aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/watchdog/watchdog-parameters.txt4
-rw-r--r--MAINTAINERS8
-rw-r--r--arch/arm/kvm/guest.c2
-rw-r--r--arch/arm64/include/asm/pgtable.h7
-rw-r--r--arch/arm64/kvm/guest.c2
-rw-r--r--arch/arm64/mm/init.c4
-rw-r--r--arch/mips/kvm/mips.c4
-rw-r--r--arch/parisc/include/asm/floppy.h2
-rw-r--r--arch/parisc/include/uapi/asm/unistd.h3
-rw-r--r--arch/parisc/kernel/ptrace.c16
-rw-r--r--arch/parisc/kernel/syscall.S5
-rw-r--r--arch/parisc/kernel/syscall_table.S1
-rw-r--r--arch/sparc/Makefile6
-rw-r--r--arch/sparc/include/uapi/asm/unistd.h3
-rw-r--r--arch/sparc/kernel/entry.S17
-rw-r--r--arch/sparc/kernel/hvcalls.S3
-rw-r--r--arch/sparc/kernel/signal_64.c2
-rw-r--r--arch/sparc/kernel/sparc_ksyms_64.c1
-rw-r--r--arch/sparc/kernel/syscalls.S36
-rw-r--r--arch/sparc/kernel/systbls_32.S2
-rw-r--r--arch/sparc/kernel/systbls_64.S4
-rw-r--r--arch/x86/kvm/vmx.c14
-rw-r--r--arch/x86/kvm/x86.c9
-rw-r--r--drivers/gpio/gpio-rcar.c42
-rw-r--r--drivers/iommu/amd_iommu.c4
-rw-r--r--drivers/iommu/amd_iommu_init.c63
-rw-r--r--drivers/iommu/dmar.c5
-rw-r--r--drivers/iommu/intel-iommu.c4
-rw-r--r--drivers/pci/host/pci-keystone-dw.c11
-rw-r--r--drivers/pci/host/pci-layerscape.c21
-rw-r--r--drivers/vfio/pci/vfio_pci.c9
-rw-r--r--drivers/vfio/platform/vfio_platform_common.c9
-rw-r--r--drivers/vfio/vfio_iommu_type1.c6
-rw-r--r--drivers/vhost/vhost.c15
-rw-r--r--drivers/video/console/fbcon.c2
-rw-r--r--drivers/virtio/virtio_pci_modern.c2
-rw-r--r--drivers/watchdog/Kconfig11
-rw-r--r--drivers/watchdog/Makefile1
-rw-r--r--drivers/watchdog/sun4v_wdt.c191
-rw-r--r--fs/btrfs/root-tree.c10
-rw-r--r--fs/cifs/cifsfs.c1
-rw-r--r--fs/cifs/cifsfs.h12
-rw-r--r--fs/cifs/cifssmb.c21
-rw-r--r--fs/cifs/smb2pdu.c24
-rw-r--r--fs/dcache.c20
-rw-r--r--fs/jffs2/README.Locking5
-rw-r--r--fs/jffs2/build.c75
-rw-r--r--fs/jffs2/file.c39
-rw-r--r--fs/jffs2/gc.c17
-rw-r--r--fs/jffs2/nodelist.h6
-rw-r--r--fs/userfaultfd.c6
-rw-r--r--include/linux/dcache.h4
-rw-r--r--include/linux/trace_events.h2
-rw-r--r--kernel/trace/trace_events.c14
-rw-r--r--kernel/trace/trace_events_filter.c13
55 files changed, 637 insertions, 183 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/MAINTAINERS b/MAINTAINERS
index da3e4d8016d0..f5e6a535bc34 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4518,6 +4518,12 @@ L: [email protected]
S: Maintained
F: drivers/dma/fsldma.*
+FREESCALE GPMI NAND DRIVER
+M: Han Xu <[email protected]>
+S: Maintained
+F: drivers/mtd/nand/gpmi-nand/*
+
FREESCALE I2C CPM DRIVER
M: Jochen Friedrich <[email protected]>
@@ -4534,7 +4540,7 @@ F: include/linux/platform_data/video-imxfb.h
F: drivers/video/fbdev/imxfb.c
FREESCALE QUAD SPI DRIVER
-M: Han Xu <[email protected]>
+M: Han Xu <[email protected]>
S: Maintained
F: drivers/mtd/spi-nor/fsl-quadspi.c
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 5fa69d7bae58..99361f11354a 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -161,7 +161,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
u64 val;
val = kvm_arm_timer_get_reg(vcpu, reg->id);
- return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id));
+ return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0;
}
static unsigned long num_core_regs(void)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index bf464de33f52..f50608674580 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -34,13 +34,13 @@
/*
* VMALLOC and SPARSEMEM_VMEMMAP ranges.
*
- * VMEMAP_SIZE: allows the whole VA space to be covered by a struct page array
+ * VMEMAP_SIZE: allows the whole linear region to be covered by a struct page array
* (rounded up to PUD_SIZE).
