* Re: [kbuild-all] [PATCH net-next 2/2] sctp: add sctp_make_op_error_limited and reuse inner functions
From: Marcelo Ricardo Leitner @ 2018-05-14 11:01 UTC (permalink / raw)
To: Ye Xiaolong
Cc: kbuild test robot, Xin Long, Neil Horman, netdev, Vlad Yasevich,
linux-sctp, kbuild-all
In-Reply-To: <20180514074053.GA21079@yexl-desktop>
On Mon, May 14, 2018 at 03:40:53PM +0800, Ye Xiaolong wrote:
> >> config: x86_64-randconfig-x006-201817 (attached as .config)
> >> compiler: gcc-7 (Debian 7.3.0-16) 7.3.0
> >> reproduce:
> >> # save the attached .config to linux build tree
> >> make ARCH=x86_64
> >>
> >> All errors (new ones prefixed by >>):
> >>
> >> net//sctp/sm_make_chunk.c: In function 'sctp_make_op_error_limited':
> >> >> net//sctp/sm_make_chunk.c:1260:9: error: implicit declaration of function 'sctp_mtu_payload'; did you mean 'sctp_do_peeloff'? [-Werror=implicit-function-declaration]
> >> size = sctp_mtu_payload(sp, size, sizeof(struct sctp_errhdr));
> >> ^~~~~~~~~~~~~~~~
> >> sctp_do_peeloff
> >> cc1: some warnings being treated as errors
> >
> >Seems the test didn't pick up the MTU refactor patchset yet.
>
> Do you mean your patchset require MTU refactor patchset as prerequisites?
Yes.
Thanks,
Marcelo
^ permalink raw reply
* [PATCH 0/5] build warnings cleanup
From: Atul Gupta @ 2018-05-14 11:00 UTC (permalink / raw)
To: herbert, linux-crypto; +Cc: gustavo, dan.carpenter, netdev, davem, atul.gupta
Build warnings cleanup reported for
- using only 128b key
- wait for buffer in sendmsg/sendpage
- check for null before using skb
- free rspq_skb_cache in error path
- indentation
Atul Gupta (5):
crypto:chtls: key len correction
crypto: chtls: wait for memory sendmsg, sendpage
crypto: chtls: dereference null variable
crypto: chtls: kbuild warnings
crypto: chtls: free beyond end rspq_skb_cache
drivers/crypto/chelsio/chtls/chtls.h | 1 +
drivers/crypto/chelsio/chtls/chtls_hw.c | 6 +-
drivers/crypto/chelsio/chtls/chtls_io.c | 104 +++++++++++++++++++++++++++---
drivers/crypto/chelsio/chtls/chtls_main.c | 3 +-
4 files changed, 98 insertions(+), 16 deletions(-)
--
1.8.3.1
^ permalink raw reply
* [PATCH 1/5] crypto:chtls: key len correction
From: Atul Gupta @ 2018-05-14 11:00 UTC (permalink / raw)
To: herbert, linux-crypto; +Cc: gustavo, dan.carpenter, netdev, davem, atul.gupta
In-Reply-To: <1526295659-29839-1-git-send-email-atul.gupta@chelsio.com>
corrected the key length to copy 128b key. Removed 192b and 256b
key as user input supports key of size 128b in gcm_ctx
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Atul Gupta <atul.gupta@chelsio.com>
---
drivers/crypto/chelsio/chtls/chtls_hw.c | 6 +-----
1 file changed, 1 insertion(+), 5 deletions(-)
diff --git a/drivers/crypto/chelsio/chtls/chtls_hw.c b/drivers/crypto/chelsio/chtls/chtls_hw.c
index 54a13aa9..55d5014 100644
--- a/drivers/crypto/chelsio/chtls/chtls_hw.c
+++ b/drivers/crypto/chelsio/chtls/chtls_hw.c
@@ -213,7 +213,7 @@ static int chtls_key_info(struct chtls_sock *csk,
struct _key_ctx *kctx,
u32 keylen, u32 optname)
{
- unsigned char key[CHCR_KEYCTX_CIPHER_KEY_SIZE_256];
+ unsigned char key[AES_KEYSIZE_128];
struct tls12_crypto_info_aes_gcm_128 *gcm_ctx;
unsigned char ghash_h[AEAD_H_SIZE];
struct crypto_cipher *cipher;
@@ -228,10 +228,6 @@ static int chtls_key_info(struct chtls_sock *csk,
if (keylen == AES_KEYSIZE_128) {
ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_128;
- } else if (keylen == AES_KEYSIZE_192) {
- ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_192;
- } else if (keylen == AES_KEYSIZE_256) {
- ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_256;
} else {
pr_err("GCM: Invalid key length %d\n", keylen);
return -EINVAL;
--
1.8.3.1
^ permalink raw reply related
* [PATCH 2/5] crypto: chtls: wait for memory sendmsg, sendpage
From: Atul Gupta @ 2018-05-14 11:00 UTC (permalink / raw)
To: herbert, linux-crypto; +Cc: gustavo, dan.carpenter, netdev, davem, atul.gupta
In-Reply-To: <1526295659-29839-1-git-send-email-atul.gupta@chelsio.com>
Reported-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Atul Gupta <atul.gupta@chelsio.com>
---
drivers/crypto/chelsio/chtls/chtls.h | 1 +
drivers/crypto/chelsio/chtls/chtls_io.c | 90 +++++++++++++++++++++++++++++--
drivers/crypto/chelsio/chtls/chtls_main.c | 1 +
3 files changed, 89 insertions(+), 3 deletions(-)
diff --git a/drivers/crypto/chelsio/chtls/chtls.h b/drivers/crypto/chelsio/chtls/chtls.h
index f4b8f1e..778c194 100644
--- a/drivers/crypto/chelsio/chtls/chtls.h
+++ b/drivers/crypto/chelsio/chtls/chtls.h
@@ -149,6 +149,7 @@ struct chtls_dev {
struct list_head rcu_node;
struct list_head na_node;
unsigned int send_page_order;
+ int max_host_sndbuf;
struct key_map kmap;
};
diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c
index 5a75be4..a4c7d2d 100644
--- a/drivers/crypto/chelsio/chtls/chtls_io.c
+++ b/drivers/crypto/chelsio/chtls/chtls_io.c
@@ -914,6 +914,78 @@ static u16 tls_header_read(struct tls_hdr *thdr, struct iov_iter *from)
return (__force u16)cpu_to_be16(thdr->length);
}
+static int csk_mem_free(struct chtls_dev *cdev, struct sock *sk)
+{
+ return (cdev->max_host_sndbuf - sk->sk_wmem_queued) > 0;
+}
+
+static int csk_wait_memory(struct chtls_dev *cdev,
+ struct sock *sk, long *timeo_p)
+{
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
+ int sndbuf, err = 0;
+ long current_timeo;
+ long vm_wait = 0;
+ bool noblock;
+
+ current_timeo = *timeo_p;
+ noblock = (*timeo_p ? false : true);
+ sndbuf = cdev->max_host_sndbuf;
+ if (sndbuf > sk->sk_wmem_queued) {
+ current_timeo = (prandom_u32() % (HZ / 5)) + 2;
+ vm_wait = (prandom_u32() % (HZ / 5)) + 2;
+ }
+
+ add_wait_queue(sk_sleep(sk), &wait);
+ while (1) {
+ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
+
+ if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
+ goto do_error;
+ if (!*timeo_p) {
+ if (noblock)
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+ goto do_nonblock;
+ }
+ if (signal_pending(current))
+ goto do_interrupted;
+ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
+ if (sndbuf > sk->sk_wmem_queued && !vm_wait)
+ break;
+
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+ sk->sk_write_pending++;
+ sk_wait_event(sk, ¤t_timeo, sk->sk_err ||
+ (sk->sk_shutdown & SEND_SHUTDOWN) ||
+ (sndbuf > sk->sk_wmem_queued && !vm_wait), &wait);
+ sk->sk_write_pending--;
+
+ if (vm_wait) {
+ vm_wait -= current_timeo;
+ current_timeo = *timeo_p;
+ if (current_timeo != MAX_SCHEDULE_TIMEOUT) {
+ current_timeo -= vm_wait;
+ if (current_timeo < 0)
+ current_timeo = 0;
+ }
+ vm_wait = 0;
+ }
+ *timeo_p = current_timeo;
+ }
+out:
+ remove_wait_queue(sk_sleep(sk), &wait);
+ return err;
+do_error:
+ err = -EPIPE;
+ goto out;
+do_nonblock:
+ err = -EAGAIN;
+ goto out;
+do_interrupted:
+ err = sock_intr_errno(*timeo_p);
+ goto out;
+}
+
int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
{
struct chtls_sock *csk = rcu_dereference_sk_user_data(sk);
@@ -952,6 +1024,8 @@ int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
copy = mss - skb->len;
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
+ if (!csk_mem_free(cdev, sk))
+ goto wait_for_sndbuf;
if (is_tls_tx(csk) && !csk->tlshws.txleft) {
struct tls_hdr hdr;
@@ -1099,8 +1173,10 @@ int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
if (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND)
push_frames_if_head(sk);
continue;
+wait_for_sndbuf:
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
- err = sk_stream_wait_memory(sk, &timeo);
+ err = csk_wait_memory(cdev, sk, &timeo);
if (err)
goto do_error;
}
@@ -1131,6 +1207,7 @@ int chtls_sendpage(struct sock *sk, struct page *page,
int offset, size_t size, int flags)
{
struct chtls_sock *csk;
+ struct chtls_dev *cdev;
int mss, err, copied;
struct tcp_sock *tp;
long timeo;
@@ -1138,6 +1215,7 @@ int chtls_sendpage(struct sock *sk, struct page *page,
tp = tcp_sk(sk);
copied = 0;
csk = rcu_dereference_sk_user_data(sk);
+ cdev = csk->cdev;
timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
err = sk_stream_wait_connect(sk, &timeo);
@@ -1156,6 +1234,8 @@ int chtls_sendpage(struct sock *sk, struct page *page,
if (!skb || (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND) ||
copy <= 0) {
new_buf:
+ if (!csk_mem_free(cdev, sk))
+ goto wait_for_sndbuf;
if (is_tls_tx(csk)) {
skb = get_record_skb(sk,
@@ -1167,7 +1247,7 @@ int chtls_sendpage(struct sock *sk, struct page *page,
skb = get_tx_skb(sk, 0);
}
if (!skb)
- goto do_error;
+ goto wait_for_memory;
copy = mss;
}
if (copy > size)
@@ -1206,8 +1286,12 @@ int chtls_sendpage(struct sock *sk, struct page *page,
if (unlikely(ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND))
push_frames_if_head(sk);
continue;
-
+wait_for_sndbuf:
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+wait_for_memory:
+ err = csk_wait_memory(cdev, sk, &timeo);
+ if (err)
+ goto do_error;
}
out:
csk_reset_flag(csk, CSK_TX_MORE_DATA);
diff --git a/drivers/crypto/chelsio/chtls/chtls_main.c b/drivers/crypto/chelsio/chtls/chtls_main.c
index 5b9dd58..e9ffc3d 100644
--- a/drivers/crypto/chelsio/chtls/chtls_main.c
+++ b/drivers/crypto/chelsio/chtls/chtls_main.c
@@ -238,6 +238,7 @@ static void *chtls_uld_add(const struct cxgb4_lld_info *info)
spin_lock_init(&cdev->idr_lock);
cdev->send_page_order = min_t(uint, get_order(32768),
send_page_order);
+ cdev->max_host_sndbuf = 48 * 1024;
if (lldi->vr->key.size)
if (chtls_init_kmap(cdev, lldi))
--
1.8.3.1
^ permalink raw reply related
* [PATCH 3/5] crypto: chtls: dereference null variable
From: Atul Gupta @ 2018-05-14 11:00 UTC (permalink / raw)
To: herbert, linux-crypto; +Cc: gustavo, dan.carpenter, netdev, davem, atul.gupta
In-Reply-To: <1526295659-29839-1-git-send-email-atul.gupta@chelsio.com>
skb dereferenced before check in sendpage
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Atul Gupta <atul.gupta@chelsio.com>
---
drivers/crypto/chelsio/chtls/chtls_io.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c
index a4c7d2d..85ddc07 100644
--- a/drivers/crypto/chelsio/chtls/chtls_io.c
+++ b/drivers/crypto/chelsio/chtls/chtls_io.c
@@ -1230,9 +1230,8 @@ int chtls_sendpage(struct sock *sk, struct page *page,
struct sk_buff *skb = skb_peek_tail(&csk->txq);
int copy, i;
- copy = mss - skb->len;
if (!skb || (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND) ||
- copy <= 0) {
+ (copy = mss - skb->len) <= 0) {
new_buf:
if (!csk_mem_free(cdev, sk))
goto wait_for_sndbuf;
--
1.8.3.1
^ permalink raw reply related
* [PATCH 4/5] crypto: chtls: kbuild warnings
From: Atul Gupta @ 2018-05-14 11:00 UTC (permalink / raw)
To: herbert, linux-crypto; +Cc: gustavo, dan.carpenter, netdev, davem, atul.gupta
In-Reply-To: <1526295659-29839-1-git-send-email-atul.gupta@chelsio.com>
- unindented continue
- check for null page
- signed return
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Atul Gupta <atul.gupta@chelsio.com>
---
drivers/crypto/chelsio/chtls/chtls_io.c | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c
index 85ddc07..0d2e7e7 100644
--- a/drivers/crypto/chelsio/chtls/chtls_io.c
+++ b/drivers/crypto/chelsio/chtls/chtls_io.c
@@ -907,11 +907,11 @@ static int chtls_skb_copy_to_page_nocache(struct sock *sk,
}
/* Read TLS header to find content type and data length */
-static u16 tls_header_read(struct tls_hdr *thdr, struct iov_iter *from)
+static int tls_header_read(struct tls_hdr *thdr, struct iov_iter *from)
{
if (copy_from_iter(thdr, sizeof(*thdr), from) != sizeof(*thdr))
return -EFAULT;
- return (__force u16)cpu_to_be16(thdr->length);
+ return (__force int)cpu_to_be16(thdr->length);
}
static int csk_mem_free(struct chtls_dev *cdev, struct sock *sk)
@@ -1083,9 +1083,10 @@ int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
int off = TCP_OFF(sk);
bool merge;
- if (page)
- pg_size <<= compound_order(page);
+ if (!page)
+ goto wait_for_memory;
+ pg_size <<= compound_order(page);
if (off < pg_size &&
skb_can_coalesce(skb, i, page, off)) {
merge = 1;
@@ -1492,7 +1493,7 @@ static int chtls_pt_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
break;
chtls_cleanup_rbuf(sk, copied);
sk_wait_data(sk, &timeo, NULL);
- continue;
+ continue;
found_ok_skb:
if (!skb->len) {
skb_dst_set(skb, NULL);
--
1.8.3.1
^ permalink raw reply related
* [PATCH 5/5] crypto: chtls: free beyond end rspq_skb_cache
From: Atul Gupta @ 2018-05-14 11:00 UTC (permalink / raw)
To: herbert, linux-crypto; +Cc: gustavo, dan.carpenter, netdev, davem, atul.gupta
In-Reply-To: <1526295659-29839-1-git-send-email-atul.gupta@chelsio.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Atul Gupta <atul.gupta@chelsio.com>
---
drivers/crypto/chelsio/chtls/chtls_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/crypto/chelsio/chtls/chtls_main.c b/drivers/crypto/chelsio/chtls/chtls_main.c
index e9ffc3d..1ef56d6 100644
--- a/drivers/crypto/chelsio/chtls/chtls_main.c
+++ b/drivers/crypto/chelsio/chtls/chtls_main.c
@@ -250,7 +250,7 @@ static void *chtls_uld_add(const struct cxgb4_lld_info *info)
return cdev;
out_rspq_skb:
- for (j = 0; j <= i; j++)
+ for (j = 0; j < i; j++)
kfree_skb(cdev->rspq_skb_cache[j]);
kfree_skb(cdev->askb);
out_skb:
--
1.8.3.1
^ permalink raw reply related
* [PATCH] crypto: chtls: generic handling of data and hdr
From: Atul Gupta @ 2018-05-14 11:11 UTC (permalink / raw)
To: herbert, linux-crypto; +Cc: netdev, davem, atul.gupta, Harsh Jain
removed redundant check and made TLS PDU and header recv
handling common as received from HW.
