From ee17e5d6201c66492a0e8053190fca2ed2b8457d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 12 Jan 2019 11:48:20 -0600 Subject: signal: Make siginmask safe when passed a signal of 0 Eric Biggers reported: > The following commit, which went into v4.20, introduced undefined behavior when > sys_rt_sigqueueinfo() is called with sig=0: > > commit 4ce5f9c9e7546915c559ffae594e6d73f918db00 > Author: Eric W. Biederman > Date: Tue Sep 25 12:59:31 2018 +0200 > > signal: Use a smaller struct siginfo in the kernel > > In sig_specific_sicodes(), used from known_siginfo_layout(), the expression > '1ULL << ((sig)-1)' is undefined as it evaluates to 1ULL << 4294967295. > > Reproducer: > > #include > #include > #include > > int main(void) > { > siginfo_t si = { .si_code = 1 }; > syscall(__NR_rt_sigqueueinfo, 0, 0, &si); > } > > UBSAN report for v5.0-rc1: > > UBSAN: Undefined behaviour in kernel/signal.c:2946:7 > shift exponent 4294967295 is too large for 64-bit type 'long unsigned int' > CPU: 2 PID: 346 Comm: syz_signal Not tainted 5.0.0-rc1 #25 > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 > Call Trace: > __dump_stack lib/dump_stack.c:77 [inline] > dump_stack+0x70/0xa5 lib/dump_stack.c:113 > ubsan_epilogue+0xd/0x40 lib/ubsan.c:159 > __ubsan_handle_shift_out_of_bounds+0x12c/0x170 lib/ubsan.c:425 > known_siginfo_layout+0xae/0xe0 kernel/signal.c:2946 > post_copy_siginfo_from_user kernel/signal.c:3009 [inline] > __copy_siginfo_from_user+0x35/0x60 kernel/signal.c:3035 > __do_sys_rt_sigqueueinfo kernel/signal.c:3553 [inline] > __se_sys_rt_sigqueueinfo kernel/signal.c:3549 [inline] > __x64_sys_rt_sigqueueinfo+0x31/0x70 kernel/signal.c:3549 > do_syscall_64+0x4c/0x1b0 arch/x86/entry/common.c:290 > entry_SYSCALL_64_after_hwframe+0x49/0xbe > RIP: 0033:0x433639 > Code: c4 18 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b 27 00 00 c3 66 2e 0f 1f 84 00 00 00 00 > RSP: 002b:00007fffcb289fc8 EFLAGS: 00000246 ORIG_RAX: 0000000000000081 > RAX: ffffffffffffffda RBX: 00000000004002e0 RCX: 0000000000433639 > RDX: 00007fffcb289fd0 RSI: 0000000000000000 RDI: 0000000000000000 > RBP: 00000000006b2018 R08: 000000000000004d R09: 0000000000000000 > R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000401560 > R13: 00000000004015f0 R14: 0000000000000000 R15: 0000000000000000 I have looked at the other callers of siginmask and they all appear to in locations where sig can not be zero. I have looked at the code generation of adding an extra test against zero and gcc was able with a simple decrement instruction to combine the two tests together. So the at most adding this test cost a single cpu cycle. In practice that decrement instruction was already present as part of the mask comparison, so the only change was when the instruction was executed. So given that it is cheap, and obviously correct to update siginmask to verify the signal is not zero. Fix this issue there to avoid any future problems. Reported-by: Eric Biggers Fixes: 4ce5f9c9e754 ("signal: Use a smaller struct siginfo in the kernel") Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index cc7e2c1cd444..9702016734b1 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -392,7 +392,7 @@ extern bool unhandled_signal(struct task_struct *tsk, int sig); #endif #define siginmask(sig, mask) \ - ((sig) < SIGRTMIN && (rt_sigmask(sig) & (mask))) + ((sig) > 0 && (sig) < SIGRTMIN && (rt_sigmask(sig) & (mask))) #define SIG_KERNEL_ONLY_MASK (\ rt_sigmask(SIGKILL) | rt_sigmask(SIGSTOP)) -- cgit v1.3-7-g2ca7 From 13054abbaa4f1fd4e6f3b4b63439ec033b4c8035 Mon Sep 17 00:00:00 2001 From: Vladis Dronov Date: Tue, 29 Jan 2019 11:58:35 +0100 Subject: HID: debug: fix the ring buffer implementation Ring buffer implementation in hid_debug_event() and hid_debug_events_read() is strange allowing lost or corrupted data. After commit 717adfdaf147 ("HID: debug: check length before copy_to_user()") it is possible to enter an infinite loop in hid_debug_events_read() by providing 0 as count, this locks up a system. Fix this by rewriting the ring buffer implementation with kfifo and simplify the code. This fixes CVE-2019-3819. v2: fix an execution logic and add a comment v3: use __set_current_state() instead of set_current_state() Link: https://bugzilla.redhat.com/show_bug.cgi?id=1669187 Cc: stable@vger.kernel.org # v4.18+ Fixes: cd667ce24796 ("HID: use debugfs for events/reports dumping") Fixes: 717adfdaf147 ("HID: debug: check length before copy_to_user()") Signed-off-by: Vladis Dronov Reviewed-by: Oleg Nesterov Signed-off-by: Benjamin Tissoires --- drivers/hid/hid-debug.c | 120 ++++++++++++++++++---------------------------- include/linux/hid-debug.h | 9 ++-- 2 files changed, 51 insertions(+), 78 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index c530476edba6..ac9fda1b5a72 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -30,6 +30,7 @@ #include #include +#include #include #include #include @@ -661,17 +662,12 @@ EXPORT_SYMBOL_GPL(hid_dump_device); /* enqueue string to 'events' ring buffer */ void hid_debug_event(struct hid_device *hdev, char *buf) { - unsigned i; struct hid_debug_list *list; unsigned long flags; spin_lock_irqsave(&hdev->debug_list_lock, flags); - list_for_each_entry(list, &hdev->debug_list, node) { - for (i = 0; buf[i]; i++) - list->hid_debug_buf[(list->tail + i) % HID_DEBUG_BUFSIZE] = - buf[i]; - list->tail = (list->tail + i) % HID_DEBUG_BUFSIZE; - } + list_for_each_entry(list, &hdev->debug_list, node) + kfifo_in(&list->hid_debug_fifo, buf, strlen(buf)); spin_unlock_irqrestore(&hdev->debug_list_lock, flags); wake_up_interruptible(&hdev->debug_wait); @@ -722,8 +718,7 @@ void hid_dump_input(struct hid_device *hdev, struct hid_usage *usage, __s32 valu hid_debug_event(hdev, buf); kfree(buf); - wake_up_interruptible(&hdev->debug_wait); - + wake_up_interruptible(&hdev->debug_wait); } EXPORT_SYMBOL_GPL(hid_dump_input); @@ -1083,8 +1078,8 @@ static int hid_debug_events_open(struct inode *inode, struct file *file) goto out; } - if (!(list->hid_debug_buf = kzalloc(HID_DEBUG_BUFSIZE, GFP_KERNEL))) { - err = -ENOMEM; + err = kfifo_alloc(&list->hid_debug_fifo, HID_DEBUG_FIFOSIZE, GFP_KERNEL); + if (err) { kfree(list); goto out; } @@ -1104,77 +1099,57 @@ static ssize_t hid_debug_events_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos) { struct hid_debug_list *list = file->private_data; - int ret = 0, len; + int ret = 0, copied; DECLARE_WAITQUEUE(wait, current); mutex_lock(&list->read_mutex); - while (ret == 0) { - if (list->head == list->tail) { - add_wait_queue(&list->hdev->debug_wait, &wait); - set_current_state(TASK_INTERRUPTIBLE); - - while (list->head == list->tail) { - if (file->f_flags & O_NONBLOCK) { - ret = -EAGAIN; - break; - } - if (signal_pending(current)) { - ret = -ERESTARTSYS; - break; - } + if (kfifo_is_empty(&list->hid_debug_fifo)) { + add_wait_queue(&list->hdev->debug_wait, &wait); + set_current_state(TASK_INTERRUPTIBLE); + + while (kfifo_is_empty(&list->hid_debug_fifo)) { + if (file->f_flags & O_NONBLOCK) { + ret = -EAGAIN; + break; + } - if (!list->hdev || !list->hdev->debug) { - ret = -EIO; - set_current_state(TASK_RUNNING); - goto out; - } + if (signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } - /* allow O_NONBLOCK from other threads */ - mutex_unlock(&list->read_mutex); - schedule(); - mutex_lock(&list->read_mutex); - set_current_state(TASK_INTERRUPTIBLE); + /* if list->hdev is NULL we cannot remove_wait_queue(). + * if list->hdev->debug is 0 then hid_debug_unregister() + * was already called and list->hdev is being destroyed. + * if we add remove_wait_queue() here we can hit a race. + */ + if (!list->hdev || !list->hdev->debug) { + ret = -EIO; + set_current_state(TASK_RUNNING); + goto out; } - set_current_state(TASK_RUNNING); - remove_wait_queue(&list->hdev->debug_wait, &wait); + /* allow O_NONBLOCK from other threads */ + mutex_unlock(&list->read_mutex); + schedule(); + mutex_lock(&list->read_mutex); + set_current_state(TASK_INTERRUPTIBLE); } - if (ret) - goto out; + __set_current_state(TASK_RUNNING); + remove_wait_queue(&list->hdev->debug_wait, &wait); - /* pass the ringbuffer contents to userspace */ -copy_rest: - if (list->tail == list->head) + if (ret) goto out; - if (list->tail > list->head) { - len = list->tail - list->head; - if (len > count) - len = count; - - if (copy_to_user(buffer + ret, &list->hid_debug_buf[list->head], len)) { - ret = -EFAULT; - goto out; - } - ret += len; - list->head += len; - } else { - len = HID_DEBUG_BUFSIZE - list->head; - if (len > count) - len = count; - - if (copy_to_user(buffer, &list->hid_debug_buf[list->head], len)) { - ret = -EFAULT; - goto out; - } - list->head = 0; - ret += len; - count -= len; - if (count > 0) - goto copy_rest; - } - } + + /* pass the fifo content to userspace, locking is not needed with only + * one concurrent reader and one concurrent writer + */ + ret = kfifo_to_user(&list->hid_debug_fifo, buffer, count, &copied); + if (ret) + goto out; + ret = copied; out: mutex_unlock(&list->read_mutex); return ret; @@ -1185,7 +1160,7 @@ static __poll_t hid_debug_events_poll(struct file *file, poll_table *wait) struct hid_debug_list *list = file->private_data; poll_wait(file, &list->hdev->debug_wait, wait); - if (list->head != list->tail) + if (!kfifo_is_empty(&list->hid_debug_fifo)) return EPOLLIN | EPOLLRDNORM; if (!list->hdev->debug) return EPOLLERR | EPOLLHUP; @@ -1200,7 +1175,7 @@ static int hid_debug_events_release(struct inode *inode, struct file *file) spin_lock_irqsave(&list->hdev->debug_list_lock, flags); list_del(&list->node); spin_unlock_irqrestore(&list->hdev->debug_list_lock, flags); - kfree(list->hid_debug_buf); + kfifo_free(&list->hid_debug_fifo); kfree(list); return 0; @@ -1246,4 +1221,3 @@ void hid_debug_exit(void) { debugfs_remove_recursive(hid_debug_root); } - diff --git a/include/linux/hid-debug.h b/include/linux/hid-debug.h index 8663f216c563..2d6100edf204 100644 --- a/include/linux/hid-debug.h +++ b/include/linux/hid-debug.h @@ -24,7 +24,10 @@ #ifdef CONFIG_DEBUG_FS +#include + #define HID_DEBUG_BUFSIZE 512 +#define HID_DEBUG_FIFOSIZE 512 void hid_dump_input(struct hid_device *, struct hid_usage *, __s32); void hid_dump_report(struct hid_device *, int , u8 *, int); @@ -37,11 +40,8 @@ void hid_debug_init(void); void hid_debug_exit(void); void hid_debug_event(struct hid_device *, char *); - struct hid_debug_list { - char *hid_debug_buf; - int head; - int tail; + DECLARE_KFIFO_PTR(hid_debug_fifo, char); struct fasync_struct *fasync; struct hid_device *hdev; struct list_head node; @@ -64,4 +64,3 @@ struct hid_debug_list { #endif #endif - -- cgit v1.3-7-g2ca7 From b284909abad48b07d3071a9fc9b5692b3e64914b Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 30 Jan 2019 07:13:58 -0600 Subject: cpu/hotplug: Fix "SMT disabled by BIOS" detection for KVM With the following commit: 73d5e2b47264 ("cpu/hotplug: detect SMT disabled by BIOS") ... the hotplug code attempted to detect when SMT was disabled by BIOS, in which case it reported SMT as permanently disabled. However, that code broke a virt hotplug scenario, where the guest is booted with only primary CPU threads, and a sibling is brought online later. The problem is that there doesn't seem to be a way to reliably distinguish between the HW "SMT disabled by BIOS" case and the virt "sibling not yet brought online" case. So the above-mentioned commit was a bit misguided, as it permanently disabled SMT for both cases, preventing future virt sibling hotplugs. Going back and reviewing the original problems which were attempted to be solved by that commit, when SMT was disabled in BIOS: 1) /sys/devices/system/cpu/smt/control showed "on" instead of "notsupported"; and 2) vmx_vm_init() was incorrectly showing the L1TF_MSG_SMT warning. I'd propose that we instead consider #1 above to not actually be a problem. Because, at least in the virt case, it's possible that SMT wasn't disabled by BIOS and a sibling thread could be brought online later. So it makes sense to just always default the smt control to "on" to allow for that possibility (assuming cpuid indicates that the CPU supports SMT). The real problem is #2, which has a simple fix: change vmx_vm_init() to query the actual current SMT state -- i.e., whether any siblings are currently online -- instead of looking at the SMT "control" sysfs value. So fix it by: a) reverting the original "fix" and its followup fix: 73d5e2b47264 ("cpu/hotplug: detect SMT disabled by BIOS") bc2d8d262cba ("cpu/hotplug: Fix SMT supported evaluation") and b) changing vmx_vm_init() to query the actual current SMT state -- instead of the sysfs control value -- to determine whether the L1TF warning is needed. This also requires the 'sched_smt_present' variable to exported, instead of 'cpu_smt_control'. Fixes: 73d5e2b47264 ("cpu/hotplug: detect SMT disabled by BIOS") Reported-by: Igor Mammedov Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Cc: Joe Mario Cc: Jiri Kosina Cc: Peter Zijlstra Cc: kvm@vger.kernel.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/e3a85d585da28cc333ecbc1e78ee9216e6da9396.1548794349.git.jpoimboe@redhat.com --- arch/x86/kernel/cpu/bugs.c | 2 +- arch/x86/kvm/vmx/vmx.c | 3 ++- include/linux/cpu.h | 2 -- kernel/cpu.c | 33 ++++----------------------------- kernel/sched/fair.c | 1 + kernel/smp.c | 2 -- 6 files changed, 8 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 1de0f4170178..01874d54f4fd 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -71,7 +71,7 @@ void __init check_bugs(void) * identify_boot_cpu() initialized SMT support information, let the * core code know. */ - cpu_smt_check_topology_early(); + cpu_smt_check_topology(); if (!IS_ENABLED(CONFIG_SMP)) { pr_info("CPU: "); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 4341175339f3..95d618045001 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -6823,7 +6824,7 @@ static int vmx_vm_init(struct kvm *kvm) * Warn upon starting the first VM in a potentially * insecure environment. */ - if (cpu_smt_control == CPU_SMT_ENABLED) + if (sched_smt_active()) pr_warn_once(L1TF_MSG_SMT); if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER) pr_warn_once(L1TF_MSG_L1D); diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 218df7f4d3e1..5041357d0297 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -180,12 +180,10 @@ enum cpuhp_smt_control { #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT) extern enum cpuhp_smt_control cpu_smt_control; extern void cpu_smt_disable(bool force); -extern void cpu_smt_check_topology_early(void); extern void cpu_smt_check_topology(void); #else # define cpu_smt_control (CPU_SMT_ENABLED) static inline void cpu_smt_disable(bool force) { } -static inline void cpu_smt_check_topology_early(void) { } static inline void cpu_smt_check_topology(void) { } #endif diff --git a/kernel/cpu.c b/kernel/cpu.c index c0c7f64573ed..d1c6d152da89 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -376,9 +376,6 @@ void __weak arch_smt_update(void) { } #ifdef CONFIG_HOTPLUG_SMT enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; -EXPORT_SYMBOL_GPL(cpu_smt_control); - -static bool cpu_smt_available __read_mostly; void __init cpu_smt_disable(bool force) { @@ -397,25 +394,11 @@ void __init cpu_smt_disable(bool force) /* * The decision whether SMT is supported can only be done after the full - * CPU identification. Called from architecture code before non boot CPUs - * are