* VMALLOC_START: beginning of the kernel VA space
* VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space,
* fixed mappings and modules
*/
-#define VMEMMAP_SIZE ALIGN((1UL << (VA_BITS - PAGE_SHIFT)) * sizeof(struct page), PUD_SIZE)
+#define VMEMMAP_SIZE ALIGN((1UL << (VA_BITS - PAGE_SHIFT - 1)) * sizeof(struct page), PUD_SIZE)
#ifndef CONFIG_KASAN
#define VMALLOC_START (VA_START)
@@ -51,7 +51,8 @@
#define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K)
-#define vmemmap ((struct page *)(VMALLOC_END + SZ_64K))
+#define VMEMMAP_START (VMALLOC_END + SZ_64K)
+#define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT))
#define FIRST_USER_ADDRESS 0UL
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index fcb778899a38..9e54ad7c240a 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -194,7 +194,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
u64 val;
val = kvm_arm_timer_get_reg(vcpu, reg->id);
- return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id));
+ return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0;
}
/**
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index f3b061e67bfe..7802f216a67a 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -319,8 +319,8 @@ void __init mem_init(void)
#endif
MLG(VMALLOC_START, VMALLOC_END),
#ifdef CONFIG_SPARSEMEM_VMEMMAP
- MLG((unsigned long)vmemmap,
- (unsigned long)vmemmap + VMEMMAP_SIZE),
+ MLG(VMEMMAP_START,
+ VMEMMAP_START + VMEMMAP_SIZE),
MLM((unsigned long)virt_to_page(PAGE_OFFSET),
(unsigned long)virt_to_page(high_memory)),
#endif
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 8bc3977576e6..3110447ab1e9 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -702,7 +702,7 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu,
} else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) {
void __user *uaddr = (void __user *)(long)reg->addr;
- return copy_to_user(uaddr, vs, 16);
+ return copy_to_user(uaddr, vs, 16) ? -EFAULT : 0;
} else {
return -EINVAL;
}
@@ -732,7 +732,7 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu,
} else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) {
void __user *uaddr = (void __user *)(long)reg->addr;
- return copy_from_user(vs, uaddr, 16);
+ return copy_from_user(vs, uaddr, 16) ? -EFAULT : 0;
} else {
return -EINVAL;
}
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/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e2951b6edbbc..0ff453749a90 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -596,6 +596,8 @@ struct vcpu_vmx {
/* Support for PML */
#define PML_ENTITY_NUM 512
struct page *pml_pg;
+
+ u64 current_tsc_ratio;
};
enum segment_cache_field {
@@ -2127,14 +2129,16 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
- /* Setup TSC multiplier */
- if (cpu_has_vmx_tsc_scaling())
- vmcs_write64(TSC_MULTIPLIER,
- vcpu->arch.tsc_scaling_ratio);
-
vmx->loaded_vmcs->cpu = cpu;
}
+ /* Setup TSC multiplier */
+ if (kvm_has_tsc_control &&
+ vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) {
+ vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio;
+ vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
+ }
+
vmx_vcpu_pi_load(vcpu, cpu);
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f4891f2ece23..eaf6ee8c28b8 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2752,7 +2752,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
}
kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
- vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD;
}
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -6619,12 +6618,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
* KVM_DEBUGREG_WONT_EXIT again.
*/
if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) {
- int i;
-
WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP);
kvm_x86_ops->sync_dirty_debug_regs(vcpu);
- for (i = 0; i < KVM_NR_DB_REGS; i++)
- vcpu->arch.eff_db[i] = vcpu->arch.db[i];
+ kvm_update_dr0123(vcpu);
+ kvm_update_dr6(vcpu);
+ kvm_update_dr7(vcpu);
+ vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD;
}
/*
diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index cf41440aff91..d9ab0cd1d205 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -196,6 +196,44 @@ static int gpio_rcar_irq_set_wake(struct irq_data *d, unsigned int on)
return 0;
}
+static void gpio_rcar_irq_bus_lock(struct irq_data *d)
+{
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+ struct gpio_rcar_priv *p = gpiochip_get_data(gc);
+
+ pm_runtime_get_sync(&p->pdev->dev);
+}
+
+static void gpio_rcar_irq_bus_sync_unlock(struct irq_data *d)
+{
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+ struct gpio_rcar_priv *p = gpiochip_get_data(gc);
+
+ pm_runtime_put(&p->pdev->dev);
+}
+
+
+static int gpio_rcar_irq_request_resources(struct irq_data *d)
+{
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+ struct gpio_rcar_priv *p = gpiochip_get_data(gc);
+ int error;
+
+ error = pm_runtime_get_sync(&p->pdev->dev);
+ if (error < 0)
+ return error;
+
+ return 0;
+}
+
+static void gpio_rcar_irq_release_resources(struct irq_data *d)
+{
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+ struct gpio_rcar_priv *p = gpiochip_get_data(gc);
+
+ pm_runtime_put(&p->pdev->dev);
+}
+
static irqreturn_t gpio_rcar_irq_handler(int irq, void *dev_id)
{
struct gpio_rcar_priv *p = dev_id;
@@ -450,6 +488,10 @@ static int gpio_rcar_probe(struct platform_device *pdev)
irq_chip->irq_unmask = gpio_rcar_irq_enable;
irq_chip->irq_set_type = gpio_rcar_irq_set_type;
irq_chip->irq_set_wake = gpio_rcar_irq_set_wake;
+ irq_chip->irq_bus_lock = gpio_rcar_irq_bus_lock;
+ irq_chip->irq_bus_sync_unlock = gpio_rcar_irq_bus_sync_unlock;
+ irq_chip->irq_request_resources = gpio_rcar_irq_request_resources;
+ irq_chip->irq_release_resources = gpio_rcar_irq_release_resources;
irq_chip->flags = IRQCHIP_SET_TYPE_MASKED | IRQCHIP_MASK_ON_SUSPEND;
ret = gpiochip_add_data(gpio_chip, p);
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index e5e223938eec..374c129219ef 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -114,6 +114,7 @@ struct kmem_cache *amd_iommu_irq_cache;
static void update_domain(struct protection_domain *domain);
static int protection_domain_init(struct protection_domain *domain);
+static void detach_device(struct device *dev);
/*
* For dynamic growth the aperture size is split into ranges of 128MB of
@@ -384,6 +385,9 @@ static void iommu_uninit_device(struct device *dev)
if (!dev_data)
return;
+ if (dev_data->domain)
+ detach_device(dev);
+
iommu_device_unlink(amd_iommu_rlookup_table[dev_data->devid]->iommu_dev,
dev);
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 013bdfff2d4d..bf4959f4225b 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -228,6 +228,10 @@ static int amd_iommu_enable_interrupts(void);
static int __init iommu_go_to_state(enum iommu_init_state state);
static void init_device_table_dma(void);
+static int iommu_pc_get_set_reg_val(struct amd_iommu *iommu,
+ u8 bank, u8 cntr, u8 fxn,
+ u64 *value, bool is_write);
+
static inline void update_last_devid(u16 devid)
{
if (devid > amd_iommu_last_bdf)
@@ -1016,6 +1020,34 @@ static void amd_iommu_erratum_746_workaround(struct amd_iommu *iommu)
}
/*
+ * Family15h Model 30h-3fh (IOMMU Mishandles ATS Write Permission)
+ * Workaround:
+ * BIOS should enable ATS write permission check by setting
+ * L2_DEBUG_3[AtsIgnoreIWDis](D0F2xF4_x47[0]) = 1b
+ */
+static void amd_iommu_ats_write_check_workaround(struct amd_iommu *iommu)
+{
+ u32 value;
+
+ if ((boot_cpu_data.x86 != 0x15) ||
+ (boot_cpu_data.x86_model < 0x30) ||
+ (boot_cpu_data.x86_model > 0x3f))
+ return;
+
+ /* Test L2_DEBUG_3[AtsIgnoreIWDis] == 1 */
+ value = iommu_read_l2(iommu, 0x47);
+
+ if (value & BIT(0))
+ return;
+
+ /* Set L2_DEBUG_3[AtsIgnoreIWDis] = 1 */
+ iommu_write_l2(iommu, 0x47, value | BIT(0));
+
+ pr_info("AMD-Vi: Applying ATS write check workaround for IOMMU at %s\n",
+ dev_name(&iommu->dev->dev));
+}
+
+/*
* This function clues the initialization function for one IOMMU
* together and also allocates the command buffer and programs the
* hardware. It does NOT enable the IOMMU. This is done afterwards.
