* [PATCH v2 net-next 2/2] net: stmmac: Add support for DWMAC5 and implement Safety Features
From: Jose Abreu @ 2018-03-29 9:40 UTC (permalink / raw)
To: netdev
Cc: Jose Abreu, David S. Miller, Joao Pinto, Giuseppe Cavallaro,
Alexandre Torgue, Andrew Lunn
In-Reply-To: <cover.1522315930.git.joabreu@synopsys.com>
This adds initial suport for DWMAC5 and implements the Automotive Safety
Package which is available from core version 5.10.
The Automotive Safety Pacakge (also called Safety Features) offers us
with error protection in the core by implementing ECC Protection in
memories, on-chip data path parity protection, FSM parity and timeout
protection and Application/CSR interface timeout protection.
In case of an uncorrectable error we call stmmac_global_err() and
reconfigure the whole core.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: Andrew Lunn <andrew@lunn.ch>
---
drivers/net/ethernet/stmicro/stmmac/Makefile | 2 +-
drivers/net/ethernet/stmicro/stmmac/common.h | 22 ++
drivers/net/ethernet/stmicro/stmmac/dwmac4.h | 4 +
drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 39 ++-
drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c | 6 +
drivers/net/ethernet/stmicro/stmmac/dwmac5.c | 298 +++++++++++++++++++++
drivers/net/ethernet/stmicro/stmmac/dwmac5.h | 52 ++++
drivers/net/ethernet/stmicro/stmmac/stmmac.h | 1 +
.../net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 39 ++-
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 34 +++
10 files changed, 494 insertions(+), 3 deletions(-)
create mode 100644 drivers/net/ethernet/stmicro/stmmac/dwmac5.c
create mode 100644 drivers/net/ethernet/stmicro/stmmac/dwmac5.h
diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index ff3f83b8..972e4ef 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -4,7 +4,7 @@ stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o ring_mode.o \
chain_mode.o dwmac_lib.o dwmac1000_core.o dwmac1000_dma.o \
dwmac100_core.o dwmac100_dma.o enh_desc.o norm_desc.o \
mmc_core.o stmmac_hwtstamp.o stmmac_ptp.o dwmac4_descs.o \
- dwmac4_dma.o dwmac4_lib.o dwmac4_core.o $(stmmac-y)
+ dwmac4_dma.o dwmac4_lib.o dwmac4_core.o dwmac5.o $(stmmac-y)
# Ordering matters. Generic driver must be last.
obj-$(CONFIG_STMMAC_PLATFORM) += stmmac-platform.o
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 2ffe76c..ad2388a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -38,6 +38,8 @@
#define DWMAC_CORE_3_40 0x34
#define DWMAC_CORE_3_50 0x35
#define DWMAC_CORE_4_00 0x40
+#define DWMAC_CORE_5_00 0x50
+#define DWMAC_CORE_5_10 0x51
#define STMMAC_CHAN0 0 /* Always supported and default for all chips */
/* These need to be power of two, and >= 4 */
@@ -174,6 +176,17 @@ struct stmmac_extra_stats {
unsigned long tx_tso_nfrags;
};
+/* Safety Feature statistics exposed by ethtool */
+struct stmmac_safety_stats {
+ unsigned long mac_errors[32];
+ unsigned long mtl_errors[32];
+ unsigned long dma_errors[32];
+};
+
+/* Number of fields in Safety Stats */
+#define STMMAC_SAFETY_FEAT_SIZE \
+ (sizeof(struct stmmac_safety_stats) / sizeof(unsigned long))
+
/* CSR Frequency Access Defines*/
#define CSR_F_35M 35000000
#define CSR_F_60M 60000000
@@ -336,6 +349,8 @@ struct dma_features {
/* TX and RX FIFO sizes */
unsigned int tx_fifo_size;
unsigned int rx_fifo_size;
+ /* Automotive Safety Package */
+ unsigned int asp;
};
/* GMAC TX FIFO is 8K, Rx FIFO is 16K */
@@ -532,6 +547,13 @@ struct stmmac_ops {
bool loopback);
void (*pcs_rane)(void __iomem *ioaddr, bool restart);
void (*pcs_get_adv_lp)(void __iomem *ioaddr, struct rgmii_adv *adv);
+ /* Safety Features */
+ int (*safety_feat_config)(void __iomem *ioaddr, unsigned int asp);
+ bool (*safety_feat_irq_status)(struct net_device *ndev,
+ void __iomem *ioaddr, unsigned int asp,
+ struct stmmac_safety_stats *stats);
+ const char *(*safety_feat_dump)(struct stmmac_safety_stats *stats,
+ int index, unsigned long *count);
};
/* PTP and HW Timer helpers */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
index 7761a26e..c7bff59 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -39,6 +39,7 @@
#define GMAC_HW_FEATURE0 0x0000011c
#define GMAC_HW_FEATURE1 0x00000120
#define GMAC_HW_FEATURE2 0x00000124
+#define GMAC_HW_FEATURE3 0x00000128
#define GMAC_MDIO_ADDR 0x00000200
#define GMAC_MDIO_DATA 0x00000204
#define GMAC_ADDR_HIGH(reg) (0x300 + reg * 8)
@@ -192,6 +193,9 @@ enum power_event {
#define GMAC_HW_FEAT_TXQCNT GENMASK(9, 6)
#define GMAC_HW_FEAT_RXQCNT GENMASK(3, 0)
+/* MAC HW features3 bitmap */
+#define GMAC_HW_FEAT_ASP GENMASK(29, 28)
+
/* MAC HW ADDR regs */
#define GMAC_HI_DCS GENMASK(18, 16)
#define GMAC_HI_DCS_SHIFT 16
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 46b9ae2..a3af92e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -20,6 +20,7 @@
#include <net/dsa.h>
#include "stmmac_pcs.h"
#include "dwmac4.h"
+#include "dwmac5.h"
static void dwmac4_core_init(struct mac_device_info *hw,
struct net_device *dev)
@@ -768,6 +769,40 @@ static const struct stmmac_ops dwmac410_ops = {
.set_filter = dwmac4_set_filter,
};
+static const struct stmmac_ops dwmac510_ops = {
+ .core_init = dwmac4_core_init,
+ .set_mac = stmmac_dwmac4_set_mac,
+ .rx_ipc = dwmac4_rx_ipc_enable,
+ .rx_queue_enable = dwmac4_rx_queue_enable,
+ .rx_queue_prio = dwmac4_rx_queue_priority,
+ .tx_queue_prio = dwmac4_tx_queue_priority,
+ .rx_queue_routing = dwmac4_rx_queue_routing,
+ .prog_mtl_rx_algorithms = dwmac4_prog_mtl_rx_algorithms,
+ .prog_mtl_tx_algorithms = dwmac4_prog_mtl_tx_algorithms,
+ .set_mtl_tx_queue_weight = dwmac4_set_mtl_tx_queue_weight,
+ .map_mtl_to_dma = dwmac4_map_mtl_dma,
+ .config_cbs = dwmac4_config_cbs,
+ .dump_regs = dwmac4_dump_regs,
+ .host_irq_status = dwmac4_irq_status,
+ .host_mtl_irq_status = dwmac4_irq_mtl_status,
+ .flow_ctrl = dwmac4_flow_ctrl,
+ .pmt = dwmac4_pmt,
+ .set_umac_addr = dwmac4_set_umac_addr,
+ .get_umac_addr = dwmac4_get_umac_addr,
+ .set_eee_mode = dwmac4_set_eee_mode,
+ .reset_eee_mode = dwmac4_reset_eee_mode,
+ .set_eee_timer = dwmac4_set_eee_timer,
+ .set_eee_pls = dwmac4_set_eee_pls,
+ .pcs_ctrl_ane = dwmac4_ctrl_ane,
+ .pcs_rane = dwmac4_rane,
+ .pcs_get_adv_lp = dwmac4_get_adv_lp,
+ .debug = dwmac4_debug,
+ .set_filter = dwmac4_set_filter,
+ .safety_feat_config = dwmac5_safety_feat_config,
+ .safety_feat_irq_status = dwmac5_safety_feat_irq_status,
+ .safety_feat_dump = dwmac5_safety_feat_dump,
+};
+
struct mac_device_info *dwmac4_setup(void __iomem *ioaddr, int mcbins,
int perfect_uc_entries, int *synopsys_id)
{
@@ -808,7 +843,9 @@ struct mac_device_info *dwmac4_setup(void __iomem *ioaddr, int mcbins,
else
mac->dma = &dwmac4_dma_ops;
- if (*synopsys_id >= DWMAC_CORE_4_00)
+ if (*synopsys_id >= DWMAC_CORE_5_10)
+ mac->mac = &dwmac510_ops;
+ else if (*synopsys_id >= DWMAC_CORE_4_00)
mac->mac = &dwmac410_ops;
else
mac->mac = &dwmac4_ops;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index c110f68..d37d457 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -373,6 +373,12 @@ static void dwmac4_get_hw_feature(void __iomem *ioaddr,
/* IEEE 1588-2002 */
dma_cap->time_stamp = 0;
+
+ /* MAC HW feature3 */
+ hw_cap = readl(ioaddr + GMAC_HW_FEATURE3);
+
+ /* 5.10 Features */
+ dma_cap->asp = (hw_cap & GMAC_HW_FEAT_ASP) >> 28;
}
/* Enable/disable TSO feature and set MSS */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
new file mode 100644
index 0000000..860de39
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
@@ -0,0 +1,298 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+// Copyright (c) 2017 Synopsys, Inc. and/or its affiliates.
+// stmmac Support for 5.xx Ethernet QoS cores
+
+#include <linux/bitops.h>
+#include <linux/iopoll.h>
+#include "common.h"
+#include "dwmac4.h"
+#include "dwmac5.h"
+
+struct dwmac5_error_desc {
+ bool valid;
+ const char *desc;
+ const char *detailed_desc;
+};
+
+#define STAT_OFF(field) offsetof(struct stmmac_safety_stats, field)
+
+static void dwmac5_log_error(struct net_device *ndev, u32 value, bool corr,
+ const char *module_name, const struct dwmac5_error_desc *desc,
+ unsigned long field_offset, struct stmmac_safety_stats *stats)
+{
+ unsigned long loc, mask;
+ u8 *bptr = (u8 *)stats;
+ unsigned long *ptr;
+
+ ptr = (unsigned long *)(bptr + field_offset);
+
+ mask = value;
+ for_each_set_bit(loc, &mask, 32) {
+ netdev_err(ndev, "Found %s error in %s: '%s: %s'\n", corr ?