Ensure that only tls header is read in cpl_rx_tls_cmp
read-ahead and skb is freed when entire data is processed.
Signed-off-by: Atul Gupta <atul.gupta@chelsio.com>
Signed-off-by: Harsh Jain <harsh@chelsio.com>
---
drivers/crypto/chelsio/chtls/chtls.h | 10 ++----
drivers/crypto/chelsio/chtls/chtls_cm.c | 12 +++++---
drivers/crypto/chelsio/chtls/chtls_io.c | 54 ++++++++-------------------------
3 files changed, 23 insertions(+), 53 deletions(-)
diff --git a/drivers/crypto/chelsio/chtls/chtls.h b/drivers/crypto/chelsio/chtls/chtls.h
index 778c194..a53a0e6 100644
--- a/drivers/crypto/chelsio/chtls/chtls.h
+++ b/drivers/crypto/chelsio/chtls/chtls.h
@@ -67,11 +67,6 @@ enum {
CPL_RET_UNKNOWN_TID = 4 /* unexpected unknown TID */
};
-#define TLS_RCV_ST_READ_HEADER 0xF0
-#define TLS_RCV_ST_READ_BODY 0xF1
-#define TLS_RCV_ST_READ_DONE 0xF2
-#define TLS_RCV_ST_READ_NB 0xF3
-
#define LISTEN_INFO_HASH_SIZE 32
#define RSPQ_HASH_BITS 5
struct listen_info {
@@ -279,6 +274,7 @@ struct tlsrx_cmp_hdr {
#define TLSRX_HDR_PKT_MAC_ERROR_F TLSRX_HDR_PKT_MAC_ERROR_V(1U)
#define TLSRX_HDR_PKT_ERROR_M 0x1F
+#define CONTENT_TYPE_ERROR 0x7F
struct ulp_mem_rw {
__be32 cmd;
@@ -348,8 +344,8 @@ enum {
ULPCB_FLAG_HOLD = 1 << 3, /* skb not ready for Tx yet */
ULPCB_FLAG_COMPL = 1 << 4, /* request WR completion */
ULPCB_FLAG_URG = 1 << 5, /* urgent data */
- ULPCB_FLAG_TLS_ND = 1 << 6, /* payload of zero length */
- ULPCB_FLAG_NO_HDR = 1 << 7, /* not a ofld wr */
+ ULPCB_FLAG_TLS_HDR = 1 << 6, /* payload with tls hdr */
+ ULPCB_FLAG_NO_HDR = 1 << 7, /* not a ofld wr */
};
/* The ULP mode/submode of an skbuff */
diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.c b/drivers/crypto/chelsio/chtls/chtls_cm.c
index 23c43b8..2bb6f03 100644
--- a/drivers/crypto/chelsio/chtls/chtls_cm.c
+++ b/drivers/crypto/chelsio/chtls/chtls_cm.c
@@ -1608,12 +1608,14 @@ static void chtls_set_hdrlen(struct sk_buff *skb, unsigned int nlen)
static void chtls_rx_hdr(struct sock *sk, struct sk_buff *skb)
{
- struct cpl_rx_tls_cmp *cmp_cpl = cplhdr(skb);
+ struct tlsrx_cmp_hdr *tls_hdr_pkt;
+ struct cpl_rx_tls_cmp *cmp_cpl;
struct sk_buff *skb_rec;
struct chtls_sock *csk;
struct chtls_hws *tlsk;
struct tcp_sock *tp;
+ cmp_cpl = cplhdr(skb);
csk = rcu_dereference_sk_user_data(sk);
tlsk = &csk->tlshws;
tp = tcp_sk(sk);
@@ -1623,16 +1625,18 @@ static void chtls_rx_hdr(struct sock *sk, struct sk_buff *skb)
skb_reset_transport_header(skb);
__skb_pull(skb, sizeof(*cmp_cpl));
+ tls_hdr_pkt = (struct tlsrx_cmp_hdr *)skb->data;
+ if (tls_hdr_pkt->res_to_mac_error & TLSRX_HDR_PKT_ERROR_M)
+ tls_hdr_pkt->type = CONTENT_TYPE_ERROR;
if (!skb->data_len)
- __skb_trim(skb, CPL_RX_TLS_CMP_LENGTH_G
- (ntohl(cmp_cpl->pdulength_length)));
+ __skb_trim(skb, TLS_HEADER_LENGTH);
tp->rcv_nxt +=
CPL_RX_TLS_CMP_PDULENGTH_G(ntohl(cmp_cpl->pdulength_length));
+ ULP_SKB_CB(skb)->flags |= ULPCB_FLAG_TLS_HDR;
skb_rec = __skb_dequeue(&tlsk->sk_recv_queue);
if (!skb_rec) {
- ULP_SKB_CB(skb)->flags |= ULPCB_FLAG_TLS_ND;
__skb_queue_tail(&sk->sk_receive_queue, skb);
} else {
chtls_set_hdrlen(skb, tlsk->pldlen);
diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c
index 0d2e7e7..9dbdea0 100644
--- a/drivers/crypto/chelsio/chtls/chtls_io.c
+++ b/drivers/crypto/chelsio/chtls/chtls_io.c
@@ -1533,31 +1533,13 @@ static int chtls_pt_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
}
}
}
- if (hws->rstate == TLS_RCV_ST_READ_BODY) {
- if (skb_copy_datagram_msg(skb, offset,
- msg, avail)) {
- if (!copied) {
- copied = -EFAULT;
- break;
- }
- }
- } else {
- struct tlsrx_cmp_hdr *tls_hdr_pkt =
- (struct tlsrx_cmp_hdr *)skb->data;
-
- if ((tls_hdr_pkt->res_to_mac_error &
- TLSRX_HDR_PKT_ERROR_M))
- tls_hdr_pkt->type = 0x7F;
-
- /* CMP pld len is for recv seq */
- hws->rcvpld = skb->hdr_len;
- if (skb_copy_datagram_msg(skb, offset, msg, avail)) {
- if (!copied) {
- copied = -EFAULT;
- break;
- }
+ if (skb_copy_datagram_msg(skb, offset, msg, avail)) {
+ if (!copied) {
+ copied = -EFAULT;
+ break;
}
}
+
copied += avail;
len -= avail;
hws->copied_seq += avail;
@@ -1565,32 +1547,20 @@ static int chtls_pt_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
if (tp->urg_data && after(tp->copied_seq, tp->urg_seq))
tp->urg_data = 0;
- if (hws->rstate == TLS_RCV_ST_READ_BODY &&
- (avail + offset) >= skb->len) {
+ if ((avail + offset) >= skb->len) {
if (likely(skb))
chtls_free_skb(sk, skb);
buffers_freed++;
- hws->rstate = TLS_RCV_ST_READ_HEADER;
- atomic_inc(&adap->chcr_stats.tls_pdu_rx);
- tp->copied_seq += hws->rcvpld;
+ if (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_TLS_HDR) {
+ tp->copied_seq += skb->len;
+ hws->rcvpld = skb->hdr_len;
+ } else {
+ tp->copied_seq += hws->rcvpld;
+ }
hws->copied_seq = 0;
if (copied >= target &&
!skb_peek(&sk->sk_receive_queue))
break;
- } else {
- if (likely(skb)) {
- if (ULP_SKB_CB(skb)->flags &
- ULPCB_FLAG_TLS_ND)
- hws->rstate =
- TLS_RCV_ST_READ_HEADER;
- else
- hws->rstate =
- TLS_RCV_ST_READ_BODY;
- chtls_free_skb(sk, skb);
- }
- buffers_freed++;
- tp->copied_seq += avail;
- hws->copied_seq = 0;
}
} while (len > 0);
--
1.8.3.1
^ permalink raw reply related
* Re: [PATCH 2/5] crypto: chtls: wait for memory sendmsg, sendpage
From: Dan Carpenter @ 2018-05-14 11:29 UTC (permalink / raw)
To: Atul Gupta; +Cc: herbert, linux-crypto, gustavo, netdev, davem
In-Reply-To: <1526295659-29839-3-git-send-email-atul.gupta@chelsio.com>
On Mon, May 14, 2018 at 04:30:56PM +0530, Atul Gupta wrote:
> Reported-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
> Signed-off-by: Atul Gupta <atul.gupta@chelsio.com>
There isn't a commit message for this. It should say what the user
visible effects of this bug are. I haven't seen Gustavo's bug report,
but probably copy and pasting that would be good?
