diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-14 10:21:34 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-14 10:21:34 -0700 |
commit | da9803dfd3955bd2f9909d55e23f188ad76dbe58 (patch) | |
tree | 9e4ea42559f82bf46340d91fa3312ea555686cf6 /arch/x86/boot/compressed/sev-es.c | |
parent | 6873139ed078bfe0341d4cbb69e5af1b323bf532 (diff) | |
parent | 0ddfb1cf3b6b07c97cff16ea69931d986f9622ee (diff) |
Merge tag 'x86_seves_for_v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 SEV-ES support from Borislav Petkov:
"SEV-ES enhances the current guest memory encryption support called SEV
by also encrypting the guest register state, making the registers
inaccessible to the hypervisor by en-/decrypting them on world
switches. Thus, it adds additional protection to Linux guests against
exfiltration, control flow and rollback attacks.
With SEV-ES, the guest is in full control of what registers the
hypervisor can access. This is provided by a guest-host exchange
mechanism based on a new exception vector called VMM Communication
Exception (#VC), a new instruction called VMGEXIT and a shared
Guest-Host Communication Block which is a decrypted page shared
between the guest and the hypervisor.
Intercepts to the hypervisor become #VC exceptions in an SEV-ES guest
so in order for that exception mechanism to work, the early x86 init
code needed to be made able to handle exceptions, which, in itself,
brings a bunch of very nice cleanups and improvements to the early
boot code like an early page fault handler, allowing for on-demand
building of the identity mapping. With that, !KASLR configurations do
not use the EFI page table anymore but switch to a kernel-controlled
one.
The main part of this series adds the support for that new exchange
mechanism. The goal has been to keep this as much as possibly separate
from the core x86 code by concentrating the machinery in two
SEV-ES-specific files:
arch/x86/kernel/sev-es-shared.c
arch/x86/kernel/sev-es.c
Other interaction with core x86 code has been kept at minimum and
behind static keys to minimize the performance impact on !SEV-ES
setups.
Work by Joerg Roedel and Thomas Lendacky and others"
* tag 'x86_seves_for_v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (73 commits)
x86/sev-es: Use GHCB accessor for setting the MMIO scratch buffer
x86/sev-es: Check required CPU features for SEV-ES
x86/efi: Add GHCB mappings when SEV-ES is active
x86/sev-es: Handle NMI State
x86/sev-es: Support CPU offline/online
x86/head/64: Don't call verify_cpu() on starting APs
x86/smpboot: Load TSS and getcpu GDT entry before loading IDT
x86/realmode: Setup AP jump table
x86/realmode: Add SEV-ES specific trampoline entry point
x86/vmware: Add VMware-specific handling for VMMCALL under SEV-ES
x86/kvm: Add KVM-specific VMMCALL handling under SEV-ES
x86/paravirt: Allow hypervisor-specific VMMCALL handling under SEV-ES
x86/sev-es: Handle #DB Events
x86/sev-es: Handle #AC Events
x86/sev-es: Handle VMMCALL Events
x86/sev-es: Handle MWAIT/MWAITX Events
x86/sev-es: Handle MONITOR/MONITORX Events
x86/sev-es: Handle INVD Events
x86/sev-es: Handle RDPMC Events
x86/sev-es: Handle RDTSC(P) Events
...
Diffstat (limited to 'arch/x86/boot/compressed/sev-es.c')
-rw-r--r-- | arch/x86/boot/compressed/sev-es.c | 214 |
1 files changed, 214 insertions, 0 deletions
diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c new file mode 100644 index 000000000000..954cb2702e23 --- /dev/null +++ b/arch/x86/boot/compressed/sev-es.c @@ -0,0 +1,214 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * AMD Encrypted Register State Support + * + * Author: Joerg Roedel <jroedel@suse.de> + */ + +/* + * 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 <asm/pgtable_types.h> +#include <asm/sev-es.h> +#include <asm/trapnr.h> +#include <asm/trap_pf.h> +#include <asm/msr-index.h> +#include <asm/fpu/xcr.h> +#include <asm/ptrace.h> +#include <asm/svm.h> + +#include "error.h" + +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; + + 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"); +} + +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; + + 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 + * trying to use that page. + */ + 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) +{ + 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) { + 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; + case SVM_EXIT_CPUID: + result = vc_handle_cpuid(boot_ghcb, &ctxt); + break; + 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"); + } +} |