Merge tag 'x86_core_for_v5.16_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 core updates from Borislav Petkov:

- Do not #GP on userspace use of CLI/STI but pretend it was a NOP to
keep old userspace from breaking. Adjust the corresponding iopl
selftest to that.

- Improve stack overflow warnings to say which stack got overflowed and
raise the exception stack sizes to 2 pages since overflowing the
single page of exception stack is very easy to do nowadays with all
the tracing machinery enabled. With that, rip out the custom mapping
of AMD SEV's too.

- A bunch of changes in preparation for FGKASLR like supporting more
than 64K section headers in the relocs tool, correct ORC lookup table
size to cover the whole kernel .text and other adjustments.

* tag 'x86_core_for_v5.16_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
selftests/x86/iopl: Adjust to the faked iopl CLI/STI usage
vmlinux.lds.h: Have ORC lookup cover entire _etext - _stext
x86/boot/compressed: Avoid duplicate malloc() implementations
x86/boot: Allow a "silent" kaslr random byte fetch
x86/tools/relocs: Support >64K section headers
x86/sev: Make the #VC exception stacks part of the default stacks storage
x86: Increase exception stack sizes
x86/mm/64: Improve stack overflow warnings
x86/iopl: Fake iopl(3) CLI/STI usage

arch/x86/boot/compressed/kaslr.c

···
 #include <generated/utsrelease.h>
 #include <asm/efi.h>
 
-/* Macros used by the included decompressor code below. */
-#define STATIC
-#include <linux/decompress/mm.h>
-
 #define _SETUP
 #include <asm/setup.h>	/* For COMMAND_LINE_SIZE */
 #undef _SETUP

arch/x86/boot/compressed/misc.c

···
 
 /* Macros used by the included decompressor code below. */
 #define STATIC		static
+/* Define an externally visible malloc()/free(). */
+#define MALLOC_VISIBLE
+#include <linux/decompress/mm.h>
 
 /*
  * Provide definitions of memzero and memmove as some of the decompressors will

arch/x86/boot/compressed/misc.h

···
 /* misc.c */
 extern memptr free_mem_ptr;
 extern memptr free_mem_end_ptr;
+void *malloc(int size);
+void free(void *where);
 extern struct boot_params *boot_params;
 void __putstr(const char *s);
 void __puthex(unsigned long value);

arch/x86/include/asm/cpu_entry_area.h

···
 
 #ifdef CONFIG_X86_64
 
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+#define VC_EXCEPTION_STKSZ	EXCEPTION_STKSZ
+#else
+#define VC_EXCEPTION_STKSZ	0
+#endif
+
 /* Macro to enforce the same ordering and stack sizes */
 #define ESTACKS_MEMBERS(guardsize, optional_stack_size)		\
 	char	DF_stack_guard[guardsize];			\
···
 
 /* The exception stacks' physical storage. No guard pages required */
 struct exception_stacks {
-	ESTACKS_MEMBERS(0, 0)
+	ESTACKS_MEMBERS(0, VC_EXCEPTION_STKSZ)
 };
 
 /* The effective cpu entry area mapping with guard pages. */

arch/x86/include/asm/insn-eval.h

···
 int insn_get_modrm_reg_off(struct insn *insn, struct pt_regs *regs);
 unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx);
 int insn_get_code_seg_params(struct pt_regs *regs);
+int insn_get_effective_ip(struct pt_regs *regs, unsigned long *ip);
 int insn_fetch_from_user(struct pt_regs *regs,
 			 unsigned char buf[MAX_INSN_SIZE]);
 int insn_fetch_from_user_inatomic(struct pt_regs *regs,

