leandrof/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ARM: kprobes: Infrastructure for table driven decoding of CPU instructions

Browse Source 
The existing ARM instruction decoding functions are a mass of if/else
code. Rather than follow this pattern for Thumb instruction decoding
this patch implements an infrastructure for a new table driven scheme.

This has several advantages:

- Reduces the kernel size by approx 2kB. (The ARM instruction decoding
  will eventually have -3.1kB code, +1.3kB data; with similar or better
  estimated savings for Thumb decoding.)

- Allows programmatic checking of decoding consistency and test case
  coverage.

- Provides more uniform source code and is therefore, arguably, clearer.

For a detailed explanation of how decoding tables work see the in-source
documentation in kprobes.h, and also for kprobe_decode_insn().

Signed-off-by: Jon Medhurst <tixy@yxit.co.uk>
Acked-by: Nicolas Pitre <nicolas.pitre@linaro.org>
This commit is contained in:
Jon Medhurst 2011-04-26 15:15:56 +01:00 committed by Tixy
parent e2960317d4
commit 0d1a095aa1
2 changed files with 505 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

258
arch/arm/kernel/kprobes-common.c
View File

@ -140,3 +140,261 @@ kprobe_check_cc * const kprobe_condition_checks[16] = {
&__check_hi, &__check_ls, &__check_ge, &__check_lt, &__check_hi, &__check_ls, &__check_ge, &__check_lt,
&__check_gt, &__check_le, &__check_al, &__check_al &__check_gt, &__check_le, &__check_al, &__check_al
}; };
/*
* Prepare an instruction slot to receive an instruction for emulating.
* This is done by placing a subroutine return after the location where the
* instruction will be placed. We also modify ARM instructions to be
* unconditional as the condition code will already be checked before any
* emulation handler is called.
*/
static kprobe_opcode_t __kprobes
prepare_emulated_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi,
bool thumb)
{
#ifdef CONFIG_THUMB2_KERNEL
if (thumb) {
u16 *thumb_insn = (u16 *)asi->insn;
thumb_insn[1] = 0x4770; /* Thumb bx lr */
thumb_insn[2] = 0x4770; /* Thumb bx lr */
return insn;
}
asi->insn[1] = 0xe12fff1e; /* ARM bx lr */
#else
asi->insn[1] = 0xe1a0f00e; /* mov pc, lr */
#endif
/* Make an ARM instruction unconditional */
if (insn < 0xe0000000)
insn = (insn | 0xe0000000) & ~0x10000000;
return insn;
}
/*
* Write a (probably modified) instruction into the slot previously prepared by
* prepare_emulated_insn
*/
static void __kprobes
set_emulated_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi,
bool thumb)
{
#ifdef CONFIG_THUMB2_KERNEL
if (thumb) {
u16 *ip = (u16 *)asi->insn;
if (is_wide_instruction(insn))
*ip++ = insn >> 16;
*ip++ = insn;
return;
}
#endif
asi->insn[0] = insn;
}
/*
* When we modify the register numbers encoded in an instruction to be emulated,
* the new values come from this define. For ARM and 32-bit Thumb instructions
* this gives...
*
* bit position 16 12 8 4 0
* ---------------+---+---+---+---+---+
* register r2 r0 r1 -- r3
*/
#define INSN_NEW_BITS 0x00020103
/* Each nibble has same value as that at INSN_NEW_BITS bit 16 */
#define INSN_SAMEAS16_BITS 0x22222222
/*
* Validate and modify each of the registers encoded in an instruction.
*
* Each nibble in regs contains a value from enum decode_reg_type. For each
* non-zero value, the corresponding nibble in pinsn is validated and modified
* according to the type.
*/
static bool __kprobes decode_regs(kprobe_opcode_t* pinsn, u32 regs)
{
kprobe_opcode_t insn = *pinsn;
kprobe_opcode_t mask = 0xf; /* Start at least significant nibble */
for (; regs != 0; regs >>= 4, mask <<= 4) {
kprobe_opcode_t new_bits = INSN_NEW_BITS;
switch (regs & 0xf) {
case REG_TYPE_NONE:
/* Nibble not a register, skip to next */
continue;
case REG_TYPE_ANY:
/* Any register is allowed */
break;
case REG_TYPE_SAMEAS16:
/* Replace register with same as at bit position 16 */
new_bits = INSN_SAMEAS16_BITS;
break;
case REG_TYPE_SP:
/* Only allow SP (R13) */
if ((insn ^ 0xdddddddd) & mask)
goto reject;
break;
case REG_TYPE_PC:
/* Only allow PC (R15) */
if ((insn ^ 0xffffffff) & mask)
goto reject;
break;
case REG_TYPE_NOSP:
/* Reject SP (R13) */
if (((insn ^ 0xdddddddd) & mask) == 0)
goto reject;
break;
case REG_TYPE_NOSPPC:
case REG_TYPE_NOSPPCX:
/* Reject SP and PC (R13 and R15) */
if (((insn ^ 0xdddddddd) & 0xdddddddd & mask) == 0)
goto reject;
break;
case REG_TYPE_NOPCWB:
if (!is_writeback(insn))
break; /* No writeback, so any register is OK */
/* fall through... */
case REG_TYPE_NOPC:
case REG_TYPE_NOPCX:
/* Reject PC (R15) */
if (((insn ^ 0xffffffff) & mask) == 0)
goto reject;
break;
}
/* Replace value of nibble with new register number... */
insn &= ~mask;
insn |= new_bits & mask;
}
*pinsn = insn;
return true;
reject:
return false;
}
static const int decode_struct_sizes[NUM_DECODE_TYPES] = {
[DECODE_TYPE_TABLE] = sizeof(struct decode_table),
[DECODE_TYPE_CUSTOM] = sizeof(struct decode_custom),
[DECODE_TYPE_SIMULATE] = sizeof(struct decode_simulate),
[DECODE_TYPE_EMULATE] = sizeof(struct decode_emulate),
[DECODE_TYPE_OR] = sizeof(struct decode_or),
[DECODE_TYPE_REJECT] = sizeof(struct decode_reject)
};
/*
* kprobe_decode_insn operates on data tables in order to decode an ARM
* architecture instruction onto which a kprobe has been placed.
*
* These instruction decoding tables are a concatenation of entries each
* of which consist of one of the following structs:
*
* decode_table
* decode_custom
* decode_simulate
* decode_emulate
* decode_or
* decode_reject
*
* Each of these starts with a struct decode_header which has the following
* fields:
*
* type_regs
* mask
* value
*
* The least significant DECODE_TYPE_BITS of type_regs contains a value
* from enum decode_type, this indicates which of the decode_* structs
* the entry contains. The value DECODE_TYPE_END indicates the end of the
* table.
*
* When the table is parsed, each entry is checked in turn to see if it
* matches the instruction to be decoded using the test:
*
* (insn & mask) == value
*
* If no match is found before the end of the table is reached then decoding
* fails with INSN_REJECTED.
*
* When a match is found, decode_regs() is called to validate and modify each
* of the registers encoded in the instruction; the data it uses to do this
* is (type_regs >> DECODE_TYPE_BITS). A validation failure will cause decoding
* to fail with INSN_REJECTED.
*
* Once the instruction has passed the above tests, further processing
* depends on the type of the table entry's decode struct.
*
*/
int __kprobes
kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi,
const union decode_item *table, bool thumb)
{
const struct decode_header *h = (struct decode_header *)table;
const struct decode_header *next;
bool matched = false;
insn = prepare_emulated_insn(insn, asi, thumb);
for (;; h = next) {
enum decode_type type = h->type_regs.bits & DECODE_TYPE_MASK;
u32 regs = h->type_regs.bits >> DECODE_TYPE_BITS;
if (type == DECODE_TYPE_END)
return INSN_REJECTED;
next = (struct decode_header *)
((uintptr_t)h + decode_struct_sizes[type]);
if (!matched && (insn & h->mask.bits) != h->value.bits)
continue;
if (!decode_regs(&insn, regs))
return INSN_REJECTED;
switch (type) {
case DECODE_TYPE_TABLE: {
struct decode_table *d = (struct decode_table *)h;
next = (struct decode_header *)d->table.table;
break;
}
case DECODE_TYPE_CUSTOM: {
struct decode_custom *d = (struct decode_custom *)h;
return (*d->decoder.decoder)(insn, asi);
}
case DECODE_TYPE_SIMULATE: {
struct decode_simulate *d = (struct decode_simulate *)h;
asi->insn_handler = d->handler.handler;
return INSN_GOOD_NO_SLOT;
}
case DECODE_TYPE_EMULATE: {
struct decode_emulate *d = (struct decode_emulate *)h;
asi->insn_handler = d->handler.handler;
set_emulated_insn(insn, asi, thumb);
return INSN_GOOD;
}
case DECODE_TYPE_OR:
matched = true;
break;
case DECODE_TYPE_REJECT:
default:
return INSN_REJECTED;
}
}
}

