Merge tag 'asoc-fix-v7.0-rc7' of https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound into for-linus

ASoC: Fixes for v7.0

A somewhat larger set of fixes than I'd like unfortunatey, not from any
one place but rather spread out over different drivers.  We've got a
bunch more fixes for the SDCA interrupt support, several relatively
minor SOF fixes, a few more driver specific fixes and a couple more AMD
quirks.

12 files changed, 707 insertions, 13 deletions

diff --git a/tools/testing/selftests/bpf/progs/verifier_precision.c b/tools/testing/selftests/bpf/progs/verifier_precision.c
index 1fe090cd6744..4794903aec8e 100644
--- a/tools/testing/selftests/bpf/progs/verifier_precision.c
+++ b/tools/testing/selftests/bpf/progs/verifier_precision.c
@@ -5,6 +5,13 @@
 #include "../../../include/linux/filter.h"
 #include "bpf_misc.h"
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} precision_map SEC(".maps");
+
 SEC("?raw_tp")
 __success __log_level(2)
 __msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
@@ -301,4 +308,338 @@ __naked int bpf_neg_5(void)
 	::: __clobber_all);
 }
 
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 4: (bf) r3 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_fetch_add((u64 *)(r10 -8), r2)")
+__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r2 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_atomic_fetch_add_precision(void)
+{
+	asm volatile (
+	"r1 = 8;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = 0;"
+	".8byte %[fetch_add_insn];"	/* r2 = atomic_fetch_add(*(u64 *)(r10 - 8), r2) */
+	"r3 = r10;"
+	"r3 += r2;"			/* mark_precise */
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(fetch_add_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_ADD | BPF_FETCH, BPF_REG_10, BPF_REG_2, -8))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 4: (bf) r3 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_xchg((u64 *)(r10 -8), r2)")
+__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r2 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_atomic_xchg_precision(void)
+{
+	asm volatile (
+	"r1 = 8;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = 0;"
+	".8byte %[xchg_insn];"		/* r2 = atomic_xchg(*(u64 *)(r10 - 8), r2) */
+	"r3 = r10;"
+	"r3 += r2;"			/* mark_precise */
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(xchg_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_XCHG, BPF_REG_10, BPF_REG_2, -8))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 4: (bf) r3 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_fetch_or((u64 *)(r10 -8), r2)")
+__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r2 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_atomic_fetch_or_precision(void)
+{
+	asm volatile (
+	"r1 = 8;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = 0;"
+	".8byte %[fetch_or_insn];"	/* r2 = atomic_fetch_or(*(u64 *)(r10 - 8), r2) */
+	"r3 = r10;"
+	"r3 += r2;"			/* mark_precise */
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(fetch_or_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_OR | BPF_FETCH, BPF_REG_10, BPF_REG_2, -8))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 4: (bf) r3 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_fetch_and((u64 *)(r10 -8), r2)")
+__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r2 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_atomic_fetch_and_precision(void)
+{
+	asm volatile (
+	"r1 = 8;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = 0;"
+	".8byte %[fetch_and_insn];"	/* r2 = atomic_fetch_and(*(u64 *)(r10 - 8), r2) */
+	"r3 = r10;"
+	"r3 += r2;"			/* mark_precise */
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(fetch_and_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_AND | BPF_FETCH, BPF_REG_10, BPF_REG_2, -8))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 4: (bf) r3 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_fetch_xor((u64 *)(r10 -8), r2)")
+__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r2 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_atomic_fetch_xor_precision(void)
+{
+	asm volatile (
+	"r1 = 8;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = 0;"
+	".8byte %[fetch_xor_insn];"	/* r2 = atomic_fetch_xor(*(u64 *)(r10 - 8), r2) */
+	"r3 = r10;"
+	"r3 += r2;"			/* mark_precise */
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(fetch_xor_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_XOR | BPF_FETCH, BPF_REG_10, BPF_REG_2, -8))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r0 stack= before 5: (bf) r3 = r10")
+__msg("mark_precise: frame0: regs=r0 stack= before 4: (db) r0 = atomic64_cmpxchg((u64 *)(r10 -8), r0, r2)")
+__msg("mark_precise: frame0: regs= stack=-8 before 3: (b7) r2 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r0 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_atomic_cmpxchg_precision(void)
+{
+	asm volatile (
+	"r1 = 8;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r0 = 0;"
+	"r2 = 0;"
+	".8byte %[cmpxchg_insn];"	/* r0 = atomic_cmpxchg(*(u64 *)(r10 - 8), r0, r2) */
+	"r3 = r10;"
+	"r3 += r0;"			/* mark_precise */
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(cmpxchg_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, BPF_REG_10, BPF_REG_2, -8))
+	: __clobber_all);
+}
+
+/* Regression test for dual precision: Both the fetched value (r2) and
+ * a reread of the same stack slot (r3) are tracked for precision. After
+ * the atomic operation, the stack slot is STACK_MISC. Thus, the ldx at
+ * insn 4 does NOT set INSN_F_STACK_ACCESS. Precision for the stack slot
+ * propagates solely through the atomic fetch's load side (insn 3).
