BackMerge v5.1-rc5 into drm-next

Need rc5 for udl fix to add udl cleanups on top.

Signed-off-by: Dave Airlie <airlied@redhat.com>

70 files changed, 1882 insertions, 368 deletions

diff --git a/tools/arch/alpha/include/uapi/asm/mman.h b/tools/arch/alpha/include/uapi/asm/mman.h
index c317d3e6867a..ea6a255ae61f 100644
--- a/tools/arch/alpha/include/uapi/asm/mman.h
+++ b/tools/arch/alpha/include/uapi/asm/mman.h
@@ -27,8 +27,6 @@
 #define MAP_NONBLOCK	0x40000
 #define MAP_NORESERVE	0x10000
 #define MAP_POPULATE	0x20000
-#define MAP_PRIVATE	0x02
-#define MAP_SHARED	0x01
 #define MAP_STACK	0x80000
 #define PROT_EXEC	0x4
 #define PROT_GROWSDOWN	0x01000000
diff --git a/tools/arch/mips/include/uapi/asm/mman.h b/tools/arch/mips/include/uapi/asm/mman.h
index de2206883abc..c8acaa138d46 100644
--- a/tools/arch/mips/include/uapi/asm/mman.h
+++ b/tools/arch/mips/include/uapi/asm/mman.h
@@ -28,8 +28,6 @@
 #define MAP_NONBLOCK	0x20000
 #define MAP_NORESERVE	0x0400
 #define MAP_POPULATE	0x10000
-#define MAP_PRIVATE	0x002
-#define MAP_SHARED	0x001
 #define MAP_STACK	0x40000
 #define PROT_EXEC	0x04
 #define PROT_GROWSDOWN	0x01000000
diff --git a/tools/arch/parisc/include/uapi/asm/mman.h b/tools/arch/parisc/include/uapi/asm/mman.h
index 1bd78758bde9..f9fd1325f5bd 100644
--- a/tools/arch/parisc/include/uapi/asm/mman.h
+++ b/tools/arch/parisc/include/uapi/asm/mman.h
@@ -27,8 +27,6 @@
 #define MAP_NONBLOCK	0x20000
 #define MAP_NORESERVE	0x4000
 #define MAP_POPULATE	0x10000
-#define MAP_PRIVATE	0x02
-#define MAP_SHARED	0x01
 #define MAP_STACK	0x40000
 #define PROT_EXEC	0x4
 #define PROT_GROWSDOWN	0x01000000
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 8c876c166ef2..26ca425f4c2c 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -463,10 +463,12 @@ struct kvm_ppc_cpu_char {
 #define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED	(1ULL << 58)
 #define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF	(1ULL << 57)
 #define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS	(1ULL << 56)
+#define KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST	(1ull << 54)
 
 #define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY	(1ULL << 63)
 #define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR		(1ULL << 62)
 #define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR	(1ULL << 61)
+#define KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE	(1ull << 58)
 
 /* Per-vcpu XICS interrupt controller state */
 #define KVM_REG_PPC_ICP_STATE	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 6d6122524711..981ff9479648 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -344,6 +344,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
diff --git a/tools/arch/xtensa/include/uapi/asm/mman.h b/tools/arch/xtensa/include/uapi/asm/mman.h
index 34dde6f44dae..f2b08c990afc 100644
--- a/tools/arch/xtensa/include/uapi/asm/mman.h
+++ b/tools/arch/xtensa/include/uapi/asm/mman.h
@@ -27,8 +27,6 @@
 #define MAP_NONBLOCK	0x20000
 #define MAP_NORESERVE	0x0400
 #define MAP_POPULATE	0x10000
-#define MAP_PRIVATE	0x002
-#define MAP_SHARED	0x001
 #define MAP_STACK	0x40000
 #define PROT_EXEC	0x4
 #define PROT_GROWSDOWN	0x01000000
diff --git a/tools/build/feature/test-libopencsd.c b/tools/build/feature/test-libopencsd.c
index d68eb4fb40cc..2b0e02c38870 100644
--- a/tools/build/feature/test-libopencsd.c
+++ b/tools/build/feature/test-libopencsd.c
@@ -4,9 +4,9 @@
 /*
  * Check OpenCSD library version is sufficient to provide required features
  */
-#define OCSD_MIN_VER ((0 << 16) | (10 << 8) | (0))
+#define OCSD_MIN_VER ((0 << 16) | (11 << 8) | (0))
 #if !defined(OCSD_VER_NUM) || (OCSD_VER_NUM < OCSD_MIN_VER)
-#error "OpenCSD >= 0.10.0 is required"
+#error "OpenCSD >= 0.11.0 is required"
 #endif
 
 int main(void)
diff --git a/tools/include/uapi/asm-generic/mman-common-tools.h b/tools/include/uapi/asm-generic/mman-common-tools.h
new file mode 100644
index 000000000000..af7d0d3a3182
--- /dev/null
+++ b/tools/include/uapi/asm-generic/mman-common-tools.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
+#define __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
+
+#include <asm-generic/mman-common.h>
+
+/* We need this because we need to have tools/include/uapi/ included in the tools
+ * header search path to get access to stuff that is not yet in the system's
+ * copy of the files in that directory, but since this cset:
+ *
+ *     746c9398f5ac ("arch: move common mmap flags to linux/mman.h")
+ *
+ * We end up making sys/mman.h, that is in the system headers, to not find the
+ * MAP_SHARED and MAP_PRIVATE defines because they are not anymore in our copy
+ * of asm-generic/mman-common.h. So we define them here and include this header
+ * from each of the per arch mman.h headers.
+ */
+#ifndef MAP_SHARED
+#define MAP_SHARED	0x01		/* Share changes */
+#define MAP_PRIVATE	0x02		/* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03	/* share + validate extension flags */
+#endif
+#endif // __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index e7ee32861d51..abd238d0f7a4 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -15,9 +15,7 @@
 #define PROT_GROWSDOWN	0x01000000	/* mprotect flag: extend change to start of growsdown vma */
 #define PROT_GROWSUP	0x02000000	/* mprotect flag: extend change to end of growsup vma */
 
-#define MAP_SHARED	0x01		/* Share changes */
-#define MAP_PRIVATE	0x02		/* Changes are private */
-#define MAP_SHARED_VALIDATE 0x03	/* share + validate extension flags */
+/* 0x01 - 0x03 are defined in linux/mman.h */
 #define MAP_TYPE	0x0f		/* Mask for type of mapping */
 #define MAP_FIXED	0x10		/* Interpret addr exactly */
 #define MAP_ANONYMOUS	0x20		/* don't use a file */
diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h
index 653687d9771b..36c197fc44a0 100644
--- a/tools/include/uapi/asm-generic/mman.h
+++ b/tools/include/uapi/asm-generic/mman.h
@@ -2,7 +2,7 @@
 #ifndef __ASM_GENERIC_MMAN_H
 #define __ASM_GENERIC_MMAN_H
 
-#include <asm-generic/mman-common.h>
+#include <asm-generic/mman-common-tools.h>
 
 #define MAP_GROWSDOWN	0x0100		/* stack-like segment */
 #define MAP_DENYWRITE	0x0800		/* ETXTBSY */
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 12cdf611d217..dee7292e1df6 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -824,8 +824,17 @@ __SYSCALL(__NR_futex_time64, sys_futex)
 __SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval)
 #endif
 
+#define __NR_pidfd_send_signal 424
+__SYSCALL(__NR_pidfd_send_signal, sys_pidfd_send_signal)
+#define __NR_io_uring_setup 425
+__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup)
+#define __NR_io_uring_enter 426
+__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter)
+#define __NR_io_uring_register 427
+__SYSCALL(__NR_io_uring_register, sys_io_uring_register)
+
 #undef __NR_syscalls
-#define __NR_syscalls 424
+#define __NR_syscalls 428
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 298b2e197744..397810fa2d33 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -1486,9 +1486,73 @@ struct drm_i915_gem_context_param {
 #define   I915_CONTEXT_MAX_USER_PRIORITY	1023 /* inclusive */
 #define   I915_CONTEXT_DEFAULT_PRIORITY		0
 #define   I915_CONTEXT_MIN_USER_PRIORITY	-1023 /* inclusive */
+	/*
+	 * When using the following param, value should be a pointer to
+	 * drm_i915_gem_context_param_sseu.
+	 */
+#define I915_CONTEXT_PARAM_SSEU		0x7
 	__u64 value;
 };
 
+/**
+ * Context SSEU programming
+ *
+ * It may be necessary for either functional or performance reason to configure
+ * a context to run with a reduced number of SSEU (where SSEU stands for Slice/
+ * Sub-slice/EU).
+ *
+ * This is done by configuring SSEU configuration using the below
+ * @struct drm_i915_gem_context_param_sseu for every supported engine which
+ * userspace intends to use.
+ *
+ * Not all GPUs or engines support this functionality in which case an error
+ * code -ENODEV will be returned.
+ *
+ * Also, flexibility of possible SSEU configuration permutations varies between
+ * GPU generations and software imposed limitations. Requesting such a
+ * combination will return an error code of -EINVAL.
+ *
+ * NOTE: When perf/OA is active the context's SSEU configuration is ignored in
+ * favour of a single global setting.
+ */
+struct drm_i915_gem_context_param_sseu {
+	/*
+	 * Engine class & instance to be configured or queried.
+	 */
+	__u16 engine_class;
+	__u16 engine_instance;
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 flags;
+
+	/*
+	 * Mask of slices to enable for the context. Valid values are a subset
+	 * of the bitmask value returned for I915_PARAM_SLICE_MASK.
+	 */
+	__u64 slice_mask;
+
+	/*
+	 * Mask of subslices to enable for the context. Valid values are a
+	 * subset of the bitmask value return by I915_PARAM_SUBSLICE_MASK.
+	 */
+	__u64 subslice_mask;
+
+	/*
+	 * Minimum/Maximum number of EUs to enable per subslice for the
+	 * context. min_eus_per_subslice must be inferior or equal to
+	 * max_eus_per_subslice.
+	 */
+	__u16 min_eus_per_subslice;
+	__u16 max_eus_per_subslice;
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 rsvd;
+};
+
 enum drm_i915_oa_format {
 	I915_OA_FORMAT_A13 = 1,	    /* HSW only */
 	I915_OA_FORMAT_A29,	    /* HSW only */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 3c38ac9a92a7..929c8e537a14 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -502,16 +502,6 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
- * 	Description
- * 		Push an element *value* in *map*. *flags* is one of:
- *
- * 		**BPF_EXIST**
- * 		If the queue/stack is full, the oldest element is removed to
- * 		make room for this.
- * 	Return
- * 		0 on success, or a negative error in case of failure.
- *
  * int bpf_probe_read(void *dst, u32 size, const void *src)
  * 	Description
  * 		For tracing programs, safely attempt to read *size* bytes from
@@ -1435,14 +1425,14 @@ union bpf_attr {
  * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx)
  * 	Description
  * 		Equivalent to bpf_get_socket_cookie() helper that accepts
- * 		*skb*, but gets socket from **struct bpf_sock_addr** contex.
+ * 		*skb*, but gets socket from **struct bpf_sock_addr** context.
  * 	Return
  * 		A 8-byte long non-decreasing number.
  *
  * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx)
  * 	Description
  * 		Equivalent to bpf_get_socket_cookie() helper that accepts
- * 		*skb*, but gets socket from **struct bpf_sock_ops** contex.
+ * 		*skb*, but gets socket from **struct bpf_sock_ops** context.
  * 	Return
  * 		A 8-byte long non-decreasing number.
  *
@@ -2098,52 +2088,52 @@ union bpf_attr {
  *	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle)
+ * int bpf_rc_repeat(void *ctx)
  *	Description
  *		This helper is used in programs implementing IR decoding, to
- *		report a successfully decoded key press with *scancode*,
- *		*toggle* value in the given *protocol*. The scancode will be
- *		translated to a keycode using the rc keymap, and reported as
- *		an input key down event. After a period a key up event is
- *		generated. This period can be extended by calling either
- *		**bpf_rc_keydown**\ () again with the same values, or calling
- *		**bpf_rc_repeat**\ ().
+ *		report a successfully decoded repeat key message. This delays
+ *		the generation of a key up event for previously generated
+ *		key down event.
  *
- *		Some protocols include a toggle bit, in case the button	was
- *		released and pressed again between consecutive scancodes.
+ *		Some IR protocols like NEC have a special IR message for
+ *		repeating last button, for when a button is held down.
  *
  *		The *ctx* should point to the lirc sample as passed into
  *		the program.
  *
- *		The *protocol* is the decoded protocol number (see
- *		**enum rc_proto** for some predefined values).
- *
  *		This helper is only available is the kernel was compiled with
  *		the **CONFIG_BPF_LIRC_MODE2** configuration option set to
  *		"**y**".
  *	Return
  *		0
  *
- * int bpf_rc_repeat(void *ctx)
+ * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle)
  *	Description
  *		This helper is used in programs implementing IR decoding, to
- *		report a successfully decoded repeat key message. This delays
- *		the generation of a key up event for previously generated
- *		key down event.
+ *		report a successfully decoded key press with *scancode*,
+ *		*toggle* value in the given *protocol*. The scancode will be
+ *		translated to a keycode using the rc keymap, and reported as
+ *		an input key down event. After a period a key up event is
+ *		generated. This period can be extended by calling either
+ *		**bpf_rc_keydown**\ () again with the same values, or calling
+ *		**bpf_rc_repeat**\ ().
  *
- *		Some IR protocols like NEC have a special IR message for
- *		repeating last button, for when a button is held down.
+ *		Some protocols include a toggle bit, in case the button	was
+ *		released and pressed again between consecutive scancodes.
  *
  *		The *ctx* should point to the lirc sample as passed into
  *		the program.
  *
+ *		The *protocol* is the decoded protocol number (see
+ *		**enum rc_proto** for some predefined values).
+ *
  *		This helper is only available is the kernel was compiled with
  *		the **CONFIG_BPF_LIRC_MODE2** configuration option set to
  *		"**y**".
  *	Return
  *		0
  *
- * uint64_t bpf_skb_cgroup_id(struct sk_buff *skb)
+ * u64 bpf_skb_cgroup_id(struct sk_buff *skb)
  * 	Description
  * 		Return the cgroup v2 id of the socket associated with the *skb*.
  * 		This is roughly similar to the **bpf_get_cgroup_classid**\ ()
@@ -2159,30 +2149,12 @@ union bpf_attr {
  * 	Return
  * 		The id is returned or 0 in case the id could not be retrieved.
  *
- * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
- *	Description
- *		Return id of cgroup v2 that is ancestor of cgroup associated
- *		with the *skb* at the *ancestor_level*.  The root cgroup is at
- *		*ancestor_level* zero and each step down the hierarchy
- *		increments the level. If *ancestor_level* == level of cgroup
- *		associated with *skb*, then return value will be same as that
- *		of **bpf_skb_cgroup_id**\ ().
- *
- *		The helper is useful to implement policies based on cgroups
- *		that are upper in hierarchy than immediate cgroup associated
- *		with *skb*.
- *
- *		The format of returned id and helper limitations are same as in
- *		**bpf_skb_cgroup_id**\ ().
- *	Return
- *		The id is returned or 0 in case the id could not be retrieved.
- *
  * u64 bpf_get_current_cgroup_id(void)
  * 	Return
  * 		A 64-bit integer containing the current cgroup id based
  * 		on the cgroup within which the current task is running.
  *
- * void* get_local_storage(void *map, u64 flags)
+ * void *bpf_get_local_storage(void *map, u64 flags)
  *	Description
  *		Get the pointer to the local storage area.
  *		The type and the size of the local storage is defined
@@ -2209,6 +2181,24 @@ union bpf_attr {
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
+ * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
+ *	Description
+ *		Return id of cgroup v2 that is ancestor of cgroup associated
+ *		with the *skb* at the *ancestor_level*.  The root cgroup is at
+ *		*ancestor_level* zero and each step down the hierarchy
+ *		increments the level. If *ancestor_level* == level of cgroup
+ *		associated with *skb*, then return value will be same as that
+ *		of **bpf_skb_cgroup_id**\ ().
+ *
+ *		The helper is useful to implement policies based on cgroups
+ *		that are upper in hierarchy than immediate cgroup associated
+ *		with *skb*.
+ *
+ *		The format of returned id and helper limitations are same as in
+ *		**bpf_skb_cgroup_id**\ ().
+ *	Return
+ *		The id is returned or 0 in case the id could not be retrieved.
+ *
  * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
  *	Description
  *		Look for TCP socket matching *tuple*, optionally in a child
@@ -2289,6 +2279,16 @@ union bpf_attr {
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
+ * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
+ * 	Description
+ * 		Push an element *value* in *map*. *flags* is one of:
+ *
+ * 		**BPF_EXIST**
+ * 			If the queue/stack is full, the oldest element is
+ * 			removed to make room for this.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
  * int bpf_map_pop_elem(struct bpf_map *map, void *value)
  * 	Description
  * 		Pop an element from *map*.
@@ -2343,29 +2343,94 @@ union bpf_attr {
  *	Return
  *		0
  *
+ * int bpf_spin_lock(struct bpf_spin_lock *lock)
+ *	Description
+ *		Acquire a spinlock represented by the pointer *lock*, which is
+ *		stored as part of a value of a map. Taking the lock allows to
+ *		safely update the rest of the fields in that value. The
+ *		spinlock can (and must) later be released with a call to
+ *		**bpf_spin_unlock**\ (\ *lock*\ ).
+ *
+ *		Spinlocks in BPF programs come with a number of restrictions
+ *		and constraints:
+ *
+ *		* **bpf_spin_lock** objects are only allowed inside maps of
+ *		  types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this
+ *		  list could be extended in the future).
+ *		* BTF description of the map is mandatory.
+ *		* The BPF program can take ONE lock at a time, since taking two
+ *		  or more could cause dead locks.
+ *		* Only one **struct bpf_spin_lock** is allowed per map element.
+ *		* When the lock is taken, calls (either BPF to BPF or helpers)
+ *		  are not allowed.
+ *		* The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not
+ *		  allowed inside a spinlock-ed region.
+ *		* The BPF program MUST call **bpf_spin_unlock**\ () to release
+ *		  the lock, on all execution paths, before it returns.
+ *		* The BPF program can access **struct bpf_spin_lock** only via
+ *		  the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ ()
+ *		  helpers. Loading or storing data into the **struct
+ *		  bpf_spin_lock** *lock*\ **;** field of a map is not allowed.
+ *		* To use the **bpf_spin_lock**\ () helper, the BTF description
+ *		  of the map value must be a struct and have **struct
+ *		  bpf_spin_lock** *anyname*\ **;** field at the top level.
+ *		  Nested lock inside another struct is not allowed.
+ *		* The **struct bpf_spin_lock** *lock* field in a map value must
+ *		  be aligned on a multiple of 4 bytes in that value.
+ *		* Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy
+ *		  the **bpf_spin_lock** field to user space.
+ *		* Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from
+ *		  a BPF program, do not update the **bpf_spin_lock** field.
+ *		* **bpf_spin_lock** cannot be on the stack or inside a
+ *		  networking packet (it can only be inside of a map values).
+ *		* **bpf_spin_lock** is available to root only.
+ *		* Tracing programs and socket filter programs cannot use
+ *		  **bpf_spin_lock**\ () due to insufficient preemption checks
+ *		  (but this may change in the future).
+ *		* **bpf_spin_lock** is not allowed in inner maps of map-in-map.
+ *	Return
+ *		0
+ *
+ * int bpf_spin_unlock(struct bpf_spin_lock *lock)
+ *	Description
+ *		Release the *lock* previously locked by a call to
+ *		**bpf_spin_lock**\ (\ *lock*\ ).
+ *	Return
+ *		0
+ *
  * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk)
  *	Description
  *		This helper gets a **struct bpf_sock** pointer such
- *		that all the fields in bpf_sock can be accessed.
+ *		that all the fields in this **bpf_sock** can be accessed.
  *	Return
- *		A **struct bpf_sock** pointer on success, or NULL in
+ *		A **struct bpf_sock** pointer on success, or **NULL** in
  *		case of failure.
  *
  * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk)
  *	Description
  *		This helper gets a **struct bpf_tcp_sock** pointer from a
  *		**struct bpf_sock** pointer.
- *
  *	Return
- *		A **struct bpf_tcp_sock** pointer on success, or NULL in
+ *		A **struct bpf_tcp_sock** pointer on success, or **NULL** in
  *		case of failure.
  *
  * int bpf_skb_ecn_set_ce(struct sk_buf *skb)
- *     Description
- *             Sets ECN of IP header to ce (congestion encountered) if
- *             current value is ect (ECN capable). Works with IPv6 and IPv4.
- *     Return
- *             1 if set, 0 if not set.
+ *	Description
+ *		Set ECN (Explicit Congestion Notification) field of IP header
+ *		to **CE** (Congestion Encountered) if current value is **ECT**
+ *		(ECN Capable Transport). Otherwise, do nothing. Works with IPv6
+ *		and IPv4.
+ *	Return
+ *		1 if the **CE** flag is set (either by the current helper call
+ *		or because it was already present), 0 if it is not set.
+ *
+ * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk)
+ *	Description
+ *		Return a **struct bpf_sock** pointer in **TCP_LISTEN** state.
+ *		**bpf_sk_release**\ () is unnecessary and not allowed.
+ *	Return
+ *		A **struct bpf_sock** pointer on success, or **NULL** in
+ *		case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2465,7 +2530,8 @@ union bpf_attr {
 	FN(spin_unlock),		\
 	FN(sk_fullsock),		\
 	FN(tcp_sock),			\
-	FN(skb_ecn_set_ce),
+	FN(skb_ecn_set_ce),		\
+	FN(get_listener_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
index 6448cdd9a350..a2f8658f1c55 100644
--- a/tools/include/uapi/linux/fcntl.h
+++ b/tools/include/uapi/linux/fcntl.h
@@ -41,6 +41,7 @@
 #define F_SEAL_SHRINK	0x0002	/* prevent file from shrinking */
 #define F_SEAL_GROW	0x0004	/* prevent file from growing */
 #define F_SEAL_WRITE	0x0008	/* prevent writes */
+#define F_SEAL_FUTURE_WRITE	0x0010  /* prevent future writes while mapped */
 /* (1U << 31) is reserved for signed error codes */
 
