From 28b0f8a6962a24ed21737578f3b1b07424635c9e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 13 Feb 2018 07:38:08 -0800 Subject: tty: make n_tty_read() always abort if hangup is in progress A tty is hung up by __tty_hangup() setting file->f_op to hung_up_tty_fops, which is skipped on ttys whose write operation isn't tty_write(). This means that, for example, /dev/console whose write op is redirected_tty_write() is never actually marked hung up. Because n_tty_read() uses the hung up status to decide whether to abort the waiting readers, the lack of hung-up marking can lead to the following scenario. 1. A session contains two processes. The leader and its child. The child ignores SIGHUP. 2. The leader exits and starts disassociating from the controlling terminal (/dev/console). 3. __tty_hangup() skips setting f_op to hung_up_tty_fops. 4. SIGHUP is delivered and ignored. 5. tty_ldisc_hangup() is invoked. It wakes up the waits which should clear the read lockers of tty->ldisc_sem. 6. The reader wakes up but because tty_hung_up_p() is false, it doesn't abort and goes back to sleep while read-holding tty->ldisc_sem. 7. The leader progresses to tty_ldisc_lock() in tty_ldisc_hangup() and is now stuck in D sleep indefinitely waiting for tty->ldisc_sem. The following is Alan's explanation on why some ttys aren't hung up. http://lkml.kernel.org/r/20171101170908.6ad08580@alans-desktop 1. It broke the serial consoles because they would hang up and close down the hardware. With tty_port that *should* be fixable properly for any cases remaining. 2. The console layer was (and still is) completely broken and doens't refcount properly. So if you turn on console hangups it breaks (as indeed does freeing consoles and half a dozen other things). As neither can be fixed quickly, this patch works around the problem by introducing a new flag, TTY_HUPPING, which is used solely to tell n_tty_read() that hang-up is in progress for the console and the readers should be aborted regardless of the hung-up status of the device. The following is a sample hung task warning caused by this issue. INFO: task agetty:2662 blocked for more than 120 seconds. Not tainted 4.11.3-dbg-tty-lockup-02478-gfd6c7ee-dirty #28 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. 0 2662 1 0x00000086 Call Trace: __schedule+0x267/0x890 schedule+0x36/0x80 schedule_timeout+0x23c/0x2e0 ldsem_down_write+0xce/0x1f6 tty_ldisc_lock+0x16/0x30 tty_ldisc_hangup+0xb3/0x1b0 __tty_hangup+0x300/0x410 disassociate_ctty+0x6c/0x290 do_exit+0x7ef/0xb00 do_group_exit+0x3f/0xa0 get_signal+0x1b3/0x5d0 do_signal+0x28/0x660 exit_to_usermode_loop+0x46/0x86 do_syscall_64+0x9c/0xb0 entry_SYSCALL64_slow_path+0x25/0x25 The following is the repro. Run "$PROG /dev/console". The parent process hangs in D state. #include #include #include #include #include #include #include #include #include #include #include #include int main(int argc, char **argv) { struct sigaction sact = { .sa_handler = SIG_IGN }; struct timespec ts1s = { .tv_sec = 1 }; pid_t pid; int fd; if (argc < 2) { fprintf(stderr, "test-hung-tty /dev/$TTY\n"); return 1; } /* fork a child to ensure that it isn't already the session leader */ pid = fork(); if (pid < 0) { perror("fork"); return 1; } if (pid > 0) { /* top parent, wait for everyone */ while (waitpid(-1, NULL, 0) >= 0) ; if (errno != ECHILD) perror("waitpid"); return 0; } /* new session, start a new session and set the controlling tty */ if (setsid() < 0) { perror("setsid"); return 1; } fd = open(argv[1], O_RDWR); if (fd < 0) { perror("open"); return 1; } if (ioctl(fd, TIOCSCTTY, 1) < 0) { perror("ioctl"); return 1; } /* fork a child, sleep a bit and exit */ pid = fork(); if (pid < 0) { perror("fork"); return 1; } if (pid > 0) { nanosleep(&ts1s, NULL); printf("Session leader exiting\n"); exit(0); } /* * The child ignores SIGHUP and keeps reading from the controlling * tty. Because SIGHUP is ignored, the child doesn't get killed on * parent exit and the bug in n_tty makes the read(2) block the * parent's control terminal hangup attempt. The parent ends up in * D sleep until the child is explicitly killed. */ sigaction(SIGHUP, &sact, NULL); printf("Child reading