linux_dsm_epyc7002/arch/powerpc/net/bpf_jit64.h
Naveen N. Rao 86be36f650 powerpc: bpf: Fix generation of load/store DW instructions
Yauheni Kaliuta pointed out that PTR_TO_STACK store/load verifier test
was failing on powerpc64 BE, and rightfully indicated that the PPC_LD()
macro is not masking away the last two bits of the offset per the ISA,
resulting in the generation of 'lwa' instruction instead of the intended
'ld' instruction.

Segher also pointed out that we can't simply mask away the last two bits
as that will result in loading/storing from/to a memory location that
was not intended.

This patch addresses this by using ldx/stdx if the offset is not
word-aligned. We load the offset into a temporary register (TMP_REG_2)
and use that as the index register in a subsequent ldx/stdx. We fix
PPC_LD() macro to mask off the last two bits, but enhance PPC_BPF_LL()
and PPC_BPF_STL() to factor in the offset value and generate the proper
instruction sequence. We also convert all existing users of PPC_LD() and
PPC_STD() to use these macros. All existing uses of these macros have
been audited to ensure that TMP_REG_2 can be clobbered.

Fixes: 156d0e290e ("powerpc/ebpf/jit: Implement JIT compiler for extended BPF")
Cc: stable@vger.kernel.org # v4.9+

Reported-by: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-03-16 01:28:22 +01:00

113 lines
3.0 KiB
C

/*
* bpf_jit64.h: BPF JIT compiler for PPC64
*
* Copyright 2016 Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
* IBM Corporation
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; version 2
* of the License.
*/
#ifndef _BPF_JIT64_H
#define _BPF_JIT64_H
#include "bpf_jit.h"
/*
* Stack layout:
* Ensure the top half (upto local_tmp_var) stays consistent
* with our redzone usage.
*
* [ prev sp ] <-------------
* [ nv gpr save area ] 6*8 |
* [ tail_call_cnt ] 8 |
* [ local_tmp_var ] 8 |
* fp (r31) --> [ ebpf stack space ] upto 512 |
* [ frame header ] 32/112 |
* sp (r1) ---> [ stack pointer ] --------------
*/
/* for gpr non volatile registers BPG_REG_6 to 10 */
#define BPF_PPC_STACK_SAVE (6*8)
/* for bpf JIT code internal usage */
#define BPF_PPC_STACK_LOCALS 16
/* stack frame excluding BPF stack, ensure this is quadword aligned */
#define BPF_PPC_STACKFRAME (STACK_FRAME_MIN_SIZE + \
BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE)
#ifndef __ASSEMBLY__
/* BPF register usage */
#define TMP_REG_1 (MAX_BPF_JIT_REG + 0)
#define TMP_REG_2 (MAX_BPF_JIT_REG + 1)
/* BPF to ppc register mappings */
static const int b2p[] = {
/* function return value */
[BPF_REG_0] = 8,
/* function arguments */
[BPF_REG_1] = 3,
[BPF_REG_2] = 4,
[BPF_REG_3] = 5,
[BPF_REG_4] = 6,
[BPF_REG_5] = 7,
/* non volatile registers */
[BPF_REG_6] = 27,
[BPF_REG_7] = 28,
[BPF_REG_8] = 29,
[BPF_REG_9] = 30,
/* frame pointer aka BPF_REG_10 */
[BPF_REG_FP] = 31,
/* eBPF jit internal registers */
[BPF_REG_AX] = 2,
[TMP_REG_1] = 9,
[TMP_REG_2] = 10
};
/* PPC NVR range -- update this if we ever use NVRs below r27 */
#define BPF_PPC_NVR_MIN 27
/*
* WARNING: These can use TMP_REG_2 if the offset is not at word boundary,
* so ensure that it isn't in use already.
*/
#define PPC_BPF_LL(r, base, i) do { \
if ((i) % 4) { \
PPC_LI(b2p[TMP_REG_2], (i)); \
PPC_LDX(r, base, b2p[TMP_REG_2]); \
} else \
PPC_LD(r, base, i); \
} while(0)
#define PPC_BPF_STL(r, base, i) do { \
if ((i) % 4) { \
PPC_LI(b2p[TMP_REG_2], (i)); \
PPC_STDX(r, base, b2p[TMP_REG_2]); \
} else \
PPC_STD(r, base, i); \
} while(0)
#define PPC_BPF_STLU(r, base, i) do { PPC_STDU(r, base, i); } while(0)
#define SEEN_FUNC 0x1000 /* might call external helpers */
#define SEEN_STACK 0x2000 /* uses BPF stack */
#define SEEN_TAILCALL 0x4000 /* uses tail calls */
struct codegen_context {
/*
* This is used to track register usage as well
* as calls to external helpers.
* - register usage is tracked with corresponding
* bits (r3-r10 and r27-r31)
* - rest of the bits can be used to track other
* things -- for now, we use bits 16 to 23
* encoded in SEEN_* macros above
*/
unsigned int seen;
unsigned int idx;
unsigned int stack_size;
};
#endif /* !__ASSEMBLY__ */
#endif