@@ -1142,8 +1174,8 @@ static void init_iommu_perf_ctr(struct amd_iommu *iommu)
amd_iommu_pc_present = true;
/* Check if the performance counters can be written to */
- if ((0 != amd_iommu_pc_get_set_reg_val(0, 0, 0, 0, &val, true)) ||
- (0 != amd_iommu_pc_get_set_reg_val(0, 0, 0, 0, &val2, false)) ||
+ if ((0 != iommu_pc_get_set_reg_val(iommu, 0, 0, 0, &val, true)) ||
+ (0 != iommu_pc_get_set_reg_val(iommu, 0, 0, 0, &val2, false)) ||
(val != val2)) {
pr_err("AMD-Vi: Unable to write to IOMMU perf counter.\n");
amd_iommu_pc_present = false;
@@ -1284,6 +1316,7 @@ static int iommu_init_pci(struct amd_iommu *iommu)
}
amd_iommu_erratum_746_workaround(iommu);
+ amd_iommu_ats_write_check_workaround(iommu);
iommu->iommu_dev = iommu_device_create(&iommu->dev->dev, iommu,
amd_iommu_groups, "ivhd%d",
@@ -2283,22 +2316,15 @@ u8 amd_iommu_pc_get_max_counters(u16 devid)
}
EXPORT_SYMBOL(amd_iommu_pc_get_max_counters);
-int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
+static int iommu_pc_get_set_reg_val(struct amd_iommu *iommu,
+ u8 bank, u8 cntr, u8 fxn,
u64 *value, bool is_write)
{
- struct amd_iommu *iommu;
u32 offset;
u32 max_offset_lim;
- /* Make sure the IOMMU PC resource is available */
- if (!amd_iommu_pc_present)
- return -ENODEV;
-
- /* Locate the iommu associated with the device ID */
- iommu = amd_iommu_rlookup_table[devid];
-
/* Check for valid iommu and pc register indexing */
- if (WARN_ON((iommu == NULL) || (fxn > 0x28) || (fxn & 7)))
+ if (WARN_ON((fxn > 0x28) || (fxn & 7)))
return -ENODEV;
offset = (u32)(((0x40|bank) << 12) | (cntr << 8) | fxn);
@@ -2322,3 +2348,16 @@ int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
return 0;
}
EXPORT_SYMBOL(amd_iommu_pc_get_set_reg_val);
+
+int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
+ u64 *value, bool is_write)
+{
+ struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
+
+ /* Make sure the IOMMU PC resource is available */
+ if (!amd_iommu_pc_present || iommu == NULL)
+ return -ENODEV;
+
+ return iommu_pc_get_set_reg_val(iommu, bank, cntr, fxn,
+ value, is_write);
+}
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index fb092f3f11cb..8ffd7568fc91 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -329,7 +329,8 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb,
/* Only care about add/remove events for physical functions */
if (pdev->is_virtfn)
return NOTIFY_DONE;
- if (action != BUS_NOTIFY_ADD_DEVICE && action != BUS_NOTIFY_DEL_DEVICE)
+ if (action != BUS_NOTIFY_ADD_DEVICE &&
+ action != BUS_NOTIFY_REMOVED_DEVICE)
return NOTIFY_DONE;
info = dmar_alloc_pci_notify_info(pdev, action);
@@ -339,7 +340,7 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb,
down_write(&dmar_global_lock);
if (action == BUS_NOTIFY_ADD_DEVICE)
dmar_pci_bus_add_dev(info);
- else if (action == BUS_NOTIFY_DEL_DEVICE)
+ else if (action == BUS_NOTIFY_REMOVED_DEVICE)
dmar_pci_bus_del_dev(info);
up_write(&dmar_global_lock);
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 986a53e3eb96..a2e1b7f14df2 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -4367,7 +4367,7 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
rmrru->devices_cnt);
if(ret < 0)
return ret;
- } else if (info->event == BUS_NOTIFY_DEL_DEVICE) {
+ } else if (info->event == BUS_NOTIFY_REMOVED_DEVICE) {
dmar_remove_dev_scope(info, rmrr->segment,
rmrru->devices, rmrru->devices_cnt);
}
@@ -4387,7 +4387,7 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
break;
else if(ret < 0)
return ret;
- } else if (info->event == BUS_NOTIFY_DEL_DEVICE) {
+ } else if (info->event == BUS_NOTIFY_REMOVED_DEVICE) {
if (dmar_remove_dev_scope(info, atsr->segment,
atsru->devices, atsru->devices_cnt))
break;
diff --git a/drivers/pci/host/pci-keystone-dw.c b/drivers/pci/host/pci-keystone-dw.c
index ed34c9520a02..6153853ca9c3 100644
--- a/drivers/pci/host/pci-keystone-dw.c
+++ b/drivers/pci/host/pci-keystone-dw.c
@@ -58,11 +58,6 @@
#define to_keystone_pcie(x) container_of(x, struct keystone_pcie, pp)
-static inline struct pcie_port *sys_to_pcie(struct pci_sys_data *sys)
-{
- return sys->private_data;
-}
-
static inline void update_reg_offset_bit_pos(u32 offset, u32 *reg_offset,
u32 *bit_pos)
{
@@ -108,7 +103,7 @@ static void ks_dw_pcie_msi_irq_ack(struct irq_data *d)
struct pcie_port *pp;
msi = irq_data_get_msi_desc(d);
- pp = sys_to_pcie(msi_desc_to_pci_sysdata(msi));
+ pp = (struct pcie_port *) msi_desc_to_pci_sysdata(msi);
ks_pcie = to_keystone_pcie(pp);
