aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/dev-tools/kselftest.rst8
-rw-r--r--Documentation/devicetree/bindings/net/qcom,ipa.yaml6
-rw-r--r--Documentation/filesystems/netfs_library.rst16
-rw-r--r--MAINTAINERS3
-rw-r--r--drivers/net/dsa/Kconfig1
-rw-r--r--drivers/net/ethernet/amd/xgbe/xgbe-drv.c14
-rw-r--r--drivers/net/ethernet/google/gve/gve_adminq.c2
-rw-r--r--drivers/net/ethernet/intel/e1000e/e1000.h4
-rw-r--r--drivers/net/ethernet/intel/e1000e/ich8lan.c20
-rw-r--r--drivers/net/ethernet/intel/e1000e/netdev.c39
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e.h1
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_main.c31
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en.h6
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/qos.c3
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c32
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c6
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h5
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c4
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c13
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h9
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_rx.c30
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_tc.c15
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_tx.c2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c4
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c9
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/port.c9
-rw-r--r--drivers/net/ethernet/microchip/sparx5/sparx5_packet.c2
-rw-r--r--drivers/net/ethernet/smsc/smc911x.c8
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c9
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h1
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c19
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c19
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/stmmac_main.c6
-rw-r--r--drivers/net/ieee802154/at86rf230.c13
-rw-r--r--drivers/net/ieee802154/ca8210.c1
-rw-r--r--drivers/net/ieee802154/mac802154_hwsim.c1
-rw-r--r--drivers/net/ieee802154/mcr20a.c4
-rw-r--r--drivers/net/ipa/ipa_power.c52
-rw-r--r--drivers/net/ipa/ipa_power.h7
-rw-r--r--drivers/net/ipa/ipa_uc.c5
-rw-r--r--drivers/net/macsec.c33
-rw-r--r--drivers/net/phy/at803x.c26
-rw-r--r--drivers/net/usb/ipheth.c6
-rw-r--r--fs/9p/fid.c9
-rw-r--r--fs/cachefiles/io.c59
-rw-r--r--fs/cifs/connect.c23
-rw-r--r--fs/cifs/file.c221
-rw-r--r--fs/cifs/fscache.c126
-rw-r--r--fs/cifs/fscache.h79
-rw-r--r--fs/cifs/inode.c8
-rw-r--r--fs/cifs/sess.c6
-rw-r--r--include/linux/ceph/libceph.h1
-rw-r--r--include/linux/ceph/messenger.h5
-rw-r--r--include/linux/if_vlan.h6
-rw-r--r--include/linux/netfs.h7
-rw-r--r--include/net/ax25.h12
-rw-r--r--include/net/neighbour.h18
-rw-r--r--include/uapi/linux/smc_diag.h11
-rw-r--r--kernel/bpf/bpf_lsm.c2
-rw-r--r--kernel/bpf/ringbuf.c2
-rw-r--r--kernel/bpf/trampoline.c5
-rw-r--r--kernel/stackleak.c5
-rw-r--r--net/ax25/af_ax25.c23
-rw-r--r--net/ax25/ax25_dev.c28
-rw-r--r--net/ax25/ax25_route.c13
-rw-r--r--net/bridge/netfilter/nft_reject_bridge.c8
-rw-r--r--net/ceph/ceph_common.c7
-rw-r--r--net/ceph/messenger.c4
-rw-r--r--net/ceph/messenger_v1.c54
-rw-r--r--net/ceph/messenger_v2.c250
-rw-r--r--net/core/neighbour.c18
-rw-r--r--net/core/rtnetlink.c6
-rw-r--r--net/ieee802154/nl802154.c8
-rw-r--r--net/ipv4/netfilter/Kconfig4
-rw-r--r--net/ipv4/tcp.c7
-rw-r--r--net/ipv4/tcp_input.c2
-rw-r--r--net/ipv6/netfilter/Kconfig4
-rw-r--r--net/ipv6/netfilter/Makefile3
-rw-r--r--net/ipv6/netfilter/nf_flow_table_ipv6.c0
-rw-r--r--net/netfilter/nf_tables_api.c1
-rw-r--r--net/netfilter/nft_byteorder.c12
-rw-r--r--net/netfilter/nft_ct.c5
-rw-r--r--net/packet/af_packet.c8
-rw-r--r--net/sched/cls_api.c11
-rw-r--r--net/smc/af_smc.c133
-rw-r--r--net/smc/smc.h20
-rw-r--r--net/smc/smc_diag.c2
-rw-r--r--security/selinux/ss/conditional.c3
-rw-r--r--tools/bpf/resolve_btfids/Makefile6
-rw-r--r--tools/include/uapi/linux/lirc.h229
-rw-r--r--tools/scripts/Makefile.include2
-rw-r--r--tools/testing/selftests/bpf/test_lirc_mode2_user.c1
-rwxr-xr-xtools/testing/selftests/cpufreq/main.sh2
-rw-r--r--tools/testing/selftests/exec/Makefile2
-rw-r--r--tools/testing/selftests/futex/Makefile4
-rw-r--r--tools/testing/selftests/kselftest_harness.h4
-rw-r--r--tools/testing/selftests/mincore/mincore_selftest.c20
-rwxr-xr-xtools/testing/selftests/netfilter/nft_concat_range.sh72
-rwxr-xr-xtools/testing/selftests/netfilter/nft_nat.sh152
-rwxr-xr-xtools/testing/selftests/netfilter/nft_zones_many.sh12
-rw-r--r--tools/testing/selftests/openat2/Makefile2
-rw-r--r--tools/testing/selftests/openat2/helpers.h12
-rw-r--r--tools/testing/selftests/openat2/openat2_test.c12
-rw-r--r--tools/testing/selftests/rtc/settings2
-rw-r--r--tools/testing/selftests/vDSO/vdso_test_abi.c135
-rwxr-xr-xtools/testing/selftests/zram/zram.sh15
-rwxr-xr-xtools/testing/selftests/zram/zram01.sh33
-rwxr-xr-xtools/testing/selftests/zram/zram02.sh1
-rwxr-xr-xtools/testing/selftests/zram/zram_lib.sh134
111 files changed, 1691 insertions, 908 deletions
diff --git a/Documentation/dev-tools/kselftest.rst b/Documentation/dev-tools/kselftest.rst
index dcefee707ccd..a833ecf12fbc 100644
--- a/Documentation/dev-tools/kselftest.rst
+++ b/Documentation/dev-tools/kselftest.rst
@@ -7,6 +7,14 @@ directory. These are intended to be small tests to exercise individual code
paths in the kernel. Tests are intended to be run after building, installing
and booting a kernel.
+Kselftest from mainline can be run on older stable kernels. Running tests
+from mainline offers the best coverage. Several test rings run mainline
+kselftest suite on stable releases. The reason is that when a new test
+gets added to test existing code to regression test a bug, we should be
+able to run that test on an older kernel. Hence, it is important to keep
+code that can still test an older kernel and make sure it skips the test
+gracefully on newer releases.
+
You can find additional information on Kselftest framework, how to
write new tests using the framework on Kselftest wiki:
diff --git a/Documentation/devicetree/bindings/net/qcom,ipa.yaml b/Documentation/devicetree/bindings/net/qcom,ipa.yaml
index b86edf67ce62..58ecc62adfaa 100644
--- a/Documentation/devicetree/bindings/net/qcom,ipa.yaml
+++ b/Documentation/devicetree/bindings/net/qcom,ipa.yaml
@@ -107,6 +107,10 @@ properties:
- const: imem
- const: config
+ qcom,qmp:
+ $ref: /schemas/types.yaml#/definitions/phandle
+ description: phandle to the AOSS side-channel message RAM
+
qcom,smem-states:
$ref: /schemas/types.yaml#/definitions/phandle-array
description: State bits used in by the AP to signal the modem.
@@ -222,6 +226,8 @@ examples:
"imem",
"config";
+ qcom,qmp = <&aoss_qmp>;
+
qcom,smem-states = <&ipa_smp2p_out 0>,
<&ipa_smp2p_out 1>;
qcom,smem-state-names = "ipa-clock-enabled-valid",
diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst
index 136f8da3d0e2..4f373a8ec47b 100644
--- a/Documentation/filesystems/netfs_library.rst
+++ b/Documentation/filesystems/netfs_library.rst
@@ -462,6 +462,10 @@ operation table looks like the following::
struct iov_iter *iter,
netfs_io_terminated_t term_func,
void *term_func_priv);
+
+ int (*query_occupancy)(struct netfs_cache_resources *cres,
+ loff_t start, size_t len, size_t granularity,
+ loff_t *_data_start, size_t *_data_len);
};
With a termination handler function pointer::
@@ -536,6 +540,18 @@ The methods defined in the table are:
indicating whether the termination is definitely happening in the caller's
context.
+ * ``query_occupancy()``
+
+ [Required] Called to find out where the next piece of data is within a
+ particular region of the cache. The start and length of the region to be
+ queried are passed in, along with the granularity to which the answer needs
+ to be aligned. The function passes back the start and length of the data,
+ if any, available within that region. Note that there may be a hole at the
+ front.
+
+ It returns 0 if some data was found, -ENODATA if there was no usable data
+ within the region or -ENOBUFS if there is no caching on this file.
+
Note that these methods are passed a pointer to the cache resource structure,
not the read request structure as they could be used in other situations where
there isn't a read request structure as well, such as writing dirty data to the
diff --git a/MAINTAINERS b/MAINTAINERS
index c820e03c4414..ce6dff39fc14 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4157,9 +4157,8 @@ N: csky
K: csky
CA8210 IEEE-802.15.4 RADIO DRIVER
-M: Harry Morris <[email protected]>
-S: Maintained
+S: Orphan
W: https://github.com/Cascoda/ca8210-linux.git
F: Documentation/devicetree/bindings/net/ieee802154/ca8210.txt
F: drivers/net/ieee802154/ca8210.c
diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig
index 7b1457a6e327..c0c91440340a 100644
--- a/drivers/net/dsa/Kconfig
+++ b/drivers/net/dsa/Kconfig
@@ -36,6 +36,7 @@ config NET_DSA_LANTIQ_GSWIP
config NET_DSA_MT7530
tristate "MediaTek MT753x and MT7621 Ethernet switch support"
select NET_DSA_TAG_MTK
+ select MEDIATEK_GE_PHY
help
This enables support for the MediaTek MT7530, MT7531, and MT7621
Ethernet switch chips.
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 492ac383f16d..a3593290886f 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -721,7 +721,9 @@ static void xgbe_stop_timers(struct xgbe_prv_data *pdata)
if (!channel->tx_ring)
break;
+ /* Deactivate the Tx timer */
del_timer_sync(&channel->tx_timer);
+ channel->tx_timer_active = 0;
}
}
@@ -2550,6 +2552,14 @@ read_again:
buf2_len = xgbe_rx_buf2_len(rdata, packet, len);
len += buf2_len;
+ if (buf2_len > rdata->rx.buf.dma_len) {
+ /* Hardware inconsistency within the descriptors
+ * that has resulted in a length underflow.
+ */
+ error = 1;
+ goto skip_data;
+ }
+
if (!skb) {
skb = xgbe_create_skb(pdata, napi, rdata,
buf1_len);
@@ -2579,8 +2589,10 @@ skip_data:
if (!last || context_next)
goto read_again;
- if (!skb)
+ if (!skb || error) {
+ dev_kfree_skb(skb);
goto next_packet;
+ }
/* Be sure we don't exceed the configured MTU */
max_len = netdev->mtu + ETH_HLEN;
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c
index 2ad7f57f7e5b..f7621ab672b9 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.c
+++ b/drivers/net/ethernet/google/gve/gve_adminq.c
@@ -301,7 +301,7 @@ static int gve_adminq_parse_err(struct gve_priv *priv, u32 status)
*/
static int gve_adminq_kick_and_wait(struct gve_priv *priv)
{
- u32 tail, head;
+ int tail, head;
int i;
tail = ioread32be(&priv->reg_bar0->adminq_event_counter);
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index c3def0ee7788..8d06c9d8ff8b 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -115,7 +115,8 @@ enum e1000_boards {
board_pch_lpt,
board_pch_spt,
board_pch_cnp,
- board_pch_tgp
+ board_pch_tgp,
+ board_pch_adp
};
struct e1000_ps_page {
@@ -502,6 +503,7 @@ extern const struct e1000_info e1000_pch_lpt_info;
extern const struct e1000_info e1000_pch_spt_info;
extern const struct e1000_info e1000_pch_cnp_info;
extern const struct e1000_info e1000_pch_tgp_info;
+extern const struct e1000_info e1000_pch_adp_info;
extern const struct e1000_info e1000_es2_info;
void e1000e_ptp_init(struct e1000_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index 5e4fc9b4e2ad..c908c84b86d2 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -6021,3 +6021,23 @@ const struct e1000_info e1000_pch_tgp_info = {
.phy_ops = &ich8_phy_ops,
.nvm_ops = &spt_nvm_ops,
};
+
+const struct e1000_info e1000_pch_adp_info = {
+ .mac = e1000_pch_adp,
+ .flags = FLAG_IS_ICH
+ | FLAG_HAS_WOL
+ | FLAG_HAS_HW_TIMESTAMP
+ | FLAG_HAS_CTRLEXT_ON_LOAD
+ | FLAG_HAS_AMT
+ | FLAG_HAS_FLASH
+ | FLAG_HAS_JUMBO_FRAMES
+ | FLAG_APME_IN_WUC,
+ .flags2 = FLAG2_HAS_PHY_STATS
+ | FLAG2_HAS_EEE,
+ .pba = 26,
+ .max_hw_frame_size = 9022,
+ .get_variants = e1000_get_variants_ich8lan,
+ .mac_ops = &ich8_mac_ops,
+ .phy_ops = &ich8_phy_ops,
+ .nvm_ops = &spt_nvm_ops,
+};
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 635a95927e93..a42aeb555f34 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -52,6 +52,7 @@ static const struct e1000_info *e1000_info_tbl[] = {
[board_pch_spt] = &e1000_pch_spt_info,
[board_pch_cnp] = &e1000_pch_cnp_info,
[board_pch_tgp] = &e1000_pch_tgp_info,
+ [board_pch_adp] = &e1000_pch_adp_info,
};
struct e1000_reg_info {
@@ -6341,7 +6342,8 @@ static void e1000e_s0ix_entry_flow(struct e1000_adapter *adapter)
u32 mac_data;
u16 phy_data;
- if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID) {
+ if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID &&
+ hw->mac.type >= e1000_pch_adp) {
/* Request ME configure the device for S0ix */
mac_data = er32(H2ME);
mac_data |= E1000_H2ME_START_DPG;
@@ -6490,7 +6492,8 @@ static void e1000e_s0ix_exit_flow(struct e1000_adapter *adapter)
u16 phy_data;
u32 i = 0;
- if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID) {
+ if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID &&
+ hw->mac.type >= e1000_pch_adp) {
/* Request ME unconfigure the device from S0ix */
mac_data = er32(H2ME);
mac_data &= ~E1000_H2ME_START_DPG;
@@ -7898,22 +7901,22 @@ static const struct pci_device_id e1000_pci_tbl[] = {
{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V14), board_pch_tgp },
{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM15), board_pch_tgp },
{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V15), board_pch_tgp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM23), board_pch_tgp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V23), board_pch_tgp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM16), board_pch_tgp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V16), board_pch_tgp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM17), board_pch_tgp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V17), board_pch_tgp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM22), board_pch_tgp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V22), board_pch_tgp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM18), board_pch_tgp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V18), board_pch_tgp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM19), board_pch_tgp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V19), board_pch_tgp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM20), board_pch_tgp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V20), board_pch_tgp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM21), board_pch_tgp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM23), board_pch_adp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V23), board_pch_adp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM16), board_pch_adp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V16), board_pch_adp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM17), board_pch_adp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V17), board_pch_adp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM22), board_pch_adp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V22), board_pch_adp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM18), board_pch_adp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V18), board_pch_adp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM19), board_pch_adp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V19), board_pch_adp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM20), board_pch_adp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V20), board_pch_adp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM21), board_pch_adp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_adp },
{ 0, 0, 0, 0, 0, 0, 0 } /* terminate list */
};
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 2e02cc68cd3f..80c5cecaf2b5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -144,6 +144,7 @@ enum i40e_state_t {
__I40E_VIRTCHNL_OP_PENDING,
__I40E_RECOVERY_MODE,
__I40E_VF_RESETS_DISABLED, /* disable resets during i40e_remove */
+ __I40E_IN_REMOVE,
__I40E_VFS_RELEASING,
/* This must be last as it determines the size of the BITMAP */
__I40E_STATE_SIZE__,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index f70c478dafdb..0c4b7dfb3b35 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -5372,7 +5372,15 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc,
/* There is no need to reset BW when mqprio mode is on. */
if (pf->flags & I40E_FLAG_TC_MQPRIO)
return 0;
- if (!vsi->mqprio_qopt.qopt.hw && !(pf->flags & I40E_FLAG_DCB_ENABLED)) {
+
+ if (!vsi->mqprio_qopt.qopt.hw) {
+ if (pf->flags & I40E_FLAG_DCB_ENABLED)
+ goto skip_reset;
+
+ if (IS_ENABLED(CONFIG_I40E_DCB) &&
+ i40e_dcb_hw_get_num_tc(&pf->hw) == 1)
+ goto skip_reset;
+
ret = i40e_set_bw_limit(vsi, vsi->seid, 0);
if (ret)
dev_info(&pf->pdev->dev,
@@ -5380,6 +5388,8 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc,
vsi->seid);
return ret;
}
+
+skip_reset:
memset(&bw_data, 0, sizeof(bw_data));
bw_data.tc_valid_bits = enabled_tc;
for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++)
@@ -10853,6 +10863,9 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit,
bool lock_acquired)
{
int ret;
+
+ if (test_bit(__I40E_IN_REMOVE, pf->state))
+ return;
/* Now we wait for GRST to settle out.
* We don't have to delete the VEBs or VSIs from the hw switch
* because the reset will make them disappear.
@@ -12212,6 +12225,8 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count)
vsi->req_queue_pairs = queue_count;
i40e_prep_for_reset(pf);
+ if (test_bit(__I40E_IN_REMOVE, pf->state))
+ return pf->alloc_rss_size;
pf->alloc_rss_size = new_rss_size;
@@ -13038,6 +13053,10 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog,
if (need_reset)
i40e_prep_for_reset(pf);
+ /* VSI shall be deleted in a moment, just return EINVAL */
+ if (test_bit(__I40E_IN_REMOVE, pf->state))
+ return -EINVAL;
+
old_prog = xchg(&vsi->xdp_prog, prog);
if (need_reset) {
@@ -15928,8 +15947,13 @@ static void i40e_remove(struct pci_dev *pdev)
i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), 0);
i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0);
- while (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
+ /* Grab __I40E_RESET_RECOVERY_PENDING and set __I40E_IN_REMOVE
+ * flags, once they are set, i40e_rebuild should not be called as
+ * i40e_prep_for_reset always returns early.