 /*
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
index d0f515d53299..fc1a64c3447b 100644
--- a/tools/include/uapi/linux/mman.h
+++ b/tools/include/uapi/linux/mman.h
@@ -12,6 +12,10 @@
 #define OVERCOMMIT_ALWAYS		1
 #define OVERCOMMIT_NEVER		2
 
+#define MAP_SHARED	0x01		/* Share changes */
+#define MAP_PRIVATE	0x02		/* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03	/* share + validate extension flags */
+
 /*
  * Huge page size encoding when MAP_HUGETLB is specified, and a huge page
  * size other than the default is desired.  See hugetlb_encode.h.
diff --git a/tools/io_uring/io_uring-bench.c b/tools/io_uring/io_uring-bench.c
index 512306a37531..0f257139b003 100644
--- a/tools/io_uring/io_uring-bench.c
+++ b/tools/io_uring/io_uring-bench.c
@@ -32,10 +32,6 @@
 #include "liburing.h"
 #include "barrier.h"
 
-#ifndef IOCQE_FLAG_CACHEHIT
-#define IOCQE_FLAG_CACHEHIT	(1U << 0)
-#endif
-
 #define min(a, b)		((a < b) ? (a) : (b))
 
 struct io_sq_ring {
@@ -85,7 +81,6 @@ struct submitter {
 	unsigned long reaps;
 	unsigned long done;
 	unsigned long calls;
-	unsigned long cachehit, cachemiss;
 	volatile int finish;
 
 	__s32 *fds;
@@ -270,10 +265,6 @@ static int reap_events(struct submitter *s)
 				return -1;
 			}
 		}
-		if (cqe->flags & IOCQE_FLAG_CACHEHIT)
-			s->cachehit++;
-		else
-			s->cachemiss++;
 		reaped++;
 		head++;
 	} while (1);
@@ -489,7 +480,7 @@ static void file_depths(char *buf)
 int main(int argc, char *argv[])
 {
 	struct submitter *s = &submitters[0];
-	unsigned long done, calls, reap, cache_hit, cache_miss;
+	unsigned long done, calls, reap;
 	int err, i, flags, fd;
 	char *fdepths;
 	void *ret;
@@ -569,44 +560,29 @@ int main(int argc, char *argv[])
 	pthread_create(&s->thread, NULL, submitter_fn, s);
 
 	fdepths = malloc(8 * s->nr_files);
-	cache_hit = cache_miss = reap = calls = done = 0;
+	reap = calls = done = 0;
 	do {
 		unsigned long this_done = 0;
 		unsigned long this_reap = 0;
 		unsigned long this_call = 0;
-		unsigned long this_cache_hit = 0;
-		unsigned long this_cache_miss = 0;
 		unsigned long rpc = 0, ipc = 0;
-		double hit = 0.0;
 
 		sleep(1);
 		this_done += s->done;
 		this_call += s->calls;
 		this_reap += s->reaps;
-		this_cache_hit += s->cachehit;
-		this_cache_miss += s->cachemiss;
-		if (this_cache_hit && this_cache_miss) {
-			unsigned long hits, total;
-
-			hits = this_cache_hit - cache_hit;
-			total = hits + this_cache_miss - cache_miss;
-			hit = (double) hits / (double) total;
-			hit *= 100.0;
-		}
 		if (this_call - calls) {
 			rpc = (this_done - done) / (this_call - calls);
 			ipc = (this_reap - reap) / (this_call - calls);
 		} else
 			rpc = ipc = -1;
 		file_depths(fdepths);
-		printf("IOPS=%lu, IOS/call=%ld/%ld, inflight=%u (%s), Cachehit=%0.2f%%\n",
+		printf("IOPS=%lu, IOS/call=%ld/%ld, inflight=%u (%s)\n",
 				this_done - done, rpc, ipc, s->inflight,
-				fdepths, hit);
+				fdepths);
 		done = this_done;
 		calls = this_call;
 		reap = this_reap;
-		cache_hit = s->cachehit;
-		cache_miss = s->cachemiss;
 	} while (!finish);
 
 	pthread_join(s->thread, &ret);
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 61aaacf0cfa1..8e7c56e9590f 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -3,7 +3,7 @@
 
 BPF_VERSION = 0
 BPF_PATCHLEVEL = 0
-BPF_EXTRAVERSION = 1
+BPF_EXTRAVERSION = 2
 
 MAKEFLAGS += --no-print-directory
 
@@ -79,8 +79,6 @@ export prefix libdir src obj
 libdir_SQ = $(subst ','\'',$(libdir))
 libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
 
-LIB_FILE = libbpf.a libbpf.so
-
 VERSION		= $(BPF_VERSION)
 PATCHLEVEL	= $(BPF_PATCHLEVEL)
 EXTRAVERSION	= $(BPF_EXTRAVERSION)
@@ -88,7 +86,10 @@ EXTRAVERSION	= $(BPF_EXTRAVERSION)
 OBJ		= $@
 N		=
 
-LIBBPF_VERSION = $(BPF_VERSION).$(BPF_PATCHLEVEL).$(BPF_EXTRAVERSION)
+LIBBPF_VERSION	= $(BPF_VERSION).$(BPF_PATCHLEVEL).$(BPF_EXTRAVERSION)
+
+LIB_TARGET	= libbpf.a libbpf.so.$(LIBBPF_VERSION)
+LIB_FILE	= libbpf.a libbpf.so*
 
 # Set compile option CFLAGS
 ifdef EXTRA_CFLAGS
@@ -128,16 +129,18 @@ all:
 export srctree OUTPUT CC LD CFLAGS V
 include $(srctree)/tools/build/Makefile.include
 
-BPF_IN    := $(OUTPUT)libbpf-in.o
-LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))
-VERSION_SCRIPT := libbpf.map
+BPF_IN		:= $(OUTPUT)libbpf-in.o
+VERSION_SCRIPT	:= libbpf.map
+
+LIB_TARGET	:= $(addprefix $(OUTPUT),$(LIB_TARGET))
+LIB_FILE	:= $(addprefix $(OUTPUT),$(LIB_FILE))
 
 GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN) | \
 			   awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {s++} END{print s}')
 VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \
 			      grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l)
 
-CMD_TARGETS = $(LIB_FILE)
+CMD_TARGETS = $(LIB_TARGET)
 
 CXX_TEST_TARGET = $(OUTPUT)test_libbpf
 
@@ -170,9 +173,13 @@ $(BPF_IN): force elfdep bpfdep
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true
 	$(Q)$(MAKE) $(build)=libbpf
 
-$(OUTPUT)libbpf.so: $(BPF_IN)
-	$(QUIET_LINK)$(CC) --shared -Wl,--version-script=$(VERSION_SCRIPT) \
-		$^ -o $@
+$(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)
+
+$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN)
+	$(QUIET_LINK)$(CC) --shared -Wl,-soname,libbpf.so.$(VERSION) \
+				    -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@
+	@ln -sf $(@F) $(OUTPUT)libbpf.so
+	@ln -sf $(@F) $(OUTPUT)libbpf.so.$(VERSION)
 
 $(OUTPUT)libbpf.a: $(BPF_IN)
 	$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
@@ -192,6 +199,12 @@ check_abi: $(OUTPUT)libbpf.so
 		exit 1;							 \
 	fi
 
+define do_install_mkdir
+	if [ ! -d '$(DESTDIR_SQ)$1' ]; then		\
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1';	\
+	fi
+endef
+
 define do_install
 	if [ ! -d '$(DESTDIR_SQ)$2' ]; then		\
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2';	\
@@ -200,14 +213,16 @@ define do_install
 endef
 
 install_lib: all_cmd
-	$(call QUIET_INSTALL, $(LIB_FILE)) \
-		$(call do_install,$(LIB_FILE),$(libdir_SQ))
+	$(call QUIET_INSTALL, $(LIB_TARGET)) \
+		$(call do_install_mkdir,$(libdir_SQ)); \
+		cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ)
 
 install_headers:
 	$(call QUIET_INSTALL, headers) \
 		$(call do_install,bpf.h,$(prefix)/include/bpf,644); \
-		$(call do_install,libbpf.h,$(prefix)/include/bpf,644);
-		$(call do_install,btf.h,$(prefix)/include/bpf,644);
+		$(call do_install,libbpf.h,$(prefix)/include/bpf,644); \
+		$(call do_install,btf.h,$(prefix)/include/bpf,644); \
+		$(call do_install,xsk.h,$(prefix)/include/bpf,644);
 
 install: install_lib
 
@@ -219,7 +234,7 @@ config-clean:
 
 clean:
 	$(call QUIET_CLEAN, libbpf) $(RM) $(TARGETS) $(CXX_TEST_TARGET) \
-		*.o *~ *.a *.so .*.d .*.cmd LIBBPF-CFLAGS
+		*.o *~ *.a *.so *.so.$(VERSION) .*.d .*.cmd LIBBPF-CFLAGS
 	$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
 
 
diff --git a/tools/lib/bpf/README.rst b/tools/lib/bpf/README.rst
index 5788479384ca..cef7b77eab69 100644
--- a/tools/lib/bpf/README.rst
+++ b/tools/lib/bpf/README.rst
@@ -111,6 +111,7 @@ starting from ``0.0.1``.
 
 Every time ABI is being changed, e.g. because a new symbol is added or
 semantic of existing symbol is changed, ABI version should be bumped.
+This bump in ABI version is at most once per kernel development cycle.
 