248
arch/arm/kernel/kprobes.h
View File

@ -1,7 +1,9 @@
/* /*
* arch/arm/kernel/kprobes.h * arch/arm/kernel/kprobes.h
* *
* Contents moved from arch/arm/include/asm/kprobes.h which is * Copyright (C) 2011 Jon Medhurst <tixy@yxit.co.uk>.
*
* Some contents moved here from arch/arm/include/asm/kprobes.h which is
* Copyright (C) 2006, 2007 Motorola Inc. * Copyright (C) 2006, 2007 Motorola Inc.
* *
* This program is free software; you can redistribute it and/or modify * This program is free software; you can redistribute it and/or modify
@ -99,4 +101,248 @@ static inline unsigned long it_advance(unsigned long cpsr)
*/ */
#define is_writeback(insn) ((insn ^ 0x01000000) & 0x01200000) #define is_writeback(insn) ((insn ^ 0x01000000) & 0x01200000)
/*
* The following definitions and macros are used to build instruction
* decoding tables for use by kprobe_decode_insn.
*
* These tables are a concatenation of entries each of which consist of one of
* the decode_* structs. All of the fields in every type of decode structure
* are of the union type decode_item, therefore the entire decode table can be
* viewed as an array of these and declared like:
*
* static const union decode_item table_name[] = {};
*
* In order to construct each entry in the table, macros are used to
* initialise a number of sequential decode_item values in a layout which
* matches the relevant struct. E.g. DECODE_SIMULATE initialise a struct
* decode_simulate by initialising four decode_item objects like this...
*
* {.bits = _type},
* {.bits = _mask},
* {.bits = _value},
* {.handler = _handler},
*
* Initialising a specified member of the union means that the compiler
* will produce a warning if the argument is of an incorrect type.
*
* Below is a list of each of the macros used to initialise entries and a
* description of the action performed when that entry is matched to an
* instruction. A match is found when (instruction & mask) == value.
*
* DECODE_TABLE(mask, value, table)
* Instruction decoding jumps to parsing the new sub-table 'table'.
*
* DECODE_CUSTOM(mask, value, decoder)
* The custom function 'decoder' is called to the complete decoding
* of an instruction.
*
* DECODE_SIMULATE(mask, value, handler)
* Set the probes instruction handler to 'handler', this will be used
* to simulate the instruction when the probe is hit. Decoding returns
* with INSN_GOOD_NO_SLOT.
*
* DECODE_EMULATE(mask, value, handler)
* Set the probes instruction handler to 'handler', this will be used
* to emulate the instruction when the probe is hit. The modified
* instruction (see below) is placed in the probes instruction slot so it
* may be called by the emulation code. Decoding returns with INSN_GOOD.
*
* DECODE_REJECT(mask, value)
* Instruction decoding fails with INSN_REJECTED
*
* DECODE_OR(mask, value)
* This allows the mask/value test of multiple table entries to be
* logically ORed. Once an 'or' entry is matched the decoding action to
* be performed is that of the next entry which isn't an 'or'. E.g.
*
* DECODE_OR (mask1, value1)
* DECODE_OR (mask2, value2)
* DECODE_SIMULATE (mask3, value3, simulation_handler)
*
* This means that if any of the three mask/value pairs match the
* instruction being decoded, then 'simulation_handler' will be used
* for it.
*
* Both the SIMULATE and EMULATE macros have a second form which take an
* additional 'regs' argument.
*
* DECODE_SIMULATEX(mask, value, handler, regs)
* DECODE_EMULATEX (mask, value, handler, regs)
*
* These are used to specify what kind of CPU register is encoded in each of the
* least significant 5 nibbles of the instruction being decoded. The regs value
* is specified using the REGS macro, this takes any of the REG_TYPE_* values
* from enum decode_reg_type as arguments; only the '*' part of the name is
* given. E.g.
*
* REGS(0, ANY, NOPC, 0, ANY)
*
* This indicates an instruction is encoded like:
*
* bits 19..16 ignore
* bits 15..12 any register allowed here
* bits 11.. 8 any register except PC allowed here
* bits 7.. 4 ignore
* bits 3.. 0 any register allowed here
*
* This register specification is checked after a decode table entry is found to
* match an instruction (through the mask/value test). Any invalid register then
