* [PATCH 1/4] mfd: altera-sysmgr: Add SOCFPGA System Manager
From: thor.thayer @ 2018-09-24 22:09 UTC (permalink / raw)
To: lee.jones, peppe.cavallaro, dinguyen, linux, alexandre.torgue,
joabreu
Cc: thor.thayer, davem, mchehab+samsung, catalin.marinas, akpm, arnd,
aisheng.dong, linux-kernel, netdev, linux-arm-kernel
In-Reply-To: <1537826946-18942-1-git-send-email-thor.thayer@linux.intel.com>
From: Thor Thayer <thor.thayer@linux.intel.com>
The SOCFPGA System Manager register block aggregates different
peripheral functions into one area.
On 32 bit ARM parts, the syscon driver is used for accesses.
On 64 bit ARM parts, the System Manager can only be accessed by
EL3 secure mode. Since a SMC call to EL3 is required, this new
driver uses regmaps similar to syscon to handle the SMC call.
Since regmaps abstract out the underlying register access, the
changes to drivers accessing the System Manager are minimal.
Signed-off-by: Thor Thayer <thor.thayer@linux.intel.com>
---
MAINTAINERS | 6 +
drivers/mfd/Kconfig | 9 ++
drivers/mfd/Makefile | 1 +
drivers/mfd/altera-sysmgr.c | 310 ++++++++++++++++++++++++++++++++++++++
include/linux/mfd/altera-sysmgr.h | 113 ++++++++++++++
5 files changed, 439 insertions(+)
create mode 100644 drivers/mfd/altera-sysmgr.c
create mode 100644 include/linux/mfd/altera-sysmgr.h
diff --git a/MAINTAINERS b/MAINTAINERS
index d9e6d86488df..bda6b2173cc6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -692,6 +692,12 @@ L: linux-gpio@vger.kernel.org
S: Maintained
F: drivers/gpio/gpio-altera.c
+ALTERA SYSTEM MANAGER DRIVER
+M: Thor Thayer <thor.thayer@linux.intel.com>
+S: Maintained
+F: drivers/mfd/altera-sysmgr.c
+F: include/linux/mfd/altera-sysgmr.h
+
ALTERA SYSTEM RESOURCE DRIVER FOR ARRIA10 DEVKIT
M: Thor Thayer <thor.thayer@linux.intel.com>
S: Maintained
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index f3a5f8d02790..1192a25186c7 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -29,6 +29,15 @@ config MFD_ALTERA_A10SR
accessing the external gpio extender (LEDs & buttons) and
power supply alarms (hwmon).
+config MFD_ALTERA_SYSMGR
+ bool "Altera SOCFPGA System Manager"
+ depends on (ARCH_SOCFPGA || ARCH_STRATIX10) && OF
+ select MFD_SYSCON
+ help
+ Select this to get System Manager support for all Altera branded
+ SOCFPGAs. The SOCFPGA System Manager handles all SOCFPGAs by
+ using syscon for ARM32 parts and SMC calls to EL3 for ARM64 parts.
+
config MFD_ACT8945A
tristate "Active-semi ACT8945A"
select MFD_CORE
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 5856a9489cbd..bc1508e3ff7b 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -232,6 +232,7 @@ obj-$(CONFIG_INTEL_SOC_PMIC_CHTDC_TI) += intel_soc_pmic_chtdc_ti.o
obj-$(CONFIG_MFD_MT6397) += mt6397-core.o
obj-$(CONFIG_MFD_ALTERA_A10SR) += altera-a10sr.o
+obj-$(CONFIG_MFD_ALTERA_SYSMGR) += altera-sysmgr.o
obj-$(CONFIG_MFD_SUN4I_GPADC) += sun4i-gpadc.o
obj-$(CONFIG_MFD_STM32_LPTIMER) += stm32-lptimer.o
diff --git a/drivers/mfd/altera-sysmgr.c b/drivers/mfd/altera-sysmgr.c
new file mode 100644
index 000000000000..29b0bfcb3f69
--- /dev/null
+++ b/drivers/mfd/altera-sysmgr.c
@@ -0,0 +1,310 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2017-2018, Intel Corporation.
+ * Copyright (C) 2012 Freescale Semiconductor, Inc.
+ * Copyright (C) 2012 Linaro Ltd.
+ *
+ * Based on syscon driver.
+ */
+
+#include <linux/arm-smccc.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/mfd/altera-sysmgr.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+static struct platform_driver sysmgr_driver;
+
+/**
+ * struct altr_sysmgr - Altera SOCFPGA System Manager
+ * @regmap: the regmap used for System Manager accesses.
+ * @base : the base address for the System Manager
+ */
+struct altr_sysmgr {
+ struct regmap *regmap;
+ void __iomem *base;
+};
+
+/**
+ * Only 1 instance of System Manager is needed but many
+ * consumers will want to access it with the matching
+ * functions below.
+ */
+static struct altr_sysmgr *p_sysmgr;
+
+/**
+ * s10_protected_reg_write
+ * Write to a protected SMC register.
+ * @base: Base address of System Manager
+ * @reg: Address offset of register
+ * @val: Value to write
+ * Return: INTEL_SIP_SMC_STATUS_OK (0) on success
+ * INTEL_SIP_SMC_REG_ERROR on error
+ * INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION if not supported
+ */
+static int s10_protected_reg_write(void __iomem *base,
+ unsigned int reg, unsigned int val)
+{
+ struct arm_smccc_res result;
+ unsigned long sysmgr_base = (unsigned long)base;
+
+ arm_smccc_smc(INTEL_SIP_SMC_REG_WRITE, sysmgr_base + reg,
+ val, 0, 0, 0, 0, 0, &result);
+
+ return (int)result.a0;
+}
+
+/**
+ * s10_protected_reg_read
+ * Read the status of a protected SMC register
+ * @base: Base address of System Manager.
+ * @reg: Address of register
+ * @val: Value read.
+ * Return: INTEL_SIP_SMC_STATUS_OK (0) on success
+ * INTEL_SIP_SMC_REG_ERROR on error
+ * INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION if not supported
+ */
+static int s10_protected_reg_read(void __iomem *base,
+ unsigned int reg, unsigned int *val)
+{
+ struct arm_smccc_res result;
+ unsigned long sysmgr_base = (unsigned long)base;
+
+ arm_smccc_smc(INTEL_SIP_SMC_REG_READ, sysmgr_base + reg,
+ 0, 0, 0, 0, 0, 0, &result);
+
+ *val = (unsigned int)result.a1;
+
+ return (int)result.a0;
+}
+
+static const struct regmap_config s10_sysmgr_regmap_cfg = {
+ .name = "s10_sysmgr",
+ .reg_bits = 32,
+ .reg_stride = 4,
+ .val_bits = 32,
+ .reg_read = s10_protected_reg_read,
+ .reg_write = s10_protected_reg_write,
+ .fast_io = true,
+ .use_single_rw = true,
+};
+
+/**
+ * socfpga_is_s10
+ * Determine if running on Stratix10 platform.
+ * Return: True if running Stratix10, otherwise false.
+ */
+static int socfpga_is_s10(void)
+{
+ return of_machine_is_compatible("altr,socfpga-stratix10");
+}
+
+/**
+ * of_sysmgr_register
+ * Create and register the Altera System Manager regmap.
+ * Return: Pointer to new sysmgr on success.
+ * Pointer error on failure.
+ */
+static struct altr_sysmgr *of_sysmgr_register(struct device_node *np)
+{
+ struct altr_sysmgr *sysmgr;
+ struct regmap *regmap;
+ u32 reg_io_width;
+ int ret;
+ struct regmap_config sysmgr_config = s10_sysmgr_regmap_cfg;
+ struct resource res;
+
+ if (!of_device_is_compatible(np, "altr,sys-mgr"))
+ return ERR_PTR(-EINVAL);
+
+ sysmgr = kzalloc(sizeof(*sysmgr), GFP_KERNEL);
+ if (!sysmgr)
+ return ERR_PTR(-ENOMEM);
+
+ if (of_address_to_resource(np, 0, &res)) {
+ ret = -ENOMEM;
+ goto err_map;
+ }
+
+ /* Need physical address for SMCC call */
+ sysmgr->base = (void __iomem *)res.start;
+
+ /*
+ * search for reg-io-width property in DT. If it is not provided,
+ * default to 4 bytes. regmap_init will return an error if values
+ * are invalid so there is no need to check them here.
+ */
+ ret = of_property_read_u32(np, "reg-io-width", ®_io_width);
+ if (ret)
+ reg_io_width = 4;
+
+ sysmgr_config.reg_stride = reg_io_width;
+ sysmgr_config.val_bits = reg_io_width * 8;
+ sysmgr_config.max_register = resource_size(&res) - reg_io_width;
+
+ regmap = regmap_init(NULL, NULL, sysmgr->base, &sysmgr_config);
+ if (IS_ERR(regmap)) {
+ pr_err("regmap init failed\n");
+ ret = PTR_ERR(regmap);
+ goto err_map;
+ }
+
+ sysmgr->regmap = regmap;
+
+ p_sysmgr = sysmgr;
+
+ return sysmgr;
+
+err_map:
+ kfree(sysmgr);
+ return ERR_PTR(ret);
+}
+
+struct regmap *altr_sysmgr_node_to_regmap(struct device_node *np)
+{
+ struct altr_sysmgr *sysmgr = NULL;
+
+ if (!socfpga_is_s10())
+ return syscon_node_to_regmap(np);
+
+ if (!p_sysmgr)
+ sysmgr = of_sysmgr_register(np);
+ else
+ sysmgr = p_sysmgr;
+
+ if (IS_ERR_OR_NULL(sysmgr))
+ return ERR_CAST(sysmgr);
+
+ return sysmgr->regmap;
+}
+EXPORT_SYMBOL_GPL(altr_sysmgr_node_to_regmap);
+
+struct regmap *altr_sysmgr_regmap_lookup_by_compatible(const char *s)
+{
+ struct device_node *sysmgr_np;
+ struct regmap *regmap;
+
+ if (!socfpga_is_s10())
+ return syscon_regmap_lookup_by_compatible(s);
+
+ sysmgr_np = of_find_compatible_node(NULL, NULL, s);
+ if (!sysmgr_np)
+ return ERR_PTR(-ENODEV);
+
+ regmap = altr_sysmgr_node_to_regmap(sysmgr_np);
+ of_node_put(sysmgr_np);
+
+ return regmap;
+}
+EXPORT_SYMBOL_GPL(altr_sysmgr_regmap_lookup_by_compatible);
+
+static int sysmgr_match_pdevname(struct device *dev, void *data)
+{
+ return !strcmp(dev_name(dev), (const char *)data);
+}
+
+struct regmap *altr_sysmgr_regmap_lookup_by_pdevname(const char *s)
+{
+ struct device *dev;
+ struct altr_sysmgr *sysmgr;
+
+ if (!socfpga_is_s10())
+ return syscon_regmap_lookup_by_pdevname(s);
+
+ dev = driver_find_device(&sysmgr_driver.driver, NULL, (void *)s,
+ sysmgr_match_pdevname);
+ if (!dev)
+ return ERR_PTR(-EPROBE_DEFER);
+
+ sysmgr = dev_get_drvdata(dev);
+
+ return sysmgr->regmap;
+}
+EXPORT_SYMBOL_GPL(altr_sysmgr_regmap_lookup_by_pdevname);
+
+struct regmap *altr_sysmgr_regmap_lookup_by_phandle(struct device_node *np,
+ const char *property)
+{
+ struct device_node *sysmgr_np;
+ struct regmap *regmap;
+
+ if (!socfpga_is_s10())
+ return syscon_regmap_lookup_by_phandle(np, property);
+
+ if (property)
+ sysmgr_np = of_parse_phandle(np, property, 0);
+ else
+ sysmgr_np = np;
+
+ if (!sysmgr_np)
+ return ERR_PTR(-ENODEV);
+
+ regmap = altr_sysmgr_node_to_regmap(sysmgr_np);
+ of_node_put(sysmgr_np);
+
+ return regmap;
+}
+EXPORT_SYMBOL_GPL(altr_sysmgr_regmap_lookup_by_phandle);
+
+static int sysmgr_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct altr_sysmgr *sysmgr;
+ struct resource *res;
+
+ if (!socfpga_is_s10())
+ return -ENODEV;
+
+ /* Skip Initialization if already created */
+ if (p_sysmgr)
+ goto finish;
+
+ sysmgr = of_sysmgr_register(pdev->dev.of_node);
+ if (IS_ERR_OR_NULL(sysmgr)) {
+ dev_err(dev, "regmap init failed\n");
+ return -ENODEV;
+ }
+
+finish:
+ platform_set_drvdata(pdev, p_sysmgr);
+
+ dev_dbg(dev, "regmap %pR registered\n", res);
+
+ return 0;
+}
+
+static const struct of_device_id altr_sysmgr_of_match[] = {
+ { .compatible = "altr,sys-mgr" },
+ {},
+};
+MODULE_DEVICE_TABLE(of, altr_sysmgr_of_match);
+
+static struct platform_driver altr_sysmgr_driver = {
+ .probe = sysmgr_probe,
+ .driver = {
+ .name = "altr,system_manager",
+ .of_match_table = altr_sysmgr_of_match,
+ },
+};
+
+static int __init altr_sysmgr_init(void)
+{
+ return platform_driver_register(&altr_sysmgr_driver);
+}
+core_initcall(altr_sysmgr_init);
+
+static void __exit altr_sysmgr_exit(void)
+{
+ platform_driver_unregister(&altr_sysmgr_driver);
+}
+module_exit(altr_sysmgr_exit);
+
+MODULE_AUTHOR("Thor Thayer <>");
+MODULE_DESCRIPTION("SOCFPGA System Manager driver");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/mfd/altera-sysmgr.h b/include/linux/mfd/altera-sysmgr.h
new file mode 100644
index 000000000000..b82116706319
--- /dev/null
+++ b/include/linux/mfd/altera-sysmgr.h
@@ -0,0 +1,113 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 Intel Corporation
+ * Copyright (C) 2012 Freescale Semiconductor, Inc.
+ * Copyright (C) 2012 Linaro Ltd.
+ */
+
+#ifndef __LINUX_MFD_ALTERA_SYSMGR_H__
+#define __LINUX_MFD_ALTERA_SYSMGR_H__
+
+#include <linux/err.h>
+#include <linux/errno.h>
+
+struct device_node;
+
+#ifdef CONFIG_MFD_ALTERA_SYSMGR
+struct regmap *altr_sysmgr_node_to_regmap(struct device_node *np);
+struct regmap *altr_sysmgr_regmap_lookup_by_compatible(const char *s);
+struct regmap *altr_sysmgr_regmap_lookup_by_pdevname(const char *s);
+struct regmap *altr_sysmgr_regmap_lookup_by_phandle(struct device_node *np,
+ const char *property);
+
+/*
+ * Functions specified by ARM SMC Calling convention:
+ *
+ * FAST call executes atomic operations, returns when the requested operation
+ * has completed.
+ * STD call starts a operation which can be preempted by a non-secure
+ * interrupt.
+ *
+ * a0..a7 is used as register names in the descriptions below, on arm32
+ * that translates to r0..r7 and on arm64 to w0..w7.
+ */
+
+#define INTEL_SIP_SMC_STD_CALL_VAL(func_num) \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_STD_CALL, ARM_SMCCC_SMC_64, \
+ ARM_SMCCC_OWNER_SIP, (func_num))
+
+#define INTEL_SIP_SMC_FAST_CALL_VAL(func_num) \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, ARM_SMCCC_SMC_64, \
+ ARM_SMCCC_OWNER_SIP, (func_num))
+
+#define INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION 0xFFFFFFFF
+#define INTEL_SIP_SMC_STATUS_OK 0x0
+#define INTEL_SIP_SMC_REG_ERROR 0x5
+
+/*
+ * Request INTEL_SIP_SMC_REG_READ
+ *
+ * Read a protected register using SMCCC
+ *
+ * Call register usage:
+ * a0: INTEL_SIP_SMC_REG_READ.
+ * a1: register address.
+ * a2-7: not used.
+ *
+ * Return status:
+ * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_REG_ERROR, or
+ * INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION
+ * a1: Value in the register
+ * a2-3: not used.
+ */
+#define INTEL_SIP_SMC_FUNCID_REG_READ 7
+#define INTEL_SIP_SMC_REG_READ \
+ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_REG_READ)
+
+/*
+ * Request INTEL_SIP_SMC_REG_WRITE
+ *
+ * Write a protected register using SMCCC
+ *
+ * Call register usage:
+ * a0: INTEL_SIP_SMC_REG_WRITE.