 For example, if current state of ``libbpf.map`` is:
 
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 1b8d8cdd3575..cf119c9b6f27 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1602,16 +1602,12 @@ static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2)
 /* Calculate type signature hash of ENUM. */
 static __u32 btf_hash_enum(struct btf_type *t)
 {
-	struct btf_enum *member = (struct btf_enum *)(t + 1);
-	__u32 vlen = BTF_INFO_VLEN(t->info);
-	__u32 h = btf_hash_common(t);
-	int i;
+	__u32 h;
 
-	for (i = 0; i < vlen; i++) {
-		h = hash_combine(h, member->name_off);
-		h = hash_combine(h, member->val);
-		member++;
-	}
+	/* don't hash vlen and enum members to support enum fwd resolving */
+	h = hash_combine(0, t->name_off);
+	h = hash_combine(h, t->info & ~0xffff);
+	h = hash_combine(h, t->size);
 	return h;
 }
 
@@ -1637,6 +1633,22 @@ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2)
 	return true;
 }
 
+static inline bool btf_is_enum_fwd(struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM &&
+	       BTF_INFO_VLEN(t->info) == 0;
+}
+
+static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2)
+{
+	if (!btf_is_enum_fwd(t1) && !btf_is_enum_fwd(t2))
+		return btf_equal_enum(t1, t2);
+	/* ignore vlen when comparing */
+	return t1->name_off == t2->name_off &&
+	       (t1->info & ~0xffff) == (t2->info & ~0xffff) &&
+	       t1->size == t2->size;
+}
+
 /*
  * Calculate type signature hash of STRUCT/UNION, ignoring referenced type IDs,
  * as referenced type IDs equivalence is established separately during type
@@ -1860,6 +1872,17 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 				new_id = cand_node->type_id;
 				break;
 			}
+			if (d->opts.dont_resolve_fwds)
+				continue;
+			if (btf_compat_enum(t, cand)) {
+				if (btf_is_enum_fwd(t)) {
+					/* resolve fwd to full enum */
+					new_id = cand_node->type_id;
+					break;
+				}
+				/* resolve canonical enum fwd to full enum */
+				d->map[cand_node->type_id] = type_id;
+			}
 		}
 		break;
 
@@ -2084,7 +2107,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 		return fwd_kind == real_kind;
 	}
 
-	if (cand_type->info != canon_type->info)
+	if (cand_kind != canon_kind)
 		return 0;
 
 	switch (cand_kind) {
@@ -2092,7 +2115,10 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 		return btf_equal_int(cand_type, canon_type);
 
 	case BTF_KIND_ENUM:
-		return btf_equal_enum(cand_type, canon_type);
+		if (d->opts.dont_resolve_fwds)
+			return btf_equal_enum(cand_type, canon_type);
+		else
+			return btf_compat_enum(cand_type, canon_type);
 
 	case BTF_KIND_FWD:
 		return btf_equal_common(cand_type, canon_type);
@@ -2103,6 +2129,8 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 	case BTF_KIND_PTR:
 	case BTF_KIND_TYPEDEF:
 	case BTF_KIND_FUNC:
+		if (cand_type->info != canon_type->info)
+			return 0;
 		return btf_dedup_is_equiv(d, cand_type->type, canon_type->type);
 
 	case BTF_KIND_ARRAY: {
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e6ad87512519..11c25d9ea431 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -840,12 +840,19 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
 			obj->efile.maps_shndx = idx;
 		else if (strcmp(name, BTF_ELF_SEC) == 0) {
 			obj->btf = btf__new(data->d_buf, data->d_size);
-			if (IS_ERR(obj->btf) || btf__load(obj->btf)) {
+			if (IS_ERR(obj->btf)) {
 				pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
 					   BTF_ELF_SEC, PTR_ERR(obj->btf));
-				if (!IS_ERR(obj->btf))
-					btf__free(obj->btf);
 				obj->btf = NULL;
+				continue;
+			}
+			err = btf__load(obj->btf);
+			if (err) {
+				pr_warning("Error loading %s into kernel: %d. Ignored and continue.\n",
+					   BTF_ELF_SEC, err);
+				btf__free(obj->btf);
+				obj->btf = NULL;
+				err = 0;
 			}
 		} else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
 			btf_ext_data = data;
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index f98ac82c9aea..8d0078b65486 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -126,8 +126,8 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg,
 	cfg->frame_headroom = usr_cfg->frame_headroom;
 }
 
-static void xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
-				      const struct xsk_socket_config *usr_cfg)
+static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
+				     const struct xsk_socket_config *usr_cfg)
 {
 	if (!usr_cfg) {
 		cfg->rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS;
@@ -135,14 +135,19 @@ static void xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
 		cfg->libbpf_flags = 0;
 		cfg->xdp_flags = 0;
 		cfg->bind_flags = 0;
-		return;
+		return 0;
 	}
 
+	if (usr_cfg->libbpf_flags & ~XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)
+		return -EINVAL;
+
 	cfg->rx_size = usr_cfg->rx_size;
 	cfg->tx_size = usr_cfg->tx_size;
 	cfg->libbpf_flags = usr_cfg->libbpf_flags;
 	cfg->xdp_flags = usr_cfg->xdp_flags;
 	cfg->bind_flags = usr_cfg->bind_flags;
+
+	return 0;
 }
 
 int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size,
@@ -557,7 +562,9 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 	}
 	strncpy(xsk->ifname, ifname, IFNAMSIZ);
 
-	xsk_set_xdp_socket_config(&xsk->config, usr_config);
+	err = xsk_set_xdp_socket_config(&xsk->config, usr_config);
+	if (err)
+		goto out_socket;
 
 	if (rx) {
 		err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING,
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index c9d038f91af6..53f8be0f4a1f 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -25,14 +25,17 @@ LIBSUBCMD		= $(LIBSUBCMD_OUTPUT)libsubcmd.a
 OBJTOOL    := $(OUTPUT)objtool
 OBJTOOL_IN := $(OBJTOOL)-in.o
 
+LIBELF_FLAGS := $(shell pkg-config libelf --cflags 2>/dev/null)
+LIBELF_LIBS  := $(shell pkg-config libelf --libs 2>/dev/null || echo -lelf)
+
 all: $(OBJTOOL)
 
 INCLUDES := -I$(srctree)/tools/include \
 	    -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \
 	    -I$(srctree)/tools/objtool/arch/$(ARCH)/include
 WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed
-CFLAGS   += -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES)
-LDFLAGS  += -lelf $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS)
+CFLAGS   += -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES) $(LIBELF_FLAGS)
+LDFLAGS  += $(LIBELF_LIBS) $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS)
 
 # Allow old libelf to be used:
 elfshdr := $(shell echo '$(pound)include <libelf.h>' | $(CC) $(CFLAGS) -x c -E - | grep elf_getshdr)
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 5dde107083c6..479196aeb409 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -165,6 +165,7 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func,
 		"fortify_panic",
 		"usercopy_abort",
 		"machine_real_restart",
+		"rewind_stack_do_exit",
 	};
 
 	if (func->bind == STB_WEAK)
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 01f7555fd933..e8c9f77e9010 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -481,8 +481,8 @@ $(madvise_behavior_array): $(madvise_hdr_dir)/mman-common.h $(madvise_behavior_t
 mmap_flags_array := $(beauty_outdir)/mmap_flags_array.c
 mmap_flags_tbl := $(srctree)/tools/perf/trace/beauty/mmap_flags.sh
 
-$(mmap_flags_array): $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl)
-	$(Q)$(SHELL) '$(mmap_flags_tbl)' $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
+$(mmap_flags_array): $(linux_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl)
+	$(Q)$(SHELL) '$(mmap_flags_tbl)' $(linux_uapi_dir) $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
 
 mount_flags_array := $(beauty_outdir)/mount_flags_array.c
 mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 2ae92fddb6d5..92ee0b4378d4 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -345,6 +345,10 @@
 334	common	rseq			__x64_sys_rseq
 # don't use numbers 387 through 423, add new calls after the last
 # 'common' entry
+424	common	pidfd_send_signal	__x64_sys_pidfd_send_signal
+425	common	io_uring_setup		__x64_sys_io_uring_setup
+426	common	io_uring_enter		__x64_sys_io_uring_enter
+427	common	io_uring_register	__x64_sys_io_uring_register
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 7b55613924de..c68ee06cae63 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -103,7 +103,7 @@ done
 # diff with extra ignore lines
 check arch/x86/lib/memcpy_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
 check arch/x86/lib/memset_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
-check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common.h>"'
+check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"'
 check include/uapi/linux/mman.h       '-I "^#include <\(uapi/\)*asm/mman.h>"'
 
 # diff non-symmetric files
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index e38518cdcbc3..74ef92f1d19a 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -107,6 +107,7 @@ import os
 from PySide.QtCore import *
 from PySide.QtGui import *
 from PySide.QtSql import *
+pyside_version_1 = True
 from decimal import *
 from ctypes import *
 from multiprocessing import Process, Array, Value, Event
@@ -1526,6 +1527,19 @@ def BranchDataPrep(query):
 			" (" + dsoname(query.value(15)) + ")")
 	return data
 
+def BranchDataPrepWA(query):
+	data = []
+	data.append(query.value(0))
+	# Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string
+	data.append("{:>19}".format(query.value(1)))
+	for i in xrange(2, 8):
+		data.append(query.value(i))
+	data.append(tohex(query.value(8)).rjust(16) + " " + query.value(9) + offstr(query.value(10)) +
+			" (" + dsoname(query.value(11)) + ")" + " -> " +
+			tohex(query.value(12)) + " " + query.value(13) + offstr(query.value(14)) +
+			" (" + dsoname(query.value(15)) + ")")
+	return data
+
 # Branch data model
 
 class BranchModel(TreeModel):
@@ -1553,7 +1567,11 @@ class BranchModel(TreeModel):
 			" AND evsel_id = " + str(self.event_id) +
 			" ORDER BY samples.id"
 			" LIMIT " + str(glb_chunk_sz))
-		self.fetcher = SQLFetcher(glb, sql, BranchDataPrep, self.AddSample)
+		if pyside_version_1 and sys.version_info[0] == 3:
+			prep = BranchDataPrepWA
+		else:
+			prep = BranchDataPrep
+		self.fetcher = SQLFetcher(glb, sql, prep, self.AddSample)
 		self.fetcher.done.connect(self.Update)
 		self.fetcher.Fetch(glb_chunk_sz)
 
@@ -2079,14 +2097,6 @@ def IsSelectable(db, table, sql = ""):
 		return False
 	return True
 
-# SQL data preparation
-
-def SQLTableDataPrep(query, count):
-	data = []
-	for i in xrange(count):
-		data.append(query.value(i))
-	return data
-
 # SQL table data model item
 
 class SQLTableItem():
@@ -2110,7 +2120,7 @@ class SQLTableModel(TableModel):
 		self.more = True
 		self.populated = 0
 		self.column_headers = column_headers
-		self.fetcher = SQLFetcher(glb, sql, lambda x, y=len(column_headers): SQLTableDataPrep(x, y), self.AddSample)
+		self.fetcher = SQLFetcher(glb, sql, lambda x, y=len(column_headers): self.SQLTableDataPrep(x, y), self.AddSample)
 		self.fetcher.done.connect(self.Update)
 		self.fetcher.Fetch(glb_chunk_sz)
 
@@ -2154,6 +2164,12 @@ class SQLTableModel(TableModel):
 	def columnHeader(self, column):
 		return self.column_headers[column]
 
+	def SQLTableDataPrep(self, query, count):
+		data = []
+		for i in xrange(count):
+			data.append(query.value(i))
+		return data
+
 # SQL automatic table data model
 
 class SQLAutoTableModel(SQLTableModel):
@@ -2182,8 +2198,32 @@ class SQLAutoTableModel(SQLTableModel):
 			QueryExec(query, "SELECT column_name FROM information_schema.columns WHERE table_schema = '" + schema + "' and table_name = '" + select_table_name + "'")
 			while query.next():
 				column_headers.append(query.value(0))
+		if pyside_version_1 and sys.version_info[0] == 3:
+			if table_name == "samples_view":
+				self.SQLTableDataPrep = self.samples_view_DataPrep
+			if table_name == "samples":
+				self.SQLTableDataPrep = self.samples_DataPrep
 		super(SQLAutoTableModel, self).__init__(glb, sql, column_headers, parent)
 
+	def samples_view_DataPrep(self, query, count):
+		data = []
+		data.append(query.value(0))
+		# Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string
+		data.append("{:>19}".format(query.value(1)))
+		for i in xrange(2, count):
+			data.append(query.value(i))
+		return data
+
+	def samples_DataPrep(self, query, count):
+		data = []
+		for i in xrange(9):
+			data.append(query.value(i))
+		# Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string
+		data.append("{:>19}".format(query.value(9)))
+		for i in xrange(10, count):
+			data.append(query.value(i))
+		return data
+
 # Base class for custom ResizeColumnsToContents
 
 class ResizeColumnsToContentsBase(QObject):
@@ -2868,9 +2908,13 @@ class LibXED():
 		ok = self.xed_format_context(2, inst.xedp, inst.bufferp, sizeof(inst.buffer), ip, 0, 0)
 		if not ok:
 			return 0, ""
+		if sys.version_info[0] == 2:
+			result = inst.buffer.value
+		else:
+			result = inst.buffer.value.decode()
 		# Return instruction length and the disassembled instruction text
 		# For now, assume the length is in byte 166
-		return inst.xedd[166], inst.buffer.value
+		return inst.xedd[166], result
 
 def TryOpen(file_name):
 	try:
@@ -2886,9 +2930,14 @@ def Is64Bit(f):
 	header = f.read(7)
 	f.seek(pos)
 	magic = header[0:4]
-	eclass = ord(header[4])
-	encoding = ord(header[5])
-	version = ord(header[6])
+	if sys.version_info[0] == 2:
+		eclass = ord(header[4])
+		encoding = ord(header[5])
+		version = ord(header[6])
+	else:
+		eclass = header[4]
+		encoding = header[5]
+		version = header[6]
 	if magic == chr(127) + "ELF" and eclass > 0 and eclass < 3 and encoding > 0 and encoding < 3 and version == 1:
 		result = True if eclass == 2 else False
 	return result
diff --git a/tools/perf/trace/beauty/mmap_flags.sh b/tools/perf/trace/beauty/mmap_flags.sh
index 32bac9c0d694..5f5eefcb3c74 100755
--- a/tools/perf/trace/beauty/mmap_flags.sh
+++ b/tools/perf/trace/beauty/mmap_flags.sh
@@ -1,15 +1,18 @@
 #!/bin/sh
 # SPDX-License-Identifier: LGPL-2.1
 
-if [ $# -ne 2 ] ; then
+if [ $# -ne 3 ] ; then
 	[ $# -eq 1 ] && hostarch=$1 || hostarch=`uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/`
+	linux_header_dir=tools/include/uapi/linux
 	header_dir=tools/include/uapi/asm-generic
 	arch_header_dir=tools/arch/${hostarch}/include/uapi/asm
 else
-	header_dir=$1
-	arch_header_dir=$2
+	linux_header_dir=$1
+	header_dir=$2
+	arch_header_dir=$3
 fi
 
+linux_mman=${linux_header_dir}/mman.h
 arch_mman=${arch_header_dir}/mman.h
 
 # those in egrep -vw are flags, we want just the bits
@@ -20,6 +23,11 @@ egrep -q $regex ${arch_mman} && \
 (egrep $regex ${arch_mman} | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
+egrep -q $regex ${linux_mman} && \
+(egrep $regex ${linux_mman} | \
+	egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
 ([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.*' ${arch_mman}) &&
 (egrep $regex ${header_dir}/mman-common.h | \
 	egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index ba4c623cd8de..39fe21e1cf93 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -387,6 +387,7 @@ cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder,
 		break;
 	case OCSD_INSTR_ISB:
 	case OCSD_INSTR_DSB_DMB:
+	case OCSD_INSTR_WFI_WFE:
 	case OCSD_INSTR_OTHER:
 	default:
 		packet->last_instr_taken_branch = false;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index ec78e93085de..6689378ee577 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -231,35 +231,6 @@ void perf_evlist__set_leader(struct perf_evlist *evlist)
 	}
 }
 
-void perf_event_attr__set_max_precise_ip(struct perf_event_attr *pattr)
-{
-	struct perf_event_attr attr = {
-		.type		= PERF_TYPE_HARDWARE,
-		.config		= PERF_COUNT_HW_CPU_CYCLES,
-		.exclude_kernel	= 1,
-		.precise_ip	= 3,
-	};
-
-	event_attr_init(&attr);
-
-	/*
-	 * Unnamed union member, not supported as struct member named
-	 * initializer in older compilers such as gcc 4.4.7
-	 */
-	attr.sample_period = 1;
-
-	while (attr.precise_ip != 0) {
-		int fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
-		if (fd != -1) {
-			close(fd);
-			break;
-		}
-		--attr.precise_ip;
-	}
-
-	pattr->precise_ip = attr.precise_ip;
-}
-
 int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise)
 {
 	struct perf_evsel *evsel = perf_evsel__new_cycles(precise);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index dcb68f34d2cd..6a94785b9100 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -315,8 +315,6 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 				     struct perf_evsel *tracking_evsel);
 
-void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr);
-
 struct perf_evsel *
 perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 7835e05f0c0a..66d066f18b5b 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -295,7 +295,6 @@ struct perf_evsel *perf_evsel__new_cycles(bool precise)
 	if (!precise)
 		goto new_event;
 
-	perf_event_attr__set_max_precise_ip(&attr);
 	/*
 	 * Now let the usual logic to set up the perf_event_attr defaults
 	 * to kick in when we return and before perf_evsel__open() is called.
@@ -305,6 +304,8 @@ new_event:
 	if (evsel == NULL)
 		goto out;
 
+	evsel->precise_max = true;
+
 	/* use asprintf() because free(evsel) assumes name is allocated */
 	if (asprintf(&evsel->name, "cycles%s%s%.*s",
 		     (attr.precise_ip || attr.exclude_kernel) ? ":" : "",
@@ -1083,7 +1084,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	}
 
 	if (evsel->precise_max)
-		perf_event_attr__set_max_precise_ip(attr);
+		attr->precise_ip = 3;
 
 	if (opts->all_user) {
 		attr->exclude_kernel = 1;
@@ -1749,6 +1750,59 @@ static bool ignore_missing_thread(struct perf_evsel *evsel,
 	return true;
 }
 
