| 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: <94a9847072098e554146ca4fa3c6f28fc1ac5b22.1612563142.git.sathyanarayanan.kuppuswamy@linux.intel.com>
Date: Fri, 5 Feb 2021 15:38:29 -0800
From: Kuppuswamy Sathyanarayanan
<sathyanarayanan.kuppuswamy@...ux.intel.com>
To: Peter Zijlstra <peterz@...radead.org>,
Andy Lutomirski <luto@...nel.org>,
Dave Hansen <dave.hansen@...el.com>
Cc: Andi Kleen <ak@...ux.intel.com>,
Kirill Shutemov <kirill.shutemov@...ux.intel.com>,
Kuppuswamy Sathyanarayanan <knsathya@...nel.org>,
Dan Williams <dan.j.williams@...el.com>,
Raj Ashok <ashok.raj@...el.com>,
Sean Christopherson <seanjc@...gle.com>,
linux-kernel@...r.kernel.org,
Kuppuswamy Sathyanarayanan
<sathyanarayanan.kuppuswamy@...ux.intel.com>
Subject: [RFC v1 12/26] x86/tdx: Handle in-kernel MMIO
From: "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
Handle #VE due to MMIO operations. MMIO triggers #VE with EPT_VIOLATION
exit reason.
For now we only handle subset of instruction that kernel uses for MMIO
oerations. User-space access triggers SIGBUS.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@...ux.intel.com>
Reviewed-by: Andi Kleen <ak@...ux.intel.com>
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@...ux.intel.com>
---
arch/x86/kernel/tdx.c | 120 ++++++++++++++++++++++++++++++++++++++++++
1 file changed, 120 insertions(+)
diff --git a/arch/x86/kernel/tdx.c b/arch/x86/kernel/tdx.c
index 3846d2807a7a..eff58329751e 100644
--- a/arch/x86/kernel/tdx.c
+++ b/arch/x86/kernel/tdx.c
@@ -6,6 +6,8 @@
#include <linux/cpu.h>
#include <asm/tdx.h>
#include <asm/vmx.h>
+#include <asm/insn.h>
+#include <linux/sched/signal.h> /* force_sig_fault() */
#ifdef CONFIG_KVM_GUEST
#include "tdx-kvm.c"
@@ -270,6 +272,121 @@ static void tdx_handle_io(struct pt_regs *regs, u32 exit_qual)
}
}
+static unsigned long tdx_mmio(int size, bool write, unsigned long addr,
+ unsigned long val)
+{
+ register long r10 asm("r10") = TDVMCALL_STANDARD;
+ register long r11 asm("r11") = EXIT_REASON_EPT_VIOLATION;
+ register long r12 asm("r12") = size;
+ register long r13 asm("r13") = write;
+ register long r14 asm("r14") = addr;
+ register long r15 asm("r15") = val;
+ register long rcx asm("rcx");
+ long ret;
+
+ /* Allow to pass R10, R11, R12, R13, R14 and R15 down to the VMM */
+ rcx = BIT(10) | BIT(11) | BIT(12) | BIT(13) | BIT(14) | BIT(15);
+
+ asm volatile(TDCALL
+ : "=a"(ret), "=r"(r10), "=r"(r11), "=r"(r12), "=r"(r13),
+ "=r"(r14), "=r"(r15)
+ : "a"(TDVMCALL), "r"(rcx), "r"(r10), "r"(r11), "r"(r12),
+ "r"(r13), "r"(r14), "r"(r15)
+ : );
+
+ WARN_ON(ret || r10);
+
+ return r11;
+}
+
+static inline void *get_reg_ptr(struct pt_regs *regs, struct insn *insn)
+{
+ static const int regoff[] = {
+ offsetof(struct pt_regs, ax),
+ offsetof(struct pt_regs, cx),
+ offsetof(struct pt_regs, dx),
+ offsetof(struct pt_regs, bx),
+ offsetof(struct pt_regs, sp),
+ offsetof(struct pt_regs, bp),
+ offsetof(struct pt_regs, si),
+ offsetof(struct pt_regs, di),
+ offsetof(struct pt_regs, r8),
+ offsetof(struct pt_regs, r9),
+ offsetof(struct pt_regs, r10),
+ offsetof(struct pt_regs, r11),
+ offsetof(struct pt_regs, r12),
+ offsetof(struct pt_regs, r13),
+ offsetof(struct pt_regs, r14),
+ offsetof(struct pt_regs, r15),
+ };
+ int regno;
+
+ regno = X86_MODRM_REG(insn->modrm.value);
+ if (X86_REX_R(insn->rex_prefix.value))
+ regno += 8;
+
+ return (void *)regs + regoff[regno];
+}
+
+static int tdx_handle_mmio(struct pt_regs *regs, struct ve_info *ve)
+{
+ int size;
+ bool write;
+ unsigned long *reg;
+ struct insn insn;
+ unsigned long val = 0;
+
+ /*
+ * User mode would mean the kernel exposed a device directly
+ * to ring3, which shouldn't happen except for things like
+ * DPDK.
+ */
+ if (user_mode(regs)) {
+ pr_err("Unexpected user-mode MMIO access.\n");
+ force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *) ve->gla);
+ return 0;
+ }
+
+ kernel_insn_init(&insn, (void *) regs->ip, MAX_INSN_SIZE);
+ insn_get_length(&insn);
+ insn_get_opcode(&insn);
+
+ write = ve->exit_qual & 0x2;
+
+ size = insn.opnd_bytes;
+ switch (insn.opcode.bytes[0]) {
+ /* MOV r/m8 r8 */
+ case 0x88:
+ /* MOV r8 r/m8 */
+ case 0x8A:
+ /* MOV r/m8 imm8 */
+ case 0xC6:
+ size = 1;
+ break;
+ }
+
+ if (inat_has_immediate(insn.attr)) {
+ BUG_ON(!write);
+ val = insn.immediate.value;
+ tdx_mmio(size, write, ve->gpa, val);
+ return insn.length;
+ }
+
+ BUG_ON(!inat_has_modrm(insn.attr));
+
+ reg = get_reg_ptr(regs, &insn);
+
+ if (write) {
+ memcpy(&val, reg, size);
+ tdx_mmio(size, write, ve->gpa, val);
+ } else {
+ val = tdx_mmio(size, write, ve->gpa, val);
+ memset(reg, 0, size);
+ memcpy(reg, &val, size);
+ }
+ return insn.length;
+}
+
void __init tdx_early_init(void)
{
if (!cpuid_has_tdx_guest())
@@ -331,6 +448,9 @@ int tdx_handle_virtualization_exception(struct pt_regs *regs,
case EXIT_REASON_IO_INSTRUCTION:
tdx_handle_io(regs, ve->exit_qual);
break;
+ case EXIT_REASON_EPT_VIOLATION:
+ ve->instr_len = tdx_handle_mmio(regs, ve);
+ break;
default:
pr_warn("Unexpected #VE: %d\n", ve->exit_reason);
return -EFAULT;
--
2.25.1
Powered by blists - more mailing lists