From: Lucas Stach l.stach@pengutronix.de

[ Upstream commit d37c120b73128690434cc093952439eef9d56af1 ]

While the interface for the MMU mapping takes phys_addr_t to hold a full 64bit address when necessary and MMUv2 is able to map physical addresses with up to 40bit, etnaviv_iommu_map() truncates the address to 32bits. Fix this by using the correct type.

Fixes: 931e97f3afd8 ("drm/etnaviv: mmuv2: support 40 bit phys address") Signed-off-by: Lucas Stach l.stach@pengutronix.de Reviewed-by: Philipp Zabel p.zabel@pengutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/etnaviv/etnaviv_mmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c index 9ba2fe48228f1..44fbc0a123bf3 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c @@ -80,10 +80,10 @@ static int etnaviv_iommu_map(struct etnaviv_iommu_context *context, u32 iova, return -EINVAL;

for_each_sgtable_dma_sg(sgt, sg, i) { - u32 pa = sg_dma_address(sg) - sg->offset; + phys_addr_t pa = sg_dma_address(sg) - sg->offset; size_t bytes = sg_dma_len(sg) + sg->offset;

- VERB("map[%d]: %08x %08x(%zx)", i, iova, pa, bytes); + VERB("map[%d]: %08x %pap(%zx)", i, iova, &pa, bytes);

ret = etnaviv_context_map(context, da, pa, bytes, prot); if (ret)

From: Rahul Tanwar rtanwar@maxlinear.com

[ Upstream commit 036177310bac5534de44ff6a7b60a4d2c0b6567c ]

Earlier version of driver used direct io remapped register read writes using readl/writel. But we need secure boot access which is only possible when registers are read & written using regmap. This is because the security bus/hook is written & coupled only with regmap layer.

Switch the driver from direct readl/writel based register accesses to regmap based register accesses.

Additionally, update the license headers to latest status.

Reviewed-by: Yi xin Zhu yzhu@maxlinear.com Signed-off-by: Rahul Tanwar rtanwar@maxlinear.com Link: https://lore.kernel.org/r/2610331918206e0e3bd18babb39393a558fb34f9.166564272... Signed-off-by: Stephen Boyd sboyd@kernel.org Stable-dep-of: 106ef3bda210 ("clk: mxl: Fix a clk entry by adding relevant flags") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/clk/x86/Kconfig | 5 +++-- drivers/clk/x86/clk-cgu-pll.c | 10 +++++---- drivers/clk/x86/clk-cgu.c | 5 +++-- drivers/clk/x86/clk-cgu.h | 38 +++++++++++++++++++---------------- drivers/clk/x86/clk-lgm.c | 13 ++++++++---- 5 files changed, 42 insertions(+), 29 deletions(-)

diff --git a/drivers/clk/x86/Kconfig b/drivers/clk/x86/Kconfig index 69642e15fcc1f..ced99e082e3dd 100644 --- a/drivers/clk/x86/Kconfig +++ b/drivers/clk/x86/Kconfig @@ -1,8 +1,9 @@ # SPDX-License-Identifier: GPL-2.0-only config CLK_LGM_CGU depends on OF && HAS_IOMEM && (X86 || COMPILE_TEST) + select MFD_SYSCON select OF_EARLY_FLATTREE bool "Clock driver for Lightning Mountain(LGM) platform" help - Clock Generation Unit(CGU) driver for Intel Lightning Mountain(LGM) - network processor SoC. + Clock Generation Unit(CGU) driver for MaxLinear's x86 based + Lightning Mountain(LGM) network processor SoC. diff --git a/drivers/clk/x86/clk-cgu-pll.c b/drivers/clk/x86/clk-cgu-pll.c index 3179557b5f784..c83083affe88e 100644 --- a/drivers/clk/x86/clk-cgu-pll.c +++ b/drivers/clk/x86/clk-cgu-pll.c @@ -1,8 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (C) 2020-2022 MaxLinear, Inc. * Copyright (C) 2020 Intel Corporation. - * Zhu YiXin yixin.zhu@intel.com - * Rahul Tanwar rahul.tanwar@intel.com + * Zhu Yixin yzhu@maxlinear.com + * Rahul Tanwar rtanwar@maxlinear.com */

#include <linux/clk-provider.h> @@ -76,8 +77,9 @@ static int lgm_pll_enable(struct clk_hw *hw)

spin_lock_irqsave(&pll->lock, flags); lgm_set_clk_val(pll->membase, pll->reg, 0, 1, 1); - ret = readl_poll_timeout_atomic(pll->membase + pll->reg, - val, (val & 0x1), 1, 100); + ret = regmap_read_poll_timeout_atomic(pll->membase, pll->reg, + val, (val & 0x1), 1, 100); + spin_unlock_irqrestore(&pll->lock, flags);

return ret; diff --git a/drivers/clk/x86/clk-cgu.c b/drivers/clk/x86/clk-cgu.c index 33de600e0c38e..f5f30a18f4869 100644 --- a/drivers/clk/x86/clk-cgu.c +++ b/drivers/clk/x86/clk-cgu.c @@ -1,8 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (C) 2020-2022 MaxLinear, Inc. * Copyright (C) 2020 Intel Corporation. - * Zhu YiXin yixin.zhu@intel.com - * Rahul Tanwar rahul.tanwar@intel.com + * Zhu Yixin yzhu@maxlinear.com + * Rahul Tanwar rtanwar@maxlinear.com */ #include <linux/clk-provider.h> #include <linux/device.h> diff --git a/drivers/clk/x86/clk-cgu.h b/drivers/clk/x86/clk-cgu.h index 4e22bfb223128..dbcb664687975 100644 --- a/drivers/clk/x86/clk-cgu.h +++ b/drivers/clk/x86/clk-cgu.h @@ -1,18 +1,19 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * Copyright(c) 2020 Intel Corporation. - * Zhu YiXin yixin.zhu@intel.com - * Rahul Tanwar rahul.tanwar@intel.com + * Copyright (C) 2020-2022 MaxLinear, Inc. + * Copyright (C) 2020 Intel Corporation. + * Zhu Yixin yzhu@maxlinear.com + * Rahul Tanwar rtanwar@maxlinear.com */

