vmcb_control_area control; u8 reserved_control[1024 - sizeof(struct vmcb_control_area)]; struct vmcb_save_area save; -}; +} __packed; #define SVM_CPUID_FUNC 0x8000000a -- cgit v1.2.3-58-ga151 From 360e7c5c4ca4fd8e627781ed42f95d58bc3bb732 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 7 Sep 2020 15:15:06 +0200 Subject: x86/cpufeatures: Add SEV-ES CPU feature Add CPU feature detection for Secure Encrypted Virtualization with Encrypted State. This feature enhances SEV by also encrypting the guest register state, making it in-accessible to the hypervisor. Signed-off-by: Tom Lendacky Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-6-joro@8bytes.org --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/kernel/cpu/amd.c | 3 ++- arch/x86/kernel/cpu/scattered.c | 1 + 3 files changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 83fc9d38eb1f..1205c1b6991a 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -236,6 +236,7 @@ #define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */ #define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */ #define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ +#define X86_FEATURE_SEV_ES ( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index dcc3d943c68f..6062ce586b95 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -614,7 +614,7 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) * If BIOS has not enabled SME then don't advertise the * SME feature (set in scattered.c). * For SEV: If BIOS has not enabled SEV then don't advertise the - * SEV feature (set in scattered.c). + * SEV and SEV_ES feature (set in scattered.c). * * In all cases, since support for SME and SEV requires long mode, * don't advertise the feature under CONFIG_X86_32. @@ -645,6 +645,7 @@ clear_all: setup_clear_cpu_cap(X86_FEATURE_SME); clear_sev: setup_clear_cpu_cap(X86_FEATURE_SEV); + setup_clear_cpu_cap(X86_FEATURE_SEV_ES); } } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 62b137c3c97a..30f354989cf1 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -41,6 +41,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 }, { X86_FEATURE_SME, CPUID_EAX, 0, 0x8000001f, 0 }, { X86_FEATURE_SEV, CPUID_EAX, 1, 0x8000001f, 0 }, + { X86_FEATURE_SEV_ES, CPUID_EAX, 3, 0x8000001f, 0 }, { 0, 0, 0, 0, 0 } }; -- cgit v1.2.3-58-ga151 From 05a2fdf3230306daee1def019b8f52cd06bd2e48 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:07 +0200 Subject: x86/traps: Move pf error codes to Move the definition of the x86 page-fault error code bits to a new header file asm/trap_pf.h. This makes it easier to include them into pre-decompression boot code. No functional changes. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-7-joro@8bytes.org --- arch/x86/include/asm/trap_pf.h | 24 ++++++++++++++++++++++++ arch/x86/include/asm/traps.h | 19 +------------------ 2 files changed, 25 insertions(+), 18 deletions(-) create mode 100644 arch/x86/include/asm/trap_pf.h diff --git a/arch/x86/include/asm/trap_pf.h b/arch/x86/include/asm/trap_pf.h new file mode 100644 index 000000000000..305bc1214aef --- /dev/null +++ b/arch/x86/include/asm/trap_pf.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_TRAP_PF_H +#define _ASM_X86_TRAP_PF_H + +/* + * Page fault error code bits: + * + * bit 0 == 0: no page found 1: protection fault + * bit 1 == 0: read access 1: write access + * bit 2 == 0: kernel-mode access 1: user-mode access + * bit 3 == 1: use of reserved bit detected + * bit 4 == 1: fault was an instruction fetch + * bit 5 == 1: protection keys block access + */ +enum x86_pf_error_code { + X86_PF_PROT = 1 << 0, + X86_PF_WRITE = 1 << 1, + X86_PF_USER = 1 << 2, + X86_PF_RSVD = 1 << 3, + X86_PF_INSTR = 1 << 4, + X86_PF_PK = 1 << 5, +}; + +#endif /* _ASM_X86_TRAP_PF_H */ diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 714b1a30e7b0..6a308355ea29 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -8,6 +8,7 @@ #include #include #include /* TRAP_TRACE, ... */ +#include #ifdef CONFIG_X86_64 asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs); @@ -41,22 +42,4 @@ void __noreturn handle_stack_overflow(const char *message, unsigned long fault_address); #endif -/* - * Page fault error code bits: - * - * bit 0 == 0: no page found 1: protection fault - * bit 1 == 0: read access 1: write access - * bit 2 == 0: kernel-mode access 1: user-mode access - * bit 3 == 1: use of reserved bit detected - * bit 4 == 1: fault was an instruction fetch - * bit 5 == 1: protection keys block access - */ -enum x86_pf_error_code { - X86_PF_PROT = 1 << 0, - X86_PF_WRITE = 1 << 1, - X86_PF_USER = 1 << 2, - X86_PF_RSVD = 1 << 3, - X86_PF_INSTR = 1 << 4, - X86_PF_PK = 1 << 5, -}; #endif /* _ASM_X86_TRAPS_H */ -- cgit v1.2.3-58-ga151 From 05a2ae7c033ee30f25fbed3ceed549a5cac398a9 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:08 +0200 Subject: x86/insn: Make inat-tables.c suitable for pre-decompression code The inat-tables.c file has some arrays in it that contain pointers to other arrays. These pointers need to be relocated when the kernel image is moved to a different location. The pre-decompression boot-code has no support for applying ELF relocations, so initialize these arrays at runtime in the pre-decompression code to make sure all pointers are correctly initialized. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Acked-by: Masami Hiramatsu Link: https://lkml.kernel.org/r/20200907131613.12703-8-joro@8bytes.org --- arch/x86/tools/gen-insn-attr-x86.awk | 50 +++++++++++++++++++++++++++++- tools/arch/x86/tools/gen-insn-attr-x86.awk | 50 +++++++++++++++++++++++++++++- 2 files changed, 98 insertions(+), 2 deletions(-) diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk index a42015b305f4..af38469afd14 100644 --- a/arch/x86/tools/gen-insn-attr-x86.awk +++ b/arch/x86/tools/gen-insn-attr-x86.awk @@ -362,6 +362,9 @@ function convert_operands(count,opnd, i,j,imm,mod) END { if (awkchecked != "") exit 1 + + print "#ifndef __BOOT_COMPRESSED\n" + # print escape opcode map's array print "/* Escape opcode map array */" print "const insn_attr_t * const inat_escape_tables[INAT_ESC_MAX + 1]" \ @@ -388,6 +391,51 @@ END { for (j = 0; j < max_lprefix; j++) if (atable[i,j]) print " ["i"]["j"] = "atable[i,j]"," - print "};" + print "};\n" + + print "#else /* !__BOOT_COMPRESSED */\n" + + print "/* Escape opcode map array */" + print "static const insn_attr_t *inat_escape_tables[INAT_ESC_MAX + 1]" \ + "[INAT_LSTPFX_MAX + 1];" + print "" + + print "/* Group opcode map array */" + print "static const insn_attr_t *inat_group_tables[INAT_GRP_MAX + 1]"\ + "[INAT_LSTPFX_MAX + 1];" + print "" + + print "/* AVX opcode map array */" + print "static const insn_attr_t *inat_avx_tables[X86_VEX_M_MAX + 1]"\ + "[INAT_LSTPFX_MAX + 1];" + print "" + + print "static void inat_init_tables(void)" + print "{" + + # print escape opcode map's array + print "\t/* Print Escape opcode map array */" + for (i = 0; i < geid; i++) + for (j = 0; j < max_lprefix; j++) + if (etable[i,j]) + print "\tinat_escape_tables["i"]["j"] = "etable[i,j]";" + print "" + + # print group opcode map's array + print "\t/* Print Group opcode map array */" + for (i = 0; i < ggid; i++) + for (j = 0; j < max_lprefix; j++) + if (gtable[i,j]) + print "\tinat_group_tables["i"]["j"] = "gtable[i,j]";" + print "" + # print AVX opcode map's array + print "\t/* Print AVX opcode map array */" + for (i = 0; i < gaid; i++) + for (j = 0; j < max_lprefix; j++) + if (atable[i,j]) + print "\tinat_avx_tables["i"]["j"] = "atable[i,j]";" + + print "}" + print "#endif" } diff --git a/tools/arch/x86/tools/gen-insn-attr-x86.awk b/tools/arch/x86/tools/gen-insn-attr-x86.awk index a42015b305f4..af38469afd14 100644 --- a/tools/arch/x86/tools/gen-insn-attr-x86.awk +++ b/tools/arch/x86/tools/gen-insn-attr-x86.awk @@ -362,6 +362,9 @@ function convert_operands(count,opnd, i,j,imm,mod) END { if (awkchecked != "") exit 1 + + print "#ifndef __BOOT_COMPRESSED\n" + # print escape opcode map's array print "/* Escape opcode map array */" print "const insn_attr_t * const inat_escape_tables[INAT_ESC_MAX + 1]" \ @@ -388,6 +391,51 @@ END { for (j = 0; j < max_lprefix; j++) if (atable[i,j]) print " ["i"]["j"] = "atable[i,j]"," - print "};" + print "};\n" + + print "#else /* !__BOOT_COMPRESSED */\n" + + print "/* Escape opcode map array */" + print "static const insn_attr_t *inat_escape_tables[INAT_ESC_MAX + 1]" \ + "[INAT_LSTPFX_MAX + 1];" + print "" + + print "/* Group opcode map array */" + print "static const insn_attr_t *inat_group_tables[INAT_GRP_MAX + 1]"\ + "[INAT_LSTPFX_MAX + 1];" + print "" + + print "/* AVX opcode map array */" + print "static const insn_attr_t *inat_avx_tables[X86_VEX_M_MAX + 1]"\ + "[INAT_LSTPFX_MAX + 1];" + print "" + + print "static void inat_init_tables(void)" + print "{" + + # print escape opcode map's array + print "\t/* Print Escape opcode map array */" + for (i = 0; i < geid; i++) + for (j = 0; j < max_lprefix; j++) + if (etable[i,j]) + print "\tinat_escape_tables["i"]["j"] = "etable[i,j]";" + print "" + + # print group opcode map's array + print "\t/* Print Group opcode map array */" + for (i = 0; i < ggid; i++) + for (j = 0; j < max_lprefix; j++) + if (gtable[i,j]) + print "\tinat_group_tables["i"]["j"] = "gtable[i,j]";" + print "" + # print AVX opcode map's array + print "\t/* Print AVX opcode map array */" + for (i = 0; i < gaid; i++) + for (j = 0; j < max_lprefix; j++) + if (atable[i,j]) + print "\tinat_avx_tables["i"]["j"] = "atable[i,j]";" + + print "}" + print "#endif" } -- cgit v1.2.3-58-ga151 From 172b75e56b08846e6fb07a88e5685ce4e24f4620 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:09 +0200 Subject: x86/umip: Factor out instruction fetch Factor out the code to fetch the instruction from user-space to a helper function. No functional changes. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-9-joro@8bytes.org --- arch/x86/include/asm/insn-eval.h | 2 ++ arch/x86/kernel/umip.c | 26 ++++++-------------------- arch/x86/lib/insn-eval.c | 38 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 46 insertions(+), 20 deletions(-) diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h index 2b6ccf2c49f1..b8b9ef1bbd06 100644 --- a/arch/x86/include/asm/insn-eval.h +++ b/arch/x86/include/asm/insn-eval.h @@ -19,5 +19,7 @@ void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs); int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs); unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx); int insn_get_code_seg_params(struct pt_regs *regs); +int insn_fetch_from_user(struct pt_regs *regs, + unsigned char buf[MAX_INSN_SIZE]); #endif /* _ASM_X86_INSN_EVAL_H */ diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c index 2c304fd0bb1a..ad135be4f1f0 100644 --- a/arch/x86/kernel/umip.c +++ b/arch/x86/kernel/umip.c @@ -335,11 +335,11 @@ static void force_sig_info_umip_fault(void __user *addr, struct pt_regs *regs) */ bool fixup_umip_exception(struct pt_regs *regs) { - int not_copied, nr_copied, reg_offset, dummy_data_size, umip_inst; - unsigned long seg_base = 0, *reg_addr; + int nr_copied, reg_offset, dummy_data_size, umip_inst; /* 10 bytes is the maximum size of the result of UMIP instructions */ unsigned char dummy_data[10] = { 0 }; unsigned char buf[MAX_INSN_SIZE]; + unsigned long *reg_addr; void __user *uaddr; struct insn insn; int seg_defs; @@ -347,26 +347,12 @@ bool fixup_umip_exception(struct pt_regs *regs) if (!regs) return false; - /* - * If not in user-space long mode, a custom code segment could be in - * use. This is true in protected mode (if the process defined a local - * descriptor table), or virtual-8086 mode. In most of the cases - * seg_base will be zero as in USER_CS. - */ - if (!user_64bit_mode(regs)) - seg_base = insn_get_seg_base(regs, INAT_SEG_REG_CS); - - if (seg_base == -1L) - return false; - - not_copied = copy_from_user(buf, (void __user *)(seg_base + regs->ip), - sizeof(buf)); - nr_copied = sizeof(buf) - not_copied; + nr_copied = insn_fetch_from_user(regs, buf); /* - * The copy_from_user above could have failed if user code is protected - * by a memory protection key. Give up on emulation in such a case. - * Should we issue a page fault? + * The insn_fetch_from_user above could have failed if user code + * is protected by a memory protection key. Give up on emulation + * in such a case. Should we issue a page fault? */ if (!nr_copied) return false; diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index 5e69603ff63f..947b7f1a0042 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -1367,3 +1367,41 @@ void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs) return (void __user *)-1L; } } + +/** + * insn_fetch_from_user() - Copy instruction bytes from user-space memory + * @regs: Structure with register values as seen when entering kernel mode + * @buf: Array to store the fetched instruction + * + * Gets the linear address of the instruction and copies the instruction bytes + * to the buf. + * + * Returns: + * + * Number of instruction bytes copied. + * + * 0 if nothing was copied. + */ +int insn_fetch_from_user(struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE]) +{ + unsigned long seg_base = 0; + int not_copied; + + /* + * If not in user-space long mode, a custom code segment could be in + * use. This is true in protected mode (if the process defined a local + * descriptor table), or virtual-8086 mode. In most of the cases + * seg_base will be zero as in USER_CS. + */ + if (!user_64bit_mode(regs)) { + seg_base = insn_get_seg_base(regs, INAT_SEG_REG_CS); + if (seg_base == -1L) + return 0; + } + + + not_copied = copy_from_user(buf, (void __user *)(seg_base + regs->ip), + MAX_INSN_SIZE); + + return MAX_INSN_SIZE - not_copied; +} -- cgit v1.2.3-58-ga151 From 172639d79977ca7b5ce6f84f6606262f4081718f Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:10 +0200 Subject: x86/umip: Factor out instruction decoding Factor out the code used to decode an instruction with the correct address and operand sizes to a helper function. No functional changes. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-10-joro@8bytes.org --- arch/x86/include/asm/insn-eval.h | 2 ++ arch/x86/kernel/umip.c | 23 +------------------- arch/x86/lib/insn-eval.c | 45 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 48 insertions(+), 22 deletions(-) diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h index b8b9ef1bbd06..392b4fe377f9 100644 --- a/arch/x86/include/asm/insn-eval.h +++ b/arch/x86/include/asm/insn-eval.h @@ -21,5 +21,7 @@ unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx); int insn_get_code_seg_params(struct pt_regs *regs); int insn_fetch_from_user(struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE]); +bool insn_decode(struct insn *insn, struct pt_regs *regs, + unsigned char buf[MAX_INSN_SIZE], int buf_size); #endif /* _ASM_X86_INSN_EVAL_H */ diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c index ad135be4f1f0..f6225bf22c02 100644 --- a/arch/x86/kernel/umip.c +++ b/arch/x86/kernel/umip.c @@ -342,7 +342,6 @@ bool fixup_umip_exception(struct pt_regs *regs) unsigned long *reg_addr; void __user *uaddr; struct insn insn; - int seg_defs; if (!regs) return false; @@ -357,27 +356,7 @@ bool fixup_umip_exception(struct pt_regs *regs) if (!nr_copied) return false; - insn_init(&insn, buf, nr_copied, user_64bit_mode(regs)); - - /* - * Override the default operand and address sizes with what is specified - * in the code segment descriptor. The instruction decoder only sets - * the address size it to either 4 or 8 address bytes and does nothing - * for the operand bytes. This OK for most of the cases, but we could - * have special cases where, for instance, a 16-bit code segment - * descriptor is used. - * If there is an address override prefix, the instruction decoder - * correctly updates these values, even for 16-bit defaults. - */ - seg_defs = insn_get_code_seg_params(regs); - if (seg_defs == -EINVAL) - return false; - - insn.addr_bytes = INSN_CODE_SEG_ADDR_SZ(seg_defs); - insn.opnd_bytes = INSN_CODE_SEG_OPND_SZ(seg_defs); - - insn_get_length(&insn); - if (nr_copied < insn.length) + if (!insn_decode(&insn, regs, buf, nr_copied)) return false; umip_inst = identify_insn(&insn); diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index 947b7f1a0042..2323c85132cf 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -1405,3 +1405,48 @@ int insn_fetch_from_user(struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE]) return MAX_INSN_SIZE - not_copied; } + +/** + * insn_decode() - Decode an instruction + * @insn: Structure to store decoded instruction + * @regs: Structure with register values as seen when entering kernel mode + * @buf: Buffer containing the instruction bytes + * @buf_size: Number of instruction bytes available in buf + * + * Decodes the instruction provided in buf and stores the decoding results in + * insn. Also determines the correct address and operand sizes. + * + * Returns: + * + * True if instruction was decoded, False otherwise. + */ +bool insn_decode(struct insn *insn, struct pt_regs *regs, + unsigned char buf[MAX_INSN_SIZE], int buf_size) +{ + int seg_defs; + + insn_init(insn, buf, buf_size, user_64bit_mode(regs)); + + /* + * Override the default operand and address sizes with what is specified + * in the code segment descriptor. The instruction decoder only sets + * the address size it to either 4 or 8 address bytes and does nothing + * for the operand bytes. This OK for most of the cases, but we could + * have special cases where, for instance, a 16-bit code segment + * descriptor is used. + * If there is an address override prefix, the instruction decoder + * correctly updates these values, even for 16-bit defaults. + */ + seg_defs = insn_get_code_seg_params(regs); + if (seg_defs == -EINVAL) + return false; + + insn->addr_bytes = INSN_CODE_SEG_ADDR_SZ(seg_defs); + insn->opnd_bytes = INSN_CODE_SEG_OPND_SZ(seg_defs); + + insn_get_length(insn); + if (buf_size < insn->length) + return false; + + return true; +} -- cgit v1.2.3-58-ga151 From 7af1bd822dd45a669fc178a35cc8183922333d56 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:11 +0200 Subject: x86/insn: Add insn_get_modrm_reg_off() Add a function to the instruction decoder which returns the pt_regs offset of the register specified in the reg field of the modrm byte. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Acked-by: Masami Hiramatsu Link: https://lkml.kernel.org/r/20200907131613.12703-11-joro@8bytes.org --- arch/x86/include/asm/insn-eval.h | 1 + arch/x86/lib/insn-eval.c | 23 +++++++++++++++++++++++ 2 files changed, 24 insertions(+) diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h index 392b4fe377f9..f748f57f1491 100644 --- a/arch/x86/include/asm/insn-eval.h +++ b/arch/x86/include/asm/insn-eval.h @@ -17,6 +17,7 @@ void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs); int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs); +int insn_get_modrm_reg_off(struct insn *insn, struct pt_regs *regs); unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx); int insn_get_code_seg_params(struct pt_regs *regs); int insn_fetch_from_user(struct pt_regs *regs, diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index 2323c85132cf..f20942ce76c6 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -20,6 +20,7 @@ enum reg_type { REG_TYPE_RM = 0, + REG_TYPE_REG, REG_TYPE_INDEX, REG_TYPE_BASE, }; @@ -439,6 +440,13 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs, regno += 8; break; + case REG_TYPE_REG: + regno = X86_MODRM_REG(insn->modrm.value); + + if (X86_REX_R(insn->rex_prefix.value)) + regno += 8; + break; + case REG_TYPE_INDEX: regno = X86_SIB_INDEX(insn->sib.value); if (X86_REX_X(insn->rex_prefix.value)) @@ -807,6 +815,21 @@ int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs) return get_reg_offset(insn, regs, REG_TYPE_RM); } +/** + * insn_get_modrm_reg_off() - Obtain register in reg part of the ModRM byte + * @insn: Instruction containing the ModRM byte + * @regs: Register values as seen when entering kernel mode + * + * Returns: + * + * The register indicated by the reg part of the ModRM byte. The + * register is obtained as an offset from the base of pt_regs. + */ +int insn_get_modrm_reg_off(struct insn *insn, struct pt_regs *regs) +{ + return get_reg_offset(insn, regs, REG_TYPE_REG); +} + /** * get_seg_base_limit() - obtain base address and limit of a segment * @insn: Instruction. Must be valid. -- cgit v1.2.3-58-ga151 From 5901781a11175a5e5ee91746ec8627f18d47eebd Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:12 +0200 Subject: x86/insn: Add insn_has_rep_prefix() helper Add a function to check whether an instruction has a REP prefix. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Reviewed-by: Masami Hiramatsu Link: https://lkml.kernel.org/r/20200907131613.12703-12-joro@8bytes.org --- arch/x86/include/asm/insn-eval.h | 1 + arch/x86/lib/insn-eval.c | 24 ++++++++++++++++++++++++ 2 files changed, 25 insertions(+) diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h index f748f57f1491..a0f839aa144d 100644 --- a/arch/x86/include/asm/insn-eval.h +++ b/arch/x86/include/asm/insn-eval.h @@ -15,6 +15,7 @@ #define INSN_CODE_SEG_OPND_SZ(params) (params & 0xf) #define INSN_CODE_SEG_PARAMS(oper_sz, addr_sz) (oper_sz | (addr_sz << 4)) +bool insn_has_rep_prefix(struct insn *insn); void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs); int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs); int insn_get_modrm_reg_off(struct insn *insn, struct pt_regs *regs); diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index f20942ce76c6..58f7fb95c7f4 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -53,6 +53,30 @@ static bool is_string_insn(struct insn *insn) } } +/** + * insn_has_rep_prefix() - Determine if instruction has a REP prefix + * @insn: Instruction containing the prefix to inspect + * + * Returns: + * + * true if the instruction has a REP prefix, false if not. + */ +bool insn_has_rep_prefix(struct insn *insn) +{ + int i; + + insn_get_prefixes(insn); + + for (i = 0; i < insn->prefixes.nbytes; i++) { + insn_byte_t p = insn->prefixes.bytes[i]; + + if (p == 0xf2 || p == 0xf3) + return true; + } + + return false; +} + /** * get_seg_reg_override_idx() - obtain segment register override index * @insn: Valid instruction with segment override prefixes -- cgit v1.2.3-58-ga151 From 6ba0efa46047936afa81460489cfd24bc95dd863 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:13 +0200 Subject: x86/boot/compressed/64: Disable red-zone usage The x86-64 ABI defines a red-zone on the stack: The 128-byte area beyond the location pointed to by %rsp is considered to be reserved and shall not be modified by signal or interrupt handlers. Therefore, functions may use this area for temporary data that is not needed across function calls. In particular, leaf functions may use this area for their entire stack frame, rather than adjusting the stack pointer in the prologue and epilogue. This area is known as the red zone. This is not compatible with exception handling, because the IRET frame written by the hardware at the stack pointer and the functions to handle the exception will overwrite the temporary variables of the interrupted function, causing undefined behavior. So disable red-zones for the pre-decompression boot code. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20200907131613.12703-13-joro@8bytes.org --- arch/x86/boot/compressed/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 3962f592633d..5343079af973 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -32,7 +32,7 @@ KBUILD_CFLAGS := -m$(BITS) -O2 KBUILD_CFLAGS += -fno-strict-aliasing $(call cc-option, -fPIE, -fPIC) KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING cflags-$(CONFIG_X86_32) := -march=i386 -cflags-$(CONFIG_X86_64) := -mcmodel=small +cflags-$(CONFIG_X86_64) := -mcmodel=small -mno-red-zone KBUILD_CFLAGS += $(cflags-y) KBUILD_CFLAGS += -mno-mmx -mno-sse KBUILD_CFLAGS += -ffreestanding -- cgit v1.2.3-58-ga151 From 64e682638eb51070ba6044535b250aad43c5564e Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:14 +0200 Subject: x86/boot/compressed/64: Add IDT Infrastructure Add code needed to setup an IDT in the early pre-decompression boot-code. The IDT is loaded first in startup_64, which is after EfiExitBootServices() has been called, and later reloaded when the kernel image has been relocated to the end of the decompression area. This allows to setup different IDT handlers before and after the relocation. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-14-joro@8bytes.org --- arch/x86/boot/compressed/Makefile | 1 + arch/x86/boot/compressed/head_64.S | 25 ++++++++++- arch/x86/boot/compressed/idt_64.c | 44 +++++++++++++++++++ arch/x86/boot/compressed/idt_handlers_64.S | 70 ++++++++++++++++++++++++++++++ arch/x86/boot/compressed/misc.h | 5 +++ arch/x86/include/asm/desc_defs.h | 3 ++ 6 files changed, 147 insertions(+), 1 deletion(-) create mode 100644 arch/x86/boot/compressed/idt_64.c create mode 100644 arch/x86/boot/compressed/idt_handlers_64.S diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 5343079af973..c661dc57674e 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -85,6 +85,7 @@ vmlinux-objs-$(CONFIG_EARLY_PRINTK) += $(obj)/early_serial_console.o vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o ifdef CONFIG_X86_64 vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr_64.o + vmlinux-objs-y += $(obj)/idt_64.o $(obj)/idt_handlers_64.o vmlinux-objs-y += $(obj)/mem_encrypt.o vmlinux-objs-y += $(obj)/pgtable_64.o endif diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 97d37f0a34f5..c634ed8636da 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -33,6 +33,7 @@ #include #include #include +#include #include "pgtable.h" /* @@ -410,6 +411,10 @@ SYM_CODE_START(startup_64) .Lon_kernel_cs: + pushq %rsi + call load_stage1_idt + popq %rsi + /* * paging_prepare() sets up the trampoline and checks if we need to * enable 5-level paging. @@ -537,6 +542,13 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) shrq $3, %rcx rep stosq +/* + * Load stage2 IDT + */ + pushq %rsi + call load_stage2_idt + popq %rsi + /* * Do the extraction, and jump to the new kernel.. */ @@ -690,10 +702,21 @@ SYM_DATA_START_LOCAL(gdt) .quad 0x0000000000000000 /* TS continued */ SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end) +SYM_DATA_START(boot_idt_desc) + .word boot_idt_end - boot_idt - 1 + .quad 0 +SYM_DATA_END(boot_idt_desc) + .balign 8 +SYM_DATA_START(boot_idt) + .rept BOOT_IDT_ENTRIES + .quad 0 + .quad 0 + .endr +SYM_DATA_END_LABEL(boot_idt, SYM_L_GLOBAL, boot_idt_end) + #ifdef CONFIG_EFI_STUB SYM_DATA(image_offset, .long 0) #endif - #ifdef CONFIG_EFI_MIXED SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0, 0) SYM_DATA(efi_is64, .byte 1) diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c new file mode 100644 index 000000000000..082cd6bca033 --- /dev/null +++ b/arch/x86/boot/compressed/idt_64.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include +#include "misc.h" + +static void set_idt_entry(int vector, void (*handler)(void)) +{ + unsigned long address = (unsigned long)handler; + gate_desc entry; + + memset(&entry, 0, sizeof(entry)); + + entry.offset_low = (u16)(address & 0xffff); + entry.segment = __KERNEL_CS; + entry.bits.type = GATE_TRAP; + entry.bits.p = 1; + entry.offset_middle = (u16)((address >> 16) & 0xffff); + entry.offset_high = (u32)(address >> 32); + + memcpy(&boot_idt[vector], &entry, sizeof(entry)); +} + +/* Have this here so we don't need to include */ +static void load_boot_idt(const struct desc_ptr *dtr) +{ + asm volatile("lidt %0"::"m" (*dtr)); +} + +/* Setup IDT before kernel jumping to .Lrelocated */ +void load_stage1_idt(void) +{ + boot_idt_desc.address = (unsigned long)boot_idt; + + load_boot_idt(&boot_idt_desc); +} + +/* Setup IDT after kernel jumping to .Lrelocated */ +void load_stage2_idt(void) +{ + boot_idt_desc.address = (unsigned long)boot_idt; + + load_boot_idt(&boot_idt_desc); +} diff --git a/arch/x86/boot/compressed/idt_handlers_64.S b/arch/x86/boot/compressed/idt_handlers_64.S new file mode 100644 index 000000000000..36dee2f40a8b --- /dev/null +++ b/arch/x86/boot/compressed/idt_handlers_64.S @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Early IDT handler entry points + * + * Copyright (C) 2019 SUSE + * + * Author: Joerg Roedel + */ + +#include + +/* For ORIG_RAX */ +#include "../../entry/calling.h" + +.macro EXCEPTION_HANDLER name function error_code=0 +SYM_FUNC_START(\name) + + /* Build pt_regs */ + .if \error_code == 0 + pushq $0 + .endif + + pushq %rdi + pushq %rsi + pushq %rdx + pushq %rcx + pushq %rax + pushq %r8 + pushq %r9 + pushq %r10 + pushq %r11 + pushq %rbx + pushq %rbp + pushq %r12 + pushq %r13 + pushq %r14 + pushq %r15 + + /* Call handler with pt_regs */ + movq %rsp, %rdi + /* Error code is second parameter */ + movq ORIG_RAX(%rsp), %rsi + call \function + + /* Restore regs */ + popq %r15 + popq %r14 + popq %r13 + popq %r12 + popq %rbp + popq %rbx + popq %r11 + popq %r10 + popq %r9 + popq %r8 + popq %rax + popq %rcx + popq %rdx + popq %rsi + popq %rdi + + /* Remove error code and return */ + addq $8, %rsp + + iretq +SYM_FUNC_END(\name) + .endm + + .text + .code64 diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 3efce27ba35c..8feb5f6f329e 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -23,6 +23,7 @@ #include #include #include +#include #define BOOT_CTYPE_H #include @@ -133,4 +134,8 @@ int count_immovable_mem_regions(void); static inline int count_immovable_mem_regions(void) { return 0; } #endif +/* idt_64.c */ +extern gate_desc boot_idt[BOOT_IDT_ENTRIES]; +extern struct desc_ptr boot_idt_desc; + #endif /* BOOT_COMPRESSED_MISC_H */ diff --git a/arch/x86/include/asm/desc_defs.h b/arch/x86/include/asm/desc_defs.h index a91f3b6e4f2a..5621fb3f2d1a 100644 --- a/arch/x86/include/asm/desc_defs.h +++ b/arch/x86/include/asm/desc_defs.h @@ -109,6 +109,9 @@ struct desc_ptr { #endif /* !__ASSEMBLY__ */ +/* Boot IDT definitions */ +#define BOOT_IDT_ENTRIES 32 + /* Access rights as returned by LAR */ #define AR_TYPE_RODATA (0 * (1 << 9)) #define AR_TYPE_RWDATA (1 * (1 << 9)) -- cgit v1.2.3-58-ga151 From 5f2bb01682b7b067783207994c7b8a3dbeb1cd83 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:15 +0200 Subject: x86/boot/compressed/64: Rename kaslr_64.c to ident_map_64.c The file contains only code related to identity-mapped page tables. Rename the file and compile it always in. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20200907131613.12703-15-joro@8bytes.org --- arch/x86/boot/compressed/Makefile | 2 +- arch/x86/boot/compressed/ident_map_64.c | 162 ++++++++++++++++++++++++++++++++ arch/x86/boot/compressed/kaslr.c | 9 -- arch/x86/boot/compressed/kaslr_64.c | 153 ------------------------------ arch/x86/boot/compressed/misc.h | 8 ++ 5 files changed, 171 insertions(+), 163 deletions(-) create mode 100644 arch/x86/boot/compressed/ident_map_64.c delete mode 100644 arch/x86/boot/compressed/kaslr_64.c diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index c661dc57674e..e7f3eba99ea2 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -84,7 +84,7 @@ vmlinux-objs-y := $(obj)/vmlinux.lds $(obj)/kernel_info.o $(obj)/head_$(BITS).o vmlinux-objs-$(CONFIG_EARLY_PRINTK) += $(obj)/early_serial_console.o vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o ifdef CONFIG_X86_64 - vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr_64.o + vmlinux-objs-y += $(obj)/ident_map_64.o vmlinux-objs-y += $(obj)/idt_64.o $(obj)/idt_handlers_64.o vmlinux-objs-y += $(obj)/mem_encrypt.o vmlinux-objs-y += $(obj)/pgtable_64.o diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c new file mode 100644 index 000000000000..d9932a133ac9 --- /dev/null +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -0,0 +1,162 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This code is used on x86_64 to create page table identity mappings on + * demand by building up a new set of page tables (or appending to the + * existing ones), and then switching over to them when ready. + * + * Copyright (C) 2015-2016 Yinghai Lu + * Copyright (C) 2016 Kees Cook + */ + +/* + * Since we're dealing with identity mappings, physical and virtual + * addresses are the same, so override these defines which are ultimately + * used by the headers in misc.h. + */ +#define __pa(x) ((unsigned long)(x)) +#define __va(x) ((void *)((unsigned long)(x))) + +/* No PAGE_TABLE_ISOLATION support needed either: */ +#undef CONFIG_PAGE_TABLE_ISOLATION + +#include "misc.h" + +/* These actually do the work of building the kernel identity maps. */ +#include +#include +/* Use the static base for this part of the boot process */ +#undef __PAGE_OFFSET +#define __PAGE_OFFSET __PAGE_OFFSET_BASE +#include "../../mm/ident_map.c" + +#ifdef CONFIG_X86_5LEVEL +unsigned int __pgtable_l5_enabled; +unsigned int pgdir_shift = 39; +unsigned int ptrs_per_p4d = 1; +#endif + +/* Used by PAGE_KERN* macros: */ +pteval_t __default_kernel_pte_mask __read_mostly = ~0; + +/* Used to track our page table allocation area. */ +struct alloc_pgt_data { + unsigned char *pgt_buf; + unsigned long pgt_buf_size; + unsigned long pgt_buf_offset; +}; + +/* + * Allocates space for a page table entry, using struct alloc_pgt_data + * above. Besides the local callers, this is used as the allocation + * callback in mapping_info below. + */ +static void *alloc_pgt_page(void *context) +{ + struct alloc_pgt_data *pages = (struct alloc_pgt_data *)context; + unsigned char *entry; + + /* Validate there is space available for a new page. */ + if (pages->pgt_buf_offset >= pages->pgt_buf_size) { + debug_putstr("out of pgt_buf in " __FILE__ "!?