+static void display_attr(struct perf_event_attr *attr)
+{
+	if (verbose >= 2) {
+		fprintf(stderr, "%.60s\n", graph_dotted_line);
+		fprintf(stderr, "perf_event_attr:\n");
+		perf_event_attr__fprintf(stderr, attr, __open_attr__fprintf, NULL);
+		fprintf(stderr, "%.60s\n", graph_dotted_line);
+	}
+}
+
+static int perf_event_open(struct perf_evsel *evsel,
+			   pid_t pid, int cpu, int group_fd,
+			   unsigned long flags)
+{
+	int precise_ip = evsel->attr.precise_ip;
+	int fd;
+
+	while (1) {
+		pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
+			  pid, cpu, group_fd, flags);
+
+		fd = sys_perf_event_open(&evsel->attr, pid, cpu, group_fd, flags);
+		if (fd >= 0)
+			break;
+
+		/*
+		 * Do quick precise_ip fallback if:
+		 *  - there is precise_ip set in perf_event_attr
+		 *  - maximum precise is requested
+		 *  - sys_perf_event_open failed with ENOTSUP error,
+		 *    which is associated with wrong precise_ip
+		 */
+		if (!precise_ip || !evsel->precise_max || (errno != ENOTSUP))
+			break;
+
+		/*
+		 * We tried all the precise_ip values, and it's
+		 * still failing, so leave it to standard fallback.
+		 */
+		if (!evsel->attr.precise_ip) {
+			evsel->attr.precise_ip = precise_ip;
+			break;
+		}
+
+		pr_debug2("\nsys_perf_event_open failed, error %d\n", -ENOTSUP);
+		evsel->attr.precise_ip--;
+		pr_debug2("decreasing precise_ip by one (%d)\n", evsel->attr.precise_ip);
+		display_attr(&evsel->attr);
+	}
+
+	return fd;
+}
+
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 		     struct thread_map *threads)
 {
@@ -1824,12 +1878,7 @@ retry_sample_id:
 	if (perf_missing_features.sample_id_all)
 		evsel->attr.sample_id_all = 0;
 
-	if (verbose >= 2) {
-		fprintf(stderr, "%.60s\n", graph_dotted_line);
-		fprintf(stderr, "perf_event_attr:\n");
-		perf_event_attr__fprintf(stderr, &evsel->attr, __open_attr__fprintf, NULL);
-		fprintf(stderr, "%.60s\n", graph_dotted_line);
-	}
+	display_attr(&evsel->attr);
 
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 
@@ -1841,13 +1890,10 @@ retry_sample_id:
 
 			group_fd = get_group_fd(evsel, cpu, thread);
 retry_open:
-			pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
-				  pid, cpus->map[cpu], group_fd, flags);
-
 			test_attr__ready();
 
-			fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu],
-						 group_fd, flags);
+			fd = perf_event_open(evsel, pid, cpus->map[cpu],
+					     group_fd, flags);
 
 			FD(evsel, cpu, thread) = fd;
 
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 6e03db142091..872fab163585 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -251,19 +251,15 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params)
 		if (!(decoder->tsc_ctc_ratio_n % decoder->tsc_ctc_ratio_d))
 			decoder->tsc_ctc_mult = decoder->tsc_ctc_ratio_n /
 						decoder->tsc_ctc_ratio_d;
-
-		/*
-		 * Allow for timestamps appearing to backwards because a TSC
-		 * packet has slipped past a MTC packet, so allow 2 MTC ticks
-		 * or ...
-		 */
-		decoder->tsc_slip = multdiv(2 << decoder->mtc_shift,
-					decoder->tsc_ctc_ratio_n,
-					decoder->tsc_ctc_ratio_d);
 	}
-	/* ... or 0x100 paranoia */
-	if (decoder->tsc_slip < 0x100)
-		decoder->tsc_slip = 0x100;
+
+	/*
+	 * A TSC packet can slip past MTC packets so that the timestamp appears
+	 * to go backwards. One estimate is that can be up to about 40 CPU
+	 * cycles, which is certainly less than 0x1000 TSC ticks, but accept
+	 * slippage an order of magnitude more to be on the safe side.
+	 */
+	decoder->tsc_slip = 0x10000;
 
 	intel_pt_log("timestamp: mtc_shift %u\n", decoder->mtc_shift);
 	intel_pt_log("timestamp: tsc_ctc_ratio_n %u\n", decoder->tsc_ctc_ratio_n);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 61959aba7e27..3c520baa198c 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1421,6 +1421,20 @@ static void machine__set_kernel_mmap(struct machine *machine,
 		machine->vmlinux_map->end = ~0ULL;
 }
 
+static void machine__update_kernel_mmap(struct machine *machine,
+				     u64 start, u64 end)
+{
+	struct map *map = machine__kernel_map(machine);
+
+	map__get(map);
+	map_groups__remove(&machine->kmaps, map);
+
+	machine__set_kernel_mmap(machine, start, end);
+
+	map_groups__insert(&machine->kmaps, map);
+	map__put(map);
+}
+
 int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
@@ -1453,17 +1467,11 @@ int machine__create_kernel_maps(struct machine *machine)
 			goto out_put;
 		}
 
-		/* we have a real start address now, so re-order the kmaps */
-		map = machine__kernel_map(machine);
-
-		map__get(map);
-		map_groups__remove(&machine->kmaps, map);
-
-		/* assume it's the last in the kmaps */
-		machine__set_kernel_mmap(machine, addr, ~0ULL);
-
-		map_groups__insert(&machine->kmaps, map);
-		map__put(map);
+		/*
+		 * we have a real start address now, so re-order the kmaps
+		 * assume it's the last in the kmaps
+		 */
+		machine__update_kernel_mmap(machine, addr, ~0ULL);
 	}
 
 	if (machine__create_extra_kernel_maps(machine, kernel))
@@ -1599,7 +1607,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		if (strstr(kernel->long_name, "vmlinux"))
 			dso__set_short_name(kernel, "[kernel.vmlinux]", false);
 
-		machine__set_kernel_mmap(machine, event->mmap.start,
+		machine__update_kernel_mmap(machine, event->mmap.start,
 					 event->mmap.start + event->mmap.len);
 
 		/*
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 6199a3174ab9..e0429f4ef335 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -732,10 +732,20 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
 
 		if (!is_arm_pmu_core(name)) {
 			pname = pe->pmu ? pe->pmu : "cpu";
+
+			/*
+			 * uncore alias may be from different PMU
+			 * with common prefix
+			 */
+			if (pmu_is_uncore(name) &&
+			    !strncmp(pname, name, strlen(pname)))
+				goto new_alias;
+
 			if (strcmp(pname, name))
 				continue;
 		}
 
+new_alias:
 		/* need type casts to override 'const' */
 		__perf_pmu__new_alias(head, NULL, (char *)pe->name,
 				(char *)pe->desc, (char *)pe->event,
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index c3fad065c89c..c7727be9719f 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -44,6 +44,7 @@
 #include <cpuid.h>
 #include <linux/capability.h>
 #include <errno.h>
+#include <math.h>
 
 char *proc_stat = "/proc/stat";
 FILE *outf;
@@ -63,7 +64,6 @@ unsigned int dump_only;
 unsigned int do_snb_cstates;
 unsigned int do_knl_cstates;
 unsigned int do_slm_cstates;
-unsigned int do_cnl_cstates;
 unsigned int use_c1_residency_msr;
 unsigned int has_aperf;
 unsigned int has_epb;
@@ -141,9 +141,21 @@ unsigned int first_counter_read = 1;
 
 #define RAPL_CORES_ENERGY_STATUS	(1 << 9)
 					/* 0x639 MSR_PP0_ENERGY_STATUS */
+#define RAPL_PER_CORE_ENERGY	(1 << 10)
+					/* Indicates cores energy collection is per-core,
+					 * not per-package. */
+#define RAPL_AMD_F17H		(1 << 11)
+					/* 0xc0010299 MSR_RAPL_PWR_UNIT */
+					/* 0xc001029a MSR_CORE_ENERGY_STAT */
+					/* 0xc001029b MSR_PKG_ENERGY_STAT */
 #define RAPL_CORES (RAPL_CORES_ENERGY_STATUS | RAPL_CORES_POWER_LIMIT)
 #define	TJMAX_DEFAULT	100
 
+/* MSRs that are not yet in the kernel-provided header. */
+#define MSR_RAPL_PWR_UNIT	0xc0010299
+#define MSR_CORE_ENERGY_STAT	0xc001029a
+#define MSR_PKG_ENERGY_STAT	0xc001029b
+
 #define MAX(a, b) ((a) > (b) ? (a) : (b))
 
 /*
@@ -187,6 +199,7 @@ struct core_data {
 	unsigned long long c7;
 	unsigned long long mc6_us;	/* duplicate as per-core for now, even though per module */
 	unsigned int core_temp_c;
+	unsigned int core_energy;	/* MSR_CORE_ENERGY_STAT */
 	unsigned int core_id;
 	unsigned long long counter[MAX_ADDED_COUNTERS];
 } *core_even, *core_odd;
@@ -273,6 +286,7 @@ struct system_summary {
 
 struct cpu_topology {
 	int physical_package_id;
+	int die_id;
 	int logical_cpu_id;
 	int physical_node_id;
 	int logical_node_id;	/* 0-based count within the package */
@@ -283,6 +297,7 @@ struct cpu_topology {
 
 struct topo_params {
 	int num_packages;
+	int num_die;
 	int num_cpus;
 	int num_cores;
 	int max_cpu_num;
@@ -314,9 +329,8 @@ int for_all_cpus(int (func)(struct thread_data *, struct core_data *, struct pkg
 	int retval, pkg_no, core_no, thread_no, node_no;
 
 	for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) {
-		for (core_no = 0; core_no < topo.cores_per_node; ++core_no) {
-			for (node_no = 0; node_no < topo.nodes_per_pkg;
-			     node_no++) {
+		for (node_no = 0; node_no < topo.nodes_per_pkg; node_no++) {
+			for (core_no = 0; core_no < topo.cores_per_node; ++core_no) {
 				for (thread_no = 0; thread_no <
 					topo.threads_per_core; ++thread_no) {
 					struct thread_data *t;
@@ -442,6 +456,7 @@ struct msr_counter bic[] = {
 	{ 0x0, "CPU" },
 	{ 0x0, "APIC" },
 	{ 0x0, "X2APIC" },
+	{ 0x0, "Die" },
 };
 
 #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
@@ -495,6 +510,7 @@ struct msr_counter bic[] = {
 #define	BIC_CPU		(1ULL << 47)
 #define	BIC_APIC	(1ULL << 48)
 #define	BIC_X2APIC	(1ULL << 49)
+#define	BIC_Die		(1ULL << 50)
 
 #define BIC_DISABLED_BY_DEFAULT	(BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC)
 
@@ -621,6 +637,8 @@ void print_header(char *delim)
 		outp += sprintf(outp, "%sTime_Of_Day_Seconds", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Package))
 		outp += sprintf(outp, "%sPackage", (printed++ ? delim : ""));
+	if (DO_BIC(BIC_Die))
+		outp += sprintf(outp, "%sDie", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Node))
 		outp += sprintf(outp, "%sNode", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Core))
@@ -667,7 +685,7 @@ void print_header(char *delim)
 
 	if (DO_BIC(BIC_CPU_c1))
 		outp += sprintf(outp, "%sCPU%%c1", (printed++ ? delim : ""));
-	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates)
+	if (DO_BIC(BIC_CPU_c3))
 		outp += sprintf(outp, "%sCPU%%c3", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_CPU_c6))
 		outp += sprintf(outp, "%sCPU%%c6", (printed++ ? delim : ""));
@@ -680,6 +698,14 @@ void print_header(char *delim)
 	if (DO_BIC(BIC_CoreTmp))
 		outp += sprintf(outp, "%sCoreTmp", (printed++ ? delim : ""));
 
+	if (do_rapl && !rapl_joules) {
+		if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY))
+			outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : ""));
+	} else if (do_rapl && rapl_joules) {
+		if (DO_BIC(BIC_Cor_J) && (do_rapl & RAPL_PER_CORE_ENERGY))
+			outp += sprintf(outp, "%sCor_J", (printed++ ? delim : ""));
+	}
+
 	for (mp = sys.cp; mp; mp = mp->next) {
 		if (mp->format == FORMAT_RAW) {
 			if (mp->width == 64)
@@ -734,7 +760,7 @@ void print_header(char *delim)
 	if (do_rapl && !rapl_joules) {
 		if (DO_BIC(BIC_PkgWatt))
 			outp += sprintf(outp, "%sPkgWatt", (printed++ ? delim : ""));
-		if (DO_BIC(BIC_CorWatt))
+		if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY))
 			outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_GFXWatt))
 			outp += sprintf(outp, "%sGFXWatt", (printed++ ? delim : ""));
@@ -747,7 +773,7 @@ void print_header(char *delim)
 	} else if (do_rapl && rapl_joules) {
 		if (DO_BIC(BIC_Pkg_J))
 			outp += sprintf(outp, "%sPkg_J", (printed++ ? delim : ""));
-		if (DO_BIC(BIC_Cor_J))
+		if (DO_BIC(BIC_Cor_J) && !(do_rapl & RAPL_PER_CORE_ENERGY))
 			outp += sprintf(outp, "%sCor_J", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_GFX_J))
 			outp += sprintf(outp, "%sGFX_J", (printed++ ? delim : ""));
@@ -808,6 +834,7 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "c6: %016llX\n", c->c6);
 		outp += sprintf(outp, "c7: %016llX\n", c->c7);
 		outp += sprintf(outp, "DTS: %dC\n", c->core_temp_c);
+		outp += sprintf(outp, "Joules: %0X\n", c->core_energy);
 
 		for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 			outp += sprintf(outp, "cADDED [%d] msr0x%x: %08llX\n",
@@ -904,6 +931,8 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (t == &average.threads) {
 		if (DO_BIC(BIC_Package))
 			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
+		if (DO_BIC(BIC_Die))
+			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_Node))
 			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_Core))
@@ -921,6 +950,12 @@ int format_counters(struct thread_data *t, struct core_data *c,
 			else
 				outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 		}
+		if (DO_BIC(BIC_Die)) {
+			if (c)
+				outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), cpus[t->cpu_id].die_id);
+			else
+				outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
+		}
 		if (DO_BIC(BIC_Node)) {
 			if (t)
 				outp += sprintf(outp, "%s%d",
@@ -1003,7 +1038,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		goto done;
 
-	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates)
+	if (DO_BIC(BIC_CPU_c3))
 		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c3/tsc);
 	if (DO_BIC(BIC_CPU_c6))
 		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c6/tsc);
@@ -1033,6 +1068,20 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		}
 	}
 
+	/*
+	 * If measurement interval exceeds minimum RAPL Joule Counter range,
+	 * indicate that results are suspect by printing "**" in fraction place.
+	 */
+	if (interval_float < rapl_joule_counter_range)
+		fmt8 = "%s%.2f";
+	else
+		fmt8 = "%6.0f**";
+
+	if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY))
+		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float);
+	if (DO_BIC(BIC_Cor_J) && (do_rapl & RAPL_PER_CORE_ENERGY))
+		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units);
+
 	/* print per-package data only for 1st core in package */
 	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
 		goto done;
@@ -1085,18 +1134,9 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (DO_BIC(BIC_SYS_LPI))
 		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->sys_lpi / 1000000.0 / interval_float);
 
-	/*
- 	 * If measurement interval exceeds minimum RAPL Joule Counter range,
- 	 * indicate that results are suspect by printing "**" in fraction place.
- 	 */
-	if (interval_float < rapl_joule_counter_range)
-		fmt8 = "%s%.2f";
-	else
-		fmt8 = "%6.0f**";
-
 	if (DO_BIC(BIC_PkgWatt))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units / interval_float);
-	if (DO_BIC(BIC_CorWatt))
+	if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units / interval_float);
 	if (DO_BIC(BIC_GFXWatt))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units / interval_float);
@@ -1104,7 +1144,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_dram * rapl_dram_energy_units / interval_float);
 	if (DO_BIC(BIC_Pkg_J))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units);
-	if (DO_BIC(BIC_Cor_J))
+	if (DO_BIC(BIC_Cor_J) && !(do_rapl & RAPL_PER_CORE_ENERGY))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units);
 	if (DO_BIC(BIC_GFX_J))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units);
@@ -1249,6 +1289,8 @@ delta_core(struct core_data *new, struct core_data *old)
 	old->core_temp_c = new->core_temp_c;
 	old->mc6_us = new->mc6_us - old->mc6_us;
 
