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, 118 insertions, 4 deletions

diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index cbb71c1b574f..4199f25c0063 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -36,6 +36,11 @@
 #include <asm/microcode.h>
 #include <asm/kasan.h>
 #include <asm/fixmap.h>
+#include <asm/realmode.h>
+#include <asm/desc.h>
+#include <asm/extable.h>
+#include <asm/trapnr.h>
+#include <asm/sev-es.h>
 
 /*
  * Manage page tables very early on.
@@ -61,6 +66,24 @@ unsigned long vmemmap_base __ro_after_init = __VMEMMAP_BASE_L4;
 EXPORT_SYMBOL(vmemmap_base);
 #endif
 
+/*
+ * GDT used on the boot CPU before switching to virtual addresses.
+ */
+static struct desc_struct startup_gdt[GDT_ENTRIES] = {
+	[GDT_ENTRY_KERNEL32_CS]         = GDT_ENTRY_INIT(0xc09b, 0, 0xfffff),
+	[GDT_ENTRY_KERNEL_CS]           = GDT_ENTRY_INIT(0xa09b, 0, 0xfffff),
+	[GDT_ENTRY_KERNEL_DS]           = GDT_ENTRY_INIT(0xc093, 0, 0xfffff),
+};
+
+/*
+ * Address needs to be set at runtime because it references the startup_gdt
+ * while the kernel still uses a direct mapping.
+ */
+static struct desc_ptr startup_gdt_descr = {
+	.size = sizeof(startup_gdt),
+	.address = 0,
+};
+
 #define __head	__section(.head.text)
 
 static void __head *fixup_pointer(void *ptr, unsigned long physaddr)
@@ -297,7 +320,7 @@ static void __init reset_early_page_tables(void)
 }
 
 /* Create a new PMD entry */
-int __init __early_make_pgtable(unsigned long address, pmdval_t pmd)
+bool __init __early_make_pgtable(unsigned long address, pmdval_t pmd)
 {
 	unsigned long physaddr = address - __PAGE_OFFSET;
 	pgdval_t pgd, *pgd_p;
@@ -307,7 +330,7 @@ int __init __early_make_pgtable(unsigned long address, pmdval_t pmd)
 
 	/* Invalid address or early pgt is done ?  */
 	if (physaddr >= MAXMEM || read_cr3_pa() != __pa_nodebug(early_top_pgt))
-		return -1;
+		return false;
 
 again:
 	pgd_p = &early_top_pgt[pgd_index(address)].pgd;
@@ -364,10 +387,10 @@ again:
 	}
 	pmd_p[pmd_index(address)] = pmd;
 
-	return 0;
+	return true;
 }
 
-int __init early_make_pgtable(unsigned long address)
+static bool __init early_make_pgtable(unsigned long address)
 {
 	unsigned long physaddr = address - __PAGE_OFFSET;
 	pmdval_t pmd;
@@ -377,6 +400,19 @@ int __init early_make_pgtable(unsigned long address)
 	return __early_make_pgtable(address, pmd);
 }
 
+void __init do_early_exception(struct pt_regs *regs, int trapnr)
+{
+	if (trapnr == X86_TRAP_PF &&
+	    early_make_pgtable(native_read_cr2()))
+		return;
+
+	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT) &&
+	    trapnr == X86_TRAP_VC && handle_vc_boot_ghcb(regs))
+		return;
+
+	early_fixup_exception(regs, trapnr);
+}
+
 /* Don't add a printk in there. printk relies on the PDA which is not initialized 
    yet. */
 static void __init clear_bss(void)
@@ -489,3 +525,81 @@ void __init x86_64_start_reservations(char *real_mode_data)
 
 	start_kernel();
 }
+
+/*
+ * Data structures and code used for IDT setup in head_64.S. The bringup-IDT is
+ * used until the idt_table takes over. On the boot CPU this happens in
+ * x86_64_start_kernel(), on secondary CPUs in start_secondary(). In both cases
+ * this happens in the functions called from head_64.S.
+ *
+ * The idt_table can't be used that early because all the code modifying it is
+ * in idt.c and can be instrumented by tracing or KASAN, which both don't work
+ * during early CPU bringup. Also the idt_table has the runtime vectors
+ * configured which require certain CPU state to be setup already (like TSS),
+ * which also hasn't happened yet in early CPU bringup.
+ */
+static gate_desc bringup_idt_table[NUM_EXCEPTION_VECTORS] __page_aligned_data;
+
+static struct desc_ptr bringup_idt_descr = {
+	.size		= (NUM_EXCEPTION_VECTORS * sizeof(gate_desc)) - 1,
+	.address	= 0, /* Set at runtime */
+};
+
+static void set_bringup_idt_handler(gate_desc *idt, int n, void *handler)
+{
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+	struct idt_data data;
+	gate_desc desc;
+
+	init_idt_data(&data, n, handler);
+	idt_init_desc(&desc, &data);
+	native_write_idt_entry(idt, n, &desc);
+#endif
+}
+
+/* This runs while still in the direct mapping */
+static void startup_64_load_idt(unsigned long physbase)
+{
+	struct desc_ptr *desc = fixup_pointer(&bringup_idt_descr, physbase);
+	gate_desc *idt = fixup_pointer(bringup_idt_table, physbase);
+
+
+	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) {
+		void *handler;
+
+		/* VMM Communication Exception */
+		handler = fixup_pointer(vc_no_ghcb, physbase);
+		set_bringup_idt_handler(idt, X86_TRAP_VC, handler);
+	}
+
+	desc->address = (unsigned long)idt;
+	native_load_idt(desc);
+}
+
+/* This is used when running on kernel addresses */
+void early_setup_idt(void)
+{
+	/* VMM Communication Exception */
+	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT))
+		set_bringup_idt_handler(bringup_idt_table, X86_TRAP_VC, vc_boot_ghcb);
+
+	bringup_idt_descr.address = (unsigned long)bringup_idt_table;
+	native_load_idt(&bringup_idt_descr);
+}
+
+/*
+ * Setup boot CPU state needed before kernel switches to virtual addresses.
+ */
+void __head startup_64_setup_env(unsigned long physbase)
+{
+	/* Load GDT */
+	startup_gdt_descr.address = (unsigned long)fixup_pointer(startup_gdt, physbase);
+	native_load_gdt(&startup_gdt_descr);
+
+	/* New GDT is live - reload data segment registers */
+	asm volatile("movl %%eax, %%ds\n"
+		     "movl %%eax, %%ss\n"
+		     "movl %%eax, %%es\n" : : "a"(__KERNEL_DS) : "memory");
+
+	startup_64_load_idt(physbase);
+}