From 1b72d43237980eab9b6ae6bb8181e51c840377e6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 21 Mar 2019 16:39:20 +0100 Subject: tick: Remove outgoing CPU from broadcast masks Valentin reported that unplugging a CPU occasionally results in a warning in the tick broadcast code which is triggered when an offline CPU is in the broadcast mask. This happens because the outgoing CPU is not removing itself from the broadcast masks, especially not from the broadcast_force_mask. The removal happens on the control CPU after the outgoing CPU is dead. It's a long standing issue, but the warning is harmless. Rework the hotplug mechanism so that the outgoing CPU removes itself from the broadcast masks after disabling interrupts and removing itself from the online mask. Reported-by: Valentin Schneider Signed-off-by: Thomas Gleixner Tested-by: Valentin Schneider Cc: Frederic Weisbecker Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1903211540180.1784@nanos.tec.linutronix.de --- kernel/cpu.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/cpu.c') diff --git a/kernel/cpu.c b/kernel/cpu.c index 025f419d16f6..f69ba38573c2 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -844,6 +844,8 @@ static int take_cpu_down(void *_param) /* Give up timekeeping duties */ tick_handover_do_timer(); + /* Remove CPU from timer broadcasting */ + tick_offline_cpu(cpu); /* Park the stopper thread */ stop_machine_park(cpu); return 0; -- cgit v1.2.3 From de7b77e5bb9451417ca57f1b6501da654587c048 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 27 Mar 2019 07:00:29 -0500 Subject: cpu/hotplug: Create SMT sysfs interface for all arches Make the /sys/devices/system/cpu/smt/* files available on all arches, so user space has a consistent way to detect whether SMT is enabled. The 'control' file now shows 'notimplemented' for architectures which don't yet have CONFIG_HOTPLUG_SMT. [ tglx: Make notimplemented a real state ] Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Cc: Andrea Arcangeli Cc: Waiman Long Cc: Peter Zijlstra Cc: Jiri Kosina Link: https://lkml.kernel.org/r/469c2b98055f2c41e75748e06447d592a64080c9.1553635520.git.jpoimboe@redhat.com --- kernel/cpu.c | 64 ++++++++++++++++++++++++++++++++++++------------------------ 1 file changed, 39 insertions(+), 25 deletions(-) (limited to 'kernel/cpu.c') diff --git a/kernel/cpu.c b/kernel/cpu.c index 6754f3ecfd94..b8bf3f93e39b 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2033,19 +2033,6 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = { #ifdef CONFIG_HOTPLUG_SMT -static const char *smt_states[] = { - [CPU_SMT_ENABLED] = "on", - [CPU_SMT_DISABLED] = "off", - [CPU_SMT_FORCE_DISABLED] = "forceoff", - [CPU_SMT_NOT_SUPPORTED] = "notsupported", -}; - -static ssize_t -show_smt_control(struct device *dev, struct device_attribute *attr, char *buf) -{ - return snprintf(buf, PAGE_SIZE - 2, "%s\n", smt_states[cpu_smt_control]); -} - static void cpuhp_offline_cpu_device(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); @@ -2116,9 +2103,10 @@ static int cpuhp_smt_enable(void) return ret; } + static ssize_t -store_smt_control(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +__store_smt_control(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { int ctrlval, ret; @@ -2156,14 +2144,44 @@ store_smt_control(struct device *dev, struct device_attribute *attr, unlock_device_hotplug(); return ret ? ret : count; } + +#else /* !CONFIG_HOTPLUG_SMT */ +static ssize_t +__store_smt_control(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + return -ENODEV; +} +#endif /* CONFIG_HOTPLUG_SMT */ + +static const char *smt_states[] = { + [CPU_SMT_ENABLED] = "on", + [CPU_SMT_DISABLED] = "off", + [CPU_SMT_FORCE_DISABLED] = "forceoff", + [CPU_SMT_NOT_SUPPORTED] = "notsupported", + [CPU_SMT_NOT_IMPLEMENTED] = "notimplemented", +}; + +static ssize_t +show_smt_control(struct device *dev, struct device_attribute *attr, char *buf) +{ + const char *state = smt_states[cpu_smt_control]; + + return snprintf(buf, PAGE_SIZE - 2, "%s\n", state); +} + +static ssize_t +store_smt_control(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + return __store_smt_control(dev, attr, buf, count); +} static DEVICE_ATTR(control, 0644, show_smt_control, store_smt_control); static ssize_t show_smt_active(struct device *dev, struct device_attribute *attr, char *buf) { - bool active = topology_max_smt_threads() > 1; - - return snprintf(buf, PAGE_SIZE - 2, "%d\n", active); + return snprintf(buf, PAGE_SIZE - 2, "%d\n", sched_smt_active()); } static DEVICE_ATTR(active, 0444, show_smt_active, NULL); @@ -2179,21 +2197,17 @@ static const struct attribute_group cpuhp_smt_attr_group = { NULL }; -static int __init cpu_smt_state_init(void) +static int __init cpu_smt_sysfs_init(void) { return sysfs_create_group(&cpu_subsys.dev_root->kobj, &cpuhp_smt_attr_group); } -#else -static inline int cpu_smt_state_init(void) { return 0; } -#endif - static int __init cpuhp_sysfs_init(void) { int cpu, ret; - ret = cpu_smt_state_init(); + ret = cpu_smt_sysfs_init(); if (ret) return ret; @@ -2214,7 +2228,7 @@ static int __init cpuhp_sysfs_init(void) return 0; } device_initcall(cpuhp_sysfs_init); -#endif +#endif /* CONFIG_SYSFS && CONFIG_HOTPLUG_CPU */ /* * cpu_bit_bitmap[] is a special, "compressed" data structure that -- cgit v1.2.3 From 98af8452945c55652de68536afdde3b520fec429 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 12 Apr 2019 15:39:28 -0500 Subject: cpu/speculation: Add 'mitigations=' cmdline option Keeping track of the number of mitigations for all the CPU speculation bugs has become overwhelming for many users. It's getting more and more complicated to decide which mitigations are needed for a given architecture. Complicating matters is the fact that each arch tends to have its own custom way to mitigate the same vulnerability. Most users fall into a few basic categories: a) they want all mitigations off; b) they want all reasonable mitigations on, with SMT enabled even if it's vulnerable; or c) they want all reasonable mitigations on, with SMT disabled if vulnerable. Define a set of curated, arch-independent options, each of which is an aggregation of existing options: - mitigations=off: Disable all mitigations. - mitigations=auto: [default] Enable all the default mitigations, but leave SMT enabled, even if it's vulnerable. - mitigations=auto,nosmt: Enable all the default mitigations, disabling SMT if needed by a mitigation. Currently, these options are placeholders which don't actually do anything. They will be fleshed out in upcoming patches. Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Tested-by: Jiri Kosina (on x86) Reviewed-by: Jiri Kosina Cc: Borislav Petkov Cc: "H . Peter Anvin" Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Jiri Kosina Cc: Waiman Long Cc: Andrea Arcangeli Cc: Jon Masters Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: linuxppc-dev@lists.ozlabs.org Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: linux-s390@vger.kernel.org Cc: Catalin Marinas Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: linux-arch@vger.kernel.org Cc: Greg Kroah-Hartman Cc: Tyler Hicks Cc: Linus Torvalds Cc: Randy Dunlap Cc: Steven Price Cc: Phil Auld Link: https://lkml.kernel.org/r/b07a8ef9b7c5055c3a4637c87d07c296d5016fe0.1555085500.git.jpoimboe@redhat.com --- kernel/cpu.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'kernel/cpu.c') diff --git a/kernel/cpu.c b/kernel/cpu.c index d1c6d152da89..e70a90634b41 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2279,3 +2279,18 @@ void __init boot_cpu_hotplug_init(void) #endif this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); } + +enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO; + +static int __init mitigations_parse_cmdline(char *arg) +{ + if (!strcmp(arg, "off")) + cpu_mitigations = CPU_MITIGATIONS_OFF; + else if (!strcmp(arg, "auto")) + cpu_mitigations = CPU_MITIGATIONS_AUTO; + else if (!strcmp(arg, "auto,nosmt")) + cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT; + + return 