+ * a1: register address
+ * a2: value to program into register.
+ * a3-7: not used.
+ *
+ * Return status:
+ * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_REG_ERROR, or
+ * INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION
+ * a1-3: not used.
+ */
+#define INTEL_SIP_SMC_FUNCID_REG_WRITE 8
+#define INTEL_SIP_SMC_REG_WRITE \
+ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_REG_WRITE)
+
+#else
+static inline struct regmap *altr_sysmgr_node_to_regmap(struct device_node *np)
+{
+ return ERR_PTR(-ENOTSUPP);
+}
+
+static inline struct regmap *
+altr_sysmgr_regmap_lookup_by_compatible(const char *s)
+{
+ return ERR_PTR(-ENOTSUPP);
+}
+
+static inline struct regmap *
+altr_sysmgr_regmap_lookup_by_pdevname(const char *s)
+{
+ return ERR_PTR(-ENOTSUPP);
+}
+
+static inline struct regmap *
+altr_sysmgr_regmap_lookup_by_phandle(struct device_node *np,
+ const char *property)
+{
+ return ERR_PTR(-ENOTSUPP);
+}
+#endif
+
+#endif /* __LINUX_MFD_ALTERA_SYSMGR_H__ */
--
2.7.4
^ permalink raw reply related
* [PATCH 3/4] arm64: defconfig: Enable CONFIG_MTD_ALTERA_SYSMGR
From: thor.thayer @ 2018-09-24 22:09 UTC (permalink / raw)
To: lee.jones, peppe.cavallaro, dinguyen, linux, alexandre.torgue,
joabreu
Cc: thor.thayer, davem, mchehab+samsung, catalin.marinas, akpm, arnd,
aisheng.dong, linux-kernel, netdev, linux-arm-kernel
In-Reply-To: <1537826946-18942-1-git-send-email-thor.thayer@linux.intel.com>
From: Thor Thayer <thor.thayer@linux.intel.com>
Enable the Stratix10 System Manager by default.
Signed-off-by: Thor Thayer <thor.thayer@linux.intel.com>
---
arch/arm64/configs/defconfig | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index f67e8d5e93ad..f15d4b1a9417 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -377,6 +377,7 @@ CONFIG_MESON_WATCHDOG=m
CONFIG_RENESAS_WDT=y
CONFIG_UNIPHIER_WATCHDOG=y
CONFIG_BCM2835_WDT=y
+CONFIG_MFD_ALTERA_SYSMGR=y
CONFIG_MFD_BD9571MWV=y
CONFIG_MFD_AXP20X_RSB=y
CONFIG_MFD_CROS_EC=y
--
2.7.4
^ permalink raw reply related
* [PATCH net-next v1 2/5] ipv6: allow link-local and multicast packets inside vrf
From: Mike Manning @ 2018-09-24 16:13 UTC (permalink / raw)
To: netdev
In-Reply-To: <20180924161326.17167-1-mmanning@vyatta.att-mail.com>
Packets that are multicast or to link-local addresses are not enslaved
to the vrf of the socket that they are received on. This is needed for
NDISC, but breaks applications that rely on receiving such packets when
in a VRF. Also to make IPv6 consistent with IPv4 which does handle
multicast packets as being enslaved, modify the VRF driver to do the
same for IPv6. As a result, the multicast address check needs to verify
the address against the enslaved rather than the l3mdev device.
Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
---
drivers/net/vrf.c | 19 +++++++++----------
net/ipv6/ip6_input.c | 19 ++++++++++++++++++-
net/ipv6/ipv6_sockglue.c | 2 +-
3 files changed, 28 insertions(+), 12 deletions(-)
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index f93547f257fb..9d817c19f3b4 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -981,24 +981,23 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
struct sk_buff *skb)
{
int orig_iif = skb->skb_iif;
- bool need_strict;
+ bool need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr);
+ bool is_ndisc = ipv6_ndisc_frame(skb);
- /* loopback traffic; do not push through packet taps again.
- * Reset pkt_type for upper layers to process skb
+ /* loopback, multicast & non-ND link-local traffic; do not push through
+ * packet taps again. Reset pkt_type for upper layers to process skb
*/
- if (skb->pkt_type == PACKET_LOOPBACK) {
+ if (skb->pkt_type == PACKET_LOOPBACK || (need_strict && !is_ndisc)) {
skb->dev = vrf_dev;
skb->skb_iif = vrf_dev->ifindex;
IP6CB(skb)->flags |= IP6SKB_L3SLAVE;
- skb->pkt_type = PACKET_HOST;
+ if (skb->pkt_type == PACKET_LOOPBACK)
+ skb->pkt_type = PACKET_HOST;
goto out;
}
- /* if packet is NDISC or addressed to multicast or link-local
- * then keep the ingress interface
- */
- need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr);
- if (!ipv6_ndisc_frame(skb) && !need_strict) {
+ /* if packet is NDISC then keep the ingress interface */
+ if (!is_ndisc) {
vrf_rx_stats(vrf_dev, skb->len);
skb->dev = vrf_dev;
skb->skb_iif = vrf_dev->ifindex;
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 96577e742afd..108f5f88ec98 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -432,15 +432,32 @@ EXPORT_SYMBOL_GPL(ip6_input);
int ip6_mc_input(struct sk_buff *skb)
{
+ int sdif = inet6_sdif(skb);
const struct ipv6hdr *hdr;
+ struct net_device *dev;
bool deliver;
__IP6_UPD_PO_STATS(dev_net(skb_dst(skb)->dev),
__in6_dev_get_safely(skb->dev), IPSTATS_MIB_INMCAST,
skb->len);
+ /* skb->dev passed may be master dev for vrfs. */
+ if (sdif) {
+ rcu_read_lock();
+ dev = dev_get_by_index_rcu(dev_net(skb->dev), sdif);
+ if (!dev) {
+ rcu_read_unlock();
+ kfree_skb(skb);
+ return -ENODEV;
+ }
+ } else {
+ dev = skb->dev;
+ }
+
hdr = ipv6_hdr(skb);
- deliver = ipv6_chk_mcast_addr(skb->dev, &hdr->daddr, NULL);
+ deliver = ipv6_chk_mcast_addr(dev, &hdr->daddr, NULL);
+ if (sdif)
+ rcu_read_unlock();
#ifdef CONFIG_IPV6_MROUTE
/*
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 7dfbc797b130..4ebd395dd3df 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -486,7 +486,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
retv = -EFAULT;
break;
}
- if (sk->sk_bound_dev_if && pkt.ipi6_ifindex != sk->sk_bound_dev_if)
+ if (!sk_dev_equal_l3scope(sk, pkt.ipi6_ifindex))
goto e_inval;
np->sticky_pktinfo.ipi6_ifindex = pkt.ipi6_ifindex;
--
2.11.0
^ permalink raw reply related
* [PATCH net-next v1 0/5] vrf: allow simultaneous service instances in default and other VRFs
From: Mike Manning @ 2018-09-24 16:13 UTC (permalink / raw)
To: netdev
Services currently have to be VRF-aware if they are using an unbound
socket. One cannot have multiple service instances running in the
default and other VRFs for services that are not VRF-aware and listen
on an unbound socket. This is because there is no way of isolating
packets received in the default VRF from those arriving in other VRFs.
This series provides this isolation subject to the existing kernel
parameter net.ipv4.tcp_l3mdev_accept not being set, given that this is
documented as allowing a single service instance to work across all
VRF domains. The functionality applies to UDP & TCP services, for IPv4
and IPv6, in particular adding VRF table handling for IPv6 multicast.
Example of running ssh instances in default and blue VRF:
$ /usr/sbin/sshd -D
$ ip vrf exec vrf-blue /usr/sbin/sshd
$ ss -ta | egrep 'State|ssh'
State Recv-Q Send-Q Local Address:Port Peer Address:Port
LISTEN 0 128 0.0.0.0%vrf-blue:ssh 0.0.0.0:*
LISTEN 0 128 0.0.0.0:ssh 0.0.0.0:*
ESTAB 0 0 192.168.122.220:ssh 192.168.122.1:50282
LISTEN 0 128 [::]%vrf-blue:ssh [::]:*
LISTEN 0 128 [::]:ssh [::]:*
ESTAB 0 0 [3000::2]%vrf-blue:ssh [3000::9]:45896
ESTAB 0 0 [2000::2]:ssh [2000::9]:46398
v1:
- Address Paolo Abeni's comments (patch 4/5)
- Fix build when CONFIG_NET_L3_MASTER_DEV not defined (patch 1/5)
Dewi Morgan (1):
ipv6: do not drop vrf udp multicast packets
Mike Manning (1):
ipv6: allow link-local and multicast packets inside vrf
Patrick Ruddy (1):
ipv6: add vrf table handling code for ipv6 mcast
Robert Shearman (2):
net: allow binding socket in a VRF when there's an unbound socket
ipv4: Allow sending multicast packets on specific i/f using VRF socket
Documentation/networking/vrf.txt | 9 ++++----
drivers/net/vrf.c | 30 ++++++++++++++++--------
include/net/inet6_hashtables.h | 5 ++--
include/net/inet_hashtables.h | 31 +++++++++++++++++++------
include/net/inet_sock.h | 13 +++++++++++
net/core/sock.c | 2 ++
net/ipv4/datagram.c | 2 +-
net/ipv4/inet_connection_sock.c | 13 ++++++++---
net/ipv4/inet_hashtables.c | 34 +++++++++++++++++-----------
net/ipv4/ip_sockglue.c | 3 +++
net/ipv4/ping.c | 2 +-
net/ipv4/raw.c | 6 ++---
net/ipv4/udp.c | 17 ++++++--------
net/ipv6/datagram.c | 5 +++-
net/ipv6/inet6_hashtables.c | 14 +++++-------
net/ipv6/ip6_input.c | 43 +++++++++++++++++++++++++++++++----
net/ipv6/ip6mr.c | 49 ++++++++++++++++++++++++++++++----------
net/ipv6/ipv6_sockglue.c | 5 +++-
net/ipv6/raw.c | 6 ++---
net/ipv6/udp.c | 22 ++++++++----------
20 files changed, 214 insertions(+), 97 deletions(-)
--
2.11.0
^ permalink raw reply
* [PATCH net-next v1 4/5] ipv6: do not drop vrf udp multicast packets
From: Mike Manning @ 2018-09-24 16:13 UTC (permalink / raw)
To: netdev; +Cc: Dewi Morgan
In-Reply-To: <20180924161326.17167-1-mmanning@vyatta.att-mail.com>
From: Dewi Morgan <morgand@vyatta.att-mail.com>
For bound udp sockets in a vrf, also check the sdif to get the index
for ingress devices enslaved to an l3mdev. Verify the multicast address
against the enslaved rather than the l3mdev device.
Signed-off-by: Dewi Morgan <morgand@vyatta.att-mail.com>
Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
---
net/ipv6/ip6_input.c | 24 ++++++++++++++++++++----
net/ipv6/udp.c | 8 +++++---
2 files changed, 25 insertions(+), 7 deletions(-)
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 108f5f88ec98..82ffb5cdd2ab 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -324,11 +324,14 @@ void ipv6_list_rcv(struct list_head *head, struct packet_type *pt,
static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
const struct inet6_protocol *ipprot;
+ int sdif = inet6_sdif(skb);
+ bool have_final = false;
struct inet6_dev *idev;
+ struct net_device *dev;
unsigned int nhoff;
+ bool deliver;
int nexthdr;
bool raw;
- bool have_final = false;
/*
* Parse extension headers
@@ -371,9 +374,22 @@ static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *sk
skb_postpull_rcsum(skb, skb_network_header(skb),
skb_network_header_len(skb));
hdr = ipv6_hdr(skb);
- if (ipv6_addr_is_multicast(&hdr->daddr) &&
- !ipv6_chk_mcast_addr(skb->dev, &hdr->daddr,
- &hdr->saddr) &&
+
+ /* skb->dev passed may be master dev for vrfs. */
+ if (sdif) {
+ dev = dev_get_by_index_rcu(dev_net(skb->dev),
+ sdif);
+ if (!dev) {
+ kfree_skb(skb);
+ return -ENODEV;
+ }
+ } else {
+ dev = skb->dev;
+ }
+
+ deliver = ipv6_chk_mcast_addr(dev, &hdr->daddr,
+ &hdr->saddr);
+ if (ipv6_addr_is_multicast(&hdr->daddr) && !deliver &&
!ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb)))
goto discard;
}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e22b7dd78c9b..35f71b7a1070 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -637,7 +637,7 @@ static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk,
__be16 loc_port, const struct in6_addr *loc_addr,
__be16 rmt_port, const struct in6_addr *rmt_addr,
- int dif, unsigned short hnum)
+ int dif, int sdif, unsigned short hnum)
{
struct inet_sock *inet = inet_sk(sk);
@@ -649,7 +649,7 @@ static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk,
(inet->inet_dport && inet->inet_dport != rmt_port) ||
(!ipv6_addr_any(&sk->sk_v6_daddr) &&
!ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) ||
- (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) ||
+ !inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif) ||
(!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)))
return false;
@@ -683,6 +683,7 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
unsigned int offset = offsetof(typeof(*sk), sk_node);
unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10);
int dif = inet6_iif(skb);
+ int sdif = inet6_sdif(skb);
struct hlist_node *node;
struct sk_buff *nskb;
@@ -697,7 +698,8 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) {
if (!__udp_v6_is_mcast_sock(net, sk, uh->dest, daddr,
- uh->source, saddr, dif, hnum))
+ uh->source, saddr, dif, sdif,
+ hnum))
continue;
/* If zero checksum and no_check is not on for
* the socket then skip it.
--
2.11.0
^ permalink raw reply related
* [PATCH net-next v1 3/5] ipv4: Allow sending multicast packets on specific i/f using VRF socket
From: Mike Manning @ 2018-09-24 16:13 UTC (permalink / raw)
To: netdev; +Cc: Robert Shearman
In-Reply-To: <20180924161326.17167-1-mmanning@vyatta.att-mail.com>
From: Robert Shearman <rshearma@vyatta.att-mail.com>
It is useful to be able to use the same socket for listening in a
specific VRF, as for sending multicast packets out of a specific
interface. However, the bound device on the socket currently takes
precedence and results in the packets not being sent.
Relax the condition on overriding the output interface to use for
sending packets out of UDP, raw and ping sockets to allow multicast
packets to be sent using the specified multicast interface.
Signed-off-by: Robert Shearman <rshearma@vyatta.att-mail.com>
Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
---
net/ipv4/datagram.c | 2 +-
net/ipv4/ping.c | 2 +-
net/ipv4/raw.c | 2 +-
net/ipv4/udp.c | 2 +-
4 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index f915abff1350..300921417f89 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -42,7 +42,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len
oif = sk->sk_bound_dev_if;
saddr = inet->inet_saddr;
if (ipv4_is_multicast(usin->sin_addr.s_addr)) {
- if (!oif)
+ if (!oif || netif_index_is_l3_master(sock_net(sk), oif))
oif = inet->mc_index;
if (!saddr)
saddr = inet->mc_addr;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 8d7aaf118a30..7ccb5f87f70b 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -779,7 +779,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
}
if (ipv4_is_multicast(daddr)) {
- if (!ipc.oif)
+ if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif))
ipc.oif = inet->mc_index;
if (!saddr)
saddr = inet->mc_addr;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 8a0d568d7aec..c55ef53d87a8 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -608,7 +608,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
tos |= RTO_ONLINK;
if (ipv4_is_multicast(daddr)) {
- if (!ipc.oif)
+ if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif))
ipc.oif = inet->mc_index;
if (!saddr)
saddr = inet->mc_addr;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 3d59ab47a85d..f81097843031 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1039,7 +1039,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
}
if (ipv4_is_multicast(daddr)) {
- if (!ipc.oif)
+ if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif))
ipc.oif = inet->mc_index;
if (!saddr)
saddr = inet->mc_addr;
--
2.11.0
^ permalink raw reply related
* [PATCH net-next v1 5/5] ipv6: add vrf table handling code for ipv6 mcast
From: Mike Manning @ 2018-09-24 16:13 UTC (permalink / raw)
To: netdev; +Cc: Patrick Ruddy
In-Reply-To: <20180924161326.17167-1-mmanning@vyatta.att-mail.com>
From: Patrick Ruddy <pruddy@vyatta.att-mail.com>
The code to obtain the correct table for the incoming interface was
missing for IPv6. This has been added along with the table creation
notification to fib rules for the RTNL_FAMILY_IP6MR address family.
