From 41d82bdb40af74a88cff4589ea7a60091b11070e Mon Sep 17 00:00:00 2001 From: Li Zhong Date: Sun, 2 Dec 2012 20:19:22 +0000 Subject: [PATCH 1/6] powerpc: Fix MAX_STACK_TRACE_ENTRIES too low warning for ppc32 This patch fixes MAX_STACK_TRACE_ENTRIES too low warning for ppc32, which is similar to commit 12660b17. Reported-by: Christian Kujau Signed-off-by: Li Zhong Tested-by: Christian Kujau Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/entry_32.S | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index d22e73e4618b..e514de57a125 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -439,6 +439,8 @@ ret_from_fork: ret_from_kernel_thread: REST_NVGPRS(r1) bl schedule_tail + li r3,0 + stw r3,0(r1) mtlr r14 mr r3,r15 PPC440EP_ERR42 From 72640d880350165c3a7b8f2e4fb4bf852ea7b606 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 21 Jan 2013 17:23:26 +0000 Subject: [PATCH 2/6] powerpc/pasemi: Fix crash on reboot commit f96972f2dc "kernel/sys.c: call disable_nonboot_cpus() in kernel_restart()" added a call to disable_nonboot_cpus() on kernel_restart(), which tries to shutdown all the CPUs except the first one. The issue with the PA Semi, is that it does not support CPU hotplug. When the call is made to __cpu_down(), it calls the notifiers CPU_DOWN_PREPARE, and then tries to take the CPU down. One of the notifiers to the CPU hotplug code, is the cpufreq. The DOWN_PREPARE will call __cpufreq_remove_dev() which calls cpufreq_driver->exit. The PA Semi exit handler unmaps regions of I/O that is used by an interrupt that goes off constantly (system_reset_common, but it goes off during normal system operations too). I'm not sure exactly what this interrupt does. Running a simple function trace, you can see it goes off quite a bit: # tracer: function # # TASK-PID CPU# TIMESTAMP FUNCTION # | | | | | -0 [001] 1558.859363: .pasemi_system_reset_exception <-.system_reset_exception -0 [000] 1558.860112: .pasemi_system_reset_exception <-.system_reset_exception -0 [000] 1558.861109: .pasemi_system_reset_exception <-.system_reset_exception -0 [001] 1558.861361: .pasemi_system_reset_exception <-.system_reset_exception -0 [000] 1558.861437: .pasemi_system_reset_exception <-.system_reset_exception When the region is unmapped, the system crashes with: Disabling non-boot CPUs ... Error taking CPU1 down: -38 Unable to handle kernel paging request for data at address 0xd0000800903a0100 Faulting instruction address: 0xc000000000055fcc Oops: Kernel access of bad area, sig: 11 [#1] PREEMPT SMP NR_CPUS=64 NUMA PA Semi PWRficient Modules linked in: shpchp NIP: c000000000055fcc LR: c000000000055fb4 CTR: c0000000000df1fc REGS: c0000000012175d0 TRAP: 0300 Not tainted (3.8.0-rc4-test-dirty) MSR: 9000000000009032 CR: 24000088 XER: 00000000 SOFTE: 0 DAR: d0000800903a0100, DSISR: 42000000 TASK = c0000000010e9008[0] 'swapper/0' THREAD: c000000001214000 CPU: 0 GPR00: d0000800903a0000 c000000001217850 c0000000012167e0 0000000000000000 GPR04: 0000000000000000 0000000000000724 0000000000000724 0000000000000000 GPR08: 0000000000000000 0000000000000000 0000000000000001 0000000000a70000 GPR12: 0000000024000080 c00000000fff0000 ffffffffffffffff 000000003ffffae0 GPR16: ffffffffffffffff 0000000000a21198 0000000000000060 0000000000000000 GPR20: 00000000008fdd35 0000000000a21258 000000003ffffaf0 0000000000000417 GPR24: 0000000000a226d0 c000000000000000 0000000000000000 0000000000000000 GPR28: c00000000138b358 0000000000000000 c000000001144818 d0000800903a0100 NIP [c000000000055fcc] .set_astate+0x5c/0xa4 LR [c000000000055fb4] .set_astate+0x44/0xa4 Call Trace: [c000000001217850] [c000000000055fb4] .set_astate+0x44/0xa4 (unreliable) [c0000000012178f0] [c00000000005647c] .restore_astate+0x2c/0x34 [c000000001217980] [c000000000054668] .pasemi_system_reset_exception+0x6c/0x88 [c000000001217a00] [c000000000019ef0] .system_reset_exception+0x48/0x84 [c000000001217a80] [c000000000001e40] system_reset_common+0x140/0x180 Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pasemi/cpufreq.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/powerpc/platforms/pasemi/cpufreq.c b/arch/powerpc/platforms/pasemi/cpufreq.c index 95d00173029f..890f30e70f98 100644 --- a/arch/powerpc/platforms/pasemi/cpufreq.c +++ b/arch/powerpc/platforms/pasemi/cpufreq.c @@ -236,6 +236,13 @@ static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy) static int pas_cpufreq_cpu_exit(struct cpufreq_policy *policy) { + /* + * We don't support CPU hotplug. Don't unmap after the system + * has already made it to a running state. + */ + if (system_state != SYSTEM_BOOTING) + return 0; + if (sdcasr_mapbase) iounmap(sdcasr_mapbase); if (sdcpwr_mapbase) From 46ed7a76ae7770cb8ba733ee2b06273397ad8b5b Mon Sep 17 00:00:00 2001 From: "Carl E. Love" Date: Thu, 29 Nov 2012 06:42:03 +0000 Subject: [PATCH 3/6] powerpc/oprofile: Fix error in oprofile power7_marked_instr_event() function The calculation for the left shift of the mask OPROFILE_PM_PMCSEL_MSK