+ "correctable" : "uncorrectable", module_name,
+ desc[loc].desc, desc[loc].detailed_desc);
+
+ /* Update counters */
+ ptr[loc]++;
+ }
+}
+
+static const struct dwmac5_error_desc dwmac5_mac_errors[32]= {
+ { true, "ATPES", "Application Transmit Interface Parity Check Error" },
+ { true, "TPES", "TSO Data Path Parity Check Error" },
+ { true, "RDPES", "Read Descriptor Parity Check Error" },
+ { true, "MPES", "MTL Data Path Parity Check Error" },
+ { true, "MTSPES", "MTL TX Status Data Path Parity Check Error" },
+ { true, "ARPES", "Application Receive Interface Data Path Parity Check Error" },
+ { true, "CWPES", "CSR Write Data Path Parity Check Error" },
+ { true, "ASRPES", "AXI Slave Read Data Path Parity Check Error" },
+ { true, "TTES", "TX FSM Timeout Error" },
+ { true, "RTES", "RX FSM Timeout Error" },
+ { true, "CTES", "CSR FSM Timeout Error" },
+ { true, "ATES", "APP FSM Timeout Error" },
+ { true, "PTES", "PTP FSM Timeout Error" },
+ { true, "T125ES", "TX125 FSM Timeout Error" },
+ { true, "R125ES", "RX125 FSM Timeout Error" },
+ { true, "RVCTES", "REV MDC FSM Timeout Error" },
+ { true, "MSTTES", "Master Read/Write Timeout Error" },
+ { true, "SLVTES", "Slave Read/Write Timeout Error" },
+ { true, "ATITES", "Application Timeout on ATI Interface Error" },
+ { true, "ARITES", "Application Timeout on ARI Interface Error" },
+ { false, "UNKNOWN", "Unknown Error" }, /* 20 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 21 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 22 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 23 */
+ { true, "FSMPES", "FSM State Parity Error" },
+ { false, "UNKNOWN", "Unknown Error" }, /* 25 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 26 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 27 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 28 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 29 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 30 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 31 */
+};
+
+static void dwmac5_handle_mac_err(struct net_device *ndev,
+ void __iomem *ioaddr, bool correctable,
+ struct stmmac_safety_stats *stats)
+{
+ u32 value;
+
+ value = readl(ioaddr + MAC_DPP_FSM_INT_STATUS);
+ writel(value, ioaddr + MAC_DPP_FSM_INT_STATUS);
+
+ dwmac5_log_error(ndev, value, correctable, "MAC", dwmac5_mac_errors,
+ STAT_OFF(mac_errors), stats);
+}
+
+static const struct dwmac5_error_desc dwmac5_mtl_errors[32]= {
+ { true, "TXCES", "MTL TX Memory Error" },
+ { true, "TXAMS", "MTL TX Memory Address Mismatch Error" },
+ { true, "TXUES", "MTL TX Memory Error" },
+ { false, "UNKNOWN", "Unknown Error" }, /* 3 */
+ { true, "RXCES", "MTL RX Memory Error" },
+ { true, "RXAMS", "MTL RX Memory Address Mismatch Error" },
+ { true, "RXUES", "MTL RX Memory Error" },
+ { false, "UNKNOWN", "Unknown Error" }, /* 7 */
+ { true, "ECES", "MTL EST Memory Error" },
+ { true, "EAMS", "MTL EST Memory Address Mismatch Error" },
+ { true, "EUES", "MTL EST Memory Error" },
+ { false, "UNKNOWN", "Unknown Error" }, /* 11 */
+ { true, "RPCES", "MTL RX Parser Memory Error" },
+ { true, "RPAMS", "MTL RX Parser Memory Address Mismatch Error" },
+ { true, "RPUES", "MTL RX Parser Memory Error" },
+ { false, "UNKNOWN", "Unknown Error" }, /* 15 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 16 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 17 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 18 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 19 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 20 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 21 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 22 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 23 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 24 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 25 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 26 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 27 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 28 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 29 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 30 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 31 */
+};
+
+static void dwmac5_handle_mtl_err(struct net_device *ndev,
+ void __iomem *ioaddr, bool correctable,
+ struct stmmac_safety_stats *stats)
+{
+ u32 value;
+
+ value = readl(ioaddr + MTL_ECC_INT_STATUS);
+ writel(value, ioaddr + MTL_ECC_INT_STATUS);
+
+ dwmac5_log_error(ndev, value, correctable, "MTL", dwmac5_mtl_errors,
+ STAT_OFF(mtl_errors), stats);
+}
+
+static const struct dwmac5_error_desc dwmac5_dma_errors[32]= {
+ { true, "TCES", "DMA TSO Memory Error" },
+ { true, "TAMS", "DMA TSO Memory Address Mismatch Error" },
+ { true, "TUES", "DMA TSO Memory Error" },
+ { false, "UNKNOWN", "Unknown Error" }, /* 3 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 4 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 5 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 6 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 7 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 8 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 9 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 10 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 11 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 12 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 13 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 14 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 15 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 16 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 17 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 18 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 19 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 20 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 21 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 22 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 23 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 24 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 25 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 26 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 27 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 28 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 29 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 30 */
+ { false, "UNKNOWN", "Unknown Error" }, /* 31 */
+};
+
+static void dwmac5_handle_dma_err(struct net_device *ndev,
+ void __iomem *ioaddr, bool correctable,
+ struct stmmac_safety_stats *stats)
+{
+ u32 value;
+
+ value = readl(ioaddr + DMA_ECC_INT_STATUS);
+ writel(value, ioaddr + DMA_ECC_INT_STATUS);
+
+ dwmac5_log_error(ndev, value, correctable, "DMA", dwmac5_dma_errors,
+ STAT_OFF(dma_errors), stats);
+}
+
+int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp)
+{
+ u32 value;
+
+ if (!asp)
+ return -EINVAL;
+
+ /* 1. Enable Safety Features */
+ value = readl(ioaddr + MTL_ECC_CONTROL);
+ value |= TSOEE; /* TSO ECC */
+ value |= MRXPEE; /* MTL RX Parser ECC */
+ value |= MESTEE; /* MTL EST ECC */
+ value |= MRXEE; /* MTL RX FIFO ECC */
+ value |= MTXEE; /* MTL TX FIFO ECC */
+ writel(value, ioaddr + MTL_ECC_CONTROL);
+
+ /* 2. Enable MTL Safety Interrupts */
+ value = readl(ioaddr + MTL_ECC_INT_ENABLE);
+ value |= RPCEIE; /* RX Parser Memory Correctable Error */
+ value |= ECEIE; /* EST Memory Correctable Error */
+ value |= RXCEIE; /* RX Memory Correctable Error */
+ value |= TXCEIE; /* TX Memory Correctable Error */
+ writel(value, ioaddr + MTL_ECC_INT_ENABLE);
+
+ /* 3. Enable DMA Safety Interrupts */
+ value = readl(ioaddr + DMA_ECC_INT_ENABLE);
+ value |= TCEIE; /* TSO Memory Correctable Error */
+ writel(value, ioaddr + DMA_ECC_INT_ENABLE);
+
+ /* Only ECC Protection for External Memory feature is selected */
+ if (asp <= 0x1)
+ return 0;
+
+ /* 5. Enable Parity and Timeout for FSM */
+ value = readl(ioaddr + MAC_FSM_CONTROL);
+ value |= PRTYEN; /* FSM Parity Feature */
+ value |= TMOUTEN; /* FSM Timeout Feature */
+ writel(value, ioaddr + MAC_FSM_CONTROL);
+
+ /* 4. Enable Data Parity Protection */
+ value = readl(ioaddr + MTL_DPP_CONTROL);
+ value |= EDPP;
+ writel(value, ioaddr + MTL_DPP_CONTROL);
+
+ /*
+ * All the Automotive Safety features are selected without the "Parity
+ * Port Enable for external interface" feature.
+ */
+ if (asp <= 0x2)
+ return 0;
+
+ value |= EPSI;
+ writel(value, ioaddr + MTL_DPP_CONTROL);
+ return 0;
+}
+
+bool dwmac5_safety_feat_irq_status(struct net_device *ndev,
+ void __iomem *ioaddr, unsigned int asp,
+ struct stmmac_safety_stats *stats)
+{
+ bool ret = false, err, corr;
+ u32 mtl, dma;
+
+ if (!asp)
+ return false;
+
+ mtl = readl(ioaddr + MTL_SAFETY_INT_STATUS);
+ dma = readl(ioaddr + DMA_SAFETY_INT_STATUS);
+
+ err = (mtl & MCSIS) || (dma & MCSIS);
+ corr = false;
+ if (err) {
+ dwmac5_handle_mac_err(ndev, ioaddr, corr, stats);
+ ret |= !corr;
+ }
+
+ err = (mtl & (MEUIS | MECIS)) || (dma & (MSUIS | MSCIS));
+ corr = (mtl & MECIS) || (dma & MSCIS);
+ if (err) {
+ dwmac5_handle_mtl_err(ndev, ioaddr, corr, stats);
+ ret |= !corr;
+ }
+
+ err = dma & (DEUIS | DECIS);
+ corr = dma & DECIS;
+ if (err) {
+ dwmac5_handle_dma_err(ndev, ioaddr, corr, stats);
+ ret |= !corr;
+ }
+
+ return ret;
+}
+
+static const struct dwmac5_error {
+ const struct dwmac5_error_desc *desc;
+} dwmac5_all_errors[] = {
+ { dwmac5_mac_errors },
+ { dwmac5_mtl_errors },
+ { dwmac5_dma_errors },
+};
+
+const char *dwmac5_safety_feat_dump(struct stmmac_safety_stats *stats,
+ int index, unsigned long *count)
+{
+ int module = index / 32, offset = index % 32;
+ unsigned long *ptr = (unsigned long *)stats;
+
+ if (module >= ARRAY_SIZE(dwmac5_all_errors))
+ return NULL;
+ if (!dwmac5_all_errors[module].desc[offset].valid)
+ return NULL;
+ if (count)
+ *count = *(ptr + index);
+ return dwmac5_all_errors[module].desc[offset].desc;
+}
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
new file mode 100644
index 0000000..a0d2c44
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+// Copyright (c) 2017 Synopsys, Inc. and/or its affiliates.
+// stmmac Support for 5.xx Ethernet QoS cores
+
+#ifndef __DWMAC5_H__
+#define __DWMAC5_H__
+
+#define MAC_DPP_FSM_INT_STATUS 0x00000140
+#define MAC_AXI_SLV_DPE_ADDR_STATUS 0x00000144
+#define MAC_FSM_CONTROL 0x00000148
+#define PRTYEN BIT(1)
+#define TMOUTEN BIT(0)
+
+#define MTL_ECC_CONTROL 0x00000cc0
+#define TSOEE BIT(4)
+#define MRXPEE BIT(3)
+#define MESTEE BIT(2)
+#define MRXEE BIT(1)
+#define MTXEE BIT(0)
+
+#define MTL_SAFETY_INT_STATUS 0x00000cc4
+#define MCSIS BIT(31)
+#define MEUIS BIT(1)
+#define MECIS BIT(0)
+#define MTL_ECC_INT_ENABLE 0x00000cc8
+#define RPCEIE BIT(12)
+#define ECEIE BIT(8)
+#define RXCEIE BIT(4)
+#define TXCEIE BIT(0)
+#define MTL_ECC_INT_STATUS 0x00000ccc
+#define MTL_DPP_CONTROL 0x00000ce0
+#define EPSI BIT(2)
+#define OPE BIT(1)
+#define EDPP BIT(0)
+
+#define DMA_SAFETY_INT_STATUS 0x00001080
+#define MSUIS BIT(29)
+#define MSCIS BIT(28)
+#define DEUIS BIT(1)
+#define DECIS BIT(0)
+#define DMA_ECC_INT_ENABLE 0x00001084
+#define TCEIE BIT(0)
+#define DMA_ECC_INT_STATUS 0x00001088
+
+int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp);
+bool dwmac5_safety_feat_irq_status(struct net_device *ndev,
+ void __iomem *ioaddr, unsigned int asp,
+ struct stmmac_safety_stats *stats);
+const char *dwmac5_safety_feat_dump(struct stmmac_safety_stats *stats,
+ int index, unsigned long *count);
+
+#endif /* __DWMAC5_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 1485d8f..da50451 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -114,6 +114,7 @@ struct stmmac_priv {
int mii_irq[PHY_MAX_ADDR];
struct stmmac_extra_stats xstats ____cacheline_aligned_in_smp;
+ struct stmmac_safety_stats sstats;
struct plat_stmmacenet_data *plat;
struct dma_features dma_cap;
struct stmmac_counters mmc;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index af30b48..2c6ed47 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -523,11 +523,23 @@ stmmac_set_pauseparam(struct net_device *netdev,
static void stmmac_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *dummy, u64 *data)
{
+ const char *(*dump)(struct stmmac_safety_stats *stats, int index,
+ unsigned long *count);
struct stmmac_priv *priv = netdev_priv(dev);
u32 rx_queues_count = priv->plat->rx_queues_to_use;
u32 tx_queues_count = priv->plat->tx_queues_to_use;
+ unsigned long count;
int i, j = 0;
+ if (priv->dma_cap.asp && priv->hw->mac->safety_feat_dump) {
+ dump = priv->hw->mac->safety_feat_dump;
+
+ for (i = 0; i < STMMAC_SAFETY_FEAT_SIZE; i++) {
+ if (dump(&priv->sstats, i, &count))
+ data[j++] = count;
+ }
+ }
+
/* Update the DMA HW counters for dwmac10/100 */
if (priv->hw->dma->dma_diagnostic_fr)
priv->hw->dma->dma_diagnostic_fr(&dev->stats,
@@ -569,7 +581,9 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
static int stmmac_get_sset_count(struct net_device *netdev, int sset)
{
struct stmmac_priv *priv = netdev_priv(netdev);
- int len;
+ const char *(*dump)(struct stmmac_safety_stats *stats, int index,
+ unsigned long *count);
+ int i, len, safety_len = 0;
switch (sset) {
case ETH_SS_STATS:
@@ -577,6 +591,16 @@ static int stmmac_get_sset_count(struct net_device *netdev, int sset)
if (priv->dma_cap.rmon)
len += STMMAC_MMC_STATS_LEN;
+ if (priv->dma_cap.asp && priv->hw->mac->safety_feat_dump) {
+ dump = priv->hw->mac->safety_feat_dump;
+
+ for (i = 0; i < STMMAC_SAFETY_FEAT_SIZE; i++) {
+ if (dump(&priv->sstats, i, NULL))
+ safety_len++;
+ }
+
+ len += safety_len;
+ }
return len;
default:
@@ -589,9 +613,22 @@ static void stmmac_get_strings(struct net_device *dev, u32 stringset, u8 *data)
int i;
u8 *p = data;
struct stmmac_priv *priv = netdev_priv(dev);
+ const char *(*dump)(struct stmmac_safety_stats *stats, int index,
+ unsigned long *count);
switch (stringset) {
case ETH_SS_STATS:
+ if (priv->dma_cap.asp && priv->hw->mac->safety_feat_dump) {
+ dump = priv->hw->mac->safety_feat_dump;
+ for (i = 0; i < STMMAC_SAFETY_FEAT_SIZE; i++) {
+ const char *desc = dump(&priv->sstats, i, NULL);
+
+ if (desc) {
+ memcpy(p, desc, ETH_GSTRING_LEN);
+ p += ETH_GSTRING_LEN;
+ }
+ }
+ }
if (priv->dma_cap.rmon)
for (i = 0; i < STMMAC_MMC_STATS_LEN; i++) {
memcpy(p, stmmac_mmc[i].stat_string,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index b75ecf3..9a16931 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2014,6 +2014,22 @@ static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode,
}
}
+static bool stmmac_safety_feat_interrupt(struct stmmac_priv *priv)
+{
+ bool ret = false;
+
+ /* Safety features are only available in cores >= 5.10 */
+ if (priv->synopsys_id < DWMAC_CORE_5_10)
+ return ret;
+ if (priv->hw->mac->safety_feat_irq_status)
+ ret = priv->hw->mac->safety_feat_irq_status(priv->dev,
+ priv->ioaddr, priv->dma_cap.asp, &priv->sstats);
+
+ if (ret)
+ stmmac_global_err(priv);
+ return ret;
+}
+
/**
* stmmac_dma_interrupt - DMA ISR
* @priv: driver private structure
@@ -2503,6 +2519,17 @@ static void stmmac_mtl_configuration(struct stmmac_priv *priv)
stmmac_mac_config_rx_queues_routing(priv);
}
+static void stmmac_safety_feat_configuration(struct stmmac_priv *priv)
+{
+ if (priv->hw->mac->safety_feat_config && priv->dma_cap.asp) {
+ netdev_info(priv->dev, "Enabling Safety Features\n");
+ priv->hw->mac->safety_feat_config(priv->ioaddr,
+ priv->dma_cap.asp);
+ } else {
+ netdev_info(priv->dev, "No Safety Features support found\n");
+ }
+}
+
/**
* stmmac_hw_setup - setup mac in a usable state.
