From ef3e035c3a9b81da8a778bc333d10637acf6c199 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 23 Oct 2014 12:58:13 -0700 Subject: 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 Tested-by: Meelis Roos Signed-off-by: David S. Miller --- arch/sparc/kernel/head_64.S | 40 ++++------------------------------------ 1 file changed, 4 insertions(+), 36 deletions(-) (limited to 'arch/sparc/kernel/head_64.S') diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index 4fdeb8040d4d..3d61fcae7ee3 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -672,14 +672,12 @@ tlb_fixup_done: sethi %hi(init_thread_union), %g6 or %g6, %lo(init_thread_union), %g6 ldx [%g6 + TI_TASK], %g4 - mov %sp, %l6 wr %g0, ASI_P, %asi mov 1, %g1 sllx %g1, THREAD_SHIFT, %g1 sub %g1, (STACKFRAME_SZ + STACK_BIAS), %g1 add %g6, %g1, %sp - mov 0, %fp /* Set per-cpu pointer initially to zero, this makes * the boot-cpu use the in-kernel-image per-cpu areas @@ -706,44 +704,14 @@ tlb_fixup_done: nop #endif - mov %l6, %o1 ! OpenPROM stack call prom_init mov %l7, %o0 ! OpenPROM cif handler - /* Initialize current_thread_info()->cpu as early as possible. - * In order to do that accurately we have to patch up the get_cpuid() - * assembler sequences. And that, in turn, requires that we know - * if we are on a Starfire box or not. While we're here, patch up - * the sun4v sequences as well. + /* To create a one-register-window buffer between the kernel's + * initial stack and the last stack frame we use from the firmware, + * do the rest of the boot from a C helper function. */ - call check_if_starfire - nop - call per_cpu_patch - nop - call sun4v_patch - nop - -#ifdef CONFIG_SMP - call hard_smp_processor_id - nop - cmp %o0, NR_CPUS - blu,pt %xcc, 1f - nop - call boot_cpu_id_too_large - nop - /* Not reached... */ - -1: -#else - mov 0, %o0 -#endif - sth %o0, [%g6 + TI_CPU] - - call prom_init_report - nop - - /* Off we go.... */ - call start_kernel + call start_early_boot nop /* Not reached... */ -- cgit v1.2.3-59-g8ed1b