> ---
> drivers/crypto/chelsio/chtls/chtls.h | 1 +
> drivers/crypto/chelsio/chtls/chtls_io.c | 90 +++++++++++++++++++++++++++++--
> drivers/crypto/chelsio/chtls/chtls_main.c | 1 +
> 3 files changed, 89 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/crypto/chelsio/chtls/chtls.h b/drivers/crypto/chelsio/chtls/chtls.h
> index f4b8f1e..778c194 100644
> --- a/drivers/crypto/chelsio/chtls/chtls.h
> +++ b/drivers/crypto/chelsio/chtls/chtls.h
> @@ -149,6 +149,7 @@ struct chtls_dev {
> struct list_head rcu_node;
> struct list_head na_node;
> unsigned int send_page_order;
> + int max_host_sndbuf;
> struct key_map kmap;
> };
>
> diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c
> index 5a75be4..a4c7d2d 100644
> --- a/drivers/crypto/chelsio/chtls/chtls_io.c
> +++ b/drivers/crypto/chelsio/chtls/chtls_io.c
> @@ -914,6 +914,78 @@ static u16 tls_header_read(struct tls_hdr *thdr, struct iov_iter *from)
> return (__force u16)cpu_to_be16(thdr->length);
> }
>
> +static int csk_mem_free(struct chtls_dev *cdev, struct sock *sk)
> +{
> + return (cdev->max_host_sndbuf - sk->sk_wmem_queued) > 0;
Why not just say:
return (max_host_sndbuf > sk->sk_wmem_queued);
> +}
> +
> +static int csk_wait_memory(struct chtls_dev *cdev,
> + struct sock *sk, long *timeo_p)
> +{
> + DEFINE_WAIT_FUNC(wait, woken_wake_function);
> + int sndbuf, err = 0;
> + long current_timeo;
> + long vm_wait = 0;
> + bool noblock;
> +
> + current_timeo = *timeo_p;
> + noblock = (*timeo_p ? false : true);
> sndbuf = cdev->max_host_sndbuf;
> + if (sndbuf > sk->sk_wmem_queued) {
You could use it here:
if (csk_mem_free(cdev, sk)) {
> + current_timeo = (prandom_u32() % (HZ / 5)) + 2;
> + vm_wait = (prandom_u32() % (HZ / 5)) + 2;
> + }
> +
> + add_wait_queue(sk_sleep(sk), &wait);
> + while (1) {
> + sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
> +
> + if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
> + goto do_error;
> + if (!*timeo_p) {
> + if (noblock)
> + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
> + goto do_nonblock;
There are missing curly braces here. I feel like these gotos make the
code worse. They don't remove duplicate lines of code. They just
spread things out so that you have to jump around to understand this
code. It's like being a kangaroo.
if (noblock) {
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
err = -EAGAIN;
goto remove_queue;
}
I always like picking a descriptive label names instead of "out:"
> + }
> + if (signal_pending(current))
> + goto do_interrupted;
> + sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
> + if (sndbuf > sk->sk_wmem_queued && !vm_wait)
> + break;
if (csk_mem_free(cdev, sk) && !vm_wait)
> +
> + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
> + sk->sk_write_pending++;
> + sk_wait_event(sk, ¤t_timeo, sk->sk_err ||
> + (sk->sk_shutdown & SEND_SHUTDOWN) ||
> + (sndbuf > sk->sk_wmem_queued && !vm_wait), &wait);
(csk_mem_free(cdev, sk) && !vm_wait), &wait);
> + sk->sk_write_pending--;
> +
> + if (vm_wait) {
> + vm_wait -= current_timeo;
> + current_timeo = *timeo_p;
> + if (current_timeo != MAX_SCHEDULE_TIMEOUT) {
> + current_timeo -= vm_wait;
> + if (current_timeo < 0)
> + current_timeo = 0;
> + }
> + vm_wait = 0;
> + }
> + *timeo_p = current_timeo;
> + }
> +out:
> + remove_wait_queue(sk_sleep(sk), &wait);
> + return err;
> +do_error:
> + err = -EPIPE;
> + goto out;
> +do_nonblock:
> + err = -EAGAIN;
> + goto out;
> +do_interrupted:
> + err = sock_intr_errno(*timeo_p);
> + goto out;
> +}
> +
regards,
dan carpenter
^ permalink raw reply
* [PATCH v3] ipvlan: call netdevice notifier when master mac address changed
From: liuqifa @ 2018-05-14 11:38 UTC (permalink / raw)
To: davem, dsahern, maheshb, weiyongjun1, maowenan, dingtianhong,
liuqifa
Cc: netdev, linux-kernel
From: Keefe Liu <liuqifa@huawei.com>
When master device's mac has been changed, the commit
32c10bbfe914 ("ipvlan: always use the current L2 addr of the
master") makes the IPVlan devices's mac changed also, but it
doesn't do related works such as flush the IPVlan devices's
arp table.
Signed-off-by: Keefe Liu <liuqifa@huawei.com>
---
drivers/net/ipvlan/ipvlan_main.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 450eec2..4377c26 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -792,8 +792,10 @@ static int ipvlan_device_event(struct notifier_block *unused,
break;
case NETDEV_CHANGEADDR:
- list_for_each_entry(ipvlan, &port->ipvlans, pnode)
+ list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
ether_addr_copy(ipvlan->dev->dev_addr, dev->dev_addr);
+ call_netdevice_notifiers(NETDEV_CHANGEADDR, ipvlan->dev);
+ }
break;
case NETDEV_PRE_TYPE_CHANGE:
--
1.8.3.1
^ permalink raw reply related
* Re: [kbuild-all] [PATCH net-next 2/2] sctp: add sctp_make_op_error_limited and reuse inner functions
From: Ye Xiaolong @ 2018-05-14 11:47 UTC (permalink / raw)
To: Marcelo Ricardo Leitner
Cc: kbuild test robot, Xin Long, Neil Horman, netdev, Vlad Yasevich,
linux-sctp, kbuild-all
In-Reply-To: <20180514110123.GA5105@localhost.localdomain>
On 05/14, Marcelo Ricardo Leitner wrote:
>On Mon, May 14, 2018 at 03:40:53PM +0800, Ye Xiaolong wrote:
>> >> config: x86_64-randconfig-x006-201817 (attached as .config)
>> >> compiler: gcc-7 (Debian 7.3.0-16) 7.3.0
>> >> reproduce:
>> >> # save the attached .config to linux build tree
>> >> make ARCH=x86_64
>> >>
>> >> All errors (new ones prefixed by >>):
>> >>
>> >> net//sctp/sm_make_chunk.c: In function 'sctp_make_op_error_limited':
>> >> >> net//sctp/sm_make_chunk.c:1260:9: error: implicit declaration of function 'sctp_mtu_payload'; did you mean 'sctp_do_peeloff'? [-Werror=implicit-function-declaration]
>> >> size = sctp_mtu_payload(sp, size, sizeof(struct sctp_errhdr));
>> >> ^~~~~~~~~~~~~~~~
>> >> sctp_do_peeloff
>> >> cc1: some warnings being treated as errors
>> >
>> >Seems the test didn't pick up the MTU refactor patchset yet.
>>
>> Do you mean your patchset require MTU refactor patchset as prerequisites?
>
>Yes.
Then it is recommended to use '--base' option of git format-patch, it would record
the base tree info in the first patch or cover letter, 0day bot would apply your
patchset to right base according to it.
Thanks,
Xiaolong
>
>Thanks,
>Marcelo
^ permalink raw reply
* [RFC][PATCH bpf v3 1/5] bpf: allow 64-bit offsets for bpf function calls
From: Sandipan Das @ 2018-05-14 11:51 UTC (permalink / raw)
To: ast, daniel; +Cc: netdev, linuxppc-dev, mpe, naveen.n.rao
The imm field of a bpf instruction is a signed 32-bit integer.
For JIT bpf-to-bpf function calls, it stores the offset of the
start address of the callee's JITed image from __bpf_call_base.
For some architectures, such as powerpc64, this offset may be
as large as 64 bits and cannot be accomodated in the imm field
without truncation.
We resolve this by:
[1] Additionally using the auxillary data of each function to
keep a list of start addresses of the JITed images for all
functions determined by the verifier.
[2] Retaining the subprog id inside the off field of the call
instructions and using it to index into the list mentioned
above and lookup the callee's address.
To make sure that the existing JIT compilers continue to work
without requiring changes, we keep the imm field as it is.
Signed-off-by: Sandipan Das <sandipan@linux.vnet.ibm.com>
---
v3: Rephrase commit message to explain solution in a point-
wise manner.
v2: Make aux->func point to the list of functions determined
by the verifier rather than allocating a separate callee
list for each function.
---
kernel/bpf/verifier.c | 15 ++++++++++++++-
1 file changed, 14 insertions(+), 1 deletion(-)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d5e1a6c4165d..aa76879f4fd1 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5373,11 +5373,24 @@ static int jit_subprogs(struct bpf_verifier_env *env)
insn->src_reg != BPF_PSEUDO_CALL)
continue;
subprog = insn->off;
- insn->off = 0;
insn->imm = (u64 (*)(u64, u64, u64, u64, u64))
func[subprog]->bpf_func -
__bpf_call_base;
}
+
+ /* we use the aux data to keep a list of the start addresses
+ * of the JITed images for each function in the program
+ *
+ * for some architectures, such as powerpc64, the imm field
+ * might not be large enough to hold the offset of the start
+ * address of the callee's JITed image from __bpf_call_base
+ *
+ * in such cases, we can lookup the start address of a callee
+ * by using its subprog id, available from the off field of
+ * the call instruction, as an index for this list
+ */
+ func[i]->aux->func = func;
+ func[i]->aux->func_cnt = env->subprog_cnt + 1;
}
for (i = 0; i < env->subprog_cnt; i++) {
old_bpf_func = func[i]->bpf_func;
--
2.14.3
^ permalink raw reply related
* [RFC][PATCH bpf v3 2/5] bpf: powerpc64: add JIT support for multi-function programs
From: Sandipan Das @ 2018-05-14 11:51 UTC (permalink / raw)
To: ast, daniel; +Cc: netdev, linuxppc-dev, mpe, naveen.n.rao
In-Reply-To: <20180514115118.8149-1-sandipan@linux.vnet.ibm.com>
This adds support for bpf-to-bpf function calls in the powerpc64
JIT compiler. The JIT compiler converts the bpf call instructions
to native branch instructions. After a round of the usual passes,
the start addresses of the JITed images for the callee functions
are known. Finally, to fixup the branch target addresses, we need
to perform an extra pass.
Because of the address range in which JITed images are allocated
on powerpc64, the offsets of the start addresses of these images
from __bpf_call_base are as large as 64 bits. So, for a function
call, we cannot use the imm field of the instruction to determine
the callee's address. Instead, we use the alternative method of
getting it from the list of function addresses in the auxillary
data of the caller by using the off field as an index.
Signed-off-by: Sandipan Das <sandipan@linux.vnet.ibm.com>
---
v3: Mention briefly about why the offsets are large.
v2: Use the off field of the instruction as an index for
aux->func to determine the start address of a callee
function.
