* [net 0/2] DPAA fixes
From: Madalin Bucur @ 2018-06-28 12:26 UTC (permalink / raw)
To: davem, netdev; +Cc: linux-kernel, Madalin Bucur
A couple of fixes for the DPAA drivers, addressing an issue
with short UDP or TCP frames (with padding) that were marked
as having a wrong checksum and dropped by the FMan hardware
and a problem with the buffer used for the scatter-gather
table being too small as per the hardware requirements.
Madalin Bucur (2):
fsl/fman: fix parser reporting bad checksum on short frames
dpaa_eth: DPAA SGT needs to be 256B
drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 15 ++++++++-------
drivers/net/ethernet/freescale/fman/fman_port.c | 8 ++++++++
2 files changed, 16 insertions(+), 7 deletions(-)
--
2.1.0
^ permalink raw reply
* [net 1/2] fsl/fman: fix parser reporting bad checksum on short frames
From: Madalin Bucur @ 2018-06-28 12:26 UTC (permalink / raw)
To: davem, netdev; +Cc: linux-kernel, Madalin Bucur
In-Reply-To: <1530188811-8918-1-git-send-email-madalin.bucur@nxp.com>
The FMan hardware parser needs to be configured to remove the
short frame padding from the checksum calculation, otherwise
short UDP and TCP frames are likely to be marked as having a
bad checksum.
Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
---
drivers/net/ethernet/freescale/fman/fman_port.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c
index 4a2d960..ee82ee1 100644
--- a/drivers/net/ethernet/freescale/fman/fman_port.c
+++ b/drivers/net/ethernet/freescale/fman/fman_port.c
@@ -324,6 +324,10 @@ struct fman_port_qmi_regs {
#define HWP_HXS_PHE_REPORT 0x00000800
#define HWP_HXS_PCAC_PSTAT 0x00000100
#define HWP_HXS_PCAC_PSTOP 0x00000001
+#define HWP_HXS_TCP_OFFSET 0xA
+#define HWP_HXS_UDP_OFFSET 0xB
+#define HWP_HXS_SH_PAD_REM 0x80000000
+
struct fman_port_hwp_regs {
struct {
u32 ssa; /* Soft Sequence Attachment */
@@ -728,6 +732,10 @@ static void init_hwp(struct fman_port *port)
iowrite32be(0xffffffff, ®s->pmda[i].lcv);
}
+ /* Short packet padding removal from checksum calculation */
+ iowrite32be(HWP_HXS_SH_PAD_REM, ®s->pmda[HWP_HXS_TCP_OFFSET].ssa);
+ iowrite32be(HWP_HXS_SH_PAD_REM, ®s->pmda[HWP_HXS_UDP_OFFSET].ssa);
+
start_port_hwp(port);
}
--
2.1.0
^ permalink raw reply related
* [net 2/2] dpaa_eth: DPAA SGT needs to be 256B
From: Madalin Bucur @ 2018-06-28 12:26 UTC (permalink / raw)
To: davem, netdev; +Cc: linux-kernel, Madalin Bucur
In-Reply-To: <1530188811-8918-1-git-send-email-madalin.bucur@nxp.com>
The DPAA HW requires that at least 256 bytes from the start of the
first scatter-gather table entry are allocated and accessible. The
hardware reads the maximum size the table can have in one access,
thus requiring that the allocation and mapping to be done for the
maximum size of 256B even if there is a smaller number of entries
in the table.
Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
---
drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 15 ++++++++-------
1 file changed, 8 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 52f4a6b..65a22cd 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -125,6 +125,9 @@ MODULE_PARM_DESC(tx_timeout, "The Tx timeout in ms");
/* Default alignment for start of data in an Rx FD */
#define DPAA_FD_DATA_ALIGNMENT 16
+/* The DPAA requires 256 bytes reserved and mapped for the SGT */
+#define DPAA_SGT_SIZE 256
+
/* Values for the L3R field of the FM Parse Results
*/
/* L3 Type field: First IP Present IPv4 */
@@ -1631,8 +1634,8 @@ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv,
if (unlikely(qm_fd_get_format(fd) == qm_fd_sg)) {
nr_frags = skb_shinfo(skb)->nr_frags;
- dma_unmap_single(dev, addr, qm_fd_get_offset(fd) +
- sizeof(struct qm_sg_entry) * (1 + nr_frags),
+ dma_unmap_single(dev, addr,
+ qm_fd_get_offset(fd) + DPAA_SGT_SIZE,
dma_dir);
/* The sgt buffer has been allocated with netdev_alloc_frag(),
@@ -1917,8 +1920,7 @@ static int skb_to_sg_fd(struct dpaa_priv *priv,
void *sgt_buf;
/* get a page frag to store the SGTable */
- sz = SKB_DATA_ALIGN(priv->tx_headroom +
- sizeof(struct qm_sg_entry) * (1 + nr_frags));
+ sz = SKB_DATA_ALIGN(priv->tx_headroom + DPAA_SGT_SIZE);
sgt_buf = netdev_alloc_frag(sz);
if (unlikely(!sgt_buf)) {
netdev_err(net_dev, "netdev_alloc_frag() failed for size %d\n",
@@ -1986,9 +1988,8 @@ static int skb_to_sg_fd(struct dpaa_priv *priv,
skbh = (struct sk_buff **)buffer_start;
*skbh = skb;
- addr = dma_map_single(dev, buffer_start, priv->tx_headroom +
- sizeof(struct qm_sg_entry) * (1 + nr_frags),
- dma_dir);
+ addr = dma_map_single(dev, buffer_start,
+ priv->tx_headroom + DPAA_SGT_SIZE, dma_dir);
if (unlikely(dma_mapping_error(dev, addr))) {
dev_err(dev, "DMA mapping failed");
err = -EINVAL;
--
2.1.0
^ permalink raw reply related
* [PATCH net-next 0/4] net: mvpp2: Add big-endian support
From: Maxime Chevallier @ 2018-06-28 12:42 UTC (permalink / raw)
To: davem
Cc: Maxime Chevallier, netdev, linux-kernel, Antoine Tenart,
thomas.petazzoni, gregory.clement, miquel.raynal, nadavh, stefanc,
ymarkman, mw
This series allows to use PPv2 on system built as big endian.
The first patch fixes the way we represent TX and RX descriptors, so that
they used fixed little endianness as expected by the PPv2 controller.
The second reworks the way we handle the software representation of the
Header Parser entries, so that we don't use a union of arrays.
The last two patches fixes some incorrect byte swapping logic, that wen't
un-noticed on little-endian.
This whole series doesn't fix any existing bug for little-endian systems, and
since big-endian never worked for this driver, I didn't include 'fixes' tags.
This was tested on MacchiatoBin (Armada 8040).
Maxime Chevallier (4):
net: mvpp2: Make TX / RX descriptors little-endian
net: mvpp2: prs: Drop unions representing TCAM and SRAM entries
net: mvpp2: prs: Drop unnecessary swab16 in vlan detection
net: mvpp2: Use htons when checking protocol info
drivers/net/ethernet/marvell/mvpp2/mvpp2.h | 58 ++++-----
drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 43 ++++---
drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c | 155 +++++++++++-------------
drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h | 41 +++----
4 files changed, 141 insertions(+), 156 deletions(-)
--
2.11.0
^ permalink raw reply
* [PATCH net-next 1/4] net: mvpp2: Make TX / RX descriptors little-endian
From: Maxime Chevallier @ 2018-06-28 12:42 UTC (permalink / raw)
To: davem
Cc: Maxime Chevallier, netdev, linux-kernel, Antoine Tenart,
thomas.petazzoni, gregory.clement, miquel.raynal, nadavh, stefanc,
ymarkman, mw
In-Reply-To: <20180628124207.11635-1-maxime.chevallier@bootlin.com>
The PPv2 controller always expect descriptors to be in little endian. We
must therefore force descriptors to use that format, and convert to the
host endianness when necessary.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
---
drivers/net/ethernet/marvell/mvpp2/mvpp2.h | 56 ++++++++++++-------------
drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 41 +++++++++---------
2 files changed, 50 insertions(+), 47 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index def00dc3eb4e..fa314b272853 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -831,52 +831,52 @@ struct mvpp2_port {
/* HW TX descriptor for PPv2.1 */
struct mvpp21_tx_desc {
- u32 command; /* Options used by HW for packet transmitting.*/
+ __le32 command; /* Options used by HW for packet transmitting.*/
u8 packet_offset; /* the offset from the buffer beginning */
u8 phys_txq; /* destination queue ID */
- u16 data_size; /* data size of transmitted packet in bytes */
- u32 buf_dma_addr; /* physical addr of transmitted buffer */
- u32 buf_cookie; /* cookie for access to TX buffer in tx path */
- u32 reserved1[3]; /* hw_cmd (for future use, BM, PON, PNC) */
- u32 reserved2; /* reserved (for future use) */
+ __le16 data_size; /* data size of transmitted packet in bytes */
+ __le32 buf_dma_addr; /* physical addr of transmitted buffer */
+ __le32 buf_cookie; /* cookie for access to TX buffer in tx path */
+ __le32 reserved1[3]; /* hw_cmd (for future use, BM, PON, PNC) */
+ __le32 reserved2; /* reserved (for future use) */
};
/* HW RX descriptor for PPv2.1 */
struct mvpp21_rx_desc {
- u32 status; /* info about received packet */
- u16 reserved1; /* parser_info (for future use, PnC) */
- u16 data_size; /* size of received packet in bytes */
- u32 buf_dma_addr; /* physical address of the buffer */
- u32 buf_cookie; /* cookie for access to RX buffer in rx path */
- u16 reserved2; /* gem_port_id (for future use, PON) */
- u16 reserved3; /* csum_l4 (for future use, PnC) */
+ __le32 status; /* info about received packet */
+ __le16 reserved1; /* parser_info (for future use, PnC) */
+ __le16 data_size; /* size of received packet in bytes */
+ __le32 buf_dma_addr; /* physical address of the buffer */
+ __le32 buf_cookie; /* cookie for access to RX buffer in rx path */
+ __le16 reserved2; /* gem_port_id (for future use, PON) */
+ __le16 reserved3; /* csum_l4 (for future use, PnC) */
u8 reserved4; /* bm_qset (for future use, BM) */
u8 reserved5;
- u16 reserved6; /* classify_info (for future use, PnC) */
- u32 reserved7; /* flow_id (for future use, PnC) */
- u32 reserved8;
+ __le16 reserved6; /* classify_info (for future use, PnC) */
+ __le32 reserved7; /* flow_id (for future use, PnC) */
+ __le32 reserved8;
};
/* HW TX descriptor for PPv2.2 */
struct mvpp22_tx_desc {
- u32 command;
+ __le32 command;
u8 packet_offset;
u8 phys_txq;
- u16 data_size;
- u64 reserved1;
- u64 buf_dma_addr_ptp;
- u64 buf_cookie_misc;
+ __le16 data_size;
+ __le64 reserved1;
+ __le64 buf_dma_addr_ptp;
+ __le64 buf_cookie_misc;
};
/* HW RX descriptor for PPv2.2 */
struct mvpp22_rx_desc {
- u32 status;
- u16 reserved1;
- u16 data_size;
- u32 reserved2;
- u32 reserved3;
- u64 buf_dma_addr_key_hash;
- u64 buf_cookie_misc;
+ __le32 status;
+ __le16 reserved1;
+ __le16 data_size;
+ __le32 reserved2;
+ __le32 reserved3;
+ __le64 buf_dma_addr_key_hash;
+ __le64 buf_cookie_misc;
};
/* Opaque type used by the driver to manipulate the HW TX and RX
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 0319ed9ef8b8..ded187a20b6c 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -151,9 +151,10 @@ static dma_addr_t mvpp2_txdesc_dma_addr_get(struct mvpp2_port *port,
struct mvpp2_tx_desc *tx_desc)
{
if (port->priv->hw_version == MVPP21)
- return tx_desc->pp21.buf_dma_addr;
+ return le32_to_cpu(tx_desc->pp21.buf_dma_addr);
else
- return tx_desc->pp22.buf_dma_addr_ptp & MVPP2_DESC_DMA_MASK;
+ return le64_to_cpu(tx_desc->pp22.buf_dma_addr_ptp) &
+ MVPP2_DESC_DMA_MASK;
}
static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port,
@@ -166,12 +167,12 @@ static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port,
offset = dma_addr & MVPP2_TX_DESC_ALIGN;
if (port->priv->hw_version == MVPP21) {
- tx_desc->pp21.buf_dma_addr = addr;
+ tx_desc->pp21.buf_dma_addr = cpu_to_le32(addr);
tx_desc->pp21.packet_offset = offset;
} else {
- u64 val = (u64)addr;
+ __le64 val = cpu_to_le64(addr);
- tx_desc->pp22.buf_dma_addr_ptp &= ~MVPP2_DESC_DMA_MASK;
+ tx_desc->pp22.buf_dma_addr_ptp &= ~cpu_to_le64(MVPP2_DESC_DMA_MASK);
tx_desc->pp22.buf_dma_addr_ptp |= val;
tx_desc->pp22.packet_offset = offset;
}
@@ -181,9 +182,9 @@ static size_t mvpp2_txdesc_size_get(struct mvpp2_port *port,
struct mvpp2_tx_desc *tx_desc)
{
if (port->priv->hw_version == MVPP21)
- return tx_desc->pp21.data_size;
+ return le16_to_cpu(tx_desc->pp21.data_size);
else
- return tx_desc->pp22.data_size;
+ return le16_to_cpu(tx_desc->pp22.data_size);
}
static void mvpp2_txdesc_size_set(struct mvpp2_port *port,
@@ -191,9 +192,9 @@ static void mvpp2_txdesc_size_set(struct mvpp2_port *port,
size_t size)
{
if (port->priv->hw_version == MVPP21)
- tx_desc->pp21.data_size = size;
+ tx_desc->pp21.data_size = cpu_to_le16(size);
else
- tx_desc->pp22.data_size = size;
+ tx_desc->pp22.data_size = cpu_to_le16(size);
}
static void mvpp2_txdesc_txq_set(struct mvpp2_port *port,
@@ -211,9 +212,9 @@ static void mvpp2_txdesc_cmd_set(struct mvpp2_port *port,
unsigned int command)
{
if (port->priv->hw_version == MVPP21)
- tx_desc->pp21.command = command;
+ tx_desc->pp21.command = cpu_to_le32(command);
else
- tx_desc->pp22.command = command;
+ tx_desc->pp22.command = cpu_to_le32(command);
}
static unsigned int mvpp2_txdesc_offset_get(struct mvpp2_port *port,
@@ -229,36 +230,38 @@ static dma_addr_t mvpp2_rxdesc_dma_addr_get(struct mvpp2_port *port,
struct mvpp2_rx_desc *rx_desc)
{
if (port->priv->hw_version == MVPP21)
- return rx_desc->pp21.buf_dma_addr;
+ return le32_to_cpu(rx_desc->pp21.buf_dma_addr);
else
- return rx_desc->pp22.buf_dma_addr_key_hash & MVPP2_DESC_DMA_MASK;
+ return le64_to_cpu(rx_desc->pp22.buf_dma_addr_key_hash) &
+ MVPP2_DESC_DMA_MASK;
}
static unsigned long mvpp2_rxdesc_cookie_get(struct mvpp2_port *port,
struct mvpp2_rx_desc *rx_desc)
{
if (port->priv->hw_version == MVPP21)
- return rx_desc->pp21.buf_cookie;
+ return le32_to_cpu(rx_desc->pp21.buf_cookie);
else
- return rx_desc->pp22.buf_cookie_misc & MVPP2_DESC_DMA_MASK;
+ return le64_to_cpu(rx_desc->pp22.buf_cookie_misc) &
+ MVPP2_DESC_DMA_MASK;
}
static size_t mvpp2_rxdesc_size_get(struct mvpp2_port *port,
struct mvpp2_rx_desc *rx_desc)
{
if (port->priv->hw_version == MVPP21)
- return rx_desc->pp21.data_size;
+ return le16_to_cpu(rx_desc->pp21.data_size);
else
- return rx_desc->pp22.data_size;
+ return le16_to_cpu(rx_desc->pp22.data_size);
}
static u32 mvpp2_rxdesc_status_get(struct mvpp2_port *port,
struct mvpp2_rx_desc *rx_desc)
{
if (port->priv->hw_version == MVPP21)
- return rx_desc->pp21.status;
+ return le32_to_cpu(rx_desc->pp21.status);
else
- return rx_desc->pp22.status;
+ return le32_to_cpu(rx_desc->pp22.status);
}
static void mvpp2_txq_inc_get(struct mvpp2_txq_pcpu *txq_pcpu)
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 2/4] net: mvpp2: prs: Drop unions representing TCAM and SRAM entries
From: Maxime Chevallier @ 2018-06-28 12:42 UTC (permalink / raw)
To: davem
Cc: Maxime Chevallier, netdev, linux-kernel, Antoine Tenart,
thomas.petazzoni, gregory.clement, miquel.raynal, nadavh, stefanc,
ymarkman, mw
In-Reply-To: <20180628124207.11635-1-maxime.chevallier@bootlin.com>
PPv2's Header Parser use some large TCAM and SRAM entries, that are
duplicated in software so that we can write them to hardware only when
we are done modifying them.
