s390/bpf: recache skb->data/hlen for skb_vlan_push/pop

Allow eBPF programs attached to TC qdiscs call skb_vlan_push/pop
via helper functions. These functions may change skb->data/hlen.
This data is cached by s390 JIT to improve performance of ld_abs/ld_ind
instructions. Therefore after a change we have to reload the data.

In case of usage of skb_vlan_push/pop, in the prologue we store
the SKB pointer on the stack and restore it after BPF_JMP_CALL
to skb_vlan_push/pop.

Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/arch/s390/net/bpf_jit.h b/arch/s390/net/bpf_jit.h
index f6498ee..f010c93 100644 (file)
--- a/arch/s390/net/bpf_jit.h
+++ b/arch/s390/net/bpf_jit.h
@@ -36,6 +36,8 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
  *           |   BPF stack   |     |
  *           |               |     |
  *           +---------------+     |
+ *           | 8 byte skbp   |     |
+ * R15+170 -> +---------------+     |
  *           | 8 byte hlen   |     |
  * R15+168 -> +---------------+     |
  *           | 4 byte align  |     |
@@ -51,11 +53,12 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
  * We get 160 bytes stack space from calling function, but only use
  * 12 * 8 byte for old backchain, r15..r6, and tail_call_cnt.
  */
-#define STK_SPACE      (MAX_BPF_STACK + 8 + 4 + 4 + 160)
+#define STK_SPACE      (MAX_BPF_STACK + 8 + 8 + 4 + 4 + 160)
 #define STK_160_UNUSED (160 - 12 * 8)
 #define STK_OFF                (STK_SPACE - STK_160_UNUSED)
 #define STK_OFF_TMP    160     /* Offset of tmp buffer on stack */
 #define STK_OFF_HLEN   168     /* Offset of SKB header length on stack */
+#define STK_OFF_SKBP   170     /* Offset of SKB pointer on stack */
 
 #define STK_OFF_R6     (160 - 11 * 8)  /* Offset of r6 on stack */
 #define STK_OFF_TCCNT  (160 - 12 * 8)  /* Offset of tail_call_cnt on stack */

diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 3dd0163..bbbac6d 100644 (file)
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -53,6 +53,7 @@ struct bpf_jit {
 #define SEEN_LITERAL   8       /* code uses literals */
 #define SEEN_FUNC      16      /* calls C functions */
 #define SEEN_TAIL_CALL 32      /* code uses tail calls */
+#define SEEN_SKB_CHANGE        64      /* code changes skb data */
 #define SEEN_STACK     (SEEN_FUNC | SEEN_MEM | SEEN_SKB)
 
 /*
@@ -382,6 +383,26 @@ static void save_restore_regs(struct bpf_jit *jit, int op)
 }
 
 /*
+ * For SKB access %b1 contains the SKB pointer. For "bpf_jit.S"
+ * we store the SKB header length on the stack and the SKB data
+ * pointer in REG_SKB_DATA.
+ */
+static void emit_load_skb_data_hlen(struct bpf_jit *jit)
+{
+       /* Header length: llgf %w1,<len>(%b1) */
+       EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_1,
+                     offsetof(struct sk_buff, len));
+       /* s %w1,<data_len>(%b1) */
+       EMIT4_DISP(0x5b000000, REG_W1, BPF_REG_1,
+                  offsetof(struct sk_buff, data_len));
+       /* stg %w1,ST_OFF_HLEN(%r0,%r15) */
+       EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15, STK_OFF_HLEN);
+       /* lg %skb_data,data_off(%b1) */
+       EMIT6_DISP_LH(0xe3000000, 0x0004, REG_SKB_DATA, REG_0,
+                     BPF_REG_1, offsetof(struct sk_buff, data));
+}
+
+/*
  * Emit function prologue
  *
  * Save registers and create stack frame if necessary.
@@ -421,25 +442,12 @@ static void bpf_jit_prologue(struct bpf_jit *jit, bool is_classic)
                        EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0,
                                      REG_15, 152);
        }
-       /*
-        * For SKB access %b1 contains the SKB pointer. For "bpf_jit.S"
-        * we store the SKB header length on the stack and the SKB data
-        * pointer in REG_SKB_DATA.
-        */
-       if (jit->seen & SEEN_SKB) {
-               /* Header length: llgf %w1,<len>(%b1) */
-               EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_1,
-                             offsetof(struct sk_buff, len));
-               /* s %w1,<data_len>(%b1) */
-               EMIT4_DISP(0x5b000000, REG_W1, BPF_REG_1,
-                          offsetof(struct sk_buff, data_len));
-               /* stg %w1,ST_OFF_HLEN(%r0,%r15) */
+       if (jit->seen & SEEN_SKB)
+               emit_load_skb_data_hlen(jit);
+       if (jit->seen & SEEN_SKB_CHANGE)
+               /* stg %b1,ST_OFF_SKBP(%r0,%r15) */
                EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15,
-                             STK_OFF_HLEN);
-               /* lg %skb_data,data_off(%b1) */
-               EMIT6_DISP_LH(0xe3000000, 0x0004, REG_SKB_DATA, REG_0,
-                             BPF_REG_1, offsetof(struct sk_buff, data));
-       }
+                             STK_OFF_SKBP);
        /* Clear A (%b0) and X (%b7) registers for converted BPF programs */
        if (is_classic) {
                if (REG_SEEN(BPF_REG_A))
@@ -967,10 +975,6 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
                 */
                const u64 func = (u64)__bpf_call_base + imm;
 
-               if (bpf_helper_changes_skb_data((void *)func))
-                       /* TODO reload skb->data, hlen */
-                       return -1;
-
                REG_SET_SEEN(BPF_REG_5);
                jit->seen |= SEEN_FUNC;
                /* lg %w1,<d(imm)>(%l) */
@@ -980,6 +984,13 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
                EMIT2(0x0d00, REG_14, REG_W1);
                /* lgr %b0,%r2: load return value into %b0 */
                EMIT4(0xb9040000, BPF_REG_0, REG_2);
+               if (bpf_helper_changes_skb_data((void *)func)) {
+                       jit->seen |= SEEN_SKB_CHANGE;
+                       /* lg %b1,ST_OFF_SKBP(%r15) */
+                       EMIT6_DISP_LH(0xe3000000, 0x0004, BPF_REG_1, REG_0,
+                                     REG_15, STK_OFF_SKBP);
+                       emit_load_skb_data_hlen(jit);
+               }
                break;
        }
        case BPF_JMP | BPF_CALL | BPF_X: