linux-sg2042/arch/s390/net/bpf_jit_comp.c

1307 lines
34 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 22:07:57 +08:00
// SPDX-License-Identifier: GPL-2.0
/*
* BPF Jit compiler for s390.
*
* Minimum build requirements:
*
* - HAVE_MARCH_Z196_FEATURES: laal, laalg
* - HAVE_MARCH_Z10_FEATURES: msfi, cgrj, clgrj
* - HAVE_MARCH_Z9_109_FEATURES: alfi, llilf, clfi, oilf, nilf
* - PACK_STACK
* - 64BIT
*
* Copyright IBM Corp. 2012,2015
*
* Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
* Michael Holzheu <holzheu@linux.vnet.ibm.com>
*/
#define KMSG_COMPONENT "bpf_jit"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
#include <linux/netdevice.h>
#include <linux/filter.h>
#include <linux/init.h>
s390/bpf: implement bpf_tail_call() helper bpf_tail_call() arguments: - ctx......: Context pointer - jmp_table: One of BPF_MAP_TYPE_PROG_ARRAY maps used as the jump table - index....: Index in the jump table In this implementation s390x JIT does stack unwinding and jumps into the callee program prologue. Caller and callee use the same stack. With this patch a tail call generates the following code on s390x: if (index >= array->map.max_entries) goto out 000003ff8001c7e4: e31030100016 llgf %r1,16(%r3) 000003ff8001c7ea: ec41001fa065 clgrj %r4,%r1,10,3ff8001c828 if (tail_call_cnt++ > MAX_TAIL_CALL_CNT) goto out; 000003ff8001c7f0: a7080001 lhi %r0,1 000003ff8001c7f4: eb10f25000fa laal %r1,%r0,592(%r15) 000003ff8001c7fa: ec120017207f clij %r1,32,2,3ff8001c828 prog = array->prog[index]; if (prog == NULL) goto out; 000003ff8001c800: eb140003000d sllg %r1,%r4,3 000003ff8001c806: e31310800004 lg %r1,128(%r3,%r1) 000003ff8001c80c: ec18000e007d clgij %r1,0,8,3ff8001c828 Restore registers before calling function 000003ff8001c812: eb68f2980004 lmg %r6,%r8,664(%r15) 000003ff8001c818: ebbff2c00004 lmg %r11,%r15,704(%r15) goto *(prog->bpf_func + tail_call_start); 000003ff8001c81e: e31100200004 lg %r1,32(%r1,%r0) 000003ff8001c824: 47f01006 bc 15,6(%r1) Reviewed-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-09 12:51:06 +08:00
#include <linux/bpf.h>
#include <asm/cacheflush.h>
#include <asm/dis.h>
#include <asm/facility.h>
#include <asm/nospec-branch.h>
#include <asm/set_memory.h>
#include "bpf_jit.h"
struct bpf_jit {
u32 seen; /* Flags to remember seen eBPF instructions */
u32 seen_reg[16]; /* Array to remember which registers are used */
u32 *addrs; /* Array with relative instruction addresses */
u8 *prg_buf; /* Start of program */
int size; /* Size of program and literal pool */
int size_prg; /* Size of program */
int prg; /* Current position in program */
int lit_start; /* Start of literal pool */
int lit; /* Current position in literal pool */
int base_ip; /* Base address for literal pool */
int ret0_ip; /* Address of return 0 */
int exit_ip; /* Address of exit */
int r1_thunk_ip; /* Address of expoline thunk for 'br %r1' */
int r14_thunk_ip; /* Address of expoline thunk for 'br %r14' */
s390/bpf: implement bpf_tail_call() helper bpf_tail_call() arguments: - ctx......: Context pointer - jmp_table: One of BPF_MAP_TYPE_PROG_ARRAY maps used as the jump table - index....: Index in the jump table In this implementation s390x JIT does stack unwinding and jumps into the callee program prologue. Caller and callee use the same stack. With this patch a tail call generates the following code on s390x: if (index >= array->map.max_entries) goto out 000003ff8001c7e4: e31030100016 llgf %r1,16(%r3) 000003ff8001c7ea: ec41001fa065 clgrj %r4,%r1,10,3ff8001c828 if (tail_call_cnt++ > MAX_TAIL_CALL_CNT) goto out; 000003ff8001c7f0: a7080001 lhi %r0,1 000003ff8001c7f4: eb10f25000fa laal %r1,%r0,592(%r15) 000003ff8001c7fa: ec120017207f clij %r1,32,2,3ff8001c828 prog = array->prog[index]; if (prog == NULL) goto out; 000003ff8001c800: eb140003000d sllg %r1,%r4,3 000003ff8001c806: e31310800004 lg %r1,128(%r3,%r1) 000003ff8001c80c: ec18000e007d clgij %r1,0,8,3ff8001c828 Restore registers before calling function 000003ff8001c812: eb68f2980004 lmg %r6,%r8,664(%r15) 000003ff8001c818: ebbff2c00004 lmg %r11,%r15,704(%r15) goto *(prog->bpf_func + tail_call_start); 000003ff8001c81e: e31100200004 lg %r1,32(%r1,%r0) 000003ff8001c824: 47f01006 bc 15,6(%r1) Reviewed-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-09 12:51:06 +08:00
int tail_call_start; /* Tail call start offset */
int labels[1]; /* Labels for local jumps */
};
#define BPF_SIZE_MAX 0xffff /* Max size for program (16 bit branches) */
#define SEEN_MEM (1 << 0) /* use mem[] for temporary storage */
#define SEEN_RET0 (1 << 1) /* ret0_ip points to a valid return 0 */
#define SEEN_LITERAL (1 << 2) /* code uses literals */
#define SEEN_FUNC (1 << 3) /* calls C functions */
#define SEEN_TAIL_CALL (1 << 4) /* code uses tail calls */
#define SEEN_REG_AX (1 << 5) /* code uses constant blinding */
#define SEEN_STACK (SEEN_FUNC | SEEN_MEM)
/*
* s390 registers
*/
#define REG_W0 (MAX_BPF_JIT_REG + 0) /* Work register 1 (even) */
#define REG_W1 (MAX_BPF_JIT_REG + 1) /* Work register 2 (odd) */
#define REG_L (MAX_BPF_JIT_REG + 2) /* Literal pool register */
#define REG_15 (MAX_BPF_JIT_REG + 3) /* Register 15 */
#define REG_0 REG_W0 /* Register 0 */
s390/bpf: implement bpf_tail_call() helper bpf_tail_call() arguments: - ctx......: Context pointer - jmp_table: One of BPF_MAP_TYPE_PROG_ARRAY maps used as the jump table - index....: Index in the jump table In this implementation s390x JIT does stack unwinding and jumps into the callee program prologue. Caller and callee use the same stack. With this patch a tail call generates the following code on s390x: if (index >= array->map.max_entries) goto out 000003ff8001c7e4: e31030100016 llgf %r1,16(%r3) 000003ff8001c7ea: ec41001fa065 clgrj %r4,%r1,10,3ff8001c828 if (tail_call_cnt++ > MAX_TAIL_CALL_CNT) goto out; 000003ff8001c7f0: a7080001 lhi %r0,1 000003ff8001c7f4: eb10f25000fa laal %r1,%r0,592(%r15) 000003ff8001c7fa: ec120017207f clij %r1,32,2,3ff8001c828 prog = array->prog[index]; if (prog == NULL) goto out; 000003ff8001c800: eb140003000d sllg %r1,%r4,3 000003ff8001c806: e31310800004 lg %r1,128(%r3,%r1) 000003ff8001c80c: ec18000e007d clgij %r1,0,8,3ff8001c828 Restore registers before calling function 000003ff8001c812: eb68f2980004 lmg %r6,%r8,664(%r15) 000003ff8001c818: ebbff2c00004 lmg %r11,%r15,704(%r15) goto *(prog->bpf_func + tail_call_start); 000003ff8001c81e: e31100200004 lg %r1,32(%r1,%r0) 000003ff8001c824: 47f01006 bc 15,6(%r1) Reviewed-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-09 12:51:06 +08:00
#define REG_1 REG_W1 /* Register 1 */
#define REG_2 BPF_REG_1 /* Register 2 */
#define REG_14 BPF_REG_0 /* Register 14 */
/*
* Mapping of BPF registers to s390 registers
*/
static const int reg2hex[] = {
/* Return code */
[BPF_REG_0] = 14,
/* Function parameters */
[BPF_REG_1] = 2,
[BPF_REG_2] = 3,
[BPF_REG_3] = 4,
[BPF_REG_4] = 5,
[BPF_REG_5] = 6,
/* Call saved registers */
[BPF_REG_6] = 7,
[BPF_REG_7] = 8,
[BPF_REG_8] = 9,
[BPF_REG_9] = 10,
/* BPF stack pointer */
[BPF_REG_FP] = 13,
/* Register for blinding */
[BPF_REG_AX] = 12,
/* Work registers for s390x backend */
[REG_W0] = 0,
[REG_W1] = 1,
[REG_L] = 11,
[REG_15] = 15,
};
static inline u32 reg(u32 dst_reg, u32 src_reg)
{
return reg2hex[dst_reg] << 4 | reg2hex[src_reg];
}
static inline u32 reg_high(u32 reg)
{
return reg2hex[reg] << 4;
}
static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
{
u32 r1 = reg2hex[b1];
if (!jit->seen_reg[r1] && r1 >= 6 && r1 <= 15)
jit->seen_reg[r1] = 1;
}
#define REG_SET_SEEN(b1) \
({ \
reg_set_seen(jit, b1); \
})
#define REG_SEEN(b1) jit->seen_reg[reg2hex[(b1)]]
/*
* EMIT macros for code generation
*/
#define _EMIT2(op) \
({ \
if (jit->prg_buf) \
*(u16 *) (jit->prg_buf + jit->prg) = op; \
jit->prg += 2; \
})
#define EMIT2(op, b1, b2) \
({ \
_EMIT2(op | reg(b1, b2)); \
REG_SET_SEEN(b1); \
REG_SET_SEEN(b2); \
})
#define _EMIT4(op) \
({ \
if (jit->prg_buf) \
*(u32 *) (jit->prg_buf + jit->prg) = op; \
jit->prg += 4; \
})
#define EMIT4(op, b1, b2) \
({ \
_EMIT4(op | reg(b1, b2)); \
REG_SET_SEEN(b1); \
REG_SET_SEEN(b2); \
})
#define EMIT4_RRF(op, b1, b2, b3) \
({ \
_EMIT4(op | reg_high(b3) << 8 | reg(b1, b2)); \
REG_SET_SEEN(b1); \
REG_SET_SEEN(b2); \
REG_SET_SEEN(b3); \
})
#define _EMIT4_DISP(op, disp) \
({ \
unsigned int __disp = (disp) & 0xfff; \
_EMIT4(op | __disp); \
})
#define EMIT4_DISP(op, b1, b2, disp) \
({ \
_EMIT4_DISP(op | reg_high(b1) << 16 | \
reg_high(b2) << 8, disp); \
REG_SET_SEEN(b1); \
REG_SET_SEEN(b2); \
})
#define EMIT4_IMM(op, b1, imm) \
({ \
unsigned int __imm = (imm) & 0xffff; \
_EMIT4(op | reg_high(b1) << 16 | __imm); \
REG_SET_SEEN(b1); \
})
#define EMIT4_PCREL(op, pcrel) \
({ \
long __pcrel = ((pcrel) >> 1) & 0xffff; \
_EMIT4(op | __pcrel); \
})
#define _EMIT6(op1, op2) \
({ \
if (jit->prg_buf) { \
*(u32 *) (jit->prg_buf + jit->prg) = op1; \
*(u16 *) (jit->prg_buf + jit->prg + 4) = op2; \
} \
jit->prg += 6; \
})
#define _EMIT6_DISP(op1, op2, disp) \
({ \
unsigned int __disp = (disp) & 0xfff; \
_EMIT6(op1 | __disp, op2); \
})
#define _EMIT6_DISP_LH(op1, op2, disp) \
({ \
u32 _disp = (u32) disp; \
unsigned int __disp_h = _disp & 0xff000; \
unsigned int __disp_l = _disp & 0x00fff; \
_EMIT6(op1 | __disp_l, op2 | __disp_h >> 4); \
})
#define EMIT6_DISP_LH(op1, op2, b1, b2, b3, disp) \
({ \
_EMIT6_DISP_LH(op1 | reg(b1, b2) << 16 | \
reg_high(b3) << 8, op2, disp); \
REG_SET_SEEN(b1); \
REG_SET_SEEN(b2); \
REG_SET_SEEN(b3); \
})
s390/bpf: implement bpf_tail_call() helper bpf_tail_call() arguments: - ctx......: Context pointer - jmp_table: One of BPF_MAP_TYPE_PROG_ARRAY maps used as the jump table - index....: Index in the jump table In this implementation s390x JIT does stack unwinding and jumps into the callee program prologue. Caller and callee use the same stack. With this patch a tail call generates the following code on s390x: if (index >= array->map.max_entries) goto out 000003ff8001c7e4: e31030100016 llgf %r1,16(%r3) 000003ff8001c7ea: ec41001fa065 clgrj %r4,%r1,10,3ff8001c828 if (tail_call_cnt++ > MAX_TAIL_CALL_CNT) goto out; 000003ff8001c7f0: a7080001 lhi %r0,1 000003ff8001c7f4: eb10f25000fa laal %r1,%r0,592(%r15) 000003ff8001c7fa: ec120017207f clij %r1,32,2,3ff8001c828 prog = array->prog[index]; if (prog == NULL) goto out; 000003ff8001c800: eb140003000d sllg %r1,%r4,3 000003ff8001c806: e31310800004 lg %r1,128(%r3,%r1) 000003ff8001c80c: ec18000e007d clgij %r1,0,8,3ff8001c828 Restore registers before calling function 000003ff8001c812: eb68f2980004 lmg %r6,%r8,664(%r15) 000003ff8001c818: ebbff2c00004 lmg %r11,%r15,704(%r15) goto *(prog->bpf_func + tail_call_start); 000003ff8001c81e: e31100200004 lg %r1,32(%r1,%r0) 000003ff8001c824: 47f01006 bc 15,6(%r1) Reviewed-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-09 12:51:06 +08:00
#define EMIT6_PCREL_LABEL(op1, op2, b1, b2, label, mask) \
({ \
int rel = (jit->labels[label] - jit->prg) >> 1; \
_EMIT6(op1 | reg(b1, b2) << 16 | (rel & 0xffff), \
op2 | mask << 12); \
REG_SET_SEEN(b1); \
REG_SET_SEEN(b2); \
})
#define EMIT6_PCREL_IMM_LABEL(op1, op2, b1, imm, label, mask) \
({ \
int rel = (jit->labels[label] - jit->prg) >> 1; \
_EMIT6(op1 | (reg_high(b1) | mask) << 16 | \
(rel & 0xffff), op2 | (imm & 0xff) << 8); \
REG_SET_SEEN(b1); \
BUILD_BUG_ON(((unsigned long) imm) > 0xff); \
})
#define EMIT6_PCREL(op1, op2, b1, b2, i, off, mask) \
({ \
/* Branch instruction needs 6 bytes */ \
int rel = (addrs[i + off + 1] - (addrs[i + 1] - 6)) / 2;\
_EMIT6(op1 | reg(b1, b2) << 16 | (rel & 0xffff), op2 | mask); \
REG_SET_SEEN(b1); \
REG_SET_SEEN(b2); \
})
#define EMIT6_PCREL_RILB(op, b, target) \
({ \
int rel = (target - jit->prg) / 2; \
_EMIT6(op | reg_high(b) << 16 | rel >> 16, rel & 0xffff); \
REG_SET_SEEN(b); \
})
#define EMIT6_PCREL_RIL(op, target) \
({ \
int rel = (target - jit->prg) / 2; \
_EMIT6(op | rel >> 16, rel & 0xffff); \
})
#define _EMIT6_IMM(op, imm) \
({ \
unsigned int __imm = (imm); \
_EMIT6(op | (__imm >> 16), __imm & 0xffff); \
})
#define EMIT6_IMM(op, b1, imm) \
({ \
_EMIT6_IMM(op | reg_high(b1) << 16, imm); \
REG_SET_SEEN(b1); \
})
#define EMIT_CONST_U32(val) \
({ \
unsigned int ret; \
ret = jit->lit - jit->base_ip; \
jit->seen |= SEEN_LITERAL; \
if (jit->prg_buf) \
*(u32 *) (jit->prg_buf + jit->lit) = (u32) val; \
jit->lit += 4; \
ret; \
})
#define EMIT_CONST_U64(val) \
({ \
unsigned int ret; \
ret = jit->lit - jit->base_ip; \
jit->seen |= SEEN_LITERAL; \
if (jit->prg_buf) \
*(u64 *) (jit->prg_buf + jit->lit) = (u64) val; \
jit->lit += 8; \
ret; \
})
#define EMIT_ZERO(b1) \
({ \
/* llgfr %dst,%dst (zero extend to 64 bit) */ \
EMIT4(0xb9160000, b1, b1); \
REG_SET_SEEN(b1); \
})
/*
* Fill whole space with illegal instructions
*/
static void jit_fill_hole(void *area, unsigned int size)
{
memset(area, 0, size);
}
/*
* Save registers from "rs" (register start) to "re" (register end) on stack
*/
static void save_regs(struct bpf_jit *jit, u32 rs, u32 re)
{
s390/bpf: implement bpf_tail_call() helper bpf_tail_call() arguments: - ctx......: Context pointer - jmp_table: One of BPF_MAP_TYPE_PROG_ARRAY maps used as the jump table - index....: Index in the jump table In this implementation s390x JIT does stack unwinding and jumps into the callee program prologue. Caller and callee use the same stack. With this patch a tail call generates the following code on s390x: if (index >= array->map.max_entries) goto out 000003ff8001c7e4: e31030100016 llgf %r1,16(%r3) 000003ff8001c7ea: ec41001fa065 clgrj %r4,%r1,10,3ff8001c828 if (tail_call_cnt++ > MAX_TAIL_CALL_CNT) goto out; 000003ff8001c7f0: a7080001 lhi %r0,1 000003ff8001c7f4: eb10f25000fa laal %r1,%r0,592(%r15) 000003ff8001c7fa: ec120017207f clij %r1,32,2,3ff8001c828 prog = array->prog[index]; if (prog == NULL) goto out; 000003ff8001c800: eb140003000d sllg %r1,%r4,3 000003ff8001c806: e31310800004 lg %r1,128(%r3,%r1) 000003ff8001c80c: ec18000e007d clgij %r1,0,8,3ff8001c828 Restore registers before calling function 000003ff8001c812: eb68f2980004 lmg %r6,%r8,664(%r15) 000003ff8001c818: ebbff2c00004 lmg %r11,%r15,704(%r15) goto *(prog->bpf_func + tail_call_start); 000003ff8001c81e: e31100200004 lg %r1,32(%r1,%r0) 000003ff8001c824: 47f01006 bc 15,6(%r1) Reviewed-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-09 12:51:06 +08:00