* @dev : pointer to the device structure.
@@ -2554,6 +2581,10 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
if (priv->synopsys_id >= DWMAC_CORE_4_00)
stmmac_mtl_configuration(priv);
+ /* Initialize Safety Features */
+ if (priv->synopsys_id >= DWMAC_CORE_5_10)
+ stmmac_safety_feat_configuration(priv);
+
ret = priv->hw->mac->rx_ipc(priv->hw);
if (!ret) {
netdev_warn(priv->dev, "RX IPC Checksum Offload disabled\n");
@@ -3729,6 +3760,9 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
/* Check if adapter is up */
if (test_bit(STMMAC_DOWN, &priv->state))
return IRQ_HANDLED;
+ /* Check if a fatal error happened */
+ if (stmmac_safety_feat_interrupt(priv))
+ return IRQ_HANDLED;
/* To handle GMAC own interrupts */
if ((priv->plat->has_gmac) || (priv->plat->has_gmac4)) {
--
2.9.3
^ permalink raw reply related
* Re: [PATCH linux-stable-4.14] tcp: reset sk_send_head in tcp_write_queue_purge
From: Timofey Titovets @ 2018-03-29 10:00 UTC (permalink / raw)
To: Willy Tarreau
Cc: davem, yongjian xu, Soheil Hassas Yeganeh, netdev, ycheng,
ncardwell, Soheil Hassas Yeganeh, Eric Dumazet
In-Reply-To: <20180320161331.GA31452@1wt.eu>
Hi,
any progress here?
I didn't find that patch applied for any 4.14.27-4.14.31
Patch rejected?
2018-03-20 19:13 GMT+03:00 Willy Tarreau <w@1wt.eu>:
> Hi David,
>
> regarding the patch below, I'm not certain whether you planned to take
> it since it's marked "not applicable" on patchwork, but I suspect it's
> only because it doesn't apply to mainline.
>
> However, please note that there are two typos in commit IDs referenced in
> the commit message that might be nice to fix before merging :
>
>> > For example, after 27fid7a8ed38 (tcp: purge write queue upon RST),
>
> - here it's "a27fd7a8ed38" (missing 'a' and extra 'i' in the middle)
>
> - and lower in the fixes tag there's the extra 'i' as well :
>
>> > Fixes: a27fid7a8ed38 (tcp: purge write queue upon RST)
>
> There was another report today on the stable list for a similar crash
> on 4.14.28 and I suspect it's the one I saw this week-end on my firewall
> after upgrading from 4.14.10 to 4.14.27 though I didn't have the symbols
> to confirm.
>
> Thanks,
> Willy
--
Have a nice day,
Timofey.
^ permalink raw reply
* [PATCH net-next] dt-bindings: net: renesas-ravb: Add support for r8a77470 SoC
From: Biju Das @ 2018-03-29 10:02 UTC (permalink / raw)
To: David S . Miller, Rob Herring, Mark Rutland, Russell King
Cc: Geert Uytterhoeven, Sergei Shtylyov, Simon Horman, Magnus Damm,
Chris Paterson, Fabrizio Castro, devicetree, linux-renesas-soc,
linux-arm-kernel, netdev, Biju Das
Add a new compatible string for the RZ/G1C (R8A77470) SoC.
Signed-off-by: Biju Das <biju.das@bp.renesas.com>
Reviewed-by: Fabrizio Castro <fabrizio.castro@bp.renesas.com>
---
Documentation/devicetree/bindings/net/renesas,ravb.txt | 1 +
1 file changed, 1 insertion(+)
diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt
index b4dc455..c306f55 100644
--- a/Documentation/devicetree/bindings/net/renesas,ravb.txt
+++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt
@@ -7,6 +7,7 @@ Required properties:
- compatible: Must contain one or more of the following:
- "renesas,etheravb-r8a7743" for the R8A7743 SoC.
- "renesas,etheravb-r8a7745" for the R8A7745 SoC.
+ - "renesas,etheravb-r8a77470" for the R8A77470 SoC.
- "renesas,etheravb-r8a7790" for the R8A7790 SoC.
- "renesas,etheravb-r8a7791" for the R8A7791 SoC.
- "renesas,etheravb-r8a7792" for the R8A7792 SoC.
--
2.7.4
^ permalink raw reply related
* [PATCH net 0/2] Fix vlan tag handling for vlan packets without ethernet headers
From: Toshiaki Makita @ 2018-03-29 10:05 UTC (permalink / raw)
To: David S. Miller; +Cc: Toshiaki Makita, netdev, Eric Dumazet
Eric Dumazet reported syzbot found a new bug which leads to underflow of
size argument of memmove(), causing crash[1]. This can be triggered by tun
devices.
The underflow happened because skb_vlan_untag() did not expect vlan packets
without ethernet headers, and tun can produce such packets.
I also checked vlan_insert_inner_tag() and found a similar bug.
This series fixes these problems.
[1] https://marc.info/?l=linux-netdev&m=152221753920510&w=2
Toshiaki Makita (2):
net: Fix untag for vlan packets without ethernet header
vlan: Fix vlan insertion for packets without ethernet header
include/linux/if_vlan.h | 15 +++++++++++++--
net/core/skbuff.c | 6 ++++--
2 files changed, 17 insertions(+), 4 deletions(-)
--
1.8.3.1
^ permalink raw reply
* [PATCH net 1/2] net: Fix untag for vlan packets without ethernet header
From: Toshiaki Makita @ 2018-03-29 10:05 UTC (permalink / raw)
To: David S. Miller; +Cc: Toshiaki Makita, netdev, Eric Dumazet
In-Reply-To: <1522317930-2951-1-git-send-email-makita.toshiaki@lab.ntt.co.jp>
In some situation vlan packets do not have ethernet headers. One example
is packets from tun devices. Users can specify vlan protocol in tun_pi
field instead of IP protocol, and skb_vlan_untag() attempts to untag such
packets.
skb_vlan_untag() (more precisely, skb_reorder_vlan_header() called by it)
however did not expect packets without ethernet headers, so in such a case
size argument for memmove() underflowed and triggered crash.
====
BUG: unable to handle kernel paging request at ffff8801cccb8000
IP: __memmove+0x24/0x1a0 arch/x86/lib/memmove_64.S:43
PGD 9cee067 P4D 9cee067 PUD 1d9401063 PMD 1cccb7063 PTE 2810100028101
Oops: 000b [#1] SMP KASAN
Dumping ftrace buffer:
(ftrace buffer empty)
Modules linked in:
CPU: 1 PID: 17663 Comm: syz-executor2 Not tainted 4.16.0-rc7+ #368
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:__memmove+0x24/0x1a0 arch/x86/lib/memmove_64.S:43
RSP: 0018:ffff8801cc046e28 EFLAGS: 00010287
RAX: ffff8801ccc244c4 RBX: fffffffffffffffe RCX: fffffffffff6c4c2
RDX: fffffffffffffffe RSI: ffff8801cccb7ffc RDI: ffff8801cccb8000
RBP: ffff8801cc046e48 R08: ffff8801ccc244be R09: ffffed0039984899
R10: 0000000000000001 R11: ffffed0039984898 R12: ffff8801ccc244c4
R13: ffff8801ccc244c0 R14: ffff8801d96b7c06 R15: ffff8801d96b7b40
FS: 00007febd562d700(0000) GS:ffff8801db300000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffff8801cccb8000 CR3: 00000001ccb2f006 CR4: 00000000001606e0
DR0: 0000000020000000 DR1: 0000000020000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000600
Call Trace:
memmove include/linux/string.h:360 [inline]
skb_reorder_vlan_header net/core/skbuff.c:5031 [inline]
skb_vlan_untag+0x470/0xc40 net/core/skbuff.c:5061
__netif_receive_skb_core+0x119c/0x3460 net/core/dev.c:4460
__netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4627
netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4701
netif_receive_skb+0xae/0x390 net/core/dev.c:4725
tun_rx_batched.isra.50+0x5ee/0x870 drivers/net/tun.c:1555
tun_get_user+0x299e/0x3c20 drivers/net/tun.c:1962
tun_chr_write_iter+0xb9/0x160 drivers/net/tun.c:1990
call_write_iter include/linux/fs.h:1782 [inline]
new_sync_write fs/read_write.c:469 [inline]
__vfs_write+0x684/0x970 fs/read_write.c:482
vfs_write+0x189/0x510 fs/read_write.c:544
SYSC_write fs/read_write.c:589 [inline]
SyS_write+0xef/0x220 fs/read_write.c:581
do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x42/0xb7
RIP: 0033:0x454879
RSP: 002b:00007febd562cc68 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 00007febd562d6d4 RCX: 0000000000454879
RDX: 0000000000000157 RSI: 0000000020000180 RDI: 0000000000000014
RBP: 000000000072bea0 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 00000000000006b0 R14: 00000000006fc120 R15: 0000000000000000
Code: 90 90 90 90 90 90 90 48 89 f8 48 83 fa 20 0f 82 03 01 00 00 48 39 fe 7d 0f 49 89 f0 49 01 d0 49 39 f8 0f 8f 9f 00 00 00 48 89 d1 <f3> a4 c3 48 81 fa a8 02 00 00 72 05 40 38 fe 74 3b 48 83 ea 20
RIP: __memmove+0x24/0x1a0 arch/x86/lib/memmove_64.S:43 RSP: ffff8801cc046e28
CR2: ffff8801cccb8000
====
We don't need to copy headers for packets which do not have preceding
headers of vlan headers, so skip memmove() in that case.
Fixes: 4bbb3e0e8239 ("net: Fix vlan untag for bridge and vlan_dev with reorder_hdr off")
Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
---
net/core/skbuff.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1e7acdc..857e4e6 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5028,8 +5028,10 @@ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
}
mac_len = skb->data - skb_mac_header(skb);
- memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb),
- mac_len - VLAN_HLEN - ETH_TLEN);
+ if (likely(mac_len > VLAN_HLEN + ETH_TLEN)) {
+ memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb),
+ mac_len - VLAN_HLEN - ETH_TLEN);
+ }
skb->mac_header += VLAN_HLEN;
return skb;
}
--
1.8.3.1
^ permalink raw reply related
* [PATCH net 2/2] vlan: Fix vlan insertion for packets without ethernet header
From: Toshiaki Makita @ 2018-03-29 10:05 UTC (permalink / raw)
To: David S. Miller; +Cc: Toshiaki Makita, netdev, Eric Dumazet
In-Reply-To: <1522317930-2951-1-git-send-email-makita.toshiaki@lab.ntt.co.jp>
In some situation vlan packets do not have ethernet headers. One example
is packets from tun devices. Users can specify vlan protocol in tun_pi
field instead of IP protocol. When we have a vlan device with reorder_hdr
disabled on top of the tun device, such packets from tun devices are
untagged in skb_vlan_untag() and vlan headers will be inserted back in
vlan_insert_inner_tag().
vlan_insert_inner_tag() however did not expect packets without ethernet
headers, so in such a case size argument for memmove() underflowed.