\n"); + debug_putaddr(pages->pgt_buf_offset); + debug_putaddr(pages->pgt_buf_size); + return NULL; + } + + entry = pages->pgt_buf + pages->pgt_buf_offset; + pages->pgt_buf_offset += PAGE_SIZE; + + return entry; +} + +/* Used to track our allocated page tables. */ +static struct alloc_pgt_data pgt_data; + +/* The top level page table entry pointer. */ +static unsigned long top_level_pgt; + +phys_addr_t physical_mask = (1ULL << __PHYSICAL_MASK_SHIFT) - 1; + +/* + * Mapping information structure passed to kernel_ident_mapping_init(). + * Due to relocation, pointers must be assigned at run time not build time. + */ +static struct x86_mapping_info mapping_info; + +/* Locates and clears a region for a new top level page table. */ +void initialize_identity_maps(void) +{ + /* If running as an SEV guest, the encryption mask is required. */ + set_sev_encryption_mask(); + + /* Exclude the encryption mask from __PHYSICAL_MASK */ + physical_mask &= ~sme_me_mask; + + /* Init mapping_info with run-time function/buffer pointers. */ + mapping_info.alloc_pgt_page = alloc_pgt_page; + mapping_info.context = &pgt_data; + mapping_info.page_flag = __PAGE_KERNEL_LARGE_EXEC | sme_me_mask; + mapping_info.kernpg_flag = _KERNPG_TABLE; + + /* + * It should be impossible for this not to already be true, + * but since calling this a second time would rewind the other + * counters, let's just make sure this is reset too. + */ + pgt_data.pgt_buf_offset = 0; + + /* + * If we came here via startup_32(), cr3 will be _pgtable already + * and we must append to the existing area instead of entirely + * overwriting it. + * + * With 5-level paging, we use '_pgtable' to allocate the p4d page table, + * the top-level page table is allocated separately. + * + * p4d_offset(top_level_pgt, 0) would cover both the 4- and 5-level + * cases. On 4-level paging it's equal to 'top_level_pgt'. + */ + top_level_pgt = read_cr3_pa(); + if (p4d_offset((pgd_t *)top_level_pgt, 0) == (p4d_t *)_pgtable) { + debug_putstr("booted via startup_32()\n"); + pgt_data.pgt_buf = _pgtable + BOOT_INIT_PGT_SIZE; + pgt_data.pgt_buf_size = BOOT_PGT_SIZE - BOOT_INIT_PGT_SIZE; + memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size); + } else { + debug_putstr("booted via startup_64()\n"); + pgt_data.pgt_buf = _pgtable; + pgt_data.pgt_buf_size = BOOT_PGT_SIZE; + memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size); + top_level_pgt = (unsigned long)alloc_pgt_page(&pgt_data); + } +} + +/* + * Adds the specified range to what will become the new identity mappings. + * Once all ranges have been added, the new mapping is activated by calling + * finalize_identity_maps() below. + */ +void add_identity_map(unsigned long start, unsigned long size) +{ + unsigned long end = start + size; + + /* Align boundary to 2M. */ + start = round_down(start, PMD_SIZE); + end = round_up(end, PMD_SIZE); + if (start >= end) + return; + + /* Build the mapping. */ + kernel_ident_mapping_init(&mapping_info, (pgd_t *)top_level_pgt, + start, end); +} + +/* + * This switches the page tables to the new level4 that has been built + * via calls to add_identity_map() above. If booted via startup_32(), + * this is effectively a no-op. + */ +void finalize_identity_maps(void) +{ + write_cr3(top_level_pgt); +} diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 877970d76249..e27de98ed038 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -40,17 +40,8 @@ #include /* For COMMAND_LINE_SIZE */ #undef _SETUP -#ifdef CONFIG_X86_5LEVEL -unsigned int __pgtable_l5_enabled; -unsigned int pgdir_shift __ro_after_init = 39; -unsigned int ptrs_per_p4d __ro_after_init = 1; -#endif - extern unsigned long get_cmd_line_ptr(void); -/* Used by PAGE_KERN* macros: */ -pteval_t __default_kernel_pte_mask __read_mostly = ~0; - /* Simplified build-specific string for starting entropy. */ static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@" LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION; diff --git a/arch/x86/boot/compressed/kaslr_64.c b/arch/x86/boot/compressed/kaslr_64.c deleted file mode 100644 index f9c5c13d979b..000000000000 --- a/arch/x86/boot/compressed/kaslr_64.c +++ /dev/null @@ -1,153 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * This code is used on x86_64 to create page table identity mappings on - * demand by building up a new set of page tables (or appending to the - * existing ones), and then switching over to them when ready. - * - * Copyright (C) 2015-2016 Yinghai Lu - * Copyright (C) 2016 Kees Cook - */ - -/* - * Since we're dealing with identity mappings, physical and virtual - * addresses are the same, so override these defines which are ultimately - * used by the headers in misc.h. - */ -#define __pa(x) ((unsigned long)(x)) -#define __va(x) ((void *)((unsigned long)(x))) - -/* No PAGE_TABLE_ISOLATION support needed either: */ -#undef CONFIG_PAGE_TABLE_ISOLATION - -#include "misc.h" - -/* These actually do the work of building the kernel identity maps. */ -#include -#include -/* Use the static base for this part of the boot process */ -#undef __PAGE_OFFSET -#define __PAGE_OFFSET __PAGE_OFFSET_BASE -#include "../../mm/ident_map.c" - -/* Used to track our page table allocation area. */ -struct alloc_pgt_data { - unsigned char *pgt_buf; - unsigned long pgt_buf_size; - unsigned long pgt_buf_offset; -}; - -/* - * Allocates space for a page table entry, using struct alloc_pgt_data - * above. Besides the local callers, this is used as the allocation - * callback in mapping_info below. - */ -static void *alloc_pgt_page(void *context) -{ - struct alloc_pgt_data *pages = (struct alloc_pgt_data *)context; - unsigned char *entry; - - /* Validate there is space available for a new page. */ - if (pages->pgt_buf_offset >= pages->pgt_buf_size) { - debug_putstr("out of pgt_buf in " __FILE__ "!?\n"); - debug_putaddr(pages->pgt_buf_offset); - debug_putaddr(pages->pgt_buf_size); - return NULL; - } - - entry = pages->pgt_buf + pages->pgt_buf_offset; - pages->pgt_buf_offset += PAGE_SIZE; - - return entry; -} - -/* Used to track our allocated page tables. */ -static struct alloc_pgt_data pgt_data; - -/* The top level page table entry pointer. */ -static unsigned long top_level_pgt; - -phys_addr_t physical_mask = (1ULL << __PHYSICAL_MASK_SHIFT) - 1; - -/* - * Mapping information structure passed to kernel_ident_mapping_init(). - * Due to relocation, pointers must be assigned at run time not build time. - */ -static struct x86_mapping_info mapping_info; - -/* Locates and clears a region for a new top level page table. */ -void initialize_identity_maps(void) -{ - /* If running as an SEV guest, the encryption mask is required. */ - set_sev_encryption_mask(); - - /* Exclude the encryption mask from __PHYSICAL_MASK */ - physical_mask &= ~sme_me_mask; - - /* Init mapping_info with run-time function/buffer pointers. */ - mapping_info.alloc_pgt_page = alloc_pgt_page; - mapping_info.context = &pgt_data; - mapping_info.page_flag = __PAGE_KERNEL_LARGE_EXEC | sme_me_mask; - mapping_info.kernpg_flag = _KERNPG_TABLE; - - /* - * It should be impossible for this not to already be true, - * but since calling this a second time would rewind the other - * counters, let's just make sure this is reset too. - */ - pgt_data.pgt_buf_offset = 0; - - /* - * If we came here via startup_32(), cr3 will be _pgtable already - * and we must append to the existing area instead of entirely - * overwriting it. - * - * With 5-level paging, we use '_pgtable' to allocate the p4d page table, - * the top-level page table is allocated separately. - * - * p4d_offset(top_level_pgt, 0) would cover both the 4- and 5-level - * cases. On 4-level paging it's equal to 'top_level_pgt'. - */ - top_level_pgt = read_cr3_pa(); - if (p4d_offset((pgd_t *)top_level_pgt, 0) == (p4d_t *)_pgtable) { - debug_putstr("booted via startup_32()\n"); - pgt_data.pgt_buf = _pgtable + BOOT_INIT_PGT_SIZE; - pgt_data.pgt_buf_size = BOOT_PGT_SIZE - BOOT_INIT_PGT_SIZE; - memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size); - } else { - debug_putstr("booted via startup_64()\n"); - pgt_data.pgt_buf = _pgtable; - pgt_data.pgt_buf_size = BOOT_PGT_SIZE; - memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size); - top_level_pgt = (unsigned long)alloc_pgt_page(&pgt_data); - } -} - -/* - * Adds the specified range to what will become the new identity mappings. - * Once all ranges have been added, the new mapping is activated by calling - * finalize_identity_maps() below. - */ -void add_identity_map(unsigned long start, unsigned long size) -{ - unsigned long end = start + size; - - /* Align boundary to 2M. */ - start = round_down(start, PMD_SIZE); - end = round_up(end, PMD_SIZE); - if (start >= end) - return; - - /* Build the mapping. */ - kernel_ident_mapping_init(&mapping_info, (pgd_t *)top_level_pgt, - start, end); -} - -/* - * This switches the page tables to the new level4 that has been built - * via calls to add_identity_map() above. If booted via startup_32(), - * this is effectively a no-op. - */ -void finalize_identity_maps(void) -{ - write_cr3(top_level_pgt); -} diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 8feb5f6f329e..98b7a1df9c59 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -134,6 +134,14 @@ int count_immovable_mem_regions(void); static inline int count_immovable_mem_regions(void) { return 0; } #endif +/* ident_map_64.c */ +#ifdef CONFIG_X86_5LEVEL +extern unsigned int __pgtable_l5_enabled, pgdir_shift, ptrs_per_p4d; +#endif + +/* Used by PAGE_KERN* macros: */ +extern pteval_t __default_kernel_pte_mask; + /* idt_64.c */ extern gate_desc boot_idt[BOOT_IDT_ENTRIES]; extern struct desc_ptr boot_idt_desc; -- cgit v1.2.3-58-ga151 From 8b0d3b3b41ab6f14f1ce6d4a6b1c5f60b825123f Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:16 +0200 Subject: x86/boot/compressed/64: Add page-fault handler Install a page-fault handler to add an identity mapping to addresses not yet mapped. Also do some checking whether the error code is sane. This makes non SEV-ES machines use the exception handling infrastructure in the pre-decompressions boot code too, making it less likely to break in the future. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20200907131613.12703-16-joro@8bytes.org --- arch/x86/boot/compressed/ident_map_64.c | 39 ++++++++++++++++++++++++++++++ arch/x86/boot/compressed/idt_64.c | 2 ++ arch/x86/boot/compressed/idt_handlers_64.S | 2 ++ arch/x86/boot/compressed/misc.h | 6 +++++ 4 files changed, 49 insertions(+) diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index d9932a133ac9..e3d980ae9c2b 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -19,10 +19,13 @@ /* No PAGE_TABLE_ISOLATION support needed either: */ #undef CONFIG_PAGE_TABLE_ISOLATION +#include "error.h" #include "misc.h" /* These actually do the work of building the kernel identity maps. */ #include +#include +#include #include /* Use the static base for this part of the boot process */ #undef __PAGE_OFFSET @@ -160,3 +163,39 @@ void finalize_identity_maps(void) { write_cr3(top_level_pgt); } + +static void do_pf_error(const char *msg, unsigned long error_code, + unsigned long address, unsigned long ip) +{ + error_putstr(msg); + + error_putstr("\nError Code: "); + error_puthex(error_code); + error_putstr("\nCR2: 0x"); + error_puthex(address); + error_putstr("\nRIP relative to _head: 0x"); + error_puthex(ip - (unsigned long)_head); + error_putstr("\n"); + + error("Stopping.\n"); +} + +void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code) +{ + unsigned long address = native_read_cr2(); + + /* + * Check for unexpected error codes. Unexpected are: + * - Faults on present pages + * - User faults + * - Reserved bits set + */ + if (error_code & (X86_PF_PROT | X86_PF_USER | X86_PF_RSVD)) + do_pf_error("Unexpected page-fault:", error_code, address, regs->ip); + + /* + * Error code is sane - now identity map the 2M region around + * the faulting address. + */ + add_identity_map(address & PMD_MASK, PMD_SIZE); +} diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c index 082cd6bca033..5f083092a86d 100644 --- a/arch/x86/boot/compressed/idt_64.c +++ b/arch/x86/boot/compressed/idt_64.c @@ -40,5 +40,7 @@ void load_stage2_idt(void) { boot_idt_desc.address = (unsigned long)boot_idt; + set_idt_entry(X86_TRAP_PF, boot_page_fault); + load_boot_idt(&boot_idt_desc); } diff --git a/arch/x86/boot/compressed/idt_handlers_64.S b/arch/x86/boot/compressed/idt_handlers_64.S index 36dee2f40a8b..b20e57504a94 100644 --- a/arch/x86/boot/compressed/idt_handlers_64.S +++ b/arch/x86/boot/compressed/idt_handlers_64.S @@ -68,3 +68,5 @@ SYM_FUNC_END(\name) .text .code64 + +EXCEPTION_HANDLER boot_page_fault do_boot_page_fault error_code=1 diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 98b7a1df9c59..f0e199174c5f 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -37,6 +37,9 @@ #define memptr unsigned #endif +/* boot/compressed/vmlinux start and end markers */ +extern char _head[], _end[]; + /* misc.c */ extern memptr free_mem_ptr; extern memptr free_mem_end_ptr; @@ -146,4 +149,7 @@ extern pteval_t __default_kernel_pte_mask; extern gate_desc boot_idt[BOOT_IDT_ENTRIES]; extern struct desc_ptr boot_idt_desc; +/* IDT Entry Points */ +void boot_page_fault(void); + #endif /* BOOT_COMPRESSED_MISC_H */ -- cgit v1.2.3-58-ga151 From ca0e22d4f011a56e974fa3a712d76e86a791559d Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:17 +0200 Subject: x86/boot/compressed/64: Always switch to own page table When booted through startup_64(), the kernel keeps running on the EFI page table until the KASLR code sets up its own page table. Without KASLR, the pre-decompression boot code never switches off the EFI page table. Change that by unconditionally switching to a kernel-controlled page table after relocation. This makes sure the kernel can make changes to the mapping when necessary, for example map pages unencrypted in SEV and SEV-ES guests. Also, remove the debug_putstr() calls in initialize_identity_maps() because the function now runs before console_init() is called. [ bp: Massage commit message. ] Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20200907131613.12703-17-joro@8bytes.org --- arch/x86/boot/compressed/head_64.S | 3 +- arch/x86/boot/compressed/ident_map_64.c | 51 +++++++++++++++++++-------------- arch/x86/boot/compressed/kaslr.c | 3 -- 3 files changed, 32 insertions(+), 25 deletions(-) diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index c634ed8636da..fb6c0392306b 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -543,10 +543,11 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) rep stosq /* - * Load stage2 IDT + * Load stage2 IDT and switch to our own page-table */ pushq %rsi call load_stage2_idt + call initialize_identity_maps popq %rsi /* diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index e3d980ae9c2b..ecf9353b064d 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -86,9 +86,31 @@ phys_addr_t physical_mask = (1ULL << __PHYSICAL_MASK_SHIFT) - 1; */ static struct x86_mapping_info mapping_info; +/* + * Adds the specified range to what will become the new identity mappings. + * Once all ranges have been added, the new mapping is activated by calling + * finalize_identity_maps() below. + */ +void add_identity_map(unsigned long start, unsigned long size) +{ + unsigned long end = start + size; + + /* Align boundary to 2M. */ + start = round_down(start, PMD_SIZE); + end = round_up(end, PMD_SIZE); + if (start >= end) + return; + + /* Build the mapping. */ + kernel_ident_mapping_init(&mapping_info, (pgd_t *)top_level_pgt, + start, end); +} + /* Locates and clears a region for a new top level page table. */ void initialize_identity_maps(void) { + unsigned long start, size; + /* If running as an SEV guest, the encryption mask is required. */ set_sev_encryption_mask(); @@ -121,37 +143,24 @@ void initialize_identity_maps(void) */ top_level_pgt = read_cr3_pa(); if (p4d_offset((pgd_t *)top_level_pgt, 0) == (p4d_t *)_pgtable) { - debug_putstr("booted via startup_32()\n"); pgt_data.pgt_buf = _pgtable + BOOT_INIT_PGT_SIZE; pgt_data.pgt_buf_size = BOOT_PGT_SIZE - BOOT_INIT_PGT_SIZE; memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size); } else { - debug_putstr("booted via startup_64()\n"); pgt_data.pgt_buf = _pgtable; pgt_data.pgt_buf_size = BOOT_PGT_SIZE; memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size); top_level_pgt = (unsigned long)alloc_pgt_page(&pgt_data); } -} -/* - * Adds the specified range to what will become the new identity mappings. - * Once all ranges have been added, the new mapping is activated by calling - * finalize_identity_maps() below. - */ -void add_identity_map(unsigned long start, unsigned long size) -{ - unsigned long end = start + size; - - /* Align boundary to 2M. */ - start = round_down(start, PMD_SIZE); - end = round_up(end, PMD_SIZE); - if (start >= end) - return; - - /* Build the mapping. */ - kernel_ident_mapping_init(&mapping_info, (pgd_t *)top_level_pgt, - start, end); + /* + * New page-table is set up - map the kernel image and load it + * into cr3. + */ + start = (unsigned long)_head; + size = _end - _head; + add_identity_map(start, size); + write_cr3(top_level_pgt); } /* diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index e27de98ed038..82662869c4cb 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -861,9 +861,6 @@ void choose_random_location(unsigned long input, boot_params->hdr.loadflags |= KASLR_FLAG; - /* Prepare to add new identity pagetables on demand. */ - initialize_identity_maps(); - if (IS_ENABLED(CONFIG_X86_32)) mem_limit = KERNEL_IMAGE_SIZE; else -- cgit v1.2.3-58-ga151 From 8570978ea030757839747aa9944ea576708be3d4 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:18 +0200 Subject: x86/boot/compressed/64: Don't pre-map memory in KASLR code With the page-fault handler in place, he identity mapping can be built on-demand. So remove the code which manually creates the mappings and unexport/remove the functions used for it. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20200907131613.12703-18-joro@8bytes.org --- arch/x86/boot/compressed/ident_map_64.c | 6 ++---- arch/x86/boot/compressed/kaslr.c | 24 +----------------------- arch/x86/boot/compressed/misc.h | 10 ---------- 3 files changed, 3 insertions(+), 37 deletions(-) diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index ecf9353b064d..c63257bf8373 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -87,11 +87,9 @@ phys_addr_t physical_mask = (1ULL << __PHYSICAL_MASK_SHIFT) - 1; static struct x86_mapping_info mapping_info; /* - * Adds the specified range to what will become the new identity mappings. - * Once all ranges have been added, the new mapping is activated by calling - * finalize_identity_maps() below. + * Adds the specified range to the identity mappings. */ -void add_identity_map(unsigned long start, unsigned long size) +static void add_identity_map(unsigned long start, unsigned long size) { unsigned long end = start + size; diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 82662869c4cb..b59547ce5b19 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -397,8 +397,6 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, */ mem_avoid[MEM_AVOID_ZO_RANGE].start = input; mem_avoid[MEM_AVOID_ZO_RANGE].size = (output + init_size) - input; - add_identity_map(mem_avoid[MEM_AVOID_ZO_RANGE].start, - mem_avoid[MEM_AVOID_ZO_RANGE].size); /* Avoid initrd. */ initrd_start = (u64)boot_params->ext_ramdisk_image << 32; @@ -416,15 +414,11 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, cmd_line_size = strnlen((char *)cmd_line, COMMAND_LINE_SIZE-1) + 1; mem_avoid[MEM_AVOID_CMDLINE].start = cmd_line; mem_avoid[MEM_AVOID_CMDLINE].size = cmd_line_size; - add_identity_map(mem_avoid[MEM_AVOID_CMDLINE].start, - mem_avoid[MEM_AVOID_CMDLINE].size); } /* Avoid boot parameters. */ mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params; mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params); - add_identity_map(mem_avoid[MEM_AVOID_BOOTPARAMS].start, - mem_avoid[MEM_AVOID_BOOTPARAMS].size); /* We don't need to set a mapping for setup_data. */ @@ -433,11 +427,6 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, /* Enumerate the immovable memory regions */ num_immovable_mem = count_immovable_mem_regions(); - -#ifdef CONFIG_X86_VERBOSE_BOOTUP - /* Make sure video RAM can be used. */ - add_identity_map(0, PMD_SIZE); -#endif } /* @@ -884,19 +873,8 @@ void choose_random_location(unsigned long input, warn("Physical KASLR disabled: no suitable memory region!"); } else { /* Update the new physical address location. */ - if (*output != random_addr) { - add_identity_map(random_addr, output_size); + if (*output != random_addr) *output = random_addr; - } - - /* - * This loads the identity mapping page table. - * This should only be done if a new physical address - * is found for the kernel, otherwise we should keep - * the old page table to make it be like the "nokaslr" - * case. - */ - finalize_identity_maps(); } diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index f0e199174c5f..9840c82a39f1 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -98,17 +98,7 @@ static inline void choose_random_location(unsigned long input, #endif #ifdef CONFIG_X86_64 -void initialize_identity_maps(void); -void add_identity_map(unsigned long start, unsigned long size); -void finalize_identity_maps(void); extern unsigned char _pgtable[]; -#else -static inline void initialize_identity_maps(void) -{ } -static inline void add_identity_map(unsigned long start, unsigned long size) -{ } -static inline void finalize_identity_maps(void) -{ } #endif #ifdef CONFIG_EARLY_PRINTK -- cgit v1.2.3-58-ga151 From 21cf2372618ef167d8c4ae04880fb873b55b2daa Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:19 +0200 Subject: x86/boot/compressed/64: Change add_identity_map() to take start and end Changing the function to take start and end as parameters instead of start and size simplifies the callers which don't need to calculate the size if they already have start and end. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20200907131613.12703-19-joro@8bytes.org --- arch/x86/boot/compressed/ident_map_64.c | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index c63257bf8373..62e42c11a336 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -89,10 +89,8 @@ static struct x86_mapping_info mapping_info; /* * Adds the specified range to the identity mappings. */ -static void add_identity_map(unsigned long start, unsigned long size) +static void add_identity_map(unsigned long start, unsigned long end) { - unsigned long end = start + size; - /* Align boundary to 2M. */ start = round_down(start, PMD_SIZE); end = round_up(end, PMD_SIZE); @@ -107,8 +105,6 @@ static void add_identity_map(unsigned long start, unsigned long size) /* Locates and clears a region for a new top level page table. */ void initialize_identity_maps(void) { - unsigned long start, size; - /* If running as an SEV guest, the encryption mask is required. */ set_sev_encryption_mask(); @@ -155,9 +151,7 @@ void initialize_identity_maps(void) * New page-table is set up - map the kernel image and load it * into cr3. */ - start = (unsigned long)_head; - size = _end - _head; - add_identity_map(start, size); + add_identity_map((unsigned long)_head, (unsigned long)_end); write_cr3(top_level_pgt); } @@ -189,7 +183,8 @@ static void do_pf_error(const char *msg, unsigned long error_code, void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code) { - unsigned long address = native_read_cr2(); + unsigned long address = native_read_cr2() & PMD_MASK; + unsigned long end = address + PMD_SIZE; /* * Check for unexpected error codes. Unexpected are: @@ -204,5 +199,5 @@ void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code) * Error code is sane - now identity map the 2M region around * the faulting address. */ - add_identity_map(address & PMD_MASK, PMD_SIZE); + add_identity_map(address, end); } -- cgit v1.2.3-58-ga151 From 29dcc60f6a19fb0aaee97bd1ae2ed8a7dc6f0cfe Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:20 +0200 Subject: x86/boot/compressed/64: Add stage1 #VC handler Add the first handler for #VC exceptions. At stage 1 there is no GHCB yet because the kernel might still be running on the EFI page table. The stage 1 handler is limited to the MSR-based protocol to talk to the hypervisor and can only support CPUID exit-codes, but that is enough to get to stage 2. [ bp: Zap superfluous newlines after rd/wrmsr instruction mnemonics. ] Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-20-joro@8bytes.org --- arch/x86/boot/compressed/Makefile | 1 + arch/x86/boot/compressed/idt_64.c | 4 ++ arch/x86/boot/compressed/idt_handlers_64.S | 4 ++ arch/x86/boot/compressed/misc.h | 1 + arch/x86/boot/compressed/sev-es.c | 45 ++++++++++++++++++++ arch/x86/include/asm/msr-index.h | 1 + arch/x86/include/asm/sev-es.h | 37 +++++++++++++++++ arch/x86/include/asm/trapnr.h | 1 + arch/x86/kernel/sev-es-shared.c | 66 ++++++++++++++++++++++++++++++ 9 files changed, 160 insertions(+) create mode 100644 arch/x86/boot/compressed/sev-es.c create mode 100644 arch/x86/include/asm/sev-es.h create mode 100644 arch/x86/kernel/sev-es-shared.c diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index e7f3eba99ea2..38f4a52a4eda 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -88,6 +88,7 @@ ifdef CONFIG_X86_64 vmlinux-objs-y += $(obj)/idt_64.o $(obj)/idt_handlers_64.o vmlinux-objs-y += $(obj)/mem_encrypt.o vmlinux-objs-y += $(obj)/pgtable_64.o + vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev-es.o endif vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c index 5f083092a86d..f3ca7324be44 100644 --- a/arch/x86/boot/compressed/idt_64.c +++ b/arch/x86/boot/compressed/idt_64.c @@ -32,6 +32,10 @@ void load_stage1_idt(void) { boot_idt_desc.address = (unsigned long)boot_idt; + + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) + set_idt_entry(X86_TRAP_VC, boot_stage1_vc); + load_boot_idt(&boot_idt_desc); } diff --git a/arch/x86/boot/compressed/idt_handlers_64.S b/arch/x86/boot/compressed/idt_handlers_64.S index b20e57504a94..92eb4df478a1 100644 --- a/arch/x86/boot/compressed/idt_handlers_64.S +++ b/arch/x86/boot/compressed/idt_handlers_64.S @@ -70,3 +70,7 @@ SYM_FUNC_END(\name) .code64 EXCEPTION_HANDLER boot_page_fault do_boot_page_fault error_code=1 + +#ifdef CONFIG_AMD_MEM_ENCRYPT +EXCEPTION_HANDLER boot_stage1_vc do_vc_no_ghcb error_code=1 +#endif diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 9840c82a39f1..eaa8b45ebccb 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -141,5 +141,6 @@ extern struct desc_ptr boot_idt_desc; /* IDT Entry Points */ void boot_page_fault(void); +void boot_stage1_vc(void); #endif /* BOOT_COMPRESSED_MISC_H */ diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c new file mode 100644 index 000000000000..99c3bcd4d61f --- /dev/null +++ b/arch/x86/boot/compressed/sev-es.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * AMD Encrypted Register State Support + * + * Author: Joerg Roedel + */ + +/* + * misc.h needs to be first because it knows how to include the other kernel + * headers in the pre-decompression code in a way that does not break + * compilation. + */ +#include "misc.h" + +#include +#include +#include +#include + +static inline u64 sev_es_rd_ghcb_msr(void) +{ + unsigned long low, high; + + asm volatile("rdmsr" : "=a" (low), "=d" (high) : + "c" (MSR_AMD64_SEV_ES_GHCB)); + + return ((high << 32) | low); +} + +static inline void sev_es_wr_ghcb_msr(u64 val) +{ + u32 low, high; + + low = val & 0xffffffffUL; + high = val >> 32; + + asm volatile("wrmsr" : : "c" (MSR_AMD64_SEV_ES_GHCB), + "a"(low), "d" (high) : "memory"); +} + +#undef __init +#define __init + +/* Include code for early handlers */ +#include "../../kernel/sev-es-shared.c" diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 2859ee4f39a8..da34fdba7c5a 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -466,6 +466,7 @@ #define MSR_AMD64_IBSBRTARGET 0xc001103b #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ +#define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 #define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) diff --git a/arch/x86/include/asm/sev-es.h b/arch/x86/include/asm/sev-es.h new file mode 100644 index 000000000000..48a44038b5d1 --- /dev/null +++ b/arch/x86/include/asm/sev-es.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * AMD Encrypted Register State Support + * + * Author: Joerg Roedel + */ + +#ifndef __ASM_ENCRYPTED_STATE_H +#define __ASM_ENCRYPTED_STATE_H + +#include + +#define GHCB_SEV_CPUID_REQ 0x004UL +#define GHCB_CPUID_REQ_EAX 0 +#define GHCB_CPUID_REQ_EBX 1 +#define GHCB_CPUID_REQ_ECX 2 +#define GHCB_CPUID_REQ_EDX 3 +#define GHCB_CPUID_REQ(fn, reg) (GHCB_SEV_CPUID_REQ | \ + (((unsigned long)reg & 3) << 30) | \ + (((unsigned long)fn) << 32)) + +#define GHCB_SEV_CPUID_RESP 0x005UL +#define GHCB_SEV_TERMINATE 0x100UL + +#define GHCB_SEV_GHCB_RESP_CODE(v) ((v) & 0xfff) +#define VMGEXIT() { asm volatile("rep; vmmcall\n\r"); } + +void do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code); + +static inline u64 lower_bits(u64 val, unsigned int bits) +{ + u64 mask = (1ULL << bits) - 1; + + return (val & mask); +} + +#endif diff --git a/arch/x86/include/asm/trapnr.h b/arch/x86/include/asm/trapnr.h index 082f45631fa9..f5d2325aa0b7 100644 --- a/arch/x86/include/asm/trapnr.h +++ b/arch/x86/include/asm/trapnr.h @@ -26,6 +26,7 @@ #define X86_TRAP_XF 19 /* SIMD Floating-Point Exception */ #define X86_TRAP_VE 20 /* Virtualization Exception */ #define X86_TRAP_CP 21 /* Control Protection Exception */ +#define X86_TRAP_VC 29 /* VMM Communication Exception */ #define X86_TRAP_IRET 32 /* IRET Exception */ #endif diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c new file mode 100644 index 000000000000..0bea32341afa --- /dev/null +++ b/arch/x86/kernel/sev-es-shared.