tty\n"); while (1) { char buf[1024]; if (read(fd, buf, sizeof(buf)) < 0) { perror("read"); return 1; } } return 0; } Signed-off-by: Tejun Heo Cc: Alan Cox Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 0a6c71e0ad01..47f8af22f216 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -364,6 +364,7 @@ struct tty_file_private { #define TTY_PTY_LOCK 16 /* pty private */ #define TTY_NO_WRITE_SPLIT 17 /* Preserve write boundaries to driver */ #define TTY_HUPPED 18 /* Post driver->hangup() */ +#define TTY_HUPPING 19 /* Hangup in progress */ #define TTY_LDISC_HALTED 22 /* Line discipline is halted */ /* Values for tty->flow_change */ -- cgit v1.2.3 From fde9fc766e96c494b82931b1d270a9a751be07c0 Mon Sep 17 00:00:00 2001 From: Matt Redfearn Date: Mon, 19 Feb 2018 16:55:06 +0000 Subject: signals: Move put_compat_sigset to compat.h to silence hardened usercopy Since commit afcc90f8621e ("usercopy: WARN() on slab cache usercopy region violations"), MIPS systems booting with a compat root filesystem emit a warning when copying compat siginfo to userspace: WARNING: CPU: 0 PID: 953 at mm/usercopy.c:81 usercopy_warn+0x98/0xe8 Bad or missing usercopy whitelist? Kernel memory exposure attempt detected from SLAB object 'task_struct' (offset 1432, size 16)! Modules linked in: CPU: 0 PID: 953 Comm: S01logging Not tainted 4.16.0-rc2 #10 Stack : ffffffff808c0000 0000000000000000 0000000000000001 65ac85163f3bdc4a 65ac85163f3bdc4a 0000000000000000 90000000ff667ab8 ffffffff808c0000 00000000000003f8 ffffffff808d0000 00000000000000d1 0000000000000000 000000000000003c 0000000000000000 ffffffff808c8ca8 ffffffff808d0000 ffffffff808d0000 ffffffff80810000 fffffc0000000000 ffffffff80785c30 0000000000000009 0000000000000051 90000000ff667eb0 90000000ff667db0 000000007fe0d938 0000000000000018 ffffffff80449958 0000000020052798 ffffffff808c0000 90000000ff664000 90000000ff667ab0 00000000100c0000 ffffffff80698810 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 ffffffff8010d02c 65ac85163f3bdc4a ... Call Trace: [] show_stack+0x9c/0x130 [] dump_stack+0x90/0xd0 [] __warn+0x100/0x118 [] warn_slowpath_fmt+0x4c/0x70 [] usercopy_warn+0x98/0xe8 [] __check_object_size+0xfc/0x250 [] put_compat_sigset+0x30/0x88 [] setup_rt_frame_n32+0xc4/0x160 [] do_signal+0x19c/0x230 [] do_notify_resume+0x60/0x78 [] work_notifysig+0x10/0x18 ---[ end trace 88fffbf69147f48a ]--- Commit 5905429ad856 ("fork: Provide usercopy whitelisting for task_struct") noted that: "While the blocked and saved_sigmask fields of task_struct are copied to userspace (via sigmask_to_save() and setup_rt_frame()), it is always copied with a static length (i.e. sizeof(sigset_t))." However, this is not true in the case of compat signals, whose sigset is copied by put_compat_sigset and receives size as an argument. At most call sites, put_compat_sigset is copying a sigset from the current task_struct. This triggers a warning when CONFIG_HARDENED_USERCOPY is active. However, by marking this function as static inline, the warning can be avoided because in all of these cases the size is constant at compile time, which is allowed. The only site where this is not the case is handling the rt_sigpending syscall, but there the copy is being made from a stack local variable so does not trigger the warning. Move put_compat_sigset to compat.h, and mark it static inline. This fixes the WARN on MIPS. Fixes: afcc90f8621e ("usercopy: WARN() on slab cache usercopy region violations") Signed-off-by: Matt Redfearn Acked-by: Kees Cook Cc: "Dmitry V . Levin" Cc: Al Viro Cc: kernel-hardening@lists.openwall.com Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/18639/ Signed-off-by: James Hogan --- include/linux/compat.h | 26 ++++++++++++++++++++++++-- kernel/compat.c | 19 ------------------- 2 files changed, 24 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 8a9643857c4a..c4139c7a0de0 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -17,6 +17,7 @@ #include #include #include /* for aio_context_t */ +#include #include #include @@ -550,8 +551,29 @@ asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp); extern int get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat); -extern int