Currently, PPv2 uses a union containing arrays of u32 and u8 to represent
these entries, to facilitate byte per byte access. This representation is
broken when we want to support big endian, and this makes the code
confusing to read.
This patch drops the union, and simply stores the TCAM and SRAM entries
as u32 arrays, each entry corresponding to a 32-bit register.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
---
drivers/net/ethernet/marvell/mvpp2/mvpp2.h | 2 +
drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c | 149 +++++++++++--------------
drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h | 41 ++++---
3 files changed, 87 insertions(+), 105 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index fa314b272853..81a66cce7fa8 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -553,6 +553,8 @@
((total_size) - NET_SKB_PAD - MVPP2_SKB_SHINFO_SIZE)
#define MVPP2_BIT_TO_BYTE(bit) ((bit) / 8)
+#define MVPP2_BIT_TO_WORD(bit) ((bit) / 32)
+#define MVPP2_BIT_IN_WORD(bit) ((bit) % 32)
/* IPv6 max L3 address size */
#define MVPP2_MAX_L3_ADDR_SIZE 16
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
index 6bb69f086794..af11feea681c 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
@@ -30,17 +30,17 @@ static int mvpp2_prs_hw_write(struct mvpp2 *priv, struct mvpp2_prs_entry *pe)
return -EINVAL;
/* Clear entry invalidation bit */
- pe->tcam.word[MVPP2_PRS_TCAM_INV_WORD] &= ~MVPP2_PRS_TCAM_INV_MASK;
+ pe->tcam[MVPP2_PRS_TCAM_INV_WORD] &= ~MVPP2_PRS_TCAM_INV_MASK;
/* Write tcam index - indirect access */
mvpp2_write(priv, MVPP2_PRS_TCAM_IDX_REG, pe->index);
for (i = 0; i < MVPP2_PRS_TCAM_WORDS; i++)
- mvpp2_write(priv, MVPP2_PRS_TCAM_DATA_REG(i), pe->tcam.word[i]);
+ mvpp2_write(priv, MVPP2_PRS_TCAM_DATA_REG(i), pe->tcam[i]);
/* Write sram index - indirect access */
mvpp2_write(priv, MVPP2_PRS_SRAM_IDX_REG, pe->index);
for (i = 0; i < MVPP2_PRS_SRAM_WORDS; i++)
- mvpp2_write(priv, MVPP2_PRS_SRAM_DATA_REG(i), pe->sram.word[i]);
+ mvpp2_write(priv, MVPP2_PRS_SRAM_DATA_REG(i), pe->sram[i]);
return 0;
}
@@ -60,18 +60,18 @@ static int mvpp2_prs_init_from_hw(struct mvpp2 *priv,
/* Write tcam index - indirect access */
mvpp2_write(priv, MVPP2_PRS_TCAM_IDX_REG, pe->index);
- pe->tcam.word[MVPP2_PRS_TCAM_INV_WORD] = mvpp2_read(priv,
+ pe->tcam[MVPP2_PRS_TCAM_INV_WORD] = mvpp2_read(priv,
MVPP2_PRS_TCAM_DATA_REG(MVPP2_PRS_TCAM_INV_WORD));
- if (pe->tcam.word[MVPP2_PRS_TCAM_INV_WORD] & MVPP2_PRS_TCAM_INV_MASK)
+ if (pe->tcam[MVPP2_PRS_TCAM_INV_WORD] & MVPP2_PRS_TCAM_INV_MASK)
return MVPP2_PRS_TCAM_ENTRY_INVALID;
for (i = 0; i < MVPP2_PRS_TCAM_WORDS; i++)
- pe->tcam.word[i] = mvpp2_read(priv, MVPP2_PRS_TCAM_DATA_REG(i));
+ pe->tcam[i] = mvpp2_read(priv, MVPP2_PRS_TCAM_DATA_REG(i));
/* Write sram index - indirect access */
mvpp2_write(priv, MVPP2_PRS_SRAM_IDX_REG, pe->index);
for (i = 0; i < MVPP2_PRS_SRAM_WORDS; i++)
- pe->sram.word[i] = mvpp2_read(priv, MVPP2_PRS_SRAM_DATA_REG(i));
+ pe->sram[i] = mvpp2_read(priv, MVPP2_PRS_SRAM_DATA_REG(i));
return 0;
}
@@ -103,42 +103,35 @@ static void mvpp2_prs_shadow_ri_set(struct mvpp2 *priv, int index,
/* Update lookup field in tcam sw entry */
static void mvpp2_prs_tcam_lu_set(struct mvpp2_prs_entry *pe, unsigned int lu)
{
- int enable_off = MVPP2_PRS_TCAM_EN_OFFS(MVPP2_PRS_TCAM_LU_BYTE);
-
- pe->tcam.byte[MVPP2_PRS_TCAM_LU_BYTE] = lu;
- pe->tcam.byte[enable_off] = MVPP2_PRS_LU_MASK;
+ pe->tcam[MVPP2_PRS_TCAM_LU_WORD] &= ~MVPP2_PRS_TCAM_LU(MVPP2_PRS_LU_MASK);
+ pe->tcam[MVPP2_PRS_TCAM_LU_WORD] &= ~MVPP2_PRS_TCAM_LU_EN(MVPP2_PRS_LU_MASK);
+ pe->tcam[MVPP2_PRS_TCAM_LU_WORD] |= MVPP2_PRS_TCAM_LU(lu & MVPP2_PRS_LU_MASK);
+ pe->tcam[MVPP2_PRS_TCAM_LU_WORD] |= MVPP2_PRS_TCAM_LU_EN(MVPP2_PRS_LU_MASK);
}
/* Update mask for single port in tcam sw entry */
static void mvpp2_prs_tcam_port_set(struct mvpp2_prs_entry *pe,
unsigned int port, bool add)
{
- int enable_off = MVPP2_PRS_TCAM_EN_OFFS(MVPP2_PRS_TCAM_PORT_BYTE);
-
if (add)
- pe->tcam.byte[enable_off] &= ~(1 << port);
+ pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] &= ~MVPP2_PRS_TCAM_PORT_EN(BIT(port));
else
- pe->tcam.byte[enable_off] |= 1 << port;
+ pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] |= MVPP2_PRS_TCAM_PORT_EN(BIT(port));
}
/* Update port map in tcam sw entry */
static void mvpp2_prs_tcam_port_map_set(struct mvpp2_prs_entry *pe,
unsigned int ports)
{
- unsigned char port_mask = MVPP2_PRS_PORT_MASK;
- int enable_off = MVPP2_PRS_TCAM_EN_OFFS(MVPP2_PRS_TCAM_PORT_BYTE);
-
- pe->tcam.byte[MVPP2_PRS_TCAM_PORT_BYTE] = 0;
- pe->tcam.byte[enable_off] &= ~port_mask;
- pe->tcam.byte[enable_off] |= ~ports & MVPP2_PRS_PORT_MASK;
+ pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] &= ~MVPP2_PRS_TCAM_PORT(MVPP2_PRS_PORT_MASK);
+ pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] &= ~MVPP2_PRS_TCAM_PORT_EN(MVPP2_PRS_PORT_MASK);
+ pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] |= MVPP2_PRS_TCAM_PORT_EN(~ports & MVPP2_PRS_PORT_MASK);
}
/* Obtain port map from tcam sw entry */
static unsigned int mvpp2_prs_tcam_port_map_get(struct mvpp2_prs_entry *pe)
{
- int enable_off = MVPP2_PRS_TCAM_EN_OFFS(MVPP2_PRS_TCAM_PORT_BYTE);
-
- return ~(pe->tcam.byte[enable_off]) & MVPP2_PRS_PORT_MASK;
+ return (~pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] >> 24) & MVPP2_PRS_PORT_MASK;
}
/* Set byte of data and its enable bits in tcam sw entry */
@@ -146,8 +139,12 @@ static void mvpp2_prs_tcam_data_byte_set(struct mvpp2_prs_entry *pe,
unsigned int offs, unsigned char byte,
unsigned char enable)
{
- pe->tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE(offs)] = byte;
- pe->tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE_EN(offs)] = enable;
+ int pos = MVPP2_PRS_BYTE_IN_WORD(offs) * BITS_PER_BYTE;
+
+ pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] &= ~(0xff << pos);
+ pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] &= ~(MVPP2_PRS_TCAM_EN(0xff) << pos);
+ pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] |= byte << pos;
+ pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] |= MVPP2_PRS_TCAM_EN(enable << pos);
}
/* Get byte of data and its enable bits from tcam sw entry */
@@ -155,46 +152,45 @@ static void mvpp2_prs_tcam_data_byte_get(struct mvpp2_prs_entry *pe,
unsigned int offs, unsigned char *byte,
unsigned char *enable)
{
- *byte = pe->tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE(offs)];
- *enable = pe->tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE_EN(offs)];
+ int pos = MVPP2_PRS_BYTE_IN_WORD(offs) * BITS_PER_BYTE;
+
+ *byte = (pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] >> pos) & 0xff;
+ *enable = (pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] >> (pos + 16)) & 0xff;
}
/* Compare tcam data bytes with a pattern */
static bool mvpp2_prs_tcam_data_cmp(struct mvpp2_prs_entry *pe, int offs,
u16 data)
{
- int off = MVPP2_PRS_TCAM_DATA_BYTE(offs);
u16 tcam_data;
- tcam_data = (pe->tcam.byte[off + 1] << 8) | pe->tcam.byte[off];
- if (tcam_data != data)
- return false;
- return true;
+ tcam_data = pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] & 0xffff;
+ return tcam_data == data;
}
/* Update ai bits in tcam sw entry */
static void mvpp2_prs_tcam_ai_update(struct mvpp2_prs_entry *pe,
unsigned int bits, unsigned int enable)
{
- int i, ai_idx = MVPP2_PRS_TCAM_AI_BYTE;
+ int i;
for (i = 0; i < MVPP2_PRS_AI_BITS; i++) {
if (!(enable & BIT(i)))
continue;
if (bits & BIT(i))
- pe->tcam.byte[ai_idx] |= 1 << i;
+ pe->tcam[MVPP2_PRS_TCAM_AI_WORD] |= BIT(i);
else
- pe->tcam.byte[ai_idx] &= ~(1 << i);
+ pe->tcam[MVPP2_PRS_TCAM_AI_WORD] &= ~BIT(i);
}
- pe->tcam.byte[MVPP2_PRS_TCAM_EN_OFFS(ai_idx)] |= enable;
+ pe->tcam[MVPP2_PRS_TCAM_AI_WORD] |= MVPP2_PRS_TCAM_AI_EN(enable);
}
/* Get ai bits from tcam sw entry */
static int mvpp2_prs_tcam_ai_get(struct mvpp2_prs_entry *pe)
{
- return pe->tcam.byte[MVPP2_PRS_TCAM_AI_BYTE];
+ return pe->tcam[MVPP2_PRS_TCAM_AI_WORD] & MVPP2_PRS_AI_MASK;
}
/* Set ethertype in tcam sw entry */
@@ -215,16 +211,16 @@ static void mvpp2_prs_match_vid(struct mvpp2_prs_entry *pe, int offset,
/* Set bits in sram sw entry */
static void mvpp2_prs_sram_bits_set(struct mvpp2_prs_entry *pe, int bit_num,
- int val)
+ u32 val)
{
- pe->sram.byte[MVPP2_BIT_TO_BYTE(bit_num)] |= (val << (bit_num % 8));
+ pe->sram[MVPP2_BIT_TO_WORD(bit_num)] |= (val << (MVPP2_BIT_IN_WORD(bit_num)));
}
/* Clear bits in sram sw entry */
static void mvpp2_prs_sram_bits_clear(struct mvpp2_prs_entry *pe, int bit_num,
- int val)
+ u32 val)
{
- pe->sram.byte[MVPP2_BIT_TO_BYTE(bit_num)] &= ~(val << (bit_num % 8));
+ pe->sram[MVPP2_BIT_TO_WORD(bit_num)] &= ~(val << (MVPP2_BIT_IN_WORD(bit_num)));
}
/* Update ri bits in sram sw entry */
@@ -234,15 +230,16 @@ static void mvpp2_prs_sram_ri_update(struct mvpp2_prs_entry *pe,
unsigned int i;
for (i = 0; i < MVPP2_PRS_SRAM_RI_CTRL_BITS; i++) {
- int ri_off = MVPP2_PRS_SRAM_RI_OFFS;
-
if (!(mask & BIT(i)))
continue;
if (bits & BIT(i))
- mvpp2_prs_sram_bits_set(pe, ri_off + i, 1);
+ mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_RI_OFFS + i,
+ 1);
else
- mvpp2_prs_sram_bits_clear(pe, ri_off + i, 1);
+ mvpp2_prs_sram_bits_clear(pe,
+ MVPP2_PRS_SRAM_RI_OFFS + i,
+ 1);
mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_RI_CTRL_OFFS + i, 1);
}
@@ -251,7 +248,7 @@ static void mvpp2_prs_sram_ri_update(struct mvpp2_prs_entry *pe,
/* Obtain ri bits from sram sw entry */
static int mvpp2_prs_sram_ri_get(struct mvpp2_prs_entry *pe)
{
- return pe->sram.word[MVPP2_PRS_SRAM_RI_WORD];
+ return pe->sram[MVPP2_PRS_SRAM_RI_WORD];
}
/* Update ai bits in sram sw entry */
@@ -259,16 +256,18 @@ static void mvpp2_prs_sram_ai_update(struct mvpp2_prs_entry *pe,
unsigned int bits, unsigned int mask)
{
unsigned int i;
- int ai_off = MVPP2_PRS_SRAM_AI_OFFS;
for (i = 0; i < MVPP2_PRS_SRAM_AI_CTRL_BITS; i++) {
if (!(mask & BIT(i)))
continue;
if (bits & BIT(i))
- mvpp2_prs_sram_bits_set(pe, ai_off + i, 1);
+ mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_AI_OFFS + i,
+ 1);
else
- mvpp2_prs_sram_bits_clear(pe, ai_off + i, 1);
+ mvpp2_prs_sram_bits_clear(pe,
+ MVPP2_PRS_SRAM_AI_OFFS + i,
+ 1);
mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_AI_CTRL_OFFS + i, 1);
}
@@ -278,12 +277,12 @@ static void mvpp2_prs_sram_ai_update(struct mvpp2_prs_entry *pe,
static int mvpp2_prs_sram_ai_get(struct mvpp2_prs_entry *pe)
{
u8 bits;
- int ai_off = MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_AI_OFFS);
- int ai_en_off = ai_off + 1;
- int ai_shift = MVPP2_PRS_SRAM_AI_OFFS % 8;
+ /* ai is stored on bits 90->97; so it spreads across two u32 */
+ int ai_off = MVPP2_BIT_TO_WORD(MVPP2_PRS_SRAM_AI_OFFS);
+ int ai_shift = MVPP2_BIT_IN_WORD(MVPP2_PRS_SRAM_AI_OFFS);
- bits = (pe->sram.byte[ai_off] >> ai_shift) |
- (pe->sram.byte[ai_en_off] << (8 - ai_shift));
+ bits = (pe->sram[ai_off] >> ai_shift) |
+ (pe->sram[ai_off + 1] << (32 - ai_shift));
return bits;
}
@@ -316,8 +315,7 @@ static void mvpp2_prs_sram_shift_set(struct mvpp2_prs_entry *pe, int shift,
