Re: Linux 4.20.16

From: Greg KH
Date: Thu Mar 14 2019 - 12:27:56 EST


diff --git a/Makefile b/Makefile
index 25b45c24bac0..2979ad27e16a 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 4
PATCHLEVEL = 20
-SUBLEVEL = 15
+SUBLEVEL = 16
EXTRAVERSION =
NAME = Shy Crocodile

diff --git a/arch/arm/boot/dts/am335x-shc.dts b/arch/arm/boot/dts/am335x-shc.dts
index 1d925ed2b102..8fbbad11a80c 100644
--- a/arch/arm/boot/dts/am335x-shc.dts
+++ b/arch/arm/boot/dts/am335x-shc.dts
@@ -215,7 +215,7 @@
pinctrl-names = "default";
pinctrl-0 = <&mmc1_pins>;
bus-width = <0x4>;
- cd-gpios = <&gpio0 6 GPIO_ACTIVE_HIGH>;
+ cd-gpios = <&gpio0 6 GPIO_ACTIVE_LOW>;
cd-inverted;
max-frequency = <26000000>;
vmmc-supply = <&vmmcsd_fixed>;
diff --git a/arch/arm/boot/dts/exynos3250.dtsi b/arch/arm/boot/dts/exynos3250.dtsi
index 27a1ee28c3bb..94efca78c42f 100644
--- a/arch/arm/boot/dts/exynos3250.dtsi
+++ b/arch/arm/boot/dts/exynos3250.dtsi
@@ -168,6 +168,9 @@
interrupt-controller;
#interrupt-cells = <3>;
interrupt-parent = <&gic>;
+ clock-names = "clkout8";
+ clocks = <&cmu CLK_FIN_PLL>;
+ #clock-cells = <1>;
};

mipi_phy: video-phy {
diff --git a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
index 2caa3132f34e..fe91b6828da3 100644
--- a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
+++ b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
@@ -49,7 +49,7 @@
};

emmc_pwrseq: pwrseq {
- pinctrl-0 = <&sd1_cd>;
+ pinctrl-0 = <&emmc_rstn>;
pinctrl-names = "default";
compatible = "mmc-pwrseq-emmc";
reset-gpios = <&gpk1 2 GPIO_ACTIVE_LOW>;
@@ -161,12 +161,6 @@
cpu0-supply = <&buck2_reg>;
};

-/* RSTN signal for eMMC */
-&sd1_cd {
- samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
- samsung,pin-drv = <EXYNOS4_PIN_DRV_LV1>;
-};
-
&pinctrl_1 {
gpio_power_key: power_key {
samsung,pins = "gpx1-3";
@@ -184,6 +178,11 @@
samsung,pins = "gpx3-7";
samsung,pin-pud = <EXYNOS_PIN_PULL_DOWN>;
};
+
+ emmc_rstn: emmc-rstn {
+ samsung,pins = "gpk1-2";
+ samsung,pin-pud = <EXYNOS_PIN_PULL_NONE>;
+ };
};

&ehci {
diff --git a/arch/arm/boot/dts/exynos5422-odroid-core.dtsi b/arch/arm/boot/dts/exynos5422-odroid-core.dtsi
index 2fac4baf1eb4..934cec60577a 100644
--- a/arch/arm/boot/dts/exynos5422-odroid-core.dtsi
+++ b/arch/arm/boot/dts/exynos5422-odroid-core.dtsi
@@ -467,7 +467,7 @@
buck8_reg: BUCK8 {
regulator-name = "vdd_1.8v_ldo";
regulator-min-microvolt = <800000>;
- regulator-max-microvolt = <1500000>;
+ regulator-max-microvolt = <2000000>;
regulator-always-on;
regulator-boot-on;
};
diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi
index 95a3c1cb877d..89ba48f4273b 100644
--- a/arch/arm/boot/dts/imx6sx.dtsi
+++ b/arch/arm/boot/dts/imx6sx.dtsi
@@ -462,7 +462,7 @@
};

gpt: gpt@2098000 {
- compatible = "fsl,imx6sx-gpt", "fsl,imx31-gpt";
+ compatible = "fsl,imx6sx-gpt", "fsl,imx6dl-gpt";
reg = <0x02098000 0x4000>;
interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&clks IMX6SX_CLK_GPT_BUS>,
diff --git a/arch/arm/boot/dts/meson.dtsi b/arch/arm/boot/dts/meson.dtsi
index 0d9faf1a51ea..a86b89086334 100644
--- a/arch/arm/boot/dts/meson.dtsi
+++ b/arch/arm/boot/dts/meson.dtsi
@@ -263,7 +263,7 @@
compatible = "amlogic,meson6-dwmac", "snps,dwmac";
reg = <0xc9410000 0x10000
0xc1108108 0x4>;
- interrupts = <GIC_SPI 8 IRQ_TYPE_EDGE_RISING>;
+ interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "macirq";
status = "disabled";
};
diff --git a/arch/arm/boot/dts/meson8b-ec100.dts b/arch/arm/boot/dts/meson8b-ec100.dts
index 0872f6e3abf5..d50fc2f60fa3 100644
--- a/arch/arm/boot/dts/meson8b-ec100.dts
+++ b/arch/arm/boot/dts/meson8b-ec100.dts
@@ -205,8 +205,7 @@
cap-sd-highspeed;
disable-wp;

- cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>;
- cd-inverted;
+ cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>;

vmmc-supply = <&vcc_3v3>;
};
diff --git a/arch/arm/boot/dts/meson8b-odroidc1.dts b/arch/arm/boot/dts/meson8b-odroidc1.dts
index 58669abda259..0f0a46ddf3ff 100644
--- a/arch/arm/boot/dts/meson8b-odroidc1.dts
+++ b/arch/arm/boot/dts/meson8b-odroidc1.dts
@@ -221,7 +221,6 @@
/* Realtek RTL8211F (0x001cc916) */
eth_phy: ethernet-phy@0 {
reg = <0>;
- eee-broken-1000t;
interrupt-parent = <&gpio_intc>;
/* GPIOH_3 */
interrupts = <17 IRQ_TYPE_LEVEL_LOW>;
@@ -273,8 +272,7 @@
cap-sd-highspeed;
disable-wp;

- cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>;
- cd-inverted;
+ cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>;

vmmc-supply = <&tflash_vdd>;
vqmmc-supply = <&tf_io>;
diff --git a/arch/arm/boot/dts/meson8m2-mxiii-plus.dts b/arch/arm/boot/dts/meson8m2-mxiii-plus.dts
index f5853610b20b..6ac02beb5fa7 100644
--- a/arch/arm/boot/dts/meson8m2-mxiii-plus.dts
+++ b/arch/arm/boot/dts/meson8m2-mxiii-plus.dts
@@ -206,8 +206,7 @@
cap-sd-highspeed;
disable-wp;

- cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>;
- cd-inverted;
+ cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>;

vmmc-supply = <&vcc_3v3>;
};
diff --git a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi
index ddc7a7bb33c0..f57acf8f66b9 100644
--- a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi
+++ b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi
@@ -105,7 +105,7 @@
interrupts-extended = <
&cpcap 15 0 &cpcap 14 0 &cpcap 28 0 &cpcap 19 0
&cpcap 18 0 &cpcap 17 0 &cpcap 16 0 &cpcap 49 0
- &cpcap 48 1
+ &cpcap 48 0
>;
interrupt-names =
"id_ground", "id_float", "se0conn", "vbusvld",
diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi
index d5fe55392230..68e675258906 100644
--- a/arch/arm/boot/dts/omap3-gta04.dtsi
+++ b/arch/arm/boot/dts/omap3-gta04.dtsi
@@ -714,11 +714,7 @@

vdda-supply = <&vdac>;

- #address-cells = <1>;
- #size-cells = <0>;
-
port {
- reg = <0>;
venc_out: endpoint {
remote-endpoint = <&opa_in>;
ti,channels = <1>;
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index 182a53991c90..826920e6b878 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -814,7 +814,7 @@
/* For debugging, it is often good idea to remove this GPIO.
It means you can remove back cover (to reboot by removing
battery) and still use the MMC card. */
- cd-gpios = <&gpio6 0 GPIO_ACTIVE_HIGH>; /* 160 */
+ cd-gpios = <&gpio6 0 GPIO_ACTIVE_LOW>; /* 160 */
};

/* most boards use vaux3, only some old versions use vmmc2 instead */
diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi
index 0d9b85317529..e142e6c70a59 100644
--- a/arch/arm/boot/dts/omap3-n950-n9.dtsi
+++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi
@@ -370,6 +370,19 @@
compatible = "ti,omap2-onenand";
reg = <0 0 0x20000>; /* CS0, offset 0, IO size 128K */

+ /*
+ * These timings are based on CONFIG_OMAP_GPMC_DEBUG=y reported
+ * bootloader set values when booted with v4.19 using both N950
+ * and N9 devices (OneNAND Manufacturer: Samsung):
+ *
+ * gpmc cs0 before gpmc_cs_program_settings:
+ * cs0 GPMC_CS_CONFIG1: 0xfd001202
+ * cs0 GPMC_CS_CONFIG2: 0x00181800
+ * cs0 GPMC_CS_CONFIG3: 0x00030300
+ * cs0 GPMC_CS_CONFIG4: 0x18001804
+ * cs0 GPMC_CS_CONFIG5: 0x03171d1d
+ * cs0 GPMC_CS_CONFIG6: 0x97080000
+ */
gpmc,sync-read;
gpmc,sync-write;
gpmc,burst-length = <16>;
@@ -379,26 +392,27 @@
gpmc,device-width = <2>;
gpmc,mux-add-data = <2>;
gpmc,cs-on-ns = <0>;
- gpmc,cs-rd-off-ns = <87>;
- gpmc,cs-wr-off-ns = <87>;
+ gpmc,cs-rd-off-ns = <122>;
+ gpmc,cs-wr-off-ns = <122>;
gpmc,adv-on-ns = <0>;
- gpmc,adv-rd-off-ns = <10>;
- gpmc,adv-wr-off-ns = <10>;
- gpmc,oe-on-ns = <15>;
- gpmc,oe-off-ns = <87>;
+ gpmc,adv-rd-off-ns = <15>;
+ gpmc,adv-wr-off-ns = <15>;
+ gpmc,oe-on-ns = <20>;
+ gpmc,oe-off-ns = <122>;
gpmc,we-on-ns = <0>;
- gpmc,we-off-ns = <87>;
- gpmc,rd-cycle-ns = <112>;
- gpmc,wr-cycle-ns = <112>;
- gpmc,access-ns = <81>;
+ gpmc,we-off-ns = <122>;
+ gpmc,rd-cycle-ns = <148>;
+ gpmc,wr-cycle-ns = <148>;
+ gpmc,access-ns = <117>;
gpmc,page-burst-access-ns = <15>;
gpmc,bus-turnaround-ns = <0>;
gpmc,cycle2cycle-delay-ns = <0>;
gpmc,wait-monitoring-ns = <0>;
- gpmc,clk-activation-ns = <5>;
- gpmc,wr-data-mux-bus-ns = <30>;
- gpmc,wr-access-ns = <81>;
- gpmc,sync-clk-ps = <15000>;
+ gpmc,clk-activation-ns = <10>;
+ gpmc,wr-data-mux-bus-ns = <40>;
+ gpmc,wr-access-ns = <117>;
+
+ gpmc,sync-clk-ps = <15000>; /* TBC; Where this value came? */

/*
* MTD partition table corresponding to Nokia's MeeGo 1.2
diff --git a/arch/arm/boot/dts/sun8i-h3-beelink-x2.dts b/arch/arm/boot/dts/sun8i-h3-beelink-x2.dts
index 5d23667dc2d2..25540b7694d5 100644
--- a/arch/arm/boot/dts/sun8i-h3-beelink-x2.dts
+++ b/arch/arm/boot/dts/sun8i-h3-beelink-x2.dts
@@ -53,7 +53,7 @@

aliases {
serial0 = &uart0;
- /* ethernet0 is the H3 emac, defined in sun8i-h3.dtsi */
+ ethernet0 = &emac;
ethernet1 = &sdiowifi;
};

diff --git a/arch/arm/plat-pxa/ssp.c b/arch/arm/plat-pxa/ssp.c
index ed36dcab80f1..f51919974183 100644
--- a/arch/arm/plat-pxa/ssp.c
+++ b/arch/arm/plat-pxa/ssp.c
@@ -190,8 +190,6 @@ static int pxa_ssp_remove(struct platform_device *pdev)
if (ssp == NULL)
return -ENODEV;

- iounmap(ssp->mmio_base);
-
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
release_mem_region(res->start, resource_size(res));

@@ -201,7 +199,6 @@ static int pxa_ssp_remove(struct platform_device *pdev)
list_del(&ssp->node);
mutex_unlock(&ssp_lock);

- kfree(ssp);
return 0;
}

diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
index f4964bee6a1a..e80a792827ed 100644
--- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
+++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
@@ -118,6 +118,7 @@
reset-gpios = <&gpio0 5 GPIO_ACTIVE_LOW>;
clocks = <&pmic>;
clock-names = "ext_clock";
+ post-power-on-delay-ms = <10>;
power-off-delay-us = <10>;
};

@@ -300,7 +301,6 @@

dwmmc_0: dwmmc0@f723d000 {
cap-mmc-highspeed;
- mmc-hs200-1_8v;
non-removable;
bus-width = <0x8>;
vmmc-supply = <&ldo19>;
diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi
index b29fe80d7288..461612a5ab5e 100644
--- a/arch/arm64/boot/dts/qcom/msm8996.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi
@@ -397,7 +397,7 @@
};

intc: interrupt-controller@9bc0000 {
- compatible = "arm,gic-v3";
+ compatible = "qcom,msm8996-gic-v3", "arm,gic-v3";
#interrupt-cells = <3>;
interrupt-controller;
#redistributor-regions = <1>;
diff --git a/arch/arm64/boot/dts/renesas/r8a7796.dtsi b/arch/arm64/boot/dts/renesas/r8a7796.dtsi
index 1ec6aaa520c1..09320caea54e 100644
--- a/arch/arm64/boot/dts/renesas/r8a7796.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a7796.dtsi
@@ -1160,6 +1160,9 @@
<&cpg CPG_CORE R8A7796_CLK_S3D1>,
<&scif_clk>;
clock-names = "fck", "brg_int", "scif_clk";
+ dmas = <&dmac1 0x13>, <&dmac1 0x12>,
+ <&dmac2 0x13>, <&dmac2 0x12>;
+ dma-names = "tx", "rx", "tx", "rx";
power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
resets = <&cpg 310>;
status = "disabled";
diff --git a/arch/arm64/boot/dts/renesas/r8a77965.dtsi b/arch/arm64/boot/dts/renesas/r8a77965.dtsi
index 83946ca2eba5..d59dada13722 100644
--- a/arch/arm64/boot/dts/renesas/r8a77965.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77965.dtsi
@@ -1028,6 +1028,9 @@
<&cpg CPG_CORE R8A77965_CLK_S3D1>,
<&scif_clk>;
clock-names = "fck", "brg_int", "scif_clk";
+ dmas = <&dmac1 0x13>, <&dmac1 0x12>,
+ <&dmac2 0x13>, <&dmac2 0x12>;
+ dma-names = "tx", "rx", "tx", "rx";
power-domains = <&sysc R8A77965_PD_ALWAYS_ON>;
resets = <&cpg 310>;
status = "disabled";
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-zcu100-revC.dts b/arch/arm64/boot/dts/xilinx/zynqmp-zcu100-revC.dts
index eb5e8bddb610..8954c8c6f547 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-zcu100-revC.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-zcu100-revC.dts
@@ -101,6 +101,7 @@
sdio_pwrseq: sdio_pwrseq {
compatible = "mmc-pwrseq-simple";
reset-gpios = <&gpio 7 GPIO_ACTIVE_LOW>; /* WIFI_EN */
+ post-power-on-delay-ms = <10>;
};
};

diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 2a5b338b2542..f17afb99890c 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -478,13 +478,13 @@ bool arch_within_kprobe_blacklist(unsigned long addr)
addr < (unsigned long)__entry_text_end) ||
(addr >= (unsigned long)__idmap_text_start &&
addr < (unsigned long)__idmap_text_end) ||
+ (addr >= (unsigned long)__hyp_text_start &&
+ addr < (unsigned long)__hyp_text_end) ||
!!search_exception_tables(addr))
return true;

if (!is_kernel_in_hyp_mode()) {
- if ((addr >= (unsigned long)__hyp_text_start &&
- addr < (unsigned long)__hyp_text_end) ||
- (addr >= (unsigned long)__hyp_idmap_text_start &&
+ if ((addr >= (unsigned long)__hyp_idmap_text_start &&
addr < (unsigned long)__hyp_idmap_text_end))
return true;
}
diff --git a/arch/mips/boot/dts/ingenic/ci20.dts b/arch/mips/boot/dts/ingenic/ci20.dts
index 50cff3cbcc6d..4f7b1fa31cf5 100644
--- a/arch/mips/boot/dts/ingenic/ci20.dts
+++ b/arch/mips/boot/dts/ingenic/ci20.dts
@@ -76,7 +76,7 @@
status = "okay";

pinctrl-names = "default";
- pinctrl-0 = <&pins_uart2>;
+ pinctrl-0 = <&pins_uart3>;
};

&uart4 {
@@ -196,9 +196,9 @@
bias-disable;
};

- pins_uart2: uart2 {
- function = "uart2";
- groups = "uart2-data", "uart2-hwflow";
+ pins_uart3: uart3 {
+ function = "uart3";
+ groups = "uart3-data", "uart3-hwflow";
bias-disable;
};

diff --git a/arch/mips/boot/dts/ingenic/jz4740.dtsi b/arch/mips/boot/dts/ingenic/jz4740.dtsi
index 6fb16fd24035..2beb78a62b7d 100644
--- a/arch/mips/boot/dts/ingenic/jz4740.dtsi
+++ b/arch/mips/boot/dts/ingenic/jz4740.dtsi
@@ -161,7 +161,7 @@
#dma-cells = <2>;

interrupt-parent = <&intc>;
- interrupts = <29>;
+ interrupts = <20>;

clocks = <&cgu JZ4740_CLK_DMA>;

diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index d4f7fd4550e1..85522c137f19 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -371,7 +371,7 @@ static inline int is_sp_move_ins(union mips_instruction *ip, int *frame_size)
static int get_frame_info(struct mips_frame_info *info)
{
bool is_mmips = IS_ENABLED(CONFIG_CPU_MICROMIPS);
- union mips_instruction insn, *ip, *ip_end;
+ union mips_instruction insn, *ip;
const unsigned int max_insns = 128;
unsigned int last_insn_size = 0;
unsigned int i;
@@ -384,10 +384,9 @@ static int get_frame_info(struct mips_frame_info *info)
if (!ip)
goto err;

- ip_end = (void *)ip + info->func_size;
-
- for (i = 0; i < max_insns && ip < ip_end; i++) {
+ for (i = 0; i < max_insns; i++) {
ip = (void *)ip + last_insn_size;
+
if (is_mmips && mm_insn_16bit(ip->halfword[0])) {
insn.word = ip->halfword[0] << 16;
last_insn_size = 2;
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index 0531f49af5c3..ce70bceb8872 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -22,7 +22,7 @@
* This decides where the kernel will search for a free chunk of vm
* space during mmap's.
*/
-#define TASK_UNMAPPED_BASE PAGE_ALIGN(TASK_SIZE >> 1)
+#define TASK_UNMAPPED_BASE PAGE_ALIGN(TASK_SIZE / 3)

#define STACK_TOP TASK_SIZE
#define STACK_TOP_MAX STACK_TOP
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 2c290e6aaa6e..6d652826b5cb 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -196,7 +196,7 @@ static void __init setup_bootmem(void)
BUG_ON(mem_size == 0);

set_max_mapnr(PFN_DOWN(mem_size));
- max_low_pfn = memblock_end_of_DRAM();
+ max_low_pfn = PFN_DOWN(memblock_end_of_DRAM());

#ifdef CONFIG_BLK_DEV_INITRD
setup_initrd();
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 1d9bfaff60bc..658ebf645f42 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -28,7 +28,8 @@ static void __init zone_sizes_init(void)
unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, };

#ifdef CONFIG_ZONE_DMA32
- max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G, max_low_pfn));
+ max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G,
+ (unsigned long) PFN_PHYS(max_low_pfn)));
#endif
max_zone_pfns[ZONE_NORMAL] = max_low_pfn;

diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 64037895b085..f105ae8651c9 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -600,6 +600,14 @@ ENTRY(trampoline_32bit_src)
leal TRAMPOLINE_32BIT_PGTABLE_OFFSET(%ecx), %eax
movl %eax, %cr3
3:
+ /* Set EFER.LME=1 as a precaution in case hypervsior pulls the rug */
+ pushl %ecx
+ movl $MSR_EFER, %ecx
+ rdmsr
+ btsl $_EFER_LME, %eax
+ wrmsr
+ popl %ecx
+
/* Enable PAE and LA57 (if required) paging modes */
movl $X86_CR4_PAE, %eax
cmpl $0, %edx
diff --git a/arch/x86/boot/compressed/pgtable.h b/arch/x86/boot/compressed/pgtable.h
index 91f75638f6e6..6ff7e81b5628 100644
--- a/arch/x86/boot/compressed/pgtable.h
+++ b/arch/x86/boot/compressed/pgtable.h
@@ -6,7 +6,7 @@
#define TRAMPOLINE_32BIT_PGTABLE_OFFSET 0

#define TRAMPOLINE_32BIT_CODE_OFFSET PAGE_SIZE
-#define TRAMPOLINE_32BIT_CODE_SIZE 0x60
+#define TRAMPOLINE_32BIT_CODE_SIZE 0x70

#define TRAMPOLINE_32BIT_STACK_END TRAMPOLINE_32BIT_SIZE

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index b684f0294f35..e2b1447192a8 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1995,7 +1995,7 @@ static int x86_pmu_commit_txn(struct pmu *pmu)
*/
static void free_fake_cpuc(struct cpu_hw_events *cpuc)
{
- kfree(cpuc->shared_regs);
+ intel_cpuc_finish(cpuc);
kfree(cpuc);
}

@@ -2007,14 +2007,11 @@ static struct cpu_hw_events *allocate_fake_cpuc(void)
cpuc = kzalloc(sizeof(*cpuc), GFP_KERNEL);
if (!cpuc)
return ERR_PTR(-ENOMEM);
-
- /* only needed, if we have extra_regs */
- if (x86_pmu.extra_regs) {
- cpuc->shared_regs = allocate_shared_regs(cpu);
- if (!cpuc->shared_regs)
- goto error;
- }
cpuc->is_fake = 1;
+
+ if (intel_cpuc_prepare(cpuc, cpu))
+ goto error;
+
return cpuc;
error:
free_fake_cpuc(cpuc);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index ede20c44cc69..3d77c736299f 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -1999,6 +1999,39 @@ static void intel_pmu_nhm_enable_all(int added)
intel_pmu_enable_all(added);
}

+static void intel_set_tfa(struct cpu_hw_events *cpuc, bool on)
+{
+ u64 val = on ? MSR_TFA_RTM_FORCE_ABORT : 0;
+
+ if (cpuc->tfa_shadow != val) {
+ cpuc->tfa_shadow = val;
+ wrmsrl(MSR_TSX_FORCE_ABORT, val);
+ }
+}
+
+static void intel_tfa_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr)
+{
+ /*
+ * We're going to use PMC3, make sure TFA is set before we touch it.
+ */
+ if (cntr == 3 && !cpuc->is_fake)
+ intel_set_tfa(cpuc, true);
+}
+
+static void intel_tfa_pmu_enable_all(int added)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+ /*
+ * If we find PMC3 is no longer used when we enable the PMU, we can
+ * clear TFA.
+ */
+ if (!test_bit(3, cpuc->active_mask))
+ intel_set_tfa(cpuc, false);
+
+ intel_pmu_enable_all(added);
+}
+
static void enable_counter_freeze(void)
{
update_debugctlmsr(get_debugctlmsr() |
@@ -2768,6 +2801,35 @@ intel_stop_scheduling(struct cpu_hw_events *cpuc)
raw_spin_unlock(&excl_cntrs->lock);
}

+static struct event_constraint *
+dyn_constraint(struct cpu_hw_events *cpuc, struct event_constraint *c, int idx)
+{
+ WARN_ON_ONCE(!cpuc->constraint_list);
+
+ if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) {
+ struct event_constraint *cx;
+
+ /*
+ * grab pre-allocated constraint entry
+ */
+ cx = &cpuc->constraint_list[idx];
+
+ /*
+ * initialize dynamic constraint
+ * with static constraint
+ */
+ *cx = *c;
+
+ /*
+ * mark constraint as dynamic
+ */
+ cx->flags |= PERF_X86_EVENT_DYNAMIC;
+ c = cx;
+ }
+
+ return c;
+}
+
static struct event_constraint *
intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
int idx, struct event_constraint *c)
@@ -2798,27 +2860,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
* only needed when constraint has not yet
* been cloned (marked dynamic)
*/
- if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) {
- struct event_constraint *cx;
-
- /*
- * grab pre-allocated constraint entry
- */
- cx = &cpuc->constraint_list[idx];
-
- /*
- * initialize dynamic constraint
- * with static constraint
- */
- *cx = *c;
-
- /*
- * mark constraint as dynamic, so we
- * can free it later on
- */
- cx->flags |= PERF_X86_EVENT_DYNAMIC;
- c = cx;
- }
+ c = dyn_constraint(cpuc, c, idx);

/*
* From here on, the constraint is dynamic.
@@ -3345,6 +3387,26 @@ glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
return c;
}

+static bool allow_tsx_force_abort = true;
+
+static struct event_constraint *
+tfa_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+ struct perf_event *event)
+{
+ struct event_constraint *c = hsw_get_event_constraints(cpuc, idx, event);
+
+ /*
+ * Without TFA we must not use PMC3.
+ */
+ if (!allow_tsx_force_abort && test_bit(3, c->idxmsk)) {
+ c = dyn_constraint(cpuc, c, idx);
+ c->idxmsk64 &= ~(1ULL << 3);
+ c->weight--;
+ }
+
+ return c;
+}
+
/*
* Broadwell:
*
@@ -3398,7 +3460,7 @@ ssize_t intel_event_sysfs_show(char *page, u64 config)
return x86_event_sysfs_show(page, config, event);
}

-struct intel_shared_regs *allocate_shared_regs(int cpu)
+static struct intel_shared_regs *allocate_shared_regs(int cpu)
{
struct intel_shared_regs *regs;
int i;
@@ -3430,23 +3492,24 @@ static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu)
return c;
}

-static int intel_pmu_cpu_prepare(int cpu)
-{
- struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);

+int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
+{
if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) {
cpuc->shared_regs = allocate_shared_regs(cpu);
if (!cpuc->shared_regs)
goto err;
}

- if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
+ if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA)) {
size_t sz = X86_PMC_IDX_MAX * sizeof(struct event_constraint);

- cpuc->constraint_list = kzalloc(sz, GFP_KERNEL);
+ cpuc->constraint_list = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu));
if (!cpuc->constraint_list)
goto err_shared_regs;
+ }

+ if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
cpuc->excl_cntrs = allocate_excl_cntrs(cpu);
if (!cpuc->excl_cntrs)
goto err_constraint_list;
@@ -3468,6 +3531,11 @@ static int intel_pmu_cpu_prepare(int cpu)
return -ENOMEM;
}

+static int intel_pmu_cpu_prepare(int cpu)
+{
+ return intel_cpuc_prepare(&per_cpu(cpu_hw_events, cpu), cpu);
+}
+
static void flip_smm_bit(void *data)
{
unsigned long set = *(unsigned long *)data;
@@ -3542,9 +3610,8 @@ static void intel_pmu_cpu_starting(int cpu)
}
}

-static void free_excl_cntrs(int cpu)
+static void free_excl_cntrs(struct cpu_hw_events *cpuc)
{
- struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
struct intel_excl_cntrs *c;

c = cpuc->excl_cntrs;
@@ -3552,9 +3619,10 @@ static void free_excl_cntrs(int cpu)
if (c->core_id == -1 || --c->refcnt == 0)
kfree(c);
cpuc->excl_cntrs = NULL;
- kfree(cpuc->constraint_list);
- cpuc->constraint_list = NULL;
}
+
+ kfree(cpuc->constraint_list);
+ cpuc->constraint_list = NULL;
}

static void intel_pmu_cpu_dying(int cpu)
@@ -3565,9 +3633,8 @@ static void intel_pmu_cpu_dying(int cpu)
disable_counter_freeze();
}

-static void intel_pmu_cpu_dead(int cpu)
+void intel_cpuc_finish(struct cpu_hw_events *cpuc)
{
- struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
struct intel_shared_regs *pc;

pc = cpuc->shared_regs;
@@ -3577,7 +3644,12 @@ static void intel_pmu_cpu_dead(int cpu)
cpuc->shared_regs = NULL;
}

- free_excl_cntrs(cpu);
+ free_excl_cntrs(cpuc);
+}
+
+static void intel_pmu_cpu_dead(int cpu)
+{
+ intel_cpuc_finish(&per_cpu(cpu_hw_events, cpu));
}

static void intel_pmu_sched_task(struct perf_event_context *ctx,
@@ -4070,8 +4142,11 @@ static struct attribute *intel_pmu_caps_attrs[] = {
NULL
};

+DEVICE_BOOL_ATTR(allow_tsx_force_abort, 0644, allow_tsx_force_abort);
+
static struct attribute *intel_pmu_attrs[] = {
&dev_attr_freeze_on_smi.attr,
+ NULL, /* &dev_attr_allow_tsx_force_abort.attr.attr */
NULL,
};