brought up. - */ -void __init cpu_smt_check_topology_early(void) -{ - if (!topology_smt_supported()) - cpu_smt_control = CPU_SMT_NOT_SUPPORTED; -} - -/* - * If SMT was disabled by BIOS, detect it here, after the CPUs have been - * brought online. This ensures the smt/l1tf sysfs entries are consistent - * with reality. cpu_smt_available is set to true during the bringup of non - * boot CPUs when a SMT sibling is detected. Note, this may overwrite - * cpu_smt_control's previous setting. + * CPU identification. Called from architecture code. */ void __init cpu_smt_check_topology(void) { - if (!cpu_smt_available) + if (!topology_smt_supported()) cpu_smt_control = CPU_SMT_NOT_SUPPORTED; } @@ -428,18 +411,10 @@ early_param("nosmt", smt_cmdline_disable); static inline bool cpu_smt_allowed(unsigned int cpu) { - if (topology_is_primary_thread(cpu)) + if (cpu_smt_control == CPU_SMT_ENABLED) return true; - /* - * If the CPU is not a 'primary' thread and the booted_once bit is - * set then the processor has SMT support. Store this information - * for the late check of SMT support in cpu_smt_check_topology(). - */ - if (per_cpu(cpuhp_state, cpu).booted_once) - cpu_smt_available = true; - - if (cpu_smt_control == CPU_SMT_ENABLED) + if (topology_is_primary_thread(cpu)) return true; /* diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 50aa2aba69bd..310d0637fe4b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5980,6 +5980,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p #ifdef CONFIG_SCHED_SMT DEFINE_STATIC_KEY_FALSE(sched_smt_present); +EXPORT_SYMBOL_GPL(sched_smt_present); static inline void set_idle_cores(int cpu, int val) { diff --git a/kernel/smp.c b/kernel/smp.c index 163c451af42e..f4cf1b0bb3b8 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -584,8 +584,6 @@ void __init smp_init(void) num_nodes, (num_nodes > 1 ? "s" : ""), num_cpus, (num_cpus > 1 ? "s" : "")); - /* Final decision about SMT support */ - cpu_smt_check_topology(); /* Any cleanup work */ smp_cpus_done(setup_max_cpus); } -- cgit v1.3-7-g2ca7 From 7d10f70fc198877b43d92bdcd7604279788b9568 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 30 Jan 2019 13:52:37 -0500 Subject: fs: Don't need to put list_lru into its own cacheline The list_lru structure is essentially just a pointer to a table of per-node LRU lists. Even if CONFIG_MEMCG_KMEM is defined, the list field is just used for LRU list registration and shrinker_id is set at initialization. Those fields won't need to be touched that often. So there is no point to make the list_lru structures to sit in their own cachelines. Signed-off-by: Waiman Long Reviewed-by: Dave Chinner Signed-off-by: Linus Torvalds --- include/linux/fs.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 811c77743dad..29d8e2cfed0e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1479,11 +1479,12 @@ struct super_block { struct user_namespace *s_user_ns; /* - * Keep the lru lists last in the structure so they always sit on their - * own individual cachelines. + * The list_lru structure is essentially just a pointer to a table + * of per-node lru lists, each of which has its own spinlock. + * There is no need to put them into separate cachelines. */ - struct list_lru s_dentry_lru ____cacheline_aligned_in_smp; - struct list_lru s_inode_lru ____cacheline_aligned_in_smp; + struct list_lru s_dentry_lru; + struct list_lru s_inode_lru; struct rcu_head rcu; struct work_struct destroy_work; -- cgit v1.3-7-g2ca7 From af0c9af1b3f66052c369d08be3f60fa9a9559e48 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 30 Jan 2019 13:52:38 -0500 Subject: fs/dcache: Track & report number of negative dentries The current dentry number tracking code doesn't distinguish between positive & negative dentries. It just reports the total number of dentries in the LRU lists. As excessive number of negative dentries can have an impact on system performance, it will be wise to track the number of positive and negative dentries separately. This patch adds tracking for the total number of negative dentries in the system LRU lists and reports it in the 5th field in the /proc/sys/fs/dentry-state file. The number, however, does not include negative dentries that are in flight but not in the LRU yet as well as those in the shrinker lists which are on the way out anyway. The number of positive dentries in the LRU lists can be roughly found by subtracting the number of negative dentries from the unused count. Matthew Wilcox had confirmed that since the introduction of the dentry_stat structure in 2.1.60, the dummy array was there, probably for future extension. They were not replacements of pre-existing fields. So no sane applications that read the value of /proc/sys/fs/dentry-state will do dummy thing if the last 2 fields of the sysctl parameter are not zero. IOW, it will be safe to use one of the dummy array entry for negative dentry count. Signed-off-by: Waiman Long Signed-off-by: Linus Torvalds --- Documentation/sysctl/fs.txt | 26 ++++++++++++++++---------- fs/dcache.c | 32 ++++++++++++++++++++++++++++++++ include/linux/dcache.h | 7 ++++--- 3 files changed, 52 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/Documentation/sysctl/fs.txt b/Documentation/sysctl/fs.txt index 819caf8ca05f..58649bd4fcfc 100644 --- a/Documentation/sysctl/fs.txt +++ b/Documentation/sysctl/fs.txt @@ -56,26 +56,32 @@ of any kernel data structures. dentry-state: -From linux/fs/dentry.c: +From linux/include/linux/dcache.h: -------------------------------------------------------------- -struct { +struct dentry_stat_t dentry_stat { int nr_dentry; int nr_unused; int age_limit; /* age in seconds */ int want_pages; /* pages requested by system */ - int dummy[2]; -} dentry_stat = {0, 0, 45, 0,}; --------------------------------------------------------------- - -Dentries are dynamically allocated and deallocated, and -nr_dentry seems to be 0 all the time. Hence it's safe to -assume that only nr_unused, age_limit and want_pages are -used. Nr_unused seems to be exactly what its name says. + int nr_negative; /* # of unused negative dentries */ + int dummy; /* Reserved for future use */ +}; +-------------------------------------------------------------- + +Dentries are dynamically allocated and deallocated. + +nr_dentry shows the total number of dentries allocated (active ++ unused). nr_unused shows the number of dentries that are not +actively used, but are saved in the LRU list for future reuse. + Age_limit is the age in seconds after which dcache entries can be reclaimed when memory is short and want_pages is nonzero when shrink_dcache_pages() has been called and the dcache isn't pruned yet. +nr_negative shows the number of unused dentries that are also +negative dentries which do not mapped to actual files. + ============================================================== dquot-max & dquot-nr: diff --git a/fs/dcache.c b/fs/dcache.c index 44e5652b2664..aac41adf4743 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -119,6 +119,7 @@ struct dentry_stat_t dentry_stat = { static DEFINE_PER_CPU(long, nr_dentry); static DEFINE_PER_CPU(long, nr_dentry_unused); +static DEFINE_PER_CPU(long, nr_dentry_negative); #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) @@ -152,11 +153,22 @@ static long get_nr_dentry_unused(void) return sum < 0 ? 0 : sum; } +static long get_nr_dentry_negative(void) +{ + int i; + long sum = 0; + + for_each_possible_cpu(i) + sum += per_cpu(nr_dentry_negative, i); + return sum < 0 ? 