+	DELTA_WRAP32(new->core_energy, old->core_energy);
+
 	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
 			old->counter[i] = new->counter[i];
@@ -1391,6 +1433,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	c->c7 = 0;
 	c->mc6_us = 0;
 	c->core_temp_c = 0;
+	c->core_energy = 0;
 
 	p->pkg_wtd_core_c0 = 0;
 	p->pkg_any_core_c0 = 0;
@@ -1473,6 +1516,8 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 
 	average.cores.core_temp_c = MAX(average.cores.core_temp_c, c->core_temp_c);
 
+	average.cores.core_energy += c->core_energy;
+
 	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
 			continue;
@@ -1818,7 +1863,7 @@ retry:
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		goto done;
 
-	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates) {
+	if (DO_BIC(BIC_CPU_c3)) {
 		if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3))
 			return -6;
 	}
@@ -1845,6 +1890,12 @@ retry:
 		c->core_temp_c = tcc_activation_temp - ((msr >> 16) & 0x7F);
 	}
 
+	if (do_rapl & RAPL_AMD_F17H) {
+		if (get_msr(cpu, MSR_CORE_ENERGY_STAT, &msr))
+			return -14;
+		c->core_energy = msr & 0xFFFFFFFF;
+	}
+
 	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 		if (get_mp(cpu, mp, &c->counter[i]))
 			return -10;
@@ -1934,6 +1985,11 @@ retry:
 			return -16;
 		p->rapl_dram_perf_status = msr & 0xFFFFFFFF;
 	}
+	if (do_rapl & RAPL_AMD_F17H) {
+		if (get_msr(cpu, MSR_PKG_ENERGY_STAT, &msr))
+			return -13;
+		p->energy_pkg = msr & 0xFFFFFFFF;
+	}
 	if (DO_BIC(BIC_PkgTmp)) {
 		if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr))
 			return -17;
@@ -2456,6 +2512,8 @@ void free_all_buffers(void)
 
 /*
  * Parse a file containing a single int.
+ * Return 0 if file can not be opened
+ * Exit if file can be opened, but can not be parsed
  */
 int parse_int_file(const char *fmt, ...)
 {
@@ -2467,7 +2525,9 @@ int parse_int_file(const char *fmt, ...)
 	va_start(args, fmt);
 	vsnprintf(path, sizeof(path), fmt, args);
 	va_end(args);
-	filep = fopen_or_die(path, "r");
+	filep = fopen(path, "r");
+	if (!filep)
+		return 0;
 	if (fscanf(filep, "%d", &value) != 1)
 		err(1, "%s: failed to parse number from file", path);
 	fclose(filep);
@@ -2488,6 +2548,11 @@ int get_physical_package_id(int cpu)
 	return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/physical_package_id", cpu);
 }
 
+int get_die_id(int cpu)
+{
+	return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/die_id", cpu);
+}
+
 int get_core_id(int cpu)
 {
 	return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/core_id", cpu);
@@ -2578,7 +2643,8 @@ int get_thread_siblings(struct cpu_topology *thiscpu)
 	filep = fopen_or_die(path, "r");
 	do {
 		offset -= BITMASK_SIZE;
-		fscanf(filep, "%lx%c", &map, &character);
+		if (fscanf(filep, "%lx%c", &map, &character) != 2)
+			err(1, "%s: failed to parse file", path);
 		for (shift = 0; shift < BITMASK_SIZE; shift++) {
 			if ((map >> shift) & 0x1) {
 				so = shift + offset;
@@ -2855,8 +2921,11 @@ int snapshot_cpu_lpi_us(void)
 	fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", "r");
 
 	retval = fscanf(fp, "%lld", &cpuidle_cur_cpu_lpi_us);
-	if (retval != 1)
-		err(1, "CPU LPI");
+	if (retval != 1) {
+		fprintf(stderr, "Disabling Low Power Idle CPU output\n");
+		BIC_NOT_PRESENT(BIC_CPU_LPI);
+		return -1;
+	}
 
 	fclose(fp);
 
@@ -2878,9 +2947,11 @@ int snapshot_sys_lpi_us(void)
 	fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us", "r");
 
 	retval = fscanf(fp, "%lld", &cpuidle_cur_sys_lpi_us);
-	if (retval != 1)
-		err(1, "SYS LPI");
-
+	if (retval != 1) {
+		fprintf(stderr, "Disabling Low Power Idle System output\n");
+		BIC_NOT_PRESENT(BIC_SYS_LPI);
+		return -1;
+	}
 	fclose(fp);
 
 	return 0;
@@ -3410,14 +3481,14 @@ dump_sysfs_cstate_config(void)
 		input = fopen(path, "r");
 		if (input == NULL)
 			continue;
-		fgets(name_buf, sizeof(name_buf), input);
+		if (!fgets(name_buf, sizeof(name_buf), input))
+			err(1, "%s: failed to read file", path);
 
 		 /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
 		sp = strchr(name_buf, '-');
 		if (!sp)
 			sp = strchrnul(name_buf, '\n');
 		*sp = '\0';
-
 		fclose(input);
 
 		sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/desc",
@@ -3425,7 +3496,8 @@ dump_sysfs_cstate_config(void)
 		input = fopen(path, "r");
 		if (input == NULL)
 			continue;
-		fgets(desc, sizeof(desc), input);
+		if (!fgets(desc, sizeof(desc), input))
+			err(1, "%s: failed to read file", path);
 
 		fprintf(outf, "cpu%d: %s: %s", base_cpu, name_buf, desc);
 		fclose(input);
@@ -3444,20 +3516,22 @@ dump_sysfs_pstate_config(void)
 			base_cpu);
 	input = fopen(path, "r");
 	if (input == NULL) {
-		fprintf(stderr, "NSFOD %s\n", path);
+		fprintf(outf, "NSFOD %s\n", path);
 		return;
 	}
-	fgets(driver_buf, sizeof(driver_buf), input);
+	if (!fgets(driver_buf, sizeof(driver_buf), input))
+		err(1, "%s: failed to read file", path);
 	fclose(input);
 
 	sprintf(path, "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_governor",
 			base_cpu);
 	input = fopen(path, "r");
 	if (input == NULL) {
-		fprintf(stderr, "NSFOD %s\n", path);
+		fprintf(outf, "NSFOD %s\n", path);
 		return;
 	}
-	fgets(governor_buf, sizeof(governor_buf), input);
+	if (!fgets(governor_buf, sizeof(governor_buf), input))
+		err(1, "%s: failed to read file", path);
 	fclose(input);
 
 	fprintf(outf, "cpu%d: cpufreq driver: %s", base_cpu, driver_buf);
@@ -3466,7 +3540,8 @@ dump_sysfs_pstate_config(void)
 	sprintf(path, "/sys/devices/system/cpu/cpufreq/boost");
 	input = fopen(path, "r");
 	if (input != NULL) {
-		fscanf(input, "%d", &turbo);
+		if (fscanf(input, "%d", &turbo) != 1)
+			err(1, "%s: failed to parse number from file", path);
 		fprintf(outf, "cpufreq boost: %d\n", turbo);
 		fclose(input);
 	}
@@ -3474,7 +3549,8 @@ dump_sysfs_pstate_config(void)
 	sprintf(path, "/sys/devices/system/cpu/intel_pstate/no_turbo");
 	input = fopen(path, "r");
 	if (input != NULL) {
-		fscanf(input, "%d", &turbo);
+		if (fscanf(input, "%d", &turbo) != 1)
+			err(1, "%s: failed to parse number from file", path);
 		fprintf(outf, "cpufreq intel_pstate no_turbo: %d\n", turbo);
 		fclose(input);
 	}
@@ -3718,7 +3794,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 #define	RAPL_POWER_GRANULARITY	0x7FFF	/* 15 bit power granularity */
 #define	RAPL_TIME_GRANULARITY	0x3F /* 6 bit time granularity */
 
-double get_tdp(unsigned int model)
+double get_tdp_intel(unsigned int model)
 {
 	unsigned long long msr;
 
@@ -3735,6 +3811,16 @@ double get_tdp(unsigned int model)
 	}
 }
 
+double get_tdp_amd(unsigned int family)
+{
+	switch (family) {
+	case 0x17:
+	default:
+		/* This is the max stock TDP of HEDT/Server Fam17h chips */
+		return 250.0;
+	}
+}
+
 /*
  * rapl_dram_energy_units_probe()
  * Energy units are either hard-coded, or come from RAPL Energy Unit MSR.
@@ -3754,21 +3840,12 @@ rapl_dram_energy_units_probe(int  model, double rapl_energy_units)
 	}
 }
 
-
-/*
- * rapl_probe()
- *
- * sets do_rapl, rapl_power_units, rapl_energy_units, rapl_time_units
- */
-void rapl_probe(unsigned int family, unsigned int model)
+void rapl_probe_intel(unsigned int family, unsigned int model)
 {
 	unsigned long long msr;
 	unsigned int time_unit;
 	double tdp;
 
-	if (!genuine_intel)
-		return;
-
 	if (family != 6)
 		return;
 
@@ -3892,13 +3969,69 @@ void rapl_probe(unsigned int family, unsigned int model)
 
 	rapl_time_units = 1.0 / (1 << (time_unit));
 
-	tdp = get_tdp(model);
+	tdp = get_tdp_intel(model);
 
 	rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
 	if (!quiet)
 		fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp);
+}
 
-	return;
+void rapl_probe_amd(unsigned int family, unsigned int model)
+{
+	unsigned long long msr;
+	unsigned int eax, ebx, ecx, edx;
+	unsigned int has_rapl = 0;
+	double tdp;
+
+	if (max_extended_level >= 0x80000007) {
+		__cpuid(0x80000007, eax, ebx, ecx, edx);
+		/* RAPL (Fam 17h) */
+		has_rapl = edx & (1 << 14);
+	}
+
+	if (!has_rapl)
+		return;
+
+	switch (family) {
+	case 0x17: /* Zen, Zen+ */
+		do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY;
+		if (rapl_joules) {
+			BIC_PRESENT(BIC_Pkg_J);
+			BIC_PRESENT(BIC_Cor_J);
+		} else {
+			BIC_PRESENT(BIC_PkgWatt);
+			BIC_PRESENT(BIC_CorWatt);
+		}
+		break;
+	default:
+		return;
+	}
+
+	if (get_msr(base_cpu, MSR_RAPL_PWR_UNIT, &msr))
+		return;
+
+	rapl_time_units = ldexp(1.0, -(msr >> 16 & 0xf));
+	rapl_energy_units = ldexp(1.0, -(msr >> 8 & 0x1f));
+	rapl_power_units = ldexp(1.0, -(msr & 0xf));
+
+	tdp = get_tdp_amd(model);
+
+	rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
+	if (!quiet)
+		fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp);
+}
+
+/*
+ * rapl_probe()
+ *
+ * sets do_rapl, rapl_power_units, rapl_energy_units, rapl_time_units
+ */
+void rapl_probe(unsigned int family, unsigned int model)
+{
+	if (genuine_intel)
+		rapl_probe_intel(family, model);
+	if (authentic_amd)
+		rapl_probe_amd(family, model);
 }
 
 void perf_limit_reasons_probe(unsigned int family, unsigned int model)
@@ -4003,6 +4136,7 @@ void print_power_limit_msr(int cpu, unsigned long long msr, char *label)
 int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 {
 	unsigned long long msr;
+	const char *msr_name;
 	int cpu;
 
 	if (!do_rapl)
@@ -4018,10 +4152,17 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		return -1;
 	}
 
-	if (get_msr(cpu, MSR_RAPL_POWER_UNIT, &msr))
-		return -1;
+	if (do_rapl & RAPL_AMD_F17H) {
+		msr_name = "MSR_RAPL_PWR_UNIT";
+		if (get_msr(cpu, MSR_RAPL_PWR_UNIT, &msr))
+			return -1;
+	} else {
+		msr_name = "MSR_RAPL_POWER_UNIT";
+		if (get_msr(cpu, MSR_RAPL_POWER_UNIT, &msr))
+			return -1;
+	}
 
-	fprintf(outf, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx (%f Watts, %f Joules, %f sec.)\n", cpu, msr,
+	fprintf(outf, "cpu%d: %s: 0x%08llx (%f Watts, %f Joules, %f sec.)\n", cpu, msr_name, msr,
 		rapl_power_units, rapl_energy_units, rapl_time_units);
 
 	if (do_rapl & RAPL_PKG_POWER_INFO) {
@@ -4451,6 +4592,9 @@ unsigned int intel_model_duplicates(unsigned int model)
 	case INTEL_FAM6_KABYLAKE_MOBILE:
 	case INTEL_FAM6_KABYLAKE_DESKTOP:
 		return INTEL_FAM6_SKYLAKE_MOBILE;
+
+	case INTEL_FAM6_ICELAKE_MOBILE:
+		return INTEL_FAM6_CANNONLAKE_MOBILE;
 	}
 	return model;
 }
@@ -4702,7 +4846,9 @@ void process_cpuid()
 	}
 	do_slm_cstates = is_slm(family, model);
 	do_knl_cstates  = is_knl(family, model);
-	do_cnl_cstates = is_cnl(family, model);
+
+	if (do_slm_cstates || do_knl_cstates || is_cnl(family, model))
+		BIC_NOT_PRESENT(BIC_CPU_c3);
 
 	if (!quiet)
 		decode_misc_pwr_mgmt_msr();
@@ -4769,6 +4915,7 @@ void topology_probe()
 	int i;
 	int max_core_id = 0;
 	int max_package_id = 0;
+	int max_die_id = 0;
 	int max_siblings = 0;
 
 	/* Initialize num_cpus, max_cpu_num */
@@ -4835,6 +4982,11 @@ void topology_probe()
 		if (cpus[i].physical_package_id > max_package_id)
 			max_package_id = cpus[i].physical_package_id;
 
+		/* get die information */
+		cpus[i].die_id = get_die_id(i);
+		if (cpus[i].die_id > max_die_id)
+			max_die_id = cpus[i].die_id;
+
 		/* get numa node information */
 		cpus[i].physical_node_id = get_physical_node_id(&cpus[i]);
 		if (cpus[i].physical_node_id > topo.max_node_num)
@@ -4860,6 +5012,13 @@ void topology_probe()
 	if (!summary_only && topo.cores_per_node > 1)
 		BIC_PRESENT(BIC_Core);
 
+	topo.num_die = max_die_id + 1;
+	if (debug > 1)
+		fprintf(outf, "max_die_id %d, sizing for %d die\n",
+				max_die_id, topo.num_die);
+	if (!summary_only && topo.num_die > 1)
+		BIC_PRESENT(BIC_Die);
+
 	topo.num_packages = max_package_id + 1;
 	if (debug > 1)
 		fprintf(outf, "max_package_id %d, sizing for %d packages\n",
@@ -4884,8 +5043,8 @@ void topology_probe()
 		if (cpu_is_not_present(i))
 			continue;
 		fprintf(outf,
-			"cpu %d pkg %d node %d lnode %d core %d thread %d\n",
-			i, cpus[i].physical_package_id,
+			"cpu %d pkg %d die %d node %d lnode %d core %d thread %d\n",
+			i, cpus[i].physical_package_id, cpus[i].die_id,
 			cpus[i].physical_node_id,
 			cpus[i].logical_node_id,
 			cpus[i].physical_core_id,
@@ -5122,7 +5281,7 @@ int get_and_dump_counters(void)
 }
 
 void print_version() {
-	fprintf(outf, "turbostat version 18.07.27"
+	fprintf(outf, "turbostat version 19.03.20"
 		" - Len Brown <lenb@kernel.org>\n");
 }
 
@@ -5319,7 +5478,8 @@ void probe_sysfs(void)
 		input = fopen(path, "r");
 		if (input == NULL)
 			continue;
-		fgets(name_buf, sizeof(name_buf), input);
+		if (!fgets(name_buf, sizeof(name_buf), input))
+			err(1, "%s: failed to read file", path);
 
 		 /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
 		sp = strchr(name_buf, '-');
@@ -5346,7 +5506,8 @@ void probe_sysfs(void)
 		input = fopen(path, "r");
 		if (input == NULL)
 			continue;
-		fgets(name_buf, sizeof(name_buf), input);
+		if (!fgets(name_buf, sizeof(name_buf), input))
+			err(1, "%s: failed to read file", path);
 		 /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
 		sp = strchr(name_buf, '-');
 		if (!sp)
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index c9433a496d54..c81fc350f7ad 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -180,6 +180,8 @@ static struct bpf_sock *(*bpf_sk_fullsock)(struct bpf_sock *sk) =
 	(void *) BPF_FUNC_sk_fullsock;
 static struct bpf_tcp_sock *(*bpf_tcp_sock)(struct bpf_sock *sk) =
 	(void *) BPF_FUNC_tcp_sock;
+static struct bpf_sock *(*bpf_get_listener_sock)(struct bpf_sock *sk) =
+	(void *) BPF_FUNC_get_listener_sock;
 static int (*bpf_skb_ecn_set_ce)(void *ctx) =
 	(void *) BPF_FUNC_skb_ecn_set_ce;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
index bcbd928c96ab..fc818bc1d729 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
@@ -39,6 +39,58 @@ static struct bpf_flow_keys pkt_v6_flow_keys = {
 	.n_proto = __bpf_constant_htons(ETH_P_IPV6),
 };
 
+#define VLAN_HLEN	4
+
+static struct {
+	struct ethhdr eth;
+	__u16 vlan_tci;
+	__u16 vlan_proto;
+	struct iphdr iph;
+	struct tcphdr tcp;
+} __packed pkt_vlan_v4 = {
+	.eth.h_proto = __bpf_constant_htons(ETH_P_8021Q),
+	.vlan_proto = __bpf_constant_htons(ETH_P_IP),
+	.iph.ihl = 5,
+	.iph.protocol = IPPROTO_TCP,
+	.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+	.tcp.urg_ptr = 123,
+	.tcp.doff = 5,
+};
+
+static struct bpf_flow_keys pkt_vlan_v4_flow_keys = {
+	.nhoff = VLAN_HLEN,
+	.thoff = VLAN_HLEN + sizeof(struct iphdr),
+	.addr_proto = ETH_P_IP,
+	.ip_proto = IPPROTO_TCP,
+	.n_proto = __bpf_constant_htons(ETH_P_IP),
+};
+
+static struct {
+	struct ethhdr eth;
+	__u16 vlan_tci;
+	__u16 vlan_proto;
+	__u16 vlan_tci2;
+	__u16 vlan_proto2;
+	struct ipv6hdr iph;
+	struct tcphdr tcp;
+} __packed pkt_vlan_v6 = {
+	.eth.h_proto = __bpf_constant_htons(ETH_P_8021AD),
+	.vlan_proto = __bpf_constant_htons(ETH_P_8021Q),
+	.vlan_proto2 = __bpf_constant_htons(ETH_P_IPV6),
+	.iph.nexthdr = IPPROTO_TCP,
+	.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+	.tcp.urg_ptr = 123,
+	.tcp.doff = 5,
+};
+
+static struct bpf_flow_keys pkt_vlan_v6_flow_keys = {
+	.nhoff = VLAN_HLEN * 2,
+	.thoff = VLAN_HLEN * 2 + sizeof(struct ipv6hdr),
+	.addr_proto = ETH_P_IPV6,
+	.ip_proto = IPPROTO_TCP,
+	.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+};
+
 void test_flow_dissector(void)
 {
 	struct bpf_flow_keys flow_keys;
@@ -68,5 +120,21 @@ void test_flow_dissector(void)
 	      err, errno, retval, duration, size, sizeof(flow_keys));
 	CHECK_FLOW_KEYS("ipv6_flow_keys", flow_keys, pkt_v6_flow_keys);
 
+	err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v4, sizeof(pkt_vlan_v4),
+				&flow_keys, &size, &retval, &duration);
+	CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv4",
+	      "err %d errno %d retval %d duration %d size %u/%lu\n",
+	      err, errno, retval, duration, size, sizeof(flow_keys));
+	CHECK_FLOW_KEYS("vlan_ipv4_flow_keys", flow_keys,
+			pkt_vlan_v4_flow_keys);
+
+	err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v6, sizeof(pkt_vlan_v6),
+				&flow_keys, &size, &retval, &duration);
+	CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv6",
+	      "err %d errno %d retval %d duration %d size %u/%lu\n",
+	      err, errno, retval, duration, size, sizeof(flow_keys));
+	CHECK_FLOW_KEYS("vlan_ipv6_flow_keys", flow_keys,
+			pkt_vlan_v6_flow_keys);
+
 	bpf_object__close(obj);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/map_lock.c b/tools/testing/selftests/bpf/prog_tests/map_lock.c
index 90f8a206340a..ee99368c595c 100644
--- a/tools/testing/selftests/bpf/prog_tests/map_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/map_lock.c
@@ -37,7 +37,7 @@ void test_map_lock(void)
 	const char *file = "./test_map_lock.o";
 	int prog_fd, map_fd[2], vars[17] = {};
 	pthread_t thread_id[6];
-	struct bpf_object *obj;
+	struct bpf_object *obj = NULL;
 	int err = 0, key = 0, i;
 	void *ret;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/spinlock.c b/tools/testing/selftests/bpf/prog_tests/spinlock.c
index 9a573a9675d7..114ebe6a438e 100644
--- a/tools/testing/selftests/bpf/prog_tests/spinlock.c
+++ b/tools/testing/selftests/bpf/prog_tests/spinlock.c
@@ -5,7 +5,7 @@ void test_spinlock(void)
 {
 	const char *file = "./test_spin_lock.o";
 	pthread_t thread_id[4];
-	struct bpf_object *obj;
+	struct bpf_object *obj = NULL;
 	int prog_fd;
 	int err = 0, i;
 	void *ret;
diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c
index 284660f5aa95..75b17cada539 100644
--- a/tools/testing/selftests/bpf/progs/bpf_flow.c
+++ b/tools/testing/selftests/bpf/progs/bpf_flow.c
@@ -92,7 +92,6 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto)
 {
 	struct bpf_flow_keys *keys = skb->flow_keys;
 
-	keys->n_proto = proto;
 	switch (proto) {
 	case bpf_htons(ETH_P_IP):
 		bpf_tail_call(skb, &jmp_table, IP);
@@ -119,10 +118,9 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto)
 SEC("flow_dissector")
 int _dissect(struct __sk_buff *skb)
 {
-	if (!skb->vlan_present)
-		return parse_eth_proto(skb, skb->protocol);
-	else
-		return parse_eth_proto(skb, skb->vlan_proto);
+	struct bpf_flow_keys *keys = skb->flow_keys;
+
+	return parse_eth_proto(skb, keys->n_proto);
 }
 
 /* Parses on IPPROTO_* */
@@ -336,15 +334,9 @@ PROG(VLAN)(struct __sk_buff *skb)
 {
 	struct bpf_flow_keys *keys = skb->flow_keys;
 	struct vlan_hdr *vlan, _vlan;
-	__be16 proto;
-
-	/* Peek back to see if single or double-tagging */
-	if (bpf_skb_load_bytes(skb, keys->thoff - sizeof(proto), &proto,
-			       sizeof(proto)))
-		return BPF_DROP;
 
 	/* Account for double-tagging */
-	if (proto == bpf_htons(ETH_P_8021AD)) {
+	if (keys->n_proto == bpf_htons(ETH_P_8021AD)) {
 		vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan);
 		if (!vlan)
 			return BPF_DROP;
@@ -352,6 +344,7 @@ PROG(VLAN)(struct __sk_buff *skb)
 		if (vlan->h_vlan_encapsulated_proto != bpf_htons(ETH_P_8021Q))
 			return BPF_DROP;
 
+		keys->nhoff += sizeof(*vlan);
 		keys->thoff += sizeof(*vlan);
 	}
 
@@ -359,12 +352,14 @@ PROG(VLAN)(struct __sk_buff *skb)
 	if (!vlan)
 		return BPF_DROP;
 
+	keys->nhoff += sizeof(*vlan);
 	keys->thoff += sizeof(*vlan);
 	/* Only allow 8021AD + 8021Q double tagging and no triple tagging.*/
 	if (vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021AD) ||
 	    vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021Q))
 		return BPF_DROP;
 
+	keys->n_proto = vlan->h_vlan_encapsulated_proto;
 	return parse_eth_proto(skb, vlan->h_vlan_encapsulated_proto);
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
index de1a43e8f610..37328f148538 100644
--- a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
@@ -8,38 +8,51 @@
 #include "bpf_helpers.h"
 #include "bpf_endian.h"
 
-enum bpf_array_idx {
-	SRV_IDX,
-	CLI_IDX,
-	__NR_BPF_ARRAY_IDX,
+enum bpf_addr_array_idx {
+	ADDR_SRV_IDX,
+	ADDR_CLI_IDX,
+	__NR_BPF_ADDR_ARRAY_IDX,
+};
+
+enum bpf_result_array_idx {
+	EGRESS_SRV_IDX,
+	EGRESS_CLI_IDX,
+	INGRESS_LISTEN_IDX,
+	__NR_BPF_RESULT_ARRAY_IDX,
+};
+
+enum bpf_linum_array_idx {
+	EGRESS_LINUM_IDX,
+	INGRESS_LINUM_IDX,
+	__NR_BPF_LINUM_ARRAY_IDX,
 };
 
 struct bpf_map_def SEC("maps") addr_map = {
 	.type = BPF_MAP_TYPE_ARRAY,
 	.key_size = sizeof(__u32),
 	.value_size = sizeof(struct sockaddr_in6),
-	.max_entries = __NR_BPF_ARRAY_IDX,
+	.max_entries = __NR_BPF_ADDR_ARRAY_IDX,
 };
 
 struct bpf_map_def SEC("maps") sock_result_map = {
 	.type = BPF_MAP_TYPE_ARRAY,
 	.key_size = sizeof(__u32),
 	.value_size = sizeof(struct bpf_sock),
-	.max_entries = __NR_BPF_ARRAY_IDX,
+	.max_entries = __NR_BPF_RESULT_ARRAY_IDX,
 };
 
 struct bpf_map_def SEC("maps") tcp_sock_result_map = {
 	.type = BPF_MAP_TYPE_ARRAY,
 	.key_size = sizeof(__u32),
 	.value_size = sizeof(struct bpf_tcp_sock),
-	.max_entries = __NR_BPF_ARRAY_IDX,
+	.max_entries = __NR_BPF_RESULT_ARRAY_IDX,
 };
 
 struct bpf_map_def SEC("maps") linum_map = {
 	.type = BPF_MAP_TYPE_ARRAY,
 	.key_size = sizeof(__u32),
 	.value_size = sizeof(__u32),
-	.max_entries = 1,
+	.max_entries = __NR_BPF_LINUM_ARRAY_IDX,
 };
 
 static bool is_loopback6(__u32 *a6)
@@ -100,18 +113,20 @@ static void tpcpy(struct bpf_tcp_sock *dst,
 
 #define RETURN {						\
 	linum = __LINE__;					\
-	bpf_map_update_elem(&linum_map, &idx0, &linum, 0);	\
+	bpf_map_update_elem(&linum_map, &linum_idx, &linum, 0);	\
 	return 1;						\
 }
 
 SEC("cgroup_skb/egress")
-int read_sock_fields(struct __sk_buff *skb)
+int egress_read_sock_fields(struct __sk_buff *skb)
 {
-	__u32 srv_idx = SRV_IDX, cli_idx = CLI_IDX, idx;
+	__u32 srv_idx = ADDR_SRV_IDX, cli_idx = ADDR_CLI_IDX, result_idx;
 	struct sockaddr_in6 *srv_sa6, *cli_sa6;
 	struct bpf_tcp_sock *tp, *tp_ret;
 	struct bpf_sock *sk, *sk_ret;
-	__u32 linum, idx0 = 0;
+	__u32 linum, linum_idx;
+
+	linum_idx = EGRESS_LINUM_IDX;
 
 	sk = skb->sk;
 	if (!sk || sk->state == 10)
@@ -132,14 +147,55 @@ int read_sock_fields(struct __sk_buff *skb)
 		RETURN;
 
 	if (sk->src_port == bpf_ntohs(srv_sa6->sin6_port))
-		idx = srv_idx;
+		result_idx = EGRESS_SRV_IDX;
 	else if (sk->src_port == bpf_ntohs(cli_sa6->sin6_port))
-		idx = cli_idx;
+		result_idx = EGRESS_CLI_IDX;
 	else
 		RETURN;
 
-	sk_ret = bpf_map_lookup_elem(&sock_result_map, &idx);
-	tp_ret = bpf_map_lookup_elem(&tcp_sock_result_map, &idx);
+	sk_ret = bpf_map_lookup_elem(&sock_result_map, &result_idx);
+	tp_ret = bpf_map_lookup_elem(&tcp_sock_result_map, &result_idx);
+	if (!sk_ret || !tp_ret)
+		RETURN;
+
+	skcpy(sk_ret, sk);
+	tpcpy(tp_ret, tp);
+
+	RETURN;
+}
+
+SEC("cgroup_skb/ingress")
+int ingress_read_sock_fields(struct __sk_buff *skb)
+{
+	__u32 srv_idx = ADDR_SRV_IDX, result_idx = INGRESS_LISTEN_IDX;
+	struct bpf_tcp_sock *tp, *tp_ret;
+	struct bpf_sock *sk, *sk_ret;
+	struct sockaddr_in6 *srv_sa6;
+	__u32 linum, linum_idx;
+
+	linum_idx = INGRESS_LINUM_IDX;
+
+	sk = skb->sk;
+	if (!sk || sk->family != AF_INET6 || !is_loopback6(sk->src_ip6))
+		RETURN;
+
+	srv_sa6 = bpf_map_lookup_elem(&addr_map, &srv_idx);
+	if (!srv_sa6 || sk->src_port != bpf_ntohs(srv_sa6->sin6_port))
+		RETURN;
+
+	if (sk->state != 10 && sk->state != 12)
+		RETURN;
+
+	sk = bpf_get_listener_sock(sk);
+	if (!sk)
+		RETURN;
+
+	tp = bpf_tcp_sock(sk);
+	if (!tp)
+		RETURN;
+
+	sk_ret = bpf_map_lookup_elem(&sock_result_map, &result_idx);
+	tp_ret = bpf_map_lookup_elem(&tcp_sock_result_map, &result_idx);
 	if (!sk_ret || !tp_ret)
 		RETURN;
 
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 38797aa627a7..ec5794e4205b 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -5777,6 +5777,53 @@ const struct btf_dedup_test dedup_tests[] = {
 	},
 },
 {
+	.descr = "dedup: void equiv check",
+	/*
+	 * // CU 1:
+	 * struct s {
+	 *	struct {} *x;
+	 * };
+	 * // CU 2:
+	 * struct s {
+	 *	int *x;
+	 * };
+	 */
+	.input = {
+		.raw_types = {
+			/* CU 1 */
+			BTF_STRUCT_ENC(0, 0, 1),				/* [1] struct {}  */
+			BTF_PTR_ENC(1),						/* [2] ptr -> [1] */
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 8),			/* [3] struct s   */
+				BTF_MEMBER_ENC(NAME_NTH(2), 2, 0),
+			/* CU 2 */
+			BTF_PTR_ENC(0),						/* [4] ptr -> void */
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 8),			/* [5] struct s   */
+				BTF_MEMBER_ENC(NAME_NTH(2), 4, 0),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0s\0x"),
+	},
+	.expect = {
+		.raw_types = {
+			/* CU 1 */
+			BTF_STRUCT_ENC(0, 0, 1),				/* [1] struct {}  */
+			BTF_PTR_ENC(1),						/* [2] ptr -> [1] */
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 8),			/* [3] struct s   */
+				BTF_MEMBER_ENC(NAME_NTH(2), 2, 0),
+			/* CU 2 */
+			BTF_PTR_ENC(0),						/* [4] ptr -> void */
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 8),			/* [5] struct s   */
+				BTF_MEMBER_ENC(NAME_NTH(2), 4, 0),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0s\0x"),
+	},
+	.opts = {
+		.dont_resolve_fwds = false,
+		.dedup_table_size = 1, /* force hash collisions */
+	},
+},
+{
 	.descr = "dedup: all possible kinds (no duplicates)",
 	.input = {
 		.raw_types = {
@@ -5874,6 +5921,50 @@ const struct btf_dedup_test dedup_tests[] = {
 		.dont_resolve_fwds = false,
 	},
 },
+{
+	.descr = "dedup: enum fwd resolution",
+	.input = {
+		.raw_types = {
+			/* [1] fwd enum 'e1' before full enum */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 4),
+			/* [2] full enum 'e1' after fwd */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+				BTF_ENUM_ENC(NAME_NTH(2), 123),
+			/* [3] full enum 'e2' before fwd */
+			BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+				BTF_ENUM_ENC(NAME_NTH(4), 456),
+			/* [4] fwd enum 'e2' after full enum */
+			BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 4),
+			/* [5] incompatible fwd enum with different size */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 1),
+			/* [6] incompatible full enum with different value */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+				BTF_ENUM_ENC(NAME_NTH(2), 321),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0e1\0e1_val\0e2\0e2_val"),
+	},
+	.expect = {
+		.raw_types = {
+			/* [1] full enum 'e1' */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+				BTF_ENUM_ENC(NAME_NTH(2), 123),
+			/* [2] full enum 'e2' */
+			BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+				BTF_ENUM_ENC(NAME_NTH(4), 456),
+			/* [3] incompatible fwd enum with different size */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 1),
+			/* [4] incompatible full enum with different value */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+				BTF_ENUM_ENC(NAME_NTH(2), 321),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0e1\0e1_val\0e2\0e2_val"),
+	},
+	.opts = {
+		.dont_resolve_fwds = false,
+	},
+},
 
