* [PATCH 07/37] atl1c: remove code related to rxq 1/2/3
From: xiong @ 2012-04-13 0:14 UTC (permalink / raw)
To: davem, netdev, linux-kernel; +Cc: qca-linux-team, nic-devel, xiong
In-Reply-To: <1334276102-15866-1-git-send-email-xiong@qca.qualcomm.com>
remove code related to rxq 1/2/3 since multi-q not support.
refine REG_RXQ_CTRL definition as well.
Signed-off-by: xiong <xiong@qca.qualcomm.com>
Tested-by: Liu David <dwliu@qca.qualcomm.com>
---
drivers/net/ethernet/atheros/atl1c/atl1c_hw.h | 29 +++++++++-------------
drivers/net/ethernet/atheros/atl1c/atl1c_main.c | 3 +-
2 files changed, 13 insertions(+), 19 deletions(-)
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
index ca45fad..18c1f18 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
@@ -493,26 +493,21 @@ int atl1c_phy_power_saving(struct atl1c_hw *hw);
#define ASPM_THRUPUT_LIMIT_NO 0x00
#define ASPM_THRUPUT_LIMIT_1M 0x01
#define ASPM_THRUPUT_LIMIT_10M 0x02
-#define ASPM_THRUPUT_LIMIT_100M 0x04
-#define RXQ1_CTRL_EN 0x10
-#define RXQ2_CTRL_EN 0x20
-#define RXQ3_CTRL_EN 0x40
-#define IPV6_CHKSUM_CTRL_EN 0x80
-#define RSS_HASH_BITS_MASK 0x00FF
-#define RSS_HASH_BITS_SHIFT 8
-#define RSS_HASH_IPV4 0x10000
-#define RSS_HASH_IPV4_TCP 0x20000
-#define RSS_HASH_IPV6 0x40000
-#define RSS_HASH_IPV6_TCP 0x80000
+#define ASPM_THRUPUT_LIMIT_100M 0x03
+#define IPV6_CHKSUM_CTRL_EN BIT(7)
#define RXQ_RFD_BURST_NUM_MASK 0x003F
#define RXQ_RFD_BURST_NUM_SHIFT 20
-#define RSS_MODE_MASK 0x0003
+#define RXQ_NUM_RFD_PREF_DEF 8
+#define RSS_MODE_MASK 3UL
#define RSS_MODE_SHIFT 26
-#define RSS_NIP_QUEUE_SEL_MASK 0x1
-#define RSS_NIP_QUEUE_SEL_SHIFT 28
-#define RRS_HASH_CTRL_EN 0x20000000
-#define RX_CUT_THRU_EN 0x40000000
-#define RXQ_CTRL_EN 0x80000000
+#define RSS_MODE_DIS 0
+#define RSS_MODE_SQSI 1
+#define RSS_MODE_MQSI 2
+#define RSS_MODE_MQMI 3
+#define RSS_NIP_QUEUE_SEL BIT(28) /* 0:q0, 1:table */
+#define RRS_HASH_CTRL_EN BIT(29)
+#define RX_CUT_THRU_EN BIT(30)
+#define RXQ_CTRL_EN BIT(31)
#define REG_RFD_FREE_THRESH 0x15A4
#define RFD_FREE_THRESH_MASK 0x003F
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index c7d7640..ca1259d 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -1137,8 +1137,7 @@ static int atl1c_stop_mac(struct atl1c_hw *hw)
u32 data;
AT_READ_REG(hw, REG_RXQ_CTRL, &data);
- data &= ~(RXQ1_CTRL_EN | RXQ2_CTRL_EN |
- RXQ3_CTRL_EN | RXQ_CTRL_EN);
+ data &= ~RXQ_CTRL_EN;
AT_WRITE_REG(hw, REG_RXQ_CTRL, data);
AT_READ_REG(hw, REG_TXQ_CTRL, &data);
--
1.7.7
^ permalink raw reply related
* [PATCH 06/37] atl1c: split 2 32bit registers of TPD to 4 16bit registers
From: xiong @ 2012-04-13 0:14 UTC (permalink / raw)
To: davem, netdev, linux-kernel; +Cc: qca-linux-team, nic-devel, xiong
In-Reply-To: <1334276102-15866-1-git-send-email-xiong@qca.qualcomm.com>
TPD producer/consumer index is 16bit wide.
16bit read/write reduce the dependency of the 2 tpd rings (hi and lo)
rename reg(157C/1580) to keep name coninsistency.
Signed-off-by: xiong <xiong@qca.qualcomm.com>
Tested-by: Liu David <dwliu@qca.qualcomm.com>
---
drivers/net/ethernet/atheros/atl1c/atl1c.h | 10 +++++-
drivers/net/ethernet/atheros/atl1c/atl1c_hw.h | 17 ++++-------
drivers/net/ethernet/atheros/atl1c/atl1c_main.c | 34 +++++-----------------
3 files changed, 22 insertions(+), 39 deletions(-)
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c.h b/drivers/net/ethernet/atheros/atl1c/atl1c.h
index f8628bc..16a5c7a 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c.h
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c.h
@@ -583,8 +583,14 @@ struct atl1c_adapter {
#define AT_WRITE_REGW(a, reg, value) (\
writew((value), ((a)->hw_addr + reg)))
-#define AT_READ_REGW(a, reg) (\
- readw((a)->hw_addr + reg))
+#define AT_READ_REGW(a, reg, pdata) do { \
+ if (unlikely((a)->hibernate)) { \
+ readw((a)->hw_addr + reg); \
+ *(u16 *)pdata = readw((a)->hw_addr + reg); \
+ } else { \
+ *(u16 *)pdata = readw((a)->hw_addr + reg); \
+ } \
+ } while (0)
#define AT_WRITE_REG_ARRAY(a, reg, offset, value) ( \
writel((value), (((a)->hw_addr + reg) + ((offset) << 2))))
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
index caff2ae..ca45fad 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
@@ -455,8 +455,8 @@ int atl1c_phy_power_saving(struct atl1c_hw *hw);
#define REG_RRD0_HEAD_ADDR_LO 0x1568
#define REG_RRD_RING_SIZE 0x1578
#define RRD_RING_SIZE_MASK 0x0FFF
-#define REG_HTPD_HEAD_ADDR_LO 0x157C
-#define REG_NTPD_HEAD_ADDR_LO 0x1580
+#define REG_TPD_PRI1_ADDR_LO 0x157C
+#define REG_TPD_PRI0_ADDR_LO 0x1580
#define REG_TPD_RING_SIZE 0x1584
#define TPD_RING_SIZE_MASK 0xFFFF
@@ -562,15 +562,10 @@ int atl1c_phy_power_saving(struct atl1c_hw *hw);
#define MB_RFDX_PROD_IDX_MASK 0xFFFF
#define REG_MB_RFD0_PROD_IDX 0x15E0
-#define MB_PRIO_PROD_IDX_MASK 0xFFFF
-#define REG_MB_PRIO_PROD_IDX 0x15F0
-#define MB_HTPD_PROD_IDX_SHIFT 0
-#define MB_NTPD_PROD_IDX_SHIFT 16
-
-#define MB_PRIO_CONS_IDX_MASK 0xFFFF
-#define REG_MB_PRIO_CONS_IDX 0x15F4
-#define MB_HTPD_CONS_IDX_SHIFT 0
-#define MB_NTPD_CONS_IDX_SHIFT 16
+#define REG_TPD_PRI1_PIDX 0x15F0 /* 16bit,hi-tpd producer idx */
+#define REG_TPD_PRI0_PIDX 0x15F2 /* 16bit,lo-tpd producer idx */
+#define REG_TPD_PRI1_CIDX 0x15F4 /* 16bit,hi-tpd consumer idx */
+#define REG_TPD_PRI0_CIDX 0x15F6 /* 16bit,lo-tpd consumer idx */
#define REG_MB_RFD01_CONS_IDX 0x15F8
#define MB_RFD0_CONS_IDX_MASK 0x0000FFFF
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index ceb9df5..c7d7640 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -995,10 +995,10 @@ static void atl1c_configure_des_ring(struct atl1c_adapter *adapter)
(u32)((tpd_ring[atl1c_trans_normal].dma &
AT_DMA_HI_ADDR_MASK) >> 32));
/* just enable normal priority TX queue */
- AT_WRITE_REG(hw, REG_NTPD_HEAD_ADDR_LO,
+ AT_WRITE_REG(hw, REG_TPD_PRI0_ADDR_LO,
(u32)(tpd_ring[atl1c_trans_normal].dma &
AT_DMA_LO_ADDR_MASK));
- AT_WRITE_REG(hw, REG_HTPD_HEAD_ADDR_LO,
+ AT_WRITE_REG(hw, REG_TPD_PRI1_ADDR_LO,
(u32)(tpd_ring[atl1c_trans_high].dma &
AT_DMA_LO_ADDR_MASK));
AT_WRITE_REG(hw, REG_TPD_RING_SIZE,
@@ -1519,16 +1519,11 @@ static bool atl1c_clean_tx_irq(struct atl1c_adapter *adapter,
struct pci_dev *pdev = adapter->pdev;
u16 next_to_clean = atomic_read(&tpd_ring->next_to_clean);
u16 hw_next_to_clean;
- u16 shift;
- u32 data;
+ u16 reg;
- if (type == atl1c_trans_high)
- shift = MB_HTPD_CONS_IDX_SHIFT;
- else
- shift = MB_NTPD_CONS_IDX_SHIFT;
+ reg = type == atl1c_trans_high ? REG_TPD_PRI1_CIDX : REG_TPD_PRI0_CIDX;
- AT_READ_REG(&adapter->hw, REG_MB_PRIO_CONS_IDX, &data);
- hw_next_to_clean = (data >> shift) & MB_PRIO_PROD_IDX_MASK;
+ AT_READ_REGW(&adapter->hw, reg, &hw_next_to_clean);
while (next_to_clean != hw_next_to_clean) {
buffer_info = &tpd_ring->buffer_info[next_to_clean];
@@ -2090,23 +2085,10 @@ static void atl1c_tx_queue(struct atl1c_adapter *adapter, struct sk_buff *skb,
struct atl1c_tpd_desc *tpd, enum atl1c_trans_queue type)
{
struct atl1c_tpd_ring *tpd_ring = &adapter->tpd_ring[type];
- u32 prod_data;
+ u16 reg;
- AT_READ_REG(&adapter->hw, REG_MB_PRIO_PROD_IDX, &prod_data);
- switch (type) {
- case atl1c_trans_high:
- prod_data &= 0xFFFF0000;
- prod_data |= tpd_ring->next_to_use & 0xFFFF;
- break;
- case atl1c_trans_normal:
- prod_data &= 0x0000FFFF;
- prod_data |= (tpd_ring->next_to_use & 0xFFFF) << 16;
- break;
- default:
- break;
- }
- wmb();
- AT_WRITE_REG(&adapter->hw, REG_MB_PRIO_PROD_IDX, prod_data);
+ reg = type == atl1c_trans_high ? REG_TPD_PRI1_PIDX : REG_TPD_PRI0_PIDX;
+ AT_WRITE_REGW(&adapter->hw, reg, tpd_ring->next_to_use);
}
static netdev_tx_t atl1c_xmit_frame(struct sk_buff *skb,
--
1.7.7
^ permalink raw reply related
* [PATCH 05/37] atl1c: remove SMB/CMB DMA related code
From: xiong @ 2012-04-13 0:14 UTC (permalink / raw)
To: davem, netdev, linux-kernel; +Cc: qca-linux-team, nic-devel, xiong
In-Reply-To: <1334276102-15866-1-git-send-email-xiong@qca.qualcomm.com>
l1c & later chips don't support DMA for SMB.
CMB is removed from hardware.
reg(15C8) is used to trig interrupt by tpd threshold.
Signed-off-by: xiong <xiong@qca.qualcomm.com>
Tested-by: Liu David <dwliu@qca.qualcomm.com>
---
drivers/net/ethernet/atheros/atl1c/atl1c.h | 19 +------------
drivers/net/ethernet/atheros/atl1c/atl1c_hw.h | 10 +-----
drivers/net/ethernet/atheros/atl1c/atl1c_main.c | 34 ++---------------------
3 files changed, 6 insertions(+), 57 deletions(-)
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c.h b/drivers/net/ethernet/atheros/atl1c/atl1c.h
index c725ee5..f8628bc 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c.h
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c.h
@@ -426,10 +426,6 @@ struct atl1c_hw {
#define ATL1C_FPGA_VERSION 0x8000
u16 link_cap_flags;
#define ATL1C_LINK_CAP_1000M 0x0001
- u16 cmb_tpd;
- u16 cmb_rrd;
- u16 cmb_rx_timer; /* 2us resolution */
- u16 cmb_tx_timer;
u32 smb_timer;
u16 rrd_thresh; /* Threshold of number of RRD produced to trigger
@@ -449,8 +445,7 @@ struct atl1c_hw {
/*
* atl1c_ring_header represents a single, contiguous block of DMA space
- * mapped for the three descriptor rings (tpd, rfd, rrd) and the two
- * message blocks (cmb, smb) described below
+ * mapped for the three descriptor rings (tpd, rfd, rrd) described below
*/
struct atl1c_ring_header {
void *desc; /* virtual address */
@@ -524,16 +519,6 @@ struct atl1c_rrd_ring {
u16 next_to_clean;
};
-struct atl1c_cmb {
- void *cmb;
- dma_addr_t dma;
-};
-
-struct atl1c_smb {
- void *smb;
- dma_addr_t dma;
-};
-
/* board specific private data structure */
struct atl1c_adapter {
struct net_device *netdev;
@@ -571,8 +556,6 @@ struct atl1c_adapter {
struct atl1c_tpd_ring tpd_ring[AT_MAX_TRANSMIT_QUEUE];
struct atl1c_rfd_ring rfd_ring;
struct atl1c_rrd_ring rrd_ring;
- struct atl1c_cmb cmb;
- struct atl1c_smb smb;
u32 bd_number; /* board number;*/
};
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
index f5c7473..caff2ae 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
@@ -447,8 +447,6 @@ int atl1c_phy_power_saving(struct atl1c_hw *hw);
*/
#define REG_RX_BASE_ADDR_HI 0x1540
#define REG_TX_BASE_ADDR_HI 0x1544
-#define REG_SMB_BASE_ADDR_HI 0x1548
-#define REG_SMB_BASE_ADDR_LO 0x154C
#define REG_RFD0_HEAD_ADDR_LO 0x1550
#define REG_RFD_RING_SIZE 0x1560
#define RFD_RING_SIZE_MASK 0x0FFF
@@ -461,7 +459,6 @@ int atl1c_phy_power_saving(struct atl1c_hw *hw);
#define REG_NTPD_HEAD_ADDR_LO 0x1580
#define REG_TPD_RING_SIZE 0x1584
#define TPD_RING_SIZE_MASK 0xFFFF
-#define REG_CMB_BASE_ADDR_LO 0x1588
/* TXQ Control Register */
#define REG_TXQ_CTRL 0x1590
@@ -556,13 +553,10 @@ int atl1c_phy_power_saving(struct atl1c_hw *hw);
#define MAC_CTRL_SMB_DIS 0x1000000
#define DMA_CTRL_SMB_NOW 0x80000000
-/* CMB/SMB Control Register */
+/* INT-triggle/SMB Control Register */
#define REG_SMB_STAT_TIMER 0x15C4 /* 2us resolution */
#define SMB_STAT_TIMER_MASK 0xFFFFFF
-#define REG_CMB_TPD_THRESH 0x15C8
-#define CMB_TPD_THRESH_MASK 0xFFFF
-#define REG_CMB_TX_TIMER 0x15CC /* 2us resolution */
-#define CMB_TX_TIMER_MASK 0xFFFF
+#define REG_TINT_TPD_THRESH 0x15C8 /* tpd th to trig intrrupt */
/* Mail box */
#define MB_RFDX_PROD_IDX_MASK 0xFFFF
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 885e892..ceb9df5 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -733,8 +733,6 @@ static int __devinit atl1c_sw_init(struct atl1c_adapter *adapter)
hw->ict = 50000; /* 100ms */
hw->smb_timer = 200000; /* 400ms */
- hw->cmb_tpd = 4;
- hw->cmb_tx_timer = 1; /* 2 us */
hw->rx_imt = 200;
hw->tx_imt = 1000;
@@ -943,8 +941,7 @@ static int atl1c_setup_ring_resources(struct atl1c_adapter *adapter)
sizeof(struct atl1c_tpd_desc) * tpd_ring->count * 2 +
sizeof(struct atl1c_rx_free_desc) * rx_desc_count +
sizeof(struct atl1c_recv_ret_status) * rx_desc_count +
- sizeof(struct atl1c_hw_stats) +
- 8 * 4 + 8 * 2;
+ 8 * 4;
ring_header->desc = pci_alloc_consistent(pdev, ring_header->size,
&ring_header->dma);
@@ -977,8 +974,6 @@ static int atl1c_setup_ring_resources(struct atl1c_adapter *adapter)
rrd_ring->count;
offset += roundup(rrd_ring->size, 8);
- adapter->smb.dma = ring_header->dma + offset;
- adapter->smb.smb = (u8 *)ring_header->desc + offset;
return 0;
err_nomem:
@@ -993,8 +988,6 @@ static void atl1c_configure_des_ring(struct atl1c_adapter *adapter)
struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring;
struct atl1c_tpd_ring *tpd_ring = (struct atl1c_tpd_ring *)
adapter->tpd_ring;
- struct atl1c_cmb *cmb = (struct atl1c_cmb *) &adapter->cmb;
- struct atl1c_smb *smb = (struct atl1c_smb *) &adapter->smb;
u32 data;
/* TPD */
@@ -1029,14 +1022,6 @@ static void atl1c_configure_des_ring(struct atl1c_adapter *adapter)
AT_WRITE_REG(hw, REG_RRD_RING_SIZE,
(rrd_ring->count & RRD_RING_SIZE_MASK));
- /* CMB */
- AT_WRITE_REG(hw, REG_CMB_BASE_ADDR_LO, cmb->dma & AT_DMA_LO_ADDR_MASK);
-
- /* SMB */
- AT_WRITE_REG(hw, REG_SMB_BASE_ADDR_HI,
- (u32)((smb->dma & AT_DMA_HI_ADDR_MASK) >> 32));
- AT_WRITE_REG(hw, REG_SMB_BASE_ADDR_LO,
- (u32)(smb->dma & AT_DMA_LO_ADDR_MASK));
if (hw->nic_type == athr_l2c_b) {
AT_WRITE_REG(hw, REG_SRAM_RXF_LEN, 0x02a0L);
AT_WRITE_REG(hw, REG_SRAM_TXF_LEN, 0x0100L);
@@ -1115,12 +1100,6 @@ static void atl1c_configure_dma(struct atl1c_adapter *adapter)
u32 dma_ctrl_data;
dma_ctrl_data = DMA_CTRL_DMAR_REQ_PRI;
- if (hw->ctrl_flags & ATL1C_CMB_ENABLE)
- dma_ctrl_data |= DMA_CTRL_CMB_EN;
- if (hw->ctrl_flags & ATL1C_SMB_ENABLE)
- dma_ctrl_data |= DMA_CTRL_SMB_EN;
- else
- dma_ctrl_data |= MAC_CTRL_SMB_DIS;
switch (hw->dma_order) {
case atl1c_dma_ord_in:
@@ -1440,16 +1419,9 @@ static int atl1c_configure(struct atl1c_adapter *adapter)
master_ctrl_data |= MASTER_CTRL_SA_TIMER_EN;
AT_WRITE_REG(hw, REG_MASTER_CTRL, master_ctrl_data);
- if (hw->ctrl_flags & ATL1C_CMB_ENABLE) {
- AT_WRITE_REG(hw, REG_CMB_TPD_THRESH,
- hw->cmb_tpd & CMB_TPD_THRESH_MASK);
- AT_WRITE_REG(hw, REG_CMB_TX_TIMER,
- hw->cmb_tx_timer & CMB_TX_TIMER_MASK);
- }
+ AT_WRITE_REG(hw, REG_SMB_STAT_TIMER,
+ hw->smb_timer & SMB_STAT_TIMER_MASK);
- if (hw->ctrl_flags & ATL1C_SMB_ENABLE)
- AT_WRITE_REG(hw, REG_SMB_STAT_TIMER,
- hw->smb_timer & SMB_STAT_TIMER_MASK);
/* set MTU */
AT_WRITE_REG(hw, REG_MTU, hw->max_frame_size + ETH_HLEN +
VLAN_HLEN + ETH_FCS_LEN);
--
1.7.7
^ permalink raw reply related
* [PATCH 04/37] atl1c: remove VPD register
From: xiong @ 2012-04-13 0:14 UTC (permalink / raw)
To: davem, netdev, linux-kernel; +Cc: qca-linux-team, nic-devel, xiong
In-Reply-To: <1334276102-15866-1-git-send-email-xiong@qca.qualcomm.com>
VPD register is only used for L1(devid=PCI_DEVICE_ID_ATTANSIC_L1) to
access external NV-memory.
l1c & later chip doesn't use it any more.
Signed-off-by: xiong <xiong@qca.qualcomm.com>
Tested-by: Liu David <dwliu@qca.qualcomm.com>
---
drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c | 1 -
drivers/net/ethernet/atheros/atl1c/atl1c_hw.h | 11 -----------
2 files changed, 0 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c b/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c
index 0a9326a..ce63615 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c
@@ -142,7 +142,6 @@ static void atl1c_get_regs(struct net_device *netdev,
memset(p, 0, AT_REGS_LEN);
regs->version = 0;
- AT_READ_REG(hw, REG_VPD_CAP, p++);
AT_READ_REG(hw, REG_PM_CTRL, p++);
AT_READ_REG(hw, REG_MAC_HALF_DUPLX_CTRL, p++);
AT_READ_REG(hw, REG_TWSI_CTRL, p++);
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
index c22d698..f5c7473 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
@@ -59,17 +59,6 @@ int atl1c_phy_power_saving(struct atl1c_hw *hw);
#define LINK_CTRL_L1_EN 0x02
#define LINK_CTRL_EXT_SYNC 0x80
-#define REG_VPD_CAP 0x6C
-#define VPD_CAP_ID_MASK 0xff
-#define VPD_CAP_ID_SHIFT 0
-#define VPD_CAP_NEXT_PTR_MASK 0xFF
-#define VPD_CAP_NEXT_PTR_SHIFT 8
-#define VPD_CAP_VPD_ADDR_MASK 0x7FFF
-#define VPD_CAP_VPD_ADDR_SHIFT 16
-#define VPD_CAP_VPD_FLAG 0x80000000
-
-#define REG_VPD_DATA 0x70
-
#define REG_PCIE_UC_SEVERITY 0x10C
#define PCIE_UC_SERVRITY_TRN 0x00000001
#define PCIE_UC_SERVRITY_DLP 0x00000010
--
1.7.7
^ permalink raw reply related
* [PATCH 03/37] atl1c: remove HDS register
From: xiong @ 2012-04-13 0:14 UTC (permalink / raw)
To: davem, netdev, linux-kernel; +Cc: qca-linux-team, nic-devel, xiong
In-Reply-To: <1334276102-15866-1-git-send-email-xiong@qca.qualcomm.com>
remove HDS register as it doesn't exist in hardware.
Signed-off-by: xiong <xiong@qca.qualcomm.com>
Tested-by: Liu David <dwliu@qca.qualcomm.com>
---
drivers/net/ethernet/atheros/atl1c/atl1c_hw.h | 7 -------
drivers/net/ethernet/atheros/atl1c/atl1c_main.c | 2 --
2 files changed, 0 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
index 855aca0..c22d698 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
@@ -669,13 +669,6 @@ int atl1c_phy_power_saving(struct atl1c_hw *hw);
#define REG_INT_RETRIG_TIMER 0x1608
#define INT_RETRIG_TIMER_MASK 0xFFFF
-#define REG_HDS_CTRL 0x160C
-#define HDS_CTRL_EN 0x0001
-#define HDS_CTRL_BACKFILLSIZE_SHIFT 8
-#define HDS_CTRL_BACKFILLSIZE_MASK 0x0FFF
-#define HDS_CTRL_MAX_HDRSIZE_SHIFT 20
-#define HDS_CTRL_MAC_HDRSIZE_MASK 0x0FFF
-
#define REG_MAC_RX_STATUS_BIN 0x1700
#define REG_MAC_RX_STATUS_END 0x175c
#define REG_MAC_TX_STATUS_BIN 0x1760
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 226be99..885e892 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -1453,8 +1453,6 @@ static int atl1c_configure(struct atl1c_adapter *adapter)
/* set MTU */
AT_WRITE_REG(hw, REG_MTU, hw->max_frame_size + ETH_HLEN +
VLAN_HLEN + ETH_FCS_LEN);
- /* HDS, disable */
- AT_WRITE_REG(hw, REG_HDS_CTRL, 0);
atl1c_configure_tx(adapter);
atl1c_configure_rx(adapter);
--
1.7.7
^ permalink raw reply related
* [PATCH 02/37] atl1c: remove multiple-RX-Q code
From: xiong @ 2012-04-13 0:14 UTC (permalink / raw)
To: davem, netdev, linux-kernel; +Cc: qca-linux-team, nic-devel, xiong
In-Reply-To: <1334276102-15866-1-git-send-email-xiong@qca.qualcomm.com>
the multiple-RX-Q in hardware doesn't work,
all related register definition & code are removed.
Signed-off-by: xiong <xiong@qca.qualcomm.com>
Tested-by: Liu David <dwliu@qca.qualcomm.com>
---
drivers/net/ethernet/atheros/atl1c/atl1c.h | 22 +--
drivers/net/ethernet/atheros/atl1c/atl1c_hw.h | 36 ----
drivers/net/ethernet/atheros/atl1c/atl1c_main.c | 216 +++++++----------------
3 files changed, 65 insertions(+), 209 deletions(-)
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c.h b/drivers/net/ethernet/atheros/atl1c/atl1c.h
index ca70e16..c725ee5 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c.h
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c.h
@@ -297,20 +297,6 @@ enum atl1c_dma_req_block {
atl1c_dma_req_4096 = 5
};
-enum atl1c_rss_mode {
- atl1c_rss_mode_disable = 0,
- atl1c_rss_sig_que = 1,
- atl1c_rss_mul_que_sig_int = 2,
- atl1c_rss_mul_que_mul_int = 4,
-};
-
-enum atl1c_rss_type {
- atl1c_rss_disable = 0,
- atl1c_rss_ipv4 = 1,
- atl1c_rss_ipv4_tcp = 2,
- atl1c_rss_ipv6 = 4,
- atl1c_rss_ipv6_tcp = 8
-};
enum atl1c_nic_type {
athr_l1c = 0,
@@ -451,9 +437,6 @@ struct atl1c_hw {
u16 tpd_thresh;
u8 tpd_burst; /* Number of TPD to prefetch in cache-aligned burst. */
u8 rfd_burst;
- enum atl1c_rss_type rss_type;
- enum atl1c_rss_mode rss_mode;
- u8 rss_hash_bits;
u32 base_cpu;
u32 indirect_tab;
u8 mac_addr[ETH_ALEN];
@@ -586,11 +569,10 @@ struct atl1c_adapter {
/* All Descriptor memory */
struct atl1c_ring_header ring_header;
struct atl1c_tpd_ring tpd_ring[AT_MAX_TRANSMIT_QUEUE];
- struct atl1c_rfd_ring rfd_ring[AT_MAX_RECEIVE_QUEUE];
- struct atl1c_rrd_ring rrd_ring[AT_MAX_RECEIVE_QUEUE];
+ struct atl1c_rfd_ring rfd_ring;
+ struct atl1c_rrd_ring rrd_ring;
struct atl1c_cmb cmb;
struct atl1c_smb smb;
- int num_rx_queues;
u32 bd_number; /* board number;*/
};
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
index 655fc6c..855aca0 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
@@ -461,17 +461,11 @@ int atl1c_phy_power_saving(struct atl1c_hw *hw);
#define REG_SMB_BASE_ADDR_HI 0x1548
#define REG_SMB_BASE_ADDR_LO 0x154C
#define REG_RFD0_HEAD_ADDR_LO 0x1550
-#define REG_RFD1_HEAD_ADDR_LO 0x1554
-#define REG_RFD2_HEAD_ADDR_LO 0x1558
-#define REG_RFD3_HEAD_ADDR_LO 0x155C
#define REG_RFD_RING_SIZE 0x1560
#define RFD_RING_SIZE_MASK 0x0FFF
#define REG_RX_BUF_SIZE 0x1564
#define RX_BUF_SIZE_MASK 0xFFFF
#define REG_RRD0_HEAD_ADDR_LO 0x1568
-#define REG_RRD1_HEAD_ADDR_LO 0x156C
-#define REG_RRD2_HEAD_ADDR_LO 0x1570
-#define REG_RRD3_HEAD_ADDR_LO 0x1574
#define REG_RRD_RING_SIZE 0x1578
#define RRD_RING_SIZE_MASK 0x0FFF
#define REG_HTPD_HEAD_ADDR_LO 0x157C
@@ -480,30 +474,6 @@ int atl1c_phy_power_saving(struct atl1c_hw *hw);
#define TPD_RING_SIZE_MASK 0xFFFF
#define REG_CMB_BASE_ADDR_LO 0x1588
-/* RSS about */
-#define REG_RSS_KEY0 0x14B0
-#define REG_RSS_KEY1 0x14B4
-#define REG_RSS_KEY2 0x14B8
-#define REG_RSS_KEY3 0x14BC
-#define REG_RSS_KEY4 0x14C0
-#define REG_RSS_KEY5 0x14C4
-#define REG_RSS_KEY6 0x14C8
-#define REG_RSS_KEY7 0x14CC
-#define REG_RSS_KEY8 0x14D0
-#define REG_RSS_KEY9 0x14D4
-#define REG_IDT_TABLE0 0x14E0
-#define REG_IDT_TABLE1 0x14E4
-#define REG_IDT_TABLE2 0x14E8
-#define REG_IDT_TABLE3 0x14EC
-#define REG_IDT_TABLE4 0x14F0
-#define REG_IDT_TABLE5 0x14F4
-#define REG_IDT_TABLE6 0x14F8
-#define REG_IDT_TABLE7 0x14FC
-#define REG_IDT_TABLE REG_IDT_TABLE0
-#define REG_RSS_HASH_VALUE 0x15B0
-#define REG_RSS_HASH_FLAG 0x15B4
-#define REG_BASE_CPU_NUMBER 0x15B8
-
/* TXQ Control Register */
#define REG_TXQ_CTRL 0x1590
#define TXQ_NUM_TPD_BURST_MASK 0xF
@@ -608,9 +578,6 @@ int atl1c_phy_power_saving(struct atl1c_hw *hw);
/* Mail box */
#define MB_RFDX_PROD_IDX_MASK 0xFFFF
#define REG_MB_RFD0_PROD_IDX 0x15E0
-#define REG_MB_RFD1_PROD_IDX 0x15E4
-#define REG_MB_RFD2_PROD_IDX 0x15E8
-#define REG_MB_RFD3_PROD_IDX 0x15EC
#define MB_PRIO_PROD_IDX_MASK 0xFFFF
#define REG_MB_PRIO_PROD_IDX 0x15F0
@@ -625,9 +592,6 @@ int atl1c_phy_power_saving(struct atl1c_hw *hw);
#define REG_MB_RFD01_CONS_IDX 0x15F8
#define MB_RFD0_CONS_IDX_MASK 0x0000FFFF
#define MB_RFD1_CONS_IDX_MASK 0xFFFF0000
-#define REG_MB_RFD23_CONS_IDX 0x15FC
-#define MB_RFD2_CONS_IDX_MASK 0x0000FFFF
-#define MB_RFD3_CONS_IDX_MASK 0xFFFF0000
/* Interrupt Status Register */
#define REG_ISR 0x1600
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 1f1f9eb..226be99 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -66,7 +66,7 @@ static void atl1c_enable_tx_ctrl(struct atl1c_hw *hw);
static void atl1c_disable_l0s_l1(struct atl1c_hw *hw);
static void atl1c_set_aspm(struct atl1c_hw *hw, bool linkup);
static void atl1c_setup_mac_ctrl(struct atl1c_adapter *adapter);
-static void atl1c_clean_rx_irq(struct atl1c_adapter *adapter, u8 que,
+static void atl1c_clean_rx_irq(struct atl1c_adapter *adapter,
int *work_done, int work_to_do);
static int atl1c_up(struct atl1c_adapter *adapter);
static void atl1c_down(struct atl1c_adapter *adapter);
@@ -75,29 +75,6 @@ static const u16 atl1c_pay_load_size[] = {
128, 256, 512, 1024, 2048, 4096,
};
-static const u16 atl1c_rfd_prod_idx_regs[AT_MAX_RECEIVE_QUEUE] =
-{
- REG_MB_RFD0_PROD_IDX,
- REG_MB_RFD1_PROD_IDX,
- REG_MB_RFD2_PROD_IDX,
- REG_MB_RFD3_PROD_IDX
-};
-
-static const u16 atl1c_rfd_addr_lo_regs[AT_MAX_RECEIVE_QUEUE] =
-{
- REG_RFD0_HEAD_ADDR_LO,
- REG_RFD1_HEAD_ADDR_LO,
- REG_RFD2_HEAD_ADDR_LO,
- REG_RFD3_HEAD_ADDR_LO
-};
-
-static const u16 atl1c_rrd_addr_lo_regs[AT_MAX_RECEIVE_QUEUE] =
-{
- REG_RRD0_HEAD_ADDR_LO,
- REG_RRD1_HEAD_ADDR_LO,
- REG_RRD2_HEAD_ADDR_LO,
- REG_RRD3_HEAD_ADDR_LO
-};
static const u32 atl1c_default_msg = NETIF_MSG_DRV | NETIF_MSG_PROBE |
NETIF_MSG_LINK | NETIF_MSG_TIMER | NETIF_MSG_IFDOWN | NETIF_MSG_IFUP;
@@ -730,9 +707,8 @@ static int __devinit atl1c_sw_init(struct atl1c_adapter *adapter)
device_set_wakeup_enable(&pdev->dev, false);
adapter->link_speed = SPEED_0;
adapter->link_duplex = FULL_DUPLEX;
- adapter->num_rx_queues = AT_DEF_RECEIVE_QUEUE;
adapter->tpd_ring[0].count = 1024;
- adapter->rfd_ring[0].count = 512;
+ adapter->rfd_ring.count = 512;
hw->vendor_id = pdev->vendor;
hw->device_id = pdev->device;
@@ -751,14 +727,6 @@ static int __devinit atl1c_sw_init(struct atl1c_adapter *adapter)
hw->phy_configured = false;
hw->preamble_len = 7;
hw->max_frame_size = adapter->netdev->mtu;
- if (adapter->num_rx_queues < 2) {
- hw->rss_type = atl1c_rss_disable;
- hw->rss_mode = atl1c_rss_mode_disable;
- } else {
- hw->rss_type = atl1c_rss_ipv4;
- hw->rss_mode = atl1c_rss_mul_que_mul_int;
- hw->rss_hash_bits = 16;
- }
hw->autoneg_advertised = ADVERTISED_Autoneg;
hw->indirect_tab = 0xE4E4E4E4;
hw->base_cpu = 0;
@@ -852,24 +820,22 @@ static void atl1c_clean_tx_ring(struct atl1c_adapter *adapter,
*/
static void atl1c_clean_rx_ring(struct atl1c_adapter *adapter)
{
- struct atl1c_rfd_ring *rfd_ring = adapter->rfd_ring;
- struct atl1c_rrd_ring *rrd_ring = adapter->rrd_ring;
+ struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring;
+ struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring;
struct atl1c_buffer *buffer_info;
struct pci_dev *pdev = adapter->pdev;
- int i, j;
+ int j;
- for (i = 0; i < adapter->num_rx_queues; i++) {
- for (j = 0; j < rfd_ring[i].count; j++) {
- buffer_info = &rfd_ring[i].buffer_info[j];
- atl1c_clean_buffer(pdev, buffer_info, 0);
- }
- /* zero out the descriptor ring */
- memset(rfd_ring[i].desc, 0, rfd_ring[i].size);
- rfd_ring[i].next_to_clean = 0;
- rfd_ring[i].next_to_use = 0;
- rrd_ring[i].next_to_use = 0;
- rrd_ring[i].next_to_clean = 0;
+ for (j = 0; j < rfd_ring->count; j++) {
+ buffer_info = &rfd_ring->buffer_info[j];
+ atl1c_clean_buffer(pdev, buffer_info, 0);
}
+ /* zero out the descriptor ring */
+ memset(rfd_ring->desc, 0, rfd_ring->size);
+ rfd_ring->next_to_clean = 0;
+ rfd_ring->next_to_use = 0;
+ rrd_ring->next_to_use = 0;
+ rrd_ring->next_to_clean = 0;
}
/*
@@ -878,8 +844,8 @@ static void atl1c_clean_rx_ring(struct atl1c_adapter *adapter)
static void atl1c_init_ring_ptrs(struct atl1c_adapter *adapter)
{
struct atl1c_tpd_ring *tpd_ring = adapter->tpd_ring;
- struct atl1c_rfd_ring *rfd_ring = adapter->rfd_ring;
- struct atl1c_rrd_ring *rrd_ring = adapter->rrd_ring;
+ struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring;
+ struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring;
struct atl1c_buffer *buffer_info;
int i, j;
@@ -891,15 +857,13 @@ static void atl1c_init_ring_ptrs(struct atl1c_adapter *adapter)
ATL1C_SET_BUFFER_STATE(&buffer_info[i],
ATL1C_BUFFER_FREE);
}
- for (i = 0; i < adapter->num_rx_queues; i++) {
- rfd_ring[i].next_to_use = 0;
- rfd_ring[i].next_to_clean = 0;
- rrd_ring[i].next_to_use = 0;
- rrd_ring[i].next_to_clean = 0;
- for (j = 0; j < rfd_ring[i].count; j++) {
- buffer_info = &rfd_ring[i].buffer_info[j];
- ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_FREE);
- }
+ rfd_ring->next_to_use = 0;
+ rfd_ring->next_to_clean = 0;
+ rrd_ring->next_to_use = 0;
+ rrd_ring->next_to_clean = 0;
+ for (j = 0; j < rfd_ring->count; j++) {
+ buffer_info = &rfd_ring->buffer_info[j];
+ ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_FREE);
}
}
@@ -936,27 +900,23 @@ static int atl1c_setup_ring_resources(struct atl1c_adapter *adapter)
{
struct pci_dev *pdev = adapter->pdev;
struct atl1c_tpd_ring *tpd_ring = adapter->tpd_ring;
- struct atl1c_rfd_ring *rfd_ring = adapter->rfd_ring;
- struct atl1c_rrd_ring *rrd_ring = adapter->rrd_ring;
+ struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring;
+ struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring;
struct atl1c_ring_header *ring_header = &adapter->ring_header;
- int num_rx_queues = adapter->num_rx_queues;
int size;
int i;
int count = 0;
int rx_desc_count = 0;
u32 offset = 0;
- rrd_ring[0].count = rfd_ring[0].count;
+ rrd_ring->count = rfd_ring->count;
for (i = 1; i < AT_MAX_TRANSMIT_QUEUE; i++)
tpd_ring[i].count = tpd_ring[0].count;
- for (i = 1; i < adapter->num_rx_queues; i++)
- rfd_ring[i].count = rrd_ring[i].count = rfd_ring[0].count;
-
/* 2 tpd queue, one high priority queue,
* another normal priority queue */
size = sizeof(struct atl1c_buffer) * (tpd_ring->count * 2 +
- rfd_ring->count * num_rx_queues);
+ rfd_ring->count);
tpd_ring->buffer_info = kzalloc(size, GFP_KERNEL);
if (unlikely(!tpd_ring->buffer_info)) {
dev_err(&pdev->dev, "kzalloc failed, size = %d\n",
@@ -969,12 +929,11 @@ static int atl1c_setup_ring_resources(struct atl1c_adapter *adapter)
count += tpd_ring[i].count;
}
- for (i = 0; i < num_rx_queues; i++) {
- rfd_ring[i].buffer_info =
- (struct atl1c_buffer *) (tpd_ring->buffer_info + count);
- count += rfd_ring[i].count;
- rx_desc_count += rfd_ring[i].count;
- }
+ rfd_ring->buffer_info =
+ (struct atl1c_buffer *) (tpd_ring->buffer_info + count);
+ count += rfd_ring->count;
+ rx_desc_count += rfd_ring->count;
+
/*
* real ring DMA buffer
* each ring/block may need up to 8 bytes for alignment, hence the
@@ -985,7 +944,7 @@ static int atl1c_setup_ring_resources(struct atl1c_adapter *adapter)
sizeof(struct atl1c_rx_free_desc) * rx_desc_count +
sizeof(struct atl1c_recv_ret_status) * rx_desc_count +
sizeof(struct atl1c_hw_stats) +
- 8 * 4 + 8 * 2 * num_rx_queues;
+ 8 * 4 + 8 * 2;
ring_header->desc = pci_alloc_consistent(pdev, ring_header->size,
&ring_header->dma);
@@ -1006,22 +965,17 @@ static int atl1c_setup_ring_resources(struct atl1c_adapter *adapter)
offset += roundup(tpd_ring[i].size, 8);
}
/* init RFD ring */
- for (i = 0; i < num_rx_queues; i++) {
- rfd_ring[i].dma = ring_header->dma + offset;
- rfd_ring[i].desc = (u8 *) ring_header->desc + offset;
- rfd_ring[i].size = sizeof(struct atl1c_rx_free_desc) *
- rfd_ring[i].count;
- offset += roundup(rfd_ring[i].size, 8);
- }
+ rfd_ring->dma = ring_header->dma + offset;
+ rfd_ring->desc = (u8 *) ring_header->desc + offset;
+ rfd_ring->size = sizeof(struct atl1c_rx_free_desc) * rfd_ring->count;
+ offset += roundup(rfd_ring->size, 8);
/* init RRD ring */
- for (i = 0; i < num_rx_queues; i++) {
- rrd_ring[i].dma = ring_header->dma + offset;
- rrd_ring[i].desc = (u8 *) ring_header->desc + offset;
- rrd_ring[i].size = sizeof(struct atl1c_recv_ret_status) *
- rrd_ring[i].count;
- offset += roundup(rrd_ring[i].size, 8);
- }
+ rrd_ring->dma = ring_header->dma + offset;
+ rrd_ring->desc = (u8 *) ring_header->desc + offset;
+ rrd_ring->size = sizeof(struct atl1c_recv_ret_status) *
+ rrd_ring->count;
+ offset += roundup(rrd_ring->size, 8);
adapter->smb.dma = ring_header->dma + offset;
adapter->smb.smb = (u8 *)ring_header->desc + offset;
@@ -1035,15 +989,12 @@ err_nomem:
static void atl1c_configure_des_ring(struct atl1c_adapter *adapter)
{
struct atl1c_hw *hw = &adapter->hw;
- struct atl1c_rfd_ring *rfd_ring = (struct atl1c_rfd_ring *)
- adapter->rfd_ring;
- struct atl1c_rrd_ring *rrd_ring = (struct atl1c_rrd_ring *)
- adapter->rrd_ring;
+ struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring;
+ struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring;
struct atl1c_tpd_ring *tpd_ring = (struct atl1c_tpd_ring *)
adapter->tpd_ring;
struct atl1c_cmb *cmb = (struct atl1c_cmb *) &adapter->cmb;
struct atl1c_smb *smb = (struct atl1c_smb *) &adapter->smb;
- int i;
u32 data;
/* TPD */
@@ -1063,22 +1014,20 @@ static void atl1c_configure_des_ring(struct atl1c_adapter *adapter)
/* RFD */
AT_WRITE_REG(hw, REG_RX_BASE_ADDR_HI,
- (u32)((rfd_ring[0].dma & AT_DMA_HI_ADDR_MASK) >> 32));
- for (i = 0; i < adapter->num_rx_queues; i++)
- AT_WRITE_REG(hw, atl1c_rfd_addr_lo_regs[i],
- (u32)(rfd_ring[i].dma & AT_DMA_LO_ADDR_MASK));
+ (u32)((rfd_ring->dma & AT_DMA_HI_ADDR_MASK) >> 32));
+ AT_WRITE_REG(hw, REG_RFD0_HEAD_ADDR_LO,
+ (u32)(rfd_ring->dma & AT_DMA_LO_ADDR_MASK));
AT_WRITE_REG(hw, REG_RFD_RING_SIZE,
- rfd_ring[0].count & RFD_RING_SIZE_MASK);
+ rfd_ring->count & RFD_RING_SIZE_MASK);
AT_WRITE_REG(hw, REG_RX_BUF_SIZE,
adapter->rx_buffer_len & RX_BUF_SIZE_MASK);
/* RRD */
- for (i = 0; i < adapter->num_rx_queues; i++)
- AT_WRITE_REG(hw, atl1c_rrd_addr_lo_regs[i],
- (u32)(rrd_ring[i].dma & AT_DMA_LO_ADDR_MASK));
+ AT_WRITE_REG(hw, REG_RRD0_HEAD_ADDR_LO,
+ (u32)(rrd_ring->dma & AT_DMA_LO_ADDR_MASK));
AT_WRITE_REG(hw, REG_RRD_RING_SIZE,
- (rrd_ring[0].count & RRD_RING_SIZE_MASK));
+ (rrd_ring->count & RRD_RING_SIZE_MASK));
/* CMB */
AT_WRITE_REG(hw, REG_CMB_BASE_ADDR_LO, cmb->dma & AT_DMA_LO_ADDR_MASK);
@@ -1152,21 +1101,7 @@ static void atl1c_configure_rx(struct atl1c_adapter *adapter)
if (hw->ctrl_flags & ATL1C_RX_IPV6_CHKSUM)
rxq_ctrl_data |= IPV6_CHKSUM_CTRL_EN;
- if (hw->rss_type == atl1c_rss_ipv4)
- rxq_ctrl_data |= RSS_HASH_IPV4;
- if (hw->rss_type == atl1c_rss_ipv4_tcp)
- rxq_ctrl_data |= RSS_HASH_IPV4_TCP;
- if (hw->rss_type == atl1c_rss_ipv6)
- rxq_ctrl_data |= RSS_HASH_IPV6;
- if (hw->rss_type == atl1c_rss_ipv6_tcp)
- rxq_ctrl_data |= RSS_HASH_IPV6_TCP;
- if (hw->rss_type != atl1c_rss_disable)
- rxq_ctrl_data |= RRS_HASH_CTRL_EN;
- rxq_ctrl_data |= (hw->rss_mode & RSS_MODE_MASK) <<
- RSS_MODE_SHIFT;
- rxq_ctrl_data |= (hw->rss_hash_bits & RSS_HASH_BITS_MASK) <<
- RSS_HASH_BITS_SHIFT;
if (hw->ctrl_flags & ATL1C_ASPM_CTRL_MON)
rxq_ctrl_data |= (ASPM_THRUPUT_LIMIT_1M &
ASPM_THRUPUT_LIMIT_MASK) << ASPM_THRUPUT_LIMIT_SHIFT;
@@ -1174,14 +1109,6 @@ static void atl1c_configure_rx(struct atl1c_adapter *adapter)
AT_WRITE_REG(hw, REG_RXQ_CTRL, rxq_ctrl_data);
}
-static void atl1c_configure_rss(struct atl1c_adapter *adapter)
-{
- struct atl1c_hw *hw = &adapter->hw;
-
- AT_WRITE_REG(hw, REG_IDT_TABLE, hw->indirect_tab);
- AT_WRITE_REG(hw, REG_BASE_CPU_NUMBER, hw->base_cpu);
-}
-
static void atl1c_configure_dma(struct atl1c_adapter *adapter)
{
struct atl1c_hw *hw = &adapter->hw;
@@ -1253,19 +1180,6 @@ static void atl1c_enable_rx_ctrl(struct atl1c_hw *hw)
u32 data;
AT_READ_REG(hw, REG_RXQ_CTRL, &data);
- switch (hw->adapter->num_rx_queues) {
- case 4:
- data |= (RXQ3_CTRL_EN | RXQ2_CTRL_EN | RXQ1_CTRL_EN);
- break;
- case 3:
- data |= (RXQ2_CTRL_EN | RXQ1_CTRL_EN);
- break;
- case 2:
- data |= RXQ1_CTRL_EN;
- break;
- default:
- break;
- }
data |= RXQ_CTRL_EN;
AT_WRITE_REG(hw, REG_RXQ_CTRL, data);
}
@@ -1544,7 +1458,6 @@ static int atl1c_configure(struct atl1c_adapter *adapter)
atl1c_configure_tx(adapter);
atl1c_configure_rx(adapter);
- atl1c_configure_rss(adapter);
atl1c_configure_dma(adapter);
return 0;
@@ -1747,9 +1660,9 @@ static inline void atl1c_rx_checksum(struct atl1c_adapter *adapter,
skb_checksum_none_assert(skb);
}
-static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter, const int ringid)
+static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter)
{
- struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring[ringid];
+ struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring;
struct pci_dev *pdev = adapter->pdev;
struct atl1c_buffer *buffer_info, *next_info;
struct sk_buff *skb;
@@ -1801,7 +1714,7 @@ static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter, const int ringid
/* TODO: update mailbox here */
wmb();
rfd_ring->next_to_use = rfd_next_to_use;
- AT_WRITE_REG(&adapter->hw, atl1c_rfd_prod_idx_regs[ringid],
+ AT_WRITE_REG(&adapter->hw, REG_MB_RFD0_PROD_IDX,
rfd_ring->next_to_use & MB_RFDX_PROD_IDX_MASK);
}
@@ -1840,7 +1753,7 @@ static void atl1c_clean_rfd(struct atl1c_rfd_ring *rfd_ring,
rfd_ring->next_to_clean = rfd_index;
}
-static void atl1c_clean_rx_irq(struct atl1c_adapter *adapter, u8 que,
+static void atl1c_clean_rx_irq(struct atl1c_adapter *adapter,
int *work_done, int work_to_do)
{
u16 rfd_num, rfd_index;
@@ -1848,8 +1761,8 @@ static void atl1c_clean_rx_irq(struct atl1c_adapter *adapter, u8 que,
u16 length;
struct pci_dev *pdev = adapter->pdev;
struct net_device *netdev = adapter->netdev;
- struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring[que];
- struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring[que];
+ struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring;
+ struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring;
struct sk_buff *skb;
struct atl1c_recv_ret_status *rrs;
struct atl1c_buffer *buffer_info;
@@ -1915,7 +1828,7 @@ rrs_checked:
count++;
}
if (count)
- atl1c_alloc_rx_buffer(adapter, que);
+ atl1c_alloc_rx_buffer(adapter);
}
/*
@@ -1932,7 +1845,7 @@ static int atl1c_clean(struct napi_struct *napi, int budget)
if (!netif_carrier_ok(adapter->netdev))
goto quit_polling;
/* just enable one RXQ */
- atl1c_clean_rx_irq(adapter, 0, &work_done, budget);
+ atl1c_clean_rx_irq(adapter, &work_done, budget);
if (work_done < budget) {
quit_polling:
@@ -2334,19 +2247,16 @@ static int atl1c_up(struct atl1c_adapter *adapter)
struct net_device *netdev = adapter->netdev;
int num;
int err;
- int i;
netif_carrier_off(netdev);
atl1c_init_ring_ptrs(adapter);
atl1c_set_multi(netdev);
atl1c_restore_vlan(adapter);
- for (i = 0; i < adapter->num_rx_queues; i++) {
- num = atl1c_alloc_rx_buffer(adapter, i);
- if (unlikely(num == 0)) {
- err = -ENOMEM;
- goto err_alloc_rx;
- }
+ num = atl1c_alloc_rx_buffer(adapter);
+ if (unlikely(num == 0)) {
+ err = -ENOMEM;
+ goto err_alloc_rx;
}
if (atl1c_configure(adapter)) {
--
1.7.7
^ permalink raw reply related
* [PATCH 01/37] atl1c: update author contact info & company/driver desciption
From: xiong @ 2012-04-13 0:14 UTC (permalink / raw)
To: davem, netdev, linux-kernel; +Cc: qca-linux-team, nic-devel, xiong
In-Reply-To: <1334276102-15866-1-git-send-email-xiong@qca.qualcomm.com>
replace unavailable email of the author since he left with a mail-list.
update company info as well, Atheros was acquired by Qualcomm.
insert "100" to driver description since it support 100M controller.
Signed-off-by: xiong <xiong@qca.qualcomm.com>
Tested-by: Liu David <dwliu@qca.qualcomm.com>
---
drivers/net/ethernet/atheros/atl1c/atl1c_main.c | 5 +++--
1 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 1ef0c92..1f1f9eb 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -54,8 +54,9 @@ static DEFINE_PCI_DEVICE_TABLE(atl1c_pci_tbl) = {
};
MODULE_DEVICE_TABLE(pci, atl1c_pci_tbl);
-MODULE_AUTHOR("Jie Yang <jie.yang@atheros.com>");
-MODULE_DESCRIPTION("Atheros 1000M Ethernet Network Driver");
+MODULE_AUTHOR("Jie Yang");
+MODULE_AUTHOR("Qualcomm Atheros Inc., <nic-devel@qualcomm.com>");
+MODULE_DESCRIPTION("Qualcom Atheros 100/1000M Ethernet Network Driver");
MODULE_LICENSE("GPL");
MODULE_VERSION(ATL1C_DRV_VERSION);
--
1.7.7
^ permalink raw reply related
* [PATCH 00/37] atl1c: update hardware settings
From: xiong @ 2012-04-13 0:14 UTC (permalink / raw)
To: davem, netdev, linux-kernel; +Cc: qca-linux-team, nic-devel, xiong
This update contains a serial of patches,
most of them are hardware settings related.
register definitions are refined for each patch.
The patches are for following main purpose:
1. improve the PCI Express Interface stability.
2. improve the PHY Link stability.
3. improve the power consumption, like ASPM and PHY Hibernation.
4. imporve the throughput, get same result with alx driver as shown
in http://linuxfoundation.org/collaborate/workgroups/networking/alx
Following NICs are tested:
AR8131/AR8132/AR8151A/AR8152A/AR8152B
These patches have addressed all sparse and checkpatch warnings.
xiong (37):
atl1c: update author contact info & company/driver desciption
atl1c: remove multiple-RX-Q code
atl1c: remove HDS register
atl1c: remove VPD register
atl1c: remove SMB/CMB DMA related code
atl1c: split 2 32bit registers of TPD to 4 16bit registers
atl1c: remove code related to rxq 1/2/3
atl1c: wrong register used to stop TXQ
atl1c: correct wrong definition of REG_DMA_CTRL
atl1c: remove dmaw_block
atl1c: using fixed TXQ configuration for l2cb and l1c
atl1c: restore max-read-request-size in Device Conrol Register
atl1c: threshold for ASPM is changed based on chip capability
atl1c: add module parameter for l1c_wait_until_idle
atl1c: update right threshold for TSO
atl1c: remove dmar_dly_cnt and dmaw_dly_cnt
atl1c: clear PCIE error status in atl1c_reset_pcie
atl1c: refine reg definition of REG_MASTER_CTRL
atl1c: clear bit MASTER_CTRL_CLK_SEL_DIS in atl1c_pcie_patch
atl1c: refine/update ASPM configuration
atl1c: refine atl1c_pcie_patch
atl1c: fix WoL(magic) issue for l2cb 1.1
atl1c: remove MDIO_REG_ADDR_MASK in atl1c_mdio_read/write
atl1c: remove REG_PHY_STATUS
atl1c: refine phy-register read/write function
atl1c: remove PHY contrl in atl1c_reset_pcie
atl1c: refine SERDES-clock related code
atl1c: remove PHY polling from atl1c_open
atl1c: update PHY reset related routine
atl1c: remove PHY reset/init for link down event
atl1c: add function atl1c_power_saving
atl1c: refine start/enable code for MAC module
atl1c: add PHY link event(up/down) patch
atl1c: clear WoL status when reset pcie
atl1c: remove code of closing register writable attribution
atl1c: refine mac address related code
atl1c: cancel task when interface closed
drivers/net/ethernet/atheros/atl1c/atl1c.h | 57 +-
drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c | 3 +-
drivers/net/ethernet/atheros/atl1c/atl1c_hw.c | 563 ++++++++----
drivers/net/ethernet/atheros/atl1c/atl1c_hw.h | 999 ++++++++++++--------
drivers/net/ethernet/atheros/atl1c/atl1c_main.c | 913 +++++++-----------
5 files changed, 1339 insertions(+), 1196 deletions(-)
--
1.7.7
^ permalink raw reply
* Re: pull request: wireless-next 2012-04-12
From: David Miller @ 2012-04-13 0:12 UTC (permalink / raw)
To: linville-2XuSBdqkA4R54TAoqtyWWQ
Cc: linux-wireless-u79uwXL29TY76Z2rM5mHXA,
netdev-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <20120412195520.GC21495-2XuSBdqkA4R54TAoqtyWWQ@public.gmane.org>
From: "John W. Linville" <linville-2XuSBdqkA4R54TAoqtyWWQ@public.gmane.org>
Date: Thu, 12 Apr 2012 15:55:20 -0400
> Welcome to the first wireless pull request for the 3.5 era! :-)
>
> Highlights of this batch include some mac80211 refactoring and
> enhancements, a number of iwlwifi updates, some ath9k updates
> (including a DFS pattern detector), and various other updates to
> rtlwifi, mwifiex, and various other drivers. Overall, nothing too
> unusual...