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * AMD Encrypted Register State Support + * + * Author: Joerg Roedel + * + * This file is not compiled stand-alone. It contains code shared + * between the pre-decompression boot code and the running Linux kernel + * and is included directly into both code-bases. + */ + +/* + * Boot VC Handler - This is the first VC handler during boot, there is no GHCB + * page yet, so it only supports the MSR based communication with the + * hypervisor and only the CPUID exit-code. + */ +void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) +{ + unsigned int fn = lower_bits(regs->ax, 32); + unsigned long val; + + /* Only CPUID is supported via MSR protocol */ + if (exit_code != SVM_EXIT_CPUID) + goto fail; + + sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EAX)); + VMGEXIT(); + val = sev_es_rd_ghcb_msr(); + if (GHCB_SEV_GHCB_RESP_CODE(val) != GHCB_SEV_CPUID_RESP) + goto fail; + regs->ax = val >> 32; + + sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EBX)); + VMGEXIT(); + val = sev_es_rd_ghcb_msr(); + if (GHCB_SEV_GHCB_RESP_CODE(val) != GHCB_SEV_CPUID_RESP) + goto fail; + regs->bx = val >> 32; + + sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_ECX)); + VMGEXIT(); + val = sev_es_rd_ghcb_msr(); + if (GHCB_SEV_GHCB_RESP_CODE(val) != GHCB_SEV_CPUID_RESP) + goto fail; + regs->cx = val >> 32; + + sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EDX)); + VMGEXIT(); + val = sev_es_rd_ghcb_msr(); + if (GHCB_SEV_GHCB_RESP_CODE(val) != GHCB_SEV_CPUID_RESP) + goto fail; + regs->dx = val >> 32; + + /* Skip over the CPUID two-byte opcode */ + regs->ip += 2; + + return; + +fail: + sev_es_wr_ghcb_msr(GHCB_SEV_TERMINATE); + VMGEXIT(); + + /* Shouldn't get here - if we do halt the machine */ + while (true) + asm volatile("hlt\n"); +} -- cgit v1.2.3-58-ga151 From c2a0304a286f386e45cea3f4b0617f0813de67fd Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:21 +0200 Subject: x86/boot/compressed/64: Call set_sev_encryption_mask() earlier Call set_sev_encryption_mask() while still on the stage 1 #VC-handler because the stage 2 handler needs the kernel's own page tables to be set up, to which calling set_sev_encryption_mask() is a prerequisite. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-21-joro@8bytes.org --- arch/x86/boot/compressed/head_64.S | 9 ++++++++- arch/x86/boot/compressed/ident_map_64.c | 3 --- 2 files changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index fb6c0392306b..42190c00d9c2 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -543,9 +543,16 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) rep stosq /* - * Load stage2 IDT and switch to our own page-table + * If running as an SEV guest, the encryption mask is required in the + * page-table setup code below. When the guest also has SEV-ES enabled + * set_sev_encryption_mask() will cause #VC exceptions, but the stage2 + * handler can't map its GHCB because the page-table is not set up yet. + * So set up the encryption mask here while still on the stage1 #VC + * handler. Then load stage2 IDT and switch to the kernel's own + * page-table. */ pushq %rsi + call set_sev_encryption_mask call load_stage2_idt call initialize_identity_maps popq %rsi diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index 62e42c11a336..b4f2a5f503cd 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -105,9 +105,6 @@ static void add_identity_map(unsigned long start, unsigned long end) /* Locates and clears a region for a new top level page table. */ void initialize_identity_maps(void) { - /* If running as an SEV guest, the encryption mask is required. */ - set_sev_encryption_mask(); - /* Exclude the encryption mask from __PHYSICAL_MASK */ physical_mask &= ~sme_me_mask; -- cgit v1.2.3-58-ga151 From 4b3fdca64a7e8ad90c87cad1fbc6991471f48dc7 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:22 +0200 Subject: x86/boot/compressed/64: Check return value of kernel_ident_mapping_init() The function can fail to create an identity mapping, check for that and bail out if it happens. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-22-joro@8bytes.org --- arch/x86/boot/compressed/ident_map_64.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index b4f2a5f503cd..aa91bebc0fe9 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -91,6 +91,8 @@ static struct x86_mapping_info mapping_info; */ static void add_identity_map(unsigned long start, unsigned long end) { + int ret; + /* Align boundary to 2M. */ start = round_down(start, PMD_SIZE); end = round_up(end, PMD_SIZE); @@ -98,8 +100,9 @@ static void add_identity_map(unsigned long start, unsigned long end) return; /* Build the mapping. */ - kernel_ident_mapping_init(&mapping_info, (pgd_t *)top_level_pgt, - start, end); + ret = kernel_ident_mapping_init(&mapping_info, (pgd_t *)top_level_pgt, start, end); + if (ret) + error("Error: kernel_ident_mapping_init() failed\n"); } /* Locates and clears a region for a new top level page table. */ -- cgit v1.2.3-58-ga151 From c81d60029a1393183d2125fcb4b64831629b8864 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:23 +0200 Subject: x86/boot/compressed/64: Add set_page_en/decrypted() helpers The functions are needed to map the GHCB for SEV-ES guests. The GHCB is used for communication with the hypervisor, so its content must not be encrypted. After the GHCB is not needed anymore it must be mapped encrypted again so that the running kernel image can safely re-use the memory. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-23-joro@8bytes.org --- arch/x86/boot/compressed/ident_map_64.c | 133 ++++++++++++++++++++++++++++++++ arch/x86/boot/compressed/misc.h | 2 + 2 files changed, 135 insertions(+) diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index aa91bebc0fe9..05742f641a06 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -24,6 +24,7 @@ /* These actually do the work of building the kernel identity maps. */ #include +#include #include #include #include @@ -165,6 +166,138 @@ void finalize_identity_maps(void) write_cr3(top_level_pgt); } +static pte_t *split_large_pmd(struct x86_mapping_info *info, + pmd_t *pmdp, unsigned long __address) +{ + unsigned long page_flags; + unsigned long address; + pte_t *pte; + pmd_t pmd; + int i; + + pte = (pte_t *)info->alloc_pgt_page(info->context); + if (!pte) + return NULL; + + address = __address & PMD_MASK; + /* No large page - clear PSE flag */ + page_flags = info->page_flag & ~_PAGE_PSE; + + /* Populate the PTEs */ + for (i = 0; i < PTRS_PER_PMD; i++) { + set_pte(&pte[i], __pte(address | page_flags)); + address += PAGE_SIZE; + } + + /* + * Ideally we need to clear the large PMD first and do a TLB + * flush before we write the new PMD. But the 2M range of the + * PMD might contain the code we execute and/or the stack + * we are on, so we can't do that. But that should be safe here + * because we are going from large to small mappings and we are + * also the only user of the page-table, so there is no chance + * of a TLB multihit. + */ + pmd = __pmd((unsigned long)pte | info->kernpg_flag); + set_pmd(pmdp, pmd); + /* Flush TLB to establish the new PMD */ + write_cr3(top_level_pgt); + + return pte + pte_index(__address); +} + +static void clflush_page(unsigned long address) +{ + unsigned int flush_size; + char *cl, *start, *end; + + /* + * Hardcode cl-size to 64 - CPUID can't be used here because that might + * cause another #VC exception and the GHCB is not ready to use yet. + */ + flush_size = 64; + start = (char *)(address & PAGE_MASK); + end = start + PAGE_SIZE; + + /* + * First make sure there are no pending writes on the cache-lines to + * flush. + */ + asm volatile("mfence" : : : "memory"); + + for (cl = start; cl != end; cl += flush_size) + clflush(cl); +} + +static int set_clr_page_flags(struct x86_mapping_info *info, + unsigned long address, + pteval_t set, pteval_t clr) +{ + pgd_t *pgdp = (pgd_t *)top_level_pgt; + p4d_t *p4dp; + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep, pte; + + /* + * First make sure there is a PMD mapping for 'address'. + * It should already exist, but keep things generic. + * + * To map the page just read from it and fault it in if there is no + * mapping yet. add_identity_map() can't be called here because that + * would unconditionally map the address on PMD level, destroying any + * PTE-level mappings that might already exist. Use assembly here so + * the access won't be optimized away. + */ + asm volatile("mov %[address], %%r9" + :: [address] "g" (*(unsigned long *)address) + : "r9", "memory"); + + /* + * The page is mapped at least with PMD size - so skip checks and walk + * directly to the PMD. + */ + p4dp = p4d_offset(pgdp, address); + pudp = pud_offset(p4dp, address); + pmdp = pmd_offset(pudp, address); + + if (pmd_large(*pmdp)) + ptep = split_large_pmd(info, pmdp, address); + else + ptep = pte_offset_kernel(pmdp, address); + + if (!ptep) + return -ENOMEM; + + /* + * Changing encryption attributes of a page requires to flush it from + * the caches. + */ + if ((set | clr) & _PAGE_ENC) + clflush_page(address); + + /* Update PTE */ + pte = *ptep; + pte = pte_set_flags(pte, set); + pte = pte_clear_flags(pte, clr); + set_pte(ptep, pte); + + /* Flush TLB after changing encryption attribute */ + write_cr3(top_level_pgt); + + return 0; +} + +int set_page_decrypted(unsigned long address) +{ + return set_clr_page_flags(&mapping_info, address, 0, _PAGE_ENC); +} + +int set_page_encrypted(unsigned long address) +{ + return set_clr_page_flags(&mapping_info, address, _PAGE_ENC, 0); +} + static void do_pf_error(const char *msg, unsigned long error_code, unsigned long address, unsigned long ip) { diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index eaa8b45ebccb..01c0fb3417ca 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -98,6 +98,8 @@ static inline void choose_random_location(unsigned long input, #endif #ifdef CONFIG_X86_64 +extern int set_page_decrypted(unsigned long address); +extern int set_page_encrypted(unsigned long address); extern unsigned char _pgtable[]; #endif -- cgit v1.2.3-58-ga151 From 597cfe48212a3f110ab0f918bf59791f453e65b7 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:24 +0200 Subject: x86/boot/compressed/64: Setup a GHCB-based VC Exception handler Install an exception handler for #VC exception that uses a GHCB. Also add the infrastructure for handling different exit-codes by decoding the instruction that caused the exception and error handling. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-24-joro@8bytes.org --- arch/x86/Kconfig | 1 + arch/x86/boot/compressed/Makefile | 5 + arch/x86/boot/compressed/idt_64.c | 4 + arch/x86/boot/compressed/idt_handlers_64.S | 3 +- arch/x86/boot/compressed/misc.c | 7 ++ arch/x86/boot/compressed/misc.h | 7 ++ arch/x86/boot/compressed/sev-es.c | 111 +++++++++++++++++++++ arch/x86/include/asm/sev-es.h | 39 ++++++++ arch/x86/include/uapi/asm/svm.h | 1 + arch/x86/kernel/sev-es-shared.c | 154 +++++++++++++++++++++++++++++ 10 files changed, 331 insertions(+), 1 deletion(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 7101ac64bb20..8289dd44efbd 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1521,6 +1521,7 @@ config AMD_MEM_ENCRYPT select DYNAMIC_PHYSICAL_MASK select ARCH_USE_MEMREMAP_PROT select ARCH_HAS_FORCE_DMA_UNENCRYPTED + select INSTRUCTION_DECODER help Say yes to enable support for the encryption of system memory. This requires an AMD processor that supports Secure Memory diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 38f4a52a4eda..c01236ae1b7c 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -44,6 +44,11 @@ KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=) KBUILD_CFLAGS += -fno-asynchronous-unwind-tables KBUILD_CFLAGS += -D__DISABLE_EXPORTS +# sev-es.c indirectly inludes inat-table.h which is generated during +# compilation and stored in $(objtree). Add the directory to the includes so +# that the compiler finds it even with out-of-tree builds (make O=/some/path). +CFLAGS_sev-es.o += -I$(objtree)/arch/x86/lib/ + KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n UBSAN_SANITIZE :=n diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c index f3ca7324be44..804a502ee0d2 100644 --- a/arch/x86/boot/compressed/idt_64.c +++ b/arch/x86/boot/compressed/idt_64.c @@ -46,5 +46,9 @@ void load_stage2_idt(void) set_idt_entry(X86_TRAP_PF, boot_page_fault); +#ifdef CONFIG_AMD_MEM_ENCRYPT + set_idt_entry(X86_TRAP_VC, boot_stage2_vc); +#endif + load_boot_idt(&boot_idt_desc); } diff --git a/arch/x86/boot/compressed/idt_handlers_64.S b/arch/x86/boot/compressed/idt_handlers_64.S index 92eb4df478a1..22890e199f5b 100644 --- a/arch/x86/boot/compressed/idt_handlers_64.S +++ b/arch/x86/boot/compressed/idt_handlers_64.S @@ -72,5 +72,6 @@ SYM_FUNC_END(\name) EXCEPTION_HANDLER boot_page_fault do_boot_page_fault error_code=1 #ifdef CONFIG_AMD_MEM_ENCRYPT -EXCEPTION_HANDLER boot_stage1_vc do_vc_no_ghcb error_code=1 +EXCEPTION_HANDLER boot_stage1_vc do_vc_no_ghcb error_code=1 +EXCEPTION_HANDLER boot_stage2_vc do_boot_stage2_vc error_code=1 #endif diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index e478e40fbe5a..267e7f93050e 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -442,6 +442,13 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, parse_elf(output); handle_relocations(output, output_len, virt_addr); debug_putstr("done.\nBooting the kernel.\n"); + + /* + * Flush GHCB from cache and map it encrypted again when running as + * SEV-ES guest. + */ + sev_es_shutdown_ghcb(); + return output; } diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 01c0fb3417ca..9995c70ca813 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -115,6 +115,12 @@ static inline void console_init(void) void set_sev_encryption_mask(void); +#ifdef CONFIG_AMD_MEM_ENCRYPT +void sev_es_shutdown_ghcb(void); +#else +static inline void sev_es_shutdown_ghcb(void) { } +#endif + /* acpi.c */ #ifdef CONFIG_ACPI acpi_physical_address get_rsdp_addr(void); @@ -144,5 +150,6 @@ extern struct desc_ptr boot_idt_desc; /* IDT Entry Points */ void boot_page_fault(void); void boot_stage1_vc(void); +void boot_stage2_vc(void); #endif /* BOOT_COMPRESSED_MISC_H */ diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c index 99c3bcd4d61f..fa62af771dd5 100644 --- a/arch/x86/boot/compressed/sev-es.c +++ b/arch/x86/boot/compressed/sev-es.c @@ -13,10 +13,17 @@ #include "misc.h" #include +#include +#include #include #include #include +#include "error.h" + +struct ghcb boot_ghcb_page __aligned(PAGE_SIZE); +struct ghcb *boot_ghcb; + static inline u64 sev_es_rd_ghcb_msr(void) { unsigned long low, high; @@ -38,8 +45,112 @@ static inline void sev_es_wr_ghcb_msr(u64 val) "a"(low), "d" (high) : "memory"); } +static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt) +{ + char buffer[MAX_INSN_SIZE]; + enum es_result ret; + + memcpy(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE); + + insn_init(&ctxt->insn, buffer, MAX_INSN_SIZE, 1); + insn_get_length(&ctxt->insn); + + ret = ctxt->insn.immediate.got ? ES_OK : ES_DECODE_FAILED; + + return ret; +} + +static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, + void *dst, char *buf, size_t size) +{ + memcpy(dst, buf, size); + + return ES_OK; +} + +static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, + void *src, char *buf, size_t size) +{ + memcpy(buf, src, size); + + return ES_OK; +} + #undef __init +#undef __pa #define __init +#define __pa(x) ((unsigned long)(x)) + +#define __BOOT_COMPRESSED + +/* Basic instruction decoding support needed */ +#include "../../lib/inat.c" +#include "../../lib/insn.c" /* Include code for early handlers */ #include "../../kernel/sev-es-shared.c" + +static bool early_setup_sev_es(void) +{ + if (!sev_es_negotiate_protocol()) + sev_es_terminate(GHCB_SEV_ES_REASON_PROTOCOL_UNSUPPORTED); + + if (set_page_decrypted((unsigned long)&boot_ghcb_page)) + return false; + + /* Page is now mapped decrypted, clear it */ + memset(&boot_ghcb_page, 0, sizeof(boot_ghcb_page)); + + boot_ghcb = &boot_ghcb_page; + + /* Initialize lookup tables for the instruction decoder */ + inat_init_tables(); + + return true; +} + +void sev_es_shutdown_ghcb(void) +{ + if (!boot_ghcb) + return; + + /* + * GHCB Page must be flushed from the cache and mapped encrypted again. + * Otherwise the running kernel will see strange cache effects when + * trying to use that page. + */ + if (set_page_encrypted((unsigned long)&boot_ghcb_page)) + error("Can't map GHCB page encrypted"); +} + +void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code) +{ + struct es_em_ctxt ctxt; + enum es_result result; + + if (!boot_ghcb && !early_setup_sev_es()) + sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST); + + vc_ghcb_invalidate(boot_ghcb); + result = vc_init_em_ctxt(&ctxt, regs, exit_code); + if (result != ES_OK) + goto finish; + + switch (exit_code) { + default: + result = ES_UNSUPPORTED; + break; + } + +finish: + if (result == ES_OK) { + vc_finish_insn(&ctxt); + } else if (result != ES_RETRY) { + /* + * For now, just halt the machine. That makes debugging easier, + * later we just call sev_es_terminate() here. + */ + while (true) + asm volatile("hlt\n"); + } +} diff --git a/arch/x86/include/asm/sev-es.h b/arch/x86/include/asm/sev-es.h index 48a44038b5d1..6dc52440c4b4 100644 --- a/arch/x86/include/asm/sev-es.h +++ b/arch/x86/include/asm/sev-es.h @@ -9,7 +9,14 @@ #define __ASM_ENCRYPTED_STATE_H #include +#include +#define GHCB_SEV_INFO 0x001UL +#define GHCB_SEV_INFO_REQ 0x002UL +#define GHCB_INFO(v) ((v) & 0xfffUL) +#define GHCB_PROTO_MAX(v) (((v) >> 48) & 0xffffUL) +#define GHCB_PROTO_MIN(v) (((v) >> 32) & 0xffffUL) +#define GHCB_PROTO_OUR 0x0001UL #define GHCB_SEV_CPUID_REQ 0x004UL #define GHCB_CPUID_REQ_EAX 0 #define GHCB_CPUID_REQ_EBX 1 @@ -19,12 +26,44 @@ (((unsigned long)reg & 3) << 30) | \ (((unsigned long)fn) << 32)) +#define GHCB_PROTOCOL_MAX 0x0001UL +#define GHCB_DEFAULT_USAGE 0x0000UL + #define GHCB_SEV_CPUID_RESP 0x005UL #define GHCB_SEV_TERMINATE 0x100UL +#define GHCB_SEV_TERMINATE_REASON(reason_set, reason_val) \ + (((((u64)reason_set) & 0x7) << 12) | \ + ((((u64)reason_val) & 0xff) << 16)) +#define GHCB_SEV_ES_REASON_GENERAL_REQUEST 0 +#define GHCB_SEV_ES_REASON_PROTOCOL_UNSUPPORTED 1 #define GHCB_SEV_GHCB_RESP_CODE(v) ((v) & 0xfff) #define VMGEXIT() { asm volatile("rep; vmmcall\n\r"); } +enum es_result { + ES_OK, /* All good */ + ES_UNSUPPORTED, /* Requested operation not supported */ + ES_VMM_ERROR, /* Unexpected state from the VMM */ + ES_DECODE_FAILED, /* Instruction decoding failed */ + ES_EXCEPTION, /* Instruction caused exception */ + ES_RETRY, /* Retry instruction emulation */ +}; + +struct es_fault_info { + unsigned long vector; + unsigned long error_code; + unsigned long cr2; +}; + +struct pt_regs; + +/* ES instruction emulation context */ +struct es_em_ctxt { + struct pt_regs *regs; + struct insn insn; + struct es_fault_info fi; +}; + void do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code); static inline u64 lower_bits(u64 val, unsigned int bits) diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index 2e8a30f06c74..c68d1618c9b0 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -29,6 +29,7 @@ #define SVM_EXIT_WRITE_DR6 0x036 #define SVM_EXIT_WRITE_DR7 0x037 #define SVM_EXIT_EXCP_BASE 0x040 +#define SVM_EXIT_LAST_EXCP 0x05f #define SVM_EXIT_INTR 0x060 #define SVM_EXIT_NMI 0x061 #define SVM_EXIT_SMI 0x062 diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index 0bea32341afa..7ac6e6b0ae57 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -9,6 +9,118 @@ * and is included directly into both code-bases. */ +static void sev_es_terminate(unsigned int reason) +{ + u64 val = GHCB_SEV_TERMINATE; + + /* + * Tell the hypervisor what went wrong - only reason-set 0 is + * currently supported. + */ + val |= GHCB_SEV_TERMINATE_REASON(0, reason); + + /* Request Guest Termination from Hypvervisor */ + sev_es_wr_ghcb_msr(val); + VMGEXIT(); + + while (true) + asm volatile("hlt\n" : : : "memory"); +} + +static bool sev_es_negotiate_protocol(void) +{ + u64 val; + + /* Do the GHCB protocol version negotiation */ + sev_es_wr_ghcb_msr(GHCB_SEV_INFO_REQ); + VMGEXIT(); + val = sev_es_rd_ghcb_msr(); + + if (GHCB_INFO(val) != GHCB_SEV_INFO) + return false; + + if (GHCB_PROTO_MAX(val) < GHCB_PROTO_OUR || + GHCB_PROTO_MIN(val) > GHCB_PROTO_OUR) + return false; + + return true; +} + +static void vc_ghcb_invalidate(struct ghcb *ghcb) +{ + memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); +} + +static bool vc_decoding_needed(unsigned long exit_code) +{ + /* Exceptions don't require to decode the instruction */ + return !(exit_code >= SVM_EXIT_EXCP_BASE && + exit_code <= SVM_EXIT_LAST_EXCP); +} + +static enum es_result vc_init_em_ctxt(struct es_em_ctxt *ctxt, + struct pt_regs *regs, + unsigned long exit_code) +{ + enum es_result ret = ES_OK; + + memset(ctxt, 0, sizeof(*ctxt)); + ctxt->regs = regs; + + if (vc_decoding_needed(exit_code)) + ret = vc_decode_insn(ctxt); + + return ret; +} + +static void vc_finish_insn(struct es_em_ctxt *ctxt) +{ + ctxt->regs->ip += ctxt->insn.length; +} + +static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, + struct es_em_ctxt *ctxt, + u64 exit_code, u64 exit_info_1, + u64 exit_info_2) +{ + enum es_result ret; + + /* Fill in protocol and format specifiers */ + ghcb->protocol_version = GHCB_PROTOCOL_MAX; + ghcb->ghcb_usage = GHCB_DEFAULT_USAGE; + + ghcb_set_sw_exit_code(ghcb, exit_code); + ghcb_set_sw_exit_info_1(ghcb, exit_info_1); + ghcb_set_sw_exit_info_2(ghcb, exit_info_2); + + sev_es_wr_ghcb_msr(__pa(ghcb)); + VMGEXIT(); + + if ((ghcb->save.sw_exit_info_1 & 0xffffffff) == 1) { + u64 info = ghcb->save.sw_exit_info_2; + unsigned long v; + + info = ghcb->save.sw_exit_info_2; + v = info & SVM_EVTINJ_VEC_MASK; + + /* Check if exception information from hypervisor is sane. */ + if ((info & SVM_EVTINJ_VALID) && + ((v == X86_TRAP_GP) || (v == X86_TRAP_UD)) && + ((info & SVM_EVTINJ_TYPE_MASK) == SVM_EVTINJ_TYPE_EXEPT)) { + ctxt->fi.vector = v; + if (info & SVM_EVTINJ_VALID_ERR) + ctxt->fi.error_code = info >> 32; + ret = ES_EXCEPTION; + } else { + ret = ES_VMM_ERROR; + } + } else { + ret = ES_OK; + } + + return ret; +} + /* * Boot VC Handler - This is the first VC handler during boot, there is no GHCB * page yet, so it only supports the MSR based communication with the @@ -64,3 +176,45 @@ fail: while (true) asm volatile("hlt\n"); } + +static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt, + void *src, char *buf, + unsigned int data_size, + unsigned int count, + bool backwards) +{ + int i, b = backwards ? -1 : 1; + enum es_result ret = ES_OK; + + for (i = 0; i < count; i++) { + void *s = src + (i * data_size * b); + char *d = buf + (i * data_size); + + ret = vc_read_mem(ctxt, s, d, data_size); + if (ret != ES_OK) + break; + } + + return ret; +} + +static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt, + void *dst, char *buf, + unsigned int data_size, + unsigned int count, + bool backwards) +{ + int i, s = backwards ? -1 : 1; + enum es_result ret = ES_OK; + + for (i = 0; i < count; i++) { + void *d = dst + (i * data_size * s); + char *b = buf + (i * data_size); + + ret = vc_write_mem(ctxt, d, b, data_size); + if (ret != ES_OK) + break; + } + + return ret; +} -- cgit v1.2.3-58-ga151 From 69add17a7c1992593a7cf775a66e0256ad4b3ef8 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:25 +0200 Subject: x86/boot/compressed/64: Unmap GHCB page before booting the kernel Force a page-fault on any further accesses to the GHCB page when they shouldn't happen anymore. This will catch any bugs where a #VC exception is raised even though none is expected anymore. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-25-joro@8bytes.org --- arch/x86/boot/compressed/ident_map_64.c | 17 +++++++++++++++-- arch/x86/boot/compressed/misc.h | 6 ++++++ arch/x86/boot/compressed/sev-es.c | 14 ++++++++++++++ 3 files changed, 35 insertions(+), 2 deletions(-) diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index 05742f641a06..063a60edcf99 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -298,6 +298,11 @@ int set_page_encrypted(unsigned long address) return set_clr_page_flags(&mapping_info, address, _PAGE_ENC, 0); } +int set_page_non_present(unsigned long address) +{ + return set_clr_page_flags(&mapping_info, address, 0, _PAGE_PRESENT); +} + static void do_pf_error(const char *msg, unsigned long error_code, unsigned long address, unsigned long ip) { @@ -316,8 +321,14 @@ static void do_pf_error(const char *msg, unsigned long error_code, void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code) { - unsigned long address = native_read_cr2() & PMD_MASK; - unsigned long end = address + PMD_SIZE; + unsigned long address = native_read_cr2(); + unsigned long end; + bool ghcb_fault; + + ghcb_fault = sev_es_check_ghcb_fault(address); + + address &= PMD_MASK; + end = address + PMD_SIZE; /* * Check for unexpected error codes. Unexpected are: @@ -327,6 +338,8 @@ void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code) */ if (error_code & (X86_PF_PROT | X86_PF_USER | X86_PF_RSVD)) do_pf_error("Unexpected page-fault:", error_code, address, regs->ip); + else if (ghcb_fault) + do_pf_error("Page-fault on GHCB page:", error_code, address, regs->ip); /* * Error code is sane - now identity map the 2M region around diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 9995c70ca813..c0e0ffeee50a 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -100,6 +100,7 @@ static inline void choose_random_location(unsigned long input, #ifdef CONFIG_X86_64 extern int set_page_decrypted(unsigned long address); extern int set_page_encrypted(unsigned long address); +extern int set_page_non_present(unsigned long address); extern unsigned char _pgtable[]; #endif @@ -117,8 +118,13 @@ void set_sev_encryption_mask(void); #ifdef CONFIG_AMD_MEM_ENCRYPT void sev_es_shutdown_ghcb(void); +extern bool sev_es_check_ghcb_fault(unsigned long address); #else static inline void sev_es_shutdown_ghcb(void) { } +static inline bool sev_es_check_ghcb_fault(unsigned long address) +{ + return false; +} #endif /* acpi.c */ diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c index fa62af771dd5..1e1fab583302 100644 --- a/arch/x86/boot/compressed/sev-es.c +++ b/arch/x86/boot/compressed/sev-es.c @@ -121,6 +121,20 @@ void sev_es_shutdown_ghcb(void) */ if (set_page_encrypted((unsigned long)&boot_ghcb_page)) error("Can't map GHCB page encrypted"); + + /* + * GHCB page is mapped encrypted again and flushed from the cache. + * Mark it non-present now to catch bugs when #VC exceptions trigger + * after this point. + */ + if (set_page_non_present((unsigned long)&boot_ghcb_page)) + error("Can't unmap GHCB page"); +} + +bool sev_es_check_ghcb_fault(unsigned long address) +{ + /* Check whether the fault was on the GHCB page */ + return ((address & PAGE_MASK) == (unsigned long)&boot_ghcb_page); } void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code) -- cgit v1.2.3-58-ga151 From 25189d08e5168c098c307a0eaae5b30c13a331ef Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 7 Sep 2020 15:15:26 +0200 Subject: x86/sev-es: Add support for handling IOIO exceptions Add support for decoding and handling #VC exceptions for IOIO events. [ jroedel@suse.de: Adapted code to #VC handling framework ] Co-developed-by: Joerg Roedel Signed-off-by: Tom Lendacky Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-26-joro@8bytes.org --- arch/x86/boot/compressed/sev-es.c | 32 ++++++ arch/x86/kernel/sev-es-shared.c | 214 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 246 insertions(+) diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c index 1e1fab583302..61504eb1ab46 100644 --- a/arch/x86/boot/compressed/sev-es.c +++ b/arch/x86/boot/compressed/sev-es.c @@ -24,6 +24,35 @@ struct ghcb boot_ghcb_page __aligned(PAGE_SIZE); struct ghcb *boot_ghcb; +/* + * Copy a version of this function here - insn-eval.c can't be used in + * pre-decompression code. + */ +static bool insn_has_rep_prefix(struct insn *insn) +{ + int i; + + insn_get_prefixes(insn); + + for (i = 0; i < insn->prefixes.nbytes; i++) { + insn_byte_t p = insn->prefixes.bytes[i]; + + if (p == 0xf2 || p == 0xf3) + return true; + } + + return false; +} + +/* + * Only a dummy for insn_get_seg_base() - Early boot-code is 64bit only and + * doesn't use segments. + */ +static unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx) +{ + return 0UL; +} + static inline u64 sev_es_rd_ghcb_msr(void) { unsigned long low, high; @@ -151,6 +180,9 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code) goto finish; switch (exit_code) { + case SVM_EXIT_IOIO: + result = vc_handle_ioio(boot_ghcb, &ctxt); + break; default: result = ES_UNSUPPORTED; break; diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index 7ac6e6b0ae57..bae7cf28455b 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -218,3 +218,217 @@ static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt, return ret; } + +#define IOIO_TYPE_STR BIT(2) +#define IOIO_TYPE_IN 1 +#define IOIO_TYPE_INS (IOIO_TYPE_IN | IOIO_TYPE_STR) +#define IOIO_TYPE_OUT 0 +#define IOIO_TYPE_OUTS (IOIO_TYPE_OUT | IOIO_TYPE_STR) + +#define IOIO_REP BIT(3) + +#define IOIO_ADDR_64 BIT(9) +#define IOIO_ADDR_32 BIT(8) +#define IOIO_ADDR_16 BIT(7) + +#define IOIO_DATA_32 BIT(6) +#define IOIO_DATA_16 BIT(5) +#define IOIO_DATA_8 BIT(4) + +#define IOIO_SEG_ES (0 << 10) +#define IOIO_SEG_DS (3 << 10) + +static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) +{ + struct insn *insn = &ctxt->insn; + *exitinfo = 0; + + switch (insn->opcode.bytes[0]) { + /* INS opcodes */ + case 0x6c: + case 0x6d: + *exitinfo |= IOIO_TYPE_INS; + *exitinfo |= IOIO_SEG_ES; + *exitinfo |= (ctxt->regs->dx & 0xffff) << 16; + break; + + /* OUTS opcodes */ + case 0x6e: + case 0x6f: + *exitinfo |= IOIO_TYPE_OUTS; + *exitinfo |= IOIO_SEG_DS; + *exitinfo |= (ctxt->regs->dx & 0xffff) << 16; + break; + + /* IN immediate opcodes */ + case 0xe4: + case 0xe5: + *exitinfo |= IOIO_TYPE_IN; + *exitinfo |= (u64)insn->immediate.value << 16; + break; + + /* OUT immediate opcodes */ + case 0xe6: + case 0xe7: + *exitinfo |= IOIO_TYPE_OUT; + *exitinfo |= (u64)insn->immediate.value << 16; + break; + + /* IN register opcodes */ + case 0xec: + case 0xed: + *exitinfo |= IOIO_TYPE_IN; + *exitinfo |= (ctxt->regs->dx & 0xffff) << 16; + break; + + /* OUT register opcodes */ + case 0xee: + case 0xef: + *exitinfo |= IOIO_TYPE_OUT; + *exitinfo |= (ctxt->regs->dx & 0xffff) << 16; + break; + + default: + return ES_DECODE_FAILED; + } + + switch (insn->opcode.bytes[0]) { + case 0x6c: + case 0x6e: + case 0xe4: + case 0xe6: + case 0xec: + case 0xee: + /* Single byte opcodes */ + *exitinfo |= IOIO_DATA_8; + break; + default: + /* Length determined by instruction parsing */ + *exitinfo |= (insn->opnd_bytes == 2) ? IOIO_DATA_16 + : IOIO_DATA_32; + } + switch (insn->addr_bytes) { + case 2: + *exitinfo |= IOIO_ADDR_16; + break; + case 4: + *exitinfo |= IOIO_ADDR_32; + break; + case 8: + *exitinfo |= IOIO_ADDR_64; + break; + } + + if (insn_has_rep_prefix(insn)) + *exitinfo |= IOIO_REP; + + return ES_OK; +} + +static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +{ + struct pt_regs *regs = ctxt->regs; + u64 exit_info_1, exit_info_2; + enum es_result ret; + + ret = vc_ioio_exitinfo(ctxt, &exit_info_1); + if (ret != ES_OK) + return ret; + + if (exit_info_1 & IOIO_TYPE_STR) { + + /* (REP) INS/OUTS */ + + bool df = ((regs->flags & X86_EFLAGS_DF) == X86_EFLAGS_DF); + unsigned int io_bytes, exit_bytes; + unsigned int ghcb_count, op_count; + unsigned long es_base; + u64 sw_scratch; + + /* + * For the string variants with rep prefix the amount of in/out + * operations per #VC exception is limited so that the kernel + * has a chance to take interrupts and re-schedule while the + * instruction is emulated. + */ + io_bytes = (exit_info_1 >> 4) & 0x7; + ghcb_count = sizeof(ghcb->shared_buffer) / io_bytes; + + op_count = (exit_info_1 & IOIO_REP) ? regs->cx : 1; + exit_info_2 = min(op_count, ghcb_count); + exit_bytes = exit_info_2 * io_bytes; + + es_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_ES); + + /* Read bytes of OUTS into the shared buffer */ + if (!