Merge branch 'x86-kdump-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x865 kdump updates from Thomas Gleixner:
 "Yet more kexec/kdump updates:

   - Properly support kexec when AMD's memory encryption (SME) is
     enabled

   - Pass reserved e820 ranges to the kexec kernel so both PCI and SME
     can work"

* 'x86-kdump-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  fs/proc/vmcore: Enable dumping of encrypted memory when SEV was active
  x86/kexec: Set the C-bit in the identity map page table when SEV is active
  x86/kexec: Do not map kexec area as decrypted when SEV is active
  x86/crash: Add e820 reserved ranges to kdump kernel's e820 table
  x86/mm: Rework ioremap resource mapping determination
  x86/e820, ioport: Add a new I/O resource descriptor IORES_DESC_RESERVED
  x86/mm: Create a workarea in the kernel for SME early encryption
  x86/mm: Identify the end of the kernel area to be reserved

5 files changed, 75 insertions, 6 deletions

diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index a55094b5f452..2bf70a2fed90 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -375,6 +375,12 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params)
 	walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1, &cmd,
 			memmap_entry_callback);
 
+	/* Add e820 reserved ranges */
+	cmd.type = E820_TYPE_RESERVED;
+	flags = IORESOURCE_MEM;
+	walk_iomem_res_desc(IORES_DESC_RESERVED, flags, 0, -1, &cmd,
+			   memmap_entry_callback);
+
 	/* Add crashk_low_res region */
 	if (crashk_low_res.end) {
 		ei.addr = crashk_low_res.start;
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 8f32e705a980..e69408bf664b 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1063,10 +1063,10 @@ static unsigned long __init e820_type_to_iores_desc(struct e820_entry *entry)
 	case E820_TYPE_NVS:		return IORES_DESC_ACPI_NV_STORAGE;
 	case E820_TYPE_PMEM:		return IORES_DESC_PERSISTENT_MEMORY;
 	case E820_TYPE_PRAM:		return IORES_DESC_PERSISTENT_MEMORY_LEGACY;
+	case E820_TYPE_RESERVED:	return IORES_DESC_RESERVED;
 	case E820_TYPE_RESERVED_KERN:	/* Fall-through: */
 	case E820_TYPE_RAM:		/* Fall-through: */
 	case E820_TYPE_UNUSABLE:	/* Fall-through: */
-	case E820_TYPE_RESERVED:	/* Fall-through: */
 	default:			return IORES_DESC_NONE;
 	}
 }
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 9184037aec62..5dcd438ad8f2 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -123,12 +123,13 @@ static void free_transition_pgtable(struct kimage *image)
 
 static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
 {
+	pgprot_t prot = PAGE_KERNEL_EXEC_NOENC;
+	unsigned long vaddr, paddr;
+	int result = -ENOMEM;
 	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
-	unsigned long vaddr, paddr;
-	int result = -ENOMEM;
 
 	vaddr = (unsigned long)relocate_kernel;
 	paddr = __pa(page_address(image->control_code_page)+PAGE_SIZE);
@@ -165,7 +166,11 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
 		set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
 	}
 	pte = pte_offset_kernel(pmd, vaddr);
-	set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC_NOENC));
+
+	if (sev_active())
+		prot = PAGE_KERNEL_EXEC;
+
+	set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, prot));
 	return 0;
 err:
 	return result;
@@ -202,6 +207,11 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
 	level4p = (pgd_t *)__va(start_pgtable);
 	clear_page(level4p);
 
+	if (sev_active()) {
+		info.page_flag   |= _PAGE_ENC;
+		info.kernpg_flag |= _PAGE_ENC;
+	}
+
 	if (direct_gbpages)
 		info.direct_gbpages = true;
 
@@ -644,8 +654,20 @@ void arch_kexec_unprotect_crashkres(void)
 	kexec_mark_crashkres(false);
 }
 
+/*
+ * During a traditional boot under SME, SME will encrypt the kernel,
+ * so the SME kexec kernel also needs to be un-encrypted in order to
+ * replicate a normal SME boot.
+ *
+ * During a traditional boot under SEV, the kernel has already been
+ * loaded encrypted, so the SEV kexec kernel needs to be encrypted in
+ * order to replicate a normal SEV boot.
+ */
 int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, gfp_t gfp)
 {
+	if (sev_active())
+		return 0;
+
 	/*
 	 * If SME is active we need to be sure that kexec pages are
 	 * not encrypted because when we boot to the new kernel the
@@ -656,6 +678,9 @@ int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, gfp_t gfp)
 
 void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages)
 {
+	if (sev_active())
+		return;
+
 	/*
 	 * If SME is active we need to reset the pages back to being
 	 * an encrypted mapping before freeing them.
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index dcbdf54fb5c1..bbe35bf879f5 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -836,8 +836,14 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
 
 void __init setup_arch(char **cmdline_p)
 {
+	/*
+	 * Reserve the memory occupied by the kernel between _text and
+	 * __end_of_kernel_reserve symbols. Any kernel sections after the
+	 * __end_of_kernel_reserve symbol must be explicitly reserved with a
+	 * separate memblock_reserve() or they will be discarded.
+	 */
 	memblock_reserve(__pa_symbol(_text),
-			 (unsigned long)__bss_stop - (unsigned long)_text);
+			 (unsigned long)__end_of_kernel_reserve - (unsigned long)_text);
 
 	/*
 	 * Make sure page 0 is always reserved because on systems with
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 0850b5149345..147cd020516a 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -368,6 +368,14 @@ SECTIONS
 		__bss_stop = .;
 	}
 
+	/*
+	 * The memory occupied from _text to here, __end_of_kernel_reserve, is
+	 * automatically reserved in setup_arch(). Anything after here must be
+	 * explicitly reserved using memblock_reserve() or it will be discarded
+	 * and treated as available memory.
+	 */
+	__end_of_kernel_reserve = .;
+
 	. = ALIGN(PAGE_SIZE);
 	.brk : AT(ADDR(.brk) - LOAD_OFFSET) {
 		__brk_base = .;
@@ -379,10 +387,34 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);		/* keep VO_INIT_SIZE page aligned */
 	_end = .;
 
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+	/*
+	 * Early scratch/workarea section: Lives outside of the kernel proper
+	 * (_text - _end).
+	 *
+	 * Resides after _end because even though the .brk section is after
+	 * __end_of_kernel_reserve, the .brk section is later reserved as a
+	 * part of the kernel. Since it is located after __end_of_kernel_reserve
+	 * it will be discarded and become part of the available memory. As
+	 * such, it can only be used by very early boot code and must not be
+	 * needed afterwards.
+	 *
+	 * Currently used by SME for performing in-place encryption of the
+	 * kernel during boot. Resides on a 2MB boundary to simplify the
+	 * pagetable setup used for SME in-place encryption.
+	 */
+	. = ALIGN(HPAGE_SIZE);
+	.init.scratch : AT(ADDR(.init.scratch) - LOAD_OFFSET) {
+		__init_scratch_begin = .;
+		*(.init.scratch)
+		. = ALIGN(HPAGE_SIZE);
+		__init_scratch_end = .;
+	}
+#endif
+
 	STABS_DEBUG
 	DWARF_DEBUG
 
-	/* Sections to be discarded */
 	DISCARDS
 	/DISCARD/ : {
 		*(.eh_frame)