Merge tag 'perf-tools-fixes-for-v6.12-2-2024-10-30' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Update more header copies with the kernel sources, including const.h,
   msr-index.h, arm64's cputype.h, kvm's, bits.h and unaligned.h

 - The return from 'write' isn't a pid, fix cut'n'paste error in 'perf
   trace'

 - Fix up the python binding build on architectures without
   HAVE_KVM_STAT_SUPPORT

 - Add some more bounds checks to augmented_raw_syscalls.bpf.c (used to
   collect syscall pointer arguments in 'perf trace') to make the
   resulting bytecode to pass the kernel BPF verifier, allowing us to go
   back accepting clang 12.0.1 as the minimum version required for
   compiling BPF sources

 - Add __NR_capget for x86 to fix a regression on running perf + intel
   PT (hw tracing) as non-root setting up the capabilities as described
   in https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html

 - Fix missing syscalltbl in non-explicitly listed architectures,
   noticed on ARM 32-bit, that still needs a .tbl generator for the
   syscall id<->name tables, should be added for v6.13

 - Handle 'perf test' failure when handling broken DWARF for ASM files

* tag 'perf-tools-fixes-for-v6.12-2-2024-10-30' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools:
  perf cap: Add __NR_capget to arch/x86 unistd
  tools headers: Update the linux/unaligned.h copy with the kernel sources
  tools headers arm64: Sync arm64's cputype.h with the kernel sources
  tools headers: Synchronize {uapi/}linux/bits.h with the kernel sources
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  perf python: Fix up the build on architectures without HAVE_KVM_STAT_SUPPORT
  perf test: Handle perftool-testsuite_probe failure due to broken DWARF
  tools headers UAPI: Sync kvm headers with the kernel sources
  perf trace: Fix non-listed archs in the syscalltbl routines
  perf build: Change the clang check back to 12.0.1
  perf trace augmented_raw_syscalls: Add more checks to pass the verifier
  perf trace augmented_raw_syscalls: Add extra array index bounds checking to satisfy some BPF verifiers
  perf trace: The return from 'write' isn't a pid
  tools headers UAPI: Sync linux/const.h with the kernel headers

5 files changed, 51 insertions, 10 deletions

diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
index 0eb24d21aac2..60044b608817 100644
--- a/tools/include/linux/bits.h
+++ b/tools/include/linux/bits.h
@@ -36,4 +36,19 @@
 #define GENMASK_ULL(h, l) \
 	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l))
 
+#if !defined(__ASSEMBLY__)
+/*
+ * Missing asm support
+ *
+ * __GENMASK_U128() depends on _BIT128() which would not work
+ * in the asm code, as it shifts an 'unsigned __init128' data
+ * type instead of direct representation of 128 bit constants
+ * such as long and unsigned long. The fundamental problem is
+ * that a 128 bit constant will get silently truncated by the
+ * gcc compiler.
+ */
+#define GENMASK_U128(h, l) \
+	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_U128(h, l))
+#endif
+
 #endif	/* __LINUX_BITS_H */
diff --git a/tools/include/linux/unaligned.h b/tools/include/linux/unaligned.h
index bc0633bc4650..395a4464fe73 100644
--- a/tools/include/linux/unaligned.h
+++ b/tools/include/linux/unaligned.h
@@ -9,16 +9,7 @@
 #pragma GCC diagnostic push
 #pragma GCC diagnostic ignored "-Wpacked"
 #pragma GCC diagnostic ignored "-Wattributes"
-
-#define __get_unaligned_t(type, ptr) ({						\
-	const struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr);	\
-	__pptr->x;								\
-})
-
-#define __put_unaligned_t(type, val, ptr) do {					\
-	struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr);		\
-	__pptr->x = (val);							\
-} while (0)
+#include <vdso/unaligned.h>
 
 #define get_unaligned(ptr)	__get_unaligned_t(typeof(*(ptr)), (ptr))
 #define put_unaligned(val, ptr) __put_unaligned_t(typeof(*(ptr)), (val), (ptr))
diff --git a/tools/include/uapi/linux/bits.h b/tools/include/uapi/linux/bits.h
index 3c2a101986a3..5ee30f882736 100644
--- a/tools/include/uapi/linux/bits.h
+++ b/tools/include/uapi/linux/bits.h
@@ -12,4 +12,7 @@
         (((~_ULL(0)) - (_ULL(1) << (l)) + 1) & \
          (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h))))
 
+#define __GENMASK_U128(h, l) \
+	((_BIT128((h)) << 1) - (_BIT128(l)))
+
 #endif /* _UAPI_LINUX_BITS_H */
diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h
index a429381e7ca5..e16be0d37746 100644
--- a/tools/include/uapi/linux/const.h
+++ b/tools/include/uapi/linux/const.h
@@ -28,6 +28,23 @@
 #define _BITUL(x)	(_UL(1) << (x))
 #define _BITULL(x)	(_ULL(1) << (x))
 
+#if !defined(__ASSEMBLY__)
+/*
+ * Missing asm support
+ *
+ * __BIT128() would not work in the asm code, as it shifts an
+ * 'unsigned __init128' data type as direct representation of
+ * 128 bit constants is not supported in the gcc compiler, as
+ * they get silently truncated.
+ *
+ * TODO: Please revisit this implementation when gcc compiler
+ * starts representing 128 bit constants directly like long
+ * and unsigned long etc. Subsequently drop the comment for
+ * GENMASK_U128() which would then start supporting asm code.
+ */
+#define _BIT128(x)	((unsigned __int128)(1) << (x))
+#endif
+
 #define __ALIGN_KERNEL(x, a)		__ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1)
 #define __ALIGN_KERNEL_MASK(x, mask)	(((x) + (mask)) & ~(mask))
 
diff --git a/tools/include/vdso/unaligned.h b/tools/include/vdso/unaligned.h
new file mode 100644
index 000000000000..eee3d2a4dbe4
--- /dev/null
+++ b/tools/include/vdso/unaligned.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __VDSO_UNALIGNED_H
+#define __VDSO_UNALIGNED_H
+
+#define __get_unaligned_t(type, ptr) ({						\
+	const struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr);	\
+	__pptr->x;								\
+})
+
+#define __put_unaligned_t(type, val, ptr) do {					\
+	struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr);		\
+	__pptr->x = (val);							\
+} while (0)
+
+#endif /* __VDSO_UNALIGNED_H */