linux-stable/arch/x86/kernel/sev-shared.c

541 lines
12 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* AMD Encrypted Register State Support
*
* Author: Joerg Roedel <jroedel@suse.de>
*
* 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.
*/
#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 __noreturn sev_es_terminate(unsigned int reason)
{
u64 val = GHCB_MSR_TERM_REQ;
/*
* Tell the hypervisor what went wrong - only reason-set 0 is
* currently supported.
*/
val |= GHCB_SEV_TERM_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_MSR_SEV_INFO_REQ);
VMGEXIT();
val = sev_es_rd_ghcb_msr();
if (GHCB_MSR_INFO(val) != GHCB_MSR_SEV_INFO_RESP)
return false;
if (GHCB_MSR_PROTO_MAX(val) < GHCB_PROTO_OUR ||
GHCB_MSR_PROTO_MIN(val) > GHCB_PROTO_OUR)
return false;
return true;
}
static __always_inline void vc_ghcb_invalidate(struct ghcb *ghcb)
{
ghcb->save.sw_exit_code = 0;
__builtin_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 verify_exception_info(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
{
u32 ret;
ret = ghcb->save.sw_exit_info_1 & GENMASK_ULL(31, 0);
if (!ret)
return ES_OK;
if (ret == 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;
return ES_EXCEPTION;
}
}
return ES_VMM_ERROR;
}
enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr,
struct es_em_ctxt *ctxt, u64 exit_code,
u64 exit_info_1, u64 exit_info_2)
{
/* 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);
/*
* Hyper-V unenlightened guests use a paravisor for communicating and
* GHCB pages are being allocated and set up by that paravisor. Linux
* should not change the GHCB page's physical address.
*/
if (set_ghcb_msr)
sev_es_wr_ghcb_msr(__pa(ghcb));
VMGEXIT();
return verify_exception_info(ghcb, ctxt);
}
/*
* 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_RESP_CODE(val) != GHCB_MSR_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_RESP_CODE(val) != GHCB_MSR_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_RESP_CODE(val) != GHCB_MSR_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_RESP_CODE(val) != GHCB_MSR_CPUID_RESP)
goto fail;
regs->dx = val >> 32;
/*
* This is a VC handler and the #VC is only raised when SEV-ES is
* active, which means SEV must be active too. Do sanity checks on the
* CPUID results to make sure the hypervisor does not trick the kernel
* into the no-sev path. This could map sensitive data unencrypted and
* make it accessible to the hypervisor.
*
* In particular, check for:
* - Availability of CPUID leaf 0x8000001f
* - SEV CPUID bit.
*
* The hypervisor might still report the wrong C-bit position, but this
* can't be checked here.
*/
x86/sev: Do not require Hypervisor CPUID bit for SEV guests A malicious hypervisor could disable the CPUID intercept for an SEV or SEV-ES guest and trick it into the no-SEV boot path, where it could potentially reveal secrets. This is not an issue for SEV-SNP guests, as the CPUID intercept can't be disabled for those. Remove the Hypervisor CPUID bit check from the SEV detection code to protect against this kind of attack and add a Hypervisor bit equals zero check to the SME detection path to prevent non-encrypted guests from trying to enable SME. This handles the following cases: 1) SEV(-ES) guest where CPUID intercept is disabled. The guest will still see leaf 0x8000001f and the SEV bit. It can retrieve the C-bit and boot normally. 2) Non-encrypted guests with intercepted CPUID will check the SEV_STATUS MSR and find it 0 and will try to enable SME. This will fail when the guest finds MSR_K8_SYSCFG to be zero, as it is emulated by KVM. But we can't rely on that, as there might be other hypervisors which return this MSR with bit 23 set. The Hypervisor bit check will prevent that the guest tries to enable SME in this case. 3) Non-encrypted guests on SEV capable hosts with CPUID intercept disabled (by a malicious hypervisor) will try to boot into the SME path. This will fail, but it is also not considered a problem because non-encrypted guests have no protection against the hypervisor anyway. [ bp: s/non-SEV/non-encrypted/g ] Signed-off-by: Joerg Roedel <jroedel@suse.de> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Tom Lendacky <thomas.lendacky@amd.com> Link: https://lkml.kernel.org/r/20210312123824.306-3-joro@8bytes.org
2021-03-12 12:38:18 +00:00
if (fn == 0x80000000 && (regs->ax < 0x8000001f))
/* SEV leaf check */
goto fail;
else if ((fn == 0x8000001f && !(regs->ax & BIT(1))))
/* SEV bit */
goto fail;
/* Skip over the CPUID two-byte opcode */
regs->ip += 2;
return;
fail:
/* Terminate the guest */
sev_es_terminate(GHCB_SEV_ES_GEN_REQ);
}
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;
}
#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 |= (u8)insn->immediate.value << 16;
break;
/* OUT immediate opcodes */
case 0xe6:
case 0xe7:
*exitinfo |= IOIO_TYPE_OUT;
*exitinfo |= (u8)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, true, 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, true, 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;
}
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, true, 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;
}
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, true, 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;
}