@@ -4564,6 +4639,15 @@ __init int intel_pmu_init(void)
tsx_attr = hsw_tsx_events_attrs;
intel_pmu_pebs_data_source_skl(
boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X);
+
+ if (boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)) {
+ x86_pmu.flags |= PMU_FL_TFA;
+ x86_pmu.get_event_constraints = tfa_get_event_constraints;
+ x86_pmu.enable_all = intel_tfa_pmu_enable_all;
+ x86_pmu.commit_scheduling = intel_tfa_commit_scheduling;
+ intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr.attr;
+ }
+
pr_cont("Skylake events, ");
name = "skylake";
break;
@@ -4715,7 +4799,7 @@ static __init int fixup_ht_bug(void)
hardlockup_detector_perf_restart();

for_each_online_cpu(c)
- free_excl_cntrs(c);
+ free_excl_cntrs(&per_cpu(cpu_hw_events, c));

cpus_read_unlock();
pr_info("PMU erratum BJ122, BV98, HSD29 workaround disabled, HT off\n");
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index d46fd6754d92..a345d079f876 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -242,6 +242,11 @@ struct cpu_hw_events {
struct intel_excl_cntrs *excl_cntrs;
int excl_thread_id; /* 0 or 1 */

+ /*
+ * SKL TSX_FORCE_ABORT shadow
+ */
+ u64 tfa_shadow;
+
/*
* AMD specific bits
*/
@@ -681,6 +686,7 @@ do { \
#define PMU_FL_EXCL_CNTRS 0x4 /* has exclusive counter requirements */
#define PMU_FL_EXCL_ENABLED 0x8 /* exclusive counter active */
#define PMU_FL_PEBS_ALL 0x10 /* all events are valid PEBS events */
+#define PMU_FL_TFA 0x20 /* deal with TSX force abort */

#define EVENT_VAR(_id) event_attr_##_id
#define EVENT_PTR(_id) &event_attr_##_id.attr.attr
@@ -889,7 +895,8 @@ struct event_constraint *
x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event);

-struct intel_shared_regs *allocate_shared_regs(int cpu);
+extern int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu);
+extern void intel_cpuc_finish(struct cpu_hw_events *cpuc);

int intel_pmu_init(void);

@@ -1025,9 +1032,13 @@ static inline int intel_pmu_init(void)
return 0;
}

-static inline struct intel_shared_regs *allocate_shared_regs(int cpu)
+static inline int intel_cpuc_prepare(struct cpu_hw_event *cpuc, int cpu)
+{
+ return 0;
+}
+
+static inline void intel_cpuc_finish(struct cpu_hw_event *cpuc)
{
- return NULL;
}

static inline int is_ht_workaround_enabled(void)
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 28c4a502b419..9246a6715cf2 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -342,6 +342,7 @@
/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */
#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */
#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */
#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 0dd6b0f4000e..d9a9993af882 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -6,7 +6,7 @@
* "Big Core" Processors (Branded as Core, Xeon, etc...)
*
* The "_X" parts are generally the EP and EX Xeons, or the
- * "Extreme" ones, like Broadwell-E.
+ * "Extreme" ones, like Broadwell-E, or Atom microserver.
*
* While adding a new CPUID for a new microarchitecture, add a new
* group to keep logically sorted out in chronological order. Within
@@ -71,6 +71,7 @@
#define INTEL_FAM6_ATOM_GOLDMONT 0x5C /* Apollo Lake */
#define INTEL_FAM6_ATOM_GOLDMONT_X 0x5F /* Denverton */
#define INTEL_FAM6_ATOM_GOLDMONT_PLUS 0x7A /* Gemini Lake */
+#define INTEL_FAM6_ATOM_TREMONT_X 0x86 /* Jacobsville */

/* Xeon Phi */

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 9e39cc8bd989..ea192e402abe 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -630,6 +630,12 @@

#define MSR_IA32_TSC_DEADLINE 0x000006E0

+
+#define MSR_TSX_FORCE_ABORT 0x0000010F
+
+#define MSR_TFA_RTM_FORCE_ABORT_BIT 0
+#define MSR_TFA_RTM_FORCE_ABORT BIT_ULL(MSR_TFA_RTM_FORCE_ABORT_BIT)
+
/* P4/Xeon+ specific */
#define MSR_IA32_MCG_EAX 0x00000180
#define MSR_IA32_MCG_EBX 0x00000181
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 8f657286d599..0ce558a8150d 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -7,7 +7,11 @@
#endif

#ifdef CONFIG_KASAN
+#ifdef CONFIG_KASAN_EXTRA
+#define KASAN_STACK_ORDER 2
+#else
#define KASAN_STACK_ORDER 1
+#endif
#else
#define KASAN_STACK_ORDER 0
#endif
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 07b5fc00b188..a4e7e100ed26 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -707,7 +707,7 @@ load_microcode_amd(bool save, u8 family, const u8 *data, size_t size)
if (!p) {
return ret;
} else {
- if (boot_cpu_data.microcode == p->patch_id)
+ if (boot_cpu_data.microcode >= p->patch_id)
return ret;

ret = UCODE_NEW;
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 278cd07228dd..9490a2845f14 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -167,6 +167,9 @@ setup_efi_state(struct boot_params *params, unsigned long params_load_addr,
struct efi_info *current_ei = &boot_params.efi_info;
struct efi_info *ei = &params->efi_info;

+ if (!efi_enabled(EFI_RUNTIME_SERVICES))
+ return 0;
+
if (!current_ei->efi_memmap_size)
return 0;

diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 30a5111ae5fd..527e69b12002 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -635,6 +635,22 @@ static void quirk_no_aersid(struct pci_dev *pdev)
DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, PCI_ANY_ID,
PCI_CLASS_BRIDGE_PCI, 8, quirk_no_aersid);

+static void quirk_intel_th_dnv(struct pci_dev *dev)
+{
+ struct resource *r = &dev->resource[4];
+
+ /*
+ * Denverton reports 2k of RTIT_BAR (intel_th resource 4), which
+ * appears to be 4 MB in reality.
+ */
+ if (r->end == r->start + 0x7ff) {
+ r->start = 0;
+ r->end = 0x3fffff;
+ r->flags |= IORESOURCE_UNSET;
+ }
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x19e1, quirk_intel_th_dnv);
+
#ifdef CONFIG_PHYS_ADDR_T_64BIT

#define AMD_141b_MMIO_BASE(x) (0x80 + (x) * 0x8)
diff --git a/arch/xtensa/configs/smp_lx200_defconfig b/arch/xtensa/configs/smp_lx200_defconfig
index 11fed6c06a7c..b5938160fb3d 100644
--- a/arch/xtensa/configs/smp_lx200_defconfig
+++ b/arch/xtensa/configs/smp_lx200_defconfig
@@ -33,6 +33,7 @@ CONFIG_SMP=y
CONFIG_HOTPLUG_CPU=y
# CONFIG_INITIALIZE_XTENSA_MMU_INSIDE_VMLINUX is not set
# CONFIG_PCI is not set
+CONFIG_VECTORS_OFFSET=0x00002000
CONFIG_XTENSA_PLATFORM_XTFPGA=y
CONFIG_CMDLINE_BOOL=y
CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=96M@0"
diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S
index 9053a5622d2c..5bd38ea2da38 100644
--- a/arch/xtensa/kernel/head.S
+++ b/arch/xtensa/kernel/head.S
@@ -280,12 +280,13 @@ should_never_return:

movi a2, cpu_start_ccount
1:
+ memw
l32i a3, a2, 0
beqi a3, 0, 1b
movi a3, 0
s32i a3, a2, 0
- memw
1:
+ memw
l32i a3, a2, 0
beqi a3, 0, 1b
wsr a3, ccount
@@ -321,11 +322,13 @@ ENTRY(cpu_restart)
rsr a0, prid
neg a2, a0
movi a3, cpu_start_id
+ memw
s32i a2, a3, 0
#if XCHAL_DCACHE_IS_WRITEBACK
dhwbi a3, 0
#endif
1:
+ memw
l32i a2, a3, 0
dhi a3, 0
bne a2, a0, 1b
diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c
index 932d64689bac..be1f280c322c 100644
--- a/arch/xtensa/kernel/smp.c
+++ b/arch/xtensa/kernel/smp.c
@@ -83,7 +83,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
{
unsigned i;

- for (i = 0; i < max_cpus; ++i)
+ for_each_possible_cpu(i)
set_cpu_present(i, true);
}

@@ -96,6 +96,11 @@ void __init smp_init_cpus(void)
pr_info("%s: Core Count = %d\n", __func__, ncpus);
pr_info("%s: Core Id = %d\n", __func__, core_id);

+ if (ncpus > NR_CPUS) {
+ ncpus = NR_CPUS;
+ pr_info("%s: limiting core count by %d\n", __func__, ncpus);
+ }
+
for (i = 0; i < ncpus; ++i)
set_cpu_possible(i, true);
}
@@ -195,9 +200,11 @@ static int boot_secondary(unsigned int cpu, struct task_struct *ts)
int i;

#ifdef CONFIG_HOTPLUG_CPU
- cpu_start_id = cpu;
- system_flush_invalidate_dcache_range(
- (unsigned long)&cpu_start_id, sizeof(cpu_start_id));
+ WRITE_ONCE(cpu_start_id, cpu);
+ /* Pairs with the third memw in the cpu_restart */
+ mb();
+ system_flush_invalidate_dcache_range((unsigned long)&cpu_start_id,
+ sizeof(cpu_start_id));
#endif
smp_call_function_single(0, mx_cpu_start, (void *)cpu, 1);

@@ -206,18 +213,21 @@ static int boot_secondary(unsigned int cpu, struct task_struct *ts)
ccount = get_ccount();
while (!ccount);

- cpu_start_ccount = ccount;
+ WRITE_ONCE(cpu_start_ccount, ccount);

- while (time_before(jiffies, timeout)) {
+ do {
+ /*
+ * Pairs with the first two memws in the
+ * .Lboot_secondary.
+ */
mb();
- if (!cpu_start_ccount)
- break;
- }
+ ccount = READ_ONCE(cpu_start_ccount);
+ } while (ccount && time_before(jiffies, timeout));

- if (cpu_start_ccount) {
+ if (ccount) {
smp_call_function_single(0, mx_cpu_stop,
- (void *)cpu, 1);
- cpu_start_ccount = 0;
+ (void *)cpu, 1);
+ WRITE_ONCE(cpu_start_ccount, 0);
return -EIO;
}
}
@@ -237,6 +247,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
pr_debug("%s: Calling wakeup_secondary(cpu:%d, idle:%p, sp: %08lx)\n",
__func__, cpu, idle, start_info.stack);

+ init_completion(&cpu_running);
ret = boot_secondary(cpu, idle);
if (ret == 0) {
wait_for_completion_timeout(&cpu_running,
@@ -298,8 +309,10 @@ void __cpu_die(unsigned int cpu)
unsigned long timeout = jiffies + msecs_to_jiffies(1000);
while (time_before(jiffies, timeout)) {
system_invalidate_dcache_range((unsigned long)&cpu_start_id,
- sizeof(cpu_start_id));
- if (cpu_start_id == -cpu) {
+ sizeof(cpu_start_id));
+ /* Pairs with the second memw in the cpu_restart */
+ mb();
+ if (READ_ONCE(cpu_start_id) == -cpu) {
platform_cpu_kill(cpu);
return;
}
diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c
index fd524a54d2ab..378186b5eb40 100644
--- a/arch/xtensa/kernel/time.c
+++ b/arch/xtensa/kernel/time.c
@@ -89,7 +89,7 @@ static int ccount_timer_shutdown(struct clock_event_device *evt)
container_of(evt, struct ccount_timer, evt);

if (timer->irq_enabled) {
- disable_irq(evt->irq);
+ disable_irq_nosync(evt->irq);
timer->irq_enabled = 0;
}
return 0;
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index 38c35c32aff2..c1c72b42dda0 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -72,6 +72,7 @@
#include <linux/sched/loadavg.h>
#include <linux/sched/signal.h>
#include <trace/events/block.h>
+#include <linux/blk-mq.h>
#include "blk-rq-qos.h"
#include "blk-stat.h"

@@ -648,6 +649,9 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio)
return;

enabled = blk_iolatency_enabled(iolat->blkiolat);
+ if (!enabled)
+ return;
+
while (blkg && blkg->parent) {
iolat = blkg_to_lat(blkg);
if (!iolat) {
@@ -657,7 +661,7 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio)
rqw = &iolat->rq_wait;

atomic_dec(&rqw->inflight);
- if (!enabled || iolat->min_lat_nsec == 0)
+ if (iolat->min_lat_nsec == 0)
goto next;
iolatency_record_time(iolat, &bio->bi_issue, now,
issue_as_root);
@@ -801,10 +805,13 @@ int blk_iolatency_init(struct request_queue *q)
return 0;
}

-static void iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val)
+/*
+ * return 1 for enabling iolatency, return -1 for disabling iolatency, otherwise
+ * return 0.
+ */
+static int iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val)
{
struct iolatency_grp *iolat = blkg_to_lat(blkg);
- struct blk_iolatency *blkiolat = iolat->blkiolat;
u64 oldval = iolat->min_lat_nsec;

iolat->min_lat_nsec = val;
@@ -813,9 +820,10 @@ static void iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val)
BLKIOLATENCY_MAX_WIN_SIZE);

if (!oldval && val)
- atomic_inc(&blkiolat->enabled);
+ return 1;
if (oldval && !val)
- atomic_dec(&blkiolat->enabled);
+ return -1;
+ return 0;
}

static void iolatency_clear_scaling(struct blkcg_gq *blkg)
@@ -847,6 +855,7 @@ static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf,
u64 lat_val = 0;
u64 oldval;
int ret;
+ int enable = 0;

ret = blkg_conf_prep(blkcg, &blkcg_policy_iolatency, buf, &ctx);
if (ret)
@@ -881,7 +890,12 @@ static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf,
blkg = ctx.blkg;
oldval = iolat->min_lat_nsec;

- iolatency_set_min_lat_nsec(blkg, lat_val);
+ enable = iolatency_set_min_lat_nsec(blkg, lat_val);
+ if (enable) {
+ WARN_ON_ONCE(!blk_get_queue(blkg->q));
+ blkg_get(blkg);
+ }
+
if (oldval != iolat->min_lat_nsec) {
iolatency_clear_scaling(blkg);
}
@@ -889,6 +903,24 @@ static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf,
ret = 0;
out:
blkg_conf_finish(&ctx);
+ if (ret == 0 && enable) {
+ struct iolatency_grp *tmp = blkg_to_lat(blkg);
+ struct blk_iolatency *blkiolat = tmp->blkiolat;
+
+ blk_mq_freeze_queue(blkg->q);
+
+ if (enable == 1)
+ atomic_inc(&blkiolat->enabled);
+ else if (enable == -1)
+ atomic_dec(&blkiolat->enabled);
+ else
+ WARN_ON_ONCE(1);
+
+ blk_mq_unfreeze_queue(blkg->q);
+
+ blkg_put(blkg);
+ blk_put_queue(blkg->q);
+ }
return ret ?: nbytes;
}

@@ -1024,8 +1056,14 @@ static void iolatency_pd_offline(struct blkg_policy_data *pd)
{
struct iolatency_grp *iolat = pd_to_lat(pd);
struct blkcg_gq *blkg = lat_to_blkg(iolat);
+ struct blk_iolatency *blkiolat = iolat->blkiolat;
+ int ret;

- iolatency_set_min_lat_nsec(blkg, 0);
+ ret = iolatency_set_min_lat_nsec(blkg, 0);
+ if (ret == 1)
+ atomic_inc(&blkiolat->enabled);
+ if (ret == -1)
+ atomic_dec(&blkiolat->enabled);
iolatency_clear_scaling(blkg);
}

diff --git a/drivers/clk/qcom/gcc-sdm845.c b/drivers/clk/qcom/gcc-sdm845.c
index f133b7f5652f..26110e74e086 100644
--- a/drivers/clk/qcom/gcc-sdm845.c
+++ b/drivers/clk/qcom/gcc-sdm845.c
@@ -115,8 +115,8 @@ static const char * const gcc_parent_names_6[] = {
"core_bi_pll_test_se",
};

-static const char * const gcc_parent_names_7[] = {
- "bi_tcxo",
+static const char * const gcc_parent_names_7_ao[] = {
+ "bi_tcxo_ao",
"gpll0",
"gpll0_out_even",
"core_bi_pll_test_se",
@@ -128,6 +128,12 @@ static const char * const gcc_parent_names_8[] = {
"core_bi_pll_test_se",
};

+static const char * const gcc_parent_names_8_ao[] = {
+ "bi_tcxo_ao",
+ "gpll0",
+ "core_bi_pll_test_se",
+};
+
static const struct parent_map gcc_parent_map_10[] = {
{ P_BI_TCXO, 0 },
{ P_GPLL0_OUT_MAIN, 1 },
@@ -210,7 +216,7 @@ static struct clk_rcg2 gcc_cpuss_ahb_clk_src = {
.freq_tbl = ftbl_gcc_cpuss_ahb_clk_src,
.clkr.hw.init = &(struct clk_init_data){
.name = "gcc_cpuss_ahb_clk_src",
- .parent_names = gcc_parent_names_7,
+ .parent_names = gcc_parent_names_7_ao,
.num_parents = 4,
.ops = &clk_rcg2_ops,
},
@@ -229,7 +235,7 @@ static struct clk_rcg2 gcc_cpuss_rbcpr_clk_src = {
.freq_tbl = ftbl_gcc_cpuss_rbcpr_clk_src,
.clkr.hw.init = &(struct clk_init_data){
.name = "gcc_cpuss_rbcpr_clk_src",
- .parent_names = gcc_parent_names_8,
+ .parent_names = gcc_parent_names_8_ao,
.num_parents = 3,
.ops = &clk_rcg2_ops,
},
diff --git a/drivers/clk/ti/divider.c b/drivers/clk/ti/divider.c
index 8d77090ad94a..0241450f3eb3 100644
--- a/drivers/clk/ti/divider.c
+++ b/drivers/clk/ti/divider.c
@@ -403,8 +403,10 @@ int ti_clk_parse_divider_data(int *div_table, int num_dividers, int max_div,
num_dividers = i;

tmp = kcalloc(valid_div + 1, sizeof(*tmp), GFP_KERNEL);
- if (!tmp)
+ if (!tmp) {
+ *table = ERR_PTR(-ENOMEM);
return -ENOMEM;
+ }

valid_div = 0;
*width = 0;
@@ -439,6 +441,7 @@ struct clk_hw *ti_clk_build_component_div(struct ti_clk_divider *setup)
{
struct clk_omap_divider *div;
struct clk_omap_reg *reg;
+ int ret;

if (!setup)
return NULL;
@@ -458,6 +461,12 @@ struct clk_hw *ti_clk_build_component_div(struct ti_clk_divider *setup)
div->flags |= CLK_DIVIDER_POWER_OF_TWO;

div->table = _get_div_table_from_setup(setup, &div->width);
+ if (IS_ERR(div->table)) {
+ ret = PTR_ERR(div->table);
+ kfree(div);
+ return ERR_PTR(ret);
+ }
+

div->shift = setup->bit_shift;
div->latch = -EINVAL;
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 4e557684f792..fe69dccfa0c0 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -203,6 +203,7 @@ struct at_xdmac_chan {
u32 save_cim;
u32 save_cnda;
u32 save_cndc;
+ u32 irq_status;
unsigned long status;
struct tasklet_struct tasklet;
struct dma_slave_config sconfig;
@@ -1580,8 +1581,8 @@ static void at_xdmac_tasklet(unsigned long data)
struct at_xdmac_desc *desc;
u32 error_mask;

- dev_dbg(chan2dev(&atchan->chan), "%s: status=0x%08lx\n",
- __func__, atchan->status);
+ dev_dbg(chan2dev(&atchan->chan), "%s: status=0x%08x\n",
+ __func__, atchan->irq_status);

error_mask = AT_XDMAC_CIS_RBEIS
| AT_XDMAC_CIS_WBEIS
@@ -1589,15 +1590,15 @@ static void at_xdmac_tasklet(unsigned long data)

if (at_xdmac_chan_is_cyclic(atchan)) {
at_xdmac_handle_cyclic(atchan);
- } else if ((atchan->status & AT_XDMAC_CIS_LIS)
- || (atchan->status & error_mask)) {
+ } else if ((atchan->irq_status & AT_XDMAC_CIS_LIS)
+ || (atchan->irq_status & error_mask)) {
struct dma_async_tx_descriptor *txd;

- if (atchan->status & AT_XDMAC_CIS_RBEIS)
+ if (atchan->irq_status & AT_XDMAC_CIS_RBEIS)
dev_err(chan2dev(&atchan->chan), "read bus error!!!");
- if (atchan->status & AT_XDMAC_CIS_WBEIS)
+ if (atchan->irq_status & AT_XDMAC_CIS_WBEIS)
dev_err(chan2dev(&atchan->chan), "write bus error!!!");
- if (atchan->status & AT_XDMAC_CIS_ROIS)
+ if (atchan->irq_status & AT_XDMAC_CIS_ROIS)
dev_err(chan2dev(&atchan->chan), "request overflow error!!!");

spin_lock(&atchan->lock);
@@ -1652,7 +1653,7 @@ static irqreturn_t at_xdmac_interrupt(int irq, void *dev_id)
atchan = &atxdmac->chan[i];
chan_imr = at_xdmac_chan_read(atchan, AT_XDMAC_CIM);
chan_status = at_xdmac_chan_read(atchan, AT_XDMAC_CIS);
- atchan->status = chan_status & chan_imr;
+ atchan->irq_status = chan_status & chan_imr;
dev_vdbg(atxdmac->dma.dev,
"%s: chan%d: imr=0x%x, status=0x%x\n",
__func__, i, chan_imr, chan_status);
@@ -1666,7 +1667,7 @@ static irqreturn_t at_xdmac_interrupt(int irq, void *dev_id)
at_xdmac_chan_read(atchan, AT_XDMAC_CDA),
at_xdmac_chan_read(atchan, AT_XDMAC_CUBC));

- if (atchan->status & (AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS))
+ if (atchan->irq_status & (AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS))
at_xdmac_write(atxdmac, AT_XDMAC_GD, atchan->mask);

tasklet_schedule(&atchan->tasklet);
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index aa1712beb0cc..7b7fba0c9253 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -642,11 +642,9 @@ static int dmatest_func(void *data)
srcs[i] = um->addr[i] + src_off;
ret = dma_mapping_error(dev->dev, um->addr[i]);
if (ret) {
- dmaengine_unmap_put(um);
result("src mapping error", total_tests,
src_off, dst_off, len, ret);
- failed_tests++;
- continue;
+ goto error_unmap_continue;
}
um->to_cnt++;
}
@@ -661,11 +659,9 @@ static int dmatest_func(void *data)
DMA_BIDIRECTIONAL);
ret = dma_mapping_error(dev->dev, dsts[i]);
if (ret) {
- dmaengine_unmap_put(um);
result("dst mapping error", total_tests,
src_off, dst_off, len, ret);
- failed_tests++;
- continue;
+ goto error_unmap_continue;
}
um->bidi_cnt++;
}
@@ -693,12 +689,10 @@ static int dmatest_func(void *data)
}

if (!tx) {
- dmaengine_unmap_put(um);
result("prep error", total_tests, src_off,
dst_off, len, ret);
msleep(100);
- failed_tests++;
- continue;
+ goto error_unmap_continue;
}

done->done = false;
@@ -707,12 +701,10 @@ static int dmatest_func(void *data)
cookie = tx->tx_submit(tx);

if (dma_submit_error(cookie)) {
- dmaengine_unmap_put(um);
result("submit error", total_tests, src_off,
dst_off, len, ret);
msleep(100);
- failed_tests++;
- continue;
+ goto error_unmap_continue;
}
dma_async_issue_pending(chan);

@@ -725,16 +717,14 @@ static int dmatest_func(void *data)
dmaengine_unmap_put(um);
result("test timed out", total_tests, src_off, dst_off,
len, 0);
- failed_tests++;
- continue;
+ goto error_unmap_continue;
} else if (status != DMA_COMPLETE) {
dmaengine_unmap_put(um);
result(status == DMA_ERROR ?
"completion error status" :
"completion busy status", total_tests, src_off,
dst_off, len, ret);
- failed_tests++;
- continue;
+ goto error_unmap_continue;
}

dmaengine_unmap_put(um);
@@ -779,6 +769,12 @@ static int dmatest_func(void *data)
verbose_result("test passed", total_tests, src_off,
dst_off, len, 0);
}
+
+ continue;
+
+error_unmap_continue:
+ dmaengine_unmap_put(um);
+ failed_tests++;
}
ktime = ktime_sub(ktime_get(), ktime);
ktime = ktime_sub(ktime, comparetime);
diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c
index 6bc8e6640d71..c51462f5aa1e 100644
--- a/drivers/firmware/iscsi_ibft.c
+++ b/drivers/firmware/iscsi_ibft.c
@@ -542,6 +542,7 @@ static umode_t __init ibft_check_tgt_for(void *data, int type)
case ISCSI_BOOT_TGT_NIC_ASSOC:
case ISCSI_BOOT_TGT_CHAP_TYPE:
rc = S_IRUGO;
+ break;
case ISCSI_BOOT_TGT_NAME:
if (tgt->tgt_name_len)
rc = S_IRUGO;
diff --git a/drivers/gpio/gpio-vf610.c b/drivers/gpio/gpio-vf610.c
index 5960396c8d9a..222170a1715f 100644
--- a/drivers/gpio/gpio-vf610.c
+++ b/drivers/gpio/gpio-vf610.c
@@ -250,6 +250,7 @@ static int vf610_gpio_probe(struct platform_device *pdev)
struct vf610_gpio_port *port;
struct resource *iores;
struct gpio_chip *gc;
+ int i;
int ret;

port = devm_kzalloc(&pdev->dev, sizeof(*port), GFP_KERNEL);
@@ -289,6 +290,10 @@ static int vf610_gpio_probe(struct platform_device *pdev)
if (ret < 0)
return ret;

+ /* Mask all GPIO interrupts */
+ for (i = 0; i < gc->ngpio; i++)
+ vf610_gpio_writel(0, port->base + PORT_PCR(i));
+
/* Clear the interrupt status register for all GPIO's */
vf610_gpio_writel(~0, port->base + PORT_ISFR);

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 59cc678de8c1..bbac15fd8caa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -1671,7 +1671,8 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj,
effective_mode &= ~S_IWUSR;

if ((adev->flags & AMD_IS_APU) &&
- (attr == &sensor_dev_attr_power1_cap_max.dev_attr.attr ||
+ (attr == &sensor_dev_attr_power1_average.dev_attr.attr ||
+ attr == &sensor_dev_attr_power1_cap_max.dev_attr.attr ||
attr == &sensor_dev_attr_power1_cap_min.dev_attr.attr||
attr == &sensor_dev_attr_power1_cap.dev_attr.attr))
return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index e45e929aaab5..90a5970af4b7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -38,6 +38,7 @@
#include "amdgpu_gem.h"
#include <drm/amdgpu_drm.h>
#include <linux/dma-buf.h>
+#include <linux/dma-fence-array.h>

static const struct dma_buf_ops amdgpu_dmabuf_ops;

@@ -189,6 +190,48 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
return ERR_PTR(ret);
}

+static int
+__reservation_object_make_exclusive(struct reservation_object *obj)
+{
+ struct dma_fence **fences;
+ unsigned int count;
+ int r;
+
+ if (!reservation_object_get_list(obj)) /* no shared fences to convert */
+ return 0;
+
+ r = reservation_object_get_fences_rcu(obj, NULL, &count, &fences);
+ if (r)
+ return r;
+
+ if (count == 0) {
+ /* Now that was unexpected. */
+ } else if (count == 1) {
+ reservation_object_add_excl_fence(obj, fences[0]);
+ dma_fence_put(fences[0]);
+ kfree(fences);
+ } else {
+ struct dma_fence_array *array;
+
+ array = dma_fence_array_create(count, fences,
+ dma_fence_context_alloc(1), 0,
+ false);
+ if (!array)
+ goto err_fences_put;
+
+ reservation_object_add_excl_fence(obj, &array->base);
+ dma_fence_put(&array->base);
+ }
+
+ return 0;
+
+err_fences_put:
+ while (count--)
+ dma_fence_put(fences[count]);
+ kfree(fences);
+ return -ENOMEM;
+}
+
/**
* amdgpu_gem_map_attach - &dma_buf_ops.attach implementation
* @dma_buf: Shared DMA buffer
@@ -220,16 +263,16 @@ static int amdgpu_gem_map_attach(struct dma_buf *dma_buf,

if (attach->dev->driver != adev->dev->driver) {
/*
- * Wait for all shared fences to complete before we switch to future
- * use of exclusive fence on this prime shared bo.
+ * We only create shared fences for internal use, but importers
+ * of the dmabuf rely on exclusive fences for implicitly
+ * tracking write hazards. As any of the current fences may
+ * correspond to a write, we need to convert all existing
+ * fences on the reservation object into a single exclusive
+ * fence.
*/
- r = reservation_object_wait_timeout_rcu(bo->tbo.resv,
- true, false,
- MAX_SCHEDULE_TIMEOUT);
- if (unlikely(r < 0)) {
- DRM_DEBUG_PRIME("Fence wait failed: %li\n", r);
+ r = __reservation_object_make_exclusive(bo->tbo.resv);
+ if (r)
goto error_unreserve;
- }
}

/* pin buffer into GTT */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 62df4bd0a0fc..16c83155ef5c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -3405,14 +3405,15 @@ void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid,
struct amdgpu_task_info *task_info)
{
struct amdgpu_vm *vm;
+ unsigned long flags;

- spin_lock(&adev->vm_manager.pasid_lock);
+ spin_lock_irqsave(&adev->vm_manager.pasid_lock, flags);

vm = idr_find(&adev->vm_manager.pasid_idr, pasid);
if (vm)
*task_info = vm->task_info;