arch/x86/include/asm/irq_stack.h

···
  *     Function calls can clobber anything except the callee-saved
  *     registers. Tell the compiler.
  */
-#define call_on_irqstack(func, asm_call, argconstr...)			\
+#define call_on_stack(stack, func, asm_call, argconstr...)		\
 {									\
 	register void *tos asm("r11");					\
 									\
-	tos = ((void *)__this_cpu_read(hardirq_stack_ptr));		\
+	tos = ((void *)(stack));					\
 									\
 	asm_inline volatile(						\
 	"movq	%%rsp, (%[tos])				\n"		\
···
 	  "memory"							\
 	);								\
 }
+
+#define ASM_CALL_ARG0							\
+	"call %P[__func]				\n"
+
+#define ASM_CALL_ARG1							\
+	"movq	%[arg1], %%rdi				\n"		\
+	ASM_CALL_ARG0
+
+#define ASM_CALL_ARG2							\
+	"movq	%[arg2], %%rsi				\n"		\
+	ASM_CALL_ARG1
+
+#define ASM_CALL_ARG3							\
+	"movq	%[arg3], %%rdx				\n"		\
+	ASM_CALL_ARG2
+
+#define call_on_irqstack(func, asm_call, argconstr...)			\
+	call_on_stack(__this_cpu_read(hardirq_stack_ptr),		\
+		      func, asm_call, argconstr)
 
 /* Macros to assert type correctness for run_*_on_irqstack macros */
 #define assert_function_type(func, proto)				\
···
  */
 #define ASM_CALL_SYSVEC							\
 	"call irq_enter_rcu				\n"		\
-	"movq	%[arg1], %%rdi				\n"		\
-	"call %P[__func]				\n"		\
+	ASM_CALL_ARG1							\
 	"call irq_exit_rcu				\n"
 
 #define SYSVEC_CONSTRAINTS	, [arg1] "r" (regs)
···
  */
 #define ASM_CALL_IRQ							\
 	"call irq_enter_rcu				\n"		\
-	"movq	%[arg1], %%rdi				\n"		\
-	"movl	%[arg2], %%esi				\n"		\
-	"call %P[__func]				\n"		\
+	ASM_CALL_ARG2							\
 	"call irq_exit_rcu				\n"
 
-#define IRQ_CONSTRAINTS	, [arg1] "r" (regs), [arg2] "r" (vector)
+#define IRQ_CONSTRAINTS	, [arg1] "r" (regs), [arg2] "r" ((unsigned long)vector)
 
 #define run_irq_on_irqstack_cond(func, regs, vector)			\
 {									\
···
 }
 
 #ifndef CONFIG_PREEMPT_RT
-#define ASM_CALL_SOFTIRQ						\
-	"call %P[__func]				\n"
-
 /*
  * Macro to invoke __do_softirq on the irq stack. This is only called from
  * task context when bottom halves are about to be reenabled and soft
···
 #define do_softirq_own_stack()						\
 {									\
 	__this_cpu_write(hardirq_stack_inuse, true);			\
-	call_on_irqstack(__do_softirq, ASM_CALL_SOFTIRQ);		\
+	call_on_irqstack(__do_softirq, ASM_CALL_ARG0);			\
 	__this_cpu_write(hardirq_stack_inuse, false);			\
 }
 

arch/x86/include/asm/page_64_types.h

···
 #define THREAD_SIZE_ORDER	(2 + KASAN_STACK_ORDER)
 #define THREAD_SIZE  (PAGE_SIZE << THREAD_SIZE_ORDER)
 
-#define EXCEPTION_STACK_ORDER (0 + KASAN_STACK_ORDER)
+#define EXCEPTION_STACK_ORDER (1 + KASAN_STACK_ORDER)
 #define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER)
 
 #define IRQ_STACK_ORDER (2 + KASAN_STACK_ORDER)

arch/x86/include/asm/processor.h

···
 	 */
 	unsigned long		iopl_emul;
 
+	unsigned int		iopl_warn:1;
 	unsigned int		sig_on_uaccess_err:1;
 
 	/*

arch/x86/include/asm/stacktrace.h

···
 bool get_stack_info_noinstr(unsigned long *stack, struct task_struct *task,
 			    struct stack_info *info);
 
+static __always_inline
+bool get_stack_guard_info(unsigned long *stack, struct stack_info *info)
+{
+	/* make sure it's not in the stack proper */
+	if (get_stack_info_noinstr(stack, current, info))
+		return false;
+	/* but if it is in the page below it, we hit a guard */
+	return get_stack_info_noinstr((void *)stack + PAGE_SIZE, current, info);
+}
+
 const char *stack_type_name(enum stack_type type);
 
 static inline bool on_stack(struct stack_info *info, void *addr, size_t len)

arch/x86/include/asm/traps.h

···
 bool fault_in_kernel_space(unsigned long address);
 