Signed-off-by: Patrick Ruddy <pruddy@vyatta.att-mail.com>
Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
---
drivers/net/vrf.c | 11 +++++++++++
net/ipv6/ip6mr.c | 49 +++++++++++++++++++++++++++++++++++++------------
2 files changed, 48 insertions(+), 12 deletions(-)
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 9d817c19f3b4..21ad4b1d7f03 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1214,8 +1214,19 @@ static int vrf_add_fib_rules(const struct net_device *dev)
goto ipmr_err;
#endif
+#if IS_ENABLED(CONFIG_IPV6_MROUTE_MULTIPLE_TABLES)
+ err = vrf_fib_rule(dev, RTNL_FAMILY_IP6MR, true);
+ if (err < 0)
+ goto ip6mr_err;
+#endif
+
return 0;
+#if IS_ENABLED(CONFIG_IPV6_MROUTE_MULTIPLE_TABLES)
+ip6mr_err:
+ vrf_fib_rule(dev, RTNL_FAMILY_IPMR, false);
+#endif
+
#if IS_ENABLED(CONFIG_IP_MROUTE_MULTIPLE_TABLES)
ipmr_err:
vrf_fib_rule(dev, AF_INET6, false);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index d0b7e0249c13..1ecc88456dc5 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -85,7 +85,8 @@ static struct mr_table *ip6mr_new_table(struct net *net, u32 id);
static void ip6mr_free_table(struct mr_table *mrt);
static void ip6_mr_forward(struct net *net, struct mr_table *mrt,
- struct sk_buff *skb, struct mfc6_cache *cache);
+ struct net_device *dev, struct sk_buff *skb,
+ struct mfc6_cache *cache);
static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt,
mifi_t mifi, int assert);
static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc,
@@ -138,6 +139,9 @@ static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6,
.flags = FIB_LOOKUP_NOREF,
};
+ /* update flow if oif or iif point to device enslaved to l3mdev */
+ l3mdev_update_flow(net, flowi6_to_flowi(flp6));
+
err = fib_rules_lookup(net->ipv6.mr6_rules_ops,
flowi6_to_flowi(flp6), 0, &arg);
if (err < 0)
@@ -164,7 +168,9 @@ static int ip6mr_rule_action(struct fib_rule *rule, struct flowi *flp,
return -EINVAL;
}
- mrt = ip6mr_get_table(rule->fr_net, rule->table);
+ arg->table = fib_rule_get_table(rule, arg);
+
+ mrt = ip6mr_get_table(rule->fr_net, arg->table);
if (!mrt)
return -EAGAIN;
res->mrt = mrt;
@@ -1014,7 +1020,7 @@ static void ip6mr_cache_resolve(struct net *net, struct mr_table *mrt,
}
rtnl_unicast(skb, net, NETLINK_CB(skb).portid);
} else
- ip6_mr_forward(net, mrt, skb, c);
+ ip6_mr_forward(net, mrt, skb->dev, skb, c);
}
}
@@ -1120,7 +1126,7 @@ static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt,
/* Queue a packet for resolution. It gets locked cache entry! */
static int ip6mr_cache_unresolved(struct mr_table *mrt, mifi_t mifi,
- struct sk_buff *skb)
+ struct sk_buff *skb, struct net_device *dev)
{
struct mfc6_cache *c;
bool found = false;
@@ -1180,6 +1186,10 @@ static int ip6mr_cache_unresolved(struct mr_table *mrt, mifi_t mifi,
kfree_skb(skb);
err = -ENOBUFS;
} else {
+ if (dev) {
+ skb->dev = dev;
+ skb->skb_iif = dev->ifindex;
+ }
skb_queue_tail(&c->_c.mfc_un.unres.unresolved, skb);
err = 0;
}
@@ -2043,11 +2053,12 @@ static int ip6mr_find_vif(struct mr_table *mrt, struct net_device *dev)
}
static void ip6_mr_forward(struct net *net, struct mr_table *mrt,
- struct sk_buff *skb, struct mfc6_cache *c)
+ struct net_device *dev, struct sk_buff *skb,
+ struct mfc6_cache *c)
{
int psend = -1;
int vif, ct;
- int true_vifi = ip6mr_find_vif(mrt, skb->dev);
+ int true_vifi = ip6mr_find_vif(mrt, dev);
vif = c->_c.mfc_parent;
c->_c.mfc_un.res.pkt++;
@@ -2073,7 +2084,7 @@ static void ip6_mr_forward(struct net *net, struct mr_table *mrt,
/*
* Wrong interface: drop packet and (maybe) send PIM assert.
*/
- if (mrt->vif_table[vif].dev != skb->dev) {
+ if (mrt->vif_table[vif].dev != dev) {
c->_c.mfc_un.res.wrong_if++;
if (true_vifi >= 0 && mrt->mroute_do_assert &&
@@ -2146,6 +2157,7 @@ static void ip6_mr_forward(struct net *net, struct mr_table *mrt,
int ip6_mr_input(struct sk_buff *skb)
{
+ struct rtable *rt = skb_rtable(skb);
struct mfc6_cache *cache;
struct net *net = dev_net(skb->dev);
struct mr_table *mrt;
@@ -2154,6 +2166,19 @@ int ip6_mr_input(struct sk_buff *skb)
.flowi6_mark = skb->mark,
};
int err;
+ struct net_device *dev;
+
+ /* skb->dev passed in is the master dev for vrfs.
+ * Get the proper interface that does have a vif associated with it.
+ */
+ dev = skb->dev;
+ if (netif_is_l3_master(skb->dev)) {
+ dev = dev_get_by_index_rcu(net, IPCB(skb)->iif);
+ if (!dev) {
+ kfree_skb(skb);
+ return -ENODEV;
+ }
+ }
err = ip6mr_fib_lookup(net, &fl6, &mrt);
if (err < 0) {
@@ -2165,7 +2190,7 @@ int ip6_mr_input(struct sk_buff *skb)
cache = ip6mr_cache_find(mrt,
&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr);
if (!cache) {
- int vif = ip6mr_find_vif(mrt, skb->dev);
+ int vif = ip6mr_find_vif(mrt, dev);
if (vif >= 0)
cache = ip6mr_cache_find_any(mrt,
@@ -2179,9 +2204,9 @@ int ip6_mr_input(struct sk_buff *skb)
if (!cache) {
int vif;
- vif = ip6mr_find_vif(mrt, skb->dev);
+ vif = ip6mr_find_vif(mrt, dev);
if (vif >= 0) {
- int err = ip6mr_cache_unresolved(mrt, vif, skb);
+ int err = ip6mr_cache_unresolved(mrt, vif, skb, dev);
read_unlock(&mrt_lock);
return err;
@@ -2191,7 +2216,7 @@ int ip6_mr_input(struct sk_buff *skb)
return -ENODEV;
}
- ip6_mr_forward(net, mrt, skb, cache);
+ ip6_mr_forward(net, mrt, dev, skb, cache);
read_unlock(&mrt_lock);
@@ -2257,7 +2282,7 @@ int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm,
iph->saddr = rt->rt6i_src.addr;
iph->daddr = rt->rt6i_dst.addr;
- err = ip6mr_cache_unresolved(mrt, vif, skb2);
+ err = ip6mr_cache_unresolved(mrt, vif, skb2, dev);
read_unlock(&mrt_lock);
return err;
--
2.11.0
^ permalink raw reply related
* [PATCH] qed: Avoid constant logical operation warning in qed_vf_pf_acquire
From: Nathan Chancellor @ 2018-09-24 22:17 UTC (permalink / raw)
To: Ariel Elior, everest-linux-l2, David S. Miller
Cc: netdev, linux-kernel, Nathan Chancellor
Clang warns when a constant is used in a boolean context as it thinks a
bitwise operation may have been intended.
drivers/net/ethernet/qlogic/qed/qed_vf.c:415:27: warning: use of logical
'&&' with constant operand [-Wconstant-logical-operand]
if (!p_iov->b_pre_fp_hsi &&
^
drivers/net/ethernet/qlogic/qed/qed_vf.c:415:27: note: use '&' for a
bitwise operation
if (!p_iov->b_pre_fp_hsi &&
^~
&
drivers/net/ethernet/qlogic/qed/qed_vf.c:415:27: note: remove constant
to silence this warning
if (!p_iov->b_pre_fp_hsi &&
~^~
1 warning generated.
This has been here since commit 1fe614d10f45 ("qed: Relax VF firmware
requirements") and I am not entirely sure why since 0 isn't a special
case. Just remove the statement causing Clang to warn since it isn't
required.
Link: https://github.com/ClangBuiltLinux/linux/issues/126
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
---
drivers/net/ethernet/qlogic/qed/qed_vf.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c
index fcd8da08274f..be118d057b92 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c
@@ -413,7 +413,6 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn)
}
if (!p_iov->b_pre_fp_hsi &&
- ETH_HSI_VER_MINOR &&
(resp->pfdev_info.minor_fp_hsi < ETH_HSI_VER_MINOR)) {
DP_INFO(p_hwfn,
"PF is using older fastpath HSI; %02x.%02x is configured\n",
--
2.19.0
^ permalink raw reply related
* [PATCH net-next v1 1/5] net: allow binding socket in a VRF when there's an unbound socket
From: Mike Manning @ 2018-09-24 16:13 UTC (permalink / raw)
To: netdev; +Cc: Robert Shearman
In-Reply-To: <20180924161326.17167-1-mmanning@vyatta.att-mail.com>
From: Robert Shearman <rshearma@vyatta.att-mail.com>
There is no easy way currently for applications that want to receive
packets in the default VRF to be isolated from packets arriving in
VRFs, which makes using VRF-unaware applications in a VRF-aware system
a potential security risk.
So change the inet socket lookup to avoid packets arriving on a device
enslaved to an l3mdev from matching unbound sockets by removing the
wildcard for non sk_bound_dev_if and instead relying on check against
the secondary device index, which will be 0 when the input device is
not enslaved to an l3mdev and so match against an unbound socket and
not match when the input device is enslaved.
The existing net.ipv4.tcp_l3mdev_accept & net.ipv4.udp_l3mdev_accept
sysctls, which are documented as allowing the working across all VRF
domains, can be used to also work in the default VRF by causing
unbound sockets to match against packets arriving on a device
enslaved to an l3mdev.
Change the socket binding to take the l3mdev into account to allow an
unbound socket to not conflict sockets bound to an l3mdev given the
datapath isolation now guaranteed.
Signed-off-by: Robert Shearman <rshearma@vyatta.att-mail.com>
Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
---
Documentation/networking/vrf.txt | 9 +++++----
include/net/inet6_hashtables.h | 5 ++---
include/net/inet_hashtables.h | 31 ++++++++++++++++++++++++-------
include/net/inet_sock.h | 13 +++++++++++++
net/core/sock.c | 2 ++
net/ipv4/inet_connection_sock.c | 13 ++++++++++---
net/ipv4/inet_hashtables.c | 34 +++++++++++++++++++++-------------
net/ipv4/ip_sockglue.c | 3 +++
net/ipv4/raw.c | 4 ++--
net/ipv4/udp.c | 15 ++++++---------
net/ipv6/datagram.c | 5 ++++-
net/ipv6/inet6_hashtables.c | 14 ++++++--------
net/ipv6/ipv6_sockglue.c | 3 +++
net/ipv6/raw.c | 6 +++---
net/ipv6/udp.c | 14 +++++---------
15 files changed, 109 insertions(+), 62 deletions(-)
diff --git a/Documentation/networking/vrf.txt b/Documentation/networking/vrf.txt
index 8ff7b4c8f91b..d4b129402d57 100644
--- a/Documentation/networking/vrf.txt
+++ b/Documentation/networking/vrf.txt
@@ -103,6 +103,11 @@ VRF device:
or to specify the output device using cmsg and IP_PKTINFO.
+By default the scope of the port bindings for unbound sockets is
+limited to the default VRF. That is, it will not be matched by packets
+arriving on interfaces enslaved to an l3mdev and processes may bind to
+the same port if they bind to an l3mdev.
+
TCP & UDP services running in the default VRF context (ie., not bound
to any VRF device) can work across all VRF domains by enabling the
tcp_l3mdev_accept and udp_l3mdev_accept sysctl options:
@@ -112,10 +117,6 @@ tcp_l3mdev_accept and udp_l3mdev_accept sysctl options:
netfilter rules on the VRF device can be used to limit access to services
running in the default VRF context as well.
-The default VRF does not have limited scope with respect to port bindings.
-That is, if a process does a wildcard bind to a port in the default VRF it
-owns the port across all VRF domains within the network namespace.