u32 off = STK_OFF_R6 + (rs - 6) * 8;
if (rs == re)
/* stg %rs,off(%r15) */
_EMIT6(0xe300f000 | rs << 20 | off, 0x0024);
else
/* stmg %rs,%re,off(%r15) */
_EMIT6_DISP(0xeb00f000 | rs << 20 | re << 16, 0x0024, off);
}
/*
* Restore registers from "rs" (register start) to "re" (register end) on stack
*/
static void restore_regs(struct bpf_jit *jit, u32 rs, u32 re, u32 stack_depth)
{
s390/bpf: implement bpf_tail_call() helper bpf_tail_call() arguments: - ctx......: Context pointer - jmp_table: One of BPF_MAP_TYPE_PROG_ARRAY maps used as the jump table - index....: Index in the jump table In this implementation s390x JIT does stack unwinding and jumps into the callee program prologue. Caller and callee use the same stack. With this patch a tail call generates the following code on s390x: if (index >= array->map.max_entries) goto out 000003ff8001c7e4: e31030100016 llgf %r1,16(%r3) 000003ff8001c7ea: ec41001fa065 clgrj %r4,%r1,10,3ff8001c828 if (tail_call_cnt++ > MAX_TAIL_CALL_CNT) goto out; 000003ff8001c7f0: a7080001 lhi %r0,1 000003ff8001c7f4: eb10f25000fa laal %r1,%r0,592(%r15) 000003ff8001c7fa: ec120017207f clij %r1,32,2,3ff8001c828 prog = array->prog[index]; if (prog == NULL) goto out; 000003ff8001c800: eb140003000d sllg %r1,%r4,3 000003ff8001c806: e31310800004 lg %r1,128(%r3,%r1) 000003ff8001c80c: ec18000e007d clgij %r1,0,8,3ff8001c828 Restore registers before calling function 000003ff8001c812: eb68f2980004 lmg %r6,%r8,664(%r15) 000003ff8001c818: ebbff2c00004 lmg %r11,%r15,704(%r15) goto *(prog->bpf_func + tail_call_start); 000003ff8001c81e: e31100200004 lg %r1,32(%r1,%r0) 000003ff8001c824: 47f01006 bc 15,6(%r1) Reviewed-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-09 12:51:06 +08:00
u32 off = STK_OFF_R6 + (rs - 6) * 8;
if (jit->seen & SEEN_STACK)
off += STK_OFF + stack_depth;
if (rs == re)
/* lg %rs,off(%r15) */
_EMIT6(0xe300f000 | rs << 20 | off, 0x0004);
else
/* lmg %rs,%re,off(%r15) */
_EMIT6_DISP(0xeb00f000 | rs << 20 | re << 16, 0x0004, off);
}
/*
* Return first seen register (from start)
*/
static int get_start(struct bpf_jit *jit, int start)
{
int i;
for (i = start; i <= 15; i++) {
if (jit->seen_reg[i])
return i;
}
return 0;
}
/*
* Return last seen register (from start) (gap >= 2)
*/
static int get_end(struct bpf_jit *jit, int start)
{
int i;
for (i = start; i < 15; i++) {
if (!jit->seen_reg[i] && !jit->seen_reg[i + 1])
return i - 1;
}
return jit->seen_reg[15] ? 15 : 14;
}
#define REGS_SAVE 1
#define REGS_RESTORE 0
/*
* Save and restore clobbered registers (6-15) on stack.
* We save/restore registers in chunks with gap >= 2 registers.
*/
static void save_restore_regs(struct bpf_jit *jit, int op, u32 stack_depth)
{
int re = 6, rs;
do {
rs = get_start(jit, re);
if (!rs)
break;
re = get_end(jit, rs + 1);
if (op == REGS_SAVE)
save_regs(jit, rs, re);
else
restore_regs(jit, rs, re, stack_depth);
re++;
} while (re <= 15);
}
/*
* Emit function prologue
*
* Save registers and create stack frame if necessary.
* See stack frame layout desription in "bpf_jit.h"!
*/
static void bpf_jit_prologue(struct bpf_jit *jit, u32 stack_depth)
{
s390/bpf: implement bpf_tail_call() helper bpf_tail_call() arguments: - ctx......: Context pointer - jmp_table: One of BPF_MAP_TYPE_PROG_ARRAY maps used as the jump table - index....: Index in the jump table In this implementation s390x JIT does stack unwinding and jumps into the callee program prologue. Caller and callee use the same stack. With this patch a tail call generates the following code on s390x: if (index >= array->map.max_entries) goto out 000003ff8001c7e4: e31030100016 llgf %r1,16(%r3) 000003ff8001c7ea: ec41001fa065 clgrj %r4,%r1,10,3ff8001c828 if (tail_call_cnt++ > MAX_TAIL_CALL_CNT) goto out; 000003ff8001c7f0: a7080001 lhi %r0,1 000003ff8001c7f4: eb10f25000fa laal %r1,%r0,592(%r15) 000003ff8001c7fa: ec120017207f clij %r1,32,2,3ff8001c828 prog = array->prog[index]; if (prog == NULL) goto out; 000003ff8001c800: eb140003000d sllg %r1,%r4,3 000003ff8001c806: e31310800004 lg %r1,128(%r3,%r1) 000003ff8001c80c: ec18000e007d clgij %r1,0,8,3ff8001c828 Restore registers before calling function 000003ff8001c812: eb68f2980004 lmg %r6,%r8,664(%r15) 000003ff8001c818: ebbff2c00004 lmg %r11,%r15,704(%r15) goto *(prog->bpf_func + tail_call_start); 000003ff8001c81e: e31100200004 lg %r1,32(%r1,%r0) 000003ff8001c824: 47f01006 bc 15,6(%r1) Reviewed-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-09 12:51:06 +08:00
if (jit->seen & SEEN_TAIL_CALL) {
/* xc STK_OFF_TCCNT(4,%r15),STK_OFF_TCCNT(%r15) */
_EMIT6(0xd703f000 | STK_OFF_TCCNT, 0xf000 | STK_OFF_TCCNT);
} else {
/* j tail_call_start: NOP if no tail calls are used */
EMIT4_PCREL(0xa7f40000, 6);
_EMIT2(0);
}
/* Tail calls have to skip above initialization */
jit->tail_call_start = jit->prg;
/* Save registers */
save_restore_regs(jit, REGS_SAVE, stack_depth);
/* Setup literal pool */
if (jit->seen & SEEN_LITERAL) {
/* basr %r13,0 */
EMIT2(0x0d00, REG_L, REG_0);
jit->base_ip = jit->prg;
}
/* Setup stack and backchain */
if (jit->seen & SEEN_STACK) {
if (jit->seen & SEEN_FUNC)
/* lgr %w1,%r15 (backchain) */
EMIT4(0xb9040000, REG_W1, REG_15);
/* la %bfp,STK_160_UNUSED(%r15) (BPF frame pointer) */
EMIT4_DISP(0x41000000, BPF_REG_FP, REG_15, STK_160_UNUSED);
/* aghi %r15,-STK_OFF */
EMIT4_IMM(0xa70b0000, REG_15, -(STK_OFF + stack_depth));
if (jit->seen & SEEN_FUNC)
/* stg %w1,152(%r15) (backchain) */
EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0,
REG_15, 152);
}
}
/*
* Function epilogue
*/
static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth)
{
/* Return 0 */
if (jit->seen & SEEN_RET0) {
jit->ret0_ip = jit->prg;
/* lghi %b0,0 */
EMIT4_IMM(0xa7090000, BPF_REG_0, 0);
}
jit->exit_ip = jit->prg;
/* Load exit code: lgr %r2,%b0 */
EMIT4(0xb9040000, REG_2, BPF_REG_0);
/* Restore registers */
save_restore_regs(jit, REGS_RESTORE, stack_depth);
if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) {
jit->r14_thunk_ip = jit->prg;
/* Generate __s390_indirect_jump_r14 thunk */
if (test_facility(35)) {
/* exrl %r0,.+10 */
EMIT6_PCREL_RIL(0xc6000000, jit->prg + 10);
} else {
/* larl %r1,.+14 */
EMIT6_PCREL_RILB(0xc0000000, REG_1, jit->prg + 14);
/* ex 0,0(%r1) */
EMIT4_DISP(0x44000000, REG_0, REG_1, 0);
}
/* j . */
EMIT4_PCREL(0xa7f40000, 0);
}
/* br %r14 */
_EMIT2(0x07fe);
if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable &&
(jit->seen & SEEN_FUNC)) {
jit->r1_thunk_ip = jit->prg;
/* Generate __s390_indirect_jump_r1 thunk */
if (test_facility(35)) {
/* exrl %r0,.+10 */
EMIT6_PCREL_RIL(0xc6000000, jit->prg + 10);
/* j . */
EMIT4_PCREL(0xa7f40000, 0);
/* br %r1 */
_EMIT2(0x07f1);
} else {
/* ex 0,S390_lowcore.br_r1_tampoline */
EMIT4_DISP(0x44000000, REG_0, REG_0,
offsetof(struct lowcore, br_r1_trampoline));
/* j . */
EMIT4_PCREL(0xa7f40000, 0);
}
}
}
/*
* Compile one eBPF instruction into s390x code
*
* NOTE: Use noinline because for gcov (-fprofile-arcs) gcc allocates a lot of
* stack space for the large switch statement.
*/
static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i)
{
struct bpf_insn *insn = &fp->insnsi[i];
int jmp_off, last, insn_count = 1;
u32 dst_reg = insn->dst_reg;
u32 src_reg = insn->src_reg;
u32 *addrs = jit->addrs;
s32 imm = insn->imm;
s16 off = insn->off;
unsigned int mask;
if (dst_reg == BPF_REG_AX || src_reg == BPF_REG_AX)
jit->seen |= SEEN_REG_AX;
switch (insn->code) {
/*
* BPF_MOV
*/
case BPF_ALU | BPF_MOV | BPF_X: /* dst = (u32) src */
/* llgfr %dst,%src */
EMIT4(0xb9160000, dst_reg, src_reg);
break;
case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */
/* lgr %dst,%src */
EMIT4(0xb9040000, dst_reg, src_reg);
break;
case BPF_ALU | BPF_MOV | BPF_K: /* dst = (u32) imm */
/* llilf %dst,imm */
EMIT6_IMM(0xc00f0000, dst_reg, imm);
break;
case BPF_ALU64 | BPF_MOV | BPF_K: /* dst = imm */
/* lgfi %dst,imm */
EMIT6_IMM(0xc0010000, dst_reg, imm);
break;
/*
* BPF_LD 64
*/
case BPF_LD | BPF_IMM | BPF_DW: /* dst = (u64) imm */
{
/* 16 byte instruction that uses two 'struct bpf_insn' */
u64 imm64;
imm64 = (u64)(u32) insn[0].imm | ((u64)(u32) insn[1].imm) << 32;
/* lg %dst,<d(imm)>(%l) */
EMIT6_DISP_LH(0xe3000000, 0x0004, dst_reg, REG_0, REG_L,
EMIT_CONST_U64(imm64));
insn_count = 2;
break;
}
/*
* BPF_ADD
*/
case BPF_ALU | BPF_ADD | BPF_X: /* dst = (u32) dst + (u32) src */
/* ar %dst,%src */
EMIT2(0x1a00, dst_reg, src_reg);
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_ADD | BPF_X: /* dst = dst + src */
/* agr %dst,%src */
EMIT4(0xb9080000, dst_reg, src_reg);
break;
case BPF_ALU | BPF_ADD | BPF_K: /* dst = (u32) dst + (u32) imm */
if (!imm)
break;
/* alfi %dst,imm */
EMIT6_IMM(0xc20b0000, dst_reg, imm);
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_ADD | BPF_K: /* dst = dst + imm */
if (!imm)
break;
/* agfi %dst,imm */
EMIT6_IMM(0xc2080000, dst_reg, imm);
break;
/*
* BPF_SUB
*/
case BPF_ALU | BPF_SUB | BPF_X: /* dst = (u32) dst - (u32) src */
/* sr %dst,%src */
EMIT2(0x1b00, dst_reg, src_reg);
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_SUB | BPF_X: /* dst = dst - src */
/* sgr %dst,%src */
EMIT4(0xb9090000, dst_reg, src_reg);
break;
case BPF_ALU | BPF_SUB | BPF_K: /* dst = (u32) dst - (u32) imm */
if (!imm)
break;
/* alfi %dst,-imm */
EMIT6_IMM(0xc20b0000, dst_reg, -imm);
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_SUB | BPF_K: /* dst = dst - imm */
if (!imm)
break;
/* agfi %dst,-imm */
EMIT6_IMM(0xc2080000, dst_reg, -imm);
break;
/*
* BPF_MUL
*/
case BPF_ALU | BPF_MUL | BPF_X: /* dst = (u32) dst * (u32) src */
/* msr %dst,%src */
EMIT4(0xb2520000, dst_reg, src_reg);
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_MUL | BPF_X: /* dst = dst * src */
/* msgr %dst,%src */
EMIT4(0xb90c0000, dst_reg, src_reg);
break;
case BPF_ALU | BPF_MUL | BPF_K: /* dst = (u32) dst * (u32) imm */
if (imm == 1)
break;
/* msfi %r5,imm */
EMIT6_IMM(0xc2010000, dst_reg, imm);
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_MUL | BPF_K: /* dst = dst * imm */
if (imm == 1)
break;
/* msgfi %dst,imm */
EMIT6_IMM(0xc2000000, dst_reg, imm);
break;
/*
* BPF_DIV / BPF_MOD
*/
case BPF_ALU | BPF_DIV | BPF_X: /* dst = (u32) dst / (u32) src */
case BPF_ALU | BPF_MOD | BPF_X: /* dst = (u32) dst % (u32) src */
{
int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
/* lhi %w0,0 */
EMIT4_IMM(0xa7080000, REG_W0, 0);
/* lr %w1,%dst */
EMIT2(0x1800, REG_W1, dst_reg);
/* dlr %w0,%src */
EMIT4(0xb9970000, REG_W0, src_reg);
/* llgfr %dst,%rc */
EMIT4(0xb9160000, dst_reg, rc_reg);
break;
}
case BPF_ALU64 | BPF_DIV | BPF_X: /* dst = dst / src */
case BPF_ALU64 | BPF_MOD | BPF_X: /* dst = dst % src */
{
int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
/* lghi %w0,0 */
EMIT4_IMM(0xa7090000, REG_W0, 0);
/* lgr %w1,%dst */
EMIT4(0xb9040000, REG_W1, dst_reg);
/* dlgr %w0,%dst */
EMIT4(0xb9870000, REG_W0, src_reg);
/* lgr %dst,%rc */
EMIT4(0xb9040000, dst_reg, rc_reg);
break;
}
case BPF_ALU | BPF_DIV | BPF_K: /* dst = (u32) dst / (u32) imm */
case BPF_ALU | BPF_MOD | BPF_K: /* dst = (u32) dst % (u32) imm */
{
int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
if (imm == 1) {
if (BPF_OP(insn->code) == BPF_MOD)
/* lhgi %dst,0 */
EMIT4_IMM(0xa7090000, dst_reg, 0);
break;
}
/* lhi %w0,0 */
EMIT4_IMM(0xa7080000, REG_W0, 0);
/* lr %w1,%dst */
EMIT2(0x1800, REG_W1, dst_reg);
/* dl %w0,<d(imm)>(%l) */
EMIT6_DISP_LH(0xe3000000, 0x0097, REG_W0, REG_0, REG_L,
EMIT_CONST_U32(imm));
/* llgfr %dst,%rc */
EMIT4(0xb9160000, dst_reg, rc_reg);
break;
}
case BPF_ALU64 | BPF_DIV | BPF_K: /* dst = dst / imm */
case BPF_ALU64 | BPF_MOD | BPF_K: /* dst = dst % imm */
{
int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
if (imm == 1) {
if (BPF_OP(insn->code) == BPF_MOD)
/* lhgi %dst,0 */
EMIT4_IMM(0xa7090000, dst_reg, 0);
break;
}
/* lghi %w0,0 */
EMIT4_IMM(0xa7090000, REG_W0, 0);
/* lgr %w1,%dst */
EMIT4(0xb9040000, REG_W1, dst_reg);
/* dlg %w0,<d(imm)>(%l) */
EMIT6_DISP_LH(0xe3000000, 0x0087, REG_W0, REG_0, REG_L,
EMIT_CONST_U64(imm));
/* lgr %dst,%rc */
EMIT4(0xb9040000, dst_reg, rc_reg);
break;
}
/*
* BPF_AND
*/
case BPF_ALU | BPF_AND | BPF_X: /* dst = (u32) dst & (u32) src */
/* nr %dst,%src */
EMIT2(0x1400, dst_reg, src_reg);
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_AND | BPF_X: /* dst = dst & src */
/* ngr %dst,%src */
EMIT4(0xb9800000, dst_reg, src_reg);
break;
case BPF_ALU | BPF_AND | BPF_K: /* dst = (u32) dst & (u32) imm */
/* nilf %dst,imm */
EMIT6_IMM(0xc00b0000, dst_reg, imm);
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_AND | BPF_K: /* dst = dst & imm */
/* ng %dst,<d(imm)>(%l) */
EMIT6_DISP_LH(0xe3000000, 0x0080, dst_reg, REG_0, REG_L,
EMIT_CONST_U64(imm));
break;
/*
* BPF_OR
*/
case BPF_ALU | BPF_OR | BPF_X: /* dst = (u32) dst | (u32) src */
/* or %dst,%src */
EMIT2(0x1600, dst_reg, src_reg);
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_OR | BPF_X: /* dst = dst | src */
/* ogr %dst,%src */
EMIT4(0xb9810000, dst_reg, src_reg);
break;
case BPF_ALU | BPF_OR | BPF_K: /* dst = (u32) dst | (u32) imm */
/* oilf %dst,imm */
EMIT6_IMM(0xc00d0000, dst_reg, imm);
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_OR | BPF_K: /* dst = dst | imm */
/* og %dst,<d(imm)>(%l) */
EMIT6_DISP_LH(0xe3000000, 0x0081, dst_reg, REG_0, REG_L,
EMIT_CONST_U64(imm));
break;
/*
* BPF_XOR
*/
case BPF_ALU | BPF_XOR | BPF_X: /* dst = (u32) dst ^ (u32) src */
/* xr %dst,%src */
EMIT2(0x1700, dst_reg, src_reg);
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_XOR | BPF_X: /* dst = dst ^ src */
/* xgr %dst,%src */
EMIT4(0xb9820000, dst_reg, src_reg);
break;
case BPF_ALU | BPF_XOR | BPF_K: /* dst = (u32) dst ^ (u32) imm */
if (!imm)
break;
/* xilf %dst,imm */
EMIT6_IMM(0xc0070000, dst_reg, imm);
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_XOR | BPF_K: /* dst = dst ^ imm */
/* xg %dst,<d(imm)>(%l) */
EMIT6_DISP_LH(0xe3000000, 0x0082, dst_reg, REG_0, REG_L,
EMIT_CONST_U64(imm));
break;
/*
* BPF_LSH
*/
case BPF_ALU | BPF_LSH | BPF_X: /* dst = (u32) dst << (u32) src */
/* sll %dst,0(%src) */
EMIT4_DISP(0x89000000, dst_reg, src_reg, 0);
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_LSH | BPF_X: /* dst = dst << src */
/* sllg %dst,%dst,0(%src) */
EMIT6_DISP_LH(0xeb000000, 0x000d, dst_reg, dst_reg, src_reg, 0);
break;
case BPF_ALU | BPF_LSH | BPF_K: /* dst = (u32) dst << (u32) imm */
if (imm == 0)
break;
/* sll %dst,imm(%r0) */
EMIT4_DISP(0x89000000, dst_reg, REG_0, imm);
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_LSH | BPF_K: /* dst = dst << imm */
if (imm == 0)
break;
/* sllg %dst,%dst,imm(%r0) */
EMIT6_DISP_LH(0xeb000000, 0x000d, dst_reg, dst_reg, REG_0, imm);
break;
/*
* BPF_RSH
*/
case BPF_ALU | BPF_RSH | BPF_X: /* dst = (u32) dst >> (u32) src */
/* srl %dst,0(%src) */
EMIT4_DISP(0x88000000, dst_reg, src_reg, 0);
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_RSH | BPF_X: /* dst = dst >> src */
/* srlg %dst,%dst,0(%src) */
EMIT6_DISP_LH(0xeb000000, 0x000c, dst_reg, dst_reg, src_reg, 0);
break;
case BPF_ALU | BPF_RSH | BPF_K: /* dst = (u32) dst >> (u32) imm */
if (imm == 0)
break;
/* srl %dst,imm(%r0) */
EMIT4_DISP(0x88000000, dst_reg, REG_0, imm);
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_RSH | BPF_K: /* dst = dst >> imm */
if (imm == 0)
break;
/* srlg %dst,%dst,imm(%r0) */
EMIT6_DISP_LH(0xeb000000, 0x000c, dst_reg, dst_reg, REG_0, imm);
break;
/*
* BPF_ARSH
*/
case BPF_ALU64 | BPF_ARSH | BPF_X: /* ((s64) dst) >>= src */
/* srag %dst,%dst,0(%src) */
EMIT6_DISP_LH(0xeb000000, 0x000a, dst_reg, dst_reg, src_reg, 0);
break;
case BPF_ALU64 | BPF_ARSH | BPF_K: /* ((s64) dst) >>= imm */
if (imm == 0)
break;
/* srag %dst,%dst,imm(%r0) */
EMIT6_DISP_LH(0xeb000000, 0x000a, dst_reg, dst_reg, REG_0, imm);
break;
/*
* BPF_NEG
*/
case BPF_ALU | BPF_NEG: /* dst = (u32) -dst */
/* lcr %dst,%dst */
EMIT2(0x1300, dst_reg, dst_reg);
EMIT_ZERO(dst_reg);
break;
case BPF_ALU64 | BPF_NEG: /* dst = -dst */
/* lcgr %dst,%dst */
EMIT4(0xb9130000, dst_reg, dst_reg);
break;
/*
* BPF_FROM_BE/LE
*/
case BPF_ALU | BPF_END | BPF_FROM_BE:
/* s390 is big endian, therefore only clear high order bytes */
switch (imm) {
case 16: /* dst = (u16) cpu_to_be16(dst) */
/* llghr %dst,%dst */
EMIT4(0xb9850000, dst_reg, dst_reg);
break;
case 32: /* dst = (u32) cpu_to_be32(dst) */
/* llgfr %dst,%dst */
EMIT4(0xb9160000, dst_reg, dst_reg);
break;
case 64: /* dst = (u64) cpu_to_be64(dst) */
break;
}
break;
case BPF_ALU | BPF_END | BPF_FROM_LE:
switch (imm) {
case 16: /* dst = (u16) cpu_to_le16(dst) */
/* lrvr %dst,%dst */
EMIT4(0xb91f0000, dst_reg, dst_reg);
/* srl %dst,16(%r0) */
EMIT4_DISP(0x88000000, dst_reg, REG_0, 16);
/* llghr %dst,%dst */
EMIT4(0xb9850000, dst_reg, dst_reg);
break;
case 32: /* dst = (u32) cpu_to_le32(dst) */
/* lrvr %dst,%dst */
EMIT4(0xb91f0000, dst_reg, dst_reg);
/* llgfr %dst,%dst */
EMIT4(0xb9160000, dst_reg, dst_reg);
break;
case 64: /* dst = (u64) cpu_to_le64(dst) */
/* lrvgr %dst,%dst */
EMIT4(0xb90f0000, dst_reg, dst_reg);
break;
}
break;
/*
* BPF_ST(X)
*/
case BPF_STX | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = src_reg */
/* stcy %src,off(%dst) */
EMIT6_DISP_LH(0xe3000000, 0x0072, src_reg, dst_reg, REG_0, off);
jit->seen |= SEEN_MEM;
break;
case BPF_STX | BPF_MEM | BPF_H: /* (u16 *)(dst + off) = src */
/* sthy %src,off(%dst) */
EMIT6_DISP_LH(0xe3000000, 0x0070, src_reg, dst_reg, REG_0, off);
jit->seen |= SEEN_MEM;
break;
case BPF_STX | BPF_MEM | BPF_W: /* *(u32 *)(dst + off) = src */
/* sty %src,off(%dst) */
EMIT6_DISP_LH(0xe3000000, 0x0050, src_reg, dst_reg, REG_0, off);
jit->seen |= SEEN_MEM;
break;
case BPF_STX | BPF_MEM | BPF_DW: /* (u64 *)(dst + off) = src */
/* stg %src,off(%dst) */
EMIT6_DISP_LH(0xe3000000, 0x0024, src_reg, dst_reg, REG_0, off);
jit->seen |= SEEN_MEM;
break;
case BPF_ST | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = imm */
/* lhi %w0,imm */
EMIT4_IMM(0xa7080000, REG_W0, (u8) imm);
/* stcy %w0,off(dst) */
EMIT6_DISP_LH(0xe3000000, 0x0072, REG_W0, dst_reg, REG_0, off);
jit->seen |= SEEN_MEM;
break;
case BPF_ST | BPF_MEM | BPF_H: /* (u16 *)(dst + off) = imm */
/* lhi %w0,imm */
EMIT4_IMM(0xa7080000, REG_W0, (u16) imm);
/* sthy %w0,off(dst) */
EMIT6_DISP_LH(0xe3000000, 0x0070, REG_W0, dst_reg, REG_0, off);
jit->seen |= SEEN_MEM;
break;
case BPF_ST | BPF_MEM | BPF_W: /* *(u32 *)(dst + off) = imm */
/* llilf %w0,imm */
EMIT6_IMM(0xc00f0000, REG_W0, (u32) imm);
/* sty %w0,off(%dst) */
EMIT6_DISP_LH(0xe3000000, 0x0050, REG_W0, dst_reg, REG_0, off);
jit->seen |= SEEN_MEM;
break;
case BPF_ST | BPF_MEM | BPF_DW: /* *(u64 *)(dst + off) = imm */
/* lgfi %w0,imm */
EMIT6_IMM(0xc0010000, REG_W0, imm);
/* stg %w0,off(%dst) */
EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W0, dst_reg, REG_0, off);
jit->seen |= SEEN_MEM;
break;
/*
* BPF_STX XADD (atomic_add)
*/
case BPF_STX | BPF_XADD | BPF_W: /* *(u32 *)(dst + off) += src */
/* laal %w0,%src,off(%dst) */
EMIT6_DISP_LH(0xeb000000, 0x00fa, REG_W0, src_reg,
dst_reg, off);
jit->seen |= SEEN_MEM;
break;
case BPF_STX | BPF_XADD | BPF_DW: /* *(u64 *)(dst + off) += src */
/* laalg %w0,%src,off(%dst) */
EMIT6_DISP_LH(0xeb000000, 0x00ea, REG_W0, src_reg,
dst_reg, off);
jit->seen |= SEEN_MEM;
break;
/*
* BPF_LDX
*/
case BPF_LDX | BPF_MEM | BPF_B: /* dst = *(u8 *)(ul) (src + off) */
/* llgc %dst,0(off,%src) */
EMIT6_DISP_LH(0xe3000000, 0x0090, dst_reg, src_reg, REG_0, off);
jit->seen |= SEEN_MEM;
break;
case BPF_LDX | BPF_MEM | BPF_H: /* dst = *(u16 *)(ul) (src + off) */
/* llgh %dst,0(off,%src) */
EMIT6_DISP_LH(0xe3000000, 0x0091, dst_reg, src_reg, REG_0, off);
jit->seen |= SEEN_MEM;
break;
case BPF_LDX | BPF_MEM | BPF_W: /* dst = *(u32 *)(ul) (src + off) */
/* llgf %dst,off(%src) */
jit->seen |= SEEN_MEM;
EMIT6_DISP_LH(0xe3000000, 0x0016, dst_reg, src_reg, REG_0, off);
break;
case BPF_LDX | BPF_MEM | BPF_DW: /* dst = *(u64 *)(ul) (src + off) */
/* lg %dst,0(off,%src) */
jit->seen |= SEEN_MEM;
EMIT6_DISP_LH(0xe3000000, 0x0004, dst_reg, src_reg, REG_0, off);
break;
/*
* BPF_JMP / CALL
*/
case BPF_JMP | BPF_CALL:
{
/*
* b0 = (__bpf_call_base + imm)(b1, b2, b3, b4, b5)
*/
const u64 func = (u64)__bpf_call_base + imm;
REG_SET_SEEN(BPF_REG_5);
jit->seen |= SEEN_FUNC;
/* lg %w1,<d(imm)>(%l) */
EMIT6_DISP_LH(0xe3000000, 0x0004, REG_W1, REG_0, REG_L,
EMIT_CONST_U64(func));
if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) {
/* brasl %r14,__s390_indirect_jump_r1 */
EMIT6_PCREL_RILB(0xc0050000, REG_14, jit->r1_thunk_ip);
} else {
/* basr %r14,%w1 */
EMIT2(0x0d00, REG_14, REG_W1);
}
/* lgr %b0,%r2: load return value into %b0 */
EMIT4(0xb9040000, BPF_REG_0, REG_2);
break;
}
case BPF_JMP | BPF_TAIL_CALL:
s390/bpf: implement bpf_tail_call() helper bpf_tail_call() arguments: - ctx......: Context pointer - jmp_table: One of BPF_MAP_TYPE_PROG_ARRAY maps used as the jump table - index....: Index in the jump table In this implementation s390x JIT does stack unwinding and jumps into the callee program prologue. Caller and callee use the same stack. With this patch a tail call generates the following code on s390x: if (index >= array->map.max_entries) goto out 000003ff8001c7e4: e31030100016 llgf %r1,16(%r3) 000003ff8001c7ea: ec41001fa065 clgrj %r4,%r1,10,3ff8001c828 if (tail_call_cnt++ > MAX_TAIL_CALL_CNT) goto out; 000003ff8001c7f0: a7080001 lhi %r0,1 000003ff8001c7f4: eb10f25000fa laal %r1,%r0,592(%r15) 000003ff8001c7fa: ec120017207f clij %r1,32,2,3ff8001c828 prog = array->prog[index]; if (prog == NULL) goto out; 000003ff8001c800: eb140003000d sllg %r1,%r4,3 000003ff8001c806: e31310800004 lg %r1,128(%r3,%r1) 000003ff8001c80c: ec18000e007d clgij %r1,0,8,3ff8001c828 Restore registers before calling function 000003ff8001c812: eb68f2980004 lmg %r6,%r8,664(%r15) 000003ff8001c818: ebbff2c00004 lmg %r11,%r15,704(%r15) goto *(prog->bpf_func + tail_call_start); 000003ff8001c81e: e31100200004 lg %r1,32(%r1,%r0) 000003ff8001c824: 47f01006 bc 15,6(%r1) Reviewed-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-09 12:51:06 +08:00
/*
* Implicit input:
* B1: pointer to ctx
* B2: pointer to bpf_array
* B3: index in bpf_array
*/
jit->seen |= SEEN_TAIL_CALL;
/*
* if (index >= array->map.max_entries)
* goto out;
*/
/* llgf %w1,map.max_entries(%b2) */
EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_2,
offsetof(struct bpf_array, map.max_entries));
/* clgrj %b3,%w1,0xa,label0: if %b3 >= %w1 goto out */
EMIT6_PCREL_LABEL(0xec000000, 0x0065, BPF_REG_3,
REG_W1, 0, 0xa);
/*
* if (tail_call_cnt++ > MAX_TAIL_CALL_CNT)
* goto out;
*/
if (jit->seen & SEEN_STACK)
off = STK_OFF_TCCNT + STK_OFF + fp->aux->stack_depth;
s390/bpf: implement bpf_tail_call() helper bpf_tail_call() arguments: - ctx......: Context pointer - jmp_table: One of BPF_MAP_TYPE_PROG_ARRAY maps used as the jump table - index....: Index in the jump table In this implementation s390x JIT does stack unwinding and jumps into the callee program prologue. Caller and callee use the same stack. With this patch a tail call generates the following code on s390x: if (index >= array->map.max_entries) goto out 000003ff8001c7e4: e31030100016 llgf %r1,16(%r3) 000003ff8001c7ea: ec41001fa065 clgrj %r4,%r1,10,3ff8001c828 if (tail_call_cnt++ > MAX_TAIL_CALL_CNT) goto out; 000003ff8001c7f0: a7080001 lhi %r0,1 000003ff8001c7f4: eb10f25000fa laal %r1,%r0,592(%r15) 000003ff8001c7fa: ec120017207f clij %r1,32,2,3ff8001c828 prog = array->prog[index]; if (prog == NULL) goto out; 000003ff8001c800: eb140003000d sllg %r1,%r4,3 000003ff8001c806: e31310800004 lg %r1,128(%r3,%r1) 000003ff8001c80c: ec18000e007d clgij %r1,0,8,3ff8001c828 Restore registers before calling function 000003ff8001c812: eb68f2980004 lmg %r6,%r8,664(%r15) 000003ff8001c818: ebbff2c00004 lmg %r11,%r15,704(%r15) goto *(prog->bpf_func + tail_call_start); 000003ff8001c81e: e31100200004 lg %r1,32(%r1,%r0) 000003ff8001c824: 47f01006 bc 15,6(%r1) Reviewed-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-09 12:51:06 +08:00
else
off = STK_OFF_TCCNT;
/* lhi %w0,1 */
EMIT4_IMM(0xa7080000, REG_W0, 1);
/* laal %w1,%w0,off(%r15) */
EMIT6_DISP_LH(0xeb000000, 0x00fa, REG_W1, REG_W0, REG_15, off);
/* clij %w1,MAX_TAIL_CALL_CNT,0x2,label0 */
EMIT6_PCREL_IMM_LABEL(0xec000000, 0x007f, REG_W1,
MAX_TAIL_CALL_CNT, 0, 0x2);
/*
* prog = array->ptrs[index];
s390/bpf: implement bpf_tail_call() helper bpf_tail_call() arguments: - ctx......: Context pointer - jmp_table: One of BPF_MAP_TYPE_PROG_ARRAY maps used as the jump table - index....: Index in the jump table In this implementation s390x JIT does stack unwinding and jumps into the callee program prologue. Caller and callee use the same stack. With this patch a tail call generates the following code on s390x: if (index >= array->map.max_entries) goto out 000003ff8001c7e4: e31030100016 llgf %r1,16(%r3) 000003ff8001c7ea: ec41001fa065 clgrj %r4,%r1,10,3ff8001c828 if (tail_call_cnt++ > MAX_TAIL_CALL_CNT) goto out; 000003ff8001c7f0: a7080001 lhi %r0,1 000003ff8001c7f4: eb10f25000fa laal %r1,%r0,592(%r15) 000003ff8001c7fa: ec120017207f clij %r1,32,2,3ff8001c828 prog = array->prog[index]; if (prog == NULL) goto out; 000003ff8001c800: eb140003000d sllg %r1,%r4,3 000003ff8001c806: e31310800004 lg %r1,128(%r3,%r1) 000003ff8001c80c: ec18000e007d clgij %r1,0,8,3ff8001c828 Restore registers before calling function 000003ff8001c812: eb68f2980004 lmg %r6,%r8,664(%r15) 000003ff8001c818: ebbff2c00004 lmg %r11,%r15,704(%r15) goto *(prog->bpf_func + tail_call_start); 000003ff8001c81e: e31100200004 lg %r1,32(%r1,%r0) 000003ff8001c824: 47f01006 bc 15,6(%r1) Reviewed-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-09 12:51:06 +08:00
* if (prog == NULL)
* goto out;
*/
/* sllg %r1,%b3,3: %r1 = index * 8 */
EMIT6_DISP_LH(0xeb000000, 0x000d, REG_1, BPF_REG_3, REG_0, 3);
/* lg %r1,prog(%b2,%r1) */
EMIT6_DISP_LH(0xe3000000, 0x0004, REG_1, BPF_REG_2,
REG_1, offsetof(struct bpf_array, ptrs));
