From 711e26c00e4c7b7cef0420c76a61e6d818e12687 Mon Sep 17 00:00:00 2001 From: Lv Ruyi Date: Sat, 9 Oct 2021 08:59:00 +0000 Subject: firmware: tegra: Fix error application of sizeof() to pointer Application of sizeof() to pointer yields the number of bytes of the pointer, but it should use the length of buffer in the code. Fixes: 06c2d9a078ab ("firmware: tegra: Reduce stack usage") Reported-by: Zeal Robot Signed-off-by: Lv Ruyi Reviewed-by: Jon Hunter Tested-by: Jon Hunter Signed-off-by: Thierry Reding --- drivers/firmware/tegra/bpmp-debugfs.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/tegra/bpmp-debugfs.c b/drivers/firmware/tegra/bpmp-debugfs.c index 6d66fe03fb6a..fd89899aeeed 100644 --- a/drivers/firmware/tegra/bpmp-debugfs.c +++ b/drivers/firmware/tegra/bpmp-debugfs.c @@ -77,13 +77,14 @@ static const char *get_filename(struct tegra_bpmp *bpmp, const char *root_path, *filename = NULL; char *root_path_buf; size_t root_len; + size_t root_path_buf_len = 512; - root_path_buf = kzalloc(512, GFP_KERNEL); + root_path_buf = kzalloc(root_path_buf_len, GFP_KERNEL); if (!root_path_buf) goto out; root_path = dentry_path(bpmp->debugfs_mirror, root_path_buf, - sizeof(root_path_buf)); + root_path_buf_len); if (IS_ERR(root_path)) goto out; -- cgit v1.2.3 From 69125b4b9440be015783312e1b8753ec96febde0 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Fri, 12 Nov 2021 11:27:12 +0000 Subject: reset: tegra-bpmp: Revert Handle errors in BPMP response Commit c045ceb5a145 ("reset: tegra-bpmp: Handle errors in BPMP response") fixed an issue in the Tegra BPMP error handling but has exposed an issue in the Tegra194 HDA driver and now resetting the Tegra194 HDA controller is failing. For now revert the commit c045ceb5a145 ("reset: tegra-bpmp: Handle errors in BPMP response") while a fix for the Tegra HDA driver is created. Fixes: c045ceb5a145 ("reset: tegra-bpmp: Handle errors in BPMP response") Signed-off-by: Jon Hunter Link: https://lore.kernel.org/r/20211112112712.21587-1-jonathanh@nvidia.com Signed-off-by: Philipp Zabel --- drivers/reset/tegra/reset-bpmp.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/drivers/reset/tegra/reset-bpmp.c b/drivers/reset/tegra/reset-bpmp.c index 4c5bba52b105..24d3395964cc 100644 --- a/drivers/reset/tegra/reset-bpmp.c +++ b/drivers/reset/tegra/reset-bpmp.c @@ -20,7 +20,6 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc, struct tegra_bpmp *bpmp = to_tegra_bpmp(rstc); struct mrq_reset_request request; struct tegra_bpmp_message msg; - int err; memset(&request, 0, sizeof(request)); request.cmd = command; @@ -31,13 +30,7 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc, msg.tx.data = &request; msg.tx.size = sizeof(request); - err = tegra_bpmp_transfer(bpmp, &msg); - if (err) - return err; - if (msg.rx.ret) - return -EINVAL; - - return 0; + return tegra_bpmp_transfer(bpmp, &msg); } static int tegra_bpmp_reset_module(struct reset_controller_dev *rstc, -- cgit v1.2.3 From f2c2e9ebb2cf476c09e59d073db031fbf7ef4914 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 20 Oct 2021 14:36:11 +0300 Subject: ARM: dts: imx6qp-prtwd3: update RGMII delays for sja1105 switch In the new behavior, the sja1105 driver expects there to be explicit RGMII delays present on the fixed-link ports, otherwise it will complain that it falls back to legacy behavior, which is to apply RGMII delays incorrectly derived from the phy-mode string. In this case, the legacy behavior of the driver is to apply both RX and TX delays. To preserve that, add explicit 2 nanosecond delays, which are identical with what the driver used to add (a 90 degree phase shift). The delays from the phy-mode are ignored by new kernels (it's still RGMII as long as it's "rgmii*" something), and the explicit {rx,tx}-internal-delay-ps properties are ignored by old kernels, so the change works both ways. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Reviewed-by: Oleksij Rempel Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx6qp-prtwd3.dts | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm/boot/dts/imx6qp-prtwd3.dts b/arch/arm/boot/dts/imx6qp-prtwd3.dts index 7648e8a02000..cf6571cc4682 100644 --- a/arch/arm/boot/dts/imx6qp-prtwd3.dts +++ b/arch/arm/boot/dts/imx6qp-prtwd3.dts @@ -178,6 +178,8 @@ label = "cpu"; ethernet = <&fec>; phy-mode = "rgmii-id"; + rx-internal-delay-ps = <2000>; + tx-internal-delay-ps = <2000>; fixed-link { speed = <100>; -- cgit v1.2.3 From e691f9282a89e24a8e87cdb91a181c6283ee5124 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 20 Oct 2021 14:36:12 +0300 Subject: ARM: dts: ls1021a-tsn: update RGMII delays for sja1105 switch In the new behavior, the sja1105 driver expects there to be explicit RGMII delays present on the fixed-link ports, otherwise it will complain that it falls back to legacy behavior, which is to apply RGMII delays incorrectly derived from the phy-mode string. In this case, the legacy behavior of the driver is to not apply delays in any direction (mostly because the SJA1105T can't do that, so this board uses PCB traces). To preserve that but also silence the driver, use explicit delays of 0 ns. The delay information from the phy-mode is ignored by new kernels (it's still RGMII as long as it's "rgmii*" something), and the explicit {rx,tx}-internal-delay-ps properties are ignored by old kernels, so the change works both ways. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Shawn Guo --- arch/arm/boot/dts/ls1021a-tsn.dts | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm/boot/dts/ls1021a-tsn.dts b/arch/arm/boot/dts/ls1021a-tsn.dts index ff0ffb22768b..1ea32fff4120 100644 --- a/arch/arm/boot/dts/ls1021a-tsn.dts +++ b/arch/arm/boot/dts/ls1021a-tsn.dts @@ -91,6 +91,8 @@ /* Internal port connected to eth2 */ ethernet = <&enet2>; phy-mode = "rgmii"; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <0>; reg = <4>; fixed-link { -- cgit v1.2.3 From 25501d8d3ab3f5dc83799731dfb8ebaf03ca5000 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 20 Oct 2021 14:36:13 +0300 Subject: arm64: dts: lx2160abluebox3: update RGMII delays for sja1105 switch In the new behavior, the sja1105 driver expects there to be explicit RGMII delays present on the fixed-link ports, otherwise it will complain that it falls back to legacy behavior, which is to apply RGMII delays incorrectly derived from the phy-mode string. In this case, the legacy behavior of the driver is to apply both RX and TX delays. To preserve that, add explicit 2 nanosecond delays, which are identical with what the driver used to add (a 90 degree phase shift). The delays from the phy-mode are ignored by new kernels (it's still RGMII as long as it's "rgmii*" something), and the explicit {rx,tx}-internal-delay-ps properties are ignored by old kernels, so the change works both ways. Signed-off-by: Vladimir Oltean Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/fsl-lx2160a-bluebox3.dts | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a-bluebox3.dts b/arch/arm64/boot/dts/freescale/fsl-lx2160a-bluebox3.dts index b21be03da0af..042c486bdda2 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2160a-bluebox3.dts +++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a-bluebox3.dts @@ -386,6 +386,8 @@ reg = <2>; ethernet = <&dpmac17>; phy-mode = "rgmii-id"; + rx-internal-delay-ps = <2000>; + tx-internal-delay-ps = <2000>; fixed-link { speed = <1000>; @@ -529,6 +531,8 @@ reg = <2>; ethernet = <&dpmac18>; phy-mode = "rgmii-id"; + rx-internal-delay-ps = <2000>; + tx-internal-delay-ps = <2000>; fixed-link { speed = <1000>; -- cgit v1.2.3 From 