0 : sum; +} + int proc_nr_dentry(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { dentry_stat.nr_dentry = get_nr_dentry(); dentry_stat.nr_unused = get_nr_dentry_unused(); + dentry_stat.nr_negative = get_nr_dentry_negative(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #endif @@ -317,6 +329,8 @@ static inline void __d_clear_type_and_inode(struct dentry *dentry) flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); WRITE_ONCE(dentry->d_flags, flags); dentry->d_inode = NULL; + if (dentry->d_flags & DCACHE_LRU_LIST) + this_cpu_inc(nr_dentry_negative); } static void dentry_free(struct dentry *dentry) @@ -371,6 +385,11 @@ static void dentry_unlink_inode(struct dentry * dentry) * The per-cpu "nr_dentry_unused" counters are updated with * the DCACHE_LRU_LIST bit. * + * The per-cpu "nr_dentry_negative" counters are only updated + * when deleted from or added to the per-superblock LRU list, not + * from/to the shrink list. That is to avoid an unneeded dec/inc + * pair when moving from LRU to shrink list in select_collect(). + * * These helper functions make sure we always follow the * rules. d_lock must be held by the caller. */ @@ -380,6 +399,8 @@ static void d_lru_add(struct dentry *dentry) D_FLAG_VERIFY(dentry, 0); dentry->d_flags |= DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); + if (d_is_negative(dentry)) + this_cpu_inc(nr_dentry_negative); WARN_ON_ONCE(!list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } @@ -388,6 +409,8 @@ static void d_lru_del(struct dentry *dentry) D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); + if (d_is_negative(dentry)) + this_cpu_dec(nr_dentry_negative); WARN_ON_ONCE(!list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } @@ -418,6 +441,8 @@ static void d_lru_isolate(struct list_lru_one *lru, struct dentry *dentry) D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); + if (d_is_negative(dentry)) + this_cpu_dec(nr_dentry_negative); list_lru_isolate(lru, &dentry->d_lru); } @@ -426,6 +451,8 @@ static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry, { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags |= DCACHE_SHRINK_LIST; + if (d_is_negative(dentry)) + this_cpu_dec(nr_dentry_negative); list_lru_isolate_move(lru, &dentry->d_lru, list); } @@ -1816,6 +1843,11 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) WARN_ON(d_in_lookup(dentry)); spin_lock(&dentry->d_lock); + /* + * Decrement negative dentry count if it was in the LRU list. + */ + if (dentry->d_flags & DCACHE_LRU_LIST) + this_cpu_dec(nr_dentry_negative); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index ef4b70f64f33..60996e64c579 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -62,9 +62,10 @@ extern const struct qstr slash_name; struct dentry_stat_t { long nr_dentry; long nr_unused; - long age_limit; /* age in seconds */ - long want_pages; /* pages requested by system */ - long dummy[2]; + long age_limit; /* age in seconds */ + long want_pages; /* pages requested by system */ + long nr_negative; /* # of unused negative dentries */ + long dummy; /* Reserved for future use */ }; extern struct dentry_stat_t dentry_stat; -- cgit v1.3-7-g2ca7 From 15efb47dc560849d0c07db96fdad5121f2cf736e Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Wed, 30 Jan 2019 18:26:02 +0100 Subject: PM-runtime: Fix deadlock with ktime_get() A deadlock has been seen when swicthing clocksources which use PM-runtime. The call path is: change_clocksource ... write_seqcount_begin ... timekeeping_update ... sh_cmt_clocksource_enable ... rpm_resume pm_runtime_mark_last_busy ktime_get do read_seqcount_begin while read_seqcount_retry .... write_seqcount_end Although we should be safe because we haven't yet changed the clocksource at that time, we can't do that because of seqcount protection. Use ktime_get_mono_fast_ns() instead which is lock safe for such cases. With ktime_get_mono_fast_ns, the timestamp is not guaranteed to be monotonic across an update and as a result can goes backward. According to update_fast_timekeeper() description: "In the worst case, this can result is a slightly wrong timestamp (a few nanoseconds)". For PM-runtime autosuspend, this means only that the suspend decision may be slightly suboptimal. Fixes: 8234f6734c5d ("PM-runtime: Switch autosuspend over to using hrtimers") Reported-by: Biju Das Signed-off-by: Vincent Guittot Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- drivers/base/power/runtime.c | 10 +++++----- include/linux/pm_runtime.h | 2 +- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 457be03b744d..0ea2139c50d8 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -130,7 +130,7 @@ u64 pm_runtime_autosuspend_expiration(struct device *dev) { int autosuspend_delay; u64 last_busy, expires = 0; - u64 now = ktime_to_ns(ktime_get()); + u64 now = ktime_get_mono_fast_ns(); if (!dev->power.use_autosuspend) goto out; @@ -909,7 +909,7 @@ static enum hrtimer_restart pm_suspend_timer_fn(struct hrtimer *timer) * If 'expires' is after the current time, we've been called * too early. */ - if (expires > 0 && expires < ktime_to_ns(ktime_get())) { + if (expires > 0 && expires < ktime_get_mono_fast_ns()) { dev->power.timer_expires = 0; rpm_suspend(dev, dev->power.timer_autosuspends ? (RPM_ASYNC | RPM_AUTO) : RPM_ASYNC); @@ -928,7 +928,7 @@ static enum hrtimer_restart pm_suspend_timer_fn(struct hrtimer *timer) int pm_schedule_suspend(struct device *dev, unsigned int delay) { unsigned long flags; - ktime_t expires; + u64 expires; int retval; spin_lock_irqsave(&dev->power.lock, flags); @@ -945,8 +945,8 @@ int pm_schedule_suspend(struct device *dev, unsigned int delay) /* Other scheduled or pending requests need to be canceled. */ pm_runtime_cancel_pending(dev); - expires = ktime_add(ktime_get(), ms_to_ktime(delay)); - dev->power.timer_expires = ktime_to_ns(expires); + expires = ktime_get_mono_fast_ns() + (u64)delay * NSEC_PER_MSEC; + dev->power.timer_expires = expires; dev->power.timer_autosuspends = 0; hrtimer_start(&dev->power.suspend_timer, expires, HRTIMER_MODE_ABS); diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 54af4eef169f..fed5be706bc9 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -105,7 +105,7 @@ static inline bool pm_runtime_callbacks_present(struct device *dev) static inline void pm_runtime_mark_last_busy(struct device *dev) { - WRITE_ONCE(dev->power.last_busy, ktime_to_ns(ktime_get())); + WRITE_ONCE(dev->power.last_busy, ktime_get_mono_fast_ns()); } static inline bool pm_runtime_is_irq_safe(struct device *dev) -- cgit v1.3-7-g2ca7 From d5256083f62e2720f75bb3c5a928a0afe47d6bc3 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 30 Jan 2019 12:49:48 +0100 Subject: ipvlan, l3mdev: fix broken l3s mode wrt local routes While implementing ipvlan l3 and l3s mode for kubernetes CNI plugin, I ran into the issue that while l3 mode is working fine, l3s mode does not have any connectivity to kube-apiserver and hence all pods end up in Error state as well. The ipvlan master device sits on top of a bond device and hostns traffic to kube-apiserver (also running in hostns) is DNATed from 10.152.183.1:443 to 139.178.29.207:37573 where the latter is the address of the bond0. While in l3 mode, a curl to https://10.152.183.1:443 or to https://139.178.29.207:37573 works fine from hostns, neither of them do in case of l3s. In the latter only a curl to https://127.0.0.1:37573 appeared to work where for local addresses of bond0 I saw kernel suddenly starting to emit ARP requests to query HW address of bond0 which remained unanswered and neighbor entries in INCOMPLETE state. These ARP requests only happen while in l3s. Debugging this further, I found the issue is that l3s mode is piggy- backing on l3 master device, and in this case local routes are using l3mdev_master_dev_rcu(dev) instead of net->loopback_dev as per commit f5a0aab84b74 ("net: ipv4: dst for local input routes should use l3mdev if relevant") and 