has an error. The calculation is should be to shift left by (max_cntrs - cntr) times the width of the pmsel field width. However, the #define OPROFILE_MAX_PMC_NUM was used instead of OPROFILE_PMSEL_FIELD_WIDTH. This patch fixes the calculation. Signed-off-by: Carl Love Acked-by: Paul Mackerras Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/oprofile/op_model_power4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/oprofile/op_model_power4.c b/arch/powerpc/oprofile/op_model_power4.c index 315f9495e9b2..f444b94935f5 100644 --- a/arch/powerpc/oprofile/op_model_power4.c +++ b/arch/powerpc/oprofile/op_model_power4.c @@ -52,7 +52,7 @@ static int power7_marked_instr_event(u64 mmcr1) for (pmc = 0; pmc < 4; pmc++) { psel = mmcr1 & (OPROFILE_PM_PMCSEL_MSK << (OPROFILE_MAX_PMC_NUM - pmc) - * OPROFILE_MAX_PMC_NUM); + * OPROFILE_PMSEL_FIELD_WIDTH); psel = (psel >> ((OPROFILE_MAX_PMC_NUM - pmc) * OPROFILE_PMSEL_FIELD_WIDTH)) & ~1ULL; unit = mmcr1 & (OPROFILE_PM_UNIT_MSK From 572177d7c77db1981ba2563e01478126482c43bc Mon Sep 17 00:00:00 2001 From: Tiejun Chen Date: Sun, 6 Jan 2013 00:49:34 +0000 Subject: [PATCH 4/6] powerpc/book3e: Disable interrupt after preempt_schedule_irq In preempt case current arch_local_irq_restore() from preempt_schedule_irq() may enable hard interrupt but we really should disable interrupts when we return from the interrupt, and so that we don't get interrupted after loading SRR0/1. Signed-off-by: Tiejun Chen CC: Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/entry_64.S | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index b310a0573625..3d990d3bd8ba 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -664,6 +664,19 @@ resume_kernel: ld r4,TI_FLAGS(r9) andi. r0,r4,_TIF_NEED_RESCHED bne 1b + + /* + * arch_local_irq_restore() from preempt_schedule_irq above may + * enable hard interrupt but we really should disable interrupts + * when we return from the interrupt, and so that we don't get + * interrupted after loading SRR0/1. + */ +#ifdef CONFIG_PPC_BOOK3E + wrteei 0 +#else + ld r10,PACAKMSR(r13) /* Get kernel MSR without EE */ + mtmsrd r10,1 /* Update machine state */ +#endif /* CONFIG_PPC_BOOK3E */ #endif /* CONFIG_PREEMPT */ .globl fast_exc_return_irq From fefd9e6f8860249b2c284d89cb2e51fa71a9503a Mon Sep 17 00:00:00 2001 From: Cong Ding Date: Mon, 14 Jan 2013 07:26:32 +0000 Subject: [PATCH 5/6] powerpc: kernel/kgdb.c: Fix memory leakage the variable backup_current_thread_info isn't freed before existing the function. Signed-off-by: Cong Ding Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/kgdb.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index c470a40b29f5..a7bc7521c064 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -154,12 +154,12 @@ static int kgdb_handle_breakpoint(struct pt_regs *regs) static int kgdb_singlestep(struct pt_regs *regs) { struct thread_info *thread_info, *exception_thread_info; - struct thread_info *backup_current_thread_info = \ - (struct thread_info *)kmalloc(sizeof(struct thread_info), GFP_KERNEL); + struct thread_info *backup_current_thread_info; if (user_mode(regs)) return 0; + backup_current_thread_info = (struct thread_info *)kmalloc(sizeof(struct thread_info), GFP_KERNEL); /* * On Book E and perhaps other processors, singlestep is handled on * the critical exception stack. This causes current_thread_info() @@ -185,6 +185,7 @@ static int kgdb_singlestep(struct pt_regs *regs) /* Restore current_thread_info lastly. */ memcpy(exception_thread_info, backup_current_thread_info, sizeof *thread_info); + kfree(backup_current_thread_info); return 1; } From 689dfa894c57842a05bf6dc9f97e6bb71ec5f386 Mon Sep 17 00:00:00 2001 From: Tiejun Chen Date: Tue, 15 Jan 2013 17:01:19 +0000 Subject: [PATCH 6/6] powerpc: Max next_tb to prevent from replaying timer interrupt With lazy interrupt, we always call __check_irq_replaysome with decrementers_next_tb to check if we need to replay timer interrupt. So in hotplug case we also need to set decrementers_next_tb as MAX to make sure __check_irq_replay don't replay timer interrupt when return as we expect, otherwise we'll trap here infinitely. Signed-off-by: Tiejun Chen Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/time.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 6f6b1cccc916..127361e093f4 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -494,10 +494,15 @@ void timer_interrupt(struct pt_regs * regs) set_dec(DECREMENTER_MAX); /* Some implementations of hotplug will get timer interrupts while - * offline, just ignore these + * offline, just ignore these and we also need to set + * decrementers_next_tb as MAX to make sure __check_irq_replay + * don't replay timer interrupt when return, otherwise we'll trap + * here infinitely :( */ - if (!cpu_online(smp_processor_id())) + if (!cpu_online(smp_processor_id())) { + *next_tb = ~(u64)0; return; + } /* Conditionally hard-enable interrupts now that the DEC has been * bumped to its maximum value