put_compat_sigset(compat_sigset_t __user *compat, - const sigset_t *set, unsigned int size); + +/* + * Defined inline such that size can be compile time constant, which avoids + * CONFIG_HARDENED_USERCOPY complaining about copies from task_struct + */ +static inline int +put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set, + unsigned int size) +{ + /* size <= sizeof(compat_sigset_t) <= sizeof(sigset_t) */ +#ifdef __BIG_ENDIAN + compat_sigset_t v; + switch (_NSIG_WORDS) { + case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3]; + case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2]; + case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1]; + case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0]; + } + return copy_to_user(compat, &v, size) ? -EFAULT : 0; +#else + return copy_to_user(compat, set, size) ? -EFAULT : 0; +#endif +} asmlinkage long compat_sys_migrate_pages(compat_pid_t pid, compat_ulong_t maxnode, const compat_ulong_t __user *old_nodes, diff --git a/kernel/compat.c b/kernel/compat.c index 3247fe761f60..3f5fa8902e7d 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -488,25 +488,6 @@ get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat) } EXPORT_SYMBOL_GPL(get_compat_sigset); -int -put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set, - unsigned int size) -{ - /* size <= sizeof(compat_sigset_t) <= sizeof(sigset_t) */ -#ifdef __BIG_ENDIAN - compat_sigset_t v; - switch (_NSIG_WORDS) { - case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3]; - case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2]; - case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1]; - case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0]; - } - return copy_to_user(compat, &v, size) ? -EFAULT : 0; -#else - return copy_to_user(compat, set, size) ? -EFAULT : 0; -#endif -} - #ifdef CONFIG_NUMA COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages, compat_uptr_t __user *, pages32, -- cgit v1.2.3 From a6f1086e29e93621a6394b94b8c0e4a4e490f38b Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Mon, 5 Mar 2018 15:22:30 -0800 Subject: PCI: Move of_irq_parse_and_map_pci() declaration under OF_IRQ Since commit 4670d610d592 ("PCI: Move OF-related PCI functions into PCI core"), sparc:allmodconfig fails to build with the following error. pcie-cadence-host.c:(.text+0x4c4): undefined reference to `of_irq_parse_and_map_pci' pcie-cadence-host.c:(.text+0x4c8): undefined reference to `of_irq_parse_and_map_pci' of_irq_parse_and_map_pci() is now only available if OF_IRQ is enabled. Make its declaration and its dummy function dependent on OF_IRQ to solve the problem. Fixes: 4670d610d592 ("PCI: Move OF-related PCI functions into PCI core") Signed-off-by: Guenter Roeck Signed-off-by: Bjorn Helgaas Acked-by: Rob Herring --- include/linux/of_pci.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h index 88865e0ebf4d..091033a6b836 100644 --- a/include/linux/of_pci.h +++ b/include/linux/of_pci.h @@ -13,7 +13,6 @@ struct device_node; struct device_node *of_pci_find_child_device(struct device_node *parent, unsigned int devfn); int of_pci_get_devfn(struct device_node *np); -int of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin); int of_pci_parse_bus_range(struct device_node *node, struct resource *res); int of_get_pci_domain_nr(struct device_node *node); int of_pci_get_max_link_speed(struct device_node *node); @@ -33,12 +32,6 @@ static inline int of_pci_get_devfn(struct device_node *np) return -EINVAL; } -static inline int -of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin) -{ - return 0; -} - static inline int of_pci_parse_bus_range(struct device_node *node, struct resource *res) { @@ -67,6 +60,16 @@ of_pci_get_max_link_speed(struct device_node *node) static inline void of_pci_check_probe_only(void) { } #endif +#if IS_ENABLED(CONFIG_OF_IRQ) +int of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin); +#else +static inline int +of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin) +{ + return 0; +} +#endif + #if defined(CONFIG_OF_ADDRESS) int of_pci_get_host_bridge_resources(struct device_node *dev, unsigned char busno, unsigned char bus_max, -- cgit v1.2.3 From cb88a0588717ba6c756cb5972d75766b273a6817 Mon Sep 17 00:00:00 2001 From: Danilo Krummrich Date: Tue, 6 Mar 2018 09:38:49 +0100 Subject: usb: quirks: add control message delay for 1b1c:1b20 Corsair Strafe RGB keyboard does not respond to usb control messages sometimes and hence generates timeouts. Commit de3af5bf259d ("usb: quirks: add delay init quirk for Corsair Strafe RGB keyboard") tried to fix those timeouts by adding USB_QUIRK_DELAY_INIT. Unfortunately, even with this quirk timeouts of usb_control_msg() can still be seen, but with a lower frequency (approx. 