+ */
+ while (test_and_set_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
usleep_range(1000, 2000);
+ set_bit(__I40E_IN_REMOVE, pf->state);
if (pf->flags & I40E_FLAG_SRIOV_ENABLED) {
set_bit(__I40E_VF_RESETS_DISABLED, pf->state);
@@ -16128,6 +16152,9 @@ static void i40e_pci_error_reset_done(struct pci_dev *pdev)
{
struct i40e_pf *pf = pci_get_drvdata(pdev);
+ if (test_bit(__I40E_IN_REMOVE, pf->state))
+ return;
+
i40e_reset_and_rebuild(pf, false, false);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 812e6810cb3b..c14e06ca64d8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -224,7 +224,7 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev)
struct mlx5e_tx_wqe {
struct mlx5_wqe_ctrl_seg ctrl;
struct mlx5_wqe_eth_seg eth;
- struct mlx5_wqe_data_seg data[0];
+ struct mlx5_wqe_data_seg data[];
};
struct mlx5e_rx_wqe_ll {
@@ -241,8 +241,8 @@ struct mlx5e_umr_wqe {
struct mlx5_wqe_umr_ctrl_seg uctrl;
struct mlx5_mkey_seg mkc;
union {
- struct mlx5_mtt inline_mtts[0];
- struct mlx5_klm inline_klms[0];
+ DECLARE_FLEX_ARRAY(struct mlx5_mtt, inline_mtts);
+ DECLARE_FLEX_ARRAY(struct mlx5_klm, inline_klms);
};
};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
index 00449df98a5e..c1e07496c89c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
@@ -570,7 +570,8 @@ static int mlx5e_htb_convert_rate(struct mlx5e_priv *priv, u64 rate,
static void mlx5e_htb_convert_ceil(struct mlx5e_priv *priv, u64 ceil, u32 *max_average_bw)
{
- *max_average_bw = div_u64(ceil, BYTES_IN_MBIT);
+ /* Hardware treats 0 as "unlimited", set at least 1. */
+ *max_average_bw = max_t(u32, div_u64(ceil, BYTES_IN_MBIT), 1);
qos_dbg(priv->mdev, "Convert: ceil %llu -> max_average_bw %u\n",
ceil, *max_average_bw);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c
index 9c076aa20306..b6f5c1bcdbcd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c
@@ -183,18 +183,7 @@ void mlx5e_rep_bond_unslave(struct mlx5_eswitch *esw,
static bool mlx5e_rep_is_lag_netdev(struct net_device *netdev)
{
- struct mlx5e_rep_priv *rpriv;
- struct mlx5e_priv *priv;
-
- /* A given netdev is not a representor or not a slave of LAG configuration */
- if (!mlx5e_eswitch_rep(netdev) || !netif_is_lag_port(netdev))
- return false;
-
- priv = netdev_priv(netdev);
- rpriv = priv->ppriv;
-
- /* Egress acl forward to vport is supported only non-uplink representor */
- return rpriv->rep->vport != MLX5_VPORT_UPLINK;
+ return netif_is_lag_port(netdev) && mlx5e_eswitch_vf_rep(netdev);
}
static void mlx5e_rep_changelowerstate_event(struct net_device *netdev, void *ptr)
@@ -210,9 +199,6 @@ static void mlx5e_rep_changelowerstate_event(struct net_device *netdev, void *pt
u16 fwd_vport_num;
int err;
- if (!mlx5e_rep_is_lag_netdev(netdev))
- return;
-
info = ptr;
lag_info = info->lower_state_info;
/* This is not an event of a representor becoming active slave */
@@ -266,9 +252,6 @@ static void mlx5e_rep_changeupper_event(struct net_device *netdev, void *ptr)
struct net_device *lag_dev;
struct mlx5e_priv *priv;
- if (!mlx5e_rep_is_lag_netdev(netdev))
- return;
-
priv = netdev_priv(netdev);
rpriv = priv->ppriv;
lag_dev = info->upper_dev;
@@ -293,6 +276,19 @@ static int mlx5e_rep_esw_bond_netevent(struct notifier_block *nb,
unsigned long event, void *ptr)
{
struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+ struct mlx5e_rep_priv *rpriv;
+ struct mlx5e_rep_bond *bond;
+ struct mlx5e_priv *priv;
+
+ if (!mlx5e_rep_is_lag_netdev(netdev))
+ return NOTIFY_DONE;
+
+ bond = container_of(nb, struct mlx5e_rep_bond, nb);
+ priv = netdev_priv(netdev);
+ rpriv = mlx5_eswitch_get_uplink_priv(priv->mdev->priv.eswitch, REP_ETH);
+ /* Verify VF representor is on the same device of the bond handling the netevent. */
+ if (rpriv->uplink_priv.bond != bond)
+ return NOTIFY_DONE;
switch (event) {
case NETDEV_CHANGELOWERSTATE:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
index c6d2f8c78db7..48dc121b2cb4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
@@ -491,7 +491,7 @@ void mlx5e_rep_bridge_init(struct mlx5e_priv *priv)
}
br_offloads->netdev_nb.notifier_call = mlx5_esw_bridge_switchdev_port_event;
- err = register_netdevice_notifier(&br_offloads->netdev_nb);
+ err = register_netdevice_notifier_net(&init_net, &br_offloads->netdev_nb);
if (err) {
esw_warn(mdev, "Failed to register bridge offloads netdevice notifier (err=%d)\n",
err);
@@ -509,7 +509,9 @@ err_register_swdev_blk:
err_register_swdev:
destroy_workqueue(br_offloads->wq);
err_alloc_wq:
+ rtnl_lock();
mlx5_esw_bridge_cleanup(esw);
+ rtnl_unlock();
}
void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv)
@@ -524,7 +526,7 @@ void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv)
return;
cancel_delayed_work_sync(&br_offloads->update_work);
- unregister_netdevice_notifier(&br_offloads->netdev_nb);
+ unregister_netdevice_notifier_net(&init_net, &br_offloads->netdev_nb);
unregister_switchdev_blocking_notifier(&br_offloads->nb_blk);
unregister_switchdev_notifier(&br_offloads->nb);
destroy_workqueue(br_offloads->wq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 4cdf8e5b24c2..b789af07829c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -167,6 +167,11 @@ static inline u16 mlx5e_txqsq_get_next_pi(struct mlx5e_txqsq *sq, u16 size)
return pi;
}
+static inline u16 mlx5e_shampo_get_cqe_header_index(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
+{
+ return be16_to_cpu(cqe->shampo.header_entry_index) & (rq->mpwqe.shampo->hd_per_wq - 1);
+}
+
struct mlx5e_shampo_umr {
u16 len;
};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 338d65e2c9ce..56e10c84a706 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -341,8 +341,10 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
/* copy the inline part if required */
if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
- memcpy(eseg->inline_hdr.start, xdptxd->data, MLX5E_XDP_MIN_INLINE);
+ memcpy(eseg->inline_hdr.start, xdptxd->data, sizeof(eseg->inline_hdr.start));
eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE);
+ memcpy(dseg, xdptxd->data + sizeof(eseg->inline_hdr.start),
+ MLX5E_XDP_MIN_INLINE - sizeof(eseg->inline_hdr.start));
dma_len -= MLX5E_XDP_MIN_INLINE;
dma_addr += MLX5E_XDP_MIN_INLINE;
dseg++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index 2db9573a3fe6..b56fea142c24 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -157,11 +157,20 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb,
/* Tunnel mode */
if (mode == XFRM_MODE_TUNNEL) {
eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2;
- eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2;
if (xo->proto == IPPROTO_IPV6)
eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6;
- if (inner_ip_hdr(skb)->protocol == IPPROTO_UDP)
+
+ switch (xo->inner_ipproto) {
+ case IPPROTO_UDP:
eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP;
+ fallthrough;
+ case IPPROTO_TCP:
+ /* IP | ESP | IP | [TCP | UDP] */
+ eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2;
+ break;
+ default:
+ break;
+ }
return;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
index b98db50c3418..428881e0adcb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
@@ -131,14 +131,17 @@ static inline bool
mlx5e_ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb,
struct mlx5_wqe_eth_seg *eseg)
{
- struct xfrm_offload *xo = xfrm_offload(skb);
+ u8 inner_ipproto;
if (!mlx5e_ipsec_eseg_meta(eseg))
return false;
eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM;
- if (xo->inner_ipproto) {
- eseg->cs_flags |= MLX5_ETH_WQE_L4_INNER_CSUM | MLX5_ETH_WQE_L3_INNER_CSUM;
+ inner_ipproto = xfrm_offload(skb)->inner_ipproto;
+ if (inner_ipproto) {
+ eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM;
+ if (inner_ipproto == IPPROTO_TCP || inner_ipproto == IPPROTO_UDP)
+ eseg->cs_flags |= MLX5_ETH_WQE_L4_INNER_CSUM;
} else if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM;
sq->stats->csum_partial_inner++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index e86ccc22fb82..ee0a8f5206e3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1117,7 +1117,7 @@ static void mlx5e_shampo_update_ipv6_udp_hdr(struct mlx5e_rq *rq, struct ipv6hdr
static void mlx5e_shampo_update_fin_psh_flags(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
struct tcphdr *skb_tcp_hd)
{
- u16 header_index = be16_to_cpu(cqe->shampo.header_entry_index);
+ u16 header_index = mlx5e_shampo_get_cqe_header_index(rq, cqe);
struct tcphdr *last_tcp_hd;
void *last_hd_addr;
@@ -1871,7 +1871,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
return skb;
}
-static void
+static struct sk_buff *
mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
struct mlx5_cqe64 *cqe, u16 header_index)
{
@@ -1895,7 +1895,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
skb = mlx5e_build_linear_skb(rq, hdr, frag_size, rx_headroom, head_size);
if (unlikely(!skb))
- return;
+ return NULL;
/* queue up for recycling/reuse */
page_ref_inc(head->page);
@@ -1907,7 +1907,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
ALIGN(head_size, sizeof(long)));
if (unlikely(!skb)) {
rq->stats->buff_alloc_err++;
- return;
+ return NULL;
}
prefetchw(skb->data);
@@ -1918,9 +1918,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
skb->tail += head_size;
skb->len += head_size;
}
- rq->hw_gro_data->skb = skb;
- NAPI_GRO_CB(skb)->count = 1;
- skb_shinfo(skb)->gso_size = mpwrq_get_cqe_byte_cnt(cqe) - head_size;
+ return skb;
}
static void
@@ -1973,13 +1971,14 @@ mlx5e_free_rx_shampo_hd_entry(struct mlx5e_rq *rq, u16 header_index)
static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
{
u16 data_bcnt = mpwrq_get_cqe_byte_cnt(cqe) - cqe->shampo.header_size;
- u16 header_index = be16_to_cpu(cqe->shampo.header_entry_index);
+ u16 header_index = mlx5e_shampo_get_cqe_header_index(rq, cqe);
u32 wqe_offset = be32_to_cpu(cqe->shampo.data_offset);
u16 cstrides = mpwrq_get_cqe_consumed_strides(cqe);
u32 data_offset = wqe_offset & (PAGE_SIZE - 1);
u32 cqe_bcnt = mpwrq_get_cqe_byte_cnt(cqe);
u16 wqe_id = be16_to_cpu(cqe->wqe_id);
u32 page_idx = wqe_offset >> PAGE_SHIFT;
+ u16 head_size = cqe->shampo.header_size;
struct sk_buff **skb = &rq->hw_gro_data->skb;
bool flush = cqe->shampo.flush;
bool match = cqe->shampo.match;
@@ -2011,9 +2010,16 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq
}
if (!*skb) {
- mlx5e_skb_from_cqe_shampo(rq, wi, cqe, header_index);
+ if (likely(head_size))
+ *skb = mlx5e_skb_from_cqe_shampo(rq, wi, cqe, header_index);
+ else
+ *skb = mlx5e_skb_from_cqe_mpwrq_nonlinear(rq, wi, cqe_bcnt, data_offset,
+ page_idx);
if (unlikely(!*skb))
goto free_hd_entry;
+
+ NAPI_GRO_CB(*skb)->count = 1;
+ skb_shinfo(*skb)->gso_size = cqe_bcnt - head_size;
} else {
NAPI_GRO_CB(*skb)->count++;
if (NAPI_GRO_CB(*skb)->count == 2 &&
@@ -2027,8 +2033,10 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq
}
}
- di = &wi->umr.dma_info[page_idx];
- mlx5e_fill_skb_data(*skb, rq, di, data_bcnt, data_offset);
+ if (likely(head_size)) {
+ di = &wi->umr.dma_info[page_idx];
+ mlx5e_fill_skb_data(*skb, rq, di, data_bcnt, data_offset);
+ }
mlx5e_shampo_complete_rx_cqe(rq, cqe, cqe_bcnt, *skb);
if (flush)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 3d908a7e1406..2022fa4a9598 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1414,7 +1414,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
if (err)
goto err_out;
- if (!attr->chain && esw_attr->int_port) {
+ if (!attr->chain && esw_attr->int_port &&
+ attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
/* If decap route device is internal port, change the
* source vport value in reg_c0 back to uplink just in
* case the rule performs goto chain > 0. If we have a miss
@@ -3191,6 +3192,18 @@ actions_match_supported(struct mlx5e_priv *priv,
return false;
}
+ if (!(~actions &
+ (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) {
+ NL_SET_ERR_MSG_MOD(extack, "Rule cannot support forward+drop action");
+ return false;
+ }
+
+ if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR &&
+ actions & MLX5_FLOW_CONTEXT_ACTION_DROP) {
+ NL_SET_ERR_MSG_MOD(extack, "Drop with modify header action is not supported");
+ return false;
+ }
+
if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR &&
!modify_header_match_supported(priv, &parse_attr->spec, flow_action,
actions, ct_flow, ct_clear, extack))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 7fd33b356cc8..ee7ecb88adc1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -208,7 +208,7 @@ static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs)
int cpy1_sz = 2 * ETH_ALEN;
int cpy2_sz = ihs - cpy1_sz;
- memcpy(vhdr, skb->data, cpy1_sz);
+ memcpy(&vhdr->addrs, skb->data, cpy1_sz);
vhdr->h_vlan_proto = skb->vlan_proto;
vhdr->h_vlan_TCI = cpu_to_be16(skb_vlan_tag_get(skb));
memcpy(&vhdr->h_vlan_encapsulated_proto, skb->data + cpy1_sz, cpy2_sz);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
index f690f430f40f..05e08cec5a8c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
@@ -1574,6 +1574,8 @@ struct mlx5_esw_bridge_offloads *mlx5_esw_bridge_init(struct mlx5_eswitch *esw)
{
struct mlx5_esw_bridge_offloads *br_offloads;
+ ASSERT_RTNL();
+
br_offloads = kvzalloc(sizeof(*br_offloads), GFP_KERNEL);
if (!br_offloads)
return ERR_PTR(-ENOMEM);
@@ -1590,6 +1592,8 @@ void mlx5_esw_bridge_cleanup(struct mlx5_eswitch *esw)
{
struct mlx5_esw_bridge_offloads *br_offloads = esw->br_offloads;
+ ASSERT_RTNL();
+
if (!br_offloads)
return;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h
index 3401188e0a60..51ac24e6ec3c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h
@@ -21,7 +21,7 @@ DECLARE_EVENT_CLASS(mlx5_esw_bridge_fdb_template,
__field(unsigned int, used)
),
TP_fast_assign(
- strncpy(__entry->dev_name,
+ strscpy(__entry->dev_name,
netdev_name(fdb->dev),
IFNAMSIZ);
memcpy(__entry->addr, fdb->key.addr, ETH_ALEN);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index 0b0234f9d694..84dbe46d5ede 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -132,7 +132,7 @@ static void mlx5_stop_sync_reset_poll(struct mlx5_core_dev *dev)
{
struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
- del_timer(&fw_reset->timer);
+ del_timer_sync(&fw_reset->timer);
}
static void mlx5_sync_reset_clear_reset_requested(struct mlx5_core_dev *dev, bool poll_health)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
index d5e47630e284..df58cba37930 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
@@ -121,12 +121,13 @@ u32 mlx5_chains_get_nf_ft_chain(struct mlx5_fs_chains *chains)
u32 mlx5_chains_get_prio_range(struct mlx5_fs_chains *chains)
{
- if (!mlx5_chains_prios_supported(chains))
- return 1;
-
if (mlx5_chains_ignore_flow_level_supported(chains))
return UINT_MAX;
+ if (!chains->dev->priv.eswitch ||
+ chains->dev->priv.eswitch->mode != MLX5_ESWITCH_OFFLOADS)
+ return 1;
+
/* We should get here only for eswitch case */
return FDB_TC_MAX_PRIO;
}
@@ -211,7 +212,7 @@ static int
create_chain_restore(struct fs_chain *chain)
{
struct mlx5_eswitch *esw = chain->chains->dev->priv.eswitch;
- char modact[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)];
+ u8 modact[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
struct mlx5_fs_chains *chains = chain->chains;
enum mlx5e_tc_attr_to_reg chain_to_reg;
struct mlx5_modify_hdr *mod_hdr;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 1ef2b6a848c1..7b16a1188aab 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -406,23 +406,24 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
switch (module_id) {
case MLX5_MODULE_ID_SFP:
- mlx5_sfp_eeprom_params_set(&query.i2c_address, &query.page, &query.offset);
+ mlx5_sfp_eeprom_params_set(&query.i2c_address, &query.page, &offset);
break;
case MLX5_MODULE_ID_QSFP:
case MLX5_MODULE_ID_QSFP_PLUS:
case MLX5_MODULE_ID_QSFP28:
- mlx5_qsfp_eeprom_params_set(&query.i2c_address, &query.page, &query.offset);
+ mlx5_qsfp_eeprom_params_set(&query.i2c_address, &query.page, &offset);
break;
default:
mlx5_core_err(dev, "Module ID not recognized: 0x%x\n", module_id);
return -EINVAL;
}
- if (query.offset + size > MLX5_EEPROM_PAGE_LENGTH)
+ if (offset + size > MLX5_EEPROM_PAGE_LENGTH)
/* Cross pages read, read until offset 256 in low page */
- size -= offset + size - MLX5_EEPROM_PAGE_LENGTH;
+ size = MLX5_EEPROM_PAGE_LENGTH - offset;
query.size = size;
+ query.offset = offset;
return mlx5_query_mcia(dev, &query, data);
}
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
index dc7e5ea6ec15..148d431fcde4 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c
@@ -145,9 +145,9 @@ static void sparx5_xtr_grp(struct sparx5 *sparx5, u8 grp, bool byte_swap)
skb_put(skb, byte_cnt - ETH_FCS_LEN);
eth_skb_pad(skb);
skb->protocol = eth_type_trans(skb, netdev);
- netif_rx(skb);
netdev->stats.rx_bytes += skb->len;
netdev->stats.rx_packets++;
+ netif_rx(skb);
}
static int sparx5_inject(struct sparx5 *sparx5,
diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c
index dd6f69ced4ee..fc9cef9dcefc 100644
--- a/drivers/net/ethernet/smsc/smc911x.c
+++ b/drivers/net/ethernet/smsc/smc911x.c
@@ -1648,7 +1648,7 @@ static int smc911x_ethtool_geteeprom(struct net_device *dev,
return ret;
if ((ret=smc911x_ethtool_read_eeprom_byte(dev, &eebuf[i]))!=0)
return ret;
- }
+ }
memcpy(data, eebuf+eeprom->offset, eeprom->len);
return 0;
}
@@ -1667,11 +1667,11 @@ static int smc911x_ethtool_seteeprom(struct net_device *dev,
return ret;
/* write byte */
if ((ret=smc911x_ethtool_write_eeprom_byte(dev, *data))!=0)
- return ret;
+ return ret;
if ((ret=smc911x_ethtool_write_eeprom_cmd(dev, E2P_CMD_EPC_CMD_WRITE_, i ))!=0)
return ret;
- }
- return 0;
+ }
+ return 0;
}
static int smc911x_ethtool_geteeprom_len(struct net_device *dev)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
index dde5b772a5af..c3f10a92b62b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
@@ -49,13 +49,15 @@ struct visconti_eth {
void __iomem *reg;
u32 phy_intf_sel;
struct clk *phy_ref_clk;
+ struct device *dev;
spinlock_t lock; /* lock to protect register update */
};
static void visconti_eth_fix_mac_speed(void *priv, unsigned int speed)
{
struct visconti_eth *dwmac = priv;
- unsigned int val, clk_sel_val;
+ struct net_device *netdev = dev_get_drvdata(dwmac->dev);
+ unsigned int val, clk_sel_val = 0;
unsigned long flags;
spin_lock_irqsave(&dwmac->lock, flags);
@@ -85,7 +87,9 @@ static void visconti_eth_fix_mac_speed(void *priv, unsigned int speed)
break;
default:
/* No bit control */
- break;
+ netdev_err(netdev, "Unsupported speed request (%d)", speed);
+ spin_unlock_irqrestore(&dwmac->lock, flags);
+ return;
}
writel(val, dwmac->reg + MAC_CTRL_REG);
@@ -229,6 +233,7 @@ static int visconti_eth_dwmac_probe(struct platform_device *pdev)
spin_lock_init(&dwmac->lock);
dwmac->reg = stmmac_res.addr;
+ dwmac->dev = &pdev->dev;
plat_dat->bsp_priv = dwmac;
plat_dat->fix_mac_speed = visconti_eth_fix_mac_speed;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
index 1914ad698cab..acd70b9a3173 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
@@ -150,6 +150,7 @@
#define NUM_DWMAC100_DMA_REGS 9
#define NUM_DWMAC1000_DMA_REGS 23
+#define NUM_DWMAC4_DMA_REGS 27
void dwmac_enable_dma_transmission(void __iomem *ioaddr);
void dwmac_enable_dma_irq(void __iomem *ioaddr, u32 chan, bool rx, bool tx);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 164dff5ec32e..abfb3cd5958d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -21,10 +21,18 @@
#include "dwxgmac2.h"
#define REG_SPACE_SIZE 0x1060
+#define GMAC4_REG_SPACE_SIZE 0x116C
#define MAC100_ETHTOOL_NAME "st_mac100"
#define GMAC_ETHTOOL_NAME "st_gmac"
#define XGMAC_ETHTOOL_NAME "st_xgmac"
+/* Same as DMA_CHAN_BASE_ADDR defined in dwmac4_dma.h
+ *
+ * It is here because dwmac_dma.h and dwmac4_dam.h can not be included at the
+ * same time due to the conflicting macro names.
+ */
+#define GMAC4_DMA_CHAN_BASE_ADDR 0x00001100
+
#define ETHTOOL_DMA_OFFSET 55
struct stmmac_stats {
@@ -434,6 +442,8 @@ static int stmmac_ethtool_get_regs_len(struct net_device *dev)
if (priv->plat->has_xgmac)
return XGMAC_REGSIZE * 4;
+ else if (priv->plat->has_gmac4)
+ return GMAC4_REG_SPACE_SIZE;
return REG_SPACE_SIZE;
}
@@ -446,8 +456,13 @@ static void stmmac_ethtool_gregs(struct net_device *dev,
stmmac_dump_mac_regs(priv, priv->hw, reg_space);
stmmac_dump_dma_regs(priv, priv->ioaddr, reg_space);
- if (!priv->plat->has_xgmac) {
- /* Copy DMA registers to where ethtool expects them */
+ /* Copy DMA registers to where ethtool expects them */
+ if (priv->plat->has_gmac4) {
+ /* GMAC4 dumps its DMA registers at its DMA_CHAN_BASE_ADDR */
+ memcpy(&reg_space[ETHTOOL_DMA_OFFSET],
+ &reg_space[GMAC4_DMA_CHAN_BASE_ADDR / 4],
+ NUM_DWMAC4_DMA_REGS * 4);
+ } else if (!priv->plat->has_xgmac) {
memcpy(&reg_space[ETHTOOL_DMA_OFFSET],
&reg_space[DMA_BUS_MODE / 4],
NUM_DWMAC1000_DMA_REGS * 4);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
index 074e2cdfb0fa..a7ec9f4d46ce 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
@@ -145,15 +145,20 @@ static int adjust_systime(void __iomem *ioaddr, u32 sec, u32 nsec,
static void get_systime(void __iomem *ioaddr, u64 *systime)
{
- u64 ns;
-
- /* Get the TSSS value */
- ns = readl(ioaddr + PTP_STNSR);
- /* Get the TSS and convert sec time value to nanosecond */
- ns += readl(ioaddr + PTP_STSR) * 1000000000ULL;
+ u64 ns, sec0, sec1;
+
+ /* Get the TSS value */
+ sec1 = readl_relaxed(ioaddr + PTP_STSR);
+ do {
+ sec0 = sec1;
+ /* Get the TSSS value */
+ ns = readl_relaxed(ioaddr + PTP_STNSR);
+ /* Get the TSS value */
+ sec1 = readl_relaxed(ioaddr + PTP_STSR);
+ } while (sec0 != sec1);
if (systime)
- *systime = ns;
+ *systime = ns + (sec1 * 1000000000ULL);
}
static void get_ptptime(void __iomem *ptpaddr, u64 *ptp_time)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 639a753266e6..bde76ea2deec 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -7252,6 +7252,10 @@ int stmmac_dvr_remove(struct device *dev)
netdev_info(priv->dev, "%s: removing driver", __func__);
+ pm_runtime_get_sync(dev);
+ pm_runtime_disable(dev);
+ pm_runtime_put_noidle(dev);
+
stmmac_stop_all_dma(priv);
stmmac_mac_set(priv, priv->ioaddr, false);
netif_carrier_off(ndev);
@@ -7270,8 +7274,6 @@ int stmmac_dvr_remove(struct device *dev)
if (priv->plat->stmmac_rst)
reset_control_assert(priv->plat->stmmac_rst);
reset_control_assert(priv->plat->stmmac_ahb_rst);
- pm_runtime_put(dev);
- pm_runtime_disable(dev);
if (priv->hw->pcs != STMMAC_PCS_TBI &&
priv->hw->pcs != STMMAC_PCS_RTBI)
stmmac_mdio_unregister(ndev);
diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index 7d67f41387f5..4f5ef8a9a9a8 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -100,6 +100,7 @@ struct at86rf230_local {
unsigned long cal_timeout;
bool is_tx;
bool is_tx_from_off;
+ bool was_tx;
u8 tx_retry;
struct sk_buff *tx_skb;
struct at86rf230_state_change tx;
@@ -343,7 +344,11 @@ at86rf230_async_error_recover_complete(void *context)
if (ctx->free)
kfree(ctx);
- ieee802154_wake_queue(lp->hw);
+ if (lp->was_tx) {
+ lp->was_tx = 0;
+ dev_kfree_skb_any(lp->tx_skb);
+ ieee802154_wake_queue(lp->hw);
+ }
}
static void
@@ -352,7 +357,11 @@ at86rf230_async_error_recover(void *context)
struct at86rf230_state_change *ctx = context;
struct at86rf230_local *lp = ctx->lp;
- lp->is_tx = 0;
+ if (lp->is_tx) {
+ lp->was_tx = 1;
+ lp->is_tx = 0;
+ }
+
at86rf230_async_state_change(lp, ctx, STATE_RX_AACK_ON,
at86rf230_async_error_recover_complete);
}
diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c
index ece6ff6049f6..f3438d3e104a 100644
--- a/drivers/net/ieee802154/ca8210.c
+++ b/drivers/net/ieee802154/ca8210.c
@@ -1771,6 +1771,7 @@ static int ca8210_async_xmit_complete(
status
);
if (status != MAC_TRANSACTION_OVERFLOW) {
+ dev_kfree_skb_any(priv->tx_skb);
ieee802154_wake_queue(priv->hw);
return 0;
}
diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c
index 8caa61ec718f..36f1c5aa98fc 100644
--- a/drivers/net/ieee802154/mac802154_hwsim.c
+++ b/drivers/net/ieee802154/mac802154_hwsim.c
@@ -786,6 +786,7 @@ static int hwsim_add_one(struct genl_info *info, struct device *dev,
goto err_pib;
}
+ pib->channel = 13;
rcu_assign_pointer(phy->pib, pib);
phy->idx = idx;
INIT_LIST_HEAD(&phy->edges);
diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c
index 8dc04e2590b1..383231b85464 100644
--- a/drivers/net/ieee802154/mcr20a.c
+++ b/drivers/net/ieee802154/mcr20a.c
@@ -976,8 +976,8 @@ static void mcr20a_hw_setup(struct mcr20a_local *lp)
dev_dbg(printdev(lp), "%s\n", __func__);
phy->symbol_duration = 16;
- phy->lifs_period = 40;
- phy->sifs_period = 12;
+ phy->lifs_period = 40 * phy->symbol_duration;
+ phy->sifs_period = 12 * phy->symbol_duration;
hw->flags = IEEE802154_HW_TX_OMIT_CKSUM |
IEEE802154_HW_AFILT |
diff --git a/drivers/net/ipa/ipa_power.c b/drivers/net/ipa/ipa_power.c
index b1c6c0fcb654..f2989aac47a6 100644
--- a/drivers/net/ipa/ipa_power.c
+++ b/drivers/net/ipa/ipa_power.c
@@ -11,6 +11,8 @@
#include <linux/pm_runtime.h>
#include <linux/bitops.h>
+#include "linux/soc/qcom/qcom_aoss.h"
+
#include "ipa.h"
#include "ipa_power.h"
#include "ipa_endpoint.h"
@@ -64,6 +66,7 @@ enum ipa_power_flag {
* struct ipa_power - IPA power management information
* @dev: IPA device pointer
* @core: IPA core clock
+ * @qmp: QMP handle for AOSS communication
* @spinlock: Protects modem TX queue enable/disable
* @flags: Boolean state flags
* @interconnect_count: Number of elements in interconnect[]
@@ -72,6 +75,7 @@ enum ipa_power_flag {
struct ipa_power {
struct device *dev;
struct clk *core;
+ struct qmp *qmp;
spinlock_t spinlock; /* used with STOPPED/STARTED power flags */
DECLARE_BITMAP(flags, IPA_POWER_FLAG_COUNT);
u32 interconnect_count;
@@ -382,6 +386,47 @@ void ipa_power_modem_queue_active(struct ipa *ipa)
clear_bit(IPA_POWER_FLAG_STARTED, ipa->power->flags);
}
+static int ipa_power_retention_init(struct ipa_power *power)
+{
+ struct qmp *qmp = qmp_get(power->dev);
+
+ if (IS_ERR(qmp)) {
+ if (PTR_ERR(qmp) == -EPROBE_DEFER)
+ return -EPROBE_DEFER;
+
+ /* We assume any other error means it's not defined/needed */
+ qmp = NULL;
+ }
+ power->qmp = qmp;
+
+ return 0;
+}
+
+static void ipa_power_retention_exit(struct ipa_power *power)
+{
+ qmp_put(power->qmp);
+ power->qmp = NULL;
+}
+
+/* Control register retention on power collapse */
+void ipa_power_retention(struct ipa *ipa, bool enable)
+{
+ static const char fmt[] = "{ class: bcm, res: ipa_pc, val: %c }";
+ struct ipa_power *power = ipa->power;
+ char buf[36]; /* Exactly enough for fmt[]; size a multiple of 4 */
+ int ret;
+
+ if (!power->qmp)
+ return; /* Not needed on this platform */
+
+ (void)snprintf(buf, sizeof(buf), fmt, enable ? '1' : '0');
+
+ ret = qmp_send(power->qmp, buf, sizeof(buf));
+ if (ret)
+ dev_err(power->dev, "error %d sending QMP %sable request\n",
+ ret, enable ? "en" : "dis");
+}
+
int ipa_power_setup(struct ipa *ipa)
{
int ret;
@@ -438,12 +483,18 @@ ipa_power_init(struct device *dev, const struct ipa_power_data *data)
if (ret)
goto err_kfree;
+ ret = ipa_power_retention_init(power);
+ if (ret)
+ goto err_interconnect_exit;
+
pm_runtime_set_autosuspend_delay(dev, IPA_AUTOSUSPEND_DELAY);
pm_runtime_use_autosuspend(dev);
pm_runtime_enable(dev);
return power;
+err_interconnect_exit:
+ ipa_interconnect_exit(power);
err_kfree:
kfree(power);
err_clk_put:
@@ -460,6 +511,7 @@ void ipa_power_exit(struct ipa_power *power)
pm_runtime_disable(dev);
pm_runtime_dont_use_autosuspend(dev);
+ ipa_power_retention_exit(power);
ipa_interconnect_exit(power);
kfree(power);
clk_put(clk);
diff --git a/drivers/net/ipa/ipa_power.h b/drivers/net/ipa/ipa_power.h
index 2151805d7fbb..6f84f057a209 100644
--- a/drivers/net/ipa/ipa_power.h
+++ b/drivers/net/ipa/ipa_power.h
@@ -41,6 +41,13 @@ void ipa_power_modem_queue_wake(struct ipa *ipa);
void ipa_power_modem_queue_active(struct ipa *ipa);
/**
+ * ipa_power_retention() - Control register retention on power collapse
+ * @ipa: IPA pointer
+ * @enable: Whether retention should be enabled or disabled
+ */
+void ipa_power_retention(struct ipa *ipa, bool enable);
+
+/**
* ipa_power_setup() - Set up IPA power management
* @ipa: IPA pointer
*
diff --git a/drivers/net/ipa/ipa_uc.c b/drivers/net/ipa/ipa_uc.c
index 856e55a080a7..fe11910518d9 100644
--- a/drivers/net/ipa/ipa_uc.c
+++ b/drivers/net/ipa/ipa_uc.c
@@ -11,6 +11,7 @@
#include "ipa.h"
#include "ipa_uc.h"
+#include "ipa_power.h"
/**
* DOC: The IPA embedded microcontroller
@@ -154,6 +155,7 @@ static void ipa_uc_response_hdlr(struct ipa *ipa, enum ipa_irq_id irq_id)
case IPA_UC_RESPONSE_INIT_COMPLETED:
if (ipa->uc_powered) {
ipa->uc_loaded = true;
+ ipa_power_retention(ipa, true);
pm_runtime_mark_last_busy(dev);
(void)pm_runtime_put_autosuspend(dev);
ipa->uc_powered = false;
@@ -184,6 +186,9 @@ void ipa_uc_deconfig(struct ipa *ipa)
ipa_interrupt_remove(ipa->interrupt, IPA_IRQ_UC_1);
ipa_interrupt_remove(ipa->interrupt, IPA_IRQ_UC_0);
+ if (ipa->uc_loaded)
+ ipa_power_retention(ipa, false);
+
if (!ipa->uc_powered)
return;
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 16aa3a478e9e..3d0874331763 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -3870,6 +3870,18 @@ static void macsec_common_dellink(struct net_device *dev, struct list_head *head
struct macsec_dev *macsec = macsec_priv(dev);
struct net_device *real_dev = macsec->real_dev;
+ /* If h/w offloading is available, propagate to the device */
+ if (macsec_is_offloaded(macsec)) {
+ const struct macsec_ops *ops;
+ struct macsec_context ctx;
+
+ ops = macsec_get_ops(netdev_priv(dev), &ctx);
+ if (ops) {
+ ctx.secy = &macsec->secy;
+ macsec_offload(ops->mdo_del_secy, &ctx);
+ }
+ }
+
unregister_netdevice_queue(dev, head);
list_del_rcu(&macsec->secys);
macsec_del_dev(macsec);
@@ -3884,18 +3896,6 @@ static void macsec_dellink(struct net_device *dev, struct list_head *head)
struct net_device *real_dev = macsec->real_dev;
struct macsec_rxh_data *rxd = macsec_data_rtnl(real_dev);
- /* If h/w offloading is available, propagate to the device */
- if (macsec_is_offloaded(macsec)) {
- const struct macsec_ops *ops;
- struct macsec_context ctx;
-
- ops = macsec_get_ops(netdev_priv(dev), &ctx);
- if (ops) {
- ctx.secy = &macsec->secy;
- macsec_offload(ops->mdo_del_secy, &ctx);
- }
- }
-
macsec_common_dellink(dev, head);
if (list_empty(&rxd->secys)) {
@@ -4018,6 +4018,15 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
!macsec_check_offload(macsec->offload, macsec))
return -EOPNOTSUPP;
+ /* send_sci must be set to true when transmit sci explicitly is set */
+ if ((data && data[IFLA_MACSEC_SCI]) &&
+ (data && data[IFLA_MACSEC_INC_SCI])) {
+ u8 send_sci = !!nla_get_u8(data[IFLA_MACSEC_INC_SCI]);
+
+ if (!send_sci)
+ return -EINVAL;
+ }
+
if (data && data[IFLA_MACSEC_ICV_LEN])
icv_len = nla_get_u8(data[IFLA_MACSEC_ICV_LEN]);
mtu = real_dev->mtu - icv_len - macsec_extra_len(true);
diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index 5b6c0d120e09..29aa811af430 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -1688,19 +1688,19 @@ static int qca808x_read_status(struct phy_device *phydev)
if (ret < 0)
return ret;
- if (phydev->link && phydev->speed == SPEED_2500)
- phydev->interface = PHY_INTERFACE_MODE_2500BASEX;
- else
- phydev->interface = PHY_INTERFACE_MODE_SMII;
-
- /* generate seed as a lower random value to make PHY linked as SLAVE easily,
- * except for master/slave configuration fault detected.