423e85e97aaf69e5198bbec6811e3825c8b5019a Mon Sep 17 00:00:00 2001 From: "Ivan T. Ivanov" Date: Tue, 16 Nov 2021 10:46:16 +0200 Subject: ARM: rockchip: Use memcpy_toio instead of memcpy on smp bring-up This fixes a potential kernel panic on memcpy when FORTIFY_SOURCE is enabled. Because memory is iomem use appropriate function for accessing it. Signed-off-by: Ivan T. Ivanov Link: https://lore.kernel.org/r/20211116084616.24811-1-iivanov@suse.de Signed-off-by: Heiko Stuebner --- arch/arm/mach-rockchip/platsmp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/mach-rockchip/platsmp.c b/arch/arm/mach-rockchip/platsmp.c index d60856898d97..5ec58d004b7d 100644 --- a/arch/arm/mach-rockchip/platsmp.c +++ b/arch/arm/mach-rockchip/platsmp.c @@ -189,7 +189,7 @@ static int __init rockchip_smp_prepare_sram(struct device_node *node) rockchip_boot_fn = __pa_symbol(secondary_startup); /* copy the trampoline to sram, that runs during startup of the core */ - memcpy(sram_base_addr, &rockchip_secondary_trampoline, trampoline_sz); + memcpy_toio(sram_base_addr, &rockchip_secondary_trampoline, trampoline_sz); flush_cache_all(); outer_clean_range(0, trampoline_sz); -- cgit v1.2.3 From 6dd0053683804427529ef3523f7872f473440a19 Mon Sep 17 00:00:00 2001 From: Artem Lapkin Date: Mon, 15 Nov 2021 16:33:21 +0800 Subject: arm64: dts: rockchip: remove mmc-hs400-enhanced-strobe from rk3399-khadas-edge Remove mmc-hs400-enhanced-strobe from the rk3399-khadas-edge dts to improve compatibility with a wider range of eMMC chips. Before (BJTD4R 29.1 GiB): [ 7.001493] mmc2: CQHCI version 5.10 [ 7.027971] mmc2: SDHCI controller on fe330000.mmc [fe330000.mmc] using ADMA ....... [ 7.207086] mmc2: mmc_select_hs400es failed, error -110 [ 7.207129] mmc2: error -110 whilst initialising MMC card [ 7.308893] mmc2: mmc_select_hs400es failed, error -110 [ 7.308921] mmc2: error -110 whilst initialising MMC card [ 7.427524] mmc2: mmc_select_hs400es failed, error -110 [ 7.427546] mmc2: error -110 whilst initialising MMC card [ 7.590993] mmc2: mmc_select_hs400es failed, error -110 [ 7.591012] mmc2: error -110 whilst initialising MMC card After: [ 6.960785] mmc2: CQHCI version 5.10 [ 6.984672] mmc2: SDHCI controller on fe330000.mmc [fe330000.mmc] using ADMA [ 7.175021] mmc2: Command Queue Engine enabled [ 7.175053] mmc2: new HS400 MMC card at address 0001 [ 7.175808] mmcblk2: mmc2:0001 BJTD4R 29.1 GiB [ 7.176033] mmcblk2boot0: mmc2:0001 BJTD4R 4.00 MiB [ 7.176245] mmcblk2boot1: mmc2:0001 BJTD4R 4.00 MiB [ 7.176495] mmcblk2rpmb: mmc2:0001 BJTD4R 4.00 MiB, chardev (242:0) Fixes: c2aacceedc86 ("arm64: dts: rockchip: Add support for Khadas Edge/Edge-V/Captain boards") Signed-off-by: Artem Lapkin Link: https://lore.kernel.org/r/20211115083321.2627461-1-art@khadas.com Signed-off-by: Heiko Stuebner --- arch/arm64/boot/dts/rockchip/rk3399-khadas-edge.dtsi | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge.dtsi index d5c7648c841d..f1fcc6b5b402 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge.dtsi @@ -705,7 +705,6 @@ &sdhci { bus-width = <8>; mmc-hs400-1_8v; - mmc-hs400-enhanced-strobe; non-removable; status = "okay"; }; -- cgit v1.2.3 From 772fb46109f635dd75db20c86b7eaf48efa46cef Mon Sep 17 00:00:00 2001 From: John Keeping Date: Tue, 2 Nov 2021 18:29:07 +0000 Subject: arm64: dts: rockchip: fix rk3308-roc-cc vcc-sd supply Correct a typo in the vin-supply property. The input supply is always-on, so this mistake doesn't affect whether the supply is actually enabled correctly. Fixes: 4403e1237be3 ("arm64: dts: rockchip: Add devicetree for board roc-rk3308-cc") Signed-off-by: John Keeping Link: https://lore.kernel.org/r/20211102182908.3409670-2-john@metanate.com Signed-off-by: Heiko Stuebner --- arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts b/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts index 665b2e69455d..ea6820902ede 100644 --- a/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts +++ b/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts @@ -97,7 +97,7 @@ regulator-max-microvolt = <3300000>; regulator-always-on; regulator-boot-on; - vim-supply = <&vcc_io>; + vin-supply = <&vcc_io>; }; vdd_core: vdd-core { -- cgit v1.2.3 From 2b454a90e2ccdd6e03f88f930036da4df577be76 Mon Sep 17 00:00:00 2001 From: John Keeping Date: Tue, 2 Nov 2021 18:29:08 +0000 Subject: arm64: dts: rockchip: fix rk3399-leez-p710 vcc3v3-lan supply Correct a typo in the vin-supply property. The input supply is always-on, so this mistake doesn't affect whether the supply is actually enabled correctly. Fixes: fc702ed49a86 ("arm64: dts: rockchip: Add dts for Leez RK3399 P710 SBC") Signed-off-by: John Keeping Link: https://lore.kernel.org/r/20211102182908.3409670-3-john@metanate.com Signed-off-by: Heiko Stuebner --- arch/arm64/boot/dts/rockchip/rk3399-leez-p710.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3399-leez-p710.dts b/arch/arm64/boot/dts/rockchip/rk3399-leez-p710.dts index 7c93f840bc64..e890166e7fd4 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-leez-p710.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-leez-p710.dts @@ -55,7 +55,7 @@ regulator-boot-on; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; - vim-supply = <&vcc3v3_sys>; + vin-supply = <&vcc3v3_sys>; }; vcc3v3_sys: vcc3v3-sys { -- cgit v1.2.3 From 8240e87f16d17a9592c9d67857a3dcdbcb98f10d Mon Sep 17 00:00:00 2001 From: Alex Bee Date: Wed, 27 Oct 2021 16:37:25 +0200 Subject: arm64: dts: rockchip: fix audio-supply for Rock Pi 4 As stated in the schematics [1] and [2] P5 the APIO5 domain is supplied by RK808-D Buck4, which in our case vcc1v8_codec - i.e. a 1.8 V regulator. Currently only white noise comes from the ES8316's output, which - for whatever reason - came up only after the the correct switch from i2s0_8ch_bus to i2s0_2ch_bus for i2s0's pinctrl was done. Fix this by setting the correct regulator for audio-supply. [1] https://dl.radxa.com/rockpi4/docs/hw/rockpi4/rockpi4_v13_sch_20181112.pdf [2] https://dl.radxa.com/rockpi4/docs/hw/rockpi4/rockpi_4c_v12_sch_20200620.pdf Fixes: 1b5715c602fd ("arm64: dts: rockchip: add ROCK Pi 4 DTS support") Signed-off-by: Alex Bee Link: https://lore.kernel.org/r/20211027143726.165809-1-knaerzche@gmail.com Signed-off-by: Heiko Stuebner --- arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi index 98136c88fa49..6a434be62819 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi @@ -502,7 +502,7 @@ status = "okay"; bt656-supply = <&vcc_3v0>; - audio-supply = <&vcc_3v0>; + audio-supply = <&vcc1v8_codec>; sdmmc-supply = <&vcc_sdio>; gpio1830-supply = <&vcc_3v0>; }; -- cgit v1.2.3 From aef4b9a89a376a9cabe5e744729914e7766c59bb Mon Sep 17 00:00:00 2001 From: Florian Klink Date: Wed, 20 Oct 2021 11:59:23 +0200 Subject: arm64: dts: rockchip: fix poweroff on helios64 Adding the rockchip,system-power-controller property here will use the rk808 to power off the system. Fixes: 09e006cfb43e ("arm64: dts: rockchip: Add basic support for Kobol's Helios64") Signed-off-by: Florian Klink Tested-by: Dennis Gilmore Link: https://lore.kernel.org/r/20211020095926.735938-2-flokli@flokli.de Signed-off-by: Heiko Stuebner --- arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts b/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts index 63c7681843da..b6ac00f64613 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts @@ -276,6 +276,7 @@ clock-output-names = "xin32k", "rk808-clkout2"; pinctrl-names = "default"; pinctrl-0 = <&pmic_int_l>; + rockchip,system-power-controller; vcc1-supply = <&vcc5v0_sys>; vcc2-supply = <&vcc5v0_sys>; vcc3-supply = <&vcc5v0_sys>; -- cgit v1.2.3 From 885633075847f475f26a29249d772cc0da85d8cd Mon Sep 17 00:00:00 2001 From: Tim Gardner Date: Mon, 25 Oct 2021 12:16:56 -0600 Subject: dmaengine: dw-axi-dmac: Fix uninitialized variable in axi_chan_block_xfer_start() Coverity complains of an uninitialized variable: 5. uninit_use_in_call: Using uninitialized value config.dst_per when calling axi_chan_config_write. [show details] 6. uninit_use_in_call: Using uninitialized value config.hs_sel_src when calling axi_chan_config_write. [show details] CID 121164 (#1-3 of 3): Uninitialized scalar variable (UNINIT) 7. uninit_use_in_call: Using uninitialized value config.src_per when calling axi_chan_config_write. [show details] 418 axi_chan_config_write(chan, &config); Fix this by initializing the structure to 0 which should at least be benign in axi_chan_config_write(). Also fix what looks like a cut-n-paste error when initializing config.hs_sel_dst. Fixes: 824351668a413 ("dmaengine: dw-axi-dmac: support DMAX_NUM_CHANNELS > 8") Cc: Eugeniy Paltsev Cc: Vinod Koul Cc: dmaengine@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Tim Gardner Link: https://lore.kernel.org/r/20211025181656.31658-1-tim.gardner@canonical.com Signed-off-by: Vinod Koul --- drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c index cd0d745eb071..33baf1591a49 100644 --- a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c +++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c @@ -373,7 +373,7 @@ static void axi_chan_block_xfer_start(struct axi_dma_chan *chan, struct axi_dma_desc *first) { u32 priority = chan->chip->dw->hdata->priority[chan->id]; - struct axi_dma_chan_config config; + struct axi_dma_chan_config config = {}; u32 irq_mask; u8 lms = 0; /* Select AXI0 master for LLI fetching */ @@ -391,7 +391,7 @@ static void axi_chan_block_xfer_start(struct axi_dma_chan *chan, config.tt_fc = DWAXIDMAC_TT_FC_MEM_TO_MEM_DMAC; config.prior = priority; config.hs_sel_dst = DWAXIDMAC_HS_SEL_HW; - config.hs_sel_dst = DWAXIDMAC_HS_SEL_HW; + config.hs_sel_src = DWAXIDMAC_HS_SEL_HW; switch (chan->direction) { case DMA_MEM_TO_DEV: dw_axi_dma_set_byte_halfword(chan, true); -- cgit v1.2.3 From 1ffc6f359f7ab114ad0d2bbe6a85cbd848709ab2 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Tue, 9 Nov 2021 22:09:56 +0100 Subject: dmaengine: dw-edma: Fix return value check for dma_set_mask_and_coherent() The commit in the Fixes: tag has changed the logic of the code and now it is likely that the probe will return an early success (0), even if not completely executed. This should lead to a crash or similar issue later on when the code accesses to some never allocated resources. Change the '!err' into a 'err' when checking if 'dma_set_mask_and_coherent()' has failed or not. While at it, simplify the code and remove the "can't success code" related to 32 DMA mask. As stated in [1], 'dma_set_mask_and_coherent(DMA_BIT_MASK(64))' can't fail if 'dev->dma_mask' is non-NULL. And if it is NULL, it would fail for the same reason when tried with DMA_BIT_MASK(32). [1]: https://lkml.org/lkml/2021/6/7/398 Fixes: ecb8c88bd31c ("dmaengine: dw-edma-pcie: switch from 'pci_' to 'dma_' API") Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/935fbb40ae930c5fe87482a41dcb73abf2257973.1636492127.git.christophe.jaillet@wanadoo.fr Signed-off-by: Vinod Koul --- drivers/dma/dw-edma/dw-edma-pcie.