[LTS 9.2] CVE-2023-46813, CVE-2023-0597

arch/x86/boot/compressed/sev.c

@@ -103,6 +103,16 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
 	return ES_OK;
 }
 
+static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size)
+{
+	return ES_OK;
+}
+
+static bool fault_in_kernel_space(unsigned long address)
+{
+	return false;
+}
+
 #undef __init
 #undef __pa
 #define __init

arch/x86/include/asm/cpu_entry_area.h

@@ -130,10 +130,6 @@ struct cpu_entry_area {
 };
 
 #define CPU_ENTRY_AREA_SIZE		(sizeof(struct cpu_entry_area))
-#define CPU_ENTRY_AREA_ARRAY_SIZE	(CPU_ENTRY_AREA_SIZE * NR_CPUS)
-
-/* Total size includes the readonly IDT mapping page as well: */
-#define CPU_ENTRY_AREA_TOTAL_SIZE	(CPU_ENTRY_AREA_ARRAY_SIZE + PAGE_SIZE)
 
 DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
 DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks);

arch/x86/include/asm/kasan.h

@@ -28,9 +28,12 @@
 #ifdef CONFIG_KASAN
 void __init kasan_early_init(void);
 void __init kasan_init(void);
+void __init kasan_populate_shadow_for_vaddr(void *va, size_t size, int nid);
 #else
 static inline void kasan_early_init(void) { }
 static inline void kasan_init(void) { }
+static inline void kasan_populate_shadow_for_vaddr(void *va, size_t size,
+						   int nid) { }
 #endif
 
 #endif

arch/x86/include/asm/pgtable_areas.h

@@ -11,6 +11,12 @@
 
 #define CPU_ENTRY_AREA_RO_IDT_VADDR	((void *)CPU_ENTRY_AREA_RO_IDT)
 
-#define CPU_ENTRY_AREA_MAP_SIZE		(CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_ARRAY_SIZE - CPU_ENTRY_AREA_BASE)
+#ifdef CONFIG_X86_32
+#define CPU_ENTRY_AREA_MAP_SIZE		(CPU_ENTRY_AREA_PER_CPU +		\
+					 (CPU_ENTRY_AREA_SIZE * NR_CPUS) -	\
+					 CPU_ENTRY_AREA_BASE)
+#else
+#define CPU_ENTRY_AREA_MAP_SIZE		P4D_SIZE
+#endif
 
 #endif /* _ASM_X86_PGTABLE_AREAS_H */

arch/x86/kernel/hw_breakpoint.c

@@ -266,7 +266,7 @@ static inline bool within_cpu_entry(unsigned long addr, unsigned long end)
 
 	/* CPU entry erea is always used for CPU entry */
 	if (within_area(addr, end, CPU_ENTRY_AREA_BASE,
-			CPU_ENTRY_AREA_TOTAL_SIZE))
+			CPU_ENTRY_AREA_MAP_SIZE))
 		return true;
 
 	/*

arch/x86/kernel/sev-shared.c

@@ -589,14 +589,36 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code)
 	sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
 }
 
+static enum es_result vc_insn_string_check(struct es_em_ctxt *ctxt,
+					   unsigned long address,
+					   bool write)
+{
+	if (user_mode(ctxt->regs) && fault_in_kernel_space(address)) {
+		ctxt->fi.vector     = X86_TRAP_PF;
+		ctxt->fi.error_code = X86_PF_USER;
+		ctxt->fi.cr2        = address;
+		if (write)
+			ctxt->fi.error_code |= X86_PF_WRITE;
+
+		return ES_EXCEPTION;
+	}
+
+	return ES_OK;
+}
+
 static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt,
 					  void *src, char *buf,
 					  unsigned int data_size,
 					  unsigned int count,
 					  bool backwards)
 {
 	int i, b = backwards ? -1 : 1;
-	enum es_result ret = ES_OK;
+	unsigned long address = (unsigned long)src;
+	enum es_result ret;
+
+	ret = vc_insn_string_check(ctxt, address, false);
+	if (ret != ES_OK)
+		return ret;
 
 	for (i = 0; i < count; i++) {
 		void *s = src + (i * data_size * b);
@@ -617,7 +639,12 @@ static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt,
 					   bool backwards)
 {
 	int i, s = backwards ? -1 : 1;
-	enum es_result ret = ES_OK;
+	unsigned long address = (unsigned long)dst;
+	enum es_result ret;
+
+	ret = vc_insn_string_check(ctxt, address, true);
+	if (ret != ES_OK)
+		return ret;
 
 	for (i = 0; i < count; i++) {
 		void *d = dst + (i * data_size * s);
@@ -653,6 +680,9 @@ static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt,
 static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
 {
 	struct insn *insn = &ctxt->insn;
+	size_t size;
+	u64 port;
+
 	*exitinfo = 0;
 
 	switch (insn->opcode.bytes[0]) {
@@ -661,49 +691,51 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
 	case 0x6d:
 		*exitinfo |= IOIO_TYPE_INS;
 		*exitinfo |= IOIO_SEG_ES;
-		*exitinfo |= (ctxt->regs->dx & 0xffff) << 16;
+		port	   = ctxt->regs->dx & 0xffff;
 		break;
 