- * the reason for not putting this code into the function link_change_notify is
- * the corner case where the link partner is also the qca8081 PHY and the seed
- * value is configured as the same value, the link can't be up and no link change
- * occurs.
- */
- if (!phydev->link) {
+ if (phydev->link) {
+ if (phydev->speed == SPEED_2500)
+ phydev->interface = PHY_INTERFACE_MODE_2500BASEX;
+ else
+ phydev->interface = PHY_INTERFACE_MODE_SGMII;
+ } else {
+ /* generate seed as a lower random value to make PHY linked as SLAVE easily,
+ * except for master/slave configuration fault detected.
+ * the reason for not putting this code into the function link_change_notify is
+ * the corner case where the link partner is also the qca8081 PHY and the seed
+ * value is configured as the same value, the link can't be up and no link change
+ * occurs.
+ */
if (phydev->master_slave_state == MASTER_SLAVE_STATE_ERR) {
qca808x_phy_ms_seed_enable(phydev, false);
} else {
diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c
index cd33955df0b6..6a769df0b421 100644
--- a/drivers/net/usb/ipheth.c
+++ b/drivers/net/usb/ipheth.c
@@ -121,7 +121,7 @@ static int ipheth_alloc_urbs(struct ipheth_device *iphone)
if (tx_buf == NULL)
goto free_rx_urb;
- rx_buf = usb_alloc_coherent(iphone->udev, IPHETH_BUF_SIZE,
+ rx_buf = usb_alloc_coherent(iphone->udev, IPHETH_BUF_SIZE + IPHETH_IP_ALIGN,
GFP_KERNEL, &rx_urb->transfer_dma);
if (rx_buf == NULL)
goto free_tx_buf;
@@ -146,7 +146,7 @@ error_nomem:
static void ipheth_free_urbs(struct ipheth_device *iphone)
{
- usb_free_coherent(iphone->udev, IPHETH_BUF_SIZE, iphone->rx_buf,
+ usb_free_coherent(iphone->udev, IPHETH_BUF_SIZE + IPHETH_IP_ALIGN, iphone->rx_buf,
iphone->rx_urb->transfer_dma);
usb_free_coherent(iphone->udev, IPHETH_BUF_SIZE, iphone->tx_buf,
iphone->tx_urb->transfer_dma);
@@ -317,7 +317,7 @@ static int ipheth_rx_submit(struct ipheth_device *dev, gfp_t mem_flags)
usb_fill_bulk_urb(dev->rx_urb, udev,
usb_rcvbulkpipe(udev, dev->bulk_in),
- dev->rx_buf, IPHETH_BUF_SIZE,
+ dev->rx_buf, IPHETH_BUF_SIZE + IPHETH_IP_ALIGN,
ipheth_rcvbulk_callback,
dev);
dev->rx_urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
diff --git a/fs/9p/fid.c b/fs/9p/fid.c
index 6aab046c98e2..79df61fe0e59 100644
--- a/fs/9p/fid.c
+++ b/fs/9p/fid.c
@@ -96,12 +96,8 @@ static struct p9_fid *v9fs_fid_find(struct dentry *dentry, kuid_t uid, int any)
dentry, dentry, from_kuid(&init_user_ns, uid),
any);
ret = NULL;
-
- if (d_inode(dentry))
- ret = v9fs_fid_find_inode(d_inode(dentry), uid);
-
/* we'll recheck under lock if there's anything to look in */
- if (!ret && dentry->d_fsdata) {
+ if (dentry->d_fsdata) {
struct hlist_head *h = (struct hlist_head *)&dentry->d_fsdata;
spin_lock(&dentry->d_lock);
@@ -113,6 +109,9 @@ static struct p9_fid *v9fs_fid_find(struct dentry *dentry, kuid_t uid, int any)
}
}
spin_unlock(&dentry->d_lock);
+ } else {
+ if (dentry->d_inode)
+ ret = v9fs_fid_find_inode(dentry->d_inode, uid);
}
return ret;
diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c
index 04eb52736990..753986ea1583 100644
--- a/fs/cachefiles/io.c
+++ b/fs/cachefiles/io.c
@@ -192,6 +192,64 @@ presubmission_error:
}
/*
+ * Query the occupancy of the cache in a region, returning where the next chunk
+ * of data starts and how long it is.
+ */
+static int cachefiles_query_occupancy(struct netfs_cache_resources *cres,
+ loff_t start, size_t len, size_t granularity,
+ loff_t *_data_start, size_t *_data_len)
+{
+ struct cachefiles_object *object;
+ struct file *file;
+ loff_t off, off2;
+
+ *_data_start = -1;
+ *_data_len = 0;
+
+ if (!fscache_wait_for_operation(cres, FSCACHE_WANT_READ))
+ return -ENOBUFS;
+
+ object = cachefiles_cres_object(cres);
+ file = cachefiles_cres_file(cres);
+ granularity = max_t(size_t, object->volume->cache->bsize, granularity);
+
+ _enter("%pD,%li,%llx,%zx/%llx",
+ file, file_inode(file)->i_ino, start, len,
+ i_size_read(file_inode(file)));
+
+ off = cachefiles_inject_read_error();
+ if (off == 0)
+ off = vfs_llseek(file, start, SEEK_DATA);
+ if (off == -ENXIO)
+ return -ENODATA; /* Beyond EOF */
+ if (off < 0 && off >= (loff_t)-MAX_ERRNO)
+ return -ENOBUFS; /* Error. */
+ if (round_up(off, granularity) >= start + len)
+ return -ENODATA; /* No data in range */
+
+ off2 = cachefiles_inject_read_error();
+ if (off2 == 0)
+ off2 = vfs_llseek(file, off, SEEK_HOLE);
+ if (off2 == -ENXIO)
+ return -ENODATA; /* Beyond EOF */
+ if (off2 < 0 && off2 >= (loff_t)-MAX_ERRNO)
+ return -ENOBUFS; /* Error. */
+
+ /* Round away partial blocks */
+ off = round_up(off, granularity);
+ off2 = round_down(off2, granularity);
+ if (off2 <= off)
+ return -ENODATA;
+
+ *_data_start = off;
+ if (off2 > start + len)
+ *_data_len = len;
+ else
+ *_data_len = off2 - off;
+ return 0;
+}
+
+/*
* Handle completion of a write to the cache.
*/
static void cachefiles_write_complete(struct kiocb *iocb, long ret)
@@ -545,6 +603,7 @@ static const struct netfs_cache_ops cachefiles_netfs_cache_ops = {
.write = cachefiles_write,
.prepare_read = cachefiles_prepare_read,
.prepare_write = cachefiles_prepare_write,
+ .query_occupancy = cachefiles_query_occupancy,
};
/*
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 11a22a30ee14..0b742bd50642 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -162,7 +162,7 @@ static void cifs_resolve_server(struct work_struct *work)
mutex_unlock(&server->srv_mutex);
}
-/**
+/*
* Mark all sessions and tcons for reconnect.
*
* @server needs to be previously set to CifsNeedReconnect.
@@ -1831,13 +1831,9 @@ void cifs_put_smb_ses(struct cifs_ses *ses)
int i;
for (i = 1; i < chan_count; i++) {
- /*
- * note: for now, we're okay accessing ses->chans
- * without chan_lock. But when chans can go away, we'll
- * need to introduce ref counting to make sure that chan
- * is not freed from under us.
- */
+ spin_unlock(&ses->chan_lock);
cifs_put_tcp_session(ses->chans[i].server, 0);
+ spin_lock(&ses->chan_lock);
ses->chans[i].server = NULL;
}
}
@@ -1981,6 +1977,19 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses)
}
}
+ ctx->workstation_name = kstrdup(ses->workstation_name, GFP_KERNEL);
+ if (!ctx->workstation_name) {
+ cifs_dbg(FYI, "Unable to allocate memory for workstation_name\n");
+ rc = -ENOMEM;
+ kfree(ctx->username);
+ ctx->username = NULL;
+ kfree_sensitive(ctx->password);
+ ctx->password = NULL;
+ kfree(ctx->domainname);
+ ctx->domainname = NULL;
+ goto out_key_put;
+ }
+
out_key_put:
up_read(&key->sem);
key_put(key);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 59334be9ed3b..e7af802dcfa6 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -4269,8 +4269,6 @@ cifs_readv_complete(struct work_struct *work)
for (i = 0; i < rdata->nr_pages; i++) {
struct page *page = rdata->pages[i];
- lru_cache_add(page);
-
if (rdata->result == 0 ||
(rdata->result == -EAGAIN && got_bytes)) {
flush_dcache_page(page);
@@ -4278,12 +4276,12 @@ cifs_readv_complete(struct work_struct *work)
} else
SetPageError(page);
- unlock_page(page);
-
if (rdata->result == 0 ||
(rdata->result == -EAGAIN && got_bytes))
cifs_readpage_to_fscache(rdata->mapping->host, page);
+ unlock_page(page);
+
got_bytes -= min_t(unsigned int, PAGE_SIZE, got_bytes);
put_page(page);
@@ -4340,7 +4338,6 @@ readpages_fill_pages(struct TCP_Server_Info *server,
* fill them until the writes are flushed.
*/
zero_user(page, 0, PAGE_SIZE);
- lru_cache_add(page);
flush_dcache_page(page);
SetPageUptodate(page);
unlock_page(page);
@@ -4350,7 +4347,6 @@ readpages_fill_pages(struct TCP_Server_Info *server,
continue;
} else {
/* no need to hold page hostage */
- lru_cache_add(page);
unlock_page(page);
put_page(page);
rdata->pages[i] = NULL;
@@ -4393,92 +4389,20 @@ cifs_readpages_copy_into_pages(struct TCP_Server_Info *server,
return readpages_fill_pages(server, rdata, iter, iter->count);
}
-static int
-readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
- unsigned int rsize, struct list_head *tmplist,
- unsigned int *nr_pages, loff_t *offset, unsigned int *bytes)
-{
- struct page *page, *tpage;
- unsigned int expected_index;
- int rc;
- gfp_t gfp = readahead_gfp_mask(mapping);
-
- INIT_LIST_HEAD(tmplist);
-
- page = lru_to_page(page_list);
-
- /*
- * Lock the page and put it in the cache. Since no one else
- * should have access to this page, we're safe to simply set
- * PG_locked without checking it first.
- */
- __SetPageLocked(page);
- rc = add_to_page_cache_locked(page, mapping,
- page->index, gfp);
-
- /* give up if we can't stick it in the cache */
- if (rc) {
- __ClearPageLocked(page);
- return rc;
- }
-
- /* move first page to the tmplist */
- *offset = (loff_t)page->index << PAGE_SHIFT;
- *bytes = PAGE_SIZE;
- *nr_pages = 1;
- list_move_tail(&page->lru, tmplist);
-
- /* now try and add more pages onto the request */
- expected_index = page->index + 1;
- list_for_each_entry_safe_reverse(page, tpage, page_list, lru) {
- /* discontinuity ? */
- if (page->index != expected_index)
- break;
-
- /* would this page push the read over the rsize? */
- if (*bytes + PAGE_SIZE > rsize)
- break;
-
- __SetPageLocked(page);
- rc = add_to_page_cache_locked(page, mapping, page->index, gfp);
- if (rc) {
- __ClearPageLocked(page);
- break;
- }
- list_move_tail(&page->lru, tmplist);
- (*bytes) += PAGE_SIZE;
- expected_index++;
- (*nr_pages)++;
- }
- return rc;
-}
-
-static int cifs_readpages(struct file *file, struct address_space *mapping,
- struct list_head *page_list, unsigned num_pages)
+static void cifs_readahead(struct readahead_control *ractl)
{
int rc;
- int err = 0;
- struct list_head tmplist;
- struct cifsFileInfo *open_file = file->private_data;
- struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
+ struct cifsFileInfo *open_file = ractl->file->private_data;
+ struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(ractl->file);
struct TCP_Server_Info *server;
pid_t pid;
- unsigned int xid;
+ unsigned int xid, nr_pages, last_batch_size = 0, cache_nr_pages = 0;
+ pgoff_t next_cached = ULONG_MAX;
+ bool caching = fscache_cookie_enabled(cifs_inode_cookie(ractl->mapping->host)) &&
+ cifs_inode_cookie(ractl->mapping->host)->cache_priv;
+ bool check_cache = caching;
xid = get_xid();
- /*
- * Reads as many pages as possible from fscache. Returns -ENOBUFS
- * immediately if the cookie is negative
- *
- * After this point, every page in the list might have PG_fscache set,
- * so we will need to clean that up off of every page we don't use.
- */
- rc = cifs_readpages_from_fscache(mapping->host, mapping, page_list,
- &num_pages);
- if (rc == 0) {
- free_xid(xid);
- return rc;
- }
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
pid = open_file->pid;
@@ -4489,39 +4413,73 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
server = cifs_pick_channel(tlink_tcon(open_file->tlink)->ses);
cifs_dbg(FYI, "%s: file=%p mapping=%p num_pages=%u\n",
- __func__, file, mapping, num_pages);
+ __func__, ractl->file, ractl->mapping, readahead_count(ractl));
/*
- * Start with the page at end of list and move it to private
- * list. Do the same with any following pages until we hit
- * the rsize limit, hit an index discontinuity, or run out of
- * pages. Issue the async read and then start the loop again
- * until the list is empty.
- *
- * Note that list order is important. The page_list is in
- * the order of declining indexes. When we put the pages in
- * the rdata->pages, then we want them in increasing order.
+ * Chop the readahead request up into rsize-sized read requests.
*/
- while (!list_empty(page_list) && !err) {
- unsigned int i, nr_pages, bytes, rsize;
- loff_t offset;
- struct page *page, *tpage;
+ while ((nr_pages = readahead_count(ractl) - last_batch_size)) {
+ unsigned int i, got, rsize;
+ struct page *page;
struct cifs_readdata *rdata;
struct cifs_credits credits_on_stack;
struct cifs_credits *credits = &credits_on_stack;
+ pgoff_t index = readahead_index(ractl) + last_batch_size;
+
+ /*
+ * Find out if we have anything cached in the range of
+ * interest, and if so, where the next chunk of cached data is.
+ */
+ if (caching) {
+ if (check_cache) {
+ rc = cifs_fscache_query_occupancy(
+ ractl->mapping->host, index, nr_pages,
+ &next_cached, &cache_nr_pages);
+ if (rc < 0)
+ caching = false;
+ check_cache = false;
+ }
+
+ if (index == next_cached) {
+ /*
+ * TODO: Send a whole batch of pages to be read
+ * by the cache.
+ */
+ page = readahead_page(ractl);
+ last_batch_size = 1 << thp_order(page);
+ if (cifs_readpage_from_fscache(ractl->mapping->host,
+ page) < 0) {
+ /*
+ * TODO: Deal with cache read failure
+ * here, but for the moment, delegate
+ * that to readpage.
+ */
+ caching = false;
+ }
+ unlock_page(page);
+ next_cached++;
+ cache_nr_pages--;
+ if (cache_nr_pages == 0)
+ check_cache = true;
+ continue;
+ }
+ }
if (open_file->invalidHandle) {
rc = cifs_reopen_file(open_file, true);
- if (rc == -EAGAIN)
- continue;
- else if (rc)
+ if (rc) {
+ if (rc == -EAGAIN)
+ continue;
break;
+ }
}
rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize,
&rsize, credits);
if (rc)
break;
+ nr_pages = min_t(size_t, rsize / PAGE_SIZE, readahead_count(ractl));
+ nr_pages = min_t(size_t, nr_pages, next_cached - index);
/*
* Give up immediately if rsize is too small to read an entire
@@ -4529,16 +4487,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
* reach this point however since we set ra_pages to 0 when the
* rsize is smaller than a cache page.
*/
- if (unlikely(rsize < PAGE_SIZE)) {
- add_credits_and_wake_if(server, credits, 0);
- free_xid(xid);
- return 0;
- }
-
- nr_pages = 0;
- err = readpages_get_pages(mapping, page_list, rsize, &tmplist,
- &nr_pages, &offset, &bytes);
- if (!nr_pages) {
+ if (unlikely(!nr_pages)) {
add_credits_and_wake_if(server, credits, 0);
break;
}
@@ -4546,36 +4495,31 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
rdata = cifs_readdata_alloc(nr_pages, cifs_readv_complete);
if (!rdata) {
/* best to give up if we're out of mem */
- list_for_each_entry_safe(page, tpage, &tmplist, lru) {
- list_del(&page->lru);
- lru_cache_add(page);
- unlock_page(page);
- put_page(page);
- }
- rc = -ENOMEM;
add_credits_and_wake_if(server, credits, 0);
break;
}
- rdata->cfile = cifsFileInfo_get(open_file);
- rdata->server = server;
- rdata->mapping = mapping;
- rdata->offset = offset;
- rdata->bytes = bytes;
- rdata->pid = pid;
- rdata->pagesz = PAGE_SIZE;
- rdata->tailsz = PAGE_SIZE;
+ got = __readahead_batch(ractl, rdata->pages, nr_pages);
+ if (got != nr_pages) {
+ pr_warn("__readahead_batch() returned %u/%u\n",
+ got, nr_pages);
+ nr_pages = got;
+ }
+
+ rdata->nr_pages = nr_pages;
+ rdata->bytes = readahead_batch_length(ractl);
+ rdata->cfile = cifsFileInfo_get(open_file);
+ rdata->server = server;
+ rdata->mapping = ractl->mapping;
+ rdata->offset = readahead_pos(ractl);
+ rdata->pid = pid;
+ rdata->pagesz = PAGE_SIZE;
+ rdata->tailsz = PAGE_SIZE;
rdata->read_into_pages = cifs_readpages_read_into_pages;
rdata->copy_into_pages = cifs_readpages_copy_into_pages;
- rdata->credits = credits_on_stack;
-
- list_for_each_entry_safe(page, tpage, &tmplist, lru) {
- list_del(&page->lru);
- rdata->pages[rdata->nr_pages++] = page;
- }
+ rdata->credits = credits_on_stack;
rc = adjust_credits(server, &rdata->credits, rdata->bytes);
-
if (!rc) {
if (rdata->cfile->invalidHandle)
rc = -EAGAIN;
@@ -4587,7 +4531,6 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
add_credits_and_wake_if(server, &rdata->credits, 0);
for (i = 0; i < rdata->nr_pages; i++) {
page = rdata->pages[i];
- lru_cache_add(page);
unlock_page(page);
put_page(page);
}
@@ -4597,10 +4540,10 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
}
kref_put(&rdata->refcount, cifs_readdata_release);
+ last_batch_size = nr_pages;
}
free_xid(xid);
- return rc;
}
/*
@@ -4924,7 +4867,7 @@ oplock_break_done:
* In the non-cached mode (mount with cache=none), we shunt off direct read and write requests
* so this method should never be called.