}
/* Set value */
- pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_SHIFT_OFFS)] =
- (unsigned char)shift;
+ pe->sram[MVPP2_BIT_TO_WORD(MVPP2_PRS_SRAM_SHIFT_OFFS)] = shift & MVPP2_PRS_SRAM_SHIFT_MASK;
/* Reset and set operation */
mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_OP_SEL_SHIFT_OFFS,
@@ -346,13 +344,8 @@ static void mvpp2_prs_sram_offset_set(struct mvpp2_prs_entry *pe,
/* Set value */
mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_UDF_OFFS,
MVPP2_PRS_SRAM_UDF_MASK);
- mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_UDF_OFFS, offset);
- pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_UDF_OFFS +
- MVPP2_PRS_SRAM_UDF_BITS)] &=
- ~(MVPP2_PRS_SRAM_UDF_MASK >> (8 - (MVPP2_PRS_SRAM_UDF_OFFS % 8)));
- pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_UDF_OFFS +
- MVPP2_PRS_SRAM_UDF_BITS)] |=
- (offset >> (8 - (MVPP2_PRS_SRAM_UDF_OFFS % 8)));
+ mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_UDF_OFFS,
+ offset & MVPP2_PRS_SRAM_UDF_MASK);
/* Set offset type */
mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_UDF_TYPE_OFFS,
@@ -362,16 +355,8 @@ static void mvpp2_prs_sram_offset_set(struct mvpp2_prs_entry *pe,
/* Set offset operation */
mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS,
MVPP2_PRS_SRAM_OP_SEL_UDF_MASK);
- mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS, op);
-
- pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS +
- MVPP2_PRS_SRAM_OP_SEL_UDF_BITS)] &=
- ~(MVPP2_PRS_SRAM_OP_SEL_UDF_MASK >>
- (8 - (MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS % 8)));
-
- pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS +
- MVPP2_PRS_SRAM_OP_SEL_UDF_BITS)] |=
- (op >> (8 - (MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS % 8)));
+ mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS,
+ op & MVPP2_PRS_SRAM_OP_SEL_UDF_MASK);
/* Set base offset as current */
mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_OP_SEL_BASE_OFFS, 1);
@@ -932,8 +917,8 @@ static int mvpp2_prs_ip4_proto(struct mvpp2 *priv, unsigned short proto,
pe.index = tid;
/* Clear ri before updating */
- pe.sram.word[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
- pe.sram.word[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
+ pe.sram[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
+ pe.sram[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
mvpp2_prs_sram_ri_update(&pe, ri, ri_mask);
mvpp2_prs_sram_ri_update(&pe, ri | MVPP2_PRS_RI_IP_FRAG_TRUE,
@@ -1433,17 +1418,13 @@ static int mvpp2_prs_etype_init(struct mvpp2 *priv)
pe.index = tid;
- /* Clear tcam data before updating */
- pe.tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE(MVPP2_ETH_TYPE_LEN)] = 0x0;
- pe.tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE_EN(MVPP2_ETH_TYPE_LEN)] = 0x0;
-
mvpp2_prs_tcam_data_byte_set(&pe, MVPP2_ETH_TYPE_LEN,
MVPP2_PRS_IPV4_HEAD,
MVPP2_PRS_IPV4_HEAD_MASK);
/* Clear ri before updating */
- pe.sram.word[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
- pe.sram.word[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
+ pe.sram[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
+ pe.sram[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_L3_IP4_OPT,
MVPP2_PRS_RI_L3_PROTO_MASK);
@@ -1644,8 +1625,8 @@ static int mvpp2_prs_pppoe_init(struct mvpp2 *priv)
MVPP2_PRS_IPV4_IHL_MASK);
/* Clear ri before updating */
- pe.sram.word[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
- pe.sram.word[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
+ pe.sram[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
+ pe.sram[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_L3_IP4,
MVPP2_PRS_RI_L3_PROTO_MASK);
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
index 22fbbc4c8b28..a7c8d0818432 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
@@ -50,17 +50,25 @@
* The fields are represented by MVPP2_PRS_TCAM_DATA_REG(5)->(0).
*/
#define MVPP2_PRS_AI_BITS 8
+#define MVPP2_PRS_AI_MASK 0xff
#define MVPP2_PRS_PORT_MASK 0xff
#define MVPP2_PRS_LU_MASK 0xf
-#define MVPP2_PRS_TCAM_DATA_BYTE(offs) \
- (((offs) - ((offs) % 2)) * 2 + ((offs) % 2))
-#define MVPP2_PRS_TCAM_DATA_BYTE_EN(offs) \
- (((offs) * 2) - ((offs) % 2) + 2)
-#define MVPP2_PRS_TCAM_AI_BYTE 16
-#define MVPP2_PRS_TCAM_PORT_BYTE 17
-#define MVPP2_PRS_TCAM_LU_BYTE 20
-#define MVPP2_PRS_TCAM_EN_OFFS(offs) ((offs) + 2)
-#define MVPP2_PRS_TCAM_INV_WORD 5
+
+/* TCAM entries in registers are accessed using 16 data bits + 16 enable bits */
+#define MVPP2_PRS_BYTE_TO_WORD(byte) ((byte) / 2)
+#define MVPP2_PRS_BYTE_IN_WORD(byte) ((byte) % 2)
+
+#define MVPP2_PRS_TCAM_EN(data) ((data) << 16)
+#define MVPP2_PRS_TCAM_AI_WORD 4
+#define MVPP2_PRS_TCAM_AI(ai) (ai)
+#define MVPP2_PRS_TCAM_AI_EN(ai) MVPP2_PRS_TCAM_EN(MVPP2_PRS_TCAM_AI(ai))
+#define MVPP2_PRS_TCAM_PORT_WORD 4
+#define MVPP2_PRS_TCAM_PORT(p) ((p) << 8)
+#define MVPP2_PRS_TCAM_PORT_EN(p) MVPP2_PRS_TCAM_EN(MVPP2_PRS_TCAM_PORT(p))
+#define MVPP2_PRS_TCAM_LU_WORD 5
+#define MVPP2_PRS_TCAM_LU(lu) (lu)
+#define MVPP2_PRS_TCAM_LU_EN(lu) MVPP2_PRS_TCAM_EN(MVPP2_PRS_TCAM_LU(lu))
+#define MVPP2_PRS_TCAM_INV_WORD 5
#define MVPP2_PRS_VID_TCAM_BYTE 2
@@ -146,6 +154,7 @@
#define MVPP2_PRS_SRAM_RI_CTRL_BITS 32
#define MVPP2_PRS_SRAM_SHIFT_OFFS 64
#define MVPP2_PRS_SRAM_SHIFT_SIGN_BIT 72
+#define MVPP2_PRS_SRAM_SHIFT_MASK 0xff
#define MVPP2_PRS_SRAM_UDF_OFFS 73
#define MVPP2_PRS_SRAM_UDF_BITS 8
#define MVPP2_PRS_SRAM_UDF_MASK 0xff
@@ -255,20 +264,10 @@ enum mvpp2_prs_lookup {
MVPP2_PRS_LU_LAST,
};
-union mvpp2_prs_tcam_entry {
- u32 word[MVPP2_PRS_TCAM_WORDS];
- u8 byte[MVPP2_PRS_TCAM_WORDS * 4];
-};
-
-union mvpp2_prs_sram_entry {
- u32 word[MVPP2_PRS_SRAM_WORDS];
- u8 byte[MVPP2_PRS_SRAM_WORDS * 4];
-};
-
struct mvpp2_prs_entry {
u32 index;
- union mvpp2_prs_tcam_entry tcam;
- union mvpp2_prs_sram_entry sram;
+ u32 tcam[MVPP2_PRS_TCAM_WORDS];
+ u32 sram[MVPP2_PRS_SRAM_WORDS];
};
struct mvpp2_prs_shadow {
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 3/4] net: mvpp2: prs: Drop unnecessary swab16 in vlan detection
From: Maxime Chevallier @ 2018-06-28 12:42 UTC (permalink / raw)
To: davem
Cc: Maxime Chevallier, netdev, linux-kernel, Antoine Tenart,
thomas.petazzoni, gregory.clement, miquel.raynal, nadavh, stefanc,
ymarkman, mw
In-Reply-To: <20180628124207.11635-1-maxime.chevallier@bootlin.com>
Vlan IDs must not be swapped when creating Header Parser entries. This
has no effect on little-endian systems, but is wrong for big-endian.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
---
drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
index af11feea681c..a882c14d7d77 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
@@ -647,7 +647,7 @@ static int mvpp2_prs_vlan_find(struct mvpp2 *priv, unsigned short tpid, int ai)
continue;
mvpp2_prs_init_from_hw(priv, &pe, tid);
- match = mvpp2_prs_tcam_data_cmp(&pe, 0, swab16(tpid));
+ match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid);
if (!match)
continue;
@@ -775,8 +775,8 @@ static int mvpp2_prs_double_vlan_find(struct mvpp2 *priv, unsigned short tpid1,
mvpp2_prs_init_from_hw(priv, &pe, tid);
- match = mvpp2_prs_tcam_data_cmp(&pe, 0, swab16(tpid1)) &&
- mvpp2_prs_tcam_data_cmp(&pe, 4, swab16(tpid2));
+ match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid1) &&
+ mvpp2_prs_tcam_data_cmp(&pe, 4, tpid2);
if (!match)
continue;
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 4/4] net: mvpp2: Use htons when checking protocol info
From: Maxime Chevallier @ 2018-06-28 12:42 UTC (permalink / raw)
To: davem
Cc: Maxime Chevallier, netdev, linux-kernel, Antoine Tenart,
thomas.petazzoni, gregory.clement, miquel.raynal, nadavh, stefanc,
ymarkman, mw
In-Reply-To: <20180628124207.11635-1-maxime.chevallier@bootlin.com>
When checking the skb->protocol field, we have to make sure we use the
proper endianness using htons, and not swab16.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
---
drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index ded187a20b6c..88f3da184d76 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -1738,7 +1738,7 @@ static u32 mvpp2_txq_desc_csum(int l3_offs, int l3_proto,
command |= (ip_hdr_len << MVPP2_TXD_IP_HLEN_SHIFT);
command |= MVPP2_TXD_IP_CSUM_DISABLE;
- if (l3_proto == swab16(ETH_P_IP)) {
+ if (l3_proto == htons(ETH_P_IP)) {
command &= ~MVPP2_TXD_IP_CSUM_DISABLE; /* enable IPv4 csum */
command &= ~MVPP2_TXD_L3_IP6; /* enable IPv4 */
} else {
--
2.11.0
^ permalink raw reply related
* Re: [PATCH net] strparser: Remove early eaten to fix full tcp receive buffer stall
From: David Miller @ 2018-06-28 12:43 UTC (permalink / raw)
To: doronrk; +Cc: davejwatson, tom, netdev
In-Reply-To: <20180627013333.3584797-1-doronrk@fb.com>
From: Doron Roberts-Kedes <doronrk@fb.com>
Date: Tue, 26 Jun 2018 18:33:33 -0700
> On receving an incomplete message, the existing code stores the
> remaining length of the cloned skb in the early_eaten field instead of
> incrementing the value returned by __strp_recv. This defers invocation
> of sock_rfree for the current skb until the next invocation of
> __strp_recv, which returns early_eaten if early_eaten is non-zero.
>
> This behavior causes a stall when the current message occupies the very
> tail end of a massive skb, and strp_peek/need_bytes indicates that the
> remainder of the current message has yet to arrive on the socket. The
> TCP receive buffer is totally full, causing the TCP window to go to
> zero, so the remainder of the message will never arrive.
>
> Incrementing the value returned by __strp_recv by the amount otherwise
> stored in early_eaten prevents stalls of this nature.
>
> Signed-off-by: Doron Roberts-Kedes <doronrk@fb.com>
Applied and queued up for -stable.
^ permalink raw reply
* Re: [PATCH net] bpfilter: include bpfilter_umh in assembly instead of using objcopy
From: David Miller @ 2018-06-28 12:43 UTC (permalink / raw)
To: ast; +Cc: daniel, torvalds, mcroce, yamada.masahiro, linux, netdev,
kernel-team
In-Reply-To: <20180627031348.285964-1-ast@kernel.org>
From: Alexei Starovoitov <ast@kernel.org>
Date: Tue, 26 Jun 2018 20:13:48 -0700
> From: Masahiro Yamada <yamada.masahiro@socionext.com>
>
> What we want here is to embed a user-space program into the kernel.
> Instead of the complex ELF magic, let's simply wrap it in the assembly
> with the '.incbin' directive.
>
> Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Applied.
^ permalink raw reply
* [less-CONFIG_NET v2 1/8] net: reorder filter code
From: Norbert Manthey @ 2018-06-28 12:45 UTC (permalink / raw)
To: Norbert Manthey, linux-kernel
Cc: Alexei Starovoitov, Daniel Borkmann, David S. Miller, netdev
In-Reply-To: <1530189936-25780-1-git-send-email-nmanthey@amazon.de>
This commit reorders the definition of functions and struct in the
file filter.c, such that in the next step we can easily cut the file
into a commonly used part, as well as a part that is only required in
case CONFIG_NET is actually set.
