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

Pull arm64 updates from Will Deacon:
 "The big highlight is support for the Scalable Vector Extension (SVE)
  which required extensive ABI work to ensure we don't break existing
  applications by blowing away their signal stack with the rather large
  new vector context (<= 2 kbit per vector register). There's further
  work to be done optimising things like exception return, but the ABI
  is solid now.

  Much of the line count comes from some new PMU drivers we have, but
  they're pretty self-contained and I suspect we'll have more of them in
  future.

  Plenty of acronym soup here:

   - initial support for the Scalable Vector Extension (SVE)

   - improved handling for SError interrupts (required to handle RAS
     events)

   - enable GCC support for 128-bit integer types

   - remove kernel text addresses from backtraces and register dumps

   - use of WFE to implement long delay()s

   - ACPI IORT updates from Lorenzo Pieralisi

   - perf PMU driver for the Statistical Profiling Extension (SPE)

   - perf PMU driver for Hisilicon's system PMUs

   - misc cleanups and non-critical fixes"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (97 commits)
  arm64: Make ARMV8_DEPRECATED depend on SYSCTL
  arm64: Implement __lshrti3 library function
  arm64: support __int128 on gcc 5+
  arm64/sve: Add documentation
  arm64/sve: Detect SVE and activate runtime support
  arm64/sve: KVM: Hide SVE from CPU features exposed to guests
  arm64/sve: KVM: Treat guest SVE use as undefined instruction execution
  arm64/sve: KVM: Prevent guests from using SVE
  arm64/sve: Add sysctl to set the default vector length for new processes
  arm64/sve: Add prctl controls for userspace vector length management
  arm64/sve: ptrace and ELF coredump support
  arm64/sve: Preserve SVE registers around EFI runtime service calls
  arm64/sve: Preserve SVE registers around kernel-mode NEON use
  arm64/sve: Probe SVE capabilities and usable vector lengths
  arm64: cpufeature: Move sys_caps_initialised declarations
  arm64/sve: Backend logic for setting the vector length
  arm64/sve: Signal handling support
  arm64/sve: Support vector length resetting for new processes
  arm64/sve: Core task context handling
  arm64/sve: Low-level CPU setup
  ...

8 files changed, 93 insertions, 10 deletions

diff --git a/include/clocksource/arm_arch_timer.h b/include/clocksource/arm_arch_timer.h
index cc805b72994a..349e5957c949 100644
--- a/include/clocksource/arm_arch_timer.h
+++ b/include/clocksource/arm_arch_timer.h
@@ -67,7 +67,9 @@ enum arch_timer_spi_nr {
 #define ARCH_TIMER_USR_VT_ACCESS_EN	(1 << 8) /* virtual timer registers */
 #define ARCH_TIMER_USR_PT_ACCESS_EN	(1 << 9) /* physical timer registers */
 
-#define ARCH_TIMER_EVT_STREAM_FREQ	10000	/* 100us */
+#define ARCH_TIMER_EVT_STREAM_PERIOD_US	100
+#define ARCH_TIMER_EVT_STREAM_FREQ				\
+	(USEC_PER_SEC / ARCH_TIMER_EVT_STREAM_PERIOD_US)
 
 struct arch_timer_kvm_info {
 	struct timecounter timecounter;
@@ -93,6 +95,7 @@ struct arch_timer_mem {
 extern u32 arch_timer_get_rate(void);
 extern u64 (*arch_timer_read_counter)(void);
 extern struct arch_timer_kvm_info *arch_timer_get_kvm_info(void);
+extern bool arch_timer_evtstrm_available(void);
 
 #else
 
@@ -106,6 +109,11 @@ static inline u64 arch_timer_read_counter(void)
 	return 0;
 }
 
+static inline bool arch_timer_evtstrm_available(void)
+{
+	return false;
+}
+
 #endif
 