 #ifdef CONFIG_VMAP_STACK
-void __noreturn handle_stack_overflow(const char *message,
-				      struct pt_regs *regs,
-				      unsigned long fault_address);
+void __noreturn handle_stack_overflow(struct pt_regs *regs,
+				      unsigned long fault_address,
+				      struct stack_info *info);
 #endif
 
 #endif /* _ASM_X86_TRAPS_H */

arch/x86/kernel/dumpstack_64.c

···
 {
 	BUILD_BUG_ON(N_EXCEPTION_STACKS != 6);
 
+	if (type == STACK_TYPE_TASK)
+		return "TASK";
+
 	if (type == STACK_TYPE_IRQ)
 		return "IRQ";
+
+	if (type == STACK_TYPE_SOFTIRQ)
+		return "SOFTIRQ";
 
 	if (type == STACK_TYPE_ENTRY) {
 		/*

arch/x86/kernel/process.c

···
 	frame->ret_addr = (unsigned long) ret_from_fork;
 	p->thread.sp = (unsigned long) fork_frame;
 	p->thread.io_bitmap = NULL;
+	p->thread.iopl_warn = 0;
 	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
 
 #ifdef CONFIG_X86_64

arch/x86/kernel/sev.c

···
 struct sev_es_runtime_data {
 	struct ghcb ghcb_page;
 
-	/* Physical storage for the per-CPU IST stack of the #VC handler */
-	char ist_stack[EXCEPTION_STKSZ] __aligned(PAGE_SIZE);
-
-	/*
-	 * Physical storage for the per-CPU fall-back stack of the #VC handler.
-	 * The fall-back stack is used when it is not safe to switch back to the
-	 * interrupted stack in the #VC entry code.
-	 */
-	char fallback_stack[EXCEPTION_STKSZ] __aligned(PAGE_SIZE);
-
 	/*
 	 * Reserve one page per CPU as backup storage for the unencrypted GHCB.
 	 * It is needed when an NMI happens while the #VC handler uses the real
···
 
 /* Needed in vc_early_forward_exception */
 void do_early_exception(struct pt_regs *regs, int trapnr);
-
-static void __init setup_vc_stacks(int cpu)
-{
-	struct sev_es_runtime_data *data;
-	struct cpu_entry_area *cea;
-	unsigned long vaddr;
-	phys_addr_t pa;
-
-	data = per_cpu(runtime_data, cpu);
-	cea  = get_cpu_entry_area(cpu);
-
-	/* Map #VC IST stack */
-	vaddr = CEA_ESTACK_BOT(&cea->estacks, VC);
-	pa    = __pa(data->ist_stack);
-	cea_set_pte((void *)vaddr, pa, PAGE_KERNEL);
-
-	/* Map VC fall-back stack */
-	vaddr = CEA_ESTACK_BOT(&cea->estacks, VC2);
-	pa    = __pa(data->fallback_stack);
-	cea_set_pte((void *)vaddr, pa, PAGE_KERNEL);
-}
 
 static __always_inline bool on_vc_stack(struct pt_regs *regs)
 {
···
 	for_each_possible_cpu(cpu) {
 		alloc_runtime_data(cpu);
 		init_ghcb(cpu);
-		setup_vc_stacks(cpu);
 	}
 
 	sev_es_setup_play_dead();

arch/x86/kernel/traps.c

···
 }
 
 #ifdef CONFIG_VMAP_STACK
-__visible void __noreturn handle_stack_overflow(const char *message,
-						struct pt_regs *regs,
-						unsigned long fault_address)
+__visible void __noreturn handle_stack_overflow(struct pt_regs *regs,
+						unsigned long fault_address,
+						struct stack_info *info)
 {
-	printk(KERN_EMERG "BUG: stack guard page was hit at %p (stack is %p..%p)\n",
-		 (void *)fault_address, current->stack,
-		 (char *)current->stack + THREAD_SIZE - 1);
-	die(message, regs, 0);
+	const char *name = stack_type_name(info->type);
+
+	printk(KERN_EMERG "BUG: %s stack guard page was hit at %p (stack is %p..%p)\n",
+	       name, (void *)fault_address, info->begin, info->end);
+
+	die("stack guard page", regs, 0);
 