>
> Please let me know if there are problems!
Pulled, thanks John.
--
To unsubscribe from this list: send the line "unsubscribe linux-wireless" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH 6/6] tilegx network driver: initial support
From: Chris Metcalf @ 2012-04-12 23:23 UTC (permalink / raw)
To: Arnd Bergmann; +Cc: linux-kernel, netdev
In-Reply-To: <201204101042.39877.arnd@arndb.de>
On 4/10/2012 6:42 AM, Arnd Bergmann wrote:
> On Monday 09 April 2012, Chris Metcalf wrote:
>> On 4/9/2012 9:49 AM, Arnd Bergmann wrote:
>>> On Friday 06 April 2012, Chris Metcalf wrote:
>>>> This change adds support for the tilegx network driver based on the
>>>> GXIO IORPC support in the tilegx software stack, using the on-chip
>>>> mPIPE packet processing engine.
>>>>
>>>> Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
>>>> ---
>>>> drivers/net/ethernet/tile/Kconfig | 1 +
>>>> drivers/net/ethernet/tile/Makefile | 4 +-
>>>> drivers/net/ethernet/tile/tilegx.c | 2045 ++++++++++++++++++++++++++++++++++++
>>>> 3 files changed, 2048 insertions(+), 2 deletions(-)
>>>> create mode 100644 drivers/net/ethernet/tile/tilegx.c
>>>
>> The actual author would rather not publish his name (I just double-checked
>> with him).
> Hmm, it doesn't look all that bad actually, the comments I had are just for
> small details.
FWIW, the author's preference doesn't have to do with the code quality, but
for his own reasons.
>>>> +/* The actual devices. */
>>>> +static struct net_device *tile_net_devs[TILE_NET_DEVS];
>>>> +
>>>> +/* The device for a given channel. HACK: We use "32", not
>>>> + * TILE_NET_CHANNELS, because it is fairly subtle that the 5 bit
>>>> + * "idesc.channel" field never exceeds TILE_NET_CHANNELS.
>>>> + */
>>>> +static struct net_device *tile_net_devs_for_channel[32];
>>> When you need to keep a list or array of device structures in a driver, you're
>>> usually doing something very wrong. The convention is to just pass the pointer
>>> around to where you need it.
>> We need "tile_net_devs_for_channel" because we share a single hardware
>> queue for all devices, and each packet's metadata contains a "channel"
>> value which indicates the device.
>
> Ok, but please remove tile_net_devs then.
> I think a better abstraction for tile_net_devs_for_channel would be
> some interface that lets you add private data to a channel so when
> you get data from a channel, you can extract that pointer from the driver
> using the channel.
I think what would be clearer is to document how and why we are using this
additional data structure. We do access via both arrays where it is
efficient to do so, so getting rid of either of them doesn't seem right.
Let's keep the "normal" tile_net_devs[] as is, indexed by devno, and make
the tile_net_devs_for_channel[] more abstracted by using the following code:
/*
* Provide support for efficiently mapping a channel to the device
* that is using that channel, or NULL if none. The pointers in this
* array are only non-NULL when pointing to active tilegx net_device
* structures, and they are cleared before the struture itself is
* released.
*
* HACK: We use "32", not TILE_NET_CHANNELS, because it is fairly
* subtle that the 5 bit "idesc.channel" field never exceeds
* TILE_NET_CHANNELS.
*/
static struct net_device *channel_to_dev[32];
static void bychannel_add(struct net_device *dev)
{
struct tile_net_priv *priv = netdev_priv(dev);
BUG_ON(channel_to_dev[priv->channel] != NULL);
channel_to_dev[priv->channel] = dev;
}
static void bychannel_delete(struct net_device *dev)
{
struct tile_net_priv *priv = netdev_priv(dev);
channel_to_dev[priv->channel] = NULL;
}
static inline struct net_device *bychannel_lookup(int channel)
{
return channel_to_dev[channel];
}
We then call bychannel_add() in the open method, and bychannel_delete() in
the close method, so it's clear that the pointers have appropriate lifetimes.
> Don't you already have a per-channel data structure?
Nope.
>> /*
>> * The on-chip I/O hardware on tilegx is configured with VA=PA for the
>> * kernel's PA range. The low-level APIs and field names use "va" and
>> * "void *" nomenclature, to be consistent with the general notion
>> * that the addresses in question are virtualizable, but in the kernel
>> * context we are actually manipulating PA values. To allow readers
>> * of the code to understand what's happening, we direct their
>> * attention to this comment by using the following two no-op functions.
>> */
>> static inline unsigned long pa_to_tile_io_addr(phys_addr_t pa)
>> {
>> BUILD_BUG_ON(sizeof(phys_addr_t) != sizeof(unsigned long));
>> return pa;
>> }
>> static inline phys_addr_t tile_io_addr_to_pa(unsigned long tile_io_addr)
>> {
>> return tile_io_addr;
>> }
>>
>> Then the individual uses in the network driver are just things like
>> "edesc_head.va = pa_to_tile_io_addr(__pa(va))" or "va =
>> __va(tile_io_addr_to_pa((unsigned long)gxio_mpipe_idesc_get_va(idesc)))"
>> which I think is a little clearer.
> Yes, although I would probably add a typedef for tile_io_addr and pass
> the virtual address in and out these helper functions.
Good ideas, done.
> For added clarity, you could make the interface look like dma_map_single(),
> which requires adding an empty unmap() function as well -- that would
> make it obvious where that data is actually used. Why do you require
> the reverse map anyway? Normally you only need to pass a bus address to
> the device but don't need to translate that back into a virtual address
> because you already had that in the beginning.
We need the reverse map since the hardware hands us an "idesc" which has
just the tile_io_addr value in it, so we need to map it back to a va to
deal with it.
I don't think the map/unmap abstraction is too helpful here, since we're
assuming that memory is all fully-mapped, as it always is on GX.
>>>> + /* Compute the "ip checksum". */
>>>> + jsum = isum_hack + htons(s_len - eh_len) + htons(id);
>>>> + jsum = __insn_v2sadu(jsum, 0);
>>>> + jsum = __insn_v2sadu(jsum, 0);
>>>> + jsum = (0xFFFF ^ jsum);
>>>> + jh->check = jsum;
>>>> +
>>>> + /* Update the tcp "seq". */
>>>> + uh->seq = htonl(seq);
>>>> +
>>>> + /* Update some flags. */
>>>> + if (!final)
>>>> + uh->fin = uh->psh = 0;
>>>> +
>>>> + /* Compute the tcp pseudo-header checksum. */
>>>> + usum = tsum_hack + htons(s_len);
>>>> + usum = __insn_v2sadu(usum, 0);
>>>> + usum = __insn_v2sadu(usum, 0);
>>>> + uh->check = usum;
>>> Why to you open-code the ip checksum functions here? Normally the stack takes
>>> care of this by calling the functions you already provide in
>>> arch/tile/lib/checksum.c
>> If there is a way to do TSO without this, we'd be happy to hear it, but
>> it's not clear how it would be possible. We are only computing a PARTIAL
>> checksum here, and letting the hardware compute the "full" checksum.
> Sounds like you're looking for csum_partial() ;-)
Well, that's a pretty heavy-weight operation on memory. Here we're just
updating from a few values held in registers, more or less. csum_partial()
didn't seem like a good fit. What I've done is move the longto16() routine
from checksum.c to <asm/checksum.h> and rename it csum_long(), then use it
like this, e.g. for the "usum" block above:
/* Compute the tcp pseudo-header checksum. */
uh->check = csum_long(tsum_hack + htons(s_len));
--
Chris Metcalf, Tilera Corp.
http://www.tilera.com
^ permalink raw reply
* [PATCH] ks8851: Fix missing mutex_lock/unlock
From: mjr @ 2012-04-12 23:15 UTC (permalink / raw)
To: fbl; +Cc: davem, sboyd, ben, bhutchings, netdev, Matt Renzelmann
From: Matt Renzelmann <mjr@cs.wisc.edu>
All calls to ks8851_rdreg* and ks8851_wrreg* should be protected with
the driver's lock mutex. A spurious interrupt may otherwise cause a
crash. Thanks to Stephen Boyd, Flavio Leitner, and Ben Hutchings for
feedback.
Signed-off-by: Matt Renzelmann <mjr@cs.wisc.edu>
---
This modified version incorporates Ben Hutchings' bugfix by removing
the incorrect call to CIDER_REV_GET.
drivers/net/ethernet/micrel/ks8851.c | 8 ++++----
1 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index c722aa6..e5dc075 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -1418,6 +1418,7 @@ static int __devinit ks8851_probe(struct spi_device *spi)
struct net_device *ndev;
struct ks8851_net *ks;
int ret;
+ unsigned cider;
ndev = alloc_etherdev(sizeof(struct ks8851_net));
if (!ndev)
@@ -1484,8 +1485,8 @@ static int __devinit ks8851_probe(struct spi_device *spi)
ks8851_soft_reset(ks, GRR_GSR);
/* simple check for a valid chip being connected to the bus */
-
- if ((ks8851_rdreg16(ks, KS_CIDER) & ~CIDER_REV_MASK) != CIDER_ID) {
+ cider = ks8851_rdreg16(ks, KS_CIDER);
+ if ((cider & ~CIDER_REV_MASK) != CIDER_ID) {
dev_err(&spi->dev, "failed to read device ID\n");
ret = -ENODEV;
goto err_id;
@@ -1516,8 +1517,7 @@ static int __devinit ks8851_probe(struct spi_device *spi)
}
netdev_info(ndev, "revision %d, MAC %pM, IRQ %d, %s EEPROM\n",
- CIDER_REV_GET(ks8851_rdreg16(ks, KS_CIDER)),
- ndev->dev_addr, ndev->irq,
+ CIDER_REV_GET(cider), ndev->dev_addr, ndev->irq,
ks->rc_ccr & CCR_EEPROM ? "has" : "no");
return 0;
--
1.7.5.4
^ permalink raw reply related
* Re: [net-next 1/4 (V3)] net: ethtool: add the EEE support
From: Ben Hutchings @ 2012-04-12 22:26 UTC (permalink / raw)
To: Giuseppe CAVALLARO; +Cc: netdev, rayagond, davem
In-Reply-To: <1333704559-11251-2-git-send-email-peppe.cavallaro@st.com>
On Fri, 2012-04-06 at 11:29 +0200, Giuseppe CAVALLARO wrote:
> This patch adds two new functions to detect if Energy-Efficient
> Ethernet (EEE) is supported and the way to enable/disable it.
>
> As Ben said, it is certainly necessary to distinguish:
>
> a. PHY is advertising EEE from
> b. Link partner is advertising EEE
> or
> c. EEE will be used (= a && b)
>
> The logic behind this code, is that .get_eee will pass
> to the user-space if the EEE is actually used and available (so point c).
> The .set_eee should used to force the MAC to disable/enable the EEE (if
> actually supported by MAC+PHY).
[...]
What I meant is that userland should be able to find out (a), and,
*separately*, either (b) or (c). That is, there must be at least 2
separate flags for this. In fact, I explicitly requested you define
supported/advertising/lp_advertising bitmasks for EEE link modes just
like we have for autonegotiation. But you've made no substantive
changes in response to my review, aside from dropping the added field in
ethtool_cmd.
What you're submitting just isn't good enough for a generic interface,
as the ethtool API is supposed to be. It's not even a good interface to
your driver.
Ben.
--
Ben Hutchings, Staff Engineer, Solarflare
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
^ permalink raw reply
* Re: [PATCH v18 08/15] seccomp: add system call filtering using BPF
From: Kees Cook @ 2012-04-12 22:19 UTC (permalink / raw)
To: Will Drewry
Cc: linux-kernel, linux-man, linux-security-module, linux-arch,
linux-doc, kernel-hardening, netdev, x86, arnd, davem, hpa, mingo,
oleg, peterz, rdunlap, mcgrathr, tglx, luto, eparis, serge.hallyn,
djm, scarybeasts, indan, pmoore, akpm, corbet, eric.dumazet,
markus, coreyb, jmorris
In-Reply-To: <1334267284-19166-8-git-send-email-wad@chromium.org>
On Thu, Apr 12, 2012 at 2:47 PM, Will Drewry <wad@chromium.org> wrote:
> This patch adds support for seccomp mode 2. Mode 2 introduces the
> ability for unprivileged processes to install system call filtering
> policy expressed in terms of a Berkeley Packet Filter (BPF) program.
> This program will be evaluated in the kernel for each system call
> the task makes and computes a result based on data in the format
> of struct seccomp_data.
>
> A filter program may be installed by calling:
> struct sock_fprog fprog = { ... };
> ...
> prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &fprog);
>
> The return value of the filter program determines if the system call is
> allowed to proceed or denied. If the first filter program installed
> allows prctl(2) calls, then the above call may be made repeatedly
> by a task to further reduce its access to the kernel. All attached
> programs must be evaluated before a system call will be allowed to
> proceed.
>
> Filter programs will be inherited across fork/clone and execve.
> However, if the task attaching the filter is unprivileged
> (!CAP_SYS_ADMIN) the no_new_privs bit will be set on the task. This
> ensures that unprivileged tasks cannot attach filters that affect
> privileged tasks (e.g., setuid binary).
>
> There are a number of benefits to this approach. A few of which are
> as follows:
> - BPF has been exposed to userland for a long time
> - BPF optimization (and JIT'ing) are well understood
> - Userland already knows its ABI: system call numbers and desired
> arguments
> - No time-of-check-time-of-use vulnerable data accesses are possible.
> - system call arguments are loaded on access only to minimize copying
> required for system call policy decisions.
>
> Mode 2 support is restricted to architectures that enable
> HAVE_ARCH_SECCOMP_FILTER. In this patch, the primary dependency is on
> syscall_get_arguments(). The full desired scope of this feature will
> add a few minor additional requirements expressed later in this series.
> Based on discussion, SECCOMP_RET_ERRNO and SECCOMP_RET_TRACE seem to be
> the desired additional functionality.
>
> No architectures are enabled in this patch.
>
> Signed-off-by: Will Drewry <wad@chromium.org>
> Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
> Reviewed-by: Indan Zupancic <indan@nul.nu>
> Acked-by: Eric Paris <eparis@redhat.com>
Acked-by: Kees Cook <keescook@chromium.org>
--
Kees Cook
ChromeOS Security
--
To unsubscribe from this list: send the line "unsubscribe linux-security-module" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH v18 07/15] arch/x86: add syscall_get_arch to syscall.h
From: Kees Cook @ 2012-04-12 22:18 UTC (permalink / raw)
To: Will Drewry
Cc: linux-kernel, linux-man, linux-security-module, linux-arch,
linux-doc, kernel-hardening, netdev, x86, arnd, davem, hpa, mingo,
oleg, peterz, rdunlap, mcgrathr, tglx, luto, eparis, serge.hallyn,
djm, scarybeasts, indan, pmoore, akpm, corbet, eric.dumazet,
markus, coreyb, jmorris
In-Reply-To: <1334267284-19166-7-git-send-email-wad@chromium.org>
On Thu, Apr 12, 2012 at 2:47 PM, Will Drewry <wad@chromium.org> wrote:
> Add syscall_get_arch() to export the current AUDIT_ARCH_* based on system call
> entry path.
>
> Signed-off-by: Will Drewry <wad@chromium.org>
> Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
> Reviewed-by: H. Peter Anvin <hpa@zytor.com>
> Acked-by: Eric Paris <eparis@redhat.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
--
Kees Cook
ChromeOS Security
^ permalink raw reply
* Re: [PATCH v18 01/15] Add PR_{GET,SET}_NO_NEW_PRIVS to prevent execve from granting privs
From: Kees Cook @ 2012-04-12 22:17 UTC (permalink / raw)
To: Will Drewry
Cc: linux-kernel, linux-man, linux-security-module, linux-arch,
linux-doc, kernel-hardening, netdev, x86, arnd, davem, hpa, mingo,
oleg, peterz, rdunlap, mcgrathr, tglx, luto, eparis, serge.hallyn,
djm, scarybeasts, indan, pmoore, akpm, corbet, eric.dumazet,
markus, coreyb, jmorris, Andy Lutomirski
In-Reply-To: <1334267284-19166-1-git-send-email-wad@chromium.org>
On Thu, Apr 12, 2012 at 2:47 PM, Will Drewry <wad@chromium.org> wrote:
> From: Andy Lutomirski <luto@amacapital.net>
>
> With this change, calling
> prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)
> disables privilege granting operations at execve-time. For example, a
> process will not be able to execute a setuid binary to change their uid
> or gid if this bit is set. The same is true for file capabilities.
>
> Additionally, LSM_UNSAFE_NO_NEW_PRIVS is defined to ensure that
> LSMs respect the requested behavior.
>
> To determine if the NO_NEW_PRIVS bit is set, a task may call
> prctl(PR_GET_NO_NEW_PRIVS, 0, 0, 0, 0);
> It returns 1 if set and 0 if it is not set. If any of the arguments are
> non-zero, it will return -1 and set errno to -EINVAL.
> (PR_SET_NO_NEW_PRIVS behaves similarly.)
>
> This functionality is desired for the proposed seccomp filter patch
> series. By using PR_SET_NO_NEW_PRIVS, it allows a task to modify the
> system call behavior for itself and its child tasks without being
> able to impact the behavior of a more privileged task.
