linux/arch/riscv/kernel/probes/kprobes.c
Jakub Kicinski ee8d72a157 bpf-next-for-netdev
-----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQTFp0I1jqZrAX+hPRXbK58LschIgwUCY+/uBgAKCRDbK58LschI
 g0ngAPwJHd1RicBuy2C4fLv0nGKZtmYZBAnTGlI2RisPxU6BRwEAwUDLHuc5K6nR
 j261okOxOy/MRxdN1NhmR6Qe7nMyQAk=
 =tYU+
 -----END PGP SIGNATURE-----

Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2023-02-17

We've added 64 non-merge commits during the last 7 day(s) which contain
a total of 158 files changed, 4190 insertions(+), 988 deletions(-).

The main changes are:

1) Add a rbtree data structure following the "next-gen data structure"
   precedent set by recently-added linked-list, that is, by using
   kfunc + kptr instead of adding a new BPF map type, from Dave Marchevsky.

2) Add a new benchmark for hashmap lookups to BPF selftests,
   from Anton Protopopov.

3) Fix bpf_fib_lookup to only return valid neighbors and add an option
   to skip the neigh table lookup, from Martin KaFai Lau.

4) Add cgroup.memory=nobpf kernel parameter option to disable BPF memory
   accouting for container environments, from Yafang Shao.

5) Batch of ice multi-buffer and driver performance fixes,
   from Alexander Lobakin.

6) Fix a bug in determining whether global subprog's argument is
   PTR_TO_CTX, which is based on type names which breaks kprobe progs,
   from Andrii Nakryiko.

7) Prep work for future -mcpu=v4 LLVM option which includes usage of
   BPF_ST insn. Thus improve BPF_ST-related value tracking in verifier,
   from Eduard Zingerman.

8) More prep work for later building selftests with Memory Sanitizer
   in order to detect usages of undefined memory, from Ilya Leoshkevich.

9) Fix xsk sockets to check IFF_UP earlier to avoid a NULL pointer
   dereference via sendmsg(), from Maciej Fijalkowski.

10) Implement BPF trampoline for RV64 JIT compiler, from Pu Lehui.

11) Fix BPF memory allocator in combination with BPF hashtab where it could
    corrupt special fields e.g. used in bpf_spin_lock, from Hou Tao.

12) Fix LoongArch BPF JIT to always use 4 instructions for function
    address so that instruction sequences don't change between passes,
    from Hengqi Chen.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (64 commits)
  selftests/bpf: Add bpf_fib_lookup test
  bpf: Add BPF_FIB_LOOKUP_SKIP_NEIGH for bpf_fib_lookup
  riscv, bpf: Add bpf trampoline support for RV64
  riscv, bpf: Add bpf_arch_text_poke support for RV64
  riscv, bpf: Factor out emit_call for kernel and bpf context
  riscv: Extend patch_text for multiple instructions
  Revert "bpf, test_run: fix &xdp_frame misplacement for LIVE_FRAMES"
  selftests/bpf: Add global subprog context passing tests
  selftests/bpf: Convert test_global_funcs test to test_loader framework
  bpf: Fix global subprog context argument resolution logic
  LoongArch, bpf: Use 4 instructions for function address in JIT
  bpf: bpf_fib_lookup should not return neigh in NUD_FAILED state
  bpf: Disable bh in bpf_test_run for xdp and tc prog
  xsk: check IFF_UP earlier in Tx path
  Fix typos in selftest/bpf files
  selftests/bpf: Use bpf_{btf,link,map,prog}_get_info_by_fd()
  samples/bpf: Use bpf_{btf,link,map,prog}_get_info_by_fd()
  bpftool: Use bpf_{btf,link,map,prog}_get_info_by_fd()
  libbpf: Use bpf_{btf,link,map,prog}_get_info_by_fd()
  libbpf: Introduce bpf_{btf,link,map,prog}_get_info_by_fd()
  ...
====================

Link: https://lore.kernel.org/r/20230217221737.31122-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-02-20 16:31:14 -08:00

378 lines
9.0 KiB
C

// SPDX-License-Identifier: GPL-2.0+
#define pr_fmt(fmt) "kprobes: " fmt
#include <linux/kprobes.h>
#include <linux/extable.h>
#include <linux/slab.h>
#include <linux/stop_machine.h>
#include <asm/ptrace.h>
#include <linux/uaccess.h>
#include <asm/sections.h>
#include <asm/cacheflush.h>
#include <asm/bug.h>
#include <asm/patch.h>
#include "decode-insn.h"
DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
static void __kprobes
post_kprobe_handler(struct kprobe *, struct kprobe_ctlblk *, struct pt_regs *);
static void __kprobes arch_prepare_ss_slot(struct kprobe *p)
{
u32 insn = __BUG_INSN_32;
unsigned long offset = GET_INSN_LENGTH(p->opcode);
p->ainsn.api.restore = (unsigned long)p->addr + offset;
patch_text(p->ainsn.api.insn, &p->opcode, 1);
patch_text((void *)((unsigned long)(p->ainsn.api.insn) + offset),
&insn, 1);
}
static void __kprobes arch_prepare_simulate(struct kprobe *p)
{
p->ainsn.api.restore = 0;
}
static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs)
{
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
if (p->ainsn.api.handler)
p->ainsn.api.handler((u32)p->opcode,
(unsigned long)p->addr, regs);
post_kprobe_handler(p, kcb, regs);
}
static bool __kprobes arch_check_kprobe(struct kprobe *p)
{
unsigned long tmp = (unsigned long)p->addr - p->offset;
unsigned long addr = (unsigned long)p->addr;
while (tmp <= addr) {
if (tmp == addr)
return true;
tmp += GET_INSN_LENGTH(*(u16 *)tmp);
}
return false;
}
int __kprobes arch_prepare_kprobe(struct kprobe *p)
{
u16 *insn = (u16 *)p->addr;
if ((unsigned long)insn & 0x1)
return -EILSEQ;
if (!arch_check_kprobe(p))
return -EILSEQ;
/* copy instruction */
p->opcode = (kprobe_opcode_t)(*insn++);
if (GET_INSN_LENGTH(p->opcode) == 4)
p->opcode |= (kprobe_opcode_t)(*insn) << 16;
/* decode instruction */
switch (riscv_probe_decode_insn(p->addr, &p->ainsn.api)) {
case INSN_REJECTED: /* insn not supported */
return -EINVAL;
case INSN_GOOD_NO_SLOT: /* insn need simulation */
p->ainsn.api.insn = NULL;
break;
case INSN_GOOD: /* instruction uses slot */
p->ainsn.api.insn = get_insn_slot();
if (!p->ainsn.api.insn)
return -ENOMEM;
break;
}
/* prepare the instruction */
if (p->ainsn.api.insn)
arch_prepare_ss_slot(p);
else
arch_prepare_simulate(p);
return 0;
}
#ifdef CONFIG_MMU
void *alloc_insn_page(void)
{
return __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, VMALLOC_END,
GFP_KERNEL, PAGE_KERNEL_READ_EXEC,
VM_FLUSH_RESET_PERMS, NUMA_NO_NODE,
__builtin_return_address(0));
}
#endif
/* install breakpoint in text */
void __kprobes arch_arm_kprobe(struct kprobe *p)
{
u32 insn = (p->opcode & __INSN_LENGTH_MASK) == __INSN_LENGTH_32 ?
__BUG_INSN_32 : __BUG_INSN_16;
patch_text(p->addr, &insn, 1);
}
/* remove breakpoint from text */
void __kprobes arch_disarm_kprobe(struct kprobe *p)
{
patch_text(p->addr, &p->opcode, 1);
}
void __kprobes arch_remove_kprobe(struct kprobe *p)
{
}
static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
{
kcb->prev_kprobe.kp = kprobe_running();
kcb->prev_kprobe.status = kcb->kprobe_status;
}
static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
{
__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
kcb->kprobe_status = kcb->prev_kprobe.status;
}
static void __kprobes set_current_kprobe(struct kprobe *p)
{
__this_cpu_write(current_kprobe, p);
}
/*
* Interrupts need to be disabled before single-step mode is set, and not
* reenabled until after single-step mode ends.
* Without disabling interrupt on local CPU, there is a chance of
* interrupt occurrence in the period of exception return and start of
* out-of-line single-step, that result in wrongly single stepping
* into the interrupt handler.
*/
static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb,
struct pt_regs *regs)
{
kcb->saved_status = regs->status;
regs->status &= ~SR_SPIE;
}
static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb,
struct pt_regs *regs)
{
regs->status = kcb->saved_status;
}
static void __kprobes setup_singlestep(struct kprobe *p,
struct pt_regs *regs,
struct kprobe_ctlblk *kcb, int reenter)
{
unsigned long slot;
if (reenter) {
save_previous_kprobe(kcb);
set_current_kprobe(p);
kcb->kprobe_status = KPROBE_REENTER;
} else {
kcb->kprobe_status = KPROBE_HIT_SS;
}
if (p->ainsn.api.insn) {
/* prepare for single stepping */
slot = (unsigned long)p->ainsn.api.insn;
/* IRQs and single stepping do not mix well. */
kprobes_save_local_irqflag(kcb, regs);
instruction_pointer_set(regs, slot);
} else {
/* insn simulation */
arch_simulate_insn(p, regs);
}
}
static int __kprobes reenter_kprobe(struct kprobe *p,
struct pt_regs *regs,
struct kprobe_ctlblk *kcb)
{
switch (kcb->kprobe_status) {
case KPROBE_HIT_SSDONE:
case KPROBE_HIT_ACTIVE:
kprobes_inc_nmissed_count(p);
setup_singlestep(p, regs, kcb, 1);
break;
case KPROBE_HIT_SS:
case KPROBE_REENTER:
pr_warn("Failed to recover from reentered kprobes.\n");
dump_kprobe(p);
BUG();
break;
default:
WARN_ON(1);
return 0;
}
return 1;
}
static void __kprobes
post_kprobe_handler(struct kprobe *cur, struct kprobe_ctlblk *kcb, struct pt_regs *regs)
{
/* return addr restore if non-branching insn */
if (cur->ainsn.api.restore != 0)
regs->epc = cur->ainsn.api.restore;
/* restore back original saved kprobe variables and continue */
if (kcb->kprobe_status == KPROBE_REENTER) {
restore_previous_kprobe(kcb);
return;
}
/* call post handler */
kcb->kprobe_status = KPROBE_HIT_SSDONE;
if (cur->post_handler) {
/* post_handler can hit breakpoint and single step
* again, so we enable D-flag for recursive exception.
*/
cur->post_handler(cur, regs, 0);
}
reset_current_kprobe();
}
int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr)
{
struct kprobe *cur = kprobe_running();
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
switch (kcb->kprobe_status) {
case KPROBE_HIT_SS:
case KPROBE_REENTER:
/*
* We are here because the instruction being single
* stepped caused a page fault. We reset the current
* kprobe and the ip points back to the probe address
* and allow the page fault handler to continue as a
* normal page fault.
*/
regs->epc = (unsigned long) cur->addr;
BUG_ON(!instruction_pointer(regs));
if (kcb->kprobe_status == KPROBE_REENTER)
restore_previous_kprobe(kcb);
else {
kprobes_restore_local_irqflag(kcb, regs);
reset_current_kprobe();
}
break;
case KPROBE_HIT_ACTIVE:
case KPROBE_HIT_SSDONE:
/*
* In case the user-specified fault handler returned
* zero, try to fix up.
*/
if (fixup_exception(regs))
return 1;
}
return 0;
}
bool __kprobes
kprobe_breakpoint_handler(struct pt_regs *regs)
{
struct kprobe *p, *cur_kprobe;
struct kprobe_ctlblk *kcb;
unsigned long addr = instruction_pointer(regs);
kcb = get_kprobe_ctlblk();
cur_kprobe = kprobe_running();
p = get_kprobe((kprobe_opcode_t *) addr);
if (p) {
if (cur_kprobe) {
if (reenter_kprobe(p, regs, kcb))
return true;
} else {
/* Probe hit */
set_current_kprobe(p);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
/*
* If we have no pre-handler or it returned 0, we
* continue with normal processing. If we have a
* pre-handler and it returned non-zero, it will
* modify the execution path and no need to single
* stepping. Let's just reset current kprobe and exit.
*
* pre_handler can hit a breakpoint and can step thru
* before return.
*/
if (!p->pre_handler || !p->pre_handler(p, regs))
setup_singlestep(p, regs, kcb, 0);
else
reset_current_kprobe();
}
return true;
}
/*
* The breakpoint instruction was removed right
* after we hit it. Another cpu has removed
* either a probepoint or a debugger breakpoint
* at this address. In either case, no further
* handling of this interrupt is appropriate.
* Return back to original instruction, and continue.
*/
return false;
}
bool __kprobes
kprobe_single_step_handler(struct pt_regs *regs)
{
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
unsigned long addr = instruction_pointer(regs);
struct kprobe *cur = kprobe_running();
if (cur && (kcb->kprobe_status & (KPROBE_HIT_SS | KPROBE_REENTER)) &&
((unsigned long)&cur->ainsn.api.insn[0] + GET_INSN_LENGTH(cur->opcode) == addr)) {
kprobes_restore_local_irqflag(kcb, regs);
post_kprobe_handler(cur, kcb, regs);
return true;
}
/* not ours, kprobes should ignore it */
return false;
}
/*
* Provide a blacklist of symbols identifying ranges which cannot be kprobed.
* This blacklist is exposed to userspace via debugfs (kprobes/blacklist).
*/
int __init arch_populate_kprobe_blacklist(void)
{
int ret;
ret = kprobe_add_area_blacklist((unsigned long)__irqentry_text_start,
(unsigned long)__irqentry_text_end);
return ret;
}
int __kprobes arch_trampoline_kprobe(struct kprobe *p)
{
return 0;
}
int __init arch_init_kprobes(void)
{
return 0;
}