Merge branch 'for-next/read-barrier-depends' into for-next/core

* for-next/read-barrier-depends:
  : Allow architectures to override __READ_ONCE()
  arm64: Reduce the number of header files pulled into vmlinux.lds.S
  compiler.h: Move compiletime_assert() macros into compiler_types.h
  checkpatch: Remove checks relating to [smp_]read_barrier_depends()
  include/linux: Remove smp_read_barrier_depends() from comments
  tools/memory-model: Remove smp_read_barrier_depends() from informal doc
  Documentation/barriers/kokr: Remove references to [smp_]read_barrier_depends()
  Documentation/barriers: Remove references to [smp_]read_barrier_depends()
  locking/barriers: Remove definitions for [smp_]read_barrier_depends()
  alpha: Replace smp_read_barrier_depends() usage with smp_[r]mb()
  vhost: Remove redundant use of read_barrier_depends() barrier
  asm/rwonce: Don't pull <asm/barrier.h> into 'asm-generic/rwonce.h'
  asm/rwonce: Remove smp_read_barrier_depends() invocation
  alpha: Override READ_ONCE() with barriered implementation
  asm/rwonce: Allow __READ_ONCE to be overridden by the architecture
  compiler.h: Split {READ,WRITE}_ONCE definitions out into rwonce.h
  tools: bpf: Use local copy of headers including uapi/linux/filter.h

3 files changed, 104 insertions, 15 deletions

diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile
index 6df1850f8353..8a69258fd8aa 100644
--- a/tools/bpf/Makefile
+++ b/tools/bpf/Makefile
@@ -9,7 +9,8 @@ MAKE = make
 INSTALL ?= install
 
 CFLAGS += -Wall -O2
-CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/include/uapi -I$(srctree)/include
+CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi \
+	  -I$(srctree)/tools/include
 
 # This will work when bpf is built in tools env. where srctree
 # isn't set and when invoked from selftests build, where srctree
diff --git a/tools/include/uapi/linux/filter.h b/tools/include/uapi/linux/filter.h
new file mode 100644
index 000000000000..eaef459e7bd4
--- /dev/null
+++ b/tools/include/uapi/linux/filter.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Linux Socket Filter Data Structures
+ */
+
+#ifndef __LINUX_FILTER_H__
+#define __LINUX_FILTER_H__
+
+
+#include <linux/types.h>
+#include <linux/bpf_common.h>
+
+/*
+ * Current version of the filter code architecture.
+ */
+#define BPF_MAJOR_VERSION 1
+#define BPF_MINOR_VERSION 1
+
+/*
+ *	Try and keep these values and structures similar to BSD, especially
+ *	the BPF code definitions which need to match so you can share filters
+ */
+ 
+struct sock_filter {	/* Filter block */
+	__u16	code;   /* Actual filter code */
+	__u8	jt;	/* Jump true */
+	__u8	jf;	/* Jump false */
+	__u32	k;      /* Generic multiuse field */
+};
+
+struct sock_fprog {	/* Required for SO_ATTACH_FILTER. */
+	unsigned short		len;	/* Number of filter blocks */
+	struct sock_filter *filter;
+};
+
+/* ret - BPF_K and BPF_X also apply */
+#define BPF_RVAL(code)  ((code) & 0x18)
+#define         BPF_A           0x10
+
+/* misc */
+#define BPF_MISCOP(code) ((code) & 0xf8)
+#define         BPF_TAX         0x00
+#define         BPF_TXA         0x80
+
+/*
+ * Macros for filter block array initializers.
+ */
+#ifndef BPF_STMT
+#define BPF_STMT(code, k) { (unsigned short)(code), 0, 0, k }
+#endif
+#ifndef BPF_JUMP
+#define BPF_JUMP(code, k, jt, jf) { (unsigned short)(code), jt, jf, k }
+#endif
+
+/*
+ * Number of scratch memory words for: BPF_ST and BPF_STX
+ */
+#define BPF_MEMWORDS 16
+
+/* RATIONALE. Negative offsets are invalid in BPF.
+   We use them to reference ancillary data.
+   Unlike introduction new instructions, it does not break
+   existing compilers/optimizers.
+ */
+#define SKF_AD_OFF    (-0x1000)
+#define SKF_AD_PROTOCOL 0
+#define SKF_AD_PKTTYPE 	4
+#define SKF_AD_IFINDEX 	8
+#define SKF_AD_NLATTR	12
+#define SKF_AD_NLATTR_NEST	16
+#define SKF_AD_MARK 	20
+#define SKF_AD_QUEUE	24
+#define SKF_AD_HATYPE	28
+#define SKF_AD_RXHASH	32
+#define SKF_AD_CPU	36
+#define SKF_AD_ALU_XOR_X	40
+#define SKF_AD_VLAN_TAG	44
+#define SKF_AD_VLAN_TAG_PRESENT 48
+#define SKF_AD_PAY_OFFSET	52
+#define SKF_AD_RANDOM	56
+#define SKF_AD_VLAN_TPID	60
+#define SKF_AD_MAX	64
+
+#define SKF_NET_OFF	(-0x100000)
+#define SKF_LL_OFF	(-0x200000)
+
+#define BPF_NET_OFF	SKF_NET_OFF
+#define BPF_LL_OFF	SKF_LL_OFF
+
+#endif /* __LINUX_FILTER_H__ */
diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt
index e91a2eb19592..01adf9e0ebac 100644
--- a/tools/memory-model/Documentation/explanation.txt
+++ b/tools/memory-model/Documentation/explanation.txt
@@ -1122,12 +1122,10 @@ maintain at least the appearance of FIFO order.
 In practice, this difficulty is solved by inserting a special fence
 between P1's two loads when the kernel is compiled for the Alpha
 architecture.  In fact, as of version 4.15, the kernel automatically
-adds this fence (called smp_read_barrier_depends() and defined as
-nothing at all on non-Alpha builds) after every READ_ONCE() and atomic
-load.  The effect of the fence is to cause the CPU not to execute any
-po-later instructions until after the local cache has finished
-processing all the stores it has already received.  Thus, if the code
-was changed to:
+adds this fence after every READ_ONCE() and atomic load on Alpha.  The
+effect of the fence is to cause the CPU not to execute any po-later
+instructions until after the local cache has finished processing all
+the stores it has already received.  Thus, if the code was changed to:
 
 	P1()
 	{
@@ -1146,14 +1144,14 @@ READ_ONCE() or another synchronization primitive rather than accessed
 directly.
 
 The LKMM requires that smp_rmb(), acquire fences, and strong fences
-share this property with smp_read_barrier_depends(): They do not allow
-the CPU to execute any po-later instructions (or po-later loads in the
-case of smp_rmb()) until all outstanding stores have been processed by
-the local cache.  In the case of a strong fence, the CPU first has to
-wait for all of its po-earlier stores to propagate to every other CPU
-in the system; then it has to wait for the local cache to process all
-the stores received as of that time -- not just the stores received
-when the strong fence began.
+share this property: They do not allow the CPU to execute any po-later
+instructions (or po-later loads in the case of smp_rmb()) until all
+outstanding stores have been processed by the local cache.  In the
+case of a strong fence, the CPU first has to wait for all of its
+po-earlier stores to propagate to every other CPU in the system; then
+it has to wait for the local cache to process all the stores received
+as of that time -- not just the stores received when the strong fence
+began.
 
 And of course, none of this matters for any architecture other than
 Alpha.