summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-08-10 19:07:44 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2020-08-10 19:07:44 -0700
commit97d052ea3fa853b9aabcc4baca1a605cb1188611 (patch)
tree48901cbccafdc5870c7dad9cce98e9338065f8a3
parent086ba2ec163b638abd2a90ef3e8bab0238d02e56 (diff)
parent0cd39f4600ed4de859383018eb10f0f724900e1b (diff)
downloadlwn-97d052ea3fa853b9aabcc4baca1a605cb1188611.tar.gz
lwn-97d052ea3fa853b9aabcc4baca1a605cb1188611.zip
Merge tag 'locking-urgent-2020-08-10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull locking updates from Thomas Gleixner: "A set of locking fixes and updates: - Untangle the header spaghetti which causes build failures in various situations caused by the lockdep additions to seqcount to validate that the write side critical sections are non-preemptible. - The seqcount associated lock debug addons which were blocked by the above fallout. seqcount writers contrary to seqlock writers must be externally serialized, which usually happens via locking - except for strict per CPU seqcounts. As the lock is not part of the seqcount, lockdep cannot validate that the lock is held. This new debug mechanism adds the concept of associated locks. sequence count has now lock type variants and corresponding initializers which take a pointer to the associated lock used for writer serialization. If lockdep is enabled the pointer is stored and write_seqcount_begin() has a lockdep assertion to validate that the lock is held. Aside of the type and the initializer no other code changes are required at the seqcount usage sites. The rest of the seqcount API is unchanged and determines the type at compile time with the help of _Generic which is possible now that the minimal GCC version has been moved up. Adding this lockdep coverage unearthed a handful of seqcount bugs which have been addressed already independent of this. While generally useful this comes with a Trojan Horse twist: On RT kernels the write side critical section can become preemtible if the writers are serialized by an associated lock, which leads to the well known reader preempts writer livelock. RT prevents this by storing the associated lock pointer independent of lockdep in the seqcount and changing the reader side to block on the lock when a reader detects that a writer is in the write side critical section. - Conversion of seqcount usage sites to associated types and initializers" * tag 'locking-urgent-2020-08-10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (25 commits) locking/seqlock, headers: Untangle the spaghetti monster locking, arch/ia64: Reduce <asm/smp.h> header dependencies by moving XTP bits into the new <asm/xtp.h> header x86/headers: Remove APIC headers from <asm/smp.h> seqcount: More consistent seqprop names seqcount: Compress SEQCNT_LOCKNAME_ZERO() seqlock: Fold seqcount_LOCKNAME_init() definition seqlock: Fold seqcount_LOCKNAME_t definition seqlock: s/__SEQ_LOCKDEP/__SEQ_LOCK/g hrtimer: Use sequence counter with associated raw spinlock kvm/eventfd: Use sequence counter with associated spinlock userfaultfd: Use sequence counter with associated spinlock NFSv4: Use sequence counter with associated spinlock iocost: Use sequence counter with associated spinlock raid5: Use sequence counter with associated spinlock vfs: Use sequence counter with associated spinlock timekeeping: Use sequence counter with associated raw spinlock xfrm: policy: Use sequence counters with associated lock netfilter: nft_set_rbtree: Use sequence counter with associated rwlock netfilter: conntrack: Use sequence counter with associated spinlock sched: tasks: Use sequence counter with associated spinlock ...
-rw-r--r--Documentation/locking/seqlock.rst52
-rw-r--r--arch/ia64/include/asm/smp.h35
-rw-r--r--arch/ia64/include/asm/xtp.h46
-rw-r--r--arch/ia64/kernel/iosapic.c1
-rw-r--r--arch/ia64/kernel/irq.c1
-rw-r--r--arch/ia64/kernel/process.c1
-rw-r--r--arch/ia64/kernel/sal.c1
-rw-r--r--arch/ia64/kernel/setup.c1
-rw-r--r--arch/ia64/kernel/smp.c1
-rw-r--r--arch/parisc/include/asm/timex.h1
-rw-r--r--arch/sh/include/asm/io.h1
-rw-r--r--arch/sh/kernel/machvec.c1
-rw-r--r--arch/sparc/include/asm/timer_64.h1
-rw-r--r--arch/sparc/include/asm/vvar.h3
-rw-r--r--arch/sparc/kernel/vdso.c1
-rw-r--r--arch/x86/include/asm/fixmap.h2
-rw-r--r--arch/x86/include/asm/smp.h10
-rw-r--r--arch/x86/include/asm/tsc.h1
-rw-r--r--arch/x86/kernel/apic/apic.c1
-rw-r--r--arch/x86/kernel/apic/apic_noop.c1
-rw-r--r--arch/x86/kernel/apic/bigsmp_32.c1
-rw-r--r--arch/x86/kernel/apic/hw_nmi.c1
-rw-r--r--arch/x86/kernel/apic/ipi.c1
-rw-r--r--arch/x86/kernel/apic/local.h1
-rw-r--r--arch/x86/kernel/apic/probe_32.c1
-rw-r--r--arch/x86/kernel/apic/probe_64.c1
-rw-r--r--arch/x86/kernel/cpu/amd.c1
-rw-r--r--arch/x86/kernel/cpu/common.c1
-rw-r--r--arch/x86/kernel/cpu/hygon.c1
-rw-r--r--arch/x86/kernel/cpu/intel.c1
-rw-r--r--arch/x86/kernel/devicetree.c1
-rw-r--r--arch/x86/kernel/irqinit.c2
-rw-r--r--arch/x86/kernel/jailhouse.c2
-rw-r--r--arch/x86/kernel/mpparse.c2
-rw-r--r--arch/x86/kernel/setup.c1
-rw-r--r--arch/x86/kernel/topology.c1
-rw-r--r--arch/x86/kernel/tsc_msr.c1
-rw-r--r--arch/x86/mm/init_32.c1
-rw-r--r--arch/x86/xen/apic.c2
-rw-r--r--arch/x86/xen/enlighten_hvm.c1
-rw-r--r--arch/x86/xen/smp_hvm.c1
-rw-r--r--arch/x86/xen/smp_pv.c1
-rw-r--r--arch/x86/xen/suspend_pv.c4
-rw-r--r--block/blk-iocost.c5
-rw-r--r--drivers/dma-buf/dma-resv.c15
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c2
-rw-r--r--drivers/iommu/intel/irq_remapping.c1
-rw-r--r--drivers/md/raid5.c2
-rw-r--r--drivers/md/raid5.h2
-rw-r--r--fs/dcache.c2
-rw-r--r--fs/fs_struct.c4
-rw-r--r--fs/nfs/nfs4_fs.h2
-rw-r--r--fs/nfs/nfs4state.c2
-rw-r--r--fs/userfaultfd.c4
-rw-r--r--include/linux/dcache.h2
-rw-r--r--include/linux/dma-resv.h4
-rw-r--r--include/linux/dynamic_queue_limits.h2
-rw-r--r--include/linux/fs_struct.h2
-rw-r--r--include/linux/hrtimer.h3
-rw-r--r--include/linux/ktime.h1
-rw-r--r--include/linux/kvm_irqfd.h2
-rw-r--r--include/linux/lockdep.h1
-rw-r--r--include/linux/mutex.h11
-rw-r--r--include/linux/sched.h3
-rw-r--r--include/linux/seqlock.h368
-rw-r--r--include/linux/time.h1
-rw-r--r--include/linux/videodev2.h1
-rw-r--r--include/linux/ww_mutex.h8
-rw-r--r--include/net/netfilter/nf_conntrack.h2
-rw-r--r--init/init_task.c3
-rw-r--r--kernel/fork.c2
-rw-r--r--kernel/locking/lockdep_proc.c2
-rw-r--r--kernel/time/hrtimer.c13
-rw-r--r--kernel/time/timekeeping.c19
-rw-r--r--net/netfilter/nf_conntrack_core.c5
-rw-r--r--net/netfilter/nft_set_rbtree.c4
-rw-r--r--net/xfrm/xfrm_policy.c10
-rw-r--r--virt/kvm/eventfd.c2
78 files changed, 501 insertions, 203 deletions
diff --git a/Documentation/locking/seqlock.rst b/Documentation/locking/seqlock.rst
index 366dd368d90a..62c5ad98c11c 100644
--- a/Documentation/locking/seqlock.rst
+++ b/Documentation/locking/seqlock.rst
@@ -87,6 +87,58 @@ Read path::
} while (read_seqcount_retry(&foo_seqcount, seq));
+.. _seqcount_locktype_t:
+
+Sequence counters with associated locks (``seqcount_LOCKTYPE_t``)
+-----------------------------------------------------------------
+
+As discussed at :ref:`seqcount_t`, sequence count write side critical
+sections must be serialized and non-preemptible. This variant of
+sequence counters associate the lock used for writer serialization at
+initialization time, which enables lockdep to validate that the write
+side critical sections are properly serialized.
+
+This lock association is a NOOP if lockdep is disabled and has neither
+storage nor runtime overhead. If lockdep is enabled, the lock pointer is
+stored in struct seqcount and lockdep's "lock is held" assertions are
+injected at the beginning of the write side critical section to validate
+that it is properly protected.
+
+For lock types which do not implicitly disable preemption, preemption
+protection is enforced in the write side function.
+
+The following sequence counters with associated locks are defined:
+
+ - ``seqcount_spinlock_t``
+ - ``seqcount_raw_spinlock_t``
+ - ``seqcount_rwlock_t``
+ - ``seqcount_mutex_t``
+ - ``seqcount_ww_mutex_t``
+
+The plain seqcount read and write APIs branch out to the specific
+seqcount_LOCKTYPE_t implementation at compile-time. This avoids kernel
+API explosion per each new seqcount LOCKTYPE.