+ */
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2,r3 stack= before 4: (79) r3 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_fetch_add((u64 *)(r10 -8), r2)")
+__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r2 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_atomic_fetch_add_dual_precision(void)
+{
+	asm volatile (
+	"r1 = 8;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = 0;"
+	".8byte %[fetch_add_insn];"	/* r2 = atomic_fetch_add(*(u64 *)(r10 - 8), r2) */
+	"r3 = *(u64 *)(r10 - 8);"
+	"r4 = r2;"
+	"r4 += r3;"
+	"r4 &= 7;"
+	"r5 = r10;"
+	"r5 += r4;"			/* mark_precise */
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(fetch_add_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_ADD | BPF_FETCH, BPF_REG_10, BPF_REG_2, -8))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r0,r3 stack= before 5: (79) r3 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: regs=r0 stack= before 4: (db) r0 = atomic64_cmpxchg((u64 *)(r10 -8), r0, r2)")
+__msg("mark_precise: frame0: regs= stack=-8 before 3: (b7) r2 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r0 = 8")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_atomic_cmpxchg_dual_precision(void)
+{
+	asm volatile (
+	"r1 = 8;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r0 = 8;"
+	"r2 = 0;"
+	".8byte %[cmpxchg_insn];"	/* r0 = atomic_cmpxchg(*(u64 *)(r10 - 8), r0, r2) */
+	"r3 = *(u64 *)(r10 - 8);"
+	"r4 = r0;"
+	"r4 += r3;"
+	"r4 &= 7;"
+	"r5 = r10;"
+	"r5 += r4;"			/* mark_precise */
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(cmpxchg_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, BPF_REG_10, BPF_REG_2, -8))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r1 stack= before 10: (57) r1 &= 7")
+__msg("mark_precise: frame0: regs=r1 stack= before 9: (db) r1 = atomic64_fetch_add((u64 *)(r0 +0), r1)")
+__not_msg("falling back to forcing all scalars precise")
+__naked int bpf_atomic_fetch_add_map_precision(void)
+{
+	asm volatile (
+	"r1 = 0;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = r10;"
+	"r2 += -8;"
+	"r1 = %[precision_map] ll;"
+	"call %[bpf_map_lookup_elem];"
+	"if r0 == 0 goto 1f;"
+	"r1 = 0;"
+	".8byte %[fetch_add_insn];"	/* r1 = atomic_fetch_add(*(u64 *)(r0 + 0), r1) */
+	"r1 &= 7;"
+	"r2 = r10;"
+	"r2 += r1;"			/* mark_precise */
+	"1: r0 = 0;"
+	"exit;"
+	:
+	: __imm_addr(precision_map),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_insn(fetch_add_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_ADD | BPF_FETCH, BPF_REG_0, BPF_REG_1, 0))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r0 stack= before 12: (57) r0 &= 7")
+__msg("mark_precise: frame0: regs=r0 stack= before 11: (db) r0 = atomic64_cmpxchg((u64 *)(r6 +0), r0, r1)")
+__not_msg("falling back to forcing all scalars precise")
+__naked int bpf_atomic_cmpxchg_map_precision(void)
+{
+	asm volatile (
+	"r1 = 0;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = r10;"
+	"r2 += -8;"
+	"r1 = %[precision_map] ll;"
+	"call %[bpf_map_lookup_elem];"
+	"if r0 == 0 goto 1f;"
+	"r6 = r0;"
+	"r0 = 0;"
+	"r1 = 0;"
+	".8byte %[cmpxchg_insn];"	/* r0 = atomic_cmpxchg(*(u64 *)(r6 + 0), r0, r1) */
+	"r0 &= 7;"
+	"r2 = r10;"
+	"r2 += r0;"			/* mark_precise */
+	"1: r0 = 0;"
+	"exit;"
+	:
+	: __imm_addr(precision_map),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_insn(cmpxchg_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, BPF_REG_6, BPF_REG_1, 0))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r1 stack= before 10: (57) r1 &= 7")
+__msg("mark_precise: frame0: regs=r1 stack= before 9: (c3) r1 = atomic_fetch_add((u32 *)(r0 +0), r1)")
+__not_msg("falling back to forcing all scalars precise")
+__naked int bpf_atomic_fetch_add_32bit_precision(void)
+{
+	asm volatile (
+	"r1 = 0;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = r10;"
+	"r2 += -8;"
+	"r1 = %[precision_map] ll;"
+	"call %[bpf_map_lookup_elem];"
+	"if r0 == 0 goto 1f;"
+	"r1 = 0;"
+	".8byte %[fetch_add_insn];"	/* r1 = atomic_fetch_add(*(u32 *)(r0 + 0), r1) */
+	"r1 &= 7;"
+	"r2 = r10;"
+	"r2 += r1;"			/* mark_precise */
+	"1: r0 = 0;"
+	"exit;"
+	:
+	: __imm_addr(precision_map),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_insn(fetch_add_insn,
+		     BPF_ATOMIC_OP(BPF_W, BPF_ADD | BPF_FETCH, BPF_REG_0, BPF_REG_1, 0))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r0 stack= before 12: (57) r0 &= 7")
+__msg("mark_precise: frame0: regs=r0 stack= before 11: (c3) r0 = atomic_cmpxchg((u32 *)(r6 +0), r0, r1)")
+__not_msg("falling back to forcing all scalars precise")
+__naked int bpf_atomic_cmpxchg_32bit_precision(void)
+{
+	asm volatile (
+	"r1 = 0;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = r10;"
+	"r2 += -8;"
+	"r1 = %[precision_map] ll;"
+	"call %[bpf_map_lookup_elem];"
+	"if r0 == 0 goto 1f;"
+	"r6 = r0;"
+	"r0 = 0;"
+	"r1 = 0;"
+	".8byte %[cmpxchg_insn];"	/* r0 = atomic_cmpxchg(*(u32 *)(r6 + 0), r0, r1) */
+	"r0 &= 7;"
+	"r2 = r10;"
+	"r2 += r0;"			/* mark_precise */
+	"1: r0 = 0;"
+	"exit;"
+	:
+	: __imm_addr(precision_map),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_insn(cmpxchg_insn,
+		     BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, BPF_REG_6, BPF_REG_1, 0))
+	: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/cgroup/lib/cgroup_util.c b/tools/testing/selftests/cgroup/lib/cgroup_util.c
index ce6c2642fd9b..6a7295347e90 100644
--- a/tools/testing/selftests/cgroup/lib/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/lib/cgroup_util.c
@@ -123,6 +123,21 @@ int cg_read_strcmp(const char *cgroup, const char *control,
 	return ret;
 }
 