- spin_unlock(&adev->vm_manager.pasid_lock);
+ spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags);
}

/**
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index f8cee95d61cc..7d5cbadbe1cb 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -92,7 +92,20 @@ static void nbio_v7_4_enable_doorbell_aperture(struct amdgpu_device *adev,
static void nbio_v7_4_enable_doorbell_selfring_aperture(struct amdgpu_device *adev,
bool enable)
{
+ u32 tmp = 0;

+ if (enable) {
+ tmp = REG_SET_FIELD(tmp, DOORBELL_SELFRING_GPA_APER_CNTL, DOORBELL_SELFRING_GPA_APER_EN, 1) |
+ REG_SET_FIELD(tmp, DOORBELL_SELFRING_GPA_APER_CNTL, DOORBELL_SELFRING_GPA_APER_MODE, 1) |
+ REG_SET_FIELD(tmp, DOORBELL_SELFRING_GPA_APER_CNTL, DOORBELL_SELFRING_GPA_APER_SIZE, 0);
+
+ WREG32_SOC15(NBIO, 0, mmDOORBELL_SELFRING_GPA_APER_BASE_LOW,
+ lower_32_bits(adev->doorbell.base));
+ WREG32_SOC15(NBIO, 0, mmDOORBELL_SELFRING_GPA_APER_BASE_HIGH,
+ upper_32_bits(adev->doorbell.base));
+ }
+
+ WREG32_SOC15(NBIO, 0, mmDOORBELL_SELFRING_GPA_APER_CNTL, tmp);
}

static void nbio_v7_4_ih_doorbell_range(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 4cc0dcb1a187..825d1cae85ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -705,11 +705,13 @@ static int soc15_common_early_init(void *handle)
break;
case CHIP_RAVEN:
if (adev->rev_id >= 0x8)
- adev->external_rev_id = adev->rev_id + 0x81;
+ adev->external_rev_id = adev->rev_id + 0x79;
else if (adev->pdev->device == 0x15d8)
adev->external_rev_id = adev->rev_id + 0x41;
+ else if (adev->rev_id == 1)
+ adev->external_rev_id = adev->rev_id + 0x20;
else
- adev->external_rev_id = 0x1;
+ adev->external_rev_id = adev->rev_id + 0x01;

if (adev->rev_id >= 0x8) {
adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
diff --git a/drivers/gpu/drm/omapdrm/dss/dsi.c b/drivers/gpu/drm/omapdrm/dss/dsi.c
index 00a9c2ab9e6c..64fb788b6647 100644
--- a/drivers/gpu/drm/omapdrm/dss/dsi.c
+++ b/drivers/gpu/drm/omapdrm/dss/dsi.c
@@ -1406,7 +1406,7 @@ static void dsi_pll_disable(struct dss_pll *pll)

static int dsi_dump_dsi_clocks(struct seq_file *s, void *p)
{
- struct dsi_data *dsi = p;
+ struct dsi_data *dsi = s->private;
struct dss_pll_clock_info *cinfo = &dsi->pll.cinfo;
enum dss_clk_source dispc_clk_src, dsi_clk_src;
int dsi_module = dsi->module_id;
@@ -1467,7 +1467,7 @@ static int dsi_dump_dsi_clocks(struct seq_file *s, void *p)
#ifdef CONFIG_OMAP2_DSS_COLLECT_IRQ_STATS
static int dsi_dump_dsi_irqs(struct seq_file *s, void *p)
{
- struct dsi_data *dsi = p;
+ struct dsi_data *dsi = s->private;
unsigned long flags;
struct dsi_irq_stats stats;

@@ -1558,7 +1558,7 @@ static int dsi_dump_dsi_irqs(struct seq_file *s, void *p)

static int dsi_dump_dsi_regs(struct seq_file *s, void *p)
{
- struct dsi_data *dsi = p;
+ struct dsi_data *dsi = s->private;

if (dsi_runtime_get(dsi))
return 0;
@@ -4751,6 +4751,17 @@ static int dsi_set_config(struct omap_dss_device *dssdev,
dsi->vm.flags |= DISPLAY_FLAGS_HSYNC_HIGH;
dsi->vm.flags &= ~DISPLAY_FLAGS_VSYNC_LOW;
dsi->vm.flags |= DISPLAY_FLAGS_VSYNC_HIGH;
+ /*
+ * HACK: These flags should be handled through the omap_dss_device bus
+ * flags, but this will only be possible when the DSI encoder will be
+ * converted to the omapdrm-managed encoder model.
+ */
+ dsi->vm.flags &= ~DISPLAY_FLAGS_PIXDATA_NEGEDGE;
+ dsi->vm.flags |= DISPLAY_FLAGS_PIXDATA_POSEDGE;
+ dsi->vm.flags &= ~DISPLAY_FLAGS_DE_LOW;
+ dsi->vm.flags |= DISPLAY_FLAGS_DE_HIGH;
+ dsi->vm.flags &= ~DISPLAY_FLAGS_SYNC_POSEDGE;
+ dsi->vm.flags |= DISPLAY_FLAGS_SYNC_NEGEDGE;

dss_mgr_set_timings(&dsi->output, &dsi->vm);

@@ -5083,15 +5094,15 @@ static int dsi_bind(struct device *dev, struct device *master, void *data)

snprintf(name, sizeof(name), "dsi%u_regs", dsi->module_id + 1);
dsi->debugfs.regs = dss_debugfs_create_file(dss, name,
- dsi_dump_dsi_regs, &dsi);
+ dsi_dump_dsi_regs, dsi);
#ifdef CONFIG_OMAP2_DSS_COLLECT_IRQ_STATS
snprintf(name, sizeof(name), "dsi%u_irqs", dsi->module_id + 1);
dsi->debugfs.irqs = dss_debugfs_create_file(dss, name,
- dsi_dump_dsi_irqs, &dsi);
+ dsi_dump_dsi_irqs, dsi);
#endif
snprintf(name, sizeof(name), "dsi%u_clks", dsi->module_id + 1);
dsi->debugfs.clks = dss_debugfs_create_file(dss, name,
- dsi_dump_dsi_clocks, &dsi);
+ dsi_dump_dsi_clocks, dsi);

return 0;
}
@@ -5104,8 +5115,6 @@ static void dsi_unbind(struct device *dev, struct device *master, void *data)
dss_debugfs_remove_file(dsi->debugfs.irqs);
dss_debugfs_remove_file(dsi->debugfs.regs);

- of_platform_depopulate(dev);
-
WARN_ON(dsi->scp_clk_refcount > 0);

dss_pll_unregister(&dsi->pll);
@@ -5457,6 +5466,8 @@ static int dsi_remove(struct platform_device *pdev)

dsi_uninit_output(dsi);

+ of_platform_depopulate(&pdev->dev);
+
pm_runtime_disable(&pdev->dev);

if (dsi->vdds_dsi_reg != NULL && dsi->vdds_dsi_enabled) {
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index d587779a80b4..a97294ac96d5 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -5676,7 +5676,7 @@ int ci_dpm_init(struct radeon_device *rdev)
u16 data_offset, size;
u8 frev, crev;
struct ci_power_info *pi;
- enum pci_bus_speed speed_cap;
+ enum pci_bus_speed speed_cap = PCI_SPEED_UNKNOWN;
struct pci_dev *root = rdev->pdev->bus->self;
int ret;

@@ -5685,7 +5685,8 @@ int ci_dpm_init(struct radeon_device *rdev)
return -ENOMEM;
rdev->pm.dpm.priv = pi;

- speed_cap = pcie_get_speed_cap(root);
+ if (!pci_is_root_bus(rdev->pdev->bus))
+ speed_cap = pcie_get_speed_cap(root);
if (speed_cap == PCI_SPEED_UNKNOWN) {
pi->sys_pcie_mask = 0;
} else {
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 8fb60b3af015..0a785ef0ab66 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -6899,7 +6899,7 @@ int si_dpm_init(struct radeon_device *rdev)
struct ni_power_info *ni_pi;
struct si_power_info *si_pi;
struct atom_clock_dividers dividers;
- enum pci_bus_speed speed_cap;
+ enum pci_bus_speed speed_cap = PCI_SPEED_UNKNOWN;
struct pci_dev *root = rdev->pdev->bus->self;
int ret;

@@ -6911,7 +6911,8 @@ int si_dpm_init(struct radeon_device *rdev)
eg_pi = &ni_pi->eg;
pi = &eg_pi->rv7xx;

- speed_cap = pcie_get_speed_cap(root);
+ if (!pci_is_root_bus(rdev->pdev->bus))
+ speed_cap = pcie_get_speed_cap(root);
if (speed_cap == PCI_SPEED_UNKNOWN) {
si_pi->sys_pcie_mask = 0;
} else {
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index f949287d926c..4e0562aa2cc9 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -760,6 +760,7 @@ static int sun4i_tcon_init_clocks(struct device *dev,
return PTR_ERR(tcon->sclk0);
}
}
+ clk_prepare_enable(tcon->sclk0);

if (tcon->quirks->has_channel_1) {
tcon->sclk1 = devm_clk_get(dev, "tcon-ch1");
@@ -774,6 +775,7 @@ static int sun4i_tcon_init_clocks(struct device *dev,

static void sun4i_tcon_free_clocks(struct sun4i_tcon *tcon)
{
+ clk_disable_unprepare(tcon->sclk0);
clk_disable_unprepare(tcon->clk);
}

diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index b1086bfb0465..cd9c65f3d404 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -1500,8 +1500,7 @@ static int omap_i2c_remove(struct platform_device *pdev)
return 0;
}

-#ifdef CONFIG_PM
-static int omap_i2c_runtime_suspend(struct device *dev)
+static int __maybe_unused omap_i2c_runtime_suspend(struct device *dev)
{
struct omap_i2c_dev *omap = dev_get_drvdata(dev);

@@ -1527,7 +1526,7 @@ static int omap_i2c_runtime_suspend(struct device *dev)
return 0;
}

-static int omap_i2c_runtime_resume(struct device *dev)
+static int __maybe_unused omap_i2c_runtime_resume(struct device *dev)
{
struct omap_i2c_dev *omap = dev_get_drvdata(dev);

@@ -1542,20 +1541,18 @@ static int omap_i2c_runtime_resume(struct device *dev)
}

static const struct dev_pm_ops omap_i2c_pm_ops = {
+ SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+ pm_runtime_force_resume)
SET_RUNTIME_PM_OPS(omap_i2c_runtime_suspend,
omap_i2c_runtime_resume, NULL)
};
-#define OMAP_I2C_PM_OPS (&omap_i2c_pm_ops)
-#else
-#define OMAP_I2C_PM_OPS NULL
-#endif /* CONFIG_PM */

static struct platform_driver omap_i2c_driver = {
.probe = omap_i2c_probe,
.remove = omap_i2c_remove,
.driver = {
.name = "omap_i2c",
- .pm = OMAP_I2C_PM_OPS,
+ .pm = &omap_i2c_pm_ops,
.of_match_table = of_match_ptr(omap_i2c_of_match),
},
};
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 676c1fd1119d..7ef385db52c3 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -356,6 +356,8 @@ struct ib_umem_odp *ib_alloc_odp_umem(struct ib_ucontext_per_mm *per_mm,
umem->writable = 1;
umem->is_odp = 1;
odp_data->per_mm = per_mm;
+ umem->owning_mm = per_mm->mm;
+ mmgrab(umem->owning_mm);

mutex_init(&odp_data->umem_mutex);
init_completion(&odp_data->notifier_completion);
@@ -388,6 +390,7 @@ struct ib_umem_odp *ib_alloc_odp_umem(struct ib_ucontext_per_mm *per_mm,
out_page_list:
vfree(odp_data->page_list);
out_odp_data:
+ mmdrop(umem->owning_mm);
kfree(odp_data);
return ERR_PTR(ret);
}
diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c
index 4baa8f4d49de..46bf74375ea6 100644
--- a/drivers/infiniband/hw/hfi1/ud.c
+++ b/drivers/infiniband/hw/hfi1/ud.c
@@ -980,7 +980,6 @@ void hfi1_ud_rcv(struct hfi1_packet *packet)
opcode == IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE) {
wc.ex.imm_data = packet->ohdr->u.ud.imm_data;
wc.wc_flags = IB_WC_WITH_IMM;
- tlen -= sizeof(u32);
} else if (opcode == IB_OPCODE_UD_SEND_ONLY) {
wc.ex.imm_data = 0;
wc.wc_flags = 0;
diff --git a/drivers/infiniband/hw/qib/qib_ud.c b/drivers/infiniband/hw/qib/qib_ud.c
index 4d4c31ea4e2d..90268b838d4e 100644
--- a/drivers/infiniband/hw/qib/qib_ud.c
+++ b/drivers/infiniband/hw/qib/qib_ud.c
@@ -513,7 +513,6 @@ void qib_ud_rcv(struct qib_ibport *ibp, struct ib_header *hdr,
opcode == IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE) {
wc.ex.imm_data = ohdr->u.ud.imm_data;
wc.wc_flags = IB_WC_WITH_IMM;
- tlen -= sizeof(u32);
} else if (opcode == IB_OPCODE_UD_SEND_ONLY) {
wc.ex.imm_data = 0;
wc.wc_flags = 0;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 1da119d901a9..73e808c1e6ad 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -248,7 +248,6 @@ struct ipoib_cm_tx {
struct list_head list;
struct net_device *dev;
struct ipoib_neigh *neigh;
- struct ipoib_path *path;
struct ipoib_tx_buf *tx_ring;
unsigned int tx_head;
unsigned int tx_tail;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 0428e01e8f69..aa9dcfc36cd3 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -1312,7 +1312,6 @@ struct ipoib_cm_tx *ipoib_cm_create_tx(struct net_device *dev, struct ipoib_path

neigh->cm = tx;
tx->neigh = neigh;
- tx->path = path;
tx->dev = dev;
list_add(&tx->list, &priv->cm.start_list);
set_bit(IPOIB_FLAG_INITIALIZED, &tx->flags);
@@ -1371,7 +1370,7 @@ static void ipoib_cm_tx_start(struct work_struct *work)
neigh->daddr + QPN_AND_OPTIONS_OFFSET);
goto free_neigh;
}
- memcpy(&pathrec, &p->path->pathrec, sizeof(pathrec));
+ memcpy(&pathrec, &path->pathrec, sizeof(pathrec));

spin_unlock_irqrestore(&priv->lock, flags);
netif_tx_unlock_bh(dev);
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index 225ae6980182..628ef617bb2f 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -1337,6 +1337,7 @@ static const struct acpi_device_id elan_acpi_id[] = {
{ "ELAN0000", 0 },
{ "ELAN0100", 0 },
{ "ELAN0600", 0 },
+ { "ELAN0601", 0 },
{ "ELAN0602", 0 },
{ "ELAN0605", 0 },
{ "ELAN0608", 0 },
diff --git a/drivers/input/tablet/wacom_serial4.c b/drivers/input/tablet/wacom_serial4.c
index 38bfaca48eab..150f9eecaca7 100644
--- a/drivers/input/tablet/wacom_serial4.c
+++ b/drivers/input/tablet/wacom_serial4.c
@@ -187,6 +187,7 @@ enum {
MODEL_DIGITIZER_II = 0x5544, /* UD */
MODEL_GRAPHIRE = 0x4554, /* ET */
MODEL_PENPARTNER = 0x4354, /* CT */
+ MODEL_ARTPAD_II = 0x4B54, /* KT */
};

static void wacom_handle_model_response(struct wacom *wacom)
@@ -245,6 +246,7 @@ static void wacom_handle_model_response(struct wacom *wacom)
wacom->flags = F_HAS_STYLUS2 | F_HAS_SCROLLWHEEL;
break;

+ case MODEL_ARTPAD_II:
case MODEL_DIGITIZER_II:
wacom->dev->name = "Wacom Digitizer II";
wacom->dev->id.version = MODEL_DIGITIZER_II;
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 325f3bad118b..4d2c5d4f586f 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -1929,16 +1929,13 @@ static void do_attach(struct iommu_dev_data *dev_data,

static void do_detach(struct iommu_dev_data *dev_data)
{
+ struct protection_domain *domain = dev_data->domain;
struct amd_iommu *iommu;
u16 alias;

iommu = amd_iommu_rlookup_table[dev_data->devid];
alias = dev_data->alias;

- /* decrease reference counters */
- dev_data->domain->dev_iommu[iommu->index] -= 1;
- dev_data->domain->dev_cnt -= 1;
-
/* Update data structures */
dev_data->domain = NULL;
list_del(&dev_data->list);
@@ -1948,6 +1945,16 @@ static void do_detach(struct iommu_dev_data *dev_data)

/* Flush the DTE entry */
device_flush_dte(dev_data);
+
+ /* Flush IOTLB */
+ domain_flush_tlb_pde(domain);
+
+ /* Wait for the flushes to finish */
+ domain_flush_complete(domain);
+
+ /* decrease reference counters - needs to happen after the flushes */
+ domain->dev_iommu[iommu->index] -= 1;
+ domain->dev_cnt -= 1;
}

/*
@@ -2555,13 +2562,13 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
bus_addr = address + s->dma_address + (j << PAGE_SHIFT);
iommu_unmap_page(domain, bus_addr, PAGE_SIZE);

- if (--mapped_pages)
+ if (--mapped_pages == 0)
goto out_free_iova;
}
}

out_free_iova:
- free_iova_fast(&dma_dom->iovad, address, npages);
+ free_iova_fast(&dma_dom->iovad, address >> PAGE_SHIFT, npages);

out_err:
return 0;
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 350f999d205b..c3aba3fc818d 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -1586,6 +1586,9 @@ static unsigned long *its_lpi_alloc(int nr_irqs, u32 *base, int *nr_ids)
nr_irqs /= 2;
} while (nr_irqs > 0);

+ if (!nr_irqs)
+ err = -ENOSPC;
+
if (err)
goto out;

@@ -2065,6 +2068,29 @@ static int __init allocate_lpi_tables(void)
return 0;
}

+static u64 its_clear_vpend_valid(void __iomem *vlpi_base)
+{
+ u32 count = 1000000; /* 1s! */
+ bool clean;
+ u64 val;
+
+ val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER);
+ val &= ~GICR_VPENDBASER_Valid;
+ gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
+
+ do {
+ val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER);
+ clean = !(val & GICR_VPENDBASER_Dirty);
+ if (!clean) {
+ count--;
+ cpu_relax();
+ udelay(1);
+ }
+ } while (!clean && count);
+
+ return val;
+}
+
static void its_cpu_init_lpis(void)
{
void __iomem *rbase = gic_data_rdist_rd_base();
@@ -2150,6 +2176,30 @@ static void its_cpu_init_lpis(void)
val |= GICR_CTLR_ENABLE_LPIS;
writel_relaxed(val, rbase + GICR_CTLR);

+ if (gic_rdists->has_vlpis) {
+ void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
+
+ /*
+ * It's possible for CPU to receive VLPIs before it is
+ * sheduled as a vPE, especially for the first CPU, and the
+ * VLPI with INTID larger than 2^(IDbits+1) will be considered
+ * as out of range and dropped by GIC.
+ * So we initialize IDbits to known value to avoid VLPI drop.
+ */
+ val = (LPI_NRBITS - 1) & GICR_VPROPBASER_IDBITS_MASK;
+ pr_debug("GICv4: CPU%d: Init IDbits to 0x%llx for GICR_VPROPBASER\n",
+ smp_processor_id(), val);
+ gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER);
+
+ /*
+ * Also clear Valid bit of GICR_VPENDBASER, in case some
+ * ancient programming gets left in and has possibility of
+ * corrupting memory.
+ */
+ val = its_clear_vpend_valid(vlpi_base);
+ WARN_ON(val & GICR_VPENDBASER_Dirty);
+ }
+
/* Make sure the GIC has seen the above */
dsb(sy);
out:
@@ -2776,26 +2826,11 @@ static void its_vpe_schedule(struct its_vpe *vpe)
static void its_vpe_deschedule(struct its_vpe *vpe)
{
void __iomem *vlpi_base = gic_data_rdist_vlpi_base();
- u32 count = 1000000; /* 1s! */
- bool clean;
u64 val;

- /* We're being scheduled out */
- val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER);
- val &= ~GICR_VPENDBASER_Valid;
- gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
-
- do {
- val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER);
- clean = !(val & GICR_VPENDBASER_Dirty);
- if (!clean) {
- count--;
- cpu_relax();
- udelay(1);
- }
- } while (!clean && count);
+ val = its_clear_vpend_valid(vlpi_base);

- if (unlikely(!clean && !count)) {
+ if (unlikely(val & GICR_VPENDBASER_Dirty)) {
pr_err_ratelimited("ITS virtual pending table not cleaning\n");
vpe->idai = false;
vpe->pending_last = true;
diff --git a/drivers/irqchip/irq-mmp.c b/drivers/irqchip/irq-mmp.c
index 25f32e1d7764..3496b61a312a 100644
--- a/drivers/irqchip/irq-mmp.c
+++ b/drivers/irqchip/irq-mmp.c
@@ -34,6 +34,9 @@
#define SEL_INT_PENDING (1 << 6)
#define SEL_INT_NUM_MASK 0x3f

+#define MMP2_ICU_INT_ROUTE_PJ4_IRQ (1 << 5)
+#define MMP2_ICU_INT_ROUTE_PJ4_FIQ (1 << 6)
+
struct icu_chip_data {
int nr_irqs;
unsigned int virq_base;
@@ -190,7 +193,8 @@ static const struct mmp_intc_conf mmp_conf = {
static const struct mmp_intc_conf mmp2_conf = {
.conf_enable = 0x20,
.conf_disable = 0x0,
- .conf_mask = 0x7f,
+ .conf_mask = MMP2_ICU_INT_ROUTE_PJ4_IRQ |
+ MMP2_ICU_INT_ROUTE_PJ4_FIQ,
};

static void __exception_irq_entry mmp_handle_irq(struct pt_regs *regs)
diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c
index 66a174979b3c..81745644f720 100644
--- a/drivers/media/rc/rc-main.c
+++ b/drivers/media/rc/rc-main.c
@@ -274,6 +274,7 @@ static unsigned int ir_update_mapping(struct rc_dev *dev,
unsigned int new_keycode)
{
int old_keycode = rc_map->scan[index].keycode;
+ int i;

/* Did the user wish to remove the mapping? */
if (new_keycode == KEY_RESERVED || new_keycode == KEY_UNKNOWN) {
@@ -288,9 +289,20 @@ static unsigned int ir_update_mapping(struct rc_dev *dev,
old_keycode == KEY_RESERVED ? "New" : "Replacing",
rc_map->scan[index].scancode, new_keycode);
rc_map->scan[index].keycode = new_keycode;
+ __set_bit(new_keycode, dev->input_dev->keybit);
}

if (old_keycode != KEY_RESERVED) {
+ /* A previous mapping was updated... */
+ __clear_bit(old_keycode, dev->input_dev->keybit);
+ /* ... but another scancode might use the same keycode */
+ for (i = 0; i < rc_map->len; i++) {
+ if (rc_map->scan[i].keycode == old_keycode) {
+ __set_bit(old_keycode, dev->input_dev->keybit);
+ break;
+ }
+ }
+
/* Possibly shrink the keytable, failure is not a problem */
ir_resize_table(dev, rc_map, GFP_ATOMIC);
}
@@ -1750,7 +1762,6 @@ static int rc_prepare_rx_device(struct rc_dev *dev)
set_bit(EV_REP, dev->input_dev->evbit);
set_bit(EV_MSC, dev->input_dev->evbit);
set_bit(MSC_SCAN, dev->input_dev->mscbit);
- bitmap_fill(dev->input_dev->keybit, KEY_CNT);

/* Pointer/mouse events */
set_bit(EV_REL, dev->input_dev->evbit);
diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
index 76dc3ee8ca21..5ad4f91662e6 100644
--- a/drivers/media/usb/uvc/uvc_driver.c
+++ b/drivers/media/usb/uvc/uvc_driver.c
@@ -1065,11 +1065,19 @@ static int uvc_parse_standard_control(struct uvc_device *dev,
return -EINVAL;
}

- /* Make sure the terminal type MSB is not null, otherwise it
- * could be confused with a unit.
+ /*
+ * Reject invalid terminal types that would cause issues:
+ *
+ * - The high byte must be non-zero, otherwise it would be
+ * confused with a unit.
+ *
+ * - Bit 15 must be 0, as we use it internally as a terminal
+ * direction flag.
+ *
+ * Other unknown types are accepted.
*/
type = get_unaligned_le16(&buffer[4]);
- if ((type & 0xff00) == 0) {
+ if ((type & 0x7f00) == 0 || (type & 0x8000) != 0) {
uvc_trace(UVC_TRACE_DESCR, "device %d videocontrol "
"interface %d INPUT_TERMINAL %d has invalid "
"type 0x%04x, skipping\n", udev->devnum,
diff --git a/drivers/net/ethernet/altera/altera_msgdma.c b/drivers/net/ethernet/altera/altera_msgdma.c
index 0fb986ba3290..0ae723f75341 100644
--- a/drivers/net/ethernet/altera/altera_msgdma.c
+++ b/drivers/net/ethernet/altera/altera_msgdma.c
@@ -145,7 +145,8 @@ u32 msgdma_tx_completions(struct altera_tse_private *priv)
& 0xffff;

if (inuse) { /* Tx FIFO is not empty */
- ready = priv->tx_prod - priv->tx_cons - inuse - 1;
+ ready = max_t(int,
+ priv->tx_prod - priv->tx_cons - inuse - 1, 0);
} else {
/* Check for buffered last packet */
status = csrrd32(priv->tx_dma_csr, msgdma_csroffs(status));
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 3d45f4c92cf6..9bbaad9f3d63 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -643,6 +643,7 @@
#define MACB_CAPS_JUMBO 0x00000020
#define MACB_CAPS_GEM_HAS_PTP 0x00000040
#define MACB_CAPS_BD_RD_PREFETCH 0x00000080
+#define MACB_CAPS_NEEDS_RSTONUBR 0x00000100
#define MACB_CAPS_FIFO_MODE 0x10000000
#define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000
#define MACB_CAPS_SG_DISABLED 0x40000000
@@ -1214,6 +1215,8 @@ struct macb {

int rx_bd_rd_prefetch;
int tx_bd_rd_prefetch;
+
+ u32 rx_intr_mask;
};

#ifdef CONFIG_MACB_USE_HWSTAMP
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 4c816e5a841f..73aa7969db96 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -56,8 +56,7 @@
/* level of occupied TX descriptors under which we wake up TX process */
#define MACB_TX_WAKEUP_THRESH(bp) (3 * (bp)->tx_ring_size / 4)

-#define MACB_RX_INT_FLAGS (MACB_BIT(RCOMP) | MACB_BIT(RXUBR) \
- | MACB_BIT(ISR_ROVR))
+#define MACB_RX_INT_FLAGS (MACB_BIT(RCOMP) | MACB_BIT(ISR_ROVR))
#define MACB_TX_ERR_FLAGS (MACB_BIT(ISR_TUND) \
| MACB_BIT(ISR_RLE) \
| MACB_BIT(TXERR))
@@ -1270,7 +1269,7 @@ static int macb_poll(struct napi_struct *napi, int budget)
queue_writel(queue, ISR, MACB_BIT(RCOMP));
napi_reschedule(napi);
} else {
- queue_writel(queue, IER, MACB_RX_INT_FLAGS);
+ queue_writel(queue, IER, bp->rx_intr_mask);
}
}

@@ -1288,7 +1287,7 @@ static void macb_hresp_error_task(unsigned long data)
u32 ctrl;

for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
- queue_writel(queue, IDR, MACB_RX_INT_FLAGS |
+ queue_writel(queue, IDR, bp->rx_intr_mask |
MACB_TX_INT_FLAGS |
MACB_BIT(HRESP));
}
@@ -1318,7 +1317,7 @@ static void macb_hresp_error_task(unsigned long data)

/* Enable interrupts */
queue_writel(queue, IER,
- MACB_RX_INT_FLAGS |
+ bp->rx_intr_mask |
MACB_TX_INT_FLAGS |
MACB_BIT(HRESP));
}
@@ -1372,14 +1371,14 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
(unsigned int)(queue - bp->queues),
(unsigned long)status);

- if (status & MACB_RX_INT_FLAGS) {
+ if (status & bp->rx_intr_mask) {
/* There's no point taking any more interrupts
* until we have processed the buffers. The
* scheduling call may fail if the poll routine
* is already scheduled, so disable interrupts
* now.
*/
- queue_writel(queue, IDR, MACB_RX_INT_FLAGS);
+ queue_writel(queue, IDR, bp->rx_intr_mask);
if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE)
queue_writel(queue, ISR, MACB_BIT(RCOMP));

@@ -1412,8 +1411,9 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
/* There is a hardware issue under heavy load where DMA can
* stop, this causes endless "used buffer descriptor read"
* interrupts but it can be cleared by re-enabling RX. See
- * the at91 manual, section 41.3.1 or the Zynq manual
- * section 16.7.4 for details.
+ * the at91rm9200 manual, section 41.3.1 or the Zynq manual
+ * section 16.7.4 for details. RXUBR is only enabled for
+ * these two versions.
*/
if (status & MACB_BIT(RXUBR)) {
ctrl = macb_readl(bp, NCR);
@@ -2263,7 +2263,7 @@ static void macb_init_hw(struct macb *bp)

