Merge tag 'perf-tools-2020-12-19' of git://git.kernel.org/pub/scm/lin…

…ux/kernel/git/acme/linux

Pull perf tools updates from Arnaldo Carvalho de Melo:
 "perf record:
   - Fix memory leak when using '--user-regs=?' to list registers

  aarch64 support:
   - Add aarch64 registers to 'perf record's' --user-regs command line
     option

  aarch64 hw tracing support:
   - Decode memory tagging properties
   - Improve ARM's auxtrace support
   - Add support for ARMv8.3-SPE

  perf kvm:
   - Add kvm-stat for arm64

  perf stat:
   - Add --quiet option

  Cleanups:
   - Fixup function names wrt what is in libperf and what is in
     tools/perf

  Build:
   - Allow building without libbpf in older systems

  New kernel features:
   - Initial support for data/code page size sample type, more to come

  perf annotate:
   - Support MIPS instruction extended support

  perf stack unwinding:
   - Fix separate debug info files when using elfutils' libdw's unwinder

  perf vendor events:
   - Update Intel's Skylake client events to v50
   - Add JSON metrics for ARM's imx8mm DDR Perf
   - Support printing metric groups for system PMUs

  perf build id:
   - Prep work for supporting having the build id provided by the kernel
     in PERF_RECORD_MMAP2 metadata events

  perf stat:
   - Support regex pattern in --for-each-cgroup

  pipe mode:
   - Allow to use stdio functions for pipe mode
   - Support 'perf report's' --header-only for pipe mode
   - Support pipe mode display in 'perf evlist'

  Documentation:
   - Update information about CAP_PERFMON"

* tag 'perf-tools-2020-12-19' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (134 commits)
  perf mem: Factor out a function to generate sort order
  perf sort: Add sort option for data page size
  perf script: Support data page size
  tools headers UAPI: Update asm-generic/unistd.h
  tools headers cpufeatures: Sync with the kernel sources
  tools headers UAPI: Sync linux/prctl.h with the kernel sources
  tools headers UAPI: Sync linux/fscrypt.h with the kernel sources
  tools headers UAPI: Sync linux/const.h with the kernel headers
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  perf trace beauty: Update copy of linux/socket.h with the kernel sources
  tools headers: Update linux/ctype.h with the kernel sources
  tools headers: Add conditional __has_builtin()
  tools headers: Get tools's linux/compiler.h closer to the kernel's
  tools headers UAPI: Sync linux/stat.h with the kernel sources
  tools headers: Syncronize linux/build_bug.h with the kernel sources
  perf tools: Reformat record's control fd man text
  perf config: Fix example command in manpage to conform to syntax specified in the SYNOPSIS section.
  perf test: Make sample-parsing test aware of PERF_SAMPLE_{CODE,DATA}_PAGE_SIZE
  perf tools: Add support to read build id from compressed elf
  perf debug: Add debug_set_file function
  ...

Documentation/admin-guide/perf-security.rst

@@ -84,11 +84,14 @@ capabilities then providing the process with CAP_PERFMON capability singly
 is recommended as the preferred secure approach to resolve double access
 denial logging related to usage of performance monitoring and observability.
 
-Unprivileged processes using perf_events system call are also subject
-for PTRACE_MODE_READ_REALCREDS ptrace access mode check [7]_ , whose
-outcome determines whether monitoring is permitted. So unprivileged
-processes provided with CAP_SYS_PTRACE capability are effectively
-permitted to pass the check.
+Prior Linux v5.9 unprivileged processes using perf_events system call
+are also subject for PTRACE_MODE_READ_REALCREDS ptrace access mode check
+[7]_ , whose outcome determines whether monitoring is permitted.
+So unprivileged processes provided with CAP_SYS_PTRACE capability are
+effectively permitted to pass the check. Starting from Linux v5.9
+CAP_SYS_PTRACE capability is not required and CAP_PERFMON is enough to
+be provided for processes to make performance monitoring and observability
+operations.
 
 Other capabilities being granted to unprivileged processes can
 effectively enable capturing of additional data required for later
@@ -99,11 +102,11 @@ CAP_SYSLOG capability permits reading kernel space memory addresses from
 Privileged Perf users groups
 ---------------------------------
 
-Mechanisms of capabilities, privileged capability-dumb files [6]_ and
-file system ACLs [10]_ can be used to create dedicated groups of
-privileged Perf users who are permitted to execute performance monitoring
-and observability without scope limits. The following steps can be
-taken to create such groups of privileged Perf users.
+Mechanisms of capabilities, privileged capability-dumb files [6]_,
+file system ACLs [10]_ and sudo [15]_ utility can be used to create
+dedicated groups of privileged Perf users who are permitted to execute
+performance monitoring and observability without limits. The following
+steps can be taken to create such groups of privileged Perf users.
 