+
+Initialization (replace "LOCKTYPE" with one of the supported locks)::
+
+ /* dynamic */
+ seqcount_LOCKTYPE_t foo_seqcount;
+ seqcount_LOCKTYPE_init(&foo_seqcount, &lock);
+
+ /* static */
+ static seqcount_LOCKTYPE_t foo_seqcount =
+ SEQCNT_LOCKTYPE_ZERO(foo_seqcount, &lock);
+
+ /* C99 struct init */
+ struct {
+ .seq = SEQCNT_LOCKTYPE_ZERO(foo.seq, &lock),
+ } foo;
+
+Write path: same as in :ref:`seqcount_t`, while running from a context
+with the associated LOCKTYPE lock acquired.
+
+Read path: same as in :ref:`seqcount_t`.
+
.. _seqlock_t:
Sequential locks (``seqlock_t``)
diff --git a/arch/ia64/include/asm/smp.h b/arch/ia64/include/asm/smp.h
index 7847ae40a181..aa92234c0142 100644
--- a/arch/ia64/include/asm/smp.h
+++ b/arch/ia64/include/asm/smp.h
@@ -18,7 +18,6 @@
#include <linux/bitops.h>
#include <linux/irqreturn.h>
-#include <asm/io.h>
#include <asm/param.h>
#include <asm/processor.h>
#include <asm/ptrace.h>
@@ -44,11 +43,6 @@ ia64_get_lid (void)
#ifdef CONFIG_SMP
-#define XTP_OFFSET 0x1e0008
-
-#define SMP_IRQ_REDIRECTION (1 << 0)
-#define SMP_IPI_REDIRECTION (1 << 1)
-
#define raw_smp_processor_id() (current_thread_info()->cpu)
extern struct smp_boot_data {
@@ -62,7 +56,6 @@ extern cpumask_t cpu_core_map[NR_CPUS];
DECLARE_PER_CPU_SHARED_ALIGNED(cpumask_t, cpu_sibling_map);
extern int smp_num_siblings;
extern void __iomem *ipi_base_addr;
-extern unsigned char smp_int_redirect;
extern volatile int ia64_cpu_to_sapicid[];
#define cpu_physical_id(i) ia64_cpu_to_sapicid[i]
@@ -84,34 +77,6 @@ cpu_logical_id (int cpuid)
return i;
}
-/*
- * XTP control functions:
- * min_xtp : route all interrupts to this CPU
- * normal_xtp: nominal XTP value
- * max_xtp : never deliver interrupts to this CPU.
- */
-
-static inline void
-min_xtp (void)
-{
- if (smp_int_redirect & SMP_IRQ_REDIRECTION)
- writeb(0x00, ipi_base_addr + XTP_OFFSET); /* XTP to min */
-}
-
-static inline void
-normal_xtp (void)
-{
- if (smp_int_redirect & SMP_IRQ_REDIRECTION)
- writeb(0x08, ipi_base_addr + XTP_OFFSET); /* XTP normal */
-}
-
-static inline void
-max_xtp (void)
-{
- if (smp_int_redirect & SMP_IRQ_REDIRECTION)
- writeb(0x0f, ipi_base_addr + XTP_OFFSET); /* Set XTP to max */
-}
-
/* Upping and downing of CPUs */
extern int __cpu_disable (void);
extern void __cpu_die (unsigned int cpu);
diff --git a/arch/ia64/include/asm/xtp.h b/arch/ia64/include/asm/xtp.h
new file mode 100644
index 000000000000..5bf1d70ad860
--- /dev/null
+++ b/arch/ia64/include/asm/xtp.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_IA64_XTP_H
+#define _ASM_IA64_XTP_H
+
+#include <asm/io.h>
+
+#ifdef CONFIG_SMP
+
+#define XTP_OFFSET 0x1e0008
+
+#define SMP_IRQ_REDIRECTION (1 << 0)
+#define SMP_IPI_REDIRECTION (1 << 1)
+
+extern unsigned char smp_int_redirect;
+
+/*
+ * XTP control functions:
+ * min_xtp : route all interrupts to this CPU
+ * normal_xtp: nominal XTP value
+ * max_xtp : never deliver interrupts to this CPU.
+ */
+
+static inline void
+min_xtp (void)
+{
+ if (smp_int_redirect & SMP_IRQ_REDIRECTION)
+ writeb(0x00, ipi_base_addr + XTP_OFFSET); /* XTP to min */
+}
+
+static inline void
+normal_xtp (void)
+{
+ if (smp_int_redirect & SMP_IRQ_REDIRECTION)
+ writeb(0x08, ipi_base_addr + XTP_OFFSET); /* XTP normal */
+}
+
+static inline void
+max_xtp (void)
+{
+ if (smp_int_redirect & SMP_IRQ_REDIRECTION)
+ writeb(0x0f, ipi_base_addr + XTP_OFFSET); /* Set XTP to max */
+}
+
+#endif /* CONFIG_SMP */
+
+#endif /* _ASM_IA64_XTP_Hy */
diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c
index fad4db20ce65..35adcf89035a 100644
--- a/arch/ia64/kernel/iosapic.c
+++ b/arch/ia64/kernel/iosapic.c
@@ -95,6 +95,7 @@
#include <asm/iosapic.h>
#include <asm/processor.h>
#include <asm/ptrace.h>
+#include <asm/xtp.h>
#undef DEBUG_INTERRUPT_ROUTING
diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c
index 0a8e5e585edc..ecef17c7c35b 100644
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -25,6 +25,7 @@
#include <linux/kernel_stat.h>
#include <asm/mca.h>
+#include <asm/xtp.h>
/*
* 'what should we do if we get a hw irq event on an illegal vector'.
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index 36eba4ba6543..f19cb97c0098 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -47,6 +47,7 @@
#include <linux/uaccess.h>
#include <asm/unwind.h>
#include <asm/user.h>
+#include <asm/xtp.h>
#include "entry.h"
diff --git a/arch/ia64/kernel/sal.c b/arch/ia64/kernel/sal.c
index c455ece977ad..e4f0705c0282 100644
--- a/arch/ia64/kernel/sal.c
+++ b/arch/ia64/kernel/sal.c
@@ -18,6 +18,7 @@
#include <asm/page.h>
#include <asm/sal.h>
#include <asm/pal.h>
+#include <asm/xtp.h>
__cacheline_aligned DEFINE_SPINLOCK(sal_lock);
unsigned long sal_platform_features;
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index d2d440fe855b..dd595fbd8006 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -65,6 +65,7 @@
#include <asm/tlbflush.h>
#include <asm/unistd.h>
#include <asm/uv/uv.h>
+#include <asm/xtp.h>
#if defined(CONFIG_SMP) && (IA64_CPU_SIZE > PAGE_SIZE)
# error "struct cpuinfo_ia64 too big!"
diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c
index 0e2742003121..7b7b64eb3129 100644
--- a/arch/ia64/kernel/smp.c
+++ b/arch/ia64/kernel/smp.c
@@ -45,6 +45,7 @@
#include <asm/tlbflush.h>
#include <asm/unistd.h>
#include <asm/mca.h>
+#include <asm/xtp.h>
/*
* Note: alignment of 4 entries/cacheline was empirically determined
diff --git a/arch/parisc/include/asm/timex.h b/arch/parisc/include/asm/timex.h
index 45537cd4d1d3..06b510f8172e 100644
--- a/arch/parisc/include/asm/timex.h
+++ b/arch/parisc/include/asm/timex.h
@@ -7,6 +7,7 @@
#ifndef _ASMPARISC_TIMEX_H
#define _ASMPARISC_TIMEX_H
+#include <asm/special_insns.h>
#define CLOCK_TICK_RATE 1193180 /* Underlying HZ */
diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h
index 26f0f9b4658b..ec587b583822 100644
--- a/arch/sh/include/asm/io.h
+++ b/arch/sh/include/asm/io.h
@@ -17,6 +17,7 @@
#include <asm/cache.h>
#include <asm/addrspace.h>
#include <asm/machvec.h>
+#include <asm/page.h>
#include <linux/pgtable.h>
#include <asm-generic/iomap.h>
diff --git a/arch/sh/kernel/machvec.c b/arch/sh/kernel/machvec.c
index beadbbdb4486..76bd8955d4fe 100644
--- a/arch/sh/kernel/machvec.c
+++ b/arch/sh/kernel/machvec.c
@@ -15,6 +15,7 @@
#include <asm/setup.h>
#include <asm/io.h>
#include <asm/irq.h>
+#include <asm/processor.h>
#define MV_NAME_SIZE 32
diff --git a/arch/sparc/include/asm/timer_64.h b/arch/sparc/include/asm/timer_64.h
index c7e4fb601a57..dcfad4613e18 100644
--- a/arch/sparc/include/asm/timer_64.h
+++ b/arch/sparc/include/asm/timer_64.h
@@ -7,6 +7,7 @@
#ifndef _SPARC64_TIMER_H
#define _SPARC64_TIMER_H
+#include <uapi/asm/asi.h>
#include <linux/types.h>
#include <linux/init.h>
diff --git a/arch/sparc/include/asm/vvar.h b/arch/sparc/include/asm/vvar.h
index 0289503d1cb0..6eaf5cfcaae1 100644
--- a/arch/sparc/include/asm/vvar.h
+++ b/arch/sparc/include/asm/vvar.h
@@ -6,7 +6,8 @@
#define _ASM_SPARC_VVAR_DATA_H
#include <asm/clocksource.h>
-#include <linux/seqlock.h>
+#include <asm/processor.h>
+#include <asm/barrier.h>
#include <linux/time.h>
#include <linux/types.h>
diff --git a/arch/sparc/kernel/vdso.c b/arch/sparc/kernel/vdso.c
index 58880662b271..0e27437eb97b 100644
--- a/arch/sparc/kernel/vdso.c
+++ b/arch/sparc/kernel/vdso.c
@@ -7,7 +7,6 @@
* a different vsyscall implementation for Linux/IA32 and for the name.