1 out of 15): [ 29.103520] usb 1-8: string descriptor 0 read error: -110 [ 34.363097] usb 1-8: can't set config #1, error -110 Adding further delays to different locations where usb control messages are issued just moves the timeouts to other locations, e.g.: [ 35.400533] usbhid 1-8:1.0: can't add hid device: -110 [ 35.401014] usbhid: probe of 1-8:1.0 failed with error -110 The only way to reliably avoid those issues is having a pause after each usb control message. In approx. 200 boot cycles no more timeouts were seen. Addionaly, keep USB_QUIRK_DELAY_INIT as it turned out to be necessary to have the delay in hub_port_connect() after hub_port_init(). The overall boot time seems not to be influenced by these additional delays, even on fast machines and lightweight distributions. Fixes: de3af5bf259d ("usb: quirks: add delay init quirk for Corsair Strafe RGB keyboard") Cc: stable@vger.kernel.org Signed-off-by: Danilo Krummrich Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/message.c | 4 ++++ drivers/usb/core/quirks.c | 3 ++- include/linux/usb/quirks.h | 3 +++ 3 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index c64cf6c4a83d..0c11d40a12bc 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -151,6 +151,10 @@ int usb_control_msg(struct usb_device *dev, unsigned int pipe, __u8 request, ret = usb_internal_control_msg(dev, pipe, dr, data, size, timeout); + /* Linger a bit, prior to the next control message. */ + if (dev->quirks & USB_QUIRK_DELAY_CTRL_MSG) + msleep(200); + kfree(dr); return ret; diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index f4a548471f0f..54b019e267c5 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -230,7 +230,8 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x1b1c, 0x1b13), .driver_info = USB_QUIRK_DELAY_INIT }, /* Corsair Strafe RGB */ - { USB_DEVICE(0x1b1c, 0x1b20), .driver_info = USB_QUIRK_DELAY_INIT }, + { USB_DEVICE(0x1b1c, 0x1b20), .driver_info = USB_QUIRK_DELAY_INIT | + USB_QUIRK_DELAY_CTRL_MSG }, /* Corsair K70 LUX */ { USB_DEVICE(0x1b1c, 0x1b36), .driver_info = USB_QUIRK_DELAY_INIT }, diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index f1fcec2fd5f8..b7a99ce56bc9 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -63,4 +63,7 @@ */ #define USB_QUIRK_DISCONNECT_SUSPEND BIT(12) +/* Device needs a pause after every control message. */ +#define USB_QUIRK_DELAY_CTRL_MSG BIT(13) + #endif /* __LINUX_USB_QUIRKS_H */ -- cgit v1.2.3 From 6417250d3f894e66a68ba1cd93676143f2376a6f Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Tue, 6 Mar 2018 19:34:42 -0800 Subject: workqueue: remove unused cancel_work() Found this by accident. There are no usages of bare cancel_work() in current kernel source. Signed-off-by: Stephen Hemminger Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 1 - kernel/workqueue.c | 8 -------- 2 files changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index bc0cda180c8b..0c3301421c57 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -456,7 +456,6 @@ extern int schedule_on_each_cpu(work_func_t func); int execute_in_process_context(work_func_t fn, struct execute_work *); extern bool flush_work(struct work_struct *work); -extern bool cancel_work(struct work_struct *work); extern bool cancel_work_sync(struct work_struct *work); extern bool flush_delayed_work(struct delayed_work *dwork); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index ccd1080dd6e7..6ec6ba65127b 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3018,14 +3018,6 @@ static bool __cancel_work(struct work_struct *work, bool is_dwork) return ret; } -/* - * See cancel_delayed_work() - */ -bool