 1. Create perf_users group of privileged Perf users, assign perf_users
    group to Perf tool executable and limit access to the executable for
@@ -133,7 +136,7 @@ taken to create such groups of privileged Perf users.
    # getcap perf
    perf = cap_sys_ptrace,cap_syslog,cap_perfmon+ep
 
-If the libcap installed doesn't yet support "cap_perfmon", use "38" instead,
+If the libcap [16]_ installed doesn't yet support "cap_perfmon", use "38" instead,
 i.e.:
 
 ::
@@ -159,6 +162,60 @@ performance monitoring and observability by using functionality of the
 configured Perf tool executable that, when executes, passes perf_events
 subsystem scope checks.
 
+In case Perf tool executable can't be assigned required capabilities (e.g.
+file system is mounted with nosuid option or extended attributes are
+not supported by the file system) then creation of the capabilities
+privileged environment, naturally shell, is possible. The shell provides
+inherent processes with CAP_PERFMON and other required capabilities so that
+performance monitoring and observability operations are available in the
+environment without limits. Access to the environment can be open via sudo
+utility for members of perf_users group only. In order to create such
+environment:
+
+1. Create shell script that uses capsh utility [16]_ to assign CAP_PERFMON
+   and other required capabilities into ambient capability set of the shell
+   process, lock the process security bits after enabling SECBIT_NO_SETUID_FIXUP,
+   SECBIT_NOROOT and SECBIT_NO_CAP_AMBIENT_RAISE bits and then change
+   the process identity to sudo caller of the script who should essentially
+   be a member of perf_users group:
+
+::
+
+   # ls -alh /usr/local/bin/perf.shell
+   -rwxr-xr-x. 1 root root 83 Oct 13 23:57 /usr/local/bin/perf.shell
+   # cat /usr/local/bin/perf.shell
+   exec /usr/sbin/capsh --iab=^cap_perfmon --secbits=239 --user=$SUDO_USER -- -l
+
+2. Extend sudo policy at /etc/sudoers file with a rule for perf_users group:
+
+::
+
+   # grep perf_users /etc/sudoers
+   %perf_users    ALL=/usr/local/bin/perf.shell
+
+3. Check that members of perf_users group have access to the privileged
+   shell and have CAP_PERFMON and other required capabilities enabled
+   in permitted, effective and ambient capability sets of an inherent process:
+
+::
+
+  $ id
+  uid=1003(capsh_test) gid=1004(capsh_test) groups=1004(capsh_test),1000(perf_users) context=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023
+  $ sudo perf.shell
+  [sudo] password for capsh_test:
+  $ grep Cap /proc/self/status
+  CapInh:        0000004000000000
+  CapPrm:        0000004000000000
+  CapEff:        0000004000000000
+  CapBnd:        000000ffffffffff
+  CapAmb:        0000004000000000
+  $ capsh --decode=0000004000000000
+  0x0000004000000000=cap_perfmon
+
+As a result, members of perf_users group have access to the privileged
+environment where they can use tools employing performance monitoring APIs
+governed by CAP_PERFMON Linux capability.
+
 This specific access control management is only available to superuser
 or root running processes with CAP_SETPCAP, CAP_SETFCAP [6]_
 capabilities.
@@ -264,3 +321,5 @@ Bibliography
 .. [12] `<http://man7.org/linux/man-pages/man5/limits.conf.5.html>`_
 .. [13] `<https://sites.google.com/site/fullycapable>`_
 .. [14] `<http://man7.org/linux/man-pages/man8/auditd.8.html>`_
+.. [15] `<https://man7.org/linux/man-pages/man8/sudo.8.html>`_
+.. [16] `<https://git.kernel.org/pub/scm/libs/libcap/libcap.git/>`_