*/
-#include <linux/seqlock.h>
#include <linux/time.h>
#include <linux/timekeeper_internal.h>
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index b9527a54db99..0f0dd645b594 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -26,9 +26,9 @@
#ifndef __ASSEMBLY__
#include <linux/kernel.h>
-#include <asm/acpi.h>
#include <asm/apicdef.h>
#include <asm/page.h>
+#include <asm/pgtable_types.h>
#ifdef CONFIG_X86_32
#include <linux/threads.h>
#include <asm/kmap_types.h>
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index e15f364efbcc..c0538f82c9a2 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -5,16 +5,6 @@
#include <linux/cpumask.h>
#include <asm/percpu.h>
-/*
- * We need the APIC definitions automatically as part of 'smp.h'
- */
-#ifdef CONFIG_X86_LOCAL_APIC
-# include <asm/mpspec.h>
-# include <asm/apic.h>
-# ifdef CONFIG_X86_IO_APIC
-# include <asm/io_apic.h>
-# endif
-#endif
#include <asm/thread_info.h>
#include <asm/cpumask.h>
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index b7b2624fba86..01a300a9700b 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -6,6 +6,7 @@
#define _ASM_X86_TSC_H
#include <asm/processor.h>
+#include <asm/cpufeature.h>
/*
* Standard way to access the cycle counter.
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index ccf726cc87b7..5f943b938167 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -46,6 +46,7 @@
#include <asm/proto.h>
#include <asm/traps.h>
#include <asm/apic.h>
+#include <asm/acpi.h>
#include <asm/io_apic.h>
#include <asm/desc.h>
#include <asm/hpet.h>
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index 98c9bb75d185..780c702969b7 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -10,6 +10,7 @@
* like self-ipi, etc...
*/
#include <linux/cpumask.h>
+#include <linux/thread_info.h>
#include <asm/apic.h>
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index 38b5b51d42f6..98d015a4405a 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -9,6 +9,7 @@
#include <linux/smp.h>
#include <asm/apic.h>
+#include <asm/io_apic.h>
#include "local.h"
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index d1fc62a67320..34a992e275ef 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -9,6 +9,7 @@
* Bits copied from original nmi.c file
*
*/
+#include <linux/thread_info.h>
#include <asm/apic.h>
#include <asm/nmi.h>
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index 6ca0f91372fd..387154e39e08 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -2,6 +2,7 @@
#include <linux/cpumask.h>
#include <linux/smp.h>
+#include <asm/io_apic.h>
#include "local.h"
diff --git a/arch/x86/kernel/apic/local.h b/arch/x86/kernel/apic/local.h
index 04797f05ce94..a997d849509a 100644
--- a/arch/x86/kernel/apic/local.h
+++ b/arch/x86/kernel/apic/local.h
@@ -10,6 +10,7 @@
#include <linux/jump_label.h>
+#include <asm/irq_vectors.h>
#include <asm/apic.h>
/* APIC flat 64 */
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 67b33d67002f..7bda71def557 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -10,6 +10,7 @@
#include <linux/errno.h>
#include <linux/smp.h>
+#include <asm/io_apic.h>
#include <asm/apic.h>
#include <asm/acpi.h>
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index 29f0e0984557..bd3835d6b535 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -8,6 +8,7 @@
* Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and
* James Cleverdon.
*/
+#include <linux/thread_info.h>
#include <asm/apic.h>
#include "local.h"
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index d4806eac9325..dcc3d943c68f 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -15,6 +15,7 @@
#include <asm/cpu.h>
#include <asm/spec-ctrl.h>
#include <asm/smp.h>
+#include <asm/numa.h>
#include <asm/pci-direct.h>
#include <asm/delay.h>
#include <asm/debugreg.h>
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 965474d78cef..c5d6f17d9b9d 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -45,6 +45,7 @@
#include <asm/mtrr.h>
#include <asm/hwcap2.h>
#include <linux/numa.h>
+#include <asm/numa.h>
#include <asm/asm.h>
#include <asm/bugs.h>
#include <asm/cpu.h>
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index 4e28c1fc8749..ac6c30e5801d 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -10,6 +10,7 @@
#include <asm/cpu.h>
#include <asm/smp.h>
+#include <asm/numa.h>
#include <asm/cacheinfo.h>
#include <asm/spec-ctrl.h>
#include <asm/delay.h>
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index b6b7b38dff5f..59a1e3ce3f14 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -23,6 +23,7 @@
#include <asm/cmdline.h>
#include <asm/traps.h>
#include <asm/resctrl.h>
+#include <asm/numa.h>
#ifdef CONFIG_X86_64
#include <linux/topology.h>
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 8d85e00bb40a..a0e8fc7d85f1 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -20,6 +20,7 @@
#include <asm/irqdomain.h>
#include <asm/hpet.h>
#include <asm/apic.h>
+#include <asm/io_apic.h>
#include <asm/pci_x86.h>
#include <asm/setup.h>
#include <asm/i8259.h>
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index dd73135d7cee..beb1bada1b0a 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -22,6 +22,8 @@
#include <asm/timer.h>
#include <asm/hw_irq.h>
#include <asm/desc.h>
+#include <asm/io_apic.h>
+#include <asm/acpi.h>
#include <asm/apic.h>
#include <asm/setup.h>
#include <asm/i8259.h>
diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c
index 6eb8b50ea07e..4eb8f2d19a87 100644
--- a/arch/x86/kernel/jailhouse.c
+++ b/arch/x86/kernel/jailhouse.c
@@ -13,6 +13,8 @@
#include <linux/reboot.h>
#include <linux/serial_8250.h>
#include <asm/apic.h>
+#include <asm/io_apic.h>
+#include <asm/acpi.h>
#include <asm/cpu.h>
#include <asm/hypervisor.h>
#include <asm/i8259.h>
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index c27b82b62c8b..411af4aa7b51 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -19,6 +19,8 @@
#include <linux/smp.h>
#include <linux/pci.h>
+#include <asm/io_apic.h>
+#include <asm/acpi.h>
#include <asm/irqdomain.h>
#include <asm/mtrr.h>
#include <asm/mpspec.h>
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index b9a68d8e06d8..3511736fbc74 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -25,6 +25,7 @@
#include <xen/xen.h>
#include <asm/apic.h>
+#include <asm/numa.h>
#include <asm/bios_ebda.h>
#include <asm/bugs.h>
#include <asm/cpu.h>
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index b8810ebbc8ae..0a2ec801b63f 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -31,6 +31,7 @@
#include <linux/init.h>
#include <linux/smp.h>
#include <linux/irq.h>
+#include <asm/io_apic.h>
#include <asm/cpu.h>
static DEFINE_PER_CPU(struct x86_cpu, cpu_devices);
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 4fec6f3a1858..46c72f2ec32f 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -7,6 +7,7 @@
*/
#include <linux/kernel.h>
+#include <linux/thread_info.h>
#include <asm/apic.h>
#include <asm/cpu_device_id.h>
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 4cb958419fb0..7c055259de3a 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -52,6 +52,7 @@
#include <asm/cpu_entry_area.h>
#include <asm/init.h>
#include <asm/pgtable_areas.h>
+#include <asm/numa.h>
#include "mm_internal.h"
diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index 5e53bfbe5823..1aff4ae65655 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -1,8 +1,10 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/init.h>
+#include <linux/thread_info.h>
#include <asm/x86_init.h>
#include <asm/apic.h>
+#include <asm/io_apic.h>
#include <asm/xen/hypercall.h>
#include <xen/xen.h>
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index 3e89b0067ff0..9e87ab010c82 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -11,6 +11,7 @@
#include <asm/cpu.h>
#include <asm/smp.h>
+#include <asm/io_apic.h>
#include <asm/reboot.h>
#include <asm/setup.h>
#include <asm/idtentry.h>
diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c
index f8d39440b292..f5e7db4f82ab 100644
--- a/arch/x86/xen/smp_hvm.c
+++ b/arch/x86/xen/smp_hvm.c
@@ -1,4 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
+#include <linux/thread_info.h>
#include <asm/smp.h>
#include <xen/events.h>
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 9ea598dcc132..47c8f4b444c9 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -29,6 +29,7 @@
#include <asm/idtentry.h>
#include <asm/desc.h>
#include <asm/cpu.h>
+#include <asm/io_apic.h>
#include <xen/interface/xen.h>
#include <xen/interface/vcpu.h>
diff --git a/arch/x86/xen/suspend_pv.c b/arch/x86/xen/suspend_pv.c
index 8303b58c79a9..cae9660f4c67 100644
--- a/arch/x86/xen/suspend_pv.c
+++ b/arch/x86/xen/suspend_pv.c
@@ -1,11 +1,11 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/types.h>
-#include <asm/fixmap.h>
-
#include <asm/xen/hypercall.h>
#include <asm/xen/page.h>
+#include <asm/fixmap.h>
+
#include "xen-ops.h"
void xen_pv_pre_suspend(void)