#ifndef __CLK_CGU_H #define __CLK_CGU_H

-#include <linux/io.h> +#include <linux/regmap.h>

struct lgm_clk_mux { struct clk_hw hw; - void __iomem *membase; + struct regmap *membase; unsigned int reg; u8 shift; u8 width; @@ -22,7 +23,7 @@ struct lgm_clk_mux {

struct lgm_clk_divider { struct clk_hw hw; - void __iomem *membase; + struct regmap *membase; unsigned int reg; u8 shift; u8 width; @@ -35,7 +36,7 @@ struct lgm_clk_divider {

struct lgm_clk_ddiv { struct clk_hw hw; - void __iomem *membase; + struct regmap *membase; unsigned int reg; u8 shift0; u8 width0; @@ -53,7 +54,7 @@ struct lgm_clk_ddiv {

struct lgm_clk_gate { struct clk_hw hw; - void __iomem *membase; + struct regmap *membase; unsigned int reg; u8 shift; unsigned long flags; @@ -77,7 +78,7 @@ enum lgm_clk_type { * @clk_data: array of hw clocks and clk number. */ struct lgm_clk_provider { - void __iomem *membase; + struct regmap *membase; struct device_node *np; struct device *dev; struct clk_hw_onecell_data clk_data; @@ -92,7 +93,7 @@ enum pll_type {

struct lgm_clk_pll { struct clk_hw hw; - void __iomem *membase; + struct regmap *membase; unsigned int reg; unsigned long flags; enum pll_type type; @@ -300,29 +301,32 @@ struct lgm_clk_branch { .div = _d, \ }

-static inline void lgm_set_clk_val(void __iomem *membase, u32 reg, +static inline void lgm_set_clk_val(struct regmap *membase, u32 reg, u8 shift, u8 width, u32 set_val) { u32 mask = (GENMASK(width - 1, 0) << shift); - u32 regval;

- regval = readl(membase + reg); - regval = (regval & ~mask) | ((set_val << shift) & mask); - writel(regval, membase + reg); + regmap_update_bits(membase, reg, mask, set_val << shift); }

-static inline u32 lgm_get_clk_val(void __iomem *membase, u32 reg, +static inline u32 lgm_get_clk_val(struct regmap *membase, u32 reg, u8 shift, u8 width) { u32 mask = (GENMASK(width - 1, 0) << shift); u32 val;

- val = readl(membase + reg); + if (regmap_read(membase, reg, &val)) { + WARN_ONCE(1, "Failed to read clk reg: 0x%x\n", reg); + return 0; + } + val = (val & mask) >> shift;

return val; }

+ + int lgm_clk_register_branches(struct lgm_clk_provider *ctx, const struct lgm_clk_branch *list, unsigned int nr_clk); diff --git a/drivers/clk/x86/clk-lgm.c b/drivers/clk/x86/clk-lgm.c index 020f4e83a5ccb..4fa2bcaf71c89 100644 --- a/drivers/clk/x86/clk-lgm.c +++ b/drivers/clk/x86/clk-lgm.c @@ -1,10 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (C) 2020-2022 MaxLinear, Inc. * Copyright (C) 2020 Intel Corporation. - * Zhu YiXin yixin.zhu@intel.com - * Rahul Tanwar rahul.tanwar@intel.com + * Zhu Yixin yzhu@maxlinear.com + * Rahul Tanwar rtanwar@maxlinear.com */ #include <linux/clk-provider.h> +#include <linux/mfd/syscon.h> #include <linux/of.h> #include <linux/platform_device.h> #include <dt-bindings/clock/intel,lgm-clk.h> @@ -433,9 +435,12 @@ static int lgm_cgu_probe(struct platform_device *pdev)

ctx->clk_data.num = CLK_NR_CLKS;

- ctx->membase = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(ctx->membase)) + ctx->membase = syscon_node_to_regmap(np); + if (IS_ERR_OR_NULL(ctx->membase)) { + dev_err(dev, "Failed to get clk CGU iomem\n"); return PTR_ERR(ctx->membase); + } +

ctx->np = np; ctx->dev = dev;

From: Rahul Tanwar rtanwar@maxlinear.com

[ Upstream commit a5d49bd369b8588c0ee9d4d0a2c0160558a3ab69 ]

In MxL's LGM SoC, gate clocks can be controlled either from CGU clk driver i.e. this driver or directly from power management driver/daemon. It is dependent on the power policy/profile requirements of the end product.

To support such use cases, provide option to override gate clks enable/disable by adding a flag GATE_CLK_HW which controls if these gate clks are controlled by HW i.e. this driver or overridden in order to allow it to be controlled by power profiles instead.

Reviewed-by: Yi xin Zhu yzhu@maxlinear.com Signed-off-by: Rahul Tanwar rtanwar@maxlinear.com Link: https://lore.kernel.org/r/bdc9c89317b5d338a6c4f1d49386b696e947a672.166564272... [sboyd@kernel.org: Add braces on many line if-else] Signed-off-by: Stephen Boyd sboyd@kernel.org Stable-dep-of: 106ef3bda210 ("clk: mxl: Fix a clk entry by adding relevant flags") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/clk/x86/clk-cgu.c | 16 +++++++++++++++- drivers/clk/x86/clk-cgu.h | 1 + 2 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/clk/x86/clk-cgu.c b/drivers/clk/x86/clk-cgu.c index 1f7e93de67bc0..4278a687076c9 100644 --- a/drivers/clk/x86/clk-cgu.c +++ b/drivers/clk/x86/clk-cgu.c @@ -354,8 +354,22 @@ int lgm_clk_register_branches(struct lgm_clk_provider *ctx, hw = lgm_clk_register_fixed_factor(ctx, list); break; case CLK_TYPE_GATE: - hw = lgm_clk_register_gate(ctx, list); + if (list->gate_flags & GATE_CLK_HW) { + hw = lgm_clk_register_gate(ctx, list); + } else { + /* + * GATE_CLKs can be controlled either from + * CGU clk driver i.e. this driver or directly + * from power management driver/daemon. It is + * dependent on the power policy/profile requirements + * of the end product. To override control of gate + * clks from this driver, provide NULL for this index + * of gate clk provider. + */ + hw = NULL; + } break; + default: dev_err(ctx->dev, "invalid clk type\n"); return -EINVAL; diff --git a/drivers/clk/x86/clk-cgu.h b/drivers/clk/x86/clk-cgu.h index 0aa0f35d63a0b..73ce84345f81e 100644 --- a/drivers/clk/x86/clk-cgu.h +++ b/drivers/clk/x86/clk-cgu.h @@ -197,6 +197,7 @@ struct lgm_clk_branch { /* clock flags definition */ #define CLOCK_FLAG_VAL_INIT BIT(16) #define MUX_CLK_SW BIT(17) +#define GATE_CLK_HW BIT(18)

#define LGM_MUX(_id, _name, _pdata, _f, _reg, \ _shift, _width, _cf, _v) \

From: Sean Anderson sean.anderson@seco.com

[ Upstream commit 36926a7d70c2d462fca1ed85bfee000d17fd8662 ]

On the T208X SoCs, MAC1 and MAC2 support XGMII. Add some new MAC dtsi fragments, and mark the QMAN ports as 10G.