>
> Another potential use is making certain privileged operations
> unprivileged. For example, chroot may be considered "safe" if it cannot
> affect privileged tasks.
>
> Note, this patch causes execve to fail when PR_SET_NO_NEW_PRIVS is
> set and AppArmor is in use. It is fixed in a subsequent patch.
>
> Signed-off-by: Andy Lutomirski <luto@amacapital.net>
> Signed-off-by: Will Drewry <wad@chromium.org>
> Acked-by: Eric Paris <eparis@redhat.com>
Acked-by: Kees Cook <keescook@chromium.org>
--
Kees Cook
ChromeOS Security
^ permalink raw reply
* Re: [PATCH v18 14/15] x86: Enable HAVE_ARCH_SECCOMP_FILTER
From: Kees Cook @ 2012-04-12 22:16 UTC (permalink / raw)
To: Will Drewry
Cc: linux-kernel, linux-man, linux-security-module, linux-arch,
linux-doc, kernel-hardening, netdev, x86, arnd, davem, hpa, mingo,
oleg, peterz, rdunlap, mcgrathr, tglx, luto, eparis, serge.hallyn,
djm, scarybeasts, indan, pmoore, akpm, corbet, eric.dumazet,
markus, coreyb, jmorris
In-Reply-To: <1334267284-19166-14-git-send-email-wad@chromium.org>
On Thu, Apr 12, 2012 at 2:48 PM, Will Drewry <wad@chromium.org> wrote:
> Enable support for seccomp filter on x86:
> - syscall_get_arch()
> - syscall_get_arguments()
> - syscall_rollback()
> - syscall_set_return_value()
> - SIGSYS siginfo_t support
> - secure_computing is called from a ptrace_event()-safe context
> - secure_computing return value is checked (see below).
>
> SECCOMP_RET_TRACE and SECCOMP_RET_TRAP may result in seccomp needing to
> skip a system call without killing the process. This is done by
> returning a non-zero (-1) value from secure_computing. This change
> makes x86 respect that return value.
>
> To ensure that minimal kernel code is exposed, a non-zero return value
> results in an immediate return to user space (with an invalid syscall
> number).
>
> Signed-off-by: Will Drewry <wad@chromium.org>
> Reviewed-by: H. Peter Anvin <hpa@zytor.com>
> Acked-by: Eric Paris <eparis@redhat.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
--
Kees Cook
ChromeOS Security
^ permalink raw reply
* Re: [PATCH v18 15/15] Documentation: prctl/seccomp_filter
From: Kees Cook @ 2012-04-12 22:11 UTC (permalink / raw)
To: Will Drewry
Cc: linux-kernel, linux-man, linux-security-module, linux-arch,
linux-doc, kernel-hardening, netdev, x86, arnd, davem, hpa, mingo,
oleg, peterz, rdunlap, mcgrathr, tglx, luto, eparis, serge.hallyn,
djm, scarybeasts, indan, pmoore, akpm, corbet, eric.dumazet,
markus, coreyb, jmorris
In-Reply-To: <1334267284-19166-15-git-send-email-wad@chromium.org>
On Thu, Apr 12, 2012 at 2:48 PM, Will Drewry <wad@chromium.org> wrote:
> Documents how system call filtering using Berkeley Packet
> Filter programs works and how it may be used.
> Includes an example for x86 and a semi-generic
> example using a macro-based code generator.
>
> Acked-by: Eric Paris <eparis@redhat.com>
> Signed-off-by: Will Drewry <wad@chromium.org>
Acked-by: Kees Cook <keescook@chromium.org>
--
Kees Cook
ChromeOS Security
^ permalink raw reply
* Re: [PATCH] ks8851: Fix missing mutex_lock/unlock
From: Ben Hutchings @ 2012-04-12 22:03 UTC (permalink / raw)
To: mjr; +Cc: fbl, davem, sboyd, ben, netdev
In-Reply-To: <1334266100-9875-1-git-send-email-mjr@cs.wisc.edu>
On Thu, 2012-04-12 at 16:28 -0500, mjr@cs.wisc.edu wrote:
> From: Matt Renzelmann <mjr@cs.wisc.edu>
>
> All calls to ks8851_rdreg* and ks8851_wrreg* should be protected with
> the driver's lock mutex. A spurious interrupt may otherwise cause a
> crash. Thanks to Stephen Boyd and Flavio Leitner for feedback.
>
> Signed-off-by: Matt Renzelmann <mjr@cs.wisc.edu>
> ---
>
> Here's the next revision. This is basically Flavio Leitner's latest
> version without the mutex. Please let me know if I'm missing
> anything and I can re-submit it.
>
> drivers/net/ethernet/micrel/ks8851.c | 8 ++++----
> 1 files changed, 4 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
> index c722aa6..6528d66 100644
> --- a/drivers/net/ethernet/micrel/ks8851.c
> +++ b/drivers/net/ethernet/micrel/ks8851.c
> @@ -1418,6 +1418,7 @@ static int __devinit ks8851_probe(struct spi_device *spi)
> struct net_device *ndev;
> struct ks8851_net *ks;
> int ret;
> + unsigned cider;
>
> ndev = alloc_etherdev(sizeof(struct ks8851_net));
> if (!ndev)
> @@ -1484,8 +1485,8 @@ static int __devinit ks8851_probe(struct spi_device *spi)
> ks8851_soft_reset(ks, GRR_GSR);
>
> /* simple check for a valid chip being connected to the bus */
> -
> - if ((ks8851_rdreg16(ks, KS_CIDER) & ~CIDER_REV_MASK) != CIDER_ID) {
> + cider = CIDER_REV_GET(ks8851_rdreg16(ks, KS_CIDER));
So now 'cider' holds the revision bits.
> + if ((cider & ~CIDER_REV_MASK) != CIDER_ID) {
But this is trying to check everything *but* the revision bits.
> dev_err(&spi->dev, "failed to read device ID\n");
> ret = -ENODEV;
> goto err_id;
> @@ -1516,8 +1517,7 @@ static int __devinit ks8851_probe(struct spi_device *spi)
> }
>
> netdev_info(ndev, "revision %d, MAC %pM, IRQ %d, %s EEPROM\n",
> - CIDER_REV_GET(ks8851_rdreg16(ks, KS_CIDER)),
> - ndev->dev_addr, ndev->irq,
> + CIDER_REV_GET(cider), ndev->dev_addr, ndev->irq,
And this is trying to extract the revision bits, as if 'cider' holds the
full register value.
I think you need to remove the first CIDER_REV_GET().
Ben.
> ks->rc_ccr & CCR_EEPROM ? "has" : "no");
>
> return 0;
--
Ben Hutchings, Staff Engineer, Solarflare
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
^ permalink raw reply
* [PATCH v18 03/15] sk_run_filter: add BPF_S_ANC_SECCOMP_LD_W
From: Will Drewry @ 2012-04-12 21:47 UTC (permalink / raw)
To: linux-kernel
Cc: linux-man, linux-security-module, linux-arch, linux-doc,
kernel-hardening, netdev, x86, arnd, davem, hpa, mingo, oleg,
peterz, rdunlap, mcgrathr, tglx, luto, eparis, serge.hallyn, djm,
scarybeasts, indan, pmoore, akpm, corbet, eric.dumazet, markus,
coreyb, keescook, jmorris, Will Drewry
In-Reply-To: <1334267284-19166-1-git-send-email-wad@chromium.org>
Introduces a new BPF ancillary instruction that all LD calls will be
mapped through when skb_run_filter() is being used for seccomp BPF. The
rewriting will be done using a secondary chk_filter function that is run
after skb_chk_filter.
The code change is guarded by CONFIG_SECCOMP_FILTER which is added,
along with the seccomp_bpf_load() function later in this series.
This is based on http://lkml.org/lkml/2012/3/2/141
Suggested-by: Indan Zupancic <indan@nul.nu>
Signed-off-by: Will Drewry <wad@chromium.org>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Eric Paris <eparis@redhat.com>
v18: rebase
...
v15: include seccomp.h explicitly for when seccomp_bpf_load exists.
v14: First cut using a single additional instruction
... v13: made bpf functions generic.
---
include/linux/filter.h | 1 +
net/core/filter.c | 6 ++++++
2 files changed, 7 insertions(+), 0 deletions(-)
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 8eeb205..aaa2e80 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -228,6 +228,7 @@ enum {
BPF_S_ANC_HATYPE,
BPF_S_ANC_RXHASH,
BPF_S_ANC_CPU,
+ BPF_S_ANC_SECCOMP_LD_W,
};
#endif /* __KERNEL__ */
diff --git a/net/core/filter.c b/net/core/filter.c
index 6f755cc..491e2e1 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -38,6 +38,7 @@
#include <linux/filter.h>
#include <linux/reciprocal_div.h>
#include <linux/ratelimit.h>
+#include <linux/seccomp.h>
/* No hurry in this branch
*
@@ -352,6 +353,11 @@ load_b:
A = 0;
continue;
}
+#ifdef CONFIG_SECCOMP_FILTER
+ case BPF_S_ANC_SECCOMP_LD_W:
+ A = seccomp_bpf_load(fentry->k);
+ continue;
+#endif
default:
WARN_RATELIMIT(1, "Unknown code:%u jt:%u tf:%u k:%u\n",
fentry->code, fentry->jt,
--
1.7.5.4
^ permalink raw reply related
* [PATCH v18 15/15] Documentation: prctl/seccomp_filter
From: Will Drewry @ 2012-04-12 21:48 UTC (permalink / raw)
To: linux-kernel
Cc: linux-man, linux-security-module, linux-arch, linux-doc,
kernel-hardening, netdev, x86, arnd, davem, hpa, mingo, oleg,
peterz, rdunlap, mcgrathr, tglx, luto, eparis, serge.hallyn, djm,
scarybeasts, indan, pmoore, akpm, corbet, eric.dumazet, markus,
coreyb, keescook, jmorris, Will Drewry
In-Reply-To: <1334267284-19166-1-git-send-email-wad@chromium.org>
Documents how system call filtering using Berkeley Packet
Filter programs works and how it may be used.
Includes an example for x86 and a semi-generic
example using a macro-based code generator.
Acked-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Will Drewry <wad@chromium.org>
v18: - added acked by
- update no new privs numbers
v17: - remove @compat note and add Pitfalls section for arch checking
(keescook@chromium.org)
v16: -
v15: -
v14: - rebase/nochanges
v13: - rebase on to 88ebdda6159ffc15699f204c33feb3e431bf9bdc
v12: - comment on the ptrace_event use
- update arch support comment
- note the behavior of SECCOMP_RET_DATA when there are multiple filters
(keescook@chromium.org)
- lots of samples/ clean up incl 64-bit bpf-direct support
(markus@chromium.org)
- rebase to linux-next
v11: - overhaul return value language, updates (keescook@chromium.org)
- comment on do_exit(SIGSYS)
v10: - update for SIGSYS
- update for new seccomp_data layout
- update for ptrace option use
v9: - updated bpf-direct.c for SIGILL
v8: - add PR_SET_NO_NEW_PRIVS to the samples.
v7: - updated for all the new stuff in v7: TRAP, TRACE
- only talk about PR_SET_SECCOMP now
- fixed bad JLE32 check (coreyb@linux.vnet.ibm.com)
- adds dropper.c: a simple system call disabler
v6: - tweak the language to note the requirement of
PR_SET_NO_NEW_PRIVS being called prior to use. (luto@mit.edu)
v5: - update sample to use system call arguments
- adds a "fancy" example using a macro-based generator
- cleaned up bpf in the sample
- update docs to mention arguments
- fix prctl value (eparis@redhat.com)
- language cleanup (rdunlap@xenotime.net)
v4: - update for no_new_privs use
- minor tweaks
v3: - call out BPF <-> Berkeley Packet Filter (rdunlap@xenotime.net)
- document use of tentative always-unprivileged
- guard sample compilation for i386 and x86_64
v2: - move code to samples (corbet@lwn.net)
---
Documentation/prctl/seccomp_filter.txt | 163 ++++++++++++++++++++++
samples/Makefile | 2 +-
samples/seccomp/Makefile | 38 +++++
samples/seccomp/bpf-direct.c | 176 +++++++++++++++++++++++
samples/seccomp/bpf-fancy.c | 102 ++++++++++++++
samples/seccomp/bpf-helper.c | 89 ++++++++++++
samples/seccomp/bpf-helper.h | 238 ++++++++++++++++++++++++++++++++
samples/seccomp/dropper.c | 68 +++++++++
8 files changed, 875 insertions(+), 1 deletions(-)
create mode 100644 Documentation/prctl/seccomp_filter.txt
create mode 100644 samples/seccomp/Makefile
create mode 100644 samples/seccomp/bpf-direct.c
create mode 100644 samples/seccomp/bpf-fancy.c
create mode 100644 samples/seccomp/bpf-helper.c
create mode 100644 samples/seccomp/bpf-helper.h
create mode 100644 samples/seccomp/dropper.c
diff --git a/Documentation/prctl/seccomp_filter.txt b/Documentation/prctl/seccomp_filter.txt
new file mode 100644
index 0000000..597c3c5
--- /dev/null
+++ b/Documentation/prctl/seccomp_filter.txt
@@ -0,0 +1,163 @@
+ SECure COMPuting with filters
+ =============================
+
+Introduction
+------------
+
+A large number of system calls are exposed to every userland process
+with many of them going unused for the entire lifetime of the process.
+As system calls change and mature, bugs are found and eradicated. A
+certain subset of userland applications benefit by having a reduced set
+of available system calls. The resulting set reduces the total kernel
+surface exposed to the application. System call filtering is meant for
+use with those applications.
+
+Seccomp filtering provides a means for a process to specify a filter for
+incoming system calls. The filter is expressed as a Berkeley Packet
+Filter (BPF) program, as with socket filters, except that the data
+operated on is related to the system call being made: system call
+number and the system call arguments. This allows for expressive
+filtering of system calls using a filter program language with a long
+history of being exposed to userland and a straightforward data set.
+
+Additionally, BPF makes it impossible for users of seccomp to fall prey
+to time-of-check-time-of-use (TOCTOU) attacks that are common in system
+call interposition frameworks. BPF programs may not dereference
+pointers which constrains all filters to solely evaluating the system
+call arguments directly.
+
+What it isn't
+-------------
+
+System call filtering isn't a sandbox. It provides a clearly defined
+mechanism for minimizing the exposed kernel surface. It is meant to be
+a tool for sandbox developers to use. Beyond that, policy for logical
+behavior and information flow should be managed with a combination of
+other system hardening techniques and, potentially, an LSM of your
+choosing. Expressive, dynamic filters provide further options down this
+path (avoiding pathological sizes or selecting which of the multiplexed
+system calls in socketcall() is allowed, for instance) which could be
+construed, incorrectly, as a more complete sandboxing solution.
+
+Usage
+-----
+
+An additional seccomp mode is added and is enabled using the same
+prctl(2) call as the strict seccomp. If the architecture has
+CONFIG_HAVE_ARCH_SECCOMP_FILTER, then filters may be added as below:
+
+PR_SET_SECCOMP:
+ Now takes an additional argument which specifies a new filter
+ using a BPF program.
+ The BPF program will be executed over struct seccomp_data
+ reflecting the system call number, arguments, and other
+ metadata. The BPF program must then return one of the
+ acceptable values to inform the kernel which action should be
+ taken.
+
+ Usage:
+ prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, prog);
+
+ The 'prog' argument is a pointer to a struct sock_fprog which
+ will contain the filter program. If the program is invalid, the
+ call will return -1 and set errno to EINVAL.
+
+ If fork/clone and execve are allowed by @prog, any child
+ processes will be constrained to the same filters and system
+ call ABI as the parent.
+
+ Prior to use, the task must call prctl(PR_SET_NO_NEW_PRIVS, 1) or
+ run with CAP_SYS_ADMIN privileges in its namespace. If these are not
+ true, -EACCES will be returned. This requirement ensures that filter
+ programs cannot be applied to child processes with greater privileges
+ than the task that installed them.
+
+ Additionally, if prctl(2) is allowed by the attached filter,
+ additional filters may be layered on which will increase evaluation
+ time, but allow for further decreasing the attack surface during
+ execution of a process.
+
+The above call returns 0 on success and non-zero on error.
+
+Return values
+-------------
+A seccomp filter may return any of the following values. If multiple
+filters exist, the return value for the evaluation of a given system
+call will always use the highest precedent value. (For example,
+SECCOMP_RET_KILL will always take precedence.)
+
+In precedence order, they are:
+
+SECCOMP_RET_KILL:
+ Results in the task exiting immediately without executing the
+ system call. The exit status of the task (status & 0x7f) will
+ be SIGSYS, not SIGKILL.
+
+SECCOMP_RET_TRAP:
+ Results in the kernel sending a SIGSYS signal to the triggering
+ task without executing the system call. The kernel will
+ rollback the register state to just before the system call
+ entry such that a signal handler in the task will be able to
+ inspect the ucontext_t->uc_mcontext registers and emulate
+ system call success or failure upon return from the signal
+ handler.
+
+ The SECCOMP_RET_DATA portion of the return value will be passed
+ as si_errno.
+
+ SIGSYS triggered by seccomp will have a si_code of SYS_SECCOMP.
+
+SECCOMP_RET_ERRNO:
+ Results in the lower 16-bits of the return value being passed
+ to userland as the errno without executing the system call.
+
+SECCOMP_RET_TRACE:
+ When returned, this value will cause the kernel to attempt to
+ notify a ptrace()-based tracer prior to executing the system
+ call. If there is no tracer present, -ENOSYS is returned to
+ userland and the system call is not executed.
+
+ A tracer will be notified if it requests PTRACE_O_TRACESECCOMP
+ using ptrace(PTRACE_SETOPTIONS). The tracer will be notified
+ of a PTRACE_EVENT_SECCOMP and the SECCOMP_RET_DATA portion of
+ the BPF program return value will be available to the tracer
+ via PTRACE_GETEVENTMSG.
+
+SECCOMP_RET_ALLOW:
+ Results in the system call being executed.
+
+If multiple filters exist, the return value for the evaluation of a
+given system call will always use the highest precedent value.
+
+Precedence is only determined using the SECCOMP_RET_ACTION mask. When
+multiple filters return values of the same precedence, only the
+SECCOMP_RET_DATA from the most recently installed filter will be
+returned.
+
+Pitfalls
+--------
+
+The biggest pitfall to avoid during use is filtering on system call
+number without checking the architecture value. Why? On any
+architecture that supports multiple system call invocation conventions,
+the system call numbers may vary based on the specific invocation. If
+the numbers in the different calling conventions overlap, then checks in
+the filters may be abused. Always check the arch value!
+
+Example
+-------
+
+The samples/seccomp/ directory contains both an x86-specific example
+and a more generic example of a higher level macro interface for BPF
+program generation.