cancel_work(struct work_struct *work) -{ - return __cancel_work(work, false); -} - /** * cancel_delayed_work - cancel a delayed work * @dwork: delayed_work to cancel -- cgit v1.2.3 From 16ca6a607d84bef0129698d8d808f501afd08d43 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 6 Mar 2018 21:48:01 +0000 Subject: KVM: arm/arm64: vgic: Don't populate multiple LRs with the same vintid The vgic code is trying to be clever when injecting GICv2 SGIs, and will happily populate LRs with the same interrupt number if they come from multiple vcpus (after all, they are distinct interrupt sources). Unfortunately, this is against the letter of the architecture, and the GICv2 architecture spec says "Each valid interrupt stored in the List registers must have a unique VirtualID for that virtual CPU interface.". GICv3 has similar (although slightly ambiguous) restrictions. This results in guests locking up when using GICv2-on-GICv3, for example. The obvious fix is to stop trying so hard, and inject a single vcpu per SGI per guest entry. After all, pending SGIs with multiple source vcpus are pretty rare, and are mostly seen in scenario where the physical CPUs are severely overcomitted. But as we now only inject a single instance of a multi-source SGI per vcpu entry, we may delay those interrupts for longer than strictly necessary, and run the risk of injecting lower priority interrupts in the meantime. In order to address this, we adopt a three stage strategy: - If we encounter a multi-source SGI in the AP list while computing its depth, we force the list to be sorted - When populating the LRs, we prevent the injection of any interrupt of lower priority than that of the first multi-source SGI we've injected. - Finally, the injection of a multi-source SGI triggers the request of a maintenance interrupt when there will be no pending interrupt in the LRs (HCR_NPIE). At the point where the last pending interrupt in the LRs switches from Pending to Active, the maintenance interrupt will be delivered, allowing us to add the remaining SGIs using the same process. Cc: stable@vger.kernel.org Fixes: 0919e84c0fc1 ("KVM: arm/arm64: vgic-new: Add IRQ sync/flush framework") Acked-by: Christoffer Dall Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 1 + include/linux/irqchip/arm-gic.h | 1 + virt/kvm/arm/vgic/vgic-v2.c | 9 +++++- virt/kvm/arm/vgic/vgic-v3.c | 9 +++++- virt/kvm/arm/vgic/vgic.c | 61 +++++++++++++++++++++++++++++--------- virt/kvm/arm/vgic/vgic.h | 2 ++ 6 files changed, 67 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index c00c4c33e432..b26eccc78fb1 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -503,6 +503,7 @@ #define ICH_HCR_EN (1 << 0) #define ICH_HCR_UIE (1 << 1) +#define ICH_HCR_NPIE (1 << 3) #define ICH_HCR_TC (1 << 10) #define ICH_HCR_TALL0 (1 << 11) #define ICH_HCR_TALL1 (1 << 12) diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h index d3453ee072fc..68d8b1f73682 100644 --- a/include/linux/irqchip/arm-gic.h +++ b/include/linux/irqchip/arm-gic.h @@ -84,6 +84,7 @@ #define GICH_HCR_EN (1 << 0) #define GICH_HCR_UIE (1 << 1) +#define GICH_HCR_NPIE (1 << 3) #define GICH_LR_VIRTUALID (0x3ff << 0) #define GICH_LR_PHYSID_CPUID_SHIFT (10) diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c index e9d840a75e7b..29556f71b691 100644 --- a/virt/kvm/arm/vgic/vgic-v2.c +++ b/virt/kvm/arm/vgic/vgic-v2.c @@ -37,6 +37,13 @@ void vgic_v2_init_lrs(void) vgic_v2_write_lr(i, 0); } +void vgic_v2_set_npie(struct kvm_vcpu *vcpu) +{ + struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2; + + cpuif->vgic_hcr |= GICH_HCR_NPIE; +} + void vgic_v2_set_underflow(struct kvm_vcpu *vcpu) { struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2; @@ -64,7 +71,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu) int lr; unsigned long flags; - cpuif->vgic_hcr &= ~GICH_HCR_UIE; + cpuif->vgic_hcr &= ~(GICH_HCR_UIE | GICH_HCR_NPIE); for (lr = 0; lr < vgic_cpu->used_lrs; lr++) { u32 val = cpuif->vgic_lr[lr]; diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index 6b329414e57a..0ff2006f3781 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -26,6 +26,13 @@ static bool group1_trap; static bool common_trap; static