Fixes: da414bb923d9 ("powerpc/mpc85xx: Add FSL QorIQ DPAA FMan support to the SoC device tree(s)") Signed-off-by: Sean Anderson sean.anderson@seco.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- .../boot/dts/fsl/qoriq-fman3-0-10g-2.dtsi | 44 +++++++++++++++++++ .../boot/dts/fsl/qoriq-fman3-0-10g-3.dtsi | 44 +++++++++++++++++++ arch/powerpc/boot/dts/fsl/t2081si-post.dtsi | 4 +- 3 files changed, 90 insertions(+), 2 deletions(-) create mode 100644 arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-2.dtsi create mode 100644 arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-3.dtsi

diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-2.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-2.dtsi new file mode 100644 index 0000000000000..437dab3fc0176 --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-2.dtsi @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0-or-later +/* + * QorIQ FMan v3 10g port #2 device tree stub [ controller @ offset 0x400000 ] + * + * Copyright 2022 Sean Anderson sean.anderson@seco.com + * Copyright 2012 - 2015 Freescale Semiconductor Inc. + */ + +fman@400000 { + fman0_rx_0x08: port@88000 { + cell-index = <0x8>; + compatible = "fsl,fman-v3-port-rx"; + reg = <0x88000 0x1000>; + fsl,fman-10g-port; + }; + + fman0_tx_0x28: port@a8000 { + cell-index = <0x28>; + compatible = "fsl,fman-v3-port-tx"; + reg = <0xa8000 0x1000>; + fsl,fman-10g-port; + }; + + ethernet@e0000 { + cell-index = <0>; + compatible = "fsl,fman-memac"; + reg = <0xe0000 0x1000>; + fsl,fman-ports = <&fman0_rx_0x08 &fman0_tx_0x28>; + ptp-timer = <&ptp_timer0>; + pcsphy-handle = <&pcsphy0>; + }; + + mdio@e1000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; + reg = <0xe1000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ + + pcsphy0: ethernet-phy@0 { + reg = <0x0>; + }; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-3.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-3.dtsi new file mode 100644 index 0000000000000..ad116b17850a8 --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-3.dtsi @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0-or-later +/* + * QorIQ FMan v3 10g port #3 device tree stub [ controller @ offset 0x400000 ] + * + * Copyright 2022 Sean Anderson sean.anderson@seco.com + * Copyright 2012 - 2015 Freescale Semiconductor Inc. + */ + +fman@400000 { + fman0_rx_0x09: port@89000 { + cell-index = <0x9>; + compatible = "fsl,fman-v3-port-rx"; + reg = <0x89000 0x1000>; + fsl,fman-10g-port; + }; + + fman0_tx_0x29: port@a9000 { + cell-index = <0x29>; + compatible = "fsl,fman-v3-port-tx"; + reg = <0xa9000 0x1000>; + fsl,fman-10g-port; + }; + + ethernet@e2000 { + cell-index = <1>; + compatible = "fsl,fman-memac"; + reg = <0xe2000 0x1000>; + fsl,fman-ports = <&fman0_rx_0x09 &fman0_tx_0x29>; + ptp-timer = <&ptp_timer0>; + pcsphy-handle = <&pcsphy1>; + }; + + mdio@e3000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio"; + reg = <0xe3000 0x1000>; + fsl,erratum-a011043; /* must ignore read errors */ + + pcsphy1: ethernet-phy@0 { + reg = <0x0>; + }; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi index ecbb447920bc6..74e17e134387d 100644 --- a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi @@ -609,8 +609,8 @@ /include/ "qoriq-bman1.dtsi"

/include/ "qoriq-fman3-0.dtsi" -/include/ "qoriq-fman3-0-1g-0.dtsi" -/include/ "qoriq-fman3-0-1g-1.dtsi" +/include/ "qoriq-fman3-0-10g-2.dtsi" +/include/ "qoriq-fman3-0-10g-3.dtsi" /include/ "qoriq-fman3-0-1g-2.dtsi" /include/ "qoriq-fman3-0-1g-3.dtsi" /include/ "qoriq-fman3-0-1g-4.dtsi"

From: Jason A. Donenfeld Jason@zx2c4.com

[ Upstream commit d7bf7f3b813e3755226bcb5114ad2ac477514ebf ]

add_latent_entropy() is called every time a process forks, in kernel_clone(). This in turn calls add_device_randomness() using the latent entropy global state. add_device_randomness() does two things:

2) Mixes into the input pool the latent entropy argument passed; and 1) Mixes in a cycle counter, a sort of measurement of when the event took place, the high precision bits of which are presumably difficult to predict.

(2) is impossible without CONFIG_GCC_PLUGIN_LATENT_ENTROPY=y. But (1) is always possible. However, currently CONFIG_GCC_PLUGIN_LATENT_ENTROPY=n disables both (1) and (2), instead of just (2).

This commit causes the CONFIG_GCC_PLUGIN_LATENT_ENTROPY=n case to still do (1) by passing NULL (len 0) to add_device_randomness() when add_latent_ entropy() is called.

Cc: Dominik Brodowski linux@dominikbrodowski.net Cc: PaX Team pageexec@freemail.hu Cc: Emese Revfy re.emese@gmail.com Fixes: 38addce8b600 ("gcc-plugins: Add latent_entropy plugin") Signed-off-by: Jason A. Donenfeld Jason@zx2c4.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/random.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/linux/random.h b/include/linux/random.h index 917470c4490ac..ed2bac6c7a8ac 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -19,14 +19,14 @@ void add_input_randomness(unsigned int type, unsigned int code, void add_interrupt_randomness(int irq) __latent_entropy; void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy);

-#if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) static inline void add_latent_entropy(void) { +#if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) add_device_randomness((const void *)&latent_entropy, sizeof(latent_entropy)); -} #else -static inline void add_latent_entropy(void) { } + add_device_randomness(NULL, 0); #endif +}

void get_random_bytes(void *buf, size_t len); size_t __must_check get_random_bytes_arch(void *buf, size_t len);

From: Sean Christopherson seanjc@google.com

[ Upstream commit 5c30e8101e8d5d020b1d7119117889756a6ed713 ]

Skip the WRMSR fastpath in SVM's VM-Exit handler if the next RIP isn't valid, e.g. because KVM is running with nrips=false. SVM must decode and emulate to skip the WRMSR if the CPU doesn't provide the next RIP. Getting the instruction bytes to decode the WRMSR requires reading guest memory, which in turn means dereferencing memslots, and that isn't safe because KVM doesn't hold SRCU when the fastpath runs.