+
+
+
+Adding architecture support
+-----------------------
+
+See arch/Kconfig for the authoritative requirements. In general, if an
+architecture supports both ptrace_event and seccomp, it will be able to
+support seccomp filter with minor fixup: SIGSYS support and seccomp return
+value checking. Then it must just add CONFIG_HAVE_ARCH_SECCOMP_FILTER
+to its arch-specific Kconfig.
diff --git a/samples/Makefile b/samples/Makefile
index 2f75851..5ef08bb 100644
--- a/samples/Makefile
+++ b/samples/Makefile
@@ -1,4 +1,4 @@
# Makefile for Linux samples code
obj-$(CONFIG_SAMPLES) += kobject/ kprobes/ tracepoints/ trace_events/ \
- hw_breakpoint/ kfifo/ kdb/ hidraw/ rpmsg/
+ hw_breakpoint/ kfifo/ kdb/ hidraw/ rpmsg/ seccomp/
diff --git a/samples/seccomp/Makefile b/samples/seccomp/Makefile
new file mode 100644
index 0000000..e8fe0f5
--- /dev/null
+++ b/samples/seccomp/Makefile
@@ -0,0 +1,38 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+
+hostprogs-$(CONFIG_SECCOMP) := bpf-fancy dropper
+bpf-fancy-objs := bpf-fancy.o bpf-helper.o
+
+HOSTCFLAGS_bpf-fancy.o += -I$(objtree)/usr/include
+HOSTCFLAGS_bpf-fancy.o += -idirafter $(objtree)/include
+HOSTCFLAGS_bpf-helper.o += -I$(objtree)/usr/include
+HOSTCFLAGS_bpf-helper.o += -idirafter $(objtree)/include
+
+HOSTCFLAGS_dropper.o += -I$(objtree)/usr/include
+HOSTCFLAGS_dropper.o += -idirafter $(objtree)/include
+dropper-objs := dropper.o
+
+# bpf-direct.c is x86-only.
+ifeq ($(SRCARCH),x86)
+# List of programs to build
+hostprogs-$(CONFIG_SECCOMP) += bpf-direct
+bpf-direct-objs := bpf-direct.o
+endif
+
+HOSTCFLAGS_bpf-direct.o += -I$(objtree)/usr/include
+HOSTCFLAGS_bpf-direct.o += -idirafter $(objtree)/include
+
+# Try to match the kernel target.
+ifeq ($(CONFIG_64BIT),)
+HOSTCFLAGS_bpf-direct.o += -m32
+HOSTCFLAGS_dropper.o += -m32
+HOSTCFLAGS_bpf-helper.o += -m32
+HOSTCFLAGS_bpf-fancy.o += -m32
+HOSTLOADLIBES_bpf-direct += -m32
+HOSTLOADLIBES_bpf-fancy += -m32
+HOSTLOADLIBES_dropper += -m32
+endif
+
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
diff --git a/samples/seccomp/bpf-direct.c b/samples/seccomp/bpf-direct.c
new file mode 100644
index 0000000..26f523e
--- /dev/null
+++ b/samples/seccomp/bpf-direct.c
@@ -0,0 +1,176 @@
+/*
+ * Seccomp filter example for x86 (32-bit and 64-bit) with BPF macros
+ *
+ * Copyright (c) 2012 The Chromium OS Authors <chromium-os-dev@chromium.org>
+ * Author: Will Drewry <wad@chromium.org>
+ *
+ * The code may be used by anyone for any purpose,
+ * and can serve as a starting point for developing
+ * applications using prctl(PR_SET_SECCOMP, 2, ...).
+ */
+#define __USE_GNU 1
+#define _GNU_SOURCE 1
+
+#include <linux/types.h>
+#include <linux/filter.h>
+#include <linux/seccomp.h>
+#include <linux/unistd.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stddef.h>
+#include <string.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+
+#define syscall_arg(_n) (offsetof(struct seccomp_data, args[_n]))
+#define syscall_nr (offsetof(struct seccomp_data, nr))
+
+#if defined(__i386__)
+#define REG_RESULT REG_EAX
+#define REG_SYSCALL REG_EAX
+#define REG_ARG0 REG_EBX
+#define REG_ARG1 REG_ECX
+#define REG_ARG2 REG_EDX
+#define REG_ARG3 REG_ESI
+#define REG_ARG4 REG_EDI
+#define REG_ARG5 REG_EBP
+#elif defined(__x86_64__)
+#define REG_RESULT REG_RAX
+#define REG_SYSCALL REG_RAX
+#define REG_ARG0 REG_RDI
+#define REG_ARG1 REG_RSI
+#define REG_ARG2 REG_RDX
+#define REG_ARG3 REG_R10
+#define REG_ARG4 REG_R8
+#define REG_ARG5 REG_R9
+#else
+#error Unsupported platform
+#endif
+
+#ifndef PR_SET_NO_NEW_PRIVS
+#define PR_SET_NO_NEW_PRIVS 38
+#endif
+
+#ifndef SYS_SECCOMP
+#define SYS_SECCOMP 1
+#endif
+
+static void emulator(int nr, siginfo_t *info, void *void_context)
+{
+ ucontext_t *ctx = (ucontext_t *)(void_context);
+ int syscall;
+ char *buf;
+ ssize_t bytes;
+ size_t len;
+ if (info->si_code != SYS_SECCOMP)
+ return;
+ if (!ctx)
+ return;
+ syscall = ctx->uc_mcontext.gregs[REG_SYSCALL];
+ buf = (char *) ctx->uc_mcontext.gregs[REG_ARG1];
+ len = (size_t) ctx->uc_mcontext.gregs[REG_ARG2];
+
+ if (syscall != __NR_write)
+ return;
+ if (ctx->uc_mcontext.gregs[REG_ARG0] != STDERR_FILENO)
+ return;
+ /* Redirect stderr messages to stdout. Doesn't handle EINTR, etc */
+ ctx->uc_mcontext.gregs[REG_RESULT] = -1;
+ if (write(STDOUT_FILENO, "[ERR] ", 6) > 0) {
+ bytes = write(STDOUT_FILENO, buf, len);
+ ctx->uc_mcontext.gregs[REG_RESULT] = bytes;
+ }
+ return;
+}
+
+static int install_emulator(void)
+{
+ struct sigaction act;
+ sigset_t mask;
+ memset(&act, 0, sizeof(act));
+ sigemptyset(&mask);
+ sigaddset(&mask, SIGSYS);
+
+ act.sa_sigaction = &emulator;
+ act.sa_flags = SA_SIGINFO;
+ if (sigaction(SIGSYS, &act, NULL) < 0) {
+ perror("sigaction");
+ return -1;
+ }
+ if (sigprocmask(SIG_UNBLOCK, &mask, NULL)) {
+ perror("sigprocmask");
+ return -1;
+ }
+ return 0;
+}
+
+static int install_filter(void)
+{
+ struct sock_filter filter[] = {
+ /* Grab the system call number */
+ BPF_STMT(BPF_LD+BPF_W+BPF_ABS, syscall_nr),
+ /* Jump table for the allowed syscalls */
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_rt_sigreturn, 0, 1),
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
+#ifdef __NR_sigreturn
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_sigreturn, 0, 1),
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
+#endif
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_exit_group, 0, 1),
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_exit, 0, 1),
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_read, 1, 0),
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, __NR_write, 3, 2),
+
+ /* Check that read is only using stdin. */
+ BPF_STMT(BPF_LD+BPF_W+BPF_ABS, syscall_arg(0)),
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, STDIN_FILENO, 4, 0),
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL),
+
+ /* Check that write is only using stdout */
+ BPF_STMT(BPF_LD+BPF_W+BPF_ABS, syscall_arg(0)),
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, STDOUT_FILENO, 1, 0),
+ /* Trap attempts to write to stderr */
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, STDERR_FILENO, 1, 2),
+
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_TRAP),
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL),
+ };
+ struct sock_fprog prog = {
+ .len = (unsigned short)(sizeof(filter)/sizeof(filter[0])),
+ .filter = filter,
+ };
+
+ if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
+ perror("prctl(NO_NEW_PRIVS)");
+ return 1;
+ }
+
+
+ if (prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog)) {
+ perror("prctl");
+ return 1;
+ }
+ return 0;
+}
+
+#define payload(_c) (_c), sizeof((_c))
+int main(int argc, char **argv)
+{
+ char buf[4096];
+ ssize_t bytes = 0;
+ if (install_emulator())
+ return 1;
+ if (install_filter())
+ return 1;
+ syscall(__NR_write, STDOUT_FILENO,
+ payload("OHAI! WHAT IS YOUR NAME? "));
+ bytes = syscall(__NR_read, STDIN_FILENO, buf, sizeof(buf));
+ syscall(__NR_write, STDOUT_FILENO, payload("HELLO, "));
+ syscall(__NR_write, STDOUT_FILENO, buf, bytes);
+ syscall(__NR_write, STDERR_FILENO,
+ payload("Error message going to STDERR\n"));
+ return 0;
+}
diff --git a/samples/seccomp/bpf-fancy.c b/samples/seccomp/bpf-fancy.c
new file mode 100644
index 0000000..8eb483a
--- /dev/null
+++ b/samples/seccomp/bpf-fancy.c
@@ -0,0 +1,102 @@
+/*
+ * Seccomp BPF example using a macro-based generator.
+ *
+ * Copyright (c) 2012 The Chromium OS Authors <chromium-os-dev@chromium.org>
+ * Author: Will Drewry <wad@chromium.org>
+ *
+ * The code may be used by anyone for any purpose,
+ * and can serve as a starting point for developing
+ * applications using prctl(PR_ATTACH_SECCOMP_FILTER).
+ */
+
+#include <linux/filter.h>
+#include <linux/seccomp.h>
+#include <linux/unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+
+#include "bpf-helper.h"
+
+#ifndef PR_SET_NO_NEW_PRIVS
+#define PR_SET_NO_NEW_PRIVS 38
+#endif
+
+int main(int argc, char **argv)
+{
+ struct bpf_labels l;
+ static const char msg1[] = "Please type something: ";
+ static const char msg2[] = "You typed: ";
+ char buf[256];
+ struct sock_filter filter[] = {
+ /* TODO: LOAD_SYSCALL_NR(arch) and enforce an arch */
+ LOAD_SYSCALL_NR,
+ SYSCALL(__NR_exit, ALLOW),
+ SYSCALL(__NR_exit_group, ALLOW),
+ SYSCALL(__NR_write, JUMP(&l, write_fd)),
+ SYSCALL(__NR_read, JUMP(&l, read)),
+ DENY, /* Don't passthrough into a label */
+
+ LABEL(&l, read),
+ ARG(0),
+ JNE(STDIN_FILENO, DENY),
+ ARG(1),
+ JNE((unsigned long)buf, DENY),
+ ARG(2),
+ JGE(sizeof(buf), DENY),
+ ALLOW,
+
+ LABEL(&l, write_fd),
+ ARG(0),
+ JEQ(STDOUT_FILENO, JUMP(&l, write_buf)),
+ JEQ(STDERR_FILENO, JUMP(&l, write_buf)),
+ DENY,
+
+ LABEL(&l, write_buf),
+ ARG(1),
+ JEQ((unsigned long)msg1, JUMP(&l, msg1_len)),
+ JEQ((unsigned long)msg2, JUMP(&l, msg2_len)),
+ JEQ((unsigned long)buf, JUMP(&l, buf_len)),
+ DENY,
+
+ LABEL(&l, msg1_len),
+ ARG(2),
+ JLT(sizeof(msg1), ALLOW),
+ DENY,
+
+ LABEL(&l, msg2_len),
+ ARG(2),
+ JLT(sizeof(msg2), ALLOW),
+ DENY,
+
+ LABEL(&l, buf_len),
+ ARG(2),
+ JLT(sizeof(buf), ALLOW),
+ DENY,
+ };
+ struct sock_fprog prog = {
+ .filter = filter,
+ .len = (unsigned short)(sizeof(filter)/sizeof(filter[0])),
+ };
+ ssize_t bytes;
+ bpf_resolve_jumps(&l, filter, sizeof(filter)/sizeof(*filter));
+
+ if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
+ perror("prctl(NO_NEW_PRIVS)");
+ return 1;
+ }
+
+ if (prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog)) {
+ perror("prctl(SECCOMP)");
+ return 1;
+ }
+ syscall(__NR_write, STDOUT_FILENO, msg1, strlen(msg1));
+ bytes = syscall(__NR_read, STDIN_FILENO, buf, sizeof(buf)-1);
+ bytes = (bytes > 0 ? bytes : 0);
+ syscall(__NR_write, STDERR_FILENO, msg2, strlen(msg2));
+ syscall(__NR_write, STDERR_FILENO, buf, bytes);
+ /* Now get killed */
+ syscall(__NR_write, STDERR_FILENO, msg2, strlen(msg2)+2);
+ return 0;
+}
diff --git a/samples/seccomp/bpf-helper.c b/samples/seccomp/bpf-helper.c
new file mode 100644
index 0000000..579cfe3
--- /dev/null
+++ b/samples/seccomp/bpf-helper.c
@@ -0,0 +1,89 @@
+/*
+ * Seccomp BPF helper functions
+ *
+ * Copyright (c) 2012 The Chromium OS Authors <chromium-os-dev@chromium.org>
+ * Author: Will Drewry <wad@chromium.org>
+ *
+ * The code may be used by anyone for any purpose,
+ * and can serve as a starting point for developing
+ * applications using prctl(PR_ATTACH_SECCOMP_FILTER).
+ */
+
+#include <stdio.h>
+#include <string.h>
+
+#include "bpf-helper.h"
+
+int bpf_resolve_jumps(struct bpf_labels *labels,
+ struct sock_filter *filter, size_t count)
+{
+ struct sock_filter *begin = filter;
+ __u8 insn = count - 1;
+
+ if (count < 1)
+ return -1;
+ /*
+ * Walk it once, backwards, to build the label table and do fixups.
+ * Since backward jumps are disallowed by BPF, this is easy.
+ */
+ filter += insn;
+ for (; filter >= begin; --insn, --filter) {
+ if (filter->code != (BPF_JMP+BPF_JA))
+ continue;
+ switch ((filter->jt<<8)|filter->jf) {
+ case (JUMP_JT<<8)|JUMP_JF:
+ if (labels->labels[filter->k].location == 0xffffffff) {
+ fprintf(stderr, "Unresolved label: '%s'\n",
+ labels->labels[filter->k].label);
+ return 1;
+ }
+ filter->k = labels->labels[filter->k].location -
+ (insn + 1);
+ filter->jt = 0;
+ filter->jf = 0;
+ continue;
+ case (LABEL_JT<<8)|LABEL_JF:
+ if (labels->labels[filter->k].location != 0xffffffff) {
+ fprintf(stderr, "Duplicate label use: '%s'\n",
+ labels->labels[filter->k].label);
+ return 1;
+ }
+ labels->labels[filter->k].location = insn;
+ filter->k = 0; /* fall through */
+ filter->jt = 0;
+ filter->jf = 0;
+ continue;
+ }
+ }
+ return 0;
+}
+
+/* Simple lookup table for labels. */
+__u32 seccomp_bpf_label(struct bpf_labels *labels, const char *label)
+{
+ struct __bpf_label *begin = labels->labels, *end;
+ int id;
+ if (labels->count == 0) {
+ begin->label = label;
+ begin->location = 0xffffffff;
+ labels->count++;
+ return 0;
+ }
+ end = begin + labels->count;
+ for (id = 0; begin < end; ++begin, ++id) {
+ if (!strcmp(label, begin->label))
+ return id;
+ }
+ begin->label = label;
+ begin->location = 0xffffffff;
+ labels->count++;
+ return id;
+}
+
+void seccomp_bpf_print(struct sock_filter *filter, size_t count)
+{
+ struct sock_filter *end = filter + count;
+ for ( ; filter < end; ++filter)
+ printf("{ code=%u,jt=%u,jf=%u,k=%u },\n",
+ filter->code, filter->jt, filter->jf, filter->k);
+}
diff --git a/samples/seccomp/bpf-helper.h b/samples/seccomp/bpf-helper.h
new file mode 100644
index 0000000..643279d
--- /dev/null
+++ b/samples/seccomp/bpf-helper.h
@@ -0,0 +1,238 @@
+/*
+ * Example wrapper around BPF macros.
+ *
+ * Copyright (c) 2012 The Chromium OS Authors <chromium-os-dev@chromium.org>
+ * Author: Will Drewry <wad@chromium.org>
+ *
+ * The code may be used by anyone for any purpose,
+ * and can serve as a starting point for developing
+ * applications using prctl(PR_SET_SECCOMP, 2, ...).
+ *
+ * No guarantees are provided with respect to the correctness
+ * or functionality of this code.