(exit_info_1 & IOIO_TYPE_IN)) { + ret = vc_insn_string_read(ctxt, + (void *)(es_base + regs->si), + ghcb->shared_buffer, io_bytes, + exit_info_2, df); + if (ret) + return ret; + } + + /* + * Issue an VMGEXIT to the HV to consume the bytes from the + * shared buffer or to have it write them into the shared buffer + * depending on the instruction: OUTS or INS. + */ + sw_scratch = __pa(ghcb) + offsetof(struct ghcb, shared_buffer); + ghcb_set_sw_scratch(ghcb, sw_scratch); + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO, + exit_info_1, exit_info_2); + if (ret != ES_OK) + return ret; + + /* Read bytes from shared buffer into the guest's destination. */ + if (exit_info_1 & IOIO_TYPE_IN) { + ret = vc_insn_string_write(ctxt, + (void *)(es_base + regs->di), + ghcb->shared_buffer, io_bytes, + exit_info_2, df); + if (ret) + return ret; + + if (df) + regs->di -= exit_bytes; + else + regs->di += exit_bytes; + } else { + if (df) + regs->si -= exit_bytes; + else + regs->si += exit_bytes; + } + + if (exit_info_1 & IOIO_REP) + regs->cx -= exit_info_2; + + ret = regs->cx ? ES_RETRY : ES_OK; + + } else { + + /* IN/OUT into/from rAX */ + + int bits = (exit_info_1 & 0x70) >> 1; + u64 rax = 0; + + if (!(exit_info_1 & IOIO_TYPE_IN)) + rax = lower_bits(regs->ax, bits); + + ghcb_set_rax(ghcb, rax); + + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO, exit_info_1, 0); + if (ret != ES_OK) + return ret; + + if (exit_info_1 & IOIO_TYPE_IN) { + if (!ghcb_rax_is_valid(ghcb)) + return ES_VMM_ERROR; + regs->ax = lower_bits(ghcb->save.rax, bits); + } + } + + return ret; +} -- cgit v1.2.3-58-ga151 From 1b4fb8545f2b00f2844c4b7619d64d98440a477c Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:27 +0200 Subject: x86/fpu: Move xgetbv()/xsetbv() into a separate header The xgetbv() function is needed in the pre-decompression boot code, but asm/fpu/internal.h can't be included there directly. Doing so opens the door to include-hell due to various include-magic in boot/compressed/misc.h. Avoid that by moving xgetbv()/xsetbv() to a separate header file and include it instead. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-27-joro@8bytes.org --- arch/x86/include/asm/fpu/internal.h | 30 +----------------------------- arch/x86/include/asm/fpu/xcr.h | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+), 29 deletions(-) create mode 100644 arch/x86/include/asm/fpu/xcr.h diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 21a8b5259477..ceeba9f63172 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -585,33 +586,4 @@ static inline void switch_fpu_finish(struct fpu *new_fpu) __write_pkru(pkru_val); } -/* - * MXCSR and XCR definitions: - */ - -static inline void ldmxcsr(u32 mxcsr) -{ - asm volatile("ldmxcsr %0" :: "m" (mxcsr)); -} - -extern unsigned int mxcsr_feature_mask; - -#define XCR_XFEATURE_ENABLED_MASK 0x00000000 - -static inline u64 xgetbv(u32 index) -{ - u32 eax, edx; - - asm volatile("xgetbv" : "=a" (eax), "=d" (edx) : "c" (index)); - return eax + ((u64)edx << 32); -} - -static inline void xsetbv(u32 index, u64 value) -{ - u32 eax = value; - u32 edx = value >> 32; - - asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index)); -} - #endif /* _ASM_X86_FPU_INTERNAL_H */ diff --git a/arch/x86/include/asm/fpu/xcr.h b/arch/x86/include/asm/fpu/xcr.h new file mode 100644 index 000000000000..1c7ab8d95da5 --- /dev/null +++ b/arch/x86/include/asm/fpu/xcr.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_FPU_XCR_H +#define _ASM_X86_FPU_XCR_H + +/* + * MXCSR and XCR definitions: + */ + +static inline void ldmxcsr(u32 mxcsr) +{ + asm volatile("ldmxcsr %0" :: "m" (mxcsr)); +} + +extern unsigned int mxcsr_feature_mask; + +#define XCR_XFEATURE_ENABLED_MASK 0x00000000 + +static inline u64 xgetbv(u32 index) +{ + u32 eax, edx; + + asm volatile("xgetbv" : "=a" (eax), "=d" (edx) : "c" (index)); + return eax + ((u64)edx << 32); +} + +static inline void xsetbv(u32 index, u64 value) +{ + u32 eax = value; + u32 edx = value >> 32; + + asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index)); +} + +#endif /* _ASM_X86_FPU_XCR_H */ -- cgit v1.2.3-58-ga151 From a7de15d489d956217b47671705ac2218ca50eaae Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 7 Sep 2020 15:15:28 +0200 Subject: x86/sev-es: Add CPUID handling to #VC handler Handle #VC exceptions caused by CPUID instructions. These happen in early boot code when the KASLR code checks for RDTSC. Signed-off-by: Tom Lendacky [ jroedel@suse.de: Adapt to #VC handling framework ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-28-joro@8bytes.org --- arch/x86/boot/compressed/sev-es.c | 4 ++++ arch/x86/kernel/sev-es-shared.c | 35 +++++++++++++++++++++++++++++++++++ 2 files changed, 39 insertions(+) diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c index 61504eb1ab46..b1790f487456 100644 --- a/arch/x86/boot/compressed/sev-es.c +++ b/arch/x86/boot/compressed/sev-es.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -183,6 +184,9 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code) case SVM_EXIT_IOIO: result = vc_handle_ioio(boot_ghcb, &ctxt); break; + case SVM_EXIT_CPUID: + result = vc_handle_cpuid(boot_ghcb, &ctxt); + break; default: result = ES_UNSUPPORTED; break; diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index bae7cf28455b..a6b41910b8ab 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -432,3 +432,38 @@ static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ret; } + +static enum es_result vc_handle_cpuid(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + struct pt_regs *regs = ctxt->regs; + u32 cr4 = native_read_cr4(); + enum es_result ret; + + ghcb_set_rax(ghcb, regs->ax); + ghcb_set_rcx(ghcb, regs->cx); + + if (cr4 & X86_CR4_OSXSAVE) + /* Safe to read xcr0 */ + ghcb_set_xcr0(ghcb, xgetbv(XCR_XFEATURE_ENABLED_MASK)); + else + /* xgetbv will cause #GP - use reset value for xcr0 */ + ghcb_set_xcr0(ghcb, 1); + + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_CPUID, 0, 0); + if (ret != ES_OK) + return ret; + + if (!(ghcb_rax_is_valid(ghcb) && + ghcb_rbx_is_valid(ghcb) && + ghcb_rcx_is_valid(ghcb) && + ghcb_rdx_is_valid(ghcb))) + return ES_VMM_ERROR; + + regs->ax = ghcb->save.rax; + regs->bx = ghcb->save.rbx; + regs->cx = ghcb->save.rcx; + regs->dx = ghcb->save.rdx; + + return ES_OK; +} -- cgit v1.2.3-58-ga151 From 4bed2266cc6f9c3f6cd91378ea4fc76edde674cf Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:29 +0200 Subject: x86/idt: Split idt_data setup out of set_intr_gate() The code to setup idt_data is needed for early exception handling, but set_intr_gate() can't be used that early because it has pv-ops in its code path which don't work that early. Split out the idt_data initialization part from set_intr_gate() so that it can be used separately. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20200907131613.12703-29-joro@8bytes.org --- arch/x86/kernel/idt.c | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 7ecf9babf0cb..53946c104fa0 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -205,18 +205,24 @@ idt_setup_from_table(gate_desc *idt, const struct idt_data *t, int size, bool sy } } +static void init_idt_data(struct idt_data *data, unsigned int n, + const void *addr) +{ + BUG_ON(n > 0xFF); + + memset(data, 0, sizeof(*data)); + data->vector = n; + data->addr = addr; + data->segment = __KERNEL_CS; + data->bits.type = GATE_INTERRUPT; + data->bits.p = 1; +} + static __init void set_intr_gate(unsigned int n, const void *addr) { struct idt_data data; - BUG_ON(n > 0xFF); - - memset(&data, 0, sizeof(data)); - data.vector = n; - data.addr = addr; - data.segment = __KERNEL_CS; - data.bits.type = GATE_INTERRUPT; - data.bits.p = 1; + init_idt_data(&data, n, addr); idt_setup_from_table(idt_table, &data, 1, false); } -- cgit v1.2.3-58-ga151 From 866b556efa1295934ed0bc20c2f208c93a873fb0 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:30 +0200 Subject: x86/head/64: Install startup GDT Handling exceptions during boot requires a working GDT. The kernel GDT can't be used on the direct mapping, so load a startup GDT and setup segments. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-30-joro@8bytes.org --- arch/x86/include/asm/setup.h | 1 + arch/x86/kernel/head64.c | 33 +++++++++++++++++++++++++++++++++ arch/x86/kernel/head_64.S | 14 ++++++++++++++ 3 files changed, 48 insertions(+) diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 84b645cc8bc9..5c2fd05bd52c 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -48,6 +48,7 @@ extern void reserve_standard_io_resources(void); extern void i386_reserve_resources(void); extern unsigned long __startup_64(unsigned long physaddr, struct boot_params *bp); extern unsigned long __startup_secondary_64(void); +extern void startup_64_setup_env(unsigned long physbase); extern int early_make_pgtable(unsigned long address); #ifdef CONFIG_X86_INTEL_MID diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index cbb71c1b574f..8c82be44be94 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -61,6 +61,24 @@ unsigned long vmemmap_base __ro_after_init = __VMEMMAP_BASE_L4; EXPORT_SYMBOL(vmemmap_base); #endif +/* + * GDT used on the boot CPU before switching to virtual addresses. + */ +static struct desc_struct startup_gdt[GDT_ENTRIES] = { + [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(0xc09b, 0, 0xfffff), + [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(0xa09b, 0, 0xfffff), + [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(0xc093, 0, 0xfffff), +}; + +/* + * Address needs to be set at runtime because it references the startup_gdt + * while the kernel still uses a direct mapping. + */ +static struct desc_ptr startup_gdt_descr = { + .size = sizeof(startup_gdt), + .address = 0, +}; + #define __head __section(.head.text) static void __head *fixup_pointer(void *ptr, unsigned long physaddr) @@ -489,3 +507,18 @@ void __init x86_64_start_reservations(char *real_mode_data) start_kernel(); } + +/* + * Setup boot CPU state needed before kernel switches to virtual addresses. + */ +void __head startup_64_setup_env(unsigned long physbase) +{ + /* Load GDT */ + startup_gdt_descr.address = (unsigned long)fixup_pointer(startup_gdt, physbase); + native_load_gdt(&startup_gdt_descr); + + /* New GDT is live - reload data segment registers */ + asm volatile("movl %%eax, %%ds\n" + "movl %%eax, %%ss\n" + "movl %%eax, %%es\n" : : "a"(__KERNEL_DS) : "memory"); +} diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 16da4ac01597..2b2e91627221 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -73,6 +73,20 @@ SYM_CODE_START_NOALIGN(startup_64) /* Set up the stack for verify_cpu(), similar to initial_stack below */ leaq (__end_init_task - SIZEOF_PTREGS)(%rip), %rsp + leaq _text(%rip), %rdi + pushq %rsi + call startup_64_setup_env + popq %rsi + + /* Now switch to __KERNEL_CS so IRET works reliably */ + pushq $__KERNEL_CS + leaq .Lon_kernel_cs(%rip), %rax + pushq %rax + lretq + +.Lon_kernel_cs: + UNWIND_HINT_EMPTY + /* Sanitize CPU configuration */ call verify_cpu -- cgit v1.2.3-58-ga151 From e04b88336360e101329add0c05e5cb1cebae64fd Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:31 +0200 Subject: x86/head/64: Load GDT after switch to virtual addresses Load the GDT right after switching to virtual addresses to make sure there is a defined GDT for exception handling. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20200907131613.12703-31-joro@8bytes.org --- arch/x86/kernel/head_64.S | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 2b2e91627221..03b03f266dc1 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -158,6 +158,14 @@ SYM_CODE_START(secondary_startup_64) 1: UNWIND_HINT_EMPTY + /* + * We must switch to a new descriptor in kernel space for the GDT + * because soon the kernel won't have access anymore to the userspace + * addresses where we're currently running on. We have to do that here + * because in 32bit we couldn't load a 64bit linear address. + */ + lgdt early_gdt_descr(%rip) + /* Check if nx is implemented */ movl $0x80000001, %eax cpuid @@ -185,14 +193,6 @@ SYM_CODE_START(secondary_startup_64) pushq $0 popfq - /* - * We must switch to a new descriptor in kernel space for the GDT - * because soon the kernel won't have access anymore to the userspace - * addresses where we're currently running on. We have to do that here - * because in 32bit we couldn't load a 64bit linear address. - */ - lgdt early_gdt_descr(%rip) - /* set up data segments */ xorl %eax,%eax movl %eax,%ds -- cgit v1.2.3-58-ga151 From 7b99819dfb60268cc1c75f83c949bc4a09221bea Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:32 +0200 Subject: x86/head/64: Load segment registers earlier Make sure segments are properly set up before setting up an IDT and doing anything that might cause a #VC exception. This is later needed for early exception handling. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20200907131613.12703-32-joro@8bytes.org --- arch/x86/kernel/head_64.S | 52 +++++++++++++++++++++++------------------------ 1 file changed, 26 insertions(+), 26 deletions(-) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 03b03f266dc1..f402087a02ac 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -166,6 +166,32 @@ SYM_CODE_START(secondary_startup_64) */ lgdt early_gdt_descr(%rip) + /* set up data segments */ + xorl %eax,%eax + movl %eax,%ds + movl %eax,%ss + movl %eax,%es + + /* + * We don't really need to load %fs or %gs, but load them anyway + * to kill any stale realmode selectors. This allows execution + * under VT hardware. + */ + movl %eax,%fs + movl %eax,%gs + + /* Set up %gs. + * + * The base of %gs always points to fixed_percpu_data. If the + * stack protector canary is enabled, it is located at %gs:40. + * Note that, on SMP, the boot cpu uses init data section until + * the per cpu areas are set up. + */ + movl $MSR_GS_BASE,%ecx + movl initial_gs(%rip),%eax + movl initial_gs+4(%rip),%edx + wrmsr + /* Check if nx is implemented */ movl $0x80000001, %eax cpuid @@ -193,32 +219,6 @@ SYM_CODE_START(secondary_startup_64) pushq $0 popfq - /* set up data segments */ - xorl %eax,%eax - movl %eax,%ds - movl %eax,%ss - movl %eax,%es - - /* - * We don't really need to load %fs or %gs, but load them anyway - * to kill any stale realmode selectors. This allows execution - * under VT hardware. - */ - movl %eax,%fs - movl %eax,%gs - - /* Set up %gs. - * - * The base of %gs always points to fixed_percpu_data. If the - * stack protector canary is enabled, it is located at %gs:40. - * Note that, on SMP, the boot cpu uses init data section until - * the per cpu areas are set up. - */ - movl $MSR_GS_BASE,%ecx - movl initial_gs(%rip),%eax - movl initial_gs+4(%rip),%edx - wrmsr - /* rsi is pointer to real mode structure with interesting info. pass it to C */ movq %rsi, %rdi -- cgit v1.2.3-58-ga151 From 3add38cb96a1ae7d152db69ab4329e809c2af2d4 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:33 +0200 Subject: x86/head/64: Switch to initial stack earlier Make sure there is a stack once the kernel runs from virtual addresses. At this stage any secondary CPU which boots will have lost its stack because the kernel switched to a new page-table which does not map the real-mode stack anymore. This is needed for handling early #VC exceptions caused by instructions like CPUID. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20200907131613.12703-33-joro@8bytes.org --- arch/x86/kernel/head_64.S | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index f402087a02ac..83050c9e54d9 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -192,6 +192,12 @@ SYM_CODE_START(secondary_startup_64) movl initial_gs+4(%rip),%edx wrmsr + /* + * Setup a boot time stack - Any secondary CPU will have lost its stack + * by now because the cr3-switch above unmaps the real-mode stack + */ + movq initial_stack(%rip), %rsp + /* Check if nx is implemented */ movl $0x80000001, %eax cpuid @@ -212,9 +218,6 @@ SYM_CODE_START(secondary_startup_64) /* Make changes effective */ movq %rax, %cr0 - /* Setup a boot time stack */ - movq initial_stack(%rip), %rsp - /* zero EFLAGS after setting rsp */ pushq $0 popfq -- cgit v1.2.3-58-ga151 From f5963ba7a45fc6ff298a34976064354be437e1d8 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:34 +0200 Subject: x86/head/64: Install a CPU bringup IDT Add a separate bringup IDT for the CPU bringup code that will be used until the kernel switches to the idt_table. There are two reasons for a separate IDT: 1) When the idt_table is set up and the secondary CPUs are booted, it contains entries (e.g. IST entries) which require certain CPU state to be set up. This includes a working TSS (for IST), MSR_GS_BASE (for stack protector) or CR4.FSGSBASE (for paranoid_entry) path. By using a dedicated IDT for early boot this state need not to be set up early. 2) The idt_table is static to idt.c, so any function using/modifying must be in idt.c too. That means that all compiler driven instrumentation like tracing or KASAN is also active in this code. But during early CPU bringup the environment is not set up for this instrumentation to work correctly. To avoid all of these hassles and make early exception handling robust, use a dedicated bringup IDT. The IDT is loaded two times, first on the boot CPU while the kernel is still running on direct mapped addresses, and again later after the switch to kernel addresses has happened. The second IDT load happens on the boot and secondary CPUs. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-34-joro@8bytes.org --- arch/x86/include/asm/setup.h | 1 + arch/x86/kernel/head64.c | 39 +++++++++++++++++++++++++++++++++++++++ arch/x86/kernel/head_64.S | 5 +++++ 3 files changed, 45 insertions(+) diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 5c2fd05bd52c..4b3ca5ade2fd 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -50,6 +50,7 @@ extern unsigned long __startup_64(unsigned long physaddr, struct boot_params *bp extern unsigned long __startup_secondary_64(void); extern void startup_64_setup_env(unsigned long physbase); extern int early_make_pgtable(unsigned long address); +extern void early_setup_idt(void); #ifdef CONFIG_X86_INTEL_MID extern void x86_intel_mid_early_setup(void); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 8c82be44be94..7bfd5c27c773 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -36,6 +36,8 @@ #include #include #include +#include +#include /* * Manage page tables very early on. @@ -508,6 +510,41 @@ void __init x86_64_start_reservations(char *real_mode_data) start_kernel(); } +/* + * Data structures and code used for IDT setup in head_64.S. The bringup-IDT is + * used until the idt_table takes over. On the boot CPU this happens in + * x86_64_start_kernel(), on secondary CPUs in start_secondary(). In both cases + * this happens in the functions called from head_64.S. + * + * The idt_table can't be used that early because all the code modifying it is + * in idt.c and can be instrumented by tracing or KASAN, which both don't work + * during early CPU bringup. Also the idt_table has the runtime vectors + * configured which require certain CPU state to be setup already (like TSS), + * which also hasn't happened yet in early CPU bringup. + */ +static gate_desc bringup_idt_table[NUM_EXCEPTION_VECTORS] __page_aligned_data; + +static struct desc_ptr bringup_idt_descr = { + .size = (NUM_EXCEPTION_VECTORS * sizeof(gate_desc)) - 1, + .address = 0, /* Set at runtime */ +}; + +/* This runs while still in the direct mapping */ +static void startup_64_load_idt(unsigned long physbase) +{ + struct desc_ptr *desc = fixup_pointer(&bringup_idt_descr, physbase); + + desc->address = (unsigned long)fixup_pointer(bringup_idt_table, physbase); + native_load_idt(desc); +} + +/* This is used when running on kernel addresses */ +void early_setup_idt(void) +{ + bringup_idt_descr.address = (unsigned long)bringup_idt_table; + native_load_idt(&bringup_idt_descr); +} + /* * Setup boot CPU state needed before kernel switches to virtual addresses. */ @@ -521,4 +558,6 @@ void __head startup_64_setup_env(unsigned long physbase) asm volatile("movl %%eax, %%ds\n" "movl %%eax, %%ss\n" "movl %%eax, %%es\n" : : "a"(__KERNEL_DS) : "memory"); + + startup_64_load_idt(physbase); } diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 83050c9e54d9..1de09b58e578 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -198,6 +198,11 @@ SYM_CODE_START(secondary_startup_64) */ movq initial_stack(%rip), %rsp + /* Setup and Load IDT */ + pushq %rsi + call early_setup_idt + popq %rsi + /* Check if nx is implemented */ movl $0x80000001, %eax cpuid -- cgit v1.2.3-58-ga151 From 097ee5b778b8970e1c2ed3ca1631b297d90acd61 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:35 +0200 Subject: x86/idt: Make IDT init functions static inlines Move these two functions from kernel/idt.c to include/asm/desc.h: * init_idt_data() * idt_init_desc() These functions are needed to setup IDT entries very early and need to be called from head64.c. To be usable this early, these functions need to be compiled without instrumentation and the stack-protector feature. These features need to be kept enabled for kernel/idt.c, so head64.c must use its own versions. [ bp: Take Kees' suggested patch title and add his Rev-by. ] Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20200907131613.12703-35-joro@8bytes.org --- arch/x86/include/asm/desc.h | 27 +++++++++++++++++++++++++++ arch/x86/include/asm/desc_defs.h | 7 +++++++ arch/x86/kernel/idt.c | 34 ---------------------------------- 3 files changed, 34 insertions(+), 34 deletions(-) diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 1ced11d31932..476082a83d1c 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -383,6 +383,33 @@ static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit) void alloc_intr_gate(unsigned int n, const void *addr); +static inline void init_idt_data(struct idt_data *data, unsigned int n, + const void *addr) +{ + BUG_ON(n > 0xFF); + + memset(data, 0, sizeof(*data)); + data->vector = n; + data->addr = addr; + data->segment = __KERNEL_CS; + data->bits.type = GATE_INTERRUPT; + data->bits.p = 1; +} + +static inline void idt_init_desc(gate_desc *gate, const struct idt_data *d) +{ + unsigned long addr = (unsigned long) d->addr; + + gate->offset_low = (u16) addr; + gate->segment = (u16) d->segment; + gate->bits = d->bits; + gate->offset_middle = (u16) (addr >> 16); +#ifdef CONFIG_X86_64 + gate->offset_high = (u32) (addr >> 32); + gate->reserved = 0; +#endif +} + extern unsigned long system_vectors[]; extern void load_current_idt(void); diff --git a/arch/x86/include/asm/desc_defs.h b/arch/x86/include/asm/desc_defs.h index 5621fb3f2d1a..f7e7099af595 100644 --- a/arch/x86/include/asm/desc_defs.h +++ b/arch/x86/include/asm/desc_defs.h @@ -74,6 +74,13 @@ struct idt_bits { p : 1; } __attribute__((packed)); +struct idt_data { + unsigned int vector; + unsigned int segment; + struct idt_bits bits; + const void *addr; +}; + struct gate_struct { u16 offset_low; u16 segment; diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 53946c104fa0..4bb4e3d6099e 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -11,13 +11,6 @@ #include #include -struct idt_data { - unsigned int vector; - unsigned int segment; - struct idt_bits bits; - const void *addr; -}; - #define DPL0 0x0 #define DPL3 0x3 @@ -178,20 +171,6 @@ bool idt_is_f00f_address(unsigned long address) } #endif -static inline void idt_init_desc(gate_desc *gate, const struct idt_data *d) -{ - unsigned long addr = (unsigned long) d->addr; - - gate->offset_low = (u16) addr; - gate->segment = (u16) d->segment; - gate->bits = d->bits; - gate->offset_middle = (u16) (addr >> 16); -#ifdef CONFIG_X86_64 - gate->offset_high = (u32) (addr >> 32); - gate->reserved = 0; -#endif -} - static __init void idt_setup_from_table(gate_desc *idt, const struct idt_data *t, int size, bool sys) { @@ -205,19 +184,6 @@ idt_setup_from_table(gate_desc *idt, const struct idt_data *t, int size, bool sy } } -static void init_idt_data(struct idt_data *data, unsigned int n, - const void *addr) -{ - BUG_ON(n > 0xFF); - - memset(data, 0, sizeof(*data)); - data->vector = n; - data->addr = addr; - data->segment = __KERNEL_CS; - data->bits.type = GATE_INTERRUPT; - data->bits.p = 1; -} - static __init void set_intr_gate(unsigned int n, const void *addr) { struct idt_data data; -- cgit v1.2.3-58-ga151 From 4b47cdbda6f1ad73b08dc7d497bac12b8f26ae0d Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:36 +0200 Subject: x86/head/64: Move early exception dispatch to C code Move the assembly coded dispatch between page-faults and all other exceptions to C code to make it easier to maintain and extend. Also change the return-type of early_make_pgtable() to bool and make it static. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-36-joro@8bytes.org --- arch/x86/include/asm/pgtable.h | 2 +- arch/x86/include/asm/setup.h | 4 +++- arch/x86/kernel/head64.c | 19 +++++++++++++++---- arch/x86/kernel/head_64.S | 11 +---------- 4 files changed, 20 insertions(+), 16 deletions(-) diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index b836138ce852..7b8f2127de37 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -28,7 +28,7 @@ #include extern pgd_t early_top_pgt[PTRS_PER_PGD]; -int __init __early_make_pgtable(unsigned long address, pmdval_t pmd); +bool __init __early_make_pgtable(unsigned long address, pmdval_t pmd); void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm); void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm, diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 4b3ca5ade2fd..7d7a064af6ff 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -39,6 +39,8 @@ void vsmp_init(void); static inline void vsmp_init(void) { } #endif +struct pt_regs; + void setup_bios_corruption_check(void); void early_platform_quirks(void); @@ -49,8 +51,8 @@ extern void i386_reserve_resources(void); extern unsigned long __startup_64(unsigned long physaddr, struct boot_params *bp); extern unsigned long __startup_secondary_64(void); extern void startup_64_setup_env(unsigned long physbase); -extern int early_make_pgtable(unsigned long address); extern void early_setup_idt(void); +extern void __init do_early_exception(struct pt_regs *regs, int trapnr); #ifdef CONFIG_X86_INTEL_MID extern void x86_intel_mid_early_setup(void); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 7bfd5c27c773..4282dac694c3 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -38,6 +38,8 @@ #include #include #include +#include +#include /* * Manage page tables very early on. @@ -317,7 +319,7 @@ static void __init reset_early_page_tables(void) } /* Create a new PMD entry */ -int __init __early_make_pgtable(unsigned long address, pmdval_t pmd) +bool __init __early_make_pgtable(unsigned long address, pmdval_t pmd) { unsigned long physaddr = address - __PAGE_OFFSET; pgdval_t pgd, *pgd_p; @@ -327,7 +329,7 @@ int __init __early_make_pgtable(unsigned long address, pmdval_t pmd) /* Invalid address or early pgt is done ? */ if (physaddr >= MAXMEM || read_cr3_pa() != __pa_nodebug(early_top_pgt)) - return -1; + return false; again: pgd_p = &early_top_pgt[pgd_index(address)].pgd; @@ -384,10 +386,10 @@ again: } pmd_p[pmd_index(address)] = pmd; - return 0; + return true; } -int __init early_make_pgtable(unsigned long address) +static bool __init early_make_pgtable(unsigned long address) { unsigned long physaddr = address - __PAGE_OFFSET; pmdval_t pmd; @@ -397,6 +399,15 @@ int __init early_make_pgtable(unsigned long address) return __early_make_pgtable(address, pmd); } +void __init do_early_exception(struct pt_regs *regs, int trapnr) +{ + if (trapnr == X86_TRAP_PF && + early_make_pgtable(native_read_cr2())) + return; + + early_fixup_exception(regs, trapnr); +} + /* Don't add a printk in there. printk relies on the PDA which is not initialized yet. */ static void __init clear_bss(void) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 1de09b58e578..3b40ec44a67d 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -341,18 +341,9 @@ SYM_CODE_START_LOCAL(early_idt_handler_common) pushq %r15 /* pt_regs->r15 */ UNWIND_HINT_REGS - cmpq $14,%rsi /* Page fault? */ - jnz 10f - GET_CR2_INTO(%rdi) /* can clobber %rax if pv */ - call early_make_pgtable - andl %eax,%eax - jz 20f /* All good */ - -10: movq %rsp,%rdi /* RDI = pt_regs; RSI is already trapnr */ - call early_fixup_exception + call do_early_exception -20: decl early_recursion_flag(%rip) jmp restore_regs_and_return_to_kernel SYM_CODE_END(early_idt_handler_common) -- cgit v1.2.3-58-ga151 From b57de6cd16395be1ebdaa9b489ffbf462bb585c4 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:37 +0200 Subject: x86/sev-es: Add SEV-ES Feature Detection Add a sev_es_active() function for checking whether SEV-ES is enabled. Also cache the value of MSR_AMD64_SEV at boot to speed up the feature checking in the running code. [ bp: Remove "!!" in sev_active() too. ] Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20200907131613.12703-37-joro@8bytes.org --- arch/x86/include/asm/mem_encrypt.h | 3 +++ arch/x86/include/asm/msr-index.h | 2 ++ arch/x86/mm/mem_encrypt.c | 9 ++++++++- arch/x86/mm/mem_encrypt_identity.c | 3 +++ 4 files changed, 16 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 5049f6c22683..4e72b73a9cb5 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -19,6 +19,7 @@ #ifdef CONFIG_AMD_MEM_ENCRYPT extern u64 sme_me_mask; +extern u64 sev_status; extern bool sev_enabled; void sme_encrypt_execute(unsigned long encrypted_kernel_vaddr, @@ -50,6 +51,7 @@ void __init mem_encrypt_init(void); bool sme_active(void); bool sev_active(void); +bool sev_es_active(void); #define __bss_decrypted __attribute__((__section__(".bss..decrypted"))) @@ -72,6 +74,7 @@ static inline void __init sme_enable(struct boot_params *bp) { } static inline bool sme_active(void) { return false; } static inline bool sev_active(void) { return false; } +static inline bool sev_es_active(void) { return false; } static inline int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0; } diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index da34fdba7c5a..249a4147c4b2 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -469,7 +469,9 @@ #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 +#define MSR_AMD64_SEV_ES_ENABLED_BIT 1 #define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) +#define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT) #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 9f1177edc2e7..a38f55676bb7 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -38,6 +38,7 @@ * section is later cleared. */ u64 sme_me_mask __section(.data) = 0; +u64 sev_status __section(.data) = 0; EXPORT_SYMBOL(sme_me_mask); DEFINE_STATIC_KEY_FALSE(sev_enable_key); EXPORT_SYMBOL_GPL(sev_enable_key); @@ -347,7 +348,13 @@ bool sme_active(void) bool sev_active(void) { - return sme_me_mask && sev_enabled; + return sev_status & MSR_AMD64_SEV_ENABLED; +} + +/* Needs to be called from non-instrumentable code */ +bool noinstr sev_es_active(void) +{ + return sev_status & MSR_AMD64_SEV_ES_ENABLED; } /* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */ diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index e2b0e2ac07bb..68d75379e06a 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -540,6 +540,9 @@ void __init sme_enable(struct boot_params *bp) if (!