tools/arch/x86/include/asm/cpufeatures.h

@@ -241,6 +241,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
 #define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
 #define X86_FEATURE_TSC_ADJUST		( 9*32+ 1) /* TSC adjustment MSR 0x3B */
+#define X86_FEATURE_SGX			( 9*32+ 2) /* Software Guard Extensions */
 #define X86_FEATURE_BMI1		( 9*32+ 3) /* 1st group bit manipulation extensions */
 #define X86_FEATURE_HLE			( 9*32+ 4) /* Hardware Lock Elision */
 #define X86_FEATURE_AVX2		( 9*32+ 5) /* AVX2 instructions */
@@ -356,6 +357,7 @@
 #define X86_FEATURE_MOVDIRI		(16*32+27) /* MOVDIRI instruction */
 #define X86_FEATURE_MOVDIR64B		(16*32+28) /* MOVDIR64B instruction */
 #define X86_FEATURE_ENQCMD		(16*32+29) /* ENQCMD and ENQCMDS instructions */
+#define X86_FEATURE_SGX_LC		(16*32+30) /* Software Guard Extensions Launch Control */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
 #define X86_FEATURE_OVERFLOW_RECOV	(17*32+ 0) /* MCA overflow recovery support */

tools/arch/x86/include/asm/disabled-features.h

@@ -62,6 +62,12 @@
 # define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31))
 #endif
 
+#ifdef CONFIG_X86_SGX
+# define DISABLE_SGX	0
+#else
+# define DISABLE_SGX	(1 << (X86_FEATURE_SGX & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -74,7 +80,7 @@
 #define DISABLED_MASK6	0
 #define DISABLED_MASK7	(DISABLE_PTI)
 #define DISABLED_MASK8	0
-#define DISABLED_MASK9	(DISABLE_SMAP)
+#define DISABLED_MASK9	(DISABLE_SMAP|DISABLE_SGX)
 #define DISABLED_MASK10	0
 #define DISABLED_MASK11	0
 #define DISABLED_MASK12	0

tools/arch/x86/include/asm/msr-index.h

@@ -139,6 +139,7 @@
 #define MSR_IA32_MCG_CAP		0x00000179
 #define MSR_IA32_MCG_STATUS		0x0000017a
 #define MSR_IA32_MCG_CTL		0x0000017b
+#define MSR_ERROR_CONTROL		0x0000017f
 #define MSR_IA32_MCG_EXT_CTL		0x000004d0
 
 #define MSR_OFFCORE_RSP_0		0x000001a6
@@ -326,8 +327,9 @@
 #define MSR_PP1_ENERGY_STATUS		0x00000641
 #define MSR_PP1_POLICY			0x00000642
 
-#define MSR_AMD_PKG_ENERGY_STATUS	0xc001029b
 #define MSR_AMD_RAPL_POWER_UNIT		0xc0010299
+#define MSR_AMD_CORE_ENERGY_STATUS		0xc001029a
+#define MSR_AMD_PKG_ENERGY_STATUS	0xc001029b
 
 /* Config TDP MSRs */
 #define MSR_CONFIG_TDP_NOMINAL		0x00000648
@@ -609,6 +611,8 @@
 #define FEAT_CTL_LOCKED				BIT(0)
 #define FEAT_CTL_VMX_ENABLED_INSIDE_SMX		BIT(1)
 #define FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX	BIT(2)
+#define FEAT_CTL_SGX_LC_ENABLED			BIT(17)
+#define FEAT_CTL_SGX_ENABLED			BIT(18)
 #define FEAT_CTL_LMCE_ENABLED			BIT(20)
 
 #define MSR_IA32_TSC_ADJUST             0x0000003b
@@ -628,6 +632,12 @@
 #define MSR_IA32_UCODE_WRITE		0x00000079
 #define MSR_IA32_UCODE_REV		0x0000008b
 
+/* Intel SGX Launch Enclave Public Key Hash MSRs */
+#define MSR_IA32_SGXLEPUBKEYHASH0	0x0000008C
+#define MSR_IA32_SGXLEPUBKEYHASH1	0x0000008D
+#define MSR_IA32_SGXLEPUBKEYHASH2	0x0000008E
+#define MSR_IA32_SGXLEPUBKEYHASH3	0x0000008F
+
 #define MSR_IA32_SMM_MONITOR_CTL	0x0000009b
 #define MSR_IA32_SMBASE			0x0000009e
 

tools/build/feature/Makefile

@@ -90,7 +90,7 @@ __BUILDXX = $(CXX) $(CXXFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$(
 ###############################
 
 $(OUTPUT)test-all.bin:
-	$(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -I/usr/include/slang -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd
+	$(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -I/usr/include/slang -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd -lcap
 
 $(OUTPUT)test-hello.bin:
 	$(BUILD)

tools/include/linux/build_bug.h

@@ -79,4 +79,9 @@
 #define __static_assert(expr, msg, ...) _Static_assert(expr, msg)
 #endif // static_assert
 