 	/* Be absolutely certain we don't return. */
-	panic("%s", message);
+	panic("%s stack guard hit", name);
 }
 #endif
 
···
 
 #ifdef CONFIG_VMAP_STACK
 	unsigned long address = read_cr2();
+	struct stack_info info;
 #endif
 
 #ifdef CONFIG_X86_ESPFIX64
···
 	 * stack even if the actual trigger for the double fault was
 	 * something else.
 	 */
-	if ((unsigned long)task_stack_page(tsk) - 1 - address < PAGE_SIZE) {
-		handle_stack_overflow("kernel stack overflow (double-fault)",
-				      regs, address);
-	}
+	if (get_stack_guard_info((void *)address, &info))
+		handle_stack_overflow(regs, address, &info);
 #endif
 
 	pr_emerg("PANIC: double fault, error_code: 0x%lx\n", error_code);
···
 
 #define GPFSTR "general protection fault"
 
+static bool fixup_iopl_exception(struct pt_regs *regs)
+{
+	struct thread_struct *t = &current->thread;
+	unsigned char byte;
+	unsigned long ip;
+
+	if (!IS_ENABLED(CONFIG_X86_IOPL_IOPERM) || t->iopl_emul != 3)
+		return false;
+
+	if (insn_get_effective_ip(regs, &ip))
+		return false;
+
+	if (get_user(byte, (const char __user *)ip))
+		return false;
+
+	if (byte != 0xfa && byte != 0xfb)
+		return false;
+
+	if (!t->iopl_warn && printk_ratelimit()) {
+		pr_err("%s[%d] attempts to use CLI/STI, pretending it's a NOP, ip:%lx",
+		       current->comm, task_pid_nr(current), ip);
+		print_vma_addr(KERN_CONT " in ", ip);
+		pr_cont("\n");
+		t->iopl_warn = 1;
+	}
+
+	regs->ip += 1;
+	return true;
+}
+
 DEFINE_IDTENTRY_ERRORCODE(exc_general_protection)
 {
 	char desc[sizeof(GPFSTR) + 50 + 2*sizeof(unsigned long) + 1] = GPFSTR;
···
 	tsk = current;
 
 	if (user_mode(regs)) {
+		if (fixup_iopl_exception(regs))
+			goto exit;
+
 		tsk->thread.error_code = error_code;
 		tsk->thread.trap_nr = X86_TRAP_GP;
 

arch/x86/lib/insn-eval.c

···
 	}
 }
 
-static int insn_get_effective_ip(struct pt_regs *regs, unsigned long *ip)
+int insn_get_effective_ip(struct pt_regs *regs, unsigned long *ip)
 {
 	unsigned long seg_base = 0;
 

arch/x86/lib/kaslr.c

···
 	unsigned long raw, random = get_boot_seed();
 	bool use_i8254 = true;
 
-	debug_putstr(purpose);
-	debug_putstr(" KASLR using");
+	if (purpose) {
+		debug_putstr(purpose);
+		debug_putstr(" KASLR using");
+	}
 
 	if (has_cpuflag(X86_FEATURE_RDRAND)) {
-		debug_putstr(" RDRAND");
+		if (purpose)
+			debug_putstr(" RDRAND");
 		if (rdrand_long(&raw)) {
 			random ^= raw;
 			use_i8254 = false;
···
 	}
 
 	if (has_cpuflag(X86_FEATURE_TSC)) {
-		debug_putstr(" RDTSC");
+		if (purpose)
+			debug_putstr(" RDTSC");
 		raw = rdtsc();
 
 		random ^= raw;
···
 	}
 
 	if (use_i8254) {
-		debug_putstr(" i8254");
+		if (purpose)
+			debug_putstr(" i8254");
 		random ^= i8254();
 	}
 
···
 	    : "a" (random), "rm" (mix_const));
 	random += raw;
 
-	debug_putstr("...\n");
+	if (purpose)
+		debug_putstr("...\n");
 
 	return random;
 }

arch/x86/mm/cpu_entry_area.c

···
 	cea_map_stack(NMI);
 	cea_map_stack(DB);
 	cea_map_stack(MCE);
+
+	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) {
+		if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) {
+			cea_map_stack(VC);
+			cea_map_stack(VC2);
+		}
+	}
 }
 #else
 static inline void percpu_setup_exception_stacks(unsigned int cpu)

arch/x86/mm/fault.c

···
 #include <asm/pgtable_areas.h>		/* VMALLOC_START, ...		*/
 #include <asm/kvm_para.h>		/* kvm_handle_async_pf		*/
 #include <asm/vdso.h>			/* fixup_vdso_exception()	*/
+#include <asm/irq_stack.h>
 
 #define CREATE_TRACE_POINTS
 #include <asm/trace/exceptions.h>
···
 page_fault_oops(struct pt_regs *regs, unsigned long error_code,
 		unsigned long address)
 {
+#ifdef CONFIG_VMAP_STACK
+	struct stack_info info;
+#endif
 	unsigned long flags;
 	int sig;
 
···
 	 * that we're in vmalloc space to avoid this.
 	 */
 	if (is_vmalloc_addr((void *)address) &&
-	    (((unsigned long)current->stack - 1 - address < PAGE_SIZE) ||
-	     address - ((unsigned long)current->stack + THREAD_SIZE) < PAGE_SIZE)) {
-		unsigned long stack = __this_cpu_ist_top_va(DF) - sizeof(void *);
+	    get_stack_guard_info((void *)address, &info)) {
 		/*
 		 * We're likely to be running with very little stack space
 		 * left.  It's plausible that we'd hit this condition but
···
 		 * and then double-fault, though, because we're likely to
 		 * break the console driver and lose most of the stack dump.
 		 */
-		asm volatile ("movq %[stack], %%rsp\n\t"
-			      "call handle_stack_overflow\n\t"
-			      "1: jmp 1b"
-			      : ASM_CALL_CONSTRAINT
-			      : "D" ("kernel stack overflow (page fault)"),
-				"S" (regs), "d" (address),
-				[stack] "rm" (stack));
+		call_on_stack(__this_cpu_ist_top_va(DF) - sizeof(void*),
+			      handle_stack_overflow,
+			      ASM_CALL_ARG3,
+			      , [arg1] "r" (regs), [arg2] "r" (address), [arg3] "r" (&info));
+
 		unreachable();
 	}
 #endif

arch/x86/tools/relocs.c

···
 static Elf_Ehdr		ehdr;
 static unsigned long	shnum;
 static unsigned int	shstrndx;
+static unsigned int	shsymtabndx;
+static unsigned int	shxsymtabndx;
+
+static int sym_index(Elf_Sym *sym);
 
 struct relocs {
 	uint32_t	*offset;
···
 	Elf_Shdr       shdr;
 	struct section *link;
 	Elf_Sym        *symtab;
+	Elf32_Word     *xsymtab;
 	Elf_Rel        *reltab;
 	char           *strtab;
 };
···
 		name = sym_strtab + sym->st_name;
 	}
 	else {
-		name = sec_name(sym->st_shndx);
+		name = sec_name(sym_index(sym));
 	}
 	return name;
 }
···
 #define elf_off_to_cpu(x)	elf32_to_cpu(x)
 #define elf_xword_to_cpu(x)	elf32_to_cpu(x)
 #endif
+
+static int sym_index(Elf_Sym *sym)
+{
+	Elf_Sym *symtab = secs[shsymtabndx].symtab;
+	Elf32_Word *xsymtab = secs[shxsymtabndx].xsymtab;
+	unsigned long offset;
+	int index;
+
+	if (sym->st_shndx != SHN_XINDEX)
+		return sym->st_shndx;
+
+	/* calculate offset of sym from head of table. */
+	offset = (unsigned long)sym - (unsigned long)symtab;
+	index = offset / sizeof(*sym);
+
+	return elf32_to_cpu(xsymtab[index]);
+}
 