We don't need to copy headers for packets which do not have preceding
headers of vlan headers, so skip memmove() in that case.
Also don't write vlan protocol in skb->data when it does not have enough
room for it.
Fixes: cbe7128c4b92 ("vlan: Fix out of order vlan headers with reorder header off")
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
---
include/linux/if_vlan.h | 15 +++++++++++++--
1 file changed, 13 insertions(+), 2 deletions(-)
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index c4a1cff..7d30892 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -323,13 +323,24 @@ static inline int __vlan_insert_inner_tag(struct sk_buff *skb,
skb_push(skb, VLAN_HLEN);
/* Move the mac header sans proto to the beginning of the new header. */
- memmove(skb->data, skb->data + VLAN_HLEN, mac_len - ETH_TLEN);
+ if (likely(mac_len > ETH_TLEN))
+ memmove(skb->data, skb->data + VLAN_HLEN, mac_len - ETH_TLEN);
skb->mac_header -= VLAN_HLEN;
veth = (struct vlan_ethhdr *)(skb->data + mac_len - ETH_HLEN);
/* first, the ethernet type */
- veth->h_vlan_proto = vlan_proto;
+ if (likely(mac_len >= ETH_TLEN)) {
+ /* h_vlan_encapsulated_proto should already be populated, and
+ * skb->data has space for h_vlan_proto
+ */
+ veth->h_vlan_proto = vlan_proto;
+ } else {
+ /* h_vlan_encapsulated_proto should not be populated, and
+ * skb->data has no space for h_vlan_proto
+ */
+ veth->h_vlan_encapsulated_proto = skb->protocol;
+ }
/* now, the TCI */
veth->h_vlan_TCI = htons(vlan_tci);
--
1.8.3.1
^ permalink raw reply related
* Re: [PATCH linux-stable-4.14] tcp: reset sk_send_head in tcp_write_queue_purge
From: Jack Wang @ 2018-03-29 10:09 UTC (permalink / raw)
To: Timofey Titovets
Cc: Willy Tarreau, davem, yongjian xu, Soheil Hassas Yeganeh, netdev,
ycheng, ncardwell, Soheil Hassas Yeganeh, Eric Dumazet
In-Reply-To: <CAGqmi75+g+p1myK9=kK8XURtOWAK7QmP4tbrVnVzRYgxOEDbrQ@mail.gmail.com>
2018-03-29 12:00 GMT+02:00 Timofey Titovets <nefelim4ag@gmail.com>:
> Hi,
> any progress here?
>
> I didn't find that patch applied for any 4.14.27-4.14.31
>
> Patch rejected?
It's in queue for 4.14.32
https://git.kernel.org/pub/scm/linux/kernel/git/stable/stable-queue.git/tree/queue-4.14/tcp-reset-sk_send_head-in-tcp_write_queue_purge.patch?id=c78a2769647faebad83a2e35a14cde382be3ff7d
>
> 2018-03-20 19:13 GMT+03:00 Willy Tarreau <w@1wt.eu>:
>> Hi David,
>>
>> regarding the patch below, I'm not certain whether you planned to take
>> it since it's marked "not applicable" on patchwork, but I suspect it's
>> only because it doesn't apply to mainline.
>>
>> However, please note that there are two typos in commit IDs referenced in
>> the commit message that might be nice to fix before merging :
>>
>>> > For example, after 27fid7a8ed38 (tcp: purge write queue upon RST),
>>
>> - here it's "a27fd7a8ed38" (missing 'a' and extra 'i' in the middle)
>>
>> - and lower in the fixes tag there's the extra 'i' as well :
>>
>>> > Fixes: a27fid7a8ed38 (tcp: purge write queue upon RST)
>>
>> There was another report today on the stable list for a similar crash
>> on 4.14.28 and I suspect it's the one I saw this week-end on my firewall
>> after upgrading from 4.14.10 to 4.14.27 though I didn't have the symbols
>> to confirm.
>>
>> Thanks,
>> Willy
>
>
>
> --
> Have a nice day,
> Timofey.
^ permalink raw reply
* [PATCH 0/2] net: mvneta: improve suspend/resume
From: Jisheng Zhang @ 2018-03-29 10:12 UTC (permalink / raw)
To: David Miller, Thomas Petazzoni; +Cc: netdev, linux-arm-kernel, linux-kernel
This series tries to optimize the mvneta's suspend/resume
implementation by only taking necessary actions.
Jisheng Zhang (2):
net: mvneta: split rxq/txq init into SW and HW parts
net: mvneta: improve suspend/resume
drivers/net/ethernet/marvell/mvneta.c | 146 +++++++++++++++++++++++++++-------
1 file changed, 119 insertions(+), 27 deletions(-)
--
2.16.3
^ permalink raw reply
* [PATCH 1/2] net: mvneta: split rxq/txq init into SW and HW parts
From: Jisheng Zhang @ 2018-03-29 10:13 UTC (permalink / raw)
To: David Miller, Thomas Petazzoni; +Cc: netdev, linux-arm-kernel, linux-kernel
In-Reply-To: <20180329181220.61d63c92@xhacker.debian>
This is to prepare the suspend/resume improvement in next patch. The
SW parts can be optimized out during resume.
Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
---
drivers/net/ethernet/marvell/mvneta.c | 70 ++++++++++++++++++++++++++---------
1 file changed, 53 insertions(+), 17 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 30aab9bf77cc..4ec69bbd1eb4 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2796,10 +2796,8 @@ static void mvneta_rx_reset(struct mvneta_port *pp)
/* Rx/Tx queue initialization/cleanup methods */
-/* Create a specified RX queue */
-static int mvneta_rxq_init(struct mvneta_port *pp,
- struct mvneta_rx_queue *rxq)
-
+static int mvneta_rxq_sw_init(struct mvneta_port *pp,
+ struct mvneta_rx_queue *rxq)
{
rxq->size = pp->rx_ring_size;
@@ -2812,6 +2810,12 @@ static int mvneta_rxq_init(struct mvneta_port *pp,
rxq->last_desc = rxq->size - 1;
+ return 0;
+}
+
+static void mvneta_rxq_hw_init(struct mvneta_port *pp,
+ struct mvneta_rx_queue *rxq)
+{
/* Set Rx descriptors queue starting address */
mvreg_write(pp, MVNETA_RXQ_BASE_ADDR_REG(rxq->id), rxq->descs_phys);
mvreg_write(pp, MVNETA_RXQ_SIZE_REG(rxq->id), rxq->size);
@@ -2835,6 +2839,20 @@ static int mvneta_rxq_init(struct mvneta_port *pp,
mvneta_rxq_short_pool_set(pp, rxq);
mvneta_rxq_non_occup_desc_add(pp, rxq, rxq->size);
}
+}
+
+/* Create a specified RX queue */
+static int mvneta_rxq_init(struct mvneta_port *pp,
+ struct mvneta_rx_queue *rxq)
+
+{
+ int ret;
+
+ ret = mvneta_rxq_sw_init(pp, rxq);
+ if (ret)
+ return ret;
+
+ mvneta_rxq_hw_init(pp, rxq);
return 0;
}
@@ -2857,9 +2875,8 @@ static void mvneta_rxq_deinit(struct mvneta_port *pp,
rxq->descs_phys = 0;
}
-/* Create and initialize a tx queue */
-static int mvneta_txq_init(struct mvneta_port *pp,
- struct mvneta_tx_queue *txq)
+static int mvneta_txq_sw_init(struct mvneta_port *pp,
+ struct mvneta_tx_queue *txq)
{
int cpu;
@@ -2872,7 +2889,6 @@ static int mvneta_txq_init(struct mvneta_port *pp,
txq->tx_stop_threshold = txq->size - MVNETA_MAX_SKB_DESCS;
txq->tx_wake_threshold = txq->tx_stop_threshold / 2;
-
/* Allocate memory for TX descriptors */
txq->descs = dma_alloc_coherent(pp->dev->dev.parent,
txq->size * MVNETA_DESC_ALIGNED_SIZE,
@@ -2882,14 +2898,6 @@ static int mvneta_txq_init(struct mvneta_port *pp,
txq->last_desc = txq->size - 1;
- /* Set maximum bandwidth for enabled TXQs */
- mvreg_write(pp, MVETH_TXQ_TOKEN_CFG_REG(txq->id), 0x03ffffff);
- mvreg_write(pp, MVETH_TXQ_TOKEN_COUNT_REG(txq->id), 0x3fffffff);
-
- /* Set Tx descriptors queue starting address */
- mvreg_write(pp, MVNETA_TXQ_BASE_ADDR_REG(txq->id), txq->descs_phys);
- mvreg_write(pp, MVNETA_TXQ_SIZE_REG(txq->id), txq->size);
-
txq->tx_skb = kmalloc_array(txq->size, sizeof(*txq->tx_skb),
GFP_KERNEL);
if (!txq->tx_skb) {
@@ -2910,7 +2918,6 @@ static int mvneta_txq_init(struct mvneta_port *pp,
txq->descs, txq->descs_phys);
return -ENOMEM;
}
- mvneta_tx_done_pkts_coal_set(pp, txq, txq->done_pkts_coal);
/* Setup XPS mapping */
if (txq_number > 1)
@@ -2923,6 +2930,35 @@ static int mvneta_txq_init(struct mvneta_port *pp,
return 0;
}
+static void mvneta_txq_hw_init(struct mvneta_port *pp,
+ struct mvneta_tx_queue *txq)
+{
+ /* Set maximum bandwidth for enabled TXQs */
+ mvreg_write(pp, MVETH_TXQ_TOKEN_CFG_REG(txq->id), 0x03ffffff);
+ mvreg_write(pp, MVETH_TXQ_TOKEN_COUNT_REG(txq->id), 0x3fffffff);
+
+ /* Set Tx descriptors queue starting address */
+ mvreg_write(pp, MVNETA_TXQ_BASE_ADDR_REG(txq->id), txq->descs_phys);
+ mvreg_write(pp, MVNETA_TXQ_SIZE_REG(txq->id), txq->size);
+
+ mvneta_tx_done_pkts_coal_set(pp, txq, txq->done_pkts_coal);
+}
+
+/* Create and initialize a tx queue */
+static int mvneta_txq_init(struct mvneta_port *pp,
+ struct mvneta_tx_queue *txq)
+{
+ int ret;
+
+ ret = mvneta_txq_sw_init(pp, txq);
+ if (ret < 0)
+ return ret;
+
+ mvneta_txq_hw_init(pp, txq);
+
+ return 0;
+}
+
/* Free allocated resources when mvneta_txq_init() fails to allocate memory*/
static void mvneta_txq_deinit(struct mvneta_port *pp,
struct mvneta_tx_queue *txq)
--
2.16.3
^ permalink raw reply related
* [PATCH 2/2] net: mvneta: improve suspend/resume
From: Jisheng Zhang @ 2018-03-29 10:15 UTC (permalink / raw)
To: David Miller, Thomas Petazzoni; +Cc: netdev, linux-arm-kernel, linux-kernel
In-Reply-To: <20180329181220.61d63c92@xhacker.debian>
Current suspend/resume implementation reuses the mvneta_open() and
mvneta_close(), but it could be optimized to take only necessary
actions during suspend/resume.
One obvious problem of current implementation is: after hundreds of
system suspend/resume cycles, the resume of mvneta could fail due to
fragmented dma coherent memory. After this patch, the non-necessary
memory alloc/free is optimized out.
Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
---
drivers/net/ethernet/marvell/mvneta.c | 76 ++++++++++++++++++++++++++++++-----
1 file changed, 66 insertions(+), 10 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 4ec69bbd1eb4..1870f1dd7093 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -4575,14 +4575,46 @@ static int mvneta_remove(struct platform_device *pdev)
#ifdef CONFIG_PM_SLEEP
static int mvneta_suspend(struct device *device)
{
+ int queue;
struct net_device *dev = dev_get_drvdata(device);
struct mvneta_port *pp = netdev_priv(dev);
- rtnl_lock();
- if (netif_running(dev))
- mvneta_stop(dev);
- rtnl_unlock();
+ if (!netif_running(dev))
+ return 0;
+
netif_device_detach(dev);
+
+ mvneta_stop_dev(pp);
+
+ if (!pp->neta_armada3700) {
+ spin_lock(&pp->lock);
+ pp->is_stopped = true;
+ spin_unlock(&pp->lock);
+
+ cpuhp_state_remove_instance_nocalls(online_hpstate,
+ &pp->node_online);
+ cpuhp_state_remove_instance_nocalls(CPUHP_NET_MVNETA_DEAD,
+ &pp->node_dead);
+ }
+
+ for (queue = 0; queue < rxq_number; queue++) {
+ struct mvneta_rx_queue *rxq = &pp->rxqs[queue];
+
+ mvneta_rxq_drop_pkts(pp, rxq);
+ }
+
+ for (queue = 0; queue < txq_number; queue++) {
+ struct mvneta_tx_queue *txq = &pp->txqs[queue];
+
+ /* Set minimum bandwidth for disabled TXQs */
+ mvreg_write(pp, MVETH_TXQ_TOKEN_CFG_REG(txq->id), 0);
+ mvreg_write(pp, MVETH_TXQ_TOKEN_COUNT_REG(txq->id), 0);
+
+ /* Set Tx descriptors queue starting address and size */
+ mvreg_write(pp, MVNETA_TXQ_BASE_ADDR_REG(txq->id), 0);
+ mvreg_write(pp, MVNETA_TXQ_SIZE_REG(txq->id), 0);
+ }
+
clk_disable_unprepare(pp->clk_bus);
clk_disable_unprepare(pp->clk);
return 0;
@@ -4593,7 +4625,7 @@ static int mvneta_resume(struct device *device)
struct platform_device *pdev = to_platform_device(device);
struct net_device *dev = dev_get_drvdata(device);
struct mvneta_port *pp = netdev_priv(dev);
- int err;
+ int err, queue;
clk_prepare_enable(pp->clk);
if (!IS_ERR(pp->clk_bus))
@@ -4614,13 +4646,37 @@ static int mvneta_resume(struct device *device)
return err;
}
+ if (!netif_running(dev))
+ return 0;
+
netif_device_attach(dev);
- rtnl_lock();
- if (netif_running(dev)) {
- mvneta_open(dev);
- mvneta_set_rx_mode(dev);
+
+ for (queue = 0; queue < rxq_number; queue++) {
+ struct mvneta_rx_queue *rxq = &pp->rxqs[queue];
+
+ rxq->next_desc_to_proc = 0;
+ mvneta_rxq_hw_init(pp, rxq);
}
- rtnl_unlock();
+
+ for (queue = 0; queue < txq_number; queue++) {
+ struct mvneta_tx_queue *txq = &pp->txqs[queue];
+
+ txq->next_desc_to_proc = 0;
+ mvneta_txq_hw_init(pp, txq);
+ }
+
+ if (!pp->neta_armada3700) {
+ spin_lock(&pp->lock);
+ pp->is_stopped = false;
+ spin_unlock(&pp->lock);
+ cpuhp_state_add_instance_nocalls(online_hpstate,
+ &pp->node_online);
+ cpuhp_state_add_instance_nocalls(CPUHP_NET_MVNETA_DEAD,
+ &pp->node_dead);
+ }
+
+ mvneta_set_rx_mode(dev);
+ mvneta_start_dev(pp);
return 0;
}
--
2.16.3
^ permalink raw reply related
* [PATCH net] net/dim: Fix int overflow
From: Tal Gilboa @ 2018-03-29 10:53 UTC (permalink / raw)
To: David S. Miller
Cc: netdev, Tariq Toukan, Tal Gilboa, Andy Gospodarek, Saeed Mahameed
When calculating difference between samples, the values
are multiplied by 100. Large values may cause int overflow
when multiplied (usually on first iteration).
Fixed by forcing 100 to be of type unsigned long.
Fixes: 4c4dbb4a7363 ("net/mlx5e: Move dynamic interrupt coalescing code to include/linux")
Signed-off-by: Tal Gilboa <talgi@mellanox.com>
---
include/linux/net_dim.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/linux/net_dim.h b/include/linux/net_dim.h
index bebeaad..29ed8fd 100644
--- a/include/linux/net_dim.h
+++ b/include/linux/net_dim.h
@@ -231,7 +231,7 @@ static inline void net_dim_exit_parking(struct net_dim *dim)
}
#define IS_SIGNIFICANT_DIFF(val, ref) \
- (((100 * abs((val) - (ref))) / (ref)) > 10) /* more than 10% difference */
+ (((100UL * abs((val) - (ref))) / (ref)) > 10) /* more than 10% difference */
static inline int net_dim_stats_compare(struct net_dim_stats *curr,
struct net_dim_stats *prev)
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next] MAINTAINERS: Update my email address from freescale to nxp
From: Claudiu Manoil @ 2018-03-29 10:58 UTC (permalink / raw)
To: David S . Miller, netdev; +Cc: linux-kernel
The freescale.com address will no longer be available.
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
---
MAINTAINERS | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 73c0cda..274ba58 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5637,7 +5637,7 @@ S: Maintained
F: drivers/dma/fsldma.*
FREESCALE eTSEC ETHERNET DRIVER (GIANFAR)
-M: Claudiu Manoil <claudiu.manoil@freescale.com>
+M: Claudiu Manoil <claudiu.manoil@nxp.com>
L: netdev@vger.kernel.org
S: Maintained
F: drivers/net/ethernet/freescale/gianfar*
--
2.7.4
^ permalink raw reply related
* [PATCH 000/109] remove in-kernel calls to syscalls
From: Dominik Brodowski @ 2018-03-29 11:22 UTC (permalink / raw)
To: linux-kernel-u79uwXL29TY76Z2rM5mHXA
Cc: Peter Zijlstra, Amir Goldstein, linux-mm-Bw31MaZKKs3YtjvyW6yDsg,
H . Peter Anvin, tautschn-vV1OtcyAfmbQXOPxS62xeg, Ingo Molnar,
linux-arch-u79uwXL29TY76Z2rM5mHXA,
linux-s390-u79uwXL29TY76Z2rM5mHXA, Andi Kleen,
user-mode-linux-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f,
x86-DgEjT+Ai2ygdnm+yROfE0A, hmclauchlan-b10kYP2dOMg,
Christoph Hellwig, Jiri Slaby, Darren Hart, Jaswinder Singh,
arnd-r2nGTMty4D4, Jeff Dike,
viro-3bDd1+5oDREiFSDQTTA3OLVCufUGDwFn, Thomas Gleixner,
netdev-u79uwXL29TY76Z2rM5mHXA,
kexec-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r, Luis R . Rodriguez,
Eric W . Biederman, linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
Andrew Morton, torvalds-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b,
"David S . Miller" <davem@
[ While most parts of this patch set have been sent out already at least
once, I send out *all* patches to lkml once again as this whole series
touches several different subsystems in sensitive areas. ]
System calls are interaction points between userspace and the kernel.
Therefore, system call functions such as sys_xyzzy() or compat_sys_xyzzy()
should only be called from userspace via the syscall table, but not from
elsewhere in the kernel.
At least on 64-bit x86, it will likely be a hard requirement from v4.17
onwards to not call system call functions in the kernel: It is better to
use use a different calling convention for system calls there, where
struct pt_regs is decoded on-the-fly in a syscall wrapper which then hands
processing over to the actual syscall function. This means that only those
parameters which are actually needed for a specific syscall are passed on
during syscall entry, instead of filling in six CPU registers with random
user space content all the time (which may cause serious trouble down the
call chain).[*]
Moreover, rules on how data may be accessed may differ between kernel data
and user data. This is another reason why calling sys_xyzzy() is
generally a bad idea, and -- at most -- acceptable in arch-specific code.
This patchset removes all in-kernel calls to syscall functions in the
kernel with the exception of arch/. On top of this, it cleans up the
three places where many syscalls are referenced or prototyped, namely
kernel/sys_ni.c, include/linux/syscalls.h and include/linux/compat.h.
Patches 1 to 101 have been sent out earlier, namely
- part 1 ( http://lkml.kernel.org/r/20180315190529.20943-1-linux-X3ehHDuj6sIIGcDfoQAp7OTW4wlIGRCZ@public.gmane.org )
- part 2 ( http://lkml.kernel.org/r/20180316170614.5392-1-linux-X3ehHDuj6sIIGcDfoQAp7OTW4wlIGRCZ@public.gmane.org )
- part 3 ( http://lkml.kernel.org/r/20180322090059.19361-1-linux-X3ehHDuj6sIIGcDfoQAp7OTW4wlIGRCZ@public.gmane.org ).
Changes since these earlier versions are:
- I have added a lot more documentation and improved the commit messages,
namely to explain the naming convention and the rationale of this
patches.
- ACKs/Reviewed-by (thanks!) were added .
- Shuffle the patches around to have them grouped together systematically:
First goes a patch which defines the goal and explains the rationale:
syscalls: define and explain goal to not call syscalls in the kernel
A few codepaths can trivially be converted to existing in-kernel interfaces:
kernel: use kernel_wait4() instead of sys_wait4()
kernel: open-code sys_rt_sigpending() in sys_sigpending()
kexec: call do_kexec_load() in compat syscall directly
mm: use do_futex() instead of sys_futex() in mm_release()
x86: use _do_fork() in compat_sys_x86_clone()
x86: remove compat_sys_x86_waitpid()
Then follow many patches which only affect specfic subsystems each, and
replace sys_*() with internal helpers named __sys_*() or do_sys_*(). Let's
start with net/:
net: socket: add __sys_recvfrom() helper; remove in-kernel call to syscall
net: socket: add __sys_sendto() helper; remove in-kernel call to syscall
net: socket: add __sys_accept4() helper; remove in-kernel call to syscall
net: socket: add __sys_socket() helper; remove in-kernel call to syscall
net: socket: add __sys_bind() helper; remove in-kernel call to syscall
net: socket: add __sys_connect() helper; remove in-kernel call to syscall
net: socket: add __sys_listen() helper; remove in-kernel call to syscall
net: socket: add __sys_getsockname() helper; remove in-kernel call to syscall
net: socket: add __sys_getpeername() helper; remove in-kernel call to syscall
net: socket: add __sys_socketpair() helper; remove in-kernel call to syscall
net: socket: add __sys_shutdown() helper; remove in-kernel call to syscall
net: socket: add __sys_setsockopt() helper; remove in-kernel call to syscall
net: socket: add __sys_getsockopt() helper; remove in-kernel call to syscall
net: socket: add do_sys_recvmmsg() helper; remove in-kernel call to syscall
net: socket: move check for forbid_cmsg_compat to __sys_...msg()
net: socket: replace calls to sys_send() with __sys_sendto()
net: socket: replace call to sys_recv() with __sys_recvfrom()
net: socket: add __compat_sys_recvfrom() helper; remove in-kernel call to compat syscall
net: socket: add __compat_sys_setsockopt() helper; remove in-kernel call to compat syscall
net: socket: add __compat_sys_getsockopt() helper; remove in-kernel call to compat syscall
net: socket: add __compat_sys_recvmmsg() helper; remove in-kernel call to compat syscall
net: socket: add __compat_sys_...msg() helpers; remove in-kernel calls to compat syscalls
The changes in ipc/ are limited to this specific subsystem. The wrappers are
named ksys_*() to denote that these functions are meant as a drop-in replacement
for the syscalls.
ipc: add semtimedop syscall/compat_syscall wrappers
ipc: add semget syscall wrapper
ipc: add semctl syscall/compat_syscall wrappers
ipc: add msgget syscall wrapper
ipc: add shmget syscall wrapper
ipc: add shmdt syscall wrapper
ipc: add shmctl syscall/compat_syscall wrappers
ipc: add msgctl syscall/compat_syscall wrappers
ipc: add msgrcv syscall/compat_syscall wrappers
ipc: add msgsnd syscall/compat_syscall wrappers
A few mindless conversions in kernel/ and mm/:
kernel: add do_getpgid() helper; remove internal call to sys_getpgid()
kernel: add do_compat_sigaltstack() helper; remove in-kernel call to compat syscall
kernel: provide ksys_*() wrappers for syscalls called by kernel/uid16.c
sched: add do_sched_yield() helper; remove in-kernel call to sched_yield()
mm: add kernel_migrate_pages() helper, move compat syscall to mm/mempolicy.c
mm: add kernel_move_pages() helper, move compat syscall to mm/migrate.c
mm: add kernel_mbind() helper; remove in-kernel call to syscall
mm: add kernel_[sg]et_mempolicy() helpers; remove in-kernel calls to syscalls
Then, let's handle those instances internal to fs/ which call syscalls:
fs: add do_readlinkat() helper; remove internal call to sys_readlinkat()
fs: add do_pipe2() helper; remove internal call to sys_pipe2()
fs: add do_renameat2() helper; remove internal call to sys_renameat2()
fs: add do_futimesat() helper; remove internal call to sys_futimesat()
fs: add do_epoll_*() helpers; remove internal calls to sys_epoll_*()
fs: add do_signalfd4() helper; remove internal calls to sys_signalfd4()
fs: add do_eventfd() helper; remove internal call to sys_eventfd()
fs: add do_lookup_dcookie() helper; remove in-kernel call to syscall
fs: add do_vmsplice() helper; remove in-kernel call to syscall
fs: add kern_select() helper; remove in-kernel call to sys_select()
fs: add do_compat_fcntl64() helper; remove in-kernel call to compat syscall
fs: add do_compat_select() helper; remove in-kernel call to compat syscall
fs: add do_compat_signalfd4() helper; remove in-kernel call to compat syscall
fs: add do_compat_futimesat() helper; remove in-kernel call to compat syscall
inotify: add do_inotify_init() helper; remove in-kernel call to syscall
fanotify: add do_fanotify_mark() helper; remove in-kernel call to syscall
fs/quota: add kernel_quotactl() helper; remove in-kernel call to syscall
fs/quota: use COMPAT_SYSCALL_DEFINE for sys32_quotactl()
Several fs- and some mm-related syscalls are called in initramfs, initrd and
init, devtmpfs, and pm code. While at least many of these instances should be
converted to use proper in-kernel VFS interfaces in future, convert them
mindlessly to ksys_*() helpers or wrappers for now.
fs: add ksys_mount() helper; remove in-kernel calls to sys_mount()
fs: add ksys_umount() helper; remove in-kernel call to sys_umount()
fs: add ksys_dup{,3}() helper; remove in-kernel calls to sys_dup{,3}()
fs: add ksys_chroot() helper; remove-in kernel calls to sys_chroot()
fs: add ksys_write() helper; remove in-kernel calls to sys_write()
fs: add ksys_chdir() helper; remove in-kernel calls to sys_chdir()
fs: add ksys_unlink() wrapper; remove in-kernel calls to sys_unlink()
hostfs: rename do_rmdir() to hostfs_do_rmdir()
fs: add ksys_rmdir() wrapper; remove in-kernel calls to sys_rmdir()
fs: add do_mkdirat() helper and ksys_mkdir() wrapper; remove in-kernel calls to syscall
fs: add do_symlinkat() helper and ksys_symlink() wrapper; remove in-kernel calls to syscall
fs: add do_mknodat() helper and ksys_mknod() wrapper; remove in-kernel calls to syscall
fs: add do_linkat() helper and ksys_link() wrapper; remove in-kernel calls to syscall
fs: add ksys_fchmod() and do_fchmodat() helpers and ksys_chmod() wrapper; remove in-kernel calls to syscall
fs: add do_faccessat() helper and ksys_access() wrapper; remove in-kernel calls to syscall
fs: add do_fchownat(), ksys_fchown() helpers and ksys_{,l}chown() wrappers
fs: add ksys_ftruncate() wrapper; remove in-kernel calls to sys_ftruncate()
fs: add ksys_close() wrapper; remove in-kernel calls to sys_close()
fs: add ksys_open() wrapper; remove in-kernel calls to sys_open()
fs: add ksys_getdents64() helper; remove in-kernel calls to sys_getdents64()
fs: add ksys_ioctl() helper; remove in-kernel calls to sys_ioctl()
fs: add ksys_lseek() helper; remove in-kernel calls to sys_lseek()
fs: add ksys_read() helper; remove in-kernel calls to sys_read()
fs: add ksys_sync() helper; remove in-kernel calls to sys_sync()
kernel: add ksys_unshare() helper; remove in-kernel calls to sys_unshare()
kernel: add ksys_setsid() helper; remove in-kernel call to sys_setsid()
To reach the goal to get rid of all in-kernel calls to syscalls for x86, we
need to handle a few further syscalls called from compat syscalls in x86 and
(mostly) from other architectures. Those could be made generic making use of
Al Viro's macro trickery. For v4.17, I'd suggest to keep it simple:
fs: add ksys_sync_file_range helper(); remove in-kernel calls to syscall
fs: add ksys_truncate() wrapper; remove in-kernel calls to sys_truncate()
fs: add ksys_p{read,write}64() helpers; remove in-kernel calls to syscalls
fs: add ksys_fallocate() wrapper; remove in-kernel calls to sys_fallocate()
mm: add ksys_fadvise64_64() helper; remove in-kernel call to sys_fadvise64_64()
mm: add ksys_mmap_pgoff() helper; remove in-kernel calls to sys_mmap_pgoff()
mm: add ksys_readahead() helper; remove in-kernel calls to sys_readahead()
x86/ioport: add ksys_ioperm() helper; remove in-kernel calls to sys_ioperm()
Then, throw in two fixes for x86:
x86: fix sys_sigreturn() return type to be long, not unsigned long
x86/sigreturn: use SYSCALL_DEFINE0 (by Michael Tautschnig)
... and clean up the three places where many syscalls are referenced or
prototyped (kernel/sys_ni.c, include/linux/syscalls.h and
include/linux/compat.h):
kexec: move sys_kexec_load() prototype to syscalls.h
syscalls: sort syscall prototypes in include/linux/syscalls.h
net: remove compat_sys_*() prototypes from net/compat.h
syscalls: sort syscall prototypes in include/linux/compat.h
syscalls/x86: auto-create compat_sys_*() prototypes
kernel/sys_ni: sort cond_syscall() entries
kernel/sys_ni: remove {sys_,sys_compat} from cond_syscall definitions
Last but not least, add a patch by Howard McLauchlan to whitelist all syscalls
for error injection:
bpf: whitelist all syscalls for error injection (by Howard McLauchlan)
Tze whole series is available at
https://git.kernel.org/pub/scm/linux/kernel/git/brodo/linux.git syscalls-next
and I intend to push this upstream early in the v4.17-rc1 cycle.
Thanks,
Dominik
Documentation/process/adding-syscalls.rst | 34 +-
arch/alpha/kernel/osf_sys.c | 2 +-
arch/arm/kernel/sys_arm.c | 2 +-
arch/arm64/kernel/sys.c | 2 +-
arch/ia64/kernel/sys_ia64.c | 4 +-
arch/m68k/kernel/sys_m68k.c | 2 +-
arch/microblaze/kernel/sys_microblaze.c | 6 +-
arch/mips/kernel/linux32.c | 22 +-
arch/mips/kernel/syscall.c | 6 +-
arch/parisc/kernel/sys_parisc.c | 30 +-
arch/powerpc/kernel/sys_ppc32.c | 18 +-
arch/powerpc/kernel/syscalls.c | 6 +-
arch/riscv/kernel/sys_riscv.c | 4 +-
arch/s390/kernel/compat_linux.c | 37 +-
arch/s390/kernel/sys_s390.c | 2 +-
arch/sh/kernel/sys_sh.c | 4 +-
arch/sh/kernel/sys_sh32.c | 12 +-
arch/sparc/kernel/setup_32.c | 2 +-
arch/sparc/kernel/sys_sparc32.c | 26 +-
arch/sparc/kernel/sys_sparc_32.c | 6 +-
arch/sparc/kernel/sys_sparc_64.c | 2 +-
arch/um/kernel/syscall.c | 2 +-
arch/x86/entry/syscalls/syscall_32.tbl | 4 +-
arch/x86/ia32/ia32_signal.c | 1 -
arch/x86/ia32/sys_ia32.c | 50 +-
arch/x86/include/asm/sys_ia32.h | 67 --
arch/x86/include/asm/syscalls.h | 3 +-
arch/x86/kernel/ioport.c | 7 +-
arch/x86/kernel/signal.c | 5 +-
arch/x86/kernel/sys_x86_64.c | 2 +-
arch/xtensa/kernel/syscall.c | 2 +-
drivers/base/devtmpfs.c | 11 +-
drivers/tty/sysrq.c | 2 +-
drivers/tty/vt/vt_ioctl.c | 6 +-
fs/autofs4/dev-ioctl.c | 2 +-
fs/binfmt_misc.c | 2 +-
fs/dcookies.c | 11 +-
fs/eventfd.c | 9 +-
fs/eventpoll.c | 23 +-
fs/fcntl.c | 12 +-
fs/file.c | 17 +-
fs/hostfs/hostfs.h | 2 +-
fs/hostfs/hostfs_kern.c | 2 +-
fs/hostfs/hostfs_user.c | 2 +-
fs/internal.h | 14 +
fs/ioctl.c | 7 +-
fs/namei.c | 61 +-
fs/namespace.c | 19 +-
fs/notify/fanotify/fanotify_user.c | 14 +-
fs/notify/inotify/inotify_user.c | 9 +-
fs/open.c | 77 +-
fs/pipe.c | 9 +-
fs/quota/compat.c | 13 +-
fs/quota/quota.c | 10 +-
fs/read_write.c | 45 +-
fs/readdir.c | 11 +-
fs/select.c | 29 +-
fs/signalfd.c | 31 +-
fs/splice.c | 12 +-
fs/stat.c | 12 +-
fs/sync.c | 19 +-
fs/utimes.c | 25 +-
include/linux/compat.h | 644 ++++++------
include/linux/futex.h | 13 +-
include/linux/kexec.h | 4 -
include/linux/quotaops.h | 3 +
include/linux/socket.h | 37 +-
include/linux/syscalls.h | 1511 +++++++++++++++++------------
include/net/compat.h | 11 -
init/do_mounts.c | 26 +-
init/do_mounts.h | 4 +-
init/do_mounts_initrd.c | 42 +-
init/do_mounts_md.c | 29 +-
init/do_mounts_rd.c | 40 +-
init/initramfs.c | 52 +-
init/main.c | 9 +-
init/noinitramfs.c | 6 +-
ipc/msg.c | 60 +-
ipc/sem.c | 44 +-
ipc/shm.c | 28 +-
ipc/syscall.c | 58 +-
ipc/util.h | 31 +
kernel/compat.c | 55 --
kernel/exit.c | 2 +-
kernel/fork.c | 11 +-
kernel/kexec.c | 52 +-
kernel/pid_namespace.c | 6 +-
kernel/power/hibernate.c | 2 +-
kernel/power/suspend.c | 2 +-
kernel/power/user.c | 2 +-
kernel/sched/core.c | 8 +-
kernel/signal.c | 29 +-
kernel/sys.c | 74 +-
kernel/sys_ni.c | 617 +++++++-----
kernel/uid16.c | 25 +-
kernel/uid16.h | 14 +
kernel/umh.c | 4 +-
mm/fadvise.c | 10 +-
mm/mempolicy.c | 92 +-
mm/migrate.c | 39 +-
mm/mmap.c | 17 +-
mm/nommu.c | 17 +-
mm/readahead.c | 7 +-
net/compat.c | 136 ++-
net/socket.c | 234 +++--
105 files changed, 3129 insertions(+), 1868 deletions(-)
delete mode 100644 arch/x86/include/asm/sys_ia32.h
create mode 100644 kernel/uid16.h
[*] An early, not-yet-ready version and partly untested (i386, x32) of the
patches required to implement this on top of this series is available at
https://git.kernel.org/pub/scm/linux/kernel/git/brodo/linux.git syscalls-WIP
--
2.16.3
^ permalink raw reply
* [PATCH 009/109] net: socket: add __sys_sendto() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-29 11:22 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_sendto() allows us to avoid the
internal calls to the sys_sendto() syscall.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 3 +++
net/compat.c | 3 ++-
net/socket.c | 19 ++++++++++++-------
3 files changed, 17 insertions(+), 8 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 40cc93b91628..54b85abc7265 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -358,5 +358,8 @@ extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg,
extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
unsigned int flags, struct sockaddr __user *addr,
int __user *addr_len);
+extern int __sys_sendto(int fd, void __user *buff, size_t len,
+ unsigned int flags, struct sockaddr __user *addr,
+ int addr_len);
#endif /* _LINUX_SOCKET_H */
diff --git a/net/compat.c b/net/compat.c
index 2d8186c277b2..fc82982d9b84 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -838,7 +838,8 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
ret = sys_send(a0, compat_ptr(a1), a[2], a[3]);
break;
case SYS_SENDTO:
- ret = sys_sendto(a0, compat_ptr(a1), a[2], a[3], compat_ptr(a[4]), a[5]);
+ ret = __sys_sendto(a0, compat_ptr(a1), a[2], a[3],
+ compat_ptr(a[4]), a[5]);
break;
case SYS_RECV:
ret = compat_sys_recv(a0, compat_ptr(a1), a[2], a[3]);
diff --git a/net/socket.c b/net/socket.c
index 712d99d8680f..3f037a21ba5e 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1711,10 +1711,8 @@ SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr,
* space and check the user space data area is readable before invoking
* the protocol.