 #endif
diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h
index 8d3f0bf80379..2f7a29242b87 100644
--- a/include/linux/acpi_iort.h
+++ b/include/linux/acpi_iort.h
@@ -49,8 +49,8 @@ static inline void acpi_configure_pmsi_domain(struct device *dev) { }
 /* IOMMU interface */
 static inline void iort_dma_setup(struct device *dev, u64 *dma_addr,
 				  u64 *size) { }
-static inline
-const struct iommu_ops *iort_iommu_configure(struct device *dev)
+static inline const struct iommu_ops *iort_iommu_configure(
+				      struct device *dev)
 { return NULL; }
 #endif
 
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index ec32c4c5eb30..201ab7267986 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -155,6 +155,9 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_S390_SF_ONLINE,
 	CPUHP_AP_PERF_ARM_CCI_ONLINE,
 	CPUHP_AP_PERF_ARM_CCN_ONLINE,
+	CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE,
+	CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE,
+	CPUHP_AP_PERF_ARM_HISI_L3_ONLINE,
 	CPUHP_AP_PERF_ARM_L2X0_ONLINE,
 	CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE,
 	CPUHP_AP_PERF_ARM_QCOM_L3_ONLINE,
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 60e3100b0809..dd418955962b 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -246,6 +246,14 @@ static inline int irq_is_percpu(unsigned int irq)
 	return desc->status_use_accessors & IRQ_PER_CPU;
 }
 
+static inline int irq_is_percpu_devid(unsigned int irq)
+{
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+	return desc->status_use_accessors & IRQ_PER_CPU_DEVID;
+}
+
 static inline void
 irq_set_lockdep_class(unsigned int irq, struct lock_class_key *class)
 {
diff --git a/include/linux/regset.h b/include/linux/regset.h
index 8e0c9febf495..494cedaafdf2 100644
--- a/include/linux/regset.h
+++ b/include/linux/regset.h
@@ -107,6 +107,28 @@ typedef int user_regset_writeback_fn(struct task_struct *target,
 				     int immediate);
 
 /**
+ * user_regset_get_size_fn - type of @get_size function in &struct user_regset
+ * @target:	thread being examined
+ * @regset:	regset being examined
+ *
+ * This call is optional; usually the pointer is %NULL.
+ *
+ * When provided, this function must return the current size of regset
+ * data, as observed by the @get function in &struct user_regset.  The
+ * value returned must be a multiple of @size.  The returned size is
+ * required to be valid only until the next time (if any) @regset is
+ * modified for @target.
+ *
+ * This function is intended for dynamically sized regsets.  A regset
+ * that is statically sized does not need to implement it.
+ *
+ * This function should not be called directly: instead, callers should
+ * call regset_size() to determine the current size of a regset.
+ */
+typedef unsigned int user_regset_get_size_fn(struct task_struct *target,
+					     const struct user_regset *regset);
+
+/**
  * struct user_regset - accessible thread CPU state
  * @n:			Number of slots (registers).
  * @size:		Size in bytes of a slot (register).
@@ -117,19 +139,33 @@ typedef int user_regset_writeback_fn(struct task_struct *target,
  * @set:		Function to store values.
  * @active:		Function to report if regset is active, or %NULL.
  * @writeback:		Function to write data back to user memory, or %NULL.
+ * @get_size:		Function to return the regset's size, or %NULL.
  *
  * This data structure describes a machine resource we call a register set.
  * This is part of the state of an individual thread, not necessarily
  * actual CPU registers per se.  A register set consists of a number of
  * similar slots, given by @n.  Each slot is @size bytes, and aligned to
- * @align bytes (which is at least @size).
+ * @align bytes (which is at least @size).  For dynamically-sized
+ * regsets, @n must contain the maximum possible number of slots for the
+ * regset, and @get_size must point to a function that returns the
+ * current regset size.
  *
- * These functions must be called only on the current thread or on a
- * thread that is in %TASK_STOPPED or %TASK_TRACED state, that we are
- * guaranteed will not be woken up and return to user mode, and that we
- * have called wait_task_inactive() on.  (The target thread always might
- * wake up for SIGKILL while these functions are working, in which case
- * that thread's user_regset state might be scrambled.)
+ * Callers that need to know only the current size of the regset and do
+ * not care about its internal structure should call regset_size()
+ * instead of inspecting @n or calling @get_size.
+ *
+ * For backward compatibility, the @get and @set methods must pad to, or
+ * accept, @n * @size bytes, even if the current regset size is smaller.
+ * The precise semantics of these operations depend on the regset being
+ * accessed.
+ *
+ * The functions to which &struct user_regset members point must be
+ * called only on the current thread or on a thread that is in
+ * %TASK_STOPPED or %TASK_TRACED state, that we are guaranteed will not
+ * be woken up and return to user mode, and that we have called
+ * wait_task_inactive() on.  (The target thread always might wake up for
+ * SIGKILL while these functions are working, in which case that
+ * thread's user_regset state might be scrambled.)
  *
  * The @pos argument must be aligned according to @align; the @count
  * argument must be a multiple of @size.  These functions are not
@@ -156,6 +192,7 @@ struct user_regset {
 	user_regset_set_fn		*set;
 	user_regset_active_fn		*active;
 	user_regset_writeback_fn	*writeback;
+	user_regset_get_size_fn		*get_size;
 	unsigned int			n;
 	unsigned int 			size;
 	unsigned int 			align;
@@ -371,5 +408,21 @@ static inline int copy_regset_from_user(struct task_struct *target,
 	return regset->set(target, regset, offset, size, NULL, data);
 }
 