 };
 
diff --git a/tools/testing/selftests/bpf/test_sock_fields.c b/tools/testing/selftests/bpf/test_sock_fields.c
index bc8943938bf5..dcae7f664dce 100644
--- a/tools/testing/selftests/bpf/test_sock_fields.c
+++ b/tools/testing/selftests/bpf/test_sock_fields.c
@@ -16,10 +16,23 @@
 #include "cgroup_helpers.h"
 #include "bpf_rlimit.h"
 
-enum bpf_array_idx {
-	SRV_IDX,
-	CLI_IDX,
-	__NR_BPF_ARRAY_IDX,
+enum bpf_addr_array_idx {
+	ADDR_SRV_IDX,
+	ADDR_CLI_IDX,
+	__NR_BPF_ADDR_ARRAY_IDX,
+};
+
+enum bpf_result_array_idx {
+	EGRESS_SRV_IDX,
+	EGRESS_CLI_IDX,
+	INGRESS_LISTEN_IDX,
+	__NR_BPF_RESULT_ARRAY_IDX,
+};
+
+enum bpf_linum_array_idx {
+	EGRESS_LINUM_IDX,
+	INGRESS_LINUM_IDX,
+	__NR_BPF_LINUM_ARRAY_IDX,
 };
 
 #define CHECK(condition, tag, format...) ({				\
@@ -41,8 +54,16 @@ static int linum_map_fd;
 static int addr_map_fd;
 static int tp_map_fd;
 static int sk_map_fd;
-static __u32 srv_idx = SRV_IDX;
-static __u32 cli_idx = CLI_IDX;
+
+static __u32 addr_srv_idx = ADDR_SRV_IDX;
+static __u32 addr_cli_idx = ADDR_CLI_IDX;
+
+static __u32 egress_srv_idx = EGRESS_SRV_IDX;
+static __u32 egress_cli_idx = EGRESS_CLI_IDX;
+static __u32 ingress_listen_idx = INGRESS_LISTEN_IDX;
+
+static __u32 egress_linum_idx = EGRESS_LINUM_IDX;
+static __u32 ingress_linum_idx = INGRESS_LINUM_IDX;
 
 static void init_loopback6(struct sockaddr_in6 *sa6)
 {
@@ -93,29 +114,46 @@ static void print_tp(const struct bpf_tcp_sock *tp)
 
 static void check_result(void)
 {
-	struct bpf_tcp_sock srv_tp, cli_tp;
-	struct bpf_sock srv_sk, cli_sk;
-	__u32 linum, idx0 = 0;
+	struct bpf_tcp_sock srv_tp, cli_tp, listen_tp;
+	struct bpf_sock srv_sk, cli_sk, listen_sk;
+	__u32 ingress_linum, egress_linum;
 	int err;
 
-	err = bpf_map_lookup_elem(linum_map_fd, &idx0, &linum);
+	err = bpf_map_lookup_elem(linum_map_fd, &egress_linum_idx,
+				  &egress_linum);
 	CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)",
 	      "err:%d errno:%d", err, errno);
 
-	err = bpf_map_lookup_elem(sk_map_fd, &srv_idx, &srv_sk);
-	CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &srv_idx)",
+	err = bpf_map_lookup_elem(linum_map_fd, &ingress_linum_idx,
+				  &ingress_linum);
+	CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)",
+	      "err:%d errno:%d", err, errno);
+
+	err = bpf_map_lookup_elem(sk_map_fd, &egress_srv_idx, &srv_sk);
+	CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &egress_srv_idx)",
+	      "err:%d errno:%d", err, errno);
+	err = bpf_map_lookup_elem(tp_map_fd, &egress_srv_idx, &srv_tp);
+	CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &egress_srv_idx)",
+	      "err:%d errno:%d", err, errno);
+
+	err = bpf_map_lookup_elem(sk_map_fd, &egress_cli_idx, &cli_sk);
+	CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &egress_cli_idx)",
 	      "err:%d errno:%d", err, errno);
-	err = bpf_map_lookup_elem(tp_map_fd, &srv_idx, &srv_tp);
-	CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &srv_idx)",
+	err = bpf_map_lookup_elem(tp_map_fd, &egress_cli_idx, &cli_tp);
+	CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &egress_cli_idx)",
 	      "err:%d errno:%d", err, errno);
 
-	err = bpf_map_lookup_elem(sk_map_fd, &cli_idx, &cli_sk);
-	CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &cli_idx)",
+	err = bpf_map_lookup_elem(sk_map_fd, &ingress_listen_idx, &listen_sk);
+	CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &ingress_listen_idx)",
 	      "err:%d errno:%d", err, errno);
-	err = bpf_map_lookup_elem(tp_map_fd, &cli_idx, &cli_tp);
-	CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &cli_idx)",
+	err = bpf_map_lookup_elem(tp_map_fd, &ingress_listen_idx, &listen_tp);
+	CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &ingress_listen_idx)",
 	      "err:%d errno:%d", err, errno);
 
+	printf("listen_sk: ");
+	print_sk(&listen_sk);
+	printf("\n");
+
 	printf("srv_sk: ");
 	print_sk(&srv_sk);
 	printf("\n");
@@ -124,6 +162,10 @@ static void check_result(void)
 	print_sk(&cli_sk);
 	printf("\n");
 
+	printf("listen_tp: ");
+	print_tp(&listen_tp);
+	printf("\n");
+
 	printf("srv_tp: ");
 	print_tp(&srv_tp);
 	printf("\n");
@@ -132,6 +174,19 @@ static void check_result(void)
 	print_tp(&cli_tp);
 	printf("\n");
 
+	CHECK(listen_sk.state != 10 ||
+	      listen_sk.family != AF_INET6 ||
+	      listen_sk.protocol != IPPROTO_TCP ||
+	      memcmp(listen_sk.src_ip6, &in6addr_loopback,
+		     sizeof(listen_sk.src_ip6)) ||
+	      listen_sk.dst_ip6[0] || listen_sk.dst_ip6[1] ||
+	      listen_sk.dst_ip6[2] || listen_sk.dst_ip6[3] ||
+	      listen_sk.src_port != ntohs(srv_sa6.sin6_port) ||
+	      listen_sk.dst_port,
+	      "Unexpected listen_sk",
+	      "Check listen_sk output. ingress_linum:%u",
+	      ingress_linum);
+
 	CHECK(srv_sk.state == 10 ||
 	      !srv_sk.state ||
 	      srv_sk.family != AF_INET6 ||
@@ -142,7 +197,8 @@ static void check_result(void)
 		     sizeof(srv_sk.dst_ip6)) ||
 	      srv_sk.src_port != ntohs(srv_sa6.sin6_port) ||
 	      srv_sk.dst_port != cli_sa6.sin6_port,
-	      "Unexpected srv_sk", "Check srv_sk output. linum:%u", linum);
+	      "Unexpected srv_sk", "Check srv_sk output. egress_linum:%u",
+	      egress_linum);
 
 	CHECK(cli_sk.state == 10 ||
 	      !cli_sk.state ||
@@ -154,21 +210,31 @@ static void check_result(void)
 		     sizeof(cli_sk.dst_ip6)) ||
 	      cli_sk.src_port != ntohs(cli_sa6.sin6_port) ||
 	      cli_sk.dst_port != srv_sa6.sin6_port,
-	      "Unexpected cli_sk", "Check cli_sk output. linum:%u", linum);
+	      "Unexpected cli_sk", "Check cli_sk output. egress_linum:%u",
+	      egress_linum);
+
+	CHECK(listen_tp.data_segs_out ||
+	      listen_tp.data_segs_in ||
+	      listen_tp.total_retrans ||
+	      listen_tp.bytes_acked,
+	      "Unexpected listen_tp", "Check listen_tp output. ingress_linum:%u",
+	      ingress_linum);
 
 	CHECK(srv_tp.data_segs_out != 1 ||
 	      srv_tp.data_segs_in ||
 	      srv_tp.snd_cwnd != 10 ||
 	      srv_tp.total_retrans ||
 	      srv_tp.bytes_acked != DATA_LEN,
-	      "Unexpected srv_tp", "Check srv_tp output. linum:%u", linum);
+	      "Unexpected srv_tp", "Check srv_tp output. egress_linum:%u",
+	      egress_linum);
 
 	CHECK(cli_tp.data_segs_out ||
 	      cli_tp.data_segs_in != 1 ||
 	      cli_tp.snd_cwnd != 10 ||
 	      cli_tp.total_retrans ||
 	      cli_tp.bytes_received != DATA_LEN,
-	      "Unexpected cli_tp", "Check cli_tp output. linum:%u", linum);
+	      "Unexpected cli_tp", "Check cli_tp output. egress_linum:%u",
+	      egress_linum);
 }
 
 static void test(void)
@@ -211,10 +277,10 @@ static void test(void)
 	      err, errno);
 
 	/* Update addr_map with srv_sa6 and cli_sa6 */
-	err = bpf_map_update_elem(addr_map_fd, &srv_idx, &srv_sa6, 0);
+	err = bpf_map_update_elem(addr_map_fd, &addr_srv_idx, &srv_sa6, 0);
 	CHECK(err, "map_update", "err:%d errno:%d", err, errno);
 
-	err = bpf_map_update_elem(addr_map_fd, &cli_idx, &cli_sa6, 0);
+	err = bpf_map_update_elem(addr_map_fd, &addr_cli_idx, &cli_sa6, 0);
 	CHECK(err, "map_update", "err:%d errno:%d", err, errno);
 
 	/* Connect from cli_sa6 to srv_sa6 */
@@ -273,9 +339,9 @@ int main(int argc, char **argv)
 	struct bpf_prog_load_attr attr = {
 		.file = "test_sock_fields_kern.o",
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-		.expected_attach_type = BPF_CGROUP_INET_EGRESS,
 	};
-	int cgroup_fd, prog_fd, err;
+	int cgroup_fd, egress_fd, ingress_fd, err;
+	struct bpf_program *ingress_prog;
 	struct bpf_object *obj;
 	struct bpf_map *map;
 
@@ -293,12 +359,24 @@ int main(int argc, char **argv)
 	err = join_cgroup(TEST_CGROUP);
 	CHECK(err, "join_cgroup", "err:%d errno:%d", err, errno);
 
-	err = bpf_prog_load_xattr(&attr, &obj, &prog_fd);
+	err = bpf_prog_load_xattr(&attr, &obj, &egress_fd);
 	CHECK(err, "bpf_prog_load_xattr()", "err:%d", err);
 
-	err = bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0);
+	ingress_prog = bpf_object__find_program_by_title(obj,
+							 "cgroup_skb/ingress");
+	CHECK(!ingress_prog,
+	      "bpf_object__find_program_by_title(cgroup_skb/ingress)",
+	      "not found");
+	ingress_fd = bpf_program__fd(ingress_prog);
+
+	err = bpf_prog_attach(egress_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0);
 	CHECK(err == -1, "bpf_prog_attach(CPF_CGROUP_INET_EGRESS)",
 	      "err:%d errno%d", err, errno);
+
+	err = bpf_prog_attach(ingress_fd, cgroup_fd,
+			      BPF_CGROUP_INET_INGRESS, 0);
+	CHECK(err == -1, "bpf_prog_attach(CPF_CGROUP_INET_INGRESS)",
+	      "err:%d errno%d", err, errno);
 	close(cgroup_fd);
 
 	map = bpf_object__find_map_by_name(obj, "addr_map");
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index 4004891afa9c..fb11240b758b 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -908,6 +908,44 @@
 	.result = REJECT,
 },
 {
+	"calls: stack depth check in dead code",
+	.insns = {
+	/* main */
+	BPF_MOV64_IMM(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call A */
+	BPF_EXIT_INSN(),
+	/* A */
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 2), /* call B */
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	/* B */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call C */
+	BPF_EXIT_INSN(),
+	/* C */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call D */
+	BPF_EXIT_INSN(),
+	/* D */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call E */
+	BPF_EXIT_INSN(),
+	/* E */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call F */
+	BPF_EXIT_INSN(),
+	/* F */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call G */
+	BPF_EXIT_INSN(),
+	/* G */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call H */
+	BPF_EXIT_INSN(),
+	/* H */
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.errstr = "call stack",
+	.result = REJECT,
+},
+{
 	"calls: spill into caller stack frame",
 	.insns = {
 	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
@@ -1940,3 +1978,28 @@
 	.errstr = "!read_ok",
 	.result = REJECT,
 },
+{
+	"calls: cross frame pruning - liveness propagation",
+	.insns = {
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
+	BPF_MOV64_IMM(BPF_REG_8, 0),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_MOV64_IMM(BPF_REG_8, 1),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
+	BPF_MOV64_IMM(BPF_REG_9, 0),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_MOV64_IMM(BPF_REG_9, 1),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_8, 1, 1),
+	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_2, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+	.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+	.errstr = "!read_ok",
+	.result = REJECT,
+},
diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c
index 3ed3593bd8b6..923f2110072d 100644
--- a/tools/testing/selftests/bpf/verifier/ref_tracking.c
+++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c
@@ -605,3 +605,171 @@
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.result = ACCEPT,
 },
+{
+	"reference tracking: use ptr from bpf_tcp_sock() after release",
+	.insns = {
+	BPF_SK_LOOKUP,
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, offsetof(struct bpf_tcp_sock, snd_cwnd)),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = REJECT,
+	.errstr = "invalid mem access",
+},
+{
+	"reference tracking: use ptr from bpf_sk_fullsock() after release",
+	.insns = {
+	BPF_SK_LOOKUP,
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, offsetof(struct bpf_sock, type)),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = REJECT,
+	.errstr = "invalid mem access",
+},
+{
+	"reference tracking: use ptr from bpf_sk_fullsock(tp) after release",
+	.insns = {
+	BPF_SK_LOOKUP,
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, type)),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = REJECT,
+	.errstr = "invalid mem access",
+},
+{
+	"reference tracking: use sk after bpf_sk_release(tp)",
+	.insns = {
+	BPF_SK_LOOKUP,
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, type)),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = REJECT,
+	.errstr = "invalid mem access",
+},
+{
+	"reference tracking: use ptr from bpf_get_listener_sock() after bpf_sk_release(sk)",
+	.insns = {
+	BPF_SK_LOOKUP,
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_get_listener_sock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, src_port)),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = ACCEPT,
+},
+{
+	"reference tracking: bpf_sk_release(listen_sk)",
+	.insns = {
+	BPF_SK_LOOKUP,
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_get_listener_sock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, type)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = REJECT,
+	.errstr = "reference has not been acquired before",
+},
+{
+	/* !bpf_sk_fullsock(sk) is checked but !bpf_tcp_sock(sk) is not checked */
+	"reference tracking: tp->snd_cwnd after bpf_sk_fullsock(sk) and bpf_tcp_sock(sk)",
+	.insns = {
+	BPF_SK_LOOKUP,
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
+	BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0, 3),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_8, offsetof(struct bpf_tcp_sock, snd_cwnd)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = REJECT,
+	.errstr = "invalid mem access",
+},
diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c
index 0ddfdf76aba5..416436231fab 100644
--- a/tools/testing/selftests/bpf/verifier/sock.c
+++ b/tools/testing/selftests/bpf/verifier/sock.c
@@ -342,7 +342,7 @@
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.result = REJECT,
-	.errstr = "type=sock_common expected=sock",
+	.errstr = "reference has not been acquired before",
 },
 {
 	"bpf_sk_release(bpf_sk_fullsock(skb->sk))",
@@ -380,5 +380,5 @@
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.result = REJECT,
-	.errstr = "type=tcp_sock expected=sock",
+	.errstr = "reference has not been acquired before",
 },
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 3c1f4bdf9000..7514fcea91a7 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -29,8 +29,8 @@ LIBKVM += $(LIBKVM_$(UNAME_M))
 INSTALL_HDR_PATH = $(top_srcdir)/usr
 LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
 LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include
-CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I..
-LDFLAGS += -pthread
+CFLAGS += -O2 -g -std=gnu99 -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I..
+LDFLAGS += -pthread -no-pie
 
 # After inclusion, $(OUTPUT) is defined and
 # $(TEST_GEN_PROGS) starts with $(OUTPUT)/
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index a84785b02557..07b71ad9734a 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -102,6 +102,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva);
 struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
 int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
 		       struct kvm_mp_state *mp_state);
 void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index b52cfdefecbf..efa0aad8b3c6 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1121,6 +1121,22 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid)
 	return rc;
 }
 
