Merge branch 'bpf-fix-broken-uapi-for-pt-regs'

Hendrik Brueckner says:

====================
Perf tool bpf selftests revealed a broken uapi for s390 and arm64.
With the BPF_PROG_TYPE_PERF_EVENT program type the bpf_perf_event
structure exports the pt_regs structure for all architectures.

This fails for s390 and arm64 because pt_regs are not part of the
user api and kept in-kernel only.  To mitigate the broken uapi,
introduce a wrapper that exports pt_regs in an asm-generic way.
For arm64, export the exising user_pt_regs structure.  For s390,
introduce a user_pt_regs structure that exports the beginning of
pt_regs.

Note that user_pt_regs must export from the beginning of pt_regs
as BPF_PROG_TYPE_PERF_EVENT program type is not the only type for
running BPF programs.

Some more background:

  For the bpf_perf_event, there is a uapi definition that is
  passed to the BPF program.  For other "probe" points like
  trace points, kprobes, and uprobes, there is no uapi and the
  BPF program is always passed pt_regs (which is OK as the BPF
  program runs in the kernel context).  The perf tool can attach
  BPF programs to all of these "probe" points and, optionally,
  can create a BPF prologue to access particular arguments
  (passed as registers).  For this, it uses DWARF/CFI
  information to obtain the register and calls a perf-arch
  backend function, regs_query_register_offset().  This function
  returns the index into (user_)pt_regs for a particular
  register.  Then, perf creates a BPF prologue that accesses
  this register based on the passed stucture from the "probe"
  point.

Part of this series, are also updates to the testing and bpf selftest
to deal with asm-specifics.  To complete the bpf support in perf, the
the regs_query_register_offset function is added for s390 to support
BPF prologue creation.

Changelog v1 -> v2:
- Correct kbuild test bot issues by including
  asm-generic/bpf_perf_event.h for archictectures that do not have
  their own asm version.
- Added patch to clean-up whitespace and coding style issues in s390
  asm/ptrace.h (#4/6) as suggested by Alexei.
====================
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

arch/alpha/include/uapi/asm/Kbuild

 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
+
+generic-y += bpf_perf_event.h

arch/arc/include/uapi/asm/Kbuild

@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h

arch/arm/include/uapi/asm/Kbuild

@@ -7,6 +7,7 @@ generated-y += unistd-oabi.h
 generated-y += unistd-eabi.h
 
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h

arch/arm64/include/asm/perf_event.h

@@ -18,6 +18,7 @@
 #define __ASM_PERF_EVENT_H
 
 #include <asm/stack_pointer.h>
+#include <asm/ptrace.h>
 
 #define	ARMV8_PMU_MAX_COUNTERS	32
 #define	ARMV8_PMU_COUNTER_MASK	(ARMV8_PMU_MAX_COUNTERS - 1)
@@ -79,6 +80,7 @@ struct pt_regs;
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 extern unsigned long perf_misc_flags(struct pt_regs *regs);
 #define perf_misc_flags(regs)	perf_misc_flags(regs)
+#define perf_arch_bpf_user_pt_regs(regs) &regs->user_regs
 #endif
 
 #define perf_arch_fetch_caller_regs(regs, __ip) { \

arch/arm64/include/uapi/asm/bpf_perf_event.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_BPF_PERF_EVENT_H__
+
+#include <asm/ptrace.h>
+
+typedef struct user_pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */

arch/blackfin/include/uapi/asm/Kbuild

@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h

arch/c6x/include/uapi/asm/Kbuild

@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h

arch/cris/include/uapi/asm/Kbuild

@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h

arch/frv/include/uapi/asm/Kbuild

 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
+
+generic-y += bpf_perf_event.h

arch/h8300/include/uapi/asm/Kbuild

@@ -2,6 +2,7 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h

arch/hexagon/include/uapi/asm/Kbuild

@@ -2,6 +2,7 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h

arch/ia64/include/uapi/asm/Kbuild

 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y += bpf_perf_event.h
 generic-y += kvm_para.h

arch/m32r/include/uapi/asm/Kbuild

 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y += bpf_perf_event.h
 generic-y += kvm_para.h
 generic-y += siginfo.h

arch/m68k/include/uapi/asm/Kbuild

@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h

arch/metag/include/uapi/asm/Kbuild

@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h

arch/microblaze/include/uapi/asm/Kbuild

@@ -2,6 +2,7 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h

arch/mips/include/uapi/asm/Kbuild

 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y += bpf_perf_event.h
 generic-y += ipcbuf.h

arch/mn10300/include/uapi/asm/Kbuild

 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y	+= bpf_perf_event.h
 generic-y	+= siginfo.h

arch/nios2/include/uapi/asm/Kbuild

@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h

arch/openrisc/include/uapi/asm/Kbuild

@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h

arch/parisc/include/uapi/asm/Kbuild

@@ -2,6 +2,7 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
+generic-y += bpf_perf_event.h
 generic-y += kvm_para.h
 generic-y += param.h
 generic-y += poll.h

arch/powerpc/include/uapi/asm/Kbuild

 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y += bpf_perf_event.h
 generic-y += param.h
 generic-y += poll.h
 generic-y += resource.h

arch/riscv/include/uapi/asm/Kbuild

@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += setup.h
 generic-y += unistd.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h

arch/s390/include/asm/perf_event.h

@@ -40,6 +40,7 @@ struct pt_regs;
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 extern unsigned long perf_misc_flags(struct pt_regs *regs);
 #define perf_misc_flags(regs) perf_misc_flags(regs)
+#define perf_arch_bpf_user_pt_regs(regs) &regs->user_regs
 
