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

4 files changed, 53 insertions, 44 deletions

diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 5601b95944fa..6c5defd6569a 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -32,9 +32,15 @@ const char *stack_type_name(enum stack_type type)
 {
 	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) {
 		/*
 		 * On 64-bit, we have a generic entry stack that we
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index eb470be0e5ae..e9ee8b526319 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -146,6 +146,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
 	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
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index c195ffe58049..74f0ec955384 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -46,16 +46,6 @@ static struct ghcb __initdata *boot_ghcb;
 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
@@ -99,27 +89,6 @@ DEFINE_STATIC_KEY_FALSE(sev_es_enable_key);
 /* 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)
 {
 	unsigned long sp = regs->sp;
@@ -788,7 +757,6 @@ void __init sev_es_init_vc_handling(void)
 	for_each_possible_cpu(cpu) {
 		alloc_runtime_data(cpu);
 		init_ghcb(cpu);
-		setup_vc_stacks(cpu);
 	}
 
 	sev_es_setup_play_dead();
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 43f70bc01762..c9d566dcf89a 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -313,17 +313,19 @@ out:
 }
 
 #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
 
@@ -353,6 +355,7 @@ DEFINE_IDTENTRY_DF(exc_double_fault)
 
 #ifdef CONFIG_VMAP_STACK
 	unsigned long address = read_cr2();
+	struct stack_info info;
 #endif
 
 #ifdef CONFIG_X86_ESPFIX64
@@ -455,10 +458,8 @@ DEFINE_IDTENTRY_DF(exc_double_fault)
 	 * 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);
@@ -528,6 +529,36 @@ static enum kernel_gp_hint get_kernel_gp_address(struct pt_regs *regs,
 
 #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;
@@ -553,6 +584,9 @@ DEFINE_IDTENTRY_ERRORCODE(exc_general_protection)
 	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;