diff options
29 files changed, 360 insertions, 62 deletions
diff --git a/Documentation/watchdog/watchdog-parameters.txt b/Documentation/watchdog/watchdog-parameters.txt index 9f9ec9f76039..4e4b6f10d841 100644 --- a/Documentation/watchdog/watchdog-parameters.txt +++ b/Documentation/watchdog/watchdog-parameters.txt @@ -400,3 +400,7 @@ wm8350_wdt: nowayout: Watchdog cannot be stopped once started (default=kernel config parameter) ------------------------------------------------- +sun4v_wdt: +timeout_ms: Watchdog timeout in milliseconds 1..180000, default=60000) +nowayout: Watchdog cannot be stopped once started +------------------------------------------------- diff --git a/arch/parisc/include/asm/floppy.h b/arch/parisc/include/asm/floppy.h index f84ff12574b7..6d8276cd25ca 100644 --- a/arch/parisc/include/asm/floppy.h +++ b/arch/parisc/include/asm/floppy.h @@ -33,7 +33,7 @@ * floppy accesses go through the track buffer. */ #define _CROSS_64KB(a,s,vdma) \ -(!vdma && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64)) +(!(vdma) && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64)) #define CROSS_64KB(a,s) _CROSS_64KB(a,s,use_virtual_dma & 1) diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h index 35bdccbb2036..b75039f92116 100644 --- a/arch/parisc/include/uapi/asm/unistd.h +++ b/arch/parisc/include/uapi/asm/unistd.h @@ -361,8 +361,9 @@ #define __NR_membarrier (__NR_Linux + 343) #define __NR_userfaultfd (__NR_Linux + 344) #define __NR_mlock2 (__NR_Linux + 345) +#define __NR_copy_file_range (__NR_Linux + 346) -#define __NR_Linux_syscalls (__NR_mlock2 + 1) +#define __NR_Linux_syscalls (__NR_copy_file_range + 1) #define __IGNORE_select /* newselect */ diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index 9585c81f755f..ce0b2b4075c7 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -269,14 +269,19 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, long do_syscall_trace_enter(struct pt_regs *regs) { - long ret = 0; - /* Do the secure computing check first. */ secure_computing_strict(regs->gr[20]); if (test_thread_flag(TIF_SYSCALL_TRACE) && - tracehook_report_syscall_entry(regs)) - ret = -1L; + tracehook_report_syscall_entry(regs)) { + /* + * Tracing decided this syscall should not happen or the + * debugger stored an invalid system call number. Skip + * the system call and the system call restart handling. + */ + regs->gr[20] = -1UL; + goto out; + } #ifdef CONFIG_64BIT if (!is_compat_task()) @@ -290,7 +295,8 @@ long do_syscall_trace_enter(struct pt_regs *regs) regs->gr[24] & 0xffffffff, regs->gr[23] & 0xffffffff); - return ret ? : regs->gr[20]; +out: + return regs->gr[20]; } void do_syscall_trace_exit(struct pt_regs *regs) diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 3fbd7252a4b2..fbafa0d0e2bf 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -343,7 +343,7 @@ tracesys_next: #endif comiclr,>>= __NR_Linux_syscalls, %r20, %r0 - b,n .Lsyscall_nosys + b,n .Ltracesys_nosys LDREGX %r20(%r19), %r19 @@ -359,6 +359,9 @@ tracesys_next: be 0(%sr7,%r19) ldo R%tracesys_exit(%r2),%r2 +.Ltracesys_nosys: + ldo -ENOSYS(%r0),%r28 /* set errno */ + /* Do *not* call this function on the gateway page, because it makes a direct call to syscall_trace. */ diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index d4ffcfbc9885..585d50fc75c0 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -441,6 +441,7 @@ ENTRY_SAME(membarrier) ENTRY_SAME(userfaultfd) ENTRY_SAME(mlock2) /* 345 */ + ENTRY_SAME(copy_file_range) .ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b)) diff --git a/arch/sparc/Makefile b/arch/sparc/Makefile index eaee14637d93..8496a074bd0e 100644 --- a/arch/sparc/Makefile +++ b/arch/sparc/Makefile @@ -24,7 +24,13 @@ LDFLAGS := -m elf32_sparc export BITS := 32 UTS_MACHINE := sparc +# We are adding -Wa,-Av8 to KBUILD_CFLAGS to deal with a specs bug in some +# versions of gcc. Some gcc versions won't pass -Av8 to binutils when you +# give -mcpu=v8. This silently worked with older bintutils versions but +# does not any more. KBUILD_CFLAGS += -m32 -mcpu=v8 -pipe -mno-fpu -fcall-used-g5 -fcall-used-g7 +KBUILD_CFLAGS += -Wa,-Av8 + KBUILD_AFLAGS += -m32 -Wa,-Av8 else diff --git a/arch/sparc/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h index 1c26d440d288..b6de8b10a55b 100644 --- a/arch/sparc/include/uapi/asm/unistd.h +++ b/arch/sparc/include/uapi/asm/unistd.h @@ -422,8 +422,9 @@ #define __NR_listen 354 #define __NR_setsockopt 355 #define __NR_mlock2 356 +#define __NR_copy_file_range 357 -#define NR_syscalls 357 +#define NR_syscalls 358 /* Bitmask values returned from kern_features system call. */ #define KERN_FEATURE_MIXED_MODE_STACK 0x00000001 diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S index 33c02b15f478..a83707c83be8 100644 --- a/arch/sparc/kernel/entry.S +++ b/arch/sparc/kernel/entry.S @@ -948,7 +948,24 @@ linux_syscall_trace: cmp %o0, 0 bne 3f mov -ENOSYS, %o0 + + /* Syscall tracing can modify the registers. */ + ld [%sp + STACKFRAME_SZ + PT_G1], %g1 + sethi %hi(sys_call_table), %l7 + ld [%sp + STACKFRAME_SZ + PT_I0], %i0 + or %l7, %lo(sys_call_table), %l7 + ld [%sp + STACKFRAME_SZ + PT_I1], %i1 + ld [%sp + STACKFRAME_SZ + PT_I2], %i2 + ld [%sp + STACKFRAME_SZ + PT_I3], %i3 + ld [%sp + STACKFRAME_SZ + PT_I4], %i4 + ld [%sp + STACKFRAME_SZ + PT_I5], %i5 + cmp %g1, NR_syscalls + bgeu 3f + mov -ENOSYS, %o0 + + sll %g1, 2, %l4 mov %i0, %o0 + ld [%l7 + %l4], %l7 mov %i1, %o1 mov %i2, %o2 mov %i3, %o3 diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S index afbaba52d2f1..d127130bf424 100644 --- a/arch/sparc/kernel/hvcalls.S +++ b/arch/sparc/kernel/hvcalls.S @@ -338,8 +338,9 @@ ENTRY(sun4v_mach_set_watchdog) mov %o1, %o4 mov HV_FAST_MACH_SET_WATCHDOG, %o5 ta HV_FAST_TRAP + brnz,a,pn %o4, 0f stx %o1, [%o4] - retl +0: retl nop ENDPROC(sun4v_mach_set_watchdog) diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index d88beff47bab..39aaec173f66 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -52,7 +52,7 @@ asmlinkage void sparc64_set_context(struct pt_regs *regs) unsigned char fenab; int err; - flush_user_windows(); + synchronize_user_stack(); if (get_thread_wsaved() || (((unsigned long)ucp) & (sizeof(unsigned long)-1)) || (!__access_ok(ucp, sizeof(*ucp)))) diff --git a/arch/sparc/kernel/sparc_ksyms_64.c b/arch/sparc/kernel/sparc_ksyms_64.c index a92d5d2c46a3..9e034f29dcc5 100644 --- a/arch/sparc/kernel/sparc_ksyms_64.c +++ b/arch/sparc/kernel/sparc_ksyms_64.c @@ -37,6 +37,7 @@ EXPORT_SYMBOL(sun4v_niagara_getperf); EXPORT_SYMBOL(sun4v_niagara_setperf); EXPORT_SYMBOL(sun4v_niagara2_getperf); EXPORT_SYMBOL(sun4v_niagara2_setperf); +EXPORT_SYMBOL(sun4v_mach_set_watchdog); /* from hweight.S */ EXPORT_SYMBOL(__arch_hweight8); diff --git a/arch/sparc/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S index bb0008927598..c4a1b5c40e4e 100644 --- a/arch/sparc/kernel/syscalls.S +++ b/arch/sparc/kernel/syscalls.S @@ -158,7 +158,25 @@ linux_syscall_trace32: add %sp, PTREGS_OFF, %o0 brnz,pn %o0, 3f mov -ENOSYS, %o0 + + /* Syscall tracing can modify the registers. */ + ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1 + sethi %hi(sys_call_table32), %l7 + ldx [%sp + PTREGS_OFF + PT_V9_I0], %i0 + or %l7, %lo(sys_call_table32), %l7 + ldx [%sp + PTREGS_OFF + PT_V9_I1], %i1 + ldx [%sp + PTREGS_OFF + PT_V9_I2], %i2 + ldx [%sp + PTREGS_OFF + PT_V9_I3], %i3 + ldx [%sp + PTREGS_OFF + PT_V9_I4], %i4 + ldx [%sp + PTREGS_OFF + PT_V9_I5], %i5 + + cmp %g1, NR_syscalls + bgeu,pn %xcc, 3f + mov -ENOSYS, %o0 + + sll %g1, 2, %l4 srl %i0, 0, %o0 + lduw [%l7 + %l4], %l7 srl %i4, 0, %o4 srl %i1, 0, %o1 srl %i2, 0, %o2 @@ -170,7 +188,25 @@ linux_syscall_trace: add %sp, PTREGS_OFF, %o0 brnz,pn %o0, 3f mov -ENOSYS, %o0 + + /* Syscall tracing can modify the registers. */ + ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1 + sethi %hi(sys_call_table64), %l7 + ldx [%sp + PTREGS_OFF + PT_V9_I0], %i0 + or %l7, %lo(sys_call_table64), %l7 + ldx [%sp + PTREGS_OFF + PT_V9_I1], %i1 + ldx [%sp + PTREGS_OFF + PT_V9_I2], %i2 + ldx [%sp + PTREGS_OFF + PT_V9_I3], %i3 + ldx [%sp + PTREGS_OFF + PT_V9_I4], %i4 + ldx [%sp + PTREGS_OFF + PT_V9_I5], %i5 + + cmp %g1, NR_syscalls + bgeu,pn %xcc, 3f + mov -ENOSYS, %o0 + + sll %g1, 2, %l4 mov %i0, %o0 + lduw [%l7 + %l4], %l7 mov %i1, %o1 mov %i2, %o2 mov %i3, %o3 diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S index e663b6c78de2..6c3dd6c52f8b 100644 --- a/arch/sparc/kernel/systbls_32.S +++ b/arch/sparc/kernel/systbls_32.S @@ -88,4 +88,4 @@ sys_call_table: /*340*/ .long sys_ni_syscall, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr /*345*/ .long sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .long sys_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen -/*355*/ .long sys_setsockopt, sys_mlock2 +/*355*/ .long sys_setsockopt, sys_mlock2, sys_copy_file_range diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index 1557121f4cdc..12b524cfcfa0 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -89,7 +89,7 @@ sys_call_table32: /*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr .word sys32_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .word sys32_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen - .word compat_sys_setsockopt, sys_mlock2 + .word compat_sys_setsockopt, sys_mlock2, sys_copy_file_range #endif /* CONFIG_COMPAT */ @@ -170,4 +170,4 @@ sys_call_table: /*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr .word sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .word sys64_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen - .word sys_setsockopt, sys_mlock2 + .word sys_setsockopt, sys_mlock2, sys_copy_file_range diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 2760a7ba3f30..8c80a48e3233 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -446,7 +446,8 @@ static long vfio_pci_ioctl(void *device_data, info.num_regions = VFIO_PCI_NUM_REGIONS; info.num_irqs = VFIO_PCI_NUM_IRQS; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_GET_REGION_INFO) { struct pci_dev *pdev = vdev->pdev; @@ -520,7 +521,8 @@ static long vfio_pci_ioctl(void *device_data, return -EINVAL; } - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_GET_IRQ_INFO) { struct vfio_irq_info info; @@ -555,7 +557,8 @@ static long vfio_pci_ioctl(void *device_data, else info.flags |= VFIO_IRQ_INFO_NORESIZE; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_SET_IRQS) { struct vfio_irq_set hdr; diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c index 418cdd9ba3f4..e65b142d3422 100644 --- a/drivers/vfio/platform/vfio_platform_common.c +++ b/drivers/vfio/platform/vfio_platform_common.c @@ -219,7 +219,8 @@ static long vfio_platform_ioctl(void *device_data, info.num_regions = vdev->num_regions; info.num_irqs = vdev->num_irqs; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_GET_REGION_INFO) { struct vfio_region_info info; @@ -240,7 +241,8 @@ static long vfio_platform_ioctl(void *device_data, info.size = vdev->regions[info.index].size; info.flags = vdev->regions[info.index].flags; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_GET_IRQ_INFO) { struct vfio_irq_info info; @@ -259,7 +261,8 @@ static long vfio_platform_ioctl(void *device_data, info.flags = vdev->irqs[info.index].flags; info.count = vdev->irqs[info.index].count; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_SET_IRQS) { struct vfio_irq_set hdr; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 6f1ea3dddbad..75b24e93cedb 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -999,7 +999,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data, info.iova_pgsizes = vfio_pgsize_bitmap(iommu); - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_IOMMU_MAP_DMA) { struct vfio_iommu_type1_dma_map map; @@ -1032,7 +1033,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data, if (ret) return ret; - return copy_to_user((void __user *)arg, &unmap, minsz); + return copy_to_user((void __user *)arg, &unmap, minsz) ? + -EFAULT : 0; } return -ENOTTY; diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c index 92f394927f24..6e92917ba77a 100644 --- a/drivers/video/console/fbcon.c +++ b/drivers/video/console/fbcon.c @@ -709,6 +709,7 @@ static int con2fb_acquire_newinfo(struct vc_data *vc, struct fb_info *info, } if (!err) { + ops->cur_blink_jiffies = HZ / 5; info->fbcon_par = ops; if (vc) @@ -956,6 +957,7 @@ static const char *fbcon_startup(void) ops->currcon = -1; ops->graphics = 1; ops->cur_rotate = -1; + ops->cur_blink_jiffies = HZ / 5; info->fbcon_par = ops; p->con_rotate = initial_rotation; set_blitting_type(vc, info); diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index 0f6d8515ba4f..80825a7e8e48 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -1569,6 +1569,17 @@ config WATCHDOG_RIO machines. The watchdog timeout period is normally one minute but can be changed with a boot-time parameter. +config WATCHDOG_SUN4V + tristate "Sun4v Watchdog support" + select WATCHDOG_CORE + depends on SPARC64 + help + Say Y here to support the hypervisor watchdog capability embedded + in the SPARC sun4v architecture. + + To compile this driver as a module, choose M here. The module will + be called sun4v_wdt. + # XTENSA Architecture # Xen Architecture diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile index f566753256ab..f6a6a387c6c7 100644 --- a/drivers/watchdog/Makefile +++ b/drivers/watchdog/Makefile @@ -179,6 +179,7 @@ obj-$(CONFIG_SH_WDT) += shwdt.o obj-$(CONFIG_WATCHDOG_RIO) += riowd.o obj-$(CONFIG_WATCHDOG_CP1XXX) += cpwd.o +obj-$(CONFIG_WATCHDOG_SUN4V) += sun4v_wdt.o # XTENSA Architecture diff --git a/drivers/watchdog/sun4v_wdt.c b/drivers/watchdog/sun4v_wdt.c new file mode 100644 index 000000000000..1467fe50a76f --- /dev/null +++ b/drivers/watchdog/sun4v_wdt.c @@ -0,0 +1,191 @@ +/* + * sun4v watchdog timer + * (c) Copyright 2016 Oracle Corporation + * + * Implement a simple watchdog driver using the built-in sun4v hypervisor + * watchdog support. If time expires, the hypervisor stops or bounces + * the guest domain. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/errno.