Don't bother trying to enable the fastpath for this case, e.g. by doing only the WRMSR and leaving the "skip" until later. NRIPS is supported on all modern CPUs (KVM has considered making it mandatory), and the next RIP will be valid the vast, vast majority of the time.

============================= WARNING: suspicious RCU usage 6.0.0-smp--4e557fcd3d80-skip #13 Tainted: G O ----------------------------- include/linux/kvm_host.h:954 suspicious rcu_dereference_check() usage!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1 1 lock held by stable/206475: #0: ffff9d9dfebcc0f0 (&vcpu->mutex){+.+.}-{3:3}, at: kvm_vcpu_ioctl+0x8b/0x620 [kvm]

stack backtrace: CPU: 152 PID: 206475 Comm: stable Tainted: G O 6.0.0-smp--4e557fcd3d80-skip #13 Hardware name: Google, Inc. Arcadia_IT_80/Arcadia_IT_80, BIOS 10.48.0 01/27/2022 Call Trace: <TASK> dump_stack_lvl+0x69/0xaa dump_stack+0x10/0x12 lockdep_rcu_suspicious+0x11e/0x130 kvm_vcpu_gfn_to_memslot+0x155/0x190 [kvm] kvm_vcpu_gfn_to_hva_prot+0x18/0x80 [kvm] paging64_walk_addr_generic+0x183/0x450 [kvm] paging64_gva_to_gpa+0x63/0xd0 [kvm] kvm_fetch_guest_virt+0x53/0xc0 [kvm] __do_insn_fetch_bytes+0x18b/0x1c0 [kvm] x86_decode_insn+0xf0/0xef0 [kvm] x86_emulate_instruction+0xba/0x790 [kvm] kvm_emulate_instruction+0x17/0x20 [kvm] __svm_skip_emulated_instruction+0x85/0x100 [kvm_amd] svm_skip_emulated_instruction+0x13/0x20 [kvm_amd] handle_fastpath_set_msr_irqoff+0xae/0x180 [kvm] svm_vcpu_run+0x4b8/0x5a0 [kvm_amd] vcpu_enter_guest+0x16ca/0x22f0 [kvm] kvm_arch_vcpu_ioctl_run+0x39d/0x900 [kvm] kvm_vcpu_ioctl+0x538/0x620 [kvm] __se_sys_ioctl+0x77/0xc0 __x64_sys_ioctl+0x1d/0x20 do_syscall_64+0x3d/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd

Fixes: 404d5d7bff0d ("KVM: X86: Introduce more exit_fastpath_completion enum values") Signed-off-by: Sean Christopherson seanjc@google.com Link: https://lore.kernel.org/r/20220930234031.1732249-1-seanjc@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/svm/svm.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index c34ba034ca111..5775983fec56e 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3480,8 +3480,14 @@ static void svm_cancel_injection(struct kvm_vcpu *vcpu)

static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) { - if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR && - to_svm(vcpu)->vmcb->control.exit_info_1) + struct vmcb_control_area *control = &to_svm(vcpu)->vmcb->control; + + /* + * Note, the next RIP must be provided as SRCU isn't held, i.e. KVM + * can't read guest memory (dereference memslots) to decode the WRMSR. + */ + if (control->exit_code == SVM_EXIT_MSR && control->exit_info_1 && + nrips && control->next_rip) return handle_fastpath_set_msr_irqoff(vcpu);

return EXIT_FASTPATH_NONE;

From: Marc Kleine-Budde mkl@pengutronix.de

[ Upstream commit f006229135b7debf4037adb1eb93e358559593db ]

Debian's gcc-13 [1] throws the following error in kvaser_usb_hydra_cmd_size():

[1] gcc version 13.0.0 20221214 (experimental) [master r13-4693-g512098a3316] (Debian 13-20221214-1)

| drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c:502:65: error: | array subscript ‘struct kvaser_cmd_ext[0]’ is partly outside array | bounds of ‘unsigned char[32]’ [-Werror=array-bounds=] | 502 | ret = le16_to_cpu(((struct kvaser_cmd_ext *)cmd)->len);

kvaser_usb_hydra_cmd_size() returns the size of given command. It depends on the command number (cmd->header.cmd_no). For extended commands (cmd->header.cmd_no == CMD_EXTENDED) the above shown code is executed.

Help gcc to recognize that this code path is not taken in all cases, by calling kvaser_usb_hydra_cmd_size() directly after assigning the command number.

Fixes: aec5fb2268b7 ("can: kvaser_usb: Add support for Kvaser USB hydra family") Cc: Jimmy Assarsson extja@kvaser.com Cc: Anssi Hannula anssi.hannula@bitwise.fi Link: https://lore.kernel.org/all/20221219110104.1073881-1-mkl@pengutronix.de Tested-by: Jimmy Assarsson extja@kvaser.com Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/can/usb/kvaser_usb/kvaser_usb_hydra.c | 33 ++++++++++++++----- 1 file changed, 24 insertions(+), 9 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c index 2764fdd7e84b3..233bbfeaa771e 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c @@ -518,6 +518,7 @@ static int kvaser_usb_hydra_send_simple_cmd(struct kvaser_usb *dev, u8 cmd_no, int channel) { struct kvaser_cmd *cmd; + size_t cmd_len; int err;

cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL); @@ -525,6 +526,7 @@ static int kvaser_usb_hydra_send_simple_cmd(struct kvaser_usb *dev, return -ENOMEM;

cmd->header.cmd_no = cmd_no; + cmd_len = kvaser_usb_hydra_cmd_size(cmd); if (channel < 0) { kvaser_usb_hydra_set_cmd_dest_he (cmd, KVASER_USB_HYDRA_HE_ADDRESS_ILLEGAL); @@ -541,7 +543,7 @@ static int kvaser_usb_hydra_send_simple_cmd(struct kvaser_usb *dev, kvaser_usb_hydra_set_cmd_transid (cmd, kvaser_usb_hydra_get_next_transid(dev));

- err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + err = kvaser_usb_send_cmd(dev, cmd, cmd_len); if (err) goto end;