+ */
+#ifndef __BPF_HELPER_H__
+#define __BPF_HELPER_H__
+
+#include <asm/bitsperlong.h> /* for __BITS_PER_LONG */
+#include <endian.h>
+#include <linux/filter.h>
+#include <linux/seccomp.h> /* for seccomp_data */
+#include <linux/types.h>
+#include <linux/unistd.h>
+#include <stddef.h>
+
+#define BPF_LABELS_MAX 256
+struct bpf_labels {
+ int count;
+ struct __bpf_label {
+ const char *label;
+ __u32 location;
+ } labels[BPF_LABELS_MAX];
+};
+
+int bpf_resolve_jumps(struct bpf_labels *labels,
+ struct sock_filter *filter, size_t count);
+__u32 seccomp_bpf_label(struct bpf_labels *labels, const char *label);
+void seccomp_bpf_print(struct sock_filter *filter, size_t count);
+
+#define JUMP_JT 0xff
+#define JUMP_JF 0xff
+#define LABEL_JT 0xfe
+#define LABEL_JF 0xfe
+
+#define ALLOW \
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW)
+#define DENY \
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL)
+#define JUMP(labels, label) \
+ BPF_JUMP(BPF_JMP+BPF_JA, FIND_LABEL((labels), (label)), \
+ JUMP_JT, JUMP_JF)
+#define LABEL(labels, label) \
+ BPF_JUMP(BPF_JMP+BPF_JA, FIND_LABEL((labels), (label)), \
+ LABEL_JT, LABEL_JF)
+#define SYSCALL(nr, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (nr), 0, 1), \
+ jt
+
+/* Lame, but just an example */
+#define FIND_LABEL(labels, label) seccomp_bpf_label((labels), #label)
+
+#define EXPAND(...) __VA_ARGS__
+/* Map all width-sensitive operations */
+#if __BITS_PER_LONG == 32
+
+#define JEQ(x, jt) JEQ32(x, EXPAND(jt))
+#define JNE(x, jt) JNE32(x, EXPAND(jt))
+#define JGT(x, jt) JGT32(x, EXPAND(jt))
+#define JLT(x, jt) JLT32(x, EXPAND(jt))
+#define JGE(x, jt) JGE32(x, EXPAND(jt))
+#define JLE(x, jt) JLE32(x, EXPAND(jt))
+#define JA(x, jt) JA32(x, EXPAND(jt))
+#define ARG(i) ARG_32(i)
+#define LO_ARG(idx) offsetof(struct seccomp_data, args[(idx)])
+
+#elif __BITS_PER_LONG == 64
+
+/* Ensure that we load the logically correct offset. */
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+#define ENDIAN(_lo, _hi) _lo, _hi
+#define LO_ARG(idx) offsetof(struct seccomp_data, args[(idx)])
+#define HI_ARG(idx) offsetof(struct seccomp_data, args[(idx)]) + sizeof(__u32)
+#elif __BYTE_ORDER == __BIG_ENDIAN
+#define ENDIAN(_lo, _hi) _hi, _lo
+#define LO_ARG(idx) offsetof(struct seccomp_data, args[(idx)]) + sizeof(__u32)
+#define HI_ARG(idx) offsetof(struct seccomp_data, args[(idx)])
+#else
+#error "Unknown endianness"
+#endif
+
+union arg64 {
+ struct {
+ __u32 ENDIAN(lo32, hi32);
+ };
+ __u64 u64;
+};
+
+#define JEQ(x, jt) \
+ JEQ64(((union arg64){.u64 = (x)}).lo32, \
+ ((union arg64){.u64 = (x)}).hi32, \
+ EXPAND(jt))
+#define JGT(x, jt) \
+ JGT64(((union arg64){.u64 = (x)}).lo32, \
+ ((union arg64){.u64 = (x)}).hi32, \
+ EXPAND(jt))
+#define JGE(x, jt) \
+ JGE64(((union arg64){.u64 = (x)}).lo32, \
+ ((union arg64){.u64 = (x)}).hi32, \
+ EXPAND(jt))
+#define JNE(x, jt) \
+ JNE64(((union arg64){.u64 = (x)}).lo32, \
+ ((union arg64){.u64 = (x)}).hi32, \
+ EXPAND(jt))
+#define JLT(x, jt) \
+ JLT64(((union arg64){.u64 = (x)}).lo32, \
+ ((union arg64){.u64 = (x)}).hi32, \
+ EXPAND(jt))
+#define JLE(x, jt) \
+ JLE64(((union arg64){.u64 = (x)}).lo32, \
+ ((union arg64){.u64 = (x)}).hi32, \
+ EXPAND(jt))
+
+#define JA(x, jt) \
+ JA64(((union arg64){.u64 = (x)}).lo32, \
+ ((union arg64){.u64 = (x)}).hi32, \
+ EXPAND(jt))
+#define ARG(i) ARG_64(i)
+
+#else
+#error __BITS_PER_LONG value unusable.
+#endif
+
+/* Loads the arg into A */
+#define ARG_32(idx) \
+ BPF_STMT(BPF_LD+BPF_W+BPF_ABS, LO_ARG(idx))
+
+/* Loads hi into A and lo in X */
+#define ARG_64(idx) \
+ BPF_STMT(BPF_LD+BPF_W+BPF_ABS, LO_ARG(idx)), \
+ BPF_STMT(BPF_ST, 0), /* lo -> M[0] */ \
+ BPF_STMT(BPF_LD+BPF_W+BPF_ABS, HI_ARG(idx)), \
+ BPF_STMT(BPF_ST, 1) /* hi -> M[1] */
+
+#define JEQ32(value, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (value), 0, 1), \
+ jt
+
+#define JNE32(value, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (value), 1, 0), \
+ jt
+
+/* Checks the lo, then swaps to check the hi. A=lo,X=hi */
+#define JEQ64(lo, hi, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \
+ BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (lo), 0, 2), \
+ BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \
+ jt, \
+ BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */
+
+#define JNE64(lo, hi, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 5, 0), \
+ BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (lo), 2, 0), \
+ BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \
+ jt, \
+ BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */
+
+#define JA32(value, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JSET+BPF_K, (value), 0, 1), \
+ jt
+
+#define JA64(lo, hi, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JSET+BPF_K, (hi), 3, 0), \
+ BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
+ BPF_JUMP(BPF_JMP+BPF_JSET+BPF_K, (lo), 0, 2), \
+ BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \
+ jt, \
+ BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */
+
+#define JGE32(value, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (value), 0, 1), \
+ jt
+
+#define JLT32(value, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (value), 1, 0), \
+ jt
+
+/* Shortcut checking if hi > arg.hi. */
+#define JGE64(lo, hi, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (hi), 4, 0), \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \
+ BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
+ BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (lo), 0, 2), \
+ BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \
+ jt, \
+ BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */
+
+#define JLT64(lo, hi, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JGE+BPF_K, (hi), 0, 4), \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \
+ BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
+ BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (lo), 2, 0), \
+ BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \
+ jt, \
+ BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */
+
+#define JGT32(value, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (value), 0, 1), \
+ jt
+
+#define JLE32(value, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (value), 1, 0), \
+ jt
+
+/* Check hi > args.hi first, then do the GE checking */
+#define JGT64(lo, hi, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (hi), 4, 0), \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 5), \
+ BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
+ BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (lo), 0, 2), \
+ BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \
+ jt, \
+ BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */
+
+#define JLE64(lo, hi, jt) \
+ BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (hi), 6, 0), \
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, (hi), 0, 3), \
+ BPF_STMT(BPF_LD+BPF_MEM, 0), /* swap in lo */ \
+ BPF_JUMP(BPF_JMP+BPF_JGT+BPF_K, (lo), 2, 0), \
+ BPF_STMT(BPF_LD+BPF_MEM, 1), /* passed: swap hi back in */ \
+ jt, \
+ BPF_STMT(BPF_LD+BPF_MEM, 1) /* failed: swap hi back in */
+
+#define LOAD_SYSCALL_NR \
+ BPF_STMT(BPF_LD+BPF_W+BPF_ABS, \
+ offsetof(struct seccomp_data, nr))
+
+#endif /* __BPF_HELPER_H__ */
diff --git a/samples/seccomp/dropper.c b/samples/seccomp/dropper.c
new file mode 100644
index 0000000..c69c347
--- /dev/null
+++ b/samples/seccomp/dropper.c
@@ -0,0 +1,68 @@
+/*
+ * Naive system call dropper built on seccomp_filter.
+ *
+ * Copyright (c) 2012 The Chromium OS Authors <chromium-os-dev@chromium.org>
+ * Author: Will Drewry <wad@chromium.org>
+ *
+ * The code may be used by anyone for any purpose,
+ * and can serve as a starting point for developing
+ * applications using prctl(PR_SET_SECCOMP, 2, ...).
+ *
+ * When run, returns the specified errno for the specified
+ * system call number against the given architecture.
+ *
+ * Run this one as root as PR_SET_NO_NEW_PRIVS is not called.
+ */
+
+#include <errno.h>
+#include <linux/audit.h>
+#include <linux/filter.h>
+#include <linux/seccomp.h>
+#include <linux/unistd.h>
+#include <stdio.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+
+static int install_filter(int nr, int arch, int error)
+{
+ struct sock_filter filter[] = {
+ BPF_STMT(BPF_LD+BPF_W+BPF_ABS,
+ (offsetof(struct seccomp_data, arch))),
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, arch, 0, 3),
+ BPF_STMT(BPF_LD+BPF_W+BPF_ABS,
+ (offsetof(struct seccomp_data, nr))),
+ BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, nr, 0, 1),
+ BPF_STMT(BPF_RET+BPF_K,
+ SECCOMP_RET_ERRNO|(error & SECCOMP_RET_DATA)),
+ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
+ };
+ struct sock_fprog prog = {
+ .len = (unsigned short)(sizeof(filter)/sizeof(filter[0])),
+ .filter = filter,
+ };
+ if (prctl(PR_SET_SECCOMP, 2, &prog)) {
+ perror("prctl");
+ return 1;
+ }
+ return 0;
+}
+
+int main(int argc, char **argv)
+{
+ if (argc < 5) {
+ fprintf(stderr, "Usage:\n"
+ "dropper <syscall_nr> <arch> <errno> <prog> [<args>]\n"
+ "Hint: AUDIT_ARCH_I386: 0x%X\n"
+ " AUDIT_ARCH_X86_64: 0x%X\n"
+ "\n", AUDIT_ARCH_I386, AUDIT_ARCH_X86_64);
+ return 1;
+ }
+ if (install_filter(strtol(argv[1], NULL, 0), strtol(argv[2], NULL, 0),
+ strtol(argv[3], NULL, 0)))
+ return 1;
+ execv(argv[4], &argv[4]);
+ printf("Failed to execv\n");
+ return 255;
+}
--
1.7.5.4
^ permalink raw reply related
* [PATCH v18 14/15] x86: Enable HAVE_ARCH_SECCOMP_FILTER
From: Will Drewry @ 2012-04-12 21:48 UTC (permalink / raw)
To: linux-kernel
Cc: linux-man, linux-security-module, linux-arch, linux-doc,
kernel-hardening, netdev, x86, arnd, davem, hpa, mingo, oleg,
peterz, rdunlap, mcgrathr, tglx, luto, eparis, serge.hallyn, djm,
scarybeasts, indan, pmoore, akpm, corbet, eric.dumazet, markus,
coreyb, keescook, jmorris, Will Drewry
In-Reply-To: <1334267284-19166-1-git-send-email-wad@chromium.org>
Enable support for seccomp filter on x86:
- syscall_get_arch()
- syscall_get_arguments()
- syscall_rollback()
- syscall_set_return_value()
- SIGSYS siginfo_t support
- secure_computing is called from a ptrace_event()-safe context
- secure_computing return value is checked (see below).
SECCOMP_RET_TRACE and SECCOMP_RET_TRAP may result in seccomp needing to
skip a system call without killing the process. This is done by
returning a non-zero (-1) value from secure_computing. This change
makes x86 respect that return value.
To ensure that minimal kernel code is exposed, a non-zero return value
results in an immediate return to user space (with an invalid syscall
number).
Signed-off-by: Will Drewry <wad@chromium.org>
Reviewed-by: H. Peter Anvin <hpa@zytor.com>
Acked-by: Eric Paris <eparis@redhat.com>
v18: rebase and tweaked change description, acked-by
v17: added reviewed by and rebased
v..: all rebases since original introduction.
---
arch/x86/Kconfig | 1 +
arch/x86/kernel/ptrace.c | 7 ++++++-
2 files changed, 7 insertions(+), 1 deletions(-)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1d14cc6..3a41c44 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -82,6 +82,7 @@ config X86
select ARCH_HAVE_NMI_SAFE_CMPXCHG
select GENERIC_IOMAP
select DCACHE_WORD_ACCESS if !DEBUG_PAGEALLOC
+ select HAVE_ARCH_SECCOMP_FILTER
config INSTRUCTION_DECODER
def_bool (KPROBES || PERF_EVENTS)
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 685845c..13b1990 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1480,7 +1480,11 @@ long syscall_trace_enter(struct pt_regs *regs)
regs->flags |= X86_EFLAGS_TF;
/* do the secure computing check first */
- secure_computing(regs->orig_ax);
+ if (secure_computing(regs->orig_ax)) {
+ /* seccomp failures shouldn't expose any additional code. */
+ ret = -1L;
+ goto out;
+ }
if (unlikely(test_thread_flag(TIF_SYSCALL_EMU)))
ret = -1L;
@@ -1505,6 +1509,7 @@ long syscall_trace_enter(struct pt_regs *regs)
regs->dx, regs->r10);
#endif
+out:
return ret ?: regs->orig_ax;
}
--
1.7.5.4
^ permalink raw reply related
* [PATCH v18 13/15] ptrace,seccomp: Add PTRACE_SECCOMP support
From: Will Drewry @ 2012-04-12 21:48 UTC (permalink / raw)
To: linux-kernel
Cc: linux-man, linux-security-module, linux-arch, linux-doc,
kernel-hardening, netdev, x86, arnd, davem, hpa, mingo, oleg,
peterz, rdunlap, mcgrathr, tglx, luto, eparis, serge.hallyn, djm,
scarybeasts, indan, pmoore, akpm, corbet, eric.dumazet, markus,
coreyb, keescook, jmorris, Will Drewry
In-Reply-To: <1334267284-19166-1-git-send-email-wad@chromium.org>
This change adds support for a new ptrace option, PTRACE_O_TRACESECCOMP,
and a new return value for seccomp BPF programs, SECCOMP_RET_TRACE.
When a tracer specifies the PTRACE_O_TRACESECCOMP ptrace option, the
tracer will be notified, via PTRACE_EVENT_SECCOMP, for any syscall that
results in a BPF program returning SECCOMP_RET_TRACE. The 16-bit
SECCOMP_RET_DATA mask of the BPF program return value will be passed as
the ptrace_message and may be retrieved using PTRACE_GETEVENTMSG.
If the subordinate process is not using seccomp filter, then no
system call notifications will occur even if the option is specified.
If there is no tracer with PTRACE_O_TRACESECCOMP when SECCOMP_RET_TRACE
is returned, the system call will not be executed and an -ENOSYS errno
will be returned to userspace.
This change adds a dependency on the system call slow path. Any future
efforts to use the system call fast path for seccomp filter will need to
address this restriction.
Signed-off-by: Will Drewry <wad@chromium.org>
Acked-by: Eric Paris <eparis@redhat.com>
v18: - rebase
- comment fatal_signal check
- acked-by
- drop secure_computing_int comment
v17: - ...
v16: - update PT_TRACE_MASK to 0xbf4 so that STOP isn't clear on SETOPTIONS call (indan@nul.nu)
[note PT_TRACE_MASK disappears in linux-next]
v15: - add audit support for non-zero return codes
- clean up style (indan@nul.nu)
v14: - rebase/nochanges
v13: - rebase on to 88ebdda6159ffc15699f204c33feb3e431bf9bdc
(Brings back a change to ptrace.c and the masks.)
v12: - rebase to linux-next
- use ptrace_event and update arch/Kconfig to mention slow-path dependency
- drop all tracehook changes and inclusion (oleg@redhat.com)
v11: - invert the logic to just make it a PTRACE_SYSCALL accelerator
(indan@nul.nu)
v10: - moved to PTRACE_O_SECCOMP / PT_TRACE_SECCOMP
v9: - n/a
v8: - guarded PTRACE_SECCOMP use with an ifdef
v7: - introduced
---
arch/Kconfig | 10 +++++-----
include/linux/ptrace.h | 5 ++++-
include/linux/seccomp.h | 1 +
kernel/seccomp.c | 16 ++++++++++++++++
4 files changed, 26 insertions(+), 6 deletions(-)
diff --git a/arch/Kconfig b/arch/Kconfig
index 66aef13..c024b3e 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -219,15 +219,15 @@ config ARCH_WANT_OLD_COMPAT_IPC
config HAVE_ARCH_SECCOMP_FILTER
bool
help
- This symbol should be selected by an architecure if it provides:
- asm/syscall.h:
+ An arch should select this symbol if it provides all of these things:
- syscall_get_arch()
- syscall_get_arguments()
- syscall_rollback()
- syscall_set_return_value()
- SIGSYS siginfo_t support must be implemented.
- __secure_computing()/secure_computing()'s return value must be
- checked, with -1 resulting in the syscall being skipped.
+ - SIGSYS siginfo_t support
+ - secure_computing is called from a ptrace_event()-safe context
+ - secure_computing return value is checked and a return value of -1
+ results in the system call being skipped immediately.
config SECCOMP_FILTER
def_bool y
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 5c71962..597e4fd 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -58,6 +58,7 @@
#define PTRACE_EVENT_EXEC 4
#define PTRACE_EVENT_VFORK_DONE 5
#define PTRACE_EVENT_EXIT 6
+#define PTRACE_EVENT_SECCOMP 7
/* Extended result codes which enabled by means other than options. */
#define PTRACE_EVENT_STOP 128
@@ -69,8 +70,9 @@
#define PTRACE_O_TRACEEXEC (1 << PTRACE_EVENT_EXEC)
#define PTRACE_O_TRACEVFORKDONE (1 << PTRACE_EVENT_VFORK_DONE)
#define PTRACE_O_TRACEEXIT (1 << PTRACE_EVENT_EXIT)
+#define PTRACE_O_TRACESECCOMP (1 << PTRACE_EVENT_SECCOMP)
-#define PTRACE_O_MASK 0x0000007f
+#define PTRACE_O_MASK 0x000000ff
#include <asm/ptrace.h>
@@ -98,6 +100,7 @@
#define PT_TRACE_EXEC PT_EVENT_FLAG(PTRACE_EVENT_EXEC)
#define PT_TRACE_VFORK_DONE PT_EVENT_FLAG(PTRACE_EVENT_VFORK_DONE)
#define PT_TRACE_EXIT PT_EVENT_FLAG(PTRACE_EVENT_EXIT)
+#define PT_TRACE_SECCOMP PT_EVENT_FLAG(PTRACE_EVENT_SECCOMP)
/* single stepping state bits (used on ARM and PA-RISC) */
#define PT_SINGLESTEP_BIT 31
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 317ccb7..5818e86 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -21,6 +21,7 @@
#define SECCOMP_RET_KILL 0x00000000U /* kill the task immediately */
#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */
#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */
+#define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */
#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */
/* Masks for the return value sections. */
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 9c38306..d9db6ec 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -24,6 +24,7 @@
#ifdef CONFIG_SECCOMP_FILTER
#include <asm/syscall.h>
#include <linux/filter.h>
+#include <linux/ptrace.h>
#include <linux/security.h>
#include <linux/slab.h>
#include <linux/tracehook.h>
@@ -408,6 +409,21 @@ int __secure_computing(int this_syscall)
/* Let the filter pass back 16 bits of data. */
seccomp_send_sigsys(this_syscall, data);
goto skip;
+ case SECCOMP_RET_TRACE:
+ /* Skip these calls if there is no tracer. */
+ if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP))
+ goto skip;
+ /* Allow the BPF to provide the event message */
+ ptrace_event(PTRACE_EVENT_SECCOMP, data);
+ /*
+ * The delivery of a fatal signal during event
+ * notification may silently skip tracer notification.
+ * Terminating the task now avoids executing a system
+ * call that may not be intended.
+ */
+ if (fatal_signal_pending(current))
+ break;
+ return 0;
case SECCOMP_RET_ALLOW:
return 0;
case SECCOMP_RET_KILL:
--
1.7.5.4
^ permalink raw reply related
* [PATCH v18 12/15] seccomp: Add SECCOMP_RET_TRAP
From: Will Drewry @ 2012-04-12 21:48 UTC (permalink / raw)
To: linux-kernel
Cc: linux-man, linux-security-module, linux-arch, linux-doc,
kernel-hardening, netdev, x86, arnd, davem, hpa, mingo, oleg,
peterz, rdunlap, mcgrathr, tglx, luto, eparis, serge.hallyn, djm,
scarybeasts, indan, pmoore, akpm, corbet, eric.dumazet, markus,
coreyb, keescook, jmorris, Will Drewry
In-Reply-To: <1334267284-19166-1-git-send-email-wad@chromium.org>
Adds a new return value to seccomp filters that triggers a SIGSYS to be
delivered with the new SYS_SECCOMP si_code.
