From 328d2168ca524d501fc4b133d6be076142bd305c Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Tue, 27 Oct 2020 15:01:17 -0700 Subject: ARC: stack unwinding: avoid indefinite looping Currently stack unwinder is a while(1) loop which relies on the dwarf unwinder to signal termination, which in turn relies on dwarf info to do so. This in theory could cause an infinite loop if the dwarf info was somehow messed up or the register contents were etc. This fix thus detects the excessive looping and breaks the loop. | Mem: 26184K used, 1009136K free, 0K shrd, 0K buff, 14416K cached | CPU: 0.0% usr 72.8% sys 0.0% nic 27.1% idle 0.0% io 0.0% irq 0.0% sirq | Load average: 4.33 2.60 1.11 2/74 139 | PID PPID USER STAT VSZ %VSZ CPU %CPU COMMAND | 133 2 root SWN 0 0.0 3 22.9 [rcu_torture_rea] | 132 2 root SWN 0 0.0 0 22.0 [rcu_torture_rea] | 131 2 root SWN 0 0.0 3 21.5 [rcu_torture_rea] | 126 2 root RW 0 0.0 2 5.4 [rcu_torture_wri] | 129 2 root SWN 0 0.0 0 0.2 [rcu_torture_fak] | 137 2 root SW 0 0.0 0 0.2 [rcu_torture_cbf] | 127 2 root SWN 0 0.0 0 0.1 [rcu_torture_fak] | 138 115 root R 1464 0.1 2 0.1 top | 130 2 root SWN 0 0.0 0 0.1 [rcu_torture_fak] | 128 2 root SWN 0 0.0 0 0.1 [rcu_torture_fak] | 115 1 root S 1472 0.1 1 0.0 -/bin/sh | 104 1 root S 1464 0.1 0 0.0 inetd | 1 0 root S 1456 0.1 2 0.0 init | 78 1 root S 1456 0.1 0 0.0 syslogd -O /var/log/messages | 134 2 root SW 0 0.0 2 0.0 [rcu_torture_sta] | 10 2 root IW 0 0.0 1 0.0 [rcu_preempt] | 88 2 root IW 0 0.0 1 0.0 [kworker/1:1-eve] | 66 2 root IW 0 0.0 2 0.0 [kworker/2:2-eve] | 39 2 root IW 0 0.0 2 0.0 [kworker/2:1-eve] | unwinder looping too long, aborting ! Cc: Signed-off-by: Vineet Gupta --- arch/arc/kernel/stacktrace.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index feba91c9d969..b23986f98450 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -112,7 +112,7 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, int (*consumer_fn) (unsigned int, void *), void *arg) { #ifdef CONFIG_ARC_DW2_UNWIND - int ret = 0; + int ret = 0, cnt = 0; unsigned int address; struct unwind_frame_info frame_info; @@ -132,6 +132,11 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, break; frame_info.regs.r63 = frame_info.regs.r31; + + if (cnt++ > 128) { + printk("unwinder looping too long, aborting !\n"); + return 0; + } } return address; /* return the last address it saw */ -- cgit v1.2.3-58-ga151 From 3b57533b460c8dc22a432684b7e8d22571f34d2e Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Thu, 29 Oct 2020 19:18:34 -0700 Subject: ARC: [plat-hsdk] Remap CCMs super early in asm boot trampoline ARC HSDK platform stopped booting on released v5.10-rc1, getting stuck in startup of non master SMP cores. This was bisected to upstream commit 7fef431be9c9ac25 "(mm/page_alloc: place pages to tail in __free_pages_core())" That commit itself is harmless, it just exposed a subtle assumption in our platform code (hence CC'ing linux-mm just as FYI in case some other arches / platforms trip on it). The upstream commit is semantically disruptive as it reverses the order of page allocations (actually it can be good test for hardware verification to exercise different memory patterns altogether). For ARC HSDK platform that meant a remapped memory region (pertaining to unused Closely Coupled Memory) started getting used early for dynamice allocations, while not effectively remapped on all the cores, triggering memory error exception on those cores. The fix is to move the CCM remapping from early platform code to to early core boot code. And while it is undesirable to riddle common boot code with platform quirks, there is no other way to do this since the faltering code involves setting up stack itself so even function calls are not allowed at that point. If anyone is interested, all the gory details can be found at Link below. Link: https://github.com/foss-for-synopsys-dwc-arc-processors/linux/issues/32 Cc: David Hildenbrand Cc: linux-mm@kvack.org Signed-off-by: Vineet Gupta --- arch/arc/kernel/head.S | 17 ++++++++++++++++- arch/arc/plat-hsdk/platform.c | 17 ----------------- 2 files changed, 16 insertions(+), 18 deletions(-) (limited to 'arch') diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 17fd1ed700cc..9152782444b5 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -67,7 +67,22 @@ sr r5, [ARC_REG_LPB_CTRL] 1: #endif /* CONFIG_ARC_LPB_DISABLE */ -#endif + + /* On HSDK, CCMs need to remapped super early */ +#ifdef CONFIG_ARC_SOC_HSDK + mov r6, 0x60000000 + lr r5, [ARC_REG_ICCM_BUILD] + breq r5, 0, 1f + sr r6, [ARC_REG_AUX_ICCM] +1: + lr r5, [ARC_REG_DCCM_BUILD] + breq r5, 0, 2f + sr r6, [ARC_REG_AUX_DCCM] +2: +#endif /* CONFIG_ARC_SOC_HSDK */ + +#endif /* CONFIG_ISA_ARCV2 */ + ; Config DSP_CTRL properly, so kernel may use integer multiply, ; multiply-accumulate, and divide operations DSP_EARLY_INIT diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c index 0b63fc095b99..b3ea1fa11f87 100644 --- a/arch/arc/plat-hsdk/platform.c +++ b/arch/arc/plat-hsdk/platform.c @@ -17,22 +17,6 @@ int arc_hsdk_axi_dmac_coherent __section(".data") = 0; #define ARC_CCM_UNUSED_ADDR 0x60000000 -static void __init hsdk_init_per_cpu(unsigned int cpu) -{ - /* - * By default ICCM is mapped to 0x7z while this area is used for - * kernel virtual mappings, so move it to currently unused area. - */ - if (cpuinfo_arc700[cpu].iccm.sz) - write_aux_reg(ARC_REG_AUX_ICCM, ARC_CCM_UNUSED_ADDR); - - /* - * By default DCCM is mapped to 0x8z while this area is used by kernel, - * so move it to currently unused area. - */ - if (cpuinfo_arc700[cpu].dccm.sz) - write_aux_reg(ARC_REG_AUX_DCCM, ARC_CCM_UNUSED_ADDR); -} #define ARC_PERIPHERAL_BASE 0xf0000000 #define CREG_BASE (ARC_PERIPHERAL_BASE + 0x1000) @@ -339,5 +323,4 @@ static const char *hsdk_compat[] __initconst = { MACHINE_START(SIMULATION, "hsdk") .dt_compat = hsdk_compat, .init_early = hsdk_init_early, - .init_per_cpu = hsdk_init_per_cpu, MACHINE_END -- cgit v1.2.3-58-ga151