(msr & MSR_AMD64_SEV_ENABLED)) return; + /* Save SEV_STATUS to avoid reading MSR again */ + sev_status = msr; + /* SEV state cannot be controlled by a command line option */ sme_me_mask = me_mask; sev_enabled = true; -- cgit v1.2.3-58-ga151 From c685eb0c12b4d4816d22ee734e91f4005b152fcd Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:38 +0200 Subject: x86/sev-es: Print SEV-ES info into the kernel log Refactor the message printed to the kernel log which indicates whether SEV or SME, etc is active. This will scale better in the future when more memory encryption features might be added. Also add SEV-ES to the list of features. [ bp: Massage. ] Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20200907131613.12703-38-joro@8bytes.org --- arch/x86/mm/mem_encrypt.c | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-) diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index a38f55676bb7..ebb7edc8bc0a 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -407,6 +407,31 @@ void __init mem_encrypt_free_decrypted_mem(void) free_init_pages("unused decrypted", vaddr, vaddr_end); } +static void print_mem_encrypt_feature_info(void) +{ + pr_info("AMD Memory Encryption Features active:"); + + /* Secure Memory Encryption */ + if (sme_active()) { + /* + * SME is mutually exclusive with any of the SEV + * features below. + */ + pr_cont(" SME\n"); + return; + } + + /* Secure Encrypted Virtualization */ + if (sev_active()) + pr_cont(" SEV"); + + /* Encrypted Register State */ + if (sev_es_active()) + pr_cont(" SEV-ES"); + + pr_cont("\n"); +} + /* Architecture __weak replacement functions */ void __init mem_encrypt_init(void) { @@ -422,8 +447,6 @@ void __init mem_encrypt_init(void) if (sev_active()) static_branch_enable(&sev_enable_key); - pr_info("AMD %s active\n", - sev_active() ? "Secure Encrypted Virtualization (SEV)" - : "Secure Memory Encryption (SME)"); + print_mem_encrypt_feature_info(); } -- cgit v1.2.3-58-ga151 From f980f9c31a923e9040dee0bc679a5f5b09e61f40 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:39 +0200 Subject: x86/sev-es: Compile early handler code into kernel image Setup sev-es.c and include the code from the pre-decompression stage to also build it into the image of the running kernel. Temporarily add __maybe_unused annotations to avoid build warnings until the functions get used. [ bp: Use the non-tracing rd/wrmsr variants because: vmlinux.o: warning: objtool: __sev_es_nmi_complete()+0x11f: \ call to do_trace_write_msr() leaves .noinstr.text section as __sev_es_nmi_complete() is noinstr due to being called from the NMI handler exc_nmi(). ] Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-39-joro@8bytes.org --- arch/x86/kernel/Makefile | 1 + arch/x86/kernel/sev-es-shared.c | 21 +++--- arch/x86/kernel/sev-es.c | 163 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 175 insertions(+), 10 deletions(-) create mode 100644 arch/x86/kernel/sev-es.c diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index e77261db2391..23bc0f830f18 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -145,6 +145,7 @@ obj-$(CONFIG_UNWINDER_ORC) += unwind_orc.o obj-$(CONFIG_UNWINDER_FRAME_POINTER) += unwind_frame.o obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o +obj-$(CONFIG_AMD_MEM_ENCRYPT) += sev-es.o ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index a6b41910b8ab..18619279a46f 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -9,7 +9,7 @@ * and is included directly into both code-bases. */ -static void sev_es_terminate(unsigned int reason) +static void __maybe_unused sev_es_terminate(unsigned int reason) { u64 val = GHCB_SEV_TERMINATE; @@ -27,7 +27,7 @@ static void sev_es_terminate(unsigned int reason) asm volatile("hlt\n" : : : "memory"); } -static bool sev_es_negotiate_protocol(void) +static bool __maybe_unused sev_es_negotiate_protocol(void) { u64 val; @@ -46,7 +46,7 @@ static bool sev_es_negotiate_protocol(void) return true; } -static void vc_ghcb_invalidate(struct ghcb *ghcb) +static void __maybe_unused vc_ghcb_invalidate(struct ghcb *ghcb) { memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); } @@ -58,9 +58,9 @@ static bool vc_decoding_needed(unsigned long exit_code) exit_code <= SVM_EXIT_LAST_EXCP); } -static enum es_result vc_init_em_ctxt(struct es_em_ctxt *ctxt, - struct pt_regs *regs, - unsigned long exit_code) +static enum es_result __maybe_unused vc_init_em_ctxt(struct es_em_ctxt *ctxt, + struct pt_regs *regs, + unsigned long exit_code) { enum es_result ret = ES_OK; @@ -73,7 +73,7 @@ static enum es_result vc_init_em_ctxt(struct es_em_ctxt *ctxt, return ret; } -static void vc_finish_insn(struct es_em_ctxt *ctxt) +static void __maybe_unused vc_finish_insn(struct es_em_ctxt *ctxt) { ctxt->regs->ip += ctxt->insn.length; } @@ -325,7 +325,8 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) return ES_OK; } -static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +static enum es_result __maybe_unused +vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { struct pt_regs *regs = ctxt->regs; u64 exit_info_1, exit_info_2; @@ -433,8 +434,8 @@ static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ret; } -static enum es_result vc_handle_cpuid(struct ghcb *ghcb, - struct es_em_ctxt *ctxt) +static enum es_result __maybe_unused vc_handle_cpuid(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) { struct pt_regs *regs = ctxt->regs; u32 cr4 = native_read_cr4(); diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c new file mode 100644 index 000000000000..4b1d217495f8 --- /dev/null +++ b/arch/x86/kernel/sev-es.c @@ -0,0 +1,163 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * AMD Memory Encryption Support + * + * Copyright (C) 2019 SUSE + * + * Author: Joerg Roedel + */ + +#include +#include + +#include +#include +#include +#include +#include +#include +#include + +static inline u64 sev_es_rd_ghcb_msr(void) +{ + return __rdmsr(MSR_AMD64_SEV_ES_GHCB); +} + +static inline void sev_es_wr_ghcb_msr(u64 val) +{ + u32 low, high; + + low = (u32)(val); + high = (u32)(val >> 32); + + native_wrmsr(MSR_AMD64_SEV_ES_GHCB, low, high); +} + +static int vc_fetch_insn_kernel(struct es_em_ctxt *ctxt, + unsigned char *buffer) +{ + return copy_from_kernel_nofault(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE); +} + +static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt) +{ + char buffer[MAX_INSN_SIZE]; + enum es_result ret; + int res; + + res = vc_fetch_insn_kernel(ctxt, buffer); + if (unlikely(res == -EFAULT)) { + ctxt->fi.vector = X86_TRAP_PF; + ctxt->fi.error_code = 0; + ctxt->fi.cr2 = ctxt->regs->ip; + return ES_EXCEPTION; + } + + insn_init(&ctxt->insn, buffer, MAX_INSN_SIZE - res, 1); + insn_get_length(&ctxt->insn); + + ret = ctxt->insn.immediate.got ? ES_OK : ES_DECODE_FAILED; + + return ret; +} + +static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, + char *dst, char *buf, size_t size) +{ + unsigned long error_code = X86_PF_PROT | X86_PF_WRITE; + char __user *target = (char __user *)dst; + u64 d8; + u32 d4; + u16 d2; + u8 d1; + + switch (size) { + case 1: + memcpy(&d1, buf, 1); + if (put_user(d1, target)) + goto fault; + break; + case 2: + memcpy(&d2, buf, 2); + if (put_user(d2, target)) + goto fault; + break; + case 4: + memcpy(&d4, buf, 4); + if (put_user(d4, target)) + goto fault; + break; + case 8: + memcpy(&d8, buf, 8); + if (put_user(d8, target)) + goto fault; + break; + default: + WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size); + return ES_UNSUPPORTED; + } + + return ES_OK; + +fault: + if (user_mode(ctxt->regs)) + error_code |= X86_PF_USER; + + ctxt->fi.vector = X86_TRAP_PF; + ctxt->fi.error_code = error_code; + ctxt->fi.cr2 = (unsigned long)dst; + + return ES_EXCEPTION; +} + +static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, + char *src, char *buf, size_t size) +{ + unsigned long error_code = X86_PF_PROT; + char __user *s = (char __user *)src; + u64 d8; + u32 d4; + u16 d2; + u8 d1; + + switch (size) { + case 1: + if (get_user(d1, s)) + goto fault; + memcpy(buf, &d1, 1); + break; + case 2: + if (get_user(d2, s)) + goto fault; + memcpy(buf, &d2, 2); + break; + case 4: + if (get_user(d4, s)) + goto fault; + memcpy(buf, &d4, 4); + break; + case 8: + if (get_user(d8, s)) + goto fault; + memcpy(buf, &d8, 8); + break; + default: + WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size); + return ES_UNSUPPORTED; + } + + return ES_OK; + +fault: + if (user_mode(ctxt->regs)) + error_code |= X86_PF_USER; + + ctxt->fi.vector = X86_TRAP_PF; + ctxt->fi.error_code = error_code; + ctxt->fi.cr2 = (unsigned long)src; + + return ES_EXCEPTION; +} + +/* Include code shared with pre-decompression boot stage */ +#include "sev-es-shared.c" -- cgit v1.2.3-58-ga151 From 74d8d9d531b4cc945a9f75aa2fc21d99ca5a9fe3 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 8 Sep 2020 14:35:17 +0200 Subject: x86/sev-es: Setup an early #VC handler Setup an early handler for #VC exceptions. There is no GHCB mapped yet, so just re-use the vc_no_ghcb_handler(). It can only handle CPUID exit-codes, but that should be enough to get the kernel through verify_cpu() and __startup_64() until it runs on virtual addresses. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov [ boot failure Error: kernel_ident_mapping_init() failed. ] Reported-by: kernel test robot Link: https://lkml.kernel.org/r/20200908123517.GA3764@8bytes.org --- arch/x86/include/asm/sev-es.h | 3 +++ arch/x86/kernel/head64.c | 25 ++++++++++++++++++++++++- arch/x86/kernel/head_64.S | 30 ++++++++++++++++++++++++++++++ 3 files changed, 57 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/sev-es.h b/arch/x86/include/asm/sev-es.h index 6dc52440c4b4..7175d432ebfe 100644 --- a/arch/x86/include/asm/sev-es.h +++ b/arch/x86/include/asm/sev-es.h @@ -73,4 +73,7 @@ static inline u64 lower_bits(u64 val, unsigned int bits) return (val & mask); } +/* Early IDT entry points for #VC handler */ +extern void vc_no_ghcb(void); + #endif diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 4282dac694c3..fc55cc9ccb0f 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -40,6 +40,7 @@ #include #include #include +#include /* * Manage page tables very early on. @@ -540,12 +541,34 @@ static struct desc_ptr bringup_idt_descr = { .address = 0, /* Set at runtime */ }; +static void set_bringup_idt_handler(gate_desc *idt, int n, void *handler) +{ +#ifdef CONFIG_AMD_MEM_ENCRYPT + struct idt_data data; + gate_desc desc; + + init_idt_data(&data, n, handler); + idt_init_desc(&desc, &data); + native_write_idt_entry(idt, n, &desc); +#endif +} + /* This runs while still in the direct mapping */ static void startup_64_load_idt(unsigned long physbase) { struct desc_ptr *desc = fixup_pointer(&bringup_idt_descr, physbase); + gate_desc *idt = fixup_pointer(bringup_idt_table, physbase); + + + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) { + void *handler; + + /* VMM Communication Exception */ + handler = fixup_pointer(vc_no_ghcb, physbase); + set_bringup_idt_handler(idt, X86_TRAP_VC, handler); + } - desc->address = (unsigned long)fixup_pointer(bringup_idt_table, physbase); + desc->address = (unsigned long)idt; native_load_idt(desc); } diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 3b40ec44a67d..6e68bca64ae4 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -348,6 +348,36 @@ SYM_CODE_START_LOCAL(early_idt_handler_common) jmp restore_regs_and_return_to_kernel SYM_CODE_END(early_idt_handler_common) +#ifdef CONFIG_AMD_MEM_ENCRYPT +/* + * VC Exception handler used during very early boot. The + * early_idt_handler_array can't be used because it returns via the + * paravirtualized INTERRUPT_RETURN and pv-ops don't work that early. + * + * This handler will end up in the .init.text section and not be + * available to boot secondary CPUs. + */ +SYM_CODE_START_NOALIGN(vc_no_ghcb) + UNWIND_HINT_IRET_REGS offset=8 + + /* Build pt_regs */ + PUSH_AND_CLEAR_REGS + + /* Call C handler */ + movq %rsp, %rdi + movq ORIG_RAX(%rsp), %rsi + call do_vc_no_ghcb + + /* Unwind pt_regs */ + POP_REGS + + /* Remove Error Code */ + addq $8, %rsp + + /* Pure iret required here - don't use INTERRUPT_RETURN */ + iretq +SYM_CODE_END(vc_no_ghcb) +#endif #define SYM_DATA_START_PAGE_ALIGNED(name) \ SYM_START(name, SYM_L_GLOBAL, .balign PAGE_SIZE) -- cgit v1.2.3-58-ga151 From 1aa9aa8ee517e0443b06e816a4fd2d15f2113615 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 8 Sep 2020 14:38:16 +0200 Subject: x86/sev-es: Setup GHCB-based boot #VC handler Add the infrastructure to handle #VC exceptions when the kernel runs on virtual addresses and has mapped a GHCB. This handler will be used until the runtime #VC handler takes over. Since the handler runs very early, disable instrumentation for sev-es.c. [ bp: Make vc_ghcb_invalidate() __always_inline so that it can be inlined in noinstr functions like __sev_es_nmi_complete(). ] Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200908123816.GB3764@8bytes.org --- arch/x86/include/asm/realmode.h | 3 ++ arch/x86/include/asm/segment.h | 2 +- arch/x86/include/asm/sev-es.h | 2 + arch/x86/kernel/Makefile | 2 + arch/x86/kernel/head64.c | 8 +++ arch/x86/kernel/head_64.S | 36 +++++++++++++ arch/x86/kernel/sev-es-shared.c | 14 ++--- arch/x86/kernel/sev-es.c | 116 ++++++++++++++++++++++++++++++++++++++++ arch/x86/mm/extable.c | 1 + 9 files changed, 176 insertions(+), 8 deletions(-) diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index b35030eeec36..96118fb041b8 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -57,6 +57,9 @@ extern unsigned char real_mode_blob_end[]; extern unsigned long initial_code; extern unsigned long initial_gs; extern unsigned long initial_stack; +#ifdef CONFIG_AMD_MEM_ENCRYPT +extern unsigned long initial_vc_handler; +#endif extern unsigned char real_mode_blob[]; extern unsigned char real_mode_relocs[]; diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 9646c300f128..4e8dec387112 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -230,7 +230,7 @@ #define NUM_EXCEPTION_VECTORS 32 /* Bitmask of exception vectors which push an error code on the stack: */ -#define EXCEPTION_ERRCODE_MASK 0x00027d00 +#define EXCEPTION_ERRCODE_MASK 0x20027d00 #define GDT_SIZE (GDT_ENTRIES*8) #define GDT_ENTRY_TLS_ENTRIES 3 diff --git a/arch/x86/include/asm/sev-es.h b/arch/x86/include/asm/sev-es.h index 7175d432ebfe..9fbeedaa66ee 100644 --- a/arch/x86/include/asm/sev-es.h +++ b/arch/x86/include/asm/sev-es.h @@ -75,5 +75,7 @@ static inline u64 lower_bits(u64 val, unsigned int bits) /* Early IDT entry points for #VC handler */ extern void vc_no_ghcb(void); +extern void vc_boot_ghcb(void); +extern bool handle_vc_boot_ghcb(struct pt_regs *regs); #endif diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 23bc0f830f18..4a3327217bf0 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -20,6 +20,7 @@ CFLAGS_REMOVE_kvmclock.o = -pg CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg CFLAGS_REMOVE_head64.o = -pg +CFLAGS_REMOVE_sev-es.o = -pg endif KASAN_SANITIZE_head$(BITS).o := n @@ -27,6 +28,7 @@ KASAN_SANITIZE_dumpstack.o := n KASAN_SANITIZE_dumpstack_$(BITS).o := n KASAN_SANITIZE_stacktrace.o := n KASAN_SANITIZE_paravirt.o := n +KASAN_SANITIZE_sev-es.o := n # With some compiler versions the generated code results in boot hangs, caused # by several compilation units. To be safe, disable all instrumentation. diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index fc55cc9ccb0f..4199f25c0063 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -406,6 +406,10 @@ void __init do_early_exception(struct pt_regs *regs, int trapnr) early_make_pgtable(native_read_cr2())) return; + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT) && + trapnr == X86_TRAP_VC && handle_vc_boot_ghcb(regs)) + return; + early_fixup_exception(regs, trapnr); } @@ -575,6 +579,10 @@ static void startup_64_load_idt(unsigned long physbase) /* This is used when running on kernel addresses */ void early_setup_idt(void) { + /* VMM Communication Exception */ + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) + set_bringup_idt_handler(bringup_idt_table, X86_TRAP_VC, vc_boot_ghcb); + bringup_idt_descr.address = (unsigned long)bringup_idt_table; native_load_idt(&bringup_idt_descr); } diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 6e68bca64ae4..1a71d0d4d575 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -279,6 +279,39 @@ SYM_CODE_START(start_cpu0) movq initial_stack(%rip), %rsp jmp .Ljump_to_C_code SYM_CODE_END(start_cpu0) +#endif + +#ifdef CONFIG_AMD_MEM_ENCRYPT +/* + * VC Exception handler used during early boot when running on kernel + * addresses, but before the switch to the idt_table can be made. + * The early_idt_handler_array can't be used here because it calls into a lot + * of __init code and this handler is also used during CPU offlining/onlining. + * Therefore this handler ends up in the .text section so that it stays around + * when .init.text is freed. + */ +SYM_CODE_START_NOALIGN(vc_boot_ghcb) + UNWIND_HINT_IRET_REGS offset=8 + + /* Build pt_regs */ + PUSH_AND_CLEAR_REGS + + /* Call C handler */ + movq %rsp, %rdi + movq ORIG_RAX(%rsp), %rsi + movq initial_vc_handler(%rip), %rax + ANNOTATE_RETPOLINE_SAFE + call *%rax + + /* Unwind pt_regs */ + POP_REGS + + /* Remove Error Code */ + addq $8, %rsp + + /* Pure iret required here - don't use INTERRUPT_RETURN */ + iretq +SYM_CODE_END(vc_boot_ghcb) #endif /* Both SMP bootup and ACPI suspend change these variables */ @@ -286,6 +319,9 @@ SYM_CODE_END(start_cpu0) .balign 8 SYM_DATA(initial_code, .quad x86_64_start_kernel) SYM_DATA(initial_gs, .quad INIT_PER_CPU_VAR(fixed_percpu_data)) +#ifdef CONFIG_AMD_MEM_ENCRYPT +SYM_DATA(initial_vc_handler, .quad handle_vc_boot_ghcb) +#endif /* * The SIZEOF_PTREGS gap is a convention which helps the in-kernel unwinder diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index 18619279a46f..53e3de0e8060 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -9,7 +9,7 @@ * and is included directly into both code-bases. */ -static void __maybe_unused sev_es_terminate(unsigned int reason) +static void sev_es_terminate(unsigned int reason) { u64 val = GHCB_SEV_TERMINATE; @@ -27,7 +27,7 @@ static void __maybe_unused sev_es_terminate(unsigned int reason) asm volatile("hlt\n" : : : "memory"); } -static bool __maybe_unused sev_es_negotiate_protocol(void) +static bool sev_es_negotiate_protocol(void) { u64 val; @@ -46,7 +46,7 @@ static bool __maybe_unused sev_es_negotiate_protocol(void) return true; } -static void __maybe_unused vc_ghcb_invalidate(struct ghcb *ghcb) +static __always_inline void vc_ghcb_invalidate(struct ghcb *ghcb) { memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); } @@ -58,9 +58,9 @@ static bool vc_decoding_needed(unsigned long exit_code) exit_code <= SVM_EXIT_LAST_EXCP); } -static enum es_result __maybe_unused vc_init_em_ctxt(struct es_em_ctxt *ctxt, - struct pt_regs *regs, - unsigned long exit_code) +static enum es_result vc_init_em_ctxt(struct es_em_ctxt *ctxt, + struct pt_regs *regs, + unsigned long exit_code) { enum es_result ret = ES_OK; @@ -73,7 +73,7 @@ static enum es_result __maybe_unused vc_init_em_ctxt(struct es_em_ctxt *ctxt, return ret; } -static void __maybe_unused vc_finish_insn(struct es_em_ctxt *ctxt) +static void vc_finish_insn(struct es_em_ctxt *ctxt) { ctxt->regs->ip += ctxt->insn.length; } diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 4b1d217495f8..213a42774aa9 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -7,7 +7,9 @@ * Author: Joerg Roedel */ +#include /* For show_regs() */ #include +#include #include #include @@ -18,6 +20,18 @@ #include #include +/* For early boot hypervisor communication in SEV-ES enabled guests */ +static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE); + +/* + * Needs to be in the .data section because we need it NULL before bss is + * cleared + */ +static struct ghcb __initdata *boot_ghcb; + +/* Needed in vc_early_forward_exception */ +void do_early_exception(struct pt_regs *regs, int trapnr); + static inline u64 sev_es_rd_ghcb_msr(void) { return __rdmsr(MSR_AMD64_SEV_ES_GHCB); @@ -161,3 +175,105 @@ fault: /* Include code shared with pre-decompression boot stage */ #include "sev-es-shared.c" + +/* + * This function runs on the first #VC exception after the kernel + * switched to virtual addresses. + */ +static bool __init sev_es_setup_ghcb(void) +{ + /* First make sure the hypervisor talks a supported protocol. */ + if (!sev_es_negotiate_protocol()) + return false; + + /* + * Clear the boot_ghcb. The first exception comes in before the bss + * section is cleared. + */ + memset(&boot_ghcb_page, 0, PAGE_SIZE); + + /* Alright - Make the boot-ghcb public */ + boot_ghcb = &boot_ghcb_page; + + return true; +} + +static void __init vc_early_forward_exception(struct es_em_ctxt *ctxt) +{ + int trapnr = ctxt->fi.vector; + + if (trapnr == X86_TRAP_PF) + native_write_cr2(ctxt->fi.cr2); + + ctxt->regs->orig_ax = ctxt->fi.error_code; + do_early_exception(ctxt->regs, trapnr); +} + +static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, + struct ghcb *ghcb, + unsigned long exit_code) +{ + enum es_result result; + + switch (exit_code) { + default: + /* + * Unexpected #VC exception + */ + result = ES_UNSUPPORTED; + } + + return result; +} + +bool __init handle_vc_boot_ghcb(struct pt_regs *regs) +{ + unsigned long exit_code = regs->orig_ax; + struct es_em_ctxt ctxt; + enum es_result result; + + /* Do initial setup or terminate the guest */ + if (unlikely(boot_ghcb == NULL && !sev_es_setup_ghcb())) + sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST); + + vc_ghcb_invalidate(boot_ghcb); + + result = vc_init_em_ctxt(&ctxt, regs, exit_code); + if (result == ES_OK) + result = vc_handle_exitcode(&ctxt, boot_ghcb, exit_code); + + /* Done - now check the result */ + switch (result) { + case ES_OK: + vc_finish_insn(&ctxt); + break; + case ES_UNSUPPORTED: + early_printk("PANIC: Unsupported exit-code 0x%02lx in early #VC exception (IP: 0x%lx)\n", + exit_code, regs->ip); + goto fail; + case ES_VMM_ERROR: + early_printk("PANIC: Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n", + exit_code, regs->ip); + goto fail; + case ES_DECODE_FAILED: + early_printk("PANIC: Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n", + exit_code, regs->ip); + goto fail; + case ES_EXCEPTION: + vc_early_forward_exception(&ctxt); + break; + case ES_RETRY: + /* Nothing to do */ + break; + default: + BUG(); + } + + return true; + +fail: + show_regs(regs); + + while (true) + halt(); +} diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 1d6cb07f4f86..3966749d07ac 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -5,6 +5,7 @@ #include #include +#include #include #include -- cgit v1.2.3-58-ga151 From 885689e47dfa1499b756a07237eb645234d93cf9 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 7 Sep 2020 15:15:42 +0200 Subject: x86/sev-es: Setup per-CPU GHCBs for the runtime handler The runtime handler needs one GHCB per-CPU. Set them up and map them unencrypted. [ bp: Touchups and simplification. ] Signed-off-by: Tom Lendacky Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-42-joro@8bytes.org --- arch/x86/include/asm/mem_encrypt.h | 2 ++ arch/x86/kernel/sev-es.c | 56 +++++++++++++++++++++++++++++++++++++- arch/x86/kernel/traps.c | 3 ++ 3 files changed, 60 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 4e72b73a9cb5..c9f5df0a1c10 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -49,6 +49,7 @@ void __init mem_encrypt_free_decrypted_mem(void); /* Architecture __weak replacement functions */ void __init mem_encrypt_init(void); +void __init sev_es_init_vc_handling(void); bool sme_active(void); bool sev_active(void); bool sev_es_active(void); @@ -72,6 +73,7 @@ static inline void __init sme_early_init(void) { } static inline void __init sme_encrypt_kernel(struct boot_params *bp) { } static inline void __init sme_enable(struct boot_params *bp) { } +static inline void sev_es_init_vc_handling(void) { } static inline bool sme_active(void) { return false; } static inline bool sev_active(void) { return false; } static inline bool sev_es_active(void) { return false; } diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 213a42774aa9..720b1b671812 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -8,8 +8,13 @@ */ #include /* For show_regs() */ -#include +#include +#include #include +#include +#include +#include +#include #include #include @@ -29,6 +34,13 @@ static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE); */ static struct ghcb __initdata *boot_ghcb; +/* #VC handler runtime per-CPU data */ +struct sev_es_runtime_data { + struct ghcb ghcb_page; +}; + +static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data); + /* Needed in vc_early_forward_exception */ void do_early_exception(struct pt_regs *regs, int trapnr); @@ -198,6 +210,48 @@ static bool __init sev_es_setup_ghcb(void) return true; } +static void __init alloc_runtime_data(int cpu) +{ + struct sev_es_runtime_data *data; + + data = memblock_alloc(sizeof(*data), PAGE_SIZE); + if (!data) + panic("Can't allocate SEV-ES runtime data"); + + per_cpu(runtime_data, cpu) = data; +} + +static void __init init_ghcb(int cpu) +{ + struct sev_es_runtime_data *data; + int err; + + data = per_cpu(runtime_data, cpu); + + err = early_set_memory_decrypted((unsigned long)&data->ghcb_page, + sizeof(data->ghcb_page)); + if (err) + panic("Can't map GHCBs unencrypted"); + + memset(&data->ghcb_page, 0, sizeof(data->ghcb_page)); +} + +void __init sev_es_init_vc_handling(void) +{ + int cpu; + + BUILD_BUG_ON(offsetof(struct sev_es_runtime_data, ghcb_page) % PAGE_SIZE); + + if (!sev_es_active()) + return; + + /* Initialize per-cpu GHCB pages */ + for_each_possible_cpu(cpu) { + alloc_runtime_data(cpu); + init_ghcb(cpu); + } +} + static void __init vc_early_forward_exception(struct es_em_ctxt *ctxt) { int trapnr = ctxt->fi.vector; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 81a2fb711091..2dc32b0ca38e 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -1074,6 +1074,9 @@ void __init trap_init(void) /* Init cpu_entry_area before IST entries are set up */ setup_cpu_entry_areas(); + /* Init GHCB memory pages when running as an SEV-ES guest */ + sev_es_init_vc_handling(); + idt_setup_traps(); /* -- cgit v1.2.3-58-ga151 From 02772fb9b68e6a72a5e17f994048df832fe2b15e Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:43 +0200 Subject: x86/sev-es: Allocate and map an IST stack for #VC handler Allocate and map an IST stack and an additional fall-back stack for the #VC handler. The memory for the stacks is allocated only when SEV-ES is active. The #VC handler needs to use an IST stack because a #VC exception can be raised from kernel space with unsafe stack, e.g. in the SYSCALL entry path. Since the #VC exception can be nested, the #VC handler switches back to the interrupted stack when entered from kernel space. If switching back is not possible, the fall-back stack is used. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-43-joro@8bytes.org --- arch/x86/include/asm/cpu_entry_area.h | 33 +++++++++++++++++++++------------ arch/x86/include/asm/page_64_types.h | 1 + arch/x86/kernel/cpu/common.c | 2 ++ arch/x86/kernel/dumpstack_64.c | 8 ++++++-- arch/x86/kernel/sev-es.c | 33 +++++++++++++++++++++++++++++++++ 5 files changed, 63 insertions(+), 14 deletions(-) diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h index 8902fdb7de13..3d52b094850a 100644 --- a/arch/x86/include/asm/cpu_entry_area.h +++ b/arch/x86/include/asm/cpu_entry_area.h @@ -11,25 +11,29 @@ #ifdef CONFIG_X86_64 /* Macro to enforce the same ordering and stack sizes */ -#define ESTACKS_MEMBERS(guardsize) \ - char DF_stack_guard[guardsize]; \ - char DF_stack[EXCEPTION_STKSZ]; \ - char NMI_stack_guard[guardsize]; \ - char NMI_stack[EXCEPTION_STKSZ]; \ - char DB_stack_guard[guardsize]; \ - char DB_stack[EXCEPTION_STKSZ]; \ - char MCE_stack_guard[guardsize]; \ - char MCE_stack[EXCEPTION_STKSZ]; \ - char IST_top_guard[guardsize]; \ +#define ESTACKS_MEMBERS(guardsize, optional_stack_size) \ + char DF_stack_guard[guardsize]; \ + char DF_stack[EXCEPTION_STKSZ]; \ + char NMI_stack_guard[guardsize]; \ + char NMI_stack[EXCEPTION_STKSZ]; \ + char DB_stack_guard[guardsize]; \ + char DB_stack[EXCEPTION_STKSZ]; \ + char MCE_stack_guard[guardsize]; \ + char MCE_stack[EXCEPTION_STKSZ]; \ + char VC_stack_guard[guardsize]; \ + char VC_stack[optional_stack_size]; \ + char VC2_stack_guard[guardsize]; \ + char VC2_stack[optional_stack_size]; \ + char IST_top_guard[guardsize]; \ /* The exception stacks' physical storage. No guard pages required */ struct exception_stacks { - ESTACKS_MEMBERS(0) + ESTACKS_MEMBERS(0, 0) }; /* The effective cpu entry area mapping with guard pages. */ struct cea_exception_stacks { - ESTACKS_MEMBERS(PAGE_SIZE) + ESTACKS_MEMBERS(PAGE_SIZE, EXCEPTION_STKSZ) }; /* @@ -40,6 +44,8 @@ enum exception_stack_ordering { ESTACK_NMI, ESTACK_DB, ESTACK_MCE, + ESTACK_VC, + ESTACK_VC2, N_EXCEPTION_STACKS }; @@ -139,4 +145,7 @@ static inline struct entry_stack *cpu_entry_stack(int cpu) #define __this_cpu_ist_top_va(name) \ CEA_ESTACK_TOP(__this_cpu_read(cea_exception_stacks), name) +#define __this_cpu_ist_bottom_va(name) \ + CEA_ESTACK_BOT(__this_cpu_read(cea_exception_stacks), name) + #endif diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 288b065955b7..d0c6c10c18a0 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -28,6 +28,7 @@ #define IST_INDEX_NMI 1 #define IST_INDEX_DB 2 #define IST_INDEX_MCE 3 +#define IST_INDEX_VC 4 /* * Set __PAGE_OFFSET to the most negative possible address + diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c5d6f17d9b9d..81fba4d4a242 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1829,6 +1829,8 @@ static inline void tss_setup_ist(struct tss_struct *tss) tss->x86_tss.ist[IST_INDEX_NMI] = __this_cpu_ist_top_va(NMI); tss->x86_tss.ist[IST_INDEX_DB] = __this_cpu_ist_top_va(DB); tss->x86_tss.ist[IST_INDEX_MCE] = __this_cpu_ist_top_va(MCE); + /* Only mapped when SEV-ES is active */ + tss->x86_tss.ist[IST_INDEX_VC] = __this_cpu_ist_top_va(VC); } #else /* CONFIG_X86_64 */ diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 4a94d38cd141..c49cf594714b 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -24,11 +24,13 @@ static const char * const exception_stack_names[] = { [ ESTACK_NMI ] = "NMI", [ ESTACK_DB ] = "#DB", [ ESTACK_MCE ] = "#MC", + [ ESTACK_VC ] = "#VC", + [ ESTACK_VC2 ] = "#VC2", }; const char *stack_type_name(enum stack_type type) { - BUILD_BUG_ON(N_EXCEPTION_STACKS != 4); + BUILD_BUG_ON(N_EXCEPTION_STACKS != 6); if (type == STACK_TYPE_IRQ) return "IRQ"; @@ -79,6 +81,8 @@ struct estack_pages estack_pages[CEA_ESTACK_PAGES] ____cacheline_aligned = { EPAGERANGE(NMI), EPAGERANGE(DB), EPAGERANGE(MCE), + EPAGERANGE(VC), + EPAGERANGE(VC2), }; static bool in_exception_stack(unsigned long *stack, struct stack_info *info) @@ -88,7 +92,7 @@ static bool in_exception_stack(unsigned long *stack, struct stack_info *info) struct pt_regs *regs; unsigned int k; - BUILD_BUG_ON(N_EXCEPTION_STACKS != 4); + BUILD_BUG_ON(N_EXCEPTION_STACKS != 6); begin = (unsigned long)__this_cpu_read(cea_exception_stacks); /* diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 720b1b671812..fae8145e4acf 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -17,6 +17,7 @@ #include #include +#include #include #include #include @@ -37,10 +38,41 @@ static struct ghcb __initdata *boot_ghcb; /* #VC handler runtime per-CPU data */ struct sev_es_runtime_data { struct ghcb ghcb_page; + + /* Physical storage for the per-CPU IST stack of the #VC handler */ + char ist_stack[EXCEPTION_STKSZ] __aligned(PAGE_SIZE); + + /* + * Physical storage for the per-CPU fall-back stack of the #VC handler. + * The fall-back stack is used when it is not safe to switch back to the + * interrupted stack in the #VC entry code. + */ + char fallback_stack[EXCEPTION_STKSZ] __aligned(PAGE_SIZE); }; static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data); +static void __init setup_vc_stacks(int cpu) +{ + struct sev_es_runtime_data *data; + struct cpu_entry_area *cea; + unsigned long vaddr; + phys_addr_t pa; + + data = per_cpu(runtime_data, cpu); + cea = get_cpu_entry_area(cpu); + + /* Map #VC IST stack */ + vaddr = CEA_ESTACK_BOT(&cea->estacks, VC); + pa = __pa(data->ist_stack); + cea_set_pte((void *)vaddr, pa, PAGE_KERNEL); + + /* Map VC fall-back stack */ + vaddr = CEA_ESTACK_BOT(&cea->estacks, VC2); + pa = __pa(data->fallback_stack); + cea_set_pte((void *)vaddr, pa, PAGE_KERNEL); +} + /* Needed in vc_early_forward_exception */ void do_early_exception(struct pt_regs *regs, int trapnr); @@ -249,6 +281,7 @@ void __init sev_es_init_vc_handling(void) for_each_possible_cpu(cpu) { alloc_runtime_data(cpu); init_ghcb(cpu); + setup_vc_stacks(cpu); } } -- cgit v1.2.3-58-ga151 From 315562c9af3d583502b35c4b223a08d95ce69864 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:44 +0200 Subject: x86/sev-es: Adjust #VC IST Stack on entering NMI handler When an NMI hits in the #VC handler entry code before it has switched to another stack, any subsequent #VC exception in the NMI code-path will overwrite the interrupted #VC handler's stack. Make sure this doesn't happen by explicitly adjusting the #VC IST entry in the NMI handler for the time it can cause #VC exceptions. [ bp: Touchups, spelling fixes. ] Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-44-joro@8bytes.org --- arch/x86/include/asm/sev-es.h | 19 ++++++++++++++++ arch/x86/kernel/nmi.c | 9 ++++++++ arch/x86/kernel/sev-es.c | 53 +++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 81 insertions(+) diff --git a/arch/x86/include/asm/sev-es.h b/arch/x86/include/asm/sev-es.h index 9fbeedaa66ee..59176e8c6b81 100644 --- a/arch/x86/include/asm/sev-es.h +++ b/arch/x86/include/asm/sev-es.h @@ -78,4 +78,23 @@ extern void vc_no_ghcb(void); extern void vc_boot_ghcb(void); extern bool handle_vc_boot_ghcb(struct pt_regs *regs); +#ifdef CONFIG_AMD_MEM_ENCRYPT +extern struct static_key_false sev_es_enable_key; +extern void __sev_es_ist_enter(struct pt_regs *regs); +extern void __sev_es_ist_exit(void); +static __always_inline void sev_es_ist_enter(struct pt_regs *regs) +{ + if (static_branch_unlikely(&sev_es_enable_key)) + __sev_es_ist_enter(regs); +} +static __always_inline void sev_es_ist_exit(void) +{ + if (static_branch_unlikely(&sev_es_enable_key)) + __sev_es_ist_exit(); +} +#else +static inline void sev_es_ist_enter(struct pt_regs *regs) { } +static inline void sev_es_ist_exit(void) { } +#endif + #endif diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 4fc9954a9560..4c89c4d3cb82 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -33,6 +33,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -488,6 +489,12 @@ DEFINE_IDTENTRY_RAW(exc_nmi) this_cpu_write(nmi_cr2, read_cr2()); nmi_restart: + /* + * Needs to happen before DR7 is accessed, because the hypervisor can + * intercept DR7 reads/writes, turning those into #VC exceptions. + */ + sev_es_ist_enter(regs); + this_cpu_write(nmi_dr7, local_db_save()); irq_state = idtentry_enter_nmi(regs); @@ -501,6 +508,8 @@ nmi_restart: local_db_restore(this_cpu_read(nmi_dr7)); + sev_es_ist_exit(); + if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) write_cr2(this_cpu_read(nmi_cr2)); if (this_cpu_dec_return(nmi_state)) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index fae8145e4acf..39ebb2d04bec 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -51,6 +51,7 @@ struct sev_es_runtime_data { }; static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data); +DEFINE_STATIC_KEY_FALSE(sev_es_enable_key); static void __init setup_vc_stacks(int cpu) { @@ -73,6 +74,55 @@ static void __init setup_vc_stacks(int cpu) cea_set_pte((void *)vaddr, pa, PAGE_KERNEL); } +static __always_inline bool on_vc_stack(unsigned long sp) +{ + return ((sp >= __this_cpu_ist_bottom_va(VC)) && (sp < __this_cpu_ist_top_va(VC))); +} + +/* + * This function handles the case when an NMI is raised in the #VC exception + * handler entry code. In this case, the IST entry for #VC must be adjusted, so + * that any subsequent #VC exception will not overwrite the stack contents of the + * interrupted #VC handler. + * + * The IST entry is adjusted unconditionally so that it can be also be + * unconditionally adjusted back in sev_es_ist_exit(). Otherwise a nested + * sev_es_ist_exit() call may adjust back the IST entry too early. + */ +void noinstr __sev_es_ist_enter(struct pt_regs *regs) +{ + unsigned long old_ist, new_ist; + + /* Read old IST entry */ + old_ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]); + + /* Make room on the IST stack */ + if (on_vc_stack(regs->sp)) + new_ist = ALIGN_DOWN(regs->sp, 8) - sizeof(old_ist); + else + new_ist = old_ist - sizeof(old_ist); + + /* Store old IST entry */ + *(unsigned long *)new_ist = old_ist; + + /* Set new IST entry */ + this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], new_ist); +} + +void noinstr __sev_es_ist_exit(void) +{ + unsigned long ist; + + /* Read IST entry */ + ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]); + + if (WARN_ON(ist == __this_cpu_ist_top_va(VC))) + return; + + /* Read back old IST entry and write it to the TSS */ + this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], *(unsigned long *)ist); +} + /* Needed in vc_early_forward_exception */ void do_early_exception(struct pt_regs *regs, int trapnr); @@ -277,6 +327,9 @@ void __init sev_es_init_vc_handling(void) if (!sev_es_active()) return; + /* Enable SEV-ES special handling */ + static_branch_enable(&sev_es_enable_key); + /* Initialize per-cpu GHCB pages */ for_each_possible_cpu(cpu) { alloc_runtime_data(cpu); -- cgit v1.2.3-58-ga151 From 6b27edd74a5e9669120f7bd0ae1f475d124c1042 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:45 +0200 Subject: x86/dumpstack/64: Add noinstr version of get_stack_info() The get_stack_info() functionality is needed in the entry code for the #VC exception handler. Provide a version of it in the .text.noinstr section which can be called safely from there. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-45-joro@8bytes.org --- arch/x86/include/asm/stacktrace.h | 2 ++ arch/x86/kernel/dumpstack.c | 7 ++++--- arch/x86/kernel/dumpstack_64.c | 38 ++++++++++++++++++++++---------------- arch/x86/mm/cpu_entry_area.c | 3 ++- 4 files changed, 30 insertions(+), 20 deletions(-) diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 5ae5a68e469d..49600643faba 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -35,6 +35,8 @@ bool in_entry_stack(unsigned long *stack, struct stack_info *info); int get_stack_info(unsigned long *stack, struct task_struct *task, struct stack_info *info, unsigned long *visit_mask); +bool get_stack_info_noinstr(unsigned long *stack, struct task_struct *task, + struct stack_info *info); const char *stack_type_name(enum stack_type type); diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 48ce44576947..74147f7b3d82 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -29,8 +29,8 @@ static int die_counter; static struct pt_regs exec_summary_regs; -bool in_task_stack(unsigned long *stack, struct task_struct *task, - struct stack_info *info) +bool noinstr in_task_stack(unsigned long *stack, struct task_struct *task, + struct stack_info *info) { unsigned long *begin = task_stack_page(task); unsigned long *end = task_stack_page(task) + THREAD_SIZE; @@ -46,7 +46,8 @@ bool in_task_stack(unsigned long *stack, struct task_struct *task, return true; } -bool in_entry_stack(unsigned long *stack, struct stack_info *info) +/* Called from get_stack_info_noinstr - so must be noinstr too */ +bool noinstr in_entry_stack(unsigned long *stack, struct stack_info *info) { struct entry_stack *ss = cpu_entry_stack(smp_processor_id()); diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index c49cf594714b..1dd851397bd9 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -85,7 +85,7 @@ struct estack_pages estack_pages[CEA_ESTACK_PAGES] ____cacheline_aligned = { EPAGERANGE(VC2), }; -static bool in_exception_stack(unsigned long *stack, struct stack_info *info) +static __always_inline bool in_exception_stack(unsigned long *stack, struct stack_info *info) { unsigned long begin, end, stk = (unsigned long)stack; const struct estack_pages *ep; @@ -126,7 +126,7 @@ static bool in_exception_stack(unsigned long *stack, struct stack_info *info) return true; } -static bool in_irq_stack(unsigned long *stack, struct stack_info *info) +static __always_inline bool in_irq_stack(unsigned long *stack, struct stack_info *info) { unsigned long *end = (unsigned long *)this_cpu_read(hardirq_stack_ptr); unsigned long *begin = end - (IRQ_STACK_SIZE / sizeof(long)); @@ -151,32 +151,38 @@ static bool in_irq_stack(unsigned long *stack, struct stack_info *info) return true; } -int get_stack_info(unsigned long *stack, struct task_struct *task, - struct stack_info *info, unsigned long *visit_mask) +bool noinstr get_stack_info_noinstr(unsigned long *stack, struct task_struct *task, + struct stack_info *info) { - if (!stack) - goto unknown; - - task = task ? : current; - if (in_task_stack(stack, task, info)) - goto recursion_check; + return true; if (task != current) - goto unknown; + return false; if (in_exception_stack(stack, info)) - goto recursion_check; + return true; if (in_irq_stack(stack, info)) - goto recursion_check; + return true; if (in_entry_stack(stack, info)) - goto recursion_check; + return true; + + return false; +} + +int get_stack_info(unsigned long *stack, struct task_struct *task, + struct stack_info *info, unsigned long *visit_mask) +{ + task = task ? : current; - goto unknown; + if (!stack) + goto unknown; + + if (!get_stack_info_noinstr(stack, task, info)) + goto unknown; -recursion_check: /* * Make sure we don't iterate through any given stack more than once. * If it comes up a second time then there's something wrong going on: diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c index 770b613790b3..f5e1e60c9095 100644 --- a/arch/x86/mm/cpu_entry_area.c +++ b/arch/x86/mm/cpu_entry_area.c @@ -21,7 +21,8 @@ DEFINE_PER_CPU(struct cea_exception_stacks*, cea_exception_stacks); DECLARE_PER_CPU_PAGE_ALIGNED(struct doublefault_stack, doublefault_stack); #endif -struct cpu_entry_area *get_cpu_entry_area(int cpu) +/* Is called from entry code, so must be noinstr */ +noinstr struct cpu_entry_area *get_cpu_entry_area(int cpu) { unsigned long va = CPU_ENTRY_AREA_PER_CPU + cpu * CPU_ENTRY_AREA_SIZE; BUILD_BUG_ON(sizeof(struct cpu_entry_area) % PAGE_SIZE != 0); -- cgit v1.2.3-58-ga151 From a13644f3a53de4e95a7bce6459f834e832ea44c5 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:46 +0200 Subject: x86/entry/64: Add entry code for #VC handler The #VC handler needs special entry code because: 1. It runs on an IST stack 2. It needs to be able to handle nested #VC exceptions To make this work, the entry code is implemented to pretend it doesn't use an IST stack. When entered from user-mode or early SYSCALL entry path it switches to the task stack. If entered from kernel-mode it tries to switch back to the previous stack in the IRET frame. The stack found in the IRET frame is validated first, and if it is not safe to use it for the #VC handler, the code will switch to a fall-back stack (the #VC2 IST stack). From there, it can cause nested exceptions again. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-46-joro@8bytes.org --- arch/x86/entry/entry_64.S | 80 +++++++++++++++++++++++++++++++++++++++++ arch/x86/include/asm/idtentry.h | 44 +++++++++++++++++++++++ arch/x86/include/asm/proto.h | 1 + arch/x86/include/asm/traps.h | 1 + arch/x86/kernel/traps.c | 45 +++++++++++++++++++++++ 5 files changed, 171 insertions(+) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 70dea9337816..15aa1896927c 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -101,6 +101,8 @@ SYM_CODE_START(entry_SYSCALL_64) SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp +SYM_INNER_LABEL(entry_SYSCALL_64_safe_stack, SYM_L_GLOBAL) + /* Construct struct pt_regs on stack */ pushq $__USER_DS /* pt_regs->ss */ pushq PER_CPU_VAR(cpu_tss_rw + TSS_sp2) /* pt_regs->sp */ @@ -446,6 +448,84 @@ _ASM_NOKPROBE(\asmsym) SYM_CODE_END(\asmsym) .endm +#ifdef CONFIG_AMD_MEM_ENCRYPT +/** + * idtentry_vc - Macro to generate entry stub for #VC + * @vector: Vector number + * @asmsym: ASM symbol for the entry point + * @cfunc: C function to be called + * + * The macro emits code to set up the kernel context for #VC. The #VC handler + * runs on an IST stack and needs to be able to cause nested #VC exceptions. + * + * To make this work the #VC entry code tries its best to pretend it doesn't use + * an IST stack by switching to the task stack if coming from user-space (which + * includes early SYSCALL entry path) or back to the stack in the IRET frame if + * entered from kernel-mode. + * + * If entered from kernel-mode the return stack is validated first, and if it is + * not safe to use (e.g. because it points to the entry stack) the #VC handler + * will switch to a fall-back stack (VC2) and call a special handler function. + * + * The macro is only used for one vector, but it is planned to be extended in + * the future for the #HV exception. + */ +.macro idtentry_vc vector asmsym cfunc +SYM_CODE_START(\asmsym) + UNWIND_HINT_IRET_REGS + ASM_CLAC + + /* + * If the entry is from userspace, switch stacks and treat it as + * a normal entry. + */ + testb $3, CS-ORIG_RAX(%rsp) + jnz .Lfrom_usermode_switch_stack_\@ + + /* + * paranoid_entry returns SWAPGS flag for paranoid_exit in EBX. + * EBX == 0 -> SWAPGS, EBX == 1 -> no SWAPGS + */ + call paranoid_entry + + UNWIND_HINT_REGS + + /* + * Switch off the IST stack to make it free for nested exceptions. The + * vc_switch_off_ist() function will switch back to the interrupted + * stack if it is safe to do so. If not it switches to the VC fall-back + * stack. + */ + movq %rsp, %rdi /* pt_regs pointer */ + call vc_switch_off_ist + movq %rax, %rsp /* Switch to new stack */ + + UNWIND_HINT_REGS + + /* Update pt_regs */ + movq ORIG_RAX(%rsp), %rsi /* get error code into 2nd argument*/ + movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */ + + movq %rsp, %rdi /* pt_regs pointer */ + + call \cfunc + + /* + * No need to switch back to the IST stack. The current stack is either + * identical to the stack in the IRET frame or the VC fall-back stack, + * so it is definitly mapped even with PTI enabled. + */ + jmp paranoid_exit + + /* Switch to the regular task stack */ +.Lfrom_usermode_switch_stack_\@: + idtentry_body safe_stack_\cfunc, has_error_code=1 + +_ASM_NOKPROBE(\asmsym) +SYM_CODE_END(\asmsym) +.endm +#endif + /* * Double fault entry. Straight paranoid. No checks from which context * this comes because for the espfix induced #DF this would do the wrong diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index a43366191212..840faaf57708 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -308,6 +308,18 @@ static __always_inline void __##func(struct pt_regs *regs) DECLARE_IDTENTRY_RAW(vector, func); \ __visible void noist_##func(struct pt_regs *regs) +/** + * DECLARE_IDTENTRY_VC - Declare functions for the VC entry point + * @vector: Vector number (ignored for C) + * @func: Function name of the entry point + * + * Maps to DECLARE_IDTENTRY_RAW_ERRORCODE, but declares also the + * safe_stack C handler. + */ +#define DECLARE_IDTENTRY_VC(vector, func) \ + DECLARE_IDTENTRY_RAW_ERRORCODE(vector, func); \ + __visible noinstr void safe_stack_##func(struct pt_regs *regs, unsigned long error_code) + /** * DEFINE_IDTENTRY_IST - Emit code for IST entry points * @func: Function name of the entry point @@ -347,6 +359,35 @@ static __always_inline void __##func(struct pt_regs *regs) #define DEFINE_IDTENTRY_DF(func) \ DEFINE_IDTENTRY_RAW_ERRORCODE(func) +/** + * DEFINE_IDTENTRY_VC_SAFE_STACK - Emit code for VMM communication handler + which runs on a safe stack. + * @func: Function name of the entry point + * + * Maps to DEFINE_IDTENTRY_RAW_ERRORCODE + */ +#define DEFINE_IDTENTRY_VC_SAFE_STACK(func) \ + DEFINE_IDTENTRY_RAW_ERRORCODE(safe_stack_##func) + +/** + * DEFINE_IDTENTRY_VC_IST - Emit code for VMM communication handler + which runs on the VC fall-back stack + * @func: Function name of the entry point + * + * Maps to DEFINE_IDTENTRY_RAW_ERRORCODE + */ +#define DEFINE_IDTENTRY_VC_IST(func) \ + DEFINE_IDTENTRY_RAW_ERRORCODE(ist_##func) + +/** + * DEFINE_IDTENTRY_VC - Emit code for VMM communication handler + * @func: Function name of the entry point + * + * Maps to DEFINE_IDTENTRY_RAW_ERRORCODE + */ +#define DEFINE_IDTENTRY_VC(func) \ + DEFINE_IDTENTRY_RAW_ERRORCODE(func) + #else /* CONFIG_X86_64 */ /** @@ -433,6 +474,9 @@ __visible noinstr void func(struct pt_regs *regs, \ # define DECLARE_IDTENTRY_XENCB(vector, func) \ DECLARE_IDTENTRY(vector, func) +# define DECLARE_IDTENTRY_VC(vector, func) \ + idtentry_vc vector asm_##func func + #else # define DECLARE_IDTENTRY_MCE(vector, func) \ DECLARE_IDTENTRY(vector, func) diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index 28996fe19301..2c35f1c01a2d 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -10,6 +10,7 @@ void syscall_init(void); #ifdef CONFIG_X86_64 void entry_SYSCALL_64(void); +void entry_SYSCALL_64_safe_stack(void); long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2); #endif diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 6a308355ea29..1b86bb3abc56 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -15,6 +15,7 @@ asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs); asmlinkage __visible notrace struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s); void __init trap_init(void); +asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *eregs); #endif #ifdef CONFIG_X86_F00F_BUG diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 2dc32b0ca38e..fc1ed40ce97d 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include #include @@ -673,6 +674,50 @@ asmlinkage __visible noinstr struct pt_regs *sync_regs(struct pt_regs *eregs) return regs; } +#ifdef CONFIG_AMD_MEM_ENCRYPT +asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *regs) +{ + unsigned long sp, *stack; + struct stack_info info; + struct pt_regs *regs_ret; + + /* + * In the SYSCALL entry path the RSP value comes from user-space - don't + * trust it and switch to the current kernel stack + */ + if (regs->ip >= (unsigned long)entry_SYSCALL_64 && + regs->ip < (unsigned long)entry_SYSCALL_64_safe_stack) { + sp = this_cpu_read(cpu_current_top_of_stack); + goto sync; + } + + /* + * From here on the RSP value is trusted. Now check whether entry + * happened from a safe stack. Not safe are the entry or unknown stacks, + * use the fall-back stack instead in this case. + */ + sp = regs->sp; + stack = (unsigned long *)sp; + + if (!get_stack_info_noinstr(stack, current, &info) || info.type == STACK_TYPE_ENTRY || + info.type >= STACK_TYPE_EXCEPTION_LAST) + sp = __this_cpu_ist_top_va(VC2); + +sync: + /* + * Found a safe stack - switch to it as if the entry didn't happen via + * IST stack. The code below only copies pt_regs, the real switch happens + * in assembly code. + */ + sp = ALIGN_DOWN(sp, 8) - sizeof(*regs_ret); + + regs_ret = (struct pt_regs *)sp; + *regs_ret = *regs; + + return regs_ret; +} +#endif + struct bad_iret_stack { void *error_entry_ret; struct pt_regs regs; -- cgit v1.2.3-58-ga151 From 0786138c78e79343c7b015d77507cbf9d5f15d00 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 7 Sep 2020 15:15:47 +0200 Subject: x86/sev-es: Add a Runtime #VC Exception Handler Add the handlers for #VC exceptions invoked at runtime. Signed-off-by: Tom Lendacky Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-47-joro@8bytes.org --- arch/x86/include/asm/idtentry.h | 6 + arch/x86/kernel/idt.c | 11 +- arch/x86/kernel/sev-es.c | 246 +++++++++++++++++++++++++++++++++++++++- 3 files changed, 255 insertions(+), 8 deletions(-) diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index 840faaf57708..58a793b46a00 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -318,6 +318,7 @@ static __always_inline void __##func(struct pt_regs *regs) */ #define DECLARE_IDTENTRY_VC(vector, func) \ DECLARE_IDTENTRY_RAW_ERRORCODE(vector, func); \ + __visible noinstr void ist_##func(struct pt_regs *regs, unsigned long error_code); \ __visible noinstr void safe_stack_##func(struct pt_regs *regs, unsigned long error_code) /** @@ -608,6 +609,11 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_DB, xenpv_exc_debug); /* #DF */ DECLARE_IDTENTRY_DF(X86_TRAP_DF, exc_double_fault); +/* #VC */ +#ifdef CONFIG_AMD_MEM_ENCRYPT +DECLARE_IDTENTRY_VC(X86_TRAP_VC, exc_vmm_communication); +#endif + #ifdef CONFIG_XEN_PV DECLARE_IDTENTRY_XENCB(X86_TRAP_OTHER, exc_xen_hypervisor_callback); #endif diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 4bb4e3d6099e..e29a6c728001 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -229,11 +229,14 @@ static const __initconst struct idt_data early_pf_idts[] = { * cpu_init() when the TSS has been initialized. */ static const __initconst struct idt_data ist_idts[] = { - ISTG(X86_TRAP_DB, asm_exc_debug, IST_INDEX_DB), - ISTG(X86_TRAP_NMI, asm_exc_nmi, IST_INDEX_NMI), - ISTG(X86_TRAP_DF, asm_exc_double_fault, IST_INDEX_DF), + ISTG(X86_TRAP_DB, asm_exc_debug, IST_INDEX_DB), + ISTG(X86_TRAP_NMI, asm_exc_nmi, IST_INDEX_NMI), + ISTG(X86_TRAP_DF, asm_exc_double_fault, IST_INDEX_DF), #ifdef CONFIG_X86_MCE - ISTG(X86_TRAP_MC, asm_exc_machine_check, IST_INDEX_MCE), + ISTG(X86_TRAP_MC, asm_exc_machine_check, IST_INDEX_MCE), +#endif +#ifdef CONFIG_AMD_MEM_ENCRYPT + ISTG(X86_TRAP_VC, asm_exc_vmm_communication, IST_INDEX_VC), #endif }; diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 39ebb2d04bec..0d6b66e93260 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -7,9 +7,12 @@ * Author: Joerg Roedel */ +#define pr_fmt(fmt) "SEV-ES: " fmt + #include /* For show_regs() */ #include #include +#include #include #include #include @@ -22,8 +25,8 @@ #include #include #include -#include -#include +#include +#include #include /* For early boot hypervisor communication in SEV-ES enabled guests */ @@ -48,11 +51,43 @@ struct sev_es_runtime_data { * interrupted stack in the #VC entry code. */ char fallback_stack[EXCEPTION_STKSZ] __aligned(PAGE_SIZE); + + /* + * Reserve one page per CPU as backup storage for the unencrypted GHCB. + * It is needed when an NMI happens while the #VC handler uses the real + * GHCB, and the NMI handler itself is causing another #VC exception. In + * that case the GHCB content of the first handler needs to be backed up + * and restored. + */ + struct ghcb backup_ghcb; + + /* + * Mark the per-cpu GHCBs as in-use to detect nested #VC exceptions. + * There is no need for it to be atomic, because nothing is written to + * the GHCB between the read and the write of ghcb_active. So it is safe + * to use it when a nested #VC exception happens before the write. + * + * This is necessary for example in the #VC->NMI->#VC case when the NMI + * happens while the first #VC handler uses the GHCB. When the NMI code + * raises a second #VC handler it might overwrite the contents of the + * GHCB written by the first handler. To avoid this the content of the + * GHCB is saved and restored when the GHCB is detected to be in use + * already. + */ + bool ghcb_active; + bool backup_ghcb_active; +}; + +struct ghcb_state { + struct ghcb *ghcb; }; static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data); DEFINE_STATIC_KEY_FALSE(sev_es_enable_key); +/* Needed in vc_early_forward_exception */ +void do_early_exception(struct pt_regs *regs, int trapnr); + static void __init setup_vc_stacks(int cpu) { struct sev_es_runtime_data *data; @@ -123,8 +158,52 @@ void noinstr __sev_es_ist_exit(void) this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], *(unsigned long *)ist); } -/* Needed in vc_early_forward_exception */ -void do_early_exception(struct pt_regs *regs, int trapnr); +static __always_inline struct ghcb *sev_es_get_ghcb(struct ghcb_state *state) +{ + struct sev_es_runtime_data *data; + struct ghcb *ghcb; + + data = this_cpu_read(runtime_data); + ghcb = &data->ghcb_page; + + if (unlikely(data->ghcb_active)) { + /* GHCB is already in use - save its contents */ + + if (unlikely(data->backup_ghcb_active)) + return NULL; + + /* Mark backup_ghcb active before writing to it */ + data->backup_ghcb_active = true; + + state->ghcb = &data->backup_ghcb; + + /* Backup GHCB content */ + *state->ghcb = *ghcb; + } else { + state->ghcb = NULL; + data->ghcb_active = true; + } + + return ghcb; +} + +static __always_inline void sev_es_put_ghcb(struct ghcb_state *state) +{ + struct sev_es_runtime_data *data; + struct ghcb *ghcb; + + data = this_cpu_read(runtime_data); + ghcb = &data->ghcb_page; + + if (state->ghcb) { + /* Restore GHCB from Backup */ + *ghcb = *state->ghcb; + data->backup_ghcb_active = false; + state->ghcb = NULL; + } else { + data->ghcb_active = false; + } +} static inline u64 sev_es_rd_ghcb_msr(void) { @@ -316,6 +395,9 @@ static void __init init_ghcb(int cpu) panic("Can't map GHCBs unencrypted"); memset(&data->ghcb_page, 0, sizeof(data->ghcb_page)); + + data->ghcb_active = false; + data->backup_ghcb_active = false; } void __init sev_es_init_vc_handling(void) @@ -336,6 +418,9 @@ void __init sev_es_init_vc_handling(void) init_ghcb(cpu); setup_vc_stacks(cpu); } + + /* Secondary CPUs use the runtime #VC handler */ + initial_vc_handler = (unsigned long)safe_stack_exc_vmm_communication; } static void __init vc_early_forward_exception(struct es_em_ctxt *ctxt) @@ -366,6 +451,159 @@ static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, return result; } +static __always_inline void vc_forward_exception(struct es_em_ctxt *ctxt) +{ + long error_code = ctxt->fi.error_code; + int trapnr = ctxt->fi.vector; + + ctxt->regs->orig_ax = ctxt->fi.error_code; + + switch (trapnr) { + case X86_TRAP_GP: + exc_general_protection(ctxt->regs, error_code); + break; + case X86_TRAP_UD: + exc_invalid_op(ctxt->regs); + break; + default: + pr_emerg("Unsupported exception in #VC instruction emulation - can't continue\n"); + BUG(); + } +} + +static __always_inline bool on_vc_fallback_stack(struct pt_regs *regs) +{ + unsigned long sp = (unsigned long)regs; + + return (sp >= __this_cpu_ist_bottom_va(VC2) && sp < __this_cpu_ist_top_va(VC2)); +} + +/* + * Main #VC exception handler. It is called when the entry code was able to + * switch off the IST to a safe kernel stack. + * + * With the current implementation it is always possible to switch to a safe + * stack because #VC exceptions only happen at known places, like intercepted + * instructions or accesses to MMIO areas/IO ports. They can also happen with + * code instrumentation when the hypervisor intercepts #DB, but the critical + * paths are forbidden to be instrumented, so #DB exceptions currently also + * only happen in safe places. + */ +DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication) +{ + struct sev_es_runtime_data *data = this_cpu_read(runtime_data); + struct ghcb_state state; + struct es_em_ctxt ctxt; + enum es_result result; + struct ghcb *ghcb; + + lockdep_assert_irqs_disabled(); + instrumentation_begin(); + + /* + * This is invoked through an interrupt gate, so IRQs are disabled. The + * code below might walk page-tables for user or kernel addresses, so + * keep the IRQs disabled to protect us against concurrent TLB flushes. + */ + + ghcb = sev_es_get_ghcb(&state); + if (!ghcb) { + /* + * Mark GHCBs inactive so that panic() is able to print the + * message. + */ + data->ghcb_active = false; + data->backup_ghcb_active = false; + + panic("Unable to handle #VC exception! GHCB and Backup GHCB are already in use"); + } + + vc_ghcb_invalidate(ghcb); + result = vc_init_em_ctxt(&ctxt, regs, error_code); + + if (result == ES_OK) + result = vc_handle_exitcode(&ctxt, ghcb, error_code); + + sev_es_put_ghcb(&state); + + /* Done - now check the result */ + switch (result) { + case ES_OK: + vc_finish_insn(&ctxt); + break; + case ES_UNSUPPORTED: + pr_err_ratelimited("Unsupported exit-code 0x%02lx in early #VC exception (IP: 0x%lx)\n", + error_code, regs->ip); + goto fail; + case ES_VMM_ERROR: + pr_err_ratelimited("Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n", + error_code, regs->ip); + goto fail; + case ES_DECODE_FAILED: + pr_err_ratelimited("Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n", + error_code, regs->ip); + goto fail; + case ES_EXCEPTION: + vc_forward_exception(&ctxt); + break; + case ES_RETRY: + /* Nothing to do */ + break; + default: + pr_emerg("Unknown result in %s():%d\n", __func__, result); + /* + * Emulating the instruction which caused the #VC exception + * failed - can't continue so print debug information + */ + BUG(); + } + +out: + instrumentation_end(); + + return; + +fail: + if (user_mode(regs)) { + /* + * Do not kill the machine if user-space triggered the + * exception. Send SIGBUS instead and let user-space deal with + * it. + */ + force_sig_fault(SIGBUS, BUS_OBJERR, (void __user *)0); + } else { + pr_emerg("PANIC: Unhandled #VC exception in kernel space (result=%d)\n", + result); + + /* Show some debug info */ + show_regs(regs); + + /* Ask hypervisor to sev_es_terminate */ + sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST); + + /* If that fails and we get here - just panic */ + panic("Returned from Terminate-Request to Hypervisor\n"); + } + + goto out; +} + +/* This handler runs on the #VC fall-back stack. It can cause further #VC exceptions */ +DEFINE_IDTENTRY_VC_IST(exc_vmm_communication) +{ + instrumentation_begin(); + panic("Can't handle #VC exception from unsupported context\n"); + instrumentation_end(); +} + +DEFINE_IDTENTRY_VC(exc_vmm_communication) +{ + if (likely(!on_vc_fallback_stack(regs))) + safe_stack_exc_vmm_communication(regs, error_code); + else + ist_exc_vmm_communication(regs, error_code); +} + bool __init handle_vc_boot_ghcb(struct pt_regs *regs) { unsigned long exit_code = regs->orig_ax; -- cgit v1.2.3-58-ga151 From d3529bb73f76d0ec8aafaca505226fa0971c1dc9 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:48 +0200 Subject: x86/sev-es: Wire up existing #VC exit-code handlers Re-use the handlers for CPUID- and IOIO-caused #VC exceptions in the early boot handler. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-48-joro@8bytes.org --- arch/x86/kernel/sev-es-shared.c | 7 +++---- arch/x86/kernel/sev-es.c | 6 ++++++ 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index 53e3de0e8060..491b557bdfba 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -325,8 +325,7 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) return ES_OK; } -static enum es_result __maybe_unused -vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { struct pt_regs *regs = ctxt->regs; u64 exit_info_1, exit_info_2; @@ -434,8 +433,8 @@ vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ret; } -static enum es_result __maybe_unused vc_handle_cpuid(struct ghcb *ghcb, - struct es_em_ctxt *ctxt) +static enum es_result vc_handle_cpuid(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) { struct pt_regs *regs = ctxt->regs; u32 cr4 = native_read_cr4(); diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 0d6b66e93260..b10a62a78c07 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -441,6 +441,12 @@ static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, enum es_result result; switch (exit_code) { + case SVM_EXIT_CPUID: + result = vc_handle_cpuid(ghcb, ctxt); + break; + case SVM_EXIT_IOIO: + result = vc_handle_ioio(ghcb, ctxt); + break; default: /* * Unexpected #VC exception -- cgit v1.2.3-58-ga151 From 5e3427a7bc432ed2e5de394ac30f160cc6c37a1f Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:49 +0200 Subject: x86/sev-es: Handle instruction fetches from user-space When a #VC exception is triggered by user-space, the instruction decoder needs to read the instruction bytes from user addresses. Enhance vc_decode_insn() to safely fetch kernel and user instructions. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-49-joro@8bytes.org --- arch/x86/kernel/sev-es.c | 31 ++++++++++++++++++++++--------- 1 file changed, 22 insertions(+), 9 deletions(-) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index b10a62a78c07..6c30dbc1144a 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -232,17 +232,30 @@ static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt) enum es_result ret; int res; - res = vc_fetch_insn_kernel(ctxt, buffer); - if (unlikely(res == -EFAULT)) { - ctxt->fi.vector = X86_TRAP_PF; - ctxt->fi.error_code = 0; - ctxt->fi.cr2 = ctxt->regs->ip; - return ES_EXCEPTION; + if (user_mode(ctxt->regs)) { + res = insn_fetch_from_user(ctxt->regs, buffer); + if (!res) { + ctxt->fi.vector = X86_TRAP_PF; + ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER; + ctxt->fi.cr2 = ctxt->regs->ip; + return ES_EXCEPTION; + } + + if (!insn_decode(&ctxt->insn, ctxt->regs, buffer, res)) + return ES_DECODE_FAILED; + } else { + res = vc_fetch_insn_kernel(ctxt, buffer); + if (res) { + ctxt->fi.vector = X86_TRAP_PF; + ctxt->fi.error_code = X86_PF_INSTR; + ctxt->fi.cr2 = ctxt->regs->ip; + return ES_EXCEPTION; + } + + insn_init(&ctxt->insn, buffer, MAX_INSN_SIZE - res, 1); + insn_get_length(&ctxt->insn); } - insn_init(&ctxt->insn, buffer, MAX_INSN_SIZE - res, 1); - insn_get_length(&ctxt->insn); - ret = ctxt->insn.immediate.got ? ES_OK : ES_DECODE_FAILED; return ret; -- cgit v1.2.3-58-ga151 From 51ee7d6e3d2b70a3f232cceffab5084a2abd6719 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 7 Sep 2020 15:15:50 +0200 Subject: x86/sev-es: Handle MMIO events Add a handler for #VC exceptions caused by MMIO intercepts. These intercepts come along as nested page faults on pages with reserved bits set. Signed-off-by: Tom Lendacky [ jroedel@suse.de: Adapt to VC handling framework ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-50-joro@8bytes.org --- arch/x86/include/uapi/asm/svm.h | 5 + arch/x86/kernel/sev-es.c | 222 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 227 insertions(+) diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index c68d1618c9b0..8f36ae021a7f 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -81,6 +81,11 @@ #define SVM_EXIT_AVIC_INCOMPLETE_IPI 0x401 #define SVM_EXIT_AVIC_UNACCELERATED_ACCESS 0x402 +/* SEV-ES software-defined VMGEXIT events */ +#define SVM_VMGEXIT_MMIO_READ 0x80000001 +#define SVM_VMGEXIT_MMIO_WRITE 0x80000002 +#define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff + #define SVM_EXIT_ERR -1 #define SVM_EXIT_REASONS \ diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 6c30dbc1144a..a170810fe4f4 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -359,6 +359,37 @@ fault: return ES_EXCEPTION; } +static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt, + unsigned long vaddr, phys_addr_t *paddr) +{ + unsigned long va = (unsigned long)vaddr; + unsigned int level; + phys_addr_t pa; + pgd_t *pgd; + pte_t *pte; + + pgd = __va(read_cr3_pa()); + pgd = &pgd[pgd_index(va)]; + pte = lookup_address_in_pgd(pgd, va, &level); + if (!pte) { + ctxt->fi.vector = X86_TRAP_PF; + ctxt->fi.cr2 = vaddr; + ctxt->fi.error_code = 0; + + if (user_mode(ctxt->regs)) + ctxt->fi.error_code |= X86_PF_USER; + + return false; + } + + pa = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; + pa |= va & ~page_level_mask(level); + + *paddr = pa; + + return true; +} + /* Include code shared with pre-decompression boot stage */ #include "sev-es-shared.c" @@ -447,6 +478,194 @@ static void __init vc_early_forward_exception(struct es_em_ctxt *ctxt) do_early_exception(ctxt->regs, trapnr); } +static long *vc_insn_get_reg(struct es_em_ctxt *ctxt) +{ + long *reg_array; + int offset; + + reg_array = (long *)ctxt->regs; + offset = insn_get_modrm_reg_off(&ctxt->insn, ctxt->regs); + + if (offset < 0) + return NULL; + + offset /= sizeof(long); + + return reg_array + offset; +} + +static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt, + unsigned int bytes, bool read) +{ + u64 exit_code, exit_info_1, exit_info_2; + unsigned long ghcb_pa = __pa(ghcb); + phys_addr_t paddr; + void __user *ref; + + ref = insn_get_addr_ref(&ctxt->insn, ctxt->regs); + if (ref == (void __user *)-1L) + return ES_UNSUPPORTED; + + exit_code = read ? SVM_VMGEXIT_MMIO_READ : SVM_VMGEXIT_MMIO_WRITE; + + if (!vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr)) { + if (!read) + ctxt->fi.error_code |= X86_PF_WRITE; + + return ES_EXCEPTION; + } + + exit_info_1 = paddr; + /* Can never be greater than 8 */ + exit_info_2 = bytes; + + ghcb->save.sw_scratch = ghcb_pa + offsetof(struct ghcb, shared_buffer); + + return sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, exit_info_1, exit_info_2); +} + +static enum es_result vc_handle_mmio_twobyte_ops(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + struct insn *insn = &ctxt->insn; + unsigned int bytes = 0; + enum es_result ret; + int sign_byte; + long *reg_data; + + switch (insn->opcode.bytes[1]) { + /* MMIO Read w/ zero-extension */ + case 0xb6: + bytes = 1; + fallthrough; + case 0xb7: + if (!bytes) + bytes = 2; + + ret = vc_do_mmio(ghcb, ctxt, bytes, true); + if (ret) + break; + + /* Zero extend based on operand size */ + reg_data = vc_insn_get_reg(ctxt); + if (!reg_data) + return ES_DECODE_FAILED; + + memset(reg_data, 0, insn->opnd_bytes); + + memcpy(reg_data, ghcb->shared_buffer, bytes); + break; + + /* MMIO Read w/ sign-extension */ + case 0xbe: + bytes = 1; + fallthrough; + case 0xbf: + if (!bytes) + bytes = 2; + + ret = vc_do_mmio(ghcb, ctxt, bytes, true); + if (ret) + break; + + /* Sign extend based on operand size */ + reg_data = vc_insn_get_reg(ctxt); + if (!reg_data) + return ES_DECODE_FAILED; + + if (bytes == 1) { + u8 *val = (u8 *)ghcb->shared_buffer; + + sign_byte = (*val & 0x80) ? 0xff : 0x00; + } else { + u16 *val = (u16 *)ghcb->shared_buffer; + + sign_byte = (*val & 0x8000) ? 0xff : 0x00; + } + memset(reg_data, sign_byte, insn->opnd_bytes); + + memcpy(reg_data, ghcb->shared_buffer, bytes); + break; + + default: + ret = ES_UNSUPPORTED; + } + + return ret; +} + +static enum es_result vc_handle_mmio(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + struct insn *insn = &ctxt->insn; + unsigned int bytes = 0; + enum es_result ret; + long *reg_data; + + switch (insn->opcode.bytes[0]) { + /* MMIO Write */ + case 0x88: + bytes = 1; + fallthrough; + case 0x89: + if (!bytes) + bytes = insn->opnd_bytes; + + reg_data = vc_insn_get_reg(ctxt); + if (!reg_data) + return ES_DECODE_FAILED; + + memcpy(ghcb->shared_buffer, reg_data, bytes); + + ret = vc_do_mmio(ghcb, ctxt, bytes, false); + break; + + case 0xc6: + bytes = 1; + fallthrough; + case 0xc7: + if (!bytes) + bytes = insn->opnd_bytes; + + memcpy(ghcb->shared_buffer, insn->immediate1.bytes, bytes); + + ret = vc_do_mmio(ghcb, ctxt, bytes, false); + break; + + /* MMIO Read */ + case 0x8a: + bytes = 1; + fallthrough; + case 0x8b: + if (!bytes) + bytes = insn->opnd_bytes; + + ret = vc_do_mmio(ghcb, ctxt, bytes, true); + if (ret) + break; + + reg_data = vc_insn_get_reg(ctxt); + if (!reg_data) + return ES_DECODE_FAILED; + + /* Zero-extend for 32-bit operation */ + if (bytes == 4) + *reg_data = 0; + + memcpy(reg_data, ghcb->shared_buffer, bytes); + break; + + /* Two-Byte Opcodes */ + case 0x0f: + ret = vc_handle_mmio_twobyte_ops(ghcb, ctxt); + break; + default: + ret = ES_UNSUPPORTED; + } + + return ret; +} + static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, struct ghcb *ghcb, unsigned long exit_code) @@ -460,6 +679,9 @@ static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, case SVM_EXIT_IOIO: result = vc_handle_ioio(ghcb, ctxt); break; + case SVM_EXIT_NPF: + result = vc_handle_mmio(ghcb, ctxt); + break; default: /* * Unexpected #VC exception -- cgit v1.2.3-58-ga151 From 0118b604c2c94c6e34982015cfa7891af4764786 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:15:51 +0200 Subject: x86/sev-es: Handle MMIO String Instructions Add handling for emulation of the MOVS instruction on MMIO regions, as done by the memcpy_toio() and memcpy_fromio() functions. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-51-joro@8bytes.org --- arch/x86/kernel/sev-es.c | 77 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 77 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index a170810fe4f4..f724b75ad235 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -594,6 +594,73 @@ static enum es_result vc_handle_mmio_twobyte_ops(struct ghcb *ghcb, return ret; } +/* + * The MOVS instruction has two memory operands, which raises the + * problem that it is not known whether the access to the source or the + * destination caused the #VC exception (and hence whether an MMIO read + * or write operation needs to be emulated). + * + * Instead of playing games with walking page-tables and trying to guess + * whether the source or destination is an MMIO range, split the move + * into two operations, a read and a write with only one memory operand. + * This will cause a nested #VC exception on the MMIO address which can + * then be handled. + * + * This implementation has the benefit that it also supports MOVS where + * source _and_ destination are MMIO regions. + * + * It will slow MOVS on MMIO down a lot, but in SEV-ES guests it is a + * rare operation. If it turns out to be a performance problem the split + * operations can be moved to memcpy_fromio() and memcpy_toio(). + */ +static enum es_result vc_handle_mmio_movs(struct es_em_ctxt *ctxt, + unsigned int bytes) +{ + unsigned long ds_base, es_base; + unsigned char *src, *dst; + unsigned char buffer[8]; + enum es_result ret; + bool rep; + int off; + + ds_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_DS); + es_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_ES); + + if (ds_base == -1L || es_base == -1L) { + ctxt->fi.vector = X86_TRAP_GP; + ctxt->fi.error_code = 0; + return ES_EXCEPTION; + } + + src = ds_base + (unsigned char *)ctxt->regs->si; + dst = es_base + (unsigned char *)ctxt->regs->di; + + ret = vc_read_mem(ctxt, src, buffer, bytes); + if (ret != ES_OK) + return ret; + + ret = vc_write_mem(ctxt, dst, buffer, bytes); + if (ret != ES_OK) + return ret; + + if (ctxt->regs->flags & X86_EFLAGS_DF) + off = -bytes; + else + off = bytes; + + ctxt->regs->si += off; + ctxt->regs->di += off; + + rep = insn_has_rep_prefix(&ctxt->insn); + if (rep) + ctxt->regs->cx -= 1; + + if (!rep || ctxt->regs->cx == 0) + return ES_OK; + else + return ES_RETRY; +} + static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { @@ -655,6 +722,16 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, memcpy(reg_data, ghcb->shared_buffer, bytes); break; + /* MOVS instruction */ + case 0xa4: + bytes = 1; + fallthrough; + case 0xa5: + if (!bytes) + bytes = insn->opnd_bytes; + + ret = vc_handle_mmio_movs(ctxt, bytes); + break; /* Two-Byte Opcodes */ case 0x0f: ret = vc_handle_mmio_twobyte_ops(ghcb, ctxt); -- cgit v1.2.3-58-ga151 From a4afa6081c88701635e1e20090f953a25f9444e0 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 7 Sep 2020 15:15:52 +0200 Subject: x86/sev-es: Handle MSR events Implement a handler for #VC exceptions caused by RDMSR/WRMSR instructions. Signed-off-by: Tom Lendacky [ jroedel@suse.de: Adapt to #VC handling infrastructure. ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-52-joro@8bytes.org --- arch/x86/kernel/sev-es.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index f724b75ad235..620510070a1a 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -393,6 +393,31 @@ static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt, /* Include code shared with pre-decompression boot stage */ #include "sev-es-shared.c" +static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +{ + struct pt_regs *regs = ctxt->regs; + enum es_result ret; + u64 exit_info_1; + + /* Is it a WRMSR? */ + exit_info_1 = (ctxt->insn.opcode.bytes[1] == 0x30) ? 1 : 0; + + ghcb_set_rcx(ghcb, regs->cx); + if (exit_info_1) { + ghcb_set_rax(ghcb, regs->ax); + ghcb_set_rdx(ghcb, regs->dx); + } + + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MSR, exit_info_1, 0); + + if ((ret == ES_OK) && (!exit_info_1)) { + regs->ax = ghcb->save.rax; + regs->dx = ghcb->save.rdx; + } + + return ret; +} + /* * This function runs on the first #VC exception after the kernel * switched to virtual addresses. @@ -756,6 +781,9 @@ static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, case SVM_EXIT_IOIO: result = vc_handle_ioio(ghcb, ctxt); break; + case SVM_EXIT_MSR: + result = vc_handle_msr(ghcb, ctxt); + break; case SVM_EXIT_NPF: result = vc_handle_mmio(ghcb, ctxt); break; -- cgit v1.2.3-58-ga151 From 479a7bf5c1f7f14eb37c6d6aeb401562efc1fcad Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 7 Sep 2020 15:15:53 +0200 Subject: x86/sev-es: Handle DR7 read/write events Add code to handle #VC exceptions on DR7 register reads and writes. This is needed early because show_regs() reads DR7 to print it out. Under SEV-ES, there is currently no support for saving/restoring the DRx registers but software expects to be able to write to the DR7 register. For now, cache the value written to DR7 and return it on read attempts, but do not touch the real hardware DR7. Signed-off-by: Tom Lendacky [ jroedel@suse.de: - Adapt to #VC handling framework - Support early usage ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-53-joro@8bytes.org --- arch/x86/kernel/sev-es.c | 85 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 85 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 620510070a1a..391b9c7f7312 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -29,6 +29,8 @@ #include #include +#define DR7_RESET_VALUE 0x400 + /* For early boot hypervisor communication in SEV-ES enabled guests */ static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE); @@ -76,6 +78,13 @@ struct sev_es_runtime_data { */ bool ghcb_active; bool backup_ghcb_active; + + /* + * Cached DR7 value - write it on DR7 writes and return it on reads. + * That value will never make it to the real hardware DR7 as debugging + * is currently unsupported in SEV-ES guests. + */ + unsigned long dr7; }; struct ghcb_state { @@ -519,6 +528,21 @@ static long *vc_insn_get_reg(struct es_em_ctxt *ctxt) return reg_array + offset; } +static long *vc_insn_get_rm(struct es_em_ctxt *ctxt) +{ + long *reg_array; + int offset; + + reg_array = (long *)ctxt->regs; + offset = insn_get_modrm_rm_off(&ctxt->insn, ctxt->regs); + + if (offset < 0) + return NULL; + + offset /= sizeof(long); + + return reg_array + offset; +} static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt, unsigned int bytes, bool read) { @@ -768,6 +792,61 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, return ret; } +static enum es_result vc_handle_dr7_write(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + struct sev_es_runtime_data *data = this_cpu_read(runtime_data); + long val, *reg = vc_insn_get_rm(ctxt); + enum es_result ret; + + if (!reg) + return ES_DECODE_FAILED; + + val = *reg; + + /* Upper 32 bits must be written as zeroes */ + if (val >> 32) { + ctxt->fi.vector = X86_TRAP_GP; + ctxt->fi.error_code = 0; + return ES_EXCEPTION; + } + + /* Clear out other reserved bits and set bit 10 */ + val = (val & 0xffff23ffL) | BIT(10); + + /* Early non-zero writes to DR7 are not supported */ + if (!data && (val & ~DR7_RESET_VALUE)) + return ES_UNSUPPORTED; + + /* Using a value of 0 for ExitInfo1 means RAX holds the value */ + ghcb_set_rax(ghcb, val); + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WRITE_DR7, 0, 0); + if (ret != ES_OK) + return ret; + + if (data) + data->dr7 = val; + + return ES_OK; +} + +static enum es_result vc_handle_dr7_read(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + struct sev_es_runtime_data *data = this_cpu_read(runtime_data); + long *reg = vc_insn_get_rm(ctxt); + + if (!reg) + return ES_DECODE_FAILED; + + if (data) + *reg = data->dr7; + else + *reg = DR7_RESET_VALUE; + + return ES_OK; +} + static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, struct ghcb *ghcb, unsigned long exit_code) @@ -775,6 +854,12 @@ static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, enum es_result result; switch (exit_code) { + case SVM_EXIT_READ_DR7: + result = vc_handle_dr7_read(ghcb, ctxt); + break; + case SVM_EXIT_WRITE_DR7: + result = vc_handle_dr7_write(ghcb, ctxt); + break; case SVM_EXIT_CPUID: result = vc_handle_cpuid(ghcb, ctxt); break; -- cgit v1.2.3-58-ga151 From a14a92fc4b420ae6713800a8ae8c3686c1a1fa20 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 7 Sep 2020 15:15:54 +0200 Subject: x86/sev-es: Handle WBINVD Events Implement a handler for #VC exceptions caused by WBINVD instructions. Signed-off-by: Tom Lendacky [ jroedel@suse.de: Adapt to #VC handling framework ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-54-joro@8bytes.org --- arch/x86/kernel/sev-es.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 391b9c7f7312..aba27c3c1633 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -847,6 +847,12 @@ static enum es_result vc_handle_dr7_read(struct ghcb *ghcb, return ES_OK; } +static enum es_result vc_handle_wbinvd(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + return sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WBINVD, 0, 0); +} + static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, struct ghcb *ghcb, unsigned long exit_code) @@ -869,6 +875,9 @@ static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, case SVM_EXIT_MSR: result = vc_handle_msr(ghcb, ctxt); break; + case SVM_EXIT_WBINVD: + result = vc_handle_wbinvd(ghcb, ctxt); + break; case SVM_EXIT_NPF: result = vc_handle_mmio(ghcb, ctxt); break; -- cgit v1.2.3-58-ga151 From 4711e7acaa125d8cc242f06e1f4d6c74e177454b Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 7 Sep 2020 15:15:55 +0200 Subject: x86/sev-es: Handle RDTSC(P) Events Implement a handler for #VC exceptions caused by RDTSC and RDTSCP instructions. Also make it available in the pre-decompression stage because the KASLR code uses RDTSC/RDTSCP to gather entropy and some hypervisors intercept these instructions. Signed-off-by: Tom Lendacky [ jroedel@suse.de: - Adapt to #VC handling infrastructure - Make it available early ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-55-joro@8bytes.org --- arch/x86/boot/compressed/sev-es.c | 4 ++++ arch/x86/kernel/sev-es-shared.c | 23 +++++++++++++++++++++++ arch/x86/kernel/sev-es.c | 4 ++++ 3 files changed, 31 insertions(+) diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c index b1790f487456..5f15e5864e0c 100644 --- a/arch/x86/boot/compressed/sev-es.c +++ b/arch/x86/boot/compressed/sev-es.c @@ -181,6 +181,10 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code) goto finish; switch (exit_code) { + case SVM_EXIT_RDTSC: + case SVM_EXIT_RDTSCP: + result = vc_handle_rdtsc(boot_ghcb, &ctxt, exit_code); + break; case SVM_EXIT_IOIO: result = vc_handle_ioio(boot_ghcb, &ctxt); break; diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index 491b557bdfba..4be8af2f9c57 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -467,3 +467,26 @@ static enum es_result vc_handle_cpuid(struct ghcb *ghcb, return ES_OK; } + +static enum es_result vc_handle_rdtsc(struct ghcb *ghcb, + struct es_em_ctxt *ctxt, + unsigned long exit_code) +{ + bool rdtscp = (exit_code == SVM_EXIT_RDTSCP); + enum es_result ret; + + ret = sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, 0, 0); + if (ret != ES_OK) + return ret; + + if (!(ghcb_rax_is_valid(ghcb) && ghcb_rdx_is_valid(ghcb) && + (!rdtscp || ghcb_rcx_is_valid(ghcb)))) + return ES_VMM_ERROR; + + ctxt->regs->ax = ghcb->save.rax; + ctxt->regs->dx = ghcb->save.rdx; + if (rdtscp) + ctxt->regs->cx = ghcb->save.rcx; + + return ES_OK; +} diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index aba27c3c1633..4d468ec325c3 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -866,6 +866,10 @@ static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, case SVM_EXIT_WRITE_DR7: result = vc_handle_dr7_write(ghcb, ctxt); break; + case SVM_EXIT_RDTSC: + case SVM_EXIT_RDTSCP: + result = vc_handle_rdtsc(ghcb, ctxt, exit_code); + break; case SVM_EXIT_CPUID: result = vc_handle_cpuid(ghcb, ctxt); break; -- cgit v1.2.3-58-ga151 From 5d55cf78a8785a7496919462f3d1a4689f62fb1d Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 7 Sep 2020 15:15:56 +0200 Subject: x86/sev-es: Handle RDPMC Events Implement a handler for #VC exceptions caused by RDPMC instructions. Signed-off-by: Tom Lendacky [ jroedel@suse.de: Adapt to #VC handling infrastructure ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-56-joro@8bytes.org --- arch/x86/kernel/sev-es.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 4d468ec325c3..b2d7287a9975 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -853,6 +853,25 @@ static enum es_result vc_handle_wbinvd(struct ghcb *ghcb, return sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WBINVD, 0, 0); } +static enum es_result vc_handle_rdpmc(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +{ + enum es_result ret; + + ghcb_set_rcx(ghcb, ctxt->regs->cx); + + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_RDPMC, 0, 0); + if (ret != ES_OK) + return ret; + + if (!(ghcb_rax_is_valid(ghcb) && ghcb_rdx_is_valid(ghcb))) + return ES_VMM_ERROR; + + ctxt->regs->ax = ghcb->save.rax; + ctxt->regs->dx = ghcb->save.rdx; + + return ES_OK; +} + static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, struct ghcb *ghcb, unsigned long exit_code) @@ -870,6 +889,9 @@ static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, case SVM_EXIT_RDTSCP: result = vc_handle_rdtsc(ghcb, ctxt, exit_code); break; + case SVM_EXIT_RDPMC: + result = vc_handle_rdpmc(ghcb, ctxt); + break; case SVM_EXIT_CPUID: result = vc_handle_cpuid(ghcb, ctxt); break; -- cgit v1.2.3-58-ga151 From 8b4ce83707cb2cff5f6d175ea38f751ac4456096 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 7 Sep 2020 15:15:57 +0200 Subject: x86/sev-es: Handle INVD Events Implement a handler for #VC exceptions caused by INVD instructions. Since Linux should never use INVD, just mark it as unsupported. Signed-off-by: Tom Lendacky [ jroedel@suse.de: Adapt to #VC handling infrastructure ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-57-joro@8bytes.org --- arch/x86/kernel/sev-es.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index b2d7287a9975..236cfc16f696 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -892,6 +892,10 @@ static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, case SVM_EXIT_RDPMC: result = vc_handle_rdpmc(ghcb, ctxt); break; + case SVM_EXIT_INVD: + pr_err_ratelimited("#VC exception for INVD??? Seriously???\n"); + result = ES_UNSUPPORTED; + break; case SVM_EXIT_CPUID: result = vc_handle_cpuid(ghcb, ctxt); break; -- cgit v1.2.3-58-ga151 From 0c2fd2ef64ef1a91d81c2f61309735ac438b68a4 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 7 Sep 2020 15:15:58 +0200 Subject: x86/sev-es: Handle MONITOR/MONITORX Events Implement a handler for #VC exceptions caused by MONITOR and MONITORX instructions. Signed-off-by: Tom Lendacky [ jroedel@suse.de: Adapt to #VC handling infrastructure ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-58-joro@8bytes.org --- arch/x86/kernel/sev-es.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 236cfc16f696..b9976e710d77 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -872,6 +872,16 @@ static enum es_result vc_handle_rdpmc(struct ghcb *ghcb, struct es_em_ctxt *ctxt return ES_OK; } +static enum es_result vc_handle_monitor(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + /* + * Treat it as a NOP and do not leak a physical address to the + * hypervisor. + */ + return ES_OK; +} + static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, struct ghcb *ghcb, unsigned long exit_code) @@ -908,6 +918,9 @@ static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, case SVM_EXIT_WBINVD: result = vc_handle_wbinvd(ghcb, ctxt); break; + case SVM_EXIT_MONITOR: + result = vc_handle_monitor(ghcb, ctxt); + break; case SVM_EXIT_NPF: result = vc_handle_mmio(ghcb, ctxt); break; -- cgit v1.2.3-58-ga151 From ded476bbe203e59cb571d6c576f680efe4a0ddff Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 7 Sep 2020 15:15:59 +0200 Subject: x86/sev-es: Handle MWAIT/MWAITX Events Implement a handler for #VC exceptions caused by MWAIT and MWAITX instructions. Signed-off-by: Tom Lendacky [ jroedel@suse.de: Adapt to #VC handling infrastructure ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-59-joro@8bytes.org --- arch/x86/kernel/sev-es.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index b9976e710d77..2aea903ceb42 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -882,6 +882,13 @@ static enum es_result vc_handle_monitor(struct ghcb *ghcb, return ES_OK; } +static enum es_result vc_handle_mwait(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + /* Treat the same as MONITOR/MONITORX */ + return ES_OK; +} + static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, struct ghcb *ghcb, unsigned long exit_code) @@ -921,6 +928,9 @@ static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, case SVM_EXIT_MONITOR: result = vc_handle_monitor(ghcb, ctxt); break; + case SVM_EXIT_MWAIT: + result = vc_handle_mwait(ghcb, ctxt); + break; case SVM_EXIT_NPF: result = vc_handle_mmio(ghcb, ctxt); break; -- cgit v1.2.3-58-ga151 From 2eb7dcf0ccc40ad3f39b000becf16661abf98102 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 7 Sep 2020 15:16:00 +0200 Subject: x86/sev-es: Handle VMMCALL Events Implement a handler for #VC exceptions caused by VMMCALL instructions. This is only a starting point, VMMCALL emulation under SEV-ES needs further hypervisor-specific changes to provide additional state. [ bp: Drop "this patch". ] Signed-off-by: Tom Lendacky [ jroedel@suse.de: Adapt to #VC handling infrastructure ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-60-joro@8bytes.org --- arch/x86/kernel/sev-es.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 2aea903ceb42..86cb4c5a7ad2 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -889,6 +889,26 @@ static enum es_result vc_handle_mwait(struct ghcb *ghcb, return ES_OK; } +static enum es_result vc_handle_vmmcall(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + enum es_result ret; + + ghcb_set_rax(ghcb, ctxt->regs->ax); + ghcb_set_cpl(ghcb, user_mode(ctxt->regs) ? 3 : 0); + + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_VMMCALL, 0, 0); + if (ret != ES_OK) + return ret; + + if (!ghcb_rax_is_valid(ghcb)) + return ES_VMM_ERROR; + + ctxt->regs->ax = ghcb->save.rax; + + return ES_OK; +} + static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, struct ghcb *ghcb, unsigned long exit_code) @@ -922,6 +942,9 @@ static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, case SVM_EXIT_MSR: result = vc_handle_msr(ghcb, ctxt); break; + case SVM_EXIT_VMMCALL: + result = vc_handle_vmmcall(ghcb, ctxt); + break; case SVM_EXIT_WBINVD: result = vc_handle_wbinvd(ghcb, ctxt); break; -- cgit v1.2.3-58-ga151 From a2d0171a9cf59637411281a929900fde80e6c1cb Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:16:01 +0200 Subject: x86/sev-es: Handle #AC Events Implement a handler for #VC exceptions caused by #AC exceptions. The #AC exception is just forwarded to do_alignment_check() and not pushed down to the hypervisor, as requested by the SEV-ES GHCB Standardization Specification. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-61-joro@8bytes.org --- arch/x86/kernel/sev-es.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 86cb4c5a7ad2..8867c481e3e2 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -909,6 +909,19 @@ static enum es_result vc_handle_vmmcall(struct ghcb *ghcb, return ES_OK; } +static enum es_result vc_handle_trap_ac(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + /* + * Calling ecx_alignment_check() directly does not work, because it + * enables IRQs and the GHCB is active. Forward the exception and call + * it later from vc_forward_exception(). + */ + ctxt->fi.vector = X86_TRAP_AC; + ctxt->fi.error_code = 0; + return ES_EXCEPTION; +} + static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, struct ghcb *ghcb, unsigned long exit_code) @@ -922,6 +935,9 @@ static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, case SVM_EXIT_WRITE_DR7: result = vc_handle_dr7_write(ghcb, ctxt); break; + case SVM_EXIT_EXCP_BASE + X86_TRAP_AC: + result = vc_handle_trap_ac(ghcb, ctxt); + break; case SVM_EXIT_RDTSC: case SVM_EXIT_RDTSCP: result = vc_handle_rdtsc(ghcb, ctxt, exit_code); @@ -981,6 +997,9 @@ static __always_inline void vc_forward_exception(struct es_em_ctxt *ctxt) case X86_TRAP_UD: exc_invalid_op(ctxt->regs); break; + case X86_TRAP_AC: + exc_alignment_check(ctxt->regs, error_code); + break; default: pr_emerg("Unsupported exception in #VC instruction emulation - can't continue\n"); BUG(); -- cgit v1.2.3-58-ga151 From cb1ad3ecea959593400dfac4f027dbc005e62c39 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:16:02 +0200 Subject: x86/sev-es: Handle #DB Events Handle #VC exceptions caused by #DB exceptions in the guest. Those must be handled outside of instrumentation_begin()/end() so that the handler will not be raised recursively. Handle them by calling the kernel's debug exception handler. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-62-joro@8bytes.org --- arch/x86/kernel/sev-es.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 8867c481e3e2..79d5190cbc6b 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -922,6 +922,14 @@ static enum es_result vc_handle_trap_ac(struct ghcb *ghcb, return ES_EXCEPTION; } +static __always_inline void vc_handle_trap_db(struct pt_regs *regs) +{ + if (user_mode(regs)) + noist_exc_debug(regs); + else + exc_debug(regs); +} + static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, struct ghcb *ghcb, unsigned long exit_code) @@ -1033,6 +1041,15 @@ DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication) struct ghcb *ghcb; lockdep_assert_irqs_disabled(); + + /* + * Handle #DB before calling into !noinstr code to avoid recursive #DB. + */ + if (error_code == SVM_EXIT_EXCP_BASE + X86_TRAP_DB) { + vc_handle_trap_db(regs); + return; + } + instrumentation_begin(); /* -- cgit v1.2.3-58-ga151 From f6a9f8a45810d2914ea422ff39bfe2e0251c50f2 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:16:03 +0200 Subject: x86/paravirt: Allow hypervisor-specific VMMCALL handling under SEV-ES Add two new paravirt callbacks to provide hypervisor-specific processor state in the GHCB and to copy state from the hypervisor back to the processor. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-63-joro@8bytes.org --- arch/x86/include/asm/x86_init.h | 16 +++++++++++++++- arch/x86/kernel/sev-es.c | 12 ++++++++++++ 2 files changed, 27 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 6807153c0410..0304e2931cd3 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -4,8 +4,10 @@ #include +struct ghcb; struct mpc_bus; struct mpc_cpu; +struct pt_regs; struct mpc_table; struct cpuinfo_x86; @@ -236,10 +238,22 @@ struct x86_legacy_features { /** * struct x86_hyper_runtime - x86 hypervisor specific runtime callbacks * - * @pin_vcpu: pin current vcpu to specified physical cpu (run rarely) + * @pin_vcpu: pin current vcpu to specified physical + * cpu (run rarely) + * @sev_es_hcall_prepare: Load additional hypervisor-specific + * state into the GHCB when doing a VMMCALL under + * SEV-ES. Called from the #VC exception handler. + * @sev_es_hcall_finish: Copies state from the GHCB back into the + * processor (or pt_regs). Also runs checks on the + * state returned from the hypervisor after a + * VMMCALL under SEV-ES. Needs to return 'false' + * if the checks fail. Called from the #VC + * exception handler. */ struct x86_hyper_runtime { void (*pin_vcpu)(int cpu); + void (*sev_es_hcall_prepare)(struct ghcb *ghcb, struct pt_regs *regs); + bool (*sev_es_hcall_finish)(struct ghcb *ghcb, struct pt_regs *regs); }; /** diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 79d5190cbc6b..6d89df9f29dc 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -897,6 +897,9 @@ static enum es_result vc_handle_vmmcall(struct ghcb *ghcb, ghcb_set_rax(ghcb, ctxt->regs->ax); ghcb_set_cpl(ghcb, user_mode(ctxt->regs) ? 