* found in the instruction will cause decoding to fail with INSN_REJECTED. In
* the above example this would happen if bits 11..8 of the instruction were
* 1111, indicating R15 or PC.
*
* As well as checking for legal combinations of registers, this data is also
* used to modify the registers encoded in the instructions so that an
* emulation routines can use it. (See decode_regs() and INSN_NEW_BITS.)
*
* Here is a real example which matches ARM instructions of the form
* "AND <Rd>,<Rn>,<Rm>,<shift> <Rs>"
*
* DECODE_EMULATEX (0x0e000090, 0x00000010, emulate_rd12rn16rm0rs8_rwflags,
* REGS(ANY, ANY, NOPC, 0, ANY)),
* ^ ^ ^ ^
* Rn Rd Rs Rm
*
* Decoding the instruction "AND R4, R5, R6, ASL R15" will be rejected because
* Rs == R15
*
* Decoding the instruction "AND R4, R5, R6, ASL R7" will be accepted and the
* instruction will be modified to "AND R0, R2, R3, ASL R1" and then placed into
* the kprobes instruction slot. This can then be called later by the handler
* function emulate_rd12rn16rm0rs8_rwflags in order to simulate the instruction.
*/
enum decode_type {
DECODE_TYPE_END,
DECODE_TYPE_TABLE,
DECODE_TYPE_CUSTOM,
DECODE_TYPE_SIMULATE,
DECODE_TYPE_EMULATE,
DECODE_TYPE_OR,
DECODE_TYPE_REJECT,
NUM_DECODE_TYPES /* Must be last enum */
};
#define DECODE_TYPE_BITS 4
#define DECODE_TYPE_MASK ((1 << DECODE_TYPE_BITS) - 1)
enum decode_reg_type {
REG_TYPE_NONE = 0, /* Not a register, ignore */
REG_TYPE_ANY, /* Any register allowed */
REG_TYPE_SAMEAS16, /* Register should be same as that at bits 19..16 */
REG_TYPE_SP, /* Register must be SP */
REG_TYPE_PC, /* Register must be PC */
REG_TYPE_NOSP, /* Register must not be SP */
REG_TYPE_NOSPPC, /* Register must not be SP or PC */
REG_TYPE_NOPC, /* Register must not be PC */
REG_TYPE_NOPCWB, /* No PC if load/store write-back flag also set */
/* The following types are used when the encoding for PC indicates
* another instruction form. This distiction only matters for test
* case coverage checks.
*/
REG_TYPE_NOPCX, /* Register must not be PC */
REG_TYPE_NOSPPCX, /* Register must not be SP or PC */
/* Alias to allow '0' arg to be used in REGS macro. */
REG_TYPE_0 = REG_TYPE_NONE
};
#define REGS(r16, r12, r8, r4, r0) \
((REG_TYPE_##r16) << 16) + \
((REG_TYPE_##r12) << 12) + \
((REG_TYPE_##r8) << 8) + \
((REG_TYPE_##r4) << 4) + \
(REG_TYPE_##r0)
union decode_item {
u32 bits;
const union decode_item *table;
kprobe_insn_handler_t *handler;
kprobe_decode_insn_t *decoder;
};
#define DECODE_END \
{.bits = DECODE_TYPE_END}
struct decode_header {
union decode_item type_regs;
union decode_item mask;
union decode_item value;
};
#define DECODE_HEADER(_type, _mask, _value, _regs) \
{.bits = (_type) | ((_regs) << DECODE_TYPE_BITS)}, \
{.bits = (_mask)}, \
{.bits = (_value)}
struct decode_table {
struct decode_header header;
union decode_item table;
};
#define DECODE_TABLE(_mask, _value, _table) \
DECODE_HEADER(DECODE_TYPE_TABLE, _mask, _value, 0), \
{.table = (_table)}
struct decode_custom {
struct decode_header header;
union decode_item decoder;
};
#define DECODE_CUSTOM(_mask, _value, _decoder) \
DECODE_HEADER(DECODE_TYPE_CUSTOM, _mask, _value, 0), \
{.decoder = (_decoder)}
struct decode_simulate {
struct decode_header header;
union decode_item handler;
};
#define DECODE_SIMULATEX(_mask, _value, _handler, _regs) \
DECODE_HEADER(DECODE_TYPE_SIMULATE, _mask, _value, _regs), \
{.handler = (_handler)}
#define DECODE_SIMULATE(_mask, _value, _handler) \
DECODE_SIMULATEX(_mask, _value, _handler, 0)
struct decode_emulate {
struct decode_header header;
union decode_item handler;
};
#define DECODE_EMULATEX(_mask, _value, _handler, _regs) \
DECODE_HEADER(DECODE_TYPE_EMULATE, _mask, _value, _regs), \
{.handler = (_handler)}
#define DECODE_EMULATE(_mask, _value, _handler) \
DECODE_EMULATEX(_mask, _value, _handler, 0)
struct decode_or {
struct decode_header header;
};
#define DECODE_OR(_mask, _value) \
DECODE_HEADER(DECODE_TYPE_OR, _mask, _value, 0)
struct decode_reject {
struct decode_header header;
};
#define DECODE_REJECT(_mask, _value) \
DECODE_HEADER(DECODE_TYPE_REJECT, _mask, _value, 0)
int kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi,
const union decode_item *table, bool thumb16);
#endif /* _ARM_KERNEL_KPROBES_H */ #endif /* _ARM_KERNEL_KPROBES_H */