0; +} +early_param("mitigations", mitigations_parse_cmdline); -- cgit v1.2.3 From 9ca12ac04bb7d7cfb28aa549dcd3d15761f15543 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 11 Apr 2019 13:34:46 +1000 Subject: kernel/cpu: Allow non-zero CPU to be primary for suspend / kexec freeze This patch provides an arch option, ARCH_SUSPEND_NONZERO_CPU, to opt-in to allowing suspend to occur on one of the housekeeping CPUs rather than hardcoded CPU0. This will allow CPU0 to be a nohz_full CPU with a later change. It may be possible for platforms with hardware/firmware restrictions on suspend/wake effectively support this by handing off the final stage to CPU0 when kernel housekeeping is no longer required. Another option is to make housekeeping / nohz_full mask dynamic at runtime, but the complexity could not be justified at this time. Signed-off-by: Nicholas Piggin Signed-off-by: Peter Zijlstra (Intel) Cc: Frederic Weisbecker Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rafael J . Wysocki Cc: Thomas Gleixner Cc: linuxppc-dev@lists.ozlabs.org Link: https://lkml.kernel.org/r/20190411033448.20842-4-npiggin@gmail.com Signed-off-by: Ingo Molnar --- kernel/cpu.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'kernel/cpu.c') diff --git a/kernel/cpu.c b/kernel/cpu.c index 6754f3ecfd94..d1bf6e2b4752 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -1199,8 +1200,15 @@ int freeze_secondary_cpus(int primary) int cpu, error = 0; cpu_maps_update_begin(); - if (!cpu_online(primary)) + if (primary == -1) { primary = cpumask_first(cpu_online_mask); + if (!housekeeping_cpu(primary, HK_FLAG_TIMER)) + primary = housekeeping_any_cpu(HK_FLAG_TIMER); + } else { + if (!cpu_online(primary)) + primary = cpumask_first(cpu_online_mask); + } + /* * We take down all of the non-boot CPUs in one shot to avoid races * with the userspace trying to use the CPU hotplug at the same time -- cgit v1.2.3 From ec527c318036a65a083ef68d8ba95789d2212246 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Thu, 30 May 2019 00:09:39 +0200 Subject: x86/power: Fix 'nosmt' vs hibernation triple fault during resume As explained in 0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once") we always, no matter what, have to bring up x86 HT siblings during boot at least once in order to avoid first MCE bringing the system to its knees. That means that whenever 'nosmt' is supplied on the kernel command-line, all the HT siblings are as a result sitting in mwait or cpudile after going through the online-offline cycle at least once. This causes a serious issue though when a kernel, which saw 'nosmt' on its commandline, is going to perform resume from hibernation: if the resume from the hibernated image is successful, cr3 is flipped in order to point to the address space of the kernel that is being resumed, which in turn means that all the HT siblings are all of a sudden mwaiting on address which is no longer valid. That results in triple fault shortly after cr3 is switched, and machine reboots. Fix this by always waking up all the SMT siblings before initiating the 'restore from hibernation' process; this guarantees that all the HT siblings will be properly carried over to the resumed kernel waiting in resume_play_dead(), and acted upon accordingly afterwards, based on the target kernel configuration. Symmetricaly, the resumed kernel has to push the SMT siblings to mwait again in case it has SMT disabled; this means it has to online all the siblings when resuming (so that they come out of hlt) and offline them again to let them reach mwait. Cc: 4.19+ # v4.19+ Debugged-by: Thomas Gleixner Fixes: 0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once") Signed-off-by: Jiri Kosina Acked-by: Pavel Machek Reviewed-by: Thomas Gleixner Reviewed-by: Josh Poimboeuf Signed-off-by: Rafael J. Wysocki --- kernel/cpu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/cpu.c') diff --git a/kernel/cpu.c b/kernel/cpu.c index f2ef10460698..077fde6fb953 