 /* Perf pt_regs extension for sample-data-entry indicators */
 struct perf_sf_sde_regs {

arch/s390/include/asm/ptrace.h

@@ -74,9 +74,14 @@ enum {
  */
 struct pt_regs 
 {
-	unsigned long args[1];
-	psw_t psw;
-	unsigned long gprs[NUM_GPRS];
+	union {
+		user_pt_regs user_regs;
+		struct {
+			unsigned long args[1];
+			psw_t psw;
+			unsigned long gprs[NUM_GPRS];
+		};
+	};
 	unsigned long orig_gpr2;
 	unsigned int int_code;
 	unsigned int int_parm;

arch/s390/include/uapi/asm/bpf_perf_event.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_BPF_PERF_EVENT_H__
+
+#include <asm/ptrace.h>
+
+typedef user_pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */

arch/s390/include/uapi/asm/ptrace.h

@@ -162,7 +162,7 @@
 #define GPR_SIZE	8
 #define CR_SIZE		8
 
-#define STACK_FRAME_OVERHEAD    160      /* size of minimum stack frame */
+#define STACK_FRAME_OVERHEAD	160	 /* size of minimum stack frame */
 
 #endif /* __s390x__ */
 
@@ -179,17 +179,16 @@
 #define ACR_SIZE	4
 
 
-#define PTRACE_OLDSETOPTIONS         21
+#define PTRACE_OLDSETOPTIONS	     21
 
 #ifndef __ASSEMBLY__
 #include <linux/stddef.h>
 #include <linux/types.h>
 
-typedef union
-{
-	float   f;
-	double  d;
-        __u64   ui;
+typedef union {
+	float	f;
+	double	d;
+	__u64	ui;
 	struct
 	{
 		__u32 hi;
@@ -197,23 +196,21 @@ typedef union
 	} fp;
 } freg_t;
 
-typedef struct
-{
-	__u32   fpc;
+typedef struct {
+	__u32	fpc;
 	__u32	pad;
-	freg_t  fprs[NUM_FPRS];              
+	freg_t	fprs[NUM_FPRS];
 } s390_fp_regs;
 
-#define FPC_EXCEPTION_MASK      0xF8000000
-#define FPC_FLAGS_MASK          0x00F80000
-#define FPC_DXC_MASK            0x0000FF00
-#define FPC_RM_MASK             0x00000003
+#define FPC_EXCEPTION_MASK	0xF8000000
+#define FPC_FLAGS_MASK		0x00F80000
+#define FPC_DXC_MASK		0x0000FF00
+#define FPC_RM_MASK		0x00000003
 
 /* this typedef defines how a Program Status Word looks like */
-typedef struct 
-{
-        unsigned long mask;
-        unsigned long addr;
+typedef struct {
+	unsigned long mask;
+	unsigned long addr;
 } __attribute__ ((aligned(8))) psw_t;
 
 #ifndef __s390x__
@@ -282,33 +279,40 @@ typedef struct
 /*
  * The s390_regs structure is used to define the elf_gregset_t.
  */
-typedef struct
-{
+typedef struct {
 	psw_t psw;
 	unsigned long gprs[NUM_GPRS];
 	unsigned int  acrs[NUM_ACRS];
 	unsigned long orig_gpr2;
 } s390_regs;
 
+/*
+ * The user_pt_regs structure exports the beginning of
+ * the in-kernel pt_regs structure to user space.
+ */
+typedef struct {
+	unsigned long args[1];
+	psw_t psw;
+	unsigned long gprs[NUM_GPRS];
+} user_pt_regs;
+
 /*
  * Now for the user space program event recording (trace) definitions.
  * The following structures are used only for the ptrace interface, don't
  * touch or even look at it if you don't want to modify the user-space
  * ptrace interface. In particular stay away from it for in-kernel PER.
  */
-typedef struct
-{
+typedef struct {
 	unsigned long cr[NUM_CR_WORDS];
 } per_cr_words;
 