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 521c29b8ae29..413e0b5c8e6b 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -406,7 +406,7 @@ struct ioc {
enum ioc_running running;
atomic64_t vtime_rate;
- seqcount_t period_seqcount;
+ seqcount_spinlock_t period_seqcount;
u32 period_at; /* wallclock starttime */
u64 period_at_vtime; /* vtime starttime */
@@ -873,7 +873,6 @@ static void ioc_now(struct ioc *ioc, struct ioc_now *now)
static void ioc_start_period(struct ioc *ioc, struct ioc_now *now)
{
- lockdep_assert_held(&ioc->lock);
WARN_ON_ONCE(ioc->running != IOC_RUNNING);
write_seqcount_begin(&ioc->period_seqcount);
@@ -2001,7 +2000,7 @@ static int blk_iocost_init(struct request_queue *q)
ioc->running = IOC_IDLE;
atomic64_set(&ioc->vtime_rate, VTIME_PER_USEC);
- seqcount_init(&ioc->period_seqcount);
+ seqcount_spinlock_init(&ioc->period_seqcount, &ioc->lock);
ioc->period_at = ktime_to_us(ktime_get());
atomic64_set(&ioc->cur_period, 0);
atomic_set(&ioc->hweight_gen, 0);
diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index 07f5273207e7..434a3314fb0e 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -52,12 +52,6 @@
DEFINE_WD_CLASS(reservation_ww_class);
EXPORT_SYMBOL(reservation_ww_class);
-struct lock_class_key reservation_seqcount_class;
-EXPORT_SYMBOL(reservation_seqcount_class);
-
-const char reservation_seqcount_string[] = "reservation_seqcount";
-EXPORT_SYMBOL(reservation_seqcount_string);
-
/**
* dma_resv_list_alloc - allocate fence list
* @shared_max: number of fences we need space for
@@ -143,9 +137,8 @@ subsys_initcall(dma_resv_lockdep);
void dma_resv_init(struct dma_resv *obj)
{
ww_mutex_init(&obj->lock, &reservation_ww_class);
+ seqcount_ww_mutex_init(&obj->seq, &obj->lock);
- __seqcount_init(&obj->seq, reservation_seqcount_string,
- &reservation_seqcount_class);
RCU_INIT_POINTER(obj->fence, NULL);
RCU_INIT_POINTER(obj->fence_excl, NULL);
}
@@ -275,7 +268,6 @@ void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence)
fobj = dma_resv_get_list(obj);
count = fobj->shared_count;
- preempt_disable();
write_seqcount_begin(&obj->seq);
for (i = 0; i < count; ++i) {
@@ -297,7 +289,6 @@ replace:
smp_store_mb(fobj->shared_count, count);
write_seqcount_end(&obj->seq);
- preempt_enable();
dma_fence_put(old);
}
EXPORT_SYMBOL(dma_resv_add_shared_fence);
@@ -324,14 +315,12 @@ void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence)
if (fence)
dma_fence_get(fence);
- preempt_disable();
write_seqcount_begin(&obj->seq);
/* write_seqcount_begin provides the necessary memory barrier */
RCU_INIT_POINTER(obj->fence_excl, fence);
if (old)
old->shared_count = 0;
write_seqcount_end(&obj->seq);
- preempt_enable();
/* inplace update, no shared fences */
while (i--)
@@ -409,13 +398,11 @@ retry:
src_list = dma_resv_get_list(dst);
old = dma_resv_get_excl(dst);
- preempt_disable();
write_seqcount_begin(&dst->seq);
/* write_seqcount_begin provides the necessary memory barrier */
RCU_INIT_POINTER(dst->fence_excl, new);
RCU_INIT_POINTER(dst->fence, dst_list);
write_seqcount_end(&dst->seq);
- preempt_enable();
dma_resv_list_free(src_list);
dma_fence_put(old);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index e5a5ba869eb4..a58af513c952 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -258,11 +258,9 @@ static int amdgpu_amdkfd_remove_eviction_fence(struct amdgpu_bo *bo,
new->shared_count = k;
/* Install the new fence list, seqcount provides the barriers */
- preempt_disable();
write_seqcount_begin(&resv->seq);
RCU_INIT_POINTER(resv->fence, new);
write_seqcount_end(&resv->seq);
- preempt_enable();
/* Drop the references to the removed fences or move them to ef_list */
for (i = j, k = 0; i < old->shared_count; ++i) {
diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
index aa096b333a99..23583b0e66a5 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -15,6 +15,7 @@
#include <linux/irqdomain.h>
#include <linux/crash_dump.h>
#include <asm/io_apic.h>
+#include <asm/apic.h>
#include <asm/smp.h>
#include <asm/cpu.h>
#include <asm/irq_remapping.h>
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index fb8d1fb14088..ef0fd4830803 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7019,7 +7019,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
} else
goto abort;
spin_lock_init(&conf->device_lock);
- seqcount_init(&conf->gen_lock);
+ seqcount_spinlock_init(&conf->gen_lock, &conf->device_lock);
mutex_init(&conf->cache_size_mutex);
init_waitqueue_head(&conf->wait_for_quiescent);
init_waitqueue_head(&conf->wait_for_stripe);
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 7fb3b26a181a..16fc29472f5c 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -582,7 +582,7 @@ struct r5conf {
int prev_chunk_sectors;
int prev_algo;
short generation; /* increments with every reshape */
- seqcount_t gen_lock; /* lock against generation changes */
+ seqcount_spinlock_t gen_lock; /* lock against generation changes */
unsigned long reshape_checkpoint; /* Time we last updated
* metadata */
long long min_offset_diff; /* minimum difference between
diff --git a/fs/dcache.c b/fs/dcache.c
index 361ea7ab30ea..ea0485861d93 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1746,7 +1746,7 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
dentry->d_lockref.count = 1;
dentry->d_flags = 0;
spin_lock_init(&dentry->d_lock);
- seqcount_init(&dentry->d_seq);
+ seqcount_spinlock_init(&dentry->d_seq, &dentry->d_lock);
dentry->d_inode = NULL;
dentry->d_parent = dentry;
dentry->d_sb = sb;
diff --git a/fs/fs_struct.c b/fs/fs_struct.c
index ca639ed967b7..04b3f5b9c629 100644
--- a/fs/fs_struct.c
+++ b/fs/fs_struct.c
@@ -117,7 +117,7 @@ struct fs_struct *copy_fs_struct(struct fs_struct *old)
fs->users = 1;
fs->in_exec = 0;
spin_lock_init(&fs->lock);
- seqcount_init(&fs->seq);
+ seqcount_spinlock_init(&fs->seq, &fs->lock);
fs->umask = old->umask;
spin_lock(&old->lock);
@@ -163,6 +163,6 @@ EXPORT_SYMBOL(current_umask);
struct fs_struct init_fs = {
.users = 1,
.lock = __SPIN_LOCK_UNLOCKED(init_fs.lock),
- .seq = SEQCNT_ZERO(init_fs.seq),
+ .seq = SEQCNT_SPINLOCK_ZERO(init_fs.seq, &init_fs.lock),
.umask = 0022,
};
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 2b7f6dcd2eb8..210e590e1f71 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -117,7 +117,7 @@ struct nfs4_state_owner {
unsigned long so_flags;
struct list_head so_states;
struct nfs_seqid_counter so_seqid;
- seqcount_t so_reclaim_seqcount;
+ seqcount_spinlock_t so_reclaim_seqcount;
struct mutex so_delegreturn_mutex;
};
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index a8dc25ce48bb..b1dba24918f8 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -509,7 +509,7 @@ nfs4_alloc_state_owner(struct nfs_server *server,
nfs4_init_seqid_counter(&sp->so_seqid);
atomic_set(&sp->so_count, 1);
INIT_LIST_HEAD(&sp->so_lru);
- seqcount_init(&sp->so_reclaim_seqcount);
+ seqcount_spinlock_init(&sp->so_reclaim_seqcount, &sp->so_lock);
mutex_init(&sp->so_delegreturn_mutex);
return sp;
}
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 6e264dded46e..0e4a3837da52 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -61,7 +61,7 @@ struct userfaultfd_ctx {
/* waitqueue head for events */
wait_queue_head_t event_wqh;
/* a refile sequence protected by fault_pending_wqh lock */
- struct seqcount refile_seq;
+ seqcount_spinlock_t refile_seq;
/* pseudo fd refcounting */
refcount_t refcount;
/* userfaultfd syscall flags */
@@ -1961,7 +1961,7 @@ static void init_once_userfaultfd_ctx(void *mem)
init_waitqueue_head(&ctx->fault_wqh);
init_waitqueue_head(&ctx->event_wqh);
init_waitqueue_head(&ctx->fd_wqh);
- seqcount_init(&ctx->refile_seq);
+ seqcount_spinlock_init(&ctx->refile_seq, &ctx->fault_pending_wqh.lock);
}
SYSCALL_DEFINE1(userfaultfd, int, flags)
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index a81f0c3cf352..65d975bf9390 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -89,7 +89,7 @@ extern struct dentry_stat_t dentry_stat;
struct dentry {
/* RCU lookup touched fields */
unsigned int d_flags; /* protected by d_lock */
- seqcount_t d_seq; /* per dentry seqlock */
+ seqcount_spinlock_t d_seq; /* per dentry seqlock */
struct hlist_bl_node d_hash; /* lookup hash list */
struct dentry *d_parent; /* parent directory */
struct qstr d_name;
diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h
index ee50d10f052b..d44a77e8a7e3 100644
--- a/include/linux/dma-resv.h
+++ b/include/linux/dma-resv.h
@@ -46,8 +46,6 @@
#include <linux/rcupdate.h>
extern struct ww_class reservation_ww_class;
-extern struct lock_class_key reservation_seqcount_class;
-extern const char reservation_seqcount_string[];
/**
* struct dma_resv_list - a list of shared fences
@@ -71,7 +69,7 @@ struct dma_resv_list {
*/
struct dma_resv {
struct ww_mutex lock;
- seqcount_t seq;
+ seqcount_ww_mutex_t seq;
struct dma_fence __rcu *fence_excl;
struct dma_resv_list __rcu *fence;
diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h
index 99fc06f0afc1..407c2f281b64 100644
--- a/include/linux/dynamic_queue_limits.h