s390/bpf: implement bpf_tail_call() helper bpf_tail_call() arguments: - ctx......: Context pointer - jmp_table: One of BPF_MAP_TYPE_PROG_ARRAY maps used as the jump table - index....: Index in the jump table In this implementation s390x JIT does stack unwinding and jumps into the callee program prologue. Caller and callee use the same stack. With this patch a tail call generates the following code on s390x: if (index >= array->map.max_entries) goto out 000003ff8001c7e4: e31030100016 llgf %r1,16(%r3) 000003ff8001c7ea: ec41001fa065 clgrj %r4,%r1,10,3ff8001c828 if (tail_call_cnt++ > MAX_TAIL_CALL_CNT) goto out; 000003ff8001c7f0: a7080001 lhi %r0,1 000003ff8001c7f4: eb10f25000fa laal %r1,%r0,592(%r15) 000003ff8001c7fa: ec120017207f clij %r1,32,2,3ff8001c828 prog = array->prog[index]; if (prog == NULL) goto out; 000003ff8001c800: eb140003000d sllg %r1,%r4,3 000003ff8001c806: e31310800004 lg %r1,128(%r3,%r1) 000003ff8001c80c: ec18000e007d clgij %r1,0,8,3ff8001c828 Restore registers before calling function 000003ff8001c812: eb68f2980004 lmg %r6,%r8,664(%r15) 000003ff8001c818: ebbff2c00004 lmg %r11,%r15,704(%r15) goto *(prog->bpf_func + tail_call_start); 000003ff8001c81e: e31100200004 lg %r1,32(%r1,%r0) 000003ff8001c824: 47f01006 bc 15,6(%r1) Reviewed-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-09 12:51:06 +08:00
/* clgij %r1,0,0x8,label0 */
EMIT6_PCREL_IMM_LABEL(0xec000000, 0x007d, REG_1, 0, 0, 0x8);
/*
* Restore registers before calling function
*/
save_restore_regs(jit, REGS_RESTORE, fp->aux->stack_depth);
s390/bpf: implement bpf_tail_call() helper bpf_tail_call() arguments: - ctx......: Context pointer - jmp_table: One of BPF_MAP_TYPE_PROG_ARRAY maps used as the jump table - index....: Index in the jump table In this implementation s390x JIT does stack unwinding and jumps into the callee program prologue. Caller and callee use the same stack. With this patch a tail call generates the following code on s390x: if (index >= array->map.max_entries) goto out 000003ff8001c7e4: e31030100016 llgf %r1,16(%r3) 000003ff8001c7ea: ec41001fa065 clgrj %r4,%r1,10,3ff8001c828 if (tail_call_cnt++ > MAX_TAIL_CALL_CNT) goto out; 000003ff8001c7f0: a7080001 lhi %r0,1 000003ff8001c7f4: eb10f25000fa laal %r1,%r0,592(%r15) 000003ff8001c7fa: ec120017207f clij %r1,32,2,3ff8001c828 prog = array->prog[index]; if (prog == NULL) goto out; 000003ff8001c800: eb140003000d sllg %r1,%r4,3 000003ff8001c806: e31310800004 lg %r1,128(%r3,%r1) 000003ff8001c80c: ec18000e007d clgij %r1,0,8,3ff8001c828 Restore registers before calling function 000003ff8001c812: eb68f2980004 lmg %r6,%r8,664(%r15) 000003ff8001c818: ebbff2c00004 lmg %r11,%r15,704(%r15) goto *(prog->bpf_func + tail_call_start); 000003ff8001c81e: e31100200004 lg %r1,32(%r1,%r0) 000003ff8001c824: 47f01006 bc 15,6(%r1) Reviewed-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-09 12:51:06 +08:00
/*
* goto *(prog->bpf_func + tail_call_start);
*/
/* lg %r1,bpf_func(%r1) */
EMIT6_DISP_LH(0xe3000000, 0x0004, REG_1, REG_1, REG_0,
offsetof(struct bpf_prog, bpf_func));
/* bc 0xf,tail_call_start(%r1) */
_EMIT4(0x47f01000 + jit->tail_call_start);
/* out: */
jit->labels[0] = jit->prg;
break;
case BPF_JMP | BPF_EXIT: /* return b0 */
last = (i == fp->len - 1) ? 1 : 0;
if (last && !(jit->seen & SEEN_RET0))
break;
/* j <exit> */
EMIT4_PCREL(0xa7f40000, jit->exit_ip - jit->prg);
break;
/*
* Branch relative (number of skipped instructions) to offset on
* condition.
*
* Condition code to mask mapping:
*
* CC | Description | Mask
* ------------------------------
* 0 | Operands equal | 8
* 1 | First operand low | 4
* 2 | First operand high | 2
* 3 | Unused | 1
*
* For s390x relative branches: ip = ip + off_bytes
* For BPF relative branches: insn = insn + off_insns + 1
*
* For example for s390x with offset 0 we jump to the branch
* instruction itself (loop) and for BPF with offset 0 we
* branch to the instruction behind the branch.
*/
case BPF_JMP | BPF_JA: /* if (true) */
mask = 0xf000; /* j */
goto branch_oc;
case BPF_JMP | BPF_JSGT | BPF_K: /* ((s64) dst > (s64) imm) */
mask = 0x2000; /* jh */
goto branch_ks;
case BPF_JMP | BPF_JSLT | BPF_K: /* ((s64) dst < (s64) imm) */
mask = 0x4000; /* jl */
goto branch_ks;
case BPF_JMP | BPF_JSGE | BPF_K: /* ((s64) dst >= (s64) imm) */
mask = 0xa000; /* jhe */
goto branch_ks;
case BPF_JMP | BPF_JSLE | BPF_K: /* ((s64) dst <= (s64) imm) */
mask = 0xc000; /* jle */
goto branch_ks;
case BPF_JMP | BPF_JGT | BPF_K: /* (dst_reg > imm) */
mask = 0x2000; /* jh */
goto branch_ku;
case BPF_JMP | BPF_JLT | BPF_K: /* (dst_reg < imm) */
mask = 0x4000; /* jl */
goto branch_ku;
case BPF_JMP | BPF_JGE | BPF_K: /* (dst_reg >= imm) */
mask = 0xa000; /* jhe */
goto branch_ku;
case BPF_JMP | BPF_JLE | BPF_K: /* (dst_reg <= imm) */
mask = 0xc000; /* jle */
goto branch_ku;
case BPF_JMP | BPF_JNE | BPF_K: /* (dst_reg != imm) */
mask = 0x7000; /* jne */
goto branch_ku;
case BPF_JMP | BPF_JEQ | BPF_K: /* (dst_reg == imm) */
mask = 0x8000; /* je */
goto branch_ku;
case BPF_JMP | BPF_JSET | BPF_K: /* (dst_reg & imm) */
mask = 0x7000; /* jnz */
/* lgfi %w1,imm (load sign extend imm) */
EMIT6_IMM(0xc0010000, REG_W1, imm);
/* ngr %w1,%dst */
EMIT4(0xb9800000, REG_W1, dst_reg);
goto branch_oc;
case BPF_JMP | BPF_JSGT | BPF_X: /* ((s64) dst > (s64) src) */
mask = 0x2000; /* jh */
goto branch_xs;
case BPF_JMP | BPF_JSLT | BPF_X: /* ((s64) dst < (s64) src) */
mask = 0x4000; /* jl */
goto branch_xs;
case BPF_JMP | BPF_JSGE | BPF_X: /* ((s64) dst >= (s64) src) */
mask = 0xa000; /* jhe */
goto branch_xs;
case BPF_JMP | BPF_JSLE | BPF_X: /* ((s64) dst <= (s64) src) */
mask = 0xc000; /* jle */
goto branch_xs;
case BPF_JMP | BPF_JGT | BPF_X: /* (dst > src) */
mask = 0x2000; /* jh */
goto branch_xu;
case BPF_JMP | BPF_JLT | BPF_X: /* (dst < src) */
mask = 0x4000; /* jl */
goto branch_xu;
case BPF_JMP | BPF_JGE | BPF_X: /* (dst >= src) */
mask = 0xa000; /* jhe */
goto branch_xu;
case BPF_JMP | BPF_JLE | BPF_X: /* (dst <= src) */
mask = 0xc000; /* jle */
goto branch_xu;
case BPF_JMP | BPF_JNE | BPF_X: /* (dst != src) */
mask = 0x7000; /* jne */
goto branch_xu;
case BPF_JMP | BPF_JEQ | BPF_X: /* (dst == src) */
mask = 0x8000; /* je */
goto branch_xu;
case BPF_JMP | BPF_JSET | BPF_X: /* (dst & src) */
mask = 0x7000; /* jnz */
/* ngrk %w1,%dst,%src */
EMIT4_RRF(0xb9e40000, REG_W1, dst_reg, src_reg);
goto branch_oc;
branch_ks:
/* lgfi %w1,imm (load sign extend imm) */
EMIT6_IMM(0xc0010000, REG_W1, imm);
/* cgrj %dst,%w1,mask,off */
EMIT6_PCREL(0xec000000, 0x0064, dst_reg, REG_W1, i, off, mask);
break;
branch_ku:
/* lgfi %w1,imm (load sign extend imm) */
EMIT6_IMM(0xc0010000, REG_W1, imm);
/* clgrj %dst,%w1,mask,off */
EMIT6_PCREL(0xec000000, 0x0065, dst_reg, REG_W1, i, off, mask);
break;
branch_xs:
/* cgrj %dst,%src,mask,off */
EMIT6_PCREL(0xec000000, 0x0064, dst_reg, src_reg, i, off, mask);
break;
branch_xu:
/* clgrj %dst,%src,mask,off */
EMIT6_PCREL(0xec000000, 0x0065, dst_reg, src_reg, i, off, mask);
break;
branch_oc:
/* brc mask,jmp_off (branch instruction needs 4 bytes) */
jmp_off = addrs[i + off + 1] - (addrs[i + 1] - 4);
EMIT4_PCREL(0xa7040000 | mask << 8, jmp_off);
break;
default: /* too complex, give up */
pr_err("Unknown opcode %02x\n", insn->code);
return -1;
}
return insn_count;
}
/*
* Compile eBPF program into s390x code
*/
static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp)
{
int i, insn_count;
jit->lit = jit->lit_start;
jit->prg = 0;
bpf_jit_prologue(jit, fp->aux->stack_depth);
for (i = 0; i < fp->len; i += insn_count) {
insn_count = bpf_jit_insn(jit, fp, i);
if (insn_count < 0)
return -1;
bpf, s390: fix jit branch offset related to ldimm64 While testing some other work that required JIT modifications, I run into test_bpf causing a hang when JIT enabled on s390. The problematic test case was the one from ddc665a4bb4b (bpf, arm64: fix jit branch offset related to ldimm64), and turns out that we do have a similar issue on s390 as well. In bpf_jit_prog() we update next instruction address after returning from bpf_jit_insn() with an insn_count. bpf_jit_insn() returns either -1 in case of error (e.g. unsupported insn), 1 or 2. The latter is only the case for ldimm64 due to spanning 2 insns, however, next address is only set to i + 1 not taking actual insn_count into account, thus fix is to use insn_count instead of 1. bpf_jit_enable in mode 2 provides also disasm on s390: Before fix: 000003ff800349b6: a7f40003 brc 15,3ff800349bc ; target 000003ff800349ba: 0000 unknown 000003ff800349bc: e3b0f0700024 stg %r11,112(%r15) 000003ff800349c2: e3e0f0880024 stg %r14,136(%r15) 000003ff800349c8: 0db0 basr %r11,%r0 000003ff800349ca: c0ef00000000 llilf %r14,0 000003ff800349d0: e320b0360004 lg %r2,54(%r11) 000003ff800349d6: e330b03e0004 lg %r3,62(%r11) 000003ff800349dc: ec23ffeda065 clgrj %r2,%r3,10,3ff800349b6 ; jmp 000003ff800349e2: e3e0b0460004 lg %r14,70(%r11) 000003ff800349e8: e3e0b04e0004 lg %r14,78(%r11) 000003ff800349ee: b904002e lgr %r2,%r14 000003ff800349f2: e3b0f0700004 lg %r11,112(%r15) 000003ff800349f8: e3e0f0880004 lg %r14,136(%r15) 000003ff800349fe: 07fe bcr 15,%r14 After fix: 000003ff80ef3db4: a7f40003 brc 15,3ff80ef3dba 000003ff80ef3db8: 0000 unknown 000003ff80ef3dba: e3b0f0700024 stg %r11,112(%r15) 000003ff80ef3dc0: e3e0f0880024 stg %r14,136(%r15) 000003ff80ef3dc6: 0db0 basr %r11,%r0 000003ff80ef3dc8: c0ef00000000 llilf %r14,0 000003ff80ef3dce: e320b0360004 lg %r2,54(%r11) 000003ff80ef3dd4: e330b03e0004 lg %r3,62(%r11) 000003ff80ef3dda: ec230006a065 clgrj %r2,%r3,10,3ff80ef3de6 ; jmp 000003ff80ef3de0: e3e0b0460004 lg %r14,70(%r11) 000003ff80ef3de6: e3e0b04e0004 lg %r14,78(%r11) ; target 000003ff80ef3dec: b904002e lgr %r2,%r14 000003ff80ef3df0: e3b0f0700004 lg %r11,112(%r15) 000003ff80ef3df6: e3e0f0880004 lg %r14,136(%r15) 000003ff80ef3dfc: 07fe bcr 15,%r14 test_bpf.ko suite runs fine after the fix. Fixes: 054623105728 ("s390/bpf: Add s390x eBPF JIT compiler backend") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Tested-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-04 20:20:54 +08:00
/* Next instruction address */
jit->addrs[i + insn_count] = jit->prg;
}
bpf_jit_epilogue(jit, fp->aux->stack_depth);
jit->lit_start = jit->prg;
jit->size = jit->lit;
jit->size_prg = jit->prg;
return 0;
}
/*
* Compile eBPF program "fp"
*/
struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
{
struct bpf_prog *tmp, *orig_fp = fp;
struct bpf_binary_header *header;
bool tmp_blinded = false;
struct bpf_jit jit;
int pass;
if (!fp->jit_requested)
return orig_fp;
tmp = bpf_jit_blind_constants(fp);
/*
* If blinding was requested and we failed during blinding,
* we must fall back to the interpreter.
*/
if (IS_ERR(tmp))
return orig_fp;
if (tmp != fp) {
tmp_blinded = true;
fp = tmp;
}
memset(&jit, 0, sizeof(jit));
jit.addrs = kcalloc(fp->len + 1, sizeof(*jit.addrs), GFP_KERNEL);
if (jit.addrs == NULL) {
fp = orig_fp;
goto out;
}
/*
* Three initial passes:
* - 1/2: Determine clobbered registers
* - 3: Calculate program size and addrs arrray
*/
for (pass = 1; pass <= 3; pass++) {
if (bpf_jit_prog(&jit, fp)) {
fp = orig_fp;
goto free_addrs;
}
}
/*
* Final pass: Allocate and generate program
*/
if (jit.size >= BPF_SIZE_MAX) {
fp = orig_fp;
goto free_addrs;
}
header = bpf_jit_binary_alloc(jit.size, &jit.prg_buf, 2, jit_fill_hole);
if (!header) {
fp = orig_fp;
goto free_addrs;
}
if (bpf_jit_prog(&jit, fp)) {
bpf_jit_binary_free(header);
fp = orig_fp;
goto free_addrs;
}
if (bpf_jit_enable > 1) {
bpf_jit_dump(fp->len, jit.size, pass, jit.prg_buf);
print_fn_code(jit.prg_buf, jit.size_prg);
}
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux Pull s390 updates from Martin Schwidefsky: - New entropy generation for the pseudo random number generator. - Early boot printk output via sclp to help debug crashes on boot. This needs to be enabled with a kernel parameter. - Add proper no-execute support with a bit in the page table entry. - Bug fixes and cleanups. * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (65 commits) s390/syscall: fix single stepped system calls s390/zcrypt: make ap_bus explicitly non-modular s390/zcrypt: Removed unneeded debug feature directory creation. s390: add missing "do {} while (0)" loop constructs to multiline macros s390/mm: add cond_resched call to kernel page table dumper s390: get rid of MACHINE_HAS_PFMF and MACHINE_HAS_HPAGE s390/mm: make memory_block_size_bytes available for !MEMORY_HOTPLUG s390: replace ACCESS_ONCE with READ_ONCE s390: Audit and remove any remaining unnecessary uses of module.h s390: mm: Audit and remove any unnecessary uses of module.h s390: kernel: Audit and remove any unnecessary uses of module.h s390/kdump: Use "LINUX" ELF note name instead of "CORE" s390: add no-execute support s390: report new vector facilities s390: use correct input data address for setup_randomness s390/sclp: get rid of common response code handling s390/sclp: don't add new lines to each printed string s390/sclp: make early sclp code readable s390/sclp: disable early sclp code as soon as the base sclp driver is active s390/sclp: move early printk code to drivers ...
2017-02-23 02:20:04 +08:00
bpf_jit_binary_lock_ro(header);
fp->bpf_func = (void *) jit.prg_buf;
fp->jited = 1;
fp->jited_len = jit.size;
free_addrs:
kfree(jit.addrs);
out:
if (tmp_blinded)
bpf_jit_prog_release_other(fp, fp == orig_fp ?
tmp : orig_fp);
return fp;
}