+/**
+ * regset_size - determine the current size of a regset
+ * @target:	thread to be examined
+ * @regset:	regset to be examined
+ *
+ * Note that the returned size is valid only until the next time
+ * (if any) @regset is modified for @target.
+ */
+static inline unsigned int regset_size(struct task_struct *target,
+				       const struct user_regset *regset)
+{
+	if (!regset->get_size)
+		return regset->n * regset->size;
+	else
+		return regset->get_size(target, regset);
+}
 
 #endif	/* <linux/regset.h> */
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index e09a4f963dc0..bb6836986200 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -418,6 +418,7 @@ typedef struct elf64_shdr {
 #define NT_ARM_HW_BREAK	0x402		/* ARM hardware breakpoint registers */
 #define NT_ARM_HW_WATCH	0x403		/* ARM hardware watchpoint registers */
 #define NT_ARM_SYSTEM_CALL	0x404	/* ARM system call number */
+#define NT_ARM_SVE	0x405		/* ARM Scalable Vector Extension registers */
 #define NT_METAG_CBUF	0x500		/* Metag catch buffer registers */
 #define NT_METAG_RPIPE	0x501		/* Metag read pipeline state */
 #define NT_METAG_TLS	0x502		/* Metag TLS pointer */
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 362493a2f950..b9a4953018ed 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -942,6 +942,7 @@ enum perf_callchain_context {
 #define PERF_AUX_FLAG_TRUNCATED		0x01	/* record was truncated to fit */
 #define PERF_AUX_FLAG_OVERWRITE		0x02	/* snapshot from overwrite mode */
 #define PERF_AUX_FLAG_PARTIAL		0x04	/* record contains gaps */
+#define PERF_AUX_FLAG_COLLISION		0x08	/* sample collided with another */
 
 #define PERF_FLAG_FD_NO_GROUP		(1UL << 0)
 #define PERF_FLAG_FD_OUTPUT		(1UL << 1)
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index b640071421f7..af5f8c2df87a 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -198,4 +198,13 @@ struct prctl_mm_map {
 # define PR_CAP_AMBIENT_LOWER		3
 # define PR_CAP_AMBIENT_CLEAR_ALL	4
 
+/* arm64 Scalable Vector Extension controls */
+/* Flag values must be kept in sync with ptrace NT_ARM_SVE interface */
+#define PR_SVE_SET_VL			50	/* set task vector length */
+# define PR_SVE_SET_VL_ONEXEC		(1 << 18) /* defer effect until exec */
+#define PR_SVE_GET_VL			51	/* get task vector length */
+/* Bits common to PR_SVE_SET_VL and PR_SVE_GET_VL */
+# define PR_SVE_VL_LEN_MASK		0xffff
+# define PR_SVE_VL_INHERIT		(1 << 17) /* inherit across exec */
+
 #endif /* _LINUX_PRCTL_H */