 #define PER_EM_MASK 0xE8000000UL
 
-typedef	struct
-{
+typedef struct {
 #ifdef __s390x__
-	unsigned                       : 32;
+	unsigned		       : 32;
 #endif /* __s390x__ */
-	unsigned em_branching          : 1;
+	unsigned em_branching	       : 1;
 	unsigned em_instruction_fetch  : 1;
 	/*
 	 * Switching on storage alteration automatically fixes
@@ -317,44 +321,41 @@ typedef	struct
 	unsigned em_storage_alteration : 1;
 	unsigned em_gpr_alt_unused     : 1;
 	unsigned em_store_real_address : 1;
-	unsigned                       : 3;
+	unsigned		       : 3;
 	unsigned branch_addr_ctl       : 1;
-	unsigned                       : 1;
+	unsigned		       : 1;
 	unsigned storage_alt_space_ctl : 1;
-	unsigned                       : 21;
+	unsigned		       : 21;
 	unsigned long starting_addr;
 	unsigned long ending_addr;
 } per_cr_bits;
 
-typedef struct
-{
+typedef struct {
 	unsigned short perc_atmid;
 	unsigned long address;
 	unsigned char access_id;
 } per_lowcore_words;
 
-typedef struct
-{
-	unsigned perc_branching          : 1;
+typedef struct {
+	unsigned perc_branching		 : 1;
 	unsigned perc_instruction_fetch  : 1;
 	unsigned perc_storage_alteration : 1;
-	unsigned perc_gpr_alt_unused     : 1;
+	unsigned perc_gpr_alt_unused	 : 1;
 	unsigned perc_store_real_address : 1;
-	unsigned                         : 3;
-	unsigned atmid_psw_bit_31        : 1;
-	unsigned atmid_validity_bit      : 1;
-	unsigned atmid_psw_bit_32        : 1;
-	unsigned atmid_psw_bit_5         : 1;
-	unsigned atmid_psw_bit_16        : 1;
-	unsigned atmid_psw_bit_17        : 1;
-	unsigned si                      : 2;
+	unsigned			 : 3;
+	unsigned atmid_psw_bit_31	 : 1;
+	unsigned atmid_validity_bit	 : 1;
+	unsigned atmid_psw_bit_32	 : 1;
+	unsigned atmid_psw_bit_5	 : 1;
+	unsigned atmid_psw_bit_16	 : 1;
+	unsigned atmid_psw_bit_17	 : 1;
+	unsigned si			 : 2;
 	unsigned long address;
-	unsigned                         : 4;
-	unsigned access_id               : 4;
+	unsigned			 : 4;
+	unsigned access_id		 : 4;
 } per_lowcore_bits;
 
-typedef struct
-{
+typedef struct {
 	union {
 		per_cr_words   words;
 		per_cr_bits    bits;
@@ -364,9 +365,9 @@ typedef struct
 	 * the kernel always sets them to zero. To enable single
 	 * stepping use ptrace(PTRACE_SINGLESTEP) instead.
 	 */
-	unsigned  single_step       : 1;
+	unsigned  single_step	    : 1;
 	unsigned  instruction_fetch : 1;
-	unsigned                    : 30;
+	unsigned		    : 30;
 	/*
 	 * These addresses are copied into cr10 & cr11 if single
 	 * stepping is switched off
@@ -376,11 +377,10 @@ typedef struct
 	union {
 		per_lowcore_words words;
 		per_lowcore_bits  bits;
-	} lowcore; 
+	} lowcore;
 } per_struct;
 
-typedef struct
-{
+typedef struct {
 	unsigned int  len;
 	unsigned long kernel_addr;
 	unsigned long process_addr;
@@ -390,12 +390,12 @@ typedef struct
  * S/390 specific non posix ptrace requests. I chose unusual values so
  * they are unlikely to clash with future ptrace definitions.
  */
-#define PTRACE_PEEKUSR_AREA           0x5000
-#define PTRACE_POKEUSR_AREA           0x5001
+#define PTRACE_PEEKUSR_AREA	      0x5000
+#define PTRACE_POKEUSR_AREA	      0x5001
 #define PTRACE_PEEKTEXT_AREA	      0x5002
 #define PTRACE_PEEKDATA_AREA	      0x5003
 #define PTRACE_POKETEXT_AREA	      0x5004
-#define PTRACE_POKEDATA_AREA 	      0x5005
+#define PTRACE_POKEDATA_AREA	      0x5005
 #define PTRACE_GET_LAST_BREAK	      0x5006
 #define PTRACE_PEEK_SYSTEM_CALL       0x5007
 #define PTRACE_POKE_SYSTEM_CALL	      0x5008
@@ -413,21 +413,19 @@ typedef struct
  * PT_PROT definition is loosely based on hppa bsd definition in
  * gdb/hppab-nat.c
  */
-#define PTRACE_PROT                       21
+#define PTRACE_PROT			  21
 
-typedef enum
-{
+typedef enum {
 	ptprot_set_access_watchpoint,
 	ptprot_set_write_watchpoint,
 	ptprot_disable_watchpoint
 } ptprot_flags;
 
-typedef struct
-{
+typedef struct {
 	unsigned long lowaddr;
 	unsigned long hiaddr;
 	ptprot_flags prot;
-} ptprot_area;                     
+} ptprot_area;
 
