Merge tag 'x86_cc_for_v6.11_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 confidential computing updates from Borislav Petkov:
 "Unrelated x86/cc changes queued here to avoid ugly cross-merges and
  conflicts:

   - Carve out CPU hotplug function declarations into a separate header
     with the goal to be able to use the lockdep assertions in a more
     flexible manner

   - As a result, refactor cacheinfo code after carving out a function
     to return the cache ID associated with a given cache level

   - Cleanups

  Add support to be able to kexec TDX guests:

   - Expand ACPI MADT CPU offlining support

   - Add machinery to prepare CoCo guests memory before kexec-ing into a
     new kernel

   - Cleanup, readjust and massage related code"

* tag 'x86_cc_for_v6.11_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  ACPI: tables: Print MULTIPROC_WAKEUP when MADT is parsed
  x86/acpi: Add support for CPU offlining for ACPI MADT wakeup method
  x86/mm: Introduce kernel_ident_mapping_free()
  x86/smp: Add smp_ops.stop_this_cpu() callback
  x86/acpi: Do not attempt to bring up secondary CPUs in the kexec case
  x86/acpi: Rename fields in the acpi_madt_multiproc_wakeup structure
  x86/mm: Do not zap page table entries mapping unaccepted memory table during kdump
  x86/mm: Make e820__end_ram_pfn() cover E820_TYPE_ACPI ranges
  x86/tdx: Convert shared memory back to private on kexec
  x86/mm: Add callbacks to prepare encrypted memory for kexec
  x86/tdx: Account shared memory
  x86/mm: Return correct level from lookup_address() if pte is none
  x86/mm: Make x86_platform.guest.enc_status_change_*() return an error
  x86/kexec: Keep CR4.MCE set during kexec for TDX guest
  x86/relocate_kernel: Use named labels for less confusion
  cpu/hotplug, x86/acpi: Disable CPU offlining for ACPI MADT wakeup
  cpu/hotplug: Add support for declaring CPU offlining not supported
  x86/apic: Mark acpi_mp_wake_* variables as __ro_after_init
  x86/acpi: Extract ACPI MADT wakeup code into a separate file
  x86/kexec: Remove spurious unconditional JMP from from identity_mapped()
  ...

Author: torvalds

arch/x86/Kconfig

@@ -1118,6 +1118,13 @@ config X86_LOCAL_APIC
 	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI
 	select IRQ_DOMAIN_HIERARCHY
 
+config ACPI_MADT_WAKEUP
+	def_bool y
+	depends on X86_64
+	depends on ACPI
+	depends on SMP
+	depends on X86_LOCAL_APIC
+
 config X86_IO_APIC
 	def_bool y
 	depends on X86_LOCAL_APIC || X86_UP_IOAPIC

arch/x86/coco/core.c

@@ -29,7 +29,6 @@ static bool noinstr intel_cc_platform_has(enum cc_attr attr)
 {
 	switch (attr) {
 	case CC_ATTR_GUEST_UNROLL_STRING_IO:
-	case CC_ATTR_HOTPLUG_DISABLED:
 	case CC_ATTR_GUEST_MEM_ENCRYPT:
 	case CC_ATTR_MEM_ENCRYPT:
 		return true;

arch/x86/coco/tdx/tdx.c

@@ -7,13 +7,15 @@
 #include <linux/cpufeature.h>
 #include <linux/export.h>
 #include <linux/io.h>
+#include <linux/kexec.h>
 #include <asm/coco.h>
 #include <asm/tdx.h>
 #include <asm/vmx.h>
 #include <asm/ia32.h>
 #include <asm/insn.h>
 #include <asm/insn-eval.h>
 #include <asm/pgtable.h>
+#include <asm/set_memory.h>
 
 /* MMIO direction */
 #define EPT_READ	0
@@ -38,6 +40,8 @@
 
 #define TDREPORT_SUBTYPE_0	0
 
+static atomic_long_t nr_shared;
+
 /* Called from __tdx_hypercall() for unrecoverable failure */
 noinstr void __noreturn __tdx_hypercall_failed(void)
 {
@@ -798,28 +802,124 @@ 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)
+static int 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;
+	if (enc && !tdx_enc_status_changed(vaddr, numpages, enc))
+		return -EIO;
+
+	return 0;
 }
 