+#ifdef __GENKSYMS__
+/* genksyms gets confused by _Static_assert */
+#define _Static_assert(expr, ...)
+#endif
+
 #endif	/* _LINUX_BUILD_BUG_H */

tools/include/linux/compiler.h

@@ -2,9 +2,7 @@
 #ifndef _TOOLS_LINUX_COMPILER_H_
 #define _TOOLS_LINUX_COMPILER_H_
 
-#ifdef __GNUC__
-#include <linux/compiler-gcc.h>
-#endif
+#include <linux/compiler_types.h>
 
 #ifndef __compiletime_error
 # define __compiletime_error(message)

tools/include/linux/compiler_types.h

@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_COMPILER_TYPES_H
+#define __LINUX_COMPILER_TYPES_H
+
+/* Builtins */
+
+/*
+ * __has_builtin is supported on gcc >= 10, clang >= 3 and icc >= 21.
+ * In the meantime, to support gcc < 10, we implement __has_builtin
+ * by hand.
+ */
+#ifndef __has_builtin
+#define __has_builtin(x) (0)
+#endif
+
+/* Compiler specific macros. */
+#ifdef __GNUC__
+#include <linux/compiler-gcc.h>
+#endif
+
+#endif /* __LINUX_COMPILER_TYPES_H */

tools/include/linux/ctype.h

@@ -2,6 +2,8 @@
 #ifndef _LINUX_CTYPE_H
 #define _LINUX_CTYPE_H
 
+#include <linux/compiler.h>
+
 /*
  * NOTE! This ctype does not handle EOF like the standard C
  * library is required to.
@@ -23,11 +25,6 @@ extern const unsigned char _ctype[];
 #define isalnum(c)	((__ismask(c)&(_U|_L|_D)) != 0)
 #define isalpha(c)	((__ismask(c)&(_U|_L)) != 0)
 #define iscntrl(c)	((__ismask(c)&(_C)) != 0)
-static inline int __isdigit(int c)
-{
-	return '0' <= c && c <= '9';
-}
-#define isdigit(c)	__isdigit(c)
 #define isgraph(c)	((__ismask(c)&(_P|_U|_L|_D)) != 0)
 #define islower(c)	((__ismask(c)&(_L)) != 0)
 #define isprint(c)	((__ismask(c)&(_P|_U|_L|_D|_SP)) != 0)
@@ -40,6 +37,16 @@ static inline int __isdigit(int c)
 #define isascii(c) (((unsigned char)(c))<=0x7f)
 #define toascii(c) (((unsigned char)(c))&0x7f)
 
+#if __has_builtin(__builtin_isdigit)
+#define  isdigit(c) __builtin_isdigit(c)
+#else
+static inline int __isdigit(int c)
+{
+	return '0' <= c && c <= '9';
+}
+#define  isdigit(c) __isdigit(c)
+#endif
+
 static inline unsigned char __tolower(unsigned char c)
 {
 	if (isupper(c))

tools/include/linux/string.h

@@ -46,4 +46,5 @@ extern char * __must_check skip_spaces(const char *);
 
 extern char *strim(char *);
 
+extern void *memchr_inv(const void *start, int c, size_t bytes);
 #endif /* _TOOLS_LINUX_STRING_H_ */

tools/include/uapi/asm-generic/unistd.h

@@ -517,7 +517,7 @@ __SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday)
 __SC_3264(__NR_adjtimex, sys_adjtimex_time32, sys_adjtimex)
 #endif
 
-/* kernel/timer.c */
+/* kernel/sys.c */
 #define __NR_getpid 172
 __SYSCALL(__NR_getpid, sys_getpid)
 #define __NR_getppid 173

tools/include/uapi/linux/const.h

@@ -28,4 +28,9 @@
 #define _BITUL(x)	(_UL(1) << (x))
 #define _BITULL(x)	(_ULL(1) << (x))
 
+#define __ALIGN_KERNEL(x, a)		__ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
+#define __ALIGN_KERNEL_MASK(x, mask)	(((x) + (mask)) & ~(mask))
+
+#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
+
 #endif /* _UAPI_LINUX_CONST_H */

tools/include/uapi/linux/fscrypt.h

@@ -20,15 +20,14 @@
 #define FSCRYPT_POLICY_FLAG_DIRECT_KEY		0x04
 #define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64	0x08
 #define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32	0x10
-#define FSCRYPT_POLICY_FLAGS_VALID		0x1F
 
