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

Merge tag 'net-5.14-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Browse Source 
Pull networking fixes from Jakub Kicinski:
 "Networking fixes for 5.14-rc4, including fixes from bpf, can, WiFi
  (mac80211) and netfilter trees.

  Current release - regressions:

   - mac80211: fix starting aggregation sessions on mesh interfaces

  Current release - new code bugs:

   - sctp: send pmtu probe only if packet loss in Search Complete state

   - bnxt_en: add missing periodic PHC overflow check

   - devlink: fix phys_port_name of virtual port and merge error

   - hns3: change the method of obtaining default ptp cycle

   - can: mcba_usb_start(): add missing urb->transfer_dma initialization

  Previous releases - regressions:

   - set true network header for ECN decapsulation

   - mlx5e: RX, avoid possible data corruption w/ relaxed ordering and
     LRO

   - phy: re-add check for PHY_BRCM_DIS_TXCRXC_NOENRGY on the BCM54811
     PHY

   - sctp: fix return value check in __sctp_rcv_asconf_lookup

  Previous releases - always broken:

   - bpf:
       - more spectre corner case fixes, introduce a BPF nospec
         instruction for mitigating Spectre v4
       - fix OOB read when printing XDP link fdinfo
       - sockmap: fix cleanup related races

   - mac80211: fix enabling 4-address mode on a sta vif after assoc

   - can:
       - raw: raw_setsockopt(): fix raw_rcv panic for sock UAF
       - j1939: j1939_session_deactivate(): clarify lifetime of session
         object, avoid UAF
       - fix number of identical memory leaks in USB drivers

   - tipc:
       - do not blindly write skb_shinfo frags when doing decryption
       - fix sleeping in tipc accept routine"

* tag 'net-5.14-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (91 commits)
  gve: Update MAINTAINERS list
  can: esd_usb2: fix memory leak
  can: ems_usb: fix memory leak
  can: usb_8dev: fix memory leak
  can: mcba_usb_start(): add missing urb->transfer_dma initialization
  can: hi311x: fix a signedness bug in hi3110_cmd()
  MAINTAINERS: add Yasushi SHOJI as reviewer for the Microchip CAN BUS Analyzer Tool driver
  bpf: Fix leakage due to insufficient speculative store bypass mitigation
  bpf: Introduce BPF nospec instruction for mitigating Spectre v4
  sis900: Fix missing pci_disable_device() in probe and remove
  net: let flow have same hash in two directions
  nfc: nfcsim: fix use after free during module unload
  tulip: windbond-840: Fix missing pci_disable_device() in probe and remove
  sctp: fix return value check in __sctp_rcv_asconf_lookup
  nfc: s3fwrn5: fix undefined parameter values in dev_err()
  net/mlx5: Fix mlx5_vport_tbl_attr chain from u16 to u32
  net/mlx5e: Fix nullptr in mlx5e_hairpin_get_mdev()
  net/mlx5: Unload device upon firmware fatal error
  net/mlx5e: Fix page allocation failure for ptp-RQ over SF
  net/mlx5e: Fix page allocation failure for trap-RQ over SF
  ...
This commit is contained in:
Linus Torvalds
2021-07-30 16:01:36 -07:00
parent e1dab4c02d 8d67041228
commit c7d1022326
104 changed files with 1241 additions and 558 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
kernel/bpf/core.c
View File

@@ -32,6 +32,8 @@
#include <linux/perf_event.h>
#include <linux/extable.h>
#include <linux/log2.h>
#include <asm/barrier.h>
#include <asm/unaligned.h>
/* Registers */
@@ -1377,6 +1379,7 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn)
/* Non-UAPI available opcodes. */
[BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS,
[BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL,
[BPF_ST | BPF_NOSPEC] = &&ST_NOSPEC,
[BPF_LDX | BPF_PROBE_MEM | BPF_B] = &&LDX_PROBE_MEM_B,
[BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H,
[BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W,
@@ -1621,7 +1624,21 @@ out:
COND_JMP(s, JSGE, >=)
COND_JMP(s, JSLE, <=)
#undef COND_JMP
/* STX and ST and LDX*/
/* ST, STX and LDX*/
ST_NOSPEC:
/* Speculation barrier for mitigating Speculative Store Bypass.
* In case of arm64, we rely on the firmware mitigation as
* controlled via the ssbd kernel parameter. Whenever the
* mitigation is enabled, it works for all of the kernel code
* with no need to provide any additional instructions here.
* In case of x86, we use 'lfence' insn for mitigation. We
* reuse preexisting logic from Spectre v1 mitigation that
* happens to produce the required code on x86 for v4 as well.
*/
#ifdef CONFIG_X86
barrier_nospec();
#endif
CONT;
#define LDST(SIZEOP, SIZE) \
STX_MEM_##SIZEOP: \
*(SIZE *)(unsigned long) (DST + insn->off) = SRC; \

16
kernel/bpf/disasm.c
View File

@@ -206,15 +206,17 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
verbose(cbs->private_data, "BUG_%02x\n", insn->code);
}
} else if (class == BPF_ST) {
if (BPF_MODE(insn->code) != BPF_MEM) {
if (BPF_MODE(insn->code) == BPF_MEM) {
verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n",
insn->code,
bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
insn->dst_reg,
insn->off, insn->imm);
} else if (BPF_MODE(insn->code) == 0xc0 /* BPF_NOSPEC, no UAPI */) {
verbose(cbs->private_data, "(%02x) nospec\n", insn->code);
} else {
verbose(cbs->private_data, "BUG_st_%02x\n", insn->code);
return;
}
verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n",
insn->code,
bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
insn->dst_reg,
insn->off, insn->imm);
} else if (class == BPF_LDX) {
if (BPF_MODE(insn->code) != BPF_MEM) {
verbose(cbs->private_data, "BUG_ldx_%02x\n", insn->code);

148
kernel/bpf/verifier.c
View File

@@ -2610,6 +2610,19 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
cur = env->cur_state->frame[env->cur_state->curframe];
if (value_regno >= 0)
reg = &cur->regs[value_regno];
if (!env->bypass_spec_v4) {
bool sanitize = reg && is_spillable_regtype(reg->type);
for (i = 0; i < size; i++) {
if (state->stack[spi].slot_type[i] == STACK_INVALID) {
sanitize = true;
break;
}
}
if (sanitize)
env->insn_aux_data[insn_idx].sanitize_stack_spill = true;
}
if (reg && size == BPF_REG_SIZE && register_is_bounded(reg) &&
!register_is_null(reg) && env->bpf_capable) {
@@ -2632,47 +2645,10 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
verbose(env, "invalid size of register spill\n");
return -EACCES;
}
if (state != cur && reg->type == PTR_TO_STACK) {
verbose(env, "cannot spill pointers to stack into stack frame of the caller\n");
return -EINVAL;
}
if (!env->bypass_spec_v4) {
bool sanitize = false;
if (state->stack[spi].slot_type[0] == STACK_SPILL &&
register_is_const(&state->stack[spi].spilled_ptr))
sanitize = true;
for (i = 0; i < BPF_REG_SIZE; i++)
if (state->stack[spi].slot_type[i] == STACK_MISC) {
sanitize = true;
break;
}
if (sanitize) {
int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off;
int soff = (-spi - 1) * BPF_REG_SIZE;
/* detected reuse of integer stack slot with a pointer
* which means either llvm is reusing stack slot or
* an attacker is trying to exploit CVE-2018-3639
* (speculative store bypass)
* Have to sanitize that slot with preemptive
* store of zero.
*/
if (*poff && *poff != soff) {
/* disallow programs where single insn stores
* into two different stack slots, since verifier
* cannot sanitize them
*/
verbose(env,
"insn %d cannot access two stack slots fp%d and fp%d",
insn_idx, *poff, soff);
return -EINVAL;
}
*poff = soff;
}
}
save_register_state(state, spi, reg);
} else {
u8 type = STACK_MISC;
@@ -6561,6 +6537,12 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env,
alu_state |= off_is_imm ? BPF_ALU_IMMEDIATE : 0;
alu_state |= ptr_is_dst_reg ?
BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
/* Limit pruning on unknown scalars to enable deep search for
* potential masking differences from other program paths.
*/
if (!off_is_imm)
env->explore_alu_limits = true;
}
err = update_alu_sanitation_state(aux, alu_state, alu_limit);
@@ -9936,8 +9918,8 @@ next:
}
/* Returns true if (rold safe implies rcur safe) */
static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
struct bpf_id_pair *idmap)
static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
struct bpf_reg_state *rcur, struct bpf_id_pair *idmap)
{
bool equal;
@@ -9963,6 +9945,8 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
return false;
switch (rold->type) {
case SCALAR_VALUE:
if (env->explore_alu_limits)
return false;
if (rcur->type == SCALAR_VALUE) {
if (!rold->precise && !rcur->precise)
return true;
@@ -10053,9 +10037,8 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
return false;
}
static bool stacksafe(struct bpf_func_state *old,
struct bpf_func_state *cur,
struct bpf_id_pair *idmap)
static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
struct bpf_func_state *cur, struct bpf_id_pair *idmap)
{
int i, spi;
@@ -10100,9 +10083,8 @@ static bool stacksafe(struct bpf_func_state *old,
continue;
if (old->stack[spi].slot_type[0] != STACK_SPILL)
continue;
if (!regsafe(&old->stack[spi].spilled_ptr,
&cur->stack[spi].spilled_ptr,
idmap))
if (!regsafe(env, &old->stack[spi].spilled_ptr,
&cur->stack[spi].spilled_ptr, idmap))
/* when explored and current stack slot are both storing
* spilled registers, check that stored pointers types
* are the same as well.
@@ -10159,10 +10141,11 @@ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_stat
memset(env->idmap_scratch, 0, sizeof(env->idmap_scratch));
for (i = 0; i < MAX_BPF_REG; i++)
if (!regsafe(&old->regs[i], &cur->regs[i], env->idmap_scratch))
if (!regsafe(env, &old->regs[i], &cur->regs[i],
env->idmap_scratch))
return false;
if (!stacksafe(old, cur, env->idmap_scratch))
if (!stacksafe(env, old, cur, env->idmap_scratch))
return false;
if (!refsafe(old, cur))
@@ -11906,35 +11889,33 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
for (i = 0; i < insn_cnt; i++, insn++) {
bpf_convert_ctx_access_t convert_ctx_access;
bool ctx_access;
if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_H) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_W) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_DW))
insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) {
type = BPF_READ;
else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) ||
insn->code == (BPF_STX | BPF_MEM | BPF_H) ||
insn->code == (BPF_STX | BPF_MEM | BPF_W) ||
insn->code == (BPF_STX | BPF_MEM | BPF_DW))
ctx_access = true;
} else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) ||
insn->code == (BPF_STX | BPF_MEM | BPF_H) ||
insn->code == (BPF_STX | BPF_MEM | BPF_W) ||
insn->code == (BPF_STX | BPF_MEM | BPF_DW) ||
insn->code == (BPF_ST | BPF_MEM | BPF_B) ||
insn->code == (BPF_ST | BPF_MEM | BPF_H) ||
insn->code == (BPF_ST | BPF_MEM | BPF_W) ||
insn->code == (BPF_ST | BPF_MEM | BPF_DW)) {
type = BPF_WRITE;
else
ctx_access = BPF_CLASS(insn->code) == BPF_STX;
} else {
continue;
}
if (type == BPF_WRITE &&
env->insn_aux_data[i + delta].sanitize_stack_off) {
env->insn_aux_data[i + delta].sanitize_stack_spill) {
struct bpf_insn patch[] = {
/* Sanitize suspicious stack slot with zero.
* There are no memory dependencies for this store,
* since it's only using frame pointer and immediate
* constant of zero
*/
BPF_ST_MEM(BPF_DW, BPF_REG_FP,
env->insn_aux_data[i + delta].sanitize_stack_off,
0),
/* the original STX instruction will immediately
* overwrite the same stack slot with appropriate value
*/
*insn,
BPF_ST_NOSPEC(),
};
cnt = ARRAY_SIZE(patch);
@@ -11948,6 +11929,9 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
continue;
}
if (!ctx_access)
continue;
switch (env->insn_aux_data[i + delta].ptr_type) {
case PTR_TO_CTX:
if (!ops->convert_ctx_access)
@@ -12752,37 +12736,6 @@ static void free_states(struct bpf_verifier_env *env)
}
}
/* The verifier is using insn_aux_data[] to store temporary data during
* verification and to store information for passes that run after the
* verification like dead code sanitization. do_check_common() for subprogram N
* may analyze many other subprograms. sanitize_insn_aux_data() clears all
* temporary data after do_check_common() finds that subprogram N cannot be
* verified independently. pass_cnt counts the number of times
* do_check_common() was run and insn->aux->seen tells the pass number
* insn_aux_data was touched. These variables are compared to clear temporary
* data from failed pass. For testing and experiments do_check_common() can be
* run multiple times even when prior attempt to verify is unsuccessful.
*
* Note that special handling is needed on !env->bypass_spec_v1 if this is
* ever called outside of error path with subsequent program rejection.
*/
static void sanitize_insn_aux_data(struct bpf_verifier_env *env)
{
struct bpf_insn *insn = env->prog->insnsi;
struct bpf_insn_aux_data *aux;
int i, class;
for (i = 0; i < env->prog->len; i++) {
class = BPF_CLASS(insn[i].code);
if (class != BPF_LDX && class != BPF_STX)
continue;
aux = &env->insn_aux_data[i];
if (aux->seen != env->pass_cnt)
continue;
memset(aux, 0, offsetof(typeof(*aux), orig_idx));
}
}
static int do_check_common(struct bpf_verifier_env *env, int subprog)
{
bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
@@ -12859,9 +12812,6 @@ out:
if (!ret && pop_log)
bpf_vlog_reset(&env->log, 0);
free_states(env);
if (ret)
/* clean aux data in case subprog was rejected */
sanitize_insn_aux_data(env);
return ret;
}