From cbf74cea070fa1f705de4712e25d9e56ae6543c7 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Mon, 30 May 2011 16:31:11 +0200 Subject: oprofile, x86: Add comments to IBS LVT offset initialization Adding a comment in the code as IBS LVT setup is not obvious at all ... Signed-off-by: Robert Richter --- arch/x86/kernel/apic/apic.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index fabf01eff77..a0bf78a0918 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -390,7 +390,8 @@ static unsigned int reserve_eilvt_offset(int offset, unsigned int new) /* * If mask=1, the LVT entry does not generate interrupts while mask=0 - * enables the vector. See also the BKDGs. + * enables the vector. See also the BKDGs. Must be called with + * preemption disabled. */ int setup_APIC_eilvt(u8 offset, u8 vector, u8 msg_type, u8 mask) -- cgit v1.2.3-70-g09d2 From fd8a7de177b6f56a0fc59ad211c197a7df06b1ad Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 20 Jul 2010 14:34:50 +0200 Subject: x86: cpu-hotplug: Prevent softirq wakeup on wrong CPU After a newly plugged CPU sets the cpu_online bit it enables interrupts and goes idle. The cpu which brought up the new cpu waits for the cpu_online bit and when it observes it, it sets the cpu_active bit for this cpu. The cpu_active bit is the relevant one for the scheduler to consider the cpu as a viable target. With forced threaded interrupt handlers which imply forced threaded softirqs we observed the following race: cpu 0 cpu 1 bringup(cpu1); set_cpu_online(smp_processor_id(), true); local_irq_enable(); while (!cpu_online(cpu1)); timer_interrupt() -> wake_up(softirq_thread_cpu1); -> enqueue_on(softirq_thread_cpu1, cpu0); ^^^^ cpu_notify(CPU_ONLINE, cpu1); -> sched_cpu_active(cpu1) -> set_cpu_active((cpu1, true); When an interrupt happens before the cpu_active bit is set by the cpu which brought up the newly onlined cpu, then the scheduler refuses to enqueue the woken thread which is bound to that newly onlined cpu on that newly onlined cpu due to the not yet set cpu_active bit and selects a fallback runqueue. Not really an expected and desirable behaviour. So far this has only been observed with forced hard/softirq threading, but in theory this could happen without forced threaded hard/softirqs as well. It's probably unobservable as it would take a massive interrupt storm on the newly onlined cpu which causes the softirq loop to wake up the softirq thread and an even longer delay of the cpu which waits for the cpu_online bit. Signed-off-by: Thomas Gleixner Reviewed-by: Peter Zijlstra Cc: stable@kernel.org # 2.6.39 --- arch/x86/kernel/smpboot.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 33a0c11797d..9fd3137230d 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -285,6 +285,19 @@ notrace static void __cpuinit start_secondary(void *unused) per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; x86_platform.nmi_init(); + /* + * Wait until the cpu which brought this one up marked it + * online before enabling interrupts. If we don't do that then + * we can end up waking up the softirq thread before this cpu + * reached the active state, which makes the scheduler unhappy + * and schedule the softirq thread on the wrong cpu. This is + * only observable with forced threaded interrupts, but in + * theory it could also happen w/o them. It's just way harder + * to achieve. + */ + while (!cpumask_test_cpu(smp_processor_id(), cpu_active_mask)) + cpu_relax(); + /* enable local interrupts */ local_irq_enable(); -- cgit v1.2.3-70-g09d2 From 977cb76d52e7aa040e18a84b29fe6fd80d79319b Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 6 Jun 2011 10:15:49 +0200 Subject: x86: devicetree: Add missing early_init_dt_setup_initrd_arch stub This patch fixes the following build failure: drivers/built-in.o: In function `early_init_dt_check_for_initrd': /home/florian/dev/kernel/x86/linux-2.6-x86/drivers/of/fdt.c:571: undefined reference to `early_init_dt_setup_initrd_arch' make: *** [.tmp_vmlinux1] Error 1 which happens as soon as we enable initrd support on a x86 devicetree platform such as Intel CE4100. Signed-off-by: Florian Fainelli Acked-by: Grant Likely Cc: Maxime Bizon Acked-by: Sebastian Andrzej Siewior Cc: stable@kernel.org # 2.6.39 Link: http://lkml.kernel.org/r/201106061015.50039.ffainelli@freebox.fr Signed-off-by: Thomas Gleixner --- arch/x86/kernel/devicetree.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 690bc846183..9aeb78a23de 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -98,6 +99,16 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS)); } +#ifdef CONFIG_BLK_DEV_INITRD +void __init early_init_dt_setup_initrd_arch(unsigned long start, + unsigned long end) +{ + initrd_start = (unsigned long)__va(start); + initrd_end = (unsigned long)__va(end); + initrd_below_start_ok = 1; +} +#endif + void __init add_dtb(u64 data) { initial_dtb = data + offsetof(struct setup_data, data); -- cgit v1.2.3-70-g09d2 From dac853ae89043f1b7752875300faf614de43c74b Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Thu, 9 Jun 2011 20:05:18 +0200 Subject: exec: delay address limit change until point of no return Unconditionally changing the address limit to USER_DS and not restoring it to its old value in the error path is wrong because it prevents us using kernel memory on repeated calls to this function. This, in fact, breaks the fallback of hard coded paths to the init program from being ever successful if the first candidate fails to load. With this patch applied switching to USER_DS is delayed until the point of no return is reached which makes it possible to have a multi-arch rootfs with one arch specific init binary for each of the (hard coded) probed paths. Since the address limit is already set to USER_DS when start_thread() will be invoked, this redundancy can be safely removed. Signed-off-by: Mathias Krause Cc: Al Viro Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- arch/x86/kernel/process_32.c | 1 - arch/x86/kernel/process_64.c | 1 - fs/exec.c | 5 +---- 3 files changed, 1 insertion(+), 6 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 8d128783af4..a3d0dc59067 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -245,7 +245,6 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) { set_user_gs(regs, 0); regs->fs = 0; - set_fs(USER_DS); regs->ds = __USER_DS; regs->es = __USER_DS; regs->ss = __USER_DS; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 6c9dd922ac0..ca6f7ab8df3 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -338,7 +338,6 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip, regs->cs = _cs; regs->ss = _ss; regs->flags = X86_EFLAGS_IF; - set_fs(USER_DS); /* * Free the old FP and other extended state */ diff --git a/fs/exec.c b/fs/exec.c index ea5f748906a..97e0d52d72f 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1093,6 +1093,7 @@ int flush_old_exec(struct linux_binprm * bprm) bprm->mm = NULL; /* We're using it now */ + set_fs(USER_DS); current->flags &= ~(PF_RANDOMIZE | PF_KTHREAD); flush_thread(); current->personality &= ~bprm->per_clear; @@ -1357,10 +1358,6 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs) if (retval) return retval; - /* kernel module loader fixup */ - /* so we don't try to load run modprobe in kernel space. */ - set_fs(USER_DS); - retval = audit_bprm(bprm); if (retval) return retval; -- cgit v1.2.3-70-g09d2 From 7ad35cf288fd63a19bf50e490440a992de808b2b Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Wed, 25 May 2011 14:00:49 +1000 Subject: x86/uv/x2apic: update for change in pci bridge handling. When I added 3448a19da479b6bd1e28e2a2be9fa16c6a6feb39 I forgot about the special uv handling code for this, so this patch fixes it up. Acked-by: Jesse Barnes Acked-by: Ingo Molnar Signed-off-by: Dave Airlie --- arch/x86/kernel/apic/x2apic_uv_x.c | 8 ++++---- drivers/pci/pci.c | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index b511a011b7d..adc66c3a1fe 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -632,14 +632,14 @@ late_initcall(uv_init_heartbeat); /* Direct Legacy VGA I/O traffic to designated IOH */ int uv_set_vga_state(struct pci_dev *pdev, bool decode, - unsigned int command_bits, bool change_bridge) + unsigned int command_bits, u32 flags) { int domain, bus, rc; - PR_DEVEL("devfn %x decode %d cmd %x chg_brdg %d\n", - pdev->devfn, decode, command_bits, change_bridge); + PR_DEVEL("devfn %x decode %d cmd %x flags %d\n", + pdev->devfn, decode, command_bits, flags); - if (!change_bridge) + if (!(flags & PCI_VGA_STATE_CHANGE_BRIDGE)) return 0; if ((command_bits & PCI_COMMAND_IO) == 0) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 56098b3e17c..5f10c23dff9 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3271,11 +3271,11 @@ void __init pci_register_set_vga_state(arch_set_vga_state_t func) } static int pci_set_vga_state_arch(struct pci_dev *dev, bool decode, - unsigned int command_bits, bool change_bridge) + unsigned int command_bits, u32 flags) { if (arch_set_vga_state) return arch_set_vga_state(dev, decode, command_bits, - change_bridge); + flags); return 0; } -- cgit v1.2.3-70-g09d2 From 60b8b1de0dd2bf246f0e074d287bb3f0bc42a755 Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Tue, 14 Jun 2011 12:45:10 -0700 Subject: x86 idle: APM requires pm_idle/default_idle unconditionally when a module [ Also from Ben Hutchings and Vitaliy Ivanov ] Commit 06ae40ce073d ("x86 idle: EXPORT_SYMBOL(default_idle, pm_idle) only when APM demands it") removed the export for pm_idle/default_idle unless the apm module was modularised and CONFIG_APM_CPU_IDLE was set. But the apm module uses pm_idle/default_idle unconditionally, CONFIG_APM_CPU_IDLE only affects the bios idle threshold. Adjust the export accordingly. [ Used #ifdef instead of #if defined() as it's shorter, and what both Ben and Vitaliy used.. Andy, you're out-voted ;) - Linus ] Reported-by: Randy Dunlap Acked-by: Jiri Kosina Acked-by: Ingo Molnar Acked-by: Len Brown Signed-off-by: Andy Whitcroft Signed-off-by: Vitaliy Ivanov Signed-off-by: Ben Hutchings Signed-off-by: Linus Torvalds --- arch/x86/kernel/process.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 2e4928d45a2..e1ba8cb24e4 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -337,7 +337,7 @@ EXPORT_SYMBOL(boot_option_idle_override); * Powermanagement idle function, if any.. */ void (*pm_idle)(void); -#if defined(CONFIG_APM_MODULE) && defined(CONFIG_APM_CPU_IDLE) +#ifdef CONFIG_APM_MODULE EXPORT_SYMBOL(pm_idle); #endif @@ -399,7 +399,7 @@ void default_idle(void) cpu_relax(); } } -#if defined(CONFIG_APM_MODULE) && defined(CONFIG_APM_CPU_IDLE) +#ifdef CONFIG_APM_MODULE EXPORT_SYMBOL(default_idle); #endif -- cgit v1.2.3-70-g09d2