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/watchdog.h> +#include <asm/hypervisor.h> +#include <asm/mdesc.h> + +#define WDT_TIMEOUT 60 +#define WDT_MAX_TIMEOUT 31536000 +#define WDT_MIN_TIMEOUT 1 +#define WDT_DEFAULT_RESOLUTION_MS 1000 /* 1 second */ + +static unsigned int timeout; +module_param(timeout, uint, 0); +MODULE_PARM_DESC(timeout, "Watchdog timeout in seconds (default=" + __MODULE_STRING(WDT_TIMEOUT) ")"); + +static bool nowayout = WATCHDOG_NOWAYOUT; +module_param(nowayout, bool, S_IRUGO); +MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" + __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); + +static int sun4v_wdt_stop(struct watchdog_device *wdd) +{ + sun4v_mach_set_watchdog(0, NULL); + + return 0; +} + +static int sun4v_wdt_ping(struct watchdog_device *wdd) +{ + int hverr; + + /* + * HV watchdog timer will round up the timeout + * passed in to the nearest multiple of the + * watchdog resolution in milliseconds. + */ + hverr = sun4v_mach_set_watchdog(wdd->timeout * 1000, NULL); + if (hverr == HV_EINVAL) + return -EINVAL; + + return 0; +} + +static int sun4v_wdt_set_timeout(struct watchdog_device *wdd, + unsigned int timeout) +{ + wdd->timeout = timeout; + + return 0; +} + +static const struct watchdog_info sun4v_wdt_ident = { + .options = WDIOF_SETTIMEOUT | + WDIOF_MAGICCLOSE | + WDIOF_KEEPALIVEPING, + .identity = "sun4v hypervisor watchdog", + .firmware_version = 0, +}; + +static struct watchdog_ops sun4v_wdt_ops = { + .owner = THIS_MODULE, + .start = sun4v_wdt_ping, + .stop = sun4v_wdt_stop, + .ping = sun4v_wdt_ping, + .set_timeout = sun4v_wdt_set_timeout, +}; + +static struct watchdog_device wdd = { + .info = &sun4v_wdt_ident, + .ops = &sun4v_wdt_ops, + .min_timeout = WDT_MIN_TIMEOUT, + .max_timeout = WDT_MAX_TIMEOUT, + .timeout = WDT_TIMEOUT, +}; + +static int __init sun4v_wdt_init(void) +{ + struct mdesc_handle *handle; + u64 node; + const u64 *value; + int err = 0; + unsigned long major = 1, minor = 1; + + /* + * There are 2 properties that can be set from the control + * domain for the watchdog. + * watchdog-resolution + * watchdog-max-timeout + * + * We can expect a handle to be returned otherwise something + * serious is wrong. Correct to return -ENODEV here. + */ + + handle = mdesc_grab(); + if (!handle) + return -ENODEV; + + node = mdesc_node_by_name(handle, MDESC_NODE_NULL, "platform"); + err = -ENODEV; + if (node == MDESC_NODE_NULL) + goto out_release; + + /* + * This is a safe way to validate if we are on the right + * platform. + */ + if (sun4v_hvapi_register(HV_GRP_CORE, major, &minor)) + goto out_hv_unreg; + + /* Allow value of watchdog-resolution up to 1s (default) */ + value = mdesc_get_property(handle, node, "watchdog-resolution", NULL); + err = -EINVAL; + if (value) { + if (*value == 0 || + *value > WDT_DEFAULT_RESOLUTION_MS) + goto out_hv_unreg; + } + + value = mdesc_get_property(handle, node, "watchdog-max-timeout", NULL); + if (value) { + /* + * If the property value (in ms) is smaller than + * min_timeout, return -EINVAL. + */ + if (*value < wdd.min_timeout * 1000) + goto out_hv_unreg; + + /* + * If the property value is smaller than + * default max_timeout then set watchdog max_timeout to + * the value of the property in seconds. + */ + if (*value < wdd.max_timeout * 1000) + wdd.max_timeout = *value / 1000; + } + + watchdog_init_timeout(&wdd, timeout, NULL); + + watchdog_set_nowayout(&wdd, nowayout); + + err = watchdog_register_device(&wdd); + if (err) + goto out_hv_unreg; + + pr_info("initialized (timeout=%ds, nowayout=%d)\n", + wdd.timeout, nowayout); + + mdesc_release(handle); + + return 0; + +out_hv_unreg: + sun4v_hvapi_unregister(HV_GRP_CORE); + +out_release: + mdesc_release(handle); + return err; +} + +static void __exit sun4v_wdt_exit(void) +{ + sun4v_hvapi_unregister(HV_GRP_CORE); + watchdog_unregister_device(&wdd); +} + +module_init(sun4v_wdt_init); +module_exit(sun4v_wdt_exit); + +MODULE_AUTHOR("Wim Coekaerts <wim.coekaerts@oracle.com>"); +MODULE_DESCRIPTION("sun4v watchdog driver"); +MODULE_LICENSE("GPL"); diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index c48ca13673e3..2eea40353e60 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1013,7 +1013,6 @@ const struct file_operations cifs_file_strict_ops = { .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, .clone_file_range = cifs_clone_file_range, - .clone_file_range = cifs_clone_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 68c4547528c4..83aac8ba50b0 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -31,19 +31,15 @@ * so that it will fit. We use hash_64 to convert the value to 31 bits, and * then add 1, to ensure that we don't end up with a 0 as the value. */ -#if BITS_PER_LONG == 64 static inline ino_t cifs_uniqueid_to_ino_t(u64 fileid) { + if ((sizeof(ino_t)) < (sizeof(u64))) + return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1; + return (ino_t)fileid; + } -#else -static inline ino_t -cifs_uniqueid_to_ino_t(u64 fileid) -{ - return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1; -} -#endif extern struct file_system_type cifs_fs_type; extern const struct address_space_operations cifs_addr_ops; diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 90b4f9f7de66..76fcb50295a3 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -1396,11 +1396,10 @@ openRetry: * current bigbuf. */ static int -cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) +discard_remaining_data(struct TCP_Server_Info *server) { unsigned int rfclen = get_rfc1002_length(server->smallbuf); int remaining = rfclen + 4 - server->total_read; - struct cifs_readdata *rdata = mid->callback_data; while (remaining > 0) { int length; @@ -1414,10 +1413,20 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) remaining -= length; } - dequeue_mid(mid, rdata->result); return 0; } +static int +cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) +{ + int length; + struct cifs_readdata *rdata = mid->callback_data; + + length = discard_remaining_data(server); + dequeue_mid(mid, rdata->result); + return length; +} + int cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) { @@ -1446,6 +1455,12 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) return length; server->total_read += length; + if (server->ops->is_status_pending && + server->ops->is_status_pending(buf, server, 0)) { + discard_remaining_data(server); + return -1; + } + /* Was the SMB read successful? */ rdata->result = server->ops->map_error(buf, false); if (rdata->result != 0) { diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 10f8d5cf5681..42e1f440eb1e 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1106,21 +1106,25 @@ parse_lease_state(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp, { char *data_offset; struct create_context *cc; - unsigned int next = 0; + unsigned int next; + unsigned int remaining; char *name; data_offset = (char *)rsp + 4 + le32_to_cpu(rsp->CreateContextsOffset); + remaining = le32_to_cpu(rsp->CreateContextsLength); cc = (struct create_context *)data_offset; - do { - cc = (struct create_context *)((char *)cc + next); + while (remaining >= sizeof(struct create_context)) { name = le16_to_cpu(cc->NameOffset) + (char *)cc; - if (le16_to_cpu(cc->NameLength) != 4 || - strncmp(name, "RqLs", 4)) { - next = le32_to_cpu(cc->Next); - continue; - } - return server->ops->parse_lease_buf(cc, epoch); - } while (next != 0); + if (le16_to_cpu(cc->NameLength) == 4 && + strncmp(name, "RqLs", 4) == 0) + return server->ops->parse_lease_buf(cc, epoch); + + next = le32_to_cpu(cc->Next); + if (!next) + break; + remaining -= next; + cc = (struct create_context *)((char *)cc + next); + } return 0; } diff --git a/fs/dcache.c b/fs/dcache.c index 92d5140de851..2398f9f94337 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -269,9 +269,6 @@ static inline int dname_external(const struct dentry *dentry) return dentry->d_name.name != dentry->d_iname; } -/* - * Make sure other CPUs see the inode attached before the type is set. - */ static inline void __d_set_inode_and_type(struct dentry *dentry, struct inode *inode, unsigned type_flags) @@ -279,28 +276,18 @@ static inline void __d_set_inode_and_type(struct dentry *dentry, unsigned flags; dentry->d_inode = inode; - smp_wmb(); flags = READ_ONCE(dentry->d_flags); flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); flags |= type_flags; WRITE_ONCE(dentry->d_flags, flags); } -/* - * Ideally, we want to make sure that other CPUs see the flags cleared before - * the inode is detached, but this is really a violation of RCU principles - * since the ordering suggests we should always set inode before flags. - * - * We should instead replace or discard the entire dentry - but that sucks - * performancewise on mass deletion/rename. - */ static inline void __d_clear_type_and_inode(struct dentry *dentry) { unsigned flags = READ_ONCE(dentry->d_flags); flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); WRITE_ONCE(dentry->d_flags, flags); - smp_wmb(); dentry->d_inode = NULL; } @@ -370,9 +357,11 @@ static void dentry_unlink_inode(struct dentry * dentry) __releases(dentry->d_inode->i_lock) { struct inode *inode = dentry->d_inode; + + raw_write_seqcount_begin(&dentry->d_seq); __d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_u.d_alias); - dentry_rcuwalk_invalidate(dentry); + raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) @@ -1758,8 +1747,9 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) spin_lock(&dentry->d_lock); if (inode) 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); - dentry_rcuwalk_invalidate(dentry); + raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); fsnotify_d_instantiate(dentry, inode); } diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 50311703135b..66cdb44616d5 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -287,6 +287,12 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address, goto out; /* + * We don't do userfault handling for the final child pid update. + */ + if (current->flags & PF_EXITING) + goto out; + + /* * Check that we can return VM_FAULT_RETRY. * * NOTE: it should become possible to return VM_FAULT_RETRY diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 7781ce110503..c4b5f4b3f8f8 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -409,9 +409,7 @@ static inline bool d_mountpoint(const struct dentry *dentry) */ static inline unsigned __d_entry_type(const struct dentry *dentry) { - unsigned type = READ_ONCE(dentry->d_flags); - smp_rmb(); - return type & DCACHE_ENTRY_TYPE; + return dentry->d_flags & DCACHE_ENTRY_TYPE; } static inline bool d_is_miss(const struct dentry *dentry) |