5f02ce24c269 ("net: l3mdev: Allow the l3mdev to be a loopback"). I found that reverting them back into using the net->loopback_dev fixed ipvlan l3s connectivity and got everything working for the CNI. Now judging from 4fbae7d83c98 ("ipvlan: Introduce l3s mode") and the l3mdev paper in [0] the only sole reason why ipvlan l3s is relying on l3 master device is to get the l3mdev_ip_rcv() receive hook for setting the dst entry of the input route without adding its own ipvlan specific hacks into the receive path, however, any l3 domain semantics beyond just that are breaking l3s operation. Note that ipvlan also has the ability to dynamically switch its internal operation from l3 to l3s for all ports via ipvlan_set_port_mode() at runtime. In any case, l3 vs l3s soley distinguishes itself by 'de-confusing' netfilter through switching skb->dev to ipvlan slave device late in NF_INET_LOCAL_IN before handing the skb to L4. Minimal fix taken here is to add a IFF_L3MDEV_RX_HANDLER flag which, if set from ipvlan setup, gets us only the wanted l3mdev_l3_rcv() hook without any additional l3mdev semantics on top. This should also have minimal impact since dev->priv_flags is already hot in cache. With this set, l3s mode is working fine and I also get things like masquerading pod traffic on the ipvlan master properly working. [0] https://netdevconf.org/1.2/papers/ahern-what-is-l3mdev-paper.pdf Fixes: f5a0aab84b74 ("net: ipv4: dst for local input routes should use l3mdev if relevant") Fixes: 5f02ce24c269 ("net: l3mdev: Allow the l3mdev to be a loopback") Fixes: 4fbae7d83c98 ("ipvlan: Introduce l3s mode") Signed-off-by: Daniel Borkmann Cc: Mahesh Bandewar Cc: David Ahern Cc: Florian Westphal Cc: Martynas Pumputis Acked-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/ipvlan/ipvlan_main.c | 6 +++--- include/linux/netdevice.h | 8 ++++++++ include/net/l3mdev.h | 3 ++- 3 files changed, 13 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 19bdde60680c..7cdac77d0c68 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -100,12 +100,12 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval, err = ipvlan_register_nf_hook(read_pnet(&port->pnet)); if (!err) { mdev->l3mdev_ops = &ipvl_l3mdev_ops; - mdev->priv_flags |= IFF_L3MDEV_MASTER; + mdev->priv_flags |= IFF_L3MDEV_RX_HANDLER; } else goto fail; } else if (port->mode == IPVLAN_MODE_L3S) { /* Old mode was L3S */ - mdev->priv_flags &= ~IFF_L3MDEV_MASTER; + mdev->priv_flags &= ~IFF_L3MDEV_RX_HANDLER; ipvlan_unregister_nf_hook(read_pnet(&port->pnet)); mdev->l3mdev_ops = NULL; } @@ -167,7 +167,7 @@ static void ipvlan_port_destroy(struct net_device *dev) struct sk_buff *skb; if (port->mode == IPVLAN_MODE_L3S) { - dev->priv_flags &= ~IFF_L3MDEV_MASTER; + dev->priv_flags &= ~IFF_L3MDEV_RX_HANDLER; ipvlan_unregister_nf_hook(dev_net(dev)); dev->l3mdev_ops = NULL; } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1377d085ef99..86dbb3e29139 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1483,6 +1483,7 @@ struct net_device_ops { * @IFF_NO_RX_HANDLER: device doesn't support the rx_handler hook * @IFF_FAILOVER: device is a failover master device * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device + * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1514,6 +1515,7 @@ enum netdev_priv_flags { IFF_NO_RX_HANDLER = 1<<26, IFF_FAILOVER = 1<<27, IFF_FAILOVER_SLAVE = 1<<28, + IFF_L3MDEV_RX_HANDLER = 1<<29, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1544,6 +1546,7 @@ enum netdev_priv_flags { #define IFF_NO_RX_HANDLER IFF_NO_RX_HANDLER #define IFF_FAILOVER IFF_FAILOVER #define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE +#define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER /** * struct net_device - The DEVICE structure. @@ -4549,6 +4552,11 @@ static inline bool netif_supports_nofcs(struct net_device *dev) return dev->priv_flags & IFF_SUPP_NOFCS; } +static inline bool netif_has_l3_rx_handler(const struct net_device *dev) +{ + return dev->priv_flags & IFF_L3MDEV_RX_HANDLER; +} + static inline bool netif_is_l3_master(const struct net_device *dev) { return dev->priv_flags & IFF_L3MDEV_MASTER; diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 78fa0ac4613c..5175fd63cd82 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -153,7 +153,8 @@ struct sk_buff *l3mdev_l3_rcv(struct sk_buff *skb, u16 proto) if (netif_is_l3_slave(skb->dev)) master = netdev_master_upper_dev_get_rcu(skb->dev); - else if (netif_is_l3_master(skb->dev)) + else if (netif_is_l3_master(skb->dev) || + netif_has_l3_rx_handler(skb->dev)) master = skb->dev; if (master && master->l3mdev_ops->l3mdev_l3_rcv) -- cgit v1.3-7-g2ca7 From 4ec5302fa906ec9d86597b236f62315bacdb9622 Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Wed, 30 Jan 2019 15:54:19 +0100 Subject: net: stmmac: Fallback to Platform Data clock in Watchdog conversion If we don't have DT then stmmac_clk will not be available. Let's add a new Platform Data field so that we can specify the refclk by this mean. This way we can still use the coalesce command in PCI based setups. Signed-off-by: Jose Abreu Cc: Joao Pinto Cc: David S. Miller Cc: Giuseppe Cavallaro Cc: Alexandre Torgue Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 14 ++++++++++---- include/linux/stmmac.h | 1 + 2 files changed, 11 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index d1f61c25d82b..5d85742a2be0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -721,8 +721,11 @@ static u32 stmmac_usec2riwt(u32 usec, struct stmmac_priv *priv) { unsigned long clk = clk_get_rate(priv->plat->stmmac_clk); - if (!clk) - return 0; + if (!clk) { + clk = priv->plat->clk_ref_rate; + if (!clk) + return 0; + } return (usec * (clk / 1000000)) / 256; } @@ -731,8 +734,11 @@ static u32 stmmac_riwt2usec(u32 riwt, struct stmmac_priv *priv) { unsigned long clk = clk_get_rate(priv->plat->stmmac_clk); - if (!clk) - return 0; + if (!clk) { + clk = priv->plat->clk_ref_rate; + if (!clk) + return 0; + } return (riwt * 256) / (clk / 1000000); } diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 7ddfc65586b0..4335bd771ce5 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -184,6 +184,7 @@ struct plat_stmmacenet_data { struct clk *pclk; struct clk *clk_ptp_ref; unsigned int clk_ptp_rate; + unsigned int clk_ref_rate; struct reset_control *stmmac_rst; struct stmmac_axi *axi; int has_gmac4; -- cgit v1.3-7-g2ca7 From 56841070ccc87b463ac037d2d1f2beb8e5e35f0c Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Thu, 31 Jan 2019 11:19:43 +0000 Subject: irqchip/gic-v3-its: Fix ITT_entry_size accessor According to ARM IHI 0069C (ID070116), we should use GITS_TYPER's bits [7:4] as ITT_entry_size instead of [8:4]. Although this is pretty annoying, it only results in a potential over-allocation of memory, and nothing bad happens. Fixes: 3dfa576bfb45 ("irqchip/gic-v3-its: Add probing for VLPI properties") Signed-off-by: Zenghui Yu [maz: massaged subject and commit message] Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 071b4cbdf010..c848a7cc502e 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -319,7 +319,7 @@ #define GITS_TYPER_PLPIS (1UL << 0) #define GITS_TYPER_VLPIS (1UL << 1) #define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT 4 -#define GITS_TYPER_ITT_ENTRY_SIZE(r) ((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0x1f) + 1) +#define GITS_TYPER_ITT_ENTRY_SIZE(r) ((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0xf) + 1) #define GITS_TYPER_IDBITS_SHIFT 8 #define GITS_TYPER_DEVBITS_SHIFT 13 #define GITS_TYPER_DEVBITS(r) ((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1) -- cgit v1.3-7-g2ca7 From 9a6d5488002fdca7134a0e59b0ae252f61042810 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 30 Jan 2019 08:41:40 -0700 Subject: ide: ensure atapi sense request aren't preempted There's an issue with how sense requests are handled in IDE. If ide-cd encounters an error, it queues a sense request. With how IDE request handling is done, this is the next request we need to handle. But it's impossible to guarantee this, as another request could come in between the sense being queued, and ->queue_rq() being run and handling it. If that request ALSO fails, then we attempt to doubly queue the single sense request we have. Since we only support one active request at the time, defer request processing when a sense request is queued. Fixes: 600335205b8d "ide: convert to blk-mq" Reported-by: He Zhe Tested-by: He Zhe Signed-off-by: Jens Axboe --- drivers/ide/ide-atapi.c | 9 +++++++- drivers/ide/ide-io.c | 61 +++++++++++++++++++++++++------------------------ drivers/ide/ide-park.c | 2 ++ drivers/ide/ide-probe.c | 23 +++++++++++++------ include/linux/ide.h | 2 ++ 5 files changed, 59 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c index da58020a144e..33a28cde126c 100644 --- a/drivers/ide/ide-atapi.c +++ b/drivers/ide/ide-atapi.c @@ -235,21 +235,28 @@ EXPORT_SYMBOL_GPL(ide_prep_sense); int ide_queue_sense_rq(ide_drive_t *drive, void *special) { - struct request *sense_rq = drive->sense_rq; + ide_hwif_t *hwif = drive->hwif; + struct request *sense_rq; + unsigned long flags; + + spin_lock_irqsave(&hwif->lock, flags); /* deferred failure from ide_prep_sense() */ if (!drive->sense_rq_armed) { printk(KERN_WARNING PFX "%s: error queuing a sense request\n", drive->name); + spin_unlock_irqrestore(&hwif->lock, flags); return -ENOMEM; } + sense_rq = drive->sense_rq; ide_req(sense_rq)->special = special; drive->sense_rq_armed = false; drive->hwif->rq = NULL; ide_insert_request_head(drive, sense_rq); + spin_unlock_irqrestore(&hwif->lock, flags); return 0; } EXPORT_SYMBOL_GPL(ide_queue_sense_rq); diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c index 8445b484ae69..b137f27a34d5 100644 --- a/drivers/ide/ide-io.c +++ b/drivers/ide/ide-io.c @@ -68,8 +68,10 @@ int ide_end_rq(ide_drive_t *drive, struct request *rq, blk_status_t error, } if (!blk_update_request(rq, error, nr_bytes)) { - if (rq == drive->sense_rq) + if (rq == drive->sense_rq) { drive->sense_rq = NULL; + drive->sense_rq_active = false; + } __blk_mq_end_request(rq, error); return 0; @@ -451,16 +453,11 @@ void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq) blk_mq_delay_run_hw_queue(q->queue_hw_ctx[0], 3); } -/* - * Issue a new request to a device. - */ -blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *hctx, - const struct blk_mq_queue_data *bd) +blk_status_t ide_issue_rq(ide_drive_t *drive, struct request *rq, + bool local_requeue) { - ide_drive_t *drive = hctx->queue->queuedata; - ide_hwif_t *hwif = drive->hwif; + ide_hwif_t *hwif = drive->hwif; struct ide_host *host = hwif->host; - struct request *rq = bd->rq; ide_startstop_t startstop; if (!blk_rq_is_passthrough(rq) && !(rq->rq_flags & RQF_DONTPREP)) { @@ -474,8 +471,6 @@ blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *hctx, if (ide_lock_host(host, hwif)) return BLK_STS_DEV_RESOURCE; - blk_mq_start_request(rq); - spin_lock_irq(&hwif->lock); if (!ide_lock_port(hwif)) { @@ -510,18 +505,6 @@ repeat: hwif->cur_dev = drive; drive->dev_flags &= ~(IDE_DFLAG_SLEEPING | IDE_DFLAG_PARKED); - /* - * we know that the queue isn't empty, but this can happen - * if ->prep_rq() decides to kill a request - */ - if (!rq) { - rq = bd->rq; - if (!rq) { - ide_unlock_port(hwif); - goto out; - } - } - /* * Sanity: don't accept a request that isn't a PM request * if we are currently power managed. This is very important as @@ -560,9 +543,12 @@ repeat: } } else { plug_device: + if (local_requeue) + list_add(&rq->queuelist, &drive->rq_list); spin_unlock_irq(&hwif->lock); ide_unlock_host(host); - ide_requeue_and_plug(drive, rq); + if (!local_requeue) + ide_requeue_and_plug(drive, rq); return BLK_STS_OK; } @@ -573,6 +559,26 @@ out: return BLK_STS_OK; } +/* + * Issue a new request to a device. + */ +blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *hctx, + const struct blk_mq_queue_data *bd) +{ + ide_drive_t *drive = hctx->queue->queuedata; + ide_hwif_t *hwif = drive->hwif; + + spin_lock_irq(&hwif->lock); + if (drive->sense_rq_active) { + spin_unlock_irq(&hwif->lock); + return BLK_STS_DEV_RESOURCE; + } + spin_unlock_irq(&hwif->lock); + + blk_mq_start_request(bd->rq); + return ide_issue_rq(drive, bd->rq, false); +} + static int drive_is_ready(ide_drive_t *drive) { ide_hwif_t *hwif = drive->hwif; @@ -893,13 +899,8 @@ EXPORT_SYMBOL_GPL(ide_pad_transfer); void ide_insert_request_head(ide_drive_t *drive, struct request *rq) { - ide_hwif_t *hwif = drive->hwif; - unsigned long flags; - - spin_lock_irqsave(&hwif->lock, flags); + drive->sense_rq_active = true; list_add_tail(&rq->queuelist, &drive->rq_list); - spin_unlock_irqrestore(&hwif->lock, flags); - kblockd_schedule_work(&drive->rq_work); } EXPORT_SYMBOL_GPL(ide_insert_request_head); diff --git a/drivers/ide/ide-park.c b/drivers/ide/ide-park.c index 102aa3bc3e7f..8af7af6001eb 100644 --- a/drivers/ide/ide-park.c +++ b/drivers/ide/ide-park.c @@ -54,7 +54,9 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout) scsi_req(rq)->cmd[0] = REQ_UNPARK_HEADS; scsi_req(rq)->cmd_len = 1; ide_req(rq)->type = ATA_PRIV_MISC; + spin_lock_irq(&hwif->lock); ide_insert_request_head(drive, rq); + spin_unlock_irq(&hwif->lock); out: return; diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index 63627be0811a..5aeaca24a28f 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -1159,18 +1159,27 @@ static void drive_rq_insert_work(struct work_struct *work) ide_drive_t *drive = container_of(work, ide_drive_t, rq_work); ide_hwif_t *hwif = drive->hwif; struct request *rq; + blk_status_t ret; LIST_HEAD(list); - spin_lock_irq(&hwif->lock); - if (!list_empty(&drive->rq_list)) - list_splice_init(&drive->rq_list, &list); - spin_unlock_irq(&hwif->lock); + blk_mq_quiesce_queue(drive->queue); - while (!list_empty(&list)) { - rq = list_first_entry(&list, struct request, queuelist); + ret = BLK_STS_OK; + spin_lock_irq(&hwif->lock); + while (!list_empty(&drive->rq_list)) { + rq = list_first_entry(&drive->rq_list, struct request, queuelist); list_del_init(&rq->queuelist); - blk_execute_rq_nowait(drive->queue, rq->rq_disk, rq, true, NULL); + + spin_unlock_irq(&hwif->lock); + ret = ide_issue_rq(drive, rq, true); + spin_lock_irq(&hwif->lock); } + spin_unlock_irq(&hwif->lock); + + blk_mq_unquiesce_queue(drive->queue); + + if (ret != BLK_STS_OK) + kblockd_schedule_work(&drive->rq_work); } static const u8 ide_hwif_to_major[] = diff --git a/include/linux/ide.h b/include/linux/ide.h index e7d29ae633cd..971cf76a78a0 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -615,6 +615,7 @@ struct ide_drive_s { /* current sense rq and buffer */ bool sense_rq_armed; + bool sense_rq_active; struct request *sense_rq; struct request_sense sense_data; @@ -1219,6 +1220,7 @@ extern void ide_stall_queue(ide_drive_t *drive, unsigned long timeout); extern void ide_timer_expiry(struct timer_list *t); extern irqreturn_t ide_intr(int irq, void *dev_id); extern blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); +extern blk_status_t ide_issue_rq(ide_drive_t *, struct request *, bool); extern void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq); void ide_init_disk(struct gendisk *, ide_drive_t *); -- cgit v1.3-7-g2ca7 From 6cab5e90ab2bd323c9f3811b6c70a4687df51e27 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 28 Jan 2019 18:43:34 -0800 Subject: bpf: run bpf programs with preemption disabled Disabled preemption is necessary for