+int cg_read_strcmp_wait(const char *cgroup, const char *control,
+			    const char *expected)
+{
+	int i, ret;
+
+	for (i = 0; i < 100; i++) {
+		ret = cg_read_strcmp(cgroup, control, expected);
+		if (!ret)
+			return ret;
+		usleep(10000);
+	}
+
+	return ret;
+}
+
 int cg_read_strstr(const char *cgroup, const char *control, const char *needle)
 {
 	char buf[PAGE_SIZE];
diff --git a/tools/testing/selftests/cgroup/lib/include/cgroup_util.h b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
index 77f386dab5e8..567b1082974c 100644
--- a/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
+++ b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
@@ -61,6 +61,8 @@ extern int cg_read(const char *cgroup, const char *control,
 		   char *buf, size_t len);
 extern int cg_read_strcmp(const char *cgroup, const char *control,
 			  const char *expected);
+extern int cg_read_strcmp_wait(const char *cgroup, const char *control,
+				   const char *expected);
 extern int cg_read_strstr(const char *cgroup, const char *control,
 			  const char *needle);
 extern long cg_read_long(const char *cgroup, const char *control);
diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c
index 102262555a59..7b83c7e7c9d4 100644
--- a/tools/testing/selftests/cgroup/test_core.c
+++ b/tools/testing/selftests/cgroup/test_core.c
@@ -233,7 +233,8 @@ static int test_cgcore_populated(const char *root)
 	if (err)
 		goto cleanup;
 