@@ -557,6 +559,7 @@ kvaser_usb_hydra_send_simple_cmd_async(struct kvaser_usb_net_priv *priv, { struct kvaser_cmd *cmd; struct kvaser_usb *dev = priv->dev; + size_t cmd_len; int err;

cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_ATOMIC); @@ -564,14 +567,14 @@ kvaser_usb_hydra_send_simple_cmd_async(struct kvaser_usb_net_priv *priv, return -ENOMEM;

cmd->header.cmd_no = cmd_no; + cmd_len = kvaser_usb_hydra_cmd_size(cmd);

kvaser_usb_hydra_set_cmd_dest_he (cmd, dev->card_data.hydra.channel_to_he[priv->channel]); kvaser_usb_hydra_set_cmd_transid (cmd, kvaser_usb_hydra_get_next_transid(dev));

- err = kvaser_usb_send_cmd_async(priv, cmd, - kvaser_usb_hydra_cmd_size(cmd)); + err = kvaser_usb_send_cmd_async(priv, cmd, cmd_len); if (err) kfree(cmd);

@@ -715,6 +718,7 @@ static int kvaser_usb_hydra_get_single_capability(struct kvaser_usb *dev, { struct kvaser_usb_dev_card_data *card_data = &dev->card_data; struct kvaser_cmd *cmd; + size_t cmd_len; u32 value = 0; u32 mask = 0; u16 cap_cmd_res; @@ -726,13 +730,14 @@ static int kvaser_usb_hydra_get_single_capability(struct kvaser_usb *dev, return -ENOMEM;

cmd->header.cmd_no = CMD_GET_CAPABILITIES_REQ; + cmd_len = kvaser_usb_hydra_cmd_size(cmd); cmd->cap_req.cap_cmd = cpu_to_le16(cap_cmd_req);

kvaser_usb_hydra_set_cmd_dest_he(cmd, card_data->hydra.sysdbg_he); kvaser_usb_hydra_set_cmd_transid (cmd, kvaser_usb_hydra_get_next_transid(dev));

- err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + err = kvaser_usb_send_cmd(dev, cmd, cmd_len); if (err) goto end;

@@ -1555,6 +1560,7 @@ static int kvaser_usb_hydra_get_busparams(struct kvaser_usb_net_priv *priv, struct kvaser_usb *dev = priv->dev; struct kvaser_usb_net_hydra_priv *hydra = priv->sub_priv; struct kvaser_cmd *cmd; + size_t cmd_len; int err;

if (!hydra) @@ -1565,6 +1571,7 @@ static int kvaser_usb_hydra_get_busparams(struct kvaser_usb_net_priv *priv, return -ENOMEM;

cmd->header.cmd_no = CMD_GET_BUSPARAMS_REQ; + cmd_len = kvaser_usb_hydra_cmd_size(cmd); kvaser_usb_hydra_set_cmd_dest_he (cmd, dev->card_data.hydra.channel_to_he[priv->channel]); kvaser_usb_hydra_set_cmd_transid @@ -1574,7 +1581,7 @@ static int kvaser_usb_hydra_get_busparams(struct kvaser_usb_net_priv *priv,

reinit_completion(&priv->get_busparams_comp);

- err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + err = kvaser_usb_send_cmd(dev, cmd, cmd_len); if (err) return err;

@@ -1601,6 +1608,7 @@ static int kvaser_usb_hydra_set_bittiming(const struct net_device *netdev, struct kvaser_cmd *cmd; struct kvaser_usb_net_priv *priv = netdev_priv(netdev); struct kvaser_usb *dev = priv->dev; + size_t cmd_len; int err;

cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL); @@ -1608,6 +1616,7 @@ static int kvaser_usb_hydra_set_bittiming(const struct net_device *netdev, return -ENOMEM;

cmd->header.cmd_no = CMD_SET_BUSPARAMS_REQ; + cmd_len = kvaser_usb_hydra_cmd_size(cmd); memcpy(&cmd->set_busparams_req.busparams_nominal, busparams, sizeof(cmd->set_busparams_req.busparams_nominal));

@@ -1616,7 +1625,7 @@ static int kvaser_usb_hydra_set_bittiming(const struct net_device *netdev, kvaser_usb_hydra_set_cmd_transid (cmd, kvaser_usb_hydra_get_next_transid(dev));

- err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + err = kvaser_usb_send_cmd(dev, cmd, cmd_len);

kfree(cmd);

@@ -1629,6 +1638,7 @@ static int kvaser_usb_hydra_set_data_bittiming(const struct net_device *netdev, struct kvaser_cmd *cmd; struct kvaser_usb_net_priv *priv = netdev_priv(netdev); struct kvaser_usb *dev = priv->dev; + size_t cmd_len; int err;

cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL); @@ -1636,6 +1646,7 @@ static int kvaser_usb_hydra_set_data_bittiming(const struct net_device *netdev, return -ENOMEM;

cmd->header.cmd_no = CMD_SET_BUSPARAMS_FD_REQ; + cmd_len = kvaser_usb_hydra_cmd_size(cmd); memcpy(&cmd->set_busparams_req.busparams_data, busparams, sizeof(cmd->set_busparams_req.busparams_data));

@@ -1653,7 +1664,7 @@ static int kvaser_usb_hydra_set_data_bittiming(const struct net_device *netdev, kvaser_usb_hydra_set_cmd_transid (cmd, kvaser_usb_hydra_get_next_transid(dev));

- err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + err = kvaser_usb_send_cmd(dev, cmd, cmd_len);

kfree(cmd);

@@ -1781,6 +1792,7 @@ static int kvaser_usb_hydra_get_software_info(struct kvaser_usb *dev) static int kvaser_usb_hydra_get_software_details(struct kvaser_usb *dev) { struct kvaser_cmd *cmd; + size_t cmd_len; int err; u32 flags; struct kvaser_usb_dev_card_data *card_data = &dev->card_data; @@ -1790,6 +1802,7 @@ static int kvaser_usb_hydra_get_software_details(struct kvaser_usb *dev) return -ENOMEM;

cmd->header.cmd_no = CMD_GET_SOFTWARE_DETAILS_REQ; + cmd_len = kvaser_usb_hydra_cmd_size(cmd); cmd->sw_detail_req.use_ext_cmd = 1; kvaser_usb_hydra_set_cmd_dest_he (cmd, KVASER_USB_HYDRA_HE_ADDRESS_ILLEGAL); @@ -1797,7 +1810,7 @@ static int kvaser_usb_hydra_get_software_details(struct kvaser_usb *dev) kvaser_usb_hydra_set_cmd_transid (cmd, kvaser_usb_hydra_get_next_transid(dev));

- err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + err = kvaser_usb_send_cmd(dev, cmd, cmd_len); if (err) goto end;

@@ -1913,6 +1926,7 @@ static int kvaser_usb_hydra_set_opt_mode(const struct kvaser_usb_net_priv *priv) { struct kvaser_usb *dev = priv->dev; struct kvaser_cmd *cmd; + size_t cmd_len; int err;

if ((priv->can.ctrlmode & @@ -1928,6 +1942,7 @@ static int kvaser_usb_hydra_set_opt_mode(const struct kvaser_usb_net_priv *priv) return -ENOMEM;

cmd->header.cmd_no = CMD_SET_DRIVERMODE_REQ; + cmd_len = kvaser_usb_hydra_cmd_size(cmd); kvaser_usb_hydra_set_cmd_dest_he (cmd, dev->card_data.hydra.channel_to_he[priv->channel]); kvaser_usb_hydra_set_cmd_transid @@ -1937,7 +1952,7 @@ static int kvaser_usb_hydra_set_opt_mode(const struct kvaser_usb_net_priv *priv) else cmd->set_ctrlmode.mode = KVASER_USB_HYDRA_CTRLMODE_NORMAL;

- err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd)); + err = kvaser_usb_send_cmd(dev, cmd, cmd_len); kfree(cmd);

return err;

From: Zheng Wang zyytlz.wz@163.com

commit 4a61648af68f5ba4884f0e3b494ee1cabc4b6620 upstream.

If intel_gvt_dma_map_guest_page failed, it will call ppgtt_invalidate_spt, which will finally free the spt. But the caller function ppgtt_populate_spt_by_guest_entry does not notice that, it will free spt again in its error path.

Fix this by canceling the mapping of DMA address and freeing sub_spt. Besides, leave the handle of spt destroy to caller function instead of callee function when error occurs.

Fixes: b901b252b6cf ("drm/i915/gvt: Add 2M huge gtt support") Signed-off-by: Zheng Wang zyytlz.wz@163.com Reviewed-by: Zhenyu Wang zhenyuw@linux.intel.com Signed-off-by: Zhenyu Wang zhenyuw@linux.intel.com Link: http://patchwork.freedesktop.org/patch/msgid/20221229165641.1192455-1-zyytlz... Signed-off-by: Ovidiu Panait ovidiu.panait@eng.windriver.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/i915/gvt/gtt.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-)

--- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -1192,10 +1192,8 @@ static int split_2MB_gtt_entry(struct in for_each_shadow_entry(sub_spt, &sub_se, sub_index) { ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu, start_gfn + sub_index, PAGE_SIZE, &dma_addr); - if (ret) { - ppgtt_invalidate_spt(spt); - return ret; - } + if (ret) + goto err; sub_se.val64 = se->val64;

/* Copy the PAT field from PDE. */ @@ -1214,6 +1212,17 @@ static int split_2MB_gtt_entry(struct in ops->set_pfn(se, sub_spt->shadow_page.mfn); ppgtt_set_shadow_entry(spt, se, index); return 0; +err: + /* Cancel the existing addess mappings of DMA addr. */ + for_each_present_shadow_entry(sub_spt, &sub_se, sub_index) { + gvt_vdbg_mm("invalidate 4K entry\n"); + ppgtt_invalidate_pte(sub_spt, &sub_se); + } + /* Release the new allocated spt. */ + trace_spt_change(sub_spt->vgpu->id, "release", sub_spt, + sub_spt->guest_page.gfn, sub_spt->shadow_page.type); + ppgtt_free_spt(sub_spt); + return ret; }

static int split_64KB_gtt_entry(struct intel_vgpu *vgpu,

From: Dave Hansen dave.hansen@linux.intel.com

commit 74e19ef0ff8061ef55957c3abd71614ef0f42f47 upstream.

The results of "access_ok()" can be mis-speculated. The result is that you can end speculatively:

if (access_ok(from, size)) // Right here

even for bad from/size combinations. On first glance, it would be ideal to just add a speculation barrier to "access_ok()" so that its results can never be mis-speculated.

But there are lots of system calls just doing access_ok() via "copy_to_user()" and friends (example: fstat() and friends). Those are generally not problematic because they do not _consume_ data from userspace other than the pointer. They are also very quick and common system calls that should not be needlessly slowed down.

"copy_from_user()" on the other hand uses a user-controller pointer and is frequently followed up with code that might affect caches. Take something like this:

if (!copy_from_user(&kernelvar, uptr, size)) do_something_with(kernelvar);

If userspace passes in an evil 'uptr' that *actually* points to a kernel addresses, and then do_something_with() has cache (or other) side-effects, it could allow userspace to infer kernel data values.

Add a barrier to the common copy_from_user() code to prevent mis-speculated values which happen after the copy.

Also add a stub for architectures that do not define barrier_nospec(). This makes the macro usable in generic code.

Since the barrier is now usable in generic code, the x86 #ifdef in the BPF code can also go away.

Reported-by: Jordy Zomer jordyzomer@google.com Suggested-by: Linus Torvalds torvalds@linuxfoundation.org Signed-off-by: Dave Hansen dave.hansen@linux.intel.com Reviewed-by: Thomas Gleixner tglx@linutronix.de Acked-by: Daniel Borkmann daniel@iogearbox.net # BPF bits Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/nospec.h | 4 ++++ kernel/bpf/core.c | 2 -- lib/usercopy.c | 7 +++++++ 3 files changed, 11 insertions(+), 2 deletions(-)

--- a/include/linux/nospec.h +++ b/include/linux/nospec.h @@ -11,6 +11,10 @@

struct task_struct;

+#ifndef barrier_nospec +# define barrier_nospec() do { } while (0) +#endif + /** * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise * @index: array element index --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1642,9 +1642,7 @@ out: * reuse preexisting logic from Spectre v1 mitigation that * happens to produce the required code on x86 for v4 as well. */ -#ifdef CONFIG_X86 barrier_nospec(); -#endif CONT; #define LDST(SIZEOP, SIZE) \ STX_MEM_##SIZEOP: \ --- a/lib/usercopy.c +++ b/lib/usercopy.c @@ -3,6 +3,7 @@ #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/uaccess.h> +#include <linux/nospec.h>

/* out-of-line parts */

@@ -12,6 +13,12 @@ unsigned long _copy_from_user(void *to, unsigned long res = n; might_fault(); if (!should_fail_usercopy() && likely(access_ok(from, n))) { + /* + * Ensure that bad access_ok() speculation will not + * lead to nasty side effects *after* the copy is + * finished: + */ + barrier_nospec(); instrument_copy_from_user(to, from, n); res = raw_copy_from_user(to, from, n); }

From: Yu Kuai yukuai3@huawei.com

commit e4c4871a73944353ea23e319de27ef73ce546623 upstream.

commit b1a811633f73 ("block: nbd: add sanity check for first_minor") checks that 'first_minor' should not be greater than 0xff, which is wrong. Whitout the commit, the details that when user pass 0x100000, it ends up create sysfs dir "/sys/block/43:0" are as follows:

nbd_dev_add disk->first_minor = index << part_shift -> default part_shift is 5, first_minor is 0x2000000 device_add_disk ddev->devt = MKDEV(disk->major, disk->first_minor) -> (0x2b << 20) | (0x2000000) = 0x2b00000 device_add device_create_sys_dev_entry format_dev_t sprintf(buffer, "%u:%u", MAJOR(dev), MINOR(dev)); -> got 43:0 sysfs_create_link -> /sys/block/43:0

By the way, with the wrong fix, when part_shift is the default value, only 8 ndb devices can be created since 8 << 5 is greater than 0xff.

Since the max bits for 'first_minor' should be the same as what MKDEV() does, which is 20. Change the upper bound of 'first_minor' from 0xff to 0xfffff.

Fixes: b1a811633f73 ("block: nbd: add sanity check for first_minor") Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Josef Bacik josef@toxicpanda.com Link: https://lore.kernel.org/r/20211102015237.2309763-2-yebin10@huawei.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Wen Yang wenyang.linux@foxmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/block/nbd.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1773,11 +1773,11 @@ static int nbd_dev_add(int index) disk->major = NBD_MAJOR;

/* Too big first_minor can cause duplicate creation of - * sysfs files/links, since first_minor will be truncated to - * byte in __device_add_disk(). + * sysfs files/links, since MKDEV() expect that the max bits of + * first_minor is 20. */ disk->first_minor = index << part_shift; - if (disk->first_minor > 0xff) { + if (disk->first_minor > MINORMASK) { err = -EINVAL; goto out_free_idr; }

From: Zhang Wensheng zhangwensheng5@huawei.com

commit 858f1bf65d3d9c00b5e2d8ca87dc79ed88267c98 upstream.

When 'index' is a big numbers, it may become negative which forced to 'int'. then 'index << part_shift' might overflow to a positive value that is not greater than '0xfffff', then sysfs might complains about duplicate creation. Because of this, move the 'index' judgment to the front will fix it and be better.

Fixes: b0d9111a2d53 ("nbd: use an idr to keep track of nbd devices") Fixes: 940c264984fd ("nbd: fix possible overflow for 'first_minor' in nbd_dev_add()") Signed-off-by: Zhang Wensheng zhangwensheng5@huawei.com Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Josef Bacik josef@toxicpanda.com Link: https://lore.kernel.org/r/20220521073749.3146892-6-yukuai3@huawei.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Wen Yang wenyang.linux@foxmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/block/nbd.c | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-)

--- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1771,17 +1771,7 @@ static int nbd_dev_add(int index) refcount_set(&nbd->refs, 1); INIT_LIST_HEAD(&nbd->list); disk->major = NBD_MAJOR; - - /* Too big first_minor can cause duplicate creation of - * sysfs files/links, since index << part_shift might overflow, or - * MKDEV() expect that the max bits of first_minor is 20. - */ disk->first_minor = index << part_shift; - if (disk->first_minor < index || disk->first_minor > MINORMASK) { - err = -EINVAL; - goto out_free_idr; - } - disk->fops = &nbd_fops; disk->private_data = nbd; sprintf(disk->disk_name, "nbd%d", index); @@ -1875,8 +1865,19 @@ static int nbd_genl_connect(struct sk_bu if (!netlink_capable(skb, CAP_SYS_ADMIN)) return -EPERM;

- if (info->attrs[NBD_ATTR_INDEX]) + if (info->attrs[NBD_ATTR_INDEX]) { index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]); + + /* + * Too big first_minor can cause duplicate creation of + * sysfs files/links, since index << part_shift might overflow, or + * MKDEV() expect that the max bits of first_minor is 20. + */ + if (index < 0 || index > MINORMASK >> part_shift) { + printk(KERN_ERR "nbd: illegal input index %d\n", index); + return -EINVAL; + } + } if (!info->attrs[NBD_ATTR_SOCKETS]) { printk(KERN_ERR "nbd: must specify at least one socket\n"); return -EINVAL;

From: Paul Moore paul@paul-moore.com

commit 6c6cd913accd77008f74a1a9d57b816db3651daa upstream.

We've moved the upstream Linux Kernel audit subsystem discussions to a new mailing list, this patch updates the MAINTAINERS info with the new list address.

Marking this for stable inclusion to help speed uptake of the new list across all of the supported kernel releases. This is a doc only patch so the risk should be close to nil.

Cc: stable@vger.kernel.org Signed-off-by: Paul Moore paul@paul-moore.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/MAINTAINERS +++ b/MAINTAINERS @@ -3001,7 +3001,7 @@ F: drivers/net/ieee802154/atusb.h AUDIT SUBSYSTEM M: Paul Moore paul@paul-moore.com M: Eric Paris eparis@redhat.com -L: linux-audit@redhat.com (moderated for non-subscribers) +L: audit@vger.kernel.org S: Supported W: https://github.com/linux-audit T: git git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/audit.git

From: Vladimir Oltean vladimir.oltean@nxp.com

commit af7b29b1deaac6da3bb7637f0e263dfab7bfc7a3 upstream.

taprio_attach() has this logic at the end, which should have been removed with the blamed patch (which is now being reverted):

/* access to the child qdiscs is not needed in offload mode */ if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { kfree(q->qdiscs); q->qdiscs = NULL; }

because otherwise, we make use of q->qdiscs[] even after this array was deallocated, namely in taprio_leaf(). Therefore, whenever one would try to attach a valid child qdisc to a fully offloaded taprio root, one would immediately dereference a NULL pointer.

$ tc qdisc replace dev eno0 handle 8001: parent root taprio \ num_tc 8 \ map 0 1 2 3 4 5 6 7 \ queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 \ max-sdu 0 0 0 0 0 200 0 0 \ base-time 200 \ sched-entry S 80 20000 \ sched-entry S a0 20000 \ sched-entry S 5f 60000 \ flags 2 $ max_frame_size=1500 $ data_rate_kbps=20000 $ port_transmit_rate_kbps=1000000 $ idleslope=$data_rate_kbps $ sendslope=$(($idleslope - $port_transmit_rate_kbps)) $ locredit=$(($max_frame_size * $sendslope / $port_transmit_rate_kbps)) $ hicredit=$(($max_frame_size * $idleslope / $port_transmit_rate_kbps)) $ tc qdisc replace dev eno0 parent 8001:7 cbs \ idleslope $idleslope \ sendslope $sendslope \ hicredit $hicredit \ locredit $locredit \ offload 0

Unable to handle kernel NULL pointer dereference at virtual address 0000000000000030 pc : taprio_leaf+0x28/0x40 lr : qdisc_leaf+0x3c/0x60 Call trace: taprio_leaf+0x28/0x40 tc_modify_qdisc+0xf0/0x72c rtnetlink_rcv_msg+0x12c/0x390 netlink_rcv_skb+0x5c/0x130 rtnetlink_rcv+0x1c/0x2c

The solution is not as obvious as the problem. The code which deallocates q->qdiscs[] is in fact copied and pasted from mqprio, which also deallocates the array in mqprio_attach() and never uses it afterwards.

Therefore, the identical cleanup logic of priv->qdiscs[] that mqprio_destroy() has is deceptive because it will never take place at qdisc_destroy() time, but just at raw ops->destroy() time (otherwise said, priv->qdiscs[] do not last for the entire lifetime of the mqprio root), but rather, this is just the twisted way in which the Qdisc API understands error path cleanup should be done (Qdisc_ops :: destroy() is called even when Qdisc_ops :: init() never succeeded).

Side note, in fact this is also what the comment in mqprio_init() says:

/* pre-allocate qdisc, attachment can't fail */

Or reworded, mqprio's priv->qdiscs[] scheme is only meant to serve as data passing between Qdisc_ops :: init() and Qdisc_ops :: attach().

[ this comment was also copied and pasted into the initial taprio commit, even though taprio_attach() came way later ]

The problem is that taprio also makes extensive use of the q->qdiscs[] array in the software fast path (taprio_enqueue() and taprio_dequeue()), but it does not keep a reference of its own on q->qdiscs[i] (you'd think that since it creates these Qdiscs, it holds the reference, but nope, this is not completely true).

To understand the difference between taprio_destroy() and mqprio_destroy() one must look before commit 13511704f8d7 ("net: taprio offload: enforce qdisc to netdev queue mapping"), because that just muddied the waters.

In the "original" taprio design, taprio always attached itself (the root Qdisc) to all netdev TX queues, so that dev_qdisc_enqueue() would go through taprio_enqueue().

It also called qdisc_refcount_inc() on itself for as many times as there were netdev TX queues, in order to counter-balance what tc_get_qdisc() does when destroying a Qdisc (simplified for brevity below):

if (n->nlmsg_type == RTM_DELQDISC) err = qdisc_graft(dev, parent=NULL, new=NULL, q, extack);

qdisc_graft(where "new" is NULL so this deletes the Qdisc):

for (i = 0; i < num_q; i++) { struct netdev_queue *dev_queue;

dev_queue = netdev_get_tx_queue(dev, i);

old = dev_graft_qdisc(dev_queue, new); if (new && i > 0) qdisc_refcount_inc(new);

qdisc_put(old); ~~~~~~~~~~~~~~ this decrements taprio's refcount once for each TX queue }

notify_and_destroy(net, skb, n, classid, rtnl_dereference(dev->qdisc), new); ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ and this finally decrements it to zero, making qdisc_put() call qdisc_destroy()

The q->qdiscs[] created using qdisc_create_dflt() (or their replacements, if taprio_graft() was ever to get called) were then privately freed by taprio_destroy().

This is still what is happening after commit 13511704f8d7 ("net: taprio offload: enforce qdisc to netdev queue mapping"), but only for software mode.

In full offload mode, the per-txq "qdisc_put(old)" calls from qdisc_graft() now deallocate the child Qdiscs rather than decrement taprio's refcount. So when notify_and_destroy(taprio) finally calls taprio_destroy(), the difference is that the child Qdiscs were already deallocated.

And this is exactly why the taprio_attach() comment "access to the child qdiscs is not needed in offload mode" is deceptive too. Not only the q->qdiscs[] array is not needed, but it is also necessary to get rid of it as soon as possible, because otherwise, we will also call qdisc_put() on the child Qdiscs in qdisc_destroy() -> taprio_destroy(), and this will cause a nasty use-after-free/refcount-saturate/whatever.

In short, the problem is that since the blamed commit, taprio_leaf() needs q->qdiscs[] to not be freed by taprio_attach(), while qdisc_destroy() -> taprio_destroy() does need q->qdiscs[] to be freed by taprio_attach() for full offload. Fixing one problem triggers the other.

All of this can be solved by making taprio keep its q->qdiscs[i] with a refcount elevated at 2 (in offloaded mode where they are attached to the netdev TX queues), both in taprio_attach() and in taprio_graft(). The generic qdisc_graft() would just decrement the child qdiscs' refcounts to 1, and taprio_destroy() would give them the final coup de grace.

However the rabbit hole of changes is getting quite deep, and the complexity increases. The blamed commit was supposed to be a bug fix in the first place, and the bug it addressed is not so significant so as to justify further rework in stable trees. So I'd rather just revert it. I don't know enough about multi-queue Qdisc design to make a proper judgement right now regarding what is/isn't idiomatic use of Qdisc concepts in taprio. I will try to study the problem more and come with a different solution in net-next.

Fixes: 1461d212ab27 ("net/sched: taprio: make qdisc_leaf() see the per-netdev-queue pfifo child qdiscs") Reported-by: Muhammad Husaini Zulkifli muhammad.husaini.zulkifli@intel.com Reported-by: Vinicius Costa Gomes vinicius.gomes@intel.com Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com Reviewed-by: Vinicius Costa Gomes vinicius.gomes@intel.com Link: https://lore.kernel.org/r/20221004220100.1650558-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sched/sch_taprio.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-)

--- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1906,14 +1906,12 @@ start_error:

static struct Qdisc *taprio_leaf(struct Qdisc *sch, unsigned long cl) { - struct taprio_sched *q = qdisc_priv(sch); - struct net_device *dev = qdisc_dev(sch); - unsigned int ntx = cl - 1; + struct netdev_queue *dev_queue = taprio_queue_get(sch, cl);

- if (ntx >= dev->num_tx_queues) + if (!dev_queue) return NULL;

- return q->qdiscs[ntx]; + return dev_queue->qdisc_sleeping; }

static unsigned long taprio_find(struct Qdisc *sch, u32 classid)