 /* Sequence of bytes for breakpoint illegal instruction.  */
 #define S390_BREAKPOINT     {0x0,0x1}
@@ -439,8 +437,7 @@ typedef struct
  * The user_regs_struct defines the way the user registers are
  * store on the stack for signal handling.
  */
-struct user_regs_struct
-{
+struct user_regs_struct {
 	psw_t psw;
 	unsigned long gprs[NUM_GPRS];
 	unsigned int  acrs[NUM_ACRS];

arch/score/include/uapi/asm/Kbuild

 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y	+= bpf_perf_event.h
 generic-y	+= siginfo.h

arch/sh/include/uapi/asm/Kbuild

@@ -2,6 +2,7 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h

arch/sparc/include/uapi/asm/Kbuild

 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y += bpf_perf_event.h
 generic-y += types.h

arch/tile/include/uapi/asm/Kbuild

 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h

arch/unicore32/include/uapi/asm/Kbuild

@@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += auxvec.h
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h

arch/x86/include/uapi/asm/Kbuild

 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y += bpf_perf_event.h
 generated-y += unistd_32.h
 generated-y += unistd_64.h
 generated-y += unistd_x32.h

arch/xtensa/include/uapi/asm/Kbuild

@@ -2,6 +2,7 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += bitsperlong.h
+generic-y += bpf_perf_event.h
 generic-y += errno.h
 generic-y += fcntl.h
 generic-y += ioctl.h

include/linux/perf_event.h

@@ -15,6 +15,7 @@
 #define _LINUX_PERF_EVENT_H
 
 #include <uapi/linux/perf_event.h>
+#include <uapi/linux/bpf_perf_event.h>
 
 /*
  * Kernel-internal data types and definitions:
@@ -787,7 +788,7 @@ struct perf_output_handle {
 };
 
 struct bpf_perf_event_data_kern {
-	struct pt_regs *regs;
+	bpf_user_pt_regs_t *regs;
 	struct perf_sample_data *data;
 	struct perf_event *event;
 };
@@ -1177,6 +1178,9 @@ extern void perf_bp_event(struct perf_event *event, void *data);
 		(user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL)
 # define perf_instruction_pointer(regs)	instruction_pointer(regs)
 #endif
+#ifndef perf_arch_bpf_user_pt_regs
+# define perf_arch_bpf_user_pt_regs(regs) regs
+#endif
 
 static inline bool has_branch_stack(struct perf_event *event)
 {

include/uapi/asm-generic/bpf_perf_event.h

+#ifndef _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__
+
+#include <linux/ptrace.h>
+
+/* Export kernel pt_regs structure */
+typedef struct pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__ */

include/uapi/linux/bpf_perf_event.h

@@ -8,11 +8,10 @@
 #ifndef _UAPI__LINUX_BPF_PERF_EVENT_H__
 #define _UAPI__LINUX_BPF_PERF_EVENT_H__
 
-#include <linux/types.h>
-#include <linux/ptrace.h>
+#include <asm/bpf_perf_event.h>
 
 struct bpf_perf_event_data {
-	struct pt_regs regs;
+	bpf_user_pt_regs_t regs;
 	__u64 sample_period;
 };
 

kernel/events/core.c

@@ -7987,11 +7987,11 @@ static void bpf_overflow_handler(struct perf_event *event,
 {
 	struct bpf_perf_event_data_kern ctx = {
 		.data = data,
-		.regs = regs,
 		.event = event,
 	};
 	int ret = 0;
 
+	ctx.regs = perf_arch_bpf_user_pt_regs(regs);
 	preempt_disable();
 	if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1))
 		goto out;

tools/arch/arm64/include/uapi/asm/bpf_perf_event.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_BPF_PERF_EVENT_H__
+
+#include <asm/ptrace.h>
+
+typedef struct user_pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */

tools/arch/s390/include/uapi/asm/bpf_perf_event.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_BPF_PERF_EVENT_H__
+
+#include <asm/ptrace.h>
+
+typedef user_pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */

tools/arch/s390/include/uapi/asm/ptrace.h

+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ *  S390 version
+ *    Copyright IBM Corp. 1999, 2000
+ *    Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com)
+ */
+
+#ifndef _UAPI_S390_PTRACE_H
+#define _UAPI_S390_PTRACE_H
+
+/*
+ * Offsets in the user_regs_struct. They are used for the ptrace
+ * system call and in entry.S
+ */
+#ifndef __s390x__
+
+#define PT_PSWMASK  0x00
+#define PT_PSWADDR  0x04
+#define PT_GPR0     0x08
+#define PT_GPR1     0x0C
+#define PT_GPR2     0x10
+#define PT_GPR3     0x14
+#define PT_GPR4     0x18
+#define PT_GPR5     0x1C
+#define PT_GPR6     0x20
+#define PT_GPR7     0x24
+#define PT_GPR8     0x28
+#define PT_GPR9     0x2C
+#define PT_GPR10    0x30
+#define PT_GPR11    0x34
+#define PT_GPR12    0x38
+#define PT_GPR13    0x3C
+#define PT_GPR14    0x40
+#define PT_GPR15    0x44
+#define PT_ACR0     0x48
+#define PT_ACR1     0x4C
+#define PT_ACR2     0x50
+#define PT_ACR3     0x54
+#define PT_ACR4	    0x58
+#define PT_ACR5	    0x5C
+#define PT_ACR6	    0x60
+#define PT_ACR7	    0x64
+#define PT_ACR8	    0x68
+#define PT_ACR9	    0x6C
+#define PT_ACR10    0x70
+#define PT_ACR11    0x74
+#define PT_ACR12    0x78
+#define PT_ACR13    0x7C
+#define PT_ACR14    0x80
+#define PT_ACR15    0x84
+#define PT_ORIGGPR2 0x88
+#define PT_FPC	    0x90
+/*
+ * A nasty fact of life that the ptrace api
+ * only supports passing of longs.
+ */
+#define PT_FPR0_HI  0x98
+#define PT_FPR0_LO  0x9C
+#define PT_FPR1_HI  0xA0
+#define PT_FPR1_LO  0xA4
+#define PT_FPR2_HI  0xA8
+#define PT_FPR2_LO  0xAC
+#define PT_FPR3_HI  0xB0
+#define PT_FPR3_LO  0xB4
+#define PT_FPR4_HI  0xB8
+#define PT_FPR4_LO  0xBC
+#define PT_FPR5_HI  0xC0
+#define PT_FPR5_LO  0xC4
+#define PT_FPR6_HI  0xC8
+#define PT_FPR6_LO  0xCC
+#define PT_FPR7_HI  0xD0
+#define PT_FPR7_LO  0xD4
+#define PT_FPR8_HI  0xD8
+#define PT_FPR8_LO  0XDC
+#define PT_FPR9_HI  0xE0
+#define PT_FPR9_LO  0xE4
+#define PT_FPR10_HI 0xE8
+#define PT_FPR10_LO 0xEC
+#define PT_FPR11_HI 0xF0
+#define PT_FPR11_LO 0xF4
+#define PT_FPR12_HI 0xF8
+#define PT_FPR12_LO 0xFC
+#define PT_FPR13_HI 0x100
+#define PT_FPR13_LO 0x104
+#define PT_FPR14_HI 0x108
+#define PT_FPR14_LO 0x10C
+#define PT_FPR15_HI 0x110
+#define PT_FPR15_LO 0x114
+#define PT_CR_9	    0x118
+#define PT_CR_10    0x11C
+#define PT_CR_11    0x120
+#define PT_IEEE_IP  0x13C
+#define PT_LASTOFF  PT_IEEE_IP
+#define PT_ENDREGS  0x140-1
+
+#define GPR_SIZE	4
+#define CR_SIZE		4
+
+#define STACK_FRAME_OVERHEAD	96	/* size of minimum stack frame */
+
+#else /* __s390x__ */
+
+#define PT_PSWMASK  0x00
+#define PT_PSWADDR  0x08
+#define PT_GPR0     0x10
+#define PT_GPR1     0x18
+#define PT_GPR2     0x20
+#define PT_GPR3     0x28
+#define PT_GPR4     0x30
+#define PT_GPR5     0x38
+#define PT_GPR6     0x40
+#define PT_GPR7     0x48
+#define PT_GPR8     0x50
+#define PT_GPR9     0x58
+#define PT_GPR10    0x60
+#define PT_GPR11    0x68
+#define PT_GPR12    0x70
+#define PT_GPR13    0x78
+#define PT_GPR14    0x80
+#define PT_GPR15    0x88
+#define PT_ACR0     0x90
+#define PT_ACR1     0x94
+#define PT_ACR2     0x98
+#define PT_ACR3     0x9C
+#define PT_ACR4	    0xA0
+#define PT_ACR5	    0xA4
+#define PT_ACR6	    0xA8
+#define PT_ACR7	    0xAC
+#define PT_ACR8	    0xB0
+#define PT_ACR9	    0xB4
+#define PT_ACR10    0xB8
+#define PT_ACR11    0xBC
+#define PT_ACR12    0xC0
+#define PT_ACR13    0xC4
+#define PT_ACR14    0xC8
+#define PT_ACR15    0xCC
+#define PT_ORIGGPR2 0xD0
+#define PT_FPC	    0xD8
+#define PT_FPR0     0xE0
+#define PT_FPR1     0xE8
+#define PT_FPR2     0xF0
+#define PT_FPR3     0xF8
+#define PT_FPR4     0x100
+#define PT_FPR5     0x108
+#define PT_FPR6     0x110
+#define PT_FPR7     0x118
+#define PT_FPR8     0x120
+#define PT_FPR9     0x128
+#define PT_FPR10    0x130
+#define PT_FPR11    0x138
+#define PT_FPR12    0x140
+#define PT_FPR13    0x148
+#define PT_FPR14    0x150
+#define PT_FPR15    0x158
+#define PT_CR_9     0x160
+#define PT_CR_10    0x168
+#define PT_CR_11    0x170
+#define PT_IEEE_IP  0x1A8
+#define PT_LASTOFF  PT_IEEE_IP
+#define PT_ENDREGS  0x1B0-1
+
+#define GPR_SIZE	8
+#define CR_SIZE		8
+
+#define STACK_FRAME_OVERHEAD	160	 /* size of minimum stack frame */
+
+#endif /* __s390x__ */
+
+#define NUM_GPRS	16
+#define NUM_FPRS	16
+#define NUM_CRS		16
+#define NUM_ACRS	16
+
+#define NUM_CR_WORDS	3
+
+#define FPR_SIZE	8
+#define FPC_SIZE	4
+#define FPC_PAD_SIZE	4 /* gcc insists on aligning the fpregs */
+#define ACR_SIZE	4
+
+
+#define PTRACE_OLDSETOPTIONS	     21
+
+#ifndef __ASSEMBLY__
+#include <linux/stddef.h>
+#include <linux/types.h>
+
+typedef union {
+	float	f;
+	double	d;
+	__u64	ui;
+	struct
+	{
+		__u32 hi;
+		__u32 lo;
+	} fp;
+} freg_t;
+
+typedef struct {
+	__u32	fpc;
+	__u32	pad;
+	freg_t	fprs[NUM_FPRS];
+} s390_fp_regs;
+
+#define FPC_EXCEPTION_MASK	0xF8000000
+#define FPC_FLAGS_MASK		0x00F80000
+#define FPC_DXC_MASK		0x0000FF00
+#define FPC_RM_MASK		0x00000003
+
+/* this typedef defines how a Program Status Word looks like */
+typedef struct {
+	unsigned long mask;
+	unsigned long addr;
+} __attribute__ ((aligned(8))) psw_t;
+
+#ifndef __s390x__
+
+#define PSW_MASK_PER		0x40000000UL
+#define PSW_MASK_DAT		0x04000000UL
+#define PSW_MASK_IO		0x02000000UL
+#define PSW_MASK_EXT		0x01000000UL
+#define PSW_MASK_KEY		0x00F00000UL
+#define PSW_MASK_BASE		0x00080000UL	/* always one */
+#define PSW_MASK_MCHECK		0x00040000UL
+#define PSW_MASK_WAIT		0x00020000UL
+#define PSW_MASK_PSTATE		0x00010000UL
+#define PSW_MASK_ASC		0x0000C000UL
+#define PSW_MASK_CC		0x00003000UL
+#define PSW_MASK_PM		0x00000F00UL
+#define PSW_MASK_RI		0x00000000UL
+#define PSW_MASK_EA		0x00000000UL
+#define PSW_MASK_BA		0x00000000UL
+
+#define PSW_MASK_USER		0x0000FF00UL
+
+#define PSW_ADDR_AMODE		0x80000000UL
+#define PSW_ADDR_INSN		0x7FFFFFFFUL
+
+#define PSW_DEFAULT_KEY		(((unsigned long) PAGE_DEFAULT_ACC) << 20)
+
+#define PSW_ASC_PRIMARY		0x00000000UL
+#define PSW_ASC_ACCREG		0x00004000UL
+#define PSW_ASC_SECONDARY	0x00008000UL
+#define PSW_ASC_HOME		0x0000C000UL
+
+#else /* __s390x__ */
+
+#define PSW_MASK_PER		0x4000000000000000UL
+#define PSW_MASK_DAT		0x0400000000000000UL
+#define PSW_MASK_IO		0x0200000000000000UL
+#define PSW_MASK_EXT		0x0100000000000000UL
+#define PSW_MASK_BASE		0x0000000000000000UL
+#define PSW_MASK_KEY		0x00F0000000000000UL
+#define PSW_MASK_MCHECK		0x0004000000000000UL
+#define PSW_MASK_WAIT		0x0002000000000000UL
+#define PSW_MASK_PSTATE		0x0001000000000000UL
+#define PSW_MASK_ASC		0x0000C00000000000UL
+#define PSW_MASK_CC		0x0000300000000000UL
+#define PSW_MASK_PM		0x00000F0000000000UL
+#define PSW_MASK_RI		0x0000008000000000UL
+#define PSW_MASK_EA		0x0000000100000000UL
+#define PSW_MASK_BA		0x0000000080000000UL
+
+#define PSW_MASK_USER		0x0000FF0180000000UL
+
+#define PSW_ADDR_AMODE		0x0000000000000000UL
+#define PSW_ADDR_INSN		0xFFFFFFFFFFFFFFFFUL
+
+#define PSW_DEFAULT_KEY		(((unsigned long) PAGE_DEFAULT_ACC) << 52)
+
+#define PSW_ASC_PRIMARY		0x0000000000000000UL
+#define PSW_ASC_ACCREG		0x0000400000000000UL
+#define PSW_ASC_SECONDARY	0x0000800000000000UL
+#define PSW_ASC_HOME		0x0000C00000000000UL
+
+#endif /* __s390x__ */
+
+
+/*
+ * The s390_regs structure is used to define the elf_gregset_t.
+ */
+typedef struct {
+	psw_t psw;
+	unsigned long gprs[NUM_GPRS];
+	unsigned int  acrs[NUM_ACRS];
+	unsigned long orig_gpr2;
+} s390_regs;
+
+/*
+ * The user_pt_regs structure exports the beginning of
+ * the in-kernel pt_regs structure to user space.
+ */
+typedef struct {
+	unsigned long args[1];
+	psw_t psw;
+	unsigned long gprs[NUM_GPRS];
+} user_pt_regs;
+
+/*
+ * Now for the user space program event recording (trace) definitions.
+ * The following structures are used only for the ptrace interface, don't
+ * touch or even look at it if you don't want to modify the user-space
+ * ptrace interface. In particular stay away from it for in-kernel PER.
+ */
+typedef struct {
+	unsigned long cr[NUM_CR_WORDS];
+} per_cr_words;
+
+#define PER_EM_MASK 0xE8000000UL
+
+typedef struct {
+#ifdef __s390x__
+	unsigned		       : 32;
+#endif /* __s390x__ */