/* Enable interrupts */
queue_writel(queue, IER,
- MACB_RX_INT_FLAGS |
+ bp->rx_intr_mask |
MACB_TX_INT_FLAGS |
MACB_BIT(HRESP));
}
@@ -3911,6 +3911,7 @@ static const struct macb_config sama5d4_config = {
};

static const struct macb_config emac_config = {
+ .caps = MACB_CAPS_NEEDS_RSTONUBR,
.clk_init = at91ether_clk_init,
.init = at91ether_init,
};
@@ -3932,7 +3933,8 @@ static const struct macb_config zynqmp_config = {
};

static const struct macb_config zynq_config = {
- .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_NO_GIGABIT_HALF,
+ .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_NO_GIGABIT_HALF |
+ MACB_CAPS_NEEDS_RSTONUBR,
.dma_burst_length = 16,
.clk_init = macb_clk_init,
.init = macb_init,
@@ -4087,6 +4089,10 @@ static int macb_probe(struct platform_device *pdev)
macb_dma_desc_get_size(bp);
}

+ bp->rx_intr_mask = MACB_RX_INT_FLAGS;
+ if (bp->caps & MACB_CAPS_NEEDS_RSTONUBR)
+ bp->rx_intr_mask |= MACB_BIT(RXUBR);
+
mac = of_get_mac_address(np);
if (mac) {
ether_addr_copy(bp->dev->dev_addr, mac);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 6242249c9f4c..b043370c2685 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -2419,6 +2419,8 @@ static int hns_nic_dev_probe(struct platform_device *pdev)
out_notify_fail:
(void)cancel_work_sync(&priv->service_task);
out_read_prop_fail:
+ /* safe for ACPI FW */
+ of_node_put(to_of_node(priv->fwnode));
free_netdev(ndev);
return ret;
}
@@ -2448,6 +2450,9 @@ static int hns_nic_dev_remove(struct platform_device *pdev)
set_bit(NIC_STATE_REMOVING, &priv->state);
(void)cancel_work_sync(&priv->service_task);

+ /* safe for ACPI FW */
+ of_node_put(to_of_node(priv->fwnode));
+
free_netdev(ndev);
return 0;
}
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index 774beda040a1..e2710ff48fb0 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -1157,16 +1157,18 @@ static int hns_get_regs_len(struct net_device *net_dev)
*/
static int hns_nic_nway_reset(struct net_device *netdev)
{
- int ret = 0;
struct phy_device *phy = netdev->phydev;

- if (netif_running(netdev)) {
- /* if autoneg is disabled, don't restart auto-negotiation */
- if (phy && phy->autoneg == AUTONEG_ENABLE)
- ret = genphy_restart_aneg(phy);
- }
+ if (!netif_running(netdev))
+ return 0;

- return ret;
+ if (!phy)
+ return -EOPNOTSUPP;
+
+ if (phy->autoneg != AUTONEG_ENABLE)
+ return -EINVAL;
+
+ return genphy_restart_aneg(phy);
}

static u32
diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c
index 017e08452d8c..baf5cc251f32 100644
--- a/drivers/net/ethernet/hisilicon/hns_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns_mdio.c
@@ -321,7 +321,7 @@ static int hns_mdio_read(struct mii_bus *bus, int phy_id, int regnum)
}

hns_mdio_cmd_write(mdio_dev, is_c45,
- MDIO_C45_WRITE_ADDR, phy_id, devad);
+ MDIO_C45_READ, phy_id, devad);
}

/* Step 5: waitting for MDIO_COMMAND_REG 's mdio_start==0,*/
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 88a8576ca9ce..f81abed29a76 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -480,19 +480,19 @@ static void qed_init_qm_pq(struct qed_hwfn *p_hwfn,

/* get pq index according to PQ_FLAGS */
static u16 *qed_init_qm_get_idx_from_flags(struct qed_hwfn *p_hwfn,
- u32 pq_flags)
+ unsigned long pq_flags)
{
struct qed_qm_info *qm_info = &p_hwfn->qm_info;

/* Can't have multiple flags set here */
- if (bitmap_weight((unsigned long *)&pq_flags,
+ if (bitmap_weight(&pq_flags,
sizeof(pq_flags) * BITS_PER_BYTE) > 1) {
- DP_ERR(p_hwfn, "requested multiple pq flags 0x%x\n", pq_flags);
+ DP_ERR(p_hwfn, "requested multiple pq flags 0x%lx\n", pq_flags);
goto err;
}

if (!(qed_get_pq_flags(p_hwfn) & pq_flags)) {
- DP_ERR(p_hwfn, "pq flag 0x%x is not set\n", pq_flags);
+ DP_ERR(p_hwfn, "pq flag 0x%lx is not set\n", pq_flags);
goto err;
}

diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index 67c02ea93906..64ac95ca4df2 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -609,6 +609,10 @@ qed_sp_update_accept_mode(struct qed_hwfn *p_hwfn,
(!!(accept_filter & QED_ACCEPT_MCAST_MATCHED) &&
!!(accept_filter & QED_ACCEPT_MCAST_UNMATCHED)));

+ SET_FIELD(state, ETH_VPORT_TX_MODE_UCAST_ACCEPT_ALL,
+ (!!(accept_filter & QED_ACCEPT_UCAST_MATCHED) &&
+ !!(accept_filter & QED_ACCEPT_UCAST_UNMATCHED)));
+
SET_FIELD(state, ETH_VPORT_TX_MODE_BCAST_ACCEPT_ALL,
!!(accept_filter & QED_ACCEPT_BCAST));

@@ -744,6 +748,11 @@ int qed_sp_vport_update(struct qed_hwfn *p_hwfn,
return rc;
}

+ if (p_params->update_ctl_frame_check) {
+ p_cmn->ctl_frame_mac_check_en = p_params->mac_chk_en;
+ p_cmn->ctl_frame_ethtype_check_en = p_params->ethtype_chk_en;
+ }
+
/* Update mcast bins for VFs, PF doesn't use this functionality */
qed_sp_update_mcast_bin(p_hwfn, p_ramrod, p_params);

@@ -2207,7 +2216,7 @@ static int qed_fill_eth_dev_info(struct qed_dev *cdev,
u16 num_queues = 0;

/* Since the feature controls only queue-zones,
- * make sure we have the contexts [rx, tx, xdp] to
+ * make sure we have the contexts [rx, xdp, tcs] to
* match.
*/
for_each_hwfn(cdev, i) {
@@ -2217,7 +2226,8 @@ static int qed_fill_eth_dev_info(struct qed_dev *cdev,
u16 cids;

cids = hwfn->pf_params.eth_pf_params.num_cons;
- num_queues += min_t(u16, l2_queues, cids / 3);
+ cids /= (2 + info->num_tc);
+ num_queues += min_t(u16, l2_queues, cids);
}

/* queues might theoretically be >256, but interrupts'
@@ -2688,7 +2698,8 @@ static int qed_configure_filter_rx_mode(struct qed_dev *cdev,
if (type == QED_FILTER_RX_MODE_TYPE_PROMISC) {
accept_flags.rx_accept_filter |= QED_ACCEPT_UCAST_UNMATCHED |
QED_ACCEPT_MCAST_UNMATCHED;
- accept_flags.tx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED;
+ accept_flags.tx_accept_filter |= QED_ACCEPT_UCAST_UNMATCHED |
+ QED_ACCEPT_MCAST_UNMATCHED;
} else if (type == QED_FILTER_RX_MODE_TYPE_MULTI_PROMISC) {
accept_flags.rx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED;
accept_flags.tx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h
index 8d80f1095d17..7127d5aaac42 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h
@@ -219,6 +219,9 @@ struct qed_sp_vport_update_params {
struct qed_rss_params *rss_params;
struct qed_filter_accept_flags accept_flags;
struct qed_sge_tpa_params *sge_tpa_params;
+ u8 update_ctl_frame_check;
+ u8 mac_chk_en;
+ u8 ethtype_chk_en;
};

int qed_sp_vport_update(struct qed_hwfn *p_hwfn,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index 9e728ec82c21..25f67c0d5c57 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -2441,19 +2441,24 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb,
{
struct qed_ll2_tx_pkt_info pkt;
const skb_frag_t *frag;
+ u8 flags = 0, nr_frags;
int rc = -EINVAL, i;
dma_addr_t mapping;
u16 vlan = 0;
- u8 flags = 0;

if (unlikely(skb->ip_summed != CHECKSUM_NONE)) {
DP_INFO(cdev, "Cannot transmit a checksummed packet\n");
return -EINVAL;
}

- if (1 + skb_shinfo(skb)->nr_frags > CORE_LL2_TX_MAX_BDS_PER_PACKET) {
+ /* Cache number of fragments from SKB since SKB may be freed by
+ * the completion routine after calling qed_ll2_prepare_tx_packet()
+ */
+ nr_frags = skb_shinfo(skb)->nr_frags;
+
+ if (1 + nr_frags > CORE_LL2_TX_MAX_BDS_PER_PACKET) {
DP_ERR(cdev, "Cannot transmit a packet with %d fragments\n",
- 1 + skb_shinfo(skb)->nr_frags);
+ 1 + nr_frags);
return -EINVAL;
}

@@ -2475,7 +2480,7 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb,
}

memset(&pkt, 0, sizeof(pkt));
- pkt.num_of_bds = 1 + skb_shinfo(skb)->nr_frags;
+ pkt.num_of_bds = 1 + nr_frags;
pkt.vlan = vlan;
pkt.bd_flags = flags;
pkt.tx_dest = QED_LL2_TX_DEST_NW;
@@ -2486,12 +2491,17 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb,
test_bit(QED_LL2_XMIT_FLAGS_FIP_DISCOVERY, &xmit_flags))
pkt.remove_stag = true;

+ /* qed_ll2_prepare_tx_packet() may actually send the packet if
+ * there are no fragments in the skb and subsequently the completion
+ * routine may run and free the SKB, so no dereferencing the SKB
+ * beyond this point unless skb has any fragments.
+ */
rc = qed_ll2_prepare_tx_packet(&cdev->hwfns[0], cdev->ll2->handle,
&pkt, 1);
if (rc)
goto err;

- for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+ for (i = 0; i < nr_frags; i++) {
frag = &skb_shinfo(skb)->frags[i];

mapping = skb_frag_dma_map(&cdev->pdev->dev, frag, 0,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h
index 3157c0d99441..dae2896e1d8e 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h
@@ -380,6 +380,7 @@ void qed_consq_setup(struct qed_hwfn *p_hwfn);
* @param p_hwfn
*/
void qed_consq_free(struct qed_hwfn *p_hwfn);
+int qed_spq_pend_post(struct qed_hwfn *p_hwfn);

/**
* @file
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index 0a9c5bb0fa48..a721b9348b6c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -402,6 +402,11 @@ int qed_eq_completion(struct qed_hwfn *p_hwfn, void *cookie)

qed_eq_prod_update(p_hwfn, qed_chain_get_prod_idx(p_chain));

+ /* Attempt to post pending requests */
+ spin_lock_bh(&p_hwfn->p_spq->lock);
+ rc = qed_spq_pend_post(p_hwfn);
+ spin_unlock_bh(&p_hwfn->p_spq->lock);
+
return rc;
}

@@ -744,7 +749,7 @@ static int qed_spq_post_list(struct qed_hwfn *p_hwfn,
return 0;
}

-static int qed_spq_pend_post(struct qed_hwfn *p_hwfn)
+int qed_spq_pend_post(struct qed_hwfn *p_hwfn)
{
struct qed_spq *p_spq = p_hwfn->p_spq;
struct qed_spq_entry *p_ent = NULL;
@@ -882,7 +887,6 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn,
struct qed_spq_entry *p_ent = NULL;
struct qed_spq_entry *tmp;
struct qed_spq_entry *found = NULL;
- int rc;

if (!p_hwfn)
return -EINVAL;
@@ -940,12 +944,7 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn,
*/
qed_spq_return_entry(p_hwfn, found);

- /* Attempt to post pending requests */
- spin_lock_bh(&p_spq->lock);
- rc = qed_spq_pend_post(p_hwfn);
- spin_unlock_bh(&p_spq->lock);
-
- return rc;
+ return 0;
}

int qed_consq_alloc(struct qed_hwfn *p_hwfn)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index ca6290fa0f30..71a7af134dd8 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -1969,7 +1969,9 @@ static void qed_iov_vf_mbx_start_vport(struct qed_hwfn *p_hwfn,
params.vport_id = vf->vport_id;
params.max_buffers_per_cqe = start->max_buffers_per_cqe;
params.mtu = vf->mtu;
- params.check_mac = true;
+
+ /* Non trusted VFs should enable control frame filtering */
+ params.check_mac = !vf->p_vf_info.is_trusted_configured;

rc = qed_sp_eth_vport_start(p_hwfn, &params);
if (rc) {
@@ -5130,6 +5132,9 @@ static void qed_iov_handle_trust_change(struct qed_hwfn *hwfn)
params.opaque_fid = vf->opaque_fid;
params.vport_id = vf->vport_id;

+ params.update_ctl_frame_check = 1;
+ params.mac_chk_en = !vf_info->is_trusted_configured;
+
if (vf_info->rx_accept_mode & mask) {
flags->update_rx_mode_config = 1;
flags->rx_accept_filter = vf_info->rx_accept_mode;
@@ -5147,7 +5152,8 @@ static void qed_iov_handle_trust_change(struct qed_hwfn *hwfn)
}

if (flags->update_rx_mode_config ||
- flags->update_tx_mode_config)
+ flags->update_tx_mode_config ||
+ params.update_ctl_frame_check)
qed_sp_vport_update(hwfn, &params,
QED_SPQ_MODE_EBLOCK, NULL);
}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c
index b6cccf44bf40..5dda547772c1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c
@@ -261,6 +261,7 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn)
struct pfvf_acquire_resp_tlv *resp = &p_iov->pf2vf_reply->acquire_resp;
struct pf_vf_pfdev_info *pfdev_info = &resp->pfdev_info;
struct vf_pf_resc_request *p_resc;
+ u8 retry_cnt = VF_ACQUIRE_THRESH;
bool resources_acquired = false;
struct vfpf_acquire_tlv *req;
int rc = 0, attempts = 0;
@@ -314,6 +315,15 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn)

/* send acquire request */
rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp));
+
+ /* Re-try acquire in case of vf-pf hw channel timeout */
+ if (retry_cnt && rc == -EBUSY) {
+ DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+ "VF retrying to acquire due to VPC timeout\n");
+ retry_cnt--;
+ continue;
+ }
+
if (rc)
goto exit;

diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index de98a974673b..4b875f652ecd 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -489,6 +489,9 @@ struct qede_reload_args {

/* Datapath functions definition */
netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev);
+u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb,
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback);
netdev_features_t qede_features_check(struct sk_buff *skb,
struct net_device *dev,
netdev_features_t features);
diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index 1a78027de071..a96da16f3404 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -1695,6 +1695,19 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev)
return NETDEV_TX_OK;
}

+u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb,
+ struct net_device *sb_dev,
+ select_queue_fallback_t fallback)
+{
+ struct qede_dev *edev = netdev_priv(dev);
+ int total_txq;
+
+ total_txq = QEDE_TSS_COUNT(edev) * edev->dev_info.num_tc;
+
+ return QEDE_TSS_COUNT(edev) ?
+ fallback(dev, skb, NULL) % total_txq : 0;
+}
+
/* 8B udp header + 8B base tunnel header + 32B option length */
#define QEDE_MAX_TUN_HDR_LEN 48

diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 46d0f2eaa0c0..f3d9c40c4115 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -631,6 +631,7 @@ static const struct net_device_ops qede_netdev_ops = {
.ndo_open = qede_open,
.ndo_stop = qede_close,
.ndo_start_xmit = qede_start_xmit,
+ .ndo_select_queue = qede_select_queue,
.ndo_set_rx_mode = qede_set_rx_mode,
.ndo_set_mac_address = qede_set_mac_addr,
.ndo_validate_addr = eth_validate_addr,
@@ -666,6 +667,7 @@ static const struct net_device_ops qede_netdev_vf_ops = {
.ndo_open = qede_open,
.ndo_stop = qede_close,
.ndo_start_xmit = qede_start_xmit,
+ .ndo_select_queue = qede_select_queue,
.ndo_set_rx_mode = qede_set_rx_mode,
.ndo_set_mac_address = qede_set_mac_addr,
.ndo_validate_addr = eth_validate_addr,
@@ -684,6 +686,7 @@ static const struct net_device_ops qede_netdev_vf_xdp_ops = {
.ndo_open = qede_open,
.ndo_stop = qede_close,
.ndo_start_xmit = qede_start_xmit,
+ .ndo_select_queue = qede_select_queue,
.ndo_set_rx_mode = qede_set_rx_mode,
.ndo_set_mac_address = qede_set_mac_addr,
.ndo_validate_addr = eth_validate_addr,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 7b923362ee55..3b174eae77c1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -1342,8 +1342,10 @@ static int rk_gmac_powerup(struct rk_priv_data *bsp_priv)
}

ret = phy_power_on(bsp_priv, true);
- if (ret)
+ if (ret) {
+ gmac_clk_enable(bsp_priv, false);
return ret;
+ }

pm_runtime_enable(dev);
pm_runtime_get_sync(dev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 9caf79ba5ef1..4d5fb4b51cc4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -719,8 +719,11 @@ static u32 stmmac_usec2riwt(u32 usec, struct stmmac_priv *priv)
{
unsigned long clk = clk_get_rate(priv->plat->stmmac_clk);

- if (!clk)
- return 0;
+ if (!clk) {
+ clk = priv->plat->clk_ref_rate;
+ if (!clk)
+ return 0;
+ }

return (usec * (clk / 1000000)) / 256;
}
@@ -729,8 +732,11 @@ static u32 stmmac_riwt2usec(u32 riwt, struct stmmac_priv *priv)
{
unsigned long clk = clk_get_rate(priv->plat->stmmac_clk);

- if (!clk)
- return 0;
+ if (!clk) {
+ clk = priv->plat->clk_ref_rate;
+ if (!clk)
+ return 0;
+ }

return (riwt * 256) / (clk / 1000000);
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 5d83d6a7694b..9340526d2a9a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3031,10 +3031,22 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)

tx_q = &priv->tx_queue[queue];

+ if (priv->tx_path_in_lpi_mode)
+ stmmac_disable_eee_mode(priv);
+
/* Manage oversized TCP frames for GMAC4 device */
if (skb_is_gso(skb) && priv->tso) {
- if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))
+ if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) {
+ /*
+ * There is no way to determine the number of TSO
+ * capable Queues. Let's use always the Queue 0
+ * because if TSO is supported then at least this
+ * one will be capable.
+ */
+ skb_set_queue_mapping(skb, 0);
+
return stmmac_tso_xmit(skb, dev);
+ }
}

if (unlikely(stmmac_tx_avail(priv, queue) < nfrags + 1)) {
@@ -3049,9 +3061,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_BUSY;
}

- if (priv->tx_path_in_lpi_mode)
- stmmac_disable_eee_mode(priv);
-
entry = tx_q->cur_tx;
first_entry = entry;
WARN_ON(tx_q->tx_skbuff[first_entry]);
diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index 59fdda67f89f..0a3b2c45549e 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -548,7 +548,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
{
.id = WCN3990_HW_1_0_DEV_VERSION,
.dev_id = 0,
- .bus = ATH10K_BUS_PCI,
+ .bus = ATH10K_BUS_SNOC,
.name = "wcn3990 hw1.0",
.continuous_frag_desc = true,
.tx_chain_mask = 0x7,
diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c
index c070a9e51ebf..fae572b38416 100644
--- a/drivers/net/wireless/ath/ath9k/init.c
+++ b/drivers/net/wireless/ath/ath9k/init.c
@@ -636,15 +636,15 @@ static int ath9k_of_init(struct ath_softc *sc)
ret = ath9k_eeprom_request(sc, eeprom_name);
if (ret)
return ret;
+
+ ah->ah_flags &= ~AH_USE_EEPROM;
+ ah->ah_flags |= AH_NO_EEP_SWAP;
}

mac = of_get_mac_address(np);
if (mac)
ether_addr_copy(common->macaddr, mac);

- ah->ah_flags &= ~AH_USE_EEPROM;
- ah->ah_flags |= AH_NO_EEP_SWAP;
-
return 0;
}

diff --git a/drivers/net/wireless/ti/wlcore/sdio.c b/drivers/net/wireless/ti/wlcore/sdio.c
index bd10165d7eec..4d4b07701149 100644
--- a/drivers/net/wireless/ti/wlcore/sdio.c
+++ b/drivers/net/wireless/ti/wlcore/sdio.c
@@ -164,6 +164,12 @@ static int wl12xx_sdio_power_on(struct wl12xx_sdio_glue *glue)
}

sdio_claim_host(func);
+ /*
+ * To guarantee that the SDIO card is power cycled, as required to make
+ * the FW programming to succeed, let's do a brute force HW reset.
+ */
+ mmc_hw_reset(card->host);
+
sdio_enable_func(func);
sdio_release_host(func);

@@ -174,20 +180,13 @@ static int wl12xx_sdio_power_off(struct wl12xx_sdio_glue *glue)
{
struct sdio_func *func = dev_to_sdio_func(glue->dev);
struct mmc_card *card = func->card;
- int error;

sdio_claim_host(func);
sdio_disable_func(func);
sdio_release_host(func);

/* Let runtime PM know the card is powered off */
- error = pm_runtime_put(&card->dev);
- if (error < 0 && error != -EBUSY) {
- dev_err(&card->dev, "%s failed: %i\n", __func__, error);
-
- return error;
- }
-
+ pm_runtime_put(&card->dev);
return 0;
}

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 5f9a5ef93969..21d7b646c73d 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1182,6 +1182,7 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
* effects say only one namespace is affected.
*/
if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) {
+ mutex_lock(&ctrl->scan_lock);
nvme_start_freeze(ctrl);
nvme_wait_freeze(ctrl);
}
@@ -1210,8 +1211,10 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
*/
if (effects & NVME_CMD_EFFECTS_LBCC)
nvme_update_formats(ctrl);
- if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK))
+ if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) {
nvme_unfreeze(ctrl);
+ mutex_unlock(&ctrl->scan_lock);
+ }
if (effects & NVME_CMD_EFFECTS_CCC)
nvme_init_identify(ctrl);
if (effects & (NVME_CMD_EFFECTS_NIC | NVME_CMD_EFFECTS_NCC))
@@ -3300,6 +3303,7 @@ static void nvme_scan_work(struct work_struct *work)
if (nvme_identify_ctrl(ctrl, &id))
return;

+ mutex_lock(&ctrl->scan_lock);
nn = le32_to_cpu(id->nn);
if (ctrl->vs >= NVME_VS(1, 1, 0) &&
!(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) {
@@ -3308,6 +3312,7 @@ static void nvme_scan_work(struct work_struct *work)
}
nvme_scan_ns_sequential(ctrl, nn);
out_free_id:
+ mutex_unlock(&ctrl->scan_lock);
kfree(id);
down_write(&ctrl->namespaces_rwsem);
list_sort(NULL, &ctrl->namespaces, ns_cmp);
@@ -3550,6 +3555,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,

ctrl->state = NVME_CTRL_NEW;
spin_lock_init(&ctrl->lock);
+ mutex_init(&ctrl->scan_lock);
INIT_LIST_HEAD(&ctrl->namespaces);
init_rwsem(&ctrl->namespaces_rwsem);
ctrl->dev = dev;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 6ffa99a10a60..5274881f9141 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -153,6 +153,7 @@ struct nvme_ctrl {
enum nvme_ctrl_state state;
bool identified;
spinlock_t lock;
+ struct mutex scan_lock;
const struct nvme_ctrl_ops *ops;
struct request_queue *admin_q;
struct request_queue *connect_q;
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index c0d01048ce4d..5c58e0ffa3ac 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2280,27 +2280,18 @@ static void nvme_reset_work(struct work_struct *work)
if (dev->ctrl.ctrl_config & NVME_CC_ENABLE)
nvme_dev_disable(dev, false);

- /*
- * Introduce CONNECTING state from nvme-fc/rdma transports to mark the
- * initializing procedure here.
- */
- if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) {
- dev_warn(dev->ctrl.device,
- "failed to mark controller CONNECTING\n");
- goto out;
- }
-
+ mutex_lock(&dev->shutdown_lock);
result = nvme_pci_enable(dev);
if (result)
- goto out;
+ goto out_unlock;

result = nvme_pci_configure_admin_queue(dev);
if (result)
- goto out;
+ goto out_unlock;

result = nvme_alloc_admin_tags(dev);
if (result)
- goto out;
+ goto out_unlock;

/*
* Limit the max command size to prevent iod->sg allocations going
@@ -2308,6 +2299,17 @@ static void nvme_reset_work(struct work_struct *work)
*/
dev->ctrl.max_hw_sectors = NVME_MAX_KB_SZ << 1;
dev->ctrl.max_segments = NVME_MAX_SEGS;
+ mutex_unlock(&dev->shutdown_lock);
+
+ /*
+ * Introduce CONNECTING state from nvme-fc/rdma transports to mark the
+ * initializing procedure here.
+ */
+ if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) {
+ dev_warn(dev->ctrl.device,
+ "failed to mark controller CONNECTING\n");
+ goto out;
+ }

result = nvme_init_identify(&dev->ctrl);
if (result)
@@ -2372,6 +2374,8 @@ static void nvme_reset_work(struct work_struct *work)
nvme_start_ctrl(&dev->ctrl);
return;

+ out_unlock:
+ mutex_unlock(&dev->shutdown_lock);
out:
nvme_remove_dead_ctrl(dev, result);
}
diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c
index 0dbcf429089f..1a8b85051b1b 100644
--- a/drivers/pci/pcie/pme.c
+++ b/drivers/pci/pcie/pme.c
@@ -432,31 +432,6 @@ static void pcie_pme_remove(struct pcie_device *srv)
kfree(get_service_data(srv));
}

-static int pcie_pme_runtime_suspend(struct pcie_device *srv)
-{
- struct pcie_pme_service_data *data = get_service_data(srv);
-
- spin_lock_irq(&data->lock);
- pcie_pme_interrupt_enable(srv->port, false);
- pcie_clear_root_pme_status(srv->port);
- data->noirq = true;
- spin_unlock_irq(&data->lock);
-
- return 0;
-}
-
-static int pcie_pme_runtime_resume(struct pcie_device *srv)
-{
- struct pcie_pme_service_data *data = get_service_data(srv);
-
- spin_lock_irq(&data->lock);
- pcie_pme_interrupt_enable(srv->port, true);
- data->noirq = false;
- spin_unlock_irq(&data->lock);
-
- return 0;
-}
-
static struct pcie_port_service_driver pcie_pme_driver = {
.name = "pcie_pme",
.port_type = PCI_EXP_TYPE_ROOT_PORT,
@@ -464,8 +439,6 @@ static struct pcie_port_service_driver pcie_pme_driver = {

.probe = pcie_pme_probe,
.suspend = pcie_pme_suspend,
- .runtime_suspend = pcie_pme_runtime_suspend,
- .runtime_resume = pcie_pme_runtime_resume,
.resume = pcie_pme_resume,
.remove = pcie_pme_remove,
};
diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c
index b03481ef99a1..98905d4a79ca 100644
--- a/drivers/pinctrl/pinctrl-mcp23s08.c
+++ b/drivers/pinctrl/pinctrl-mcp23s08.c
@@ -832,8 +832,13 @@ static int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev,
break;

case MCP_TYPE_S18:
+ one_regmap_config =
+ devm_kmemdup(dev, &mcp23x17_regmap,
+ sizeof(struct regmap_config), GFP_KERNEL);
+ if (!one_regmap_config)
+ return -ENOMEM;
mcp->regmap = devm_regmap_init(dev, &mcp23sxx_spi_regmap, mcp,
- &mcp23x17_regmap);
+ one_regmap_config);
mcp->reg_shift = 1;
mcp->chip.ngpio = 16;
mcp->chip.label = "mcp23s18";
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 54f6a40c75c6..0430cad6d84e 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -901,6 +901,7 @@ config TOSHIBA_WMI
config ACPI_CMPC
tristate "CMPC Laptop Extras"
depends on ACPI && INPUT
+ depends on BACKLIGHT_LCD_SUPPORT
depends on RFKILL || RFKILL=n
select BACKLIGHT_CLASS_DEVICE
help
@@ -1124,6 +1125,7 @@ config INTEL_OAKTRAIL
config SAMSUNG_Q10
tristate "Samsung Q10 Extras"
depends on ACPI
+ depends on BACKLIGHT_LCD_SUPPORT
select BACKLIGHT_CLASS_DEVICE
---help---
This driver provides support for backlight control on Samsung Q10
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 99af1a0a3314..8f2af450152f 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -22,6 +22,7 @@
#include <linux/hashtable.h>
#include <linux/ip.h>
#include <linux/refcount.h>
+#include <linux/workqueue.h>

#include <net/ipv6.h>
#include <net/if_inet6.h>
@@ -790,6 +791,7 @@ struct qeth_card {
struct qeth_seqno seqno;
struct qeth_card_options options;

+ struct workqueue_struct *event_wq;
wait_queue_head_t wait_q;
spinlock_t mclock;
unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
@@ -968,7 +970,6 @@ extern const struct attribute_group *qeth_osn_attr_groups[];
extern const struct attribute_group qeth_device_attr_group;
extern const struct attribute_group qeth_device_blkt_group;
extern const struct device_type qeth_generic_devtype;
-extern struct workqueue_struct *qeth_wq;

int qeth_card_hw_is_reachable(struct qeth_card *);
const char *qeth_get_cardname_short(struct qeth_card *);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 0c9a5250dd93..ebbc3ad504f9 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -76,8 +76,7 @@ static void qeth_notify_skbs(struct qeth_qdio_out_q *queue,
static void qeth_release_skbs(struct qeth_qdio_out_buffer *buf);
static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *, int);

-struct workqueue_struct *qeth_wq;
-EXPORT_SYMBOL_GPL(qeth_wq);
+static struct workqueue_struct *qeth_wq;

int qeth_card_hw_is_reachable(struct qeth_card *card)
{
@@ -568,6 +567,7 @@ static int __qeth_issue_next_read(struct qeth_card *card)
QETH_DBF_MESSAGE(2, "error %i on device %x when starting next read ccw!\n",
rc, CARD_DEVID(card));
atomic_set(&channel->irq_pending, 0);
+ qeth_release_buffer(channel, iob);
card->read_or_write_problem = 1;
qeth_schedule_recovery(card);
wake_up(&card->wait_q);
@@ -1129,6 +1129,8 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
rc = qeth_get_problem(card, cdev, irb);
if (rc) {
card->read_or_write_problem = 1;
+ if (iob)
+ qeth_release_buffer(iob->channel, iob);
qeth_clear_ipacmd_list(card);
qeth_schedule_recovery(card);
goto out;
@@ -1468,6 +1470,10 @@ static struct qeth_card *qeth_alloc_card(struct ccwgroup_device *gdev)
CARD_RDEV(card) = gdev->cdev[0];
CARD_WDEV(card) = gdev->cdev[1];
CARD_DDEV(card) = gdev->cdev[2];
+
+ card->event_wq = alloc_ordered_workqueue("%s", 0, dev_name(&gdev->dev));
+ if (!card->event_wq)
+ goto out_wq;
if (qeth_setup_channel(&card->read, true))
goto out_ip;
if (qeth_setup_channel(&card->write, true))
@@ -1483,6 +1489,8 @@ static struct qeth_card *qeth_alloc_card(struct ccwgroup_device *gdev)
out_channel:
qeth_clean_channel(&card->read);
out_ip:
+ destroy_workqueue(card->event_wq);
+out_wq:
dev_set_drvdata(&gdev->dev, NULL);
kfree(card);
out:
@@ -1811,6 +1819,7 @@ static int qeth_idx_activate_get_answer(struct qeth_card *card,
QETH_DBF_MESSAGE(2, "Error2 in activating channel rc=%d\n", rc);
QETH_DBF_TEXT_(SETUP, 2, "2err%d", rc);
atomic_set(&channel->irq_pending, 0);
+ qeth_release_buffer(channel, iob);
wake_up(&card->wait_q);
return rc;
}
@@ -1880,6 +1889,7 @@ static int qeth_idx_activate_channel(struct qeth_card *card,
rc);
QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc);
atomic_set(&channel->irq_pending, 0);
+ qeth_release_buffer(channel, iob);
wake_up(&card->wait_q);
return rc;
}
@@ -2060,6 +2070,7 @@ int qeth_send_control_data(struct qeth_card *card, int len,
}
reply = qeth_alloc_reply(card);
if (!reply) {
+ qeth_release_buffer(channel, iob);
return -ENOMEM;
}
reply->callback = reply_cb;
@@ -2391,11 +2402,12 @@ static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *q, int bidx)
return 0;
}

-static void qeth_free_qdio_out_buf(struct qeth_qdio_out_q *q)
+static void qeth_free_output_queue(struct qeth_qdio_out_q *q)
{
if (!q)
return;

+ qeth_clear_outq_buffers(q, 1);
qdio_free_buffers(q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q);
kfree(q);
}
@@ -2469,10 +2481,8 @@ static int qeth_alloc_qdio_buffers(struct qeth_card *card)
card->qdio.out_qs[i]->bufs[j] = NULL;
}
out_freeoutq:
- while (i > 0) {
- qeth_free_qdio_out_buf(card->qdio.out_qs[--i]);
- qeth_clear_outq_buffers(card->qdio.out_qs[i], 1);
- }
+ while (i > 0)
+ qeth_free_output_queue(card->qdio.out_qs[--i]);
kfree(card->qdio.out_qs);
card->qdio.out_qs = NULL;
out_freepool:
@@ -2505,10 +2515,8 @@ static void qeth_free_qdio_buffers(struct qeth_card *card)
qeth_free_buffer_pool(card);
/* free outbound qdio_qs */
if (card->qdio.out_qs) {
- for (i = 0; i < card->qdio.no_out_queues; ++i) {
- qeth_clear_outq_buffers(card->qdio.out_qs[i], 1);
- qeth_free_qdio_out_buf(card->qdio.out_qs[i]);
- }
+ for (i = 0; i < card->qdio.no_out_queues; i++)
+ qeth_free_output_queue(card->qdio.out_qs[i]);
kfree(card->qdio.out_qs);
card->qdio.out_qs = NULL;
}
@@ -5035,6 +5043,7 @@ static void qeth_core_free_card(struct qeth_card *card)
qeth_clean_channel(&card->read);
qeth_clean_channel(&card->write);
qeth_clean_channel(&card->data);
+ destroy_workqueue(card->event_wq);
qeth_free_qdio_buffers(card);
unregister_service_level(&card->qeth_service_level);
dev_set_drvdata(&card->gdev->dev, NULL);
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 8d3601891c62..a6c55cbf3d69 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -391,6 +391,8 @@ static void qeth_l2_stop_card(struct qeth_card *card, int recovery_mode)
qeth_clear_cmd_buffers(&card->read);
qeth_clear_cmd_buffers(&card->write);
}
+
+ flush_workqueue(card->event_wq);
}

static int qeth_l2_process_inbound_buffer(struct qeth_card *card,
@@ -823,6 +825,8 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev)

if (cgdev->state == CCWGROUP_ONLINE)
qeth_l2_set_offline(cgdev);
+
+ cancel_work_sync(&card->close_dev_work);
if (qeth_netdev_is_registered(card->dev))
unregister_netdev(card->dev);
}
@@ -1453,7 +1457,7 @@ static void qeth_bridge_state_change(struct qeth_card *card,
data->card = card;
memcpy(&data->qports, qports,
sizeof(struct qeth_sbp_state_change) + extrasize);
- queue_work(qeth_wq, &data->worker);
+ queue_work(card->event_wq, &data->worker);
}

struct qeth_bridge_host_data {
@@ -1525,7 +1529,7 @@ static void qeth_bridge_host_event(struct qeth_card *card,
data->card = card;
memcpy(&data->hostevs, hostevs,
sizeof(struct qeth_ipacmd_addr_change) + extrasize);
- queue_work(qeth_wq, &data->worker);
+ queue_work(card->event_wq, &data->worker);
}

/* SETBRIDGEPORT support; sending commands */
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index f08b745c2007..29a2408b9282 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -1436,6 +1436,8 @@ static void qeth_l3_stop_card(struct qeth_card *card, int recovery_mode)
qeth_clear_cmd_buffers(&card->read);
qeth_clear_cmd_buffers(&card->write);
}
+
+ flush_workqueue(card->event_wq);
}

/*
@@ -2428,6 +2430,7 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev)
if (cgdev->state == CCWGROUP_ONLINE)
qeth_l3_set_offline(cgdev);

+ cancel_work_sync(&card->close_dev_work);
if (qeth_netdev_is_registered(card->dev))
unregister_netdev(card->dev);
qeth_l3_clear_ip_htable(card, 0);
diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c
index 6be77b3aa8a5..ac79f2088b31 100644
--- a/drivers/scsi/53c700.c
+++ b/drivers/scsi/53c700.c
@@ -295,7 +295,7 @@ NCR_700_detect(struct scsi_host_template *tpnt,
if(tpnt->sdev_attrs == NULL)
tpnt->sdev_attrs = NCR_700_dev_attrs;

- memory = dma_alloc_attrs(hostdata->dev, TOTAL_MEM_SIZE, &pScript,
+ memory = dma_alloc_attrs(dev, TOTAL_MEM_SIZE, &pScript,
GFP_KERNEL, DMA_ATTR_NON_CONSISTENT);
if(memory == NULL) {
printk(KERN_ERR "53c700: Failed to allocate memory for driver, detaching\n");
diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index 1e77d96a18f2..055fe61ea539 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -1304,8 +1304,9 @@ static void aac_handle_aif(struct aac_dev * dev, struct fib * fibptr)
ADD : DELETE;
break;
}
- case AifBuManagerEvent:
- aac_handle_aif_bu(dev, aifcmd);
+ break;
+ case AifBuManagerEvent:
+ aac_handle_aif_bu(dev, aifcmd);
break;
}

diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c
index 350257c13a5b..bc9f2a2365f4 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_io.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_io.c
@@ -240,6 +240,7 @@ struct bnx2fc_cmd_mgr *bnx2fc_cmd_mgr_alloc(struct bnx2fc_hba *hba)
return NULL;
}

+ cmgr->hba = hba;
cmgr->free_list = kcalloc(arr_sz, sizeof(*cmgr->free_list),
GFP_KERNEL);
if (!cmgr->free_list) {
@@ -256,7 +257,6 @@ struct bnx2fc_cmd_mgr *bnx2fc_cmd_mgr_alloc(struct bnx2fc_hba *hba)
goto mem_err;
}

- cmgr->hba = hba;
cmgr->cmds = (struct bnx2fc_cmd **)(cmgr + 1);

for (i = 0; i < arr_sz; i++) {
@@ -295,7 +295,7 @@ struct bnx2fc_cmd_mgr *bnx2fc_cmd_mgr_alloc(struct bnx2fc_hba *hba)

/* Allocate pool of io_bdts - one for each bnx2fc_cmd */
mem_size = num_ios * sizeof(struct io_bdt *);
- cmgr->io_bdt_pool = kmalloc(mem_size, GFP_KERNEL);
+ cmgr->io_bdt_pool = kzalloc(mem_size, GFP_KERNEL);
if (!cmgr->io_bdt_pool) {
printk(KERN_ERR PFX "failed to alloc io_bdt_pool\n");
goto mem_err;
diff --git a/drivers/scsi/libfc/fc_lport.c b/drivers/scsi/libfc/fc_lport.c
index be83590ed955..ff943f477d6f 100644
--- a/drivers/scsi/libfc/fc_lport.c
+++ b/drivers/scsi/libfc/fc_lport.c
@@ -1726,14 +1726,14 @@ void fc_lport_flogi_resp(struct fc_seq *sp, struct fc_frame *fp,
fc_frame_payload_op(fp) != ELS_LS_ACC) {
FC_LPORT_DBG(lport, "FLOGI not accepted or bad response\n");
fc_lport_error(lport, fp);
- goto err;
+ goto out;
}

flp = fc_frame_payload_get(fp, sizeof(*flp));
if (!flp) {
FC_LPORT_DBG(lport, "FLOGI bad response\n");
fc_lport_error(lport, fp);
- goto err;
+ goto out;
}

mfs = ntohs(flp->fl_csp.sp_bb_data) &
@@ -1743,7 +1743,7 @@ void fc_lport_flogi_resp(struct fc_seq *sp, struct fc_frame *fp,
FC_LPORT_DBG(lport, "FLOGI bad mfs:%hu response, "
"lport->mfs:%hu\n", mfs, lport->mfs);
fc_lport_error(lport, fp);
- goto err;
+ goto out;
}

if (mfs <= lport->mfs) {
diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c
index 1e1c0f1b9e69..8ed2113f5a1e 100644
--- a/drivers/scsi/libfc/fc_rport.c
+++ b/drivers/scsi/libfc/fc_rport.c
@@ -184,7 +184,6 @@ void fc_rport_destroy(struct kref *kref)
struct fc_rport_priv *rdata;

rdata = container_of(kref, struct fc_rport_priv, kref);
- WARN_ON(!list_empty(&rdata->peers));
kfree_rcu(rdata, rcu);
}
EXPORT_SYMBOL(fc_rport_destroy);
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 60bcc6df97a9..65305b3848bc 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -62,7 +62,7 @@

/* make sure inq_product_rev string corresponds to this version */
#define SDEBUG_VERSION "0188" /* format to fit INQUIRY revision field */
-static const char *sdebug_version_date = "20180128";
+static const char *sdebug_version_date = "20190125";

#define MY_NAME "scsi_debug"

@@ -735,7 +735,7 @@ static inline bool scsi_debug_lbp(void)
(sdebug_lbpu || sdebug_lbpws || sdebug_lbpws10);
}

-static void *fake_store(unsigned long long lba)
+static void *lba2fake_store(unsigned long long lba)
{
lba = do_div(lba, sdebug_store_sectors);

@@ -2514,8 +2514,8 @@ static int do_device_access(struct scsi_cmnd *scmd, u32 sg_skip, u64 lba,
return ret;
}

-/* If fake_store(lba,num) compares equal to arr(num), then copy top half of
- * arr into fake_store(lba,num) and return true. If comparison fails then
+/* If lba2fake_store(lba,num) compares equal to arr(num), then copy top half of
+ * arr into lba2fake_store(lba,num) and return true. If comparison fails then
* return false. */
static bool comp_write_worker(u64 lba, u32 num, const u8 *arr)
{
@@ -2643,7 +2643,7 @@ static int prot_verify_read(struct scsi_cmnd *SCpnt, sector_t start_sec,
if (sdt->app_tag == cpu_to_be16(0xffff))
continue;

- ret = dif_verify(sdt, fake_store(sector), sector, ei_lba);
+ ret = dif_verify(sdt, lba2fake_store(sector), sector, ei_lba);
if (ret) {
dif_errors++;
return ret;
@@ -3261,10 +3261,12 @@ static int resp_write_scat(struct scsi_cmnd *scp,
static int resp_write_same(struct scsi_cmnd *scp, u64 lba, u32 num,
u32 ei_lba, bool unmap, bool ndob)
{
+ int ret;
unsigned long iflags;
unsigned long long i;
- int ret;
- u64 lba_off;
+ u32 lb_size = sdebug_sector_size;
+ u64 block, lbaa;
+ u8 *fs1p;

ret = check_device_access_params(scp, lba, num);
if (ret)
@@ -3276,31 +3278,30 @@ static int resp_write_same(struct scsi_cmnd *scp, u64 lba, u32 num,
unmap_region(lba, num);
goto out;
}
-
- lba_off = lba * sdebug_sector_size;
+ lbaa = lba;
+ block = do_div(lbaa, sdebug_store_sectors);
/* if ndob then zero 1 logical block, else fetch 1 logical block */
+ fs1p = fake_storep + (block * lb_size);
if (ndob) {
- memset(fake_storep + lba_off, 0, sdebug_sector_size);
+ memset(fs1p, 0, lb_size);
ret = 0;
} else
- ret = fetch_to_dev_buffer(scp, fake_storep + lba_off,
- sdebug_sector_size);
+ ret = fetch_to_dev_buffer(scp, fs1p, lb_size);

if (-1 == ret) {
write_unlock_irqrestore(&atomic_rw, iflags);
return DID_ERROR << 16;
- } else if (sdebug_verbose && !ndob && (ret < sdebug_sector_size))
+ } else if (sdebug_verbose && !ndob && (ret < lb_size))
sdev_printk(KERN_INFO, scp->device,
"%s: %s: lb size=%u, IO sent=%d bytes\n",
- my_name, "write same",
- sdebug_sector_size, ret);
+ my_name, "write same", lb_size, ret);

/* Copy first sector to remaining blocks */
- for (i = 1 ; i < num ; i++)
- memcpy(fake_storep + ((lba + i) * sdebug_sector_size),
- fake_storep + lba_off,
- sdebug_sector_size);
-
+ for (i = 1 ; i < num ; i++) {
+ lbaa = lba + i;
+ block = do_div(lbaa, sdebug_store_sectors);
+ memmove(fake_storep + (block * lb_size), fs1p, lb_size);
+ }
if (scsi_debug_lbp())
map_region(lba, num);
out:
diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c
index 5ce24718c2fd..d8b3ba047c28 100644
--- a/drivers/soc/fsl/qbman/qman.c
+++ b/drivers/soc/fsl/qbman/qman.c
@@ -1124,18 +1124,19 @@ static void qm_mr_process_task(struct work_struct *work);
static irqreturn_t portal_isr(int irq, void *ptr)
{
struct qman_portal *p = ptr;
-
- u32 clear = QM_DQAVAIL_MASK | p->irq_sources;
u32 is = qm_in(&p->p, QM_REG_ISR) & p->irq_sources;
+ u32 clear = 0;

if (unlikely(!is))
return IRQ_NONE;

/* DQRR-handling if it's interrupt-driven */
- if (is & QM_PIRQ_DQRI)
+ if (is & QM_PIRQ_DQRI) {
__poll_portal_fast(p, QMAN_POLL_LIMIT);
+ clear = QM_DQAVAIL_MASK | QM_PIRQ_DQRI;
+ }
/* Handling of anything else that's interrupt-driven */
- clear |= __poll_portal_slow(p, is);
+ clear |= __poll_portal_slow(p, is) & QM_PIRQ_SLOW;
qm_out(&p->p, QM_REG_ISR, clear);
return IRQ_HANDLED;
}
diff --git a/drivers/staging/erofs/namei.c b/drivers/staging/erofs/namei.c
index 5596c52e246d..ecc51ef0753f 100644
--- a/drivers/staging/erofs/namei.c
+++ b/drivers/staging/erofs/namei.c
@@ -15,74 +15,77 @@

#include <trace/events/erofs.h>

-/* based on the value of qn->len is accurate */
-static inline int dirnamecmp(struct qstr *qn,
- struct qstr *qd, unsigned int *matched)
+struct erofs_qstr {
+ const unsigned char *name;
+ const unsigned char *end;
+};
+
+/* based on the end of qn is accurate and it must have the trailing '\0' */
+static inline int dirnamecmp(const struct erofs_qstr *qn,
+ const struct erofs_qstr *qd,
+ unsigned int *matched)
{
- unsigned int i = *matched, len = min(qn->len, qd->len);
-loop:
- if (unlikely(i >= len)) {
- *matched = i;
- if (qn->len < qd->len) {
- /*
- * actually (qn->len == qd->len)
- * when qd->name[i] == '\0'
- */
- return qd->name[i] == '\0' ? 0 : -1;
+ unsigned int i = *matched;
+
+ /*
+ * on-disk error, let's only BUG_ON in the debugging mode.
+ * otherwise, it will return 1 to just skip the invalid name
+ * and go on (in consideration of the lookup performance).
+ */
+ DBG_BUGON(qd->name > qd->end);
+
+ /* qd could not have trailing '\0' */
+ /* However it is absolutely safe if < qd->end */
+ while (qd->name + i < qd->end && qd->name[i] != '\0') {
+ if (qn->name[i] != qd->name[i]) {
+ *matched = i;
+ return qn->name[i] > qd->name[i] ? 1 : -1;
}
- return (qn->len > qd->len);
+ ++i;
}
-
- if (qn->name[i] != qd->name[i]) {
- *matched = i;
- return qn->name[i] > qd->name[i] ? 1 : -1;
- }
-
- ++i;
- goto loop;
+ *matched = i;
+ /* See comments in __d_alloc on the terminating NUL character */
+ return qn->name[i] == '\0' ? 0 : 1;
}

-static struct erofs_dirent *find_target_dirent(
- struct qstr *name,
- u8 *data, int maxsize)
+#define nameoff_from_disk(off, sz) (le16_to_cpu(off) & ((sz) - 1))
+
+static struct erofs_dirent *find_target_dirent(struct erofs_qstr *name,
+ u8 *data,
+ unsigned int dirblksize,
+ const int ndirents)
{
- unsigned int ndirents, head, back;
+ int head, back;
unsigned int startprfx, endprfx;
struct erofs_dirent *const de = (struct erofs_dirent *)data;

- /* make sure that maxsize is valid */
- BUG_ON(maxsize < sizeof(struct erofs_dirent));
-
- ndirents = le16_to_cpu(de->nameoff) / sizeof(*de);
-
- /* corrupted dir (may be unnecessary...) */
- BUG_ON(!ndirents);
-
- head = 0;
+ /* since the 1st dirent has been evaluated previously */
+ head = 1;
back = ndirents - 1;
startprfx = endprfx = 0;

while (head <= back) {
- unsigned int mid = head + (back - head) / 2;
- unsigned int nameoff = le16_to_cpu(de[mid].nameoff);
+ const int mid = head + (back - head) / 2;
+ const int nameoff = nameoff_from_disk(de[mid].nameoff,
+ dirblksize);
unsigned int matched = min(startprfx, endprfx);
-
- struct qstr dname = QSTR_INIT(data + nameoff,
- unlikely(mid >= ndirents - 1) ?
- maxsize - nameoff :
- le16_to_cpu(de[mid + 1].nameoff) - nameoff);
+ struct erofs_qstr dname = {
+ .name = data + nameoff,
+ .end = unlikely(mid >= ndirents - 1) ?
+ data + dirblksize :
+ data + nameoff_from_disk(de[mid + 1].nameoff,
+ dirblksize)
+ };

/* string comparison without already matched prefix */
int ret = dirnamecmp(name, &dname, &matched);

- if (unlikely(!ret))
+ if (unlikely(!ret)) {
return de + mid;
- else if (ret > 0) {
+ } else if (ret > 0) {
head = mid + 1;
startprfx = matched;
- } else if (unlikely(mid < 1)) /* fix "mid" overflow */
- break;
- else {
+ } else {
back = mid - 1;
endprfx = matched;
}
@@ -91,12 +94,12 @@ static struct erofs_dirent *find_target_dirent(
return ERR_PTR(-ENOENT);
}

-static struct page *find_target_block_classic(
- struct inode *dir,
- struct qstr *name, int *_diff)
+static struct page *find_target_block_classic(struct inode *dir,
+ struct erofs_qstr *name,
+ int *_ndirents)
{
unsigned int startprfx, endprfx;
- unsigned int head, back;
+ int head, back;
struct address_space *const mapping = dir->i_mapping;
struct page *candidate = ERR_PTR(-ENOENT);

@@ -105,41 +108,43 @@ static struct page *find_target_block_classic(
back = inode_datablocks(dir) - 1;

while (head <= back) {
- unsigned int mid = head + (back - head) / 2;
+ const int mid = head + (back - head) / 2;
struct page *page = read_mapping_page(mapping, mid, NULL);

- if (IS_ERR(page)) {
-exact_out:
- if (!IS_ERR(candidate)) /* valid candidate */
- put_page(candidate);
- return page;
- } else {
- int diff;
- unsigned int ndirents, matched;
- struct qstr dname;
+ if (!IS_ERR(page)) {
struct erofs_dirent *de = kmap_atomic(page);
- unsigned int nameoff = le16_to_cpu(de->nameoff);
-
- ndirents = nameoff / sizeof(*de);
+ const int nameoff = nameoff_from_disk(de->nameoff,
+ EROFS_BLKSIZ);
+ const int ndirents = nameoff / sizeof(*de);
+ int diff;
+ unsigned int matched;
+ struct erofs_qstr dname;

- /* corrupted dir (should have one entry at least) */
- BUG_ON(!ndirents || nameoff > PAGE_SIZE);
+ if (unlikely(!ndirents)) {
+ DBG_BUGON(1);
+ kunmap_atomic(de);
+ put_page(page);
+ page = ERR_PTR(-EIO);
+ goto out;
+ }

matched = min(startprfx, endprfx);

dname.name = (u8 *)de + nameoff;
- dname.len = ndirents == 1 ?
- /* since the rest of the last page is 0 */
- EROFS_BLKSIZ - nameoff
- : le16_to_cpu(de[1].nameoff) - nameoff;
+ if (ndirents == 1)
+ dname.end = (u8 *)de + EROFS_BLKSIZ;
+ else
+ dname.end = (u8 *)de +
+ nameoff_from_disk(de[1].nameoff,
+ EROFS_BLKSIZ);

/* string comparison without already matched prefix */
diff = dirnamecmp(name, &dname, &matched);
kunmap_atomic(de);

if (unlikely(!diff)) {
- *_diff = 0;
- goto exact_out;
+ *_ndirents = 0;
+ goto out;
} else if (diff > 0) {
head = mid + 1;
startprfx = matched;
@@ -147,45 +152,51 @@ static struct page *find_target_block_classic(
if (likely(!IS_ERR(candidate)))
put_page(candidate);
candidate = page;
+ *_ndirents = ndirents;
} else {
put_page(page);

- if (unlikely(mid < 1)) /* fix "mid" overflow */
- break;
-
back = mid - 1;
endprfx = matched;
}
+ continue;
}
+out: /* free if the candidate is valid */
+ if (!IS_ERR(candidate))
+ put_page(candidate);
+ return page;
}
- *_diff = 1;
return candidate;
}

int erofs_namei(struct inode *dir,
- struct qstr *name,
- erofs_nid_t *nid, unsigned int *d_type)
+ struct qstr *name,
+ erofs_nid_t *nid, unsigned int *d_type)
{
- int diff;
+ int ndirents;
struct page *page;
- u8 *data;
+ void *data;
struct erofs_dirent *de;
+ struct erofs_qstr qn;

if (unlikely(!dir->i_size))
return -ENOENT;

- diff = 1;
- page = find_target_block_classic(dir, name, &diff);
+ qn.name = name->name;
+ qn.end = name->name + name->len;
+
+ ndirents = 0;
+ page = find_target_block_classic(dir, &qn, &ndirents);

if (unlikely(IS_ERR(page)))
return PTR_ERR(page);

data = kmap_atomic(page);
/* the target page has been mapped */
- de = likely(diff) ?
- /* since the rest of the last page is 0 */
- find_target_dirent(name, data, EROFS_BLKSIZ) :
- (struct erofs_dirent *)data;
+ if (ndirents)
+ de = find_target_dirent(&qn, data, EROFS_BLKSIZ, ndirents);
+ else
+ de = (struct erofs_dirent *)data;

if (likely(!IS_ERR(de))) {
*nid = le64_to_cpu(de->nid);
diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c
index cb7fcd7c0ad8..c1e9ea621f41 100644
--- a/drivers/usb/dwc3/dwc3-exynos.c
+++ b/drivers/usb/dwc3/dwc3-exynos.c
@@ -78,7 +78,7 @@ static int dwc3_exynos_probe(struct platform_device *pdev)
for (i = 0; i < exynos->num_clks; i++) {
ret = clk_prepare_enable(exynos->clks[i]);
if (ret) {
- while (--i > 0)
+ while (i-- > 0)
clk_disable_unprepare(exynos->clks[i]);
return ret;
}
@@ -223,7 +223,7 @@ static int dwc3_exynos_resume(struct device *dev)
for (i = 0; i < exynos->num_clks; i++) {
ret = clk_prepare_enable(exynos->clks[i]);
if (ret) {
- while (--i > 0)
+ while (i-- > 0)
clk_disable_unprepare(exynos->clks[i]);
return ret;
}
diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig
index d7312eed6088..91ea3083e7ad 100644
--- a/drivers/usb/phy/Kconfig
+++ b/drivers/usb/phy/Kconfig
@@ -21,7 +21,7 @@ config AB8500_USB

config FSL_USB2_OTG
bool "Freescale USB OTG Transceiver Driver"
- depends on USB_EHCI_FSL && USB_FSL_USB2 && USB_OTG_FSM && PM
+ depends on USB_EHCI_FSL && USB_FSL_USB2 && USB_OTG_FSM=y && PM
depends on USB_GADGET || !USB_GADGET # if USB_GADGET=m, this can't be 'y'
select USB_PHY
help
diff --git a/fs/autofs/expire.c b/fs/autofs/expire.c
index d441244b79df..28d9c2b1b3bb 100644
--- a/fs/autofs/expire.c
+++ b/fs/autofs/expire.c
@@ -596,7 +596,6 @@ int autofs_expire_run(struct super_block *sb,
pkt.len = dentry->d_name.len;
memcpy(pkt.name, dentry->d_name.name, pkt.len);
pkt.name[pkt.len] = '\0';
- dput(dentry);

if (copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire)))
ret = -EFAULT;
@@ -609,6 +608,8 @@ int autofs_expire_run(struct super_block *sb,
complete_all(&ino->expire_complete);
spin_unlock(&sbi->fs_lock);

+ dput(dentry);
+
return ret;
}

diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c
index 846c052569dd..3c14a8e45ffb 100644
--- a/fs/autofs/inode.c
+++ b/fs/autofs/inode.c
@@ -255,8 +255,10 @@ int autofs_fill_super(struct super_block *s, void *data, int silent)
}
root_inode = autofs_get_inode(s, S_IFDIR | 0755);
root = d_make_root(root_inode);
- if (!root)
+ if (!root) {
+ ret = -ENOMEM;
goto fail_ino;
+ }
pipe = NULL;

root->d_fsdata = ino;
diff --git a/fs/buffer.c b/fs/buffer.c
index 1286c2b95498..72e33ffa00ff 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -200,6 +200,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
struct buffer_head *head;
struct page *page;
int all_mapped = 1;
+ static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1);

index = block >> (PAGE_SHIFT - bd_inode->i_blkbits);
page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED);
@@ -227,15 +228,15 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
* file io on the block device and getblk. It gets dealt with
* elsewhere, don't buffer_error if we had some unmapped buffers
*/
- if (all_mapped) {
- printk("__find_get_block_slow() failed. "
- "block=%llu, b_blocknr=%llu\n",
- (unsigned long long)block,
- (unsigned long long)bh->b_blocknr);
- printk("b_state=0x%08lx, b_size=%zu\n",
- bh->b_state, bh->b_size);
- printk("device %pg blocksize: %d\n", bdev,
- 1 << bd_inode->i_blkbits);
+ ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE);
+ if (all_mapped && __ratelimit(&last_warned)) {
+ printk("__find_get_block_slow() failed. block=%llu, "
+ "b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, "
+ "device %pg blocksize: %d\n",
+ (unsigned long long)block,
+ (unsigned long long)bh->b_blocknr,
+ bh->b_state, bh->b_size, bdev,
+ 1 << bd_inode->i_blkbits);
}
out_unlock:
spin_unlock(&bd_mapping->private_lock);
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index 5671d5ee7f58..eaf39fb71f8b 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -84,8 +84,8 @@

#define NUMBER_OF_SMB2_COMMANDS 0x0013

-/* 4 len + 52 transform hdr + 64 hdr + 56 create rsp */
-#define MAX_SMB2_HDR_SIZE 0x00b0
+/* 52 transform hdr + 64 hdr + 88 create rsp */
+#define MAX_SMB2_HDR_SIZE 204

