sparc64: Fix register corruption in top-most kernel stack frame during boot.

Meelis Roos reported that kernels built with gcc-4.9 do not boot, we
eventually narrowed this down to only impacting machines using
UltraSPARC-III and derivitive cpus.

The crash happens right when the first user process is spawned:

[   54.451346] Kernel panic - not syncing: Attempted to kill init! exitcode=0x00000004
[   54.451346]
[   54.571516] CPU: 1 PID: 1 Comm: init Not tainted 3.16.0-rc2-00211-gd7933ab #96
[   54.666431] Call Trace:
[   54.698453]  [0000000000762f8c] panic+0xb0/0x224
[   54.759071]  [000000000045cf68] do_exit+0x948/0x960
[   54.823123]  [000000000042cbc0] fault_in_user_windows+0xe0/0x100
[   54.902036]  [0000000000404ad0] __handle_user_windows+0x0/0x10
[   54.978662] Press Stop-A (L1-A) to return to the boot prom
[   55.050713] ---[ end Kernel panic - not syncing: Attempted to kill init! exitcode=0x00000004

Further investigation showed that compiling only per_cpu_patch() with
an older compiler fixes the boot.

Detailed analysis showed that the function is not being miscompiled by
gcc-4.9, but it is using a different register allocation ordering.

With the gcc-4.9 compiled function, something during the code patching
causes some of the %i* input registers to get corrupted.  Perhaps
we have a TLB miss path into the firmware that is deep enough to
cause a register window spill and subsequent restore when we get
back from the TLB miss trap.

Let's plug this up by doing two things:

1) Stop using the firmware stack for client interface calls into
   the firmware.  Just use the kernel's stack.

2) As soon as we can, call into a new function "start_early_boot()"
   to put a one-register-window buffer between the firmware's
   deepest stack frame and the top-most initial kernel one.

Reported-by: Meelis Roos <mroos@linux.ee>
Tested-by: Meelis Roos <mroos@linux.ee>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 20 insertions, 8 deletions

diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index e629b8377587..c38d19fc27ba 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -30,6 +30,7 @@
 #include <linux/cpu.h>
 #include <linux/initrd.h>
 #include <linux/module.h>
+#include <linux/start_kernel.h>
 
 #include <asm/io.h>
 #include <asm/processor.h>
@@ -162,7 +163,7 @@ char reboot_command[COMMAND_LINE_SIZE];
 
 static struct pt_regs fake_swapper_regs = { { 0, }, 0, 0, 0, 0 };
 
-void __init per_cpu_patch(void)
+static void __init per_cpu_patch(void)
 {
 	struct cpuid_patch_entry *p;
 	unsigned long ver;
@@ -254,7 +255,7 @@ void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *start,
 	}
 }
 
-void __init sun4v_patch(void)
+static void __init sun4v_patch(void)
 {
 	extern void sun4v_hvapi_init(void);
 
@@ -323,14 +324,25 @@ static void __init pause_patch(void)
 	}
 }
 
-#ifdef CONFIG_SMP
-void __init boot_cpu_id_too_large(int cpu)
+void __init start_early_boot(void)
 {
-	prom_printf("Serious problem, boot cpu id (%d) >= NR_CPUS (%d)\n",
-		    cpu, NR_CPUS);
-	prom_halt();
+	int cpu;
+
+	check_if_starfire();
+	per_cpu_patch();
+	sun4v_patch();
+
+	cpu = hard_smp_processor_id();
+	if (cpu >= NR_CPUS) {
+		prom_printf("Serious problem, boot cpu id (%d) >= NR_CPUS (%d)\n",
+			    cpu, NR_CPUS);
+		prom_halt();
+	}
+	current_thread_info()->cpu = cpu;
+
+	prom_init_report();
+	start_kernel();
 }
-#endif
 
 /* On Ultra, we support all of the v8 capabilities. */
 unsigned long sparc64_elf_hwcap = (HWCAP_SPARC_FLUSH | HWCAP_SPARC_STBAR |