This is part of the effort to split CONFIG_SECCOMP_FILTER and
CONFIG_NET.
Signed-off-by: Norbert Manthey <nmanthey@amazon.de>
---
net/core/filter.c | 330 +++++++++++++++++++++++++++---------------------------
1 file changed, 165 insertions(+), 165 deletions(-)
diff --git a/net/core/filter.c b/net/core/filter.c
index e7f12e9..61c24c9 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -69,58 +69,6 @@
#include <net/seg6.h>
#include <net/seg6_local.h>
-/**
- * sk_filter_trim_cap - run a packet through a socket filter
- * @sk: sock associated with &sk_buff
- * @skb: buffer to filter
- * @cap: limit on how short the eBPF program may trim the packet
- *
- * Run the eBPF program and then cut skb->data to correct size returned by
- * the program. If pkt_len is 0 we toss packet. If skb->len is smaller
- * than pkt_len we keep whole skb->data. This is the socket level
- * wrapper to BPF_PROG_RUN. It returns 0 if the packet should
- * be accepted or -EPERM if the packet should be tossed.
- *
- */
-int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap)
-{
- int err;
- struct sk_filter *filter;
-
- /*
- * If the skb was allocated from pfmemalloc reserves, only
- * allow SOCK_MEMALLOC sockets to use it as this socket is
- * helping free memory
- */
- if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) {
- NET_INC_STATS(sock_net(sk), LINUX_MIB_PFMEMALLOCDROP);
- return -ENOMEM;
- }
- err = BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb);
- if (err)
- return err;
-
- err = security_sock_rcv_skb(sk, skb);
- if (err)
- return err;
-
- rcu_read_lock();
- filter = rcu_dereference(sk->sk_filter);
- if (filter) {
- struct sock *save_sk = skb->sk;
- unsigned int pkt_len;
-
- skb->sk = sk;
- pkt_len = bpf_prog_run_save_cb(filter->prog, skb);
- skb->sk = save_sk;
- err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM;
- }
- rcu_read_unlock();
-
- return err;
-}
-EXPORT_SYMBOL(sk_filter_trim_cap);
-
BPF_CALL_1(bpf_skb_get_pay_offset, struct sk_buff *, skb)
{
return skb_get_poff(skb);
@@ -256,12 +204,6 @@ BPF_CALL_0(bpf_get_raw_cpu_id)
return raw_smp_processor_id();
}
-static const struct bpf_func_proto bpf_get_raw_smp_processor_id_proto = {
- .func = bpf_get_raw_cpu_id,
- .gpl_only = false,
- .ret_type = RET_INTEGER,
-};
-
static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg,
struct bpf_insn *insn_buf)
{
@@ -1138,71 +1080,6 @@ static void __bpf_prog_release(struct bpf_prog *prog)
}
}
-static void __sk_filter_release(struct sk_filter *fp)
-{
- __bpf_prog_release(fp->prog);
- kfree(fp);
-}
-
-/**
- * sk_filter_release_rcu - Release a socket filter by rcu_head
- * @rcu: rcu_head that contains the sk_filter to free
- */
-static void sk_filter_release_rcu(struct rcu_head *rcu)
-{
- struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu);
-
- __sk_filter_release(fp);
-}
-
-/**
- * sk_filter_release - release a socket filter
- * @fp: filter to remove
- *
- * Remove a filter from a socket and release its resources.
- */
-static void sk_filter_release(struct sk_filter *fp)
-{
- if (refcount_dec_and_test(&fp->refcnt))
- call_rcu(&fp->rcu, sk_filter_release_rcu);
-}
-
-void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
-{
- u32 filter_size = bpf_prog_size(fp->prog->len);
-
- atomic_sub(filter_size, &sk->sk_omem_alloc);
- sk_filter_release(fp);
-}
-
-/* try to charge the socket memory if there is space available
- * return true on success
- */
-static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
-{
- u32 filter_size = bpf_prog_size(fp->prog->len);
-
- /* same check as in sock_kmalloc() */
- if (filter_size <= sysctl_optmem_max &&
- atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) {
- atomic_add(filter_size, &sk->sk_omem_alloc);
- return true;
- }
- return false;
-}
-
-bool sk_filter_charge(struct sock *sk, struct sk_filter *fp)
-{
- if (!refcount_inc_not_zero(&fp->refcnt))
- return false;
-
- if (!__sk_filter_charge(sk, fp)) {
- sk_filter_release(fp);
- return false;
- }
- return true;
-}
-
static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
{
struct sock_filter *old_prog;
@@ -1314,19 +1191,22 @@ static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp,
}
/**
- * bpf_prog_create - create an unattached filter
+ * bpf_prog_create_from_user - create an unattached filter from user buffer
* @pfp: the unattached filter that is created
* @fprog: the filter program
+ * @trans: post-classic verifier transformation handler
+ * @save_orig: save classic BPF program
*
- * Create a filter independent of any socket. We first run some
- * sanity checks on it to make sure it does not explode on us later.
- * If an error occurs or there is insufficient memory for the filter
- * a negative errno code is returned. On success the return is zero.
+ * This function effectively does the same as bpf_prog_create(), only
+ * that it builds up its insns buffer from user space provided buffer.
+ * It also allows for passing a bpf_aux_classic_check_t handler.
*/
-int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog)
+int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
+ bpf_aux_classic_check_t trans, bool save_orig)
{
unsigned int fsize = bpf_classic_proglen(fprog);
struct bpf_prog *fp;
+ int err;
/* Make sure new filter is there and in the right amounts. */
if (!bpf_check_basics_ok(fprog->filter, fprog->len))
@@ -1336,44 +1216,177 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog)
if (!fp)
return -ENOMEM;
- memcpy(fp->insns, fprog->filter, fsize);
+ if (copy_from_user(fp->insns, fprog->filter, fsize)) {
+ __bpf_prog_free(fp);
+ return -EFAULT;
+ }
fp->len = fprog->len;
- /* Since unattached filters are not copied back to user
- * space through sk_get_filter(), we do not need to hold
- * a copy here, and can spare us the work.
- */
fp->orig_prog = NULL;
+ if (save_orig) {
+ err = bpf_prog_store_orig_filter(fp, fprog);
+ if (err) {
+ __bpf_prog_free(fp);
+ return -ENOMEM;
+ }
+ }
+
/* bpf_prepare_filter() already takes care of freeing
* memory in case something goes wrong.
*/
- fp = bpf_prepare_filter(fp, NULL);
+ fp = bpf_prepare_filter(fp, trans);
if (IS_ERR(fp))
return PTR_ERR(fp);
*pfp = fp;
return 0;
}
-EXPORT_SYMBOL_GPL(bpf_prog_create);
+EXPORT_SYMBOL_GPL(bpf_prog_create_from_user);
+
+void bpf_prog_destroy(struct bpf_prog *fp)
+{
+ __bpf_prog_release(fp);
+}
+EXPORT_SYMBOL_GPL(bpf_prog_destroy);
/**
- * bpf_prog_create_from_user - create an unattached filter from user buffer
+ * sk_filter_trim_cap - run a packet through a socket filter
+ * @sk: sock associated with &sk_buff
+ * @skb: buffer to filter
+ * @cap: limit on how short the eBPF program may trim the packet
+ *
+ * Run the eBPF program and then cut skb->data to correct size returned by
+ * the program. If pkt_len is 0 we toss packet. If skb->len is smaller
+ * than pkt_len we keep whole skb->data. This is the socket level
+ * wrapper to BPF_PROG_RUN. It returns 0 if the packet should
+ * be accepted or -EPERM if the packet should be tossed.
+ *
+ */
+int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap)
+{
+ int err;
+ struct sk_filter *filter;
+
+ /*
+ * If the skb was allocated from pfmemalloc reserves, only
+ * allow SOCK_MEMALLOC sockets to use it as this socket is
+ * helping free memory
+ */
+ if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) {
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_PFMEMALLOCDROP);
+ return -ENOMEM;
+ }
+ err = BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb);
+ if (err)
+ return err;
+
+ err = security_sock_rcv_skb(sk, skb);
+ if (err)
+ return err;
+
+ rcu_read_lock();
+ filter = rcu_dereference(sk->sk_filter);
+ if (filter) {
+ struct sock *save_sk = skb->sk;
+ unsigned int pkt_len;
+
+ skb->sk = sk;
+ pkt_len = bpf_prog_run_save_cb(filter->prog, skb);
+ skb->sk = save_sk;
+ err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM;
+ }
+ rcu_read_unlock();
+
+ return err;
+}
+EXPORT_SYMBOL(sk_filter_trim_cap);
+
+static const struct bpf_func_proto bpf_get_raw_smp_processor_id_proto = {
+ .func = bpf_get_raw_cpu_id,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+};
+
+static void __sk_filter_release(struct sk_filter *fp)
+{
+ __bpf_prog_release(fp->prog);
+ kfree(fp);
+}
+
+/**
+ * sk_filter_release_rcu - Release a socket filter by rcu_head
+ * @rcu: rcu_head that contains the sk_filter to free
+ */
+static void sk_filter_release_rcu(struct rcu_head *rcu)
+{
+ struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu);
+
+ __sk_filter_release(fp);
+}
+
+/**
+ * sk_filter_release - release a socket filter
+ * @fp: filter to remove
+ *
+ * Remove a filter from a socket and release its resources.
+ */
+static void sk_filter_release(struct sk_filter *fp)
+{
+ if (refcount_dec_and_test(&fp->refcnt))
+ call_rcu(&fp->rcu, sk_filter_release_rcu);
+}
+
+void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
+{
+ u32 filter_size = bpf_prog_size(fp->prog->len);
+
+ atomic_sub(filter_size, &sk->sk_omem_alloc);
+ sk_filter_release(fp);
+}
+
+/* try to charge the socket memory if there is space available
+ * return true on success
+ */
+static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
+{
+ u32 filter_size = bpf_prog_size(fp->prog->len);
+
+ /* same check as in sock_kmalloc() */
+ if (filter_size <= sysctl_optmem_max &&
+ atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) {
+ atomic_add(filter_size, &sk->sk_omem_alloc);
+ return true;
+ }
+ return false;
+}
+
+bool sk_filter_charge(struct sock *sk, struct sk_filter *fp)
+{
+ if (!refcount_inc_not_zero(&fp->refcnt))
+ return false;
+
+ if (!__sk_filter_charge(sk, fp)) {
+ sk_filter_release(fp);
+ return false;
+ }
+ return true;
+}
+
+/**
+ * bpf_prog_create - create an unattached filter
* @pfp: the unattached filter that is created
* @fprog: the filter program
- * @trans: post-classic verifier transformation handler
- * @save_orig: save classic BPF program
*
- * This function effectively does the same as bpf_prog_create(), only
- * that it builds up its insns buffer from user space provided buffer.
- * It also allows for passing a bpf_aux_classic_check_t handler.
+ * Create a filter independent of any socket. We first run some
+ * sanity checks on it to make sure it does not explode on us later.
+ * If an error occurs or there is insufficient memory for the filter
+ * a negative errno code is returned. On success the return is zero.
*/
-int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
- bpf_aux_classic_check_t trans, bool save_orig)
+int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog)
{
unsigned int fsize = bpf_classic_proglen(fprog);
struct bpf_prog *fp;
- int err;
/* Make sure new filter is there and in the right amounts. */
if (!bpf_check_basics_ok(fprog->filter, fprog->len))
@@ -1383,39 +1396,26 @@ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
if (!fp)
return -ENOMEM;
- if (copy_from_user(fp->insns, fprog->filter, fsize)) {
- __bpf_prog_free(fp);
- return -EFAULT;
- }
+ memcpy(fp->insns, fprog->filter, fsize);
fp->len = fprog->len;
+ /* Since unattached filters are not copied back to user
+ * space through sk_get_filter(), we do not need to hold
+ * a copy here, and can spare us the work.
+ */
fp->orig_prog = NULL;
- if (save_orig) {
- err = bpf_prog_store_orig_filter(fp, fprog);
- if (err) {
- __bpf_prog_free(fp);
- return -ENOMEM;
- }
- }
-
/* bpf_prepare_filter() already takes care of freeing
* memory in case something goes wrong.
*/
- fp = bpf_prepare_filter(fp, trans);
+ fp = bpf_prepare_filter(fp, NULL);
if (IS_ERR(fp))
return PTR_ERR(fp);
*pfp = fp;
return 0;
}
-EXPORT_SYMBOL_GPL(bpf_prog_create_from_user);
-
-void bpf_prog_destroy(struct bpf_prog *fp)
-{
- __bpf_prog_release(fp);
-}
-EXPORT_SYMBOL_GPL(bpf_prog_destroy);
+EXPORT_SYMBOL_GPL(bpf_prog_create);
static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
{
--
2.7.4
Amazon Development Center Germany GmbH
Berlin - Dresden - Aachen
main office: Krausenstr. 38, 10117 Berlin
Geschaeftsfuehrer: Dr. Ralf Herbrich, Christian Schlaeger
Ust-ID: DE289237879
Eingetragen am Amtsgericht Charlottenburg HRB 149173 B
^ permalink raw reply related
* [less-CONFIG_NET v2 2/8] net: reorder flow_dissector
From: Norbert Manthey @ 2018-06-28 12:45 UTC (permalink / raw)
To: Norbert Manthey, linux-kernel
Cc: David S. Miller, David Ahern, Jiri Pirko, Jon Maloy, Simon Horman,
Paolo Abeni, Tom Herbert, Michal Kubecek, Sven Eckelmann,
WANG Cong, netdev
In-Reply-To: <1530189936-25780-1-git-send-email-nmanthey@amazon.de>
This commit reorders the definitions, such that in the next step we
can easily cut the file into a commonly used part, as well as a part
that is only required in case CONFIG_NET is used.
This is part of the effort to split CONFIG_SECCOMP_FILTER and
CONFIG_NET.