 /* Encryption algorithms */
 #define FSCRYPT_MODE_AES_256_XTS		1
 #define FSCRYPT_MODE_AES_256_CTS		4
 #define FSCRYPT_MODE_AES_128_CBC		5
 #define FSCRYPT_MODE_AES_128_CTS		6
 #define FSCRYPT_MODE_ADIANTUM			9
-#define __FSCRYPT_MODE_MAX			9
+/* If adding a mode number > 9, update FSCRYPT_MODE_MAX in fscrypt_private.h */
 
 /*
  * Legacy policy version; ad-hoc KDF and no key verification.
@@ -177,7 +176,7 @@ struct fscrypt_get_key_status_arg {
 #define FS_POLICY_FLAGS_PAD_32		FSCRYPT_POLICY_FLAGS_PAD_32
 #define FS_POLICY_FLAGS_PAD_MASK	FSCRYPT_POLICY_FLAGS_PAD_MASK
 #define FS_POLICY_FLAG_DIRECT_KEY	FSCRYPT_POLICY_FLAG_DIRECT_KEY
-#define FS_POLICY_FLAGS_VALID		FSCRYPT_POLICY_FLAGS_VALID
+#define FS_POLICY_FLAGS_VALID		0x07	/* contains old flags only */
 #define FS_ENCRYPTION_MODE_INVALID	0	/* never used */
 #define FS_ENCRYPTION_MODE_AES_256_XTS	FSCRYPT_MODE_AES_256_XTS
 #define FS_ENCRYPTION_MODE_AES_256_GCM	2	/* never used */

tools/include/uapi/linux/perf_event.h

@@ -143,8 +143,10 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_PHYS_ADDR			= 1U << 19,
 	PERF_SAMPLE_AUX				= 1U << 20,
 	PERF_SAMPLE_CGROUP			= 1U << 21,
+	PERF_SAMPLE_DATA_PAGE_SIZE		= 1U << 22,
+	PERF_SAMPLE_CODE_PAGE_SIZE		= 1U << 23,
 
-	PERF_SAMPLE_MAX = 1U << 22,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 24,		/* non-ABI */
 
 	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63, /* non-ABI; internal use */
 };
@@ -896,6 +898,8 @@ enum perf_event_type {
 	 *	{ u64			phys_addr;} && PERF_SAMPLE_PHYS_ADDR
 	 *	{ u64			size;
 	 *	  char			data[size]; } && PERF_SAMPLE_AUX
+	 *	{ u64			data_page_size;} && PERF_SAMPLE_DATA_PAGE_SIZE
+	 *	{ u64			code_page_size;} && PERF_SAMPLE_CODE_PAGE_SIZE
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,

tools/include/uapi/linux/prctl.h

@@ -247,4 +247,9 @@ struct prctl_mm_map {
 #define PR_SET_IO_FLUSHER		57
 #define PR_GET_IO_FLUSHER		58
 
+/* Dispatch syscalls to a userspace handler */
+#define PR_SET_SYSCALL_USER_DISPATCH	59
+# define PR_SYS_DISPATCH_OFF		0
+# define PR_SYS_DISPATCH_ON		1
+
 #endif /* _LINUX_PRCTL_H */

tools/include/uapi/linux/stat.h

@@ -171,9 +171,12 @@ struct statx {
  * be of use to ordinary userspace programs such as GUIs or ls rather than
  * specialised tools.
  *
- * Note that the flags marked [I] correspond to generic FS_IOC_FLAGS
+ * Note that the flags marked [I] correspond to the FS_IOC_SETFLAGS flags
  * semantically.  Where possible, the numerical value is picked to correspond
- * also.
+ * also.  Note that the DAX attribute indicates that the file is in the CPU
+ * direct access state.  It does not correspond to the per-inode flag that
+ * some filesystems support.
+ *
  */
 #define STATX_ATTR_COMPRESSED		0x00000004 /* [I] File is compressed by the fs */
 #define STATX_ATTR_IMMUTABLE		0x00000010 /* [I] File is marked immutable */
@@ -183,7 +186,7 @@ struct statx {
 #define STATX_ATTR_AUTOMOUNT		0x00001000 /* Dir: Automount trigger */
 #define STATX_ATTR_MOUNT_ROOT		0x00002000 /* Root of a mount */
 #define STATX_ATTR_VERITY		0x00100000 /* [I] Verity protected file */
-#define STATX_ATTR_DAX			0x00002000 /* [I] File is DAX */
+#define STATX_ATTR_DAX			0x00200000 /* File is currently in DAX state */
 
 
 #endif /* _UAPI_LINUX_STAT_H */