3 : 0); + if (x86_platform.hyper.sev_es_hcall_prepare) + x86_platform.hyper.sev_es_hcall_prepare(ghcb, ctxt->regs); + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_VMMCALL, 0, 0); if (ret != ES_OK) return ret; @@ -906,6 +909,15 @@ static enum es_result vc_handle_vmmcall(struct ghcb *ghcb, ctxt->regs->ax = ghcb->save.rax; + /* + * Call sev_es_hcall_finish() after regs->ax is already set. + * This allows the hypervisor handler to overwrite it again if + * necessary. + */ + if (x86_platform.hyper.sev_es_hcall_finish && + !x86_platform.hyper.sev_es_hcall_finish(ghcb, ctxt->regs)) + return ES_VMM_ERROR; + return ES_OK; } -- cgit v1.2.3-58-ga151 From 99419b251e5427b89dbfae103d8a2f469efaa4b2 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 7 Sep 2020 15:16:04 +0200 Subject: x86/kvm: Add KVM-specific VMMCALL handling under SEV-ES Implement the callbacks to copy the processor state required by KVM to the GHCB. Signed-off-by: Tom Lendacky [ jroedel@suse.de: - Split out of a larger patch - Adapt to different callback functions ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-64-joro@8bytes.org --- arch/x86/kernel/kvm.c | 35 +++++++++++++++++++++++++++++------ 1 file changed, 29 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 08320b0b2b27..0f9597275e9c 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -36,6 +36,8 @@ #include #include #include +#include +#include DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled); @@ -746,13 +748,34 @@ static void __init kvm_init_platform(void) x86_platform.apic_post_init = kvm_apic_init; } +#if defined(CONFIG_AMD_MEM_ENCRYPT) +static void kvm_sev_es_hcall_prepare(struct ghcb *ghcb, struct pt_regs *regs) +{ + /* RAX and CPL are already in the GHCB */ + ghcb_set_rbx(ghcb, regs->bx); + ghcb_set_rcx(ghcb, regs->cx); + ghcb_set_rdx(ghcb, regs->dx); + ghcb_set_rsi(ghcb, regs->si); +} + +static bool kvm_sev_es_hcall_finish(struct ghcb *ghcb, struct pt_regs *regs) +{ + /* No checking of the return state needed */ + return true; +} +#endif + const __initconst struct hypervisor_x86 x86_hyper_kvm = { - .name = "KVM", - .detect = kvm_detect, - .type = X86_HYPER_KVM, - .init.guest_late_init = kvm_guest_init, - .init.x2apic_available = kvm_para_available, - .init.init_platform = kvm_init_platform, + .name = "KVM", + .detect = kvm_detect, + .type = X86_HYPER_KVM, + .init.guest_late_init = kvm_guest_init, + .init.x2apic_available = kvm_para_available, + .init.init_platform = kvm_init_platform, +#if defined(CONFIG_AMD_MEM_ENCRYPT) + .runtime.sev_es_hcall_prepare = kvm_sev_es_hcall_prepare, + .runtime.sev_es_hcall_finish = kvm_sev_es_hcall_finish, +#endif }; static __init int activate_jump_labels(void) -- cgit v1.2.3-58-ga151 From 1a222de8dcfb903d039810b0823570ee0be4e6c6 Mon Sep 17 00:00:00 2001 From: Doug Covelli Date: Mon, 7 Sep 2020 15:16:05 +0200 Subject: x86/vmware: Add VMware-specific handling for VMMCALL under SEV-ES Add VMware-specific handling for #VC faults caused by VMMCALL instructions. Signed-off-by: Doug Covelli Signed-off-by: Tom Lendacky [ jroedel@suse.de: - Adapt to different paravirt interface ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-65-joro@8bytes.org --- arch/x86/kernel/cpu/vmware.c | 50 +++++++++++++++++++++++++++++++++++++++----- 1 file changed, 45 insertions(+), 5 deletions(-) diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 9b6fafa69be9..924571fe5864 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -33,6 +33,7 @@ #include #include #include +#include #undef pr_fmt #define pr_fmt(fmt) "vmware: " fmt @@ -476,10 +477,49 @@ static bool __init vmware_legacy_x2apic_available(void) (eax & (1 << VMWARE_CMD_LEGACY_X2APIC)) != 0; } +#ifdef CONFIG_AMD_MEM_ENCRYPT +static void vmware_sev_es_hcall_prepare(struct ghcb *ghcb, + struct pt_regs *regs) +{ + /* Copy VMWARE specific Hypercall parameters to the GHCB */ + ghcb_set_rip(ghcb, regs->ip); + ghcb_set_rbx(ghcb, regs->bx); + ghcb_set_rcx(ghcb, regs->cx); + ghcb_set_rdx(ghcb, regs->dx); + ghcb_set_rsi(ghcb, regs->si); + ghcb_set_rdi(ghcb, regs->di); + ghcb_set_rbp(ghcb, regs->bp); +} + +static bool vmware_sev_es_hcall_finish(struct ghcb *ghcb, struct pt_regs *regs) +{ + if (!(ghcb_rbx_is_valid(ghcb) && + ghcb_rcx_is_valid(ghcb) && + ghcb_rdx_is_valid(ghcb) && + ghcb_rsi_is_valid(ghcb) && + ghcb_rdi_is_valid(ghcb) && + ghcb_rbp_is_valid(ghcb))) + return false; + + regs->bx = ghcb->save.rbx; + regs->cx = ghcb->save.rcx; + regs->dx = ghcb->save.rdx; + regs->si = ghcb->save.rsi; + regs->di = ghcb->save.rdi; + regs->bp = ghcb->save.rbp; + + return true; +} +#endif + const __initconst struct hypervisor_x86 x86_hyper_vmware = { - .name = "VMware", - .detect = vmware_platform, - .type = X86_HYPER_VMWARE, - .init.init_platform = vmware_platform_setup, - .init.x2apic_available = vmware_legacy_x2apic_available, + .name = "VMware", + .detect = vmware_platform, + .type = X86_HYPER_VMWARE, + .init.init_platform = vmware_platform_setup, + .init.x2apic_available = vmware_legacy_x2apic_available, +#ifdef CONFIG_AMD_MEM_ENCRYPT + .runtime.sev_es_hcall_prepare = vmware_sev_es_hcall_prepare, + .runtime.sev_es_hcall_finish = vmware_sev_es_hcall_finish, +#endif }; -- cgit v1.2.3-58-ga151 From bf5ff276448f64f1f9ef9ffc9e231026e3887d3d Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:16:06 +0200 Subject: x86/realmode: Add SEV-ES specific trampoline entry point The code at the trampoline entry point is executed in real-mode. In real-mode, #VC exceptions can't be handled so anything that might cause such an exception must be avoided. In the standard trampoline entry code this is the WBINVD instruction and the call to verify_cpu(), which are both not needed anyway when running as an SEV-ES guest. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-66-joro@8bytes.org --- arch/x86/include/asm/realmode.h | 3 +++ arch/x86/realmode/rm/header.S | 3 +++ arch/x86/realmode/rm/trampoline_64.S | 20 ++++++++++++++++++++ 3 files changed, 26 insertions(+) diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index 96118fb041b8..4d4d853f6841 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -21,6 +21,9 @@ struct real_mode_header { /* SMP trampoline */ u32 trampoline_start; u32 trampoline_header; +#ifdef CONFIG_AMD_MEM_ENCRYPT + u32 sev_es_trampoline_start; +#endif #ifdef CONFIG_X86_64 u32 trampoline_pgd; #endif diff --git a/arch/x86/realmode/rm/header.S b/arch/x86/realmode/rm/header.S index af04512c02d9..8c1db5bf5d78 100644 --- a/arch/x86/realmode/rm/header.S +++ b/arch/x86/realmode/rm/header.S @@ -20,6 +20,9 @@ SYM_DATA_START(real_mode_header) /* SMP trampoline */ .long pa_trampoline_start .long pa_trampoline_header +#ifdef CONFIG_AMD_MEM_ENCRYPT + .long pa_sev_es_trampoline_start +#endif #ifdef CONFIG_X86_64 .long pa_trampoline_pgd; #endif diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index 251758ed7443..84c5d1b33d10 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -56,6 +56,7 @@ SYM_CODE_START(trampoline_start) testl %eax, %eax # Check for return code jnz no_longmode +.Lswitch_to_protected: /* * GDT tables in non default location kernel can be beyond 16MB and * lgdt will not be able to load the address as in real mode default @@ -80,6 +81,25 @@ no_longmode: jmp no_longmode SYM_CODE_END(trampoline_start) +#ifdef CONFIG_AMD_MEM_ENCRYPT +/* SEV-ES supports non-zero IP for entry points - no alignment needed */ +SYM_CODE_START(sev_es_trampoline_start) + cli # We should be safe anyway + + LJMPW_RM(1f) +1: + mov %cs, %ax # Code and data in the same place + mov %ax, %ds + mov %ax, %es + mov %ax, %ss + + # Setup stack + movl $rm_stack_end, %esp + + jmp .Lswitch_to_protected +SYM_CODE_END(sev_es_trampoline_start) +#endif /* CONFIG_AMD_MEM_ENCRYPT */ + #include "../kernel/verify_cpu.S" .section ".text32","ax" -- cgit v1.2.3-58-ga151 From 8940ac9ced8bc1c48c4e28b0784e3234c9d14469 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 7 Sep 2020 15:16:07 +0200 Subject: x86/realmode: Setup AP jump table As part of the GHCB specification, the booting of APs under SEV-ES requires an AP jump table when transitioning from one layer of code to another (e.g. when going from UEFI to the OS). As a result, each layer that parks an AP must provide the physical address of an AP jump table to the next layer via the hypervisor. Upon booting of the kernel, read the AP jump table address from the hypervisor. Under SEV-ES, APs are started using the INIT-SIPI-SIPI sequence. Before issuing the first SIPI request for an AP, the start CS and IP is programmed into the AP jump table. Upon issuing the SIPI request, the AP will awaken and jump to that start CS:IP address. Signed-off-by: Tom Lendacky [ jroedel@suse.de: - Adapted to different code base - Moved AP table setup from SIPI sending path to real-mode setup code - Fix sparse warnings ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-67-joro@8bytes.org --- arch/x86/include/asm/sev-es.h | 5 +++ arch/x86/include/uapi/asm/svm.h | 3 ++ arch/x86/kernel/sev-es.c | 69 +++++++++++++++++++++++++++++++++++++++++ arch/x86/realmode/init.c | 18 +++++++++-- 4 files changed, 93 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/sev-es.h b/arch/x86/include/asm/sev-es.h index 59176e8c6b81..db88e1c3442d 100644 --- a/arch/x86/include/asm/sev-es.h +++ b/arch/x86/include/asm/sev-es.h @@ -73,6 +73,9 @@ static inline u64 lower_bits(u64 val, unsigned int bits) return (val & mask); } +struct real_mode_header; +enum stack_type; + /* Early IDT entry points for #VC handler */ extern void vc_no_ghcb(void); extern void vc_boot_ghcb(void); @@ -92,9 +95,11 @@ static __always_inline void sev_es_ist_exit(void) if (static_branch_unlikely(&sev_es_enable_key)) __sev_es_ist_exit(); } +extern int sev_es_setup_ap_jump_table(struct real_mode_header *rmh); #else static inline void sev_es_ist_enter(struct pt_regs *regs) { } static inline void sev_es_ist_exit(void) { } +static inline int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { return 0; } #endif #endif diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index 8f36ae021a7f..346b8a7155e8 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -84,6 +84,9 @@ /* SEV-ES software-defined VMGEXIT events */ #define SVM_VMGEXIT_MMIO_READ 0x80000001 #define SVM_VMGEXIT_MMIO_WRITE 0x80000002 +#define SVM_VMGEXIT_AP_JUMP_TABLE 0x80000005 +#define SVM_VMGEXIT_SET_AP_JUMP_TABLE 0 +#define SVM_VMGEXIT_GET_AP_JUMP_TABLE 1 #define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff #define SVM_EXIT_ERR -1 diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 6d89df9f29dc..9ad36ce92b82 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -21,6 +21,7 @@ #include #include +#include #include #include #include @@ -214,6 +215,9 @@ static __always_inline void sev_es_put_ghcb(struct ghcb_state *state) } } +/* Needed in vc_early_forward_exception */ +void do_early_exception(struct pt_regs *regs, int trapnr); + static inline u64 sev_es_rd_ghcb_msr(void) { return __rdmsr(MSR_AMD64_SEV_ES_GHCB); @@ -402,6 +406,71 @@ static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt, /* Include code shared with pre-decompression boot stage */ #include "sev-es-shared.c" +static u64 get_jump_table_addr(void) +{ + struct ghcb_state state; + unsigned long flags; + struct ghcb *ghcb; + u64 ret = 0; + + local_irq_save(flags); + + ghcb = sev_es_get_ghcb(&state); + + vc_ghcb_invalidate(ghcb); + ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_JUMP_TABLE); + ghcb_set_sw_exit_info_1(ghcb, SVM_VMGEXIT_GET_AP_JUMP_TABLE); + ghcb_set_sw_exit_info_2(ghcb, 0); + + sev_es_wr_ghcb_msr(__pa(ghcb)); + VMGEXIT(); + + if (ghcb_sw_exit_info_1_is_valid(ghcb) && + ghcb_sw_exit_info_2_is_valid(ghcb)) + ret = ghcb->save.sw_exit_info_2; + + sev_es_put_ghcb(&state); + + local_irq_restore(flags); + + return ret; +} + +int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) +{ + u16 startup_cs, startup_ip; + phys_addr_t jump_table_pa; + u64 jump_table_addr; + u16 __iomem *jump_table; + + jump_table_addr = get_jump_table_addr(); + + /* On UP guests there is no jump table so this is not a failure */ + if (!jump_table_addr) + return 0; + + /* Check if AP Jump Table is page-aligned */ + if (jump_table_addr & ~PAGE_MASK) + return -EINVAL; + + jump_table_pa = jump_table_addr & PAGE_MASK; + + startup_cs = (u16)(rmh->trampoline_start >> 4); + startup_ip = (u16)(rmh->sev_es_trampoline_start - + rmh->trampoline_start); + + jump_table = ioremap_encrypted(jump_table_pa, PAGE_SIZE); + if (!jump_table) + return -EIO; + + writew(startup_ip, &jump_table[0]); + writew(startup_cs, &jump_table[1]); + + iounmap(jump_table); + + return 0; +} + static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { struct pt_regs *regs = ctxt->regs; diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 1ed1208931e0..3fb9b60be07a 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -9,6 +9,7 @@ #include #include #include +#include struct real_mode_header *real_mode_header; u32 *trampoline_cr4_features; @@ -38,6 +39,19 @@ void __init reserve_real_mode(void) crash_reserve_low_1M(); } +static void sme_sev_setup_real_mode(struct trampoline_header *th) +{ +#ifdef CONFIG_AMD_MEM_ENCRYPT + if (sme_active()) + th->flags |= TH_FLAGS_SME_ACTIVE; + + if (sev_es_active()) { + if (sev_es_setup_ap_jump_table(real_mode_header)) + panic("Failed to get/update SEV-ES AP Jump Table"); + } +#endif +} + static void __init setup_real_mode(void) { u16 real_mode_seg; @@ -104,13 +118,13 @@ static void __init setup_real_mode(void) *trampoline_cr4_features = mmu_cr4_features; trampoline_header->flags = 0; - if (sme_active()) - trampoline_header->flags |= TH_FLAGS_SME_ACTIVE; trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd); trampoline_pgd[0] = trampoline_pgd_entry.pgd; trampoline_pgd[511] = init_top_pgt[511].pgd; #endif + + sme_sev_setup_real_mode(trampoline_header); } /* -- cgit v1.2.3-58-ga151 From 520d030852b4c9babfce9a79d8b5320b6b5545e6 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:16:08 +0200 Subject: x86/smpboot: Load TSS and getcpu GDT entry before loading IDT The IDT on 64-bit contains vectors which use paranoid_entry() and/or IST stacks. To make these vectors work, the TSS and the getcpu GDT entry need to be set up before the IDT is loaded. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-68-joro@8bytes.org --- arch/x86/include/asm/processor.h | 1 + arch/x86/kernel/cpu/common.c | 23 +++++++++++++++++++++++ arch/x86/kernel/smpboot.c | 2 +- 3 files changed, 25 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 97143d87994c..615dd440bed8 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -696,6 +696,7 @@ extern void load_direct_gdt(int); extern void load_fixmap_gdt(int); extern void load_percpu_segment(int); extern void cpu_init(void); +extern void cpu_init_exception_handling(void); extern void cr4_init(void); static inline unsigned long get_debugctlmsr(void) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 81fba4d4a242..beffea22e2af 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1862,6 +1862,29 @@ static inline void tss_setup_io_bitmap(struct tss_struct *tss) #endif } +/* + * Setup everything needed to handle exceptions from the IDT, including the IST + * exceptions which use paranoid_entry(). + */ +void cpu_init_exception_handling(void) +{ + struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw); + int cpu = raw_smp_processor_id(); + + /* paranoid_entry() gets the CPU number from the GDT */ + setup_getcpu(cpu); + + /* IST vectors need TSS to be set up. */ + tss_setup_ist(tss); + tss_setup_io_bitmap(tss); + set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); + + load_TR_desc(); + + /* Finally load the IDT */ + load_current_idt(); +} + /* * cpu_init() initializes state that is per-CPU. Some data is already * initialized (naturally) in the bootstrap process, such as the GDT diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index f5ef689dd62a..de776b2e6046 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -227,7 +227,7 @@ static void notrace start_secondary(void *unused) load_cr3(swapper_pg_dir); __flush_tlb_all(); #endif - load_current_idt(); + cpu_init_exception_handling(); cpu_init(); x86_cpuinit.early_percpu_clock_init(); preempt_disable(); -- cgit v1.2.3-58-ga151 From 3ecacdbd23956a549d93023f86adc87b4a9d6520 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:16:09 +0200 Subject: x86/head/64: Don't call verify_cpu() on starting APs The APs are not ready to handle exceptions when verify_cpu() is called in secondary_startup_64(). Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20200907131613.12703-69-joro@8bytes.org --- arch/x86/include/asm/realmode.h | 1 + arch/x86/kernel/head_64.S | 12 ++++++++++++ arch/x86/realmode/init.c | 6 ++++++ 3 files changed, 19 insertions(+) diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index 4d4d853f6841..5db5d083c873 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -72,6 +72,7 @@ extern unsigned char startup_32_smp[]; extern unsigned char boot_gdt[]; #else extern unsigned char secondary_startup_64[]; +extern unsigned char secondary_startup_64_no_verify[]; #endif static inline size_t real_mode_size_needed(void) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 1a71d0d4d575..7eb2a1c87969 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -125,6 +125,18 @@ SYM_CODE_START(secondary_startup_64) /* Sanitize CPU configuration */ call verify_cpu + /* + * The secondary_startup_64_no_verify entry point is only used by + * SEV-ES guests. In those guests the call to verify_cpu() would cause + * #VC exceptions which can not be handled at this stage of secondary + * CPU bringup. + * + * All non SEV-ES systems, especially Intel systems, need to execute + * verify_cpu() above to make sure NX is enabled. + */ +SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) + UNWIND_HINT_EMPTY + /* * Retrieve the modifier (SME encryption mask if SME is active) to be * added to the initial pgdir entry that will be programmed into CR3. diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 3fb9b60be07a..22fda7d99159 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -46,6 +46,12 @@ static void sme_sev_setup_real_mode(struct trampoline_header *th) th->flags |= TH_FLAGS_SME_ACTIVE; if (sev_es_active()) { + /* + * Skip the call to verify_cpu() in secondary_startup_64 as it + * will cause #VC exceptions when the AP can't handle them yet. + */ + th->start = (u64) secondary_startup_64_no_verify; + if (sev_es_setup_ap_jump_table(real_mode_header)) panic("Failed to get/update SEV-ES AP Jump Table"); } -- cgit v1.2.3-58-ga151 From 094794f59720d7e877a1eeb372ecedeed6b441ab Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:16:10 +0200 Subject: x86/sev-es: Support CPU offline/online Add a play_dead handler when running under SEV-ES. This is needed because the hypervisor can't deliver an SIPI request to restart the AP. Instead, the kernel has to issue a VMGEXIT to halt the VCPU until the hypervisor wakes it up again. Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-70-joro@8bytes.org --- arch/x86/include/uapi/asm/svm.h | 1 + arch/x86/kernel/sev-es.c | 63 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 64 insertions(+) diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index 346b8a7155e8..c1dcf3e114e4 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -84,6 +84,7 @@ /* SEV-ES software-defined VMGEXIT events */ #define SVM_VMGEXIT_MMIO_READ 0x80000001 #define SVM_VMGEXIT_MMIO_WRITE 0x80000002 +#define SVM_VMGEXIT_AP_HLT_LOOP 0x80000004 #define SVM_VMGEXIT_AP_JUMP_TABLE 0x80000005 #define SVM_VMGEXIT_SET_AP_JUMP_TABLE 0 #define SVM_VMGEXIT_GET_AP_JUMP_TABLE 1 diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 9ad36ce92b82..d1bcd0dca583 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -29,6 +29,8 @@ #include #include #include +#include +#include #define DR7_RESET_VALUE 0x400 @@ -518,6 +520,65 @@ static bool __init sev_es_setup_ghcb(void) return true; } +#ifdef CONFIG_HOTPLUG_CPU +static void sev_es_ap_hlt_loop(void) +{ + struct ghcb_state state; + struct ghcb *ghcb; + + ghcb = sev_es_get_ghcb(&state); + + while (true) { + vc_ghcb_invalidate(ghcb); + ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_HLT_LOOP); + ghcb_set_sw_exit_info_1(ghcb, 0); + ghcb_set_sw_exit_info_2(ghcb, 0); + + sev_es_wr_ghcb_msr(__pa(ghcb)); + VMGEXIT(); + + /* Wakeup signal? */ + if (ghcb_sw_exit_info_2_is_valid(ghcb) && + ghcb->save.sw_exit_info_2) + break; + } + + sev_es_put_ghcb(&state); +} + +/* + * Play_dead handler when running under SEV-ES. This is needed because + * the hypervisor can't deliver an SIPI request to restart the AP. + * Instead the kernel has to issue a VMGEXIT to halt the VCPU until the + * hypervisor wakes it up again. + */ +static void sev_es_play_dead(void) +{ + play_dead_common(); + + /* IRQs now disabled */ + + sev_es_ap_hlt_loop(); + + /* + * If we get here, the VCPU was woken up again. Jump to CPU + * startup code to get it back online. + */ + start_cpu0(); +} +#else /* CONFIG_HOTPLUG_CPU */ +#define sev_es_play_dead native_play_dead +#endif /* CONFIG_HOTPLUG_CPU */ + +#ifdef CONFIG_SMP +static void __init sev_es_setup_play_dead(void) +{ + smp_ops.play_dead = sev_es_play_dead; +} +#else +static inline void sev_es_setup_play_dead(void) { } +#endif + static void __init alloc_runtime_data(int cpu) { struct sev_es_runtime_data *data; @@ -566,6 +627,8 @@ void __init sev_es_init_vc_handling(void) setup_vc_stacks(cpu); } + sev_es_setup_play_dead(); + /* Secondary CPUs use the runtime #VC handler */ initial_vc_handler = (unsigned long)safe_stack_exc_vmm_communication; } -- cgit v1.2.3-58-ga151 From 4ca68e023b11e4d5908bf9ee326fab01111d77d5 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 7 Sep 2020 15:16:11 +0200 Subject: x86/sev-es: Handle NMI State When running under SEV-ES, the kernel has to tell the hypervisor when to open the NMI window again after an NMI was injected. This is done with an NMI-complete message to the hypervisor. Add code to the kernel's NMI handler to send this message right at the beginning of do_nmi(). This always allows nesting NMIs. [ bp: Mark __sev_es_nmi_complete() noinstr: vmlinux.o: warning: objtool: exc_nmi()+0x17: call to __sev_es_nmi_complete() leaves .noinstr.text section While at it, use __pa_nodebug() for the same reason due to CONFIG_DEBUG_VIRTUAL=y: vmlinux.o: warning: objtool: __sev_es_nmi_complete()+0xd9: call to __phys_addr() leaves .noinstr.text section ] Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200907131613.12703-71-joro@8bytes.org --- arch/x86/include/asm/sev-es.h | 7 +++++++ arch/x86/include/uapi/asm/svm.h | 1 + arch/x86/kernel/nmi.c | 6 ++++++ arch/x86/kernel/sev-es.c | 18 ++++++++++++++++++ 4 files changed, 32 insertions(+) diff --git a/arch/x86/include/asm/sev-es.h b/arch/x86/include/asm/sev-es.h index db88e1c3442d..e919f09ae33c 100644 --- a/arch/x86/include/asm/sev-es.h +++ b/arch/x86/include/asm/sev-es.h @@ -96,10 +96,17 @@ static __always_inline void sev_es_ist_exit(void) __sev_es_ist_exit(); } extern int sev_es_setup_ap_jump_table(struct real_mode_header *rmh); +extern void __sev_es_nmi_complete(void); +static __always_inline void sev_es_nmi_complete(void) +{ + if (static_branch_unlikely(&sev_es_enable_key)) + __sev_es_nmi_complete(); +} #else static inline void sev_es_ist_enter(struct pt_regs *regs) { } static inline void sev_es_ist_exit(void) { } static inline int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { return 0; } +static inline void sev_es_nmi_complete(void) { } #endif #endif diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index c1dcf3e114e4..a7a3403645e5 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -84,6 +84,7 @@ /* SEV-ES software-defined VMGEXIT events */ #define SVM_VMGEXIT_MMIO_READ 0x80000001 #define SVM_VMGEXIT_MMIO_WRITE 0x80000002 +#define SVM_VMGEXIT_NMI_COMPLETE 0x80000003 #define SVM_VMGEXIT_AP_HLT_LOOP 0x80000004 #define SVM_VMGEXIT_AP_JUMP_TABLE 0x80000005 #define SVM_VMGEXIT_SET_AP_JUMP_TABLE 0 diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 4c89c4d3cb82..56b64d779856 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -478,6 +478,12 @@ DEFINE_IDTENTRY_RAW(exc_nmi) { bool irq_state; + /* + * Re-enable NMIs right here when running as an SEV-ES guest. This might + * cause nested NMIs, but those can be handled safely. + */ + sev_es_nmi_complete(); + if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id())) return; diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index d1bcd0dca583..b6518e96dedb 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -408,6 +408,24 @@ static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt, /* Include code shared with pre-decompression boot stage */ #include "sev-es-shared.c" +void noinstr __sev_es_nmi_complete(void) +{ + struct ghcb_state state; + struct ghcb *ghcb; + + ghcb = sev_es_get_ghcb(&state); + + vc_ghcb_invalidate(ghcb); + ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_NMI_COMPLETE); + ghcb_set_sw_exit_info_1(ghcb, 0); + ghcb_set_sw_exit_info_2(ghcb, 0); + + sev_es_wr_ghcb_msr(__pa_nodebug(ghcb)); + VMGEXIT(); + + sev_es_put_ghcb(&state); +} + static u64 get_jump_table_addr(void) { struct ghcb_state state; -- cgit v1.2.3-58-ga151 From 39336f4ffb2478ad384075cf4ba7ef2e5db2bbd7 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 7 Sep 2020 15:16:12 +0200 Subject: x86/efi: Add GHCB mappings when SEV-ES is active Calling down to EFI runtime services can result in the firmware performing VMGEXIT calls. The firmware is likely to use the GHCB of the OS (e.g., for setting EFI variables), so each GHCB in the system needs to be identity-mapped in the EFI page tables, as unencrypted, to avoid page faults. Signed-off-by: Tom Lendacky [ jroedel@suse.de: Moved GHCB mapping loop to sev-es.c ] Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Acked-by: Ard Biesheuvel Link: https://lkml.kernel.org/r/20200907131613.12703-72-joro@8bytes.org --- arch/x86/boot/compressed/sev-es.c | 1 + arch/x86/include/asm/sev-es.h | 2 ++ arch/x86/kernel/sev-es.c | 30 ++++++++++++++++++++++++++++++ arch/x86/platform/efi/efi_64.c | 10 ++++++++++ 4 files changed, 43 insertions(+) diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c index 5f15e5864e0c..2a6c7c375244 100644 --- a/arch/x86/boot/compressed/sev-es.c +++ b/arch/x86/boot/compressed/sev-es.c @@ -12,6 +12,7 @@ */ #include "misc.h" +#include #include #include #include diff --git a/arch/x86/include/asm/sev-es.h b/arch/x86/include/asm/sev-es.h index e919f09ae33c..cf1d957c7091 100644 --- a/arch/x86/include/asm/sev-es.h +++ b/arch/x86/include/asm/sev-es.h @@ -102,11 +102,13 @@ static __always_inline void sev_es_nmi_complete(void) if (static_branch_unlikely(&sev_es_enable_key)) __sev_es_nmi_complete(); } +extern int __init sev_es_efi_map_ghcbs(pgd_t *pgd); #else static inline void sev_es_ist_enter(struct pt_regs *regs) { } static inline void sev_es_ist_exit(void) { } static inline int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { return 0; } static inline void sev_es_nmi_complete(void) { } +static inline int sev_es_efi_map_ghcbs(pgd_t *pgd) { return 0; } #endif #endif diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index b6518e96dedb..8cac9f80bfc3 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -491,6 +491,36 @@ int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) return 0; } +/* + * This is needed by the OVMF UEFI firmware which will use whatever it finds in + * the GHCB MSR as its GHCB to talk to the hypervisor. So make sure the per-cpu + * runtime GHCBs used by the kernel are also mapped in the EFI page-table. + */ +int __init sev_es_efi_map_ghcbs(pgd_t *pgd) +{ + struct sev_es_runtime_data *data; + unsigned long address, pflags; + int cpu; + u64 pfn; + + if (!sev_es_active()) + return 0; + + pflags = _PAGE_NX | _PAGE_RW; + + for_each_possible_cpu(cpu) { + data = per_cpu(runtime_data, cpu); + + address = __pa(&data->ghcb_page); + pfn = address >> PAGE_SHIFT; + + if (kernel_map_pages_in_pgd(pgd, pfn, address, 1, pflags)) + return 1; + } + + return 0; +} + static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { struct pt_regs *regs = ctxt->regs; diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 6af4da1149ba..8f5759df7776 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -47,6 +47,7 @@ #include #include #include +#include /* * We allocate runtime services regions top-down, starting from -4G, i.e. @@ -229,6 +230,15 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) return 1; } + /* + * When SEV-ES is active, the GHCB as set by the kernel will be used + * by firmware. Create a 1:1 unencrypted mapping for each GHCB. + */ + if (sev_es_efi_map_ghcbs(pgd)) { + pr_err("Failed to create 1:1 mapping for the GHCBs!\n"); + return 1; + } + /* * When making calls to the firmware everything needs to be 1:1 * mapped and addressable with 32-bit pointers. Map the kernel -- cgit v1.2.3-58-ga151 From f5ed777586e08e09c4b6f1e87161a145ee1431cf Mon Sep 17 00:00:00 2001 From: Martin Radev Date: Mon, 7 Sep 2020 15:16:13 +0200 Subject: x86/sev-es: Check required CPU features for SEV-ES Make sure the machine supports RDRAND, otherwise there is no trusted source of randomness in the system. To also check this in the pre-decompression stage, make has_cpuflag() not depend on CONFIG_RANDOMIZE_BASE anymore. Signed-off-by: Martin Radev Signed-off-by: Joerg Roedel Signed-off-by: Borislav Petkov Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20200907131613.12703-73-joro@8bytes.org --- arch/x86/boot/compressed/cpuflags.c | 4 ---- arch/x86/boot/compressed/misc.h | 5 +++-- arch/x86/boot/compressed/sev-es.c | 3 +++ arch/x86/kernel/sev-es-shared.c | 15 +++++++++++++++ arch/x86/kernel/sev-es.c | 3 +++ 5 files changed, 24 insertions(+), 6 deletions(-) diff --git a/arch/x86/boot/compressed/cpuflags.c b/arch/x86/boot/compressed/cpuflags.c index 6448a8196d32..0cc1323896d1 100644 --- a/arch/x86/boot/compressed/cpuflags.c +++ b/arch/x86/boot/compressed/cpuflags.c @@ -1,6 +1,4 @@ // SPDX-License-Identifier: GPL-2.0 -#ifdef CONFIG_RANDOMIZE_BASE - #include "../cpuflags.c" bool has_cpuflag(int flag) @@ -9,5 +7,3 @@ bool has_cpuflag(int flag) return test_bit(flag, cpu.flags); } - -#endif diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index c0e0ffeee50a..6d31f1b4c4d1 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -85,8 +85,6 @@ void choose_random_location(unsigned long input, unsigned long *output, unsigned long output_size, unsigned long *virt_addr); -/* cpuflags.c */ -bool has_cpuflag(int flag); #else static inline void choose_random_location(unsigned long input, unsigned long input_size, @@ -97,6 +95,9 @@ static inline void choose_random_location(unsigned long input, } #endif +/* cpuflags.c */ +bool has_cpuflag(int flag); + #ifdef CONFIG_X86_64 extern int set_page_decrypted(unsigned long address); extern int set_page_encrypted(unsigned long address); diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c index 2a6c7c375244..954cb2702e23 100644 --- a/arch/x86/boot/compressed/sev-es.c +++ b/arch/x86/boot/compressed/sev-es.c @@ -145,6 +145,9 @@ void sev_es_shutdown_ghcb(void) if (!boot_ghcb) return; + if (!sev_es_check_cpu_features()) + error("SEV-ES CPU Features missing."); + /* * GHCB Page must be flushed from the cache and mapped encrypted again. * Otherwise the running kernel will see strange cache effects when diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index 4be8af2f9c57..5f83ccaab877 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -9,6 +9,21 @@ * and is included directly into both code-bases. */ +#ifndef __BOOT_COMPRESSED +#define error(v) pr_err(v) +#define has_cpuflag(f) boot_cpu_has(f) +#endif + +static bool __init sev_es_check_cpu_features(void) +{ + if (!has_cpuflag(X86_FEATURE_RDRAND)) { + error("RDRAND instruction not supported - no trusted source of randomness available\n"); + return false; + } + + return true; +} + static void sev_es_terminate(unsigned int reason) { u64 val = GHCB_SEV_TERMINATE; diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 8cac9f80bfc3..6fcfdd32769f 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -665,6 +665,9 @@ void __init sev_es_init_vc_handling(void) if (!sev_es_active()) return; + if (!sev_es_check_cpu_features()) + panic("SEV-ES CPU Features missing"); + /* Enable SEV-ES special handling */ static_branch_enable(&sev_es_enable_key); -- cgit v1.2.3-58-ga151 From 0ddfb1cf3b6b07c97cff16ea69931d986f9622ee Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Fri, 25 Sep 2020 08:38:26 -0500 Subject: x86/sev-es: Use GHCB accessor for setting the MMIO scratch buffer Use ghcb_set_sw_scratch() to set the GHCB scratch field, which will also set the corresponding bit in the GHCB valid_bitmap field to denote that sw_scratch is actually valid. Signed-off-by: Tom Lendacky Signed-off-by: Borislav Petkov Reviewed-by: Joerg Roedel Link: https://lkml.kernel.org/r/ba84deabdf44a7a880454fb351d189c6ad79d4ba.1601041106.git.thomas.lendacky@amd.com --- arch/x86/kernel/sev-es.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 6fcfdd32769f..4a96726fbaf8 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -751,7 +751,7 @@ static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt, /* Can never be greater than 8 */ exit_info_2 = bytes; - ghcb->save.sw_scratch = ghcb_pa + offsetof(struct ghcb, shared_buffer); + ghcb_set_sw_scratch(ghcb, ghcb_pa + offsetof(struct ghcb, shared_buffer)); return sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, exit_info_1, exit_info_2); } -- cgit v1.2.3-58-ga151