-
################################################################################
Using iproute2 for VRFs
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 6e91e38a31da..9db98af46985 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -115,9 +115,8 @@ int inet6_hash(struct sock *sk);
((__sk)->sk_family == AF_INET6) && \
ipv6_addr_equal(&(__sk)->sk_v6_daddr, (__saddr)) && \
ipv6_addr_equal(&(__sk)->sk_v6_rcv_saddr, (__daddr)) && \
- (!(__sk)->sk_bound_dev_if || \
- ((__sk)->sk_bound_dev_if == (__dif)) || \
- ((__sk)->sk_bound_dev_if == (__sdif))) && \
+ (((__sk)->sk_bound_dev_if == (__dif)) || \
+ ((__sk)->sk_bound_dev_if == (__sdif))) && \
net_eq(sock_net(__sk), (__net)))
#endif /* _INET6_HASHTABLES_H */
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 9141e95529e7..866efd35ded4 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -79,6 +79,7 @@ struct inet_ehash_bucket {
struct inet_bind_bucket {
possible_net_t ib_net;
+ int l3mdev;
unsigned short port;
signed char fastreuse;
signed char fastreuseport;
@@ -188,10 +189,28 @@ static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
hashinfo->ehash_locks = NULL;
}
+#ifdef CONFIG_NET_L3_MASTER_DEV
+static inline bool inet_sk_bound_dev_eq(struct net *net, int bound_dev_if,
+ int dif, int sdif)
+{
+ if (!bound_dev_if)
+ return !sdif || net->ipv4.sysctl_tcp_l3mdev_accept;
+ return bound_dev_if == dif || bound_dev_if == sdif;
+}
+#else
+static inline bool inet_sk_bound_dev_eq(struct net *net, int bound_dev_if,
+ int dif, int sdif)
+{
+ if (!bound_dev_if)
+ return true;
+ return bound_dev_if == dif;
+}
+#endif
+
struct inet_bind_bucket *
inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net,
struct inet_bind_hashbucket *head,
- const unsigned short snum);
+ const unsigned short snum, int l3mdev);
void inet_bind_bucket_destroy(struct kmem_cache *cachep,
struct inet_bind_bucket *tb);
@@ -282,9 +301,8 @@ static inline struct sock *inet_lookup_listener(struct net *net,
#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \
(((__sk)->sk_portpair == (__ports)) && \
((__sk)->sk_addrpair == (__cookie)) && \
- (!(__sk)->sk_bound_dev_if || \
- ((__sk)->sk_bound_dev_if == (__dif)) || \
- ((__sk)->sk_bound_dev_if == (__sdif))) && \
+ (((__sk)->sk_bound_dev_if == (__dif)) || \
+ ((__sk)->sk_bound_dev_if == (__sdif))) && \
net_eq(sock_net(__sk), (__net)))
#else /* 32-bit arch */
#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
@@ -294,9 +312,8 @@ static inline struct sock *inet_lookup_listener(struct net *net,
(((__sk)->sk_portpair == (__ports)) && \
((__sk)->sk_daddr == (__saddr)) && \
((__sk)->sk_rcv_saddr == (__daddr)) && \
- (!(__sk)->sk_bound_dev_if || \
- ((__sk)->sk_bound_dev_if == (__dif)) || \
- ((__sk)->sk_bound_dev_if == (__sdif))) && \
+ (((__sk)->sk_bound_dev_if == (__dif)) || \
+ ((__sk)->sk_bound_dev_if == (__sdif))) && \
net_eq(sock_net(__sk), (__net)))
#endif /* 64-bit arch */
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index e03b93360f33..92e0aa3958f6 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -130,6 +130,19 @@ static inline int inet_request_bound_dev_if(const struct sock *sk,
return sk->sk_bound_dev_if;
}
+static inline int inet_sk_bound_l3mdev(const struct sock *sk)
+{
+#ifdef CONFIG_NET_L3_MASTER_DEV
+ struct net *net = sock_net(sk);
+
+ if (!net->ipv4.sysctl_tcp_l3mdev_accept)
+ return l3mdev_master_ifindex_by_index(net,
+ sk->sk_bound_dev_if);
+#endif
+
+ return 0;
+}
+
static inline struct ip_options_rcu *ireq_opt_deref(const struct inet_request_sock *ireq)
{
return rcu_dereference_check(ireq->ireq_opt,
diff --git a/net/core/sock.c b/net/core/sock.c
index 3730eb855095..da1cbb88a6bf 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -567,6 +567,8 @@ static int sock_setbindtodevice(struct sock *sk, char __user *optval,
lock_sock(sk);
sk->sk_bound_dev_if = index;
+ if (sk->sk_prot->rehash)
+ sk->sk_prot->rehash(sk);
sk_dst_reset(sk);
release_sock(sk);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index dfd5009f96ef..97bba5b3d69f 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -183,7 +183,9 @@ inet_csk_find_open_port(struct sock *sk, struct inet_bind_bucket **tb_ret, int *
int i, low, high, attempt_half;
struct inet_bind_bucket *tb;
u32 remaining, offset;
+ int l3mdev;
+ l3mdev = inet_sk_bound_l3mdev(sk);
attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0;
other_half_scan:
inet_get_local_port_range(net, &low, &high);
@@ -219,7 +221,8 @@ inet_csk_find_open_port(struct sock *sk, struct inet_bind_bucket **tb_ret, int *
hinfo->bhash_size)];
spin_lock_bh(&head->lock);
inet_bind_bucket_for_each(tb, &head->chain)
- if (net_eq(ib_net(tb), net) && tb->port == port) {
+ if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
+ tb->port == port) {
if (!inet_csk_bind_conflict(sk, tb, false, false))
goto success;
goto next_port;
@@ -293,6 +296,9 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
struct net *net = sock_net(sk);
struct inet_bind_bucket *tb = NULL;
kuid_t uid = sock_i_uid(sk);
+ int l3mdev;
+
+ l3mdev = inet_sk_bound_l3mdev(sk);
if (!port) {
head = inet_csk_find_open_port(sk, &tb, &port);
@@ -306,11 +312,12 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
hinfo->bhash_size)];
spin_lock_bh(&head->lock);
inet_bind_bucket_for_each(tb, &head->chain)
- if (net_eq(ib_net(tb), net) && tb->port == port)
+ if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
+ tb->port == port)
goto tb_found;
tb_not_found:
tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
- net, head, port);
+ net, head, port, l3mdev);
if (!tb)
goto fail_unlock;
tb_found:
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index f5c9ef2586de..2ec684057ebd 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -65,12 +65,14 @@ static u32 sk_ehashfn(const struct sock *sk)
struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
struct net *net,
struct inet_bind_hashbucket *head,
- const unsigned short snum)
+ const unsigned short snum,
+ int l3mdev)
{
struct inet_bind_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC);
if (tb) {
write_pnet(&tb->ib_net, net);
+ tb->l3mdev = l3mdev;
tb->port = snum;
tb->fastreuse = 0;
tb->fastreuseport = 0;
@@ -135,6 +137,7 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
table->bhash_size);
struct inet_bind_hashbucket *head = &table->bhash[bhash];
struct inet_bind_bucket *tb;
+ int l3mdev;
spin_lock(&head->lock);
tb = inet_csk(sk)->icsk_bind_hash;
@@ -143,6 +146,8 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
return -ENOENT;
}
if (tb->port != port) {
+ l3mdev = inet_sk_bound_l3mdev(sk);
+
/* NOTE: using tproxy and redirecting skbs to a proxy
* on a different listener port breaks the assumption
* that the listener socket's icsk_bind_hash is the same
@@ -150,12 +155,13 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
* create a new bind bucket for the child here. */
inet_bind_bucket_for_each(tb, &head->chain) {
if (net_eq(ib_net(tb), sock_net(sk)) &&
- tb->port == port)
+ tb->l3mdev == l3mdev && tb->port == port)
break;
}
if (!tb) {
tb = inet_bind_bucket_create(table->bind_bucket_cachep,
- sock_net(sk), head, port);
+ sock_net(sk), head, port,
+ l3mdev);
if (!tb) {
spin_unlock(&head->lock);
return -ENOMEM;
@@ -229,6 +235,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
{
int score = -1;
struct inet_sock *inet = inet_sk(sk);
+ bool dev_match;
if (net_eq(sock_net(sk), net) && inet->inet_num == hnum &&
!ipv6_only_sock(sk)) {
@@ -239,15 +246,12 @@ static inline int compute_score(struct sock *sk, struct net *net,
return -1;
score += 4;
}
- if (sk->sk_bound_dev_if || exact_dif) {
- bool dev_match = (sk->sk_bound_dev_if == dif ||
- sk->sk_bound_dev_if == sdif);
+ dev_match = inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
+ dif, sdif);
+ if (!dev_match)
+ return -1;
+ score += 4;
- if (!dev_match)
- return -1;
- if (sk->sk_bound_dev_if)
- score += 4;
- }
if (sk->sk_incoming_cpu == raw_smp_processor_id())
score++;
}
@@ -675,6 +679,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
u32 remaining, offset;
int ret, i, low, high;
static u32 hint;
+ int l3mdev;
if (port) {
head = &hinfo->bhash[inet_bhashfn(net, port,
@@ -693,6 +698,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
return ret;
}
+ l3mdev = inet_sk_bound_l3mdev(sk);
+
inet_get_local_port_range(net, &low, &high);
high++; /* [32768, 60999] -> [32768, 61000[ */
remaining = high - low;
@@ -719,7 +726,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
* the established check is already unique enough.
*/
inet_bind_bucket_for_each(tb, &head->chain) {
- if (net_eq(ib_net(tb), net) && tb->port == port) {
+ if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
+ tb->port == port) {
if (tb->fastreuse >= 0 ||
tb->fastreuseport >= 0)
goto next_port;
@@ -732,7 +740,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
}
tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
- net, head, port);
+ net, head, port, l3mdev);
if (!tb) {
spin_unlock_bh(&head->lock);
return -ENOMEM;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index c0fe5ad996f2..026971314c43 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -892,6 +892,9 @@ static int do_ip_setsockopt(struct sock *sk, int level,
dev_put(dev);
err = -EINVAL;
+ if (!sk->sk_bound_dev_if && midx)
+ break;
+
if (sk->sk_bound_dev_if &&
mreq.imr_ifindex != sk->sk_bound_dev_if &&
(!midx || midx != sk->sk_bound_dev_if))
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 33df4d76db2d..8a0d568d7aec 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -70,6 +70,7 @@
#include <net/snmp.h>
#include <net/tcp_states.h>
#include <net/inet_common.h>
+#include <net/inet_hashtables.h>
#include <net/checksum.h>
#include <net/xfrm.h>
#include <linux/rtnetlink.h>
@@ -131,8 +132,7 @@ struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
if (net_eq(sock_net(sk), net) && inet->inet_num == num &&
!(inet->inet_daddr && inet->inet_daddr != raddr) &&
!(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) &&
- !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif &&
- sk->sk_bound_dev_if != sdif))
+ inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
goto found; /* gotcha */
}
sk = NULL;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index f4e35b2ff8b8..3d59ab47a85d 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -371,6 +371,7 @@ static int compute_score(struct sock *sk, struct net *net,
{
int score;
struct inet_sock *inet;
+ bool dev_match;
if (!net_eq(sock_net(sk), net) ||
udp_sk(sk)->udp_port_hash != hnum ||
@@ -398,15 +399,11 @@ static int compute_score(struct sock *sk, struct net *net,
score += 4;
}
- if (sk->sk_bound_dev_if || exact_dif) {
- bool dev_match = (sk->sk_bound_dev_if == dif ||
- sk->sk_bound_dev_if == sdif);
-
- if (!dev_match)
- return -1;
- if (sk->sk_bound_dev_if)
- score += 4;
- }
+ dev_match = inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
+ dif, sdif);
+ if (!dev_match)
+ return -1;
+ score += 4;
if (sk->sk_incoming_cpu == raw_smp_processor_id())
score++;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 1ede7a16a0be..4813293d4fad 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -782,7 +782,10 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
if (src_info->ipi6_ifindex) {
if (fl6->flowi6_oif &&
- src_info->ipi6_ifindex != fl6->flowi6_oif)
+ src_info->ipi6_ifindex != fl6->flowi6_oif &&
+ (sk->sk_bound_dev_if != fl6->flowi6_oif ||
+ !sk_dev_equal_l3scope(
+ sk, src_info->ipi6_ifindex)))
return -EINVAL;
fl6->flowi6_oif = src_info->ipi6_ifindex;
}
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 3d7c7460a0c5..5eeeba7181a1 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -99,6 +99,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
const int dif, const int sdif, bool exact_dif)
{
int score = -1;
+ bool dev_match;
if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum &&
sk->sk_family == PF_INET6) {
@@ -109,15 +110,12 @@ static inline int compute_score(struct sock *sk, struct net *net,
return -1;
score++;
}
- if (sk->sk_bound_dev_if || exact_dif) {
- bool dev_match = (sk->sk_bound_dev_if == dif ||
- sk->sk_bound_dev_if == sdif);
+ dev_match = inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
+ dif, sdif);
+ if (!dev_match)
+ return -1;
+ score++;
- if (!dev_match)
- return -1;
- if (sk->sk_bound_dev_if)
- score++;
- }
if (sk->sk_incoming_cpu == raw_smp_processor_id())
score++;
}
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index c0cac9cc3a28..7dfbc797b130 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -626,6 +626,9 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
rcu_read_unlock();
+ if (!sk->sk_bound_dev_if && midx)
+ goto e_inval;
+
if (sk->sk_bound_dev_if &&
sk->sk_bound_dev_if != val &&
(!midx || midx != sk->sk_bound_dev_if))
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 413d98bf24f4..2f61a9f1a2b2 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -49,6 +49,7 @@
#include <net/transp_v6.h>
#include <net/udp.h>
#include <net/inet_common.h>
+#include <net/inet_hashtables.h>
#include <net/tcp_states.h>
#if IS_ENABLED(CONFIG_IPV6_MIP6)
#include <net/mip6.h>
@@ -86,9 +87,8 @@ struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
!ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr))
continue;
- if (sk->sk_bound_dev_if &&
- sk->sk_bound_dev_if != dif &&
- sk->sk_bound_dev_if != sdif)
+ if (!inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
+ dif, sdif))
continue;
if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 83f4c77c79d8..e22b7dd78c9b 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -117,6 +117,7 @@ static int compute_score(struct sock *sk, struct net *net,
{
int score;
struct inet_sock *inet;
+ bool dev_match;
if (!net_eq(sock_net(sk), net) ||
udp_sk(sk)->udp_port_hash != hnum ||
@@ -144,15 +145,10 @@ static int compute_score(struct sock *sk, struct net *net,
score++;
}
- if (sk->sk_bound_dev_if || exact_dif) {
- bool dev_match = (sk->sk_bound_dev_if == dif ||
- sk->sk_bound_dev_if == sdif);
-
- if (!dev_match)
- return -1;
- if (sk->sk_bound_dev_if)
- score++;
- }
+ dev_match = inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif);
+ if (!dev_match)
+ return -1;
+ score++;
if (sk->sk_incoming_cpu == raw_smp_processor_id())
score++;
--
2.11.0
^ permalink raw reply related
* Re: [PATCH v2 2/3] dt-bindings: can: rcar_can: Add r8a774a1 support
From: Rob Herring @ 2018-09-24 16:17 UTC (permalink / raw)
To: Fabrizio Castro
Cc: Wolfgang Grandegger, Marc Kleine-Budde, Mark Rutland,
David S. Miller, Sergei Shtylyov, linux-can, linux-kernel, netdev,
devicetree, Simon Horman, Geert Uytterhoeven, Chris Paterson,
Biju Das, linux-renesas-soc
In-Reply-To: <1536576195-11520-3-git-send-email-fabrizio.castro@bp.renesas.com>
On Mon, Sep 10, 2018 at 11:43:14AM +0100, Fabrizio Castro wrote:
> Document RZ/G2M (r8a774a1) SoC specific bindings.
>
> Signed-off-by: Fabrizio Castro <fabrizio.castro@bp.renesas.com>
> Signed-off-by: Chris Paterson <Chris.Paterson2@renesas.com>
> Reviewed-by: Biju Das <biju.das@bp.renesas.com>
> ---
> v1->v2:
> * dropped "renesas,rzg-gen2-can" and fixed "clocks" property description
> as per Geert's comments.
>
> This patch applies on top of next-20180910.
>
> Documentation/devicetree/bindings/net/can/rcar_can.txt | 18 +++++++++++++-----
> 1 file changed, 13 insertions(+), 5 deletions(-)
Reviewed-by: Rob Herring <robh@kernel.org>
^ permalink raw reply
* Re: [Regression] openvswitch: Add eventmask support to CT action.
From: Jarno Rajahalme @ 2018-09-24 22:21 UTC (permalink / raw)
To: Joseph Salisbury
Cc: gvrose8192, joe, davem, pshelar, netdev, ovs dev,
linux-kernel@vger.kernel.org, james.page, christian.ehrhardt,
1736390
In-Reply-To: <0d69e5b1-ac17-52c4-04f9-34ad1eb9f2eb@canonical.com>
> On Sep 21, 2018, at 2:37 AM, Joseph Salisbury <joseph.salisbury@canonical.com> wrote:
>
> Hi Jarno,
>
> A kernel bug report was opened against Ubuntu [0]. This bug is a
> regression introduced in v4.12-rc1. The latest mainline kernel was
> tested and still exhibits the bug. The following commit was identified
> as the cause of the regression:
>
> 120645513f55 ("openvswitch: Add eventmask support to CT action.")
>
> I was hoping to get your feedback, since you are the patch author. Do
> you think gathering any additional data will help diagnose this issue?
>
>
> Thanks,
>
> Joe
>
> http://pad.lv/1736390
>
I spent a while looking what could cause an i386-only issue like reported due to this commit, but could not come up with anything solid. Essentially the commit is setting the ‘ctmask’ field of a CT eceche extension. The purpose of the ‘ctmask’ is to limit the type of conntrack events for which a report Is delivered to any monitors in userspace. With a non-default (default is all-ones) ‘ctmask’ the code paths taken in nf_conntrack_eventmask_report() and nf_ct_deliver_cached_events() are changed to skip the generation of event reports for some event types. While it is hard to see how this could manifest as a bug in i386, this should be the only effect of the commit referred to above.
OVS probes for the kernel support of this feature and only uses the OVS_CT_ATTR_EVENTMASK attribute if support for it in the kernel is detected. The option of reverting the commit will cause additional CPU use and potential buffering issues for CT event monitors in userspace. If you need to revert the commit please try to do so only for the affected architecture (i386).
However, while reviewing all the uses of ‘ctmask’ and the associated nf_ct_ecache_ext_add() calls in the kernel with Joe we figured it would be worth trying a change where ‘ctmask’ is set in the CT template instead on the actual CT entry directly. This is a long shot in the sense of changing the behavior, but the only thing we could come up now. I have attached the patch below, please try it in your test rig.
commit a717743bd355b3a25a83b196403db9d010b311b2 (HEAD -> ovs-set-ctmask-in-template)
Author: Jarno Rajahalme <jarno@covalent.io>
Date: Mon Sep 24 14:34:26 2018 -0700
openvswitch: Set CT mask in template
Set the conntrack event mask in the template rather than on the conntrack
entry itself. init_conntrack() (called via nf_conntrack_in()) will pick
the event mask from the template.
Signed-off-by: Jarno Rajahalme <jarno@ovn.org>
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 86a75105af1a..ae1fb06828da 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1169,21 +1169,6 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key,
}
}
#endif
-
- /* Set the conntrack event mask if given. NEW and DELETE events have
- * their own groups, but the NFNLGRP_CONNTRACK_UPDATE group listener
- * typically would receive many kinds of updates. Setting the event
- * mask allows those events to be filtered. The set event mask will
- * remain in effect for the lifetime of the connection unless changed
- * by a further CT action with both the commit flag and the eventmask
- * option. */
- if (info->have_eventmask) {
- struct nf_conntrack_ecache *cache = nf_ct_ecache_find(ct);
-
- if (cache)
- cache->ctmask = info->eventmask;
- }
-
/* Apply changes before confirming the connection so that the initial
* conntrack NEW netlink event carries the values given in the CT
* action.