---
arch/powerpc/net/bpf_jit_comp64.c | 79 ++++++++++++++++++++++++++++++++++-----
1 file changed, 69 insertions(+), 10 deletions(-)
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 1bdb1aff0619..25939892d8f7 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -256,7 +256,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32
/* Assemble the body code between the prologue & epilogue */
static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
struct codegen_context *ctx,
- u32 *addrs)
+ u32 *addrs, bool extra_pass)
{
const struct bpf_insn *insn = fp->insnsi;
int flen = fp->len;
@@ -712,11 +712,23 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
break;
/*
- * Call kernel helper
+ * Call kernel helper or bpf function
*/
case BPF_JMP | BPF_CALL:
ctx->seen |= SEEN_FUNC;
- func = (u8 *) __bpf_call_base + imm;
+
+ /* bpf function call */
+ if (insn[i].src_reg == BPF_PSEUDO_CALL && extra_pass)
+ if (fp->aux->func && off < fp->aux->func_cnt)
+ /* use the subprog id from the off
+ * field to lookup the callee address
+ */
+ func = (u8 *) fp->aux->func[off]->bpf_func;
+ else
+ return -EINVAL;
+ /* kernel helper call */
+ else
+ func = (u8 *) __bpf_call_base + imm;
bpf_jit_emit_func_call(image, ctx, (u64)func);
@@ -864,6 +876,14 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
return 0;
}
+struct powerpc64_jit_data {
+ struct bpf_binary_header *header;
+ u32 *addrs;
+ u8 *image;
+ u32 proglen;
+ struct codegen_context ctx;
+};
+
struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
{
u32 proglen;
@@ -871,6 +891,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
u8 *image = NULL;
u32 *code_base;
u32 *addrs;
+ struct powerpc64_jit_data *jit_data;
struct codegen_context cgctx;
int pass;
int flen;
@@ -878,6 +899,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
struct bpf_prog *org_fp = fp;
struct bpf_prog *tmp_fp;
bool bpf_blinded = false;
+ bool extra_pass = false;
if (!fp->jit_requested)
return org_fp;
@@ -891,7 +913,28 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
fp = tmp_fp;
}
+ jit_data = fp->aux->jit_data;
+ if (!jit_data) {
+ jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL);
+ if (!jit_data) {
+ fp = org_fp;
+ goto out;
+ }
+ fp->aux->jit_data = jit_data;
+ }
+
flen = fp->len;
+ addrs = jit_data->addrs;
+ if (addrs) {
+ cgctx = jit_data->ctx;
+ image = jit_data->image;
+ bpf_hdr = jit_data->header;
+ proglen = jit_data->proglen;
+ alloclen = proglen + FUNCTION_DESCR_SIZE;
+ extra_pass = true;
+ goto skip_init_ctx;
+ }
+
addrs = kzalloc((flen+1) * sizeof(*addrs), GFP_KERNEL);
if (addrs == NULL) {
fp = org_fp;
@@ -904,10 +947,10 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
cgctx.stack_size = round_up(fp->aux->stack_depth, 16);
/* Scouting faux-generate pass 0 */
- if (bpf_jit_build_body(fp, 0, &cgctx, addrs)) {
+ if (bpf_jit_build_body(fp, 0, &cgctx, addrs, false)) {
/* We hit something illegal or unsupported. */
fp = org_fp;
- goto out;
+ goto out_addrs;
}
/*
@@ -925,9 +968,10 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
bpf_jit_fill_ill_insns);
if (!bpf_hdr) {
fp = org_fp;
- goto out;
+ goto out_addrs;
}
+skip_init_ctx:
code_base = (u32 *)(image + FUNCTION_DESCR_SIZE);
/* Code generation passes 1-2 */
@@ -935,7 +979,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
/* Now build the prologue, body code & epilogue for real. */
cgctx.idx = 0;
bpf_jit_build_prologue(code_base, &cgctx);
- bpf_jit_build_body(fp, code_base, &cgctx, addrs);
+ bpf_jit_build_body(fp, code_base, &cgctx, addrs, extra_pass);
bpf_jit_build_epilogue(code_base, &cgctx);
if (bpf_jit_enable > 1)
@@ -956,15 +1000,30 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
((u64 *)image)[1] = local_paca->kernel_toc;
#endif
+ bpf_flush_icache(bpf_hdr, (u8 *)bpf_hdr + (bpf_hdr->pages * PAGE_SIZE));
+
+ if (!fp->is_func || extra_pass) {
+ bpf_jit_binary_lock_ro(bpf_hdr);
+ } else {
+ jit_data->addrs = addrs;
+ jit_data->ctx = cgctx;
+ jit_data->proglen = proglen;
+ jit_data->image = image;
+ jit_data->header = bpf_hdr;
+ }
+
fp->bpf_func = (void *)image;
fp->jited = 1;
fp->jited_len = alloclen;
- bpf_flush_icache(bpf_hdr, (u8 *)bpf_hdr + (bpf_hdr->pages * PAGE_SIZE));
+ if (!fp->is_func || extra_pass) {
+out_addrs:
+ kfree(addrs);
+ kfree(jit_data);
+ fp->aux->jit_data = NULL;
+ }
out:
- kfree(addrs);
-
if (bpf_blinded)
bpf_jit_prog_release_other(fp, fp == org_fp ? tmp_fp : org_fp);
--
2.14.3
^ permalink raw reply related
* [RFC][PATCH bpf v3 3/5] bpf: get JITed function addresses via syscall
From: Sandipan Das @ 2018-05-14 11:51 UTC (permalink / raw)
To: ast, daniel; +Cc: netdev, linuxppc-dev, mpe, naveen.n.rao
In-Reply-To: <20180514115118.8149-1-sandipan@linux.vnet.ibm.com>
This adds new two new fields to struct bpf_prog_info. For
multi-function programs, these fields can be used to pass
a list of kernel symbol addresses for all functions in a
given program and to userspace using the bpf system call
with the BPF_OBJ_GET_INFO_BY_FD command.
When bpf_jit_kallsyms is enabled, we can get the address
of the corresponding kernel symbol for a callee function
and resolve the symbol's name. The address is determined
by adding the value of the call instruction's imm field
to __bpf_call_base. This offset gets assigned to the imm
field by the verifier.
For some architectures, such as powerpc64, the imm field
is not large enough to hold this offset.
We resolve this by:
[1] Assigning the subprog id to the imm field of a call
instruction in the verifier instead of the offset of
the callee's symbol's address from __bpf_call_base.
[2] Determining the address of a callee's corresponding
symbol by using the imm field as an index for the
list of function addresses now available from the
program info.
Suggested-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sandipan Das <sandipan@linux.vnet.ibm.com>
---
include/uapi/linux/bpf.h | 2 ++
kernel/bpf/syscall.c | 18 ++++++++++++++++++
kernel/bpf/verifier.c | 7 +------
3 files changed, 21 insertions(+), 6 deletions(-)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 93d5a4eeec2a..b9c9c7690337 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2108,6 +2108,8 @@ struct bpf_prog_info {
__u32 xlated_prog_len;
__aligned_u64 jited_prog_insns;
__aligned_u64 xlated_prog_insns;
+ __aligned_u64 jited_funcs;
+ __u32 nr_jited_funcs;
__u64 load_time; /* ns since boottime */
__u32 created_by_uid;
__u32 nr_map_ids;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 9b87198deea2..600da849233d 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1924,6 +1924,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
if (!capable(CAP_SYS_ADMIN)) {
info.jited_prog_len = 0;
info.xlated_prog_len = 0;
+ info.nr_jited_funcs = 0;
goto done;
}
@@ -1972,6 +1973,23 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
}
}
+ ulen = info.nr_jited_funcs;
+ info.nr_jited_funcs = prog->aux->func_cnt;
+ if (info.nr_jited_funcs && ulen) {
+ u64 __user *user_jited_funcs = u64_to_user_ptr(info.jited_funcs);
+ u32 i;
+
+ /* copy the start addresses of the JITed images for all
+ * functions
+ */
+ ulen = min_t(u32, info.nr_jited_funcs, ulen);
+ for (i = 0; i < ulen; i++) {
+ if (put_user((u64) prog->aux->func[i]->bpf_func & PAGE_MASK,
+ &user_jited_funcs[i]))
+ return -EFAULT;
+ }
+ }
+
done:
if (copy_to_user(uinfo, &info, info_len) ||
put_user(info_len, &uattr->info.info_len))
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index aa76879f4fd1..fc864eb3e29d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5416,17 +5416,12 @@ static int jit_subprogs(struct bpf_verifier_env *env)
* later look the same as if they were interpreted only.
*/
for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
- unsigned long addr;
-
if (insn->code != (BPF_JMP | BPF_CALL) ||
insn->src_reg != BPF_PSEUDO_CALL)
continue;
insn->off = env->insn_aux_data[i].call_imm;
subprog = find_subprog(env, i + insn->off + 1);
- addr = (unsigned long)func[subprog]->bpf_func;
- addr &= PAGE_MASK;
- insn->imm = (u64 (*)(u64, u64, u64, u64, u64))
- addr - __bpf_call_base;
+ insn->imm = subprog;
}
prog->jited = 1;
--
2.14.3
^ permalink raw reply related
* [RFC][PATCH bpf v3 4/5] tools: bpf: sync bpf uapi header
From: Sandipan Das @ 2018-05-14 11:51 UTC (permalink / raw)
To: ast, daniel; +Cc: netdev, linuxppc-dev, mpe, naveen.n.rao
In-Reply-To: <20180514115118.8149-1-sandipan@linux.vnet.ibm.com>
Syncing the bpf.h uapi header with tools so that struct
bpf_prog_info has the new fields for storing the kernel
symbol addresses for the JITed functions in a program.
Signed-off-by: Sandipan Das <sandipan@linux.vnet.ibm.com>
---
tools/include/uapi/linux/bpf.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 83a95ae388dd..98857dc3469a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2107,6 +2107,8 @@ struct bpf_prog_info {
__u32 xlated_prog_len;
__aligned_u64 jited_prog_insns;
__aligned_u64 xlated_prog_insns;
+ __aligned_u64 jited_funcs;
+ __u32 nr_jited_funcs;
__u64 load_time; /* ns since boottime */
__u32 created_by_uid;
__u32 nr_map_ids;
--
2.14.3
^ permalink raw reply related
* [RFC][PATCH bpf v3 5/5] tools: bpftool: resolve call addresses without using imm field
From: Sandipan Das @ 2018-05-14 11:51 UTC (permalink / raw)
To: ast, daniel; +Cc: netdev, linuxppc-dev, mpe, naveen.n.rao
In-Reply-To: <20180514115118.8149-1-sandipan@linux.vnet.ibm.com>
Currently, we resolve the callee's address for a JITed function
call by using the imm field of the call instruction as an offset
from __bpf_call_base. If bpf_jit_kallsyms is enabled, we further
use this address to get the callee's kernel symbol's name.
For some architectures, such as powerpc64, the imm field is not
large enough to hold this offset. So, instead of assigning this
offset to the imm field, the verifier now assigns the subprog
id. Also, a list of kernel symbol addresses for all the JITed
functions is provided in the program info. We now use the imm
field as an index for this list to lookup a callee's symbol's
address and resolve its name.
Suggested-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sandipan Das <sandipan@linux.vnet.ibm.com>
---
tools/bpf/bpftool/prog.c | 33 +++++++++++++++++++++++++++++++++
tools/bpf/bpftool/xlated_dumper.c | 24 +++++++++++++++++-------
tools/bpf/bpftool/xlated_dumper.h | 2 ++
3 files changed, 52 insertions(+), 7 deletions(-)
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 9bdfdf2d3fbe..0ba947c7deec 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -428,6 +428,8 @@ static int do_dump(int argc, char **argv)
bool opcodes = false;
bool visual = false;
unsigned char *buf;
+ __u64 *addrs = NULL;
+ __u32 nr_addrs = 0;
__u32 *member_len;
__u64 *member_ptr;
ssize_t n;
@@ -496,11 +498,27 @@ static int do_dump(int argc, char **argv)
return -1;
}
+ if (info.nr_jited_funcs) {
+ nr_addrs = info.nr_jited_funcs;
+ addrs = (__u64 *) malloc(nr_addrs * sizeof(__u64));
+ if (!addrs) {
+ p_err("mem alloc failed");
+ free(buf);
+ close(fd);
+ return -1;
+ }
+ }
+
memset(&info, 0, sizeof(info));
*member_ptr = ptr_to_u64(buf);
*member_len = buf_size;
+ if (nr_addrs) {
+ info.jited_funcs = ptr_to_u64(addrs);
+ info.nr_jited_funcs = nr_addrs;
+ }
+
err = bpf_obj_get_info_by_fd(fd, &info, &len);
close(fd);
if (err) {
@@ -513,6 +531,11 @@ static int do_dump(int argc, char **argv)
goto err_free;
}
+ if (info.nr_jited_funcs > nr_addrs) {
+ p_err("too many addresses returned");
+ goto err_free;
+ }
+
if ((member_len == &info.jited_prog_len &&
info.jited_prog_insns == 0) ||
(member_len == &info.xlated_prog_len &&
@@ -558,6 +581,12 @@ static int do_dump(int argc, char **argv)
dump_xlated_cfg(buf, *member_len);
} else {
kernel_syms_load(&dd);
+
+ if (info.nr_jited_funcs) {
+ dd.jited_funcs = (u64 *) info.jited_funcs;
+ dd.nr_jited_funcs = info.nr_jited_funcs;
+ }
+
if (json_output)
dump_xlated_json(&dd, buf, *member_len, opcodes);
else
@@ -566,10 +595,14 @@ static int do_dump(int argc, char **argv)
}
free(buf);
+ if (nr_addrs)
+ free(addrs);
return 0;
err_free:
free(buf);
+ if (nr_addrs)
+ free(addrs);
return -1;
}
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index 7a3173b76c16..70943612b667 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -178,8 +178,12 @@ static const char *print_call_pcrel(struct dump_data *dd,
snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
"%+d#%s", insn->off, sym->name);
else
- snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
- "%+d#0x%lx", insn->off, address);
+ if (address)
+ snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
+ "%+d#0x%lx", insn->off, address);
+ else
+ snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
+ "%+d", insn->off);
return dd->scratch_buff;
}
@@ -200,14 +204,20 @@ static const char *print_call(void *private_data,
const struct bpf_insn *insn)
{
struct dump_data *dd = private_data;
- unsigned long address = dd->address_call_base + insn->imm;
- struct kernel_sym *sym;
+ unsigned long address = 0;
+ struct kernel_sym *sym = NULL;
- sym = kernel_syms_search(dd, address);
- if (insn->src_reg == BPF_PSEUDO_CALL)
+ if (insn->src_reg == BPF_PSEUDO_CALL) {
+ if (dd->nr_jited_funcs) {
+ address = dd->jited_funcs[insn->imm];
+ sym = kernel_syms_search(dd, address);
+ }
return print_call_pcrel(dd, sym, address, insn);
- else
+ } else {
+ address = dd->address_call_base + insn->imm;
+ sym = kernel_syms_search(dd, address);
return print_call_helper(dd, sym, address);
+ }
}
static const char *print_imm(void *private_data,
diff --git a/tools/bpf/bpftool/xlated_dumper.h b/tools/bpf/bpftool/xlated_dumper.h
index b34affa7ef2d..6afc03a5fbad 100644
--- a/tools/bpf/bpftool/xlated_dumper.h
+++ b/tools/bpf/bpftool/xlated_dumper.h
@@ -47,6 +47,8 @@ struct kernel_sym {
struct dump_data {
unsigned long address_call_base;
+ unsigned long *jited_funcs;
+ unsigned int nr_jited_funcs;
struct kernel_sym *sym_mapping;
__u32 sym_count;
char scratch_buff[SYM_MAX_NAME + 8];
--
2.14.3
^ permalink raw reply related
* Re: [PATCH net-next 1/2] cxgb4: Add support for FW_ETH_TX_PKT_VM_WR
From: kbuild test robot @ 2018-05-14 11:51 UTC (permalink / raw)
To: Ganesh Goudar
Cc: kbuild-all, netdev, davem, nirranjan, indranil, venkatesh,
Arjun Vynipadath, Casey Leedom, Ganesh Goudar
In-Reply-To: <1526284511-10490-1-git-send-email-ganeshgr@chelsio.com>
[-- Attachment #1: Type: text/plain, Size: 835 bytes --]
Hi Arjun,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on net-next/master]
url: https://github.com/0day-ci/linux/commits/Ganesh-Goudar/cxgb4-Add-support-for-FW_ETH_TX_PKT_VM_WR/20180514-163558
config: x86_64-acpi-redef (attached as .config)
compiler: gcc-7 (Debian 7.3.0-16) 7.3.0
reproduce:
# save the attached .config to linux build tree
make ARCH=x86_64
All errors (new ones prefixed by >>):
drivers/net/ethernet/chelsio/cxgb4vf/sge.o: In function `t4vf_eth_xmit':
>> sge.c:(.text+0x14c4): multiple definition of `t4vf_eth_xmit'
drivers/net/ethernet/chelsio/cxgb4/sge.o:sge.c:(.text+0x3072): first defined here
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 30415 bytes --]
^ permalink raw reply
* [PATCH v3] selftests: add headers_install to lib.mk
From: Anders Roxell @ 2018-05-14 11:58 UTC (permalink / raw)
To: yamada.masahiro, michal.lkml, shuah, bamv2005, brgl, pbonzini,
akpm, rppt, aarcange
Cc: linux-kbuild, linux-kernel, linux-kselftest, netdev,
Anders Roxell
In-Reply-To: <20180413090351.25662-1-anders.roxell@linaro.org>
If the kernel headers aren't installed we can't build all the tests.
Add a new make target rule 'khdr' in the file lib.mk to generate the
kernel headers and that gets include for every test-dir Makefile that
includes lib.mk If the testdir in turn have its own sub-dirs the
top_srcdir needs to be set to the linux-rootdir to be able to generate
the kernel headers.
Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Reviewed-by: Fathi Boudra <fathi.boudra@linaro.org>
---
Makefile | 14 +-------------
scripts/subarch.include | 13 +++++++++++++
tools/testing/selftests/android/Makefile | 2 +-
tools/testing/selftests/android/ion/Makefile | 1 +
tools/testing/selftests/bpf/Makefile | 5 ++---
tools/testing/selftests/futex/functional/Makefile | 1 +
tools/testing/selftests/gpio/Makefile | 7 ++-----
tools/testing/selftests/kvm/Makefile | 7 ++-----
tools/testing/selftests/lib.mk | 10 ++++++++++
tools/testing/selftests/vm/Makefile | 4 ----
10 files changed, 33 insertions(+), 31 deletions(-)
create mode 100644 scripts/subarch.include
diff --git a/Makefile b/Makefile
index 6395c79ffe40..bad0a8f6e874 100644
--- a/Makefile
+++ b/Makefile
@@ -286,19 +286,7 @@ KERNELRELEASE = $(shell cat include/config/kernel.release 2> /dev/null)
KERNELVERSION = $(VERSION)$(if $(PATCHLEVEL),.$(PATCHLEVEL)$(if $(SUBLEVEL),.$(SUBLEVEL)))$(EXTRAVERSION)
export VERSION PATCHLEVEL SUBLEVEL KERNELRELEASE KERNELVERSION
-# SUBARCH tells the usermode build what the underlying arch is. That is set
-# first, and if a usermode build is happening, the "ARCH=um" on the command
-# line overrides the setting of ARCH below. If a native build is happening,
-# then ARCH is assigned, getting whatever value it gets normally, and
-# SUBARCH is subsequently ignored.
-
-SUBARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
- -e s/sun4u/sparc64/ \
- -e s/arm.*/arm/ -e s/sa110/arm/ \
- -e s/s390x/s390/ -e s/parisc64/parisc/ \
- -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
- -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \
- -e s/riscv.*/riscv/)
+include scripts/subarch.include
# Cross compiling and selecting different set of gcc/bin-utils
# ---------------------------------------------------------------------------
diff --git a/scripts/subarch.include b/scripts/subarch.include
new file mode 100644
index 000000000000..650682821126
--- /dev/null
+++ b/scripts/subarch.include
@@ -0,0 +1,13 @@
+# SUBARCH tells the usermode build what the underlying arch is. That is set
+# first, and if a usermode build is happening, the "ARCH=um" on the command
+# line overrides the setting of ARCH below. If a native build is happening,
+# then ARCH is assigned, getting whatever value it gets normally, and
+# SUBARCH is subsequently ignored.
+
+SUBARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
+ -e s/sun4u/sparc64/ \
+ -e s/arm.*/arm/ -e s/sa110/arm/ \
+ -e s/s390x/s390/ -e s/parisc64/parisc/ \
+ -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
+ -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \
+ -e s/riscv.*/riscv/)
diff --git a/tools/testing/selftests/android/Makefile b/tools/testing/selftests/android/Makefile
index 72c25a3cb658..d9a725478375 100644
--- a/tools/testing/selftests/android/Makefile
+++ b/tools/testing/selftests/android/Makefile
@@ -6,7 +6,7 @@ TEST_PROGS := run.sh
include ../lib.mk
-all:
+all: khdr
@for DIR in $(SUBDIRS); do \
BUILD_TARGET=$(OUTPUT)/$$DIR; \
mkdir $$BUILD_TARGET -p; \
diff --git a/tools/testing/selftests/android/ion/Makefile b/tools/testing/selftests/android/ion/Makefile
index e03695287f76..f3be7dcc060a 100644
--- a/tools/testing/selftests/android/ion/Makefile
+++ b/tools/testing/selftests/android/ion/Makefile
@@ -10,6 +10,7 @@ $(TEST_GEN_FILES): ipcsocket.c ionutils.c
TEST_PROGS := ion_test.sh
+top_srcdir = ../../../../..
include ../../lib.mk
$(OUTPUT)/ionapp_export: ionapp_export.c ipcsocket.c ionutils.c
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 438d4f93875b..9741609a0eb1 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -16,9 +16,8 @@ LDLIBS += -lcap -lelf -lrt -lpthread
TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read
all: $(TEST_CUSTOM_PROGS)
-$(TEST_CUSTOM_PROGS): urandom_read
-
-urandom_read: urandom_read.c
+$(TEST_CUSTOM_PROGS):| khdr
+$(TEST_CUSTOM_PROGS): urandom_read.c
$(CC) -o $(TEST_CUSTOM_PROGS) -static $<
# Order correspond to 'make run_tests' order
diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile
index ff8feca49746..ad1eeb14fda7 100644
--- a/tools/testing/selftests/futex/functional/Makefile
+++ b/tools/testing/selftests/futex/functional/Makefile
@@ -18,6 +18,7 @@ TEST_GEN_FILES := \
TEST_PROGS := run.sh
+top_srcdir = ../../../../..
include ../../lib.mk
$(TEST_GEN_FILES): $(HEADERS)
diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile
index 1bbb47565c55..4665cdbf1a8d 100644
--- a/tools/testing/selftests/gpio/Makefile
+++ b/tools/testing/selftests/gpio/Makefile
@@ -21,11 +21,8 @@ endef
CFLAGS += -O2 -g -std=gnu99 -Wall -I../../../../usr/include/
LDLIBS += -lmount -I/usr/include/libmount
-$(BINARIES): ../../../gpio/gpio-utils.o ../../../../usr/include/linux/gpio.h
+$(BINARIES):| khdr
+$(BINARIES): ../../../gpio/gpio-utils.o
../../../gpio/gpio-utils.o:
make ARCH=$(ARCH) CROSS_COMPILE=$(CROSS_COMPILE) -C ../../../gpio
-
-../../../../usr/include/linux/gpio.h:
- make -C ../../../.. headers_install INSTALL_HDR_PATH=$(shell pwd)/../../../../usr/
-
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index d9d00319b07c..bcb69380bbab 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -32,9 +32,6 @@ $(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c
$(OUTPUT)/libkvm.a: $(LIBKVM_OBJ)
$(AR) crs $@ $^
-$(LINUX_HDR_PATH):
- make -C $(top_srcdir) headers_install
-
-all: $(STATIC_LIBS) $(LINUX_HDR_PATH)
+all: $(STATIC_LIBS)
$(TEST_GEN_PROGS): $(STATIC_LIBS)
-$(TEST_GEN_PROGS) $(LIBKVM_OBJ): | $(LINUX_HDR_PATH)
+$(STATIC_LIBS):| khdr
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 6466294366dc..9515af872e16 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -16,8 +16,18 @@ TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS))
TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED))
TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES))
+top_srcdir ?= ../../../..
+include $(top_srcdir)/scripts/subarch.include
+ARCH ?= $(SUBARCH)
+
all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
+.PHONY: khdr
+khdr:
+ make ARCH=$(ARCH) -C $(top_srcdir) headers_install
+
+$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES):| khdr
+
.ONESHELL:
define RUN_TEST_PRINT_RESULT
TEST_HDR_MSG="selftests: "`basename $$PWD`:" $$BASENAME_TEST"; \
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index fdefa2295ddc..58759454b1d0 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -25,10 +25,6 @@ TEST_PROGS := run_vmtests
include ../lib.mk
-$(OUTPUT)/userfaultfd: ../../../../usr/include/linux/kernel.h
$(OUTPUT)/userfaultfd: LDLIBS += -lpthread
$(OUTPUT)/mlock-random-test: LDLIBS += -lcap
-
-../../../../usr/include/linux/kernel.h:
- make -C ../../../.. headers_install
--
2.17.0
^ permalink raw reply related
* Re: [PATCH RESEND net-next v2 1/8] dt-bindings: net: dwmac-sun8i: Clean up clock delay chain descriptions
From: Andrew Lunn @ 2018-05-14 12:03 UTC (permalink / raw)
To: Maxime Ripard
Cc: Chen-Yu Tsai, Giuseppe Cavallaro, linux-arm-kernel, devicetree,
netdev, Corentin Labbe, Icenowy Zheng, Rob Herring
In-Reply-To: <20180514072113.yts3shbojvbxj4tq@flea>
> > Currently no other board requires this, but this is already part of the
> > binding. The new stuff limits the range for a specific SoC, simply because
> > that is the range supported by the control register. Not implementing, i.e.
> > supporting the whole range from the property, which might get truncated,
> > doesn't make much sense to me.
>
> With that driver we don't, but the previous design had the same
> feature and it was used on more boards. It was simply initialized
> statically in U-Boot, and not in Linux through the DT like it is done
> here.
If there are boards which do need it, then i'm fine with it. I would
also prefer that Linux does set it, and don't rely on U-boot.
Andrew
^ permalink raw reply
* Re: [PATCH] net: phy: micrel: workaround for errata #2 for KSZ9031
From: Andrew Lunn @ 2018-05-14 12:11 UTC (permalink / raw)
To: Marco Felsch
Cc: robh+dt, mark.rutland, f.fainelli, netdev, devicetree, kernel,
Markus Niebel
In-Reply-To: <20180514082218.29158-1-m.felsch@pengutronix.de>
On Mon, May 14, 2018 at 10:22:18AM +0200, Marco Felsch wrote:
> From: Markus Niebel <Markus.Niebel@tqs.de>
>
> handle errata #2 for KSZ9031: force 1000Base-T master
>
> Attention: enabling the workaround will cause no link to
> other GIGE master.
Hi Marco
It would be good to document why this is needed, when to use it, what
problems it fixes, etc. At the moment, there is not enough information
to decide if you should turn it on.
Andrew
^ permalink raw reply
* [PATCH net 1/2] vmxnet3: set the DMA mask before the first DMA map operation
From: hpreg @ 2018-05-14 12:14 UTC (permalink / raw)
To: netdev; +Cc: Regis Duchesne, Ronak Doshi, VMware, Inc., open list
The DMA mask must be set before, not after, the first DMA map operation, or
the first DMA map operation could in theory fail on some systems.