bool gicv4_enable; +void vgic_v3_set_npie(struct kvm_vcpu *vcpu) +{ + struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3; + + cpuif->vgic_hcr |= ICH_HCR_NPIE; +} + void vgic_v3_set_underflow(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3; @@ -47,7 +54,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) int lr; unsigned long flags; - cpuif->vgic_hcr &= ~ICH_HCR_UIE; + cpuif->vgic_hcr &= ~(ICH_HCR_UIE | ICH_HCR_NPIE); for (lr = 0; lr < vgic_cpu->used_lrs; lr++) { u64 val = cpuif->vgic_lr[lr]; diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c index 0001858a2c23..8201899126f6 100644 --- a/virt/kvm/arm/vgic/vgic.c +++ b/virt/kvm/arm/vgic/vgic.c @@ -710,22 +710,37 @@ static inline void vgic_set_underflow(struct kvm_vcpu *vcpu) vgic_v3_set_underflow(vcpu); } +static inline void vgic_set_npie(struct kvm_vcpu *vcpu) +{ + if (kvm_vgic_global_state.type == VGIC_V2) + vgic_v2_set_npie(vcpu); + else + vgic_v3_set_npie(vcpu); +} + /* Requires the ap_list_lock to be held. */ -static int compute_ap_list_depth(struct kvm_vcpu *vcpu) +static int compute_ap_list_depth(struct kvm_vcpu *vcpu, + bool *multi_sgi) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_irq *irq; int count = 0; + *multi_sgi = false; + DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&vgic_cpu->ap_list_lock)); list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { spin_lock(&irq->irq_lock); /* GICv2 SGIs can count for more than one... */ - if (vgic_irq_is_sgi(irq->intid) && irq->source) - count += hweight8(irq->source); - else + if (vgic_irq_is_sgi(irq->intid) && irq->source) { + int w = hweight8(irq->source); + + count += w; + *multi_sgi |= (w > 1); + } else { count++; + } spin_unlock(&irq->irq_lock); } return count; @@ -736,28 +751,43 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_irq *irq; - int count = 0; + int count; + bool npie = false; + bool multi_sgi; + u8 prio = 0xff; DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&vgic_cpu->ap_list_lock)); - if (compute_ap_list_depth(vcpu) > kvm_vgic_global_state.nr_lr) + count = compute_ap_list_depth(vcpu, &multi_sgi); + if (count > kvm_vgic_global_state.nr_lr || multi_sgi) vgic_sort_ap_list(vcpu); + count = 0; + list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { spin_lock(&irq->irq_lock); - if (unlikely(vgic_target_oracle(irq) != vcpu)) - goto next; - /* - * If we get an SGI with multiple sources, try to get - * them in all at once. + * If we have multi-SGIs in the pipeline, we need to + * guarantee that they are all seen before any IRQ of + * lower priority. In that case, we need to filter out + * these interrupts by exiting early. This is easy as + * the AP list has been sorted already. */ - do { + if (multi_sgi && irq->priority > prio) { + spin_unlock(&irq->irq_lock); + break; + } + + if (likely(vgic_target_oracle(irq) == vcpu)) { vgic_populate_lr(vcpu, irq, count++); - } while (irq->source && count < kvm_vgic_global_state.nr_lr); -next: + if (irq->source) { + npie = true; + prio = irq->priority; + } + } + spin_unlock(&irq->irq_lock); if (count == kvm_vgic_global_state.nr_lr) { @@ -768,6 +798,9 @@ next: } } + if (npie) + vgic_set_npie(vcpu); + vcpu->arch.vgic_cpu.used_lrs = count; /* Nuke remaining LRs */ diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index 5b11859a1a1e..f5b8519e5546 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -160,6 +160,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu); void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr); void vgic_v2_clear_lr(struct kvm_vcpu *vcpu, int lr); void vgic_v2_set_underflow(struct kvm_vcpu *vcpu); +void vgic_v2_set_npie(struct kvm_vcpu *vcpu); int vgic_v2_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr); int vgic_v2_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write, int offset, u32 *val); @@ -189,6 +190,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu); void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr); void vgic_v3_clear_lr(struct kvm_vcpu *vcpu, int lr); void vgic_v3_set_underflow(struct kvm_vcpu *vcpu); +void vgic_v3_set_npie(struct kvm_vcpu *vcpu); void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); void