@@ -1625,6 +1610,20 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr,
return -ENOMEM;
}
+ /* Set the conntrack event mask if given. NEW and DELETE events have
+ * their own groups, but the NFNLGRP_CONNTRACK_UPDATE group listener
+ * typically would receive many kinds of updates. Setting the event
+ * mask allows those events to be filtered. The set event mask will
+ * remain in effect for the lifetime of the connection unless changed
+ * by a further CT action with both the commit flag and the eventmask
+ * option. */
+ if (ct_info.have_eventmask) {
+ if (!nf_ct_ecache_ext_add(ct_info.ct, ct_info.eventmask, 0, GFP_KERNEL)) {
+ OVS_NLERR(log, "Failed to allocate ecache for conntrack template");
+ return -ENOMEM;
+ }
+ }
+
__set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status);
nf_conntrack_get(&ct_info.ct->ct_general);
^ permalink raw reply related
* [PATCH net-next v3 00/10] Refactor classifier API to work with Qdisc/blocks without rtnl lock
From: Vlad Buslov @ 2018-09-24 16:18 UTC (permalink / raw)
To: netdev
Cc: jhs, xiyou.wangcong, jiri, davem, stephen, ktkhai,
nicolas.dichtel, gregkh, mark.rutland, leon, paulmck, fw, dsahern,
christian, lucien.xin, jakub.kicinski, jbenc, Vlad Buslov
Currently, all netlink protocol handlers for updating rules, actions and
qdiscs are protected with single global rtnl lock which removes any
possibility for parallelism. This patch set is a third step to remove
rtnl lock dependency from TC rules update path.
Recently, new rtnl registration flag RTNL_FLAG_DOIT_UNLOCKED was added.
Handlers registered with this flag are called without RTNL taken. End
goal is to have rule update handlers(RTM_NEWTFILTER, RTM_DELTFILTER,
etc.) to be registered with UNLOCKED flag to allow parallel execution.
However, there is no intention to completely remove or split rtnl lock
itself. This patch set addresses specific problems in implementation of
classifiers API that prevent its control path from being executed
concurrently. Additional changes are required to refactor classifiers
API and individual classifiers for parallel execution. This patch set
lays groundwork to eventually register rule update handlers as
rtnl-unlocked by modifying code in cls API that works with Qdiscs and
blocks. Following patch set does the same for chains and classifiers.
The goal of this change is to refactor tcf_block_find() and its
dependencies to allow concurrent execution:
- Extend Qdisc API with rcu to lookup and take reference to Qdisc
without relying on rtnl lock.
- Extend tcf_block with atomic reference counting and rcu.
- Always take reference to tcf_block while working with it.
- Implement tcf_block_release() to release resources obtained by
tcf_block_find()
- Create infrastructure to allow registering Qdiscs with class ops that
do not require the caller to hold rtnl lock.
All three netlink rule update handlers use tcf_block_find() to lookup
Qdisc and block, and this patch set introduces additional means of
synchronization to substitute rtnl lock in cls API.
Some functions in cls and sch APIs have historic names that no longer
clearly describe their intent. In order not make this code even more
confusing when introducing their concurrency-friendly versions, rename
these functions to describe actual implementation.
Changes from V2 to V3:
- Patch 1:
- Explicitly include refcount.h in rtnetlink.h.
- Patch 3:
- Move rcu_head field to the end of struct Qdisc.
- Rearrange local variable declarations in qdisc_lookup_rcu().
- Patch 5:
- Remove tcf_qdisc_put() and inline its content to callers.
Changes from V1 to V2:
- Rebase on latest net-next.
- Patch 8 - remove.
- Patch 9 - fold into patch 11.
- Patch 11:
- Rename tcf_block_{get|put}() to tcf_block_refcnt_{get|put}().
- Patch 13 - remove.
Vlad Buslov (10):
net: core: netlink: add helper refcount dec and lock function
net: sched: rename qdisc_destroy() to qdisc_put()
net: sched: extend Qdisc with rcu
net: sched: add helper function to take reference to Qdisc
net: sched: use Qdisc rcu API instead of relying on rtnl lock
net: sched: change tcf block reference counter type to refcount_t
net: sched: implement functions to put and flush all chains
net: sched: protect block idr with spinlock
net: sched: implement tcf_block_refcnt_{get|put}()
net: sched: use reference counting for tcf blocks on rules update
include/linux/rtnetlink.h | 7 ++
include/net/pkt_sched.h | 1 +
include/net/sch_generic.h | 20 +++-
net/core/rtnetlink.c | 6 ++
net/sched/cls_api.c | 242 +++++++++++++++++++++++++++++++++-------------
net/sched/sch_api.c | 24 ++++-
net/sched/sch_atm.c | 2 +-
net/sched/sch_cbq.c | 2 +-
net/sched/sch_cbs.c | 2 +-
net/sched/sch_drr.c | 4 +-
net/sched/sch_dsmark.c | 2 +-
net/sched/sch_fifo.c | 2 +-
net/sched/sch_generic.c | 48 +++++++--
net/sched/sch_hfsc.c | 2 +-
net/sched/sch_htb.c | 4 +-
net/sched/sch_mq.c | 4 +-
net/sched/sch_mqprio.c | 4 +-
net/sched/sch_multiq.c | 6 +-
net/sched/sch_netem.c | 2 +-
net/sched/sch_prio.c | 6 +-
net/sched/sch_qfq.c | 4 +-
net/sched/sch_red.c | 4 +-
net/sched/sch_sfb.c | 4 +-
net/sched/sch_tbf.c | 4 +-
24 files changed, 294 insertions(+), 112 deletions(-)
--
2.7.5
^ permalink raw reply
* [PATCH net-next v3 01/10] net: core: netlink: add helper refcount dec and lock function
From: Vlad Buslov @ 2018-09-24 16:22 UTC (permalink / raw)
To: netdev
Cc: jhs, xiyou.wangcong, jiri, davem, stephen, ktkhai,
nicolas.dichtel, gregkh, mark.rutland, leon, paulmck, fw, dsahern,
christian, lucien.xin, jakub.kicinski, jbenc, Vlad Buslov
In-Reply-To: <1537806178-10944-1-git-send-email-vladbu@mellanox.com>
Rtnl lock is encapsulated in netlink and cannot be accessed by other
modules directly. This means that reference counted objects that rely on
rtnl lock cannot use it with refcounter helper function that atomically
releases decrements reference and obtains mutex.
This patch implements simple wrapper function around refcount_dec_and_lock
that obtains rtnl lock if reference counter value reached 0.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
include/linux/rtnetlink.h | 2 ++
net/core/rtnetlink.c | 6 ++++++
2 files changed, 8 insertions(+)
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 5225832bd6ff..9cdd76348d9a 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -6,6 +6,7 @@
#include <linux/mutex.h>
#include <linux/netdevice.h>
#include <linux/wait.h>
+#include <linux/refcount.h>
#include <uapi/linux/rtnetlink.h>
extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo);
@@ -34,6 +35,7 @@ extern void rtnl_unlock(void);
extern int rtnl_trylock(void);
extern int rtnl_is_locked(void);
extern int rtnl_lock_killable(void);
+extern bool refcount_dec_and_rtnl_lock(refcount_t *r);
extern wait_queue_head_t netdev_unregistering_wq;
extern struct rw_semaphore pernet_ops_rwsem;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 80a7e18c65fb..35162e1b06ad 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -130,6 +130,12 @@ int rtnl_is_locked(void)
}
EXPORT_SYMBOL(rtnl_is_locked);
+bool refcount_dec_and_rtnl_lock(refcount_t *r)
+{
+ return refcount_dec_and_mutex_lock(r, &rtnl_mutex);
+}
+EXPORT_SYMBOL(refcount_dec_and_rtnl_lock);
+
#ifdef CONFIG_PROVE_LOCKING
bool lockdep_rtnl_is_held(void)
{
--
2.7.5
^ permalink raw reply related
* [PATCH net-next v3 00/10] Refactor classifier API to work with Qdisc/blocks without rtnl lock
From: Vlad Buslov @ 2018-09-24 16:22 UTC (permalink / raw)
To: netdev
Cc: jhs, xiyou.wangcong, jiri, davem, stephen, ktkhai,
nicolas.dichtel, gregkh, mark.rutland, leon, paulmck, fw, dsahern,
christian, lucien.xin, jakub.kicinski, jbenc, Vlad Buslov
Currently, all netlink protocol handlers for updating rules, actions and
qdiscs are protected with single global rtnl lock which removes any
possibility for parallelism. This patch set is a third step to remove
rtnl lock dependency from TC rules update path.
Recently, new rtnl registration flag RTNL_FLAG_DOIT_UNLOCKED was added.
Handlers registered with this flag are called without RTNL taken. End
goal is to have rule update handlers(RTM_NEWTFILTER, RTM_DELTFILTER,
etc.) to be registered with UNLOCKED flag to allow parallel execution.
However, there is no intention to completely remove or split rtnl lock
itself. This patch set addresses specific problems in implementation of
classifiers API that prevent its control path from being executed
concurrently. Additional changes are required to refactor classifiers
API and individual classifiers for parallel execution. This patch set
lays groundwork to eventually register rule update handlers as
rtnl-unlocked by modifying code in cls API that works with Qdiscs and
blocks. Following patch set does the same for chains and classifiers.
The goal of this change is to refactor tcf_block_find() and its
dependencies to allow concurrent execution:
- Extend Qdisc API with rcu to lookup and take reference to Qdisc
without relying on rtnl lock.
- Extend tcf_block with atomic reference counting and rcu.
- Always take reference to tcf_block while working with it.
- Implement tcf_block_release() to release resources obtained by
tcf_block_find()
- Create infrastructure to allow registering Qdiscs with class ops that
do not require the caller to hold rtnl lock.
All three netlink rule update handlers use tcf_block_find() to lookup
Qdisc and block, and this patch set introduces additional means of
synchronization to substitute rtnl lock in cls API.
Some functions in cls and sch APIs have historic names that no longer
clearly describe their intent. In order not make this code even more
confusing when introducing their concurrency-friendly versions, rename
these functions to describe actual implementation.
Changes from V2 to V3:
- Patch 1:
- Explicitly include refcount.h in rtnetlink.h.
- Patch 3:
- Move rcu_head field to the end of struct Qdisc.
- Rearrange local variable declarations in qdisc_lookup_rcu().
- Patch 5:
- Remove tcf_qdisc_put() and inline its content to callers.
Changes from V1 to V2:
- Rebase on latest net-next.
- Patch 8 - remove.
- Patch 9 - fold into patch 11.
- Patch 11:
- Rename tcf_block_{get|put}() to tcf_block_refcnt_{get|put}().
- Patch 13 - remove.
Vlad Buslov (10):
net: core: netlink: add helper refcount dec and lock function
net: sched: rename qdisc_destroy() to qdisc_put()
net: sched: extend Qdisc with rcu
net: sched: add helper function to take reference to Qdisc
net: sched: use Qdisc rcu API instead of relying on rtnl lock
net: sched: change tcf block reference counter type to refcount_t
net: sched: implement functions to put and flush all chains
net: sched: protect block idr with spinlock
net: sched: implement tcf_block_refcnt_{get|put}()
net: sched: use reference counting for tcf blocks on rules update
include/linux/rtnetlink.h | 7 ++
include/net/pkt_sched.h | 1 +
include/net/sch_generic.h | 20 +++-
net/core/rtnetlink.c | 6 ++
net/sched/cls_api.c | 242 +++++++++++++++++++++++++++++++++-------------
net/sched/sch_api.c | 24 ++++-
net/sched/sch_atm.c | 2 +-
net/sched/sch_cbq.c | 2 +-
net/sched/sch_cbs.c | 2 +-
net/sched/sch_drr.c | 4 +-
net/sched/sch_dsmark.c | 2 +-
net/sched/sch_fifo.c | 2 +-
net/sched/sch_generic.c | 48 +++++++--
net/sched/sch_hfsc.c | 2 +-
net/sched/sch_htb.c | 4 +-
net/sched/sch_mq.c | 4 +-
net/sched/sch_mqprio.c | 4 +-
net/sched/sch_multiq.c | 6 +-
net/sched/sch_netem.c | 2 +-
net/sched/sch_prio.c | 6 +-
net/sched/sch_qfq.c | 4 +-
net/sched/sch_red.c | 4 +-
net/sched/sch_sfb.c | 4 +-
net/sched/sch_tbf.c | 4 +-
24 files changed, 294 insertions(+), 112 deletions(-)
--
2.7.5
^ permalink raw reply
* [PATCH net-next v3 03/10] net: sched: extend Qdisc with rcu
From: Vlad Buslov @ 2018-09-24 16:22 UTC (permalink / raw)
To: netdev
Cc: jhs, xiyou.wangcong, jiri, davem, stephen, ktkhai,
nicolas.dichtel, gregkh, mark.rutland, leon, paulmck, fw, dsahern,
christian, lucien.xin, jakub.kicinski, jbenc, Vlad Buslov
In-Reply-To: <1537806178-10944-1-git-send-email-vladbu@mellanox.com>
Currently, Qdisc API functions assume that users have rtnl lock taken. To
implement rtnl unlocked classifiers update interface, Qdisc API must be
extended with functions that do not require rtnl lock.
Extend Qdisc structure with rcu. Implement special version of put function
qdisc_put_unlocked() that is called without rtnl lock taken. This function
only takes rtnl lock if Qdisc reference counter reached zero and is
intended to be used as optimization.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
include/linux/rtnetlink.h | 5 +++++
include/net/pkt_sched.h | 1 +
include/net/sch_generic.h | 2 ++
net/sched/sch_api.c | 18 ++++++++++++++++++
net/sched/sch_generic.c | 25 ++++++++++++++++++++++++-
5 files changed, 50 insertions(+), 1 deletion(-)
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 9cdd76348d9a..bb9cb84114c1 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -85,6 +85,11 @@ static inline struct netdev_queue *dev_ingress_queue(struct net_device *dev)
return rtnl_dereference(dev->ingress_queue);
}
+static inline struct netdev_queue *dev_ingress_queue_rcu(struct net_device *dev)
+{
+ return rcu_dereference(dev->ingress_queue);
+}
+
struct netdev_queue *dev_ingress_queue_create(struct net_device *dev);
#ifdef CONFIG_NET_INGRESS
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 7dc769e5452b..a16fbe9a2a67 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -102,6 +102,7 @@ int qdisc_set_default(const char *id);
void qdisc_hash_add(struct Qdisc *q, bool invisible);
void qdisc_hash_del(struct Qdisc *q);
struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle);
+struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle);
struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r,
struct nlattr *tab,
struct netlink_ext_ack *extack);
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index fadb1a4d4ee8..091b40c198ff 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -105,6 +105,7 @@ struct Qdisc {
spinlock_t busylock ____cacheline_aligned_in_smp;
spinlock_t seqlock;
+ struct rcu_head rcu;
};
static inline void qdisc_refcount_inc(struct Qdisc *qdisc)
@@ -555,6 +556,7 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
struct Qdisc *qdisc);
void qdisc_reset(struct Qdisc *qdisc);
void qdisc_put(struct Qdisc *qdisc);
+void qdisc_put_unlocked(struct Qdisc *qdisc);
void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n,
unsigned int len);
struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 2096138c4bf6..22e9799e5b69 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -314,6 +314,24 @@ struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle)
return q;
}
+struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle)
+{
+ struct netdev_queue *nq;
+ struct Qdisc *q;
+
+ if (!handle)
+ return NULL;
+ q = qdisc_match_from_root(dev->qdisc, handle);
+ if (q)
+ goto out;
+
+ nq = dev_ingress_queue_rcu(dev);
+ if (nq)
+ q = qdisc_match_from_root(nq->qdisc_sleeping, handle);
+out:
+ return q;
+}
+
static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid)
{
unsigned long cl;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 3e7696f3e053..531fac1d2875 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -941,6 +941,13 @@ void qdisc_free(struct Qdisc *qdisc)
kfree((char *) qdisc - qdisc->padded);
}
+void qdisc_free_cb(struct rcu_head *head)
+{
+ struct Qdisc *q = container_of(head, struct Qdisc, rcu);
+
+ qdisc_free(q);
+}
+
static void qdisc_destroy(struct Qdisc *qdisc)
{
const struct Qdisc_ops *ops = qdisc->ops;
@@ -970,7 +977,7 @@ static void qdisc_destroy(struct Qdisc *qdisc)
kfree_skb_list(skb);
}
- qdisc_free(qdisc);
+ call_rcu(&qdisc->rcu, qdisc_free_cb);
}
void qdisc_put(struct Qdisc *qdisc)
@@ -983,6 +990,22 @@ void qdisc_put(struct Qdisc *qdisc)
}
EXPORT_SYMBOL(qdisc_put);
+/* Version of qdisc_put() that is called with rtnl mutex unlocked.
+ * Intended to be used as optimization, this function only takes rtnl lock if
+ * qdisc reference counter reached zero.
+ */
+
+void qdisc_put_unlocked(struct Qdisc *qdisc)
+{
+ if (qdisc->flags & TCQ_F_BUILTIN ||
+ !refcount_dec_and_rtnl_lock(&qdisc->refcnt))
+ return;
+
+ qdisc_destroy(qdisc);
+ rtnl_unlock();
+}
+EXPORT_SYMBOL(qdisc_put_unlocked);
+
/* Attach toplevel qdisc to device queue. */
struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
struct Qdisc *qdisc)
--
2.7.5
^ permalink raw reply related
* [PATCH net-next v3 06/10] net: sched: change tcf block reference counter type to refcount_t
From: Vlad Buslov @ 2018-09-24 16:22 UTC (permalink / raw)
To: netdev
Cc: jhs, xiyou.wangcong, jiri, davem, stephen, ktkhai,
nicolas.dichtel, gregkh, mark.rutland, leon, paulmck, fw, dsahern,
christian, lucien.xin, jakub.kicinski, jbenc, Vlad Buslov
In-Reply-To: <1537806178-10944-1-git-send-email-vladbu@mellanox.com>
As a preparation for removing rtnl lock dependency from rules update path,
change tcf block reference counter type to refcount_t to allow modification
by concurrent users.
In block put function perform decrement and check reference counter once to
accommodate concurrent modification by unlocked users. After this change
tcf_chain_put at the end of block put function is called with
block->refcnt==0 and will deallocate block after the last chain is
released, so there is no need to manually deallocate block in this case.
However, if block reference counter reached 0 and there are no chains to
release, block must still be deallocated manually.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
include/net/sch_generic.h | 2 +-
net/sched/cls_api.c | 59 ++++++++++++++++++++++++++++-------------------
2 files changed, 36 insertions(+), 25 deletions(-)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 43b17f82d8ee..4a86f4d33f07 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -345,7 +345,7 @@ struct tcf_chain {
struct tcf_block {
struct list_head chain_list;
u32 index; /* block index for shared blocks */
- unsigned int refcnt;
+ refcount_t refcnt;
struct net *net;
struct Qdisc *q;
struct list_head cb_list;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index c33636e7b431..90843b6a8fa9 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -240,7 +240,7 @@ static void tcf_chain_destroy(struct tcf_chain *chain)
if (!chain->index)
block->chain0.chain = NULL;
kfree(chain);
- if (list_empty(&block->chain_list) && block->refcnt == 0)
+ if (list_empty(&block->chain_list) && !refcount_read(&block->refcnt))
kfree(block);
}
@@ -510,7 +510,7 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q,
INIT_LIST_HEAD(&block->owner_list);
INIT_LIST_HEAD(&block->chain0.filter_chain_list);
- block->refcnt = 1;
+ refcount_set(&block->refcnt, 1);
block->net = net;
block->index = block_index;
@@ -710,7 +710,7 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
/* block_index not 0 means the shared block is requested */
block = tcf_block_lookup(net, ei->block_index);
if (block)
- block->refcnt++;
+ refcount_inc(&block->refcnt);
}
if (!block) {
@@ -753,7 +753,7 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
err_block_insert:
kfree(block);
} else {
- block->refcnt--;
+ refcount_dec(&block->refcnt);
}
return err;
}
@@ -793,34 +793,45 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
tcf_chain0_head_change_cb_del(block, ei);
tcf_block_owner_del(block, q, ei->binder_type);
- if (block->refcnt == 1) {
- if (tcf_block_shared(block))
- tcf_block_remove(block, block->net);
-
- /* Hold a refcnt for all chains, so that they don't disappear
- * while we are iterating.
+ if (refcount_dec_and_test(&block->refcnt)) {
+ /* Flushing/putting all chains will cause the block to be
+ * deallocated when last chain is freed. However, if chain_list
+ * is empty, block has to be manually deallocated. After block
+ * reference counter reached 0, it is no longer possible to
+ * increment it or add new chains to block.
*/
- list_for_each_entry(chain, &block->chain_list, list)
- tcf_chain_hold(chain);
+ bool free_block = list_empty(&block->chain_list);
- list_for_each_entry(chain, &block->chain_list, list)
- tcf_chain_flush(chain);
- }
+ if (tcf_block_shared(block))
+ tcf_block_remove(block, block->net);
- tcf_block_offload_unbind(block, q, ei);
+ if (!free_block) {
+ /* Hold a refcnt for all chains, so that they don't
+ * disappear while we are iterating.
+ */
+ list_for_each_entry(chain, &block->chain_list, list)
+ tcf_chain_hold(chain);
- if (block->refcnt == 1) {
- /* At this point, all the chains should have refcnt >= 1. */
- list_for_each_entry_safe(chain, tmp, &block->chain_list, list) {
- tcf_chain_put_explicitly_created(chain);
- tcf_chain_put(chain);
+ list_for_each_entry(chain, &block->chain_list, list)
+ tcf_chain_flush(chain);
}
- block->refcnt--;
- if (list_empty(&block->chain_list))
+ tcf_block_offload_unbind(block, q, ei);
+
+ if (free_block) {
kfree(block);
+ } else {
+ /* At this point, all the chains should have
+ * refcnt >= 1.
+ */
+ list_for_each_entry_safe(chain, tmp, &block->chain_list,
+ list) {
+ tcf_chain_put_explicitly_created(chain);
+ tcf_chain_put(chain);
+ }
+ }
} else {
- block->refcnt--;
+ tcf_block_offload_unbind(block, q, ei);
}
}
EXPORT_SYMBOL(tcf_block_put_ext);
--
2.7.5
^ permalink raw reply related
* [PATCH net-next v3 04/10] net: sched: add helper function to take reference to Qdisc
From: Vlad Buslov @ 2018-09-24 16:22 UTC (permalink / raw)
To: netdev
Cc: jhs, xiyou.wangcong, jiri, davem, stephen, ktkhai,
nicolas.dichtel, gregkh, mark.rutland, leon, paulmck, fw, dsahern,
christian, lucien.xin, jakub.kicinski, jbenc, Vlad Buslov
In-Reply-To: <1537806178-10944-1-git-send-email-vladbu@mellanox.com>
Implement function to take reference to Qdisc that relies on rcu read lock
instead of rtnl mutex. Function only takes reference to Qdisc if reference
counter isn't zero. Intended to be used by unlocked cls API.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
include/net/sch_generic.h | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 091b40c198ff..43b17f82d8ee 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -115,6 +115,19 @@ static inline void qdisc_refcount_inc(struct Qdisc *qdisc)
refcount_inc(&qdisc->refcnt);
}
+/* Intended to be used by unlocked users, when concurrent qdisc release is
+ * possible.
+ */
+
+static inline struct Qdisc *qdisc_refcount_inc_nz(struct Qdisc *qdisc)
+{
+ if (qdisc->flags & TCQ_F_BUILTIN)
+ return qdisc;
+ if (refcount_inc_not_zero(&qdisc->refcnt))
+ return qdisc;
+ return NULL;
+}
+
static inline bool qdisc_is_running(struct Qdisc *qdisc)
{
if (qdisc->flags & TCQ_F_NOLOCK)
--
2.7.5
^ permalink raw reply related
* [PATCH net-next v3 09/10] net: sched: implement tcf_block_refcnt_{get|put}()
From: Vlad Buslov @ 2018-09-24 16:22 UTC (permalink / raw)
To: netdev
Cc: jhs, xiyou.wangcong, jiri, davem, stephen, ktkhai,
nicolas.dichtel, gregkh, mark.rutland, leon, paulmck, fw, dsahern,
christian, lucien.xin, jakub.kicinski, jbenc, Vlad Buslov
In-Reply-To: <1537806178-10944-1-git-send-email-vladbu@mellanox.com>
Implement get/put function for blocks that only take/release the reference
and perform deallocation. These functions are intended to be used by
unlocked rules update path to always hold reference to block while working
with it. They use on new fine-grained locking mechanisms introduced in
previous patches in this set, instead of relying on global protection
provided by rtnl lock.
Extract code that is common with tcf_block_detach_ext() into common
function __tcf_block_put().
Extend tcf_block with rcu to allow safe deallocation when it is accessed
concurrently.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
include/net/sch_generic.h | 1 +
net/sched/cls_api.c | 74 ++++++++++++++++++++++++++++++++---------------
2 files changed, 51 insertions(+), 24 deletions(-)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 4a86f4d33f07..7a6b71ee5433 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -357,6 +357,7 @@ struct tcf_block {
struct tcf_chain *chain;
struct list_head filter_chain_list;
} chain0;
+ struct rcu_head rcu;
};
static inline void tcf_block_offload_inc(struct tcf_block *block, u32 *flags)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 5a21888d0ee9..49e3c10532ad 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -241,7 +241,7 @@ static void tcf_chain_destroy(struct tcf_chain *chain)
block->chain0.chain = NULL;
kfree(chain);
if (list_empty(&block->chain_list) && !refcount_read(&block->refcnt))
- kfree(block);
+ kfree_rcu(block, rcu);
}
static void tcf_chain_hold(struct tcf_chain *chain)
@@ -537,6 +537,19 @@ static struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index)
return idr_find(&tn->idr, block_index);
}
+static struct tcf_block *tcf_block_refcnt_get(struct net *net, u32 block_index)
+{
+ struct tcf_block *block;
+
+ rcu_read_lock();
+ block = tcf_block_lookup(net, block_index);
+ if (block && !refcount_inc_not_zero(&block->refcnt))
+ block = NULL;
+ rcu_read_unlock();
+
+ return block;
+}
+
static void tcf_block_flush_all_chains(struct tcf_block *block)
{
struct tcf_chain *chain;
@@ -562,6 +575,40 @@ static void tcf_block_put_all_chains(struct tcf_block *block)
}
}
+static void __tcf_block_put(struct tcf_block *block, struct Qdisc *q,
+ struct tcf_block_ext_info *ei)
+{
+ if (refcount_dec_and_test(&block->refcnt)) {
+ /* Flushing/putting all chains will cause the block to be
+ * deallocated when last chain is freed. However, if chain_list
+ * is empty, block has to be manually deallocated. After block
+ * reference counter reached 0, it is no longer possible to
+ * increment it or add new chains to block.
+ */
+ bool free_block = list_empty(&block->chain_list);
+
+ if (tcf_block_shared(block))
+ tcf_block_remove(block, block->net);
+ if (!free_block)
+ tcf_block_flush_all_chains(block);
+
+ if (q)
+ tcf_block_offload_unbind(block, q, ei);
+
+ if (free_block)
+ kfree_rcu(block, rcu);
+ else
+ tcf_block_put_all_chains(block);
+ } else if (q) {
+ tcf_block_offload_unbind(block, q, ei);
+ }
+}
+
+static void tcf_block_refcnt_put(struct tcf_block *block)
+{
+ __tcf_block_put(block, NULL, NULL);
+}
+
/* Find tcf block.
* Set q, parent, cl when appropriate.
*/
@@ -786,7 +833,7 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
if (tcf_block_shared(block))
tcf_block_remove(block, net);
err_block_insert:
- kfree(block);
+ kfree_rcu(block, rcu);
} else {
refcount_dec(&block->refcnt);
}
@@ -826,28 +873,7 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
tcf_chain0_head_change_cb_del(block, ei);
tcf_block_owner_del(block, q, ei->binder_type);
- if (refcount_dec_and_test(&block->refcnt)) {
- /* Flushing/putting all chains will cause the block to be
- * deallocated when last chain is freed. However, if chain_list
- * is empty, block has to be manually deallocated. After block
- * reference counter reached 0, it is no longer possible to
- * increment it or add new chains to block.
- */
- bool free_block = list_empty(&block->chain_list);
-
- if (tcf_block_shared(block))
- tcf_block_remove(block, block->net);
- if (!free_block)
- tcf_block_flush_all_chains(block);
- tcf_block_offload_unbind(block, q, ei);
-
- if (free_block)
- kfree(block);
- else
- tcf_block_put_all_chains(block);
- } else {
- tcf_block_offload_unbind(block, q, ei);
- }
+ __tcf_block_put(block, q, ei);
}
EXPORT_SYMBOL(tcf_block_put_ext);
--
2.7.5
^ permalink raw reply related
* [PATCH net-next v3 10/10] net: sched: use reference counting for tcf blocks on rules update
From: Vlad Buslov @ 2018-09-24 16:22 UTC (permalink / raw)
To: netdev
Cc: jhs, xiyou.wangcong, jiri, davem, stephen, ktkhai,
nicolas.dichtel, gregkh, mark.rutland, leon, paulmck, fw, dsahern,
christian, lucien.xin, jakub.kicinski, jbenc, Vlad Buslov
In-Reply-To: <1537806178-10944-1-git-send-email-vladbu@mellanox.com>
In order to remove dependency on rtnl lock on rules update path, always
take reference to block while using it on rules update path. Change
tcf_block_get() error handling to properly release block with reference
counting, instead of just destroying it, in order to accommodate potential
concurrent users.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
net/sched/cls_api.c | 38 +++++++++++++++++++++-----------------
1 file changed, 21 insertions(+), 17 deletions(-)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 49e3c10532ad..3de47e99b788 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -622,7 +622,7 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q,
int err = 0;
if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
- block = tcf_block_lookup(net, block_index);
+ block = tcf_block_refcnt_get(net, block_index);
if (!block) {
NL_SET_ERR_MSG(extack, "Block of given index was not found");
return ERR_PTR(-EINVAL);
@@ -702,6 +702,14 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q,
err = -EOPNOTSUPP;
goto errout_qdisc;
}
+
+ /* Always take reference to block in order to support execution
+ * of rules update path of cls API without rtnl lock. Caller
+ * must release block when it is finished using it. 'if' block
+ * of this conditional obtain reference to block by calling
+ * tcf_block_refcnt_get().
+ */
+ refcount_inc(&block->refcnt);
}
return block;
@@ -716,6 +724,9 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q,
static void tcf_block_release(struct Qdisc *q, struct tcf_block *block)
{
+ if (!IS_ERR_OR_NULL(block))
+ tcf_block_refcnt_put(block);
+
if (q)
qdisc_put(q);
}
@@ -785,21 +796,16 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
{
struct net *net = qdisc_net(q);
struct tcf_block *block = NULL;
- bool created = false;
int err;
- if (ei->block_index) {
+ if (ei->block_index)
/* block_index not 0 means the shared block is requested */
- block = tcf_block_lookup(net, ei->block_index);
- if (block)
- refcount_inc(&block->refcnt);
- }
+ block = tcf_block_refcnt_get(net, ei->block_index);
if (!block) {
block = tcf_block_create(net, q, ei->block_index, extack);
if (IS_ERR(block))
return PTR_ERR(block);
- created = true;
if (tcf_block_shared(block)) {
err = tcf_block_insert(block, net, extack);
if (err)
@@ -829,14 +835,8 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
err_chain0_head_change_cb_add:
tcf_block_owner_del(block, q, ei->binder_type);
err_block_owner_add:
- if (created) {
- if (tcf_block_shared(block))
- tcf_block_remove(block, net);
err_block_insert:
- kfree_rcu(block, rcu);
- } else {
- refcount_dec(&block->refcnt);
- }
+ tcf_block_refcnt_put(block);
return err;
}
EXPORT_SYMBOL(tcf_block_get_ext);
@@ -1730,7 +1730,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
return err;
if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
- block = tcf_block_lookup(net, tcm->tcm_block_index);
+ block = tcf_block_refcnt_get(net, tcm->tcm_block_index);
if (!block)
goto out;
/* If we work with block index, q is NULL and parent value
@@ -1789,6 +1789,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
}
}
+ if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK)
+ tcf_block_refcnt_put(block);
cb->args[0] = index;
out:
@@ -2055,7 +2057,7 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
return err;
if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
- block = tcf_block_lookup(net, tcm->tcm_block_index);
+ block = tcf_block_refcnt_get(net, tcm->tcm_block_index);
if (!block)
goto out;
/* If we work with block index, q is NULL and parent value
@@ -2122,6 +2124,8 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
index++;
}
+ if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK)
+ tcf_block_refcnt_put(block);
cb->args[0] = index;
out:
--
2.7.5
^ permalink raw reply related
* [PATCH net-next v3 08/10] net: sched: protect block idr with spinlock
From: Vlad Buslov @ 2018-09-24 16:22 UTC (permalink / raw)
To: netdev
Cc: jhs, xiyou.wangcong, jiri, davem, stephen, ktkhai,
nicolas.dichtel, gregkh, mark.rutland, leon, paulmck, fw, dsahern,
christian, lucien.xin, jakub.kicinski, jbenc, Vlad Buslov
In-Reply-To: <1537806178-10944-1-git-send-email-vladbu@mellanox.com>
Protect block idr access with spinlock, instead of relying on rtnl lock.
