Merge tag 'irqchip-5.16' into irq/core

Merge irqchip updates for Linux 5.16 from Marc Zyngier:

- A large cross-arch rework to move irq_enter()/irq_exit() into
  the arch code, and removing it from the generic irq code.
  Thanks to Mark Rutland for the huge effort!

- A few irqchip drivers are made modular (broadcom, meson), because
  that's apparently a thing...

- A new driver for the Microchip External Interrupt Controller

- The irq_cpu_offline()/irq_cpu_online() API is now deprecated and
  can only be selected on the Cavium Octeon platform. Once this
  platform is removed, the API will be removed at the same time.

- A sprinkle of devm_* helper, as people seem to love that.

- The usual spattering of small fixes and minor improvements.

* tag 'irqchip-5.16': (912 commits)
  h8300: Fix linux/irqchip.h include mess
  dt-bindings: irqchip: renesas-irqc: Document r8a774e1 bindings
  MIPS: irq: Avoid an unused-variable error
  genirq: Hide irq_cpu_{on,off}line() behind a deprecated option
  irqchip/mips-gic: Get rid of the reliance on irq_cpu_online()
  MIPS: loongson64: Drop call to irq_cpu_offline()
  irq: remove handle_domain_{irq,nmi}()
  irq: remove CONFIG_HANDLE_DOMAIN_IRQ_IRQENTRY
  irq: riscv: perform irqentry in entry code
  irq: openrisc: perform irqentry in entry code
  irq: csky: perform irqentry in entry code
  irq: arm64: perform irqentry in entry code
  irq: arm: perform irqentry in entry code
  irq: add a (temporary) CONFIG_HANDLE_DOMAIN_IRQ_IRQENTRY
  irq: nds32: avoid CONFIG_HANDLE_DOMAIN_IRQ
  irq: arc: avoid CONFIG_HANDLE_DOMAIN_IRQ
  irq: add generic_handle_arch_irq()
  irq: unexport handle_irq_desc()
  irq: simplify handle_domain_{irq,nmi}()
  irq: mips: simplify do_domain_IRQ()
  ...

Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20211029083332.3680101-1-maz@kernel.org

72 files changed, 1592 insertions, 404 deletions

diff --git a/tools/arch/x86/include/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h
index 60a89dba01b6..60a89dba01b6 100644
--- a/tools/arch/x86/include/asm/unistd_32.h
+++ b/tools/arch/x86/include/uapi/asm/unistd_32.h
diff --git a/tools/arch/x86/include/asm/unistd_64.h b/tools/arch/x86/include/uapi/asm/unistd_64.h
index 4205ed4158bf..cb52a3a8b8fc 100644
--- a/tools/arch/x86/include/asm/unistd_64.h
+++ b/tools/arch/x86/include/uapi/asm/unistd_64.h
@@ -1,7 +1,4 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __NR_userfaultfd
-#define __NR_userfaultfd 282
-#endif
 #ifndef __NR_perf_event_open
 # define __NR_perf_event_open 298
 #endif
diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c
index c41f95815480..797699462cd8 100644
--- a/tools/arch/x86/lib/insn.c
+++ b/tools/arch/x86/lib/insn.c
@@ -37,10 +37,10 @@
 	((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr)
 
 #define __get_next(t, insn)	\
-	({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); leXX_to_cpu(t, r); })
+	({ t r; memcpy(&r, insn->next_byte, sizeof(t)); insn->next_byte += sizeof(t); leXX_to_cpu(t, r); })
 
 #define __peek_nbyte_next(t, insn, n)	\
-	({ t r = *(t*)((insn)->next_byte + n); leXX_to_cpu(t, r); })
+	({ t r; memcpy(&r, (insn)->next_byte + n, sizeof(t)); leXX_to_cpu(t, r); })
 
 #define get_next(t, insn)	\
 	({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); })
diff --git a/tools/bootconfig/include/linux/memblock.h b/tools/bootconfig/include/linux/memblock.h
index 7862f217d85d..f2e506f7d57f 100644
--- a/tools/bootconfig/include/linux/memblock.h
+++ b/tools/bootconfig/include/linux/memblock.h
@@ -4,9 +4,8 @@
 
 #include <stdlib.h>
 
-#define __pa(addr)	(addr)
 #define SMP_CACHE_BYTES	0
 #define memblock_alloc(size, align)	malloc(size)
-#define memblock_free(paddr, size)	free(paddr)
+#define memblock_free_ptr(paddr, size)	free(paddr)
 
 #endif
diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
index 95c072b70d0e..8816f06fc6c7 100644
--- a/tools/include/linux/compiler-gcc.h
+++ b/tools/include/linux/compiler-gcc.h
@@ -16,9 +16,9 @@
 # define __fallthrough __attribute__ ((fallthrough))
 #endif
 
-#if GCC_VERSION >= 40300
+#if __has_attribute(__error__)
 # define __compiletime_error(message) __attribute__((error(message)))
-#endif /* GCC_VERSION >= 40300 */
+#endif
 
 /* &a[0] degrades to a pointer: a different type from an array */
 #define __must_be_array(a)	BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
@@ -38,7 +38,3 @@
 #endif
 #define __printf(a, b)	__attribute__((format(printf, a, b)))
 #define __scanf(a, b)	__attribute__((format(scanf, a, b)))
-
-#if GCC_VERSION >= 50100
-#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
-#endif
diff --git a/tools/include/linux/overflow.h b/tools/include/linux/overflow.h
index 8712ff70995f..dcb0c1bf6866 100644
--- a/tools/include/linux/overflow.h
+++ b/tools/include/linux/overflow.h
@@ -5,12 +5,9 @@
 #include <linux/compiler.h>
 
 /*
- * In the fallback code below, we need to compute the minimum and
- * maximum values representable in a given type. These macros may also
- * be useful elsewhere, so we provide them outside the
- * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block.
- *
- * It would seem more obvious to do something like
+ * We need to compute the minimum and maximum values representable in a given
+ * type. These macros may also be useful elsewhere. It would seem more obvious
+ * to do something like:
  *
  * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0)
  * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0)
@@ -36,8 +33,6 @@
 #define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T)))
 #define type_min(T) ((T)((T)-type_max(T)-(T)1))
 
-
-#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW
 /*
  * For simplicity and code hygiene, the fallback code below insists on
  * a, b and *d having the same type (similar to the min() and max()
@@ -73,135 +68,6 @@
 	__builtin_mul_overflow(__a, __b, __d);	\
 })
 
-#else
-
-
-/* Checking for unsigned overflow is relatively easy without causing UB. */
-#define __unsigned_add_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = __a + __b;			\
-	*__d < __a;				\
-})
-#define __unsigned_sub_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = __a - __b;			\
-	__a < __b;				\
-})
-/*
- * If one of a or b is a compile-time constant, this avoids a division.
- */
-#define __unsigned_mul_overflow(a, b, d) ({		\
-	typeof(a) __a = (a);				\
-	typeof(b) __b = (b);				\
-	typeof(d) __d = (d);				\
-	(void) (&__a == &__b);				\
-	(void) (&__a == __d);				\
-	*__d = __a * __b;				\
-	__builtin_constant_p(__b) ?			\
-	  __b > 0 && __a > type_max(typeof(__a)) / __b : \
-	  __a > 0 && __b > type_max(typeof(__b)) / __a;	 \
-})
-
-/*
- * For signed types, detecting overflow is much harder, especially if
- * we want to avoid UB. But the interface of these macros is such that
- * we must provide a result in *d, and in fact we must produce the
- * result promised by gcc's builtins, which is simply the possibly
- * wrapped-around value. Fortunately, we can just formally do the
- * operations in the widest relevant unsigned type (u64) and then
- * truncate the result - gcc is smart enough to generate the same code
- * with and without the (u64) casts.
- */
-
-/*
- * Adding two signed integers can overflow only if they have the same
- * sign, and overflow has happened iff the result has the opposite
- * sign.
- */
-#define __signed_add_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = (u64)__a + (u64)__b;		\
-	(((~(__a ^ __b)) & (*__d ^ __a))	\
-		& type_min(typeof(__a))) != 0;	\
-})
-
-/*
- * Subtraction is similar, except that overflow can now happen only
- * when the signs are opposite. In this case, overflow has happened if
- * the result has the opposite sign of a.
- */
-#define __signed_sub_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = (u64)__a - (u64)__b;		\
-	((((__a ^ __b)) & (*__d ^ __a))		\
-		& type_min(typeof(__a))) != 0;	\
-})
-
-/*
- * Signed multiplication is rather hard. gcc always follows C99, so
- * division is truncated towards 0. This means that we can write the
- * overflow check like this:
- *
- * (a > 0 && (b > MAX/a || b < MIN/a)) ||
- * (a < -1 && (b > MIN/a || b < MAX/a) ||
- * (a == -1 && b == MIN)
- *
- * The redundant casts of -1 are to silence an annoying -Wtype-limits
- * (included in -Wextra) warning: When the type is u8 or u16, the
- * __b_c_e in check_mul_overflow obviously selects
- * __unsigned_mul_overflow, but unfortunately gcc still parses this
- * code and warns about the limited range of __b.
- */
-
-#define __signed_mul_overflow(a, b, d) ({				\
-	typeof(a) __a = (a);						\
-	typeof(b) __b = (b);						\
-	typeof(d) __d = (d);						\
-	typeof(a) __tmax = type_max(typeof(a));				\
-	typeof(a) __tmin = type_min(typeof(a));				\
-	(void) (&__a == &__b);						\
-	(void) (&__a == __d);						\
-	*__d = (u64)__a * (u64)__b;					\
-	(__b > 0   && (__a > __tmax/__b || __a < __tmin/__b)) ||	\
-	(__b < (typeof(__b))-1  && (__a > __tmin/__b || __a < __tmax/__b)) || \
-	(__b == (typeof(__b))-1 && __a == __tmin);			\
-})
-
-
-#define check_add_overflow(a, b, d)					\
-	__builtin_choose_expr(is_signed_type(typeof(a)),		\
-			__signed_add_overflow(a, b, d),			\
-			__unsigned_add_overflow(a, b, d))
-
-#define check_sub_overflow(a, b, d)					\
-	__builtin_choose_expr(is_signed_type(typeof(a)),		\
-			__signed_sub_overflow(a, b, d),			\
-			__unsigned_sub_overflow(a, b, d))
-
-#define check_mul_overflow(a, b, d)					\
-	__builtin_choose_expr(is_signed_type(typeof(a)),		\
-			__signed_mul_overflow(a, b, d),			\
-			__unsigned_mul_overflow(a, b, d))
-
-
-#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */
-
 /**
  * array_size() - Calculate size of 2-dimensional array.
  *
diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
index 10911a8cad0f..2df880cefdae 100644
--- a/tools/lib/bpf/linker.c
+++ b/tools/lib/bpf/linker.c
@@ -1649,11 +1649,17 @@ static bool btf_is_non_static(const struct btf_type *t)
 static int find_glob_sym_btf(struct src_obj *obj, Elf64_Sym *sym, const char *sym_name,
 			     int *out_btf_sec_id, int *out_btf_id)
 {
-	int i, j, n = btf__get_nr_types(obj->btf), m, btf_id = 0;
+	int i, j, n, m, btf_id = 0;
 	const struct btf_type *t;
 	const struct btf_var_secinfo *vi;
 	const char *name;
 
+	if (!obj->btf) {
+		pr_warn("failed to find BTF info for object '%s'\n", obj->filename);
+		return -EINVAL;
+	}
+
+	n = btf__get_nr_types(obj->btf);
 	for (i = 1; i <= n; i++) {
 		t = btf__type_by_id(obj->btf, i);
 
diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
index d8886720e83d..8441e3e1aaac 100644
--- a/tools/lib/perf/evsel.c
+++ b/tools/lib/perf/evsel.c
@@ -43,7 +43,7 @@ void perf_evsel__delete(struct perf_evsel *evsel)
 	free(evsel);
 }
 