This allows in-process system call emulation, including just specifying
an errno or cleanly dumping core, rather than just dying.
Suggested-by: Markus Gutschke <markus@chromium.org>
Suggested-by: Julien Tinnes <jln@chromium.org>
Signed-off-by: Will Drewry <wad@chromium.org>
Acked-by: Eric Paris <eparis@redhat.com>
v18: - acked-by, rebase
- don't mention secure_computing_int() anymore
v15: - use audit_seccomp/skip
- pad out error spacing; clean up switch (indan@nul.nu)
v14: - n/a
v13: - rebase on to 88ebdda6159ffc15699f204c33feb3e431bf9bdc
v12: - rebase on to linux-next
v11: - clarify the comment (indan@nul.nu)
- s/sigtrap/sigsys
v10: - use SIGSYS, syscall_get_arch, updates arch/Kconfig
note suggested-by (though original suggestion had other behaviors)
v9: - changes to SIGILL
v8: - clean up based on changes to dependent patches
v7: - introduction
---
arch/Kconfig | 14 +++++++++-----
include/asm-generic/siginfo.h | 2 +-
include/linux/seccomp.h | 1 +
kernel/seccomp.c | 26 ++++++++++++++++++++++++++
4 files changed, 37 insertions(+), 6 deletions(-)
diff --git a/arch/Kconfig b/arch/Kconfig
index beaab68..66aef13 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -219,11 +219,15 @@ config ARCH_WANT_OLD_COMPAT_IPC
config HAVE_ARCH_SECCOMP_FILTER
bool
help
- This symbol should be selected by an architecure if it provides
- asm/syscall.h, specifically syscall_get_arguments(),
- syscall_get_arch(), and syscall_set_return_value(). Additionally,
- its system call entry path must respect a return value of -1 from
- __secure_computing() and/or secure_computing().
+ This symbol should be selected by an architecure if it provides:
+ asm/syscall.h:
+ - syscall_get_arch()
+ - syscall_get_arguments()
+ - syscall_rollback()
+ - syscall_set_return_value()
+ SIGSYS siginfo_t support must be implemented.
+ __secure_computing()/secure_computing()'s return value must be
+ checked, with -1 resulting in the syscall being skipped.
config SECCOMP_FILTER
def_bool y
diff --git a/include/asm-generic/siginfo.h b/include/asm-generic/siginfo.h
index 31306f5..af5d035 100644
--- a/include/asm-generic/siginfo.h
+++ b/include/asm-generic/siginfo.h
@@ -93,7 +93,7 @@ typedef struct siginfo {
/* SIGSYS */
struct {
- void __user *_call_addr; /* calling insn */
+ void __user *_call_addr; /* calling user insn */
int _syscall; /* triggering system call number */
unsigned int _arch; /* AUDIT_ARCH_* of syscall */
} _sigsys;
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index b4ce2c8..317ccb7 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -19,6 +19,7 @@
* selects the least permissive choice.
*/
#define SECCOMP_RET_KILL 0x00000000U /* kill the task immediately */
+#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */
#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */
#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 5f78fb6..9c38306 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -332,6 +332,26 @@ void put_seccomp_filter(struct task_struct *tsk)
kfree(freeme);
}
}
+
+/**
+ * seccomp_send_sigsys - signals the task to allow in-process syscall emulation
+ * @syscall: syscall number to send to userland
+ * @reason: filter-supplied reason code to send to userland (via si_errno)
+ *
+ * Forces a SIGSYS with a code of SYS_SECCOMP and related sigsys info.
+ */
+static void seccomp_send_sigsys(int syscall, int reason)
+{
+ struct siginfo info;
+ memset(&info, 0, sizeof(info));
+ info.si_signo = SIGSYS;
+ info.si_code = SYS_SECCOMP;
+ info.si_call_addr = (void __user *)KSTK_EIP(current);
+ info.si_errno = reason;
+ info.si_arch = syscall_get_arch(current, task_pt_regs(current));
+ info.si_syscall = syscall;
+ force_sig_info(SIGSYS, &info, current);
+}
#endif /* CONFIG_SECCOMP_FILTER */
/*
@@ -382,6 +402,12 @@ int __secure_computing(int this_syscall)
syscall_set_return_value(current, task_pt_regs(current),
-data, 0);
goto skip;
+ case SECCOMP_RET_TRAP:
+ /* Show the handler the original registers. */
+ syscall_rollback(current, task_pt_regs(current));
+ /* Let the filter pass back 16 bits of data. */
+ seccomp_send_sigsys(this_syscall, data);
+ goto skip;
case SECCOMP_RET_ALLOW:
return 0;
case SECCOMP_RET_KILL:
--
1.7.5.4
^ permalink raw reply related
* [PATCH v18 11/15] signal, x86: add SIGSYS info and make it synchronous.
From: Will Drewry @ 2012-04-12 21:48 UTC (permalink / raw)
To: linux-kernel
Cc: linux-man, linux-security-module, linux-arch, linux-doc,
kernel-hardening, netdev, x86, arnd, davem, hpa, mingo, oleg,
peterz, rdunlap, mcgrathr, tglx, luto, eparis, serge.hallyn, djm,
scarybeasts, indan, pmoore, akpm, corbet, eric.dumazet, markus,
coreyb, keescook, jmorris, Will Drewry
In-Reply-To: <1334267284-19166-1-git-send-email-wad@chromium.org>
This change enables SIGSYS, defines _sigfields._sigsys, and adds
x86 (compat) arch support. _sigsys defines fields which allow
a signal handler to receive the triggering system call number,
the relevant AUDIT_ARCH_* value for that number, and the address
of the callsite.
SIGSYS is added to the SYNCHRONOUS_MASK because it is desirable for it
to have setup_frame() called for it. The goal is to ensure that
ucontext_t reflects the machine state from the time-of-syscall and not
from another signal handler.
The first consumer of SIGSYS would be seccomp filter. In particular,
a filter program could specify a new return value, SECCOMP_RET_TRAP,
which would result in the system call being denied and the calling
thread signaled. This also means that implementing arch-specific
support can be dependent upon HAVE_ARCH_SECCOMP_FILTER.
Suggested-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Will Drewry <wad@chromium.org>
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Reviewed-by: H. Peter Anvin <hpa@zytor.com>
Acked-by: Eric Paris <eparis@redhat.com>
v18: - added acked by, rebase
v17: - rebase and reviewed-by addition
v14: - rebase/nochanges
v13: - rebase on to 88ebdda6159ffc15699f204c33feb3e431bf9bdc
v12: - reworded changelog (oleg@redhat.com)
v11: - fix dropped words in the change description
- added fallback copy_siginfo support.
- added __ARCH_SIGSYS define to allow stepped arch support.
v10: - first version based on suggestion
---
arch/x86/ia32/ia32_signal.c | 4 ++++
arch/x86/include/asm/ia32.h | 6 ++++++
include/asm-generic/siginfo.h | 22 ++++++++++++++++++++++
kernel/signal.c | 9 ++++++++-
4 files changed, 40 insertions(+), 1 deletions(-)
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index a69245b..0b3f235 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -67,6 +67,10 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
switch (from->si_code >> 16) {
case __SI_FAULT >> 16:
break;
+ case __SI_SYS >> 16:
+ put_user_ex(from->si_syscall, &to->si_syscall);
+ put_user_ex(from->si_arch, &to->si_arch);
+ break;
case __SI_CHLD >> 16:
if (ia32) {
put_user_ex(from->si_utime, &to->si_utime);
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index ee52760..b04cbdb 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -144,6 +144,12 @@ typedef struct compat_siginfo {
int _band; /* POLL_IN, POLL_OUT, POLL_MSG */
int _fd;
} _sigpoll;
+
+ struct {
+ unsigned int _call_addr; /* calling insn */
+ int _syscall; /* triggering system call number */
+ unsigned int _arch; /* AUDIT_ARCH_* of syscall */
+ } _sigsys;
} _sifields;
} compat_siginfo_t;
diff --git a/include/asm-generic/siginfo.h b/include/asm-generic/siginfo.h
index 0dd4e87..31306f5 100644
--- a/include/asm-generic/siginfo.h
+++ b/include/asm-generic/siginfo.h
@@ -90,9 +90,18 @@ typedef struct siginfo {
__ARCH_SI_BAND_T _band; /* POLL_IN, POLL_OUT, POLL_MSG */
int _fd;
} _sigpoll;
+
+ /* SIGSYS */
+ struct {
+ void __user *_call_addr; /* calling insn */
+ int _syscall; /* triggering system call number */
+ unsigned int _arch; /* AUDIT_ARCH_* of syscall */
+ } _sigsys;
} _sifields;
} siginfo_t;
+/* If the arch shares siginfo, then it has SIGSYS. */
+#define __ARCH_SIGSYS
#endif
/*
@@ -116,6 +125,11 @@ typedef struct siginfo {
#define si_addr_lsb _sifields._sigfault._addr_lsb
#define si_band _sifields._sigpoll._band
#define si_fd _sifields._sigpoll._fd
+#ifdef __ARCH_SIGSYS
+#define si_call_addr _sifields._sigsys._call_addr
+#define si_syscall _sifields._sigsys._syscall
+#define si_arch _sifields._sigsys._arch
+#endif
#ifdef __KERNEL__
#define __SI_MASK 0xffff0000u
@@ -126,6 +140,7 @@ typedef struct siginfo {
#define __SI_CHLD (4 << 16)
#define __SI_RT (5 << 16)
#define __SI_MESGQ (6 << 16)
+#define __SI_SYS (7 << 16)
#define __SI_CODE(T,N) ((T) | ((N) & 0xffff))
#else
#define __SI_KILL 0
@@ -135,6 +150,7 @@ typedef struct siginfo {
#define __SI_CHLD 0
#define __SI_RT 0
#define __SI_MESGQ 0
+#define __SI_SYS 0
#define __SI_CODE(T,N) (N)
#endif
@@ -232,6 +248,12 @@ typedef struct siginfo {
#define NSIGPOLL 6
/*
+ * SIGSYS si_codes
+ */
+#define SYS_SECCOMP (__SI_SYS|1) /* seccomp triggered */
+#define NSIGSYS 1
+
+/*
* sigevent definitions
*
* It seems likely that SIGEV_THREAD will have to be handled from
diff --git a/kernel/signal.c b/kernel/signal.c
index 17afcaf..1a006b5 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -160,7 +160,7 @@ void recalc_sigpending(void)
#define SYNCHRONOUS_MASK \
(sigmask(SIGSEGV) | sigmask(SIGBUS) | sigmask(SIGILL) | \
- sigmask(SIGTRAP) | sigmask(SIGFPE))
+ sigmask(SIGTRAP) | sigmask(SIGFPE) | sigmask(SIGSYS))
int next_signal(struct sigpending *pending, sigset_t *mask)
{
@@ -2706,6 +2706,13 @@ int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from)
err |= __put_user(from->si_uid, &to->si_uid);
err |= __put_user(from->si_ptr, &to->si_ptr);
break;
+#ifdef __ARCH_SIGSYS
+ case __SI_SYS:
+ err |= __put_user(from->si_call_addr, &to->si_call_addr);
+ err |= __put_user(from->si_syscall, &to->si_syscall);
+ err |= __put_user(from->si_arch, &to->si_arch);
+ break;
+#endif
default: /* this is just in case for now ... */
err |= __put_user(from->si_pid, &to->si_pid);
err |= __put_user(from->si_uid, &to->si_uid);
--
1.7.5.4
^ permalink raw reply related
* [PATCH v18 10/15] seccomp: add SECCOMP_RET_ERRNO
From: Will Drewry @ 2012-04-12 21:47 UTC (permalink / raw)
To: linux-kernel
Cc: linux-man, linux-security-module, linux-arch, linux-doc,
kernel-hardening, netdev, x86, arnd, davem, hpa, mingo, oleg,
peterz, rdunlap, mcgrathr, tglx, luto, eparis, serge.hallyn, djm,
scarybeasts, indan, pmoore, akpm, corbet, eric.dumazet, markus,
coreyb, keescook, jmorris, Will Drewry
In-Reply-To: <1334267284-19166-1-git-send-email-wad@chromium.org>
This change adds the SECCOMP_RET_ERRNO as a valid return value from a
seccomp filter. Additionally, it makes the first use of the lower
16-bits for storing a filter-supplied errno. 16-bits is more than
enough for the errno-base.h calls.
Returning errors instead of immediately terminating processes that
violate seccomp policy allow for broader use of this functionality
for kernel attack surface reduction. For example, a linux container
could maintain a whitelist of pre-existing system calls but drop
all new ones with errnos. This would keep a logically static attack
surface while providing errnos that may allow for graceful failure
without the downside of do_exit() on a bad call.
This change also changes the signature of __secure_computing. It
appears the only direct caller is the arm entry code and it clobbers
any possible return value (register) immediately.
Signed-off-by: Will Drewry <wad@chromium.org>
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Eric Paris <eparis@redhat.com>
v18: - fix up comments and rebase
- fix bad var name which was fixed in later revs
- remove _int() and just change the __secure_computing signature
v16-v17: ...
v15: - use audit_seccomp and add a skip label. (eparis@redhat.com)
- clean up and pad out return codes (indan@nul.nu)
v14: - no change/rebase
v13: - rebase on to 88ebdda6159ffc15699f204c33feb3e431bf9bdc
v12: - move to WARN_ON if filter is NULL
(oleg@redhat.com, luto@mit.edu, keescook@chromium.org)
- return immediately for filter==NULL (keescook@chromium.org)
- change evaluation to only compare the ACTION so that layered
errnos don't result in the lowest one being returned.
(keeschook@chromium.org)
v11: - check for NULL filter (keescook@chromium.org)
v10: - change loaders to fn
v9: - n/a
v8: - update Kconfig to note new need for syscall_set_return_value.
- reordered such that TRAP behavior follows on later.
- made the for loop a little less indent-y
v7: - introduced
---
arch/Kconfig | 6 ++++--
include/linux/seccomp.h | 10 ++++++----
kernel/seccomp.c | 42 ++++++++++++++++++++++++++++++++----------
3 files changed, 42 insertions(+), 16 deletions(-)
diff --git a/arch/Kconfig b/arch/Kconfig
index 91c2c73..beaab68 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -220,8 +220,10 @@ config HAVE_ARCH_SECCOMP_FILTER
bool
help
This symbol should be selected by an architecure if it provides
- asm/syscall.h, specifically syscall_get_arguments() and
- syscall_get_arch().
+ asm/syscall.h, specifically syscall_get_arguments(),
+ syscall_get_arch(), and syscall_set_return_value(). Additionally,
+ its system call entry path must respect a return value of -1 from
+ __secure_computing() and/or secure_computing().
config SECCOMP_FILTER
def_bool y
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 86bb68f..b4ce2c8 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -12,13 +12,14 @@
/*
* All BPF programs must return a 32-bit value.
- * The bottom 16-bits are reserved for future use.
+ * The bottom 16-bits are for optional return data.
* The upper 16-bits are ordered from least permissive values to most.
*
* The ordering ensures that a min_t() over composed return values always
* selects the least permissive choice.
*/
#define SECCOMP_RET_KILL 0x00000000U /* kill the task immediately */
+#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */
#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */
/* Masks for the return value sections. */
@@ -64,11 +65,12 @@ struct seccomp {
struct seccomp_filter *filter;
};
-extern void __secure_computing(int);
-static inline void secure_computing(int this_syscall)
+extern int __secure_computing(int);
+static inline int secure_computing(int this_syscall)
{
if (unlikely(test_thread_flag(TIF_SECCOMP)))
- __secure_computing(this_syscall);
+ return __secure_computing(this_syscall);
+ return 0;
}
extern long prctl_get_seccomp(void);
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 0f7c709..5f78fb6 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -199,15 +199,20 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
static u32 seccomp_run_filters(int syscall)
{
struct seccomp_filter *f;
- u32 ret = SECCOMP_RET_KILL;
+ u32 ret = SECCOMP_RET_ALLOW;
+
+ /* Ensure unexpected behavior doesn't result in failing open. */
+ if (WARN_ON(current->seccomp.filter == NULL))
+ return SECCOMP_RET_KILL;
+
/*
* All filters in the list are evaluated and the lowest BPF return
- * value always takes priority.
+ * value always takes priority (ignoring the DATA).
*/
for (f = current->seccomp.filter; f; f = f->prev) {
- ret = sk_run_filter(NULL, f->insns);
- if (ret != SECCOMP_RET_ALLOW)
- break;
+ u32 cur_ret = sk_run_filter(NULL, f->insns);
+ if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
+ ret = cur_ret;
}
return ret;
}
@@ -346,11 +351,13 @@ static int mode1_syscalls_32[] = {
};
#endif
-void __secure_computing(int this_syscall)
+int __secure_computing(int this_syscall)
{
int mode = current->seccomp.mode;
int exit_sig = 0;
int *syscall;
+ u32 ret = SECCOMP_RET_KILL;
+ int data;
switch (mode) {
case SECCOMP_MODE_STRICT:
@@ -361,14 +368,26 @@ void __secure_computing(int this_syscall)
#endif
do {
if (*syscall == this_syscall)
- return;
+ return 0;
} while (*++syscall);
exit_sig = SIGKILL;
break;
#ifdef CONFIG_SECCOMP_FILTER
case SECCOMP_MODE_FILTER:
- if (seccomp_run_filters(this_syscall) == SECCOMP_RET_ALLOW)
- return;
+ ret = seccomp_run_filters(this_syscall);
+ data = ret & SECCOMP_RET_DATA;
+ switch (ret & SECCOMP_RET_ACTION) {
+ case SECCOMP_RET_ERRNO:
+ /* Set the low-order 16-bits as a errno. */
+ syscall_set_return_value(current, task_pt_regs(current),
+ -data, 0);
+ goto skip;
+ case SECCOMP_RET_ALLOW:
+ return 0;
+ case SECCOMP_RET_KILL:
+ default:
+ break;
+ }
exit_sig = SIGSYS;
break;
#endif
@@ -379,8 +398,11 @@ void __secure_computing(int this_syscall)
#ifdef SECCOMP_DEBUG
dump_stack();
#endif
- audit_seccomp(this_syscall, exit_code, SECCOMP_RET_KILL);
+ audit_seccomp(this_syscall, exit_sig, ret);
do_exit(exit_sig);
+skip:
+ audit_seccomp(this_syscall, exit_sig, ret);
+ return -1;
}
long prctl_get_seccomp(void)
--
1.7.5.4
^ 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