 static void read_ehdr(FILE *fp)
 {
···
 static void read_symtabs(FILE *fp)
 {
 	int i,j;
+
 	for (i = 0; i < shnum; i++) {
 		struct section *sec = &secs[i];
-		if (sec->shdr.sh_type != SHT_SYMTAB) {
+		int num_syms;
+
+		switch (sec->shdr.sh_type) {
+		case SHT_SYMTAB_SHNDX:
+			sec->xsymtab = malloc(sec->shdr.sh_size);
+			if (!sec->xsymtab) {
+				die("malloc of %" FMT " bytes for xsymtab failed\n",
+				    sec->shdr.sh_size);
+			}
+			if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) {
+				die("Seek to %" FMT " failed: %s\n",
+				    sec->shdr.sh_offset, strerror(errno));
+			}
+			if (fread(sec->xsymtab, 1, sec->shdr.sh_size, fp)
+			    != sec->shdr.sh_size) {
+				die("Cannot read extended symbol table: %s\n",
+				    strerror(errno));
+			}
+			shxsymtabndx = i;
 			continue;
-		}
-		sec->symtab = malloc(sec->shdr.sh_size);
-		if (!sec->symtab) {
-			die("malloc of %" FMT " bytes for symtab failed\n",
-			    sec->shdr.sh_size);
-		}
-		if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) {
-			die("Seek to %" FMT " failed: %s\n",
-			    sec->shdr.sh_offset, strerror(errno));
-		}
-		if (fread(sec->symtab, 1, sec->shdr.sh_size, fp)
-		    != sec->shdr.sh_size) {
-			die("Cannot read symbol table: %s\n",
-				strerror(errno));
-		}
-		for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Sym); j++) {
-			Elf_Sym *sym = &sec->symtab[j];
-			sym->st_name  = elf_word_to_cpu(sym->st_name);
-			sym->st_value = elf_addr_to_cpu(sym->st_value);
-			sym->st_size  = elf_xword_to_cpu(sym->st_size);
-			sym->st_shndx = elf_half_to_cpu(sym->st_shndx);
+
+		case SHT_SYMTAB:
+			num_syms = sec->shdr.sh_size / sizeof(Elf_Sym);
+
+			sec->symtab = malloc(sec->shdr.sh_size);
+			if (!sec->symtab) {
+				die("malloc of %" FMT " bytes for symtab failed\n",
+				    sec->shdr.sh_size);
+			}
+			if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) {
+				die("Seek to %" FMT " failed: %s\n",
+				    sec->shdr.sh_offset, strerror(errno));
+			}
+			if (fread(sec->symtab, 1, sec->shdr.sh_size, fp)
+			    != sec->shdr.sh_size) {
+				die("Cannot read symbol table: %s\n",
+				    strerror(errno));
+			}
+			for (j = 0; j < num_syms; j++) {
+				Elf_Sym *sym = &sec->symtab[j];
+
+				sym->st_name  = elf_word_to_cpu(sym->st_name);
+				sym->st_value = elf_addr_to_cpu(sym->st_value);
+				sym->st_size  = elf_xword_to_cpu(sym->st_size);
+				sym->st_shndx = elf_half_to_cpu(sym->st_shndx);
+			}
+			shsymtabndx = i;
+			continue;
+
+		default:
+			continue;
 		}
 	}
 }
···
  */
 static int is_percpu_sym(ElfW(Sym) *sym, const char *symname)
 {
-	return (sym->st_shndx == per_cpu_shndx) &&
+	int shndx = sym_index(sym);
+
+	return (shndx == per_cpu_shndx) &&
 		strcmp(symname, "__init_begin") &&
 		strcmp(symname, "__per_cpu_load") &&
 		strncmp(symname, "init_per_cpu_", 13);
···
 		sec_name(sec->shdr.sh_info),
 		rel_type(ELF_R_TYPE(rel->r_info)),
 		symname,
-		sec_name(sym->st_shndx));
+		sec_name(sym_index(sym)));
 	return 0;
 }
 

include/asm-generic/vmlinux.lds.h

···
 		KEEP(*(.orc_unwind))					\
 		__stop_orc_unwind = .;					\
 	}								\
+	text_size = _etext - _stext;					\
 	. = ALIGN(4);							\
 	.orc_lookup : AT(ADDR(.orc_lookup) - LOAD_OFFSET) {		\
 		orc_lookup = .;						\
-		. += (((SIZEOF(.text) + LOOKUP_BLOCK_SIZE - 1) /	\
+		. += (((text_size + LOOKUP_BLOCK_SIZE - 1) /		\
 			LOOKUP_BLOCK_SIZE) + 1) * 4;			\
 		orc_lookup_end = .;					\
 	}

include/linux/decompress/mm.h

···
 #define STATIC_RW_DATA static
 #endif
 
+/*
+ * When an architecture needs to share the malloc()/free() implementation
+ * between compilation units, it needs to have non-local visibility.
+ */
+#ifndef MALLOC_VISIBLE
+#define MALLOC_VISIBLE static
+#endif
+
 /* A trivial malloc implementation, adapted from
  *  malloc by Hannu Savolainen 1993 and Matthias Urlichs 1994
  */
 STATIC_RW_DATA unsigned long malloc_ptr;
 STATIC_RW_DATA int malloc_count;
 