proper access to per-cpu maps from BPF programs. But the sender side of socket filters didn't have preemption disabled: unix_dgram_sendmsg->sk_filter->sk_filter_trim_cap->bpf_prog_run_save_cb->BPF_PROG_RUN and a combination of af_packet with tun device didn't disable either: tpacket_snd->packet_direct_xmit->packet_pick_tx_queue->ndo_select_queue-> tun_select_queue->tun_ebpf_select_queue->bpf_prog_run_clear_cb->BPF_PROG_RUN Disable preemption before executing BPF programs (both classic and extended). Reported-by: Jann Horn Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- include/linux/filter.h | 21 ++++++++++++++++++--- kernel/bpf/cgroup.c | 2 +- 2 files changed, 19 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index ad106d845b22..e532fcc6e4b5 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -591,8 +591,8 @@ static inline u8 *bpf_skb_cb(struct sk_buff *skb) return qdisc_skb_cb(skb)->data; } -static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, - struct sk_buff *skb) +static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog, + struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); u8 cb_saved[BPF_SKB_CB_LEN]; @@ -611,15 +611,30 @@ static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, return res; } +static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, + struct sk_buff *skb) +{ + u32 res; + + preempt_disable(); + res = __bpf_prog_run_save_cb(prog, skb); + preempt_enable(); + return res; +} + static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); + u32 res; if (unlikely(prog->cb_access)) memset(cb_data, 0, BPF_SKB_CB_LEN); - return BPF_PROG_RUN(prog, skb); + preempt_disable(); + res = BPF_PROG_RUN(prog, skb); + preempt_enable(); + return res; } static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index ab612fe9862f..d17d05570a3f 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -572,7 +572,7 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, bpf_compute_and_save_data_end(skb, &saved_data_end); ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb, - bpf_prog_run_save_cb); + __bpf_prog_run_save_cb); bpf_restore_data_end(skb, saved_data_end); __skb_pull(skb, offset); skb->sk = save_sk; -- cgit v1.3-7-g2ca7 From 9bcdeb51bd7d2ae9fe65ea4d60643d2aeef5bfe3 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Fri, 1 Feb 2019 14:20:31 -0800 Subject: oom, oom_reaper: do not enqueue same task twice Arkadiusz reported that enabling memcg's group oom killing causes strange memcg statistics where there is no task in a memcg despite the number of tasks in that memcg is not 0. It turned out that there is a bug in wake_oom_reaper() which allows enqueuing same task twice which makes impossible to decrease the number of tasks in that memcg due to a refcount leak. This bug existed since the OOM reaper became invokable from task_will_free_mem(current) path in out_of_memory() in Linux 4.7, T1@P1 |T2@P1 |T3@P1 |OOM reaper ----------+----------+----------+------------ # Processing an OOM victim in a different memcg domain. try_charge() mem_cgroup_out_of_memory() mutex_lock(&oom_lock) try_charge() mem_cgroup_out_of_memory() mutex_lock(&oom_lock) try_charge() mem_cgroup_out_of_memory() mutex_lock(&oom_lock) out_of_memory() oom_kill_process(P1) do_send_sig_info(SIGKILL, @P1) mark_oom_victim(T1@P1) wake_oom_reaper(T1@P1) # T1@P1 is enqueued. mutex_unlock(&oom_lock) out_of_memory() mark_oom_victim(T2@P1) wake_oom_reaper(T2@P1) # T2@P1 is enqueued. mutex_unlock(&oom_lock) out_of_memory() mark_oom_victim(T1@P1) wake_oom_reaper(T1@P1) # T1@P1 is enqueued again due to oom_reaper_list == T2@P1 && T1@P1->oom_reaper_list == NULL. mutex_unlock(&oom_lock) # Completed processing an OOM victim in a different memcg domain. spin_lock(&oom_reaper_lock) # T1P1 is dequeued. spin_unlock(&oom_reaper_lock) but memcg's group oom killing made it easier to trigger this bug by calling wake_oom_reaper() on the same task from one out_of_memory() request. Fix this bug using an approach used by commit 855b018325737f76 ("oom, oom_reaper: disable oom_reaper for oom_kill_allocating_task"). As a side effect of this patch, this patch also avoids enqueuing multiple threads sharing memory via task_will_free_mem(current) path. Link: http://lkml.kernel.org/r/e865a044-2c10-9858-f4ef-254bc71d6cc2@i-love.sakura.ne.jp Link: http://lkml.kernel.org/r/5ee34fc6-1485-34f8-8790-903ddabaa809@i-love.sakura.ne.jp Fixes: af8e15cc85a25315 ("oom, oom_reaper: do not enqueue task if it is on the oom_reaper_list head") Signed-off-by: Tetsuo Handa Reported-by: Arkadiusz Miskiewicz Tested-by: Arkadiusz Miskiewicz Acked-by: Michal Hocko Acked-by: Roman Gushchin Cc: Tejun Heo Cc: Aleksa Sarai Cc: Jay Kamat Cc: Johannes Weiner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/coredump.h | 1 + mm/oom_kill.c | 4 ++-- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index ec912d01126f..ecdc6542070f 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -71,6 +71,7 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ #define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ #define MMF_OOM_VICTIM 25 /* mm is the oom victim */ +#define MMF_OOM_REAP_QUEUED 26 /* mm was queued for oom_reaper */ #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ diff --git a/mm/oom_kill.c b/mm/oom_kill.c index f0e8cd9edb1a..059e617a1847 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -647,8 +647,8 @@ static int oom_reaper(void *unused) static void wake_oom_reaper(struct task_struct *tsk) { - /* tsk is already queued? */ - if (tsk == oom_reaper_list || tsk->oom_reaper_list) + /* mm is already queued? */ + if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags)) return; get_task_struct(tsk); -- cgit v1.3-7-g2ca7 From b13bc35193d9e7a8c050a24928ca5c9e7c9a009b Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Fri, 1 Feb 2019 14:20:51 -0800 Subject: mm/hotplug: invalid PFNs from pfn_to_online_page() On an arm64 ThunderX2 server, the first kmemleak scan would crash [1] with CONFIG_DEBUG_VM_PGFLAGS=y due to page_to_nid() found a pfn that is not directly mapped (MEMBLOCK_NOMAP). Hence, the page->flags is uninitialized. This is due to the commit 9f1eb38e0e11 ("mm, kmemleak: little optimization while scanning") starts to use pfn_to_online_page() instead of pfn_valid(). However, in the CONFIG_MEMORY_HOTPLUG=y case, pfn_to_online_page() does not call memblock_is_map_memory() while pfn_valid() does. Historically, the commit 68709f45385a ("arm64: only consider memblocks with NOMAP cleared for linear mapping") causes pages marked as nomap being no long reassigned to the new zone in memmap_init_zone() by calling __init_single_page(). Since the commit 2d070eab2e82 ("mm: consider zone which is not fully populated to have holes") introduced pfn_to_online_page() and was designed to return a valid pfn only, but it is clearly broken on arm64. Therefore, let pfn_to_online_page() call pfn_valid_within(), so it can handle nomap thanks to the commit f52bb98f5ade ("arm64: mm: always enable CONFIG_HOLES_IN_ZONE"), while it will be optimized away on architectures where have no HOLES_IN_ZONE. [1] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000006 Mem abort info: ESR = 0x96000005 Exception class = DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 Data abort info: ISV = 0, ISS = 0x00000005 CM = 0, WnR = 0 Internal error: Oops: 96000005 [#1] SMP CPU: 60 PID: 1408 Comm: kmemleak Not tainted 5.0.0-rc2+ #8 pstate: 60400009 (nZCv daif +PAN -UAO) pc : page_mapping+0x24/0x144 lr : __dump_page+0x34/0x3dc sp : ffff00003a5cfd10 x29: ffff00003a5cfd10 x28: 000000000000802f x27: 0000000000000000 x26: 0000000000277d00 x25: ffff000010791f56 x24: ffff7fe000000000 x23: ffff000010772f8b x22: ffff00001125f670 