Signed-off-by: Norbert Manthey <nmanthey@amazon.de>
---
net/core/flow_dissector.c | 206 +++++++++++++++++++++++-----------------------
1 file changed, 103 insertions(+), 103 deletions(-)
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 53f96e4..76d0b23 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1085,36 +1085,6 @@ static inline size_t flow_keys_hash_length(const struct flow_keys *flow)
return (sizeof(*flow) - diff) / sizeof(u32);
}
-__be32 flow_get_u32_src(const struct flow_keys *flow)
-{
- switch (flow->control.addr_type) {
- case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
- return flow->addrs.v4addrs.src;
- case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
- return (__force __be32)ipv6_addr_hash(
- &flow->addrs.v6addrs.src);
- case FLOW_DISSECTOR_KEY_TIPC:
- return flow->addrs.tipckey.key;
- default:
- return 0;
- }
-}
-EXPORT_SYMBOL(flow_get_u32_src);
-
-__be32 flow_get_u32_dst(const struct flow_keys *flow)
-{
- switch (flow->control.addr_type) {
- case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
- return flow->addrs.v4addrs.dst;
- case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
- return (__force __be32)ipv6_addr_hash(
- &flow->addrs.v6addrs.dst);
- default:
- return 0;
- }
-}
-EXPORT_SYMBOL(flow_get_u32_dst);
-
static inline void __flow_hash_consistentify(struct flow_keys *keys)
{
int addr_diff, i;
@@ -1162,49 +1132,6 @@ static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval)
return hash;
}
-u32 flow_hash_from_keys(struct flow_keys *keys)
-{
- __flow_hash_secret_init();
- return __flow_hash_from_keys(keys, hashrnd);
-}
-EXPORT_SYMBOL(flow_hash_from_keys);
-
-static inline u32 ___skb_get_hash(const struct sk_buff *skb,
- struct flow_keys *keys, u32 keyval)
-{
- skb_flow_dissect_flow_keys(skb, keys,
- FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
-
- return __flow_hash_from_keys(keys, keyval);
-}
-
-struct _flow_keys_digest_data {
- __be16 n_proto;
- u8 ip_proto;
- u8 padding;
- __be32 ports;
- __be32 src;
- __be32 dst;
-};
-
-void make_flow_keys_digest(struct flow_keys_digest *digest,
- const struct flow_keys *flow)
-{
- struct _flow_keys_digest_data *data =
- (struct _flow_keys_digest_data *)digest;
-
- BUILD_BUG_ON(sizeof(*data) > sizeof(*digest));
-
- memset(digest, 0, sizeof(*digest));
-
- data->n_proto = flow->basic.n_proto;
- data->ip_proto = flow->basic.ip_proto;
- data->ports = flow->ports.ports;
- data->src = flow->addrs.v4addrs.src;
- data->dst = flow->addrs.v4addrs.dst;
-}
-EXPORT_SYMBOL(make_flow_keys_digest);
-
static struct flow_dissector flow_keys_dissector_symmetric __read_mostly;
u32 __skb_get_hash_symmetric(const struct sk_buff *skb)
@@ -1222,36 +1149,6 @@ u32 __skb_get_hash_symmetric(const struct sk_buff *skb)
}
EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric);
-/**
- * __skb_get_hash: calculate a flow hash
- * @skb: sk_buff to calculate flow hash from
- *
- * This function calculates a flow hash based on src/dst addresses
- * and src/dst port numbers. Sets hash in skb to non-zero hash value
- * on success, zero indicates no valid hash. Also, sets l4_hash in skb
- * if hash is a canonical 4-tuple hash over transport ports.
- */
-void __skb_get_hash(struct sk_buff *skb)
-{
- struct flow_keys keys;
- u32 hash;
-
- __flow_hash_secret_init();
-
- hash = ___skb_get_hash(skb, &keys, hashrnd);
-
- __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys));
-}
-EXPORT_SYMBOL(__skb_get_hash);
-
-__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb)
-{
- struct flow_keys keys;
-
- return ___skb_get_hash(skb, &keys, perturb);
-}
-EXPORT_SYMBOL(skb_get_hash_perturb);
-
u32 __skb_get_poff(const struct sk_buff *skb, void *data,
const struct flow_keys_basic *keys, int hlen)
{
@@ -1322,6 +1219,109 @@ u32 skb_get_poff(const struct sk_buff *skb)
return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb));
}
+__be32 flow_get_u32_src(const struct flow_keys *flow)
+{
+ switch (flow->control.addr_type) {
+ case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
+ return flow->addrs.v4addrs.src;
+ case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
+ return (__force __be32)ipv6_addr_hash(
+ &flow->addrs.v6addrs.src);
+ case FLOW_DISSECTOR_KEY_TIPC:
+ return flow->addrs.tipckey.key;
+ default:
+ return 0;
+ }
+}
+EXPORT_SYMBOL(flow_get_u32_src);
+
+__be32 flow_get_u32_dst(const struct flow_keys *flow)
+{
+ switch (flow->control.addr_type) {
+ case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
+ return flow->addrs.v4addrs.dst;
+ case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
+ return (__force __be32)ipv6_addr_hash(
+ &flow->addrs.v6addrs.dst);
+ default:
+ return 0;
+ }
+}
+EXPORT_SYMBOL(flow_get_u32_dst);
+
+u32 flow_hash_from_keys(struct flow_keys *keys)
+{
+ __flow_hash_secret_init();
+ return __flow_hash_from_keys(keys, hashrnd);
+}
+EXPORT_SYMBOL(flow_hash_from_keys);
+
+static inline u32 ___skb_get_hash(const struct sk_buff *skb,
+ struct flow_keys *keys, u32 keyval)
+{
+ skb_flow_dissect_flow_keys(skb, keys,
+ FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
+
+ return __flow_hash_from_keys(keys, keyval);
+}
+
+struct _flow_keys_digest_data {
+ __be16 n_proto;
+ u8 ip_proto;
+ u8 padding;
+ __be32 ports;
+ __be32 src;
+ __be32 dst;
+};
+
+void make_flow_keys_digest(struct flow_keys_digest *digest,
+ const struct flow_keys *flow)
+{
+ struct _flow_keys_digest_data *data =
+ (struct _flow_keys_digest_data *)digest;
+
+ BUILD_BUG_ON(sizeof(*data) > sizeof(*digest));
+
+ memset(digest, 0, sizeof(*digest));
+
+ data->n_proto = flow->basic.n_proto;
+ data->ip_proto = flow->basic.ip_proto;
+ data->ports = flow->ports.ports;
+ data->src = flow->addrs.v4addrs.src;
+ data->dst = flow->addrs.v4addrs.dst;
+}
+EXPORT_SYMBOL(make_flow_keys_digest);
+
+/**
+ * __skb_get_hash: calculate a flow hash
+ * @skb: sk_buff to calculate flow hash from
+ *
+ * This function calculates a flow hash based on src/dst addresses
+ * and src/dst port numbers. Sets hash in skb to non-zero hash value
+ * on success, zero indicates no valid hash. Also, sets l4_hash in skb
+ * if hash is a canonical 4-tuple hash over transport ports.
+ */
+void __skb_get_hash(struct sk_buff *skb)
+{
+ struct flow_keys keys;
+ u32 hash;
+
+ __flow_hash_secret_init();
+
+ hash = ___skb_get_hash(skb, &keys, hashrnd);
+
+ __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys));
+}
+EXPORT_SYMBOL(__skb_get_hash);
+
+__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb)
+{
+ struct flow_keys keys;
+
+ return ___skb_get_hash(skb, &keys, perturb);
+}
+EXPORT_SYMBOL(skb_get_hash_perturb);
+
__u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys)
{
memset(keys, 0, sizeof(*keys));
--
2.7.4
Amazon Development Center Germany GmbH
Berlin - Dresden - Aachen
main office: Krausenstr. 38, 10117 Berlin
Geschaeftsfuehrer: Dr. Ralf Herbrich, Christian Schlaeger
Ust-ID: DE289237879
Eingetragen am Amtsgericht Charlottenburg HRB 149173 B
^ permalink raw reply related
* [less-CONFIG_NET v2 3/8] seccomp: include net
From: Norbert Manthey @ 2018-06-28 12:45 UTC (permalink / raw)
To: Norbert Manthey, linux-kernel
Cc: Alexei Starovoitov, Daniel Borkmann, David S. Miller, netdev
In-Reply-To: <1530189936-25780-1-git-send-email-nmanthey@amazon.de>
When we want to use CONFIG_SECCOMP_FILTER without CONFIG_NET, we have
to ensure that the required files that would be pulled in via
CONFIG_NET are compiled when dropping CONFIG_NET.
Signed-off-by: Norbert Manthey <nmanthey@amazon.de>
---
kernel/bpf/Makefile | 1 +
net/Makefile | 5 +++++
2 files changed, 6 insertions(+)
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index f27f549..16936c0 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -5,6 +5,7 @@ obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
obj-$(CONFIG_BPF_SYSCALL) += disasm.o
obj-$(CONFIG_BPF_SYSCALL) += btf.o
+
ifeq ($(CONFIG_NET),y)
obj-$(CONFIG_BPF_SYSCALL) += devmap.o
obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
diff --git a/net/Makefile b/net/Makefile
index 13ec0d5..f3fb03a 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -11,6 +11,11 @@ obj-$(CONFIG_NET) := socket.o core/
tmp-$(CONFIG_COMPAT) := compat.o
obj-$(CONFIG_NET) += $(tmp-y)
+ifneq ($(CONFIG_NET),y)
+obj-$(CONFIG_SECCOMP_FILTER) += core/filter.o
+obj-$(CONFIG_SECCOMP_FILTER) += core/flow_dissector.o
+endif
+
# LLC has to be linked before the files in net/802/
obj-$(CONFIG_LLC) += llc/
obj-$(CONFIG_NET) += ethernet/ 802/ sched/ netlink/ bpf/
--
2.7.4
Amazon Development Center Germany GmbH
Berlin - Dresden - Aachen
main office: Krausenstr. 38, 10117 Berlin
Geschaeftsfuehrer: Dr. Ralf Herbrich, Christian Schlaeger
Ust-ID: DE289237879
Eingetragen am Amtsgericht Charlottenburg HRB 149173 B
^ permalink raw reply related
* [less-CONFIG_NET v2 5/8] seccomp: cut off functions not required
From: Norbert Manthey @ 2018-06-28 12:45 UTC (permalink / raw)
To: Norbert Manthey, linux-kernel
Cc: Alexei Starovoitov, Daniel Borkmann, David S. Miller,
Ido Schimmel, Paolo Abeni, Andrew Lunn, Tom Herbert, Simon Horman,
Michal Kubecek, John Crispin, Sven Eckelmann, WANG Cong,
David Ahern, Jon Maloy, netdev
In-Reply-To: <1530189936-25780-1-git-send-email-nmanthey@amazon.de>
When using CONFIG_SECCOMP_FILTER, not all functions of filter.c and
flow_dissector.c are required. To not pull in more dependencies,
guard the functions that are not required with CONFIG_NET defines.
This way, these functions are enabled in case the file is compiled
because of CONFIG_NET, but they are not present when the file is
compiled because of other configurations.
Signed-off-by: Norbert Manthey <nmanthey@amazon.de>
---
net/core/filter.c | 2 ++
net/core/flow_dissector.c | 2 ++
2 files changed, 4 insertions(+)
diff --git a/net/core/filter.c b/net/core/filter.c
index 61c24c9..410189c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1250,6 +1250,7 @@ void bpf_prog_destroy(struct bpf_prog *fp)
}
EXPORT_SYMBOL_GPL(bpf_prog_destroy);
+#if defined(CONFIG_NET)
/**
* sk_filter_trim_cap - run a packet through a socket filter
* @sk: sock associated with &sk_buff
@@ -6823,3 +6824,4 @@ int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf,
release_sock(sk);
return ret;
}
+#endif // CONFIG_NET
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 76d0b23..f5ba8e9 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1219,6 +1219,7 @@ u32 skb_get_poff(const struct sk_buff *skb)
return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb));
}
+#if defined(CONFIG_NET)
__be32 flow_get_u32_src(const struct flow_keys *flow)
{
switch (flow->control.addr_type) {
@@ -1340,6 +1341,7 @@ __u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys)
return flow_hash_from_keys(keys);
}
EXPORT_SYMBOL(__get_hash_from_flowi6);
+#endif // CONFIG_NET
static const struct flow_dissector_key flow_keys_dissector_keys[] = {
{
--
2.7.4
Amazon Development Center Germany GmbH
Berlin - Dresden - Aachen
main office: Krausenstr. 38, 10117 Berlin
Geschaeftsfuehrer: Dr. Ralf Herbrich, Christian Schlaeger
Ust-ID: DE289237879
Eingetragen am Amtsgericht Charlottenburg HRB 149173 B
^ permalink raw reply related
* [less-CONFIG_NET v2 6/8] bpf: avoid duplicate definitions
From: Norbert Manthey @ 2018-06-28 12:45 UTC (permalink / raw)
To: Norbert Manthey, linux-kernel; +Cc: Alexei Starovoitov, Daniel Borkmann, netdev
In-Reply-To: <1530189936-25780-1-git-send-email-nmanthey@amazon.de>
With the aim of making CONFIG_SECCOMP_FILTER independent of CONFIG_NET,
some bpf functions are not required to provide net functionality, as
already implemented in the header include/linux/bpf.h. However, the source
files assumed to be only included if CONFIG_NET is activated.
To be able to include the source files while CONFIG_NET is disabled, make
sure the functions defined in the header include/linux/bpf.h are not
included in the source file.
To reduce the amount of #ifdef CONFIG_NET guards, the position of the
functions __bpf_map_offload_destroy and bpf_map_offload_map_alloc has been
swapped.
Signed-off-by: Norbert Manthey <nmanthey@amazon.de>
---
kernel/bpf/offload.c | 22 +++++++++++++---------
1 file changed, 13 insertions(+), 9 deletions(-)
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index ac747d5..7042dbe 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -32,6 +32,7 @@ static DECLARE_RWSEM(bpf_devs_lock);
static LIST_HEAD(bpf_prog_offload_devs);
static LIST_HEAD(bpf_map_offload_devs);
+#ifdef CONFIG_NET
static int bpf_dev_offload_check(struct net_device *netdev)
{
if (!netdev)
@@ -84,6 +85,7 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
kfree(offload);
return err;
}
+#endif // CONFIG_NET
static int __bpf_offload_ndo(struct bpf_prog *prog, enum bpf_netdev_command cmd,
struct netdev_bpf *data)
@@ -291,6 +293,16 @@ static int bpf_map_offload_ndo(struct bpf_offloaded_map *offmap,
return netdev->netdev_ops->ndo_bpf(netdev, &data);
}
+static void __bpf_map_offload_destroy(struct bpf_offloaded_map *offmap)
+{
+ WARN_ON(bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_FREE));
+ /* Make sure BPF_MAP_GET_NEXT_ID can't find this dead map */
+ bpf_map_free_id(&offmap->map, true);
+ list_del_init(&offmap->offloads);
+ offmap->netdev = NULL;
+}
+
+#ifdef CONFIG_NET
struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
{
struct net *net = current->nsproxy->net_ns;
@@ -333,15 +345,6 @@ struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
return ERR_PTR(err);
}
-static void __bpf_map_offload_destroy(struct bpf_offloaded_map *offmap)
-{
- WARN_ON(bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_FREE));
- /* Make sure BPF_MAP_GET_NEXT_ID can't find this dead map */
- bpf_map_free_id(&offmap->map, true);
- list_del_init(&offmap->offloads);
- offmap->netdev = NULL;
-}
-
void bpf_map_offload_map_free(struct bpf_map *map)
{
struct bpf_offloaded_map *offmap = map_to_offmap(map);
@@ -355,6 +358,7 @@ void bpf_map_offload_map_free(struct bpf_map *map)
kfree(offmap);
}
+#endif // CONFIG_NET
int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value)
{
--
2.7.4
Amazon Development Center Germany GmbH
Berlin - Dresden - Aachen
main office: Krausenstr. 38, 10117 Berlin
Geschaeftsfuehrer: Dr. Ralf Herbrich, Christian Schlaeger
Ust-ID: DE289237879
Eingetragen am Amtsgericht Charlottenburg HRB 149173 B
^ permalink raw reply related
* Re: [PATCH] net: phy: DP83TC811: Fix diabling interrupts
From: Andrew Lunn @ 2018-06-28 12:47 UTC (permalink / raw)
To: Dan Murphy; +Cc: f.fainelli, netdev
In-Reply-To: <20180628121332.10457-1-dmurphy@ti.com>
On Thu, Jun 28, 2018 at 07:13:32AM -0500, Dan Murphy wrote:
> Fix a bug where INT_STAT1 was written twice and
> INT_STAT2 was ignored when disabling interrupts.