vgic_v3_enable(struct kvm_vcpu *vcpu); -- cgit v1.2.3 From 95dd77580ccd66a0da96e6d4696945b8cea39431 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 14 Mar 2018 18:20:29 -0500 Subject: fs: Teach path_connected to handle nfs filesystems with multiple roots. On nfsv2 and nfsv3 the nfs server can export subsets of the same filesystem and report the same filesystem identifier, so that the nfs client can know they are the same filesystem. The subsets can be from disjoint directory trees. The nfsv2 and nfsv3 filesystems provides no way to find the common root of all directory trees exported form the server with the same filesystem identifier. The practical result is that in struct super s_root for nfs s_root is not necessarily the root of the filesystem. The nfs mount code sets s_root to the root of the first subset of the nfs filesystem that the kernel mounts. This effects the dcache invalidation code in generic_shutdown_super currently called shrunk_dcache_for_umount and that code for years has gone through an additional list of dentries that might be dentry trees that need to be freed to accomodate nfs. When I wrote path_connected I did not realize nfs was so special, and it's hueristic for avoiding calling is_subdir can fail. The practical case where this fails is when there is a move of a directory from the subtree exposed by one nfs mount to the subtree exposed by another nfs mount. This move can happen either locally or remotely. With the remote case requiring that the move directory be cached before the move and that after the move someone walks the path to where the move directory now exists and in so doing causes the already cached directory to be moved in the dcache through the magic of d_splice_alias. If someone whose working directory is in the move directory or a subdirectory and now starts calling .. from the initial mount of nfs (where s_root == mnt_root), then path_connected as a heuristic will not bother with the is_subdir check. As s_root really is not the root of the nfs filesystem this heuristic is wrong, and the path may actually not be connected and path_connected can fail. The is_subdir function might be cheap enough that we can call it unconditionally. Verifying that will take some benchmarking and the result may not be the same on all kernels this fix needs to be backported to. So I am avoiding that for now. Filesystems with snapshots such as nilfs and btrfs do something similar. But as the directory tree of the snapshots are disjoint from one another and from the main directory tree rename won't move things between them and this problem will not occur. Cc: stable@vger.kernel.org Reported-by: Al Viro Fixes: 397d425dc26d ("vfs: Test for and handle paths that are unreachable from their mnt_root") Signed-off-by: "Eric W. Biederman" Signed-off-by: Al Viro --- fs/namei.c | 5 +++-- fs/nfs/super.c | 2 ++ include/linux/fs.h | 1 + 3 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/namei.c b/fs/namei.c index 921ae32dbc80..cafa365eeb70 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -559,9 +559,10 @@ static int __nd_alloc_stack(struct nameidata *nd) static bool path_connected(const struct path *path) { struct vfsmount *mnt = path->mnt; + struct super_block *sb = mnt->mnt_sb; - /* Only bind mounts can have disconnected paths */ - if (mnt->mnt_root == mnt->mnt_sb->s_root) + /* Bind mounts and multi-root filesystems can have disconnected paths */ + if (!(sb->s_iflags & SB_I_MULTIROOT) && (mnt->mnt_root == sb->s_root)) return true; return is_subdir(path->dentry, mnt->mnt_root); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 29bacdc56f6a..5e470e233c83 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2631,6 +2631,8 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server, /* initial superblock/root creation */ mount_info->fill_super(s, mount_info); nfs_get_cache_cookie(s, mount_info->parsed, mount_info->cloned); + if (!