-#define FD(e, x, y) (*(int *) xyarray__entry(e->fd, x, y))
+#define FD(e, x, y) ((int *) xyarray__entry(e->fd, x, y))
 #define MMAP(e, x, y) (e->mmap ? ((struct perf_mmap *) xyarray__entry(e->mmap, x, y)) : NULL)
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
@@ -54,7 +54,10 @@ int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 		int cpu, thread;
 		for (cpu = 0; cpu < ncpus; cpu++) {
 			for (thread = 0; thread < nthreads; thread++) {
-				FD(evsel, cpu, thread) = -1;
+				int *fd = FD(evsel, cpu, thread);
+
+				if (fd)
+					*fd = -1;
 			}
 		}
 	}
@@ -80,7 +83,7 @@ sys_perf_event_open(struct perf_event_attr *attr,
 static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *group_fd)
 {
 	struct perf_evsel *leader = evsel->leader;
-	int fd;
+	int *fd;
 
 	if (evsel == leader) {
 		*group_fd = -1;
@@ -95,10 +98,10 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *grou
 		return -ENOTCONN;
 
 	fd = FD(leader, cpu, thread);
-	if (fd == -1)
+	if (fd == NULL || *fd == -1)
 		return -EBADF;
 
-	*group_fd = fd;
+	*group_fd = *fd;
 
 	return 0;
 }
@@ -138,7 +141,11 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 		for (thread = 0; thread < threads->nr; thread++) {
-			int fd, group_fd;
+			int fd, group_fd, *evsel_fd;
+
+			evsel_fd = FD(evsel, cpu, thread);
+			if (evsel_fd == NULL)
+				return -EINVAL;
 
 			err = get_group_fd(evsel, cpu, thread, &group_fd);
 			if (err < 0)
@@ -151,7 +158,7 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 			if (fd < 0)
 				return -errno;
 
-			FD(evsel, cpu, thread) = fd;
+			*evsel_fd = fd;
 		}
 	}
 
@@ -163,9 +170,12 @@ static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu)
 	int thread;
 
 	for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) {
-		if (FD(evsel, cpu, thread) >= 0)
-			close(FD(evsel, cpu, thread));
-		FD(evsel, cpu, thread) = -1;
+		int *fd = FD(evsel, cpu, thread);
+
+		if (fd && *fd >= 0) {
+			close(*fd);
+			*fd = -1;
+		}
 	}
 }
 
@@ -209,13 +219,12 @@ void perf_evsel__munmap(struct perf_evsel *evsel)
 
 	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
 		for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
-			int fd = FD(evsel, cpu, thread);
-			struct perf_mmap *map = MMAP(evsel, cpu, thread);
+			int *fd = FD(evsel, cpu, thread);
 
-			if (fd < 0)
+			if (fd == NULL || *fd < 0)
 				continue;
 
-			perf_mmap__munmap(map);
+			perf_mmap__munmap(MMAP(evsel, cpu, thread));
 		}
 	}
 
@@ -239,15 +248,16 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
 
 	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
 		for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
-			int fd = FD(evsel, cpu, thread);
-			struct perf_mmap *map = MMAP(evsel, cpu, thread);
+			int *fd = FD(evsel, cpu, thread);
+			struct perf_mmap *map;
 
-			if (fd < 0)
+			if (fd == NULL || *fd < 0)
 				continue;
 
+			map = MMAP(evsel, cpu, thread);
 			perf_mmap__init(map, NULL, false, NULL);
 
-			ret = perf_mmap__mmap(map, &mp, fd, cpu);
+			ret = perf_mmap__mmap(map, &mp, *fd, cpu);
 			if (ret) {
 				perf_evsel__munmap(evsel);
 				return ret;
@@ -260,7 +270,9 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
 
 void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread)
 {
-	if (FD(evsel, cpu, thread) < 0 || MMAP(evsel, cpu, thread) == NULL)
+	int *fd = FD(evsel, cpu, thread);
+
+	if (fd == NULL || *fd < 0 || MMAP(evsel, cpu, thread) == NULL)
 		return NULL;
 
 	return MMAP(evsel, cpu, thread)->base;
@@ -295,17 +307,18 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
 		     struct perf_counts_values *count)
 {
 	size_t size = perf_evsel__read_size(evsel);