offset = d->irq - irq_linear_revmap(pp->irq_domain, 0);
update_reg_offset_bit_pos(offset, &reg_offset, &bit_pos);
@@ -146,7 +141,7 @@ static void ks_dw_pcie_msi_irq_mask(struct irq_data *d)
u32 offset;
msi = irq_data_get_msi_desc(d);
- pp = sys_to_pcie(msi_desc_to_pci_sysdata(msi));
+ pp = (struct pcie_port *) msi_desc_to_pci_sysdata(msi);
ks_pcie = to_keystone_pcie(pp);
offset = d->irq - irq_linear_revmap(pp->irq_domain, 0);
@@ -167,7 +162,7 @@ static void ks_dw_pcie_msi_irq_unmask(struct irq_data *d)
u32 offset;
msi = irq_data_get_msi_desc(d);
- pp = sys_to_pcie(msi_desc_to_pci_sysdata(msi));
+ pp = (struct pcie_port *) msi_desc_to_pci_sysdata(msi);
ks_pcie = to_keystone_pcie(pp);
offset = d->irq - irq_linear_revmap(pp->irq_domain, 0);
diff --git a/drivers/pci/host/pci-layerscape.c b/drivers/pci/host/pci-layerscape.c
index 3923bed93c7e..f39961bcf7aa 100644
--- a/drivers/pci/host/pci-layerscape.c
+++ b/drivers/pci/host/pci-layerscape.c
@@ -77,6 +77,16 @@ static void ls_pcie_fix_class(struct ls_pcie *pcie)
iowrite16(PCI_CLASS_BRIDGE_PCI, pcie->dbi + PCI_CLASS_DEVICE);
}
+/* Drop MSG TLP except for Vendor MSG */
+static void ls_pcie_drop_msg_tlp(struct ls_pcie *pcie)
+{
+ u32 val;
+
+ val = ioread32(pcie->dbi + PCIE_STRFMR1);
+ val &= 0xDFFFFFFF;
+ iowrite32(val, pcie->dbi + PCIE_STRFMR1);
+}
+
static int ls1021_pcie_link_up(struct pcie_port *pp)
{
u32 state;
@@ -97,7 +107,7 @@ static int ls1021_pcie_link_up(struct pcie_port *pp)
static void ls1021_pcie_host_init(struct pcie_port *pp)
{
struct ls_pcie *pcie = to_ls_pcie(pp);
- u32 val, index[2];
+ u32 index[2];
pcie->scfg = syscon_regmap_lookup_by_phandle(pp->dev->of_node,
"fsl,pcie-scfg");
@@ -116,13 +126,7 @@ static void ls1021_pcie_host_init(struct pcie_port *pp)
dw_pcie_setup_rc(pp);
- /*
- * LS1021A Workaround for internal TKT228622
- * to fix the INTx hang issue
- */
- val = ioread32(pcie->dbi + PCIE_STRFMR1);
- val &= 0xffff;
- iowrite32(val, pcie->dbi + PCIE_STRFMR1);
+ ls_pcie_drop_msg_tlp(pcie);
}
static int ls_pcie_link_up(struct pcie_port *pp)
@@ -147,6 +151,7 @@ static void ls_pcie_host_init(struct pcie_port *pp)
iowrite32(1, pcie->dbi + PCIE_DBI_RO_WR_EN);
ls_pcie_fix_class(pcie);
ls_pcie_clear_multifunction(pcie);
+ ls_pcie_drop_msg_tlp(pcie);
iowrite32(0, pcie->dbi + PCIE_DBI_RO_WR_EN);
}
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/vhost/vhost.c b/drivers/vhost/vhost.c
index ad2146a9ab2d..236553e81027 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1156,6 +1156,8 @@ int vhost_init_used(struct vhost_virtqueue *vq)
{
__virtio16 last_used_idx;
int r;
+ bool is_le = vq->is_le;
+
if (!vq->private_data) {
vq->is_le = virtio_legacy_is_little_endian();
return 0;
@@ -1165,15 +1167,20 @@ int vhost_init_used(struct vhost_virtqueue *vq)
r = vhost_update_used_flags(vq);
if (r)
- return r;
+ goto err;
vq->signalled_used_valid = false;
- if (!access_ok(VERIFY_READ, &vq->used->idx, sizeof vq->used->idx))
- return -EFAULT;
+ if (!access_ok(VERIFY_READ, &vq->used->idx, sizeof vq->used->idx)) {
+ r = -EFAULT;
+ goto err;
+ }
r = __get_user(last_used_idx, &vq->used->idx);
if (r)
- return r;
+ goto err;
vq->last_used_idx = vhost16_to_cpu(vq, last_used_idx);
return 0;
+err:
+ vq->is_le = is_le;
+ return r;
}
EXPORT_SYMBOL_GPL(vhost_init_used);
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/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index c0c11fad4611..7760fc1a2218 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -679,7 +679,7 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
pci_read_config_dword(pci_dev,
notify + offsetof(struct virtio_pci_notify_cap,
- cap.length),
+ cap.offset),
&notify_offset);
/* We don't know how many VQs we'll map, ahead of the time.
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 <[email protected]>");
+MODULE_DESCRIPTION("sun4v watchdog driver");
+MODULE_LICENSE("GPL");
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 7cf8509deda7..2c849b08a91b 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -310,8 +310,16 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root)
set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state);
err = btrfs_insert_fs_root(root->fs_info, root);
+ /*
+ * The root might have been inserted already, as before we look
+ * for orphan roots, log replay might have happened, which
+ * triggers a transaction commit and qgroup accounting, which
+ * in turn reads and inserts fs roots while doing backref
+ * walking.