*
- * Direct IO is not yet supported in the cached mode.
+ * Direct IO is not yet supported in the cached mode.
*/
static ssize_t
cifs_direct_io(struct kiocb *iocb, struct iov_iter *iter)
@@ -5006,7 +4949,7 @@ static int cifs_set_page_dirty(struct page *page)
const struct address_space_operations cifs_addr_ops = {
.readpage = cifs_readpage,
- .readpages = cifs_readpages,
+ .readahead = cifs_readahead,
.writepage = cifs_writepage,
.writepages = cifs_writepages,
.write_begin = cifs_write_begin,
diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c
index efaac4d5ff55..33af72e0ac0c 100644
--- a/fs/cifs/fscache.c
+++ b/fs/cifs/fscache.c
@@ -134,37 +134,127 @@ void cifs_fscache_release_inode_cookie(struct inode *inode)
}
}
+static inline void fscache_end_operation(struct netfs_cache_resources *cres)
+{
+ const struct netfs_cache_ops *ops = fscache_operation_valid(cres);
+
+ if (ops)
+ ops->end_operation(cres);
+}
+
/*
- * Retrieve a page from FS-Cache
+ * Fallback page reading interface.
*/
-int __cifs_readpage_from_fscache(struct inode *inode, struct page *page)
+static int fscache_fallback_read_page(struct inode *inode, struct page *page)
{
- cifs_dbg(FYI, "%s: (fsc:%p, p:%p, i:0x%p\n",
- __func__, CIFS_I(inode)->fscache, page, inode);
- return -ENOBUFS; // Needs conversion to using netfslib
+ struct netfs_cache_resources cres;
+ struct fscache_cookie *cookie = cifs_inode_cookie(inode);
+ struct iov_iter iter;
+ struct bio_vec bvec[1];
+ int ret;
+
+ memset(&cres, 0, sizeof(cres));
+ bvec[0].bv_page = page;
+ bvec[0].bv_offset = 0;
+ bvec[0].bv_len = PAGE_SIZE;
+ iov_iter_bvec(&iter, READ, bvec, ARRAY_SIZE(bvec), PAGE_SIZE);
+
+ ret = fscache_begin_read_operation(&cres, cookie);
+ if (ret < 0)
+ return ret;
+
+ ret = fscache_read(&cres, page_offset(page), &iter, NETFS_READ_HOLE_FAIL,
+ NULL, NULL);
+ fscache_end_operation(&cres);
+ return ret;
}
/*
- * Retrieve a set of pages from FS-Cache
+ * Fallback page writing interface.
*/
-int __cifs_readpages_from_fscache(struct inode *inode,
- struct address_space *mapping,
- struct list_head *pages,
- unsigned *nr_pages)
+static int fscache_fallback_write_page(struct inode *inode, struct page *page,
+ bool no_space_allocated_yet)
{
- cifs_dbg(FYI, "%s: (0x%p/%u/0x%p)\n",
- __func__, CIFS_I(inode)->fscache, *nr_pages, inode);
- return -ENOBUFS; // Needs conversion to using netfslib
+ struct netfs_cache_resources cres;
+ struct fscache_cookie *cookie = cifs_inode_cookie(inode);
+ struct iov_iter iter;
+ struct bio_vec bvec[1];
+ loff_t start = page_offset(page);
+ size_t len = PAGE_SIZE;
+ int ret;
+
+ memset(&cres, 0, sizeof(cres));
+ bvec[0].bv_page = page;
+ bvec[0].bv_offset = 0;
+ bvec[0].bv_len = PAGE_SIZE;
+ iov_iter_bvec(&iter, WRITE, bvec, ARRAY_SIZE(bvec), PAGE_SIZE);
+
+ ret = fscache_begin_write_operation(&cres, cookie);
+ if (ret < 0)
+ return ret;
+
+ ret = cres.ops->prepare_write(&cres, &start, &len, i_size_read(inode),
+ no_space_allocated_yet);
+ if (ret == 0)
+ ret = fscache_write(&cres, page_offset(page), &iter, NULL, NULL);
+ fscache_end_operation(&cres);
+ return ret;
}
-void __cifs_readpage_to_fscache(struct inode *inode, struct page *page)
+/*
+ * Retrieve a page from FS-Cache
+ */
+int __cifs_readpage_from_fscache(struct inode *inode, struct page *page)
{
- struct cifsInodeInfo *cifsi = CIFS_I(inode);
+ int ret;
- WARN_ON(!cifsi->fscache);
+ cifs_dbg(FYI, "%s: (fsc:%p, p:%p, i:0x%p\n",
+ __func__, cifs_inode_cookie(inode), page, inode);
+ ret = fscache_fallback_read_page(inode, page);
+ if (ret < 0)
+ return ret;
+
+ /* Read completed synchronously */
+ SetPageUptodate(page);
+ return 0;
+}
+
+void __cifs_readpage_to_fscache(struct inode *inode, struct page *page)
+{
cifs_dbg(FYI, "%s: (fsc: %p, p: %p, i: %p)\n",
- __func__, cifsi->fscache, page, inode);
+ __func__, cifs_inode_cookie(inode), page, inode);
+
+ fscache_fallback_write_page(inode, page, true);
+}
+
+/*
+ * Query the cache occupancy.
+ */
+int __cifs_fscache_query_occupancy(struct inode *inode,
+ pgoff_t first, unsigned int nr_pages,
+ pgoff_t *_data_first,
+ unsigned int *_data_nr_pages)
+{
+ struct netfs_cache_resources cres;
+ struct fscache_cookie *cookie = cifs_inode_cookie(inode);
+ loff_t start, data_start;
+ size_t len, data_len;
+ int ret;
- // Needs conversion to using netfslib
+ ret = fscache_begin_read_operation(&cres, cookie);
+ if (ret < 0)
+ return ret;
+
+ start = first * PAGE_SIZE;
+ len = nr_pages * PAGE_SIZE;
+ ret = cres.ops->query_occupancy(&cres, start, len, PAGE_SIZE,
+ &data_start, &data_len);
+ if (ret == 0) {
+ *_data_first = data_start / PAGE_SIZE;
+ *_data_nr_pages = len / PAGE_SIZE;
+ }
+
+ fscache_end_operation(&cres);
+ return ret;
}
diff --git a/fs/cifs/fscache.h b/fs/cifs/fscache.h
index c6ca49ac33d4..55129908e2c1 100644
--- a/fs/cifs/fscache.h
+++ b/fs/cifs/fscache.h
@@ -9,6 +9,7 @@
#ifndef _CIFS_FSCACHE_H
#define _CIFS_FSCACHE_H
+#include <linux/swap.h>
#include <linux/fscache.h>
#include "cifsglob.h"
@@ -58,14 +59,6 @@ void cifs_fscache_fill_coherency(struct inode *inode,
}
-extern int cifs_fscache_release_page(struct page *page, gfp_t gfp);
-extern int __cifs_readpage_from_fscache(struct inode *, struct page *);
-extern int __cifs_readpages_from_fscache(struct inode *,
- struct address_space *,
- struct list_head *,
- unsigned *);
-extern void __cifs_readpage_to_fscache(struct inode *, struct page *);
-
static inline struct fscache_cookie *cifs_inode_cookie(struct inode *inode)
{
return CIFS_I(inode)->fscache;
@@ -80,33 +73,52 @@ static inline void cifs_invalidate_cache(struct inode *inode, unsigned int flags
i_size_read(inode), flags);
}
-static inline int cifs_readpage_from_fscache(struct inode *inode,
- struct page *page)
-{
- if (CIFS_I(inode)->fscache)
- return __cifs_readpage_from_fscache(inode, page);
+extern int __cifs_fscache_query_occupancy(struct inode *inode,
+ pgoff_t first, unsigned int nr_pages,
+ pgoff_t *_data_first,
+ unsigned int *_data_nr_pages);
- return -ENOBUFS;
+static inline int cifs_fscache_query_occupancy(struct inode *inode,
+ pgoff_t first, unsigned int nr_pages,
+ pgoff_t *_data_first,
+ unsigned int *_data_nr_pages)
+{
+ if (!cifs_inode_cookie(inode))
+ return -ENOBUFS;
+ return __cifs_fscache_query_occupancy(inode, first, nr_pages,
+ _data_first, _data_nr_pages);
}
-static inline int cifs_readpages_from_fscache(struct inode *inode,
- struct address_space *mapping,
- struct list_head *pages,
- unsigned *nr_pages)
+extern int __cifs_readpage_from_fscache(struct inode *pinode, struct page *ppage);
+extern void __cifs_readpage_to_fscache(struct inode *pinode, struct page *ppage);
+
+
+static inline int cifs_readpage_from_fscache(struct inode *inode,
+ struct page *page)
{
- if (CIFS_I(inode)->fscache)
- return __cifs_readpages_from_fscache(inode, mapping, pages,
- nr_pages);
+ if (cifs_inode_cookie(inode))
+ return __cifs_readpage_from_fscache(inode, page);
return -ENOBUFS;
}
static inline void cifs_readpage_to_fscache(struct inode *inode,
struct page *page)
{
- if (PageFsCache(page))
+ if (cifs_inode_cookie(inode))
__cifs_readpage_to_fscache(inode, page);
}
+static inline int cifs_fscache_release_page(struct page *page, gfp_t gfp)
+{
+ if (PageFsCache(page)) {
+ if (current_is_kswapd() || !(gfp & __GFP_FS))
+ return false;
+ wait_on_page_fscache(page);
+ fscache_note_page_release(cifs_inode_cookie(page->mapping->host));
+ }
+ return true;
+}
+
#else /* CONFIG_CIFS_FSCACHE */
static inline
void cifs_fscache_fill_coherency(struct inode *inode,
@@ -123,22 +135,29 @@ static inline void cifs_fscache_unuse_inode_cookie(struct inode *inode, bool upd
static inline struct fscache_cookie *cifs_inode_cookie(struct inode *inode) { return NULL; }
static inline void cifs_invalidate_cache(struct inode *inode, unsigned int flags) {}
-static inline int
-cifs_readpage_from_fscache(struct inode *inode, struct page *page)
+static inline int cifs_fscache_query_occupancy(struct inode *inode,
+ pgoff_t first, unsigned int nr_pages,
+ pgoff_t *_data_first,
+ unsigned int *_data_nr_pages)
{
+ *_data_first = ULONG_MAX;
+ *_data_nr_pages = 0;
return -ENOBUFS;
}
-static inline int cifs_readpages_from_fscache(struct inode *inode,
- struct address_space *mapping,
- struct list_head *pages,
- unsigned *nr_pages)
+static inline int
+cifs_readpage_from_fscache(struct inode *inode, struct page *page)
{
return -ENOBUFS;
}
-static inline void cifs_readpage_to_fscache(struct inode *inode,
- struct page *page) {}
+static inline
+void cifs_readpage_to_fscache(struct inode *inode, struct page *page) {}
+
+static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp)
+{
+ return true; /* May release page */
+}
#endif /* CONFIG_CIFS_FSCACHE */
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 7d8b3ceb2af3..60d853c92f6a 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -83,6 +83,7 @@ static void cifs_set_ops(struct inode *inode)
static void
cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr)
{
+ struct cifs_fscache_inode_coherency_data cd;
struct cifsInodeInfo *cifs_i = CIFS_I(inode);
cifs_dbg(FYI, "%s: revalidating inode %llu\n",
@@ -113,6 +114,9 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr)
cifs_dbg(FYI, "%s: invalidating inode %llu mapping\n",
__func__, cifs_i->uniqueid);
set_bit(CIFS_INO_INVALID_MAPPING, &cifs_i->flags);
+ /* Invalidate fscache cookie */
+ cifs_fscache_fill_coherency(&cifs_i->vfs_inode, &cd);
+ fscache_invalidate(cifs_inode_cookie(inode), &cd, i_size_read(inode), 0);
}
/*
@@ -2261,8 +2265,6 @@ cifs_dentry_needs_reval(struct dentry *dentry)
int
cifs_invalidate_mapping(struct inode *inode)
{
- struct cifs_fscache_inode_coherency_data cd;
- struct cifsInodeInfo *cifsi = CIFS_I(inode);
int rc = 0;
if (inode->i_mapping && inode->i_mapping->nrpages != 0) {
@@ -2272,8 +2274,6 @@ cifs_invalidate_mapping(struct inode *inode)
__func__, inode);
}
- cifs_fscache_fill_coherency(&cifsi->vfs_inode, &cd);
- fscache_invalidate(cifs_inode_cookie(inode), &cd, i_size_read(inode), 0);
return rc;
}
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index dc3b16d1be09..5723d50340e5 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -713,7 +713,11 @@ static int size_of_ntlmssp_blob(struct cifs_ses *ses, int base_size)
else
sz += sizeof(__le16);
- sz += sizeof(__le16) * strnlen(ses->workstation_name, CIFS_MAX_WORKSTATION_LEN);
+ if (ses->workstation_name)
+ sz += sizeof(__le16) * strnlen(ses->workstation_name,
+ CIFS_MAX_WORKSTATION_LEN);
+ else
+ sz += sizeof(__le16);
return sz;
}
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 6a89ea410e43..edf62eaa6285 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -35,6 +35,7 @@
#define CEPH_OPT_TCP_NODELAY (1<<4) /* TCP_NODELAY on TCP sockets */
#define CEPH_OPT_NOMSGSIGN (1<<5) /* don't sign msgs (msgr1) */
#define CEPH_OPT_ABORT_ON_FULL (1<<6) /* abort w/ ENOSPC when full */
+#define CEPH_OPT_RXBOUNCE (1<<7) /* double-buffer read data */
#define CEPH_OPT_DEFAULT (CEPH_OPT_TCP_NODELAY)
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index ff99ce094cfa..e7f2fb2fc207 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -383,6 +383,10 @@ struct ceph_connection_v2_info {
struct ceph_gcm_nonce in_gcm_nonce;
struct ceph_gcm_nonce out_gcm_nonce;
+ struct page **in_enc_pages;
+ int in_enc_page_cnt;
+ int in_enc_resid;
+ int in_enc_i;
struct page **out_enc_pages;
int out_enc_page_cnt;
int out_enc_resid;
@@ -457,6 +461,7 @@ struct ceph_connection {
struct ceph_msg *out_msg; /* sending message (== tail of
out_sent) */
+ struct page *bounce_page;
u32 in_front_crc, in_middle_crc, in_data_crc; /* calculated crc */
struct timespec64 last_keepalive_ack; /* keepalive2 ack stamp */
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 8420fe504927..2be4dd7e90a9 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -46,8 +46,10 @@ struct vlan_hdr {
* @h_vlan_encapsulated_proto: packet type ID or len
*/
struct vlan_ethhdr {
- unsigned char h_dest[ETH_ALEN];
- unsigned char h_source[ETH_ALEN];
+ struct_group(addrs,
+ unsigned char h_dest[ETH_ALEN];
+ unsigned char h_source[ETH_ALEN];
+ );
__be16 h_vlan_proto;
__be16 h_vlan_TCI;
__be16 h_vlan_encapsulated_proto;
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index b46c39d98bbd..614f22213e21 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -244,6 +244,13 @@ struct netfs_cache_ops {
int (*prepare_write)(struct netfs_cache_resources *cres,
loff_t *_start, size_t *_len, loff_t i_size,
bool no_space_allocated_yet);
+
+ /* Query the occupancy of the cache in a region, returning where the
+ * next chunk of data starts and how long it is.
+ */
+ int (*query_occupancy)(struct netfs_cache_resources *cres,
+ loff_t start, size_t len, size_t granularity,
+ loff_t *_data_start, size_t *_data_len);
};
struct readahead_control;
diff --git a/include/net/ax25.h b/include/net/ax25.h
index 526e49589197..8221af1811df 100644
--- a/include/net/ax25.h
+++ b/include/net/ax25.h
@@ -239,6 +239,7 @@ typedef struct ax25_dev {
#if defined(CONFIG_AX25_DAMA_SLAVE) || defined(CONFIG_AX25_DAMA_MASTER)
ax25_dama_info dama;
#endif
+ refcount_t refcount;
} ax25_dev;
typedef struct ax25_cb {
@@ -293,6 +294,17 @@ static __inline__ void ax25_cb_put(ax25_cb *ax25)
}
}
+static inline void ax25_dev_hold(ax25_dev *ax25_dev)
+{
+ refcount_inc(&ax25_dev->refcount);
+}
+
+static inline void ax25_dev_put(ax25_dev *ax25_dev)
+{
+ if (refcount_dec_and_test(&ax25_dev->refcount)) {
+ kfree(ax25_dev);
+ }
+}
static inline __be16 ax25_type_trans(struct sk_buff *skb, struct net_device *dev)
{
skb->dev = dev;
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 937389e04c8e..87419f7f5421 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -350,7 +350,8 @@ static inline struct neighbour *neigh_create(struct neigh_table *tbl,
return __neigh_create(tbl, pkey, dev, true);
}
void neigh_destroy(struct neighbour *neigh);
-int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb);
+int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb,
+ const bool immediate_ok);
int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags,
u32 nlmsg_pid);
void __neigh_set_probe_once(struct neighbour *neigh);
@@ -460,17 +461,24 @@ static inline struct neighbour * neigh_clone(struct neighbour *neigh)
#define neigh_hold(n) refcount_inc(&(n)->refcnt)
-static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
+static __always_inline int neigh_event_send_probe(struct neighbour *neigh,
+ struct sk_buff *skb,
+ const bool immediate_ok)
{
unsigned long now = jiffies;
-
+
if (READ_ONCE(neigh->used) != now)
WRITE_ONCE(neigh->used, now);
- if (!(neigh->nud_state&(NUD_CONNECTED|NUD_DELAY|NUD_PROBE)))
- return __neigh_event_send(neigh, skb);
+ if (!(neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE)))
+ return __neigh_event_send(neigh, skb, immediate_ok);
return 0;
}
+static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
+{
+ return neigh_event_send_probe(neigh, skb, true);
+}
+
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb)
{
diff --git a/include/uapi/linux/smc_diag.h b/include/uapi/linux/smc_diag.h
index c7008d87f1a4..8cb3a6fef553 100644
--- a/include/uapi/linux/smc_diag.h
+++ b/include/uapi/linux/smc_diag.h
@@ -84,12 +84,11 @@ struct smc_diag_conninfo {
/* SMC_DIAG_LINKINFO */
struct smc_diag_linkinfo {
- __u8 link_id; /* link identifier */
- __u8 ibname[IB_DEVICE_NAME_MAX]; /* name of the RDMA device */
- __u8 ibport; /* RDMA device port number */
- __u8 gid[40]; /* local GID */
- __u8 peer_gid[40]; /* peer GID */
- __aligned_u64 net_cookie; /* RDMA device net namespace */
+ __u8 link_id; /* link identifier */
+ __u8 ibname[IB_DEVICE_NAME_MAX]; /* name of the RDMA device */
+ __u8 ibport; /* RDMA device port number */
+ __u8 gid[40]; /* local GID */
+ __u8 peer_gid[40]; /* peer GID */
};
struct smc_diag_lgrinfo {
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index 06062370c3b8..9e4ecc990647 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -207,7 +207,7 @@ BTF_ID(func, bpf_lsm_socket_socketpair)
BTF_ID(func, bpf_lsm_syslog)
BTF_ID(func, bpf_lsm_task_alloc)
-BTF_ID(func, bpf_lsm_task_getsecid_subj)
+BTF_ID(func, bpf_lsm_current_getsecid_subj)
BTF_ID(func, bpf_lsm_task_getsecid_obj)
BTF_ID(func, bpf_lsm_task_prctl)
BTF_ID(func, bpf_lsm_task_setscheduler)
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 638d7fd7b375..710ba9de12ce 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -104,7 +104,7 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node)
}
rb = vmap(pages, nr_meta_pages + 2 * nr_data_pages,
- VM_ALLOC | VM_USERMAP, PAGE_KERNEL);
+ VM_MAP | VM_USERMAP, PAGE_KERNEL);
if (rb) {
kmemleak_not_leak(pages);
rb->pages = pages;
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 4b6974a195c1..5e7edf913060 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -550,11 +550,12 @@ static __always_inline u64 notrace bpf_prog_start_time(void)
static void notrace inc_misses_counter(struct bpf_prog *prog)
{
struct bpf_prog_stats *stats;
+ unsigned int flags;
stats = this_cpu_ptr(prog->stats);
- u64_stats_update_begin(&stats->syncp);
+ flags = u64_stats_update_begin_irqsave(&stats->syncp);
u64_stats_inc(&stats->misses);
- u64_stats_update_end(&stats->syncp);
+ u64_stats_update_end_irqrestore(&stats->syncp, flags);
}
/* The logic is similar to bpf_prog_run(), but with an explicit
diff --git a/kernel/stackleak.c b/kernel/stackleak.c
index 66b8af394e58..ddb5a7f48d69 100644
--- a/kernel/stackleak.c
+++ b/kernel/stackleak.c
@@ -70,7 +70,7 @@ late_initcall(stackleak_sysctls_init);
#define skip_erasing() false
#endif /* CONFIG_STACKLEAK_RUNTIME_DISABLE */