-static bool tdx_enc_status_change_finish(unsigned long vaddr, int numpages,
+static int 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;
+	if (!enc && !tdx_enc_status_changed(vaddr, numpages, enc))
+		return -EIO;
+
+	if (enc)
+		atomic_long_sub(numpages, &nr_shared);
+	else
+		atomic_long_add(numpages, &nr_shared);
+
+	return 0;
+}
+
+/* Stop new private<->shared conversions */
+static void tdx_kexec_begin(void)
+{
+	if (!IS_ENABLED(CONFIG_KEXEC_CORE))
+		return;
+
+	/*
+	 * Crash kernel reaches here with interrupts disabled: can't wait for
+	 * conversions to finish.
+	 *
+	 * If race happened, just report and proceed.
+	 */
+	if (!set_memory_enc_stop_conversion())
+		pr_warn("Failed to stop shared<->private conversions\n");
+}
+
+/* Walk direct mapping and convert all shared memory back to private */
+static void tdx_kexec_finish(void)
+{
+	unsigned long addr, end;
+	long found = 0, shared;
+
+	if (!IS_ENABLED(CONFIG_KEXEC_CORE))
+		return;
+
+	lockdep_assert_irqs_disabled();
+
+	addr = PAGE_OFFSET;
+	end  = PAGE_OFFSET + get_max_mapped();
+
+	while (addr < end) {
+		unsigned long size;
+		unsigned int level;
+		pte_t *pte;
+
+		pte = lookup_address(addr, &level);
+		size = page_level_size(level);
+
+		if (pte && pte_decrypted(*pte)) {
+			int pages = size / PAGE_SIZE;
+
+			/*
+			 * Touching memory with shared bit set triggers implicit
+			 * conversion to shared.
+			 *
+			 * Make sure nobody touches the shared range from
+			 * now on.
+			 */
+			set_pte(pte, __pte(0));
+
+			/*
+			 * Memory encryption state persists across kexec.
+			 * If tdx_enc_status_changed() fails in the first
+			 * kernel, it leaves memory in an unknown state.
+			 *
+			 * If that memory remains shared, accessing it in the
+			 * *next* kernel through a private mapping will result
+			 * in an unrecoverable guest shutdown.
+			 *
+			 * The kdump kernel boot is not impacted as it uses
+			 * a pre-reserved memory range that is always private.
+			 * However, gathering crash information could lead to
+			 * a crash if it accesses unconverted memory through
+			 * a private mapping which is possible when accessing
+			 * that memory through /proc/vmcore, for example.
+			 *
+			 * In all cases, print error info in order to leave
+			 * enough bread crumbs for debugging.
+			 */
+			if (!tdx_enc_status_changed(addr, pages, true)) {
+				pr_err("Failed to unshare range %#lx-%#lx\n",
+				       addr, addr + size);
+			}
+
+			found += pages;
+		}
+
+		addr += size;
+	}
+
+	__flush_tlb_all();
+
+	shared = atomic_long_read(&nr_shared);
+	if (shared != found) {
+		pr_err("shared page accounting is off\n");
+		pr_err("nr_shared = %ld, nr_found = %ld\n", shared, found);
+	}
 }
 
 void __init tdx_early_init(void)
@@ -881,6 +981,9 @@ void __init tdx_early_init(void)
 	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_kexec_begin	     = tdx_kexec_begin;
+	x86_platform.guest.enc_kexec_finish	     = tdx_kexec_finish;
+
 	/*
 	 * TDX intercepts the RDMSR to read the X2APIC ID in the parallel
 	 * bringup low level code. That raises #VE which cannot be handled

arch/x86/hyperv/ivm.c

@@ -523,9 +523,9 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[],
  * transition is complete, hv_vtom_set_host_visibility() marks the pages
  * as "present" again.
  */
-static bool hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc)
+static int hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc)
 {
-	return !set_memory_np(kbuffer, pagecount);
+	return set_memory_np(kbuffer, pagecount);
 }
 
 /*
@@ -536,20 +536,19 @@ static bool hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc
  * with host. This function works as wrap of hv_mark_gpa_visibility()
  * with memory base and size.
  */
-static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bool enc)
+static int hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bool enc)
 {
 	enum hv_mem_host_visibility visibility = enc ?
 			VMBUS_PAGE_NOT_VISIBLE : VMBUS_PAGE_VISIBLE_READ_WRITE;
 	u64 *pfn_array;
 	phys_addr_t paddr;
+	int i, pfn, err;
 	void *vaddr;
 	int ret = 0;
-	bool result = true;
-	int i, pfn;
 
 	pfn_array = kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);
 	if (!pfn_array) {
-		result = false;
+		ret = -ENOMEM;
 		goto err_set_memory_p;
 	}
 
@@ -568,10 +567,8 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo
 		if (pfn == HV_MAX_MODIFY_GPA_REP_COUNT || i == pagecount - 1) {
 			ret = hv_mark_gpa_visibility(pfn, pfn_array,
 						     visibility);
-			if (ret) {
-				result = false;
+			if (ret)
 				goto err_free_pfn_array;
-			}
 			pfn = 0;
 		}
 	}
@@ -586,10 +583,11 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo
 	 * order to avoid leaving the memory range in a "broken" state. Setting
 	 * the PRESENT bits shouldn't fail, but return an error if it does.
 	 */
-	if (set_memory_p(kbuffer, pagecount))
-		result = false;
+	err = set_memory_p(kbuffer, pagecount);
+	if (err && !ret)
+		ret = err;
 
-	return result;
+	return ret;
 }
 
 static bool hv_vtom_tlb_flush_required(bool private)

arch/x86/include/asm/acpi.h

@@ -78,6 +78,13 @@ static inline bool acpi_skip_set_wakeup_address(void)
 
 #define acpi_skip_set_wakeup_address acpi_skip_set_wakeup_address
 
+union acpi_subtable_headers;
+
+int __init acpi_parse_mp_wake(union acpi_subtable_headers *header,
+			      const unsigned long end);
+
+void asm_acpi_mp_play_dead(u64 reset_vector, u64 pgd_pa);
+
 /*
  * Check if the CPU can handle C2 and deeper
  */

arch/x86/include/asm/init.h

@@ -6,6 +6,7 @@
 
 struct x86_mapping_info {
 	void *(*alloc_pgt_page)(void *); /* allocate buf for page table */
+	void (*free_pgt_page)(void *, void *); /* free buf for page table */
 	void *context;			 /* context for alloc_pgt_page */
 	unsigned long page_flag;	 /* page flag for PMD or PUD entry */
 	unsigned long offset;		 /* ident mapping offset */
@@ -16,4 +17,6 @@ struct x86_mapping_info {
 int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
 				unsigned long pstart, unsigned long pend);
 
+void kernel_ident_mapping_free(struct x86_mapping_info *info, pgd_t *pgd);
+
 #endif /* _ASM_X86_INIT_H */

arch/x86/include/asm/pgtable.h

@@ -140,6 +140,11 @@ static inline int pte_young(pte_t pte)
 	return pte_flags(pte) & _PAGE_ACCESSED;
 }
 
+static inline bool pte_decrypted(pte_t pte)
+{
+	return cc_mkdec(pte_val(pte)) == pte_val(pte);
+}
+
 #define pmd_dirty pmd_dirty
 static inline bool pmd_dirty(pmd_t pmd)
 {

arch/x86/include/asm/pgtable_types.h

@@ -549,6 +549,7 @@ enum pg_level {
 	PG_LEVEL_2M,
 	PG_LEVEL_1G,
 	PG_LEVEL_512G,
+	PG_LEVEL_256T,
 	PG_LEVEL_NUM
 };
 

arch/x86/include/asm/set_memory.h

@@ -49,8 +49,11 @@ int set_memory_wb(unsigned long addr, int numpages);
 int set_memory_np(unsigned long addr, int numpages);
 int set_memory_p(unsigned long addr, int numpages);
 int set_memory_4k(unsigned long addr, int numpages);
+
+bool set_memory_enc_stop_conversion(void);
 int set_memory_encrypted(unsigned long addr, int numpages);
 int set_memory_decrypted(unsigned long addr, int numpages);
+
 int set_memory_np_noalias(unsigned long addr, int numpages);
 int set_memory_nonglobal(unsigned long addr, int numpages);
 int set_memory_global(unsigned long addr, int numpages);

arch/x86/include/asm/smp.h

@@ -35,6 +35,7 @@ struct smp_ops {
 	int (*cpu_disable)(void);
 	void (*cpu_die)(unsigned int cpu);
 	void (*play_dead)(void);
+	void (*stop_this_cpu)(void);
 
 	void (*send_call_func_ipi)(const struct cpumask *mask);
 	void (*send_call_func_single_ipi)(int cpu);