+++ b/include/linux/dynamic_queue_limits.h
@@ -38,6 +38,8 @@
#ifdef __KERNEL__
+#include <asm/bug.h>
+
struct dql {
/* Fields accessed in enqueue path (dql_queued) */
unsigned int num_queued; /* Total ever queued */
diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h
index cf1015abfbf2..783b48dedb72 100644
--- a/include/linux/fs_struct.h
+++ b/include/linux/fs_struct.h
@@ -9,7 +9,7 @@
struct fs_struct {
int users;
spinlock_t lock;
- seqcount_t seq;
+ seqcount_spinlock_t seq;
int umask;
int in_exec;
struct path root, pwd;
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 15c8ac313678..107cedd7019a 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -17,6 +17,7 @@
#include <linux/init.h>
#include <linux/list.h>
#include <linux/percpu.h>
+#include <linux/seqlock.h>
#include <linux/timer.h>
#include <linux/timerqueue.h>
@@ -159,7 +160,7 @@ struct hrtimer_clock_base {
struct hrtimer_cpu_base *cpu_base;
unsigned int index;
clockid_t clockid;
- seqcount_t seq;
+ seqcount_raw_spinlock_t seq;
struct hrtimer *running;
struct timerqueue_head active;
ktime_t (*get_time)(void);
diff --git a/include/linux/ktime.h b/include/linux/ktime.h
index 42d2e6ac35f2..a12b5523cc18 100644
--- a/include/linux/ktime.h
+++ b/include/linux/ktime.h
@@ -23,6 +23,7 @@
#include <linux/time.h>
#include <linux/jiffies.h>
+#include <asm/bug.h>
/* Nanosecond scalar representation for kernel time values */
typedef s64 ktime_t;
diff --git a/include/linux/kvm_irqfd.h b/include/linux/kvm_irqfd.h
index dc1da020305b..dac047abdba7 100644
--- a/include/linux/kvm_irqfd.h
+++ b/include/linux/kvm_irqfd.h
@@ -42,7 +42,7 @@ struct kvm_kernel_irqfd {
wait_queue_entry_t wait;
/* Update side is protected by irqfds.lock */
struct kvm_kernel_irq_routing_entry irq_entry;
- seqcount_t irq_entry_sc;
+ seqcount_spinlock_t irq_entry_sc;
/* Used for level IRQ fast-path */
int gsi;
struct work_struct inject;
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 39a35699d0d6..62a382d1845b 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -11,6 +11,7 @@
#define __LINUX_LOCKDEP_H
#include <linux/lockdep_types.h>
+#include <linux/smp.h>
#include <asm/percpu.h>
struct task_struct;
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index ae197cc00cc8..dcd185cbfe79 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -65,6 +65,17 @@ struct mutex {
#endif
};
+struct ww_class;
+struct ww_acquire_ctx;
+
+struct ww_mutex {
+ struct mutex base;
+ struct ww_acquire_ctx *ctx;
+#ifdef CONFIG_DEBUG_MUTEXES
+ struct ww_class *ww_class;
+#endif
+};
+
/*
* This is the control structure for tasks blocked on mutex,
* which resides on the blocked task's kernel stack:
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 52bcc9f48e17..53ddc02e2e79 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -32,6 +32,7 @@
#include <linux/task_io_accounting.h>
#include <linux/posix-timers.h>
#include <linux/rseq.h>
+#include <linux/seqlock.h>
#include <linux/kcsan.h>
/* task_struct member predeclarations (sorted alphabetically): */
@@ -1049,7 +1050,7 @@ struct task_struct {
/* Protected by ->alloc_lock: */
nodemask_t mems_allowed;
/* Seqence number to catch updates: */
- seqcount_t mems_allowed_seq;
+ seqcount_spinlock_t mems_allowed_seq;
int cpuset_mem_spread_rotor;
int cpuset_slab_spread_rotor;
#endif
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 54bc20496392..962d9768945f 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -10,13 +10,16 @@
*
* Copyrights:
* - Based on x86_64 vsyscall gettimeofday: Keith Owens, Andrea Arcangeli
+ * - Sequence counters with associated locks, (C) 2020 Linutronix GmbH
*/
-#include <linux/spinlock.h>
-#include <linux/preempt.h>
-#include <linux/lockdep.h>
#include <linux/compiler.h>
#include <linux/kcsan-checks.h>
+#include <linux/lockdep.h>
+#include <linux/mutex.h>
+#include <linux/preempt.h>
+#include <linux/spinlock.h>
+
#include <asm/processor.h>
/*
@@ -48,6 +51,10 @@
* This mechanism can't be used if the protected data contains pointers,
* as the writer can invalidate a pointer that a reader is following.
*
+ * If the write serialization mechanism is one of the common kernel
+ * locking primitives, use a sequence counter with associated lock
+ * (seqcount_LOCKTYPE_t) instead.
+ *
* If it's desired to automatically handle the sequence counter writer
* serialization and non-preemptibility requirements, use a sequential
* lock (seqlock_t) instead.
@@ -72,17 +79,18 @@ static inline void __seqcount_init(seqcount_t *s, const char *name,
}
#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define SEQCOUNT_DEP_MAP_INIT(lockname) \
- .dep_map = { .name = #lockname } \
+
+# define SEQCOUNT_DEP_MAP_INIT(lockname) \
+ .dep_map = { .name = #lockname }
/**
* seqcount_init() - runtime initializer for seqcount_t
* @s: Pointer to the seqcount_t instance
*/
-# define seqcount_init(s) \
- do { \
- static struct lock_class_key __key; \
- __seqcount_init((s), #s, &__key); \
+# define seqcount_init(s) \
+ do { \
+ static struct lock_class_key __key; \
+ __seqcount_init((s), #s, &__key); \
} while (0)
static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
@@ -108,9 +116,143 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
*/
#define SEQCNT_ZERO(name) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(name) }
+/*
+ * Sequence counters with associated locks (seqcount_LOCKTYPE_t)
+ *
+ * A sequence counter which associates the lock used for writer
+ * serialization at initialization time. This enables lockdep to validate
+ * that the write side critical section is properly serialized.
+ *
+ * For associated locks which do not implicitly disable preemption,
+ * preemption protection is enforced in the write side function.
+ *
+ * Lockdep is never used in any for the raw write variants.
+ *
+ * See Documentation/locking/seqlock.rst
+ */
+
+#ifdef CONFIG_LOCKDEP
+#define __SEQ_LOCK(expr) expr
+#else
+#define __SEQ_LOCK(expr)
+#endif
+
+/**
+ * typedef seqcount_LOCKNAME_t - sequence counter with LOCKTYPR associated
+ * @seqcount: The real sequence counter
+ * @lock: Pointer to the associated spinlock
+ *
+ * A plain sequence counter with external writer synchronization by a
+ * spinlock. The spinlock is associated to the sequence count in the
+ * static initializer or init function. This enables lockdep to validate
+ * that the write side critical section is properly serialized.
+ */
+
+/**
+ * seqcount_LOCKNAME_init() - runtime initializer for seqcount_LOCKNAME_t
+ * @s: Pointer to the seqcount_LOCKNAME_t instance
+ * @lock: Pointer to the associated LOCKTYPE
+ */
+
+/*
+ * SEQCOUNT_LOCKTYPE() - Instantiate seqcount_LOCKNAME_t and helpers
+ * @locktype: actual typename
+ * @lockname: name
+ * @preemptible: preemptibility of above locktype
+ * @lockmember: argument for lockdep_assert_held()
+ */
+#define SEQCOUNT_LOCKTYPE(locktype, lockname, preemptible, lockmember) \
+typedef struct seqcount_##lockname { \
+ seqcount_t seqcount; \
+ __SEQ_LOCK(locktype *lock); \
+} seqcount_##lockname##_t; \
+ \
+static __always_inline void \
+seqcount_##lockname##_init(seqcount_##lockname##_t *s, locktype *lock) \
+{ \
+ seqcount_init(&s->seqcount); \
+ __SEQ_LOCK(s->lock = lock); \
+} \
+ \
+static __always_inline seqcount_t * \
+__seqcount_##lockname##_ptr(seqcount_##lockname##_t *s) \
+{ \
+ return &s->seqcount; \
+} \
+ \
+static __always_inline bool \
+__seqcount_##lockname##_preemptible(seqcount_##lockname##_t *s) \
+{ \
+ return preemptible; \
+} \
+ \
+static __always_inline void \
+__seqcount_##lockname##_assert(seqcount_##lockname##_t *s) \
+{ \
+ __SEQ_LOCK(lockdep_assert_held(lockmember)); \
+}
+
+/*
+ * __seqprop() for seqcount_t
+ */
+
+static inline seqcount_t *__seqcount_ptr(seqcount_t *s)
+{
+ return s;
+}
+
+static inline bool __seqcount_preemptible(seqcount_t *s)
+{
+ return false;
+}
+
+static inline void __seqcount_assert(seqcount_t *s)
+{
+ lockdep_assert_preemption_disabled();
+}
+
+SEQCOUNT_LOCKTYPE(raw_spinlock_t, raw_spinlock, false, s->lock)
+SEQCOUNT_LOCKTYPE(spinlock_t, spinlock, false, s->lock)
+SEQCOUNT_LOCKTYPE(rwlock_t, rwlock, false, s->lock)
+SEQCOUNT_LOCKTYPE(struct mutex, mutex, true, s->lock)
+SEQCOUNT_LOCKTYPE(struct ww_mutex, ww_mutex, true, &s->lock->base)
+
+/**
+ * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t
+ * @name: Name of the seqcount_LOCKNAME_t instance
+ * @lock: Pointer to the associated LOCKTYPE
+ */
+
+#define SEQCOUNT_LOCKTYPE_ZERO(seq_name, assoc_lock) { \
+ .seqcount = SEQCNT_ZERO(seq_name.seqcount), \
+ __SEQ_LOCK(.lock = (assoc_lock)) \
+}
+
+#define SEQCNT_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKTYPE_ZERO(name, lock)
+#define SEQCNT_RAW_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKTYPE_ZERO(name, lock)
+#define SEQCNT_RWLOCK_ZERO(name, lock) SEQCOUNT_LOCKTYPE_ZERO(name, lock)
+#define SEQCNT_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKTYPE_ZERO(name, lock)
+#define SEQCNT_WW_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKTYPE_ZERO(name, lock)
+
+
+#define __seqprop_case(s, lockname, prop) \
+ seqcount_##lockname##_t: __seqcount_##lockname##_##prop((void *)(s))
+
+#define __seqprop(s, prop) _Generic(*(s), \
+ seqcount_t: __seqcount_##prop((void *)(s)), \
+ __seqprop_case((s), raw_spinlock, prop), \
+ __seqprop_case((s), spinlock, prop), \
+ __seqprop_case((s), rwlock, prop), \
+ __seqprop_case((s), mutex, prop), \
+ __seqprop_case((s), ww_mutex, prop))
+
+#define __seqcount_ptr(s) __seqprop(s, ptr)
+#define __seqcount_lock_preemptible(s) __seqprop(s, preemptible)
+#define __seqcount_assert_lock_held(s) __seqprop(s, assert)
+
/**
* __read_seqcount_begin() - begin a seqcount_t read section w/o barrier
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
*
* __read_seqcount_begin is like read_seqcount_begin, but has no smp_rmb()
* barrier. Callers should ensure that smp_rmb() or equivalent ordering is
@@ -122,7 +264,10 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
*
* Return: count to be passed to read_seqcount_retry()
*/
-static inline unsigned __read_seqcount_begin(const seqcount_t *s)
+#define __read_seqcount_begin(s) \
+ __read_seqcount_t_begin(__seqcount_ptr(s))
+
+static inline unsigned __read_seqcount_t_begin(const seqcount_t *s)
{
unsigned ret;
@@ -138,32 +283,38 @@ repeat:
/**
* raw_read_seqcount_begin() - begin a seqcount_t read section w/o lockdep
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
*
* Return: count to be passed to read_seqcount_retry()
*/
-static inline unsigned raw_read_seqcount_begin(const seqcount_t *s)
+#define raw_read_seqcount_begin(s) \
+ raw_read_seqcount_t_begin(__seqcount_ptr(s))
+
+static inline unsigned raw_read_seqcount_t_begin(const seqcount_t *s)
{
- unsigned ret = __read_seqcount_begin(s);
+ unsigned ret = __read_seqcount_t_begin(s);
smp_rmb();
return ret;
}
/**
* read_seqcount_begin() - begin a seqcount_t read critical section
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
*
* Return: count to be passed to read_seqcount_retry()
*/
-static inline unsigned read_seqcount_begin(const seqcount_t *s)
+#define read_seqcount_begin(s) \
+ read_seqcount_t_begin(__seqcount_ptr(s))
+
+static inline unsigned read_seqcount_t_begin(const seqcount_t *s)
{
seqcount_lockdep_reader_access(s);
- return raw_read_seqcount_begin(s);
+ return raw_read_seqcount_t_begin(s);
}
/**
* raw_read_seqcount() - read the raw seqcount_t counter value
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
*
* raw_read_seqcount opens a read critical section of the given
* seqcount_t, without any lockdep checking, and without checking or
@@ -172,7 +323,10 @@ static inline unsigned read_seqcount_begin(const seqcount_t *s)
*
* Return: count to be passed to read_seqcount_retry()
*/
-static inline unsigned raw_read_seqcount(const seqcount_t *s)
+#define raw_read_seqcount(s) \
+ raw_read_seqcount_t(__seqcount_ptr(s))
+
+static inline unsigned raw_read_seqcount_t(const seqcount_t *s)
{
unsigned ret = READ_ONCE(s->sequence);
smp_rmb();
@@ -183,7 +337,7 @@ static inline unsigned raw_read_seqcount(const seqcount_t *s)
/**
* raw_seqcount_begin() - begin a seqcount_t read critical section w/o
* lockdep and w/o counter stabilization
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
*
* raw_seqcount_begin opens a read critical section of the given
* seqcount_t. Unlike read_seqcount_begin(), this function will not wait
@@ -197,18 +351,21 @@ static inline unsigned raw_read_seqcount(const seqcount_t *s)
*
* Return: count to be passed to read_seqcount_retry()
*/
-static inline unsigned raw_seqcount_begin(const seqcount_t *s)
+#define raw_seqcount_begin(s) \
+ raw_seqcount_t_begin(__seqcount_ptr(s))
+
+static inline unsigned raw_seqcount_t_begin(const seqcount_t *s)
{
/*
* If the counter is odd, let read_seqcount_retry() fail
* by decrementing the counter.
*/
- return raw_read_seqcount(s) & ~1;
+ return raw_read_seqcount_t(s) & ~1;
}
/**
* __read_seqcount_retry() - end a seqcount_t read section w/o barrier
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
* @start: count, from read_seqcount_begin()
*
* __read_seqcount_retry is like read_seqcount_retry, but has no smp_rmb()
@@ -221,7 +378,10 @@ static inline unsigned raw_seqcount_begin(const seqcount_t *s)
*
* Return: true if a read section retry is required, else false
*/
-static inline int __read_seqcount_retry(const seqcount_t *s, unsigned start)
+#define __read_seqcount_retry(s, start) \
+ __read_seqcount_t_retry(__seqcount_ptr(s), start)
+
+static inline int __read_seqcount_t_retry(const seqcount_t *s, unsigned start)
{
kcsan_atomic_next(0);
return unlikely(READ_ONCE(s->sequence) != start);
@@ -229,7 +389,7 @@ static inline int __read_seqcount_retry(const seqcount_t *s, unsigned start)
/**
* read_seqcount_retry() - end a seqcount_t read critical section
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
* @start: count, from read_seqcount_begin()
*
* read_seqcount_retry closes the read critical section of given
@@ -238,17 +398,28 @@ static inline int __read_seqcount_retry(const seqcount_t *s, unsigned start)
*
* Return: true if a read section retry is required, else false
*/
-static inline int read_seqcount_retry(const seqcount_t *s, unsigned start)
+#define read_seqcount_retry(s, start) \
+ read_seqcount_t_retry(__seqcount_ptr(s), start)
+
+static inline int read_seqcount_t_retry(const seqcount_t *s, unsigned start)
{
smp_rmb();
- return __read_seqcount_retry(s, start);
+ return __read_seqcount_t_retry(s, start);
}
/**
* raw_write_seqcount_begin() - start a seqcount_t write section w/o lockdep
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
*/
-static inline void raw_write_seqcount_begin(seqcount_t *s)
+#define raw_write_seqcount_begin(s) \
+do { \
+ if (__seqcount_lock_preemptible(s)) \
+ preempt_disable(); \
+ \
+ raw_write_seqcount_t_begin(__seqcount_ptr(s)); \
+} while (0)
+
+static inline void raw_write_seqcount_t_begin(seqcount_t *s)
{
kcsan_nestable_atomic_begin();
s->sequence++;
@@ -257,49 +428,50 @@ static inline void raw_write_seqcount_begin(seqcount_t *s)
/**
* raw_write_seqcount_end() - end a seqcount_t write section w/o lockdep
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
*/
-static inline void raw_write_seqcount_end(seqcount_t *s)
+#define raw_write_seqcount_end(s) \
+do { \
+ raw_write_seqcount_t_end(__seqcount_ptr(s)); \
+ \
+ if (__seqcount_lock_preemptible(s)) \
+ preempt_enable(); \
+} while (0)
+
+static inline void raw_write_seqcount_t_end(seqcount_t *s)
{
smp_wmb();
s->sequence++;
kcsan_nestable_atomic_end();
}
-static inline void __write_seqcount_begin_nested(seqcount_t *s, int subclass)
-{
- raw_write_seqcount_begin(s);
- seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_);
-}
-
/**
* write_seqcount_begin_nested() - start a seqcount_t write section with
* custom lockdep nesting level
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
* @subclass: lockdep nesting level
*
* See Documentation/locking/lockdep-design.rst
*/
-static inline void write_seqcount_begin_nested(seqcount_t *s, int subclass)
+#define write_seqcount_begin_nested(s, subclass) \
+do { \
+ __seqcount_assert_lock_held(s); \
+ \
+ if (__seqcount_lock_preemptible(s)) \
+ preempt_disable(); \
+ \
+ write_seqcount_t_begin_nested(__seqcount_ptr(s), subclass); \
+} while (0)
+
+static inline void write_seqcount_t_begin_nested(seqcount_t *s, int subclass)
{
- lockdep_assert_preemption_disabled();
- __write_seqcount_begin_nested(s, subclass);
-}
-
-/*
- * A write_seqcount_begin() variant w/o lockdep non-preemptibility checks.
- *
- * Use for internal seqlock.h code where it's known that preemption is
- * already disabled. For example, seqlock_t write side functions.
- */
-static inline void __write_seqcount_begin(seqcount_t *s)
-{
- __write_seqcount_begin_nested(s, 0);
+ raw_write_seqcount_t_begin(s);
+ seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_);
}
/**
* write_seqcount_begin() - start a seqcount_t write side critical section
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
*
* write_seqcount_begin opens a write side critical section of the given
* seqcount_t.
@@ -308,26 +480,44 @@ static inline void __write_seqcount_begin(seqcount_t *s)
* non-preemptible. If readers can be invoked from hardirq or softirq
* context, interrupts or bottom halves must be respectively disabled.
*/
-static inline void write_seqcount_begin(seqcount_t *s)
+#define write_seqcount_begin(s) \
+do { \
+ __seqcount_assert_lock_held(s); \
+ \
+ if (__seqcount_lock_preemptible(s)) \
+ preempt_disable(); \
+ \
+ write_seqcount_t_begin(__seqcount_ptr(s)); \
+} while (0)
+
+static inline void write_seqcount_t_begin(seqcount_t *s)
{
- write_seqcount_begin_nested(s, 0);
+ write_seqcount_t_begin_nested(s, 0);
}
/**
* write_seqcount_end() - end a seqcount_t write side critical section
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
*
* The write section must've been opened with write_seqcount_begin().