+ */
+ if (err == -EEXIST)
+ err = 0;
if (err) {
- BUG_ON(err == -EEXIST);
btrfs_free_fs_root(root);
break;
}
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/jffs2/README.Locking b/fs/jffs2/README.Locking
index 3ea36554107f..8918ac905a3b 100644
--- a/fs/jffs2/README.Locking
+++ b/fs/jffs2/README.Locking
@@ -2,10 +2,6 @@
JFFS2 LOCKING DOCUMENTATION
---------------------------
-At least theoretically, JFFS2 does not require the Big Kernel Lock
-(BKL), which was always helpfully obtained for it by Linux 2.4 VFS
-code. It has its own locking, as described below.
-
This document attempts to describe the existing locking rules for
JFFS2. It is not expected to remain perfectly up to date, but ought to
be fairly close.
@@ -69,6 +65,7 @@ Ordering constraints:
any f->sem held.
2. Never attempt to lock two file mutexes in one thread.
No ordering rules have been made for doing so.
+ 3. Never lock a page cache page with f->sem held.
erase_completion_lock spinlock
diff --git a/fs/jffs2/build.c b/fs/jffs2/build.c
index 0ae91ad6df2d..b288c8ae1236 100644
--- a/fs/jffs2/build.c
+++ b/fs/jffs2/build.c
@@ -50,7 +50,8 @@ next_inode(int *i, struct jffs2_inode_cache *ic, struct jffs2_sb_info *c)
static void jffs2_build_inode_pass1(struct jffs2_sb_info *c,
- struct jffs2_inode_cache *ic)
+ struct jffs2_inode_cache *ic,
+ int *dir_hardlinks)
{
struct jffs2_full_dirent *fd;
@@ -69,19 +70,21 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c,
dbg_fsbuild("child \"%s\" (ino #%u) of dir ino #%u doesn't exist!\n",
fd->name, fd->ino, ic->ino);
jffs2_mark_node_obsolete(c, fd->raw);
+ /* Clear the ic/raw union so it doesn't cause problems later. */
+ fd->ic = NULL;
continue;
}
+ /* From this point, fd->raw is no longer used so we can set fd->ic */
+ fd->ic = child_ic;
+ child_ic->pino_nlink++;
+ /* If we appear (at this stage) to have hard-linked directories,
+ * set a flag to trigger a scan later */
if (fd->type == DT_DIR) {
- if (child_ic->pino_nlink) {
- JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u appears to be a hard link\n",
- fd->name, fd->ino, ic->ino);
- /* TODO: What do we do about it? */
- } else {
- child_ic->pino_nlink = ic->ino;
- }
- } else
- child_ic->pino_nlink++;
+ child_ic->flags |= INO_FLAGS_IS_DIR;
+ if (child_ic->pino_nlink > 1)
+ *dir_hardlinks = 1;
+ }
dbg_fsbuild("increased nlink for child \"%s\" (ino #%u)\n", fd->name, fd->ino);
/* Can't free scan_dents so far. We might need them in pass 2 */
@@ -95,8 +98,7 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c,
*/
static int jffs2_build_filesystem(struct jffs2_sb_info *c)
{
- int ret;
- int i;
+ int ret, i, dir_hardlinks = 0;
struct jffs2_inode_cache *ic;
struct jffs2_full_dirent *fd;
struct jffs2_full_dirent *dead_fds = NULL;
@@ -120,7 +122,7 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c)
/* Now scan the directory tree, increasing nlink according to every dirent found. */
for_each_inode(i, c, ic) {
if (ic->scan_dents) {
- jffs2_build_inode_pass1(c, ic);
+ jffs2_build_inode_pass1(c, ic, &dir_hardlinks);
cond_resched();
}
}
@@ -156,6 +158,20 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c)
}
dbg_fsbuild("pass 2a complete\n");
+
+ if (dir_hardlinks) {
+ /* If we detected directory hardlinks earlier, *hopefully*
+ * they are gone now because some of the links were from
+ * dead directories which still had some old dirents lying
+ * around and not yet garbage-collected, but which have
+ * been discarded above. So clear the pino_nlink field
+ * in each directory, so that the final scan below can
+ * print appropriate warnings. */
+ for_each_inode(i, c, ic) {
+ if (ic->flags & INO_FLAGS_IS_DIR)
+ ic->pino_nlink = 0;
+ }
+ }
dbg_fsbuild("freeing temporary data structures\n");
/* Finally, we can scan again and free the dirent structs */
@@ -163,6 +179,33 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c)
while(ic->scan_dents) {
fd = ic->scan_dents;
ic->scan_dents = fd->next;
+ /* We do use the pino_nlink field to count nlink of
+ * directories during fs build, so set it to the
+ * parent ino# now. Now that there's hopefully only
+ * one. */
+ if (fd->type == DT_DIR) {
+ if (!fd->ic) {
+ /* We'll have complained about it and marked the coresponding
+ raw node obsolete already. Just skip it. */