Take tn->idr_lock spinlock during block insertion and removal.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
net/sched/cls_api.c | 15 +++++++++++++--
1 file changed, 13 insertions(+), 2 deletions(-)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index cb7422af5e51..5a21888d0ee9 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -473,6 +473,7 @@ tcf_chain0_head_change_cb_del(struct tcf_block *block,
}
struct tcf_net {
+ spinlock_t idr_lock; /* Protects idr */
struct idr idr;
};
@@ -482,16 +483,25 @@ static int tcf_block_insert(struct tcf_block *block, struct net *net,
struct netlink_ext_ack *extack)
{
struct tcf_net *tn = net_generic(net, tcf_net_id);
+ int err;
+
+ idr_preload(GFP_KERNEL);
+ spin_lock(&tn->idr_lock);
+ err = idr_alloc_u32(&tn->idr, block, &block->index, block->index,
+ GFP_NOWAIT);
+ spin_unlock(&tn->idr_lock);
+ idr_preload_end();
- return idr_alloc_u32(&tn->idr, block, &block->index, block->index,
- GFP_KERNEL);
+ return err;
}
static void tcf_block_remove(struct tcf_block *block, struct net *net)
{
struct tcf_net *tn = net_generic(net, tcf_net_id);
+ spin_lock(&tn->idr_lock);
idr_remove(&tn->idr, block->index);
+ spin_unlock(&tn->idr_lock);
}
static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q,
@@ -2278,6 +2288,7 @@ static __net_init int tcf_net_init(struct net *net)
{
struct tcf_net *tn = net_generic(net, tcf_net_id);
+ spin_lock_init(&tn->idr_lock);
idr_init(&tn->idr);
return 0;
}
--
2.7.5
^ permalink raw reply related
* [PATCH net-next v3 07/10] net: sched: implement functions to put and flush all chains
From: Vlad Buslov @ 2018-09-24 16:22 UTC (permalink / raw)
To: netdev
Cc: jhs, xiyou.wangcong, jiri, davem, stephen, ktkhai,
nicolas.dichtel, gregkh, mark.rutland, leon, paulmck, fw, dsahern,
christian, lucien.xin, jakub.kicinski, jbenc, Vlad Buslov
In-Reply-To: <1537806178-10944-1-git-send-email-vladbu@mellanox.com>
Extract code that flushes and puts all chains on tcf block to two
standalone function to be shared with functions that locklessly get/put
reference to block.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
net/sched/cls_api.c | 55 +++++++++++++++++++++++++++++------------------------
1 file changed, 30 insertions(+), 25 deletions(-)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 90843b6a8fa9..cb7422af5e51 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -527,6 +527,31 @@ static struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index)
return idr_find(&tn->idr, block_index);
}
+static void tcf_block_flush_all_chains(struct tcf_block *block)
+{
+ struct tcf_chain *chain;
+
+ /* Hold a refcnt for all chains, so that they don't disappear
+ * while we are iterating.
+ */
+ list_for_each_entry(chain, &block->chain_list, list)
+ tcf_chain_hold(chain);
+
+ list_for_each_entry(chain, &block->chain_list, list)
+ tcf_chain_flush(chain);
+}
+
+static void tcf_block_put_all_chains(struct tcf_block *block)
+{
+ struct tcf_chain *chain, *tmp;
+
+ /* At this point, all the chains should have refcnt >= 1. */
+ list_for_each_entry_safe(chain, tmp, &block->chain_list, list) {
+ tcf_chain_put_explicitly_created(chain);
+ tcf_chain_put(chain);
+ }
+}
+
/* Find tcf block.
* Set q, parent, cl when appropriate.
*/
@@ -786,8 +811,6 @@ EXPORT_SYMBOL(tcf_block_get);
void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
struct tcf_block_ext_info *ei)
{
- struct tcf_chain *chain, *tmp;
-
if (!block)
return;
tcf_chain0_head_change_cb_del(block, ei);
@@ -804,32 +827,14 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
if (tcf_block_shared(block))
tcf_block_remove(block, block->net);
-
- if (!free_block) {
- /* Hold a refcnt for all chains, so that they don't
- * disappear while we are iterating.
- */
- list_for_each_entry(chain, &block->chain_list, list)
- tcf_chain_hold(chain);
-
- list_for_each_entry(chain, &block->chain_list, list)
- tcf_chain_flush(chain);
- }
-
+ if (!free_block)
+ tcf_block_flush_all_chains(block);
tcf_block_offload_unbind(block, q, ei);
- if (free_block) {
+ if (free_block)
kfree(block);
- } else {
- /* At this point, all the chains should have
- * refcnt >= 1.
- */
- list_for_each_entry_safe(chain, tmp, &block->chain_list,
- list) {
- tcf_chain_put_explicitly_created(chain);
- tcf_chain_put(chain);
- }
- }
+ else
+ tcf_block_put_all_chains(block);
} else {
tcf_block_offload_unbind(block, q, ei);
}
--
2.7.5
^ permalink raw reply related
* [PATCH net-next v3 05/10] net: sched: use Qdisc rcu API instead of relying on rtnl lock
From: Vlad Buslov @ 2018-09-24 16:22 UTC (permalink / raw)
To: netdev
Cc: jhs, xiyou.wangcong, jiri, davem, stephen, ktkhai,
nicolas.dichtel, gregkh, mark.rutland, leon, paulmck, fw, dsahern,
christian, lucien.xin, jakub.kicinski, jbenc, Vlad Buslov
In-Reply-To: <1537806178-10944-1-git-send-email-vladbu@mellanox.com>
As a preparation from removing rtnl lock dependency from rules update path,
use Qdisc rcu and reference counting capabilities instead of relying on
rtnl lock while working with Qdiscs. Create new tcf_block_release()
function, and use it to free resources taken by tcf_block_find().
Currently, this function only releases Qdisc and it is extended in next
patches in this series.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
net/sched/cls_api.c | 79 +++++++++++++++++++++++++++++++++++++++++++----------
1 file changed, 64 insertions(+), 15 deletions(-)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 0a75cb2e5e7b..c33636e7b431 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -537,6 +537,7 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q,
struct netlink_ext_ack *extack)
{
struct tcf_block *block;
+ int err = 0;
if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
block = tcf_block_lookup(net, block_index);
@@ -548,55 +549,93 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q,
const struct Qdisc_class_ops *cops;
struct net_device *dev;
+ rcu_read_lock();
+
/* Find link */
- dev = __dev_get_by_index(net, ifindex);
- if (!dev)
+ dev = dev_get_by_index_rcu(net, ifindex);
+ if (!dev) {
+ rcu_read_unlock();
return ERR_PTR(-ENODEV);
+ }
/* Find qdisc */
if (!*parent) {
*q = dev->qdisc;
*parent = (*q)->handle;
} else {
- *q = qdisc_lookup(dev, TC_H_MAJ(*parent));
+ *q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent));
if (!*q) {
NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists");
- return ERR_PTR(-EINVAL);
+ err = -EINVAL;
+ goto errout_rcu;
}
}
+ *q = qdisc_refcount_inc_nz(*q);
+ if (!*q) {
+ NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists");
+ err = -EINVAL;
+ goto errout_rcu;
+ }
+
/* Is it classful? */
cops = (*q)->ops->cl_ops;
if (!cops) {
NL_SET_ERR_MSG(extack, "Qdisc not classful");
- return ERR_PTR(-EINVAL);
+ err = -EINVAL;
+ goto errout_rcu;
}
if (!cops->tcf_block) {
NL_SET_ERR_MSG(extack, "Class doesn't support blocks");
- return ERR_PTR(-EOPNOTSUPP);
+ err = -EOPNOTSUPP;
+ goto errout_rcu;
}
+ /* At this point we know that qdisc is not noop_qdisc,
+ * which means that qdisc holds a reference to net_device
+ * and we hold a reference to qdisc, so it is safe to release
+ * rcu read lock.
+ */
+ rcu_read_unlock();
+
/* Do we search for filter, attached to class? */
if (TC_H_MIN(*parent)) {
*cl = cops->find(*q, *parent);
if (*cl == 0) {
NL_SET_ERR_MSG(extack, "Specified class doesn't exist");
- return ERR_PTR(-ENOENT);
+ err = -ENOENT;
+ goto errout_qdisc;
}
}
/* And the last stroke */
block = cops->tcf_block(*q, *cl, extack);
- if (!block)
- return ERR_PTR(-EINVAL);
+ if (!block) {
+ err = -EINVAL;
+ goto errout_qdisc;
+ }
if (tcf_block_shared(block)) {
NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters");
- return ERR_PTR(-EOPNOTSUPP);
+ err = -EOPNOTSUPP;
+ goto errout_qdisc;
}
}
return block;
+
+errout_rcu:
+ rcu_read_unlock();
+errout_qdisc:
+ if (*q)
+ qdisc_put(*q);
+ return ERR_PTR(err);
+}
+
+static void tcf_block_release(struct Qdisc *q, struct tcf_block *block)
+{
+ if (q)
+ qdisc_put(q);
}
struct tcf_block_owner_item {
@@ -1332,6 +1371,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
errout:
if (chain)
tcf_chain_put(chain);
+ tcf_block_release(q, block);
if (err == -EAGAIN)
/* Replay the request. */
goto replay;
@@ -1453,6 +1493,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
errout:
if (chain)
tcf_chain_put(chain);
+ tcf_block_release(q, block);
return err;
}
@@ -1538,6 +1579,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
errout:
if (chain)
tcf_chain_put(chain);
+ tcf_block_release(q, block);
return err;
}
@@ -1854,7 +1896,8 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
if (chain_index > TC_ACT_EXT_VAL_MASK) {
NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
- return -EINVAL;
+ err = -EINVAL;
+ goto errout_block;
}
chain = tcf_chain_lookup(block, chain_index);
if (n->nlmsg_type == RTM_NEWCHAIN) {
@@ -1866,23 +1909,27 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
tcf_chain_hold(chain);
} else {
NL_SET_ERR_MSG(extack, "Filter chain already exists");
- return -EEXIST;
+ err = -EEXIST;
+ goto errout_block;
}
} else {
if (!(n->nlmsg_flags & NLM_F_CREATE)) {
NL_SET_ERR_MSG(extack, "Need both RTM_NEWCHAIN and NLM_F_CREATE to create a new chain");
- return -ENOENT;
+ err = -ENOENT;
+ goto errout_block;
}
chain = tcf_chain_create(block, chain_index);
if (!chain) {
NL_SET_ERR_MSG(extack, "Failed to create filter chain");
- return -ENOMEM;
+ err = -ENOMEM;
+ goto errout_block;
}
}
} else {
if (!chain || tcf_chain_held_by_acts_only(chain)) {
NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
- return -EINVAL;
+ err = -EINVAL;
+ goto errout_block;
}
tcf_chain_hold(chain);
}
@@ -1926,6 +1973,8 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
errout:
tcf_chain_put(chain);
+errout_block:
+ tcf_block_release(q, block);
if (err == -EAGAIN)
/* Replay the request. */
goto replay;
--
2.7.5
^ permalink raw reply related
* [PATCH net-next v3 02/10] net: sched: rename qdisc_destroy() to qdisc_put()
From: Vlad Buslov @ 2018-09-24 16:22 UTC (permalink / raw)
To: netdev
Cc: jhs, xiyou.wangcong, jiri, davem, stephen, ktkhai,
nicolas.dichtel, gregkh, mark.rutland, leon, paulmck, fw, dsahern,
christian, lucien.xin, jakub.kicinski, jbenc, Vlad Buslov
In-Reply-To: <1537806178-10944-1-git-send-email-vladbu@mellanox.com>
Current implementation of qdisc_destroy() decrements Qdisc reference
counter and only actually destroy Qdisc if reference counter value reached
zero. Rename qdisc_destroy() to qdisc_put() in order for it to better
describe the way in which this function currently implemented and used.