#define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe)
#define SMB2_TRANSFORM_PROTO_NUM cpu_to_le32(0x424d53fd)
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 82377017130f..d31b6c72b476 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -21,8 +21,13 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
spin_lock(&sb->s_inode_list_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
spin_lock(&inode->i_lock);
+ /*
+ * We must skip inodes in unusual state. We may also skip
+ * inodes without pages but we deliberately won't in case
+ * we need to reschedule to avoid softlockups.
+ */
if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
- (inode->i_mapping->nrpages == 0)) {
+ (inode->i_mapping->nrpages == 0 && !need_resched())) {
spin_unlock(&inode->i_lock);
continue;
}
@@ -30,6 +35,7 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
spin_unlock(&inode->i_lock);
spin_unlock(&sb->s_inode_list_lock);

+ cond_resched();
invalidate_mapping_pages(inode->i_mapping, 0, -1);
iput(toput_inode);
toput_inode = inode;
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 05431324b262..57cdce53b64b 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -107,7 +107,7 @@ static int glock_wake_function(wait_queue_entry_t *wait, unsigned int mode,

static wait_queue_head_t *glock_waitqueue(struct lm_lockname *name)
{
- u32 hash = jhash2((u32 *)name, sizeof(*name) / 4, 0);
+ u32 hash = jhash2((u32 *)name, ht_parms.key_len / 4, 0);

return glock_wait_table + hash_32(hash, GLOCK_WAIT_TABLE_BITS);
}
diff --git a/fs/iomap.c b/fs/iomap.c
index ce837d962d47..83d9a196fe3e 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -116,6 +116,12 @@ iomap_page_create(struct inode *inode, struct page *page)
atomic_set(&iop->read_count, 0);
atomic_set(&iop->write_count, 0);
bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE);
+
+ /*
+ * migrate_page_move_mapping() assumes that pages with private data have
+ * their count elevated by 1.
+ */
+ get_page(page);
set_page_private(page, (unsigned long)iop);
SetPagePrivate(page);
return iop;
@@ -132,6 +138,7 @@ iomap_page_release(struct page *page)
WARN_ON_ONCE(atomic_read(&iop->write_count));
ClearPagePrivate(page);
set_page_private(page, 0);
+ put_page(page);
kfree(iop);
}

@@ -569,8 +576,10 @@ iomap_migrate_page(struct address_space *mapping, struct page *newpage,

if (page_has_private(page)) {
ClearPagePrivate(page);
+ get_page(newpage);
set_page_private(newpage, page_private(page));
set_page_private(page, 0);
+ put_page(page);
SetPagePrivate(newpage);
}

@@ -1797,6 +1806,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
loff_t pos = iocb->ki_pos, start = pos;
loff_t end = iocb->ki_pos + count - 1, ret = 0;
unsigned int flags = IOMAP_DIRECT;
+ bool wait_for_completion = is_sync_kiocb(iocb);
struct blk_plug plug;
struct iomap_dio *dio;

@@ -1816,7 +1826,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
dio->end_io = end_io;
dio->error = 0;
dio->flags = 0;
- dio->wait_for_completion = is_sync_kiocb(iocb);

dio->submit.iter = iter;
dio->submit.waiter = current;
@@ -1871,7 +1880,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
dio_warn_stale_pagecache(iocb->ki_filp);
ret = 0;

- if (iov_iter_rw(iter) == WRITE && !dio->wait_for_completion &&
+ if (iov_iter_rw(iter) == WRITE && !wait_for_completion &&
!inode->i_sb->s_dio_done_wq) {
ret = sb_init_dio_done_wq(inode->i_sb);
if (ret < 0)
@@ -1887,7 +1896,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
if (ret <= 0) {
/* magic error code to fall back to buffered I/O */
if (ret == -ENOTBLK) {
- dio->wait_for_completion = true;
+ wait_for_completion = true;
ret = 0;
}
break;
@@ -1909,8 +1918,24 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
if (dio->flags & IOMAP_DIO_WRITE_FUA)
dio->flags &= ~IOMAP_DIO_NEED_SYNC;

+ /*
+ * We are about to drop our additional submission reference, which
+ * might be the last reference to the dio. There are three three
+ * different ways we can progress here:
+ *
+ * (a) If this is the last reference we will always complete and free
+ * the dio ourselves.
+ * (b) If this is not the last reference, and we serve an asynchronous
+ * iocb, we must never touch the dio after the decrement, the
+ * I/O completion handler will complete and free it.
+ * (c) If this is not the last reference, but we serve a synchronous
+ * iocb, the I/O completion handler will wake us up on the drop
+ * of the final reference, and we will complete and free it here
+ * after we got woken by the I/O completion handler.
+ */
+ dio->wait_for_completion = wait_for_completion;
if (!atomic_dec_and_test(&dio->ref)) {
- if (!dio->wait_for_completion)
+ if (!wait_for_completion)
return -EIOCBQUEUED;

for (;;) {
@@ -1927,9 +1952,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
__set_current_state(TASK_RUNNING);
}

- ret = iomap_dio_complete(dio);
-
- return ret;
+ return iomap_dio_complete(dio);

out_free_dio:
kfree(dio);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 5ef2c71348bd..6b666d187907 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1906,6 +1906,11 @@ static int nfs_parse_devname(const char *dev_name,
size_t len;
char *end;

+ if (unlikely(!dev_name || !*dev_name)) {
+ dfprintk(MOUNT, "NFS: device name not specified\n");
+ return -EINVAL;
+ }
+
/* Is the host name protected with square brakcets? */
if (*dev_name == '[') {
end = strchr(++dev_name, ']');
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 8ae109429a88..e39bac94dead 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -256,7 +256,7 @@ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry,
inode = proc_get_inode(dir->i_sb, de);
if (!inode)
return ERR_PTR(-ENOMEM);
- d_set_d_op(dentry, &proc_misc_dentry_ops);
+ d_set_d_op(dentry, de->proc_dops);
return d_splice_alias(inode, dentry);
}
read_unlock(&proc_subdir_lock);
@@ -429,6 +429,8 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
INIT_LIST_HEAD(&ent->pde_openers);
proc_set_user(ent, (*parent)->uid, (*parent)->gid);

+ ent->proc_dops = &proc_misc_dentry_ops;
+
out:
return ent;
}
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 5185d7f6a51e..95b14196f284 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -44,6 +44,7 @@ struct proc_dir_entry {
struct completion *pde_unload_completion;
const struct inode_operations *proc_iops;
const struct file_operations *proc_fops;
+ const struct dentry_operations *proc_dops;
union {
const struct seq_operations *seq_ops;
int (*single_show)(struct seq_file *, void *);
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index d5e0fcb3439e..a7b12435519e 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -38,6 +38,22 @@ static struct net *get_proc_net(const struct inode *inode)
return maybe_get_net(PDE_NET(PDE(inode)));
}

+static int proc_net_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+ return 0;
+}
+
+static const struct dentry_operations proc_net_dentry_ops = {
+ .d_revalidate = proc_net_d_revalidate,
+ .d_delete = always_delete_dentry,
+};
+
+static void pde_force_lookup(struct proc_dir_entry *pde)
+{
+ /* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */
+ pde->proc_dops = &proc_net_dentry_ops;
+}
+
static int seq_open_net(struct inode *inode, struct file *file)
{
unsigned int state_size = PDE(inode)->state_size;
@@ -90,6 +106,7 @@ struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode,
p = proc_create_reg(name, mode, &parent, data);
if (!p)
return NULL;
+ pde_force_lookup(p);
p->proc_fops = &proc_net_seq_fops;
p->seq_ops = ops;
p->state_size = state_size;
@@ -133,6 +150,7 @@ struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode
p = proc_create_reg(name, mode, &parent, data);
if (!p)
return NULL;
+ pde_force_lookup(p);
p->proc_fops = &proc_net_seq_fops;
p->seq_ops = ops;
p->state_size = state_size;
@@ -181,6 +199,7 @@ struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode,
p = proc_create_reg(name, mode, &parent, data);
if (!p)
return NULL;
+ pde_force_lookup(p);
p->proc_fops = &proc_net_single_fops;
p->single_show = show;
return proc_register(parent, p);
@@ -223,6 +242,7 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo
p = proc_create_reg(name, mode, &parent, data);
if (!p)
return NULL;
+ pde_force_lookup(p);
p->proc_fops = &proc_net_single_fops;
p->single_show = show;
p->write = write;
diff --git a/include/drm/drm_cache.h b/include/drm/drm_cache.h
index bfe1639df02d..97fc498dc767 100644
--- a/include/drm/drm_cache.h
+++ b/include/drm/drm_cache.h
@@ -47,6 +47,24 @@ static inline bool drm_arch_can_wc_memory(void)
return false;
#elif defined(CONFIG_MIPS) && defined(CONFIG_CPU_LOONGSON3)
return false;
+#elif defined(CONFIG_ARM) || defined(CONFIG_ARM64)
+ /*
+ * The DRM driver stack is designed to work with cache coherent devices
+ * only, but permits an optimization to be enabled in some cases, where
+ * for some buffers, both the CPU and the GPU use uncached mappings,
+ * removing the need for DMA snooping and allocation in the CPU caches.
+ *
+ * The use of uncached GPU mappings relies on the correct implementation
+ * of the PCIe NoSnoop TLP attribute by the platform, otherwise the GPU
+ * will use cached mappings nonetheless. On x86 platforms, this does not
+ * seem to matter, as uncached CPU mappings will snoop the caches in any
+ * case. However, on ARM and arm64, enabling this optimization on a
+ * platform where NoSnoop is ignored results in loss of coherency, which
+ * breaks correct operation of the device. Since we have no way of
+ * detecting whether NoSnoop works or not, just disable this
+ * optimization entirely for ARM and arm64.
+ */
+ return false;
#else
return true;
#endif
diff --git a/include/linux/filter.h b/include/linux/filter.h
index b776626aeb84..958eddbc44d3 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -591,8 +591,8 @@ static inline u8 *bpf_skb_cb(struct sk_buff *skb)
return qdisc_skb_cb(skb)->data;
}

-static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog,
- struct sk_buff *skb)
+static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog,
+ struct sk_buff *skb)
{
u8 *cb_data = bpf_skb_cb(skb);
u8 cb_saved[BPF_SKB_CB_LEN];
@@ -611,15 +611,30 @@ static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog,
return res;
}

+static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog,
+ struct sk_buff *skb)
+{
+ u32 res;
+
+ preempt_disable();
+ res = __bpf_prog_run_save_cb(prog, skb);
+ preempt_enable();
+ return res;
+}
+
static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog,
struct sk_buff *skb)
{
u8 *cb_data = bpf_skb_cb(skb);
+ u32 res;

if (unlikely(prog->cb_access))
memset(cb_data, 0, BPF_SKB_CB_LEN);

- return BPF_PROG_RUN(prog, skb);
+ preempt_disable();
+ res = BPF_PROG_RUN(prog, skb);
+ preempt_enable();
+ return res;
}

static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog,
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 071b4cbdf010..c848a7cc502e 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -319,7 +319,7 @@
#define GITS_TYPER_PLPIS (1UL << 0)
#define GITS_TYPER_VLPIS (1UL << 1)
#define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT 4
-#define GITS_TYPER_ITT_ENTRY_SIZE(r) ((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0x1f) + 1)
+#define GITS_TYPER_ITT_ENTRY_SIZE(r) ((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0xf) + 1)
#define GITS_TYPER_IDBITS_SHIFT 8
#define GITS_TYPER_DEVBITS_SHIFT 13
#define GITS_TYPER_DEVBITS(r) ((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1)
diff --git a/include/linux/signal.h b/include/linux/signal.h
index f428e86f4800..b5d99482d3fe 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -388,7 +388,7 @@ extern bool unhandled_signal(struct task_struct *tsk, int sig);
#endif

#define siginmask(sig, mask) \
- ((sig) < SIGRTMIN && (rt_sigmask(sig) & (mask)))
+ ((sig) > 0 && (sig) < SIGRTMIN && (rt_sigmask(sig) & (mask)))

#define SIG_KERNEL_ONLY_MASK (\
rt_sigmask(SIGKILL) | rt_sigmask(SIGSTOP))
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 7ddfc65586b0..4335bd771ce5 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -184,6 +184,7 @@ struct plat_stmmacenet_data {
struct clk *pclk;
struct clk *clk_ptp_ref;
unsigned int clk_ptp_rate;
+ unsigned int clk_ref_rate;
struct reset_control *stmmac_rst;
struct stmmac_axi *axi;
int has_gmac4;
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 841835a387e1..b4984bbbe157 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -469,9 +469,7 @@ struct nft_set_binding {
int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
struct nft_set_binding *binding);
void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
- struct nft_set_binding *binding);
-void nf_tables_rebind_set(const struct nft_ctx *ctx, struct nft_set *set,
- struct nft_set_binding *binding);
+ struct nft_set_binding *binding, bool commit);
void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set);

/**
@@ -721,6 +719,13 @@ struct nft_expr_type {
#define NFT_EXPR_STATEFUL 0x1
#define NFT_EXPR_GC 0x2

+enum nft_trans_phase {
+ NFT_TRANS_PREPARE,
+ NFT_TRANS_ABORT,
+ NFT_TRANS_COMMIT,
+ NFT_TRANS_RELEASE
+};
+
/**
* struct nft_expr_ops - nf_tables expression operations
*
@@ -750,7 +755,8 @@ struct nft_expr_ops {
void (*activate)(const struct nft_ctx *ctx,
const struct nft_expr *expr);
void (*deactivate)(const struct nft_ctx *ctx,
- const struct nft_expr *expr);
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase);
void (*destroy)(const struct nft_ctx *ctx,
const struct nft_expr *expr);
void (*destroy_clone)(const struct nft_ctx *ctx,
@@ -1323,12 +1329,15 @@ struct nft_trans_rule {
struct nft_trans_set {
struct nft_set *set;
u32 set_id;
+ bool bound;
};

#define nft_trans_set(trans) \
(((struct nft_trans_set *)trans->data)->set)
#define nft_trans_set_id(trans) \
(((struct nft_trans_set *)trans->data)->set_id)
+#define nft_trans_set_bound(trans) \
+ (((struct nft_trans_set *)trans->data)->bound)

struct nft_trans_chain {
bool update;
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 9425c2fb872f..6c24b1fb2db8 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -572,7 +572,7 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
bpf_compute_and_save_data_end(skb, &saved_data_end);

ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb,
- bpf_prog_run_save_cb);
+ __bpf_prog_run_save_cb);
bpf_restore_data_end(skb, saved_data_end);
__skb_pull(skb, offset);
skb->sk = save_sk;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 2c1790288138..3388c0b85a57 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -677,7 +677,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
}

if (htab_is_prealloc(htab)) {
- pcpu_freelist_push(&htab->freelist, &l->fnode);
+ __pcpu_freelist_push(&htab->freelist, &l->fnode);
} else {
atomic_dec(&htab->count);
l->htab = htab;
@@ -739,7 +739,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
} else {
struct pcpu_freelist_node *l;

- l = pcpu_freelist_pop(&htab->freelist);
+ l = __pcpu_freelist_pop(&htab->freelist);
if (!l)
return ERR_PTR(-E2BIG);
l_new = container_of(l, struct htab_elem, fnode);
diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c
index 673fa6fe2d73..0c1b4ba9e90e 100644
--- a/kernel/bpf/percpu_freelist.c
+++ b/kernel/bpf/percpu_freelist.c
@@ -28,8 +28,8 @@ void pcpu_freelist_destroy(struct pcpu_freelist *s)
free_percpu(s->freelist);
}

-static inline void __pcpu_freelist_push(struct pcpu_freelist_head *head,
- struct pcpu_freelist_node *node)
+static inline void ___pcpu_freelist_push(struct pcpu_freelist_head *head,
+ struct pcpu_freelist_node *node)
{
raw_spin_lock(&head->lock);
node->next = head->first;
@@ -37,12 +37,22 @@ static inline void __pcpu_freelist_push(struct pcpu_freelist_head *head,
raw_spin_unlock(&head->lock);
}

-void pcpu_freelist_push(struct pcpu_freelist *s,
+void __pcpu_freelist_push(struct pcpu_freelist *s,
struct pcpu_freelist_node *node)
{
struct pcpu_freelist_head *head = this_cpu_ptr(s->freelist);

- __pcpu_freelist_push(head, node);
+ ___pcpu_freelist_push(head, node);
+}
+
+void pcpu_freelist_push(struct pcpu_freelist *s,
+ struct pcpu_freelist_node *node)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __pcpu_freelist_push(s, node);
+ local_irq_restore(flags);
}

void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size,
@@ -63,7 +73,7 @@ void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size,
for_each_possible_cpu(cpu) {
again:
head = per_cpu_ptr(s->freelist, cpu);
- __pcpu_freelist_push(head, buf);
+ ___pcpu_freelist_push(head, buf);
i++;
buf += elem_size;
if (i == nr_elems)
@@ -74,14 +84,12 @@ void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size,
local_irq_restore(flags);
}

-struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s)
+struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *s)
{
struct pcpu_freelist_head *head;
struct pcpu_freelist_node *node;
- unsigned long flags;
int orig_cpu, cpu;

- local_irq_save(flags);
orig_cpu = cpu = raw_smp_processor_id();
while (1) {
head = per_cpu_ptr(s->freelist, cpu);
@@ -89,16 +97,25 @@ struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s)
node = head->first;
if (node) {
head->first = node->next;
- raw_spin_unlock_irqrestore(&head->lock, flags);
+ raw_spin_unlock(&head->lock);
return node;
}
raw_spin_unlock(&head->lock);
cpu = cpumask_next(cpu, cpu_possible_mask);
if (cpu >= nr_cpu_ids)
cpu = 0;
- if (cpu == orig_cpu) {
- local_irq_restore(flags);
+ if (cpu == orig_cpu)
return NULL;
- }
}
}
+
+struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s)
+{
+ struct pcpu_freelist_node *ret;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ ret = __pcpu_freelist_pop(s);
+ local_irq_restore(flags);
+ return ret;
+}
diff --git a/kernel/bpf/percpu_freelist.h b/kernel/bpf/percpu_freelist.h
index 3049aae8ea1e..c3960118e617 100644
--- a/kernel/bpf/percpu_freelist.h
+++ b/kernel/bpf/percpu_freelist.h
@@ -22,8 +22,12 @@ struct pcpu_freelist_node {
struct pcpu_freelist_node *next;
};

+/* pcpu_freelist_* do spin_lock_irqsave. */
void pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *);
struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *);
+/* __pcpu_freelist_* do spin_lock only. caller must disable irqs. */
+void __pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *);
+struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *);
void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size,
u32 nr_elems);
int pcpu_freelist_init(struct pcpu_freelist *);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index cf5040fd5434..5f03ddf7b615 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -712,8 +712,13 @@ static int map_lookup_elem(union bpf_attr *attr)

if (bpf_map_is_dev_bound(map)) {
err = bpf_map_offload_lookup_elem(map, key, value);
- } else if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
- map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
+ goto done;
+ }
+
+ preempt_disable();
+ this_cpu_inc(bpf_prog_active);
+ if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
err = bpf_percpu_hash_copy(map, key, value);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
err = bpf_percpu_array_copy(map, key, value);
@@ -743,7 +748,10 @@ static int map_lookup_elem(union bpf_attr *attr)
}
rcu_read_unlock();
}
+ this_cpu_dec(bpf_prog_active);
+ preempt_enable();

+done:
if (err)
goto free_value;

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 699bc25d6204..18997730b665 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -436,18 +436,18 @@ int perf_proc_update_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
- int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
-
- if (ret || !write)
- return ret;
-
+ int ret;
+ int perf_cpu = sysctl_perf_cpu_time_max_percent;
/*
* If throttling is disabled don't allow the write:
*/
- if (sysctl_perf_cpu_time_max_percent == 100 ||
- sysctl_perf_cpu_time_max_percent == 0)
+ if (write && (perf_cpu == 100 || perf_cpu == 0))
return -EINVAL;

+ ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+ if (ret || !write)
+ return ret;
+
max_samples_per_tick = DIV_ROUND_UP(sysctl_perf_event_sample_rate, HZ);
perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate;
update_perf_cpu_limits();
diff --git a/kernel/relay.c b/kernel/relay.c
index 04f248644e06..9e0f52375487 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -428,6 +428,8 @@ static struct dentry *relay_create_buf_file(struct rchan *chan,
dentry = chan->cb->create_buf_file(tmpname, chan->parent,
S_IRUSR, buf,
&chan->is_global);
+ if (IS_ERR(dentry))
+ dentry = NULL;

kfree(tmpname);

@@ -461,7 +463,7 @@ static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu)
dentry = chan->cb->create_buf_file(NULL, NULL,
S_IRUSR, buf,
&chan->is_global);
- if (WARN_ON(dentry))
+ if (IS_ERR_OR_NULL(dentry))
goto free_buf;
}

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index fe24de3fbc93..c3484785b179 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -124,6 +124,7 @@
* sampling of the aggregate task states would be.
*/

+#include "../workqueue_internal.h"
#include <linux/sched/loadavg.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
@@ -480,9 +481,6 @@ static void psi_group_change(struct psi_group *group, int cpu,
groupc->tasks[t]++;

write_seqcount_end(&groupc->seq);
-
- if (!delayed_work_pending(&group->clock_work))
- schedule_delayed_work(&group->clock_work, PSI_FREQ);
}

static struct psi_group *iterate_groups(struct task_struct *task, void **iter)
@@ -513,6 +511,7 @@ void psi_task_change(struct task_struct *task, int clear, int set)
{
int cpu = task_cpu(task);
struct psi_group *group;
+ bool wake_clock = true;
void *iter = NULL;

if (!task->pid)
@@ -530,8 +529,22 @@ void psi_task_change(struct task_struct *task, int clear, int set)
task->psi_flags &= ~clear;
task->psi_flags |= set;

- while ((group = iterate_groups(task, &iter)))
+ /*
+ * Periodic aggregation shuts off if there is a period of no
+ * task changes, so we wake it back up if necessary. However,
+ * don't do this if the task change is the aggregation worker
+ * itself going to sleep, or we'll ping-pong forever.
+ */
+ if (unlikely((clear & TSK_RUNNING) &&
+ (task->flags & PF_WQ_WORKER) &&
+ wq_worker_last_func(task) == psi_update_work))
+ wake_clock = false;
+
+ while ((group = iterate_groups(task, &iter))) {
psi_group_change(group, cpu, clear, set);
+ if (wake_clock && !delayed_work_pending(&group->clock_work))
+ schedule_delayed_work(&group->clock_work, PSI_FREQ);
+ }
}

void psi_memstall_tick(struct task_struct *task, int cpu)
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 9864a35c8bb5..6c28d519447d 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1158,22 +1158,12 @@ static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *

int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
{
- int err;
-
- mutex_lock(&bpf_event_mutex);
- err = __bpf_probe_register(btp, prog);
- mutex_unlock(&bpf_event_mutex);
- return err;
+ return __bpf_probe_register(btp, prog);
}

int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
{
- int err;
-
- mutex_lock(&bpf_event_mutex);
- err = tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog);
- mutex_unlock(&bpf_event_mutex);
- return err;
+ return tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog);
}

int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 0280deac392e..288b2105bbb1 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -909,6 +909,26 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task)
return to_wakeup ? to_wakeup->task : NULL;
}

+/**
+ * wq_worker_last_func - retrieve worker's last work function
+ *
+ * Determine the last function a worker executed. This is called from
+ * the scheduler to get a worker's last known identity.
+ *
+ * CONTEXT:
+ * spin_lock_irq(rq->lock)
+ *
+ * Return:
+ * The last work function %current executed as a worker, NULL if it
+ * hasn't executed any work yet.
+ */
+work_func_t wq_worker_last_func(struct task_struct *task)
+{
+ struct worker *worker = kthread_data(task);
+
+ return worker->last_func;
+}
+
/**
* worker_set_flags - set worker flags and adjust nr_running accordingly
* @worker: self
@@ -2184,6 +2204,9 @@ __acquires(&pool->lock)
if (unlikely(cpu_intensive))
worker_clr_flags(worker, WORKER_CPU_INTENSIVE);

+ /* tag the worker for identification in schedule() */
+ worker->last_func = worker->current_func;
+
/* we're done with it, release */
hash_del(&worker->hentry);
worker->current_work = NULL;
diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h
index 66fbb5a9e633..cb68b03ca89a 100644
--- a/kernel/workqueue_internal.h
+++ b/kernel/workqueue_internal.h
@@ -53,6 +53,9 @@ struct worker {

/* used only by rescuers to point to the target workqueue */
struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */
+
+ /* used by the scheduler to determine a worker's last known identity */
+ work_func_t last_func;
};

/**
@@ -67,9 +70,10 @@ static inline struct worker *current_wq_worker(void)

/*
* Scheduler hooks for concurrency managed workqueue. Only to be used from
- * sched/core.c and workqueue.c.
+ * sched/ and workqueue.c.
*/
void wq_worker_waking_up(struct task_struct *task, int cpu);
struct task_struct *wq_worker_sleeping(struct task_struct *task);
+work_func_t wq_worker_last_func(struct task_struct *task);

#endif /* _KERNEL_WORKQUEUE_INTERNAL_H */
diff --git a/lib/test_kmod.c b/lib/test_kmod.c
index d82d022111e0..9cf77628fc91 100644
--- a/lib/test_kmod.c
+++ b/lib/test_kmod.c
@@ -632,7 +632,7 @@ static void __kmod_config_free(struct test_config *config)
config->test_driver = NULL;

kfree_const(config->test_fs);
- config->test_driver = NULL;
+ config->test_fs = NULL;
}

static void kmod_config_free(struct kmod_test_device *test_dev)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 21d94b5677e8..cb201163666f 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1189,11 +1189,13 @@ static inline int pageblock_free(struct page *page)
return PageBuddy(page) && page_order(page) >= pageblock_order;
}

-/* Return the start of the next active pageblock after a given page */
-static struct page *next_active_pageblock(struct page *page)
+/* Return the pfn of the start of the next active pageblock after a given pfn */
+static unsigned long next_active_pageblock(unsigned long pfn)
{
+ struct page *page = pfn_to_page(pfn);
+
/* Ensure the starting page is pageblock-aligned */
- BUG_ON(page_to_pfn(page) & (pageblock_nr_pages - 1));
+ BUG_ON(pfn & (pageblock_nr_pages - 1));

/* If the entire pageblock is free, move to the end of free page */
if (pageblock_free(page)) {
@@ -1201,16 +1203,16 @@ static struct page *next_active_pageblock(struct page *page)
/* be careful. we don't have locks, page_order can be changed.*/
order = page_order(page);
if ((order < MAX_ORDER) && (order >= pageblock_order))
- return page + (1 << order);
+ return pfn + (1 << order);
}

- return page + pageblock_nr_pages;
+ return pfn + pageblock_nr_pages;
}

-static bool is_pageblock_removable_nolock(struct page *page)
+static bool is_pageblock_removable_nolock(unsigned long pfn)
{
+ struct page *page = pfn_to_page(pfn);
struct zone *zone;
- unsigned long pfn;

/*
* We have to be careful here because we are iterating over memory
@@ -1233,12 +1235,14 @@ static bool is_pageblock_removable_nolock(struct page *page)
/* Checks if this range of memory is likely to be hot-removable. */
bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
{
- struct page *page = pfn_to_page(start_pfn);
- struct page *end_page = page + nr_pages;
+ unsigned long end_pfn, pfn;
+
+ end_pfn = min(start_pfn + nr_pages,
+ zone_end_pfn(page_zone(pfn_to_page(start_pfn))));

/* Check the starting page of each pageblock within the range */
- for (; page < end_page; page = next_active_pageblock(page)) {
- if (!is_pageblock_removable_nolock(page))
+ for (pfn = start_pfn; pfn < end_pfn; pfn = next_active_pageblock(pfn)) {
+ if (!is_pageblock_removable_nolock(pfn))
return false;
cond_resched();
}
@@ -1274,6 +1278,9 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
i++;
if (i == MAX_ORDER_NR_PAGES || pfn + i >= end_pfn)
continue;
+ /* Check if we got outside of the zone */
+ if (zone && !zone_spans_pfn(zone, pfn + i))
+ return 0;
page = pfn_to_page(pfn + i);
if (zone && page_zone(page) != zone)
return 0;
diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c
index e8090f099eb8..ef0dec20c7d8 100644
--- a/net/batman-adv/bat_v_elp.c
+++ b/net/batman-adv/bat_v_elp.c
@@ -104,6 +104,9 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh)

ret = cfg80211_get_station(real_netdev, neigh->addr, &sinfo);

+ /* free the TID stats immediately */
+ cfg80211_sinfo_release_content(&sinfo);
+
dev_put(real_netdev);
if (ret == -ENOENT) {
/* Node is not associated anymore! It would be
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 5e55cef0cec3..6693e209efe8 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -2293,9 +2293,12 @@ static int compat_do_replace(struct net *net, void __user *user,

xt_compat_lock(NFPROTO_BRIDGE);

- ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries);
- if (ret < 0)
- goto out_unlock;
+ if (tmp.nentries) {
+ ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries);
+ if (ret < 0)
+ goto out_unlock;
+ }
+
ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state);
if (ret < 0)
goto out_unlock;
diff --git a/net/core/filter.c b/net/core/filter.c
index 16350f8c8815..821050957aca 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3927,10 +3927,12 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
/* Only some socketops are supported */
switch (optname) {
case SO_RCVBUF:
+ val = min_t(u32, val, sysctl_rmem_max);
sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF);
break;
case SO_SNDBUF:
+ val = min_t(u32, val, sysctl_wmem_max);
sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF);
break;
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 54d854807630..97fc71d90159 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -545,8 +545,8 @@ static void sk_psock_destroy_deferred(struct work_struct *gc)
struct sk_psock *psock = container_of(gc, struct sk_psock, gc);

/* No sk_callback_lock since already detached. */
- if (psock->parser.enabled)
- strp_done(&psock->parser.strp);
+ strp_stop(&psock->parser.strp);
+ strp_done(&psock->parser.strp);

cancel_work_sync(&psock->work);

diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index d7b43e700023..68a21bf75dd0 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -74,6 +74,33 @@ static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi,
return 0;
}

+static int vti_input_ipip(struct sk_buff *skb, int nexthdr, __be32 spi,
+ int encap_type)
+{
+ struct ip_tunnel *tunnel;
+ const struct iphdr *iph = ip_hdr(skb);
+ struct net *net = dev_net(skb->dev);
+ struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
+
+ tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+ iph->saddr, iph->daddr, 0);
+ if (tunnel) {
+ if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+ goto drop;
+
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
+
+ skb->dev = tunnel->dev;
+
+ return xfrm_input(skb, nexthdr, spi, encap_type);
+ }
+
+ return -EINVAL;
+drop:
+ kfree_skb(skb);
+ return 0;
+}
+
static int vti_rcv(struct sk_buff *skb)
{
XFRM_SPI_SKB_CB(skb)->family = AF_INET;
@@ -82,6 +109,14 @@ static int vti_rcv(struct sk_buff *skb)
return vti_input(skb, ip_hdr(skb)->protocol, 0, 0);
}

+static int vti_rcv_ipip(struct sk_buff *skb)
+{
+ XFRM_SPI_SKB_CB(skb)->family = AF_INET;
+ XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
+
+ return vti_input_ipip(skb, ip_hdr(skb)->protocol, ip_hdr(skb)->saddr, 0);
+}
+
static int vti_rcv_cb(struct sk_buff *skb, int err)
{
unsigned short family;
@@ -435,6 +470,12 @@ static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = {
.priority = 100,
};

+static struct xfrm_tunnel ipip_handler __read_mostly = {
+ .handler = vti_rcv_ipip,
+ .err_handler = vti4_err,
+ .priority = 0,
+};
+
static int __net_init vti_init_net(struct net *net)
{
int err;
@@ -603,6 +644,13 @@ static int __init vti_init(void)
if (err < 0)
goto xfrm_proto_comp_failed;

+ msg = "ipip tunnel";
+ err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
+ if (err < 0) {
+ pr_info("%s: cant't register tunnel\n",__func__);
+ goto xfrm_tunnel_failed;
+ }
+
msg = "netlink interface";
err = rtnl_link_register(&vti_link_ops);
if (err < 0)
@@ -612,6 +660,8 @@ static int __init vti_init(void)

rtnl_link_failed:
xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
+xfrm_tunnel_failed:
+ xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
xfrm_proto_comp_failed:
xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
xfrm_proto_ah_failed:
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 432141f04af3..7d6318664eb2 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2220,6 +2220,18 @@ static int ip_vs_set_timeout(struct netns_ipvs *ipvs, struct ip_vs_timeout_user
u->tcp_fin_timeout,
u->udp_timeout);

+#ifdef CONFIG_IP_VS_PROTO_TCP
+ if (u->tcp_timeout < 0 || u->tcp_timeout > (INT_MAX / HZ) ||
+ u->tcp_fin_timeout < 0 || u->tcp_fin_timeout > (INT_MAX / HZ)) {
+ return -EINVAL;
+ }
+#endif
+
+#ifdef CONFIG_IP_VS_PROTO_UDP
+ if (u->udp_timeout < 0 || u->udp_timeout > (INT_MAX / HZ))
+ return -EINVAL;
+#endif
+
#ifdef CONFIG_IP_VS_PROTO_TCP
if (u->tcp_timeout) {
pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP);
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index e92e749aff53..830b1328fe97 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1007,6 +1007,22 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
}

if (nf_ct_key_equal(h, tuple, zone, net)) {
+ /* Tuple is taken already, so caller will need to find
+ * a new source port to use.
+ *
+ * Only exception:
+ * If the *original tuples* are identical, then both
+ * conntracks refer to the same flow.
+ * This is a rare situation, it can occur e.g. when
+ * more than one UDP packet is sent from same socket
+ * in different threads.
+ *
+ * Let nf_ct_resolve_clash() deal with this later.
+ */
+ if (nf_ct_tuple_equal(&ignored_conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
+ &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple))
+ continue;
+
NF_CT_STAT_INC_ATOMIC(net, found);
rcu_read_unlock();
return 1;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 5114a0d2a41e..36d4717fee3b 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -116,6 +116,23 @@ static void nft_trans_destroy(struct nft_trans *trans)
kfree(trans);
}

+static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set)
+{
+ struct net *net = ctx->net;
+ struct nft_trans *trans;
+
+ if (!nft_set_is_anonymous(set))
+ return;
+
+ list_for_each_entry_reverse(trans, &net->nft.commit_list, list) {
+ if (trans->msg_type == NFT_MSG_NEWSET &&
+ nft_trans_set(trans) == set) {
+ nft_trans_set_bound(trans) = true;
+ break;
+ }
+ }
+}
+
static int nf_tables_register_hook(struct net *net,
const struct nft_table *table,
struct nft_chain *chain)
@@ -211,18 +228,6 @@ static int nft_delchain(struct nft_ctx *ctx)
return err;
}

-/* either expr ops provide both activate/deactivate, or neither */
-static bool nft_expr_check_ops(const struct nft_expr_ops *ops)
-{
- if (!ops)
- return true;
-
- if (WARN_ON_ONCE((!ops->activate ^ !ops->deactivate)))
- return false;
-
- return true;
-}
-
static void nft_rule_expr_activate(const struct nft_ctx *ctx,
struct nft_rule *rule)
{
@@ -238,14 +243,15 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx,
}

static void nft_rule_expr_deactivate(const struct nft_ctx *ctx,
- struct nft_rule *rule)
+ struct nft_rule *rule,
+ enum nft_trans_phase phase)
{
struct nft_expr *expr;

expr = nft_expr_first(rule);
while (expr != nft_expr_last(rule) && expr->ops) {
if (expr->ops->deactivate)
- expr->ops->deactivate(ctx, expr);
+ expr->ops->deactivate(ctx, expr, phase);

expr = nft_expr_next(expr);
}
@@ -296,7 +302,7 @@ static int nft_delrule(struct nft_ctx *ctx, struct nft_rule *rule)
nft_trans_destroy(trans);
return err;
}
- nft_rule_expr_deactivate(ctx, rule);
+ nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_PREPARE);

return 0;
}
@@ -1932,9 +1938,6 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk,
*/
int nft_register_expr(struct nft_expr_type *type)
{
- if (!nft_expr_check_ops(type->ops))
- return -EINVAL;
-
nfnl_lock(NFNL_SUBSYS_NFTABLES);
if (type->family == NFPROTO_UNSPEC)
list_add_tail_rcu(&type->list, &nf_tables_expressions);
@@ -2082,10 +2085,6 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx,
err = PTR_ERR(ops);
goto err1;
}
- if (!nft_expr_check_ops(ops)) {
- err = -EINVAL;
- goto err1;
- }
} else
ops = type->ops;

@@ -2482,7 +2481,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
static void nf_tables_rule_release(const struct nft_ctx *ctx,
struct nft_rule *rule)
{
- nft_rule_expr_deactivate(ctx, rule);
+ nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE);
nf_tables_rule_destroy(ctx, rule);
}

@@ -3679,39 +3678,30 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
bind:
binding->chain = ctx->chain;
list_add_tail_rcu(&binding->list, &set->bindings);
+ nft_set_trans_bind(ctx, set);
+
return 0;
}
EXPORT_SYMBOL_GPL(nf_tables_bind_set);

-void nf_tables_rebind_set(const struct nft_ctx *ctx, struct nft_set *set,
- struct nft_set_binding *binding)
-{
- if (list_empty(&set->bindings) && nft_set_is_anonymous(set) &&
- nft_is_active(ctx->net, set))
- list_add_tail_rcu(&set->list, &ctx->table->sets);
-
- list_add_tail_rcu(&binding->list, &set->bindings);
-}
-EXPORT_SYMBOL_GPL(nf_tables_rebind_set);
-
void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
- struct nft_set_binding *binding)
+ struct nft_set_binding *binding, bool event)
{
list_del_rcu(&binding->list);

- if (list_empty(&set->bindings) && nft_set_is_anonymous(set) &&
- nft_is_active(ctx->net, set))
+ if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) {
list_del_rcu(&set->list);
+ if (event)
+ nf_tables_set_notify(ctx, set, NFT_MSG_DELSET,
+ GFP_KERNEL);
+ }
}
EXPORT_SYMBOL_GPL(nf_tables_unbind_set);

void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set)
{
- if (list_empty(&set->bindings) && nft_set_is_anonymous(set) &&
- nft_is_active(ctx->net, set)) {
- nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_ATOMIC);
+ if (list_empty(&set->bindings) && nft_set_is_anonymous(set))
nft_set_destroy(set);
- }
}
EXPORT_SYMBOL_GPL(nf_tables_destroy_set);

@@ -6504,6 +6494,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
nf_tables_rule_notify(&trans->ctx,
nft_trans_rule(trans),
NFT_MSG_DELRULE);
+ nft_rule_expr_deactivate(&trans->ctx,
+ nft_trans_rule(trans),
+ NFT_TRANS_COMMIT);
break;
case NFT_MSG_NEWSET:
nft_clear(net, nft_trans_set(trans));
@@ -6590,7 +6583,8 @@ static void nf_tables_abort_release(struct nft_trans *trans)
nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans));
break;
case NFT_MSG_NEWSET:
- nft_set_destroy(nft_trans_set(trans));
+ if (!nft_trans_set_bound(trans))
+ nft_set_destroy(nft_trans_set(trans));
break;
case NFT_MSG_NEWSETELEM:
nft_set_elem_destroy(nft_trans_elem_set(trans),
@@ -6651,7 +6645,9 @@ static int __nf_tables_abort(struct net *net)
case NFT_MSG_NEWRULE:
trans->ctx.chain->use--;
list_del_rcu(&nft_trans_rule(trans)->list);
- nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans));
+ nft_rule_expr_deactivate(&trans->ctx,
+ nft_trans_rule(trans),
+ NFT_TRANS_ABORT);
break;
case NFT_MSG_DELRULE:
trans->ctx.chain->use++;
@@ -6661,7 +6657,8 @@ static int __nf_tables_abort(struct net *net)
break;
case NFT_MSG_NEWSET:
trans->ctx.table->use--;
- list_del_rcu(&nft_trans_set(trans)->list);
+ if (!nft_trans_set_bound(trans))
+ list_del_rcu(&nft_trans_set(trans)->list);
break;
case NFT_MSG_DELSET:
trans->ctx.table->use++;
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index c90a4640723f..0a4bad55a8aa 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -22,11 +22,15 @@
#include <linux/netfilter_bridge/ebtables.h>
#include <linux/netfilter_arp/arp_tables.h>
#include <net/netfilter/nf_tables.h>
+#include <net/netns/generic.h>

struct nft_xt {
struct list_head head;
struct nft_expr_ops ops;
- unsigned int refcnt;
+ refcount_t refcnt;
+
+ /* used only when transaction mutex is locked */
+ unsigned int listcnt;

/* Unlike other expressions, ops doesn't have static storage duration.
* nft core assumes they do. We use kfree_rcu so that nft core can
@@ -43,10 +47,39 @@ struct nft_xt_match_priv {
void *info;
};

+struct nft_compat_net {
+ struct list_head nft_target_list;
+ struct list_head nft_match_list;
+};
+
+static unsigned int nft_compat_net_id __read_mostly;
+static struct nft_expr_type nft_match_type;
+static struct nft_expr_type nft_target_type;
+
+static struct nft_compat_net *nft_compat_pernet(struct net *net)
+{
+ return net_generic(net, nft_compat_net_id);
+}
+
+static void nft_xt_get(struct nft_xt *xt)
+{
+ /* refcount_inc() warns on 0 -> 1 transition, but we can't
+ * init the reference count to 1 in .select_ops -- we can't
+ * undo such an increase when another expression inside the same
+ * rule fails afterwards.
+ */
+ if (xt->listcnt == 0)
+ refcount_set(&xt->refcnt, 1);
+ else
+ refcount_inc(&xt->refcnt);
+
+ xt->listcnt++;
+}
+
static bool nft_xt_put(struct nft_xt *xt)
{
- if (--xt->refcnt == 0) {
- list_del(&xt->head);
+ if (refcount_dec_and_test(&xt->refcnt)) {
+ WARN_ON_ONCE(!list_empty(&xt->head));
kfree_rcu(xt, rcu_head);
return true;
}
@@ -273,7 +306,7 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
return -EINVAL;

nft_xt = container_of(expr->ops, struct nft_xt, ops);
- nft_xt->refcnt++;
+ nft_xt_get(nft_xt);
return 0;
}

@@ -487,7 +520,7 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
return ret;

nft_xt = container_of(expr->ops, struct nft_xt, ops);
- nft_xt->refcnt++;
+ nft_xt_get(nft_xt);
return 0;
}

@@ -541,6 +574,18 @@ nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
__nft_match_destroy(ctx, expr, nft_expr_priv(expr));
}

+static void nft_compat_deactivate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase)
+{
+ struct nft_xt *xt = container_of(expr->ops, struct nft_xt, ops);
+
+ if (phase == NFT_TRANS_ABORT || phase == NFT_TRANS_COMMIT) {
+ if (--xt->listcnt == 0)
+ list_del_init(&xt->head);
+ }
+}
+
static void
nft_match_large_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
{
@@ -735,10 +780,6 @@ static const struct nfnetlink_subsystem nfnl_compat_subsys = {
.cb = nfnl_nft_compat_cb,
};

-static LIST_HEAD(nft_match_list);
-
-static struct nft_expr_type nft_match_type;
-
static bool nft_match_cmp(const struct xt_match *match,
const char *name, u32 rev, u32 family)
{
@@ -750,6 +791,7 @@ static const struct nft_expr_ops *
nft_match_select_ops(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
+ struct nft_compat_net *cn;
struct nft_xt *nft_match;
struct xt_match *match;
unsigned int matchsize;
@@ -766,8 +808,10 @@ nft_match_select_ops(const struct nft_ctx *ctx,
rev = ntohl(nla_get_be32(tb[NFTA_MATCH_REV]));
family = ctx->family;

+ cn = nft_compat_pernet(ctx->net);
+
/* Re-use the existing match if it's already loaded. */
- list_for_each_entry(nft_match, &nft_match_list, head) {
+ list_for_each_entry(nft_match, &cn->nft_match_list, head) {
struct xt_match *match = nft_match->ops.data;

if (nft_match_cmp(match, mt_name, rev, family))
@@ -790,11 +834,12 @@ nft_match_select_ops(const struct nft_ctx *ctx,
goto err;
}

- nft_match->refcnt = 0;
+ refcount_set(&nft_match->refcnt, 0);
nft_match->ops.type = &nft_match_type;
nft_match->ops.eval = nft_match_eval;
nft_match->ops.init = nft_match_init;
nft_match->ops.destroy = nft_match_destroy;
+ nft_match->ops.deactivate = nft_compat_deactivate;
nft_match->ops.dump = nft_match_dump;
nft_match->ops.validate = nft_match_validate;
nft_match->ops.data = match;
@@ -811,7 +856,8 @@ nft_match_select_ops(const struct nft_ctx *ctx,

nft_match->ops.size = matchsize;

- list_add(&nft_match->head, &nft_match_list);
+ nft_match->listcnt = 0;
+ list_add(&nft_match->head, &cn->nft_match_list);

return &nft_match->ops;
err:
@@ -827,10 +873,6 @@ static struct nft_expr_type nft_match_type __read_mostly = {
.owner = THIS_MODULE,
};

-static LIST_HEAD(nft_target_list);
-
-static struct nft_expr_type nft_target_type;
-
static bool nft_target_cmp(const struct xt_target *tg,
const char *name, u32 rev, u32 family)
{
@@ -842,6 +884,7 @@ static const struct nft_expr_ops *
nft_target_select_ops(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
+ struct nft_compat_net *cn;
struct nft_xt *nft_target;
struct xt_target *target;
char *tg_name;
@@ -862,8 +905,9 @@ nft_target_select_ops(const struct nft_ctx *ctx,
strcmp(tg_name, "standard") == 0)
return ERR_PTR(-EINVAL);

+ cn = nft_compat_pernet(ctx->net);
/* Re-use the existing target if it's already loaded. */
- list_for_each_entry(nft_target, &nft_target_list, head) {
+ list_for_each_entry(nft_target, &cn->nft_target_list, head) {
struct xt_target *target = nft_target->ops.data;

if (!target->target)
@@ -894,11 +938,12 @@ nft_target_select_ops(const struct nft_ctx *ctx,
goto err;
}

- nft_target->refcnt = 0;
+ refcount_set(&nft_target->refcnt, 0);
nft_target->ops.type = &nft_target_type;
nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize));
nft_target->ops.init = nft_target_init;
nft_target->ops.destroy = nft_target_destroy;
+ nft_target->ops.deactivate = nft_compat_deactivate;
nft_target->ops.dump = nft_target_dump;
nft_target->ops.validate = nft_target_validate;
nft_target->ops.data = target;
@@ -908,7 +953,8 @@ nft_target_select_ops(const struct nft_ctx *ctx,
else
nft_target->ops.eval = nft_target_eval_xt;

- list_add(&nft_target->head, &nft_target_list);
+ nft_target->listcnt = 0;
+ list_add(&nft_target->head, &cn->nft_target_list);

return &nft_target->ops;
err:
@@ -924,13 +970,74 @@ static struct nft_expr_type nft_target_type __read_mostly = {
.owner = THIS_MODULE,
};

+static int __net_init nft_compat_init_net(struct net *net)
+{
+ struct nft_compat_net *cn = nft_compat_pernet(net);
+
+ INIT_LIST_HEAD(&cn->nft_target_list);
+ INIT_LIST_HEAD(&cn->nft_match_list);
+
+ return 0;
+}
+
+static void __net_exit nft_compat_exit_net(struct net *net)
+{
+ struct nft_compat_net *cn = nft_compat_pernet(net);
+ struct nft_xt *xt, *next;
+
+ if (list_empty(&cn->nft_match_list) &&
+ list_empty(&cn->nft_target_list))
+ return;
+
+ /* If there was an error that caused nft_xt expr to not be initialized
+ * fully and noone else requested the same expression later, the lists
+ * contain 0-refcount entries that still hold module reference.
+ *
+ * Clean them here.
+ */
+ mutex_lock(&net->nft.commit_mutex);
+ list_for_each_entry_safe(xt, next, &cn->nft_target_list, head) {
+ struct xt_target *target = xt->ops.data;
+
+ list_del_init(&xt->head);
+
+ if (refcount_read(&xt->refcnt))
+ continue;
+ module_put(target->me);
+ kfree(xt);
+ }
+
+ list_for_each_entry_safe(xt, next, &cn->nft_match_list, head) {
+ struct xt_match *match = xt->ops.data;
+
+ list_del_init(&xt->head);
+
+ if (refcount_read(&xt->refcnt))
+ continue;
+ module_put(match->me);
+ kfree(xt);
+ }
+ mutex_unlock(&net->nft.commit_mutex);
+}
+
+static struct pernet_operations nft_compat_net_ops = {
+ .init = nft_compat_init_net,
+ .exit = nft_compat_exit_net,
+ .id = &nft_compat_net_id,
+ .size = sizeof(struct nft_compat_net),
+};
+
static int __init nft_compat_module_init(void)
{
int ret;

+ ret = register_pernet_subsys(&nft_compat_net_ops);
+ if (ret < 0)
+ goto err_target;
+
ret = nft_register_expr(&nft_match_type);
if (ret < 0)
- return ret;
+ goto err_pernet;

ret = nft_register_expr(&nft_target_type);
if (ret < 0)
@@ -943,45 +1050,21 @@ static int __init nft_compat_module_init(void)
}

return ret;
-
err_target:
nft_unregister_expr(&nft_target_type);
err_match:
nft_unregister_expr(&nft_match_type);
+err_pernet:
+ unregister_pernet_subsys(&nft_compat_net_ops);
return ret;
}

static void __exit nft_compat_module_exit(void)
{
- struct nft_xt *xt, *next;
-
- /* list should be empty here, it can be non-empty only in case there
- * was an error that caused nft_xt expr to not be initialized fully
- * and noone else requested the same expression later.
- *
- * In this case, the lists contain 0-refcount entries that still
- * hold module reference.
- */
- list_for_each_entry_safe(xt, next, &nft_target_list, head) {
- struct xt_target *target = xt->ops.data;
-
- if (WARN_ON_ONCE(xt->refcnt))
- continue;
- module_put(target->me);
- kfree(xt);
- }
-
- list_for_each_entry_safe(xt, next, &nft_match_list, head) {
- struct xt_match *match = xt->ops.data;
-
- if (WARN_ON_ONCE(xt->refcnt))
- continue;
- module_put(match->me);
- kfree(xt);
- }
nfnetlink_subsys_unregister(&nfnl_compat_subsys);
nft_unregister_expr(&nft_target_type);
nft_unregister_expr(&nft_match_type);
+ unregister_pernet_subsys(&nft_compat_net_ops);
}

MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFT_COMPAT);
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 07d4efd3d851..f1172f99752b 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -235,20 +235,17 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
return err;
}

-static void nft_dynset_activate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
-{
- struct nft_dynset *priv = nft_expr_priv(expr);
-
- nf_tables_rebind_set(ctx, priv->set, &priv->binding);
-}
-
static void nft_dynset_deactivate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase)
{
struct nft_dynset *priv = nft_expr_priv(expr);

- nf_tables_unbind_set(ctx, priv->set, &priv->binding);
+ if (phase == NFT_TRANS_PREPARE)
+ return;
+
+ nf_tables_unbind_set(ctx, priv->set, &priv->binding,
+ phase == NFT_TRANS_COMMIT);
}

static void nft_dynset_destroy(const struct nft_ctx *ctx,
@@ -296,7 +293,6 @@ static const struct nft_expr_ops nft_dynset_ops = {
.eval = nft_dynset_eval,
.init = nft_dynset_init,
.destroy = nft_dynset_destroy,
- .activate = nft_dynset_activate,
.deactivate = nft_dynset_deactivate,
.dump = nft_dynset_dump,
};
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index 0777a93211e2..3f6d1d2a6281 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -72,10 +72,14 @@ static void nft_immediate_activate(const struct nft_ctx *ctx,
}

static void nft_immediate_deactivate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase)
{
const struct nft_immediate_expr *priv = nft_expr_priv(expr);

+ if (phase == NFT_TRANS_COMMIT)
+ return;
+
return nft_data_release(&priv->data, nft_dreg_to_type(priv->dreg));
}

diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 227b2b15a19c..14496da5141d 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -121,20 +121,17 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
return 0;
}

-static void nft_lookup_activate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
-{
- struct nft_lookup *priv = nft_expr_priv(expr);
-
- nf_tables_rebind_set(ctx, priv->set, &priv->binding);
-}
-
static void nft_lookup_deactivate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase)
{
struct nft_lookup *priv = nft_expr_priv(expr);

- nf_tables_unbind_set(ctx, priv->set, &priv->binding);
+ if (phase == NFT_TRANS_PREPARE)
+ return;
+
+ nf_tables_unbind_set(ctx, priv->set, &priv->binding,
+ phase == NFT_TRANS_COMMIT);
}

static void nft_lookup_destroy(const struct nft_ctx *ctx,
@@ -225,7 +222,6 @@ static const struct nft_expr_ops nft_lookup_ops = {
.size = NFT_EXPR_SIZE(sizeof(struct nft_lookup)),
.eval = nft_lookup_eval,
.init = nft_lookup_init,
- .activate = nft_lookup_activate,
.deactivate = nft_lookup_deactivate,
.destroy = nft_lookup_destroy,
.dump = nft_lookup_dump,
diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c
index a3185ca2a3a9..ae178e914486 100644
--- a/net/netfilter/nft_objref.c
+++ b/net/netfilter/nft_objref.c
@@ -155,20 +155,17 @@ static int nft_objref_map_dump(struct sk_buff *skb, const struct nft_expr *expr)
return -1;
}

-static void nft_objref_map_activate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
-{
- struct nft_objref_map *priv = nft_expr_priv(expr);
-
- nf_tables_rebind_set(ctx, priv->set, &priv->binding);
-}
-
static void nft_objref_map_deactivate(const struct nft_ctx *ctx,
- const struct nft_expr *expr)
+ const struct nft_expr *expr,
+ enum nft_trans_phase phase)
{
struct nft_objref_map *priv = nft_expr_priv(expr);

- nf_tables_unbind_set(ctx, priv->set, &priv->binding);
+ if (phase == NFT_TRANS_PREPARE)
+ return;
+
+ nf_tables_unbind_set(ctx, priv->set, &priv->binding,
+ phase == NFT_TRANS_COMMIT);
}

static void nft_objref_map_destroy(const struct nft_ctx *ctx,
@@ -185,7 +182,6 @@ static const struct nft_expr_ops nft_objref_map_ops = {
.size = NFT_EXPR_SIZE(sizeof(struct nft_objref_map)),
.eval = nft_objref_map_eval,
.init = nft_objref_map_init,
- .activate = nft_objref_map_activate,
.deactivate = nft_objref_map_deactivate,
.destroy = nft_objref_map_destroy,
.dump = nft_objref_map_dump,
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 5d3cce9e8744..15eb5d3d4750 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -75,6 +75,9 @@ static u32 virtio_transport_get_local_cid(void)
{
struct virtio_vsock *vsock = virtio_vsock_get();

+ if (!vsock)
+ return VMADDR_CID_ANY;
+
return vsock->guest_cid;
}

@@ -584,10 +587,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev)

virtio_vsock_update_guest_cid(vsock);

- ret = vsock_core_init(&virtio_transport.transport);
- if (ret < 0)
- goto out_vqs;
-
vsock->rx_buf_nr = 0;
vsock->rx_buf_max_nr = 0;
atomic_set(&vsock->queued_replies, 0);
@@ -618,8 +617,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev)
mutex_unlock(&the_virtio_vsock_mutex);
return 0;

-out_vqs:
- vsock->vdev->config->del_vqs(vsock->vdev);
out:
kfree(vsock);
mutex_unlock(&the_virtio_vsock_mutex);
@@ -637,6 +634,9 @@ static void virtio_vsock_remove(struct virtio_device *vdev)
flush_work(&vsock->event_work);
flush_work(&vsock->send_pkt_work);

+ /* Reset all connected sockets when the device disappear */
+ vsock_for_each_connected_socket(virtio_vsock_reset_sock);
+
vdev->config->reset(vdev);

mutex_lock(&vsock->rx_lock);
@@ -669,7 +669,6 @@ static void virtio_vsock_remove(struct virtio_device *vdev)

mutex_lock(&the_virtio_vsock_mutex);
the_virtio_vsock = NULL;
- vsock_core_exit();
mutex_unlock(&the_virtio_vsock_mutex);

vdev->config->del_vqs(vdev);
@@ -702,14 +701,28 @@ static int __init virtio_vsock_init(void)
virtio_vsock_workqueue = alloc_workqueue("virtio_vsock", 0, 0);
if (!virtio_vsock_workqueue)
return -ENOMEM;
+
ret = register_virtio_driver(&virtio_vsock_driver);
if (ret)
- destroy_workqueue(virtio_vsock_workqueue);
+ goto out_wq;
+
+ ret = vsock_core_init(&virtio_transport.transport);
+ if (ret)
+ goto out_vdr;
+
+ return 0;
+
+out_vdr:
+ unregister_virtio_driver(&virtio_vsock_driver);
+out_wq:
+ destroy_workqueue(virtio_vsock_workqueue);
return ret;
+
}

static void __exit virtio_vsock_exit(void)
{
+ vsock_core_exit();
unregister_virtio_driver(&virtio_vsock_driver);
destroy_workqueue(virtio_vsock_workqueue);
}
diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
index 08c88de0ffda..11975ec8d566 100644
--- a/security/apparmor/domain.c
+++ b/security/apparmor/domain.c
@@ -1444,7 +1444,10 @@ int aa_change_profile(const char *fqname, int flags)
new = aa_label_merge(label, target, GFP_KERNEL);
if (IS_ERR_OR_NULL(new)) {
info = "failed to build target label";
- error = PTR_ERR(new);
+ if (!new)
+ error = -ENOMEM;
+ else
+ error = PTR_ERR(new);
new = NULL;
perms.allow = 0;
goto audit;
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 42446a216f3b..7d1eeb084968 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -1598,12 +1598,14 @@ static unsigned int apparmor_ipv4_postroute(void *priv,
return apparmor_ip_postroute(priv, skb, state);
}

+#if IS_ENABLED(CONFIG_IPV6)
static unsigned int apparmor_ipv6_postroute(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
return apparmor_ip_postroute(priv, skb, state);
}
+#endif

static const struct nf_hook_ops apparmor_nf_ops[] = {
{
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 9988d5c126b6..94094168c4a6 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -439,6 +439,20 @@ static char **parse_bytes(char **argv, const char *name, unsigned char *val,
return argv + i;
}

+/* on per cpu maps we must copy the provided value on all value instances */
+static void fill_per_cpu_value(struct bpf_map_info *info, void *value)
+{
+ unsigned int i, n, step;
+
+ if (!map_is_per_cpu(info->type))
+ return;
+
+ n = get_possible_cpus();
+ step = round_up(info->value_size, 8);
+ for (i = 1; i < n; i++)
+ memcpy(value + i * step, value, info->value_size);
+}
+
static int parse_elem(char **argv, struct bpf_map_info *info,
void *key, void *value, __u32 key_size, __u32 value_size,
__u32 *flags, __u32 **value_fd)
@@ -518,6 +532,8 @@ static int parse_elem(char **argv, struct bpf_map_info *info,
argv = parse_bytes(argv, "value", value, value_size);
if (!argv)
return -1;
+
+ fill_per_cpu_value(info, value);
}

return parse_elem(argv, info, key, NULL, key_size, value_size,
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 69b01a6158bd..91b9de5f4e17 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -130,13 +130,14 @@ static void print_boot_time(__u64 nsecs, char *buf, unsigned int size)

static int prog_fd_by_tag(unsigned char *tag)
{
- struct bpf_prog_info info = {};
- __u32 len = sizeof(info);
unsigned int id = 0;
int err;
int fd;

while (true) {
+ struct bpf_prog_info info = {};
+ __u32 len = sizeof(info);
+
err = bpf_prog_get_next_id(id, &id);
if (err) {
p_err("%s", strerror(errno));
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index a7b4d3f611c5..d8791e0e5f75 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1633,13 +1633,8 @@ static void perf_sample__fprint_metric(struct perf_script *script,
.force_header = false,
};
struct perf_evsel *ev2;
- static bool init;
u64 val;

- if (!init) {
- perf_stat__init_shadow_stats();
- init = true;
- }
if (!evsel->stats)
perf_evlist__alloc_stats(script->session->evlist, false);
if (evsel_script(evsel->leader)->gnum++ == 0)
@@ -1746,7 +1741,7 @@ static void process_event(struct perf_script *script,
return;
}

- if (PRINT_FIELD(TRACE)) {
+ if (PRINT_FIELD(TRACE) && sample->raw_data) {
event_format__fprintf(evsel->tp_format, sample->cpu,
sample->raw_data, sample->raw_size, fp);
}
@@ -2305,6 +2300,8 @@ static int __cmd_script(struct perf_script *script)

signal(SIGINT, sig_handler);

+ perf_stat__init_shadow_stats();
+
/* override event processing functions */
if (script->show_task_events) {
script->tool.comm = process_comm_event;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 835619476370..c108519ddd61 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2424,19 +2424,30 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);

static bool perf_evlist__add_vfs_getname(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname");
+ bool found = false;
+ struct perf_evsel *evsel, *tmp;
+ struct parse_events_error err = { .idx = 0, };
+ int ret = parse_events(evlist, "probe:vfs_getname*", &err);

- if (IS_ERR(evsel))
+ if (ret)
return false;

- if (perf_evsel__field(evsel, "pathname") == NULL) {
+ evlist__for_each_entry_safe(evlist, evsel, tmp) {
+ if (!strstarts(perf_evsel__name(evsel), "probe:vfs_getname"))
+ continue;
+
+ if (perf_evsel__field(evsel, "pathname")) {
+ evsel->handler = trace__vfs_getname;
+ found = true;
+ continue;
+ }
+
+ list_del_init(&evsel->node);
+ evsel->evlist = NULL;
perf_evsel__delete(evsel);
- return false;
}

- evsel->handler = trace__vfs_getname;
- perf_evlist__add(evlist, evsel);
- return true;
+ return found;
}

static struct perf_evsel *perf_evsel__new_pgfault(u64 config)
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 1ccbd3342069..383674f448fc 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -134,7 +134,12 @@ struct cpu_map *cpu_map__new(const char *cpu_list)
if (!cpu_list)
return cpu_map__read_all_cpu_map();

- if (!isdigit(*cpu_list))
+ /*
+ * must handle the case of empty cpumap to cover
+ * TOPOLOGY header for NUMA nodes with no CPU
+ * ( e.g., because of CPU hotplug)
+ */
+ if (!isdigit(*cpu_list) && *cpu_list != '\0')
goto out;

while (isdigit(*cpu_list)) {
@@ -181,8 +186,10 @@ struct cpu_map *cpu_map__new(const char *cpu_list)

if (nr_cpus > 0)
cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
- else
+ else if (*cpu_list != '\0')
cpus = cpu_map__default_new();
+ else
+ cpus = cpu_map__dummy_new();
invalid:
free(tmp_cpus);
out:
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index 1904e7f6ec84..77126a5fa9b6 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -359,8 +359,10 @@ void ordered_events__free(struct ordered_events *oe)
* Current buffer might not have all the events allocated
* yet, we need to free only allocated ones ...
*/
- list_del(&oe->buffer->list);
- ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe);
+ if (oe->buffer) {
+ list_del(&oe->buffer->list);
+ ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe);
+ }

/* ... and continue with the rest */
list_for_each_entry_safe(buffer, tmp, &oe->to_free, list) {
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 63f758c655d5..64d1f36dee99 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -17,6 +17,8 @@ if cc == "clang":
vars[var] = sub("-mcet", "", vars[var])
if not clang_has_option("-fcf-protection"):
vars[var] = sub("-fcf-protection", "", vars[var])
+ if not clang_has_option("-fstack-clash-protection"):
+ vars[var] = sub("-fstack-clash-protection", "", vars[var])

from distutils.core import setup, Extension

diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 66a84d5846c8..03cb8c6d620a 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -87,6 +87,11 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym)
return GELF_ST_TYPE(sym->st_info);
}

+static inline uint8_t elf_sym__visibility(const GElf_Sym *sym)
+{
+ return GELF_ST_VISIBILITY(sym->st_other);
+}
+
#ifndef STT_GNU_IFUNC
#define STT_GNU_IFUNC 10
#endif
@@ -111,7 +116,9 @@ static inline int elf_sym__is_label(const GElf_Sym *sym)
return elf_sym__type(sym) == STT_NOTYPE &&
sym->st_name != 0 &&
sym->st_shndx != SHN_UNDEF &&
- sym->st_shndx != SHN_ABS;
+ sym->st_shndx != SHN_ABS &&
+ elf_sym__visibility(sym) != STV_HIDDEN &&
+ elf_sym__visibility(sym) != STV_INTERNAL;
}

static bool elf_sym__filter(GElf_Sym *sym)
diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h
index 315a44fa32af..84fd6f1bf33e 100644
--- a/tools/testing/selftests/bpf/bpf_util.h
+++ b/tools/testing/selftests/bpf/bpf_util.h
@@ -13,7 +13,7 @@ static inline unsigned int bpf_num_possible_cpus(void)
unsigned int start, end, possible_cpus = 0;
char buff[128];
FILE *fp;
- int n;
+ int len, n, i, j = 0;

fp = fopen(fcpu, "r");
if (!fp) {
@@ -21,17 +21,27 @@ static inline unsigned int bpf_num_possible_cpus(void)
exit(1);
}

- while (fgets(buff, sizeof(buff), fp)) {
- n = sscanf(buff, "%u-%u", &start, &end);
- if (n == 0) {
- printf("Failed to retrieve # possible CPUs!\n");
- exit(1);
- } else if (n == 1) {
- end = start;
+ if (!fgets(buff, sizeof(buff), fp)) {
+ printf("Failed to read %s!\n", fcpu);
+ exit(1);
+ }
+
+ len = strlen(buff);
+ for (i = 0; i <= len; i++) {
+ if (buff[i] == ',' || buff[i] == '\0') {
+ buff[i] = '\0';
+ n = sscanf(&buff[j], "%u-%u", &start, &end);
+ if (n <= 0) {
+ printf("Failed to retrieve # possible CPUs!\n");
+ exit(1);
+ } else if (n == 1) {
+ end = start;
+ }
+ possible_cpus += end - start + 1;
+ j = i + 1;
}
- possible_cpus = start == 0 ? end + 1 : 0;
- break;
}
+
fclose(fp);

return possible_cpus;
diff --git a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh
index bab13dd025a6..0d26b5e3f966 100755
--- a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh
+++ b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh
@@ -37,6 +37,10 @@ prerequisite()
exit $ksft_skip
fi

+ present_cpus=`cat $SYSFS/devices/system/cpu/present`
+ present_max=${present_cpus##*-}
+ echo "present_cpus = $present_cpus present_max = $present_max"
+
echo -e "\t Cpus in online state: $online_cpus"

offline_cpus=`cat $SYSFS/devices/system/cpu/offline`
@@ -151,6 +155,8 @@ online_cpus=0
online_max=0
offline_cpus=0
offline_max=0
+present_cpus=0
+present_max=0

while getopts e:ahp: opt; do
case $opt in
@@ -190,9 +196,10 @@ if [ $allcpus -eq 0 ]; then
online_cpu_expect_success $online_max

if [[ $offline_cpus -gt 0 ]]; then
- echo -e "\t offline to online to offline: cpu $offline_max"
- online_cpu_expect_success $offline_max
- offline_cpu_expect_success $offline_max
+ echo -e "\t offline to online to offline: cpu $present_max"
+ online_cpu_expect_success $present_max
+ offline_cpu_expect_success $present_max
+ online_cpu $present_max
fi
exit 0
else
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 923570a9708a..68e2295e7589 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -19,6 +19,6 @@ TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
KSFT_KHDR_INSTALL := 1
include ../lib.mk

-$(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma
+$(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma
$(OUTPUT)/tcp_mmap: LDFLAGS += -lpthread
$(OUTPUT)/tcp_inq: LDFLAGS += -lpthread
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index 47ed6cef93fb..c9ff2b47bd1c 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -1,6 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
# Makefile for netfilter selftests

-TEST_PROGS := nft_trans_stress.sh
+TEST_PROGS := nft_trans_stress.sh nft_nat.sh

include ../lib.mk
diff --git a/tools/testing/selftests/netfilter/config b/tools/testing/selftests/netfilter/config
index 1017313e41a8..59caa8f71cd8 100644
--- a/tools/testing/selftests/netfilter/config
+++ b/tools/testing/selftests/netfilter/config
@@ -1,2 +1,2 @@
CONFIG_NET_NS=y
-NF_TABLES_INET=y
+CONFIG_NF_TABLES_INET=y
diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh
new file mode 100755
index 000000000000..8ec76681605c
--- /dev/null
+++ b/tools/testing/selftests/netfilter/nft_nat.sh
@@ -0,0 +1,762 @@
+#!/bin/bash
+#
+# This test is for basic NAT functionality: snat, dnat, redirect, masquerade.
+#
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+
+nft --version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without nft tool"
+ exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without ip tool"
+ exit $ksft_skip
+fi
+
+ip netns add ns0
+ip netns add ns1
+ip netns add ns2
+
+ip link add veth0 netns ns0 type veth peer name eth0 netns ns1
+ip link add veth1 netns ns0 type veth peer name eth0 netns ns2
+
+ip -net ns0 link set lo up
+ip -net ns0 link set veth0 up
+ip -net ns0 addr add 10.0.1.1/24 dev veth0
+ip -net ns0 addr add dead:1::1/64 dev veth0
+
+ip -net ns0 link set veth1 up
+ip -net ns0 addr add 10.0.2.1/24 dev veth1
+ip -net ns0 addr add dead:2::1/64 dev veth1
+
+for i in 1 2; do
+ ip -net ns$i link set lo up
+ ip -net ns$i link set eth0 up
+ ip -net ns$i addr add 10.0.$i.99/24 dev eth0
+ ip -net ns$i route add default via 10.0.$i.1
+ ip -net ns$i addr add dead:$i::99/64 dev eth0
+ ip -net ns$i route add default via dead:$i::1
+done
+
+bad_counter()
+{
+ local ns=$1
+ local counter=$2
+ local expect=$3
+
+ echo "ERROR: $counter counter in $ns has unexpected value (expected $expect)" 1>&2
+ ip netns exec $ns nft list counter inet filter $counter 1>&2
+}
+
+check_counters()
+{
+ ns=$1
+ local lret=0
+
+ cnt=$(ip netns exec $ns nft list counter inet filter ns0in | grep -q "packets 1 bytes 84")
+ if [ $? -ne 0 ]; then
+ bad_counter $ns ns0in "packets 1 bytes 84"
+ lret=1
+ fi
+ cnt=$(ip netns exec $ns nft list counter inet filter ns0out | grep -q "packets 1 bytes 84")
+ if [ $? -ne 0 ]; then
+ bad_counter $ns ns0out "packets 1 bytes 84"
+ lret=1
+ fi
+
+ expect="packets 1 bytes 104"
+ cnt=$(ip netns exec $ns nft list counter inet filter ns0in6 | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter $ns ns0in6 "$expect"
+ lret=1
+ fi
+ cnt=$(ip netns exec $ns nft list counter inet filter ns0out6 | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter $ns ns0out6 "$expect"
+ lret=1
+ fi
+
+ return $lret
+}
+
+check_ns0_counters()
+{
+ local ns=$1
+ local lret=0
+
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns0in | grep -q "packets 0 bytes 0")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 ns0in "packets 0 bytes 0"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns0in6 | grep -q "packets 0 bytes 0")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 ns0in6 "packets 0 bytes 0"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns0out | grep -q "packets 0 bytes 0")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 ns0out "packets 0 bytes 0"
+ lret=1
+ fi
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns0out6 | grep -q "packets 0 bytes 0")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 ns0out6 "packets 0 bytes 0"
+ lret=1
+ fi
+
+ for dir in "in" "out" ; do
+ expect="packets 1 bytes 84"
+ cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 $ns$dir "$expect"
+ lret=1
+ fi
+
+ expect="packets 1 bytes 104"
+ cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir}6 | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 $ns$dir6 "$expect"
+ lret=1
+ fi
+ done
+
+ return $lret
+}
+
+reset_counters()
+{
+ for i in 0 1 2;do
+ ip netns exec ns$i nft reset counters inet > /dev/null
+ done
+}
+
+test_local_dnat6()
+{
+ local lret=0
+ip netns exec ns0 nft -f - <<EOF
+table ip6 nat {
+ chain output {
+ type nat hook output priority 0; policy accept;
+ ip6 daddr dead:1::99 dnat to dead:2::99
+ }
+}
+EOF
+ if [ $? -ne 0 ]; then
+ echo "SKIP: Could not add add ip6 dnat hook"
+ return $ksft_skip
+ fi
+
+ # ping netns1, expect rewrite to netns2
+ ip netns exec ns0 ping -q -c 1 dead:1::99 > /dev/null
+ if [ $? -ne 0 ]; then
+ lret=1
+ echo "ERROR: ping6 failed"
+ return $lret
+ fi
+
+ expect="packets 0 bytes 0"
+ for dir in "in6" "out6" ; do
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+
+ expect="packets 1 bytes 104"
+ for dir in "in6" "out6" ; do
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 ns2$dir "$expect"
+ lret=1
+ fi
+ done
+
+ # expect 0 count in ns1
+ expect="packets 0 bytes 0"
+ for dir in "in6" "out6" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns0$dir "$expect"
+ lret=1
+ fi
+ done
+
+ # expect 1 packet in ns2
+ expect="packets 1 bytes 104"
+ for dir in "in6" "out6" ; do
+ cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns0$dir "$expect"
+ lret=1
+ fi
+ done
+
+ test $lret -eq 0 && echo "PASS: ipv6 ping to ns1 was NATted to ns2"
+ ip netns exec ns0 nft flush chain ip6 nat output
+
+ return $lret
+}
+
+test_local_dnat()
+{
+ local lret=0
+ip netns exec ns0 nft -f - <<EOF
+table ip nat {
+ chain output {
+ type nat hook output priority 0; policy accept;
+ ip daddr 10.0.1.99 dnat to 10.0.2.99
+ }
+}
+EOF
+ # ping netns1, expect rewrite to netns2
+ ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null
+ if [ $? -ne 0 ]; then
+ lret=1
+ echo "ERROR: ping failed"
+ return $lret
+ fi
+
+ expect="packets 0 bytes 0"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+
+ expect="packets 1 bytes 84"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 ns2$dir "$expect"
+ lret=1
+ fi
+ done
+
+ # expect 0 count in ns1
+ expect="packets 0 bytes 0"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns0$dir "$expect"
+ lret=1
+ fi
+ done
+
+ # expect 1 packet in ns2
+ expect="packets 1 bytes 84"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns0$dir "$expect"
+ lret=1
+ fi
+ done
+
+ test $lret -eq 0 && echo "PASS: ping to ns1 was NATted to ns2"
+
+ ip netns exec ns0 nft flush chain ip nat output
+
+ reset_counters
+ ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null
+ if [ $? -ne 0 ]; then
+ lret=1
+ echo "ERROR: ping failed"
+ return $lret
+ fi
+
+ expect="packets 1 bytes 84"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+ expect="packets 0 bytes 0"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 ns2$dir "$expect"
+ lret=1
+ fi
+ done
+
+ # expect 1 count in ns1
+ expect="packets 1 bytes 84"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns0 ns0$dir "$expect"
+ lret=1
+ fi
+ done
+
+ # expect 0 packet in ns2
+ expect="packets 0 bytes 0"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns2$dir "$expect"
+ lret=1
+ fi
+ done
+
+ test $lret -eq 0 && echo "PASS: ping to ns1 OK after nat output chain flush"
+
+ return $lret
+}
+
+
+test_masquerade6()
+{
+ local lret=0
+
+ ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
+
+ ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannot ping ns1 from ns2 via ipv6"
+ return 1
+ lret=1
+ fi
+
+ expect="packets 1 bytes 104"
+ for dir in "in6" "out6" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns2$dir "$expect"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+
+ reset_counters
+
+# add masquerading rule
+ip netns exec ns0 nft -f - <<EOF
+table ip6 nat {
+ chain postrouting {
+ type nat hook postrouting priority 0; policy accept;
+ meta oif veth0 masquerade
+ }
+}
+EOF
+ ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerading"
+ lret=1
+ fi
+
+ # ns1 should have seen packets from ns0, due to masquerade
+ expect="packets 1 bytes 104"
+ for dir in "in6" "out6" ; do
+
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns0$dir "$expect"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+
+ # ns1 should not have seen packets from ns2, due to masquerade
+ expect="packets 0 bytes 0"
+ for dir in "in6" "out6" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns0$dir "$expect"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+
+ ip netns exec ns0 nft flush chain ip6 nat postrouting
+ if [ $? -ne 0 ]; then
+ echo "ERROR: Could not flush ip6 nat postrouting" 1>&2
+ lret=1
+ fi
+
+ test $lret -eq 0 && echo "PASS: IPv6 masquerade for ns2"
+
+ return $lret
+}
+
+test_masquerade()
+{
+ local lret=0
+
+ ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
+ ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+
+ ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: canot ping ns1 from ns2"
+ lret=1
+ fi
+
+ expect="packets 1 bytes 84"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns2$dir "$expect"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+
+ reset_counters
+
+# add masquerading rule
+ip netns exec ns0 nft -f - <<EOF
+table ip nat {
+ chain postrouting {
+ type nat hook postrouting priority 0; policy accept;
+ meta oif veth0 masquerade
+ }
+}
+EOF
+ ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannot ping ns1 from ns2 with active ip masquerading"
+ lret=1
+ fi
+
+ # ns1 should have seen packets from ns0, due to masquerade
+ expect="packets 1 bytes 84"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns0$dir "$expect"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+
+ # ns1 should not have seen packets from ns2, due to masquerade
+ expect="packets 0 bytes 0"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns0$dir "$expect"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+
+ ip netns exec ns0 nft flush chain ip nat postrouting
+ if [ $? -ne 0 ]; then
+ echo "ERROR: Could not flush nat postrouting" 1>&2
+ lret=1
+ fi
+
+ test $lret -eq 0 && echo "PASS: IP masquerade for ns2"
+
+ return $lret
+}
+
+test_redirect6()
+{
+ local lret=0
+
+ ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
+
+ ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannnot ping ns1 from ns2 via ipv6"
+ lret=1
+ fi
+
+ expect="packets 1 bytes 104"
+ for dir in "in6" "out6" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns2$dir "$expect"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+
+ reset_counters
+
+# add redirect rule
+ip netns exec ns0 nft -f - <<EOF
+table ip6 nat {
+ chain prerouting {
+ type nat hook prerouting priority 0; policy accept;
+ meta iif veth1 meta l4proto icmpv6 ip6 saddr dead:2::99 ip6 daddr dead:1::99 redirect
+ }
+}
+EOF
+ ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannot ping ns1 from ns2 with active ip6 redirect"
+ lret=1
+ fi
+
+ # ns1 should have seen no packets from ns2, due to redirection
+ expect="packets 0 bytes 0"
+ for dir in "in6" "out6" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns0$dir "$expect"
+ lret=1
+ fi
+ done
+
+ # ns0 should have seen packets from ns2, due to masquerade
+ expect="packets 1 bytes 104"
+ for dir in "in6" "out6" ; do
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns0$dir "$expect"
+ lret=1
+ fi
+ done
+
+ ip netns exec ns0 nft delete table ip6 nat
+ if [ $? -ne 0 ]; then
+ echo "ERROR: Could not delete ip6 nat table" 1>&2
+ lret=1
+ fi
+
+ test $lret -eq 0 && echo "PASS: IPv6 redirection for ns2"
+
+ return $lret
+}
+
+test_redirect()
+{
+ local lret=0
+
+ ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
+ ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+
+ ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannot ping ns1 from ns2"
+ lret=1
+ fi
+
+ expect="packets 1 bytes 84"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns2$dir "$expect"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns2 ns1$dir "$expect"
+ lret=1
+ fi
+ done
+
+ reset_counters
+
+# add redirect rule
+ip netns exec ns0 nft -f - <<EOF
+table ip nat {
+ chain prerouting {
+ type nat hook prerouting priority 0; policy accept;
+ meta iif veth1 ip protocol icmp ip saddr 10.0.2.99 ip daddr 10.0.1.99 redirect
+ }
+}
+EOF
+ ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannot ping ns1 from ns2 with active ip redirect"
+ lret=1
+ fi
+
+ # ns1 should have seen no packets from ns2, due to redirection
+ expect="packets 0 bytes 0"
+ for dir in "in" "out" ; do
+
+ cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns0$dir "$expect"
+ lret=1
+ fi
+ done
+
+ # ns0 should have seen packets from ns2, due to masquerade
+ expect="packets 1 bytes 84"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter ns1 ns0$dir "$expect"
+ lret=1
+ fi
+ done
+
+ ip netns exec ns0 nft delete table ip nat
+ if [ $? -ne 0 ]; then
+ echo "ERROR: Could not delete nat table" 1>&2
+ lret=1
+ fi
+
+ test $lret -eq 0 && echo "PASS: IP redirection for ns2"
+
+ return $lret
+}
+
+
+# ip netns exec ns0 ping -c 1 -q 10.0.$i.99
+for i in 0 1 2; do
+ip netns exec ns$i nft -f - <<EOF
+table inet filter {
+ counter ns0in {}
+ counter ns1in {}
+ counter ns2in {}
+
+ counter ns0out {}
+ counter ns1out {}
+ counter ns2out {}
+
+ counter ns0in6 {}
+ counter ns1in6 {}
+ counter ns2in6 {}
+
+ counter ns0out6 {}
+ counter ns1out6 {}
+ counter ns2out6 {}
+
+ map nsincounter {
+ type ipv4_addr : counter
+ elements = { 10.0.1.1 : "ns0in",
+ 10.0.2.1 : "ns0in",
+ 10.0.1.99 : "ns1in",
+ 10.0.2.99 : "ns2in" }
+ }
+
+ map nsincounter6 {
+ type ipv6_addr : counter
+ elements = { dead:1::1 : "ns0in6",
+ dead:2::1 : "ns0in6",
+ dead:1::99 : "ns1in6",
+ dead:2::99 : "ns2in6" }
+ }
+
+ map nsoutcounter {
+ type ipv4_addr : counter
+ elements = { 10.0.1.1 : "ns0out",
+ 10.0.2.1 : "ns0out",
+ 10.0.1.99: "ns1out",
+ 10.0.2.99: "ns2out" }
+ }
+
+ map nsoutcounter6 {
+ type ipv6_addr : counter
+ elements = { dead:1::1 : "ns0out6",
+ dead:2::1 : "ns0out6",
+ dead:1::99 : "ns1out6",
+ dead:2::99 : "ns2out6" }
+ }
+
+ chain input {
+ type filter hook input priority 0; policy accept;
+ counter name ip saddr map @nsincounter
+ icmpv6 type { "echo-request", "echo-reply" } counter name ip6 saddr map @nsincounter6
+ }
+ chain output {
+ type filter hook output priority 0; policy accept;
+ counter name ip daddr map @nsoutcounter
+ icmpv6 type { "echo-request", "echo-reply" } counter name ip6 daddr map @nsoutcounter6
+ }
+}
+EOF
+done
+
+sleep 3
+# test basic connectivity
+for i in 1 2; do
+ ip netns exec ns0 ping -c 1 -q 10.0.$i.99 > /dev/null
+ if [ $? -ne 0 ];then
+ echo "ERROR: Could not reach other namespace(s)" 1>&2
+ ret=1
+ fi
+
+ ip netns exec ns0 ping -c 1 -q dead:$i::99 > /dev/null
+ if [ $? -ne 0 ];then
+ echo "ERROR: Could not reach other namespace(s) via ipv6" 1>&2
+ ret=1
+ fi
+ check_counters ns$i
+ if [ $? -ne 0 ]; then
+ ret=1
+ fi
+
+ check_ns0_counters ns$i
+ if [ $? -ne 0 ]; then
+ ret=1
+ fi
+ reset_counters
+done
+
+if [ $ret -eq 0 ];then
+ echo "PASS: netns routing/connectivity: ns0 can reach ns1 and ns2"
+fi
+
+reset_counters
+test_local_dnat
+test_local_dnat6
+
+reset_counters
+test_masquerade
+test_masquerade6
+
+reset_counters
+test_redirect
+test_redirect6
+
+for i in 0 1 2; do ip netns del ns$i;done
+
+exit $ret
diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore
index 82121a81681f..29bac5ef9a93 100644
--- a/tools/testing/selftests/proc/.gitignore
+++ b/tools/testing/selftests/proc/.gitignore
@@ -10,4 +10,5 @@
/proc-uptime-002
/read
/self
+/setns-dcache
/thread-self
diff --git a/tools/testing/selftests/proc/Makefile b/tools/testing/selftests/proc/Makefile
index 1c12c34cf85d..434d033ee067 100644
--- a/tools/testing/selftests/proc/Makefile
+++ b/tools/testing/selftests/proc/Makefile
@@ -14,6 +14,7 @@ TEST_GEN_PROGS += proc-uptime-001
TEST_GEN_PROGS += proc-uptime-002
TEST_GEN_PROGS += read
TEST_GEN_PROGS += self
+TEST_GEN_PROGS += setns-dcache
TEST_GEN_PROGS += thread-self

include ../lib.mk
diff --git a/tools/testing/selftests/proc/setns-dcache.c b/tools/testing/selftests/proc/setns-dcache.c
new file mode 100644
index 000000000000..60ab197a73fc
--- /dev/null
+++ b/tools/testing/selftests/proc/setns-dcache.c
@@ -0,0 +1,129 @@
+/*
+ * Copyright © 2019 Alexey Dobriyan <adobriyan@xxxxxxxxx>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+/*
+ * Test that setns(CLONE_NEWNET) points to new /proc/net content even
+ * if old one is in dcache.
+ *
+ * FIXME /proc/net/unix is under CONFIG_UNIX which can be disabled.
+ */
+#undef NDEBUG
+#include <assert.h>
+#include <errno.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+
+static pid_t pid = -1;
+
+static void f(void)
+{
+ if (pid > 0) {
+ kill(pid, SIGTERM);
+ }
+}
+
+int main(void)
+{
+ int fd[2];
+ char _ = 0;
+ int nsfd;
+
+ atexit(f);
+
+ /* Check for priviledges and syscall availability straight away. */
+ if (unshare(CLONE_NEWNET) == -1) {
+ if (errno == ENOSYS || errno == EPERM) {
+ return 4;
+ }
+ return 1;
+ }
+ /* Distinguisher between two otherwise empty net namespaces. */
+ if (socket(AF_UNIX, SOCK_STREAM, 0) == -1) {
+ return 1;
+ }
+
+ if (pipe(fd) == -1) {
+ return 1;
+ }
+
+ pid = fork();
+ if (pid == -1) {
+ return 1;
+ }
+
+ if (pid == 0) {
+ if (unshare(CLONE_NEWNET) == -1) {
+ return 1;
+ }
+
+ if (write(fd[1], &_, 1) != 1) {
+ return 1;
+ }
+
+ pause();
+
+ return 0;
+ }
+
+ if (read(fd[0], &_, 1) != 1) {
+ return 1;
+ }
+
+ {
+ char buf[64];
+ snprintf(buf, sizeof(buf), "/proc/%u/ns/net", pid);
+ nsfd = open(buf, O_RDONLY);
+ if (nsfd == -1) {
+ return 1;
+ }
+ }
+
+ /* Reliably pin dentry into dcache. */
+ (void)open("/proc/net/unix", O_RDONLY);
+
+ if (setns(nsfd, CLONE_NEWNET) == -1) {
+ return 1;
+ }
+
+ kill(pid, SIGTERM);
+ pid = 0;
+
+ {
+ char buf[4096];
+ ssize_t rv;
+ int fd;
+
+ fd = open("/proc/net/unix", O_RDONLY);
+ if (fd == -1) {
+ return 1;
+ }
+
+#define S "Num RefCount Protocol Flags Type St Inode Path\n"
+ rv = read(fd, buf, sizeof(buf));
+
+ assert(rv == strlen(S));
+ assert(memcmp(buf, S, strlen(S)) == 0);
+ }
+
+ return 0;
+}
diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile
index c02683cfb6c9..7656c7ce79d9 100644
--- a/tools/testing/selftests/timers/Makefile
+++ b/tools/testing/selftests/timers/Makefile
@@ -1,6 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
CFLAGS += -O3 -Wl,-no-as-needed -Wall
-LDFLAGS += -lrt -lpthread -lm
+LDLIBS += -lrt -lpthread -lm

# these are all "safe" tests that don't modify
# system time or require escalated privileges