x21: ffff000011311000 x20: ffff000010772f8b x19: fffffffffffffffe x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: ffff802698b19600 x13: ffff802698b1a200 x12: ffff802698b16f00 x11: ffff802698b1a400 x10: 0000000000001400 x9 : 0000000000000001 x8 : ffff00001121a000 x7 : 0000000000000000 x6 : ffff0000102c53b8 x5 : 0000000000000000 x4 : 0000000000000003 x3 : 0000000000000100 x2 : 0000000000000000 x1 : ffff000010772f8b x0 : ffffffffffffffff Process kmemleak (pid: 1408, stack limit = 0x(____ptrval____)) Call trace: page_mapping+0x24/0x144 __dump_page+0x34/0x3dc dump_page+0x28/0x4c kmemleak_scan+0x4ac/0x680 kmemleak_scan_thread+0xb4/0xdc kthread+0x12c/0x13c ret_from_fork+0x10/0x18 Code: d503201f f9400660 36000040 d1000413 (f9400661) ---[ end trace 4d4bd7f573490c8e ]--- Kernel panic - not syncing: Fatal exception SMP: stopping secondary CPUs Kernel Offset: disabled CPU features: 0x002,20000c38 Memory Limit: none ---[ end Kernel panic - not syncing: Fatal exception ]--- Link: http://lkml.kernel.org/r/20190122132916.28360-1-cai@lca.pw Fixes: 9f1eb38e0e11 ("mm, kmemleak: little optimization while scanning") Signed-off-by: Qian Cai Acked-by: Michal Hocko Cc: Oscar Salvador Cc: Catalin Marinas Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 07da5c6c5ba0..368267c1b71b 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -21,14 +21,16 @@ struct vmem_altmap; * walkers which rely on the fully initialized page->flags and others * should use this rather than pfn_valid && pfn_to_page */ -#define pfn_to_online_page(pfn) \ -({ \ - struct page *___page = NULL; \ - unsigned long ___nr = pfn_to_section_nr(pfn); \ - \ - if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr))\ - ___page = pfn_to_page(pfn); \ - ___page; \ +#define pfn_to_online_page(pfn) \ +({ \ + struct page *___page = NULL; \ + unsigned long ___pfn = pfn; \ + unsigned long ___nr = pfn_to_section_nr(___pfn); \ + \ + if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr) && \ + pfn_valid_within(___pfn)) \ + ___page = pfn_to_page(___pfn); \ + ___page; \ }) /* -- cgit v1.3-7-g2ca7 From e6d429313ea5c776d2e76b4494df69102e6b7115 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 29 Jan 2019 17:44:36 -0500 Subject: x86/resctrl: Avoid confusion over the new X86_RESCTRL config "Resource Control" is a very broad term for this CPU feature, and a term that is also associated with containers, cgroups etc. This can easily cause confusion. Make the user prompt more specific. Match the config symbol name. [ bp: In the future, the corresponding ARM arch-specific code will be under ARM_CPU_RESCTRL and the arch-agnostic bits will be carved out under the CPU_RESCTRL umbrella symbol. ] Signed-off-by: Johannes Weiner Signed-off-by: Borislav Petkov Cc: Babu Moger Cc: Fenghua Yu Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: James Morse Cc: Jonathan Corbet Cc: "Kirill A. Shutemov" Cc: linux-doc@vger.kernel.org Cc: Peter Zijlstra Cc: Pu Wen Cc: Reinette Chatre Cc: Thomas Gleixner Cc: Tony Luck Cc: x86-ml Link: https://lkml.kernel.org/r/20190130195621.GA30653@cmpxchg.org --- Documentation/x86/resctrl_ui.txt | 2 +- arch/x86/Kconfig | 6 +++--- arch/x86/include/asm/resctrl_sched.h | 4 ++-- arch/x86/kernel/cpu/Makefile | 2 +- arch/x86/kernel/cpu/resctrl/Makefile | 4 ++-- include/linux/sched.h | 2 +- 6 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/Documentation/x86/resctrl_ui.txt b/Documentation/x86/resctrl_ui.txt index e8e8d14d3c4e..c1f95b59e14d 100644 --- a/Documentation/x86/resctrl_ui.txt +++ b/Documentation/x86/resctrl_ui.txt @@ -9,7 +9,7 @@ Fenghua Yu Tony Luck Vikas Shivappa -This feature is enabled by the CONFIG_X86_RESCTRL and the x86 /proc/cpuinfo +This feature is enabled by the CONFIG_X86_CPU_RESCTRL and the x86 /proc/cpuinfo flag bits: RDT (Resource Director Technology) Allocation - "rdt_a" CAT (Cache Allocation Technology) - "cat_l3", "cat_l2" diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 26387c7bf305..68261430fe6e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -446,12 +446,12 @@ config RETPOLINE branches. Requires a compiler with -mindirect-branch=thunk-extern support for full protection. The kernel may run slower. -config X86_RESCTRL - bool "Resource Control support" +config X86_CPU_RESCTRL + bool "x86 CPU resource control support" depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD) select KERNFS help - Enable Resource Control support. + Enable x86 CPU resource control support. Provide support for the allocation and monitoring of system resources usage by the CPU. diff --git a/arch/x86/include/asm/resctrl_sched.h b/arch/x86/include/asm/resctrl_sched.h index 40ebddde6ac2..f6b7fe2833cc 100644 --- a/arch/x86/include/asm/resctrl_sched.h +++ b/arch/x86/include/asm/resctrl_sched.h @@ -2,7 +2,7 @@ #ifndef _ASM_X86_RESCTRL_SCHED_H #define _ASM_X86_RESCTRL_SCHED_H -#ifdef CONFIG_X86_RESCTRL +#ifdef CONFIG_X86_CPU_RESCTRL #include #include @@ -88,6 +88,6 @@ static inline void resctrl_sched_in(void) static inline void resctrl_sched_in(void) {} -#endif /* CONFIG_X86_RESCTRL */ +#endif /* CONFIG_X86_CPU_RESCTRL */ #endif /* _ASM_X86_RESCTRL_SCHED_H */ diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index b6fa0869f7aa..cfd24f9f7614 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -39,7 +39,7 @@ obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o obj-$(CONFIG_X86_MCE) += mce/ obj-$(CONFIG_MTRR) += mtrr/ obj-$(CONFIG_MICROCODE) += microcode/ -obj-$(CONFIG_X86_RESCTRL) += resctrl/ +obj-$(CONFIG_X86_CPU_RESCTRL) += resctrl/ obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o diff --git a/arch/x86/kernel/cpu/resctrl/Makefile b/arch/x86/kernel/cpu/resctrl/Makefile index 1cabe6fd8e11..4a06c37b9cf1 100644 --- a/arch/x86/kernel/cpu/resctrl/Makefile +++ b/arch/x86/kernel/cpu/resctrl/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_X86_RESCTRL) += core.o rdtgroup.o monitor.o -obj-$(CONFIG_X86_RESCTRL) += ctrlmondata.o pseudo_lock.o +obj-$(CONFIG_X86_CPU_RESCTRL) += core.o rdtgroup.o monitor.o +obj-$(CONFIG_X86_CPU_RESCTRL) += ctrlmondata.o pseudo_lock.o CFLAGS_pseudo_lock.o = -I$(src) diff --git a/include/linux/sched.h b/include/linux/sched.h index 224666226e87..8c328b14c424 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -995,7 +995,7 @@ struct task_struct { /* cg_list protected by css_set_lock and tsk->alloc_lock: */ struct list_head cg_list; #endif -#ifdef CONFIG_X86_RESCTRL +#ifdef CONFIG_X86_CPU_RESCTRL u32 closid; u32 rmid; #endif -- cgit v1.3-7-g2ca7 From 0803de78049fe1b0baf44bcddc727b036fb9139b Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 7 Feb 2019 11:55:39 +0100 Subject: blktrace: Show requests without sector Currently, blktrace will not show requests that don't have any data as rq->__sector is initialized to -1 which is out of device range and thus discarded by act_log_check(). This is most notably the case for cache flush requests sent to the device. Fix the problem by making blk_rq_trace_sector() return 0 for requests without initialized sector. Reviewed-by: Johannes Thumshirn Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 8804753805ac..7bb2d8de9f30 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -116,7 +116,13 @@ extern void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes); static inline sector_t blk_rq_trace_sector(struct request *rq) { - return blk_rq_is_passthrough(rq) ? 0 : blk_rq_pos(rq); + /* + * Tracing should ignore starting sector for passthrough requests and + * requests where starting sector didn't get set. + */ + if (blk_rq_is_passthrough(rq) || blk_rq_pos(rq) == (sector_t)-1) + return 0; + return blk_rq_pos(rq); } static inline unsigned int blk_rq_trace_nr_sectors(struct request *rq) -- cgit v1.3-7-g2ca7