+ continue;
+ }
+
+ /* We *have* to have set this in jffs2_build_inode_pass1() */
+ BUG_ON(!(fd->ic->flags & INO_FLAGS_IS_DIR));
+
+ /* We clear ic->pino_nlink ∀ directories' ic *only* if dir_hardlinks
+ * is set. Otherwise, we know this should never trigger anyway, so
+ * we don't do the check. And ic->pino_nlink still contains the nlink
+ * value (which is 1). */
+ if (dir_hardlinks && fd->ic->pino_nlink) {
+ JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u is also hard linked from dir ino #%u\n",
+ fd->name, fd->ino, ic->ino, fd->ic->pino_nlink);
+ /* Should we unlink it from its previous parent? */
+ }
+
+ /* For directories, ic->pino_nlink holds that parent inode # */
+ fd->ic->pino_nlink = ic->ino;
+ }
jffs2_free_full_dirent(fd);
}
ic->scan_dents = NULL;
@@ -241,11 +284,7 @@ static void jffs2_build_remove_unlinked_inode(struct jffs2_sb_info *c,
/* Reduce nlink of the child. If it's now zero, stick it on the
dead_fds list to be cleaned up later. Else just free the fd */
-
- if (fd->type == DT_DIR)
- child_ic->pino_nlink = 0;
- else
- child_ic->pino_nlink--;
+ child_ic->pino_nlink--;
if (!child_ic->pino_nlink) {
dbg_fsbuild("inode #%u (\"%s\") now has no links; adding to dead_fds list.\n",
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index c5ac5944bc1b..cad86bac3453 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -137,39 +137,33 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
struct page *pg;
struct inode *inode = mapping->host;
struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode);
- struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
- struct jffs2_raw_inode ri;
- uint32_t alloc_len = 0;
pgoff_t index = pos >> PAGE_CACHE_SHIFT;
uint32_t pageofs = index << PAGE_CACHE_SHIFT;
int ret = 0;
- jffs2_dbg(1, "%s()\n", __func__);
-
- if (pageofs > inode->i_size) {
- ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len,
- ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE);
- if (ret)
- return ret;
- }
-
- mutex_lock(&f->sem);
pg = grab_cache_page_write_begin(mapping, index, flags);
- if (!pg) {
- if (alloc_len)
- jffs2_complete_reservation(c);
- mutex_unlock(&f->sem);
+ if (!pg)
return -ENOMEM;
- }
*pagep = pg;
- if (alloc_len) {
+ jffs2_dbg(1, "%s()\n", __func__);
+
+ if (pageofs > inode->i_size) {
/* Make new hole frag from old EOF to new page */
+ struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
+ struct jffs2_raw_inode ri;
struct jffs2_full_dnode *fn;
+ uint32_t alloc_len;
jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new page\n",
(unsigned int)inode->i_size, pageofs);
+ ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len,
+ ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE);
+ if (ret)
+ goto out_page;
+
+ mutex_lock(&f->sem);
memset(&ri, 0, sizeof(ri));
ri.magic = cpu_to_je16(JFFS2_MAGIC_BITMASK);
@@ -196,6 +190,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
if (IS_ERR(fn)) {
ret = PTR_ERR(fn);
jffs2_complete_reservation(c);
+ mutex_unlock(&f->sem);
goto out_page;
}
ret = jffs2_add_full_dnode_to_inode(c, f, fn);
@@ -210,10 +205,12 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
jffs2_mark_node_obsolete(c, fn->raw);
jffs2_free_full_dnode(fn);
jffs2_complete_reservation(c);
+ mutex_unlock(&f->sem);
goto out_page;
}
jffs2_complete_reservation(c);
inode->i_size = pageofs;
+ mutex_unlock(&f->sem);
}
/*
@@ -222,18 +219,18 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
* case of a short-copy.
*/
if (!PageUptodate(pg)) {
+ mutex_lock(&f->sem);
ret = jffs2_do_readpage_nolock(inode, pg);
+ mutex_unlock(&f->sem);
if (ret)
goto out_page;
}
- mutex_unlock(&f->sem);
jffs2_dbg(1, "end write_begin(). pg->flags %lx\n", pg->flags);
return ret;
out_page:
unlock_page(pg);
page_cache_release(pg);
- mutex_unlock(&f->sem);
return ret;
}
diff --git a/fs/jffs2/gc.c b/fs/jffs2/gc.c
index 5a2dec2b064c..95d5880a63ee 100644
--- a/fs/jffs2/gc.c
+++ b/fs/jffs2/gc.c
@@ -1296,14 +1296,17 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era
BUG_ON(start > orig_start);
}
- /* First, use readpage() to read the appropriate page into the page cache */
- /* Q: What happens if we actually try to GC the _same_ page for which commit_write()
- * triggered garbage collection in the first place?