*/
-static inline void write_seqcount_end(seqcount_t *s)
+#define write_seqcount_end(s) \
+do { \
+ write_seqcount_t_end(__seqcount_ptr(s)); \
+ \
+ if (__seqcount_lock_preemptible(s)) \
+ preempt_enable(); \
+} while (0)
+
+static inline void write_seqcount_t_end(seqcount_t *s)
{
seqcount_release(&s->dep_map, _RET_IP_);
- raw_write_seqcount_end(s);
+ raw_write_seqcount_t_end(s);
}
/**
* raw_write_seqcount_barrier() - do a seqcount_t write barrier
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
*
* This can be used to provide an ordering guarantee instead of the usual
* consistency guarantee. It is one wmb cheaper, because it can collapse
@@ -366,7 +556,10 @@ static inline void write_seqcount_end(seqcount_t *s)
* WRITE_ONCE(X, false);
* }
*/
-static inline void raw_write_seqcount_barrier(seqcount_t *s)
+#define raw_write_seqcount_barrier(s) \
+ raw_write_seqcount_t_barrier(__seqcount_ptr(s))
+
+static inline void raw_write_seqcount_t_barrier(seqcount_t *s)
{
kcsan_nestable_atomic_begin();
s->sequence++;
@@ -378,12 +571,15 @@ static inline void raw_write_seqcount_barrier(seqcount_t *s)
/**
* write_seqcount_invalidate() - invalidate in-progress seqcount_t read
* side operations
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
*
* After write_seqcount_invalidate, no seqcount_t read side operations
* will complete successfully and see data older than this.
*/
-static inline void write_seqcount_invalidate(seqcount_t *s)
+#define write_seqcount_invalidate(s) \
+ write_seqcount_t_invalidate(__seqcount_ptr(s))
+
+static inline void write_seqcount_t_invalidate(seqcount_t *s)
{
smp_wmb();
kcsan_nestable_atomic_begin();
@@ -393,7 +589,7 @@ static inline void write_seqcount_invalidate(seqcount_t *s)
/**
* raw_read_seqcount_latch() - pick even/odd seqcount_t latch data copy
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
*
* Use seqcount_t latching to switch between two storage places protected
* by a sequence counter. Doing so allows having interruptible, preemptible,
@@ -406,7 +602,10 @@ static inline void write_seqcount_invalidate(seqcount_t *s)
* picking which data copy to read. The full counter value must then be
* checked with read_seqcount_retry().
*/
-static inline int raw_read_seqcount_latch(seqcount_t *s)
+#define raw_read_seqcount_latch(s) \
+ raw_read_seqcount_t_latch(__seqcount_ptr(s))
+
+static inline int raw_read_seqcount_t_latch(seqcount_t *s)
{
/* Pairs with the first smp_wmb() in raw_write_seqcount_latch() */
int seq = READ_ONCE(s->sequence); /* ^^^ */
@@ -415,7 +614,7 @@ static inline int raw_read_seqcount_latch(seqcount_t *s)
/**
* raw_write_seqcount_latch() - redirect readers to even/odd copy
- * @s: Pointer to seqcount_t
+ * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
*
* The latch technique is a multiversion concurrency control method that allows
* queries during non-atomic modifications. If you can guarantee queries never
@@ -494,7 +693,10 @@ static inline int raw_read_seqcount_latch(seqcount_t *s)
* When data is a dynamic data structure; one should use regular RCU
* patterns to manage the lifetimes of the objects within.
*/
-static inline void raw_write_seqcount_latch(seqcount_t *s)
+#define raw_write_seqcount_latch(s) \
+ raw_write_seqcount_t_latch(__seqcount_ptr(s))
+
+static inline void raw_write_seqcount_t_latch(seqcount_t *s)
{
smp_wmb(); /* prior stores before incrementing "sequence" */
s->sequence++;
@@ -516,20 +718,20 @@ typedef struct {
spinlock_t lock;
} seqlock_t;
-#define __SEQLOCK_UNLOCKED(lockname) \
- { \
- .seqcount = SEQCNT_ZERO(lockname), \
- .lock = __SPIN_LOCK_UNLOCKED(lockname) \
+#define __SEQLOCK_UNLOCKED(lockname) \
+ { \
+ .seqcount = SEQCNT_ZERO(lockname), \
+ .lock = __SPIN_LOCK_UNLOCKED(lockname) \
}
/**
* seqlock_init() - dynamic initializer for seqlock_t
* @sl: Pointer to the seqlock_t instance
*/
-#define seqlock_init(sl) \
- do { \
- seqcount_init(&(sl)->seqcount); \
- spin_lock_init(&(sl)->lock); \
+#define seqlock_init(sl) \
+ do { \
+ seqcount_init(&(sl)->seqcount); \
+ spin_lock_init(&(sl)->lock); \
} while (0)
/**
@@ -592,7 +794,7 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
static inline void write_seqlock(seqlock_t *sl)
{
spin_lock(&sl->lock);
- __write_seqcount_begin(&sl->seqcount);
+ write_seqcount_t_begin(&sl->seqcount);
}
/**
@@ -604,7 +806,7 @@ static inline void write_seqlock(seqlock_t *sl)
*/
static inline void write_sequnlock(seqlock_t *sl)
{
- write_seqcount_end(&sl->seqcount);
+ write_seqcount_t_end(&sl->seqcount);
spin_unlock(&sl->lock);
}
@@ -618,7 +820,7 @@ static inline void write_sequnlock(seqlock_t *sl)
static inline void write_seqlock_bh(seqlock_t *sl)
{
spin_lock_bh(&sl->lock);
- __write_seqcount_begin(&sl->seqcount);
+ write_seqcount_t_begin(&sl->seqcount);
}
/**
@@ -631,7 +833,7 @@ static inline void write_seqlock_bh(seqlock_t *sl)
*/
static inline void write_sequnlock_bh(seqlock_t *sl)
{
- write_seqcount_end(&sl->seqcount);
+ write_seqcount_t_end(&sl->seqcount);
spin_unlock_bh(&sl->lock);
}
@@ -645,7 +847,7 @@ static inline void write_sequnlock_bh(seqlock_t *sl)
static inline void write_seqlock_irq(seqlock_t *sl)
{
spin_lock_irq(&sl->lock);
- __write_seqcount_begin(&sl->seqcount);
+ write_seqcount_t_begin(&sl->seqcount);
}
/**
@@ -657,7 +859,7 @@ static inline void write_seqlock_irq(seqlock_t *sl)
*/
static inline void write_sequnlock_irq(seqlock_t *sl)
{
- write_seqcount_end(&sl->seqcount);
+ write_seqcount_t_end(&sl->seqcount);
spin_unlock_irq(&sl->lock);
}
@@ -666,7 +868,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
unsigned long flags;
spin_lock_irqsave(&sl->lock, flags);
- __write_seqcount_begin(&sl->seqcount);
+ write_seqcount_t_begin(&sl->seqcount);
return flags;
}
@@ -695,13 +897,13 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
static inline void
write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags)
{
- write_seqcount_end(&sl->seqcount);
+ write_seqcount_t_end(&sl->seqcount);
spin_unlock_irqrestore(&sl->lock, flags);
}
/**
* read_seqlock_excl() - begin a seqlock_t locking reader section
- * @sl: Pointer to seqlock_t
+ * @sl: Pointer to seqlock_t
*
* read_seqlock_excl opens a seqlock_t locking reader critical section. A
* locking reader exclusively locks out *both* other writers *and* other
diff --git a/include/linux/time.h b/include/linux/time.h
index 4c325bf44ce0..b142cb5f5a53 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -3,7 +3,6 @@
#define _LINUX_TIME_H
# include <linux/cache.h>
-# include <linux/seqlock.h>
# include <linux/math64.h>
# include <linux/time64.h>
diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h
index 16c0ed6c50a7..219037f4c08d 100644
--- a/include/linux/videodev2.h
+++ b/include/linux/videodev2.h
@@ -57,6 +57,7 @@
#define __LINUX_VIDEODEV2_H
#include <linux/time.h> /* need struct timeval */
+#include <linux/kernel.h>
#include <uapi/linux/videodev2.h>
#endif /* __LINUX_VIDEODEV2_H */
diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h
index d7554252404c..850424e5d030 100644
--- a/include/linux/ww_mutex.h
+++ b/include/linux/ww_mutex.h
@@ -48,14 +48,6 @@ struct ww_acquire_ctx {
#endif
};
-struct ww_mutex {
- struct mutex base;
- struct ww_acquire_ctx *ctx;
-#ifdef CONFIG_DEBUG_MUTEXES
- struct ww_class *ww_class;
-#endif
-};
-
#ifdef CONFIG_DEBUG_LOCK_ALLOC
# define __WW_CLASS_MUTEX_INITIALIZER(lockname, class) \
, .ww_class = class
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index c7bfddfc65b0..439379ca9ffa 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -298,7 +298,7 @@ int nf_conntrack_hash_resize(unsigned int hashsize);
extern struct hlist_nulls_head *nf_conntrack_hash;
extern unsigned int nf_conntrack_htable_size;
-extern seqcount_t nf_conntrack_generation;
+extern seqcount_spinlock_t nf_conntrack_generation;
extern unsigned int nf_conntrack_max;
/* must be called with rcu read lock held */
diff --git a/init/init_task.c b/init/init_task.c
index a3eb3847e1f4..89024e8c4e95 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -154,7 +154,8 @@ struct task_struct init_task
.trc_holdout_list = LIST_HEAD_INIT(init_task.trc_holdout_list),
#endif
#ifdef CONFIG_CPUSETS
- .mems_allowed_seq = SEQCNT_ZERO(init_task.mems_allowed_seq),
+ .mems_allowed_seq = SEQCNT_SPINLOCK_ZERO(init_task.mems_allowed_seq,
+ &init_task.alloc_lock),
#endif
#ifdef CONFIG_RT_MUTEXES
.pi_waiters = RB_ROOT_CACHED,
diff --git a/kernel/fork.c b/kernel/fork.c
index 35e9894d394c..4d32190861bd 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2011,7 +2011,7 @@ static __latent_entropy struct task_struct *copy_process(
#ifdef CONFIG_CPUSETS
p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
p->cpuset_slab_spread_rotor = NUMA_NO_NODE;
- seqcount_init(&p->mems_allowed_seq);
+ seqcount_spinlock_init(&p->mems_allowed_seq, &p->alloc_lock);
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
memset(&p->irqtrace, 0, sizeof(p->irqtrace));
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index 5525cd3ba0c8..02ef87f50df2 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -423,7 +423,7 @@ static void seq_lock_time(struct seq_file *m, struct lock_time *lt)
seq_time(m, lt->min);
seq_time(m, lt->max);
seq_time(m, lt->total);
- seq_time(m, lt->nr ? div_s64(lt->total, lt->nr) : 0);
+ seq_time(m, lt->nr ? div64_u64(lt->total, lt->nr) : 0);
}
static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index d89da1c7e005..c4038511d5c9 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -135,7 +135,11 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
* timer->base->cpu_base
*/
static struct hrtimer_cpu_base migration_cpu_base = {
- .clock_base = { { .cpu_base = &migration_cpu_base, }, },
+ .clock_base = { {
+ .cpu_base = &migration_cpu_base,
+ .seq = SEQCNT_RAW_SPINLOCK_ZERO(migration_cpu_base.seq,
+ &migration_cpu_base.lock),
+ }, },
};
#define migration_base migration_cpu_base.clock_base[0]
@@ -1998,8 +2002,11 @@ int hrtimers_prepare_cpu(unsigned int cpu)
int i;
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
- cpu_base->clock_base[i].cpu_base = cpu_base;
- timerqueue_init_head(&cpu_base->clock_base[i].active);
+ struct hrtimer_clock_base *clock_b = &cpu_base->clock_base[i];
+
+ clock_b->cpu_base = cpu_base;
+ seqcount_raw_spinlock_init(&clock_b->seq, &cpu_base->lock);
+ timerqueue_init_head(&clock_b->active);
}
cpu_base->cpu = cpu;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 63a632f9896c..406306b33452 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -39,18 +39,19 @@ enum timekeeping_adv_mode {
TK_ADV_FREQ
};
+static DEFINE_RAW_SPINLOCK(timekeeper_lock);
+
/*
* The most important data for readout fits into a single 64 byte
* cache line.