-asmlinkage void notrace stackleak_erase(void)
+asmlinkage void noinstr stackleak_erase(void)
{
/* It would be nice not to have 'kstack_ptr' and 'boundary' on stack */
unsigned long kstack_ptr = current->lowest_stack;
@@ -124,9 +124,8 @@ asmlinkage void notrace stackleak_erase(void)
/* Reset the 'lowest_stack' value for the next syscall */
current->lowest_stack = current_top_of_stack() - THREAD_SIZE/64;
}
-NOKPROBE_SYMBOL(stackleak_erase);
-void __used __no_caller_saved_registers notrace stackleak_track_stack(void)
+void __used __no_caller_saved_registers noinstr stackleak_track_stack(void)
{
unsigned long sp = current_stack_pointer;
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 02f43f3e2c56..3e49d28824ed 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -77,6 +77,7 @@ static void ax25_kill_by_device(struct net_device *dev)
{
ax25_dev *ax25_dev;
ax25_cb *s;
+ struct sock *sk;
if ((ax25_dev = ax25_dev_ax25dev(dev)) == NULL)
return;
@@ -85,13 +86,16 @@ static void ax25_kill_by_device(struct net_device *dev)
again:
ax25_for_each(s, &ax25_list) {
if (s->ax25_dev == ax25_dev) {
+ sk = s->sk;
+ sock_hold(sk);
spin_unlock_bh(&ax25_list_lock);
- lock_sock(s->sk);
+ lock_sock(sk);
s->ax25_dev = NULL;
- release_sock(s->sk);
+ ax25_dev_put(ax25_dev);
+ release_sock(sk);
ax25_disconnect(s, ENETUNREACH);
spin_lock_bh(&ax25_list_lock);
-
+ sock_put(sk);
/* The entry could have been deleted from the
* list meanwhile and thus the next pointer is
* no longer valid. Play it safe and restart
@@ -355,21 +359,25 @@ static int ax25_ctl_ioctl(const unsigned int cmd, void __user *arg)
if (copy_from_user(&ax25_ctl, arg, sizeof(ax25_ctl)))
return -EFAULT;
- if ((ax25_dev = ax25_addr_ax25dev(&ax25_ctl.port_addr)) == NULL)
- return -ENODEV;
-
if (ax25_ctl.digi_count > AX25_MAX_DIGIS)
return -EINVAL;
if (ax25_ctl.arg > ULONG_MAX / HZ && ax25_ctl.cmd != AX25_KILL)
return -EINVAL;
+ ax25_dev = ax25_addr_ax25dev(&ax25_ctl.port_addr);
+ if (!ax25_dev)
+ return -ENODEV;
+
digi.ndigi = ax25_ctl.digi_count;
for (k = 0; k < digi.ndigi; k++)
digi.calls[k] = ax25_ctl.digi_addr[k];
- if ((ax25 = ax25_find_cb(&ax25_ctl.source_addr, &ax25_ctl.dest_addr, &digi, ax25_dev->dev)) == NULL)
+ ax25 = ax25_find_cb(&ax25_ctl.source_addr, &ax25_ctl.dest_addr, &digi, ax25_dev->dev);
+ if (!ax25) {
+ ax25_dev_put(ax25_dev);
return -ENOTCONN;
+ }
switch (ax25_ctl.cmd) {
case AX25_KILL:
@@ -436,6 +444,7 @@ static int ax25_ctl_ioctl(const unsigned int cmd, void __user *arg)
}
out_put:
+ ax25_dev_put(ax25_dev);
ax25_cb_put(ax25);
return ret;
diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c
index 256fadb94df3..d2a244e1c260 100644
--- a/net/ax25/ax25_dev.c
+++ b/net/ax25/ax25_dev.c
@@ -37,6 +37,7 @@ ax25_dev *ax25_addr_ax25dev(ax25_address *addr)
for (ax25_dev = ax25_dev_list; ax25_dev != NULL; ax25_dev = ax25_dev->next)
if (ax25cmp(addr, (const ax25_address *)ax25_dev->dev->dev_addr) == 0) {
res = ax25_dev;
+ ax25_dev_hold(ax25_dev);
}
spin_unlock_bh(&ax25_dev_lock);
@@ -56,6 +57,7 @@ void ax25_dev_device_up(struct net_device *dev)
return;
}
+ refcount_set(&ax25_dev->refcount, 1);
dev->ax25_ptr = ax25_dev;
ax25_dev->dev = dev;
dev_hold_track(dev, &ax25_dev->dev_tracker, GFP_ATOMIC);
@@ -84,6 +86,7 @@ void ax25_dev_device_up(struct net_device *dev)
ax25_dev->next = ax25_dev_list;
ax25_dev_list = ax25_dev;
spin_unlock_bh(&ax25_dev_lock);
+ ax25_dev_hold(ax25_dev);
ax25_register_dev_sysctl(ax25_dev);
}
@@ -113,9 +116,10 @@ void ax25_dev_device_down(struct net_device *dev)
if ((s = ax25_dev_list) == ax25_dev) {
ax25_dev_list = s->next;
spin_unlock_bh(&ax25_dev_lock);
+ ax25_dev_put(ax25_dev);
dev->ax25_ptr = NULL;
dev_put_track(dev, &ax25_dev->dev_tracker);
- kfree(ax25_dev);
+ ax25_dev_put(ax25_dev);
return;
}
@@ -123,9 +127,10 @@ void ax25_dev_device_down(struct net_device *dev)
if (s->next == ax25_dev) {
s->next = ax25_dev->next;
spin_unlock_bh(&ax25_dev_lock);
+ ax25_dev_put(ax25_dev);
dev->ax25_ptr = NULL;
dev_put_track(dev, &ax25_dev->dev_tracker);
- kfree(ax25_dev);
+ ax25_dev_put(ax25_dev);
return;
}
@@ -133,6 +138,7 @@ void ax25_dev_device_down(struct net_device *dev)
}
spin_unlock_bh(&ax25_dev_lock);
dev->ax25_ptr = NULL;
+ ax25_dev_put(ax25_dev);
}
int ax25_fwd_ioctl(unsigned int cmd, struct ax25_fwd_struct *fwd)
@@ -144,20 +150,32 @@ int ax25_fwd_ioctl(unsigned int cmd, struct ax25_fwd_struct *fwd)
switch (cmd) {
case SIOCAX25ADDFWD:
- if ((fwd_dev = ax25_addr_ax25dev(&fwd->port_to)) == NULL)
+ fwd_dev = ax25_addr_ax25dev(&fwd->port_to);
+ if (!fwd_dev) {
+ ax25_dev_put(ax25_dev);
return -EINVAL;
- if (ax25_dev->forward != NULL)
+ }
+ if (ax25_dev->forward) {
+ ax25_dev_put(fwd_dev);
+ ax25_dev_put(ax25_dev);
return -EINVAL;
+ }
ax25_dev->forward = fwd_dev->dev;
+ ax25_dev_put(fwd_dev);
+ ax25_dev_put(ax25_dev);
break;
case SIOCAX25DELFWD:
- if (ax25_dev->forward == NULL)
+ if (!ax25_dev->forward) {
+ ax25_dev_put(ax25_dev);
return -EINVAL;
+ }
ax25_dev->forward = NULL;
+ ax25_dev_put(ax25_dev);
break;
default:
+ ax25_dev_put(ax25_dev);
return -EINVAL;
}
diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c
index d0b2e094bd55..9751207f7757 100644
--- a/net/ax25/ax25_route.c
+++ b/net/ax25/ax25_route.c
@@ -75,11 +75,13 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
ax25_dev *ax25_dev;
int i;
- if ((ax25_dev = ax25_addr_ax25dev(&route->port_addr)) == NULL)
- return -EINVAL;
if (route->digi_count > AX25_MAX_DIGIS)
return -EINVAL;
+ ax25_dev = ax25_addr_ax25dev(&route->port_addr);
+ if (!ax25_dev)
+ return -EINVAL;
+
write_lock_bh(&ax25_route_lock);
ax25_rt = ax25_route_list;
@@ -91,6 +93,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
if (route->digi_count != 0) {
if ((ax25_rt->digipeat = kmalloc(sizeof(ax25_digi), GFP_ATOMIC)) == NULL) {
write_unlock_bh(&ax25_route_lock);
+ ax25_dev_put(ax25_dev);
return -ENOMEM;
}
ax25_rt->digipeat->lastrepeat = -1;
@@ -101,6 +104,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
}
}
write_unlock_bh(&ax25_route_lock);
+ ax25_dev_put(ax25_dev);
return 0;
}
ax25_rt = ax25_rt->next;
@@ -108,6 +112,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
if ((ax25_rt = kmalloc(sizeof(ax25_route), GFP_ATOMIC)) == NULL) {
write_unlock_bh(&ax25_route_lock);
+ ax25_dev_put(ax25_dev);
return -ENOMEM;
}
@@ -120,6 +125,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
if ((ax25_rt->digipeat = kmalloc(sizeof(ax25_digi), GFP_ATOMIC)) == NULL) {
write_unlock_bh(&ax25_route_lock);
kfree(ax25_rt);
+ ax25_dev_put(ax25_dev);
return -ENOMEM;
}
ax25_rt->digipeat->lastrepeat = -1;
@@ -132,6 +138,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route)
ax25_rt->next = ax25_route_list;
ax25_route_list = ax25_rt;
write_unlock_bh(&ax25_route_lock);
+ ax25_dev_put(ax25_dev);
return 0;
}
@@ -173,6 +180,7 @@ static int ax25_rt_del(struct ax25_routes_struct *route)
}
}
write_unlock_bh(&ax25_route_lock);
+ ax25_dev_put(ax25_dev);
return 0;
}
@@ -215,6 +223,7 @@ static int ax25_rt_opt(struct ax25_route_opt_struct *rt_option)
out:
write_unlock_bh(&ax25_route_lock);
+ ax25_dev_put(ax25_dev);
return err;
}
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index eba0efe64d05..fbf858ddec35 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -49,7 +49,7 @@ static void nft_reject_br_send_v4_tcp_reset(struct net *net,
{
struct sk_buff *nskb;
- nskb = nf_reject_skb_v4_tcp_reset(net, oldskb, dev, hook);
+ nskb = nf_reject_skb_v4_tcp_reset(net, oldskb, NULL, hook);
if (!nskb)
return;
@@ -65,7 +65,7 @@ static void nft_reject_br_send_v4_unreach(struct net *net,
{
struct sk_buff *nskb;
- nskb = nf_reject_skb_v4_unreach(net, oldskb, dev, hook, code);
+ nskb = nf_reject_skb_v4_unreach(net, oldskb, NULL, hook, code);
if (!nskb)
return;
@@ -81,7 +81,7 @@ static void nft_reject_br_send_v6_tcp_reset(struct net *net,
{
struct sk_buff *nskb;
- nskb = nf_reject_skb_v6_tcp_reset(net, oldskb, dev, hook);
+ nskb = nf_reject_skb_v6_tcp_reset(net, oldskb, NULL, hook);
if (!nskb)
return;
@@ -98,7 +98,7 @@ static void nft_reject_br_send_v6_unreach(struct net *net,
{
struct sk_buff *nskb;
- nskb = nf_reject_skb_v6_unreach(net, oldskb, dev, hook, code);
+ nskb = nf_reject_skb_v6_unreach(net, oldskb, NULL, hook, code);
if (!nskb)
return;
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index ecc400a0b7bb..4c6441536d55 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -246,6 +246,7 @@ enum {
Opt_cephx_sign_messages,
Opt_tcp_nodelay,
Opt_abort_on_full,
+ Opt_rxbounce,
};
enum {
@@ -295,6 +296,7 @@ static const struct fs_parameter_spec ceph_parameters[] = {
fsparam_u32 ("osdkeepalive", Opt_osdkeepalivetimeout),
fsparam_enum ("read_from_replica", Opt_read_from_replica,
ceph_param_read_from_replica),
+ fsparam_flag ("rxbounce", Opt_rxbounce),
fsparam_enum ("ms_mode", Opt_ms_mode,
ceph_param_ms_mode),
fsparam_string ("secret", Opt_secret),
@@ -584,6 +586,9 @@ int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt,
case Opt_abort_on_full:
opt->flags |= CEPH_OPT_ABORT_ON_FULL;
break;
+ case Opt_rxbounce:
+ opt->flags |= CEPH_OPT_RXBOUNCE;
+ break;
default:
BUG();
@@ -660,6 +665,8 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client,
seq_puts(m, "notcp_nodelay,");
if (show_all && (opt->flags & CEPH_OPT_ABORT_ON_FULL))
seq_puts(m, "abort_on_full,");
+ if (opt->flags & CEPH_OPT_RXBOUNCE)
+ seq_puts(m, "rxbounce,");
if (opt->mount_timeout != CEPH_MOUNT_TIMEOUT_DEFAULT)
seq_printf(m, "mount_timeout=%d,",
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 45eba2dcb67a..d3bb656308b4 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -515,6 +515,10 @@ static void ceph_con_reset_protocol(struct ceph_connection *con)
ceph_msg_put(con->out_msg);
con->out_msg = NULL;
}
+ if (con->bounce_page) {
+ __free_page(con->bounce_page);
+ con->bounce_page = NULL;
+ }
if (ceph_msgr2(from_msgr(con->msgr)))
ceph_con_v2_reset_protocol(con);
diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c
index 2cb5ffdf071a..6b014eca3a13 100644
--- a/net/ceph/messenger_v1.c
+++ b/net/ceph/messenger_v1.c
@@ -992,8 +992,7 @@ static int read_partial_message_section(struct ceph_connection *con,
static int read_partial_msg_data(struct ceph_connection *con)
{
- struct ceph_msg *msg = con->in_msg;
- struct ceph_msg_data_cursor *cursor = &msg->cursor;
+ struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor;
bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
struct page *page;
size_t page_offset;
@@ -1001,9 +1000,6 @@ static int read_partial_msg_data(struct ceph_connection *con)
u32 crc = 0;
int ret;
- if (!msg->num_data_items)
- return -EIO;
-
if (do_datacrc)
crc = con->in_data_crc;
while (cursor->total_resid) {
@@ -1031,6 +1027,46 @@ static int read_partial_msg_data(struct ceph_connection *con)
return 1; /* must return > 0 to indicate success */
}
+static int read_partial_msg_data_bounce(struct ceph_connection *con)
+{
+ struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor;
+ struct page *page;
+ size_t off, len;
+ u32 crc;
+ int ret;
+
+ if (unlikely(!con->bounce_page)) {
+ con->bounce_page = alloc_page(GFP_NOIO);
+ if (!con->bounce_page) {
+ pr_err("failed to allocate bounce page\n");
+ return -ENOMEM;
+ }
+ }
+
+ crc = con->in_data_crc;
+ while (cursor->total_resid) {
+ if (!cursor->resid) {
+ ceph_msg_data_advance(cursor, 0);
+ continue;
+ }
+
+ page = ceph_msg_data_next(cursor, &off, &len, NULL);
+ ret = ceph_tcp_recvpage(con->sock, con->bounce_page, 0, len);
+ if (ret <= 0) {
+ con->in_data_crc = crc;
+ return ret;
+ }
+
+ crc = crc32c(crc, page_address(con->bounce_page), ret);
+ memcpy_to_page(page, off, page_address(con->bounce_page), ret);
+
+ ceph_msg_data_advance(cursor, ret);
+ }
+ con->in_data_crc = crc;
+
+ return 1; /* must return > 0 to indicate success */
+}
+
/*
* read (part of) a message.
*/
@@ -1141,7 +1177,13 @@ static int read_partial_message(struct ceph_connection *con)
/* (page) data */
if (data_len) {
- ret = read_partial_msg_data(con);
+ if (!m->num_data_items)
+ return -EIO;
+
+ if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE))
+ ret = read_partial_msg_data_bounce(con);
+ else
+ ret = read_partial_msg_data(con);
if (ret <= 0)
return ret;
}
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index c4099b641b38..c81379f93ad5 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -57,8 +57,9 @@
#define IN_S_HANDLE_CONTROL_REMAINDER 3
#define IN_S_PREPARE_READ_DATA 4
#define IN_S_PREPARE_READ_DATA_CONT 5
-#define IN_S_HANDLE_EPILOGUE 6
-#define IN_S_FINISH_SKIP 7
+#define IN_S_PREPARE_READ_ENC_PAGE 6
+#define IN_S_HANDLE_EPILOGUE 7
+#define IN_S_FINISH_SKIP 8
#define OUT_S_QUEUE_DATA 1
#define OUT_S_QUEUE_DATA_CONT 2
@@ -1032,22 +1033,41 @@ static int decrypt_control_remainder(struct ceph_connection *con)
padded_len(rem_len) + CEPH_GCM_TAG_LEN);
}
-static int decrypt_message(struct ceph_connection *con)
+static int decrypt_tail(struct ceph_connection *con)
{
+ struct sg_table enc_sgt = {};
struct sg_table sgt = {};
+ int tail_len;
int ret;
+ tail_len = tail_onwire_len(con->in_msg, true);
+ ret = sg_alloc_table_from_pages(&enc_sgt, con->v2.in_enc_pages,
+ con->v2.in_enc_page_cnt, 0, tail_len,
+ GFP_NOIO);
+ if (ret)
+ goto out;
+
ret = setup_message_sgs(&sgt, con->in_msg, FRONT_PAD(con->v2.in_buf),
MIDDLE_PAD(con->v2.in_buf), DATA_PAD(con->v2.in_buf),
con->v2.in_buf, true);
if (ret)
goto out;
- ret = gcm_crypt(con, false, sgt.sgl, sgt.sgl,
- tail_onwire_len(con->in_msg, true));
+ dout("%s con %p msg %p enc_page_cnt %d sg_cnt %d\n", __func__, con,
+ con->in_msg, con->v2.in_enc_page_cnt, sgt.orig_nents);
+ ret = gcm_crypt(con, false, enc_sgt.sgl, sgt.sgl, tail_len);
+ if (ret)
+ goto out;
+
+ WARN_ON(!con->v2.in_enc_page_cnt);
+ ceph_release_page_vector(con->v2.in_enc_pages,
+ con->v2.in_enc_page_cnt);
+ con->v2.in_enc_pages = NULL;
+ con->v2.in_enc_page_cnt = 0;
out:
sg_free_table(&sgt);
+ sg_free_table(&enc_sgt);
return ret;
}
@@ -1733,54 +1753,157 @@ static int prepare_read_control_remainder(struct ceph_connection *con)
return 0;
}
-static void prepare_read_data(struct ceph_connection *con)
+static int prepare_read_data(struct ceph_connection *con)
{
struct bio_vec bv;
- if (!con_secure(con))
- con->in_data_crc = -1;
+ con->in_data_crc = -1;
ceph_msg_data_cursor_init(&con->v2.in_cursor, con->in_msg,
data_len(con->in_msg));
get_bvec_at(&con->v2.in_cursor, &bv);
- set_in_bvec(con, &bv);
+ if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) {
+ if (unlikely(!con->bounce_page)) {
+ con->bounce_page = alloc_page(GFP_NOIO);
+ if (!con->bounce_page) {
+ pr_err("failed to allocate bounce page\n");
+ return -ENOMEM;
+ }
+ }
+
+ bv.bv_page = con->bounce_page;
+ bv.bv_offset = 0;
+ set_in_bvec(con, &bv);
+ } else {
+ set_in_bvec(con, &bv);
+ }
con->v2.in_state = IN_S_PREPARE_READ_DATA_CONT;
+ return 0;
}
static void prepare_read_data_cont(struct ceph_connection *con)
{
struct bio_vec bv;
- if (!con_secure(con))
+ if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) {
+ con->in_data_crc = crc32c(con->in_data_crc,
+ page_address(con->bounce_page),
+ con->v2.in_bvec.bv_len);
+
+ get_bvec_at(&con->v2.in_cursor, &bv);
+ memcpy_to_page(bv.bv_page, bv.bv_offset,
+ page_address(con->bounce_page),
+ con->v2.in_bvec.bv_len);
+ } else {
con->in_data_crc = ceph_crc32c_page(con->in_data_crc,
con->v2.in_bvec.bv_page,
con->v2.in_bvec.bv_offset,
con->v2.in_bvec.bv_len);
+ }
ceph_msg_data_advance(&con->v2.in_cursor, con->v2.in_bvec.bv_len);
if (con->v2.in_cursor.total_resid) {
get_bvec_at(&con->v2.in_cursor, &bv);
- set_in_bvec(con, &bv);
+ if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) {
+ bv.bv_page = con->bounce_page;
+ bv.bv_offset = 0;
+ set_in_bvec(con, &bv);
+ } else {
+ set_in_bvec(con, &bv);
+ }
WARN_ON(con->v2.in_state != IN_S_PREPARE_READ_DATA_CONT);
return;
}
/*
- * We've read all data. Prepare to read data padding (if any)
- * and epilogue.
+ * We've read all data. Prepare to read epilogue.
*/
reset_in_kvecs(con);
- if (con_secure(con)) {
- if (need_padding(data_len(con->in_msg)))
- add_in_kvec(con, DATA_PAD(con->v2.in_buf),
- padding_len(data_len(con->in_msg)));
- add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_SECURE_LEN);
+ add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_PLAIN_LEN);
+ con->v2.in_state = IN_S_HANDLE_EPILOGUE;
+}
+
+static int prepare_read_tail_plain(struct ceph_connection *con)
+{
+ struct ceph_msg *msg = con->in_msg;
+
+ if (!front_len(msg) && !middle_len(msg)) {
+ WARN_ON(!data_len(msg));
+ return prepare_read_data(con);
+ }
+
+ reset_in_kvecs(con);
+ if (front_len(msg)) {
+ add_in_kvec(con, msg->front.iov_base, front_len(msg));
+ WARN_ON(msg->front.iov_len != front_len(msg));
+ }
+ if (middle_len(msg)) {
+ add_in_kvec(con, msg->middle->vec.iov_base, middle_len(msg));
+ WARN_ON(msg->middle->vec.iov_len != middle_len(msg));
+ }
+
+ if (data_len(msg)) {
+ con->v2.in_state = IN_S_PREPARE_READ_DATA;
} else {
add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_PLAIN_LEN);
+ con->v2.in_state = IN_S_HANDLE_EPILOGUE;
}
+ return 0;
+}
+
+static void prepare_read_enc_page(struct ceph_connection *con)
+{
+ struct bio_vec bv;
+
+ dout("%s con %p i %d resid %d\n", __func__, con, con->v2.in_enc_i,
+ con->v2.in_enc_resid);
+ WARN_ON(!con->v2.in_enc_resid);
+
+ bv.bv_page = con->v2.in_enc_pages[con->v2.in_enc_i];
+ bv.bv_offset = 0;
+ bv.bv_len = min(con->v2.in_enc_resid, (int)PAGE_SIZE);
+
+ set_in_bvec(con, &bv);
+ con->v2.in_enc_i++;
+ con->v2.in_enc_resid -= bv.bv_len;
+
+ if (con->v2.in_enc_resid) {
+ con->v2.in_state = IN_S_PREPARE_READ_ENC_PAGE;
+ return;
+ }
+
+ /*
+ * We are set to read the last piece of ciphertext (ending
+ * with epilogue) + auth tag.