+void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+	int ret;
+
+	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+	vcpu->state->immediate_exit = 1;
+	ret = ioctl(vcpu->fd, KVM_RUN, NULL);
+	vcpu->state->immediate_exit = 0;
+
+	TEST_ASSERT(ret == -1 && errno == EINTR,
+		    "KVM_RUN IOCTL didn't exit immediately, rc: %i, errno: %i",
+		    ret, errno);
+}
+
 /*
  * VM VCPU Set MP State
  *
diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
index d503a51fad30..7c2c4d4055a8 100644
--- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
+++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
@@ -87,22 +87,25 @@ int main(int argc, char *argv[])
 	while (1) {
 		rc = _vcpu_run(vm, VCPU_ID);
 
-		if (run->exit_reason == KVM_EXIT_IO) {
-			switch (get_ucall(vm, VCPU_ID, &uc)) {
-			case UCALL_SYNC:
-				/* emulate hypervisor clearing CR4.OSXSAVE */
-				vcpu_sregs_get(vm, VCPU_ID, &sregs);
-				sregs.cr4 &= ~X86_CR4_OSXSAVE;
-				vcpu_sregs_set(vm, VCPU_ID, &sregs);
-				break;
-			case UCALL_ABORT:
-				TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
-				break;
-			case UCALL_DONE:
-				goto done;
-			default:
-				TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
-			}
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Unexpected exit reason: %u (%s),\n",
+			    run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_SYNC:
+			/* emulate hypervisor clearing CR4.OSXSAVE */
+			vcpu_sregs_get(vm, VCPU_ID, &sregs);
+			sregs.cr4 &= ~X86_CR4_OSXSAVE;
+			vcpu_sregs_set(vm, VCPU_ID, &sregs);
+			break;
+		case UCALL_ABORT:
+			TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
+			break;
+		case UCALL_DONE:
+			goto done;
+		default:
+			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
 		}
 	}
 
diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c
index 4b3f556265f1..30f75856cf39 100644
--- a/tools/testing/selftests/kvm/x86_64/state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/state_test.c
@@ -134,6 +134,11 @@ int main(int argc, char *argv[])
 
 	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
 
+	if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) {
+		fprintf(stderr, "immediate_exit not available, skipping test\n");
+		exit(KSFT_SKIP);
+	}
+
 	/* Create VM */
 	vm = vm_create_default(VCPU_ID, 0, guest_code);
 	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
@@ -156,8 +161,6 @@ int main(int argc, char *argv[])
 			    stage, run->exit_reason,
 			    exit_reason_str(run->exit_reason));
 
-		memset(&regs1, 0, sizeof(regs1));
-		vcpu_regs_get(vm, VCPU_ID, &regs1);
 		switch (get_ucall(vm, VCPU_ID, &uc)) {
 		case UCALL_ABORT:
 			TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
@@ -176,6 +179,17 @@ int main(int argc, char *argv[])
 			    uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx",
 			    stage, (ulong)uc.args[1]);
 
+		/*
+		 * When KVM exits to userspace with KVM_EXIT_IO, KVM guarantees
+		 * guest state is consistent only after userspace re-enters the
+		 * kernel with KVM_RUN.  Complete IO prior to migrating state
+		 * to a new VM.
+		 */
+		vcpu_run_complete_io(vm, VCPU_ID);
+
+		memset(&regs1, 0, sizeof(regs1));
+		vcpu_regs_get(vm, VCPU_ID, &regs1);
+
 		state = vcpu_save_state(vm, VCPU_ID);
 		kvm_vm_release(vm);
 
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
index 5970cee6d05f..b074ea9b6fe8 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
@@ -286,5 +286,30 @@
         "teardown": [
             "$TC action flush action bpf"
         ]
+    },
+    {
+        "id": "b8a1",
+        "name": "Replace bpf action with invalid goto_chain control",
+        "category": [
+            "actions",
+            "bpf"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action bpf",
+                0,
+                1,
+                255
+            ],
+            "$TC action add action bpf bytecode '1,6 0 0 4294967295' pass index 90"
+        ],
+        "cmdUnderTest": "$TC action replace action bpf bytecode '1,6 0 0 4294967295' goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC action list action bpf",
+        "matchPattern": "action order [0-9]*: bpf.* default-action pass.*index 90",
+        "matchCount": "1",
+        "teardown": [
+            "$TC action flush action bpf"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json b/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json
index 13147a1f5731..cadde8f41fcd 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json
@@ -287,5 +287,30 @@
         "teardown": [
             "$TC actions flush action connmark"
         ]
+    },
+    {
+        "id": "c506",
+        "name": "Replace connmark with invalid goto chain control",
+        "category": [
+            "actions",
+            "connmark"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action connmark",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action connmark pass index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action connmark goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action connmark index 90",
+        "matchPattern": "action order [0-9]+: connmark zone 0 pass.*index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action connmark"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json
index a022792d392a..ddabb2fbb7c7 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json
@@ -500,5 +500,30 @@
         "matchPattern": "^[ \t]+index [0-9]+ ref",
         "matchCount": "0",
         "teardown": []
+    },
+    {
+        "id": "d128",
+        "name": "Replace csum action with invalid goto chain control",
+        "category": [
+            "actions",
+            "csum"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action csum",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action csum iph index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action csum iph goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action csum index 90",
+        "matchPattern": "action order [0-9]*: csum \\(iph\\) action pass.*index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action csum"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
index 89189a03ce3d..814b7a8a478b 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
@@ -560,5 +560,30 @@
         "teardown": [
             "$TC actions flush action gact"
         ]
+    },
+    {
+        "id": "ca89",
+        "name": "Replace gact action with invalid goto chain control",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action pass random determ drop 2 index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action goto chain 42 random determ drop 5 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action pass.*random type determ drop val 2.*index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
index 0da3545cabdb..c13a68b98fc7 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
@@ -1060,5 +1060,30 @@
         "matchPattern": "action order [0-9]*: ife encode action pipe.*allow prio.*index 4",
         "matchCount": "0",
         "teardown": []
+    },
+    {
+        "id": "a0e2",
+        "name": "Replace ife encode action with invalid goto chain control",
+        "category": [
+            "actions",
+            "ife"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action ife",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action ife encode allow mark pass index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action ife encode allow mark goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action ife index 90",
+        "matchPattern": "action order [0-9]*: ife encode action pass.*type 0[xX]ED3E .*allow mark.*index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action ife"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
index db49fd0f8445..6e5fb3d25681 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
@@ -434,5 +434,30 @@
         "teardown": [
             "$TC actions flush action mirred"
         ]
+    },
+    {
+        "id": "2a9a",
+        "name": "Replace mirred action with invalid goto chain control",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action mirred ingress mirror dev lo drop index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action mirred ingress mirror dev lo goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action mirred index 90",
+        "matchPattern": "action order [0-9]*: mirred \\(Ingress Mirror to device lo\\) drop.*index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json b/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json
index 0080dc2fd41c..bc12c1ccad30 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json
@@ -589,5 +589,30 @@
         "teardown": [
             "$TC actions flush action nat"
         ]
+    },
+    {
+        "id": "4b12",
+        "name": "Replace nat action with invalid goto chain control",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action nat ingress 1.18.1.1 1.18.2.2 drop index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action nat ingress 1.18.1.1 1.18.2.2 goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action nat index 90",
+        "matchPattern": "action order [0-9]+:  nat ingress 1.18.1.1/32 1.18.2.2 drop.*index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json
new file mode 100644
index 000000000000..b73ceb9e28b1
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json
@@ -0,0 +1,51 @@
+[
+    {
+        "id": "319a",
+        "name": "Add pedit action that mangles IP TTL",
+        "category": [
+            "actions",
+            "pedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action pedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action pedit ex munge ip ttl set 10",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action pedit",
+        "matchPattern": "action order [0-9]+:  pedit action pass keys 1.*index 1 ref.*key #0  at ipv4\\+8: val 0a000000 mask 00ffffff",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action pedit"
+        ]
+    },
+    {
+        "id": "7e67",
+        "name": "Replace pedit action with invalid goto chain",
+        "category": [
+            "actions",
+            "pedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action pedit",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action pedit ex munge ip ttl set 10 pass index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action pedit ex munge ip ttl set 10 goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions ls action pedit",
+        "matchPattern": "action order [0-9]+:  pedit action pass keys 1.*index 90 ref.*key #0  at ipv4\\+8: val 0a000000 mask 00ffffff",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action pedit"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
index 4086a50a670e..b8268da5adaa 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
@@ -739,5 +739,30 @@
         "teardown": [
             "$TC actions flush action police"
         ]
+    },
+    {
+        "id": "689e",
+        "name": "Replace police action with invalid goto chain control",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action police rate 3mbit burst 250k drop index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action police rate 3mbit burst 250k goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action police index 90",
+        "matchPattern": "action order [0-9]*:  police 0x5a rate 3Mbit burst 250Kb mtu 2Kb action drop",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json
index 3aca33c00039..ddabb160a11b 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json
@@ -144,6 +144,30 @@
         ]
     },
     {
+        "id": "7571",
+        "name": "Add sample action with invalid rate",
+        "category": [
+            "actions",
+            "sample"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action sample",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action sample rate 0 group 1 index 2",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action sample index 2",
+        "matchPattern": "action order [0-9]+: sample rate 1/0 group 1.*index 2 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action sample"
+        ]
+    },
+    {
         "id": "b6d4",
         "name": "Add sample action with mandatory arguments and invalid control action",
         "category": [
@@ -584,5 +608,30 @@
         "teardown": [
             "$TC actions flush action sample"
         ]
+    },
+    {
+        "id": "0a6e",
+        "name": "Replace sample action with invalid goto chain control",
+        "category": [
+            "actions",
+            "sample"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action sample",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action sample rate 1024 group 4 pass index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action sample rate 1024 group 7 goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action sample",
+        "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 pass.*index 90",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action sample"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
index e89a7aa4012d..8e8c1ae12260 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
@@ -126,5 +126,30 @@
         "teardown": [
             ""
         ]
+    },
+    {
+        "id": "b776",
+        "name": "Replace simple action with invalid goto chain control",
+        "category": [
+            "actions",
+            "simple"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action simple",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action simple sdata \"hello\" pass index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action simple sdata \"world\" goto chain 42 index  90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action simple",
+        "matchPattern": "action order [0-9]*: Simple <hello>.*index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action simple"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
index 5aaf593b914a..ecd96eda7f6a 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
@@ -484,5 +484,30 @@
         "teardown": [
             "$TC actions flush action skbedit"
         ]
+    },
+    {
+        "id": "1b2b",
+        "name": "Replace skbedit action with invalid goto_chain control",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action skbedit ptype host pass index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action skbedit ptype host goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*: skbedit  ptype host pass.*index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
index fe3326e939c1..6eb4c4f97060 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
@@ -392,5 +392,30 @@
         "teardown": [
             "$TC actions flush action skbmod"
         ]
+    },
+    {
+        "id": "b651",
+        "name": "Replace skbmod action with invalid goto_chain control",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action skbmod set etype 0x1111 pass index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action skbmod set etype 0x1111 goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pass set etype 0x1111\\s+index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json b/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json
index e7e15a7336b6..28453a445fdb 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json
@@ -884,5 +884,30 @@
         "teardown": [
 	    "$TC actions flush action tunnel_key"
 	]
+    },
+    {
+        "id": "8242",
+        "name": "Replace tunnel_key set action with invalid goto chain",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 nocsum id 1 pass index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action tunnel_key set src_ip 10.10.10.2 dst_ip 20.20.20.1 dst_port 3129 id 2 csum goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 90",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 10.10.10.1.*dst_ip 20.20.20.2.*key_id 1.*dst_port 3128.*csum pass.*index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json
index 69ea09eefffc..cc7c7d758008 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json
@@ -688,5 +688,30 @@
         "teardown": [
             "$TC actions flush action vlan"
         ]
+    },
+    {
+        "id": "e394",
+        "name": "Replace vlan push action with invalid goto chain control",
+        "category": [
+            "actions",
+            "vlan"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action vlan",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action vlan push id 500 pass index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action vlan push id 500 goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action vlan index 90",
+        "matchPattern": "action order [0-9]+: vlan.*push id 500 protocol 802.1Q priority 0 pass.*index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action vlan"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
index 99a5ffca1088..2d096b2abf2c 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
@@ -19,6 +19,26 @@
         ]
     },
     {
+        "id": "2638",
+        "name": "Add matchall and try to get it",
+        "category": [
+            "filter",
+            "matchall"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 clsact",
+            "$TC filter add dev $DEV1 protocol all pref 1 ingress handle 0x1234 matchall action ok"
+        ],
+        "cmdUnderTest": "$TC filter get dev $DEV1 protocol all pref 1 ingress handle 0x1234 matchall",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1 ingress",
+        "matchPattern": "filter protocol all pref 1 matchall chain 0 handle 0x1234",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 clsact"
+        ]
+    },
+    {
         "id": "d052",
         "name": "Add 1M filters with the same action",
         "category": [
diff --git a/tools/testing/selftests/tpm2/tpm2.py b/tools/testing/selftests/tpm2/tpm2.py
index 40ea95ce2ead..828c18584624 100644
--- a/tools/testing/selftests/tpm2/tpm2.py
+++ b/tools/testing/selftests/tpm2/tpm2.py
@@ -22,6 +22,7 @@ TPM2_CC_UNSEAL = 0x015E
 TPM2_CC_FLUSH_CONTEXT = 0x0165
 TPM2_CC_START_AUTH_SESSION = 0x0176
 TPM2_CC_GET_CAPABILITY	= 0x017A
+TPM2_CC_GET_RANDOM = 0x017B
 TPM2_CC_PCR_READ = 0x017E
 TPM2_CC_POLICY_PCR = 0x017F
 TPM2_CC_PCR_EXTEND = 0x0182
@@ -357,9 +358,9 @@ class Client:
         self.flags = flags
 
         if (self.flags & Client.FLAG_SPACE) == 0:
-            self.tpm = open('/dev/tpm0', 'r+b')
+            self.tpm = open('/dev/tpm0', 'r+b', buffering=0)
         else:
-            self.tpm = open('/dev/tpmrm0', 'r+b')
+            self.tpm = open('/dev/tpmrm0', 'r+b', buffering=0)
 
     def close(self):
         self.tpm.close()
diff --git a/tools/testing/selftests/tpm2/tpm2_tests.py b/tools/testing/selftests/tpm2/tpm2_tests.py
index 3bb066fea4a0..d4973be53493 100644
--- a/tools/testing/selftests/tpm2/tpm2_tests.py
+++ b/tools/testing/selftests/tpm2/tpm2_tests.py
@@ -158,6 +158,69 @@ class SmokeTest(unittest.TestCase):
             pass
         self.assertEqual(rejected, True)
 
+    def test_read_partial_resp(self):
+        try:
+            fmt = '>HIIH'
+            cmd = struct.pack(fmt,
+                              tpm2.TPM2_ST_NO_SESSIONS,
+                              struct.calcsize(fmt),
+                              tpm2.TPM2_CC_GET_RANDOM,
+                              0x20)
+            self.client.tpm.write(cmd)
+            hdr = self.client.tpm.read(10)
+            sz = struct.unpack('>I', hdr[2:6])[0]
+            rsp = self.client.tpm.read()
+        except:
+            pass
+        self.assertEqual(sz, 10 + 2 + 32)
+        self.assertEqual(len(rsp), 2 + 32)
+
+    def test_read_partial_overwrite(self):
+        try:
+            fmt = '>HIIH'
+            cmd = struct.pack(fmt,
+                              tpm2.TPM2_ST_NO_SESSIONS,
+                              struct.calcsize(fmt),
+                              tpm2.TPM2_CC_GET_RANDOM,
+                              0x20)
+            self.client.tpm.write(cmd)
+            # Read part of the respone
+            rsp1 = self.client.tpm.read(15)
+
+            # Send a new cmd
+            self.client.tpm.write(cmd)
+
+            # Read the whole respone
+            rsp2 = self.client.tpm.read()
+        except:
+            pass
+        self.assertEqual(len(rsp1), 15)
+        self.assertEqual(len(rsp2), 10 + 2 + 32)
+
+    def test_send_two_cmds(self):
+        rejected = False
+        try:
+            fmt = '>HIIH'
+            cmd = struct.pack(fmt,
+                              tpm2.TPM2_ST_NO_SESSIONS,
+                              struct.calcsize(fmt),
+                              tpm2.TPM2_CC_GET_RANDOM,
+                              0x20)
+            self.client.tpm.write(cmd)
+
+            # expect the second one to raise -EBUSY error
+            self.client.tpm.write(cmd)
+            rsp = self.client.tpm.read()
+
+        except IOError, e:
+            # read the response
+            rsp = self.client.tpm.read()
+            rejected = True
+            pass
+        except:
+            pass
+        self.assertEqual(rejected, True)
+
 class SpaceTest(unittest.TestCase):
     def setUp(self):
         logging.basicConfig(filename='SpaceTest.log', level=logging.DEBUG)