*/
static struct {
- seqcount_t seq;
+ seqcount_raw_spinlock_t seq;
struct timekeeper timekeeper;
} tk_core ____cacheline_aligned = {
- .seq = SEQCNT_ZERO(tk_core.seq),
+ .seq = SEQCNT_RAW_SPINLOCK_ZERO(tk_core.seq, &timekeeper_lock),
};
-static DEFINE_RAW_SPINLOCK(timekeeper_lock);
static struct timekeeper shadow_timekeeper;
/**
@@ -63,7 +64,7 @@ static struct timekeeper shadow_timekeeper;
* See @update_fast_timekeeper() below.
*/
struct tk_fast {
- seqcount_t seq;
+ seqcount_raw_spinlock_t seq;
struct tk_read_base base[2];
};
@@ -80,11 +81,13 @@ static struct clocksource dummy_clock = {
};
static struct tk_fast tk_fast_mono ____cacheline_aligned = {
+ .seq = SEQCNT_RAW_SPINLOCK_ZERO(tk_fast_mono.seq, &timekeeper_lock),
.base[0] = { .clock = &dummy_clock, },
.base[1] = { .clock = &dummy_clock, },
};
static struct tk_fast tk_fast_raw ____cacheline_aligned = {
+ .seq = SEQCNT_RAW_SPINLOCK_ZERO(tk_fast_raw.seq, &timekeeper_lock),
.base[0] = { .clock = &dummy_clock, },
.base[1] = { .clock = &dummy_clock, },
};
@@ -157,7 +160,7 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
* tk_clock_read - atomic clocksource read() helper
*
* This helper is necessary to use in the read paths because, while the
- * seqlock ensures we don't return a bad value while structures are updated,
+ * seqcount ensures we don't return a bad value while structures are updated,
* it doesn't protect from potential crashes. There is the possibility that
* the tkr's clocksource may change between the read reference, and the
* clock reference passed to the read function. This can cause crashes if
@@ -222,10 +225,10 @@ static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr)
unsigned int seq;
/*
- * Since we're called holding a seqlock, the data may shift
+ * Since we're called holding a seqcount, the data may shift
* under us while we're doing the calculation. This can cause
* false positives, since we'd note a problem but throw the
- * results away. So nest another seqlock here to atomically
+ * results away. So nest another seqcount here to atomically
* grab the points we are checking with.
*/
do {
@@ -486,7 +489,7 @@ EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns);
*
* To keep it NMI safe since we're accessing from tracing, we're not using a
* separate timekeeper with updates to monotonic clock and boot offset
- * protected with seqlocks. This has the following minor side effects:
+ * protected with seqcounts. This has the following minor side effects:
*
* (1) Its possible that a timestamp be taken after the boot offset is updated
* but before the timekeeper is updated. If this happens, the new boot offset
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index e38b60fc183e..5b97d233f89b 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -180,7 +180,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_htable_size);
unsigned int nf_conntrack_max __read_mostly;
EXPORT_SYMBOL_GPL(nf_conntrack_max);
-seqcount_t nf_conntrack_generation __read_mostly;
+seqcount_spinlock_t nf_conntrack_generation __read_mostly;
static unsigned int nf_conntrack_hash_rnd __read_mostly;
static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple,
@@ -2588,7 +2588,8 @@ int nf_conntrack_init_start(void)
/* struct nf_ct_ext uses u8 to store offsets/size */
BUILD_BUG_ON(total_extension_size() > 255u);
- seqcount_init(&nf_conntrack_generation);
+ seqcount_spinlock_init(&nf_conntrack_generation,
+ &nf_conntrack_locks_all_lock);
for (i = 0; i < CONNTRACK_LOCKS; i++)
spin_lock_init(&nf_conntrack_locks[i]);
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index b6aad3fc46c3..4b2834fd17b2 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -18,7 +18,7 @@
struct nft_rbtree {
struct rb_root root;
rwlock_t lock;
- seqcount_t count;
+ seqcount_rwlock_t count;
struct delayed_work gc_work;
};
@@ -523,7 +523,7 @@ static int nft_rbtree_init(const struct nft_set *set,
struct nft_rbtree *priv = nft_set_priv(set);
rwlock_init(&priv->lock);
- seqcount_init(&priv->count);
+ seqcount_rwlock_init(&priv->count, &priv->lock);
priv->root = RB_ROOT;
INIT_DEFERRABLE_WORK(&priv->gc_work, nft_rbtree_gc);
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 042ea9b40c7b..d5280fd6f9c1 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -122,7 +122,7 @@ struct xfrm_pol_inexact_bin {
/* list containing '*:*' policies */
struct hlist_head hhead;
- seqcount_t count;
+ seqcount_spinlock_t count;
/* tree sorted by daddr/prefix */
struct rb_root root_d;
@@ -155,7 +155,7 @@ static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1]
__read_mostly;
static struct kmem_cache *xfrm_dst_cache __ro_after_init;
-static __read_mostly seqcount_t xfrm_policy_hash_generation;
+static __read_mostly seqcount_mutex_t xfrm_policy_hash_generation;
static struct rhashtable xfrm_policy_inexact_table;
static const struct rhashtable_params xfrm_pol_inexact_params;
@@ -719,7 +719,7 @@ xfrm_policy_inexact_alloc_bin(const struct xfrm_policy *pol, u8 dir)
INIT_HLIST_HEAD(&bin->hhead);
bin->root_d = RB_ROOT;
bin->root_s = RB_ROOT;
- seqcount_init(&bin->count);
+ seqcount_spinlock_init(&bin->count, &net->xfrm.xfrm_policy_lock);
prev = rhashtable_lookup_get_insert_key(&xfrm_policy_inexact_table,
&bin->k, &bin->head,
@@ -1899,7 +1899,7 @@ static int xfrm_policy_match(const struct xfrm_policy *pol,
static struct xfrm_pol_inexact_node *
xfrm_policy_lookup_inexact_addr(const struct rb_root *r,
- seqcount_t *count,
+ seqcount_spinlock_t *count,
const xfrm_address_t *addr, u16 family)
{
const struct rb_node *parent;
@@ -4157,7 +4157,7 @@ void __init xfrm_init(void)
{
register_pernet_subsys(&xfrm_net_ops);
xfrm_dev_init();
- seqcount_init(&xfrm_policy_hash_generation);
+ seqcount_mutex_init(&xfrm_policy_hash_generation, &hash_resize_mutex);
xfrm_input_init();
#ifdef CONFIG_XFRM_ESPINTCP
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index ef7ed916ad4a..d6408bb497dc 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -303,7 +303,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
INIT_LIST_HEAD(&irqfd->list);
INIT_WORK(&irqfd->inject, irqfd_inject);
INIT_WORK(&irqfd->shutdown, irqfd_shutdown);
- seqcount_init(&irqfd->irq_entry_sc);
+ seqcount_spinlock_init(&irqfd->irq_entry_sc, &kvm->irqfds.lock);
f = fdget(args->fd);
if (!f.file) {