+ */
+ WARN_ON(con->v2.in_enc_i != con->v2.in_enc_page_cnt);
con->v2.in_state = IN_S_HANDLE_EPILOGUE;
}
+static int prepare_read_tail_secure(struct ceph_connection *con)
+{
+ struct page **enc_pages;
+ int enc_page_cnt;
+ int tail_len;
+
+ tail_len = tail_onwire_len(con->in_msg, true);
+ WARN_ON(!tail_len);
+
+ enc_page_cnt = calc_pages_for(0, tail_len);
+ enc_pages = ceph_alloc_page_vector(enc_page_cnt, GFP_NOIO);
+ if (IS_ERR(enc_pages))
+ return PTR_ERR(enc_pages);
+
+ WARN_ON(con->v2.in_enc_pages || con->v2.in_enc_page_cnt);
+ con->v2.in_enc_pages = enc_pages;
+ con->v2.in_enc_page_cnt = enc_page_cnt;
+ con->v2.in_enc_resid = tail_len;
+ con->v2.in_enc_i = 0;
+
+ prepare_read_enc_page(con);
+ return 0;
+}
+
static void __finish_skip(struct ceph_connection *con)
{
con->in_seq++;
@@ -2589,47 +2712,26 @@ static int __handle_control(struct ceph_connection *con, void *p)
}
msg = con->in_msg; /* set in process_message_header() */
- if (!front_len(msg) && !middle_len(msg)) {
- if (!data_len(msg))
- return process_message(con);
-
- prepare_read_data(con);
- return 0;
- }
-
- reset_in_kvecs(con);
if (front_len(msg)) {
WARN_ON(front_len(msg) > msg->front_alloc_len);
- add_in_kvec(con, msg->front.iov_base, front_len(msg));
msg->front.iov_len = front_len(msg);
-
- if (con_secure(con) && need_padding(front_len(msg)))
- add_in_kvec(con, FRONT_PAD(con->v2.in_buf),
- padding_len(front_len(msg)));
} else {
msg->front.iov_len = 0;
}
if (middle_len(msg)) {
WARN_ON(middle_len(msg) > msg->middle->alloc_len);
- add_in_kvec(con, msg->middle->vec.iov_base, middle_len(msg));
msg->middle->vec.iov_len = middle_len(msg);
-
- if (con_secure(con) && need_padding(middle_len(msg)))
- add_in_kvec(con, MIDDLE_PAD(con->v2.in_buf),
- padding_len(middle_len(msg)));
} else if (msg->middle) {
msg->middle->vec.iov_len = 0;
}
- if (data_len(msg)) {
- con->v2.in_state = IN_S_PREPARE_READ_DATA;
- } else {
- add_in_kvec(con, con->v2.in_buf,
- con_secure(con) ? CEPH_EPILOGUE_SECURE_LEN :
- CEPH_EPILOGUE_PLAIN_LEN);
- con->v2.in_state = IN_S_HANDLE_EPILOGUE;
- }
- return 0;
+ if (!front_len(msg) && !middle_len(msg) && !data_len(msg))
+ return process_message(con);
+
+ if (con_secure(con))
+ return prepare_read_tail_secure(con);
+
+ return prepare_read_tail_plain(con);
}
static int handle_preamble(struct ceph_connection *con)
@@ -2717,7 +2819,7 @@ static int handle_epilogue(struct ceph_connection *con)
int ret;
if (con_secure(con)) {
- ret = decrypt_message(con);
+ ret = decrypt_tail(con);
if (ret) {
if (ret == -EBADMSG)
con->error_msg = "integrity error, bad epilogue auth tag";
@@ -2785,13 +2887,16 @@ static int populate_in_iter(struct ceph_connection *con)
ret = handle_control_remainder(con);
break;
case IN_S_PREPARE_READ_DATA:
- prepare_read_data(con);
- ret = 0;
+ ret = prepare_read_data(con);
break;
case IN_S_PREPARE_READ_DATA_CONT:
prepare_read_data_cont(con);
ret = 0;
break;
+ case IN_S_PREPARE_READ_ENC_PAGE:
+ prepare_read_enc_page(con);
+ ret = 0;
+ break;
case IN_S_HANDLE_EPILOGUE:
ret = handle_epilogue(con);
break;
@@ -3326,20 +3431,16 @@ void ceph_con_v2_revoke(struct ceph_connection *con)
static void revoke_at_prepare_read_data(struct ceph_connection *con)
{
- int remaining; /* data + [data padding] + epilogue */
+ int remaining;
int resid;
+ WARN_ON(con_secure(con));
WARN_ON(!data_len(con->in_msg));
WARN_ON(!iov_iter_is_kvec(&con->v2.in_iter));
resid = iov_iter_count(&con->v2.in_iter);
WARN_ON(!resid);
- if (con_secure(con))
- remaining = padded_len(data_len(con->in_msg)) +
- CEPH_EPILOGUE_SECURE_LEN;
- else
- remaining = data_len(con->in_msg) + CEPH_EPILOGUE_PLAIN_LEN;
-
+ remaining = data_len(con->in_msg) + CEPH_EPILOGUE_PLAIN_LEN;
dout("%s con %p resid %d remaining %d\n", __func__, con, resid,
remaining);
con->v2.in_iter.count -= resid;
@@ -3350,8 +3451,9 @@ static void revoke_at_prepare_read_data(struct ceph_connection *con)
static void revoke_at_prepare_read_data_cont(struct ceph_connection *con)
{
int recved, resid; /* current piece of data */
- int remaining; /* [data padding] + epilogue */
+ int remaining;
+ WARN_ON(con_secure(con));
WARN_ON(!data_len(con->in_msg));
WARN_ON(!iov_iter_is_bvec(&con->v2.in_iter));
resid = iov_iter_count(&con->v2.in_iter);
@@ -3363,12 +3465,7 @@ static void revoke_at_prepare_read_data_cont(struct ceph_connection *con)
ceph_msg_data_advance(&con->v2.in_cursor, recved);
WARN_ON(resid > con->v2.in_cursor.total_resid);
- if (con_secure(con))
- remaining = padding_len(data_len(con->in_msg)) +
- CEPH_EPILOGUE_SECURE_LEN;
- else
- remaining = CEPH_EPILOGUE_PLAIN_LEN;
-
+ remaining = CEPH_EPILOGUE_PLAIN_LEN;
dout("%s con %p total_resid %zu remaining %d\n", __func__, con,
con->v2.in_cursor.total_resid, remaining);
con->v2.in_iter.count -= resid;
@@ -3376,11 +3473,26 @@ static void revoke_at_prepare_read_data_cont(struct ceph_connection *con)
con->v2.in_state = IN_S_FINISH_SKIP;
}
+static void revoke_at_prepare_read_enc_page(struct ceph_connection *con)
+{
+ int resid; /* current enc page (not necessarily data) */
+
+ WARN_ON(!con_secure(con));
+ WARN_ON(!iov_iter_is_bvec(&con->v2.in_iter));
+ resid = iov_iter_count(&con->v2.in_iter);
+ WARN_ON(!resid || resid > con->v2.in_bvec.bv_len);
+
+ dout("%s con %p resid %d enc_resid %d\n", __func__, con, resid,
+ con->v2.in_enc_resid);
+ con->v2.in_iter.count -= resid;
+ set_in_skip(con, resid + con->v2.in_enc_resid);
+ con->v2.in_state = IN_S_FINISH_SKIP;
+}
+
static void revoke_at_handle_epilogue(struct ceph_connection *con)
{
int resid;
- WARN_ON(!iov_iter_is_kvec(&con->v2.in_iter));
resid = iov_iter_count(&con->v2.in_iter);
WARN_ON(!resid);
@@ -3399,6 +3511,9 @@ void ceph_con_v2_revoke_incoming(struct ceph_connection *con)
case IN_S_PREPARE_READ_DATA_CONT:
revoke_at_prepare_read_data_cont(con);
break;
+ case IN_S_PREPARE_READ_ENC_PAGE:
+ revoke_at_prepare_read_enc_page(con);
+ break;
case IN_S_HANDLE_EPILOGUE:
revoke_at_handle_epilogue(con);
break;
@@ -3432,6 +3547,13 @@ void ceph_con_v2_reset_protocol(struct ceph_connection *con)
clear_out_sign_kvecs(con);
free_conn_bufs(con);
+ if (con->v2.in_enc_pages) {
+ WARN_ON(!con->v2.in_enc_page_cnt);
+ ceph_release_page_vector(con->v2.in_enc_pages,
+ con->v2.in_enc_page_cnt);
+ con->v2.in_enc_pages = NULL;
+ con->v2.in_enc_page_cnt = 0;
+ }
if (con->v2.out_enc_pages) {
WARN_ON(!con->v2.out_enc_page_cnt);
ceph_release_page_vector(con->v2.out_enc_pages,
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 6c2016f7f3d1..ec0bf737b076 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1133,7 +1133,8 @@ out:
neigh_release(neigh);
}
-int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
+int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb,
+ const bool immediate_ok)
{
int rc;
bool immediate_probe = false;
@@ -1154,12 +1155,17 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
atomic_set(&neigh->probes,
NEIGH_VAR(neigh->parms, UCAST_PROBES));
neigh_del_timer(neigh);
- neigh->nud_state = NUD_INCOMPLETE;
+ neigh->nud_state = NUD_INCOMPLETE;
neigh->updated = now;
- next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME),
- HZ/100);
+ if (!immediate_ok) {
+ next = now + 1;
+ } else {
+ immediate_probe = true;
+ next = now + max(NEIGH_VAR(neigh->parms,
+ RETRANS_TIME),
+ HZ / 100);
+ }
neigh_add_timer(neigh, next);
- immediate_probe = true;
} else {
neigh->nud_state = NUD_FAILED;
neigh->updated = jiffies;
@@ -1571,7 +1577,7 @@ static void neigh_managed_work(struct work_struct *work)
write_lock_bh(&tbl->lock);
list_for_each_entry(neigh, &tbl->managed_list, managed_list)
- neigh_event_send(neigh, NULL);
+ neigh_event_send_probe(neigh, NULL, false);
queue_delayed_work(system_power_efficient_wq, &tbl->managed_work,
NEIGH_VAR(&tbl->parms, DELAY_PROBE_TIME));
write_unlock_bh(&tbl->lock);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e476403231f0..710da8a36729 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3275,8 +3275,8 @@ static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct nlattr *slave_attr[RTNL_SLAVE_MAX_TYPE + 1];
unsigned char name_assign_type = NET_NAME_USER;
struct nlattr *linkinfo[IFLA_INFO_MAX + 1];
- const struct rtnl_link_ops *m_ops = NULL;
- struct net_device *master_dev = NULL;
+ const struct rtnl_link_ops *m_ops;
+ struct net_device *master_dev;
struct net *net = sock_net(skb->sk);
const struct rtnl_link_ops *ops;
struct nlattr *tb[IFLA_MAX + 1];
@@ -3314,6 +3314,8 @@ replay:
else
dev = NULL;
+ master_dev = NULL;
+ m_ops = NULL;
if (dev) {
master_dev = netdev_master_upper_dev_get(dev);
if (master_dev)
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 277124f206e0..e0b072aecf0f 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -1441,7 +1441,7 @@ static int nl802154_send_key(struct sk_buff *msg, u32 cmd, u32 portid,
hdr = nl802154hdr_put(msg, portid, seq, flags, cmd);
if (!hdr)
- return -1;
+ return -ENOBUFS;
if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex))
goto nla_put_failure;
@@ -1634,7 +1634,7 @@ static int nl802154_send_device(struct sk_buff *msg, u32 cmd, u32 portid,
hdr = nl802154hdr_put(msg, portid, seq, flags, cmd);
if (!hdr)
- return -1;
+ return -ENOBUFS;
if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex))
goto nla_put_failure;
@@ -1812,7 +1812,7 @@ static int nl802154_send_devkey(struct sk_buff *msg, u32 cmd, u32 portid,
hdr = nl802154hdr_put(msg, portid, seq, flags, cmd);
if (!hdr)
- return -1;
+ return -ENOBUFS;
if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex))
goto nla_put_failure;
@@ -1988,7 +1988,7 @@ static int nl802154_send_seclevel(struct sk_buff *msg, u32 cmd, u32 portid,
hdr = nl802154hdr_put(msg, portid, seq, flags, cmd);
if (!hdr)
- return -1;
+ return -ENOBUFS;
if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex))
goto nla_put_failure;
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 67087f95579f..aab384126f61 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -58,10 +58,6 @@ config NF_TABLES_ARP
endif # NF_TABLES
-config NF_FLOW_TABLE_IPV4
- tristate
- select NF_FLOW_TABLE_INET
-
config NF_DUP_IPV4
tristate "Netfilter IPv4 packet duplication to alternate destination"
depends on !NF_CONNTRACK || NF_CONNTRACK
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 78e81465f5f3..bdf108f544a4 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1322,10 +1322,13 @@ new_segment:
/* skb changing from pure zc to mixed, must charge zc */
if (unlikely(skb_zcopy_pure(skb))) {
- if (!sk_wmem_schedule(sk, skb->data_len))
+ u32 extra = skb->truesize -
+ SKB_TRUESIZE(skb_end_offset(skb));
+
+ if (!sk_wmem_schedule(sk, extra))
goto wait_for_space;
- sk_mem_charge(sk, skb->data_len);
+ sk_mem_charge(sk, extra);
skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY;
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index dc49a3d551eb..bfe4112e000c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1660,6 +1660,8 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
(mss != tcp_skb_seglen(skb)))
goto out;
+ if (!tcp_skb_can_collapse(prev, skb))
+ goto out;
len = skb->len;
pcount = tcp_skb_pcount(skb);
if (tcp_skb_shift(prev, skb, pcount, len))
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 97d3d1b36dbc..0ba62f4868f9 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -47,10 +47,6 @@ config NFT_FIB_IPV6
endif # NF_TABLES_IPV6
endif # NF_TABLES
-config NF_FLOW_TABLE_IPV6
- tristate
- select NF_FLOW_TABLE_INET
-
config NF_DUP_IPV6
tristate "Netfilter IPv6 packet duplication to alternate destination"
depends on !NF_CONNTRACK || NF_CONNTRACK
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index b85383606df7..b8d6dc9aeeb6 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -28,9 +28,6 @@ obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
obj-$(CONFIG_NFT_DUP_IPV6) += nft_dup_ipv6.o
obj-$(CONFIG_NFT_FIB_IPV6) += nft_fib_ipv6.o
-# flow table support
-obj-$(CONFIG_NF_FLOW_TABLE_IPV6) += nf_flow_table_ipv6.o
-
# matches
obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
obj-$(CONFIG_IP6_NF_MATCH_EUI64) += ip6t_eui64.o
diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c
deleted file mode 100644
index e69de29bb2d1..000000000000
--- a/net/ipv6/netfilter/nf_flow_table_ipv6.c
+++ /dev/null
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index cf454f8ca2b0..5fa16990da95 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2011,7 +2011,6 @@ static void nft_last_rule(struct nft_rule_blob *blob, const void *ptr)
prule = (struct nft_rule_dp *)ptr;
prule->is_last = 1;
- ptr += offsetof(struct nft_rule_dp, data);
/* blob size does not include the trailer rule */
}
diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c
index 9d5947ab8d4e..e646e9ee4a98 100644
--- a/net/netfilter/nft_byteorder.c
+++ b/net/netfilter/nft_byteorder.c
@@ -167,12 +167,24 @@ nla_put_failure:
return -1;
}
+static bool nft_byteorder_reduce(struct nft_regs_track *track,
+ const struct nft_expr *expr)
+{
+ struct nft_byteorder *priv = nft_expr_priv(expr);
+
+ track->regs[priv->dreg].selector = NULL;
+ track->regs[priv->dreg].bitwise = NULL;
+
+ return false;
+}
+
static const struct nft_expr_ops nft_byteorder_ops = {
.type = &nft_byteorder_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_byteorder)),
.eval = nft_byteorder_eval,
.init = nft_byteorder_init,
.dump = nft_byteorder_dump,
+ .reduce = nft_byteorder_reduce,
};
struct nft_expr_type nft_byteorder_type __read_mostly = {
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 518d96c8c247..5adf8bb628a8 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -260,9 +260,12 @@ static void nft_ct_set_zone_eval(const struct nft_expr *expr,
ct = this_cpu_read(nft_ct_pcpu_template);
if (likely(refcount_read(&ct->ct_general.use) == 1)) {
+ refcount_inc(&ct->ct_general.use);
nf_ct_zone_add(ct, &zone);
} else {
- /* previous skb got queued to userspace */
+ /* previous skb got queued to userspace, allocate temporary
+ * one until percpu template can be reused.
+ */
ct = nf_ct_tmpl_alloc(nft_net(pkt), &zone, GFP_ATOMIC);
if (!ct) {
regs->verdict.code = NF_DROP;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 85ea7ddb48db..ab87f22cc7ec 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1789,7 +1789,10 @@ static int fanout_add(struct sock *sk, struct fanout_args *args)
err = -ENOSPC;
if (refcount_read(&match->sk_ref) < match->max_num_members) {
__dev_remove_pack(&po->prot_hook);
- po->fanout = match;
+
+ /* Paired with packet_setsockopt(PACKET_FANOUT_DATA) */
+ WRITE_ONCE(po->fanout, match);
+
po->rollover = rollover;
rollover = NULL;
refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1);
@@ -3934,7 +3937,8 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval,
}
case PACKET_FANOUT_DATA:
{
- if (!po->fanout)
+ /* Paired with the WRITE_ONCE() in fanout_add() */
+ if (!READ_ONCE(po->fanout))
return -EINVAL;
return fanout_set_data(po, optval, optlen);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index d4e27c679123..5f0f346b576f 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1945,9 +1945,9 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
bool prio_allocate;
u32 parent;
u32 chain_index;
- struct Qdisc *q = NULL;
+ struct Qdisc *q;
struct tcf_chain_info chain_info;
- struct tcf_chain *chain = NULL;
+ struct tcf_chain *chain;
struct tcf_block *block;
struct tcf_proto *tp;
unsigned long cl;
@@ -1976,6 +1976,8 @@ replay:
tp = NULL;
cl = 0;
block = NULL;
+ q = NULL;
+ chain = NULL;
flags = 0;
if (prio == 0) {
@@ -2798,8 +2800,8 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
struct tcmsg *t;
u32 parent;
u32 chain_index;
- struct Qdisc *q = NULL;
- struct tcf_chain *chain = NULL;
+ struct Qdisc *q;
+ struct tcf_chain *chain;
struct tcf_block *block;
unsigned long cl;
int err;
@@ -2809,6 +2811,7 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
return -EPERM;
replay:
+ q = NULL;
err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX,
rtm_tca_policy, extack);
if (err < 0)
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index d5ea62b82bb8..8c89d0b0ca18 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -566,17 +566,115 @@ static void smc_stat_fallback(struct smc_sock *smc)
mutex_unlock(&net->smc.mutex_fback_rsn);
}
+/* must be called under rcu read lock */
+static void smc_fback_wakeup_waitqueue(struct smc_sock *smc, void *key)
+{
+ struct socket_wq *wq;
+ __poll_t flags;
+
+ wq = rcu_dereference(smc->sk.sk_wq);
+ if (!skwq_has_sleeper(wq))
+ return;
+
+ /* wake up smc sk->sk_wq */
+ if (!key) {
+ /* sk_state_change */
+ wake_up_interruptible_all(&wq->wait);
+ } else {
+ flags = key_to_poll(key);
+ if (flags & (EPOLLIN | EPOLLOUT))
+ /* sk_data_ready or sk_write_space */
+ wake_up_interruptible_sync_poll(&wq->wait, flags);
+ else if (flags & EPOLLERR)
+ /* sk_error_report */
+ wake_up_interruptible_poll(&wq->wait, flags);
+ }
+}
+
+static int smc_fback_mark_woken(wait_queue_entry_t *wait,
+ unsigned int mode, int sync, void *key)
+{
+ struct smc_mark_woken *mark =
+ container_of(wait, struct smc_mark_woken, wait_entry);
+
+ mark->woken = true;
+ mark->key = key;
+ return 0;
+}
+
+static void smc_fback_forward_wakeup(struct smc_sock *smc, struct sock *clcsk,
+ void (*clcsock_callback)(struct sock *sk))
+{
+ struct smc_mark_woken mark = { .woken = false };
+ struct socket_wq *wq;
+
+ init_waitqueue_func_entry(&mark.wait_entry,
+ smc_fback_mark_woken);
+ rcu_read_lock();
+ wq = rcu_dereference(clcsk->sk_wq);
+ if (!wq)
+ goto out;
+ add_wait_queue(sk_sleep(clcsk), &mark.wait_entry);
+ clcsock_callback(clcsk);
+ remove_wait_queue(sk_sleep(clcsk), &mark.wait_entry);
+
+ if (mark.woken)
+ smc_fback_wakeup_waitqueue(smc, mark.key);
+out:
+ rcu_read_unlock();
+}
+
+static void smc_fback_state_change(struct sock *clcsk)
+{
+ struct smc_sock *smc =
+ smc_clcsock_user_data(clcsk);
+
+ if (!smc)
+ return;
+ smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_state_change);
+}
+
+static void smc_fback_data_ready(struct sock *clcsk)
+{
+ struct smc_sock *smc =
+ smc_clcsock_user_data(clcsk);
+
+ if (!smc)
+ return;
+ smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_data_ready);
+}
+
+static void smc_fback_write_space(struct sock *clcsk)
+{
+ struct smc_sock *smc =
+ smc_clcsock_user_data(clcsk);
+
+ if (!smc)
+ return;
+ smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_write_space);
+}
+
+static void smc_fback_error_report(struct sock *clcsk)
+{
+ struct smc_sock *smc =
+ smc_clcsock_user_data(clcsk);
+
+ if (!smc)
+ return;
+ smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_error_report);
+}
+
static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
{
- wait_queue_head_t *smc_wait = sk_sleep(&smc->sk);
- wait_queue_head_t *clc_wait;
- unsigned long flags;
+ struct sock *clcsk;
mutex_lock(&smc->clcsock_release_lock);
if (!smc->clcsock) {
mutex_unlock(&smc->clcsock_release_lock);
return -EBADF;
}
+ clcsk = smc->clcsock->sk;
+
smc->use_fallback = true;
smc->fallback_rsn = reason_code;
smc_stat_fallback(smc);
@@ -587,16 +685,22 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
smc->clcsock->wq.fasync_list =
smc->sk.sk_socket->wq.fasync_list;
- /* There may be some entries remaining in
- * smc socket->wq, which should be removed
- * to clcsocket->wq during the fallback.
+ /* There might be some wait entries remaining
+ * in smc sk->sk_wq and they should be woken up
+ * as clcsock's wait queue is woken up.
*/
- clc_wait = sk_sleep(smc->clcsock->sk);
- spin_lock_irqsave(&smc_wait->lock, flags);
- spin_lock_nested(&clc_wait->lock, SINGLE_DEPTH_NESTING);
- list_splice_init(&smc_wait->head, &clc_wait->head);
- spin_unlock(&clc_wait->lock);
- spin_unlock_irqrestore(&smc_wait->lock, flags);
+ smc->clcsk_state_change = clcsk->sk_state_change;
+ smc->clcsk_data_ready = clcsk->sk_data_ready;
+ smc->clcsk_write_space = clcsk->sk_write_space;
+ smc->clcsk_error_report = clcsk->sk_error_report;
+
+ clcsk->sk_state_change = smc_fback_state_change;
+ clcsk->sk_data_ready = smc_fback_data_ready;
+ clcsk->sk_write_space = smc_fback_write_space;
+ clcsk->sk_error_report = smc_fback_error_report;
+
+ smc->clcsock->sk->sk_user_data =
+ (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY);
}
mutex_unlock(&smc->clcsock_release_lock);
return 0;
@@ -2115,10 +2219,9 @@ out:
static void smc_clcsock_data_ready(struct sock *listen_clcsock)
{
- struct smc_sock *lsmc;
+ struct smc_sock *lsmc =
+ smc_clcsock_user_data(listen_clcsock);
- lsmc = (struct smc_sock *)
- ((uintptr_t)listen_clcsock->sk_user_data & ~SK_USER_DATA_NOCOPY);
if (!lsmc)
return;
lsmc->clcsk_data_ready(listen_clcsock);
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 3d0b8e300deb..37b2001a0255 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -139,6 +139,12 @@ enum smc_urg_state {
SMC_URG_READ = 3, /* data was already read */
};
+struct smc_mark_woken {
+ bool woken;
+ void *key;
+ wait_queue_entry_t wait_entry;
+};
+
struct smc_connection {
struct rb_node alert_node;
struct smc_link_group *lgr; /* link group of connection */
@@ -228,8 +234,14 @@ struct smc_connection {
struct smc_sock { /* smc sock container */
struct sock sk;
struct socket *clcsock; /* internal tcp socket */
+ void (*clcsk_state_change)(struct sock *sk);
+ /* original stat_change fct. */
void (*clcsk_data_ready)(struct sock *sk);
- /* original data_ready fct. **/
+ /* original data_ready fct. */
+ void (*clcsk_write_space)(struct sock *sk);
+ /* original write_space fct. */
+ void (*clcsk_error_report)(struct sock *sk);
+ /* original error_report fct. */
struct smc_connection conn; /* smc connection */
struct smc_sock *listen_smc; /* listen parent */
struct work_struct connect_work; /* handle non-blocking connect*/
@@ -264,6 +276,12 @@ static inline struct smc_sock *smc_sk(const struct sock *sk)
return (struct smc_sock *)sk;
}
+static inline struct smc_sock *smc_clcsock_user_data(struct sock *clcsk)
+{
+ return (struct smc_sock *)
+ ((uintptr_t)clcsk->sk_user_data & ~SK_USER_DATA_NOCOPY);
+}
+
extern struct workqueue_struct *smc_hs_wq; /* wq for handshake work */
extern struct workqueue_struct *smc_close_wq; /* wq for close work */
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index b8898c787d23..1fca2f90a9c7 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -146,13 +146,11 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
(req->diag_ext & (1 << (SMC_DIAG_LGRINFO - 1))) &&
!list_empty(&smc->conn.lgr->list)) {
struct smc_link *link = smc->conn.lnk;
- struct net *net = read_pnet(&link->smcibdev->ibdev->coredev.rdma_net);
struct smc_diag_lgrinfo linfo = {
.role = smc->conn.lgr->role,
.lnk[0].ibport = link->ibport,
.lnk[0].link_id = link->link_id,
- .lnk[0].net_cookie = net->net_cookie,
};
memcpy(linfo.lnk[0].ibname,
diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c
index 2ec6e5cd25d9..feb206f3acb4 100644
--- a/security/selinux/ss/conditional.c
+++ b/security/selinux/ss/conditional.c
@@ -152,6 +152,8 @@ static void cond_list_destroy(struct policydb *p)
for (i = 0; i < p->cond_list_len; i++)
cond_node_destroy(&p->cond_list[i]);
kfree(p->cond_list);
+ p->cond_list = NULL;
+ p->cond_list_len = 0;
}
void cond_policydb_destroy(struct policydb *p)
@@ -441,7 +443,6 @@ int cond_read_list(struct policydb *p, void *fp)
return 0;
err:
cond_list_destroy(p);
- p->cond_list = NULL;
return rc;
}
diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile
index 9ddeca947635..320a88ac28c9 100644
--- a/tools/bpf/resolve_btfids/Makefile
+++ b/tools/bpf/resolve_btfids/Makefile
@@ -9,7 +9,11 @@ ifeq ($(V),1)
msg =
else
Q = @
- msg = @printf ' %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))";
+ ifeq ($(silent),1)
+ msg =
+ else
+ msg = @printf ' %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))";
+ endif
MAKEFLAGS=--no-print-directory
endif
diff --git a/tools/include/uapi/linux/lirc.h b/tools/include/uapi/linux/lirc.h
deleted file mode 100644
index 45fcbf99d72e..000000000000
--- a/tools/include/uapi/linux/lirc.h
+++ /dev/null
@@ -1,229 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * lirc.h - linux infrared remote control header file
- * last modified 2010/07/13 by Jarod Wilson
- */
-
-#ifndef _LINUX_LIRC_H
-#define _LINUX_LIRC_H
-
-#include <linux/types.h>
-#include <linux/ioctl.h>
-
-#define PULSE_BIT 0x01000000
-#define PULSE_MASK 0x00FFFFFF
-
-#define LIRC_MODE2_SPACE 0x00000000
-#define LIRC_MODE2_PULSE 0x01000000
-#define LIRC_MODE2_FREQUENCY 0x02000000
-#define LIRC_MODE2_TIMEOUT 0x03000000
-
-#define LIRC_VALUE_MASK 0x00FFFFFF
-#define LIRC_MODE2_MASK 0xFF000000
-
-#define LIRC_SPACE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_SPACE)
-#define LIRC_PULSE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_PULSE)
-#define LIRC_FREQUENCY(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_FREQUENCY)
-#define LIRC_TIMEOUT(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_TIMEOUT)
-
-#define LIRC_VALUE(val) ((val)&LIRC_VALUE_MASK)
-#define LIRC_MODE2(val) ((val)&LIRC_MODE2_MASK)
-
-#define LIRC_IS_SPACE(val) (LIRC_MODE2(val) == LIRC_MODE2_SPACE)
-#define LIRC_IS_PULSE(val) (LIRC_MODE2(val) == LIRC_MODE2_PULSE)
-#define LIRC_IS_FREQUENCY(val) (LIRC_MODE2(val) == LIRC_MODE2_FREQUENCY)
-#define LIRC_IS_TIMEOUT(val) (LIRC_MODE2(val) == LIRC_MODE2_TIMEOUT)
-
-/* used heavily by lirc userspace */
-#define lirc_t int
-
-/*** lirc compatible hardware features ***/
-
-#define LIRC_MODE2SEND(x) (x)
-#define LIRC_SEND2MODE(x) (x)
-#define LIRC_MODE2REC(x) ((x) << 16)
-#define LIRC_REC2MODE(x) ((x) >> 16)
-
-#define LIRC_MODE_RAW 0x00000001
-#define LIRC_MODE_PULSE 0x00000002
-#define LIRC_MODE_MODE2 0x00000004
-#define LIRC_MODE_SCANCODE 0x00000008
-#define LIRC_MODE_LIRCCODE 0x00000010
-
-
-#define LIRC_CAN_SEND_RAW LIRC_MODE2SEND(LIRC_MODE_RAW)
-#define LIRC_CAN_SEND_PULSE LIRC_MODE2SEND(LIRC_MODE_PULSE)
-#define LIRC_CAN_SEND_MODE2 LIRC_MODE2SEND(LIRC_MODE_MODE2)
-#define LIRC_CAN_SEND_LIRCCODE LIRC_MODE2SEND(LIRC_MODE_LIRCCODE)
-
-#define LIRC_CAN_SEND_MASK 0x0000003f
-
-#define LIRC_CAN_SET_SEND_CARRIER 0x00000100
-#define LIRC_CAN_SET_SEND_DUTY_CYCLE 0x00000200
-#define LIRC_CAN_SET_TRANSMITTER_MASK 0x00000400
-
-#define LIRC_CAN_REC_RAW LIRC_MODE2REC(LIRC_MODE_RAW)
-#define LIRC_CAN_REC_PULSE LIRC_MODE2REC(LIRC_MODE_PULSE)
-#define LIRC_CAN_REC_MODE2 LIRC_MODE2REC(LIRC_MODE_MODE2)
-#define LIRC_CAN_REC_SCANCODE LIRC_MODE2REC(LIRC_MODE_SCANCODE)
-#define LIRC_CAN_REC_LIRCCODE LIRC_MODE2REC(LIRC_MODE_LIRCCODE)
-
-#define LIRC_CAN_REC_MASK LIRC_MODE2REC(LIRC_CAN_SEND_MASK)
-
-#define LIRC_CAN_SET_REC_CARRIER (LIRC_CAN_SET_SEND_CARRIER << 16)
-#define LIRC_CAN_SET_REC_DUTY_CYCLE (LIRC_CAN_SET_SEND_DUTY_CYCLE << 16)
-
-#define LIRC_CAN_SET_REC_DUTY_CYCLE_RANGE 0x40000000
-#define LIRC_CAN_SET_REC_CARRIER_RANGE 0x80000000
-#define LIRC_CAN_GET_REC_RESOLUTION 0x20000000
-#define LIRC_CAN_SET_REC_TIMEOUT 0x10000000
-#define LIRC_CAN_SET_REC_FILTER 0x08000000
-
-#define LIRC_CAN_MEASURE_CARRIER 0x02000000
-#define LIRC_CAN_USE_WIDEBAND_RECEIVER 0x04000000
-
-#define LIRC_CAN_SEND(x) ((x)&LIRC_CAN_SEND_MASK)
-#define LIRC_CAN_REC(x) ((x)&LIRC_CAN_REC_MASK)
-
-#define LIRC_CAN_NOTIFY_DECODE 0x01000000
-
-/*** IOCTL commands for lirc driver ***/
-
-#define LIRC_GET_FEATURES _IOR('i', 0x00000000, __u32)
-
-#define LIRC_GET_SEND_MODE _IOR('i', 0x00000001, __u32)
-#define LIRC_GET_REC_MODE _IOR('i', 0x00000002, __u32)
-#define LIRC_GET_REC_RESOLUTION _IOR('i', 0x00000007, __u32)
-
-#define LIRC_GET_MIN_TIMEOUT _IOR('i', 0x00000008, __u32)
-#define LIRC_GET_MAX_TIMEOUT _IOR('i', 0x00000009, __u32)
-
-/* code length in bits, currently only for LIRC_MODE_LIRCCODE */
-#define LIRC_GET_LENGTH _IOR('i', 0x0000000f, __u32)
-
-#define LIRC_SET_SEND_MODE _IOW('i', 0x00000011, __u32)
-#define LIRC_SET_REC_MODE _IOW('i', 0x00000012, __u32)
-/* Note: these can reset the according pulse_width */
-#define LIRC_SET_SEND_CARRIER _IOW('i', 0x00000013, __u32)
-#define LIRC_SET_REC_CARRIER _IOW('i', 0x00000014, __u32)
-#define LIRC_SET_SEND_DUTY_CYCLE _IOW('i', 0x00000015, __u32)
-#define LIRC_SET_TRANSMITTER_MASK _IOW('i', 0x00000017, __u32)
-
-/*
- * when a timeout != 0 is set the driver will send a
- * LIRC_MODE2_TIMEOUT data packet, otherwise LIRC_MODE2_TIMEOUT is
- * never sent, timeout is disabled by default
- */
-#define LIRC_SET_REC_TIMEOUT _IOW('i', 0x00000018, __u32)
-
-/* 1 enables, 0 disables timeout reports in MODE2 */
-#define LIRC_SET_REC_TIMEOUT_REPORTS _IOW('i', 0x00000019, __u32)
-
-/*
- * if enabled from the next key press on the driver will send
- * LIRC_MODE2_FREQUENCY packets
- */
-#define LIRC_SET_MEASURE_CARRIER_MODE _IOW('i', 0x0000001d, __u32)
-
-/*
- * to set a range use LIRC_SET_REC_CARRIER_RANGE with the
- * lower bound first and later LIRC_SET_REC_CARRIER with the upper bound
- */
-#define LIRC_SET_REC_CARRIER_RANGE _IOW('i', 0x0000001f, __u32)
-
-#define LIRC_SET_WIDEBAND_RECEIVER _IOW('i', 0x00000023, __u32)
-
-/*
- * Return the recording timeout, which is either set by
- * the ioctl LIRC_SET_REC_TIMEOUT or by the kernel after setting the protocols.
