Merge tag 'x86_tdx_for_6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 tdx updates from Dave Hansen:

 - Fix a race window where load_unaligned_zeropad() could cause a fatal
   shutdown during TDX private<=>shared conversion

   The race has never been observed in practice but might allow
   load_unaligned_zeropad() to catch a TDX page in the middle of its
   conversion process which would lead to a fatal and unrecoverable
   guest shutdown.

 - Annotate sites where VM "exit reasons" are reused as hypercall
   numbers.

* tag 'x86_tdx_for_6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mm: Fix enc_status_change_finish_noop()
  x86/tdx: Fix race between set_memory_encrypted() and load_unaligned_zeropad()
  x86/mm: Allow guest.enc_status_change_prepare() to fail
  x86/tdx: Wrap exit reason with hcall_func()

Author: torvalds

arch/x86/boot/compressed/tdx.c

@@ -20,7 +20,7 @@ static inline unsigned int tdx_io_in(int size, u16 port)
 {
 	struct tdx_hypercall_args args = {
 		.r10 = TDX_HYPERCALL_STANDARD,
-		.r11 = EXIT_REASON_IO_INSTRUCTION,
+		.r11 = hcall_func(EXIT_REASON_IO_INSTRUCTION),
 		.r12 = size,
 		.r13 = 0,
 		.r14 = port,
@@ -36,7 +36,7 @@ static inline void tdx_io_out(int size, u16 port, u32 value)
 {
 	struct tdx_hypercall_args args = {
 		.r10 = TDX_HYPERCALL_STANDARD,
-		.r11 = EXIT_REASON_IO_INSTRUCTION,
+		.r11 = hcall_func(EXIT_REASON_IO_INSTRUCTION),
 		.r12 = size,
 		.r13 = 1,
 		.r14 = port,

arch/x86/coco/tdx/tdx.c

@@ -44,17 +44,6 @@ noinstr void __tdx_hypercall_failed(void)
 	panic("TDVMCALL failed. TDX module bug?");
 }
 
-/*
- * The TDG.VP.VMCALL-Instruction-execution sub-functions are defined
- * independently from but are currently matched 1:1 with VMX EXIT_REASONs.
- * Reusing the KVM EXIT_REASON macros makes it easier to connect the host and
- * guest sides of these calls.
- */
-static __always_inline u64 hcall_func(u64 exit_reason)
-{
-	return exit_reason;
-}
-
 #ifdef CONFIG_KVM_GUEST
 long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, unsigned long p2,
 		       unsigned long p3, unsigned long p4)
@@ -744,6 +733,30 @@ static bool tdx_enc_status_changed(unsigned long vaddr, int numpages, bool enc)
 	return true;
 }
 
+static bool tdx_enc_status_change_prepare(unsigned long vaddr, int numpages,
+					  bool enc)
+{
+	/*
+	 * Only handle shared->private conversion here.
+	 * See the comment in tdx_early_init().
+	 */
+	if (enc)
+		return tdx_enc_status_changed(vaddr, numpages, enc);
+	return true;
+}
+
+static bool tdx_enc_status_change_finish(unsigned long vaddr, int numpages,
+					 bool enc)
+{
+	/*
+	 * Only handle private->shared conversion here.
+	 * See the comment in tdx_early_init().
+	 */
+	if (!enc)
+		return tdx_enc_status_changed(vaddr, numpages, enc);
+	return true;
+}
+
 void __init tdx_early_init(void)
 {
 	u64 cc_mask;
@@ -771,9 +784,30 @@ void __init tdx_early_init(void)
 	 */
 	physical_mask &= cc_mask - 1;
 