Extract code that deallocates Qdisc into new private qdisc_destroy()
function. It is intended to be shared between regular qdisc_put() and its
unlocked version that is introduced in next patch in this series.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
---
include/net/sch_generic.h | 2 +-
net/sched/sch_api.c | 6 +++---
net/sched/sch_atm.c | 2 +-
net/sched/sch_cbq.c | 2 +-
net/sched/sch_cbs.c | 2 +-
net/sched/sch_drr.c | 4 ++--
net/sched/sch_dsmark.c | 2 +-
net/sched/sch_fifo.c | 2 +-
net/sched/sch_generic.c | 23 ++++++++++++++---------
net/sched/sch_hfsc.c | 2 +-
net/sched/sch_htb.c | 4 ++--
net/sched/sch_mq.c | 4 ++--
net/sched/sch_mqprio.c | 4 ++--
net/sched/sch_multiq.c | 6 +++---
net/sched/sch_netem.c | 2 +-
net/sched/sch_prio.c | 6 +++---
net/sched/sch_qfq.c | 4 ++--
net/sched/sch_red.c | 4 ++--
net/sched/sch_sfb.c | 4 ++--
net/sched/sch_tbf.c | 4 ++--
20 files changed, 47 insertions(+), 42 deletions(-)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index d326fd553b58..fadb1a4d4ee8 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -554,7 +554,7 @@ void dev_deactivate_many(struct list_head *head);
struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
struct Qdisc *qdisc);
void qdisc_reset(struct Qdisc *qdisc);
-void qdisc_destroy(struct Qdisc *qdisc);
+void qdisc_put(struct Qdisc *qdisc);
void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n,
unsigned int len);
struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 411c40344b77..2096138c4bf6 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -920,7 +920,7 @@ static void notify_and_destroy(struct net *net, struct sk_buff *skb,
qdisc_notify(net, skb, n, clid, old, new);
if (old)
- qdisc_destroy(old);
+ qdisc_put(old);
}
/* Graft qdisc "new" to class "classid" of qdisc "parent" or
@@ -973,7 +973,7 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
qdisc_refcount_inc(new);
if (!ingress)
- qdisc_destroy(old);
+ qdisc_put(old);
}
skip:
@@ -1561,7 +1561,7 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
err = qdisc_graft(dev, p, skb, n, clid, q, NULL, extack);
if (err) {
if (q)
- qdisc_destroy(q);
+ qdisc_put(q);
return err;
}
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index cd49afca9617..d714d3747bcb 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -150,7 +150,7 @@ static void atm_tc_put(struct Qdisc *sch, unsigned long cl)
pr_debug("atm_tc_put: destroying\n");
list_del_init(&flow->list);
pr_debug("atm_tc_put: qdisc %p\n", flow->q);
- qdisc_destroy(flow->q);
+ qdisc_put(flow->q);
tcf_block_put(flow->block);
if (flow->sock) {
pr_debug("atm_tc_put: f_count %ld\n",
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index f42025d53cfe..4dc05409e3fb 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1418,7 +1418,7 @@ static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl)
WARN_ON(cl->filters);
tcf_block_put(cl->block);
- qdisc_destroy(cl->q);
+ qdisc_put(cl->q);
qdisc_put_rtab(cl->R_tab);
gen_kill_estimator(&cl->rate_est);
if (cl != &q->link)
diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index e26a24017faa..e689e11b6d0f 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -379,7 +379,7 @@ static void cbs_destroy(struct Qdisc *sch)
cbs_disable_offload(dev, q);
if (q->qdisc)
- qdisc_destroy(q->qdisc);
+ qdisc_put(q->qdisc);
}
static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb)
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index e0b0cf8a9939..cdebaed0f8cf 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -134,7 +134,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
tca[TCA_RATE]);
if (err) {
NL_SET_ERR_MSG(extack, "Failed to replace estimator");
- qdisc_destroy(cl->qdisc);
+ qdisc_put(cl->qdisc);
kfree(cl);
return err;
}
@@ -153,7 +153,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
static void drr_destroy_class(struct Qdisc *sch, struct drr_class *cl)
{
gen_kill_estimator(&cl->rate_est);
- qdisc_destroy(cl->qdisc);
+ qdisc_put(cl->qdisc);
kfree(cl);
}
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 049714c57075..f6f480784bc6 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -412,7 +412,7 @@ static void dsmark_destroy(struct Qdisc *sch)
pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
tcf_block_put(p->block);
- qdisc_destroy(p->q);
+ qdisc_put(p->q);
if (p->mv != p->embedded)
kfree(p->mv);
}
diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index 24893d3b5d22..3809c9bf8896 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -177,7 +177,7 @@ struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops,
if (q) {
err = fifo_set_limit(q, limit);
if (err < 0) {
- qdisc_destroy(q);
+ qdisc_put(q);
q = NULL;
}
}
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index a64132a5db36..3e7696f3e053 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -901,7 +901,7 @@ struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
if (!ops->init || ops->init(sch, NULL, extack) == 0)
return sch;
- qdisc_destroy(sch);
+ qdisc_put(sch);
return NULL;
}
EXPORT_SYMBOL(qdisc_create_dflt);
@@ -941,15 +941,11 @@ void qdisc_free(struct Qdisc *qdisc)
kfree((char *) qdisc - qdisc->padded);
}
-void qdisc_destroy(struct Qdisc *qdisc)
+static void qdisc_destroy(struct Qdisc *qdisc)
{
const struct Qdisc_ops *ops = qdisc->ops;
struct sk_buff *skb, *tmp;
- if (qdisc->flags & TCQ_F_BUILTIN ||
- !refcount_dec_and_test(&qdisc->refcnt))
- return;
-
#ifdef CONFIG_NET_SCHED
qdisc_hash_del(qdisc);
@@ -976,7 +972,16 @@ void qdisc_destroy(struct Qdisc *qdisc)
qdisc_free(qdisc);
}
-EXPORT_SYMBOL(qdisc_destroy);
+
+void qdisc_put(struct Qdisc *qdisc)
+{
+ if (qdisc->flags & TCQ_F_BUILTIN ||
+ !refcount_dec_and_test(&qdisc->refcnt))
+ return;
+
+ qdisc_destroy(qdisc);
+}
+EXPORT_SYMBOL(qdisc_put);
/* Attach toplevel qdisc to device queue. */
struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
@@ -1270,7 +1275,7 @@ static void shutdown_scheduler_queue(struct net_device *dev,
rcu_assign_pointer(dev_queue->qdisc, qdisc_default);
dev_queue->qdisc_sleeping = qdisc_default;
- qdisc_destroy(qdisc);
+ qdisc_put(qdisc);
}
}
@@ -1279,7 +1284,7 @@ void dev_shutdown(struct net_device *dev)
netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc);
if (dev_ingress_queue(dev))
shutdown_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc);
- qdisc_destroy(dev->qdisc);
+ qdisc_put(dev->qdisc);
dev->qdisc = &noop_qdisc;
WARN_ON(timer_pending(&dev->watchdog_timer));
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 3278a76f6861..b18ec1f6de60 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1092,7 +1092,7 @@ hfsc_destroy_class(struct Qdisc *sch, struct hfsc_class *cl)
struct hfsc_sched *q = qdisc_priv(sch);
tcf_block_put(cl->block);
- qdisc_destroy(cl->qdisc);
+ qdisc_put(cl->qdisc);
gen_kill_estimator(&cl->rate_est);
if (cl != &q->root)
kfree(cl);
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 18ac2d6ca294..58b449490757 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1208,7 +1208,7 @@ static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl)
{
if (!cl->level) {
WARN_ON(!cl->leaf.q);
- qdisc_destroy(cl->leaf.q);
+ qdisc_put(cl->leaf.q);
}
gen_kill_estimator(&cl->rate_est);
tcf_block_put(cl->block);
@@ -1409,7 +1409,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
/* turn parent into inner node */
qdisc_reset(parent->leaf.q);
qdisc_tree_reduce_backlog(parent->leaf.q, qlen, backlog);
- qdisc_destroy(parent->leaf.q);
+ qdisc_put(parent->leaf.q);
if (parent->prio_activity)
htb_deactivate(q, parent);
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index d6b8ae4ed7a3..f20f3a0f8424 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -65,7 +65,7 @@ static void mq_destroy(struct Qdisc *sch)
if (!priv->qdiscs)
return;
for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++)
- qdisc_destroy(priv->qdiscs[ntx]);
+ qdisc_put(priv->qdiscs[ntx]);
kfree(priv->qdiscs);
}
@@ -119,7 +119,7 @@ static void mq_attach(struct Qdisc *sch)
qdisc = priv->qdiscs[ntx];
old = dev_graft_qdisc(qdisc->dev_queue, qdisc);
if (old)
- qdisc_destroy(old);
+ qdisc_put(old);
#ifdef CONFIG_NET_SCHED
if (ntx < dev->real_num_tx_queues)
qdisc_hash_add(qdisc, false);
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 0e9d761cdd80..d364e63c396d 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -40,7 +40,7 @@ static void mqprio_destroy(struct Qdisc *sch)
for (ntx = 0;
ntx < dev->num_tx_queues && priv->qdiscs[ntx];
ntx++)
- qdisc_destroy(priv->qdiscs[ntx]);
+ qdisc_put(priv->qdiscs[ntx]);
kfree(priv->qdiscs);
}
@@ -300,7 +300,7 @@ static void mqprio_attach(struct Qdisc *sch)
qdisc = priv->qdiscs[ntx];
old = dev_graft_qdisc(qdisc->dev_queue, qdisc);
if (old)
- qdisc_destroy(old);
+ qdisc_put(old);
if (ntx < dev->real_num_tx_queues)
qdisc_hash_add(qdisc, false);
}
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 1da7ea8de0ad..7410ce4d0321 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -175,7 +175,7 @@ multiq_destroy(struct Qdisc *sch)
tcf_block_put(q->block);
for (band = 0; band < q->bands; band++)
- qdisc_destroy(q->queues[band]);
+ qdisc_put(q->queues[band]);
kfree(q->queues);
}
@@ -204,7 +204,7 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt,
q->queues[i] = &noop_qdisc;
qdisc_tree_reduce_backlog(child, child->q.qlen,
child->qstats.backlog);
- qdisc_destroy(child);
+ qdisc_put(child);
}
}
@@ -228,7 +228,7 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt,
qdisc_tree_reduce_backlog(old,
old->q.qlen,
old->qstats.backlog);
- qdisc_destroy(old);
+ qdisc_put(old);
}
sch_tree_unlock(sch);
}
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 506e1960ed7f..57b3ad9394ad 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -1022,7 +1022,7 @@ static void netem_destroy(struct Qdisc *sch)
qdisc_watchdog_cancel(&q->watchdog);
if (q->qdisc)
- qdisc_destroy(q->qdisc);
+ qdisc_put(q->qdisc);
dist_free(q->delay_dist);
dist_free(q->slot_dist);
}
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 222e53d3d27a..f8af98621179 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -175,7 +175,7 @@ prio_destroy(struct Qdisc *sch)
tcf_block_put(q->block);
prio_offload(sch, NULL);
for (prio = 0; prio < q->bands; prio++)
- qdisc_destroy(q->queues[prio]);
+ qdisc_put(q->queues[prio]);
}
static int prio_tune(struct Qdisc *sch, struct nlattr *opt,
@@ -205,7 +205,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt,
extack);
if (!queues[i]) {
while (i > oldbands)
- qdisc_destroy(queues[--i]);
+ qdisc_put(queues[--i]);
return -ENOMEM;
}
}
@@ -220,7 +220,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt,
qdisc_tree_reduce_backlog(child, child->q.qlen,
child->qstats.backlog);
- qdisc_destroy(child);
+ qdisc_put(child);
}
for (i = oldbands; i < q->bands; i++) {
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index bb1a9c11fc54..dc37c4ead439 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -526,7 +526,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
return 0;
destroy_class:
- qdisc_destroy(cl->qdisc);
+ qdisc_put(cl->qdisc);
kfree(cl);
return err;
}
@@ -537,7 +537,7 @@ static void qfq_destroy_class(struct Qdisc *sch, struct qfq_class *cl)
qfq_rm_from_agg(q, cl);
gen_kill_estimator(&cl->rate_est);
- qdisc_destroy(cl->qdisc);
+ qdisc_put(cl->qdisc);
kfree(cl);
}
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 56c181c3feeb..3ce6c0a2c493 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -181,7 +181,7 @@ static void red_destroy(struct Qdisc *sch)
del_timer_sync(&q->adapt_timer);
red_offload(sch, false);
- qdisc_destroy(q->qdisc);
+ qdisc_put(q->qdisc);
}
static const struct nla_policy red_policy[TCA_RED_MAX + 1] = {
@@ -233,7 +233,7 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt,
if (child) {
qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
q->qdisc->qstats.backlog);
- qdisc_destroy(q->qdisc);
+ qdisc_put(q->qdisc);
q->qdisc = child;
}
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 7cbdad8419b7..bab506b01a32 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -469,7 +469,7 @@ static void sfb_destroy(struct Qdisc *sch)
struct sfb_sched_data *q = qdisc_priv(sch);
tcf_block_put(q->block);
- qdisc_destroy(q->qdisc);
+ qdisc_put(q->qdisc);
}
static const struct nla_policy sfb_policy[TCA_SFB_MAX + 1] = {
@@ -523,7 +523,7 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt,
qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
q->qdisc->qstats.backlog);
- qdisc_destroy(q->qdisc);
+ qdisc_put(q->qdisc);
q->qdisc = child;
q->rehash_interval = msecs_to_jiffies(ctl->rehash_interval);
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index a4530e85bd02..942dcca09cf2 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -392,7 +392,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
if (child) {
qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
q->qdisc->qstats.backlog);
- qdisc_destroy(q->qdisc);
+ qdisc_put(q->qdisc);
q->qdisc = child;
}
q->limit = qopt->limit;
@@ -438,7 +438,7 @@ static void tbf_destroy(struct Qdisc *sch)
struct tbf_sched_data *q = qdisc_priv(sch);
qdisc_watchdog_cancel(&q->watchdog);
- qdisc_destroy(q->qdisc);
+ qdisc_put(q->qdisc);
}
static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb)
--
2.7.5
^ permalink raw reply related
* Re: [PATCH v2 net-next 9/9] devlink: Add Documentation/networking/devlink-params-bnxt.txt
From: Jakub Kicinski @ 2018-09-24 16:24 UTC (permalink / raw)
To: Vasundhara Volam; +Cc: davem, michael.chan, netdev
In-Reply-To: <1537766181-18994-10-git-send-email-vasundhara-v.volam@broadcom.com>
On Mon, 24 Sep 2018 10:46:21 +0530, Vasundhara Volam wrote:
> This patch adds a new file to add information about configuration
> parameters that are supported by bnxt_en driver via devlink.
>
> Cc: "David S. Miller" <davem@davemloft.net>
> Cc: Jonathan Corbet <corbet@lwn.net>
> Cc: linux-doc@vger.kernel.org
> Cc: Jiri Pirko <jiri@mellanox.com>
> Cc: Michael Chan <michael.chan@broadcom.com>
>
> Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
> ---
> Documentation/networking/devlink-params-bnxt.txt | 35 ++++++++++++++++++++++++
> 1 file changed, 35 insertions(+)
> create mode 100644 Documentation/networking/devlink-params-bnxt.txt
>
> diff --git a/Documentation/networking/devlink-params-bnxt.txt b/Documentation/networking/devlink-params-bnxt.txt
> new file mode 100644
> index 0000000..ca7c457
> --- /dev/null
> +++ b/Documentation/networking/devlink-params-bnxt.txt
> @@ -0,0 +1,35 @@
> +enable_sriov [DEVICE, GENERIC]
> + Enable Single Root I/O Virtualisation (SRIOV) in
> + the device.
> + Type: Boolean
> + Configuration mode: Permanent
> +
> +ignore_ari [DEVICE, GENERIC]
> + Ignore Alternative Routing-ID Interpretation (ARI)
> + capability. If enabled, adapter will ignore ARI
> + capability even when platforms has the support
> + enabled and creates same number of partitions when
> + platform does not support ARI.
> + Type: Boolean
> + Configuration mode: Permanent
> +
> +msix_vec_per_pf_max [DEVICE, GENERIC]
> + Provides the maximum number of MSIX interrupts that
> + a device can create. Value is same across all
> + physical functions (PFs) in the device.
> + Type: u32
> + Configuration mode: Permanent
> +
> +msix_vec_per_pf_min [DEVICE, GENERIC]
> + Provides the minimum number of MSIX interrupts required
> + or the device initialization. Value is same across all
> + physical functions (PFs) in the device.
> + Type: u32
> + Configuration mode: Permanent
Why duplicate the description of the generic parameters?
> +gre_ver_check [DEVICE, DRIVER-SPECIFIC]
> + Generic Routing Encapsulation (GRE) version check will
> + be enabled in the device. If disabled, device skips
> + version checking for incoming packets.
> + Type: Boolean
> + Configuration mode: Permanent
^ permalink raw reply
* [PATCH 0/5] Introducing ixgbe AF_XDP ZC support
From: Björn Töpel @ 2018-09-24 16:35 UTC (permalink / raw)
To: jeffrey.t.kirsher, intel-wired-lan
Cc: Björn Töpel, magnus.karlsson, magnus.karlsson, ast,
daniel, netdev, brouer, u9012063, tuc
From: Björn Töpel <bjorn.topel@intel.com>
This patch set introduces zero-copy AF_XDP support for Intel's ixgbe
driver.
The ixgbe zero-copy code is located in its own file ixgbe_xsk.[ch],
analogous to the i40e ZC support. Again, as in i40e, code paths have
been copied from the XDP path to the zero-copy path. Going forward we
will try to generalize more code between the AF_XDP ZC drivers, and
also reduce the heavy C&P.
We have run some benchmarks on a dual socket system with two Broadwell
E5 2660 @ 2.0 GHz with hyperthreading turned off. Each socket has 14
cores which gives a total of 28, but only two cores are used in these
experiments. One for TR/RX and one for the user space application. The
memory is DDR4 @ 2133 MT/s (1067 MHz) and the size of each DIMM is
8192MB and with 8 of those DIMMs in the system we have 64 GB of total
memory. The compiler used is GCC 7.3.0. The NIC is Intel
82599ES/X520-2 10Gbit/s using the ixgbe driver.
Below are the results in Mpps of the 82599ES/X520-2 NIC benchmark runs
for 64B and 1500B packets, generated by a commercial packet generator
HW blasting packets at full 10Gbit/s line rate. The results are with
retpoline and all other spectre and meltdown fixes.
AF_XDP performance 64B packets:
Benchmark XDP_DRV with zerocopy
rxdrop 14.7
txpush 14.6
l2fwd 11.1
AF_XDP performance 1500B packets:
Benchmark XDP_DRV with zerocopy
rxdrop 0.8
l2fwd 0.8
XDP performance on our system as a base line.
64B packets:
XDP stats CPU Mpps issue-pps
XDP-RX CPU 16 14.7 0
1500B packets:
XDP stats CPU Mpps issue-pps
XDP-RX CPU 16 0.8 0
The structure of the patch set is as follows:
Patch 1: Introduce Rx/Tx ring enable/disable functionality
Patch 2: Preparatory patche to ixgbe driver code for RX
Patch 3: ixgbe zero-copy support for RX
Patch 4: Preparatory patch to ixgbe driver code for TX
Patch 5: ixgbe zero-copy support for TX
Cheers!
Björn
Björn Töpel (5):
ixgbe: added Rx/Tx ring disable/enable functions
ixgbe: move common Rx functions to ixgbe_txrx_common.h
ixgbe: add AF_XDP zero-copy Rx support
ixgbe: move common Tx functions to ixgbe_txrx_common.h
ixgbe: add AF_XDP zero-copy Tx support
drivers/net/ethernet/intel/ixgbe/Makefile | 3 +-
drivers/net/ethernet/intel/ixgbe/ixgbe.h | 27 +-
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 290 ++++++-
.../ethernet/intel/ixgbe/ixgbe_txrx_common.h | 50 ++
drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c | 814 ++++++++++++++++++
5 files changed, 1139 insertions(+), 45 deletions(-)
create mode 100644 drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
create mode 100644 drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
--
2.17.1
^ permalink raw reply
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