*/
-
-SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len,
- unsigned int, flags, struct sockaddr __user *, addr,
- int, addr_len)
+int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags,
+ struct sockaddr __user *addr, int addr_len)
{
struct socket *sock;
struct sockaddr_storage address;
@@ -1752,6 +1750,13 @@ SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len,
return err;
}
+SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len,
+ unsigned int, flags, struct sockaddr __user *, addr,
+ int, addr_len)
+{
+ return __sys_sendto(fd, buff, len, flags, addr, addr_len);
+}
+
/*
* Send a datagram down a socket.
*/
@@ -1759,7 +1764,7 @@ SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len,
SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len,
unsigned int, flags)
{
- return sys_sendto(fd, buff, len, flags, NULL, 0);
+ return __sys_sendto(fd, buff, len, flags, NULL, 0);
}
/*
@@ -2484,8 +2489,8 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
err = sys_send(a0, (void __user *)a1, a[2], a[3]);
break;
case SYS_SENDTO:
- err = sys_sendto(a0, (void __user *)a1, a[2], a[3],
- (struct sockaddr __user *)a[4], a[5]);
+ err = __sys_sendto(a0, (void __user *)a1, a[2], a[3],
+ (struct sockaddr __user *)a[4], a[5]);
break;
case SYS_RECV:
err = sys_recv(a0, (void __user *)a1, a[2], a[3]);
--
2.16.3
^ permalink raw reply related
* [PATCH 010/109] net: socket: add __sys_accept4() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-29 11:22 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_accept4() allows us to avoid the
internal calls to the sys_accept4() syscall.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 2 ++
net/compat.c | 4 ++--
net/socket.c | 20 +++++++++++++-------
3 files changed, 17 insertions(+), 9 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 54b85abc7265..6a9840271676 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -361,5 +361,7 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
extern int __sys_sendto(int fd, void __user *buff, size_t len,
unsigned int flags, struct sockaddr __user *addr,
int addr_len);
+extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
+ int __user *upeer_addrlen, int flags);
#endif /* _LINUX_SOCKET_H */
diff --git a/net/compat.c b/net/compat.c
index fc82982d9b84..0ff9f7451b6f 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -823,7 +823,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
ret = sys_listen(a0, a1);
break;
case SYS_ACCEPT:
- ret = sys_accept4(a0, compat_ptr(a1), compat_ptr(a[2]), 0);
+ ret = __sys_accept4(a0, compat_ptr(a1), compat_ptr(a[2]), 0);
break;
case SYS_GETSOCKNAME:
ret = sys_getsockname(a0, compat_ptr(a1), compat_ptr(a[2]));
@@ -873,7 +873,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
compat_ptr(a[4]));
break;
case SYS_ACCEPT4:
- ret = sys_accept4(a0, compat_ptr(a1), compat_ptr(a[2]), a[3]);
+ ret = __sys_accept4(a0, compat_ptr(a1), compat_ptr(a[2]), a[3]);
break;
default:
ret = -EINVAL;
diff --git a/net/socket.c b/net/socket.c
index 3f037a21ba5e..45f6ea0d57a5 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1519,8 +1519,8 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog)
* clean when we restucture accept also.
*/
-SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
- int __user *, upeer_addrlen, int, flags)
+int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
+ int __user *upeer_addrlen, int flags)
{
struct socket *sock, *newsock;
struct file *newfile;
@@ -1599,10 +1599,16 @@ SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
goto out_put;
}
+SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
+ int __user *, upeer_addrlen, int, flags)
+{
+ return __sys_accept4(fd, upeer_sockaddr, upeer_addrlen, flags);
+}
+
SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr,
int __user *, upeer_addrlen)
{
- return sys_accept4(fd, upeer_sockaddr, upeer_addrlen, 0);
+ return __sys_accept4(fd, upeer_sockaddr, upeer_addrlen, 0);
}
/*
@@ -2469,8 +2475,8 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
err = sys_listen(a0, a1);
break;
case SYS_ACCEPT:
- err = sys_accept4(a0, (struct sockaddr __user *)a1,
- (int __user *)a[2], 0);
+ err = __sys_accept4(a0, (struct sockaddr __user *)a1,
+ (int __user *)a[2], 0);
break;
case SYS_GETSOCKNAME:
err =
@@ -2525,8 +2531,8 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
(struct timespec __user *)a[4]);
break;
case SYS_ACCEPT4:
- err = sys_accept4(a0, (struct sockaddr __user *)a1,
- (int __user *)a[2], a[3]);
+ err = __sys_accept4(a0, (struct sockaddr __user *)a1,
+ (int __user *)a[2], a[3]);
break;
default:
err = -EINVAL;
--
2.16.3
^ permalink raw reply related
* [PATCH 011/109] net: socket: add __sys_socket() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-29 11:22 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_socket() allows us to avoid the
internal calls to the sys_socket() syscall.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 1 +
net/compat.c | 2 +-
net/socket.c | 9 +++++++--
3 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 6a9840271676..f8d040434a13 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -363,5 +363,6 @@ extern int __sys_sendto(int fd, void __user *buff, size_t len,
int addr_len);
extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
int __user *upeer_addrlen, int flags);
+extern int __sys_socket(int family, int type, int protocol);
#endif /* _LINUX_SOCKET_H */
diff --git a/net/compat.c b/net/compat.c
index 0ff9f7451b6f..5b3b74c5812e 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -811,7 +811,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
switch (call) {
case SYS_SOCKET:
- ret = sys_socket(a0, a1, a[2]);
+ ret = __sys_socket(a0, a1, a[2]);
break;
case SYS_BIND:
ret = sys_bind(a0, compat_ptr(a1), a[2]);
diff --git a/net/socket.c b/net/socket.c
index 45f6ea0d57a5..07f379e50def 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1332,7 +1332,7 @@ int sock_create_kern(struct net *net, int family, int type, int protocol, struct
}
EXPORT_SYMBOL(sock_create_kern);
-SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol)
+int __sys_socket(int family, int type, int protocol)
{
int retval;
struct socket *sock;
@@ -1359,6 +1359,11 @@ SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol)
return sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK));
}
+SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol)
+{
+ return __sys_socket(family, type, protocol);
+}
+
/*
* Create a pair of connected sockets.
*/
@@ -2463,7 +2468,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
switch (call) {
case SYS_SOCKET:
- err = sys_socket(a0, a1, a[2]);
+ err = __sys_socket(a0, a1, a[2]);
break;
case SYS_BIND:
err = sys_bind(a0, (struct sockaddr __user *)a1, a[2]);
--
2.16.3
^ permalink raw reply related
* [PATCH 012/109] net: socket: add __sys_bind() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-29 11:22 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_bind() allows us to avoid the
internal calls to the sys_bind() syscall.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 1 +
net/compat.c | 2 +-
net/socket.c | 9 +++++++--
3 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index f8d040434a13..e9cee272da13 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -364,5 +364,6 @@ extern int __sys_sendto(int fd, void __user *buff, size_t len,
extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
int __user *upeer_addrlen, int flags);
extern int __sys_socket(int family, int type, int protocol);
+extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen);
#endif /* _LINUX_SOCKET_H */
diff --git a/net/compat.c b/net/compat.c
index 5b3b74c5812e..bba555b1d863 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -814,7 +814,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
ret = __sys_socket(a0, a1, a[2]);
break;
case SYS_BIND:
- ret = sys_bind(a0, compat_ptr(a1), a[2]);
+ ret = __sys_bind(a0, compat_ptr(a1), a[2]);
break;
case SYS_CONNECT:
ret = sys_connect(a0, compat_ptr(a1), a[2]);
diff --git a/net/socket.c b/net/socket.c
index 07f379e50def..291cdae97341 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1462,7 +1462,7 @@ SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol,
* the protocol layer (having also checked the address is ok).
*/
-SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen)
+int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen)
{
struct socket *sock;
struct sockaddr_storage address;
@@ -1485,6 +1485,11 @@ SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen)
return err;
}
+SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen)
+{
+ return __sys_bind(fd, umyaddr, addrlen);
+}
+
/*
* Perform a listen. Basically, we allow the protocol to do anything
* necessary for a listen, and if that works, we mark the socket as
@@ -2471,7 +2476,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
err = __sys_socket(a0, a1, a[2]);
break;
case SYS_BIND:
- err = sys_bind(a0, (struct sockaddr __user *)a1, a[2]);
+ err = __sys_bind(a0, (struct sockaddr __user *)a1, a[2]);
break;
case SYS_CONNECT:
err = sys_connect(a0, (struct sockaddr __user *)a1, a[2]);
--
2.16.3
^ permalink raw reply related
* [PATCH 013/109] net: socket: add __sys_connect() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-29 11:22 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_connect() allows us to avoid the
internal calls to the sys_connect() syscall.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 2 ++
net/compat.c | 2 +-
net/socket.c | 11 ++++++++---
3 files changed, 11 insertions(+), 4 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index e9cee272da13..7daa344d7320 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -365,5 +365,7 @@ extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
int __user *upeer_addrlen, int flags);
extern int __sys_socket(int family, int type, int protocol);
extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen);
+extern int __sys_connect(int fd, struct sockaddr __user *uservaddr,
+ int addrlen);
#endif /* _LINUX_SOCKET_H */
diff --git a/net/compat.c b/net/compat.c
index bba555b1d863..7ab6352268f3 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -817,7 +817,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
ret = __sys_bind(a0, compat_ptr(a1), a[2]);
break;
case SYS_CONNECT:
- ret = sys_connect(a0, compat_ptr(a1), a[2]);
+ ret = __sys_connect(a0, compat_ptr(a1), a[2]);
break;
case SYS_LISTEN:
ret = sys_listen(a0, a1);
diff --git a/net/socket.c b/net/socket.c
index 291cdae97341..64bdfdf6c6e7 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1633,8 +1633,7 @@ SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr,
* include the -EINPROGRESS status for such sockets.
*/
-SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr,
- int, addrlen)
+int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen)
{
struct socket *sock;
struct sockaddr_storage address;
@@ -1660,6 +1659,12 @@ SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr,
return err;
}
+SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr,
+ int, addrlen)
+{
+ return __sys_connect(fd, uservaddr, addrlen);
+}
+
/*
* Get the local address ('name') of a socket object. Move the obtained
* name to user space.
@@ -2479,7 +2484,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
err = __sys_bind(a0, (struct sockaddr __user *)a1, a[2]);
break;
case SYS_CONNECT:
- err = sys_connect(a0, (struct sockaddr __user *)a1, a[2]);
+ err = __sys_connect(a0, (struct sockaddr __user *)a1, a[2]);
break;
case SYS_LISTEN:
err = sys_listen(a0, a1);
--
2.16.3
^ permalink raw reply related
* [PATCH 014/109] net: socket: add __sys_listen() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-29 11:22 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_listen() allows us to avoid the
internal calls to the sys_listen() syscall.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 1 +
net/compat.c | 2 +-
net/socket.c | 9 +++++++--
3 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 7daa344d7320..7e37af25509d 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -367,5 +367,6 @@ extern int __sys_socket(int family, int type, int protocol);
extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen);
extern int __sys_connect(int fd, struct sockaddr __user *uservaddr,
int addrlen);
+extern int __sys_listen(int fd, int backlog);
#endif /* _LINUX_SOCKET_H */
diff --git a/net/compat.c b/net/compat.c
index 7ab6352268f3..c80cb973f383 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -820,7 +820,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
ret = __sys_connect(a0, compat_ptr(a1), a[2]);
break;
case SYS_LISTEN:
- ret = sys_listen(a0, a1);
+ ret = __sys_listen(a0, a1);
break;
case SYS_ACCEPT:
ret = __sys_accept4(a0, compat_ptr(a1), compat_ptr(a[2]), 0);
diff --git a/net/socket.c b/net/socket.c
index 64bdfdf6c6e7..67d9d70a4734 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1496,7 +1496,7 @@ SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen)
* ready for listening.