 	/* OUTS opcodes */
 	case 0x6e:
 	case 0x6f:
 		*exitinfo |= IOIO_TYPE_OUTS;
 		*exitinfo |= IOIO_SEG_DS;
-		*exitinfo |= (ctxt->regs->dx & 0xffff) << 16;
+		port	   = ctxt->regs->dx & 0xffff;
 		break;
 
 	/* IN immediate opcodes */
 	case 0xe4:
 	case 0xe5:
 		*exitinfo |= IOIO_TYPE_IN;
-		*exitinfo |= (u8)insn->immediate.value << 16;
+		port	   = (u8)insn->immediate.value & 0xffff;
 		break;
 
 	/* OUT immediate opcodes */
 	case 0xe6:
 	case 0xe7:
 		*exitinfo |= IOIO_TYPE_OUT;
-		*exitinfo |= (u8)insn->immediate.value << 16;
+		port	   = (u8)insn->immediate.value & 0xffff;
 		break;
 
 	/* IN register opcodes */
 	case 0xec:
 	case 0xed:
 		*exitinfo |= IOIO_TYPE_IN;
-		*exitinfo |= (ctxt->regs->dx & 0xffff) << 16;
+		port	   = ctxt->regs->dx & 0xffff;
 		break;
 
 	/* OUT register opcodes */
 	case 0xee:
 	case 0xef:
 		*exitinfo |= IOIO_TYPE_OUT;
-		*exitinfo |= (ctxt->regs->dx & 0xffff) << 16;
+		port	   = ctxt->regs->dx & 0xffff;
 		break;
 
 	default:
 		return ES_DECODE_FAILED;
 	}
 
+	*exitinfo |= port << 16;
+
 	switch (insn->opcode.bytes[0]) {
 	case 0x6c:
 	case 0x6e:
@@ -713,12 +745,15 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
 	case 0xee:
 		/* Single byte opcodes */
 		*exitinfo |= IOIO_DATA_8;
+		size       = 1;
 		break;
 	default:
 		/* Length determined by instruction parsing */
 		*exitinfo |= (insn->opnd_bytes == 2) ? IOIO_DATA_16
 						     : IOIO_DATA_32;
+		size       = (insn->opnd_bytes == 2) ? 2 : 4;
 	}
+
 	switch (insn->addr_bytes) {
 	case 2:
 		*exitinfo |= IOIO_ADDR_16;
@@ -734,7 +769,7 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
 	if (insn_has_rep_prefix(insn))
 		*exitinfo |= IOIO_REP;
 
-	return ES_OK;
+	return vc_ioio_check(ctxt, (u16)port, size);
 }
 
 static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)

arch/x86/kernel/sev.c

@@ -493,6 +493,33 @@ static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt
 	return ES_OK;
 }
 
+static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size)
+{
+	BUG_ON(size > 4);
+
+	if (user_mode(ctxt->regs)) {
+		struct thread_struct *t = &current->thread;
+		struct io_bitmap *iobm = t->io_bitmap;
+		size_t idx;
+
+		if (!iobm)
+			goto fault;
+
+		for (idx = port; idx < port + size; ++idx) {
+			if (test_bit(idx, iobm->bitmap))
+				goto fault;
+		}
+	}
+
+	return ES_OK;
+
+fault:
+	ctxt->fi.vector = X86_TRAP_GP;
+	ctxt->fi.error_code = 0;
+
+	return ES_EXCEPTION;
+}
+
 /* Include code shared with pre-decompression boot stage */
 #include "sev-shared.c"
 
@@ -1533,6 +1560,9 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 			return ES_DECODE_FAILED;
 	}
 
+	if (user_mode(ctxt->regs))
+		return ES_UNSUPPORTED;
+
 	switch (mmio) {
 	case MMIO_WRITE:
 		memcpy(ghcb->shared_buffer, reg_data, bytes);

arch/x86/mm/cpu_entry_area.c

@@ -5,26 +5,72 @@
 #include <linux/kallsyms.h>
 #include <linux/kcore.h>
 #include <linux/pgtable.h>
+#include <linux/prandom.h>
 
 #include <asm/cpu_entry_area.h>
 #include <asm/fixmap.h>
 #include <asm/desc.h>
+#include <asm/kasan.h>
+#include <asm/setup.h>
 
 static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage);
 
 #ifdef CONFIG_X86_64
 static DEFINE_PER_CPU_PAGE_ALIGNED(struct exception_stacks, exception_stacks);
 DEFINE_PER_CPU(struct cea_exception_stacks*, cea_exception_stacks);
-#endif
 