-	if (cg_read_strcmp(cg_test_d, "cgroup.events", "populated 0\n"))
+	if (cg_read_strcmp_wait(cg_test_d, "cgroup.events",
+				   "populated 0\n"))
 		goto cleanup;
 
 	/* Remove cgroup. */
diff --git a/tools/testing/selftests/cgroup/test_kill.c b/tools/testing/selftests/cgroup/test_kill.c
index c8c9d306925b..f6cd23a8ecc7 100644
--- a/tools/testing/selftests/cgroup/test_kill.c
+++ b/tools/testing/selftests/cgroup/test_kill.c
@@ -86,7 +86,7 @@ cleanup:
 		wait_for_pid(pids[i]);
 
 	if (ret == KSFT_PASS &&
-	    cg_read_strcmp(cgroup, "cgroup.events", "populated 0\n"))
+	    cg_read_strcmp_wait(cgroup, "cgroup.events", "populated 0\n"))
 		ret = KSFT_FAIL;
 
 	if (cgroup)
@@ -190,7 +190,8 @@ cleanup:
 		wait_for_pid(pids[i]);
 
 	if (ret == KSFT_PASS &&
-	    cg_read_strcmp(cgroup[0], "cgroup.events", "populated 0\n"))
+	    cg_read_strcmp_wait(cgroup[0], "cgroup.events",
+				   "populated 0\n"))
 		ret = KSFT_FAIL;
 
 	for (i = 9; i >= 0 && cgroup[i]; i--) {
@@ -251,7 +252,7 @@ cleanup:
 		wait_for_pid(pid);
 
 	if (ret == KSFT_PASS &&
-	    cg_read_strcmp(cgroup, "cgroup.events", "populated 0\n"))
+	    cg_read_strcmp_wait(cgroup, "cgroup.events", "populated 0\n"))
 		ret = KSFT_FAIL;
 
 	if (cgroup)
diff --git a/tools/testing/selftests/riscv/vector/validate_v_ptrace.c b/tools/testing/selftests/riscv/vector/validate_v_ptrace.c
index 3589549f7228..74b6f6bcf067 100644
--- a/tools/testing/selftests/riscv/vector/validate_v_ptrace.c
+++ b/tools/testing/selftests/riscv/vector/validate_v_ptrace.c
@@ -290,10 +290,11 @@ TEST(ptrace_v_syscall_clobbering)
 
 		/* verify initial vsetvli settings */
 
-		if (is_xtheadvector_supported())
+		if (is_xtheadvector_supported()) {
 			EXPECT_EQ(5UL, regset_data->vtype);
-		else
+		} else {
 			EXPECT_EQ(9UL, regset_data->vtype);
+		}
 
 		EXPECT_EQ(regset_data->vlenb, regset_data->vl);
 		EXPECT_EQ(vlenb, regset_data->vlenb);
@@ -346,8 +347,8 @@ FIXTURE_TEARDOWN(v_csr_invalid)
 {
 }
 
-#define VECTOR_1_0		BIT(0)
-#define XTHEAD_VECTOR_0_7	BIT(1)
+#define VECTOR_1_0		_BITUL(0)
+#define XTHEAD_VECTOR_0_7	_BITUL(1)
 
 #define vector_test(x)		((x) & VECTOR_1_0)
 #define xthead_test(x)		((x) & XTHEAD_VECTOR_0_7)
@@ -619,10 +620,11 @@ TEST_F(v_csr_invalid, ptrace_v_invalid_values)
 
 		/* verify initial vsetvli settings */
 
-		if (is_xtheadvector_supported())
+		if (is_xtheadvector_supported()) {
 			EXPECT_EQ(5UL, regset_data->vtype);
-		else
+		} else {
 			EXPECT_EQ(9UL, regset_data->vtype);
+		}
 
 		EXPECT_EQ(regset_data->vlenb, regset_data->vl);
 		EXPECT_EQ(vlenb, regset_data->vlenb);
@@ -827,10 +829,11 @@ TEST_F(v_csr_valid, ptrace_v_valid_values)
 
 		/* verify initial vsetvli settings */
 
-		if (is_xtheadvector_supported())
+		if (is_xtheadvector_supported()) {
 			EXPECT_EQ(5UL, regset_data->vtype);
-		else
+		} else {
 			EXPECT_EQ(9UL, regset_data->vtype);
+		}
 
 		EXPECT_EQ(regset_data->vlenb, regset_data->vl);
 		EXPECT_EQ(vlenb, regset_data->vlenb);
diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile
index 006300ac6dff..1c9ca328cca1 100644
--- a/tools/testing/selftests/sched_ext/Makefile
+++ b/tools/testing/selftests/sched_ext/Makefile
@@ -188,6 +188,7 @@ auto-test-targets :=			\
 	rt_stall			\
 	test_example			\
 	total_bw			\
+	cyclic_kick_wait		\
 
 testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets)))
 
diff --git a/tools/testing/selftests/sched_ext/cyclic_kick_wait.bpf.c b/tools/testing/selftests/sched_ext/cyclic_kick_wait.bpf.c
new file mode 100644
index 000000000000..cb34d3335917
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/cyclic_kick_wait.bpf.c
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Stress concurrent SCX_KICK_WAIT calls to reproduce wait-cycle deadlock.
+ *
+ * Three CPUs are designated from userspace. Every enqueue from one of the
+ * three CPUs kicks the next CPU in the ring with SCX_KICK_WAIT, creating a
+ * persistent A -> B -> C -> A wait cycle pressure.
+ */
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+const volatile s32 test_cpu_a;
+const volatile s32 test_cpu_b;
+const volatile s32 test_cpu_c;
+
+u64 nr_enqueues;
+u64 nr_wait_kicks;
+
+UEI_DEFINE(uei);
+
+static s32 target_cpu(s32 cpu)
+{
+	if (cpu == test_cpu_a)
+		return test_cpu_b;
+	if (cpu == test_cpu_b)
+		return test_cpu_c;
+	if (cpu == test_cpu_c)
+		return test_cpu_a;
+	return -1;
+}
+
+void BPF_STRUCT_OPS(cyclic_kick_wait_enqueue, struct task_struct *p,
+		    u64 enq_flags)
+{
+	s32 this_cpu = bpf_get_smp_processor_id();
+	s32 tgt;
+
+	__sync_fetch_and_add(&nr_enqueues, 1);
+
+	if (p->flags & PF_KTHREAD) {
+		scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_INF,
+				   enq_flags | SCX_ENQ_PREEMPT);
+		return;
+	}
+
+	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+
+	tgt = target_cpu(this_cpu);
+	if (tgt < 0 || tgt == this_cpu)
+		return;
+
+	__sync_fetch_and_add(&nr_wait_kicks, 1);
+	scx_bpf_kick_cpu(tgt, SCX_KICK_WAIT);
+}
+
+void BPF_STRUCT_OPS(cyclic_kick_wait_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops cyclic_kick_wait_ops = {
+	.enqueue		= cyclic_kick_wait_enqueue,
+	.exit			= cyclic_kick_wait_exit,
+	.name			= "cyclic_kick_wait",
+	.timeout_ms		= 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/cyclic_kick_wait.c b/tools/testing/selftests/sched_ext/cyclic_kick_wait.c
new file mode 100644
index 000000000000..c2e5aa9de715
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/cyclic_kick_wait.c
@@ -0,0 +1,194 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Test SCX_KICK_WAIT forward progress under cyclic wait pressure.
+ *
+ * SCX_KICK_WAIT busy-waits until the target CPU enters the scheduling path.
+ * If multiple CPUs form a wait cycle (A waits for B, B waits for C, C waits
+ * for A), all CPUs deadlock unless the implementation breaks the cycle.
+ *
+ * This test creates that scenario: three CPUs are arranged in a ring. The BPF
+ * scheduler's ops.enqueue() kicks the next CPU in the ring with SCX_KICK_WAIT
+ * on every enqueue. Userspace pins 4 worker threads per CPU that loop calling
+ * sched_yield(), generating a steady stream of enqueues and thus sustained
+ * A->B->C->A kick_wait cycle pressure. The test passes if the system remains
+ * responsive for 5 seconds without the scheduler being killed by the watchdog.
+ */
+#define _GNU_SOURCE
+
+#include <bpf/bpf.h>
+#include <errno.h>
+#include <pthread.h>
+#include <sched.h>
+#include <scx/common.h>
+#include <stdint.h>
+#include <string.h>
+#include <time.h>
+#include <unistd.h>
+
+#include "scx_test.h"
+#include "cyclic_kick_wait.bpf.skel.h"
+
+#define WORKERS_PER_CPU	4
+#define NR_TEST_CPUS	3
+#define NR_WORKERS	(NR_TEST_CPUS * WORKERS_PER_CPU)
+
+struct worker_ctx {
+	pthread_t tid;
+	int cpu;
+	volatile bool stop;
+	volatile __u64 iters;
+	bool started;
+};
+
+static void *worker_fn(void *arg)
+{
+	struct worker_ctx *worker = arg;
+	cpu_set_t mask;
+
+	CPU_ZERO(&mask);
+	CPU_SET(worker->cpu, &mask);
+
+	if (sched_setaffinity(0, sizeof(mask), &mask))
+		return (void *)(uintptr_t)errno;
+
+	while (!worker->stop) {
+		sched_yield();
+		worker->iters++;
+	}
+
+	return NULL;
+}
+
+static int join_worker(struct worker_ctx *worker)
+{
+	void *ret;
+	struct timespec ts;
+	int err;
+
+	if (!worker->started)
+		return 0;
+
+	if (clock_gettime(CLOCK_REALTIME, &ts))
+		return -errno;
+
+	ts.tv_sec += 2;
+	err = pthread_timedjoin_np(worker->tid, &ret, &ts);
+	if (err == ETIMEDOUT)
+		pthread_detach(worker->tid);
+	if (err)
+		return -err;
+
+	if ((uintptr_t)ret)
+		return -(int)(uintptr_t)ret;
+
+	return 0;
+}
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct cyclic_kick_wait *skel;
+
+	skel = cyclic_kick_wait__open();
+	SCX_FAIL_IF(!skel, "Failed to open skel");
+	SCX_ENUM_INIT(skel);
+
+	*ctx = skel;
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct cyclic_kick_wait *skel = ctx;
+	struct worker_ctx workers[NR_WORKERS] = {};
+	struct bpf_link *link = NULL;
+	enum scx_test_status status = SCX_TEST_PASS;
+	int test_cpus[NR_TEST_CPUS];
+	int nr_cpus = 0;
+	cpu_set_t mask;
+	int ret, i;
+
+	if (sched_getaffinity(0, sizeof(mask), &mask)) {
+		SCX_ERR("Failed to get affinity (%d)", errno);
+		return SCX_TEST_FAIL;
+	}
+
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		if (CPU_ISSET(i, &mask))
+			test_cpus[nr_cpus++] = i;
+		if (nr_cpus == NR_TEST_CPUS)
+			break;
+	}
+
+	if (nr_cpus < NR_TEST_CPUS)
+		return SCX_TEST_SKIP;
+
+	skel->rodata->test_cpu_a = test_cpus[0];
+	skel->rodata->test_cpu_b = test_cpus[1];
+	skel->rodata->test_cpu_c = test_cpus[2];
+
+	if (cyclic_kick_wait__load(skel)) {
+		SCX_ERR("Failed to load skel");
+		return SCX_TEST_FAIL;
+	}
+
+	link = bpf_map__attach_struct_ops(skel->maps.cyclic_kick_wait_ops);
+	if (!link) {
+		SCX_ERR("Failed to attach scheduler");
+		return SCX_TEST_FAIL;
+	}
+
+	for (i = 0; i < NR_WORKERS; i++)
+		workers[i].cpu = test_cpus[i / WORKERS_PER_CPU];
+
+	for (i = 0; i < NR_WORKERS; i++) {
+		ret = pthread_create(&workers[i].tid, NULL, worker_fn, &workers[i]);
+		if (ret) {
+			SCX_ERR("Failed to create worker thread %d (%d)", i, ret);
+			status = SCX_TEST_FAIL;
+			goto out;
+		}
+		workers[i].started = true;
+	}
+
+	sleep(5);
+
+	if (skel->data->uei.kind != EXIT_KIND(SCX_EXIT_NONE)) {
+		SCX_ERR("Scheduler exited unexpectedly (kind=%llu code=%lld)",
+			(unsigned long long)skel->data->uei.kind,
+			(long long)skel->data->uei.exit_code);
+		status = SCX_TEST_FAIL;
+	}
+
+out:
+	for (i = 0; i < NR_WORKERS; i++)
+		workers[i].stop = true;
+
+	for (i = 0; i < NR_WORKERS; i++) {
+		ret = join_worker(&workers[i]);
+		if (ret && status == SCX_TEST_PASS) {
+			SCX_ERR("Failed to join worker thread %d (%d)", i, ret);
+			status = SCX_TEST_FAIL;
+		}
+	}
+
+	if (link)
+		bpf_link__destroy(link);
+
+	return status;
+}
+
+static void cleanup(void *ctx)
+{
+	struct cyclic_kick_wait *skel = ctx;
+
+	cyclic_kick_wait__destroy(skel);
+}
+
+struct scx_test cyclic_kick_wait = {
+	.name = "cyclic_kick_wait",
+	.description = "Verify SCX_KICK_WAIT forward progress under a 3-CPU wait cycle",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&cyclic_kick_wait)
diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json b/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json
index 8d10042b489b..dbce6436ed26 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json
@@ -22,5 +22,49 @@
         "teardown": [
             "$TC qdisc del dev $DUMMY root handle 1: htb default 1"
         ]
+    },
+    {
+        "id": "b7e3",
+        "name": "Empty fw filter on shared block - rejected at config time",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$TC qdisc add dev $DEV1 egress_block 1 clsact"
+        ],
+        "cmdUnderTest": "$TC filter add block 1 protocol ip prio 1 fw",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter show block 1",
+        "matchPattern": "fw",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 clsact"
+        ]
+    },
+    {
+        "id": "c8f4",
+        "name": "Flow filter on shared block without baseclass - rejected at config time",
+        "category": [
+            "filter",
+            "flow"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress_block 1 clsact"
+        ],
+        "cmdUnderTest": "$TC filter add block 1 protocol ip prio 1 handle 1 flow map key dst",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter show block 1",
+        "matchPattern": "flow",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 clsact"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index 6a39640aa2a8..1e5efb2a31eb 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -1111,5 +1111,30 @@
         "teardown": [
             "$TC qdisc del dev $DUMMY root handle 1:"
         ]
+    },
+    {
+        "id": "a3d7",
+        "name": "HFSC with large m1 - no divide-by-zero on class reactivation",
+        "category": [
+            "qdisc",
+            "hfsc"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$TC qdisc replace dev $DUMMY root handle 1: hfsc default 1",
+            "$TC class replace dev $DUMMY parent 1: classid 1:1 hfsc rt m1 32gbit d 1ms m2 0bit ls m1 32gbit d 1ms m2 0bit",
+            "ping -I$DUMMY -f -c1 -s64 -W1 10.10.10.1 || true",
+            "sleep 1"
+        ],
+        "cmdUnderTest": "ping -I$DUMMY -f -c1 -s64 -W1 10.10.10.1 || true",
+        "expExitCode": "0",
+        "verifyCmd": "$TC qdisc show dev $DUMMY",
+        "matchPattern": "qdisc hfsc 1: root",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
     }
 ]
diff --git a/tools/tracing/rtla/src/timerlat_bpf.h b/tools/tracing/rtla/src/timerlat_bpf.h
index 169abeaf4363..f7c5675737fe 100644
--- a/tools/tracing/rtla/src/timerlat_bpf.h
+++ b/tools/tracing/rtla/src/timerlat_bpf.h
@@ -12,7 +12,6 @@ enum summary_field {
 };
 
 #ifndef __bpf__
-#include <bpf/libbpf.h>
 #ifdef HAVE_BPF_SKEL
 int timerlat_bpf_init(struct timerlat_params *params);
 int timerlat_bpf_attach(void);