*/
-SYSCALL_DEFINE2(listen, int, fd, int, backlog)
+int __sys_listen(int fd, int backlog)
{
struct socket *sock;
int err, fput_needed;
@@ -1517,6 +1517,11 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog)
return err;
}
+SYSCALL_DEFINE2(listen, int, fd, int, backlog)
+{
+ return __sys_listen(fd, backlog);
+}
+
/*
* For accept, we attempt to create a new socket, set up the link
* with the client, wake up the client, then return the new
@@ -2487,7 +2492,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
err = __sys_connect(a0, (struct sockaddr __user *)a1, a[2]);
break;
case SYS_LISTEN:
- err = sys_listen(a0, a1);
+ err = __sys_listen(a0, a1);
break;
case SYS_ACCEPT:
err = __sys_accept4(a0, (struct sockaddr __user *)a1,
--
2.16.3
^ permalink raw reply related
* [PATCH 015/109] net: socket: add __sys_getsockname() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-29 11:22 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_getsockname() allows us to avoid the
internal calls to the sys_getsockname() syscall.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 2 ++
net/compat.c | 2 +-
net/socket.c | 14 ++++++++++----
3 files changed, 13 insertions(+), 5 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 7e37af25509d..ef0226a61b03 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -368,5 +368,7 @@ extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen);
extern int __sys_connect(int fd, struct sockaddr __user *uservaddr,
int addrlen);
extern int __sys_listen(int fd, int backlog);
+extern int __sys_getsockname(int fd, struct sockaddr __user *usockaddr,
+ int __user *usockaddr_len);
#endif /* _LINUX_SOCKET_H */
diff --git a/net/compat.c b/net/compat.c
index c80cb973f383..efd28d02608c 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -826,7 +826,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
ret = __sys_accept4(a0, compat_ptr(a1), compat_ptr(a[2]), 0);
break;
case SYS_GETSOCKNAME:
- ret = sys_getsockname(a0, compat_ptr(a1), compat_ptr(a[2]));
+ ret = __sys_getsockname(a0, compat_ptr(a1), compat_ptr(a[2]));
break;
case SYS_GETPEERNAME:
ret = sys_getpeername(a0, compat_ptr(a1), compat_ptr(a[2]));
diff --git a/net/socket.c b/net/socket.c
index 67d9d70a4734..b61e0d20f37b 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1675,8 +1675,8 @@ SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr,
* name to user space.
*/
-SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr,
- int __user *, usockaddr_len)
+int __sys_getsockname(int fd, struct sockaddr __user *usockaddr,
+ int __user *usockaddr_len)
{
struct socket *sock;
struct sockaddr_storage address;
@@ -1701,6 +1701,12 @@ SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr,
return err;
}
+SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr,
+ int __user *, usockaddr_len)
+{
+ return __sys_getsockname(fd, usockaddr, usockaddr_len);
+}
+
/*
* Get the remote address ('name') of a socket object. Move the obtained
* name to user space.
@@ -2500,8 +2506,8 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
break;
case SYS_GETSOCKNAME:
err =
- sys_getsockname(a0, (struct sockaddr __user *)a1,
- (int __user *)a[2]);
+ __sys_getsockname(a0, (struct sockaddr __user *)a1,
+ (int __user *)a[2]);
break;
case SYS_GETPEERNAME:
err =
--
2.16.3
^ permalink raw reply related
* [PATCH 016/109] net: socket: add __sys_getpeername() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-29 11:22 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_getpeername() allows us to avoid the
internal calls to the sys_getpeername() syscall.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 2 ++
net/compat.c | 2 +-
net/socket.c | 14 ++++++++++----
3 files changed, 13 insertions(+), 5 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index ef0226a61b03..9ba003e92fea 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -370,5 +370,7 @@ extern int __sys_connect(int fd, struct sockaddr __user *uservaddr,
extern int __sys_listen(int fd, int backlog);
extern int __sys_getsockname(int fd, struct sockaddr __user *usockaddr,
int __user *usockaddr_len);
+extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr,
+ int __user *usockaddr_len);
#endif /* _LINUX_SOCKET_H */
diff --git a/net/compat.c b/net/compat.c
index efd28d02608c..74017f618eb1 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -829,7 +829,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
ret = __sys_getsockname(a0, compat_ptr(a1), compat_ptr(a[2]));
break;
case SYS_GETPEERNAME:
- ret = sys_getpeername(a0, compat_ptr(a1), compat_ptr(a[2]));
+ ret = __sys_getpeername(a0, compat_ptr(a1), compat_ptr(a[2]));
break;
case SYS_SOCKETPAIR:
ret = sys_socketpair(a0, a1, a[2], compat_ptr(a[3]));
diff --git a/net/socket.c b/net/socket.c
index b61e0d20f37b..007fb9483279 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1712,8 +1712,8 @@ SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr,
* name to user space.
*/
-SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr,
- int __user *, usockaddr_len)
+int __sys_getpeername(int fd, struct sockaddr __user *usockaddr,
+ int __user *usockaddr_len)
{
struct socket *sock;
struct sockaddr_storage address;
@@ -1738,6 +1738,12 @@ SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr,
return err;
}
+SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr,
+ int __user *, usockaddr_len)
+{
+ return __sys_getpeername(fd, usockaddr, usockaddr_len);
+}
+
/*
* Send a datagram to a given address. We move the address into kernel
* space and check the user space data area is readable before invoking
@@ -2511,8 +2517,8 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
break;
case SYS_GETPEERNAME:
err =
- sys_getpeername(a0, (struct sockaddr __user *)a1,
- (int __user *)a[2]);
+ __sys_getpeername(a0, (struct sockaddr __user *)a1,
+ (int __user *)a[2]);
break;
case SYS_SOCKETPAIR:
err = sys_socketpair(a0, a1, a[2], (int __user *)a[3]);
--
2.16.3
^ permalink raw reply related
* [PATCH 017/109] net: socket: add __sys_socketpair() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-29 11:22 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_socketpair() allows us to avoid the
internal calls to the sys_socketpair() syscall.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 2 ++
net/compat.c | 2 +-
net/socket.c | 11 ++++++++---
3 files changed, 11 insertions(+), 4 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 9ba003e92fea..dbdddf0d079e 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -372,5 +372,7 @@ extern int __sys_getsockname(int fd, struct sockaddr __user *usockaddr,
int __user *usockaddr_len);
extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr,
int __user *usockaddr_len);
+extern int __sys_socketpair(int family, int type, int protocol,
+ int __user *usockvec);
#endif /* _LINUX_SOCKET_H */
diff --git a/net/compat.c b/net/compat.c
index 74017f618eb1..04db26316438 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -832,7 +832,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
ret = __sys_getpeername(a0, compat_ptr(a1), compat_ptr(a[2]));
break;
case SYS_SOCKETPAIR:
- ret = sys_socketpair(a0, a1, a[2], compat_ptr(a[3]));
+ ret = __sys_socketpair(a0, a1, a[2], compat_ptr(a[3]));
break;
case SYS_SEND:
ret = sys_send(a0, compat_ptr(a1), a[2], a[3]);
diff --git a/net/socket.c b/net/socket.c
index 007fb9483279..5861821f46f5 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1368,8 +1368,7 @@ SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol)
* Create a pair of connected sockets.
*/
-SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol,
- int __user *, usockvec)
+int __sys_socketpair(int family, int type, int protocol, int __user *usockvec)
{
struct socket *sock1, *sock2;
int fd1, fd2, err;
@@ -1454,6 +1453,12 @@ SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol,
return err;
}
+SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol,
+ int __user *, usockvec)
+{
+ return __sys_socketpair(family, type, protocol, usockvec);
+}
+
/*
* Bind a name to a socket. Nothing much to do here since it's
* the protocol's responsibility to handle the local address.
@@ -2521,7 +2526,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
(int __user *)a[2]);
break;
case SYS_SOCKETPAIR:
- err = sys_socketpair(a0, a1, a[2], (int __user *)a[3]);
+ err = __sys_socketpair(a0, a1, a[2], (int __user *)a[3]);
break;
case SYS_SEND:
err = sys_send(a0, (void __user *)a1, a[2], a[3]);
--
2.16.3
^ permalink raw reply related
* [PATCH 018/109] net: socket: add __sys_shutdown() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-29 11:22 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_shutdown() allows us to avoid the
internal calls to the sys_shutdown() syscall.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 1 +
net/compat.c | 2 +-
net/socket.c | 9 +++++++--
3 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index dbdddf0d079e..b205138b69f1 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -374,5 +374,6 @@ extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr,
int __user *usockaddr_len);
extern int __sys_socketpair(int family, int type, int protocol,
int __user *usockvec);
+extern int __sys_shutdown(int fd, int how);
#endif /* _LINUX_SOCKET_H */
diff --git a/net/compat.c b/net/compat.c
index 04db26316438..f1ec23e9dfce 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -849,7 +849,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
compat_ptr(a[4]), compat_ptr(a[5]));
break;
case SYS_SHUTDOWN:
- ret = sys_shutdown(a0, a1);
+ ret = __sys_shutdown(a0, a1);
break;
case SYS_SETSOCKOPT:
ret = compat_sys_setsockopt(a0, a1, a[2],
diff --git a/net/socket.c b/net/socket.c
index 5861821f46f5..ad5dfd6a1d59 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1942,7 +1942,7 @@ SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
* Shutdown a socket.
*/
-SYSCALL_DEFINE2(shutdown, int, fd, int, how)
+int __sys_shutdown(int fd, int how)
{
int err, fput_needed;
struct socket *sock;
@@ -1957,6 +1957,11 @@ SYSCALL_DEFINE2(shutdown, int, fd, int, how)
return err;
}
+SYSCALL_DEFINE2(shutdown, int, fd, int, how)
+{
+ return __sys_shutdown(fd, how);
+}
+
/* A couple of helpful macros for getting the address of the 32/64 bit
* fields which are the same type (int / unsigned) on our platforms.
*/
@@ -2544,7 +2549,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
(int __user *)a[5]);
break;
case SYS_SHUTDOWN:
- err = sys_shutdown(a0, a1);
+ err = __sys_shutdown(a0, a1);
break;
case SYS_SETSOCKOPT:
err = sys_setsockopt(a0, a1, a[2], (char __user *)a[3], a[4]);
--
2.16.3
^ permalink raw reply related
* [PATCH 019/109] net: socket: add __sys_setsockopt() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-29 11:22 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_setsockopt() allows us to avoid the
internal calls to the sys_setsockopt() syscall.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 1 +
net/socket.c | 13 ++++++++++---
2 files changed, 11 insertions(+), 3 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index b205138b69f1..cad120e4ed4b 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -376,4 +376,5 @@ extern int __sys_socketpair(int family, int type, int protocol,
int __user *usockvec);
extern int __sys_shutdown(int fd, int how);
+
#endif /* _LINUX_SOCKET_H */
diff --git a/net/socket.c b/net/socket.c
index ad5dfd6a1d59..5dd2e39a6cd4 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1878,8 +1878,8 @@ SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size,
* to pass the user mode parameter for the protocols to sort out.
*/
-SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
- char __user *, optval, int, optlen)
+static int __sys_setsockopt(int fd, int level, int optname,
+ char __user *optval, int optlen)
{
int err, fput_needed;
struct socket *sock;
@@ -1907,6 +1907,12 @@ SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
return err;
}
+SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
+ char __user *, optval, int, optlen)
+{
+ return __sys_setsockopt(fd, level, optname, optval, optlen);
+}
+
/*
* Get a socket option. Because we don't know the option lengths we have
* to pass a user mode parameter for the protocols to sort out.
@@ -2552,7 +2558,8 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
err = __sys_shutdown(a0, a1);
break;
case SYS_SETSOCKOPT:
- err = sys_setsockopt(a0, a1, a[2], (char __user *)a[3], a[4]);
+ err = __sys_setsockopt(a0, a1, a[2], (char __user *)a[3],
+ a[4]);
break;
case SYS_GETSOCKOPT:
err =
--
2.16.3
^ permalink raw reply related
* [PATCH 020/109] net: socket: add __sys_getsockopt() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-29 11:22 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_getsockopt() allows us to avoid the
internal calls to the sys_getsockopt() syscall.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
net/socket.c | 14 ++++++++++----
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/net/socket.c b/net/socket.c
index 5dd2e39a6cd4..a05289b1f863 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1918,8 +1918,8 @@ SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
* to pass a user mode parameter for the protocols to sort out.
*/
-SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
- char __user *, optval, int __user *, optlen)
+static int __sys_getsockopt(int fd, int level, int optname,
+ char __user *optval, int __user *optlen)
{
int err, fput_needed;
struct socket *sock;
@@ -1944,6 +1944,12 @@ SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
return err;
}
+SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
+ char __user *, optval, int __user *, optlen)
+{
+ return __sys_getsockopt(fd, level, optname, optval, optlen);
+}
+
/*
* Shutdown a socket.
*/
@@ -2563,8 +2569,8 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
break;
case SYS_GETSOCKOPT:
err =
- sys_getsockopt(a0, a1, a[2], (char __user *)a[3],
- (int __user *)a[4]);
+ __sys_getsockopt(a0, a1, a[2], (char __user *)a[3],
+ (int __user *)a[4]);
break;
case SYS_SENDMSG:
err = sys_sendmsg(a0, (struct user_msghdr __user *)a1, a[2]);
--
2.16.3
^ 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