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2061,7 +2061,7 @@ static void cpuhp_online_cpu_device(unsigned int cpu) kobject_uevent(&dev->kobj, KOBJ_ONLINE); } -static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) +int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { int cpu, ret = 0; @@ -2093,7 +2093,7 @@ static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) return ret; } -static int cpuhp_smt_enable(void) +int cpuhp_smt_enable(void) { int cpu, ret = 0; -- cgit v1.2.3 From 1bf72720281770162c87990697eae1ba2f1d917a Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 16 May 2019 09:09:35 +0200 Subject: cpu/speculation: Warn on unsupported mitigations= parameter Currently, if the user specifies an unsupported mitigation strategy on the kernel command line, it will be ignored silently. The code will fall back to the default strategy, possibly leaving the system more vulnerable than expected. This may happen due to e.g. a simple typo, or, for a stable kernel release, because not all mitigation strategies have been backported. Inform the user by printing a message. Fixes: 98af8452945c5565 ("cpu/speculation: Add 'mitigations=' cmdline option") Signed-off-by: Geert Uytterhoeven Signed-off-by: Thomas Gleixner Acked-by: Josh Poimboeuf Cc: Peter Zijlstra Cc: Jiri Kosina Cc: Greg Kroah-Hartman Cc: Ben Hutchings Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20190516070935.22546-1-geert@linux-m68k.org --- kernel/cpu.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel/cpu.c') diff --git a/kernel/cpu.c b/kernel/cpu.c index 077fde6fb953..551db494f153 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2339,6 +2339,9 @@ static int __init mitigations_parse_cmdline(char *arg) cpu_mitigations = CPU_MITIGATIONS_AUTO; else if (!strcmp(arg, "auto,nosmt")) cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT; + else + pr_crit("Unsupported mitigations=%s, system may still be vulnerable\n", + arg); return 0; } -- cgit v1.2.3 From 33d4a5a7a5b4d02915d765064b2319e90a11cbde Mon Sep 17 00:00:00 2001 From: Eiichi Tsukata Date: Thu, 27 Jun 2019 11:47:32 +0900 Subject: cpu/hotplug: Fix out-of-bounds read when setting fail state Setting invalid value to /sys/devices/system/cpu/cpuX/hotplug/fail can control `struct cpuhp_step *sp` address, results in the following global-out-of-bounds read. Reproducer: # echo -2 > /sys/devices/system/cpu/cpu0/hotplug/fail KASAN report: BUG: KASAN: global-out-of-bounds in write_cpuhp_fail+0x2cd/0x2e0 Read of size 8 at addr ffffffff89734438 by task bash/1941 CPU: 0 PID: 1941 Comm: bash Not tainted 5.2.0-rc6+ #31 Call Trace: write_cpuhp_fail+0x2cd/0x2e0 dev_attr_store+0x58/0x80 sysfs_kf_write+0x13d/0x1a0 kernfs_fop_write+0x2bc/0x460 vfs_write+0x1e1/0x560 ksys_write+0x126/0x250 do_syscall_64+0xc1/0x390 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7f05e4f4c970 The buggy address belongs to the variable: cpu_hotplug_lock+0x98/0xa0 Memory state around the buggy address: ffffffff89734300: fa fa fa fa 00 00 00 00 00 00 00 00 00 00 00 00 ffffffff89734380: fa fa fa fa 00 00 00 00 00 00 00 00 00 00 00 00 >ffffffff89734400: 00 00 00 00 fa fa fa fa 00 00 00 00 fa fa fa fa ^ ffffffff89734480: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffffffff89734500: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 Add a sanity check for the value written from user space. Fixes: 1db49484f21ed ("smp/hotplug: Hotplug state fail injection") Signed-off-by: Eiichi Tsukata Signed-off-by: Thomas Gleixner Cc: peterz@infradead.org Link: https://lkml.kernel.org/r/20190627024732.31672-1-devel@etsukata.com --- kernel/cpu.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel/cpu.c') diff --git a/kernel/cpu.c b/kernel/cpu.c index 551db494f153..ef1c565edc5d 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1964,6 +1964,9 @@ static ssize_t write_cpuhp_fail(struct device *dev, if (ret) return ret; + if (fail < CPUHP_OFFLINE || fail > CPUHP_ONLINE) + return -EINVAL; + /* * Cannot fail STARTING/DYING callbacks. */ -- cgit v1.2.3