Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 and cross-arch updates from Catalin Marinas:
 "Here's a slightly wider-spread set of updates for 5.9.

  Going outside the usual arch/arm64/ area is the removal of
  read_barrier_depends() series from Will and the MSI/IOMMU ID
  translation series from Lorenzo.

  The notable arm64 updates include ARMv8.4 TLBI range operations and
  translation level hint, time namespace support, and perf.

  Summary:

   - Removal of the tremendously unpopular read_barrier_depends()
     barrier, which is a NOP on all architectures apart from Alpha, in
     favour of allowing architectures to override READ_ONCE() and do
     whatever dance they need to do to ensure address dependencies
     provide LOAD -> LOAD/STORE ordering.

     This work also offers a potential solution if compilers are shown
     to convert LOAD -> LOAD address dependencies into control
     dependencies (e.g. under LTO), as weakly ordered architectures will
     effectively be able to upgrade READ_ONCE() to smp_load_acquire().
     The latter case is not used yet, but will be discussed further at
     LPC.

   - Make the MSI/IOMMU input/output ID translation PCI agnostic,
     augment the MSI/IOMMU ACPI/OF ID mapping APIs to accept an input ID
     bus-specific parameter and apply the resulting changes to the
     device ID space provided by the Freescale FSL bus.

   - arm64 support for TLBI range operations and translation table level
     hints (part of the ARMv8.4 architecture version).

   - Time namespace support for arm64.

   - Export the virtual and physical address sizes in vmcoreinfo for
     makedumpfile and crash utilities.

   - CPU feature handling cleanups and checks for programmer errors
     (overlapping bit-fields).

   - ACPI updates for arm64: disallow AML accesses to EFI code regions
     and kernel memory.

   - perf updates for arm64.

   - Miscellaneous fixes and cleanups, most notably PLT counting
     optimisation for module loading, recordmcount fix to ignore
     relocations other than R_AARCH64_CALL26, CMA areas reserved for
     gigantic pages on 16K and 64K configurations.

   - Trivial typos, duplicate words"

Link: http://lkml.kernel.org/r/20200710165203.31284-1-will@kernel.org
Link: http://lkml.kernel.org/r/20200619082013.13661-1-lorenzo.pieralisi@arm.com

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (82 commits)
  arm64: use IRQ_STACK_SIZE instead of THREAD_SIZE for irq stack
  arm64/mm: save memory access in check_and_switch_context() fast switch path
  arm64: sigcontext.h: delete duplicated word
  arm64: ptrace.h: delete duplicated word
  arm64: pgtable-hwdef.h: delete duplicated words
  bus: fsl-mc: Add ACPI support for fsl-mc
  bus/fsl-mc: Refactor the MSI domain creation in the DPRC driver
  of/irq: Make of_msi_map_rid() PCI bus agnostic
  of/irq: make of_msi_map_get_device_domain() bus agnostic
  dt-bindings: arm: fsl: Add msi-map device-tree binding for fsl-mc bus
  of/device: Add input id to of_dma_configure()
  of/iommu: Make of_map_rid() PCI agnostic
  ACPI/IORT: Add an input ID to acpi_dma_configure()
  ACPI/IORT: Remove useless PCI bus walk
  ACPI/IORT: Make iort_msi_map_rid() PCI agnostic
  ACPI/IORT: Make iort_get_device_domain IRQ domain agnostic
  ACPI/IORT: Make iort_match_node_callback walk the ACPI namespace for NC
  arm64: enable time namespace support
  arm64/vdso: Restrict splitting VVAR VMA
  arm64/vdso: Handle faults on timens page
  ...

4 files changed, 124 insertions, 18 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/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 7b2d6fc9e6ed..21a1edd08cbe 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -532,9 +532,10 @@ struct perf_event_mmap_page {
 				cap_bit0_is_deprecated	: 1, /* Always 1, signals that bit 0 is zero */
 
 				cap_user_rdpmc		: 1, /* The RDPMC instruction can be used to read counts */
-				cap_user_time		: 1, /* The time_* fields are used */
+				cap_user_time		: 1, /* The time_{shift,mult,offset} fields are used */
 				cap_user_time_zero	: 1, /* The time_zero field is used */
-				cap_____res		: 59;
+				cap_user_time_short	: 1, /* the time_{cycle,mask} fields are used */
+				cap_____res		: 58;
 		};
 	};
 
@@ -593,13 +594,29 @@ struct perf_event_mmap_page {
 	 *               ((rem * time_mult) >> time_shift);
 	 */
 	__u64	time_zero;
+
 	__u32	size;			/* Header size up to __reserved[] fields. */
+	__u32	__reserved_1;
+
+	/*
+	 * If cap_usr_time_short, the hardware clock is less than 64bit wide
+	 * and we must compute the 'cyc' value, as used by cap_usr_time, as:
+	 *
+	 *   cyc = time_cycles + ((cyc - time_cycles) & time_mask)
+	 *
+	 * NOTE: this form is explicitly chosen such that cap_usr_time_short
+	 *       is a correction on top of cap_usr_time, and code that doesn't
+	 *       know about cap_usr_time_short still works under the assumption
+	 *       the counter doesn't wrap.
+	 */
+	__u64	time_cycles;
+	__u64	time_mask;
 
 		/*
 		 * Hole for extension of the self monitor capabilities
 		 */
 
-	__u8	__reserved[118*8+4];	/* align to 1k. */
+	__u8	__reserved[116*8];	/* align to 1k. */
 
 	/*
 	 * Control data for the mmap() data buffer.
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.