Hi Dan
You should put in the subject line which tree this is for, eg.
[PATCH net].
Also, you should add a fixes tag, indicating when this bug as added.
Fixes: b753a9faaf9a ("net: phy: DP83TC811: Introduce support for the DP83TC811 phy")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Andrew
^ permalink raw reply
* Re: [PATCH net] tcp: add one more quick ack after after ECN events
From: David Miller @ 2018-06-28 13:02 UTC (permalink / raw)
To: edumazet; +Cc: netdev, eric.dumazet, brakmo
In-Reply-To: <20180627154721.195722-1-edumazet@google.com>
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 27 Jun 2018 08:47:21 -0700
> Larry Brakmo proposal ( https://patchwork.ozlabs.org/patch/935233/
> tcp: force cwnd at least 2 in tcp_cwnd_reduction) made us rethink
> about our recent patch removing ~16 quick acks after ECN events.
>
> tcp_enter_quickack_mode(sk, 1) makes sure one immediate ack is sent,
> but in the case the sender cwnd was lowered to 1, we do not want
> to have a delayed ack for the next packet we will receive.
>
> Fixes: 522040ea5fdd ("tcp: do not aggressively quick ack after ECN events")
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> Reported-by: Neal Cardwell <ncardwell@google.com>
> Cc: Lawrence Brakmo <brakmo@fb.com>
Applied.
^ permalink raw reply
* Re: [PATCH net 1/1] net/smc: rebuild nonblocking connect
From: David Miller @ 2018-06-28 13:04 UTC (permalink / raw)
To: ubraun
Cc: netdev, linux-s390, schwidefsky, heiko.carstens, raspl,
xiyou.wangcong, eric.dumazet
In-Reply-To: <20180627155950.21153-1-ubraun@linux.ibm.com>
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Wed, 27 Jun 2018 17:59:50 +0200
> The recent poll change may lead to stalls for non-blocking connecting
> SMC sockets, since sock_poll_wait is no longer performed on the
> internal CLC socket, but on the outer SMC socket. kernel_connect() on
> the internal CLC socket returns with -EINPROGRESS, but the wake up
> logic does not work in all cases. If the internal CLC socket is still
> in state TCP_SYN_SENT when polled, sock_poll_wait() from sock_poll()
> does not sleep. It is supposed to sleep till the state of the internal
> CLC socket switches to TCP_ESTABLISHED.
>
> This problem triggered a redesign of the SMC nonblocking connect logic.
> This patch introduces a connect worker covering all connect steps
> followed by a wake up of socket waiters. It allows to get rid of all
> delays and locks in smc_poll().
>
> Fixes: c0129a061442 ("smc: convert to ->poll_mask")
> Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Applied.
^ permalink raw reply
* Re: [PATCH net-next] netem: slotting with non-uniform distribution
From: David Miller @ 2018-06-28 13:07 UTC (permalink / raw)
To: ysseung; +Cc: netdev
In-Reply-To: <20180627173219.112027-1-ysseung@google.com>
From: Yousuk Seung <ysseung@google.com>
Date: Wed, 27 Jun 2018 10:32:19 -0700
> Extend slotting with support for non-uniform distributions. This is
> similar to netem's non-uniform distribution delay feature.
>
> Commit f043efeae2f1 ("netem: support delivering packets in delayed
> time slots") added the slotting feature to approximate the behaviors
> of media with packet aggregation but only supported a uniform
> distribution for delays between transmission attempts. Tests with TCP
> BBR with emulated wifi links with non-uniform distributions produced
> more useful results.
>
> Syntax:
> slot dist DISTRIBUTION DELAY JITTER [packets MAX_PACKETS] \
> [bytes MAX_BYTES]
>
> The syntax and use of the distribution table is the same as in the
> non-uniform distribution delay feature. A file DISTRIBUTION must be
> present in TC_LIB_DIR (e.g. /usr/lib/tc) containing numbers scaled by
> NETEM_DIST_SCALE. A random value x is selected from the table and it
> takes DELAY + ( x * JITTER ) as delay. Correlation between values is not
> supported.
>
> Examples:
> Normal distribution delay with mean = 800us and stdev = 100us.
> > tc qdisc add dev eth0 root netem slot dist normal 800us 100us
>
> Optionally set the max slot size in bytes and/or packets.
> > tc qdisc add dev eth0 root netem slot dist normal 800us 100us \
> bytes 64k packets 42
>
> Signed-off-by: Yousuk Seung <ysseung@google.com>
> Acked-by: Eric Dumazet <edumazet@google.com>
> Acked-by: Neal Cardwell <ncardwell@google.com>
Applied.
^ permalink raw reply
* [PATCH] wlcore: Fix memory leak in wlcore_cmd_wait_for_event_or_timeout
From: Gustavo A. R. Silva @ 2018-06-28 13:08 UTC (permalink / raw)
To: Tony Lindgren, Kalle Valo, David S. Miller
Cc: linux-wireless-u79uwXL29TY76Z2rM5mHXA,
netdev-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA, Gustavo A. R. Silva
In case memory resources for *events_vector* were allocated, release
them before return.
Addresses-Coverity-ID: 1470194 ("Resource leak")
Fixes: 4ec7cece87b3 ("wlcore: Add missing PM call for wlcore_cmd_wait_for_event_or_timeout()")
Signed-off-by: Gustavo A. R. Silva <gustavo-L1vi/lXTdts+Va1GwOuvDg@public.gmane.org>
---
drivers/net/wireless/ti/wlcore/cmd.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/wireless/ti/wlcore/cmd.c b/drivers/net/wireless/ti/wlcore/cmd.c
index 836c616..9039687 100644
--- a/drivers/net/wireless/ti/wlcore/cmd.c
+++ b/drivers/net/wireless/ti/wlcore/cmd.c
@@ -195,8 +195,7 @@ int wlcore_cmd_wait_for_event_or_timeout(struct wl1271 *wl,
ret = pm_runtime_get_sync(wl->dev);
if (ret < 0) {
pm_runtime_put_noidle(wl->dev);
^ permalink raw reply related
* [patch net-next v2 0/9] net: sched: introduce chain templates support with offloading to mlxsw
From: Jiri Pirko @ 2018-06-28 13:08 UTC (permalink / raw)
To: netdev
Cc: davem, jhs, xiyou.wangcong, jakub.kicinski, simon.horman,
john.hurley, dsahern, mlxsw, sridhar.samudrala
From: Jiri Pirko <jiri@mellanox.com>
For the TC clsact offload these days, some of HW drivers need
to hold a magic ball. The reason is, with the first inserted rule inside
HW they need to guess what fields will be used for the matching. If
later on this guess proves to be wrong and user adds a filter with a
different field to match, there's a problem. Mlxsw resolves it now with
couple of patterns. Those try to cover as many match fields as possible.
This aproach is far from optimal, both performance-wise and scale-wise.
Also, there is a combination of filters that in certain order won't
succeed.
Most of the time, when user inserts filters in chain, he knows right away
how the filters are going to look like - what type and option will they
have. For example, he knows that he will only insert filters of type
flower matching destination IP address. He can specify a template that
would cover all the filters in the chain.
This patchset is providing the possibility to user to provide such
template to kernel and propagate it all the way down to device
drivers.
See the examples below.
Create dummy device with clsact first:
# ip link add type dummy
# tc qdisc add dev dummy0 clsact
There is no template assigned by default:
# tc chaintemplate show dev dummy0 ingress
Add a template of type flower allowing to insert rules matching on last
2 bytes of destination mac address:
# tc chaintemplate add dev dummy0 ingress proto ip flower dst_mac 00:00:00:00:00:00/00:00:00:00:FF:FF
The template is now showed in the list:
# tc chaintemplate show dev dummy0 ingress
chaintemplate flower chain 0
dst_mac 00:00:00:00:00:00/00:00:00:00:ff:ff
eth_type ipv4
Add another template, this time for chain number 22:
# tc chaintemplate add dev dummy0 ingress proto ip chain 22 flower dst_ip 0.0.0.0/16
# tc chaintemplate show dev dummy0 ingress
chaintemplate flower chain 0
dst_mac 00:00:00:00:00:00/00:00:00:00:ff:ff
eth_type ipv4
chaintemplate flower chain 22
eth_type ipv4
dst_ip 0.0.0.0/16
Add a filter that fits the template:
# tc filter add dev dummy0 ingress proto ip flower dst_mac aa:bb:cc:dd:ee:ff/00:00:00:00:00:0F action drop
Addition of filters that does not fit the template would fail:
# tc filter add dev dummy0 ingress proto ip flower dst_mac aa:11:22:33:44:55/00:00:00:FF:00:00 action drop
Error: Mask does not fit the template.
We have an error talking to the kernel, -1
# tc filter add dev dummy0 ingress proto ip flower dst_ip 10.0.0.1 action drop
Error: Mask does not fit the template.
We have an error talking to the kernel, -1
Additions of filters to chain 22:
# tc filter add dev dummy0 ingress proto ip chain 22 flower dst_ip 10.0.0.1/8 action drop
# tc filter add dev dummy0 ingress proto ip chain 22 flower dst_ip 10.0.0.1 action drop
Error: Mask does not fit the template.
We have an error talking to the kernel, -1
# tc filter add dev dummy0 ingress proto ip chain 22 flower dst_ip 10.0.0.1/24 action drop
Error: Mask does not fit the template.
We have an error talking to the kernel, -1
Removal of a template from non-empty chain would fail:
# tc chaintemplate del dev dummy0 ingress
Error: The chain is not empty, unable to delete template.
We have an error talking to the kernel, -1
Once the chain is flushed, the template could be removed:
# tc filter del dev dummy0 ingress
# tc chaintemplate del dev dummy0 ingress
---
v1->v2:
- patch 5:
- rebase on top of the reoffload pathset
- patch 6:
- remove leftover extack arg in fl_hw_create_tmplt()
- rebase on top of the reoffload pathset
- patch 9:
- adjust to the userspace cmdline changes
Jiri Pirko (9):
net: sched: push ops lookup bits into tcf_proto_lookup_ops()
net: sched: introduce chain templates
net: sched: cls_flower: move key/mask dumping into a separate function
net: sched: cls_flower: change fl_init_dissector to accept mask and
dissector
net: sched: cls_flower: implement chain templates
net: sched: cls_flower: propagate chain teplate creation and
destruction to drivers
mlxsw: spectrum: Implement chain template hinting
selftests: forwarding: move shblock tc support check to a separate
helper
selftests: forwarding: add tests for TC chain templates
drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 5 +
drivers/net/ethernet/mellanox/mlxsw/spectrum.h | 12 +-
drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c | 12 +-
.../ethernet/mellanox/mlxsw/spectrum_acl_tcam.c | 25 +-
.../net/ethernet/mellanox/mlxsw/spectrum_flower.c | 44 ++-
include/net/pkt_cls.h | 2 +
include/net/sch_generic.h | 14 +-
include/uapi/linux/rtnetlink.h | 7 +
net/sched/cls_api.c | 424 +++++++++++++++++++--
net/sched/cls_basic.c | 2 +-
net/sched/cls_bpf.c | 3 +-
net/sched/cls_cgroup.c | 2 +-
net/sched/cls_flow.c | 3 +-
net/sched/cls_flower.c | 250 +++++++++---
net/sched/cls_fw.c | 3 +-
net/sched/cls_matchall.c | 3 +-
net/sched/cls_route.c | 2 +-
net/sched/cls_rsvp.h | 3 +-
net/sched/cls_tcindex.c | 2 +-
net/sched/cls_u32.c | 2 +-
security/selinux/nlmsgtab.c | 2 +-
tools/testing/selftests/net/forwarding/lib.sh | 12 +
.../selftests/net/forwarding/tc_chaintemplates.sh | 160 ++++++++
.../selftests/net/forwarding/tc_shblocks.sh | 2 +
24 files changed, 900 insertions(+), 96 deletions(-)
create mode 100755 tools/testing/selftests/net/forwarding/tc_chaintemplates.sh
--
2.14.4
^ permalink raw reply
* [patch net-next v2 1/9] net: sched: push ops lookup bits into tcf_proto_lookup_ops()
From: Jiri Pirko @ 2018-06-28 13:08 UTC (permalink / raw)
To: netdev
Cc: davem, jhs, xiyou.wangcong, jakub.kicinski, simon.horman,
john.hurley, dsahern, mlxsw, sridhar.samudrala
In-Reply-To: <20180628130907.951-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@mellanox.com>
Push all bits that take care of ops lookup, including module loading
outside tcf_proto_create() function, into tcf_proto_lookup_ops()
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
net/sched/cls_api.c | 53 +++++++++++++++++++++++++++++++----------------------
1 file changed, 31 insertions(+), 22 deletions(-)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index bbf8dda96b0e..b74909fa68a3 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -39,7 +39,7 @@ static DEFINE_RWLOCK(cls_mod_lock);
/* Find classifier type by string name */
-static const struct tcf_proto_ops *tcf_proto_lookup_ops(const char *kind)
+static const struct tcf_proto_ops *__tcf_proto_lookup_ops(const char *kind)
{
const struct tcf_proto_ops *t, *res = NULL;
@@ -57,6 +57,33 @@ static const struct tcf_proto_ops *tcf_proto_lookup_ops(const char *kind)
return res;
}
+static const struct tcf_proto_ops *
+tcf_proto_lookup_ops(const char *kind, struct netlink_ext_ack *extack)
+{
+ const struct tcf_proto_ops *ops;
+
+ ops = __tcf_proto_lookup_ops(kind);
+ if (ops)
+ return ops;
+#ifdef CONFIG_MODULES
+ rtnl_unlock();
+ request_module("cls_%s", kind);
+ rtnl_lock();
+ ops = __tcf_proto_lookup_ops(kind);
+ /* We dropped the RTNL semaphore in order to perform
+ * the module load. So, even if we succeeded in loading
+ * the module we have to replay the request. We indicate
+ * this using -EAGAIN.
+ */
+ if (ops) {
+ module_put(ops->owner);
+ return ERR_PTR(-EAGAIN);
+ }
+#endif
+ NL_SET_ERR_MSG(extack, "TC classifier not found");
+ return ERR_PTR(-ENOENT);
+}
+
/* Register(unregister) new classifier type */
int register_tcf_proto_ops(struct tcf_proto_ops *ops)
@@ -133,27 +160,9 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol,
if (!tp)
return ERR_PTR(-ENOBUFS);
- err = -ENOENT;
- tp->ops = tcf_proto_lookup_ops(kind);
- if (!tp->ops) {
-#ifdef CONFIG_MODULES
- rtnl_unlock();
- request_module("cls_%s", kind);
- rtnl_lock();
- tp->ops = tcf_proto_lookup_ops(kind);
- /* We dropped the RTNL semaphore in order to perform
- * the module load. So, even if we succeeded in loading
- * the module we have to replay the request. We indicate
- * this using -EAGAIN.