+	unsigned em_branching	       : 1;
+	unsigned em_instruction_fetch  : 1;
+	/*
+	 * Switching on storage alteration automatically fixes
+	 * the storage alteration event bit in the users std.
+	 */
+	unsigned em_storage_alteration : 1;
+	unsigned em_gpr_alt_unused     : 1;
+	unsigned em_store_real_address : 1;
+	unsigned		       : 3;
+	unsigned branch_addr_ctl       : 1;
+	unsigned		       : 1;
+	unsigned storage_alt_space_ctl : 1;
+	unsigned		       : 21;
+	unsigned long starting_addr;
+	unsigned long ending_addr;
+} per_cr_bits;
+
+typedef struct {
+	unsigned short perc_atmid;
+	unsigned long address;
+	unsigned char access_id;
+} per_lowcore_words;
+
+typedef struct {
+	unsigned perc_branching		 : 1;
+	unsigned perc_instruction_fetch  : 1;
+	unsigned perc_storage_alteration : 1;
+	unsigned perc_gpr_alt_unused	 : 1;
+	unsigned perc_store_real_address : 1;
+	unsigned			 : 3;
+	unsigned atmid_psw_bit_31	 : 1;
+	unsigned atmid_validity_bit	 : 1;
+	unsigned atmid_psw_bit_32	 : 1;
+	unsigned atmid_psw_bit_5	 : 1;
+	unsigned atmid_psw_bit_16	 : 1;
+	unsigned atmid_psw_bit_17	 : 1;
+	unsigned si			 : 2;
+	unsigned long address;
+	unsigned			 : 4;
+	unsigned access_id		 : 4;
+} per_lowcore_bits;
+
+typedef struct {
+	union {
+		per_cr_words   words;
+		per_cr_bits    bits;
+	} control_regs;
+	/*
+	 * The single_step and instruction_fetch bits are obsolete,
+	 * the kernel always sets them to zero. To enable single
+	 * stepping use ptrace(PTRACE_SINGLESTEP) instead.
+	 */
+	unsigned  single_step	    : 1;
+	unsigned  instruction_fetch : 1;
+	unsigned		    : 30;
+	/*
+	 * These addresses are copied into cr10 & cr11 if single
+	 * stepping is switched off
+	 */
+	unsigned long starting_addr;
+	unsigned long ending_addr;
+	union {
+		per_lowcore_words words;
+		per_lowcore_bits  bits;
+	} lowcore;
+} per_struct;
+
+typedef struct {
+	unsigned int  len;
+	unsigned long kernel_addr;
+	unsigned long process_addr;
+} ptrace_area;
+
+/*
+ * S/390 specific non posix ptrace requests. I chose unusual values so
+ * they are unlikely to clash with future ptrace definitions.
+ */
+#define PTRACE_PEEKUSR_AREA	      0x5000
+#define PTRACE_POKEUSR_AREA	      0x5001
+#define PTRACE_PEEKTEXT_AREA	      0x5002
+#define PTRACE_PEEKDATA_AREA	      0x5003
+#define PTRACE_POKETEXT_AREA	      0x5004
+#define PTRACE_POKEDATA_AREA	      0x5005
+#define PTRACE_GET_LAST_BREAK	      0x5006
+#define PTRACE_PEEK_SYSTEM_CALL       0x5007
+#define PTRACE_POKE_SYSTEM_CALL	      0x5008
+#define PTRACE_ENABLE_TE	      0x5009
+#define PTRACE_DISABLE_TE	      0x5010
+#define PTRACE_TE_ABORT_RAND	      0x5011
+
+/*
+ * The numbers chosen here are somewhat arbitrary but absolutely MUST
+ * not overlap with any of the number assigned in <linux/ptrace.h>.
+ */
+#define PTRACE_SINGLEBLOCK	12	/* resume execution until next branch */
+
+/*
+ * PT_PROT definition is loosely based on hppa bsd definition in
+ * gdb/hppab-nat.c
+ */
+#define PTRACE_PROT			  21
+
+typedef enum {
+	ptprot_set_access_watchpoint,
+	ptprot_set_write_watchpoint,
+	ptprot_disable_watchpoint
+} ptprot_flags;
+
+typedef struct {
+	unsigned long lowaddr;
+	unsigned long hiaddr;
+	ptprot_flags prot;
+} ptprot_area;
+
+/* Sequence of bytes for breakpoint illegal instruction.  */
+#define S390_BREAKPOINT     {0x0,0x1}
+#define S390_BREAKPOINT_U16 ((__u16)0x0001)
+#define S390_SYSCALL_OPCODE ((__u16)0x0a00)
+#define S390_SYSCALL_SIZE   2
+
+/*
+ * The user_regs_struct defines the way the user registers are
+ * store on the stack for signal handling.
+ */
+struct user_regs_struct {
+	psw_t psw;
+	unsigned long gprs[NUM_GPRS];
+	unsigned int  acrs[NUM_ACRS];
+	unsigned long orig_gpr2;
+	s390_fp_regs fp_regs;
+	/*
+	 * These per registers are in here so that gdb can modify them
+	 * itself as there is no "official" ptrace interface for hardware
+	 * watchpoints. This is the way intel does it.
+	 */
+	per_struct per_info;
+	unsigned long ieee_instruction_pointer;	/* obsolete, always 0 */
+};
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _UAPI_S390_PTRACE_H */