- * A: I _think_ it's OK. read_cache_page shouldn't deadlock, we'll write out the
- * page OK. We'll actually write it out again in commit_write, which is a little
- * suboptimal, but at least we're correct.
- */
+ /* The rules state that we must obtain the page lock *before* f->sem, so
+ * drop f->sem temporarily. Since we also hold c->alloc_sem, nothing's
+ * actually going to *change* so we're safe; we only allow reading.
+ *
+ * It is important to note that jffs2_write_begin() will ensure that its
+ * page is marked Uptodate before allocating space. That means that if we
+ * end up here trying to GC the *same* page that jffs2_write_begin() is
+ * trying to write out, read_cache_page() will not deadlock. */
+ mutex_unlock(&f->sem);
pg_ptr = jffs2_gc_fetch_page(c, f, start, &pg);
+ mutex_lock(&f->sem);
if (IS_ERR(pg_ptr)) {
pr_warn("read_cache_page() returned error: %ld\n",
diff --git a/fs/jffs2/nodelist.h b/fs/jffs2/nodelist.h
index fa35ff79ab35..0637271f3770 100644
--- a/fs/jffs2/nodelist.h
+++ b/fs/jffs2/nodelist.h
@@ -194,6 +194,7 @@ struct jffs2_inode_cache {
#define INO_STATE_CLEARING 6 /* In clear_inode() */
#define INO_FLAGS_XATTR_CHECKED 0x01 /* has no duplicate xattr_ref */
+#define INO_FLAGS_IS_DIR 0x02 /* is a directory */
#define RAWNODE_CLASS_INODE_CACHE 0
#define RAWNODE_CLASS_XATTR_DATUM 1
@@ -249,7 +250,10 @@ struct jffs2_readinode_info
struct jffs2_full_dirent
{
- struct jffs2_raw_node_ref *raw;
+ union {
+ struct jffs2_raw_node_ref *raw;
+ struct jffs2_inode_cache *ic; /* Just during part of build */
+ };
struct jffs2_full_dirent *next;
uint32_t version;
uint32_t ino; /* == zero for unlink */
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)
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 429fdfc3baf5..925730bc9fc1 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -568,6 +568,8 @@ enum {
FILTER_DYN_STRING,
FILTER_PTR_STRING,
FILTER_TRACE_FN,
+ FILTER_COMM,
+ FILTER_CPU,
};
extern int trace_event_raw_init(struct trace_event_call *call);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index ab09829d3b97..05ddc0820771 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -97,16 +97,16 @@ trace_find_event_field(struct trace_event_call *call, char *name)
struct ftrace_event_field *field;
struct list_head *head;
- field = __find_event_field(&ftrace_generic_fields, name);
+ head = trace_get_fields(call);
+ field = __find_event_field(head, name);
if (field)
return field;
- field = __find_event_field(&ftrace_common_fields, name);
+ field = __find_event_field(&ftrace_generic_fields, name);
if (field)
return field;
- head = trace_get_fields(call);
- return __find_event_field(head, name);
+ return __find_event_field(&ftrace_common_fields, name);
}
static int __trace_define_field(struct list_head *head, const char *type,
@@ -171,8 +171,10 @@ static int trace_define_generic_fields(void)
{
int ret;
- __generic_field(int, cpu, FILTER_OTHER);
- __generic_field(char *, comm, FILTER_PTR_STRING);
+ __generic_field(int, CPU, FILTER_CPU);
+ __generic_field(int, cpu, FILTER_CPU);
+ __generic_field(char *, COMM, FILTER_COMM);
+ __generic_field(char *, comm, FILTER_COMM);
return ret;
}
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index f93a219b18da..6816302542b2 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1043,13 +1043,14 @@ static int init_pred(struct filter_parse_state *ps,
return -EINVAL;
}
- if (is_string_field(field)) {
+ if (field->filter_type == FILTER_COMM) {
+ filter_build_regex(pred);
+ fn = filter_pred_comm;
+ pred->regex.field_len = TASK_COMM_LEN;
+ } else if (is_string_field(field)) {
filter_build_regex(pred);
- if (!strcmp(field->name, "comm")) {
- fn = filter_pred_comm;
- pred->regex.field_len = TASK_COMM_LEN;
- } else if (field->filter_type == FILTER_STATIC_STRING) {
+ if (field->filter_type == FILTER_STATIC_STRING) {
fn = filter_pred_string;
pred->regex.field_len = field->size;
} else if (field->filter_type == FILTER_DYN_STRING)
@@ -1072,7 +1073,7 @@ static int init_pred(struct filter_parse_state *ps,
}
pred->val = val;
- if (!strcmp(field->name, "cpu"))
+ if (field->filter_type == FILTER_CPU)
fn = filter_pred_cpu;
else
fn = select_comparison_fn(pred->op, field->size,