(server->flags & NFS_MOUNT_UNSHARED)) + s->s_iflags |= SB_I_MULTIROOT; } mntroot = nfs_get_root(s, mount_info->mntfh, dev_name); diff --git a/include/linux/fs.h b/include/linux/fs.h index 2a815560fda0..0430e03febaa 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1317,6 +1317,7 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ #define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ #define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ +#define SB_I_MULTIROOT 0x00000008 /* Multiple roots to the dentry tree */ /* sb->s_iflags to limit user namespace mounts */ #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ -- cgit v1.2.3 From b3a5d111994450909158929560906f2c1c6c1d85 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 14 Mar 2018 12:45:12 -0700 Subject: percpu_ref: Update doc to dissuade users from depending on internal RCU grace periods percpu_ref internally uses sched-RCU to implement the percpu -> atomic mode switching and the documentation suggested that this could be depended upon. This doesn't seem like a good idea. * percpu_ref uses sched-RCU which has different grace periods regular RCU. Users may combine percpu_ref with regular RCU usage and incorrectly believe that regular RCU grace periods are performed by percpu_ref. This can lead to, for example, use-after-free due to premature freeing. * percpu_ref has a grace period when switching from percpu to atomic mode. It doesn't have one between the last put and release. This distinction is subtle and can lead to surprising bugs. * percpu_ref allows starting in and switching to atomic mode manually for debugging and other purposes. This means that there may not be any grace periods from kill to release. This patch makes it clear that the grace periods are percpu_ref's internal implementation detail and can't be depended upon by the users. Signed-off-by: Tejun Heo Cc: Kent Overstreet Cc: Linus Torvalds Signed-off-by: Tejun Heo --- include/linux/percpu-refcount.h | 18 ++++++++++++------ lib/percpu-refcount.c | 2 ++ 2 files changed, 14 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 864d167a1073..009cdf3d65b6 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -30,10 +30,14 @@ * calls io_destroy() or the process exits. * * In the aio code, kill_ioctx() is called when we wish to destroy a kioctx; it - * calls percpu_ref_kill(), then hlist_del_rcu() and synchronize_rcu() to remove - * the kioctx from the proccess's list of kioctxs - after that, there can't be - * any new users of the kioctx (from lookup_ioctx()) and it's then safe to drop - * the initial ref with percpu_ref_put(). + * removes the kioctx from the proccess's table of kioctxs and kills percpu_ref. + * After that, there can't be any new users of the kioctx (from lookup_ioctx()) + * and it's then safe to drop the initial ref with percpu_ref_put(). + * + * Note that the free path, free_ioctx(), needs to go through explicit call_rcu() + * to synchronize with RCU protected lookup_ioctx(). percpu_ref operations don't + * imply RCU grace periods of any kind and if a user wants to combine percpu_ref + * with RCU protection, it must be done explicitly. * * Code that does a two stage shutdown like this often needs some kind of * explicit synchronization to ensure the initial refcount can only be dropped @@ -113,8 +117,10 @@ void percpu_ref_reinit(struct percpu_ref *ref); * Must be used to drop the initial ref on a percpu refcount; must be called * precisely once before shutdown. * - * Puts @ref in non percpu mode, then does a call_rcu() before gathering up the - * percpu counters and dropping the initial ref. + * Switches @ref into atomic mode before gathering up the percpu counters + * and dropping the initial ref. + * + * There are no implied RCU grace periods between kill and release. */ static inline void percpu_ref_kill(struct percpu_ref *ref) { diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c index 30e7dd88148b..9f96fa7bc000 100644 --- a/lib/percpu-refcount.c +++ b/lib/percpu-refcount.c @@ -322,6 +322,8 @@ EXPORT_SYMBOL_GPL(percpu_ref_switch_to_percpu); * This function normally doesn't block and can be called from any context * but it may block if @confirm_kill is specified and @ref is in the * process of switching to atomic mode by percpu_ref_switch_to_atomic(). + * + * There are no implied RCU grace periods between kill and release. */ void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill) -- cgit v1.2.3