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

+#ifndef _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__
+
+#include <linux/ptrace.h>
+
+/* Export kernel pt_regs structure */
+typedef struct pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__ */

tools/include/uapi/linux/bpf_perf_event.h

+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /* Copyright (c) 2016 Facebook
  *
  * This program is free software; you can redistribute it and/or
@@ -7,11 +8,10 @@
 #ifndef _UAPI__LINUX_BPF_PERF_EVENT_H__
 #define _UAPI__LINUX_BPF_PERF_EVENT_H__
 
-#include <linux/types.h>
-#include <linux/ptrace.h>
+#include <asm/bpf_perf_event.h>
 
 struct bpf_perf_event_data {
-	struct pt_regs regs;
+	bpf_user_pt_regs_t regs;
 	__u64 sample_period;
 };
 

tools/perf/arch/s390/Makefile

@@ -2,3 +2,4 @@ ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
 HAVE_KVM_STAT_SUPPORT := 1
+PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1

tools/perf/arch/s390/util/dwarf-regs.c

@@ -2,17 +2,43 @@
 /*
  * Mapping of DWARF debug register numbers into register names.
  *
- *    Copyright IBM Corp. 2010
- *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>,
+ * Copyright IBM Corp. 2010, 2017
+ * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>,
+ *	      Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
  *
  */
 
+#include <errno.h>
 #include <stddef.h>
-#include <dwarf-regs.h>
+#include <stdlib.h>
 #include <linux/kernel.h>
+#include <asm/ptrace.h>
+#include <string.h>
+#include <dwarf-regs.h>
 #include "dwarf-regs-table.h"
 
 const char *get_arch_regstr(unsigned int n)
 {
 	return (n >= ARRAY_SIZE(s390_dwarf_regs)) ? NULL : s390_dwarf_regs[n];
 }
+
+/*
+ * Convert the register name into an offset to struct pt_regs (kernel).
+ * This is required by the BPF prologue generator.  The BPF
+ * program is called in the BPF overflow handler in the perf
+ * core.
+ */
+int regs_query_register_offset(const char *name)
+{
+	unsigned long gpr;
+
+	if (!name || strncmp(name, "%r", 2))
+		return -EINVAL;
+
+	errno = 0;
+	gpr = strtoul(name + 2, NULL, 10);
+	if (errno || gpr >= 16)
+		return -EINVAL;
+
+	return offsetof(user_pt_regs, gprs) + 8 * gpr;
+}

tools/perf/check-headers.sh

@@ -30,6 +30,7 @@ arch/x86/include/uapi/asm/vmx.h
 arch/powerpc/include/uapi/asm/kvm.h
 arch/s390/include/uapi/asm/kvm.h
 arch/s390/include/uapi/asm/kvm_perf.h
+arch/s390/include/uapi/asm/ptrace.h
 arch/s390/include/uapi/asm/sie.h
 arch/arm/include/uapi/asm/kvm.h
 arch/arm64/include/uapi/asm/kvm.h

tools/testing/selftests/bpf/Makefile

 # SPDX-License-Identifier: GPL-2.0
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+endif
+include $(srctree)/tools/scripts/Makefile.arch
+
+$(call detected_var,SRCARCH)
+
 LIBDIR := ../../../lib
 BPFDIR := $(LIBDIR)/bpf
 APIDIR := ../../../include/uapi
+ASMDIR:= ../../../arch/$(ARCH)/include/uapi
 GENDIR := ../../../../include/generated
 GENHDR := $(GENDIR)/autoconf.h
 
@@ -9,7 +21,7 @@ ifneq ($(wildcard $(GENHDR)),)
   GENFLAGS := -DHAVE_GENHDR
 endif
 
-CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include
+CFLAGS += -Wall -O2 -I$(APIDIR) -I$(ASMDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include
 LDLIBS += -lcap -lelf
 
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \