From: Sasha Levin Date: Sat, 22 Apr 2023 01:03:14 +0000 (-0400) Subject: Fixes for 5.15 X-Git-Tag: v4.14.314~82 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=ffd342b95df7cf63fcae78426f017e234b540038;p=thirdparty%2Fkernel%2Fstable-queue.git Fixes for 5.15 Signed-off-by: Sasha Levin --- diff --git a/queue-5.15/arm-dts-rockchip-fix-a-typo-error-for-rk3288-spdif-n.patch b/queue-5.15/arm-dts-rockchip-fix-a-typo-error-for-rk3288-spdif-n.patch new file mode 100644 index 00000000000..8aa55b75d46 --- /dev/null +++ b/queue-5.15/arm-dts-rockchip-fix-a-typo-error-for-rk3288-spdif-n.patch @@ -0,0 +1,37 @@ +From 7ed25226f8623326e19c4249ebc741e9feb06de1 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 8 Feb 2023 17:14:11 +0800 +Subject: ARM: dts: rockchip: fix a typo error for rk3288 spdif node + +From: Jianqun Xu + +[ Upstream commit 02c84f91adb9a64b75ec97d772675c02a3e65ed7 ] + +Fix the address in the spdif node name. + +Fixes: 874e568e500a ("ARM: dts: rockchip: Add SPDIF transceiver for RK3288") +Signed-off-by: Jianqun Xu +Reviewed-by: Sjoerd Simons +Link: https://lore.kernel.org/r/20230208091411.1603142-1-jay.xu@rock-chips.com +Signed-off-by: Heiko Stuebner +Signed-off-by: Sasha Levin +--- + arch/arm/boot/dts/rk3288.dtsi | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi +index 8670c948ca8da..2e6138eeacd15 100644 +--- a/arch/arm/boot/dts/rk3288.dtsi ++++ b/arch/arm/boot/dts/rk3288.dtsi +@@ -940,7 +940,7 @@ + status = "disabled"; + }; + +- spdif: sound@ff88b0000 { ++ spdif: sound@ff8b0000 { + compatible = "rockchip,rk3288-spdif", "rockchip,rk3066-spdif"; + reg = <0x0 0xff8b0000 0x0 0x10000>; + #sound-dai-cells = <0>; +-- +2.39.2 + diff --git a/queue-5.15/arm64-dts-imx8mm-evk-correct-pmic-clock-source.patch b/queue-5.15/arm64-dts-imx8mm-evk-correct-pmic-clock-source.patch new file mode 100644 index 00000000000..81143c70ef8 --- /dev/null +++ b/queue-5.15/arm64-dts-imx8mm-evk-correct-pmic-clock-source.patch @@ -0,0 +1,36 @@ +From 6a9b5ebb3bc7169b61ab24abcdb60e903a65437a Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 27 Mar 2023 18:03:21 +0800 +Subject: arm64: dts: imx8mm-evk: correct pmic clock source + +From: Peng Fan + +[ Upstream commit 85af7ffd24da38e416a14bd6bf207154d94faa83 ] + +The osc_32k supports #clock-cells as 0, using an id is wrong, drop it. + +Fixes: a6a355ede574 ("arm64: dts: imx8mm-evk: Add 32.768 kHz clock to PMIC") +Signed-off-by: Peng Fan +Reviewed-by: Marco Felsch +Signed-off-by: Shawn Guo +Signed-off-by: Sasha Levin +--- + arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi +index e033d0257b5a1..ff5324e94ee82 100644 +--- a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi ++++ b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi +@@ -136,7 +136,7 @@ + rohm,reset-snvs-powered; + + #clock-cells = <0>; +- clocks = <&osc_32k 0>; ++ clocks = <&osc_32k>; + clock-output-names = "clk-32k-out"; + + regulators { +-- +2.39.2 + diff --git a/queue-5.15/arm64-dts-meson-g12-common-specify-full-dmc-range.patch b/queue-5.15/arm64-dts-meson-g12-common-specify-full-dmc-range.patch new file mode 100644 index 00000000000..5f397313222 --- /dev/null +++ b/queue-5.15/arm64-dts-meson-g12-common-specify-full-dmc-range.patch @@ -0,0 +1,44 @@ +From ed51201e1d995b0b72ac41cd3962a38d853016a9 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 27 Mar 2023 14:09:30 +0200 +Subject: arm64: dts: meson-g12-common: specify full DMC range + +From: Marc Gonzalez + +[ Upstream commit aec4353114a408b3a831a22ba34942d05943e462 ] + +According to S905X2 Datasheet - Revision 07: +DRAM Memory Controller (DMC) register area spans ff638000-ff63a000. + +According to DeviceTree Specification - Release v0.4-rc1: +simple-bus nodes do not require reg property. + +Fixes: 1499218c80c99a ("arm64: dts: move common G12A & G12B modes to meson-g12-common.dtsi") +Signed-off-by: Marc Gonzalez +Reviewed-by: Martin Blumenstingl +Link: https://lore.kernel.org/r/20230327120932.2158389-2-mgonzalez@freebox.fr +Signed-off-by: Neil Armstrong +Signed-off-by: Sasha Levin +--- + arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi | 3 +-- + 1 file changed, 1 insertion(+), 2 deletions(-) + +diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi +index 899cfe416aef4..369334076467a 100644 +--- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi ++++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi +@@ -1610,10 +1610,9 @@ + + dmc: bus@38000 { + compatible = "simple-bus"; +- reg = <0x0 0x38000 0x0 0x400>; + #address-cells = <2>; + #size-cells = <2>; +- ranges = <0x0 0x0 0x0 0x38000 0x0 0x400>; ++ ranges = <0x0 0x0 0x0 0x38000 0x0 0x2000>; + + canvas: video-lut@48 { + compatible = "amlogic,canvas"; +-- +2.39.2 + diff --git a/queue-5.15/arm64-dts-qcom-ipq8074-hk01-enable-qmp-device-not-th.patch b/queue-5.15/arm64-dts-qcom-ipq8074-hk01-enable-qmp-device-not-th.patch new file mode 100644 index 00000000000..e8390c153c0 --- /dev/null +++ b/queue-5.15/arm64-dts-qcom-ipq8074-hk01-enable-qmp-device-not-th.patch @@ -0,0 +1,44 @@ +From 64b1597c9c73def55361df49d516fa190b9e9560 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 24 Mar 2023 05:16:50 +0300 +Subject: arm64: dts: qcom: ipq8074-hk01: enable QMP device, not the PHY node + +From: Dmitry Baryshkov + +[ Upstream commit 72630ba422b70ea0874fc90d526353cf71c72488 ] + +Correct PCIe PHY enablement to refer the QMP device nodes rather than +PHY device nodes. QMP nodes have 'status = "disabled"' property in the +ipq8074.dtsi, while PHY nodes do not correspond to the actual device and +do not have the status property. + +Fixes: e8a7fdc505bb ("arm64: dts: ipq8074: qcom: Re-arrange dts nodes based on address") +Signed-off-by: Dmitry Baryshkov +Signed-off-by: Bjorn Andersson +Link: https://lore.kernel.org/r/20230324021651.1799969-1-dmitry.baryshkov@linaro.org +Signed-off-by: Sasha Levin +--- + arch/arm64/boot/dts/qcom/ipq8074-hk01.dts | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/arch/arm64/boot/dts/qcom/ipq8074-hk01.dts b/arch/arm64/boot/dts/qcom/ipq8074-hk01.dts +index cc08dc4eb56a5..68698cdf56c46 100644 +--- a/arch/arm64/boot/dts/qcom/ipq8074-hk01.dts ++++ b/arch/arm64/boot/dts/qcom/ipq8074-hk01.dts +@@ -60,11 +60,11 @@ + perst-gpio = <&tlmm 58 0x1>; + }; + +-&pcie_phy0 { ++&pcie_qmp0 { + status = "okay"; + }; + +-&pcie_phy1 { ++&pcie_qmp1 { + status = "okay"; + }; + +-- +2.39.2 + diff --git a/queue-5.15/bnxt_en-do-not-initialize-ptp-on-older-p3-p4-chips.patch b/queue-5.15/bnxt_en-do-not-initialize-ptp-on-older-p3-p4-chips.patch new file mode 100644 index 00000000000..320691a6ea1 --- /dev/null +++ b/queue-5.15/bnxt_en-do-not-initialize-ptp-on-older-p3-p4-chips.patch @@ -0,0 +1,48 @@ +From e1bf318661065ea1f7a5d64ed25555c33874b6b5 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Sun, 16 Apr 2023 23:58:18 -0700 +Subject: bnxt_en: Do not initialize PTP on older P3/P4 chips + +From: Michael Chan + +[ Upstream commit e8b51a1a15d5a3cce231e0669f6a161dc5bb9b75 ] + +The driver does not support PTP on these older chips and it is assuming +that firmware on these older chips will not return the +PORT_MAC_PTP_QCFG_RESP_FLAGS_HWRM_ACCESS flag in __bnxt_hwrm_ptp_qcfg(), +causing the function to abort quietly. + +But newer firmware now sets this flag and so __bnxt_hwrm_ptp_qcfg() +will proceed further. Eventually it will fail in bnxt_ptp_init() -> +bnxt_map_ptp_regs() because there is no code to support the older chips. +The driver will then complain: + +"PTP initialization failed.\n" + +Fix it so that we abort quietly earlier without going through the +unnecessary steps and alarming the user with the warning log. + +Fixes: ae5c42f0b92c ("bnxt_en: Get PTP hardware capability from firmware") +Signed-off-by: Michael Chan +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c +index 4ef90e0cb8f8e..38fc2286f7cbd 100644 +--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c ++++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c +@@ -7437,7 +7437,7 @@ static int __bnxt_hwrm_ptp_qcfg(struct bnxt *bp) + u8 flags; + int rc; + +- if (bp->hwrm_spec_code < 0x10801) { ++ if (bp->hwrm_spec_code < 0x10801 || !BNXT_CHIP_P5_THOR(bp)) { + rc = -ENODEV; + goto no_ptp; + } +-- +2.39.2 + diff --git a/queue-5.15/bonding-fix-memory-leak-when-changing-bond-type-to-e.patch b/queue-5.15/bonding-fix-memory-leak-when-changing-bond-type-to-e.patch new file mode 100644 index 00000000000..add8979902b --- /dev/null +++ b/queue-5.15/bonding-fix-memory-leak-when-changing-bond-type-to-e.patch @@ -0,0 +1,141 @@ +From 5319215de5e7c1f7f41ebf98533a2542ebb0074f Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 17 Apr 2023 09:12:16 +0300 +Subject: bonding: Fix memory leak when changing bond type to Ethernet + +From: Ido Schimmel + +[ Upstream commit c484fcc058bada604d7e4e5228d4affb646ddbc2 ] + +When a net device is put administratively up, its 'IFF_UP' flag is set +(if not set already) and a 'NETDEV_UP' notification is emitted, which +causes the 8021q driver to add VLAN ID 0 on the device. The reverse +happens when a net device is put administratively down. + +When changing the type of a bond to Ethernet, its 'IFF_UP' flag is +incorrectly cleared, resulting in the kernel skipping the above process +and VLAN ID 0 being leaked [1]. + +Fix by restoring the flag when changing the type to Ethernet, in a +similar fashion to the restoration of the 'IFF_SLAVE' flag. + +The issue can be reproduced using the script in [2], with example out +before and after the fix in [3]. + +[1] +unreferenced object 0xffff888103479900 (size 256): + comm "ip", pid 329, jiffies 4294775225 (age 28.561s) + hex dump (first 32 bytes): + 00 a0 0c 15 81 88 ff ff 00 00 00 00 00 00 00 00 ................ + 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ + backtrace: + [] kmalloc_trace+0x2a/0xe0 + [] vlan_vid_add+0x30c/0x790 + [] vlan_device_event+0x1491/0x21a0 + [] notifier_call_chain+0xbe/0x1f0 + [] call_netdevice_notifiers_info+0xba/0x150 + [] __dev_notify_flags+0x132/0x2e0 + [] dev_change_flags+0x11f/0x180 + [] do_setlink+0xb96/0x4060 + [] __rtnl_newlink+0xc0a/0x18a0 + [] rtnl_newlink+0x6c/0xa0 + [] rtnetlink_rcv_msg+0x43e/0xe00 + [] netlink_rcv_skb+0x170/0x440 + [] netlink_unicast+0x53f/0x810 + [] netlink_sendmsg+0x96b/0xe90 + [] ____sys_sendmsg+0x30f/0xa70 + [] ___sys_sendmsg+0x13a/0x1e0 +unreferenced object 0xffff88810f6a83e0 (size 32): + comm "ip", pid 329, jiffies 4294775225 (age 28.561s) + hex dump (first 32 bytes): + a0 99 47 03 81 88 ff ff a0 99 47 03 81 88 ff ff ..G.......G..... + 81 00 00 00 01 00 00 00 cc cc cc cc cc cc cc cc ................ + backtrace: + [] kmalloc_trace+0x2a/0xe0 + [] vlan_vid_add+0x409/0x790 + [] vlan_device_event+0x1491/0x21a0 + [] notifier_call_chain+0xbe/0x1f0 + [] call_netdevice_notifiers_info+0xba/0x150 + [] __dev_notify_flags+0x132/0x2e0 + [] dev_change_flags+0x11f/0x180 + [] do_setlink+0xb96/0x4060 + [] __rtnl_newlink+0xc0a/0x18a0 + [] rtnl_newlink+0x6c/0xa0 + [] rtnetlink_rcv_msg+0x43e/0xe00 + [] netlink_rcv_skb+0x170/0x440 + [] netlink_unicast+0x53f/0x810 + [] netlink_sendmsg+0x96b/0xe90 + [] ____sys_sendmsg+0x30f/0xa70 + [] ___sys_sendmsg+0x13a/0x1e0 + +[2] +ip link add name t-nlmon type nlmon +ip link add name t-dummy type dummy +ip link add name t-bond type bond mode active-backup + +ip link set dev t-bond up +ip link set dev t-nlmon master t-bond +ip link set dev t-nlmon nomaster +ip link show dev t-bond +ip link set dev t-dummy master t-bond +ip link show dev t-bond + +ip link del dev t-bond +ip link del dev t-dummy +ip link del dev t-nlmon + +[3] +Before: + +12: t-bond: mtu 1500 qdisc noqueue state DOWN mode DEFAULT group default qlen 1000 + link/netlink +12: t-bond: mtu 1500 qdisc noqueue state UP mode DEFAULT group default qlen 1000 + link/ether 46:57:39:a4:46:a2 brd ff:ff:ff:ff:ff:ff + +After: + +12: t-bond: mtu 1500 qdisc noqueue state DOWN mode DEFAULT group default qlen 1000 + link/netlink +12: t-bond: mtu 1500 qdisc noqueue state UP mode DEFAULT group default qlen 1000 + link/ether 66:48:7b:74:b6:8a brd ff:ff:ff:ff:ff:ff + +Fixes: e36b9d16c6a6 ("bonding: clean muticast addresses when device changes type") +Fixes: 75c78500ddad ("bonding: remap muticast addresses without using dev_close() and dev_open()") +Fixes: 9ec7eb60dcbc ("bonding: restore IFF_MASTER/SLAVE flags on bond enslave ether type change") +Reported-by: Mirsad Goran Todorovac +Link: https://lore.kernel.org/netdev/78a8a03b-6070-3e6b-5042-f848dab16fb8@alu.unizg.hr/ +Tested-by: Mirsad Goran Todorovac +Signed-off-by: Ido Schimmel +Acked-by: Jay Vosburgh +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/bonding/bond_main.c | 7 ++++--- + 1 file changed, 4 insertions(+), 3 deletions(-) + +diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c +index e1dc94f01cb5a..2816b6fc17392 100644 +--- a/drivers/net/bonding/bond_main.c ++++ b/drivers/net/bonding/bond_main.c +@@ -1746,14 +1746,15 @@ void bond_lower_state_changed(struct slave *slave) + + /* The bonding driver uses ether_setup() to convert a master bond device + * to ARPHRD_ETHER, that resets the target netdevice's flags so we always +- * have to restore the IFF_MASTER flag, and only restore IFF_SLAVE if it was set ++ * have to restore the IFF_MASTER flag, and only restore IFF_SLAVE and IFF_UP ++ * if they were set + */ + static void bond_ether_setup(struct net_device *bond_dev) + { +- unsigned int slave_flag = bond_dev->flags & IFF_SLAVE; ++ unsigned int flags = bond_dev->flags & (IFF_SLAVE | IFF_UP); + + ether_setup(bond_dev); +- bond_dev->flags |= IFF_MASTER | slave_flag; ++ bond_dev->flags |= IFF_MASTER | flags; + bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING; + } + +-- +2.39.2 + diff --git a/queue-5.15/bpf-fix-incorrect-verifier-pruning-due-to-missing-re.patch b/queue-5.15/bpf-fix-incorrect-verifier-pruning-due-to-missing-re.patch new file mode 100644 index 00000000000..92383d52efc --- /dev/null +++ b/queue-5.15/bpf-fix-incorrect-verifier-pruning-due-to-missing-re.patch @@ -0,0 +1,425 @@ +From ff17592c271f1d1142ec94211bb53575696949be Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 11 Apr 2023 15:24:13 +0000 +Subject: bpf: Fix incorrect verifier pruning due to missing register precision + taints + +From: Daniel Borkmann + +[ Upstream commit 71b547f561247897a0a14f3082730156c0533fed ] + +Juan Jose et al reported an issue found via fuzzing where the verifier's +pruning logic prematurely marks a program path as safe. + +Consider the following program: + + 0: (b7) r6 = 1024 + 1: (b7) r7 = 0 + 2: (b7) r8 = 0 + 3: (b7) r9 = -2147483648 + 4: (97) r6 %= 1025 + 5: (05) goto pc+0 + 6: (bd) if r6 <= r9 goto pc+2 + 7: (97) r6 %= 1 + 8: (b7) r9 = 0 + 9: (bd) if r6 <= r9 goto pc+1 + 10: (b7) r6 = 0 + 11: (b7) r0 = 0 + 12: (63) *(u32 *)(r10 -4) = r0 + 13: (18) r4 = 0xffff888103693400 // map_ptr(ks=4,vs=48) + 15: (bf) r1 = r4 + 16: (bf) r2 = r10 + 17: (07) r2 += -4 + 18: (85) call bpf_map_lookup_elem#1 + 19: (55) if r0 != 0x0 goto pc+1 + 20: (95) exit + 21: (77) r6 >>= 10 + 22: (27) r6 *= 8192 + 23: (bf) r1 = r0 + 24: (0f) r0 += r6 + 25: (79) r3 = *(u64 *)(r0 +0) + 26: (7b) *(u64 *)(r1 +0) = r3 + 27: (95) exit + +The verifier treats this as safe, leading to oob read/write access due +to an incorrect verifier conclusion: + + func#0 @0 + 0: R1=ctx(off=0,imm=0) R10=fp0 + 0: (b7) r6 = 1024 ; R6_w=1024 + 1: (b7) r7 = 0 ; R7_w=0 + 2: (b7) r8 = 0 ; R8_w=0 + 3: (b7) r9 = -2147483648 ; R9_w=-2147483648 + 4: (97) r6 %= 1025 ; R6_w=scalar() + 5: (05) goto pc+0 + 6: (bd) if r6 <= r9 goto pc+2 ; R6_w=scalar(umin=18446744071562067969,var_off=(0xffffffff00000000; 0xffffffff)) R9_w=-2147483648 + 7: (97) r6 %= 1 ; R6_w=scalar() + 8: (b7) r9 = 0 ; R9=0 + 9: (bd) if r6 <= r9 goto pc+1 ; R6=scalar(umin=1) R9=0 + 10: (b7) r6 = 0 ; R6_w=0 + 11: (b7) r0 = 0 ; R0_w=0 + 12: (63) *(u32 *)(r10 -4) = r0 + last_idx 12 first_idx 9 + regs=1 stack=0 before 11: (b7) r0 = 0 + 13: R0_w=0 R10=fp0 fp-8=0000???? + 13: (18) r4 = 0xffff8ad3886c2a00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) + 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) + 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 + 17: (07) r2 += -4 ; R2_w=fp-4 + 18: (85) call bpf_map_lookup_elem#1 ; R0=map_value_or_null(id=1,off=0,ks=4,vs=48,imm=0) + 19: (55) if r0 != 0x0 goto pc+1 ; R0=0 + 20: (95) exit + + from 19 to 21: R0=map_value(off=0,ks=4,vs=48,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 fp-8=mmmm???? + 21: (77) r6 >>= 10 ; R6_w=0 + 22: (27) r6 *= 8192 ; R6_w=0 + 23: (bf) r1 = r0 ; R0=map_value(off=0,ks=4,vs=48,imm=0) R1_w=map_value(off=0,ks=4,vs=48,imm=0) + 24: (0f) r0 += r6 + last_idx 24 first_idx 19 + regs=40 stack=0 before 23: (bf) r1 = r0 + regs=40 stack=0 before 22: (27) r6 *= 8192 + regs=40 stack=0 before 21: (77) r6 >>= 10 + regs=40 stack=0 before 19: (55) if r0 != 0x0 goto pc+1 + parent didn't have regs=40 stack=0 marks: R0_rw=map_value_or_null(id=1,off=0,ks=4,vs=48,imm=0) R6_rw=P0 R7=0 R8=0 R9=0 R10=fp0 fp-8=mmmm???? + last_idx 18 first_idx 9 + regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 + regs=40 stack=0 before 17: (07) r2 += -4 + regs=40 stack=0 before 16: (bf) r2 = r10 + regs=40 stack=0 before 15: (bf) r1 = r4 + regs=40 stack=0 before 13: (18) r4 = 0xffff8ad3886c2a00 + regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 + regs=40 stack=0 before 11: (b7) r0 = 0 + regs=40 stack=0 before 10: (b7) r6 = 0 + 25: (79) r3 = *(u64 *)(r0 +0) ; R0_w=map_value(off=0,ks=4,vs=48,imm=0) R3_w=scalar() + 26: (7b) *(u64 *)(r1 +0) = r3 ; R1_w=map_value(off=0,ks=4,vs=48,imm=0) R3_w=scalar() + 27: (95) exit + + from 9 to 11: R1=ctx(off=0,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 + 11: (b7) r0 = 0 ; R0_w=0 + 12: (63) *(u32 *)(r10 -4) = r0 + last_idx 12 first_idx 11 + regs=1 stack=0 before 11: (b7) r0 = 0 + 13: R0_w=0 R10=fp0 fp-8=0000???? + 13: (18) r4 = 0xffff8ad3886c2a00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) + 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) + 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 + 17: (07) r2 += -4 ; R2_w=fp-4 + 18: (85) call bpf_map_lookup_elem#1 + frame 0: propagating r6 + last_idx 19 first_idx 11 + regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 + regs=40 stack=0 before 17: (07) r2 += -4 + regs=40 stack=0 before 16: (bf) r2 = r10 + regs=40 stack=0 before 15: (bf) r1 = r4 + regs=40 stack=0 before 13: (18) r4 = 0xffff8ad3886c2a00 + regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 + regs=40 stack=0 before 11: (b7) r0 = 0 + parent didn't have regs=40 stack=0 marks: R1=ctx(off=0,imm=0) R6_r=P0 R7=0 R8=0 R9=0 R10=fp0 + last_idx 9 first_idx 9 + regs=40 stack=0 before 9: (bd) if r6 <= r9 goto pc+1 + parent didn't have regs=40 stack=0 marks: R1=ctx(off=0,imm=0) R6_rw=Pscalar() R7_w=0 R8_w=0 R9_rw=0 R10=fp0 + last_idx 8 first_idx 0 + regs=40 stack=0 before 8: (b7) r9 = 0 + regs=40 stack=0 before 7: (97) r6 %= 1 + regs=40 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 + regs=40 stack=0 before 5: (05) goto pc+0 + regs=40 stack=0 before 4: (97) r6 %= 1025 + regs=40 stack=0 before 3: (b7) r9 = -2147483648 + regs=40 stack=0 before 2: (b7) r8 = 0 + regs=40 stack=0 before 1: (b7) r7 = 0 + regs=40 stack=0 before 0: (b7) r6 = 1024 + 19: safe + frame 0: propagating r6 + last_idx 9 first_idx 0 + regs=40 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 + regs=40 stack=0 before 5: (05) goto pc+0 + regs=40 stack=0 before 4: (97) r6 %= 1025 + regs=40 stack=0 before 3: (b7) r9 = -2147483648 + regs=40 stack=0 before 2: (b7) r8 = 0 + regs=40 stack=0 before 1: (b7) r7 = 0 + regs=40 stack=0 before 0: (b7) r6 = 1024 + + from 6 to 9: safe + verification time 110 usec + stack depth 4 + processed 36 insns (limit 1000000) max_states_per_insn 0 total_states 3 peak_states 3 mark_read 2 + +The verifier considers this program as safe by mistakenly pruning unsafe +code paths. In the above func#0, code lines 0-10 are of interest. In line +0-3 registers r6 to r9 are initialized with known scalar values. In line 4 +the register r6 is reset to an unknown scalar given the verifier does not +track modulo operations. Due to this, the verifier can also not determine +precisely which branches in line 6 and 9 are taken, therefore it needs to +explore them both. + +As can be seen, the verifier starts with exploring the false/fall-through +paths first. The 'from 19 to 21' path has both r6=0 and r9=0 and the pointer +arithmetic on r0 += r6 is therefore considered safe. Given the arithmetic, +r6 is correctly marked for precision tracking where backtracking kicks in +where it walks back the current path all the way where r6 was set to 0 in +the fall-through branch. + +Next, the pruning logics pops the path 'from 9 to 11' from the stack. Also +here, the state of the registers is the same, that is, r6=0 and r9=0, so +that at line 19 the path can be pruned as it is considered safe. It is +interesting to note that the conditional in line 9 turned r6 into a more +precise state, that is, in the fall-through path at the beginning of line +10, it is R6=scalar(umin=1), and in the branch-taken path (which is analyzed +here) at the beginning of line 11, r6 turned into a known const r6=0 as +r9=0 prior to that and therefore (unsigned) r6 <= 0 concludes that r6 must +be 0 (**): + + [...] ; R6_w=scalar() + 9: (bd) if r6 <= r9 goto pc+1 ; R6=scalar(umin=1) R9=0 + [...] + + from 9 to 11: R1=ctx(off=0,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 + [...] + +The next path is 'from 6 to 9'. The verifier considers the old and current +state equivalent, and therefore prunes the search incorrectly. Looking into +the two states which are being compared by the pruning logic at line 9, the +old state consists of R6_rwD=Pscalar() R9_rwD=0 R10=fp0 and the new state +consists of R1=ctx(off=0,imm=0) R6_w=scalar(umax=18446744071562067968) +R7_w=0 R8_w=0 R9_w=-2147483648 R10=fp0. While r6 had the reg->precise flag +correctly set in the old state, r9 did not. Both r6'es are considered as +equivalent given the old one is a superset of the current, more precise one, +however, r9's actual values (0 vs 0x80000000) mismatch. Given the old r9 +did not have reg->precise flag set, the verifier does not consider the +register as contributing to the precision state of r6, and therefore it +considered both r9 states as equivalent. However, for this specific pruned +path (which is also the actual path taken at runtime), register r6 will be +0x400 and r9 0x80000000 when reaching line 21, thus oob-accessing the map. + +The purpose of precision tracking is to initially mark registers (including +spilled ones) as imprecise to help verifier's pruning logic finding equivalent +states it can then prune if they don't contribute to the program's safety +aspects. For example, if registers are used for pointer arithmetic or to pass +constant length to a helper, then the verifier sets reg->precise flag and +backtracks the BPF program instruction sequence and chain of verifier states +to ensure that the given register or stack slot including their dependencies +are marked as precisely tracked scalar. This also includes any other registers +and slots that contribute to a tracked state of given registers/stack slot. +This backtracking relies on recorded jmp_history and is able to traverse +entire chain of parent states. This process ends only when all the necessary +registers/slots and their transitive dependencies are marked as precise. + +The backtrack_insn() is called from the current instruction up to the first +instruction, and its purpose is to compute a bitmask of registers and stack +slots that need precision tracking in the parent's verifier state. For example, +if a current instruction is r6 = r7, then r6 needs precision after this +instruction and r7 needs precision before this instruction, that is, in the +parent state. Hence for the latter r7 is marked and r6 unmarked. + +For the class of jmp/jmp32 instructions, backtrack_insn() today only looks +at call and exit instructions and for all other conditionals the masks +remain as-is. However, in the given situation register r6 has a dependency +on r9 (as described above in **), so also that one needs to be marked for +precision tracking. In other words, if an imprecise register influences a +precise one, then the imprecise register should also be marked precise. +Meaning, in the parent state both dest and src register need to be tracked +for precision and therefore the marking must be more conservative by setting +reg->precise flag for both. The precision propagation needs to cover both +for the conditional: if the src reg was marked but not the dst reg and vice +versa. + +After the fix the program is correctly rejected: + + func#0 @0 + 0: R1=ctx(off=0,imm=0) R10=fp0 + 0: (b7) r6 = 1024 ; R6_w=1024 + 1: (b7) r7 = 0 ; R7_w=0 + 2: (b7) r8 = 0 ; R8_w=0 + 3: (b7) r9 = -2147483648 ; R9_w=-2147483648 + 4: (97) r6 %= 1025 ; R6_w=scalar() + 5: (05) goto pc+0 + 6: (bd) if r6 <= r9 goto pc+2 ; R6_w=scalar(umin=18446744071562067969,var_off=(0xffffffff80000000; 0x7fffffff),u32_min=-2147483648) R9_w=-2147483648 + 7: (97) r6 %= 1 ; R6_w=scalar() + 8: (b7) r9 = 0 ; R9=0 + 9: (bd) if r6 <= r9 goto pc+1 ; R6=scalar(umin=1) R9=0 + 10: (b7) r6 = 0 ; R6_w=0 + 11: (b7) r0 = 0 ; R0_w=0 + 12: (63) *(u32 *)(r10 -4) = r0 + last_idx 12 first_idx 9 + regs=1 stack=0 before 11: (b7) r0 = 0 + 13: R0_w=0 R10=fp0 fp-8=0000???? + 13: (18) r4 = 0xffff9290dc5bfe00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) + 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) + 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 + 17: (07) r2 += -4 ; R2_w=fp-4 + 18: (85) call bpf_map_lookup_elem#1 ; R0=map_value_or_null(id=1,off=0,ks=4,vs=48,imm=0) + 19: (55) if r0 != 0x0 goto pc+1 ; R0=0 + 20: (95) exit + + from 19 to 21: R0=map_value(off=0,ks=4,vs=48,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 fp-8=mmmm???? + 21: (77) r6 >>= 10 ; R6_w=0 + 22: (27) r6 *= 8192 ; R6_w=0 + 23: (bf) r1 = r0 ; R0=map_value(off=0,ks=4,vs=48,imm=0) R1_w=map_value(off=0,ks=4,vs=48,imm=0) + 24: (0f) r0 += r6 + last_idx 24 first_idx 19 + regs=40 stack=0 before 23: (bf) r1 = r0 + regs=40 stack=0 before 22: (27) r6 *= 8192 + regs=40 stack=0 before 21: (77) r6 >>= 10 + regs=40 stack=0 before 19: (55) if r0 != 0x0 goto pc+1 + parent didn't have regs=40 stack=0 marks: R0_rw=map_value_or_null(id=1,off=0,ks=4,vs=48,imm=0) R6_rw=P0 R7=0 R8=0 R9=0 R10=fp0 fp-8=mmmm???? + last_idx 18 first_idx 9 + regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 + regs=40 stack=0 before 17: (07) r2 += -4 + regs=40 stack=0 before 16: (bf) r2 = r10 + regs=40 stack=0 before 15: (bf) r1 = r4 + regs=40 stack=0 before 13: (18) r4 = 0xffff9290dc5bfe00 + regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 + regs=40 stack=0 before 11: (b7) r0 = 0 + regs=40 stack=0 before 10: (b7) r6 = 0 + 25: (79) r3 = *(u64 *)(r0 +0) ; R0_w=map_value(off=0,ks=4,vs=48,imm=0) R3_w=scalar() + 26: (7b) *(u64 *)(r1 +0) = r3 ; R1_w=map_value(off=0,ks=4,vs=48,imm=0) R3_w=scalar() + 27: (95) exit + + from 9 to 11: R1=ctx(off=0,imm=0) R6=0 R7=0 R8=0 R9=0 R10=fp0 + 11: (b7) r0 = 0 ; R0_w=0 + 12: (63) *(u32 *)(r10 -4) = r0 + last_idx 12 first_idx 11 + regs=1 stack=0 before 11: (b7) r0 = 0 + 13: R0_w=0 R10=fp0 fp-8=0000???? + 13: (18) r4 = 0xffff9290dc5bfe00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) + 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) + 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 + 17: (07) r2 += -4 ; R2_w=fp-4 + 18: (85) call bpf_map_lookup_elem#1 + frame 0: propagating r6 + last_idx 19 first_idx 11 + regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 + regs=40 stack=0 before 17: (07) r2 += -4 + regs=40 stack=0 before 16: (bf) r2 = r10 + regs=40 stack=0 before 15: (bf) r1 = r4 + regs=40 stack=0 before 13: (18) r4 = 0xffff9290dc5bfe00 + regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 + regs=40 stack=0 before 11: (b7) r0 = 0 + parent didn't have regs=40 stack=0 marks: R1=ctx(off=0,imm=0) R6_r=P0 R7=0 R8=0 R9=0 R10=fp0 + last_idx 9 first_idx 9 + regs=40 stack=0 before 9: (bd) if r6 <= r9 goto pc+1 + parent didn't have regs=240 stack=0 marks: R1=ctx(off=0,imm=0) R6_rw=Pscalar() R7_w=0 R8_w=0 R9_rw=P0 R10=fp0 + last_idx 8 first_idx 0 + regs=240 stack=0 before 8: (b7) r9 = 0 + regs=40 stack=0 before 7: (97) r6 %= 1 + regs=40 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 + regs=240 stack=0 before 5: (05) goto pc+0 + regs=240 stack=0 before 4: (97) r6 %= 1025 + regs=240 stack=0 before 3: (b7) r9 = -2147483648 + regs=40 stack=0 before 2: (b7) r8 = 0 + regs=40 stack=0 before 1: (b7) r7 = 0 + regs=40 stack=0 before 0: (b7) r6 = 1024 + 19: safe + + from 6 to 9: R1=ctx(off=0,imm=0) R6_w=scalar(umax=18446744071562067968) R7_w=0 R8_w=0 R9_w=-2147483648 R10=fp0 + 9: (bd) if r6 <= r9 goto pc+1 + last_idx 9 first_idx 0 + regs=40 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 + regs=240 stack=0 before 5: (05) goto pc+0 + regs=240 stack=0 before 4: (97) r6 %= 1025 + regs=240 stack=0 before 3: (b7) r9 = -2147483648 + regs=40 stack=0 before 2: (b7) r8 = 0 + regs=40 stack=0 before 1: (b7) r7 = 0 + regs=40 stack=0 before 0: (b7) r6 = 1024 + last_idx 9 first_idx 0 + regs=200 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 + regs=240 stack=0 before 5: (05) goto pc+0 + regs=240 stack=0 before 4: (97) r6 %= 1025 + regs=240 stack=0 before 3: (b7) r9 = -2147483648 + regs=40 stack=0 before 2: (b7) r8 = 0 + regs=40 stack=0 before 1: (b7) r7 = 0 + regs=40 stack=0 before 0: (b7) r6 = 1024 + 11: R6=scalar(umax=18446744071562067968) R9=-2147483648 + 11: (b7) r0 = 0 ; R0_w=0 + 12: (63) *(u32 *)(r10 -4) = r0 + last_idx 12 first_idx 11 + regs=1 stack=0 before 11: (b7) r0 = 0 + 13: R0_w=0 R10=fp0 fp-8=0000???? + 13: (18) r4 = 0xffff9290dc5bfe00 ; R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) + 15: (bf) r1 = r4 ; R1_w=map_ptr(off=0,ks=4,vs=48,imm=0) R4_w=map_ptr(off=0,ks=4,vs=48,imm=0) + 16: (bf) r2 = r10 ; R2_w=fp0 R10=fp0 + 17: (07) r2 += -4 ; R2_w=fp-4 + 18: (85) call bpf_map_lookup_elem#1 ; R0_w=map_value_or_null(id=3,off=0,ks=4,vs=48,imm=0) + 19: (55) if r0 != 0x0 goto pc+1 ; R0_w=0 + 20: (95) exit + + from 19 to 21: R0=map_value(off=0,ks=4,vs=48,imm=0) R6=scalar(umax=18446744071562067968) R7=0 R8=0 R9=-2147483648 R10=fp0 fp-8=mmmm???? + 21: (77) r6 >>= 10 ; R6_w=scalar(umax=18014398507384832,var_off=(0x0; 0x3fffffffffffff)) + 22: (27) r6 *= 8192 ; R6_w=scalar(smax=9223372036854767616,umax=18446744073709543424,var_off=(0x0; 0xffffffffffffe000),s32_max=2147475456,u32_max=-8192) + 23: (bf) r1 = r0 ; R0=map_value(off=0,ks=4,vs=48,imm=0) R1_w=map_value(off=0,ks=4,vs=48,imm=0) + 24: (0f) r0 += r6 + last_idx 24 first_idx 21 + regs=40 stack=0 before 23: (bf) r1 = r0 + regs=40 stack=0 before 22: (27) r6 *= 8192 + regs=40 stack=0 before 21: (77) r6 >>= 10 + parent didn't have regs=40 stack=0 marks: R0_rw=map_value(off=0,ks=4,vs=48,imm=0) R6_r=Pscalar(umax=18446744071562067968) R7=0 R8=0 R9=-2147483648 R10=fp0 fp-8=mmmm???? + last_idx 19 first_idx 11 + regs=40 stack=0 before 19: (55) if r0 != 0x0 goto pc+1 + regs=40 stack=0 before 18: (85) call bpf_map_lookup_elem#1 + regs=40 stack=0 before 17: (07) r2 += -4 + regs=40 stack=0 before 16: (bf) r2 = r10 + regs=40 stack=0 before 15: (bf) r1 = r4 + regs=40 stack=0 before 13: (18) r4 = 0xffff9290dc5bfe00 + regs=40 stack=0 before 12: (63) *(u32 *)(r10 -4) = r0 + regs=40 stack=0 before 11: (b7) r0 = 0 + parent didn't have regs=40 stack=0 marks: R1=ctx(off=0,imm=0) R6_rw=Pscalar(umax=18446744071562067968) R7_w=0 R8_w=0 R9_w=-2147483648 R10=fp0 + last_idx 9 first_idx 0 + regs=40 stack=0 before 9: (bd) if r6 <= r9 goto pc+1 + regs=240 stack=0 before 6: (bd) if r6 <= r9 goto pc+2 + regs=240 stack=0 before 5: (05) goto pc+0 + regs=240 stack=0 before 4: (97) r6 %= 1025 + regs=240 stack=0 before 3: (b7) r9 = -2147483648 + regs=40 stack=0 before 2: (b7) r8 = 0 + regs=40 stack=0 before 1: (b7) r7 = 0 + regs=40 stack=0 before 0: (b7) r6 = 1024 + math between map_value pointer and register with unbounded min value is not allowed + verification time 886 usec + stack depth 4 + processed 49 insns (limit 1000000) max_states_per_insn 1 total_states 5 peak_states 5 mark_read 2 + +Fixes: b5dc0163d8fd ("bpf: precise scalar_value tracking") +Reported-by: Juan Jose Lopez Jaimez +Reported-by: Meador Inge +Reported-by: Simon Scannell +Reported-by: Nenad Stojanovski +Signed-off-by: Daniel Borkmann +Co-developed-by: Andrii Nakryiko +Signed-off-by: Andrii Nakryiko +Reviewed-by: John Fastabend +Reviewed-by: Juan Jose Lopez Jaimez +Reviewed-by: Meador Inge +Reviewed-by: Simon Scannell +Signed-off-by: Sasha Levin +--- + kernel/bpf/verifier.c | 15 +++++++++++++++ + 1 file changed, 15 insertions(+) + +diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c +index 1c95d97e7aa53..37d4b5f5ec0c3 100644 +--- a/kernel/bpf/verifier.c ++++ b/kernel/bpf/verifier.c +@@ -2279,6 +2279,21 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, + } + } else if (opcode == BPF_EXIT) { + return -ENOTSUPP; ++ } else if (BPF_SRC(insn->code) == BPF_X) { ++ if (!(*reg_mask & (dreg | sreg))) ++ return 0; ++ /* dreg sreg ++ * Both dreg and sreg need precision before ++ * this insn. If only sreg was marked precise ++ * before it would be equally necessary to ++ * propagate it to dreg. ++ */ ++ *reg_mask |= (sreg | dreg); ++ /* else dreg K ++ * Only dreg still needs precision before ++ * this insn, so for the K-based conditional ++ * there is nothing new to be marked. ++ */ + } + } else if (class == BPF_LD) { + if (!(*reg_mask & dreg)) +-- +2.39.2 + diff --git a/queue-5.15/e1000e-disable-tso-on-i219-lm-card-to-increase-speed.patch b/queue-5.15/e1000e-disable-tso-on-i219-lm-card-to-increase-speed.patch new file mode 100644 index 00000000000..8894a7cc0fd --- /dev/null +++ b/queue-5.15/e1000e-disable-tso-on-i219-lm-card-to-increase-speed.patch @@ -0,0 +1,100 @@ +From 72a8cf5c8725399007ee64023dbe6a033bef9719 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 17 Apr 2023 13:53:45 -0700 +Subject: e1000e: Disable TSO on i219-LM card to increase speed + +From: Sebastian Basierski + +[ Upstream commit 67d47b95119ad589b0a0b16b88b1dd9a04061ced ] + +While using i219-LM card currently it was only possible to achieve +about 60% of maximum speed due to regression introduced in Linux 5.8. +This was caused by TSO not being disabled by default despite commit +f29801030ac6 ("e1000e: Disable TSO for buffer overrun workaround"). +Fix that by disabling TSO during driver probe. + +Fixes: f29801030ac6 ("e1000e: Disable TSO for buffer overrun workaround") +Signed-off-by: Sebastian Basierski +Signed-off-by: Mateusz Palczewski +Tested-by: Naama Meir +Signed-off-by: Tony Nguyen +Reviewed-by: Simon Horman +Link: https://lore.kernel.org/r/20230417205345.1030801-1-anthony.l.nguyen@intel.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/e1000e/netdev.c | 51 +++++++++++----------- + 1 file changed, 26 insertions(+), 25 deletions(-) + +diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c +index 7e41ce188cc6a..6b7d162af3e5e 100644 +--- a/drivers/net/ethernet/intel/e1000e/netdev.c ++++ b/drivers/net/ethernet/intel/e1000e/netdev.c +@@ -5298,31 +5298,6 @@ static void e1000_watchdog_task(struct work_struct *work) + ew32(TARC(0), tarc0); + } + +- /* disable TSO for pcie and 10/100 speeds, to avoid +- * some hardware issues +- */ +- if (!(adapter->flags & FLAG_TSO_FORCE)) { +- switch (adapter->link_speed) { +- case SPEED_10: +- case SPEED_100: +- e_info("10/100 speed: disabling TSO\n"); +- netdev->features &= ~NETIF_F_TSO; +- netdev->features &= ~NETIF_F_TSO6; +- break; +- case SPEED_1000: +- netdev->features |= NETIF_F_TSO; +- netdev->features |= NETIF_F_TSO6; +- break; +- default: +- /* oops */ +- break; +- } +- if (hw->mac.type == e1000_pch_spt) { +- netdev->features &= ~NETIF_F_TSO; +- netdev->features &= ~NETIF_F_TSO6; +- } +- } +- + /* enable transmits in the hardware, need to do this + * after setting TARC(0) + */ +@@ -7543,6 +7518,32 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) + NETIF_F_RXCSUM | + NETIF_F_HW_CSUM); + ++ /* disable TSO for pcie and 10/100 speeds to avoid ++ * some hardware issues and for i219 to fix transfer ++ * speed being capped at 60% ++ */ ++ if (!(adapter->flags & FLAG_TSO_FORCE)) { ++ switch (adapter->link_speed) { ++ case SPEED_10: ++ case SPEED_100: ++ e_info("10/100 speed: disabling TSO\n"); ++ netdev->features &= ~NETIF_F_TSO; ++ netdev->features &= ~NETIF_F_TSO6; ++ break; ++ case SPEED_1000: ++ netdev->features |= NETIF_F_TSO; ++ netdev->features |= NETIF_F_TSO6; ++ break; ++ default: ++ /* oops */ ++ break; ++ } ++ if (hw->mac.type == e1000_pch_spt) { ++ netdev->features &= ~NETIF_F_TSO; ++ netdev->features &= ~NETIF_F_TSO6; ++ } ++ } ++ + /* Set user-changeable features (subset of all device features) */ + netdev->hw_features = netdev->features; + netdev->hw_features |= NETIF_F_RXFCS; +-- +2.39.2 + diff --git a/queue-5.15/f2fs-fix-f2fs_truncate_partial_nodes-ftrace-event.patch b/queue-5.15/f2fs-fix-f2fs_truncate_partial_nodes-ftrace-event.patch new file mode 100644 index 00000000000..ed3210b4890 --- /dev/null +++ b/queue-5.15/f2fs-fix-f2fs_truncate_partial_nodes-ftrace-event.patch @@ -0,0 +1,47 @@ +From 6cbcd3800857b5e73a98275794a04aea4511e578 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 6 Mar 2023 12:25:49 +0000 +Subject: f2fs: Fix f2fs_truncate_partial_nodes ftrace event + +From: Douglas Raillard + +[ Upstream commit 0b04d4c0542e8573a837b1d81b94209e48723b25 ] + +Fix the nid_t field so that its size is correctly reported in the text +format embedded in trace.dat files. As it stands, it is reported as +being of size 4: + + field:nid_t nid[3]; offset:24; size:4; signed:0; + +Instead of 12: + + field:nid_t nid[3]; offset:24; size:12; signed:0; + +This also fixes the reported offset of subsequent fields so that they +match with the actual struct layout. + +Signed-off-by: Douglas Raillard +Reviewed-by: Mukesh Ojha +Reviewed-by: Chao Yu +Signed-off-by: Jaegeuk Kim +Signed-off-by: Sasha Levin +--- + include/trace/events/f2fs.h | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h +index 4cb055af1ec0b..f5dcf7c9b7076 100644 +--- a/include/trace/events/f2fs.h ++++ b/include/trace/events/f2fs.h +@@ -513,7 +513,7 @@ TRACE_EVENT(f2fs_truncate_partial_nodes, + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) +- __field(nid_t, nid[3]) ++ __array(nid_t, nid, 3) + __field(int, depth) + __field(int, err) + ), +-- +2.39.2 + diff --git a/queue-5.15/i40e-fix-accessing-vsi-active_filters-without-holdin.patch b/queue-5.15/i40e-fix-accessing-vsi-active_filters-without-holdin.patch new file mode 100644 index 00000000000..8d84f241d24 --- /dev/null +++ b/queue-5.15/i40e-fix-accessing-vsi-active_filters-without-holdin.patch @@ -0,0 +1,49 @@ +From 11c5823aa3beb0ed5461f915cb9dbe7a571a5321 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 24 Mar 2023 18:16:38 +0100 +Subject: i40e: fix accessing vsi->active_filters without holding lock + +From: Aleksandr Loktionov + +[ Upstream commit 8485d093b076e59baff424552e8aecfc5bd2d261 ] + +Fix accessing vsi->active_filters without holding the mac_filter_hash_lock. +Move vsi->active_filters = 0 inside critical section and +move clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state) after the critical +section to ensure the new filters from other threads can be added only after +filters cleaning in the critical section is finished. + +Fixes: 278e7d0b9d68 ("i40e: store MAC/VLAN filters in a hash with the MAC Address as key") +Signed-off-by: Aleksandr Loktionov +Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) +Signed-off-by: Tony Nguyen +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/i40e/i40e_main.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c +index 85d48efce1d00..cafbabc687565 100644 +--- a/drivers/net/ethernet/intel/i40e/i40e_main.c ++++ b/drivers/net/ethernet/intel/i40e/i40e_main.c +@@ -13945,15 +13945,15 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) + vsi->id = ctxt.vsi_number; + } + +- vsi->active_filters = 0; +- clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); + spin_lock_bh(&vsi->mac_filter_hash_lock); ++ vsi->active_filters = 0; + /* If macvlan filters already exist, force them to get loaded */ + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { + f->state = I40E_FILTER_NEW; + f_count++; + } + spin_unlock_bh(&vsi->mac_filter_hash_lock); ++ clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); + + if (f_count) { + vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; +-- +2.39.2 + diff --git a/queue-5.15/i40e-fix-i40e_setup_misc_vector-error-handling.patch b/queue-5.15/i40e-fix-i40e_setup_misc_vector-error-handling.patch new file mode 100644 index 00000000000..b128e79611d --- /dev/null +++ b/queue-5.15/i40e-fix-i40e_setup_misc_vector-error-handling.patch @@ -0,0 +1,43 @@ +From c456a4369de28e324a178fd24759fd13f40223b4 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 3 Apr 2023 07:13:18 +0200 +Subject: i40e: fix i40e_setup_misc_vector() error handling + +From: Aleksandr Loktionov + +[ Upstream commit c86c00c6935505929cc9adb29ddb85e48c71f828 ] + +Add error handling of i40e_setup_misc_vector() in i40e_rebuild(). +In case interrupt vectors setup fails do not re-open vsi-s and +do not bring up vf-s, we have no interrupts to serve a traffic +anyway. + +Fixes: 41c445ff0f48 ("i40e: main driver core") +Signed-off-by: Aleksandr Loktionov +Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) +Signed-off-by: Tony Nguyen +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/i40e/i40e_main.c | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c +index cafbabc687565..3ebd589e56b5b 100644 +--- a/drivers/net/ethernet/intel/i40e/i40e_main.c ++++ b/drivers/net/ethernet/intel/i40e/i40e_main.c +@@ -10923,8 +10923,11 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) + pf->hw.aq.asq_last_status)); + } + /* reinit the misc interrupt */ +- if (pf->flags & I40E_FLAG_MSIX_ENABLED) ++ if (pf->flags & I40E_FLAG_MSIX_ENABLED) { + ret = i40e_setup_misc_vector(pf); ++ if (ret) ++ goto end_unlock; ++ } + + /* Add a filter to drop all Flow control frames from any VSI from being + * transmitted. By doing so we stop a malicious VF from sending out +-- +2.39.2 + diff --git a/queue-5.15/input-i8042-add-quirk-for-fujitsu-lifebook-a574-h.patch b/queue-5.15/input-i8042-add-quirk-for-fujitsu-lifebook-a574-h.patch new file mode 100644 index 00000000000..8d92cad1238 --- /dev/null +++ b/queue-5.15/input-i8042-add-quirk-for-fujitsu-lifebook-a574-h.patch @@ -0,0 +1,43 @@ +From 8cec3dc672450479c92653d482b147a662bf9ba5 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 17 Mar 2023 03:19:51 -0700 +Subject: Input: i8042 - add quirk for Fujitsu Lifebook A574/H + +From: Jonathan Denose + +[ Upstream commit f5bad62f9107b701a6def7cac1f5f65862219b83 ] + +Fujitsu Lifebook A574/H requires the nomux option to properly +probe the touchpad, especially when waking from sleep. + +Signed-off-by: Jonathan Denose +Reviewed-by: Hans de Goede +Link: https://lore.kernel.org/r/20230303152623.45859-1-jdenose@google.com +Signed-off-by: Dmitry Torokhov +Signed-off-by: Sasha Levin +--- + drivers/input/serio/i8042-x86ia64io.h | 8 ++++++++ + 1 file changed, 8 insertions(+) + +diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h +index 239c777f8271c..339e765bcf5ae 100644 +--- a/drivers/input/serio/i8042-x86ia64io.h ++++ b/drivers/input/serio/i8042-x86ia64io.h +@@ -601,6 +601,14 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX) + }, ++ { ++ /* Fujitsu Lifebook A574/H */ ++ .matches = { ++ DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), ++ DMI_MATCH(DMI_PRODUCT_NAME, "FMVA0501PZ"), ++ }, ++ .driver_data = (void *)(SERIO_QUIRK_NOMUX) ++ }, + { + /* Gigabyte M912 */ + .matches = { +-- +2.39.2 + diff --git a/queue-5.15/mlxfw-fix-null-ptr-deref-in-mlxfw_mfa2_tlv_next.patch b/queue-5.15/mlxfw-fix-null-ptr-deref-in-mlxfw_mfa2_tlv_next.patch new file mode 100644 index 00000000000..e05bdee4c2c --- /dev/null +++ b/queue-5.15/mlxfw-fix-null-ptr-deref-in-mlxfw_mfa2_tlv_next.patch @@ -0,0 +1,45 @@ +From 9d0b3684b07e7ee673a4a2835ceb4aa3c49ed2bf Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 17 Apr 2023 05:07:18 -0700 +Subject: mlxfw: fix null-ptr-deref in mlxfw_mfa2_tlv_next() + +From: Nikita Zhandarovich + +[ Upstream commit c0e73276f0fcbbd3d4736ba975d7dc7a48791b0c ] + +Function mlxfw_mfa2_tlv_multi_get() returns NULL if 'tlv' in +question does not pass checks in mlxfw_mfa2_tlv_payload_get(). This +behaviour may lead to NULL pointer dereference in 'multi->total_len'. +Fix this issue by testing mlxfw_mfa2_tlv_multi_get()'s return value +against NULL. + +Found by Linux Verification Center (linuxtesting.org) with static +analysis tool SVACE. + +Fixes: 410ed13cae39 ("Add the mlxfw module for Mellanox firmware flash process") +Co-developed-by: Natalia Petrova +Signed-off-by: Nikita Zhandarovich +Reviewed-by: Ido Schimmel +Link: https://lore.kernel.org/r/20230417120718.52325-1-n.zhandarovich@fintech.ru +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c | 2 ++ + 1 file changed, 2 insertions(+) + +diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c +index 017d68f1e1232..972c571b41587 100644 +--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c ++++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c +@@ -31,6 +31,8 @@ mlxfw_mfa2_tlv_next(const struct mlxfw_mfa2_file *mfa2_file, + + if (tlv->type == MLXFW_MFA2_TLV_MULTI_PART) { + multi = mlxfw_mfa2_tlv_multi_get(mfa2_file, tlv); ++ if (!multi) ++ return NULL; + tlv_len = NLA_ALIGN(tlv_len + be16_to_cpu(multi->total_len)); + } + +-- +2.39.2 + diff --git a/queue-5.15/mlxsw-pci-fix-possible-crash-during-initialization.patch b/queue-5.15/mlxsw-pci-fix-possible-crash-during-initialization.patch new file mode 100644 index 00000000000..d5b91ef04d8 --- /dev/null +++ b/queue-5.15/mlxsw-pci-fix-possible-crash-during-initialization.patch @@ -0,0 +1,62 @@ +From 85b0d123568ed71df7aa0b9ce128118f1068162c Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 17 Apr 2023 18:52:51 +0200 +Subject: mlxsw: pci: Fix possible crash during initialization + +From: Ido Schimmel + +[ Upstream commit 1f64757ee2bb22a93ec89b4c71707297e8cca0ba ] + +During initialization the driver issues a reset command via its command +interface in order to remove previous configuration from the device. + +After issuing the reset, the driver waits for 200ms before polling on +the "system_status" register using memory-mapped IO until the device +reaches a ready state (0x5E). The wait is necessary because the reset +command only triggers the reset, but the reset itself happens +asynchronously. If the driver starts polling too soon, the read of the +"system_status" register will never return and the system will crash +[1]. + +The issue was discovered when the device was flashed with a development +firmware version where the reset routine took longer to complete. The +issue was fixed in the firmware, but it exposed the fact that the +current wait time is borderline. + +Fix by increasing the wait time from 200ms to 400ms. With this patch and +the buggy firmware version, the issue did not reproduce in 10 reboots +whereas without the patch the issue is reproduced quite consistently. + +[1] +mce: CPUs not responding to MCE broadcast (may include false positives): 0,4 +mce: CPUs not responding to MCE broadcast (may include false positives): 0,4 +Kernel panic - not syncing: Timeout: Not all CPUs entered broadcast exception handler +Shutting down cpus with NMI +Kernel Offset: 0x12000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) + +Fixes: ac004e84164e ("mlxsw: pci: Wait longer before accessing the device after reset") +Signed-off-by: Ido Schimmel +Reviewed-by: Petr Machata +Signed-off-by: Petr Machata +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/mellanox/mlxsw/pci_hw.h | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h +index 7b531228d6c0f..25e9f47db2a62 100644 +--- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h ++++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h +@@ -26,7 +26,7 @@ + #define MLXSW_PCI_CIR_TIMEOUT_MSECS 1000 + + #define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 900000 +-#define MLXSW_PCI_SW_RESET_WAIT_MSECS 200 ++#define MLXSW_PCI_SW_RESET_WAIT_MSECS 400 + #define MLXSW_PCI_FW_READY 0xA1844 + #define MLXSW_PCI_FW_READY_MASK 0xFFFF + #define MLXSW_PCI_FW_READY_MAGIC 0x5E +-- +2.39.2 + diff --git a/queue-5.15/net-dsa-b53-mmap-add-phy-ops.patch b/queue-5.15/net-dsa-b53-mmap-add-phy-ops.patch new file mode 100644 index 00000000000..3aa75b47c82 --- /dev/null +++ b/queue-5.15/net-dsa-b53-mmap-add-phy-ops.patch @@ -0,0 +1,59 @@ +From 5b610bf45860983d0c8aaa5ed082fb1e50af5eb7 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 23 Mar 2023 20:48:41 +0100 +Subject: net: dsa: b53: mmap: add phy ops +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: Álvaro Fernández Rojas + +[ Upstream commit 45977e58ce65ed0459edc9a0466d9dfea09463f5 ] + +Implement phy_read16() and phy_write16() ops for B53 MMAP to avoid accessing +B53_PORT_MII_PAGE registers which hangs the device. +This access should be done through the MDIO Mux bus controller. + +Signed-off-by: Álvaro Fernández Rojas +Acked-by: Florian Fainelli +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/dsa/b53/b53_mmap.c | 14 ++++++++++++++ + 1 file changed, 14 insertions(+) + +diff --git a/drivers/net/dsa/b53/b53_mmap.c b/drivers/net/dsa/b53/b53_mmap.c +index 3388f620fac99..ca6f53c630676 100644 +--- a/drivers/net/dsa/b53/b53_mmap.c ++++ b/drivers/net/dsa/b53/b53_mmap.c +@@ -216,6 +216,18 @@ static int b53_mmap_write64(struct b53_device *dev, u8 page, u8 reg, + return 0; + } + ++static int b53_mmap_phy_read16(struct b53_device *dev, int addr, int reg, ++ u16 *value) ++{ ++ return -EIO; ++} ++ ++static int b53_mmap_phy_write16(struct b53_device *dev, int addr, int reg, ++ u16 value) ++{ ++ return -EIO; ++} ++ + static const struct b53_io_ops b53_mmap_ops = { + .read8 = b53_mmap_read8, + .read16 = b53_mmap_read16, +@@ -227,6 +239,8 @@ static const struct b53_io_ops b53_mmap_ops = { + .write32 = b53_mmap_write32, + .write48 = b53_mmap_write48, + .write64 = b53_mmap_write64, ++ .phy_read16 = b53_mmap_phy_read16, ++ .phy_write16 = b53_mmap_phy_write16, + }; + + static int b53_mmap_probe_of(struct platform_device *pdev, +-- +2.39.2 + diff --git a/queue-5.15/net-rpl-fix-rpl-header-size-calculation.patch b/queue-5.15/net-rpl-fix-rpl-header-size-calculation.patch new file mode 100644 index 00000000000..c88388d618f --- /dev/null +++ b/queue-5.15/net-rpl-fix-rpl-header-size-calculation.patch @@ -0,0 +1,47 @@ +From e7c669de15cfddad768898860e3604a93de3c0bd Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 17 Apr 2023 09:00:52 -0400 +Subject: net: rpl: fix rpl header size calculation + +From: Alexander Aring + +[ Upstream commit 4e006c7a6dac0ead4c1bf606000aa90a372fc253 ] + +This patch fixes a missing 8 byte for the header size calculation. The +ipv6_rpl_srh_size() is used to check a skb_pull() on skb->data which +points to skb_transport_header(). Currently we only check on the +calculated addresses fields using CmprI and CmprE fields, see: + +https://www.rfc-editor.org/rfc/rfc6554#section-3 + +there is however a missing 8 byte inside the calculation which stands +for the fields before the addresses field. Those 8 bytes are represented +by sizeof(struct ipv6_rpl_sr_hdr) expression. + +Fixes: 8610c7c6e3bd ("net: ipv6: add support for rpl sr exthdr") +Signed-off-by: Alexander Aring +Reported-by: maxpl0it +Reviewed-by: David Ahern +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/ipv6/rpl.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +diff --git a/net/ipv6/rpl.c b/net/ipv6/rpl.c +index 488aec9e1a74f..d1876f1922255 100644 +--- a/net/ipv6/rpl.c ++++ b/net/ipv6/rpl.c +@@ -32,7 +32,8 @@ static void *ipv6_rpl_segdata_pos(const struct ipv6_rpl_sr_hdr *hdr, int i) + size_t ipv6_rpl_srh_size(unsigned char n, unsigned char cmpri, + unsigned char cmpre) + { +- return (n * IPV6_PFXTAIL_LEN(cmpri)) + IPV6_PFXTAIL_LEN(cmpre); ++ return sizeof(struct ipv6_rpl_sr_hdr) + (n * IPV6_PFXTAIL_LEN(cmpri)) + ++ IPV6_PFXTAIL_LEN(cmpre); + } + + void ipv6_rpl_srh_decompress(struct ipv6_rpl_sr_hdr *outhdr, +-- +2.39.2 + diff --git a/queue-5.15/net-sched-sch_qfq-prevent-slab-out-of-bounds-in-qfq_.patch b/queue-5.15/net-sched-sch_qfq-prevent-slab-out-of-bounds-in-qfq_.patch new file mode 100644 index 00000000000..89bd4a3f3b2 --- /dev/null +++ b/queue-5.15/net-sched-sch_qfq-prevent-slab-out-of-bounds-in-qfq_.patch @@ -0,0 +1,134 @@ +From ec20b4edbe0b9661fb702412a9c06a27009789c2 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 13 Apr 2023 19:35:54 +0900 +Subject: net: sched: sch_qfq: prevent slab-out-of-bounds in qfq_activate_agg + +From: Gwangun Jung + +[ Upstream commit 3037933448f60f9acb705997eae62013ecb81e0d ] + +If the TCA_QFQ_LMAX value is not offered through nlattr, lmax is determined by the MTU value of the network device. +The MTU of the loopback device can be set up to 2^31-1. +As a result, it is possible to have an lmax value that exceeds QFQ_MIN_LMAX. + +Due to the invalid lmax value, an index is generated that exceeds the QFQ_MAX_INDEX(=24) value, causing out-of-bounds read/write errors. + +The following reports a oob access: + +[ 84.582666] BUG: KASAN: slab-out-of-bounds in qfq_activate_agg.constprop.0 (net/sched/sch_qfq.c:1027 net/sched/sch_qfq.c:1060 net/sched/sch_qfq.c:1313) +[ 84.583267] Read of size 4 at addr ffff88810f676948 by task ping/301 +[ 84.583686] +[ 84.583797] CPU: 3 PID: 301 Comm: ping Not tainted 6.3.0-rc5 #1 +[ 84.584164] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 +[ 84.584644] Call Trace: +[ 84.584787] +[ 84.584906] dump_stack_lvl (lib/dump_stack.c:107 (discriminator 1)) +[ 84.585108] print_report (mm/kasan/report.c:320 mm/kasan/report.c:430) +[ 84.585570] kasan_report (mm/kasan/report.c:538) +[ 84.585988] qfq_activate_agg.constprop.0 (net/sched/sch_qfq.c:1027 net/sched/sch_qfq.c:1060 net/sched/sch_qfq.c:1313) +[ 84.586599] qfq_enqueue (net/sched/sch_qfq.c:1255) +[ 84.587607] dev_qdisc_enqueue (net/core/dev.c:3776) +[ 84.587749] __dev_queue_xmit (./include/net/sch_generic.h:186 net/core/dev.c:3865 net/core/dev.c:4212) +[ 84.588763] ip_finish_output2 (./include/net/neighbour.h:546 net/ipv4/ip_output.c:228) +[ 84.589460] ip_output (net/ipv4/ip_output.c:430) +[ 84.590132] ip_push_pending_frames (./include/net/dst.h:444 net/ipv4/ip_output.c:126 net/ipv4/ip_output.c:1586 net/ipv4/ip_output.c:1606) +[ 84.590285] raw_sendmsg (net/ipv4/raw.c:649) +[ 84.591960] sock_sendmsg (net/socket.c:724 net/socket.c:747) +[ 84.592084] __sys_sendto (net/socket.c:2142) +[ 84.593306] __x64_sys_sendto (net/socket.c:2150) +[ 84.593779] do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) +[ 84.593902] entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) +[ 84.594070] RIP: 0033:0x7fe568032066 +[ 84.594192] Code: 0e 0d 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 41 89 ca 64 8b 04 25 18 00 00 00 85 c09[ 84.594796] RSP: 002b:00007ffce388b4e8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c + +Code starting with the faulting instruction +=========================================== +[ 84.595047] RAX: ffffffffffffffda RBX: 00007ffce388cc70 RCX: 00007fe568032066 +[ 84.595281] RDX: 0000000000000040 RSI: 00005605fdad6d10 RDI: 0000000000000003 +[ 84.595515] RBP: 00005605fdad6d10 R08: 00007ffce388eeec R09: 0000000000000010 +[ 84.595749] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000040 +[ 84.595984] R13: 00007ffce388cc30 R14: 00007ffce388b4f0 R15: 0000001d00000001 +[ 84.596218] +[ 84.596295] +[ 84.596351] Allocated by task 291: +[ 84.596467] kasan_save_stack (mm/kasan/common.c:46) +[ 84.596597] kasan_set_track (mm/kasan/common.c:52) +[ 84.596725] __kasan_kmalloc (mm/kasan/common.c:384) +[ 84.596852] __kmalloc_node (./include/linux/kasan.h:196 mm/slab_common.c:967 mm/slab_common.c:974) +[ 84.596979] qdisc_alloc (./include/linux/slab.h:610 ./include/linux/slab.h:731 net/sched/sch_generic.c:938) +[ 84.597100] qdisc_create (net/sched/sch_api.c:1244) +[ 84.597222] tc_modify_qdisc (net/sched/sch_api.c:1680) +[ 84.597357] rtnetlink_rcv_msg (net/core/rtnetlink.c:6174) +[ 84.597495] netlink_rcv_skb (net/netlink/af_netlink.c:2574) +[ 84.597627] netlink_unicast (net/netlink/af_netlink.c:1340 net/netlink/af_netlink.c:1365) +[ 84.597759] netlink_sendmsg (net/netlink/af_netlink.c:1942) +[ 84.597891] sock_sendmsg (net/socket.c:724 net/socket.c:747) +[ 84.598016] ____sys_sendmsg (net/socket.c:2501) +[ 84.598147] ___sys_sendmsg (net/socket.c:2557) +[ 84.598275] __sys_sendmsg (./include/linux/file.h:31 net/socket.c:2586) +[ 84.598399] do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) +[ 84.598520] entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) +[ 84.598688] +[ 84.598744] The buggy address belongs to the object at ffff88810f674000 +[ 84.598744] which belongs to the cache kmalloc-8k of size 8192 +[ 84.599135] The buggy address is located 2664 bytes to the right of +[ 84.599135] allocated 7904-byte region [ffff88810f674000, ffff88810f675ee0) +[ 84.599544] +[ 84.599598] The buggy address belongs to the physical page: +[ 84.599777] page:00000000e638567f refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x10f670 +[ 84.600074] head:00000000e638567f order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0 +[ 84.600330] flags: 0x200000000010200(slab|head|node=0|zone=2) +[ 84.600517] raw: 0200000000010200 ffff888100043180 dead000000000122 0000000000000000 +[ 84.600764] raw: 0000000000000000 0000000080020002 00000001ffffffff 0000000000000000 +[ 84.601009] page dumped because: kasan: bad access detected +[ 84.601187] +[ 84.601241] Memory state around the buggy address: +[ 84.601396] ffff88810f676800: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc +[ 84.601620] ffff88810f676880: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc +[ 84.601845] >ffff88810f676900: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc +[ 84.602069] ^ +[ 84.602243] ffff88810f676980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc +[ 84.602468] ffff88810f676a00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc +[ 84.602693] ================================================================== +[ 84.602924] Disabling lock debugging due to kernel taint + +Fixes: 3015f3d2a3cd ("pkt_sched: enable QFQ to support TSO/GSO") +Reported-by: Gwangun Jung +Signed-off-by: Gwangun Jung +Acked-by: Jamal Hadi Salim +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/sched/sch_qfq.c | 13 +++++++------ + 1 file changed, 7 insertions(+), 6 deletions(-) + +diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c +index 50e51c1322fc1..4c51aeb78f141 100644 +--- a/net/sched/sch_qfq.c ++++ b/net/sched/sch_qfq.c +@@ -421,15 +421,16 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, + } else + weight = 1; + +- if (tb[TCA_QFQ_LMAX]) { ++ if (tb[TCA_QFQ_LMAX]) + lmax = nla_get_u32(tb[TCA_QFQ_LMAX]); +- if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { +- pr_notice("qfq: invalid max length %u\n", lmax); +- return -EINVAL; +- } +- } else ++ else + lmax = psched_mtu(qdisc_dev(sch)); + ++ if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { ++ pr_notice("qfq: invalid max length %u\n", lmax); ++ return -EINVAL; ++ } ++ + inv_w = ONE_FP / weight; + weight = ONE_FP / inv_w; + +-- +2.39.2 + diff --git a/queue-5.15/netfilter-br_netfilter-fix-recent-physdev-match-brea.patch b/queue-5.15/netfilter-br_netfilter-fix-recent-physdev-match-brea.patch new file mode 100644 index 00000000000..103cc0e5f3b --- /dev/null +++ b/queue-5.15/netfilter-br_netfilter-fix-recent-physdev-match-brea.patch @@ -0,0 +1,71 @@ +From 77200266a1a3d4a28104e3e5d15afda15cf29b89 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 3 Apr 2023 13:54:37 +0200 +Subject: netfilter: br_netfilter: fix recent physdev match breakage + +From: Florian Westphal + +[ Upstream commit 94623f579ce338b5fa61b5acaa5beb8aa657fb9e ] + +Recent attempt to ensure PREROUTING hook is executed again when a +decrypted ipsec packet received on a bridge passes through the network +stack a second time broke the physdev match in INPUT hook. + +We can't discard the nf_bridge info strct from sabotage_in hook, as +this is needed by the physdev match. + +Keep the struct around and handle this with another conditional instead. + +Fixes: 2b272bb558f1 ("netfilter: br_netfilter: disable sabotage_in hook after first suppression") +Reported-and-tested-by: Farid BENAMROUCHE +Signed-off-by: Florian Westphal +Signed-off-by: Pablo Neira Ayuso +Signed-off-by: Sasha Levin +--- + include/linux/skbuff.h | 1 + + net/bridge/br_netfilter_hooks.c | 17 +++++++++++------ + 2 files changed, 12 insertions(+), 6 deletions(-) + +diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h +index 19e595cab23ac..ef00dd3108362 100644 +--- a/include/linux/skbuff.h ++++ b/include/linux/skbuff.h +@@ -259,6 +259,7 @@ struct nf_bridge_info { + u8 pkt_otherhost:1; + u8 in_prerouting:1; + u8 bridged_dnat:1; ++ u8 sabotage_in_done:1; + __u16 frag_max_size; + struct net_device *physindev; + +diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c +index f3c7cfba31e1b..f14beb9a62edb 100644 +--- a/net/bridge/br_netfilter_hooks.c ++++ b/net/bridge/br_netfilter_hooks.c +@@ -868,12 +868,17 @@ static unsigned int ip_sabotage_in(void *priv, + { + struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); + +- if (nf_bridge && !nf_bridge->in_prerouting && +- !netif_is_l3_master(skb->dev) && +- !netif_is_l3_slave(skb->dev)) { +- nf_bridge_info_free(skb); +- state->okfn(state->net, state->sk, skb); +- return NF_STOLEN; ++ if (nf_bridge) { ++ if (nf_bridge->sabotage_in_done) ++ return NF_ACCEPT; ++ ++ if (!nf_bridge->in_prerouting && ++ !netif_is_l3_master(skb->dev) && ++ !netif_is_l3_slave(skb->dev)) { ++ nf_bridge->sabotage_in_done = 1; ++ state->okfn(state->net, state->sk, skb); ++ return NF_STOLEN; ++ } + } + + return NF_ACCEPT; +-- +2.39.2 + diff --git a/queue-5.15/netfilter-nf_tables-fix-ifdef-to-also-consider-nf_ta.patch b/queue-5.15/netfilter-nf_tables-fix-ifdef-to-also-consider-nf_ta.patch new file mode 100644 index 00000000000..1b79433874c --- /dev/null +++ b/queue-5.15/netfilter-nf_tables-fix-ifdef-to-also-consider-nf_ta.patch @@ -0,0 +1,47 @@ +From 011b8536b26b06d30fbc21e9c82b8d3d21bf7d72 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 17 Apr 2023 10:21:36 +0200 +Subject: netfilter: nf_tables: fix ifdef to also consider nf_tables=m + +From: Florian Westphal + +[ Upstream commit c55c0e91c813589dc55bea6bf9a9fbfaa10ae41d ] + +nftables can be built as a module, so fix the preprocessor conditional +accordingly. + +Fixes: 478b360a47b7 ("netfilter: nf_tables: fix nf_trace always-on with XT_TRACE=n") +Reported-by: Florian Fainelli +Reported-by: Jakub Kicinski +Signed-off-by: Florian Westphal +Signed-off-by: Pablo Neira Ayuso +Signed-off-by: Sasha Levin +--- + include/linux/skbuff.h | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h +index ef00dd3108362..7ed1d4472c0c8 100644 +--- a/include/linux/skbuff.h ++++ b/include/linux/skbuff.h +@@ -4462,7 +4462,7 @@ static inline void nf_reset_ct(struct sk_buff *skb) + + static inline void nf_reset_trace(struct sk_buff *skb) + { +-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) ++#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) + skb->nf_trace = 0; + #endif + } +@@ -4482,7 +4482,7 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, + dst->_nfct = src->_nfct; + nf_conntrack_get(skb_nfct(src)); + #endif +-#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) ++#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) + if (copy) + dst->nf_trace = src->nf_trace; + #endif +-- +2.39.2 + diff --git a/queue-5.15/netfilter-nf_tables-tighten-netlink-attribute-requir.patch b/queue-5.15/netfilter-nf_tables-tighten-netlink-attribute-requir.patch new file mode 100644 index 00000000000..fe97d7d5e3c --- /dev/null +++ b/queue-5.15/netfilter-nf_tables-tighten-netlink-attribute-requir.patch @@ -0,0 +1,37 @@ +From 0014ae979950dfe10c4fc58ea26bba6406664658 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 17 Apr 2023 17:50:28 +0200 +Subject: netfilter: nf_tables: tighten netlink attribute requirements for + catch-all elements + +From: Pablo Neira Ayuso + +[ Upstream commit d4eb7e39929a3b1ff30fb751b4859fc2410702a0 ] + +If NFT_SET_ELEM_CATCHALL is set on, then userspace provides no set element +key. Otherwise, bail out with -EINVAL. + +Fixes: aaa31047a6d2 ("netfilter: nftables: add catch-all set element support") +Signed-off-by: Pablo Neira Ayuso +Signed-off-by: Sasha Levin +--- + net/netfilter/nf_tables_api.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c +index aecb2f1e7af10..d950041364d5f 100644 +--- a/net/netfilter/nf_tables_api.c ++++ b/net/netfilter/nf_tables_api.c +@@ -5895,7 +5895,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, + if (err < 0) + return err; + +- if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL)) ++ if (((flags & NFT_SET_ELEM_CATCHALL) && nla[NFTA_SET_ELEM_KEY]) || ++ (!(flags & NFT_SET_ELEM_CATCHALL) && !nla[NFTA_SET_ELEM_KEY])) + return -EINVAL; + + if (flags != 0) { +-- +2.39.2 + diff --git a/queue-5.15/netfilter-nf_tables-validate-catch-all-set-elements.patch b/queue-5.15/netfilter-nf_tables-validate-catch-all-set-elements.patch new file mode 100644 index 00000000000..4ae09771bec --- /dev/null +++ b/queue-5.15/netfilter-nf_tables-validate-catch-all-set-elements.patch @@ -0,0 +1,177 @@ +From eb75a588db16ed3aef28e2fa25b0d4f4bf755780 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 17 Apr 2023 12:14:29 +0200 +Subject: netfilter: nf_tables: validate catch-all set elements + +From: Pablo Neira Ayuso + +[ Upstream commit d46fc894147cf98dd6e8210aa99ed46854191840 ] + +catch-all set element might jump/goto to chain that uses expressions +that require validation. + +Fixes: aaa31047a6d2 ("netfilter: nftables: add catch-all set element support") +Signed-off-by: Pablo Neira Ayuso +Signed-off-by: Sasha Levin +--- + include/net/netfilter/nf_tables.h | 4 ++ + net/netfilter/nf_tables_api.c | 64 ++++++++++++++++++++++++++++--- + net/netfilter/nft_lookup.c | 36 ++--------------- + 3 files changed, 66 insertions(+), 38 deletions(-) + +diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h +index 80df8ff5e6752..8def00a04541e 100644 +--- a/include/net/netfilter/nf_tables.h ++++ b/include/net/netfilter/nf_tables.h +@@ -1030,6 +1030,10 @@ struct nft_chain { + }; + + int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain); ++int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, ++ const struct nft_set_iter *iter, ++ struct nft_set_elem *elem); ++int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set); + + enum nft_chain_types { + NFT_CHAIN_T_DEFAULT = 0, +diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c +index dc276b6802ca9..aecb2f1e7af10 100644 +--- a/net/netfilter/nf_tables_api.c ++++ b/net/netfilter/nf_tables_api.c +@@ -3294,6 +3294,64 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) + return 0; + } + ++int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, ++ const struct nft_set_iter *iter, ++ struct nft_set_elem *elem) ++{ ++ const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); ++ struct nft_ctx *pctx = (struct nft_ctx *)ctx; ++ const struct nft_data *data; ++ int err; ++ ++ if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && ++ *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) ++ return 0; ++ ++ data = nft_set_ext_data(ext); ++ switch (data->verdict.code) { ++ case NFT_JUMP: ++ case NFT_GOTO: ++ pctx->level++; ++ err = nft_chain_validate(ctx, data->verdict.chain); ++ if (err < 0) ++ return err; ++ pctx->level--; ++ break; ++ default: ++ break; ++ } ++ ++ return 0; ++} ++ ++struct nft_set_elem_catchall { ++ struct list_head list; ++ struct rcu_head rcu; ++ void *elem; ++}; ++ ++int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set) ++{ ++ u8 genmask = nft_genmask_next(ctx->net); ++ struct nft_set_elem_catchall *catchall; ++ struct nft_set_elem elem; ++ struct nft_set_ext *ext; ++ int ret = 0; ++ ++ list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ++ ext = nft_set_elem_ext(set, catchall->elem); ++ if (!nft_set_elem_active(ext, genmask)) ++ continue; ++ ++ elem.priv = catchall->elem; ++ ret = nft_setelem_validate(ctx, set, NULL, &elem); ++ if (ret < 0) ++ return ret; ++ } ++ ++ return ret; ++} ++ + static struct nft_rule *nft_rule_lookup_byid(const struct net *net, + const struct nft_chain *chain, + const struct nlattr *nla); +@@ -4598,12 +4656,6 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, + return err; + } + +-struct nft_set_elem_catchall { +- struct list_head list; +- struct rcu_head rcu; +- void *elem; +-}; +- + static void nft_set_catchall_destroy(const struct nft_ctx *ctx, + struct nft_set *set) + { +diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c +index 90becbf5bff3d..bd3485dd930f5 100644 +--- a/net/netfilter/nft_lookup.c ++++ b/net/netfilter/nft_lookup.c +@@ -198,37 +198,6 @@ static int nft_lookup_dump(struct sk_buff *skb, const struct nft_expr *expr) + return -1; + } + +-static int nft_lookup_validate_setelem(const struct nft_ctx *ctx, +- struct nft_set *set, +- const struct nft_set_iter *iter, +- struct nft_set_elem *elem) +-{ +- const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); +- struct nft_ctx *pctx = (struct nft_ctx *)ctx; +- const struct nft_data *data; +- int err; +- +- if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && +- *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) +- return 0; +- +- data = nft_set_ext_data(ext); +- switch (data->verdict.code) { +- case NFT_JUMP: +- case NFT_GOTO: +- pctx->level++; +- err = nft_chain_validate(ctx, data->verdict.chain); +- if (err < 0) +- return err; +- pctx->level--; +- break; +- default: +- break; +- } +- +- return 0; +-} +- + static int nft_lookup_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **d) +@@ -244,9 +213,12 @@ static int nft_lookup_validate(const struct nft_ctx *ctx, + iter.skip = 0; + iter.count = 0; + iter.err = 0; +- iter.fn = nft_lookup_validate_setelem; ++ iter.fn = nft_setelem_validate; + + priv->set->ops->walk(ctx, priv->set, &iter); ++ if (!iter.err) ++ iter.err = nft_set_catchall_validate(ctx, priv->set); ++ + if (iter.err < 0) + return iter.err; + +-- +2.39.2 + diff --git a/queue-5.15/nvme-tcp-fix-a-possible-uaf-when-failing-to-allocate.patch b/queue-5.15/nvme-tcp-fix-a-possible-uaf-when-failing-to-allocate.patch new file mode 100644 index 00000000000..26e2b5af97c --- /dev/null +++ b/queue-5.15/nvme-tcp-fix-a-possible-uaf-when-failing-to-allocate.patch @@ -0,0 +1,157 @@ +From a15e1c9b0952fa102318dc14ecdcf598fea78c10 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 20 Mar 2023 15:33:34 +0200 +Subject: nvme-tcp: fix a possible UAF when failing to allocate an io queue + +From: Sagi Grimberg + +[ Upstream commit 88eaba80328b31ef81813a1207b4056efd7006a6 ] + +When we allocate a nvme-tcp queue, we set the data_ready callback before +we actually need to use it. This creates the potential that if a stray +controller sends us data on the socket before we connect, we can trigger +the io_work and start consuming the socket. + +In this case reported: we failed to allocate one of the io queues, and +as we start releasing the queues that we already allocated, we get +a UAF [1] from the io_work which is running before it should really. + +Fix this by setting the socket ops callbacks only before we start the +queue, so that we can't accidentally schedule the io_work in the +initialization phase before the queue started. While we are at it, +rename nvme_tcp_restore_sock_calls to pair with nvme_tcp_setup_sock_ops. + +[1]: +[16802.107284] nvme nvme4: starting error recovery +[16802.109166] nvme nvme4: Reconnecting in 10 seconds... +[16812.173535] nvme nvme4: failed to connect socket: -111 +[16812.173745] nvme nvme4: Failed reconnect attempt 1 +[16812.173747] nvme nvme4: Reconnecting in 10 seconds... +[16822.413555] nvme nvme4: failed to connect socket: -111 +[16822.413762] nvme nvme4: Failed reconnect attempt 2 +[16822.413765] nvme nvme4: Reconnecting in 10 seconds... +[16832.661274] nvme nvme4: creating 32 I/O queues. +[16833.919887] BUG: kernel NULL pointer dereference, address: 0000000000000088 +[16833.920068] nvme nvme4: Failed reconnect attempt 3 +[16833.920094] #PF: supervisor write access in kernel mode +[16833.920261] nvme nvme4: Reconnecting in 10 seconds... +[16833.920368] #PF: error_code(0x0002) - not-present page +[16833.921086] Workqueue: nvme_tcp_wq nvme_tcp_io_work [nvme_tcp] +[16833.921191] RIP: 0010:_raw_spin_lock_bh+0x17/0x30 +... +[16833.923138] Call Trace: +[16833.923271] +[16833.923402] lock_sock_nested+0x1e/0x50 +[16833.923545] nvme_tcp_try_recv+0x40/0xa0 [nvme_tcp] +[16833.923685] nvme_tcp_io_work+0x68/0xa0 [nvme_tcp] +[16833.923824] process_one_work+0x1e8/0x390 +[16833.923969] worker_thread+0x53/0x3d0 +[16833.924104] ? process_one_work+0x390/0x390 +[16833.924240] kthread+0x124/0x150 +[16833.924376] ? set_kthread_struct+0x50/0x50 +[16833.924518] ret_from_fork+0x1f/0x30 +[16833.924655] + +Reported-by: Yanjun Zhang +Signed-off-by: Sagi Grimberg +Tested-by: Yanjun Zhang +Signed-off-by: Christoph Hellwig +Signed-off-by: Sasha Levin +--- + drivers/nvme/host/tcp.c | 46 +++++++++++++++++++++++------------------ + 1 file changed, 26 insertions(+), 20 deletions(-) + +diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c +index 96d8d7844e846..fb47d0603e051 100644 +--- a/drivers/nvme/host/tcp.c ++++ b/drivers/nvme/host/tcp.c +@@ -1563,22 +1563,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, + if (ret) + goto err_init_connect; + +- queue->rd_enabled = true; + set_bit(NVME_TCP_Q_ALLOCATED, &queue->flags); +- nvme_tcp_init_recv_ctx(queue); +- +- write_lock_bh(&queue->sock->sk->sk_callback_lock); +- queue->sock->sk->sk_user_data = queue; +- queue->state_change = queue->sock->sk->sk_state_change; +- queue->data_ready = queue->sock->sk->sk_data_ready; +- queue->write_space = queue->sock->sk->sk_write_space; +- queue->sock->sk->sk_data_ready = nvme_tcp_data_ready; +- queue->sock->sk->sk_state_change = nvme_tcp_state_change; +- queue->sock->sk->sk_write_space = nvme_tcp_write_space; +-#ifdef CONFIG_NET_RX_BUSY_POLL +- queue->sock->sk->sk_ll_usec = 1; +-#endif +- write_unlock_bh(&queue->sock->sk->sk_callback_lock); + + return 0; + +@@ -1598,7 +1583,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, + return ret; + } + +-static void nvme_tcp_restore_sock_calls(struct nvme_tcp_queue *queue) ++static void nvme_tcp_restore_sock_ops(struct nvme_tcp_queue *queue) + { + struct socket *sock = queue->sock; + +@@ -1613,7 +1598,7 @@ static void nvme_tcp_restore_sock_calls(struct nvme_tcp_queue *queue) + static void __nvme_tcp_stop_queue(struct nvme_tcp_queue *queue) + { + kernel_sock_shutdown(queue->sock, SHUT_RDWR); +- nvme_tcp_restore_sock_calls(queue); ++ nvme_tcp_restore_sock_ops(queue); + cancel_work_sync(&queue->io_work); + } + +@@ -1628,21 +1613,42 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid) + mutex_unlock(&queue->queue_lock); + } + ++static void nvme_tcp_setup_sock_ops(struct nvme_tcp_queue *queue) ++{ ++ write_lock_bh(&queue->sock->sk->sk_callback_lock); ++ queue->sock->sk->sk_user_data = queue; ++ queue->state_change = queue->sock->sk->sk_state_change; ++ queue->data_ready = queue->sock->sk->sk_data_ready; ++ queue->write_space = queue->sock->sk->sk_write_space; ++ queue->sock->sk->sk_data_ready = nvme_tcp_data_ready; ++ queue->sock->sk->sk_state_change = nvme_tcp_state_change; ++ queue->sock->sk->sk_write_space = nvme_tcp_write_space; ++#ifdef CONFIG_NET_RX_BUSY_POLL ++ queue->sock->sk->sk_ll_usec = 1; ++#endif ++ write_unlock_bh(&queue->sock->sk->sk_callback_lock); ++} ++ + static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx) + { + struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); ++ struct nvme_tcp_queue *queue = &ctrl->queues[idx]; + int ret; + ++ queue->rd_enabled = true; ++ nvme_tcp_init_recv_ctx(queue); ++ nvme_tcp_setup_sock_ops(queue); ++ + if (idx) + ret = nvmf_connect_io_queue(nctrl, idx); + else + ret = nvmf_connect_admin_queue(nctrl); + + if (!ret) { +- set_bit(NVME_TCP_Q_LIVE, &ctrl->queues[idx].flags); ++ set_bit(NVME_TCP_Q_LIVE, &queue->flags); + } else { +- if (test_bit(NVME_TCP_Q_ALLOCATED, &ctrl->queues[idx].flags)) +- __nvme_tcp_stop_queue(&ctrl->queues[idx]); ++ if (test_bit(NVME_TCP_Q_ALLOCATED, &queue->flags)) ++ __nvme_tcp_stop_queue(queue); + dev_err(nctrl->device, + "failed to connect queue: %d ret=%d\n", idx, ret); + } +-- +2.39.2 + diff --git a/queue-5.15/platform-x86-gigabyte-wmi-add-support-for-a320m-s2h-.patch b/queue-5.15/platform-x86-gigabyte-wmi-add-support-for-a320m-s2h-.patch new file mode 100644 index 00000000000..26bf703cb98 --- /dev/null +++ b/queue-5.15/platform-x86-gigabyte-wmi-add-support-for-a320m-s2h-.patch @@ -0,0 +1,39 @@ +From 8a082a7052ab23e73802b751950458a6352cb897 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Sat, 18 Mar 2023 20:14:41 +1100 +Subject: platform/x86 (gigabyte-wmi): Add support for A320M-S2H V2 +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: Frank Crawford + +[ Upstream commit b7c994f8c35e916e27c60803bb21457bc1373500 ] + +Add support for A320M-S2H V2. Tested using module force_load option. + +Signed-off-by: Frank Crawford +Acked-by: Thomas Weißschuh +Link: https://lore.kernel.org/r/20230318091441.1240921-1-frank@crawford.emu.id.au +Reviewed-by: Hans de Goede +Signed-off-by: Hans de Goede +Signed-off-by: Sasha Levin +--- + drivers/platform/x86/gigabyte-wmi.c | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/drivers/platform/x86/gigabyte-wmi.c b/drivers/platform/x86/gigabyte-wmi.c +index 0163e912fafec..aea4f3144b68f 100644 +--- a/drivers/platform/x86/gigabyte-wmi.c ++++ b/drivers/platform/x86/gigabyte-wmi.c +@@ -140,6 +140,7 @@ static u8 gigabyte_wmi_detect_sensor_usability(struct wmi_device *wdev) + }} + + static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = { ++ DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("A320M-S2H V2-CF"), + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M DS3H-CF"), + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M DS3H WIFI-CF"), + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M S2H V2"), +-- +2.39.2 + diff --git a/queue-5.15/platform-x86-gigabyte-wmi-add-support-for-x570s-aoru.patch b/queue-5.15/platform-x86-gigabyte-wmi-add-support-for-x570s-aoru.patch new file mode 100644 index 00000000000..efba4c76a17 --- /dev/null +++ b/queue-5.15/platform-x86-gigabyte-wmi-add-support-for-x570s-aoru.patch @@ -0,0 +1,34 @@ +From 09add911cfc35ad6cff6f9c846c95341d3a40e22 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 31 Mar 2023 19:31:48 +0200 +Subject: platform/x86: gigabyte-wmi: add support for X570S AORUS ELITE + +From: Hans de Goede + +[ Upstream commit 52f91e51944808d83dfe2d5582601b5e84e472cc ] + +Add "X570S AORUS ELITE" to known working boards + +Reported-by: Brandon Nielsen +Link: https://lore.kernel.org/r/20230331014902.7864-1-nielsenb@jetfuse.net +Signed-off-by: Hans de Goede +Signed-off-by: Sasha Levin +--- + drivers/platform/x86/gigabyte-wmi.c | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/drivers/platform/x86/gigabyte-wmi.c b/drivers/platform/x86/gigabyte-wmi.c +index aea4f3144b68f..bf1b98dd00b99 100644 +--- a/drivers/platform/x86/gigabyte-wmi.c ++++ b/drivers/platform/x86/gigabyte-wmi.c +@@ -156,6 +156,7 @@ static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = { + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 GAMING X"), + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 I AORUS PRO WIFI"), + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 UD"), ++ DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570S AORUS ELITE"), + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("Z690M AORUS ELITE AX DDR4"), + { } + }; +-- +2.39.2 + diff --git a/queue-5.15/regulator-fan53555-explicitly-include-bits-header.patch b/queue-5.15/regulator-fan53555-explicitly-include-bits-header.patch new file mode 100644 index 00000000000..c5c5e1f390f --- /dev/null +++ b/queue-5.15/regulator-fan53555-explicitly-include-bits-header.patch @@ -0,0 +1,59 @@ +From ca816a51050f58a0fa02fcf7bdb9c3a3b3358247 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 6 Apr 2023 20:18:00 +0300 +Subject: regulator: fan53555: Explicitly include bits header + +From: Cristian Ciocaltea + +[ Upstream commit 4fb9a5060f73627303bc531ceaab1b19d0a24aef ] + +Since commit f2a9eb975ab2 ("regulator: fan53555: Add support for +FAN53526") the driver makes use of the BIT() macro, but relies on the +bits header being implicitly included. + +Explicitly pull the header in to avoid potential build failures in some +configurations. + +While here, reorder include directives alphabetically. + +Fixes: f2a9eb975ab2 ("regulator: fan53555: Add support for FAN53526") +Signed-off-by: Cristian Ciocaltea +Link: https://lore.kernel.org/r/20230406171806.948290-3-cristian.ciocaltea@collabora.com +Signed-off-by: Mark Brown +Signed-off-by: Sasha Levin +--- + drivers/regulator/fan53555.c | 11 ++++++----- + 1 file changed, 6 insertions(+), 5 deletions(-) + +diff --git a/drivers/regulator/fan53555.c b/drivers/regulator/fan53555.c +index dac1fb584fa35..df53464afe3a0 100644 +--- a/drivers/regulator/fan53555.c ++++ b/drivers/regulator/fan53555.c +@@ -8,18 +8,19 @@ + // Copyright (c) 2012 Marvell Technology Ltd. + // Yunfan Zhang + ++#include ++#include ++#include + #include ++#include + #include +-#include + #include ++#include + #include ++#include + #include + #include +-#include +-#include + #include +-#include +-#include + + /* Voltage setting */ + #define FAN53555_VSEL0 0x00 +-- +2.39.2 + diff --git a/queue-5.15/regulator-fan53555-fix-wrong-tcs_slew_mask.patch b/queue-5.15/regulator-fan53555-fix-wrong-tcs_slew_mask.patch new file mode 100644 index 00000000000..205330c729f --- /dev/null +++ b/queue-5.15/regulator-fan53555-fix-wrong-tcs_slew_mask.patch @@ -0,0 +1,40 @@ +From 8523ac4ba2b89abe305c9cb2d927279f449fbc27 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 6 Apr 2023 20:18:01 +0300 +Subject: regulator: fan53555: Fix wrong TCS_SLEW_MASK + +From: Cristian Ciocaltea + +[ Upstream commit c5d5b55b3c1a314137a251efc1001dfd435c6242 ] + +The support for TCS4525 regulator has been introduced with a wrong +ramp-rate mask, which has been defined as a logical expression instead +of a bit shift operation. + +For clarity, fix it using GENMASK() macro. + +Fixes: 914df8faa7d6 ("regulator: fan53555: Add TCS4525 DCDC support") +Signed-off-by: Cristian Ciocaltea +Link: https://lore.kernel.org/r/20230406171806.948290-4-cristian.ciocaltea@collabora.com +Signed-off-by: Mark Brown +Signed-off-by: Sasha Levin +--- + drivers/regulator/fan53555.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/regulator/fan53555.c b/drivers/regulator/fan53555.c +index df53464afe3a0..ecd5a50c61660 100644 +--- a/drivers/regulator/fan53555.c ++++ b/drivers/regulator/fan53555.c +@@ -61,7 +61,7 @@ + #define TCS_VSEL1_MODE (1 << 6) + + #define TCS_SLEW_SHIFT 3 +-#define TCS_SLEW_MASK (0x3 < 3) ++#define TCS_SLEW_MASK GENMASK(4, 3) + + enum fan53555_vendor { + FAN53526_VENDOR_FAIRCHILD = 0, +-- +2.39.2 + diff --git a/queue-5.15/s390-ptrace-fix-ptrace_get_last_break-error-handling.patch b/queue-5.15/s390-ptrace-fix-ptrace_get_last_break-error-handling.patch new file mode 100644 index 00000000000..c790c47dde7 --- /dev/null +++ b/queue-5.15/s390-ptrace-fix-ptrace_get_last_break-error-handling.patch @@ -0,0 +1,49 @@ +From 02c08bcafba77f5edd29f1e541a9768bacfcf1e7 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 6 Mar 2023 12:31:30 +0100 +Subject: s390/ptrace: fix PTRACE_GET_LAST_BREAK error handling + +From: Heiko Carstens + +[ Upstream commit f9bbf25e7b2b74b52b2f269216a92657774f239c ] + +Return -EFAULT if put_user() for the PTRACE_GET_LAST_BREAK +request fails, instead of silently ignoring it. + +Reviewed-by: Sven Schnelle +Signed-off-by: Heiko Carstens +Signed-off-by: Vasily Gorbik +Signed-off-by: Sasha Levin +--- + arch/s390/kernel/ptrace.c | 8 ++------ + 1 file changed, 2 insertions(+), 6 deletions(-) + +diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c +index 0ea3d02b378de..516c21baf3ad3 100644 +--- a/arch/s390/kernel/ptrace.c ++++ b/arch/s390/kernel/ptrace.c +@@ -481,9 +481,7 @@ long arch_ptrace(struct task_struct *child, long request, + } + return 0; + case PTRACE_GET_LAST_BREAK: +- put_user(child->thread.last_break, +- (unsigned long __user *) data); +- return 0; ++ return put_user(child->thread.last_break, (unsigned long __user *)data); + case PTRACE_ENABLE_TE: + if (!MACHINE_HAS_TE) + return -EIO; +@@ -837,9 +835,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, + } + return 0; + case PTRACE_GET_LAST_BREAK: +- put_user(child->thread.last_break, +- (unsigned int __user *) data); +- return 0; ++ return put_user(child->thread.last_break, (unsigned int __user *)data); + } + return compat_ptrace_request(child, request, addr, data); + } +-- +2.39.2 + diff --git a/queue-5.15/scsi-core-improve-scsi_vpd_inquiry-checks.patch b/queue-5.15/scsi-core-improve-scsi_vpd_inquiry-checks.patch new file mode 100644 index 00000000000..df00d727599 --- /dev/null +++ b/queue-5.15/scsi-core-improve-scsi_vpd_inquiry-checks.patch @@ -0,0 +1,60 @@ +From 7c31e20b5ef9ab5cf7dc79456abe14874af916b0 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 22 Mar 2023 11:22:11 +0900 +Subject: scsi: core: Improve scsi_vpd_inquiry() checks + +From: Damien Le Moal + +[ Upstream commit f0aa59a33d2ac2267d260fe21eaf92500df8e7b4 ] + +Some USB-SATA adapters have broken behavior when an unsupported VPD page is +probed: Depending on the VPD page number, a 4-byte header with a valid VPD +page number but with a 0 length is returned. Currently, scsi_vpd_inquiry() +only checks that the page number is valid to determine if the page is +valid, which results in receiving only the 4-byte header for the +non-existent page. This error manifests itself very often with page 0xb9 +for the Concurrent Positioning Ranges detection done by sd_read_cpr(), +resulting in the following error message: + +sd 0:0:0:0: [sda] Invalid Concurrent Positioning Ranges VPD page + +Prevent such misleading error message by adding a check in +scsi_vpd_inquiry() to verify that the page length is not 0. + +Signed-off-by: Damien Le Moal +Link: https://lore.kernel.org/r/20230322022211.116327-1-damien.lemoal@opensource.wdc.com +Reviewed-by: Benjamin Block +Signed-off-by: Martin K. Petersen +Signed-off-by: Sasha Levin +--- + drivers/scsi/scsi.c | 11 +++++++++-- + 1 file changed, 9 insertions(+), 2 deletions(-) + +diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c +index 4fc9466d820a7..a499a57150720 100644 +--- a/drivers/scsi/scsi.c ++++ b/drivers/scsi/scsi.c +@@ -323,11 +323,18 @@ static int scsi_vpd_inquiry(struct scsi_device *sdev, unsigned char *buffer, + if (result) + return -EIO; + +- /* Sanity check that we got the page back that we asked for */ ++ /* ++ * Sanity check that we got the page back that we asked for and that ++ * the page size is not 0. ++ */ + if (buffer[1] != page) + return -EIO; + +- return get_unaligned_be16(&buffer[2]) + 4; ++ result = get_unaligned_be16(&buffer[2]); ++ if (!result) ++ return -EIO; ++ ++ return result + 4; + } + + /** +-- +2.39.2 + diff --git a/queue-5.15/scsi-megaraid_sas-fix-fw_crash_buffer_show.patch b/queue-5.15/scsi-megaraid_sas-fix-fw_crash_buffer_show.patch new file mode 100644 index 00000000000..e705426fba4 --- /dev/null +++ b/queue-5.15/scsi-megaraid_sas-fix-fw_crash_buffer_show.patch @@ -0,0 +1,36 @@ +From 11b385aa4070f65e5e1b5c9135835ec266a540a7 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 24 Mar 2023 14:52:49 +0100 +Subject: scsi: megaraid_sas: Fix fw_crash_buffer_show() + +From: Tomas Henzl + +[ Upstream commit 0808ed6ebbc292222ca069d339744870f6d801da ] + +If crash_dump_buf is not allocated then crash dump can't be available. +Replace logical 'and' with 'or'. + +Signed-off-by: Tomas Henzl +Link: https://lore.kernel.org/r/20230324135249.9733-1-thenzl@redhat.com +Signed-off-by: Martin K. Petersen +Signed-off-by: Sasha Levin +--- + drivers/scsi/megaraid/megaraid_sas_base.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c +index 88e164e3d2eac..f7da1876e7a38 100644 +--- a/drivers/scsi/megaraid/megaraid_sas_base.c ++++ b/drivers/scsi/megaraid/megaraid_sas_base.c +@@ -3302,7 +3302,7 @@ fw_crash_buffer_show(struct device *cdev, + + spin_lock_irqsave(&instance->crashdump_lock, flags); + buff_offset = instance->fw_crash_buffer_offset; +- if (!instance->crash_dump_buf && ++ if (!instance->crash_dump_buf || + !((instance->fw_crash_state == AVAILABLE) || + (instance->fw_crash_state == COPYING))) { + dev_err(&instance->pdev->dev, +-- +2.39.2 + diff --git a/queue-5.15/selftests-sigaltstack-fix-wuninitialized.patch b/queue-5.15/selftests-sigaltstack-fix-wuninitialized.patch new file mode 100644 index 00000000000..0a226ec58c5 --- /dev/null +++ b/queue-5.15/selftests-sigaltstack-fix-wuninitialized.patch @@ -0,0 +1,95 @@ +From 526982fa01c80fc47a592e373b71e5f6e78aaa1b Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 8 Mar 2023 11:59:33 -0800 +Subject: selftests: sigaltstack: fix -Wuninitialized + +From: Nick Desaulniers + +[ Upstream commit 05107edc910135d27fe557267dc45be9630bf3dd ] + +Building sigaltstack with clang via: +$ ARCH=x86 make LLVM=1 -C tools/testing/selftests/sigaltstack/ + +produces the following warning: + warning: variable 'sp' is uninitialized when used here [-Wuninitialized] + if (sp < (unsigned long)sstack || + ^~ + +Clang expects these to be declared at global scope; we've fixed this in +the kernel proper by using the macro `current_stack_pointer`. This is +defined in different headers for different target architectures, so just +create a new header that defines the arch-specific register names for +the stack pointer register, and define it for more targets (at least the +ones that support current_stack_pointer/ARCH_HAS_CURRENT_STACK_POINTER). + +Reported-by: Linux Kernel Functional Testing +Link: https://lore.kernel.org/lkml/CA+G9fYsi3OOu7yCsMutpzKDnBMAzJBCPimBp86LhGBa0eCnEpA@mail.gmail.com/ +Signed-off-by: Nick Desaulniers +Reviewed-by: Kees Cook +Tested-by: Linux Kernel Functional Testing +Tested-by: Anders Roxell +Signed-off-by: Shuah Khan +Signed-off-by: Sasha Levin +--- + .../sigaltstack/current_stack_pointer.h | 23 +++++++++++++++++++ + tools/testing/selftests/sigaltstack/sas.c | 7 +----- + 2 files changed, 24 insertions(+), 6 deletions(-) + create mode 100644 tools/testing/selftests/sigaltstack/current_stack_pointer.h + +diff --git a/tools/testing/selftests/sigaltstack/current_stack_pointer.h b/tools/testing/selftests/sigaltstack/current_stack_pointer.h +new file mode 100644 +index 0000000000000..ea9bdf3a90b16 +--- /dev/null ++++ b/tools/testing/selftests/sigaltstack/current_stack_pointer.h +@@ -0,0 +1,23 @@ ++/* SPDX-License-Identifier: GPL-2.0 */ ++ ++#if __alpha__ ++register unsigned long sp asm("$30"); ++#elif __arm__ || __aarch64__ || __csky__ || __m68k__ || __mips__ || __riscv ++register unsigned long sp asm("sp"); ++#elif __i386__ ++register unsigned long sp asm("esp"); ++#elif __loongarch64 ++register unsigned long sp asm("$sp"); ++#elif __ppc__ ++register unsigned long sp asm("r1"); ++#elif __s390x__ ++register unsigned long sp asm("%15"); ++#elif __sh__ ++register unsigned long sp asm("r15"); ++#elif __x86_64__ ++register unsigned long sp asm("rsp"); ++#elif __XTENSA__ ++register unsigned long sp asm("a1"); ++#else ++#error "implement current_stack_pointer equivalent" ++#endif +diff --git a/tools/testing/selftests/sigaltstack/sas.c b/tools/testing/selftests/sigaltstack/sas.c +index c53b070755b65..98d37cb744fb2 100644 +--- a/tools/testing/selftests/sigaltstack/sas.c ++++ b/tools/testing/selftests/sigaltstack/sas.c +@@ -20,6 +20,7 @@ + #include + + #include "../kselftest.h" ++#include "current_stack_pointer.h" + + #ifndef SS_AUTODISARM + #define SS_AUTODISARM (1U << 31) +@@ -46,12 +47,6 @@ void my_usr1(int sig, siginfo_t *si, void *u) + stack_t stk; + struct stk_data *p; + +-#if __s390x__ +- register unsigned long sp asm("%15"); +-#else +- register unsigned long sp asm("sp"); +-#endif +- + if (sp < (unsigned long)sstack || + sp >= (unsigned long)sstack + stack_size) { + ksft_exit_fail_msg("SP is not on sigaltstack\n"); +-- +2.39.2 + diff --git a/queue-5.15/series b/queue-5.15/series new file mode 100644 index 00000000000..046a9c78396 --- /dev/null +++ b/queue-5.15/series @@ -0,0 +1,35 @@ +arm-dts-rockchip-fix-a-typo-error-for-rk3288-spdif-n.patch +arm64-dts-qcom-ipq8074-hk01-enable-qmp-device-not-th.patch +arm64-dts-meson-g12-common-specify-full-dmc-range.patch +arm64-dts-imx8mm-evk-correct-pmic-clock-source.patch +netfilter-br_netfilter-fix-recent-physdev-match-brea.patch +regulator-fan53555-explicitly-include-bits-header.patch +regulator-fan53555-fix-wrong-tcs_slew_mask.patch +net-sched-sch_qfq-prevent-slab-out-of-bounds-in-qfq_.patch +virtio_net-bugfix-overflow-inside-xdp_linearize_page.patch +sfc-split-state_ready-in-to-state_net_down-and-state.patch +sfc-fix-use-after-free-due-to-selftest_work.patch +netfilter-nf_tables-fix-ifdef-to-also-consider-nf_ta.patch +i40e-fix-accessing-vsi-active_filters-without-holdin.patch +i40e-fix-i40e_setup_misc_vector-error-handling.patch +netfilter-nf_tables-validate-catch-all-set-elements.patch +netfilter-nf_tables-tighten-netlink-attribute-requir.patch +bnxt_en-do-not-initialize-ptp-on-older-p3-p4-chips.patch +mlxfw-fix-null-ptr-deref-in-mlxfw_mfa2_tlv_next.patch +bonding-fix-memory-leak-when-changing-bond-type-to-e.patch +net-rpl-fix-rpl-header-size-calculation.patch +mlxsw-pci-fix-possible-crash-during-initialization.patch +spi-spi-rockchip-fix-missing-unwind-goto-in-rockchip.patch +bpf-fix-incorrect-verifier-pruning-due-to-missing-re.patch +e1000e-disable-tso-on-i219-lm-card-to-increase-speed.patch +f2fs-fix-f2fs_truncate_partial_nodes-ftrace-event.patch +input-i8042-add-quirk-for-fujitsu-lifebook-a574-h.patch +platform-x86-gigabyte-wmi-add-support-for-a320m-s2h-.patch +selftests-sigaltstack-fix-wuninitialized.patch +scsi-megaraid_sas-fix-fw_crash_buffer_show.patch +scsi-core-improve-scsi_vpd_inquiry-checks.patch +net-dsa-b53-mmap-add-phy-ops.patch +s390-ptrace-fix-ptrace_get_last_break-error-handling.patch +nvme-tcp-fix-a-possible-uaf-when-failing-to-allocate.patch +xen-netback-use-same-error-messages-for-same-errors.patch +platform-x86-gigabyte-wmi-add-support-for-x570s-aoru.patch diff --git a/queue-5.15/sfc-fix-use-after-free-due-to-selftest_work.patch b/queue-5.15/sfc-fix-use-after-free-due-to-selftest_work.patch new file mode 100644 index 00000000000..dfd2550e6d3 --- /dev/null +++ b/queue-5.15/sfc-fix-use-after-free-due-to-selftest_work.patch @@ -0,0 +1,90 @@ +From 2c710f5fe2cb7fe1d542e54a9c9a5ff7b82aad2d Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 14 Apr 2023 23:23:06 +0800 +Subject: sfc: Fix use-after-free due to selftest_work + +From: Ding Hui + +[ Upstream commit a80bb8e7233b2ad6ff119646b6e33fb3edcec37b ] + +There is a use-after-free scenario that is: + +When the NIC is down, user set mac address or vlan tag to VF, +the xxx_set_vf_mac() or xxx_set_vf_vlan() will invoke efx_net_stop() +and efx_net_open(), since netif_running() is false, the port will not +start and keep port_enabled false, but selftest_work is scheduled +in efx_net_open(). + +If we remove the device before selftest_work run, the efx_stop_port() +will not be called since the NIC is down, and then efx is freed, +we will soon get a UAF in run_timer_softirq() like this: + +[ 1178.907941] ================================================================== +[ 1178.907948] BUG: KASAN: use-after-free in run_timer_softirq+0xdea/0xe90 +[ 1178.907950] Write of size 8 at addr ff11001f449cdc80 by task swapper/47/0 +[ 1178.907950] +[ 1178.907953] CPU: 47 PID: 0 Comm: swapper/47 Kdump: loaded Tainted: G O --------- -t - 4.18.0 #1 +[ 1178.907954] Hardware name: SANGFOR X620G40/WI2HG-208T1061A, BIOS SPYH051032-U01 04/01/2022 +[ 1178.907955] Call Trace: +[ 1178.907956] +[ 1178.907960] dump_stack+0x71/0xab +[ 1178.907963] print_address_description+0x6b/0x290 +[ 1178.907965] ? run_timer_softirq+0xdea/0xe90 +[ 1178.907967] kasan_report+0x14a/0x2b0 +[ 1178.907968] run_timer_softirq+0xdea/0xe90 +[ 1178.907971] ? init_timer_key+0x170/0x170 +[ 1178.907973] ? hrtimer_cancel+0x20/0x20 +[ 1178.907976] ? sched_clock+0x5/0x10 +[ 1178.907978] ? sched_clock_cpu+0x18/0x170 +[ 1178.907981] __do_softirq+0x1c8/0x5fa +[ 1178.907985] irq_exit+0x213/0x240 +[ 1178.907987] smp_apic_timer_interrupt+0xd0/0x330 +[ 1178.907989] apic_timer_interrupt+0xf/0x20 +[ 1178.907990] +[ 1178.907991] RIP: 0010:mwait_idle+0xae/0x370 + +If the NIC is not actually brought up, there is no need to schedule +selftest_work, so let's move invoking efx_selftest_async_start() +into efx_start_all(), and it will be canceled by broughting down. + +Fixes: dd40781e3a4e ("sfc: Run event/IRQ self-test asynchronously when interface is brought up") +Fixes: e340be923012 ("sfc: add ndo_set_vf_mac() function for EF10") +Debugged-by: Huang Cun +Cc: Donglin Peng +Suggested-by: Martin Habets +Signed-off-by: Ding Hui +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/sfc/efx.c | 1 - + drivers/net/ethernet/sfc/efx_common.c | 2 ++ + 2 files changed, 2 insertions(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c +index 7ab592844df83..41eb6f9f5596e 100644 +--- a/drivers/net/ethernet/sfc/efx.c ++++ b/drivers/net/ethernet/sfc/efx.c +@@ -540,7 +540,6 @@ int efx_net_open(struct net_device *net_dev) + else + efx->state = STATE_NET_UP; + +- efx_selftest_async_start(efx); + return 0; + } + +diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c +index 7c90e1e2d161b..6038b7e3e8236 100644 +--- a/drivers/net/ethernet/sfc/efx_common.c ++++ b/drivers/net/ethernet/sfc/efx_common.c +@@ -542,6 +542,8 @@ void efx_start_all(struct efx_nic *efx) + /* Start the hardware monitor if there is one */ + efx_start_monitor(efx); + ++ efx_selftest_async_start(efx); ++ + /* Link state detection is normally event-driven; we have + * to poll now because we could have missed a change + */ +-- +2.39.2 + diff --git a/queue-5.15/sfc-split-state_ready-in-to-state_net_down-and-state.patch b/queue-5.15/sfc-split-state_ready-in-to-state_net_down-and-state.patch new file mode 100644 index 00000000000..ab5b37f327b --- /dev/null +++ b/queue-5.15/sfc-split-state_ready-in-to-state_net_down-and-state.patch @@ -0,0 +1,313 @@ +From 823187051285a59011874fde27ede909d213cfec Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 28 Jun 2022 14:58:55 +0100 +Subject: sfc: Split STATE_READY in to STATE_NET_DOWN and STATE_NET_UP. + +From: Jonathan Cooper + +[ Upstream commit 813cf9d1e753e1e0a247d3d685212a06141b483e ] + +This patch splits the READY state in to NET_UP and NET_DOWN. This +is to prepare for future work to delay resource allocation until +interface up so that we can use resources more efficiently in +SRIOV environments, and also to lay the ground work for an extra +PROBED state where we don't create a network interface, +for VDPA operation. + +Signed-off-by: Jonathan Cooper +Acked-by: Martin Habets +Signed-off-by: David S. Miller +Stable-dep-of: a80bb8e7233b ("sfc: Fix use-after-free due to selftest_work") +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/sfc/ef100_netdev.c | 6 ++- + drivers/net/ethernet/sfc/efx.c | 29 ++++++------- + drivers/net/ethernet/sfc/efx_common.c | 10 ++--- + drivers/net/ethernet/sfc/efx_common.h | 6 +-- + drivers/net/ethernet/sfc/ethtool_common.c | 2 +- + drivers/net/ethernet/sfc/net_driver.h | 50 +++++++++++++++++++++-- + 6 files changed, 72 insertions(+), 31 deletions(-) + +diff --git a/drivers/net/ethernet/sfc/ef100_netdev.c b/drivers/net/ethernet/sfc/ef100_netdev.c +index 63a44ee763be7..b9429e8faba1e 100644 +--- a/drivers/net/ethernet/sfc/ef100_netdev.c ++++ b/drivers/net/ethernet/sfc/ef100_netdev.c +@@ -96,6 +96,8 @@ static int ef100_net_stop(struct net_device *net_dev) + efx_mcdi_free_vis(efx); + efx_remove_interrupts(efx); + ++ efx->state = STATE_NET_DOWN; ++ + return 0; + } + +@@ -172,6 +174,8 @@ static int ef100_net_open(struct net_device *net_dev) + efx_link_status_changed(efx); + mutex_unlock(&efx->mac_lock); + ++ efx->state = STATE_NET_UP; ++ + return 0; + + fail: +@@ -272,7 +276,7 @@ int ef100_register_netdev(struct efx_nic *efx) + /* Always start with carrier off; PHY events will detect the link */ + netif_carrier_off(net_dev); + +- efx->state = STATE_READY; ++ efx->state = STATE_NET_DOWN; + rtnl_unlock(); + efx_init_mcdi_logging(efx); + +diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c +index 16a896360f3fb..7ab592844df83 100644 +--- a/drivers/net/ethernet/sfc/efx.c ++++ b/drivers/net/ethernet/sfc/efx.c +@@ -105,14 +105,6 @@ static int efx_xdp(struct net_device *dev, struct netdev_bpf *xdp); + static int efx_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **xdpfs, + u32 flags); + +-#define EFX_ASSERT_RESET_SERIALISED(efx) \ +- do { \ +- if ((efx->state == STATE_READY) || \ +- (efx->state == STATE_RECOVERY) || \ +- (efx->state == STATE_DISABLED)) \ +- ASSERT_RTNL(); \ +- } while (0) +- + /************************************************************************** + * + * Port handling +@@ -377,6 +369,8 @@ static int efx_probe_all(struct efx_nic *efx) + if (rc) + goto fail5; + ++ efx->state = STATE_NET_DOWN; ++ + return 0; + + fail5: +@@ -543,6 +537,9 @@ int efx_net_open(struct net_device *net_dev) + efx_start_all(efx); + if (efx->state == STATE_DISABLED || efx->reset_pending) + netif_device_detach(efx->net_dev); ++ else ++ efx->state = STATE_NET_UP; ++ + efx_selftest_async_start(efx); + return 0; + } +@@ -719,8 +716,6 @@ static int efx_register_netdev(struct efx_nic *efx) + * already requested. If so, the NIC is probably hosed so we + * abort. + */ +- efx->state = STATE_READY; +- smp_mb(); /* ensure we change state before checking reset_pending */ + if (efx->reset_pending) { + pci_err(efx->pci_dev, "aborting probe due to scheduled reset\n"); + rc = -EIO; +@@ -747,6 +742,8 @@ static int efx_register_netdev(struct efx_nic *efx) + + efx_associate(efx); + ++ efx->state = STATE_NET_DOWN; ++ + rtnl_unlock(); + + rc = device_create_file(&efx->pci_dev->dev, &dev_attr_phy_type); +@@ -848,7 +845,7 @@ static void efx_pci_remove_main(struct efx_nic *efx) + /* Flush reset_work. It can no longer be scheduled since we + * are not READY. + */ +- BUG_ON(efx->state == STATE_READY); ++ WARN_ON(efx_net_active(efx->state)); + efx_flush_reset_workqueue(efx); + + efx_disable_interrupts(efx); +@@ -1153,13 +1150,13 @@ static int efx_pm_freeze(struct device *dev) + + rtnl_lock(); + +- if (efx->state != STATE_DISABLED) { +- efx->state = STATE_UNINIT; +- ++ if (efx_net_active(efx->state)) { + efx_device_detach_sync(efx); + + efx_stop_all(efx); + efx_disable_interrupts(efx); ++ ++ efx->state = efx_freeze(efx->state); + } + + rtnl_unlock(); +@@ -1174,7 +1171,7 @@ static int efx_pm_thaw(struct device *dev) + + rtnl_lock(); + +- if (efx->state != STATE_DISABLED) { ++ if (efx_frozen(efx->state)) { + rc = efx_enable_interrupts(efx); + if (rc) + goto fail; +@@ -1187,7 +1184,7 @@ static int efx_pm_thaw(struct device *dev) + + efx_device_attach_if_not_resetting(efx); + +- efx->state = STATE_READY; ++ efx->state = efx_thaw(efx->state); + + efx->type->resume_wol(efx); + } +diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c +index 896b592531972..7c90e1e2d161b 100644 +--- a/drivers/net/ethernet/sfc/efx_common.c ++++ b/drivers/net/ethernet/sfc/efx_common.c +@@ -897,7 +897,7 @@ static void efx_reset_work(struct work_struct *data) + * have changed by now. Now that we have the RTNL lock, + * it cannot change again. + */ +- if (efx->state == STATE_READY) ++ if (efx_net_active(efx->state)) + (void)efx_reset(efx, method); + + rtnl_unlock(); +@@ -907,7 +907,7 @@ void efx_schedule_reset(struct efx_nic *efx, enum reset_type type) + { + enum reset_type method; + +- if (efx->state == STATE_RECOVERY) { ++ if (efx_recovering(efx->state)) { + netif_dbg(efx, drv, efx->net_dev, + "recovering: skip scheduling %s reset\n", + RESET_TYPE(type)); +@@ -942,7 +942,7 @@ void efx_schedule_reset(struct efx_nic *efx, enum reset_type type) + /* If we're not READY then just leave the flags set as the cue + * to abort probing or reschedule the reset later. + */ +- if (READ_ONCE(efx->state) != STATE_READY) ++ if (!efx_net_active(READ_ONCE(efx->state))) + return; + + /* efx_process_channel() will no longer read events once a +@@ -1216,7 +1216,7 @@ static pci_ers_result_t efx_io_error_detected(struct pci_dev *pdev, + rtnl_lock(); + + if (efx->state != STATE_DISABLED) { +- efx->state = STATE_RECOVERY; ++ efx->state = efx_recover(efx->state); + efx->reset_pending = 0; + + efx_device_detach_sync(efx); +@@ -1270,7 +1270,7 @@ static void efx_io_resume(struct pci_dev *pdev) + netif_err(efx, hw, efx->net_dev, + "efx_reset failed after PCI error (%d)\n", rc); + } else { +- efx->state = STATE_READY; ++ efx->state = efx_recovered(efx->state); + netif_dbg(efx, hw, efx->net_dev, + "Done resetting and resuming IO after PCI error.\n"); + } +diff --git a/drivers/net/ethernet/sfc/efx_common.h b/drivers/net/ethernet/sfc/efx_common.h +index 65513fd0cf6c4..c72e819da8fd3 100644 +--- a/drivers/net/ethernet/sfc/efx_common.h ++++ b/drivers/net/ethernet/sfc/efx_common.h +@@ -45,9 +45,7 @@ int efx_reconfigure_port(struct efx_nic *efx); + + #define EFX_ASSERT_RESET_SERIALISED(efx) \ + do { \ +- if ((efx->state == STATE_READY) || \ +- (efx->state == STATE_RECOVERY) || \ +- (efx->state == STATE_DISABLED)) \ ++ if (efx->state != STATE_UNINIT) \ + ASSERT_RTNL(); \ + } while (0) + +@@ -64,7 +62,7 @@ void efx_port_dummy_op_void(struct efx_nic *efx); + + static inline int efx_check_disabled(struct efx_nic *efx) + { +- if (efx->state == STATE_DISABLED || efx->state == STATE_RECOVERY) { ++ if (efx->state == STATE_DISABLED || efx_recovering(efx->state)) { + netif_err(efx, drv, efx->net_dev, + "device is disabled due to earlier errors\n"); + return -EIO; +diff --git a/drivers/net/ethernet/sfc/ethtool_common.c b/drivers/net/ethernet/sfc/ethtool_common.c +index bd552c7dffcb1..3846b76b89720 100644 +--- a/drivers/net/ethernet/sfc/ethtool_common.c ++++ b/drivers/net/ethernet/sfc/ethtool_common.c +@@ -137,7 +137,7 @@ void efx_ethtool_self_test(struct net_device *net_dev, + if (!efx_tests) + goto fail; + +- if (efx->state != STATE_READY) { ++ if (!efx_net_active(efx->state)) { + rc = -EBUSY; + goto out; + } +diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h +index bf097264d8fbe..6df500dbb6b7f 100644 +--- a/drivers/net/ethernet/sfc/net_driver.h ++++ b/drivers/net/ethernet/sfc/net_driver.h +@@ -627,12 +627,54 @@ enum efx_int_mode { + #define EFX_INT_MODE_USE_MSI(x) (((x)->interrupt_mode) <= EFX_INT_MODE_MSI) + + enum nic_state { +- STATE_UNINIT = 0, /* device being probed/removed or is frozen */ +- STATE_READY = 1, /* hardware ready and netdev registered */ +- STATE_DISABLED = 2, /* device disabled due to hardware errors */ +- STATE_RECOVERY = 3, /* device recovering from PCI error */ ++ STATE_UNINIT = 0, /* device being probed/removed */ ++ STATE_NET_DOWN, /* hardware probed and netdev registered */ ++ STATE_NET_UP, /* ready for traffic */ ++ STATE_DISABLED, /* device disabled due to hardware errors */ ++ ++ STATE_RECOVERY = 0x100,/* recovering from PCI error */ ++ STATE_FROZEN = 0x200, /* frozen by power management */ + }; + ++static inline bool efx_net_active(enum nic_state state) ++{ ++ return state == STATE_NET_DOWN || state == STATE_NET_UP; ++} ++ ++static inline bool efx_frozen(enum nic_state state) ++{ ++ return state & STATE_FROZEN; ++} ++ ++static inline bool efx_recovering(enum nic_state state) ++{ ++ return state & STATE_RECOVERY; ++} ++ ++static inline enum nic_state efx_freeze(enum nic_state state) ++{ ++ WARN_ON(!efx_net_active(state)); ++ return state | STATE_FROZEN; ++} ++ ++static inline enum nic_state efx_thaw(enum nic_state state) ++{ ++ WARN_ON(!efx_frozen(state)); ++ return state & ~STATE_FROZEN; ++} ++ ++static inline enum nic_state efx_recover(enum nic_state state) ++{ ++ WARN_ON(!efx_net_active(state)); ++ return state | STATE_RECOVERY; ++} ++ ++static inline enum nic_state efx_recovered(enum nic_state state) ++{ ++ WARN_ON(!efx_recovering(state)); ++ return state & ~STATE_RECOVERY; ++} ++ + /* Forward declaration */ + struct efx_nic; + +-- +2.39.2 + diff --git a/queue-5.15/spi-spi-rockchip-fix-missing-unwind-goto-in-rockchip.patch b/queue-5.15/spi-spi-rockchip-fix-missing-unwind-goto-in-rockchip.patch new file mode 100644 index 00000000000..0380b281823 --- /dev/null +++ b/queue-5.15/spi-spi-rockchip-fix-missing-unwind-goto-in-rockchip.patch @@ -0,0 +1,40 @@ +From c8c4d529b469df17a27ed73d5e81479b402cb0e8 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 19 Apr 2023 07:50:29 -0400 +Subject: spi: spi-rockchip: Fix missing unwind goto in rockchip_sfc_probe() + +From: Li Lanzhe + +[ Upstream commit 359f5b0d4e26b7a7bcc574d6148b31a17cefe47d ] + +If devm_request_irq() fails, then we are directly return 'ret' without +clk_disable_unprepare(sfc->clk) and clk_disable_unprepare(sfc->hclk). + +Fix this by changing direct return to a goto 'err_irq'. + +Fixes: 0b89fc0a367e ("spi: rockchip-sfc: add rockchip serial flash controller") +Signed-off-by: Li Lanzhe +Reviewed-by: Dongliang Mu +Link: https://lore.kernel.org/r/20230419115030.6029-1-u202212060@hust.edu.cn +Signed-off-by: Mark Brown +Signed-off-by: Sasha Levin +--- + drivers/spi/spi-rockchip-sfc.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/spi/spi-rockchip-sfc.c b/drivers/spi/spi-rockchip-sfc.c +index a46b385440273..014106f8f978c 100644 +--- a/drivers/spi/spi-rockchip-sfc.c ++++ b/drivers/spi/spi-rockchip-sfc.c +@@ -634,7 +634,7 @@ static int rockchip_sfc_probe(struct platform_device *pdev) + if (ret) { + dev_err(dev, "Failed to request irq\n"); + +- return ret; ++ goto err_irq; + } + + ret = rockchip_sfc_init(sfc); +-- +2.39.2 + diff --git a/queue-5.15/virtio_net-bugfix-overflow-inside-xdp_linearize_page.patch b/queue-5.15/virtio_net-bugfix-overflow-inside-xdp_linearize_page.patch new file mode 100644 index 00000000000..b90c18c37bb --- /dev/null +++ b/queue-5.15/virtio_net-bugfix-overflow-inside-xdp_linearize_page.patch @@ -0,0 +1,59 @@ +From c2cc6b1c8d4e0addab770956ef43e9331054d709 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 14 Apr 2023 14:08:35 +0800 +Subject: virtio_net: bugfix overflow inside xdp_linearize_page() + +From: Xuan Zhuo + +[ Upstream commit 853618d5886bf94812f31228091cd37d308230f7 ] + +Here we copy the data from the original buf to the new page. But we +not check that it may be overflow. + +As long as the size received(including vnethdr) is greater than 3840 +(PAGE_SIZE -VIRTIO_XDP_HEADROOM). Then the memcpy will overflow. + +And this is completely possible, as long as the MTU is large, such +as 4096. In our test environment, this will cause crash. Since crash is +caused by the written memory, it is meaningless, so I do not include it. + +Fixes: 72979a6c3590 ("virtio_net: xdp, add slowpath case for non contiguous buffers") +Signed-off-by: Xuan Zhuo +Acked-by: Jason Wang +Acked-by: Michael S. Tsirkin +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/virtio_net.c | 8 ++++++-- + 1 file changed, 6 insertions(+), 2 deletions(-) + +diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c +index 66ca2ea19ba60..8a380086ac257 100644 +--- a/drivers/net/virtio_net.c ++++ b/drivers/net/virtio_net.c +@@ -679,8 +679,13 @@ static struct page *xdp_linearize_page(struct receive_queue *rq, + int page_off, + unsigned int *len) + { +- struct page *page = alloc_page(GFP_ATOMIC); ++ int tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); ++ struct page *page; + ++ if (page_off + *len + tailroom > PAGE_SIZE) ++ return NULL; ++ ++ page = alloc_page(GFP_ATOMIC); + if (!page) + return NULL; + +@@ -688,7 +693,6 @@ static struct page *xdp_linearize_page(struct receive_queue *rq, + page_off += *len; + + while (--*num_buf) { +- int tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + unsigned int buflen; + void *buf; + int off; +-- +2.39.2 + diff --git a/queue-5.15/xen-netback-use-same-error-messages-for-same-errors.patch b/queue-5.15/xen-netback-use-same-error-messages-for-same-errors.patch new file mode 100644 index 00000000000..80a23379000 --- /dev/null +++ b/queue-5.15/xen-netback-use-same-error-messages-for-same-errors.patch @@ -0,0 +1,42 @@ +From 875fca353793e8c878c12c3c11083ac149eb46c4 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 29 Mar 2023 10:02:59 +0200 +Subject: xen/netback: use same error messages for same errors + +From: Juergen Gross + +[ Upstream commit 2eca98e5b24d01c02b46c67be05a5f98cc9789b1 ] + +Issue the same error message in case an illegal page boundary crossing +has been detected in both cases where this is tested. + +Suggested-by: Jan Beulich +Signed-off-by: Juergen Gross +Reviewed-by: Jan Beulich +Link: https://lore.kernel.org/r/20230329080259.14823-1-jgross@suse.com +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + drivers/net/xen-netback/netback.c | 6 ++---- + 1 file changed, 2 insertions(+), 4 deletions(-) + +diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c +index 303d8ebbaafc4..63118b56c5289 100644 +--- a/drivers/net/xen-netback/netback.c ++++ b/drivers/net/xen-netback/netback.c +@@ -996,10 +996,8 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, + + /* No crossing a page as the payload mustn't fragment. */ + if (unlikely((txreq.offset + txreq.size) > XEN_PAGE_SIZE)) { +- netdev_err(queue->vif->dev, +- "txreq.offset: %u, size: %u, end: %lu\n", +- txreq.offset, txreq.size, +- (unsigned long)(txreq.offset&~XEN_PAGE_MASK) + txreq.size); ++ netdev_err(queue->vif->dev, "Cross page boundary, txreq.offset: %u, size: %u\n", ++ txreq.offset, txreq.size); + xenvif_fatal_tx_err(queue->vif); + break; + } +-- +2.39.2 +