-	x86_platform.guest.enc_cache_flush_required = tdx_cache_flush_required;
-	x86_platform.guest.enc_tlb_flush_required   = tdx_tlb_flush_required;
-	x86_platform.guest.enc_status_change_finish = tdx_enc_status_changed;
+	/*
+	 * The kernel mapping should match the TDX metadata for the page.
+	 * load_unaligned_zeropad() can touch memory *adjacent* to that which is
+	 * owned by the caller and can catch even _momentary_ mismatches.  Bad
+	 * things happen on mismatch:
+	 *
+	 *   - Private mapping => Shared Page  == Guest shutdown
+         *   - Shared mapping  => Private Page == Recoverable #VE
+	 *
+	 * guest.enc_status_change_prepare() converts the page from
+	 * shared=>private before the mapping becomes private.
+	 *
+	 * guest.enc_status_change_finish() converts the page from
+	 * private=>shared after the mapping becomes private.
+	 *
+	 * In both cases there is a temporary shared mapping to a private page,
+	 * which can result in a #VE.  But, there is never a private mapping to
+	 * a shared page.
+	 */
+	x86_platform.guest.enc_status_change_prepare = tdx_enc_status_change_prepare;
+	x86_platform.guest.enc_status_change_finish  = tdx_enc_status_change_finish;
+
+	x86_platform.guest.enc_cache_flush_required  = tdx_cache_flush_required;
+	x86_platform.guest.enc_tlb_flush_required    = tdx_tlb_flush_required;
 
 	/*
 	 * TDX intercepts the RDMSR to read the X2APIC ID in the parallel

arch/x86/include/asm/shared/tdx.h

@@ -93,5 +93,16 @@ u64 __tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9,
 
 bool tdx_accept_memory(phys_addr_t start, phys_addr_t end);
 
+/*
+ * The TDG.VP.VMCALL-Instruction-execution sub-functions are defined
+ * independently from but are currently matched 1:1 with VMX EXIT_REASONs.
+ * Reusing the KVM EXIT_REASON macros makes it easier to connect the host and
+ * guest sides of these calls.
+ */
+static __always_inline u64 hcall_func(u64 exit_reason)
+{
+        return exit_reason;
+}
+
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_X86_SHARED_TDX_H */

arch/x86/include/asm/x86_init.h

@@ -150,7 +150,7 @@ struct x86_init_acpi {
  * @enc_cache_flush_required	Returns true if a cache flush is needed before changing page encryption status
  */
 struct x86_guest {
-	void (*enc_status_change_prepare)(unsigned long vaddr, int npages, bool enc);
+	bool (*enc_status_change_prepare)(unsigned long vaddr, int npages, bool enc);
 	bool (*enc_status_change_finish)(unsigned long vaddr, int npages, bool enc);
 	bool (*enc_tlb_flush_required)(bool enc);
 	bool (*enc_cache_flush_required)(void);

arch/x86/kernel/x86_init.c

@@ -131,8 +131,8 @@ struct x86_cpuinit_ops x86_cpuinit = {
 
 static void default_nmi_init(void) { };
 
-static void enc_status_change_prepare_noop(unsigned long vaddr, int npages, bool enc) { }
-static bool enc_status_change_finish_noop(unsigned long vaddr, int npages, bool enc) { return false; }
+static bool enc_status_change_prepare_noop(unsigned long vaddr, int npages, bool enc) { return true; }
+static bool enc_status_change_finish_noop(unsigned long vaddr, int npages, bool enc) { return true; }
 static bool enc_tlb_flush_required_noop(bool enc) { return false; }
 static bool enc_cache_flush_required_noop(void) { return false; }
 static bool is_private_mmio_noop(u64 addr) {return false; }

arch/x86/mm/mem_encrypt_amd.c

@@ -319,14 +319,16 @@ static void enc_dec_hypercall(unsigned long vaddr, int npages, bool enc)
 #endif
 }
 
-static void amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool enc)
+static bool amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool enc)
 {
 	/*
 	 * To maintain the security guarantees of SEV-SNP guests, make sure
 	 * to invalidate the memory before encryption attribute is cleared.
 	 */
 	if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && !enc)
 		snp_set_memory_shared(vaddr, npages);
+
+	return true;
 }
 
 /* Return true unconditionally: return value doesn't matter for the SEV side */

arch/x86/mm/pat/set_memory.c

@@ -2152,7 +2152,8 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc)
 		cpa_flush(&cpa, x86_platform.guest.enc_cache_flush_required());
 
 	/* Notify hypervisor that we are about to set/clr encryption attribute. */
-	x86_platform.guest.enc_status_change_prepare(addr, numpages, enc);
+	if (!x86_platform.guest.enc_status_change_prepare(addr, numpages, enc))
+		return -EIO;
 
 	ret = __change_page_attr_set_clr(&cpa, 1);