- */
- if (tp->ops) {
- module_put(tp->ops->owner);
- err = -EAGAIN;
- } else {
- NL_SET_ERR_MSG(extack, "TC classifier not found");
- err = -ENOENT;
- }
-#endif
+ tp->ops = tcf_proto_lookup_ops(kind, extack);
+ if (IS_ERR(tp->ops)) {
+ err = PTR_ERR(tp->ops);
goto errout;
}
tp->classify = tp->ops->classify;
--
2.14.4
^ permalink raw reply related
* [patch net-next v2 2/9] net: sched: introduce chain templates
From: Jiri Pirko @ 2018-06-28 13:09 UTC (permalink / raw)
To: netdev
Cc: davem, jhs, xiyou.wangcong, jakub.kicinski, simon.horman,
john.hurley, dsahern, mlxsw, sridhar.samudrala
In-Reply-To: <20180628130907.951-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@mellanox.com>
Introduce a group of new tc-rtnl commands to allow user to set per-chain
template. Templates lock down individual chains for particular
classifier type/options combinations. The classifier needs to support
templates, otherwise kernel would reply with error.
For example, to lock chain 22 to allow only filters of type
flower with destination mac address, user needs to do:
chain 22 flower dst_mac 00:00:00:00:00:00/FF:FF:FF:FF:FF:FF
In case the chain already contains some filters it is not possible to
add or remove template. That is permitted only for empty chains.
Alongside with add/del commands, introduce also get/dump and
notifications.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
include/net/sch_generic.h | 14 +-
include/uapi/linux/rtnetlink.h | 7 +
net/sched/cls_api.c | 371 ++++++++++++++++++++++++++++++++++++++++-
net/sched/cls_basic.c | 2 +-
net/sched/cls_bpf.c | 3 +-
net/sched/cls_cgroup.c | 2 +-
net/sched/cls_flow.c | 3 +-
net/sched/cls_flower.c | 3 +-
net/sched/cls_fw.c | 3 +-
net/sched/cls_matchall.c | 3 +-
net/sched/cls_route.c | 2 +-
net/sched/cls_rsvp.h | 3 +-
net/sched/cls_tcindex.c | 2 +-
net/sched/cls_u32.c | 2 +-
security/selinux/nlmsgtab.c | 2 +-
15 files changed, 405 insertions(+), 17 deletions(-)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 7432100027b7..e826ffa166aa 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -238,6 +238,8 @@ struct tcf_result {
};
};
+struct tcf_chain;
+
struct tcf_proto_ops {
struct list_head head;
char kind[IFNAMSIZ];
@@ -253,7 +255,7 @@ struct tcf_proto_ops {
int (*change)(struct net *net, struct sk_buff *,
struct tcf_proto*, unsigned long,
u32 handle, struct nlattr **,
- void **, bool,
+ void **, bool, void *tmplt_priv,
struct netlink_ext_ack *);
int (*delete)(struct tcf_proto *tp, void *arg,
bool *last,
@@ -263,10 +265,18 @@ struct tcf_proto_ops {
tc_setup_cb_t *cb, void *cb_priv,
struct netlink_ext_ack *extack);
void (*bind_class)(void *, u32, unsigned long);
+ void * (*tmplt_create)(struct net *net,
+ struct tcf_chain *chain,
+ struct nlattr **tca,
+ struct netlink_ext_ack *extack);
+ void (*tmplt_destroy)(void *tmplt_priv);
/* rtnetlink specific */
int (*dump)(struct net*, struct tcf_proto*, void *,
struct sk_buff *skb, struct tcmsg*);
+ int (*tmplt_dump)(struct sk_buff *skb,
+ struct net *net,
+ void *tmplt_priv);
struct module *owner;
};
@@ -305,6 +315,8 @@ struct tcf_chain {
struct tcf_block *block;
u32 index; /* chain index */
unsigned int refcnt;
+ const struct tcf_proto_ops *tmplt_ops;
+ void *tmplt_priv;
};
struct tcf_block {
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 7d8502313c99..45fd8cc1fdb2 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -150,6 +150,13 @@ enum {
RTM_NEWCACHEREPORT = 96,
#define RTM_NEWCACHEREPORT RTM_NEWCACHEREPORT
+ RTM_NEWCHAINTMPLT = 100,
+#define RTM_NEWCHAINTMPLT RTM_NEWCHAINTMPLT
+ RTM_DELCHAINTMPLT,
+#define RTM_DELCHAINTMPLT RTM_DELCHAINTMPLT
+ RTM_GETCHAINTMPLT,
+#define RTM_GETCHAINTMPLT RTM_GETCHAINTMPLT
+
__RTM_MAX,
#define RTM_MAX (((__RTM_MAX + 3) & ~3) - 1)
};
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index b74909fa68a3..e8a0fd5a41a7 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -227,7 +227,7 @@ static void tcf_chain_head_change(struct tcf_chain *chain,
tcf_chain_head_change_item(item, tp_head);
}
-static void tcf_chain_flush(struct tcf_chain *chain)
+static void tcf_chain_flush(struct tcf_chain *chain, bool destroy_template)
{
struct tcf_proto *tp = rtnl_dereference(chain->filter_chain);
@@ -238,6 +238,11 @@ static void tcf_chain_flush(struct tcf_chain *chain)
tp = rtnl_dereference(chain->filter_chain);
tcf_chain_put(chain);
}
+ if (destroy_template && chain->tmplt_ops) {
+ chain->tmplt_ops->tmplt_destroy(chain->tmplt_priv);
+ module_put(chain->tmplt_ops->owner);
+ tcf_chain_put(chain);
+ }
}
static void tcf_chain_destroy(struct tcf_chain *chain)
@@ -696,7 +701,7 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
tcf_chain_hold(chain);
list_for_each_entry(chain, &block->chain_list, list)
- tcf_chain_flush(chain);
+ tcf_chain_flush(chain, true);
}
tcf_block_offload_unbind(block, q, ei);
@@ -1236,9 +1241,15 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
goto errout;
}
+ if (chain->tmplt_ops && chain->tmplt_ops != tp->ops) {
+ NL_SET_ERR_MSG(extack, "Chain template is set to a different filter kind");
+ err = -EINVAL;
+ goto errout;
+ }
+
err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh,
n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE,
- extack);
+ chain->tmplt_priv, extack);
if (err == 0) {
if (tp_created)
tcf_chain_tp_insert(chain, &chain_info, tp);
@@ -1319,7 +1330,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
if (prio == 0) {
tfilter_notify_chain(net, skb, block, q, parent, n,
chain, RTM_DELTFILTER);
- tcf_chain_flush(chain);
+ tcf_chain_flush(chain, false);
err = 0;
goto errout;
}
@@ -1615,6 +1626,354 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
return skb->len;
}
+static int tc_tmplt_fill_node(struct tcf_chain *chain, struct net *net,
+ struct sk_buff *skb, struct tcf_block *block,
+ struct Qdisc *q, u32 parent,
+ u32 portid, u32 seq, u16 flags, int event)
+{
+ unsigned char *b = skb_tail_pointer(skb);
+ const struct tcf_proto_ops *ops;
+ struct nlmsghdr *nlh;
+ struct tcmsg *tcm;
+ void *priv;
+
+ ops = chain->tmplt_ops;
+ priv = chain->tmplt_priv;
+
+ nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
+ if (!nlh)
+ goto out_nlmsg_trim;
+ tcm = nlmsg_data(nlh);
+ tcm->tcm_family = AF_UNSPEC;
+ tcm->tcm__pad1 = 0;
+ tcm->tcm__pad2 = 0;
+ tcm->tcm_handle = 0;
+ if (q) {
+ tcm->tcm_ifindex = qdisc_dev(q)->ifindex;
+ tcm->tcm_parent = parent;
+ } else {
+ tcm->tcm_ifindex = TCM_IFINDEX_MAGIC_BLOCK;
+ tcm->tcm_block_index = block->index;
+ }
+
+ if (nla_put_string(skb, TCA_KIND, ops->kind))
+ goto nla_put_failure;
+ if (nla_put_u32(skb, TCA_CHAIN, chain->index))
+ goto nla_put_failure;
+ if (ops->tmplt_dump(skb, net, priv) < 0)
+ goto nla_put_failure;
+
+ nlh->nlmsg_len = skb_tail_pointer(skb) - b;
+ return skb->len;
+
+out_nlmsg_trim:
+nla_put_failure:
+ nlmsg_trim(skb, b);
+ return -EMSGSIZE;
+}
+
+static int tc_tmplt_notify(struct tcf_chain *chain, struct net *net,
+ struct sk_buff *oskb, struct nlmsghdr *n,
+ struct tcf_block *block, struct Qdisc *q,
+ u32 parent, int event, bool unicast)
+{
+ u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
+ struct sk_buff *skb;
+
+ skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+ if (!skb)
+ return -ENOBUFS;
+
+ if (tc_tmplt_fill_node(chain, net, skb, block, q, parent, portid,
+ n->nlmsg_seq, n->nlmsg_flags, event) <= 0) {
+ kfree_skb(skb);
+ return -EINVAL;
+ }
+
+ if (unicast)
+ return netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT);
+
+ return rtnetlink_send(skb, net, portid, RTNLGRP_TC,
+ n->nlmsg_flags & NLM_F_ECHO);
+}
+
+static int tc_ctl_tmplt_add(struct tcf_chain *chain, struct net *net,
+ struct sk_buff *skb, struct nlmsghdr *n,
+ struct tcf_block *block, struct Qdisc *q,
+ u32 parent, struct nlattr **tca,
+ struct netlink_ext_ack *extack)
+{
+ const struct tcf_proto_ops *ops;
+ void *tmplt_priv;
+
+ if (chain->tmplt_ops) {
+ NL_SET_ERR_MSG(extack, "A template is already set for the chain");
+ return -EBUSY;
+ }
+ if (chain->filter_chain) {
+ NL_SET_ERR_MSG(extack, "The chain is not empty, unable to add template");
+ return -EBUSY;
+ }
+ if (!(n->nlmsg_flags & NLM_F_CREATE)) {
+ NL_SET_ERR_MSG(extack, "Need NLM_F_CREATE to create a new chain template");
+ return -ENOENT;
+ }
+ ops = tcf_proto_lookup_ops(nla_data(tca[TCA_KIND]), extack);
+ if (IS_ERR(ops))
+ return PTR_ERR(ops);
+ if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) {
+ NL_SET_ERR_MSG(extack, "Chain templates are not supported with this classifier");
+ return -EOPNOTSUPP;
+ }
+
+ tmplt_priv = ops->tmplt_create(net, chain, tca, extack);
+ if (IS_ERR(tmplt_priv)) {
+ module_put(ops->owner);
+ return PTR_ERR(tmplt_priv);
+ }
+ chain->tmplt_ops = ops;
+ chain->tmplt_priv = tmplt_priv;
+ tc_tmplt_notify(chain, net, skb, n, block, q, parent,
+ RTM_NEWCHAINTMPLT, false);
+ return 0;
+}
+
+static int tc_ctl_tmplt_del(struct tcf_chain *chain, struct net *net,
+ struct sk_buff *skb, struct nlmsghdr *n,
+ struct tcf_block *block, struct Qdisc *q,
+ u32 parent, struct netlink_ext_ack *extack)
+{
+ const struct tcf_proto_ops *ops = chain->tmplt_ops;
+
+ if (!ops) {
+ NL_SET_ERR_MSG(extack, "Unable to delete template as this chain does not have template");
+ return -ENOENT;
+ }
+ if (chain->filter_chain) {
+ NL_SET_ERR_MSG(extack, "The chain is not empty, unable to delete template");
+ return -EBUSY;
+ }
+ if (!ops->tmplt_create) {
+ NL_SET_ERR_MSG(extack, "Chain templates are not supported with this classifier");
+ return -EOPNOTSUPP;
+ }
+ tc_tmplt_notify(chain, net, skb, n, block, q, parent,
+ RTM_DELCHAINTMPLT, false);
+ ops->tmplt_destroy(chain->tmplt_priv);
+ module_put(ops->owner);
+ chain->tmplt_ops = NULL;
+ chain->tmplt_priv = NULL;
+ return 0;
+}
+
+static int tc_ctl_tmplt_get(struct tcf_chain *chain, struct net *net,
+ struct sk_buff *skb, struct nlmsghdr *n,
+ struct tcf_block *block, struct Qdisc *q,
+ u32 parent, struct netlink_ext_ack *extack)
+{
+ const struct tcf_proto_ops *ops = chain->tmplt_ops;
+ int err;
+
+ if (!ops) {
+ NL_SET_ERR_MSG(extack, "Unable to get template as this chain does not have template");
+ return -ENOENT;
+ }
+ err = tc_tmplt_notify(chain, net, skb, n, block, q, parent,
+ RTM_NEWCHAINTMPLT, true);
+ if (err < 0)
+ NL_SET_ERR_MSG(extack, "Failed to send chain template notify message");
+ return err;
+}
+
+/* Add/delete/get a chain template */
+
+static int tc_ctl_tmplt(struct sk_buff *skb, struct nlmsghdr *n,
+ struct netlink_ext_ack *extack)
+{
+ struct net *net = sock_net(skb->sk);
+ struct nlattr *tca[TCA_MAX + 1];
+ struct tcmsg *t;
+ u32 parent;
+ u32 chain_index;
+ struct Qdisc *q = NULL;
+ struct tcf_chain *chain = NULL;
+ struct tcf_block *block;
+ unsigned long cl;
+ int err;
+
+ if (n->nlmsg_type != RTM_GETCHAINTMPLT &&
+ !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
+ return -EPERM;
+
+replay:
+ err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack);
+ if (err < 0)
+ return err;
+
+ t = nlmsg_data(n);
+ parent = t->tcm_parent;
+ cl = 0;
+
+ /* Find filter chain. */
+
+ block = tcf_block_find(net, &q, &parent, &cl,
+ t->tcm_ifindex, t->tcm_block_index, extack);
+ if (IS_ERR(block)) {
+ err = PTR_ERR(block);
+ goto errout;
+ }
+
+ chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
+ if (chain_index > TC_ACT_EXT_VAL_MASK) {
+ NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
+ err = -EINVAL;
+ goto errout;
+ }
+ chain = tcf_chain_get(block, chain_index,
+ n->nlmsg_type == RTM_NEWCHAINTMPLT);
+ if (!chain) {
+ NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
+ err = n->nlmsg_type == RTM_NEWTFILTER ? -ENOMEM : -EINVAL;
+ goto errout;
+ }
+
+ switch (n->nlmsg_type) {
+ case RTM_NEWCHAINTMPLT:
+ err = tc_ctl_tmplt_add(chain, net, skb, n, block,
+ q, parent, tca, extack);
+ /* In case the chain template was successfully added,
+ * take a reference to the chain. This ensures that
+ * an empty chain with template does not disappear
+ * at the end of this function.
+ */
+ if (!err)
+ tcf_chain_hold(chain);
+ break;
+ case RTM_DELCHAINTMPLT:
+ err = tc_ctl_tmplt_del(chain, net, skb, n, block,
+ q, parent, extack);
+ /* In case the chain template was successfully deleted,
+ * put a reference to the chain previously taken
+ * during template addition.