Fixes: b0eb57cb97e78 ("VMXNET3: Add support for virtual IOMMU")
Signed-off-by: Regis Duchesne <hpreg@vmware.com>
Acked-by: Ronak Doshi <doshir@vmware.com>
---
drivers/net/vmxnet3/vmxnet3_drv.c | 50 +++++++++++++++++++--------------------
drivers/net/vmxnet3/vmxnet3_int.h | 8 ++++---
2 files changed, 30 insertions(+), 28 deletions(-)
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 9ebe2a6..ed58685 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -2688,7 +2688,7 @@ vmxnet3_set_mac_addr(struct net_device *netdev, void *p)
/* ==================== initialization and cleanup routines ============ */
static int
-vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter, bool *dma64)
+vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter)
{
int err;
unsigned long mmio_start, mmio_len;
@@ -2700,30 +2700,12 @@ vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter, bool *dma64)
return err;
}
- if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) == 0) {
- if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)) != 0) {
- dev_err(&pdev->dev,
- "pci_set_consistent_dma_mask failed\n");
- err = -EIO;
- goto err_set_mask;
- }
- *dma64 = true;
- } else {
- if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) != 0) {
- dev_err(&pdev->dev,
- "pci_set_dma_mask failed\n");
- err = -EIO;
- goto err_set_mask;
- }
- *dma64 = false;
- }
-
err = pci_request_selected_regions(pdev, (1 << 2) - 1,
vmxnet3_driver_name);
if (err) {
dev_err(&pdev->dev,
"Failed to request region for adapter: error %d\n", err);
- goto err_set_mask;
+ goto err_enable_device;
}
pci_set_master(pdev);
@@ -2751,7 +2733,7 @@ vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter, bool *dma64)
iounmap(adapter->hw_addr0);
err_ioremap:
pci_release_selected_regions(pdev, (1 << 2) - 1);
-err_set_mask:
+err_enable_device:
pci_disable_device(pdev);
return err;
}
@@ -3254,7 +3236,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
#endif
};
int err;
- bool dma64 = false; /* stupid gcc */
+ bool dma64;
u32 ver;
struct net_device *netdev;
struct vmxnet3_adapter *adapter;
@@ -3300,6 +3282,24 @@ vmxnet3_probe_device(struct pci_dev *pdev,
adapter->rx_ring_size = VMXNET3_DEF_RX_RING_SIZE;
adapter->rx_ring2_size = VMXNET3_DEF_RX_RING2_SIZE;
+ if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) == 0) {
+ if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)) != 0) {
+ dev_err(&pdev->dev,
+ "pci_set_consistent_dma_mask failed\n");
+ err = -EIO;
+ goto err_set_mask;
+ }
+ dma64 = true;
+ } else {
+ if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) != 0) {
+ dev_err(&pdev->dev,
+ "pci_set_dma_mask failed\n");
+ err = -EIO;
+ goto err_set_mask;
+ }
+ dma64 = false;
+ }
+
spin_lock_init(&adapter->cmd_lock);
adapter->adapter_pa = dma_map_single(&adapter->pdev->dev, adapter,
sizeof(struct vmxnet3_adapter),
@@ -3307,7 +3307,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
if (dma_mapping_error(&adapter->pdev->dev, adapter->adapter_pa)) {
dev_err(&pdev->dev, "Failed to map dma\n");
err = -EFAULT;
- goto err_dma_map;
+ goto err_set_mask;
}
adapter->shared = dma_alloc_coherent(
&adapter->pdev->dev,
@@ -3358,7 +3358,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
}
#endif /* VMXNET3_RSS */
- err = vmxnet3_alloc_pci_resources(adapter, &dma64);
+ err = vmxnet3_alloc_pci_resources(adapter);
if (err < 0)
goto err_alloc_pci;
@@ -3504,7 +3504,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
err_alloc_shared:
dma_unmap_single(&adapter->pdev->dev, adapter->adapter_pa,
sizeof(struct vmxnet3_adapter), PCI_DMA_TODEVICE);
-err_dma_map:
+err_set_mask:
free_netdev(netdev);
return err;
}
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index a332646..b379bed 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -69,10 +69,12 @@
/*
* Version numbers
*/
-#define VMXNET3_DRIVER_VERSION_STRING "1.4.14.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING "1.4.15.0-k"
-/* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */
-#define VMXNET3_DRIVER_VERSION_NUM 0x01040e00
+/* Each byte of this 32-bit integer encodes a version number in
+ * VMXNET3_DRIVER_VERSION_STRING.
+ */
+#define VMXNET3_DRIVER_VERSION_NUM 0x01040f00
#if defined(CONFIG_PCI_MSI)
/* RSS only makes sense if MSI-X is supported. */
--
2.7.4
^ permalink raw reply related
* [PATCH net 2/2] vmxnet3: use DMA memory barriers where required
From: hpreg @ 2018-05-14 12:14 UTC (permalink / raw)
To: netdev; +Cc: Regis Duchesne, Ronak Doshi, VMware, Inc., open list
The gen bits must be read first from (resp. written last to) DMA memory.
The proper way to enforce this on Linux is to call dma_rmb() (resp.
dma_wmb()).
Signed-off-by: Regis Duchesne <hpreg@vmware.com>
Acked-by: Ronak Doshi <doshir@vmware.com>
---
drivers/net/vmxnet3/vmxnet3_drv.c | 22 ++++++++++++++++++++++
drivers/net/vmxnet3/vmxnet3_int.h | 4 ++--
2 files changed, 24 insertions(+), 2 deletions(-)
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index ed58685..27a9bb8 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -369,6 +369,11 @@ vmxnet3_tq_tx_complete(struct vmxnet3_tx_queue *tq,
gdesc = tq->comp_ring.base + tq->comp_ring.next2proc;
while (VMXNET3_TCD_GET_GEN(&gdesc->tcd) == tq->comp_ring.gen) {
+ /* Prevent any &gdesc->tcd field from being (speculatively)
+ * read before (&gdesc->tcd)->gen is read.
+ */
+ dma_rmb();
+
completed += vmxnet3_unmap_pkt(VMXNET3_TCD_GET_TXIDX(
&gdesc->tcd), tq, adapter->pdev,
adapter);
@@ -1103,6 +1108,11 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
gdesc->txd.tci = skb_vlan_tag_get(skb);
}
+ /* Ensure that the write to (&gdesc->txd)->gen will be observed after
+ * all other writes to &gdesc->txd.
+ */
+ dma_wmb();
+
/* finally flips the GEN bit of the SOP desc. */
gdesc->dword[2] = cpu_to_le32(le32_to_cpu(gdesc->dword[2]) ^
VMXNET3_TXD_GEN);
@@ -1298,6 +1308,12 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
*/
break;
}
+
+ /* Prevent any rcd field from being (speculatively) read before
+ * rcd->gen is read.
+ */
+ dma_rmb();
+
BUG_ON(rcd->rqID != rq->qid && rcd->rqID != rq->qid2 &&
rcd->rqID != rq->dataRingQid);
idx = rcd->rxdIdx;
@@ -1528,6 +1544,12 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
ring->next2comp = idx;
num_to_alloc = vmxnet3_cmd_ring_desc_avail(ring);
ring = rq->rx_ring + ring_idx;
+
+ /* Ensure that the writes to rxd->gen bits will be observed
+ * after all other writes to rxd objects.
+ */
+ dma_wmb();
+
while (num_to_alloc) {
vmxnet3_getRxDesc(rxd, &ring->base[ring->next2fill].rxd,
&rxCmdDesc);
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index b379bed..a2c554f 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -69,12 +69,12 @@
/*
* Version numbers
*/
-#define VMXNET3_DRIVER_VERSION_STRING "1.4.15.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING "1.4.16.0-k"
/* Each byte of this 32-bit integer encodes a version number in
* VMXNET3_DRIVER_VERSION_STRING.
*/
-#define VMXNET3_DRIVER_VERSION_NUM 0x01040f00
+#define VMXNET3_DRIVER_VERSION_NUM 0x01041000
#if defined(CONFIG_PCI_MSI)
/* RSS only makes sense if MSI-X is supported. */
--
2.7.4
^ permalink raw reply related
* Re: [kbuild-all] [PATCH net-next 2/2] sctp: add sctp_make_op_error_limited and reuse inner functions
From: Marcelo Ricardo Leitner @ 2018-05-14 12:16 UTC (permalink / raw)
To: Ye Xiaolong
Cc: kbuild test robot, Xin Long, Neil Horman, netdev, Vlad Yasevich,
linux-sctp, kbuild-all
In-Reply-To: <20180514114720.GA25280@yexl-desktop>
On Mon, May 14, 2018 at 07:47:20PM +0800, Ye Xiaolong wrote:
> On 05/14, Marcelo Ricardo Leitner wrote:
> >On Mon, May 14, 2018 at 03:40:53PM +0800, Ye Xiaolong wrote:
> >> >> config: x86_64-randconfig-x006-201817 (attached as .config)
> >> >> compiler: gcc-7 (Debian 7.3.0-16) 7.3.0
> >> >> reproduce:
> >> >> # save the attached .config to linux build tree
> >> >> make ARCH=x86_64
> >> >>
> >> >> All errors (new ones prefixed by >>):
> >> >>
> >> >> net//sctp/sm_make_chunk.c: In function 'sctp_make_op_error_limited':
> >> >> >> net//sctp/sm_make_chunk.c:1260:9: error: implicit declaration of function 'sctp_mtu_payload'; did you mean 'sctp_do_peeloff'? [-Werror=implicit-function-declaration]
> >> >> size = sctp_mtu_payload(sp, size, sizeof(struct sctp_errhdr));
> >> >> ^~~~~~~~~~~~~~~~
> >> >> sctp_do_peeloff
> >> >> cc1: some warnings being treated as errors
> >> >
> >> >Seems the test didn't pick up the MTU refactor patchset yet.
> >>
> >> Do you mean your patchset require MTU refactor patchset as prerequisites?
> >
> >Yes.
>
> Then it is recommended to use '--base' option of git format-patch, it would record
> the base tree info in the first patch or cover letter, 0day bot would apply your
> patchset to right base according to it.
Nice. I wasn't aware of it. Thanks.
Considering that the MTU refactor patchset was already applied on
net-next when the bot did the test, why should I have to specify the
base?
Marcelo
^ permalink raw reply
* [PATCH net-next] cxgb4: add tc flower match support for tunnel VNI
From: Ganesh Goudar @ 2018-05-14 12:21 UTC (permalink / raw)
To: netdev, davem
Cc: nirranjan, indranil, venkatesh, Kumar Sanghvi, Ganesh Goudar
From: Kumar Sanghvi <kumaras@chelsio.com>
Adds support for matching flows based on tunnel VNI value.
Introduces fw APIs for allocating/removing MPS entries related
to encapsulation. And uses the same while adding/deleting filters
for offloading flows based on tunnel VNI match.
Signed-off-by: Kumar Sanghvi <kumaras@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
---
drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 9 +++
drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c | 91 ++++++++++++++++++++--
.../net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c | 18 +++++
drivers/net/ethernet/chelsio/cxgb4/l2t.c | 2 +-
drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 86 ++++++++++++++++++++
drivers/net/ethernet/chelsio/cxgb4/t4_regs.h | 4 +
drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h | 34 ++++++++
7 files changed, 237 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index d2a7777..ce47daf 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -1045,6 +1045,7 @@ struct ch_sched_queue {
#define VF_BITWIDTH 8
#define IVLAN_BITWIDTH 16
#define OVLAN_BITWIDTH 16
+#define ENCAP_VNI_BITWIDTH 24
/* Filter matching rules. These consist of a set of ingress packet field
* (value, mask) tuples. The associated ingress packet field matches the
@@ -1075,6 +1076,7 @@ struct ch_filter_tuple {
uint32_t ivlan_vld:1; /* inner VLAN valid */
uint32_t ovlan_vld:1; /* outer VLAN valid */
uint32_t pfvf_vld:1; /* PF/VF valid */
+ uint32_t encap_vld:1; /* Encapsulation valid */
uint32_t macidx:MACIDX_BITWIDTH; /* exact match MAC index */
uint32_t fcoe:FCOE_BITWIDTH; /* FCoE packet */
uint32_t iport:IPORT_BITWIDTH; /* ingress port */
@@ -1085,6 +1087,7 @@ struct ch_filter_tuple {
uint32_t vf:VF_BITWIDTH; /* PCI-E VF ID */
uint32_t ivlan:IVLAN_BITWIDTH; /* inner VLAN */
uint32_t ovlan:OVLAN_BITWIDTH; /* outer VLAN */
+ uint32_t vni:ENCAP_VNI_BITWIDTH; /* VNI of tunnel */
/* Uncompressed header matching field rules. These are always
* available for field rules.
