Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf
Alexei Starovoitov says:
====================
pull-request: bpf 2018-12-15
The following pull-request contains BPF updates for your *net* tree.
The main changes are:
1) fix liveness propagation of callee saved registers, from Jakub.
2) fix overflow in bpf_jit_limit knob, from Daniel.
3) bpf_flow_dissector api fix, from Stanislav.
4) bpf_perf_event api fix on powerpc, from Sandipan.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h
index 8bf1b63..16a4981 100644
--- a/arch/powerpc/include/asm/perf_event.h
+++ b/arch/powerpc/include/asm/perf_event.h
@@ -26,6 +26,8 @@
#include <asm/ptrace.h>
#include <asm/reg.h>
+#define perf_arch_bpf_user_pt_regs(regs) ®s->user_regs
+
/*
* Overload regs->result to specify whether we should use the MSR (result
* is zero) or the SIAR (result is non zero).
diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild
index a658091..3712152 100644
--- a/arch/powerpc/include/uapi/asm/Kbuild
+++ b/arch/powerpc/include/uapi/asm/Kbuild
@@ -1,7 +1,6 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-generic-y += bpf_perf_event.h
generic-y += param.h
generic-y += poll.h
generic-y += resource.h
diff --git a/arch/powerpc/include/uapi/asm/bpf_perf_event.h b/arch/powerpc/include/uapi/asm/bpf_perf_event.h
new file mode 100644
index 0000000..b551b74
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/bpf_perf_event.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_BPF_PERF_EVENT_H__
+
+#include <asm/ptrace.h>
+
+typedef struct user_pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 795ff0b..a8b9d90 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -861,7 +861,7 @@
extern int bpf_jit_enable;
extern int bpf_jit_harden;
extern int bpf_jit_kallsyms;
-extern int bpf_jit_limit;
+extern long bpf_jit_limit;
typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index b1a3545..b2890c2 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -365,13 +365,11 @@
}
#ifdef CONFIG_BPF_JIT
-# define BPF_JIT_LIMIT_DEFAULT (PAGE_SIZE * 40000)
-
/* All BPF JIT sysctl knobs here. */
int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON);
int bpf_jit_harden __read_mostly;
int bpf_jit_kallsyms __read_mostly;
-int bpf_jit_limit __read_mostly = BPF_JIT_LIMIT_DEFAULT;
+long bpf_jit_limit __read_mostly;
static __always_inline void
bpf_get_prog_addr_region(const struct bpf_prog *prog,
@@ -580,16 +578,27 @@
static atomic_long_t bpf_jit_current;
+/* Can be overridden by an arch's JIT compiler if it has a custom,
+ * dedicated BPF backend memory area, or if neither of the two
+ * below apply.
+ */
+u64 __weak bpf_jit_alloc_exec_limit(void)
+{
#if defined(MODULES_VADDR)
+ return MODULES_END - MODULES_VADDR;
+#else
+ return VMALLOC_END - VMALLOC_START;
+#endif
+}
+
static int __init bpf_jit_charge_init(void)
{
/* Only used as heuristic here to derive limit. */
- bpf_jit_limit = min_t(u64, round_up((MODULES_END - MODULES_VADDR) >> 2,
- PAGE_SIZE), INT_MAX);
+ bpf_jit_limit = min_t(u64, round_up(bpf_jit_alloc_exec_limit() >> 2,
+ PAGE_SIZE), LONG_MAX);
return 0;
}
pure_initcall(bpf_jit_charge_init);
-#endif
static int bpf_jit_charge_modmem(u32 pages)
{
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index fc760d0..51ba84d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5102,9 +5102,16 @@
}
new_sl->next = env->explored_states[insn_idx];
env->explored_states[insn_idx] = new_sl;
- /* connect new state to parentage chain */
- for (i = 0; i < BPF_REG_FP; i++)
- cur_regs(env)[i].parent = &new->frame[new->curframe]->regs[i];
+ /* connect new state to parentage chain. Current frame needs all
+ * registers connected. Only r6 - r9 of the callers are alive (pushed
+ * to the stack implicitly by JITs) so in callers' frames connect just
+ * r6 - r9 as an optimization. Callers will have r1 - r5 connected to
+ * the state of the call instruction (with WRITTEN set), and r0 comes
+ * from callee with its full parentage chain, anyway.
+ */
+ for (j = 0; j <= cur->curframe; j++)
+ for (i = j < cur->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++)
+ cur->frame[j]->regs[i].parent = &new->frame[j]->regs[i];
/* clear write marks in current state: the writes we did are not writes
* our child did, so they don't screen off its reads from us.
* (There are no read marks in current state, because reads always mark
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 588f475..af68207 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -783,6 +783,7 @@
/* Pass parameters to the BPF program */
cb->qdisc_cb.flow_keys = &flow_keys;
flow_keys.nhoff = nhoff;
+ flow_keys.thoff = nhoff;
bpf_compute_data_pointers((struct sk_buff *)skb);
result = BPF_PROG_RUN(attached, skb);
@@ -790,9 +791,12 @@
/* Restore state */
memcpy(cb, &cb_saved, sizeof(cb_saved));
+ flow_keys.nhoff = clamp_t(u16, flow_keys.nhoff, 0, skb->len);
+ flow_keys.thoff = clamp_t(u16, flow_keys.thoff,
+ flow_keys.nhoff, skb->len);
+
__skb_flow_bpf_to_target(&flow_keys, flow_dissector,
target_container);
- key_control->thoff = min_t(u16, key_control->thoff, skb->len);
rcu_read_unlock();
return result == BPF_OK;
}
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 37b4667..d67ec17 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -28,6 +28,8 @@
static int min_sndbuf = SOCK_MIN_SNDBUF;
static int min_rcvbuf = SOCK_MIN_RCVBUF;
static int max_skb_frags = MAX_SKB_FRAGS;
+static long long_one __maybe_unused = 1;
+static long long_max __maybe_unused = LONG_MAX;
static int net_msg_warn; /* Unused, but still a sysctl */
@@ -289,6 +291,17 @@
return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
}
+
+static int
+proc_dolongvec_minmax_bpf_restricted(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
+}
#endif
static struct ctl_table net_core_table[] = {
@@ -398,10 +411,11 @@
{
.procname = "bpf_jit_limit",
.data = &bpf_jit_limit,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(long),
.mode = 0600,
- .proc_handler = proc_dointvec_minmax_bpf_restricted,
- .extra1 = &one,
+ .proc_handler = proc_dolongvec_minmax_bpf_restricted,
+ .extra1 = &long_one,
+ .extra2 = &long_max,
},
#endif
{
diff --git a/tools/testing/selftests/bpf/bpf_flow.c b/tools/testing/selftests/bpf/bpf_flow.c
index 107350a..df9d32f 100644
--- a/tools/testing/selftests/bpf/bpf_flow.c
+++ b/tools/testing/selftests/bpf/bpf_flow.c
@@ -70,18 +70,18 @@
{
void *data_end = (void *)(long)skb->data_end;
void *data = (void *)(long)skb->data;
- __u16 nhoff = skb->flow_keys->nhoff;
+ __u16 thoff = skb->flow_keys->thoff;
__u8 *hdr;
/* Verifies this variable offset does not overflow */
- if (nhoff > (USHRT_MAX - hdr_size))
+ if (thoff > (USHRT_MAX - hdr_size))
return NULL;
- hdr = data + nhoff;
+ hdr = data + thoff;
if (hdr + hdr_size <= data_end)
return hdr;
- if (bpf_skb_load_bytes(skb, nhoff, buffer, hdr_size))
+ if (bpf_skb_load_bytes(skb, thoff, buffer, hdr_size))
return NULL;
return buffer;
@@ -158,13 +158,13 @@
/* Only inspect standard GRE packets with version 0 */
return BPF_OK;
- keys->nhoff += sizeof(*gre); /* Step over GRE Flags and Proto */
+ keys->thoff += sizeof(*gre); /* Step over GRE Flags and Proto */
if (GRE_IS_CSUM(gre->flags))
- keys->nhoff += 4; /* Step over chksum and Padding */
+ keys->thoff += 4; /* Step over chksum and Padding */
if (GRE_IS_KEY(gre->flags))
- keys->nhoff += 4; /* Step over key */
+ keys->thoff += 4; /* Step over key */
if (GRE_IS_SEQ(gre->flags))
- keys->nhoff += 4; /* Step over sequence number */
+ keys->thoff += 4; /* Step over sequence number */
keys->is_encap = true;
@@ -174,7 +174,7 @@
if (!eth)
return BPF_DROP;
- keys->nhoff += sizeof(*eth);
+ keys->thoff += sizeof(*eth);
return parse_eth_proto(skb, eth->h_proto);
} else {
@@ -191,7 +191,6 @@
if ((__u8 *)tcp + (tcp->doff << 2) > data_end)
return BPF_DROP;
- keys->thoff = keys->nhoff;
keys->sport = tcp->source;
keys->dport = tcp->dest;
return BPF_OK;
@@ -201,7 +200,6 @@
if (!udp)
return BPF_DROP;
- keys->thoff = keys->nhoff;
keys->sport = udp->source;
keys->dport = udp->dest;
return BPF_OK;
@@ -252,8 +250,8 @@
keys->ipv4_src = iph->saddr;
keys->ipv4_dst = iph->daddr;
- keys->nhoff += iph->ihl << 2;
- if (data + keys->nhoff > data_end)
+ keys->thoff += iph->ihl << 2;
+ if (data + keys->thoff > data_end)
return BPF_DROP;
if (iph->frag_off & bpf_htons(IP_MF | IP_OFFSET)) {
@@ -285,7 +283,7 @@
keys->addr_proto = ETH_P_IPV6;
memcpy(&keys->ipv6_src, &ip6h->saddr, 2*sizeof(ip6h->saddr));
- keys->nhoff += sizeof(struct ipv6hdr);
+ keys->thoff += sizeof(struct ipv6hdr);
return parse_ipv6_proto(skb, ip6h->nexthdr);
}
@@ -301,7 +299,7 @@
/* hlen is in 8-octets and does not include the first 8 bytes
* of the header
*/
- skb->flow_keys->nhoff += (1 + ip6h->hdrlen) << 3;
+ skb->flow_keys->thoff += (1 + ip6h->hdrlen) << 3;
return parse_ipv6_proto(skb, ip6h->nexthdr);
}
@@ -315,7 +313,7 @@
if (!fragh)
return BPF_DROP;
- keys->nhoff += sizeof(*fragh);
+ keys->thoff += sizeof(*fragh);
keys->is_frag = true;
if (!(fragh->frag_off & bpf_htons(IP6_OFFSET)))
keys->is_first_frag = true;
@@ -341,7 +339,7 @@
__be16 proto;
/* Peek back to see if single or double-tagging */
- if (bpf_skb_load_bytes(skb, keys->nhoff - sizeof(proto), &proto,
+ if (bpf_skb_load_bytes(skb, keys->thoff - sizeof(proto), &proto,
sizeof(proto)))
return BPF_DROP;
@@ -354,14 +352,14 @@
if (vlan->h_vlan_encapsulated_proto != bpf_htons(ETH_P_8021Q))
return BPF_DROP;
- keys->nhoff += sizeof(*vlan);
+ keys->thoff += sizeof(*vlan);
}
vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan);
if (!vlan)
return BPF_DROP;
- keys->nhoff += sizeof(*vlan);
+ keys->thoff += sizeof(*vlan);
/* Only allow 8021AD + 8021Q double tagging and no triple tagging.*/
if (vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021AD) ||
vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021Q))
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index df6f751..f8eac4a 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -13915,6 +13915,34 @@
.result_unpriv = REJECT,
.result = ACCEPT,
},
+ {
+ "calls: cross frame pruning",
+ .insns = {
+ /* r8 = !!random();
+ * call pruner()
+ * if (r8)
+ * do something bad;
+ */
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_prandom_u32),
+ BPF_MOV64_IMM(BPF_REG_8, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_MOV64_IMM(BPF_REG_8, 1),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_8, 1, 1),
+ BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+ .errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+ .result_unpriv = REJECT,
+ .errstr = "!read_ok",
+ .result = REJECT,
+ },
};
static int probe_filter_length(const struct bpf_insn *fp)
@@ -13940,7 +13968,7 @@
return fd;
}
-static int create_prog_dummy1(enum bpf_map_type prog_type)
+static int create_prog_dummy1(enum bpf_prog_type prog_type)
{
struct bpf_insn prog[] = {
BPF_MOV64_IMM(BPF_REG_0, 42),
@@ -13951,7 +13979,7 @@
ARRAY_SIZE(prog), "GPL", 0, NULL, 0);
}
-static int create_prog_dummy2(enum bpf_map_type prog_type, int mfd, int idx)
+static int create_prog_dummy2(enum bpf_prog_type prog_type, int mfd, int idx)
{
struct bpf_insn prog[] = {
BPF_MOV64_IMM(BPF_REG_3, idx),
@@ -13966,7 +13994,7 @@
ARRAY_SIZE(prog), "GPL", 0, NULL, 0);
}
-static int create_prog_array(enum bpf_map_type prog_type, uint32_t max_elem,
+static int create_prog_array(enum bpf_prog_type prog_type, uint32_t max_elem,
int p1key)
{
int p2key = 1;
@@ -14037,7 +14065,7 @@
static char bpf_vlog[UINT_MAX >> 8];
-static void do_test_fixup(struct bpf_test *test, enum bpf_map_type prog_type,
+static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
struct bpf_insn *prog, int *map_fds)
{
int *fixup_map_hash_8b = test->fixup_map_hash_8b;
@@ -14166,7 +14194,7 @@
do {
prog[*fixup_map_stacktrace].imm = map_fds[12];
fixup_map_stacktrace++;
- } while (fixup_map_stacktrace);
+ } while (*fixup_map_stacktrace);
}
}