-#ifdef CONFIG_X86_32
+static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, _cea_offset);
+
+static __always_inline unsigned int cea_offset(unsigned int cpu)
+{
+	return per_cpu(_cea_offset, cpu);
+}
+
+static __init void init_cea_offsets(void)
+{
+	unsigned int max_cea;
+	unsigned int i, j;
+
+	if (!kaslr_enabled()) {
+		for_each_possible_cpu(i)
+			per_cpu(_cea_offset, i) = i;
+		return;
+	}
+
+	max_cea = (CPU_ENTRY_AREA_MAP_SIZE - PAGE_SIZE) / CPU_ENTRY_AREA_SIZE;
+
+	/* O(sodding terrible) */
+	for_each_possible_cpu(i) {
+		unsigned int cea;
+
+again:
+		cea = prandom_u32_max(max_cea);
+
+		for_each_possible_cpu(j) {
+			if (cea_offset(j) == cea)
+				goto again;
+
+			if (i == j)
+				break;
+		}
+
+		per_cpu(_cea_offset, i) = cea;
+	}
+}
+#else /* !X86_64 */
 DECLARE_PER_CPU_PAGE_ALIGNED(struct doublefault_stack, doublefault_stack);
+
+static __always_inline unsigned int cea_offset(unsigned int cpu)
+{
+	return cpu;
+}
+static inline void init_cea_offsets(void) { }
 #endif
 
 /* Is called from entry code, so must be noinstr */
 noinstr struct cpu_entry_area *get_cpu_entry_area(int cpu)
 {
-	unsigned long va = CPU_ENTRY_AREA_PER_CPU + cpu * CPU_ENTRY_AREA_SIZE;
+	unsigned long va = CPU_ENTRY_AREA_PER_CPU + cea_offset(cpu) * CPU_ENTRY_AREA_SIZE;
 	BUILD_BUG_ON(sizeof(struct cpu_entry_area) % PAGE_SIZE != 0);
 
 	return (struct cpu_entry_area *) va;
@@ -152,6 +198,9 @@ static void __init setup_cpu_entry_area(unsigned int cpu)
 	pgprot_t tss_prot = PAGE_KERNEL;
 #endif
 
+	kasan_populate_shadow_for_vaddr(cea, CPU_ENTRY_AREA_SIZE,
+					early_cpu_to_node(cpu));
+
 	cea_set_pte(&cea->gdt, get_cpu_gdt_paddr(cpu), gdt_prot);
 
 	cea_map_percpu_pages(&cea->entry_stack_page,
@@ -205,7 +254,6 @@ static __init void setup_cpu_entry_area_ptes(void)
 
 	/* The +1 is for the readonly IDT: */
 	BUILD_BUG_ON((CPU_ENTRY_AREA_PAGES+1)*PAGE_SIZE != CPU_ENTRY_AREA_MAP_SIZE);
-	BUILD_BUG_ON(CPU_ENTRY_AREA_TOTAL_SIZE != CPU_ENTRY_AREA_MAP_SIZE);
 	BUG_ON(CPU_ENTRY_AREA_BASE & ~PMD_MASK);
 
 	start = CPU_ENTRY_AREA_BASE;
@@ -221,6 +269,8 @@ void __init setup_cpu_entry_areas(void)
 {
 	unsigned int cpu;
 
+	init_cea_offsets();
+
 	setup_cpu_entry_area_ptes();
 
 	for_each_possible_cpu(cpu)

arch/x86/mm/kasan_init_64.c

@@ -316,6 +316,18 @@ void __init kasan_early_init(void)
 	kasan_map_early_shadow(init_top_pgt);
 }
 
+void __init kasan_populate_shadow_for_vaddr(void *va, size_t size, int nid)
+{
+	unsigned long shadow_start, shadow_end;
+
+	shadow_start = (unsigned long)kasan_mem_to_shadow(va);
+	shadow_start = round_down(shadow_start, PAGE_SIZE);
+	shadow_end = (unsigned long)kasan_mem_to_shadow(va + size);
+	shadow_end = round_up(shadow_end, PAGE_SIZE);
+
+	kasan_populate_shadow(shadow_start, shadow_end, nid);
+}
+
 void __init kasan_init(void)
 {
 	int i;
@@ -393,9 +405,6 @@ void __init kasan_init(void)
 		kasan_mem_to_shadow((void *)VMALLOC_END + 1),
 		shadow_cpu_entry_begin);
 
-	kasan_populate_shadow((unsigned long)shadow_cpu_entry_begin,
-			      (unsigned long)shadow_cpu_entry_end, 0);
-
 	kasan_populate_early_shadow(shadow_cpu_entry_end,
 			kasan_mem_to_shadow((void *)__START_KERNEL_map));