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
  ...

1 files changed, 130 insertions, 0 deletions

diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index 5e69603ff63f..58f7fb95c7f4 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,
 };
@@ -53,6 +54,30 @@ 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
  *
@@ -439,6 +464,13 @@ 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))
@@ -808,6 +840,21 @@ int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs)
 }
 
 /**
+ * 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.
  * @regs:	Register values as seen when entering kernel mode
@@ -1367,3 +1414,86 @@ 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;
+}
+
+/**
+ * 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;
+}