- */
-#define LIRC_GET_REC_TIMEOUT _IOR('i', 0x00000024, __u32)
-
-/*
- * struct lirc_scancode - decoded scancode with protocol for use with
- * LIRC_MODE_SCANCODE
- *
- * @timestamp: Timestamp in nanoseconds using CLOCK_MONOTONIC when IR
- * was decoded.
- * @flags: should be 0 for transmit. When receiving scancodes,
- * LIRC_SCANCODE_FLAG_TOGGLE or LIRC_SCANCODE_FLAG_REPEAT can be set
- * depending on the protocol
- * @rc_proto: see enum rc_proto
- * @keycode: the translated keycode. Set to 0 for transmit.
- * @scancode: the scancode received or to be sent
- */
-struct lirc_scancode {
- __u64 timestamp;
- __u16 flags;
- __u16 rc_proto;
- __u32 keycode;
- __u64 scancode;
-};
-
-/* Set if the toggle bit of rc-5 or rc-6 is enabled */
-#define LIRC_SCANCODE_FLAG_TOGGLE 1
-/* Set if this is a nec or sanyo repeat */
-#define LIRC_SCANCODE_FLAG_REPEAT 2
-
-/**
- * enum rc_proto - the Remote Controller protocol
- *
- * @RC_PROTO_UNKNOWN: Protocol not known
- * @RC_PROTO_OTHER: Protocol known but proprietary
- * @RC_PROTO_RC5: Philips RC5 protocol
- * @RC_PROTO_RC5X_20: Philips RC5x 20 bit protocol
- * @RC_PROTO_RC5_SZ: StreamZap variant of RC5
- * @RC_PROTO_JVC: JVC protocol
- * @RC_PROTO_SONY12: Sony 12 bit protocol
- * @RC_PROTO_SONY15: Sony 15 bit protocol
- * @RC_PROTO_SONY20: Sony 20 bit protocol
- * @RC_PROTO_NEC: NEC protocol
- * @RC_PROTO_NECX: Extended NEC protocol
- * @RC_PROTO_NEC32: NEC 32 bit protocol
- * @RC_PROTO_SANYO: Sanyo protocol
- * @RC_PROTO_MCIR2_KBD: RC6-ish MCE keyboard
- * @RC_PROTO_MCIR2_MSE: RC6-ish MCE mouse
- * @RC_PROTO_RC6_0: Philips RC6-0-16 protocol
- * @RC_PROTO_RC6_6A_20: Philips RC6-6A-20 protocol
- * @RC_PROTO_RC6_6A_24: Philips RC6-6A-24 protocol
- * @RC_PROTO_RC6_6A_32: Philips RC6-6A-32 protocol
- * @RC_PROTO_RC6_MCE: MCE (Philips RC6-6A-32 subtype) protocol
- * @RC_PROTO_SHARP: Sharp protocol
- * @RC_PROTO_XMP: XMP protocol
- * @RC_PROTO_CEC: CEC protocol
- * @RC_PROTO_IMON: iMon Pad protocol
- * @RC_PROTO_RCMM12: RC-MM protocol 12 bits
- * @RC_PROTO_RCMM24: RC-MM protocol 24 bits
- * @RC_PROTO_RCMM32: RC-MM protocol 32 bits
- */
-enum rc_proto {
- RC_PROTO_UNKNOWN = 0,
- RC_PROTO_OTHER = 1,
- RC_PROTO_RC5 = 2,
- RC_PROTO_RC5X_20 = 3,
- RC_PROTO_RC5_SZ = 4,
- RC_PROTO_JVC = 5,
- RC_PROTO_SONY12 = 6,
- RC_PROTO_SONY15 = 7,
- RC_PROTO_SONY20 = 8,
- RC_PROTO_NEC = 9,
- RC_PROTO_NECX = 10,
- RC_PROTO_NEC32 = 11,
- RC_PROTO_SANYO = 12,
- RC_PROTO_MCIR2_KBD = 13,
- RC_PROTO_MCIR2_MSE = 14,
- RC_PROTO_RC6_0 = 15,
- RC_PROTO_RC6_6A_20 = 16,
- RC_PROTO_RC6_6A_24 = 17,
- RC_PROTO_RC6_6A_32 = 18,
- RC_PROTO_RC6_MCE = 19,
- RC_PROTO_SHARP = 20,
- RC_PROTO_XMP = 21,
- RC_PROTO_CEC = 22,
- RC_PROTO_IMON = 23,
- RC_PROTO_RCMM12 = 24,
- RC_PROTO_RCMM24 = 25,
- RC_PROTO_RCMM32 = 26,
-};
-
-#endif
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index b0be5f40a3f1..79d102304470 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -90,7 +90,7 @@ EXTRA_WARNINGS += -Wstrict-aliasing=3
else ifneq ($(CROSS_COMPILE),)
CLANG_CROSS_FLAGS := --target=$(notdir $(CROSS_COMPILE:%-=%))
-GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)gcc))
+GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)gcc 2>/dev/null))
ifneq ($(GCC_TOOLCHAIN_DIR),)
CLANG_CROSS_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE))
CLANG_CROSS_FLAGS += --sysroot=$(shell $(CROSS_COMPILE)gcc -print-sysroot)
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_user.c b/tools/testing/selftests/bpf/test_lirc_mode2_user.c
index ebf68dce5504..2893e9f2f1e0 100644
--- a/tools/testing/selftests/bpf/test_lirc_mode2_user.c
+++ b/tools/testing/selftests/bpf/test_lirc_mode2_user.c
@@ -28,7 +28,6 @@
// 5. We can read keycode from same /dev/lirc device
#include <linux/bpf.h>
-#include <linux/lirc.h>
#include <linux/input.h>
#include <errno.h>
#include <stdio.h>
diff --git a/tools/testing/selftests/cpufreq/main.sh b/tools/testing/selftests/cpufreq/main.sh
index 31f8c9a76c5f..60ce18ed0666 100755
--- a/tools/testing/selftests/cpufreq/main.sh
+++ b/tools/testing/selftests/cpufreq/main.sh
@@ -194,5 +194,5 @@ prerequisite
# Run requested functions
clear_dumps $OUTFILE
-do_test >> $OUTFILE.txt
+do_test | tee -a $OUTFILE.txt
dmesg_dumps $OUTFILE
diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile
index dd61118df66e..12c5e27d32c1 100644
--- a/tools/testing/selftests/exec/Makefile
+++ b/tools/testing/selftests/exec/Makefile
@@ -5,7 +5,7 @@ CFLAGS += -D_GNU_SOURCE
TEST_PROGS := binfmt_script non-regular
TEST_GEN_PROGS := execveat load_address_4096 load_address_2097152 load_address_16777216
-TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir pipe
+TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir
# Makefile is a run-time dependency, since it's accessed by the execveat test
TEST_FILES := Makefile
diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile
index 12631f0076a1..11e157d7533b 100644
--- a/tools/testing/selftests/futex/Makefile
+++ b/tools/testing/selftests/futex/Makefile
@@ -11,7 +11,7 @@ all:
@for DIR in $(SUBDIRS); do \
BUILD_TARGET=$(OUTPUT)/$$DIR; \
mkdir $$BUILD_TARGET -p; \
- make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
+ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
if [ -e $$DIR/$(TEST_PROGS) ]; then \
rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/; \
fi \
@@ -32,6 +32,6 @@ override define CLEAN
@for DIR in $(SUBDIRS); do \
BUILD_TARGET=$(OUTPUT)/$$DIR; \
mkdir $$BUILD_TARGET -p; \
- make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
+ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
done
endef
diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index 471eaa7b3a3f..11779405dc80 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -877,7 +877,8 @@ static void __timeout_handler(int sig, siginfo_t *info, void *ucontext)
}
t->timed_out = true;
- kill(t->pid, SIGKILL);
+ // signal process group
+ kill(-(t->pid), SIGKILL);
}
void __wait_for_test(struct __test_metadata *t)
@@ -987,6 +988,7 @@ void __run_test(struct __fixture_metadata *f,
ksft_print_msg("ERROR SPAWNING TEST CHILD\n");
t->passed = 0;
} else if (t->pid == 0) {
+ setpgrp();
t->fn(t, variant);
if (t->skip)
_exit(255);
diff --git a/tools/testing/selftests/mincore/mincore_selftest.c b/tools/testing/selftests/mincore/mincore_selftest.c
index e54106643337..4c88238fc8f0 100644
--- a/tools/testing/selftests/mincore/mincore_selftest.c
+++ b/tools/testing/selftests/mincore/mincore_selftest.c
@@ -207,15 +207,21 @@ TEST(check_file_mmap)
errno = 0;
fd = open(".", O_TMPFILE | O_RDWR, 0600);
- ASSERT_NE(-1, fd) {
- TH_LOG("Can't create temporary file: %s",
- strerror(errno));
+ if (fd < 0) {
+ ASSERT_EQ(errno, EOPNOTSUPP) {
+ TH_LOG("Can't create temporary file: %s",
+ strerror(errno));
+ }
+ SKIP(goto out_free, "O_TMPFILE not supported by filesystem.");
}
errno = 0;
retval = fallocate(fd, 0, 0, FILE_SIZE);
- ASSERT_EQ(0, retval) {
- TH_LOG("Error allocating space for the temporary file: %s",
- strerror(errno));
+ if (retval) {
+ ASSERT_EQ(errno, EOPNOTSUPP) {
+ TH_LOG("Error allocating space for the temporary file: %s",
+ strerror(errno));
+ }
+ SKIP(goto out_close, "fallocate not supported by filesystem.");
}
/*
@@ -271,7 +277,9 @@ TEST(check_file_mmap)
}
munmap(addr, FILE_SIZE);
+out_close:
close(fd);
+out_free:
free(vec);
}
diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh
index ed61f6cab60f..df322e47a54f 100755
--- a/tools/testing/selftests/netfilter/nft_concat_range.sh
+++ b/tools/testing/selftests/netfilter/nft_concat_range.sh
@@ -27,7 +27,7 @@ TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto
net6_port_net6_port net_port_mac_proto_net"
# Reported bugs, also described by TYPE_ variables below
-BUGS="flush_remove_add"
+BUGS="flush_remove_add reload"
# List of possible paths to pktgen script from kernel tree for performance tests
PKTGEN_SCRIPT_PATHS="
@@ -354,6 +354,23 @@ TYPE_flush_remove_add="
display Add two elements, flush, re-add
"
+TYPE_reload="
+display net,mac with reload
+type_spec ipv4_addr . ether_addr
+chain_spec ip daddr . ether saddr
+dst addr4
+src mac
+start 1
+count 1
+src_delta 2000
+tools sendip nc bash
+proto udp
+
+race_repeat 0
+
+perf_duration 0
+"
+
# Set template for all tests, types and rules are filled in depending on test
set_template='
flush ruleset
@@ -1473,6 +1490,59 @@ test_bug_flush_remove_add() {
nft flush ruleset
}
+# - add ranged element, check that packets match it
+# - reload the set, check packets still match
+test_bug_reload() {
+ setup veth send_"${proto}" set || return ${KSELFTEST_SKIP}
+ rstart=${start}
+
+ range_size=1
+ for i in $(seq "${start}" $((start + count))); do
+ end=$((start + range_size))
+
+ # Avoid negative or zero-sized port ranges
+ if [ $((end / 65534)) -gt $((start / 65534)) ]; then
+ start=${end}
+ end=$((end + 1))
+ fi
+ srcstart=$((start + src_delta))
+ srcend=$((end + src_delta))
+
+ add "$(format)" || return 1
+ range_size=$((range_size + 1))
+ start=$((end + range_size))
+ done
+
+ # check kernel does allocate pcpu sctrach map
+ # for reload with no elemet add/delete
+ ( echo flush set inet filter test ;
+ nft list set inet filter test ) | nft -f -
+
+ start=${rstart}
+ range_size=1
+
+ for i in $(seq "${start}" $((start + count))); do
+ end=$((start + range_size))
+
+ # Avoid negative or zero-sized port ranges
+ if [ $((end / 65534)) -gt $((start / 65534)) ]; then
+ start=${end}
+ end=$((end + 1))
+ fi
+ srcstart=$((start + src_delta))
+ srcend=$((end + src_delta))
+
+ for j in $(seq ${start} $((range_size / 2 + 1)) ${end}); do
+ send_match "${j}" $((j + src_delta)) || return 1
+ done
+
+ range_size=$((range_size + 1))
+ start=$((end + range_size))
+ done
+
+ nft flush ruleset
+}
+
test_reported_issues() {
eval test_bug_"${subtest}"
}
diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh
index 349a319a9e51..79fe627b9e81 100755
--- a/tools/testing/selftests/netfilter/nft_nat.sh
+++ b/tools/testing/selftests/netfilter/nft_nat.sh
@@ -899,6 +899,144 @@ EOF
ip netns exec "$ns0" nft delete table $family nat
}
+test_stateless_nat_ip()
+{
+ local lret=0
+
+ ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
+ ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+
+ ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannot ping $ns1 from $ns2 before loading stateless rules"
+ return 1
+ fi
+
+ip netns exec "$ns0" nft -f /dev/stdin <<EOF
+table ip stateless {
+ map xlate_in {
+ typeof meta iifname . ip saddr . ip daddr : ip daddr
+ elements = {
+ "veth1" . 10.0.2.99 . 10.0.1.99 : 10.0.2.2,
+ }
+ }
+ map xlate_out {
+ typeof meta iifname . ip saddr . ip daddr : ip daddr
+ elements = {
+ "veth0" . 10.0.1.99 . 10.0.2.2 : 10.0.2.99
+ }
+ }
+
+ chain prerouting {
+ type filter hook prerouting priority -400; policy accept;
+ ip saddr set meta iifname . ip saddr . ip daddr map @xlate_in
+ ip daddr set meta iifname . ip saddr . ip daddr map @xlate_out
+ }
+}
+EOF
+ if [ $? -ne 0 ]; then
+ echo "SKIP: Could not add ip statless rules"
+ return $ksft_skip
+ fi
+
+ reset_counters
+
+ ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannot ping $ns1 from $ns2 with stateless rules"
+ lret=1
+ fi
+
+ # ns1 should have seen packets from .2.2, due to stateless rewrite.
+ expect="packets 1 bytes 84"
+ cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0insl | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter "$ns1" ns0insl "$expect" "test_stateless 1"
+ lret=1
+ fi
+
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter "$ns2" ns1$dir "$expect" "test_stateless 2"
+ lret=1
+ fi
+ done
+
+ # ns1 should not have seen packets from ns2, due to masquerade
+ expect="packets 0 bytes 0"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter "$ns1" ns0$dir "$expect" "test_stateless 3"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter "$ns0" ns1$dir "$expect" "test_stateless 4"
+ lret=1
+ fi
+ done
+
+ reset_counters
+
+ socat -h > /dev/null 2>&1
+ if [ $? -ne 0 ];then
+ echo "SKIP: Could not run stateless nat frag test without socat tool"
+ if [ $lret -eq 0 ]; then
+ return $ksft_skip
+ fi
+
+ ip netns exec "$ns0" nft delete table ip stateless
+ return $lret
+ fi
+
+ local tmpfile=$(mktemp)
+ dd if=/dev/urandom of=$tmpfile bs=4096 count=1 2>/dev/null
+
+ local outfile=$(mktemp)
+ ip netns exec "$ns1" timeout 3 socat -u UDP4-RECV:4233 OPEN:$outfile < /dev/null &
+ sc_r=$!
+
+ sleep 1
+ # re-do with large ping -> ip fragmentation
+ ip netns exec "$ns2" timeout 3 socat - UDP4-SENDTO:"10.0.1.99:4233" < "$tmpfile" > /dev/null
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: failed to test udp $ns1 to $ns2 with stateless ip nat" 1>&2
+ lret=1
+ fi
+
+ wait
+
+ cmp "$tmpfile" "$outfile"
+ if [ $? -ne 0 ]; then
+ ls -l "$tmpfile" "$outfile"
+ echo "ERROR: in and output file mismatch when checking udp with stateless nat" 1>&2
+ lret=1
+ fi
+
+ rm -f "$tmpfile" "$outfile"
+
+ # ns1 should have seen packets from 2.2, due to stateless rewrite.
+ expect="packets 3 bytes 4164"
+ cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0insl | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter "$ns1" ns0insl "$expect" "test_stateless 5"
+ lret=1
+ fi
+
+ ip netns exec "$ns0" nft delete table ip stateless
+ if [ $? -ne 0 ]; then
+ echo "ERROR: Could not delete table ip stateless" 1>&2
+ lret=1
+ fi
+
+ test $lret -eq 0 && echo "PASS: IP statless for $ns2"
+
+ return $lret
+}
+
# ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99
for i in 0 1 2; do
ip netns exec ns$i-$sfx nft -f /dev/stdin <<EOF
@@ -965,6 +1103,19 @@ table inet filter {
EOF
done
+# special case for stateless nat check, counter needs to
+# be done before (input) ip defragmentation
+ip netns exec ns1-$sfx nft -f /dev/stdin <<EOF
+table inet filter {
+ counter ns0insl {}
+
+ chain pre {
+ type filter hook prerouting priority -400; policy accept;
+ ip saddr 10.0.2.2 counter name "ns0insl"
+ }
+}
+EOF
+
sleep 3
# test basic connectivity
for i in 1 2; do
@@ -1019,6 +1170,7 @@ $test_inet_nat && test_redirect inet
$test_inet_nat && test_redirect6 inet
test_port_shadowing
+test_stateless_nat_ip
if [ $ret -ne 0 ];then
echo -n "FAIL: "
diff --git a/tools/testing/selftests/netfilter/nft_zones_many.sh b/tools/testing/selftests/netfilter/nft_zones_many.sh
index 04633119b29a..5a8db0b48928 100755
--- a/tools/testing/selftests/netfilter/nft_zones_many.sh
+++ b/tools/testing/selftests/netfilter/nft_zones_many.sh
@@ -9,7 +9,7 @@ ns="ns-$sfx"
# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4
-zones=20000
+zones=2000
have_ct_tool=0
ret=0
@@ -75,10 +75,10 @@ EOF
while [ $i -lt $max_zones ]; do
local start=$(date +%s%3N)
- i=$((i + 10000))
+ i=$((i + 1000))
j=$((j + 1))
# nft rule in output places each packet in a different zone.
- dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345
+ dd if=/dev/zero of=/dev/stdout bs=8k count=1000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345
if [ $? -ne 0 ] ;then
ret=1
break
@@ -86,7 +86,7 @@ EOF
stop=$(date +%s%3N)
local duration=$((stop-start))
- echo "PASS: added 10000 entries in $duration ms (now $i total, loop $j)"
+ echo "PASS: added 1000 entries in $duration ms (now $i total, loop $j)"
done
if [ $have_ct_tool -eq 1 ]; then
@@ -128,11 +128,11 @@ test_conntrack_tool() {
break
fi
- if [ $((i%10000)) -eq 0 ];then
+ if [ $((i%1000)) -eq 0 ];then
stop=$(date +%s%3N)
local duration=$((stop-start))
- echo "PASS: added 10000 entries in $duration ms (now $i total)"
+ echo "PASS: added 1000 entries in $duration ms (now $i total)"
start=$stop
fi
done
diff --git a/tools/testing/selftests/openat2/Makefile b/tools/testing/selftests/openat2/Makefile
index 4b93b1417b86..843ba56d8e49 100644
--- a/tools/testing/selftests/openat2/Makefile
+++ b/tools/testing/selftests/openat2/Makefile
@@ -5,4 +5,4 @@ TEST_GEN_PROGS := openat2_test resolve_test rename_attack_test
include ../lib.mk
-$(TEST_GEN_PROGS): helpers.c
+$(TEST_GEN_PROGS): helpers.c helpers.h
diff --git a/tools/testing/selftests/openat2/helpers.h b/tools/testing/selftests/openat2/helpers.h
index a6ea27344db2..7056340b9339 100644
--- a/tools/testing/selftests/openat2/helpers.h
+++ b/tools/testing/selftests/openat2/helpers.h
@@ -9,6 +9,7 @@
#define _GNU_SOURCE
#include <stdint.h>
+#include <stdbool.h>
#include <errno.h>
#include <linux/types.h>
#include "../kselftest.h"
@@ -62,11 +63,12 @@ bool needs_openat2(const struct open_how *how);
(similar to chroot(2)). */
#endif /* RESOLVE_IN_ROOT */
-#define E_func(func, ...) \
- do { \
- if (func(__VA_ARGS__) < 0) \
- ksft_exit_fail_msg("%s:%d %s failed\n", \
- __FILE__, __LINE__, #func);\
+#define E_func(func, ...) \
+ do { \
+ errno = 0; \
+ if (func(__VA_ARGS__) < 0) \
+ ksft_exit_fail_msg("%s:%d %s failed - errno:%d\n", \
+ __FILE__, __LINE__, #func, errno); \
} while (0)
#define E_asprintf(...) E_func(asprintf, __VA_ARGS__)
diff --git a/tools/testing/selftests/openat2/openat2_test.c b/tools/testing/selftests/openat2/openat2_test.c
index 1bddbe934204..7fb902099de4 100644
--- a/tools/testing/selftests/openat2/openat2_test.c
+++ b/tools/testing/selftests/openat2/openat2_test.c
@@ -259,6 +259,16 @@ void test_openat2_flags(void)
unlink(path);
fd = sys_openat2(AT_FDCWD, path, &test->how);
+ if (fd < 0 && fd == -EOPNOTSUPP) {
+ /*
+ * Skip the testcase if it failed because not supported
+ * by FS. (e.g. a valid O_TMPFILE combination on NFS)
+ */
+ ksft_test_result_skip("openat2 with %s fails with %d (%s)\n",
+ test->name, fd, strerror(-fd));
+ goto next;
+ }
+
if (test->err >= 0)
failed = (fd < 0);
else
@@ -303,7 +313,7 @@ skip:
else
resultfn("openat2 with %s fails with %d (%s)\n",
test->name, test->err, strerror(-test->err));
-
+next:
free(fdpath);
fflush(stdout);
}
diff --git a/tools/testing/selftests/rtc/settings b/tools/testing/selftests/rtc/settings
index ba4d85f74cd6..a953c96aa16e 100644
--- a/tools/testing/selftests/rtc/settings
+++ b/tools/testing/selftests/rtc/settings
@@ -1 +1 @@
-timeout=90
+timeout=180
diff --git a/tools/testing/selftests/vDSO/vdso_test_abi.c b/tools/testing/selftests/vDSO/vdso_test_abi.c
index 3d603f1394af..883ca85424bc 100644
--- a/tools/testing/selftests/vDSO/vdso_test_abi.c
+++ b/tools/testing/selftests/vDSO/vdso_test_abi.c
@@ -33,110 +33,114 @@ typedef long (*vdso_clock_gettime_t)(clockid_t clk_id, struct timespec *ts);
typedef long (*vdso_clock_getres_t)(clockid_t clk_id, struct timespec *ts);
typedef time_t (*vdso_time_t)(time_t *t);
-static int vdso_test_gettimeofday(void)
+#define VDSO_TEST_PASS_MSG() "\n%s(): PASS\n", __func__
+#define VDSO_TEST_FAIL_MSG(x) "\n%s(): %s FAIL\n", __func__, x
+#define VDSO_TEST_SKIP_MSG(x) "\n%s(): SKIP: Could not find %s\n", __func__, x
+
+static void vdso_test_gettimeofday(void)
{
/* Find gettimeofday. */
vdso_gettimeofday_t vdso_gettimeofday =
(vdso_gettimeofday_t)vdso_sym(version, name[0]);
if (!vdso_gettimeofday) {
- printf("Could not find %s\n", name[0]);
- return KSFT_SKIP;
+ ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[0]));
+ return;
}
struct timeval tv;
long ret = vdso_gettimeofday(&tv, 0);
if (ret == 0) {
- printf("The time is %lld.%06lld\n",
- (long long)tv.tv_sec, (long long)tv.tv_usec);
+ ksft_print_msg("The time is %lld.%06lld\n",
+ (long long)tv.tv_sec, (long long)tv.tv_usec);
+ ksft_test_result_pass(VDSO_TEST_PASS_MSG());
} else {
- printf("%s failed\n", name[0]);
- return KSFT_FAIL;
+ ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[0]));
}
-
- return KSFT_PASS;
}
-static int vdso_test_clock_gettime(clockid_t clk_id)
+static void vdso_test_clock_gettime(clockid_t clk_id)
{
/* Find clock_gettime. */
vdso_clock_gettime_t vdso_clock_gettime =
(vdso_clock_gettime_t)vdso_sym(version, name[1]);
if (!vdso_clock_gettime) {
- printf("Could not find %s\n", name[1]);
- return KSFT_SKIP;
+ ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[1]));
+ return;
}
struct timespec ts;
long ret = vdso_clock_gettime(clk_id, &ts);
if (ret == 0) {
- printf("The time is %lld.%06lld\n",
- (long long)ts.tv_sec, (long long)ts.tv_nsec);
+ ksft_print_msg("The time is %lld.%06lld\n",
+ (long long)ts.tv_sec, (long long)ts.tv_nsec);
+ ksft_test_result_pass(VDSO_TEST_PASS_MSG());
} else {
- printf("%s failed\n", name[1]);
- return KSFT_FAIL;
+ ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[1]));
}
-
- return KSFT_PASS;
}
-static int vdso_test_time(void)
+static void vdso_test_time(void)
{
/* Find time. */
vdso_time_t vdso_time =
(vdso_time_t)vdso_sym(version, name[2]);
if (!vdso_time) {
- printf("Could not find %s\n", name[2]);
- return KSFT_SKIP;
+ ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[2]));
+ return;
}
long ret = vdso_time(NULL);
if (ret > 0) {
- printf("The time in hours since January 1, 1970 is %lld\n",
+ ksft_print_msg("The time in hours since January 1, 1970 is %lld\n",
(long long)(ret / 3600));
+ ksft_test_result_pass(VDSO_TEST_PASS_MSG());
} else {
- printf("%s failed\n", name[2]);
- return KSFT_FAIL;
+ ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[2]));
}
-
- return KSFT_PASS;
}
-static int vdso_test_clock_getres(clockid_t clk_id)
+static void vdso_test_clock_getres(clockid_t clk_id)
{
+ int clock_getres_fail = 0;
+
/* Find clock_getres. */
vdso_clock_getres_t vdso_clock_getres =
(vdso_clock_getres_t)vdso_sym(version, name[3]);
if (!vdso_clock_getres) {
- printf("Could not find %s\n", name[3]);
- return KSFT_SKIP;
+ ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[3]));
+ return;
}
struct timespec ts, sys_ts;
long ret = vdso_clock_getres(clk_id, &ts);
if (ret == 0) {
- printf("The resolution is %lld %lld\n",
- (long long)ts.tv_sec, (long long)ts.tv_nsec);
+ ksft_print_msg("The vdso resolution is %lld %lld\n",
+ (long long)ts.tv_sec, (long long)ts.tv_nsec);
} else {
- printf("%s failed\n", name[3]);
- return KSFT_FAIL;
+ clock_getres_fail++;
}
ret = syscall(SYS_clock_getres, clk_id, &sys_ts);
- if ((sys_ts.tv_sec != ts.tv_sec) || (sys_ts.tv_nsec != ts.tv_nsec)) {
- printf("%s failed\n", name[3]);
- return KSFT_FAIL;
- }
+ ksft_print_msg("The syscall resolution is %lld %lld\n",
+ (long long)sys_ts.tv_sec, (long long)sys_ts.tv_nsec);
- return KSFT_PASS;
+ if ((sys_ts.tv_sec != ts.tv_sec) || (sys_ts.tv_nsec != ts.tv_nsec))
+ clock_getres_fail++;
+
+ if (clock_getres_fail > 0) {
+ ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[3]));
+ } else {
+ ksft_test_result_pass(VDSO_TEST_PASS_MSG());
+ }
}
const char *vdso_clock_name[12] = {
@@ -158,36 +162,23 @@ const char *vdso_clock_name[12] = {
* This function calls vdso_test_clock_gettime and vdso_test_clock_getres
* with different values for clock_id.
*/
-static inline int vdso_test_clock(clockid_t clock_id)
+static inline void vdso_test_clock(clockid_t clock_id)
{
- int ret0, ret1;
-
- ret0 = vdso_test_clock_gettime(clock_id);
- /* A skipped test is considered passed */
- if (ret0 == KSFT_SKIP)
- ret0 = KSFT_PASS;
-
- ret1 = vdso_test_clock_getres(clock_id);
- /* A skipped test is considered passed */
- if (ret1 == KSFT_SKIP)
- ret1 = KSFT_PASS;
+ ksft_print_msg("\nclock_id: %s\n", vdso_clock_name[clock_id]);
- ret0 += ret1;
+ vdso_test_clock_gettime(clock_id);
- printf("clock_id: %s", vdso_clock_name[clock_id]);
-
- if (ret0 > 0)
- printf(" [FAIL]\n");
- else
- printf(" [PASS]\n");
-
- return ret0;
+ vdso_test_clock_getres(clock_id);
}
+#define VDSO_TEST_PLAN 16
+
int main(int argc, char **argv)
{
unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR);
- int ret;
+
+ ksft_print_header();
+ ksft_set_plan(VDSO_TEST_PLAN);
if (!sysinfo_ehdr) {
printf("AT_SYSINFO_EHDR is not present!\n");
@@ -201,44 +192,42 @@ int main(int argc, char **argv)
vdso_init_from_sysinfo_ehdr(getauxval(AT_SYSINFO_EHDR));
- ret = vdso_test_gettimeofday();
+ vdso_test_gettimeofday();
#if _POSIX_TIMERS > 0
#ifdef CLOCK_REALTIME
- ret += vdso_test_clock(CLOCK_REALTIME);
+ vdso_test_clock(CLOCK_REALTIME);
#endif
#ifdef CLOCK_BOOTTIME
- ret += vdso_test_clock(CLOCK_BOOTTIME);
+ vdso_test_clock(CLOCK_BOOTTIME);
#endif
#ifdef CLOCK_TAI
- ret += vdso_test_clock(CLOCK_TAI);
+ vdso_test_clock(CLOCK_TAI);
#endif
#ifdef CLOCK_REALTIME_COARSE
- ret += vdso_test_clock(CLOCK_REALTIME_COARSE);
+ vdso_test_clock(CLOCK_REALTIME_COARSE);
#endif
#ifdef CLOCK_MONOTONIC
- ret += vdso_test_clock(CLOCK_MONOTONIC);
+ vdso_test_clock(CLOCK_MONOTONIC);
#endif
#ifdef CLOCK_MONOTONIC_RAW
- ret += vdso_test_clock(CLOCK_MONOTONIC_RAW);
+ vdso_test_clock(CLOCK_MONOTONIC_RAW);
#endif
#ifdef CLOCK_MONOTONIC_COARSE
- ret += vdso_test_clock(CLOCK_MONOTONIC_COARSE);
+ vdso_test_clock(CLOCK_MONOTONIC_COARSE);
#endif
#endif
- ret += vdso_test_time();
-
- if (ret > 0)
- return KSFT_FAIL;
+ vdso_test_time();
- return KSFT_PASS;
+ ksft_print_cnts();
+ return ksft_get_fail_cnt() == 0 ? KSFT_PASS : KSFT_FAIL;
}
diff --git a/tools/testing/selftests/zram/zram.sh b/tools/testing/selftests/zram/zram.sh
index 232e958ec454..b0b91d9b0dc2 100755
--- a/tools/testing/selftests/zram/zram.sh
+++ b/tools/testing/selftests/zram/zram.sh
@@ -2,9 +2,6 @@
# SPDX-License-Identifier: GPL-2.0
TCID="zram.sh"
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
. ./zram_lib.sh
run_zram () {
@@ -18,14 +15,4 @@ echo ""
check_prereqs
-# check zram module exists
-MODULE_PATH=/lib/modules/`uname -r`/kernel/drivers/block/zram/zram.ko
-if [ -f $MODULE_PATH ]; then
- run_zram
-elif [ -b /dev/zram0 ]; then
- run_zram
-else
- echo "$TCID : No zram.ko module or /dev/zram0 device file not found"
- echo "$TCID : CONFIG_ZRAM is not set"
- exit $ksft_skip
-fi
+run_zram
diff --git a/tools/testing/selftests/zram/zram01.sh b/tools/testing/selftests/zram/zram01.sh
index 114863d9fb87..8f4affe34f3e 100755
--- a/tools/testing/selftests/zram/zram01.sh
+++ b/tools/testing/selftests/zram/zram01.sh
@@ -33,9 +33,7 @@ zram_algs="lzo"
zram_fill_fs()
{
- local mem_free0=$(free -m | awk 'NR==2 {print $4}')
-
- for i in $(seq 0 $(($dev_num - 1))); do
+ for i in $(seq $dev_start $dev_end); do
echo "fill zram$i..."
local b=0
while [ true ]; do
@@ -45,29 +43,17 @@ zram_fill_fs()
b=$(($b + 1))
done
echo "zram$i can be filled with '$b' KB"
- done
- local mem_free1=$(free -m | awk 'NR==2 {print $4}')
- local used_mem=$(($mem_free0 - $mem_free1))
+ local mem_used_total=`awk '{print $3}' "/sys/block/zram$i/mm_stat"`
+ local v=$((100 * 1024 * $b / $mem_used_total))
+ if [ "$v" -lt 100 ]; then
+ echo "FAIL compression ratio: 0.$v:1"
+ ERR_CODE=-1
+ return
+ fi
- local total_size=0
- for sm in $zram_sizes; do
- local s=$(echo $sm | sed 's/M//')
- total_size=$(($total_size + $s))
+ echo "zram compression ratio: $(echo "scale=2; $v / 100 " | bc):1: OK"
done
-
- echo "zram used ${used_mem}M, zram disk sizes ${total_size}M"
-
- local v=$((100 * $total_size / $used_mem))
-
- if [ "$v" -lt 100 ]; then
- echo "FAIL compression ratio: 0.$v:1"
- ERR_CODE=-1
- zram_cleanup
- return
- fi
-
- echo "zram compression ratio: $(echo "scale=2; $v / 100 " | bc):1: OK"
}
check_prereqs
@@ -81,7 +67,6 @@ zram_mount
zram_fill_fs
zram_cleanup
-zram_unload
if [ $ERR_CODE -ne 0 ]; then
echo "$TCID : [FAIL]"
diff --git a/tools/testing/selftests/zram/zram02.sh b/tools/testing/selftests/zram/zram02.sh
index e83b404807c0..2418b0c4ed13 100755
--- a/tools/testing/selftests/zram/zram02.sh
+++ b/tools/testing/selftests/zram/zram02.sh
@@ -36,7 +36,6 @@ zram_set_memlimit
zram_makeswap
zram_swapoff
zram_cleanup
-zram_unload
if [ $ERR_CODE -ne 0 ]; then
echo "$TCID : [FAIL]"
diff --git a/tools/testing/selftests/zram/zram_lib.sh b/tools/testing/selftests/zram/zram_lib.sh
index 6f872f266fd1..21ec1966de76 100755
--- a/tools/testing/selftests/zram/zram_lib.sh
+++ b/tools/testing/selftests/zram/zram_lib.sh
@@ -5,12 +5,17 @@
# Author: Alexey Kodanev <[email protected]>
# Modified: Naresh Kamboju <[email protected]>
-MODULE=0
dev_makeswap=-1
dev_mounted=-1
-
+dev_start=0
+dev_end=-1
+module_load=-1
+sys_control=-1
# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4
+kernel_version=`uname -r | cut -d'.' -f1,2`
+kernel_major=${kernel_version%.*}
+kernel_minor=${kernel_version#*.}
trap INT
@@ -25,68 +30,104 @@ check_prereqs()
fi
}
+kernel_gte()
+{
+ major=${1%.*}
+ minor=${1#*.}
+
+ if [ $kernel_major -gt $major ]; then
+ return 0
+ elif [[ $kernel_major -eq $major && $kernel_minor -ge $minor ]]; then
+ return 0
+ fi
+
+ return 1
+}
+
zram_cleanup()
{
echo "zram cleanup"
local i=
- for i in $(seq 0 $dev_makeswap); do
+ for i in $(seq $dev_start $dev_makeswap); do
swapoff /dev/zram$i
done
- for i in $(seq 0 $dev_mounted); do
+ for i in $(seq $dev_start $dev_mounted); do
umount /dev/zram$i
done
- for i in $(seq 0 $(($dev_num - 1))); do
+ for i in $(seq $dev_start $dev_end); do
echo 1 > /sys/block/zram${i}/reset
rm -rf zram$i
done
-}
+ if [ $sys_control -eq 1 ]; then
+ for i in $(seq $dev_start $dev_end); do
+ echo $i > /sys/class/zram-control/hot_remove
+ done
+ fi
-zram_unload()
-{
- if [ $MODULE -ne 0 ] ; then
- echo "zram rmmod zram"
+ if [ $module_load -eq 1 ]; then
rmmod zram > /dev/null 2>&1
fi
}
zram_load()
{
- # check zram module exists
- MODULE_PATH=/lib/modules/`uname -r`/kernel/drivers/block/zram/zram.ko
- if [ -f $MODULE_PATH ]; then
- MODULE=1
- echo "create '$dev_num' zram device(s)"
- modprobe zram num_devices=$dev_num
- if [ $? -ne 0 ]; then
- echo "failed to insert zram module"
- exit 1
- fi
-
- dev_num_created=$(ls /dev/zram* | wc -w)
+ echo "create '$dev_num' zram device(s)"
+
+ # zram module loaded, new kernel
+ if [ -d "/sys/class/zram-control" ]; then
+ echo "zram modules already loaded, kernel supports" \
+ "zram-control interface"
+ dev_start=$(ls /dev/zram* | wc -w)
+ dev_end=$(($dev_start + $dev_num - 1))
+ sys_control=1
+
+ for i in $(seq $dev_start $dev_end); do
+ cat /sys/class/zram-control/hot_add > /dev/null
+ done
+
+ echo "all zram devices (/dev/zram$dev_start~$dev_end" \
+ "successfully created"
+ return 0
+ fi
- if [ "$dev_num_created" -ne "$dev_num" ]; then
- echo "unexpected num of devices: $dev_num_created"
- ERR_CODE=-1
+ # detect old kernel or built-in
+ modprobe zram num_devices=$dev_num
+ if [ ! -d "/sys/class/zram-control" ]; then
+ if grep -q '^zram' /proc/modules; then
+ rmmod zram > /dev/null 2>&1
+ if [ $? -ne 0 ]; then
+ echo "zram module is being used on old kernel" \
+ "without zram-control interface"
+ exit $ksft_skip
+ fi
else
- echo "zram load module successful"
+ echo "test needs CONFIG_ZRAM=m on old kernel without" \
+ "zram-control interface"
+ exit $ksft_skip
fi
- elif [ -b /dev/zram0 ]; then
- echo "/dev/zram0 device file found: OK"
- else
- echo "ERROR: No zram.ko module or no /dev/zram0 device found"
- echo "$TCID : CONFIG_ZRAM is not set"
- exit 1
+ modprobe zram num_devices=$dev_num
fi
+
+ module_load=1
+ dev_end=$(($dev_num - 1))
+ echo "all zram devices (/dev/zram0~$dev_end) successfully created"
}
zram_max_streams()
{
echo "set max_comp_streams to zram device(s)"
- local i=0
+ kernel_gte 4.7
+ if [ $? -eq 0 ]; then
+ echo "The device attribute max_comp_streams was"\
+ "deprecated in 4.7"
+ return 0
+ fi
+
+ local i=$dev_start
for max_s in $zram_max_streams; do
local sys_path="/sys/block/zram${i}/max_comp_streams"
echo $max_s > $sys_path || \
@@ -98,7 +139,7 @@ zram_max_streams()
echo "FAIL can't set max_streams '$max_s', get $max_stream"
i=$(($i + 1))
- echo "$sys_path = '$max_streams' ($i/$dev_num)"
+ echo "$sys_path = '$max_streams'"
done
echo "zram max streams: OK"
@@ -108,15 +149,16 @@ zram_compress_alg()
{
echo "test that we can set compression algorithm"
- local algs=$(cat /sys/block/zram0/comp_algorithm)
+ local i=$dev_start
+ local algs=$(cat /sys/block/zram${i}/comp_algorithm)
echo "supported algs: $algs"
- local i=0
+
for alg in $zram_algs; do
local sys_path="/sys/block/zram${i}/comp_algorithm"
echo "$alg" > $sys_path || \
echo "FAIL can't set '$alg' to $sys_path"
i=$(($i + 1))
- echo "$sys_path = '$alg' ($i/$dev_num)"
+ echo "$sys_path = '$alg'"
done
echo "zram set compression algorithm: OK"
@@ -125,14 +167,14 @@ zram_compress_alg()
zram_set_disksizes()
{
echo "set disk size to zram device(s)"
- local i=0
+ local i=$dev_start
for ds in $zram_sizes; do
local sys_path="/sys/block/zram${i}/disksize"
echo "$ds" > $sys_path || \
echo "FAIL can't set '$ds' to $sys_path"
i=$(($i + 1))
- echo "$sys_path = '$ds' ($i/$dev_num)"
+ echo "$sys_path = '$ds'"
done
echo "zram set disksizes: OK"
@@ -142,14 +184,14 @@ zram_set_memlimit()
{
echo "set memory limit to zram device(s)"
- local i=0
+ local i=$dev_start
for ds in $zram_mem_limits; do
local sys_path="/sys/block/zram${i}/mem_limit"
echo "$ds" > $sys_path || \
echo "FAIL can't set '$ds' to $sys_path"
i=$(($i + 1))
- echo "$sys_path = '$ds' ($i/$dev_num)"
+ echo "$sys_path = '$ds'"
done
echo "zram set memory limit: OK"
@@ -158,8 +200,8 @@ zram_set_memlimit()
zram_makeswap()
{
echo "make swap with zram device(s)"
- local i=0
- for i in $(seq 0 $(($dev_num - 1))); do
+ local i=$dev_start
+ for i in $(seq $dev_start $dev_end); do
mkswap /dev/zram$i > err.log 2>&1
if [ $? -ne 0 ]; then
cat err.log
@@ -182,7 +224,7 @@ zram_makeswap()
zram_swapoff()
{
local i=
- for i in $(seq 0 $dev_makeswap); do
+ for i in $(seq $dev_start $dev_end); do
swapoff /dev/zram$i > err.log 2>&1
if [ $? -ne 0 ]; then
cat err.log
@@ -196,7 +238,7 @@ zram_swapoff()
zram_makefs()
{
- local i=0
+ local i=$dev_start
for fs in $zram_filesystems; do
# if requested fs not supported default it to ext2
which mkfs.$fs > /dev/null 2>&1 || fs=ext2
@@ -215,7 +257,7 @@ zram_makefs()
zram_mount()
{
local i=0
- for i in $(seq 0 $(($dev_num - 1))); do
+ for i in $(seq $dev_start $dev_end); do
echo "mount /dev/zram$i"
mkdir zram$i
mount /dev/zram$i zram$i > /dev/null || \