+ */
+ if (!err)
+ tcf_chain_put(chain);
+ break;
+ case RTM_GETCHAINTMPLT:
+ err = tc_ctl_tmplt_get(chain, net, skb, n, block,
+ q, parent, extack);
+ break;
+ default:
+ err = -EOPNOTSUPP;
+ NL_SET_ERR_MSG(extack, "Unsupported message type");
+ break;
+ }
+errout:
+ if (chain)
+ tcf_chain_put(chain);
+ if (err == -EAGAIN)
+ /* Replay the request. */
+ goto replay;
+ return err;
+}
+
+/* called with RTNL */
+static int tc_dump_tmplt(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct net *net = sock_net(skb->sk);
+ struct nlattr *tca[TCA_MAX + 1];
+ struct Qdisc *q = NULL;
+ struct tcf_block *block;
+ struct tcf_chain *chain;
+ struct tcmsg *tcm = nlmsg_data(cb->nlh);
+ long index_start;
+ long index;
+ u32 parent;
+ int err;
+
+ if (nlmsg_len(cb->nlh) < sizeof(*tcm))
+ return skb->len;
+
+ err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, NULL, NULL);
+ if (err)
+ return err;
+
+ if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
+ block = tcf_block_lookup(net, tcm->tcm_block_index);
+ if (!block)
+ goto out;
+ /* If we work with block index, q is NULL and parent value
+ * will never be used in the following code. The check
+ * in tcf_fill_node prevents it. However, compiler does not
+ * see that far, so set parent to zero to silence the warning
+ * about parent being uninitialized.
+ */
+ parent = 0;
+ } else {
+ const struct Qdisc_class_ops *cops;
+ struct net_device *dev;
+ unsigned long cl = 0;
+
+ dev = __dev_get_by_index(net, tcm->tcm_ifindex);
+ if (!dev)
+ return skb->len;
+
+ parent = tcm->tcm_parent;
+ if (!parent) {
+ q = dev->qdisc;
+ parent = q->handle;
+ } else {
+ q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
+ }
+ if (!q)
+ goto out;
+ cops = q->ops->cl_ops;
+ if (!cops)
+ goto out;
+ if (!cops->tcf_block)
+ goto out;
+ if (TC_H_MIN(tcm->tcm_parent)) {
+ cl = cops->find(q, tcm->tcm_parent);
+ if (cl == 0)
+ goto out;
+ }
+ block = cops->tcf_block(q, cl, NULL);
+ if (!block)
+ goto out;
+ if (tcf_block_shared(block))
+ q = NULL;
+ }
+
+ index_start = cb->args[0];
+ index = 0;
+
+ list_for_each_entry(chain, &block->chain_list, list) {
+ if ((tca[TCA_CHAIN] &&
+ nla_get_u32(tca[TCA_CHAIN]) != chain->index) ||
+ !chain->tmplt_ops)
+ continue;
+ if (index < index_start) {
+ index++;
+ continue;
+ }
+ err = tc_tmplt_fill_node(chain, net, skb, block, q, parent,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, NLM_F_MULTI,
+ RTM_NEWCHAINTMPLT);
+ if (err <= 0)
+ break;
+ index++;
+ }
+
+ cb->args[0] = index;
+
+out:
+ /* If we did no progress, the error (EMSGSIZE) is real */
+ if (skb->len == 0 && err)
+ return err;
+ return skb->len;
+}
+
void tcf_exts_destroy(struct tcf_exts *exts)
{
#ifdef CONFIG_NET_CLS_ACT
@@ -1840,6 +2199,10 @@ static int __init tc_filter_init(void)
rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL, 0);
rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_get_tfilter,
tc_dump_tfilter, 0);
+ rtnl_register(PF_UNSPEC, RTM_NEWCHAINTMPLT, tc_ctl_tmplt, NULL, 0);
+ rtnl_register(PF_UNSPEC, RTM_DELCHAINTMPLT, tc_ctl_tmplt, NULL, 0);
+ rtnl_register(PF_UNSPEC, RTM_GETCHAINTMPLT, tc_ctl_tmplt,
+ tc_dump_tmplt, 0);
return 0;
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index 95367f37098d..a690acac7e6e 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -168,7 +168,7 @@ static int basic_set_parms(struct net *net, struct tcf_proto *tp,
static int basic_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base, u32 handle,
struct nlattr **tca, void **arg, bool ovr,
- struct netlink_ext_ack *extack)
+ void *tmplt_priv, struct netlink_ext_ack *extack)
{
int err;
struct basic_head *head = rtnl_dereference(tp->root);
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 66e0ac9811f9..d46af854f0c8 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -457,7 +457,8 @@ static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp,
static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca,
- void **arg, bool ovr, struct netlink_ext_ack *extack)
+ void **arg, bool ovr, void *tmplt_priv,
+ struct netlink_ext_ack *extack)
{
struct cls_bpf_head *head = rtnl_dereference(tp->root);
struct cls_bpf_prog *oldprog = *arg;
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 3bc01bdde165..ca5d0315432c 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -78,7 +78,7 @@ static void cls_cgroup_destroy_work(struct work_struct *work)
static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca,
- void **arg, bool ovr,
+ void **arg, bool ovr, void *tmplt_priv,
struct netlink_ext_ack *extack)
{
struct nlattr *tb[TCA_CGROUP_MAX + 1];
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 2bb043cd436b..2a21e26fcee0 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -391,7 +391,8 @@ static void flow_destroy_filter_work(struct work_struct *work)
static int flow_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca,
- void **arg, bool ovr, struct netlink_ext_ack *extack)
+ void **arg, bool ovr, void *tmplt_priv,
+ struct netlink_ext_ack *extack)
{
struct flow_head *head = rtnl_dereference(tp->root);
struct flow_filter *fold, *fnew;
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 352876bb901b..62efa7289ac4 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -929,7 +929,8 @@ static int fl_set_parms(struct net *net, struct tcf_proto *tp,
static int fl_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca,
- void **arg, bool ovr, struct netlink_ext_ack *extack)
+ void **arg, bool ovr, void *tmplt_priv,
+ struct netlink_ext_ack *extack)
{
struct cls_fl_head *head = rtnl_dereference(tp->root);
struct cls_fl_filter *fold = *arg;
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index 29eeeaf3ea44..a1d40d48aa24 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -250,7 +250,8 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp,
static int fw_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca, void **arg,
- bool ovr, struct netlink_ext_ack *extack)
+ bool ovr, void *tmplt_priv,
+ struct netlink_ext_ack *extack)
{
struct fw_head *head = rtnl_dereference(tp->root);
struct fw_filter *f = *arg;
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index af16f36ed578..013cf0db5b22 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -154,7 +154,8 @@ static int mall_set_parms(struct net *net, struct tcf_proto *tp,
static int mall_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle, struct nlattr **tca,
- void **arg, bool ovr, struct netlink_ext_ack *extack)
+ void **arg, bool ovr, void *tmplt_priv,
+ struct netlink_ext_ack *extack)
{
struct cls_mall_head *head = rtnl_dereference(tp->root);
struct nlattr *tb[TCA_MATCHALL_MAX + 1];
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 0404aa5fa7cb..321eb746fe01 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -468,7 +468,7 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp,
static int route4_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base, u32 handle,
struct nlattr **tca, void **arg, bool ovr,
- struct netlink_ext_ack *extack)
+ void *tmplt_priv, struct netlink_ext_ack *extack)
{
struct route4_head *head = rtnl_dereference(tp->root);
struct route4_filter __rcu **fp;
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index e9ccf7daea7d..371618720ef2 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -477,7 +477,8 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base,
u32 handle,
struct nlattr **tca,
- void **arg, bool ovr, struct netlink_ext_ack *extack)
+ void **arg, bool ovr, void *tmplt_priv,
+ struct netlink_ext_ack *extack)
{
struct rsvp_head *data = rtnl_dereference(tp->root);
struct rsvp_filter *f, *nfp;
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 32f4bbd82f35..d9fb5d56c60d 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -500,7 +500,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
static int
tcindex_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base, u32 handle,
- struct nlattr **tca, void **arg, bool ovr,
+ struct nlattr **tca, void **arg, bool ovr, void *tmplt_priv,
struct netlink_ext_ack *extack)
{
struct nlattr *opt = tca[TCA_OPTIONS];
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index d5d2a6dc3921..6300514a5a7c 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -905,7 +905,7 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp,
static int u32_change(struct net *net, struct sk_buff *in_skb,
struct tcf_proto *tp, unsigned long base, u32 handle,
struct nlattr **tca, void **arg, bool ovr,
- struct netlink_ext_ack *extack)
+ void *tmplt_priv, struct netlink_ext_ack *extack)
{
struct tc_u_common *tp_c = tp->data;
struct tc_u_hnode *ht;
diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c
index 7b7433a1a34c..825777efc83e 100644
--- a/security/selinux/nlmsgtab.c
+++ b/security/selinux/nlmsgtab.c
@@ -159,7 +159,7 @@ int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm)
switch (sclass) {
case SECCLASS_NETLINK_ROUTE_SOCKET:
/* RTM_MAX always point to RTM_SETxxxx, ie RTM_NEWxxx + 3 */
- BUILD_BUG_ON(RTM_MAX != (RTM_NEWCACHEREPORT + 3));
+ BUILD_BUG_ON(RTM_MAX != (RTM_NEWCHAINTMPLT + 3));
err = nlmsg_perm(nlmsg_type, perm, nlmsg_route_perms,
sizeof(nlmsg_route_perms));
break;
--
2.14.4
^ permalink raw reply related
* [patch net-next v2 3/9] net: sched: cls_flower: move key/mask dumping into a separate function
From: Jiri Pirko @ 2018-06-28 13:09 UTC (permalink / raw)
To: netdev
Cc: davem, jhs, xiyou.wangcong, jakub.kicinski, simon.horman,
john.hurley, dsahern, mlxsw, sridhar.samudrala
In-Reply-To: <20180628130907.951-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@mellanox.com>
Push key/mask dumping from fl_dump() into a separate function
fl_dump_key(), that will be reused for template dumping.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
net/sched/cls_flower.c | 62 ++++++++++++++++++++++++++++++--------------------
1 file changed, 37 insertions(+), 25 deletions(-)
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 62efa7289ac4..0e8991e49860 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1260,29 +1260,9 @@ static int fl_dump_key_flags(struct sk_buff *skb, u32 flags_key, u32 flags_mask)
return nla_put(skb, TCA_FLOWER_KEY_FLAGS_MASK, 4, &_mask);
}
-static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
- struct sk_buff *skb, struct tcmsg *t)
+static int fl_dump_key(struct sk_buff *skb, struct net *net,
+ struct fl_flow_key *key, struct fl_flow_key *mask)
{
- struct cls_fl_filter *f = fh;
- struct nlattr *nest;
- struct fl_flow_key *key, *mask;
-
- if (!f)
- return skb->len;
-
- t->tcm_handle = f->handle;
-
- nest = nla_nest_start(skb, TCA_OPTIONS);
- if (!nest)
- goto nla_put_failure;
-
- if (f->res.classid &&
- nla_put_u32(skb, TCA_FLOWER_CLASSID, f->res.classid))
- goto nla_put_failure;
-
- key = &f->key;
- mask = &f->mask->key;
-
if (mask->indev_ifindex) {
struct net_device *dev;
@@ -1291,9 +1271,6 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
goto nla_put_failure;
}
- if (!tc_skip_hw(f->flags))
- fl_hw_update_stats(tp, f);
-
if (fl_dump_key_val(skb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST,
mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK,
sizeof(key->eth.dst)) ||
@@ -1447,6 +1424,41 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
if (fl_dump_key_flags(skb, key->control.flags, mask->control.flags))
goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
+}
+
+static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
+ struct sk_buff *skb, struct tcmsg *t)
+{
+ struct cls_fl_filter *f = fh;
+ struct nlattr *nest;
+ struct fl_flow_key *key, *mask;
+
+ if (!f)
+ return skb->len;
+
+ t->tcm_handle = f->handle;
+
+ nest = nla_nest_start(skb, TCA_OPTIONS);
+ if (!nest)
+ goto nla_put_failure;
+
+ if (f->res.classid &&
+ nla_put_u32(skb, TCA_FLOWER_CLASSID, f->res.classid))
+ goto nla_put_failure;
+
+ key = &f->key;
+ mask = &f->mask->key;
+
+ if (fl_dump_key(skb, net, key, mask))
+ goto nla_put_failure;
+
+ if (!tc_skip_hw(f->flags))
+ fl_hw_update_stats(tp, f);
+
if (f->flags && nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags))
goto nla_put_failure;
--
2.14.4
^ permalink raw reply related
* [patch net-next v2 4/9] net: sched: cls_flower: change fl_init_dissector to accept mask and dissector
From: Jiri Pirko @ 2018-06-28 13:09 UTC (permalink / raw)
To: netdev
Cc: davem, jhs, xiyou.wangcong, jakub.kicinski, simon.horman,
john.hurley, dsahern, mlxsw, sridhar.samudrala
In-Reply-To: <20180628130907.951-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@mellanox.com>
This function is going to be used for templates as well, so we need to
pass the pointer separately.
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
net/sched/cls_flower.c | 39 ++++++++++++++++++++-------------------
1 file changed, 20 insertions(+), 19 deletions(-)
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 0e8991e49860..0f753260594d 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -795,47 +795,48 @@ static int fl_init_mask_hashtable(struct fl_flow_mask *mask)
FL_KEY_SET(keys, cnt, id, member); \
} while(0);
-static void fl_init_dissector(struct fl_flow_mask *mask)
+static void fl_init_dissector(struct flow_dissector *dissector,
+ struct fl_flow_key *mask)
{
struct flow_dissector_key keys[FLOW_DISSECTOR_KEY_MAX];
size_t cnt = 0;
FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_CONTROL, control);
FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_BASIC, basic);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_ETH_ADDRS, eth);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_PORTS, tp);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_IP, ip);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_TCP, tcp);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_ICMP, icmp);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_ARP, arp);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_MPLS, mpls);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_VLAN, vlan);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_ENC_KEYID, enc_key_id);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, enc_ipv4);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, enc_ipv6);
- if (FL_KEY_IS_MASKED(&mask->key, enc_ipv4) ||
- FL_KEY_IS_MASKED(&mask->key, enc_ipv6))
+ if (FL_KEY_IS_MASKED(mask, enc_ipv4) ||
+ FL_KEY_IS_MASKED(mask, enc_ipv6))
FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_ENC_CONTROL,
enc_control);
- FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_ENC_PORTS, enc_tp);
- skb_flow_dissector_init(&mask->dissector, keys, cnt);
+ skb_flow_dissector_init(dissector, keys, cnt);
}
static struct fl_flow_mask *fl_create_new_mask(struct cls_fl_head *head,
@@ -854,7 +855,7 @@ static struct fl_flow_mask *fl_create_new_mask(struct cls_fl_head *head,
if (err)
goto errout_free;
- fl_init_dissector(newmask);
+ fl_init_dissector(&newmask->dissector, &newmask->key);
INIT_LIST_HEAD_RCU(&newmask->filters);
--
2.14.4
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox