| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20220519180739.2xnq7mjpa6hzcbsn@black.fi.intel.com>
Date: Thu, 19 May 2022 21:07:39 +0300
From: "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
To: Dave Hansen <dave.hansen@...el.com>
Cc: seanjc@...gle.com, tglx@...utronix.de, mingo@...hat.com,
bp@...en8.de, luto@...nel.org, peterz@...radead.org,
sathyanarayanan.kuppuswamy@...ux.intel.com, ak@...ux.intel.com,
dan.j.williams@...el.com, david@...hat.com, hpa@...or.com,
thomas.lendacky@....com, x86@...nel.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH] x86/tdx: Handle load_unaligned_zeropad() page-cross to a
shared page
On Tue, May 17, 2022 at 03:16:42PM -0700, Dave Hansen wrote:
> See? Now everybody that goes and writes a new #VE exception helper has
> a chance of actually getting this right. As it stands, if someone adds
> one more of these, they'll probably get random behavior. This way, they
> actually have to choose. They _might_ even go looking at the SDM.
Okay. See below. Does it match what you had in mind?
If it is okay. I will do proper patches.
BTW, I found a bug in tdx_early_handle_ve(). It didn't update RIP.
I don't know how it happend. Maybe got lost on the way upstream.
diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index 9955b5a89df8..d2635ac52d9b 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -123,7 +123,7 @@ static u64 __cpuidle __halt(const bool irq_disabled, const bool do_sti)
return __tdx_hypercall(&args, do_sti ? TDX_HCALL_ISSUE_STI : 0);
}
-static bool handle_halt(void)
+static int handle_halt(struct ve_info *ve)
{
/*
* Since non safe halt is mainly used in CPU offlining
@@ -134,9 +134,9 @@ static bool handle_halt(void)
const bool do_sti = false;
if (__halt(irq_disabled, do_sti))
- return false;
+ return -EIO;
- return true;
+ return ve->instr_len;
}
void __cpuidle tdx_safe_halt(void)
@@ -156,7 +156,7 @@ void __cpuidle tdx_safe_halt(void)
WARN_ONCE(1, "HLT instruction emulation failed\n");
}
-static bool read_msr(struct pt_regs *regs)
+static int read_msr(struct pt_regs *regs, struct ve_info *ve)
{
struct tdx_hypercall_args args = {
.r10 = TDX_HYPERCALL_STANDARD,
@@ -170,14 +170,14 @@ static bool read_msr(struct pt_regs *regs)
* (GHCI), section titled "TDG.VP.VMCALL<Instruction.RDMSR>".
*/
if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT))
- return false;
+ return -EIO;
regs->ax = lower_32_bits(args.r11);
regs->dx = upper_32_bits(args.r11);
- return true;
+ return ve->instr_len;
}
-static bool write_msr(struct pt_regs *regs)
+static int write_msr(struct pt_regs *regs, struct ve_info *ve)
{
struct tdx_hypercall_args args = {
.r10 = TDX_HYPERCALL_STANDARD,
@@ -191,10 +191,13 @@ static bool write_msr(struct pt_regs *regs)
* can be found in TDX Guest-Host-Communication Interface
* (GHCI) section titled "TDG.VP.VMCALL<Instruction.WRMSR>".
*/
- return !__tdx_hypercall(&args, 0);
+ if (__tdx_hypercall(&args, 0))
+ return -EIO;
+
+ return ve->instr_len;
}
-static bool handle_cpuid(struct pt_regs *regs)
+static int handle_cpuid(struct pt_regs *regs, struct ve_info *ve)
{
struct tdx_hypercall_args args = {
.r10 = TDX_HYPERCALL_STANDARD,
@@ -212,7 +215,7 @@ static bool handle_cpuid(struct pt_regs *regs)
*/
if (regs->ax < 0x40000000 || regs->ax > 0x4FFFFFFF) {
regs->ax = regs->bx = regs->cx = regs->dx = 0;
- return true;
+ return ve->instr_len;
}
/*
@@ -221,7 +224,7 @@ static bool handle_cpuid(struct pt_regs *regs)
* (GHCI), section titled "VP.VMCALL<Instruction.CPUID>".
*/
if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT))
- return false;
+ return -EIO;
/*
* As per TDX GHCI CPUID ABI, r12-r15 registers contain contents of
@@ -233,7 +236,7 @@ static bool handle_cpuid(struct pt_regs *regs)
regs->cx = args.r14;
regs->dx = args.r15;
- return true;
+ return ve->instr_len;
}
static bool mmio_read(int size, unsigned long addr, unsigned long *val)
@@ -259,7 +262,7 @@ static bool mmio_write(int size, unsigned long addr, unsigned long val)
EPT_WRITE, addr, val);
}
-static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve)
+static int handle_mmio(struct pt_regs *regs, struct ve_info *ve)
{
char buffer[MAX_INSN_SIZE];
unsigned long *reg, val;
@@ -270,7 +273,7 @@ static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve)
/* Only in-kernel MMIO is supported */
if (WARN_ON_ONCE(user_mode(regs)))
- return false;
+ return -EFAULT;
/*
* load_unaligned_zeropad() relies on exception fixups in case of the
@@ -287,37 +290,37 @@ static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve)
*/
if (fixup_exception(regs, X86_TRAP_VE, 0, ve->gla)) {
/* regs->ip is adjusted by fixup_exception() */
- ve->instr_len = 0;
-
- return true;
+ return 0;
}
if (copy_from_kernel_nofault(buffer, (void *)regs->ip, MAX_INSN_SIZE))
- return false;
+ return -EFAULT;
if (insn_decode(&insn, buffer, MAX_INSN_SIZE, INSN_MODE_64))
- return false;
+ return -EINVAL;
mmio = insn_decode_mmio(&insn, &size);
if (WARN_ON_ONCE(mmio == MMIO_DECODE_FAILED))
- return false;
+ return -EINVAL;
if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) {
reg = insn_get_modrm_reg_ptr(&insn, regs);
if (!reg)
- return false;
+ return -EINVAL;
}
- ve->instr_len = insn.length;
-
/* Handle writes first */
switch (mmio) {
case MMIO_WRITE:
memcpy(&val, reg, size);
- return mmio_write(size, ve->gpa, val);
+ if (!mmio_write(size, ve->gpa, val))
+ return -EIO;
+ return insn.length;
case MMIO_WRITE_IMM:
val = insn.immediate.value;
- return mmio_write(size, ve->gpa, val);
+ if (!mmio_write(size, ve->gpa, val))
+ return -EIO;
+ return insn.length;
case MMIO_READ:
case MMIO_READ_ZERO_EXTEND:
case MMIO_READ_SIGN_EXTEND:
@@ -330,15 +333,15 @@ static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve)
* decoded or handled properly. It was likely not using io.h
* helpers or accessed MMIO accidentally.
*/
- return false;
+ return -EINVAL;
default:
WARN_ONCE(1, "Unknown insn_decode_mmio() decode value?");
- return false;
+ return -EINVAL;
}
/* Handle reads */
if (!mmio_read(size, ve->gpa, &val))
- return false;
+ return -EIO;
switch (mmio) {
case MMIO_READ:
@@ -360,13 +363,13 @@ static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve)
default:
/* All other cases has to be covered with the first switch() */
WARN_ON_ONCE(1);
- return false;
+ return -EINVAL;
}
if (extend_size)
memset(reg, extend_val, extend_size);
memcpy(reg, &val, size);
- return true;
+ return insn.length;
}
static bool handle_in(struct pt_regs *regs, int size, int port)
@@ -417,13 +420,14 @@ static bool handle_out(struct pt_regs *regs, int size, int port)
*
* Return True on success or False on failure.
*/
-static bool handle_io(struct pt_regs *regs, u32 exit_qual)
+static int handle_io(struct pt_regs *regs, struct ve_info *ve)
{
+ u32 exit_qual = ve->exit_qual;
int size, port;
- bool in;
+ bool in, ret;
if (VE_IS_IO_STRING(exit_qual))
- return false;
+ return -EIO;
in = VE_IS_IO_IN(exit_qual);
size = VE_GET_IO_SIZE(exit_qual);
@@ -431,9 +435,13 @@ static bool handle_io(struct pt_regs *regs, u32 exit_qual)
if (in)
- return handle_in(regs, size, port);
+ ret = handle_in(regs, size, port);
else
- return handle_out(regs, size, port);
+ ret = handle_out(regs, size, port);
+ if (!ret)
+ return -EIO;
+
+ return ve->instr_len;
}
/*
@@ -443,13 +451,19 @@ static bool handle_io(struct pt_regs *regs, u32 exit_qual)
__init bool tdx_early_handle_ve(struct pt_regs *regs)
{
struct ve_info ve;
+ int ret;
tdx_get_ve_info(&ve);
if (ve.exit_reason != EXIT_REASON_IO_INSTRUCTION)
return false;
- return handle_io(regs, ve.exit_qual);
+ ret = handle_io(regs, &ve);
+ if (ret < 0)
+ return false;
+
+ regs->ip += ret;
+ return true;
}
void tdx_get_ve_info(struct ve_info *ve)
@@ -483,53 +497,55 @@ void tdx_get_ve_info(struct ve_info *ve)
}
/* Handle the user initiated #VE */
-static bool virt_exception_user(struct pt_regs *regs, struct ve_info *ve)
+static int virt_exception_user(struct pt_regs *regs, struct ve_info *ve)
{
switch (ve->exit_reason) {
case EXIT_REASON_CPUID:
- return handle_cpuid(regs);
+ return handle_cpuid(regs, ve);
default:
pr_warn("Unexpected #VE: %lld\n", ve->exit_reason);
- return false;
+ return -EIO;
}
}
/* Handle the kernel #VE */
-static bool virt_exception_kernel(struct pt_regs *regs, struct ve_info *ve)
+static int virt_exception_kernel(struct pt_regs *regs, struct ve_info *ve)
{
switch (ve->exit_reason) {
case EXIT_REASON_HLT:
- return handle_halt();
+ return handle_halt(ve);
case EXIT_REASON_MSR_READ:
- return read_msr(regs);
+ return read_msr(regs, ve);
case EXIT_REASON_MSR_WRITE:
- return write_msr(regs);
+ return write_msr(regs, ve);
case EXIT_REASON_CPUID:
- return handle_cpuid(regs);
+ return handle_cpuid(regs, ve);
case EXIT_REASON_EPT_VIOLATION:
return handle_mmio(regs, ve);
case EXIT_REASON_IO_INSTRUCTION:
- return handle_io(regs, ve->exit_qual);
+ return handle_io(regs, ve);
default:
pr_warn("Unexpected #VE: %lld\n", ve->exit_reason);
- return false;
+ return -EIO;
}
}
bool tdx_handle_virt_exception(struct pt_regs *regs, struct ve_info *ve)
{
- bool ret;
+ int ret;
if (user_mode(regs))
ret = virt_exception_user(regs, ve);
else
ret = virt_exception_kernel(regs, ve);
+ if (ret < 0)
+ return false;
+
/* After successful #VE handling, move the IP */
- if (ret)
- regs->ip += ve->instr_len;
+ regs->ip += ret;
- return ret;
+ return true;
}
static bool tdx_tlb_flush_required(bool private)
--
Kirill A. Shutemov
Powered by blists - more mailing lists