-static void *malloc(int size)
+MALLOC_VISIBLE void *malloc(int size)
 {
 	void *p;
 
···
 	return p;
 }
 
-static void free(void *where)
+MALLOC_VISIBLE void free(void *where)
 {
 	malloc_count--;
 	if (!malloc_count)

tools/testing/selftests/x86/iopl.c

···
 	printf("[OK]\toutb to 0x%02hx failed\n", port);
 }
 
-static bool try_cli(void)
+#define RET_FAULTED	0
+#define RET_FAIL	1
+#define RET_EMUL	2
+
+static int try_cli(void)
 {
+	unsigned long flags;
+
 	sethandler(SIGSEGV, sigsegv, SA_RESETHAND);
 	if (sigsetjmp(jmpbuf, 1) != 0) {
-		return false;
+		return RET_FAULTED;
 	} else {
-		asm volatile ("cli");
-		return true;
+		asm volatile("cli; pushf; pop %[flags]"
+				: [flags] "=rm" (flags));
+
+		/* X86_FLAGS_IF */
+		if (!(flags & (1 << 9)))
+			return RET_FAIL;
+		else
+			return RET_EMUL;
 	}
 	clearhandler(SIGSEGV);
 }
 
-static bool try_sti(void)
+static int try_sti(bool irqs_off)
 {
+	unsigned long flags;
+
 	sethandler(SIGSEGV, sigsegv, SA_RESETHAND);
 	if (sigsetjmp(jmpbuf, 1) != 0) {
-		return false;
+		return RET_FAULTED;
 	} else {
-		asm volatile ("sti");
-		return true;
+		asm volatile("sti; pushf; pop %[flags]"
+				: [flags] "=rm" (flags));
+
+		/* X86_FLAGS_IF */
+		if (irqs_off && (flags & (1 << 9)))
+			return RET_FAIL;
+		else
+			return RET_EMUL;
 	}
 	clearhandler(SIGSEGV);
 }
 
-static void expect_gp_sti(void)
+static void expect_gp_sti(bool irqs_off)
 {
-	if (try_sti()) {
+	int ret = try_sti(irqs_off);
+
+	switch (ret) {
+	case RET_FAULTED:
+		printf("[OK]\tSTI faulted\n");
+		break;
+	case RET_EMUL:
+		printf("[OK]\tSTI NOPped\n");
+		break;
+	default:
 		printf("[FAIL]\tSTI worked\n");
 		nerrs++;
-	} else {
-		printf("[OK]\tSTI faulted\n");
 	}
 }
 
-static void expect_gp_cli(void)
+/*
+ * Returns whether it managed to disable interrupts.
+ */
+static bool test_cli(void)
 {
-	if (try_cli()) {
+	int ret = try_cli();
+
+	switch (ret) {
+	case RET_FAULTED:
+		printf("[OK]\tCLI faulted\n");
+		break;
+	case RET_EMUL:
+		printf("[OK]\tCLI NOPped\n");
+		break;
+	default:
 		printf("[FAIL]\tCLI worked\n");
 		nerrs++;
-	} else {
-		printf("[OK]\tCLI faulted\n");
+		return true;
 	}
+
+	return false;
 }
 
 int main(void)
···
 	}
 
 	/* Make sure that CLI/STI are blocked even with IOPL level 3 */
-	expect_gp_cli();
-	expect_gp_sti();
+	expect_gp_sti(test_cli());
 	expect_ok_outb(0x80);
 
 	/* Establish an I/O bitmap to test the restore */
···
 	printf("[RUN]\tparent: write to 0x80 (should fail)\n");
 
 	expect_gp_outb(0x80);
-	expect_gp_cli();
-	expect_gp_sti();
+	expect_gp_sti(test_cli());
 
 	/* Test the capability checks. */
 	printf("\tiopl(3)\n");