@@ -1703,6 +1706,12 @@ int t4_set_rxmode(struct adapter *adap, unsigned int mbox, unsigned int viid,
int t4_free_raw_mac_filt(struct adapter *adap, unsigned int viid,
const u8 *addr, const u8 *mask, unsigned int idx,
u8 lookup_type, u8 port_id, bool sleep_ok);
+int t4_free_encap_mac_filt(struct adapter *adap, unsigned int viid, int idx,
+ bool sleep_ok);
+int t4_alloc_encap_mac_filt(struct adapter *adap, unsigned int viid,
+ const u8 *addr, const u8 *mask, unsigned int vni,
+ unsigned int vni_mask, u8 dip_hit, u8 lookup_type,
+ bool sleep_ok);
int t4_alloc_raw_mac_filt(struct adapter *adap, unsigned int viid,
const u8 *addr, const u8 *mask, unsigned int idx,
u8 lookup_type, u8 port_id, bool sleep_ok);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index aae9802..ac4d7f7 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -265,6 +265,8 @@ static int validate_filter(struct net_device *dev,
fs->mask.pfvf_vld) ||
unsupported(fconf, VNIC_ID_F, fs->val.ovlan_vld,
fs->mask.ovlan_vld) ||
+ unsupported(fconf, VNIC_ID_F, fs->val.encap_vld,
+ fs->mask.encap_vld) ||
unsupported(fconf, VLAN_F, fs->val.ivlan_vld, fs->mask.ivlan_vld))
return -EOPNOTSUPP;
@@ -275,8 +277,12 @@ static int validate_filter(struct net_device *dev,
* carries that overlap, we need to translate any PF/VF
* specification into that internal format below.
*/
- if (is_field_set(fs->val.pfvf_vld, fs->mask.pfvf_vld) &&
- is_field_set(fs->val.ovlan_vld, fs->mask.ovlan_vld))
+ if ((is_field_set(fs->val.pfvf_vld, fs->mask.pfvf_vld) &&
+ is_field_set(fs->val.ovlan_vld, fs->mask.ovlan_vld)) ||
+ (is_field_set(fs->val.pfvf_vld, fs->mask.pfvf_vld) &&
+ is_field_set(fs->val.encap_vld, fs->mask.encap_vld)) ||
+ (is_field_set(fs->val.ovlan_vld, fs->mask.ovlan_vld) &&
+ is_field_set(fs->val.encap_vld, fs->mask.encap_vld)))
return -EOPNOTSUPP;
if (unsupported(iconf, VNIC_F, fs->val.pfvf_vld, fs->mask.pfvf_vld) ||
(is_field_set(fs->val.ovlan_vld, fs->mask.ovlan_vld) &&
@@ -306,6 +312,9 @@ static int validate_filter(struct net_device *dev,
fs->newvlan == VLAN_REWRITE))
return -EOPNOTSUPP;
+ if (fs->val.encap_vld &&
+ CHELSIO_CHIP_VERSION(adapter->params.chip) < CHELSIO_T6)
+ return -EOPNOTSUPP;
return 0;
}
@@ -705,6 +714,8 @@ int delete_filter(struct adapter *adapter, unsigned int fidx)
*/
void clear_filter(struct adapter *adap, struct filter_entry *f)
{
+ struct port_info *pi = netdev_priv(f->dev);
+
/* If the new or old filter have loopback rewriteing rules then we'll
* need to free any existing L2T, SMT, CLIP entries of filter
* rule.
@@ -715,6 +726,12 @@ void clear_filter(struct adapter *adap, struct filter_entry *f)
if (f->smt)
cxgb4_smt_release(f->smt);
+ if (f->fs.val.encap_vld && f->fs.val.ovlan_vld)
+ if (atomic_dec_and_test(&adap->mps_encap[f->fs.val.ovlan &
+ 0x1ff].refcnt))
+ t4_free_encap_mac_filt(adap, pi->viid,
+ f->fs.val.ovlan & 0x1ff, 0);
+
if ((f->fs.hash || is_t6(adap->params.chip)) && f->fs.type)
cxgb4_clip_release(f->dev, (const u32 *)&f->fs.val.lip, 1);
@@ -840,6 +857,10 @@ bool is_filter_exact_match(struct adapter *adap,
if (!is_hashfilter(adap))
return false;
+ /* Keep tunnel VNI match disabled for hash-filters for now */
+ if (fs->mask.encap_vld)
+ return false;
+
if (fs->type) {
if (is_inaddr_any(fs->val.fip, AF_INET6) ||
!is_addr_all_mask(fs->mask.fip, AF_INET6))
@@ -961,8 +982,12 @@ static u64 hash_filter_ntuple(struct ch_filter_specification *fs,
ntuple |= (u64)(fs->val.tos) << tp->tos_shift;
if (tp->vnic_shift >= 0) {
- if ((adap->params.tp.ingress_config & VNIC_F) &&
- fs->mask.pfvf_vld)
+ if ((adap->params.tp.ingress_config & USE_ENC_IDX_F) &&
+ fs->mask.encap_vld)
+ ntuple |= (u64)((fs->val.encap_vld << 16) |
+ (fs->val.ovlan)) << tp->vnic_shift;
+ else if ((adap->params.tp.ingress_config & VNIC_F) &&
+ fs->mask.pfvf_vld)
ntuple |= (u64)((fs->val.pfvf_vld << 16) |
(fs->val.pf << 13) |
(fs->val.vf)) << tp->vnic_shift;
@@ -1076,6 +1101,7 @@ static int cxgb4_set_hash_filter(struct net_device *dev,
struct filter_ctx *ctx)
{
struct adapter *adapter = netdev2adap(dev);
+ struct port_info *pi = netdev_priv(dev);
struct tid_info *t = &adapter->tids;
struct filter_entry *f;
struct sk_buff *skb;
@@ -1142,13 +1168,34 @@ static int cxgb4_set_hash_filter(struct net_device *dev,
f->fs.mask.ovlan = (fs->mask.pf << 13) | fs->mask.vf;
f->fs.val.ovlan_vld = fs->val.pfvf_vld;
f->fs.mask.ovlan_vld = fs->mask.pfvf_vld;
+ } else if (iconf & USE_ENC_IDX_F) {
+ if (f->fs.val.encap_vld) {
+ struct port_info *pi = netdev_priv(f->dev);
+ u8 match_all_mac[] = { 0, 0, 0, 0, 0, 0 };
+
+ /* allocate MPS TCAM entry */
+ ret = t4_alloc_encap_mac_filt(adapter, pi->viid,
+ match_all_mac,
+ match_all_mac,
+ f->fs.val.vni,
+ f->fs.mask.vni,
+ 0, 1, 1);
+ if (ret < 0)
+ goto free_atid;
+
+ atomic_inc(&adapter->mps_encap[ret].refcnt);
+ f->fs.val.ovlan = ret;
+ f->fs.mask.ovlan = 0xffff;
+ f->fs.val.ovlan_vld = 1;
+ f->fs.mask.ovlan_vld = 1;
+ }
}
size = sizeof(struct cpl_t6_act_open_req);
if (f->fs.type) {
ret = cxgb4_clip_get(f->dev, (const u32 *)&f->fs.val.lip, 1);
if (ret)
- goto free_atid;
+ goto free_mps;
skb = alloc_skb(size, GFP_KERNEL);
if (!skb) {
@@ -1163,7 +1210,7 @@ static int cxgb4_set_hash_filter(struct net_device *dev,
skb = alloc_skb(size, GFP_KERNEL);
if (!skb) {
ret = -ENOMEM;
- goto free_atid;
+ goto free_mps;
}
mk_act_open_req(f, skb,
@@ -1179,6 +1226,10 @@ static int cxgb4_set_hash_filter(struct net_device *dev,
free_clip:
cxgb4_clip_release(f->dev, (const u32 *)&f->fs.val.lip, 1);
+free_mps:
+ if (f->fs.val.encap_vld && f->fs.val.ovlan_vld)
+ t4_free_encap_mac_filt(adapter, pi->viid, f->fs.val.ovlan, 1);
+
free_atid:
cxgb4_free_atid(t, atid);
@@ -1360,6 +1411,27 @@ int __cxgb4_set_filter(struct net_device *dev, int filter_id,
f->fs.mask.ovlan = (fs->mask.pf << 13) | fs->mask.vf;
f->fs.val.ovlan_vld = fs->val.pfvf_vld;
f->fs.mask.ovlan_vld = fs->mask.pfvf_vld;
+ } else if (iconf & USE_ENC_IDX_F) {
+ if (f->fs.val.encap_vld) {
+ struct port_info *pi = netdev_priv(f->dev);
+ u8 match_all_mac[] = { 0, 0, 0, 0, 0, 0 };
+
+ /* allocate MPS TCAM entry */
+ ret = t4_alloc_encap_mac_filt(adapter, pi->viid,
+ match_all_mac,
+ match_all_mac,
+ f->fs.val.vni,
+ f->fs.mask.vni,
+ 0, 1, 1);
+ if (ret < 0)
+ goto free_clip;
+
+ atomic_inc(&adapter->mps_encap[ret].refcnt);
+ f->fs.val.ovlan = ret;
+ f->fs.mask.ovlan = 0x1ff;
+ f->fs.val.ovlan_vld = 1;
+ f->fs.mask.ovlan_vld = 1;
+ }
}
/* Attempt to set the filter. If we don't succeed, we clear
@@ -1376,6 +1448,13 @@ int __cxgb4_set_filter(struct net_device *dev, int filter_id,
}
return ret;
+
+free_clip:
+ if (is_t6(adapter->params.chip) && f->fs.type)
+ cxgb4_clip_release(f->dev, (const u32 *)&f->fs.val.lip, 1);
+ cxgb4_clear_ftid(&adapter->tids, filter_id,
+ fs->type ? PF_INET6 : PF_INET, chip_ver);
+ return ret;
}
static int cxgb4_del_hash_filter(struct net_device *dev, int filter_id,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
index 3656336..3ddd2c4 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
@@ -194,6 +194,23 @@ static void cxgb4_process_flow_match(struct net_device *dev,
fs->mask.tos = mask->tos;
}
+ if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+ struct flow_dissector_key_keyid *key, *mask;
+
+ key = skb_flow_dissector_target(cls->dissector,
+ FLOW_DISSECTOR_KEY_ENC_KEYID,
+ cls->key);
+ mask = skb_flow_dissector_target(cls->dissector,
+ FLOW_DISSECTOR_KEY_ENC_KEYID,
+ cls->mask);
+ fs->val.vni = be32_to_cpu(key->keyid);
+ fs->mask.vni = be32_to_cpu(mask->keyid);
+ if (fs->mask.vni) {
+ fs->val.encap_vld = 1;
+ fs->mask.encap_vld = 1;
+ }
+ }
+
if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
struct flow_dissector_key_vlan *key, *mask;
u16 vlan_tci, vlan_tci_mask;
@@ -247,6 +264,7 @@ static int cxgb4_validate_flow_match(struct net_device *dev,
BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
BIT(FLOW_DISSECTOR_KEY_PORTS) |
+ BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) |
BIT(FLOW_DISSECTOR_KEY_VLAN) |
BIT(FLOW_DISSECTOR_KEY_IP))) {
netdev_warn(dev, "Unsupported key used: 0x%x\n",
diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
index 1817a03..77c2c53 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
@@ -491,7 +491,7 @@ u64 cxgb4_select_ntuple(struct net_device *dev,
if (tp->protocol_shift >= 0)
ntuple |= (u64)IPPROTO_TCP << tp->protocol_shift;
- if (tp->vnic_shift >= 0) {
+ if (tp->vnic_shift >= 0 && (tp->ingress_config & VNIC_F)) {
u32 viid = cxgb4_port_viid(dev);
u32 vf = FW_VIID_VIN_G(viid);
u32 pf = FW_VIID_PFN_G(viid);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 7cb3ef4..df5e7c7 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -7513,6 +7513,43 @@ int t4_set_rxmode(struct adapter *adap, unsigned int mbox, unsigned int viid,
}
/**
+ * t4_free_encap_mac_filt - frees MPS entry at given index
+ * @adap: the adapter
+ * @viid: the VI id
+ * @idx: index of MPS entry to be freed
+ * @sleep_ok: call is allowed to sleep
+ *
+ * Frees the MPS entry at supplied index
+ *
+ * Returns a negative error number or zero on success
+ */
+int t4_free_encap_mac_filt(struct adapter *adap, unsigned int viid,
+ int idx, bool sleep_ok)
+{
+ struct fw_vi_mac_exact *p;
+ u8 addr[] = {0, 0, 0, 0, 0, 0};
+ struct fw_vi_mac_cmd c;
+ int ret = 0;
+ u32 exact;
+
+ memset(&c, 0, sizeof(c));
+ c.op_to_viid = cpu_to_be32(FW_CMD_OP_V(FW_VI_MAC_CMD) |
+ FW_CMD_REQUEST_F | FW_CMD_WRITE_F |
+ FW_CMD_EXEC_V(0) |
+ FW_VI_MAC_CMD_VIID_V(viid));
+ exact = FW_VI_MAC_CMD_ENTRY_TYPE_V(FW_VI_MAC_TYPE_EXACTMAC);
+ c.freemacs_to_len16 = cpu_to_be32(FW_VI_MAC_CMD_FREEMACS_V(0) |
+ exact |
+ FW_CMD_LEN16_V(1));
+ p = c.u.exact;
+ p->valid_to_idx = cpu_to_be16(FW_VI_MAC_CMD_VALID_F |
+ FW_VI_MAC_CMD_IDX_V(idx));
+ memcpy(p->macaddr, addr, sizeof(p->macaddr));
+ ret = t4_wr_mbox_meat(adap, adap->mbox, &c, sizeof(c), &c, sleep_ok);
+ return ret;
+}
+
+/**
* t4_free_raw_mac_filt - Frees a raw mac entry in mps tcam
* @adap: the adapter
* @viid: the VI id
@@ -7563,6 +7600,55 @@ int t4_free_raw_mac_filt(struct adapter *adap, unsigned int viid,
}
/**
+ * t4_alloc_encap_mac_filt - Adds a mac entry in mps tcam with VNI support
+ * @adap: the adapter
+ * @viid: the VI id
+ * @mac: the MAC address
+ * @mask: the mask
+ * @vni: the VNI id for the tunnel protocol
+ * @vni_mask: mask for the VNI id
+ * @dip_hit: to enable DIP match for the MPS entry
+ * @lookup_type: MAC address for inner (1) or outer (0) header
+ * @sleep_ok: call is allowed to sleep
+ *
+ * Allocates an MPS entry with specified MAC address and VNI value.
+ *
+ * Returns a negative error number or the allocated index for this mac.
+ */
+int t4_alloc_encap_mac_filt(struct adapter *adap, unsigned int viid,
+ const u8 *addr, const u8 *mask, unsigned int vni,
+ unsigned int vni_mask, u8 dip_hit, u8 lookup_type,
+ bool sleep_ok)
+{
+ struct fw_vi_mac_cmd c;
+ struct fw_vi_mac_vni *p = c.u.exact_vni;
+ int ret = 0;
+ u32 val;
+
+ memset(&c, 0, sizeof(c));
+ c.op_to_viid = cpu_to_be32(FW_CMD_OP_V(FW_VI_MAC_CMD) |
+ FW_CMD_REQUEST_F | FW_CMD_WRITE_F |
+ FW_VI_MAC_CMD_VIID_V(viid));
+ val = FW_CMD_LEN16_V(1) |
+ FW_VI_MAC_CMD_ENTRY_TYPE_V(FW_VI_MAC_TYPE_EXACTMAC_VNI);
+ c.freemacs_to_len16 = cpu_to_be32(val);
+ p->valid_to_idx = cpu_to_be16(FW_VI_MAC_CMD_VALID_F |
+ FW_VI_MAC_CMD_IDX_V(FW_VI_MAC_ADD_MAC));
+ memcpy(p->macaddr, addr, sizeof(p->macaddr));
+ memcpy(p->macaddr_mask, mask, sizeof(p->macaddr_mask));
+
+ p->lookup_type_to_vni =
+ cpu_to_be32(FW_VI_MAC_CMD_VNI_V(vni) |
+ FW_VI_MAC_CMD_DIP_HIT_V(dip_hit) |
+ FW_VI_MAC_CMD_LOOKUP_TYPE_V(lookup_type));
+ p->vni_mask_pkd = cpu_to_be32(FW_VI_MAC_CMD_VNI_MASK_V(vni_mask));
+ ret = t4_wr_mbox_meat(adap, adap->mbox, &c, sizeof(c), &c, sleep_ok);
+ if (ret == 0)
+ ret = FW_VI_MAC_CMD_IDX_G(be16_to_cpu(p->valid_to_idx));
+ return ret;
+}
+
+/**
* t4_alloc_raw_mac_filt - Adds a mac entry in mps tcam
* @adap: the adapter
* @viid: the VI id
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index 276fdf2..843f8ca 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -1598,6 +1598,10 @@
#define VNIC_V(x) ((x) << VNIC_S)
#define VNIC_F VNIC_V(1U)
+#define USE_ENC_IDX_S 13
+#define USE_ENC_IDX_V(x) ((x) << USE_ENC_IDX_S)
+#define USE_ENC_IDX_F USE_ENC_IDX_V(1U)
+
#define CSUM_HAS_PSEUDO_HDR_S 10
#define CSUM_HAS_PSEUDO_HDR_V(x) ((x) << CSUM_HAS_PSEUDO_HDR_S)
#define CSUM_HAS_PSEUDO_HDR_F CSUM_HAS_PSEUDO_HDR_V(1U)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
index 0e007ee..e6b2e95 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
@@ -2158,6 +2158,14 @@ struct fw_vi_mac_cmd {
__be64 data0m_pkd;
__be32 data1m[2];
} raw;
+ struct fw_vi_mac_vni {
+ __be16 valid_to_idx;
+ __u8 macaddr[6];
+ __be16 r7;
+ __u8 macaddr_mask[6];
+ __be32 lookup_type_to_vni;
+ __be32 vni_mask_pkd;
+ } exact_vni[2];
} u;
};
@@ -2205,6 +2213,32 @@ struct fw_vi_mac_cmd {
#define FW_VI_MAC_CMD_RAW_IDX_G(x) \
(((x) >> FW_VI_MAC_CMD_RAW_IDX_S) & FW_VI_MAC_CMD_RAW_IDX_M)
+#define FW_VI_MAC_CMD_LOOKUP_TYPE_S 31
+#define FW_VI_MAC_CMD_LOOKUP_TYPE_M 0x1
+#define FW_VI_MAC_CMD_LOOKUP_TYPE_V(x) ((x) << FW_VI_MAC_CMD_LOOKUP_TYPE_S)
+#define FW_VI_MAC_CMD_LOOKUP_TYPE_G(x) \
+ (((x) >> FW_VI_MAC_CMD_LOOKUP_TYPE_S) & FW_VI_MAC_CMD_LOOKUP_TYPE_M)
+#define FW_VI_MAC_CMD_LOOKUP_TYPE_F FW_VI_MAC_CMD_LOOKUP_TYPE_V(1U)
+
+#define FW_VI_MAC_CMD_DIP_HIT_S 30
+#define FW_VI_MAC_CMD_DIP_HIT_M 0x1
+#define FW_VI_MAC_CMD_DIP_HIT_V(x) ((x) << FW_VI_MAC_CMD_DIP_HIT_S)
+#define FW_VI_MAC_CMD_DIP_HIT_G(x) \
+ (((x) >> FW_VI_MAC_CMD_DIP_HIT_S) & FW_VI_MAC_CMD_DIP_HIT_M)
+#define FW_VI_MAC_CMD_DIP_HIT_F FW_VI_MAC_CMD_DIP_HIT_V(1U)
+
+#define FW_VI_MAC_CMD_VNI_S 0
+#define FW_VI_MAC_CMD_VNI_M 0xffffff
+#define FW_VI_MAC_CMD_VNI_V(x) ((x) << FW_VI_MAC_CMD_VNI_S)
+#define FW_VI_MAC_CMD_VNI_G(x) \
+ (((x) >> FW_VI_MAC_CMD_VNI_S) & FW_VI_MAC_CMD_VNI_M)
+
+#define FW_VI_MAC_CMD_VNI_MASK_S 0
+#define FW_VI_MAC_CMD_VNI_MASK_M 0xffffff
+#define FW_VI_MAC_CMD_VNI_MASK_V(x) ((x) << FW_VI_MAC_CMD_VNI_MASK_S)
+#define FW_VI_MAC_CMD_VNI_MASK_G(x) \
+ (((x) >> FW_VI_MAC_CMD_VNI_MASK_S) & FW_VI_MAC_CMD_VNI_MASK_M)
+
#define FW_RXMODE_MTU_NO_CHG 65535
struct fw_vi_rxmode_cmd {
--
2.1.0
^ permalink raw reply related
* [PATCH net 1/2] vmxnet3: set the DMA mask before the first DMA map operation
From: hpreg @ 2018-05-14 12:28 UTC (permalink / raw)
To: netdev; +Cc: Regis Duchesne, Ronak Doshi, VMware, Inc., open list
The DMA mask must be set before, not after, the first DMA map operation, or
the first DMA map operation could in theory fail on some systems.
Fixes: b0eb57cb97e78 ("VMXNET3: Add support for virtual IOMMU")
Signed-off-by: Regis Duchesne <hpreg@vmware.com>
Acked-by: Ronak Doshi <doshir@vmware.com>
---
drivers/net/vmxnet3/vmxnet3_drv.c | 50 +++++++++++++++++++--------------------
drivers/net/vmxnet3/vmxnet3_int.h | 8 ++++---
2 files changed, 30 insertions(+), 28 deletions(-)
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 9ebe2a6..ed58685 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -2688,7 +2688,7 @@ vmxnet3_set_mac_addr(struct net_device *netdev, void *p)
/* ==================== initialization and cleanup routines ============ */
static int
-vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter, bool *dma64)
+vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter)
{
int err;
unsigned long mmio_start, mmio_len;
@@ -2700,30 +2700,12 @@ vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter, bool *dma64)
return err;
}
- if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) == 0) {
- if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)) != 0) {
- dev_err(&pdev->dev,
- "pci_set_consistent_dma_mask failed\n");
- err = -EIO;
- goto err_set_mask;
- }
- *dma64 = true;
- } else {
- if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) != 0) {
- dev_err(&pdev->dev,
- "pci_set_dma_mask failed\n");
- err = -EIO;
- goto err_set_mask;
- }
- *dma64 = false;
- }
-
err = pci_request_selected_regions(pdev, (1 << 2) - 1,
vmxnet3_driver_name);
if (err) {
dev_err(&pdev->dev,
"Failed to request region for adapter: error %d\n", err);
- goto err_set_mask;
+ goto err_enable_device;
}
pci_set_master(pdev);
@@ -2751,7 +2733,7 @@ vmxnet3_alloc_pci_resources(struct vmxnet3_adapter *adapter, bool *dma64)
iounmap(adapter->hw_addr0);
err_ioremap:
pci_release_selected_regions(pdev, (1 << 2) - 1);
-err_set_mask:
+err_enable_device:
pci_disable_device(pdev);
return err;
}
@@ -3254,7 +3236,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
#endif
};
int err;
- bool dma64 = false; /* stupid gcc */
+ bool dma64;
u32 ver;
struct net_device *netdev;
struct vmxnet3_adapter *adapter;
@@ -3300,6 +3282,24 @@ vmxnet3_probe_device(struct pci_dev *pdev,
adapter->rx_ring_size = VMXNET3_DEF_RX_RING_SIZE;
adapter->rx_ring2_size = VMXNET3_DEF_RX_RING2_SIZE;
+ if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) == 0) {
+ if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)) != 0) {
+ dev_err(&pdev->dev,
+ "pci_set_consistent_dma_mask failed\n");
+ err = -EIO;
+ goto err_set_mask;
+ }
+ dma64 = true;
+ } else {
+ if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32)) != 0) {
+ dev_err(&pdev->dev,
+ "pci_set_dma_mask failed\n");
+ err = -EIO;
+ goto err_set_mask;
+ }
+ dma64 = false;
+ }
+
spin_lock_init(&adapter->cmd_lock);
adapter->adapter_pa = dma_map_single(&adapter->pdev->dev, adapter,
sizeof(struct vmxnet3_adapter),
@@ -3307,7 +3307,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
if (dma_mapping_error(&adapter->pdev->dev, adapter->adapter_pa)) {
dev_err(&pdev->dev, "Failed to map dma\n");
err = -EFAULT;
- goto err_dma_map;
+ goto err_set_mask;
}
adapter->shared = dma_alloc_coherent(
&adapter->pdev->dev,
@@ -3358,7 +3358,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
}
#endif /* VMXNET3_RSS */
- err = vmxnet3_alloc_pci_resources(adapter, &dma64);
+ err = vmxnet3_alloc_pci_resources(adapter);
if (err < 0)
goto err_alloc_pci;
@@ -3504,7 +3504,7 @@ vmxnet3_probe_device(struct pci_dev *pdev,
err_alloc_shared:
dma_unmap_single(&adapter->pdev->dev, adapter->adapter_pa,
sizeof(struct vmxnet3_adapter), PCI_DMA_TODEVICE);
-err_dma_map:
+err_set_mask:
free_netdev(netdev);
return err;
}
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index a332646..b379bed 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -69,10 +69,12 @@
/*
* Version numbers
*/
-#define VMXNET3_DRIVER_VERSION_STRING "1.4.14.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING "1.4.15.0-k"
-/* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */
-#define VMXNET3_DRIVER_VERSION_NUM 0x01040e00
+/* Each byte of this 32-bit integer encodes a version number in
+ * VMXNET3_DRIVER_VERSION_STRING.
+ */
+#define VMXNET3_DRIVER_VERSION_NUM 0x01040f00
#if defined(CONFIG_PCI_MSI)
/* RSS only makes sense if MSI-X is supported. */
--
2.7.4
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox