Merge tag 'x86_urgent_for_v5.12-rc4' of git://git.kernel.org/pub/scm/…

…linux/kernel/git/tip/tip

Pull x86 fixes from Borislav Petkov:
 "The freshest pile of shiny x86 fixes for 5.12:

   - Add the arch-specific mapping between physical and logical CPUs to
     fix devicetree-node lookups

   - Restore the IRQ2 ignore logic

   - Fix get_nr_restart_syscall() to return the correct restart syscall
     number. Split in a 4-patches set to avoid kABI breakage when
     backporting to dead kernels"

* tag 'x86_urgent_for_v5.12-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/apic/of: Fix CPU devicetree-node lookups
  x86/ioapic: Ignore IRQ2 again
  x86: Introduce restart_block->arch_data to remove TS_COMPAT_RESTART
  x86: Introduce TS_COMPAT_RESTART to fix get_nr_restart_syscall()
  x86: Move TS_COMPAT back to asm/thread_info.h
  kernel, fs: Introduce and use set_restart_fn() and arch_set_restart_data()

arch/x86/include/asm/processor.h

@@ -551,15 +551,6 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset,
 	*size = fpu_kernel_xstate_size;
 }
 
-/*
- * Thread-synchronous status.
- *
- * This is different from the flags in that nobody else
- * ever touches our thread-synchronous status, so we don't
- * have to worry about atomic accesses.
- */
-#define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
-
 static inline void
 native_load_sp0(unsigned long sp0)
 {

arch/x86/include/asm/thread_info.h

@@ -205,10 +205,23 @@ static inline int arch_within_stack_frames(const void * const stack,
 
 #endif
 
+/*
+ * Thread-synchronous status.
+ *
+ * This is different from the flags in that nobody else
+ * ever touches our thread-synchronous status, so we don't
+ * have to worry about atomic accesses.
+ */
+#define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
+
+#ifndef __ASSEMBLY__
 #ifdef CONFIG_COMPAT
 #define TS_I386_REGS_POKED	0x0004	/* regs poked by 32-bit ptracer */
+
+#define arch_set_restart_data(restart)	\
+	do { restart->arch_data = current_thread_info()->status; } while (0)
+
 #endif
-#ifndef __ASSEMBLY__
 
 #ifdef CONFIG_X86_32
 #define in_ia32_syscall() true

arch/x86/kernel/apic/apic.c

@@ -2342,6 +2342,11 @@ static int cpuid_to_apicid[] = {
 	[0 ... NR_CPUS - 1] = -1,
 };
 
+bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
+{
+	return phys_id == cpuid_to_apicid[cpu];
+}
+
 #ifdef CONFIG_SMP
 /**
  * apic_id_is_primary_thread - Check whether APIC ID belongs to a primary thread

arch/x86/kernel/apic/io_apic.c

@@ -1032,6 +1032,16 @@ static int mp_map_pin_to_irq(u32 gsi, int idx, int ioapic, int pin,
 	if (idx >= 0 && test_bit(mp_irqs[idx].srcbus, mp_bus_not_pci)) {
 		irq = mp_irqs[idx].srcbusirq;
 		legacy = mp_is_legacy_irq(irq);
+		/*
+		 * IRQ2 is unusable for historical reasons on systems which
+		 * have a legacy PIC. See the comment vs. IRQ2 further down.
+		 *
+		 * If this gets removed at some point then the related code
+		 * in lapic_assign_system_vectors() needs to be adjusted as
+		 * well.
+		 */
+		if (legacy && irq == PIC_CASCADE_IR)
+			return -EINVAL;
 	}
 
 	mutex_lock(&ioapic_mutex);

arch/x86/kernel/signal.c

@@ -766,30 +766,8 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 
 static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs)
 {
-	/*
-	 * This function is fundamentally broken as currently
-	 * implemented.
-	 *
-	 * The idea is that we want to trigger a call to the
-	 * restart_block() syscall and that we want in_ia32_syscall(),
-	 * in_x32_syscall(), etc. to match whatever they were in the
-	 * syscall being restarted.  We assume that the syscall
-	 * instruction at (regs->ip - 2) matches whatever syscall
-	 * instruction we used to enter in the first place.
-	 *
-	 * The problem is that we can get here when ptrace pokes
-	 * syscall-like values into regs even if we're not in a syscall
-	 * at all.
-	 *
-	 * For now, we maintain historical behavior and guess based on
-	 * stored state.  We could do better by saving the actual
-	 * syscall arch in restart_block or (with caveats on x32) by
-	 * checking if regs->ip points to 'int $0x80'.  The current
-	 * behavior is incorrect if a tracer has a different bitness
-	 * than the tracee.
-	 */
 #ifdef CONFIG_IA32_EMULATION
-	if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED))
+	if (current->restart_block.arch_data & TS_COMPAT)
 		return __NR_ia32_restart_syscall;
 #endif
 #ifdef CONFIG_X86_X32_ABI

fs/select.c

@@ -1055,10 +1055,9 @@ static long do_restart_poll(struct restart_block *restart_block)
 
 	ret = do_sys_poll(ufds, nfds, to);
 
-	if (ret == -ERESTARTNOHAND) {
-		restart_block->fn = do_restart_poll;
-		ret = -ERESTART_RESTARTBLOCK;
-	}
+	if (ret == -ERESTARTNOHAND)
+		ret = set_restart_fn(restart_block, do_restart_poll);
+
 	return ret;
 }
 
@@ -1080,7 +1079,6 @@ SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
 		struct restart_block *restart_block;
 
 		restart_block = &current->restart_block;
-		restart_block->fn = do_restart_poll;
 		restart_block->poll.ufds = ufds;
 		restart_block->poll.nfds = nfds;
 
@@ -1091,7 +1089,7 @@ SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
 		} else
 			restart_block->poll.has_timeout = 0;
 
-		ret = -ERESTART_RESTARTBLOCK;
+		ret = set_restart_fn(restart_block, do_restart_poll);
 	}
 	return ret;
 }

include/linux/restart_block.h

@@ -23,6 +23,7 @@ enum timespec_type {
  * System call restart block.
  */
 struct restart_block {
+	unsigned long arch_data;
 	long (*fn)(struct restart_block *);
 	union {
 		/* For futex_wait and futex_wait_requeue_pi */

include/linux/thread_info.h

@@ -11,6 +11,7 @@
 #include <linux/types.h>
 #include <linux/bug.h>
 #include <linux/restart_block.h>
+#include <linux/errno.h>
 
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 /*
@@ -59,6 +60,18 @@ enum syscall_work_bit {
 
 #ifdef __KERNEL__
 
+#ifndef arch_set_restart_data
+#define arch_set_restart_data(restart) do { } while (0)
+#endif
+
+static inline long set_restart_fn(struct restart_block *restart,
+					long (*fn)(struct restart_block *))
+{
+	restart->fn = fn;
+	arch_set_restart_data(restart);
+	return -ERESTART_RESTARTBLOCK;
+}
+
 #ifndef THREAD_ALIGN
 #define THREAD_ALIGN	THREAD_SIZE
 #endif

kernel/futex.c

@@ -2728,14 +2728,13 @@ static int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
 		goto out;
 
 	restart = &current->restart_block;
-	restart->fn = futex_wait_restart;
 	restart->futex.uaddr = uaddr;
 	restart->futex.val = val;
 	restart->futex.time = *abs_time;
 	restart->futex.bitset = bitset;
 	restart->futex.flags = flags | FLAGS_HAS_TIMEOUT;
 
-	ret = -ERESTART_RESTARTBLOCK;
+	ret = set_restart_fn(restart, futex_wait_restart);
 
 out:
 	if (to) {

kernel/time/alarmtimer.c

@@ -854,9 +854,9 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
 	if (flags == TIMER_ABSTIME)
 		return -ERESTARTNOHAND;
 
-	restart->fn = alarm_timer_nsleep_restart;
 	restart->nanosleep.clockid = type;
 	restart->nanosleep.expires = exp;
+	set_restart_fn(restart, alarm_timer_nsleep_restart);
 	return ret;
 }
 

kernel/time/hrtimer.c

@@ -1957,9 +1957,9 @@ long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode,
 	}
 
 	restart = &current->restart_block;
-	restart->fn = hrtimer_nanosleep_restart;
 	restart->nanosleep.clockid = t.timer.base->clockid;
 	restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer);
+	set_restart_fn(restart, hrtimer_nanosleep_restart);
 out:
 	destroy_hrtimer_on_stack(&t.timer);
 	return ret;

kernel/time/posix-cpu-timers.c

@@ -1480,8 +1480,8 @@ static int posix_cpu_nsleep(const clockid_t which_clock, int flags,
 		if (flags & TIMER_ABSTIME)
 			return -ERESTARTNOHAND;
 
-		restart_block->fn = posix_cpu_nsleep_restart;
 		restart_block->nanosleep.clockid = which_clock;
+		set_restart_fn(restart_block, posix_cpu_nsleep_restart);
 	}
 	return error;
 }