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/drivers/dma/dw-edma/dw-edma-pcie.c b/drivers/dma/dw-edma/dw-edma-pcie.c index 198f6cd8ac1b..cee7aa231d7b 100644 --- a/drivers/dma/dw-edma/dw-edma-pcie.c +++ b/drivers/dma/dw-edma/dw-edma-pcie.c @@ -187,17 +187,9 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, /* DMA configuration */ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (!err) { + if (err) { pci_err(pdev, "DMA mask 64 set failed\n"); return err; - } else { - pci_err(pdev, "DMA mask 64 set failed\n"); - - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - pci_err(pdev, "DMA mask 32 set failed\n"); - return err; - } } /* Data structure allocation */ -- cgit v1.2.3 From fa51b16d05583c7aebbc06330afb50276243d198 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 17 Nov 2021 10:03:51 -0700 Subject: dmaengine: idxd: fix calling wq quiesce inside spinlock Dan reports that smatch has found idxd_wq_quiesce() is being called inside the idxd->dev_lock. idxd_wq_quiesce() calls wait_for_completion() and therefore it can sleep. Move the call outside of the spinlock as it does not need device lock. Fixes: 5b0c68c473a1 ("dmaengine: idxd: support reporting of halt interrupt") Reported-by: Dan Carpenter Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/163716858508.1721911.15051495873516709923.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/irq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index 17f2f8a31b63..cf2c8bc4f147 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -137,10 +137,10 @@ halt: INIT_WORK(&idxd->work, idxd_device_reinit); queue_work(idxd->wq, &idxd->work); } else { - spin_lock(&idxd->dev_lock); idxd->state = IDXD_DEV_HALTED; idxd_wqs_quiesce(idxd); idxd_wqs_unmap_portal(idxd); + spin_lock(&idxd->dev_lock); idxd_device_clear_state(idxd); dev_err(&idxd->pdev->dev, "idxd halted, need %s.\n", -- cgit v1.2.3 From c88c5e461939a06ae769a01649d5c6b5a156f883 Mon Sep 17 00:00:00 2001 From: Mathew McBride Date: Mon, 22 Nov 2021 02:55:54 +0000 Subject: arm64: dts: ten64: remove redundant interrupt declaration for gpio-keys gpio-keys already 'inherits' the interrupts from the controller of the specified GPIO, so having another declaration is redundant. On >=v5.15 this started causing an oops under gpio_keys_probe as the IRQ was already claimed. Signed-off-by: Mathew McBride Fixes: 418962eea358 ("arm64: dts: add device tree for Traverse Ten64 (LS1088A)") Cc: stable@vger.kernel.org Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts b/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts index 3063851c2fb9..d3f03dcbb8c3 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts @@ -38,7 +38,6 @@ powerdn { label = "External Power Down"; gpios = <&gpio1 17 GPIO_ACTIVE_LOW>; - interrupts = <&gpio1 17 IRQ_TYPE_EDGE_FALLING>; linux,code = ; }; @@ -46,7 +45,6 @@ admin { label = "ADMIN button"; gpios = <&gpio3 8 GPIO_ACTIVE_HIGH>; - interrupts = <&gpio3 8 IRQ_TYPE_EDGE_RISING>; linux,code = ; }; }; -- cgit v1.2.3 From 6331b8765cd0634a4e4cdcc1a6f1a74196616b94 Mon Sep 17 00:00:00 2001 From: Bin Meng Date: Wed, 16 Jun 2021 15:46:44 +0800 Subject: riscv: dts: unleashed: Add gpio card detect to mmc-spi-slot Per HiFive Unleashed schematics, the card detect signal of the micro SD card is connected to gpio pin #11, which should be reflected in the DT via the property, as described in Documentation/devicetree/bindings/mmc/mmc-spi-slot.txt. [1] https://sifive.cdn.prismic.io/sifive/c52a8e32-05ce-4aaf-95c8-7bf8453f8698_hifive-unleashed-a00-schematics-1.pdf Signed-off-by: Bin Meng Fixes: d573b5558abb ("riscv: dts: add initial board data for the SiFive HiFive Unmatched") Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts index ba304d4c455c..ced0d4e47938 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts @@ -76,6 +76,7 @@ spi-max-frequency = <20000000>; voltage-ranges = <3300 3300>; disable-wp; + gpios = <&gpio 11 GPIO_ACTIVE_LOW>; }; }; -- cgit v1.2.3 From 298d03c2d7f1b5daacb6d4f4053fd3d677d67087 Mon Sep 17 00:00:00 2001 From: Bin Meng Date: Wed, 16 Jun 2021 15:46:45 +0800 Subject: riscv: dts: unmatched: Add gpio card detect to mmc-spi-slot Per HiFive Unmatched schematics, the card detect signal of the micro SD card is connected to gpio pin #15, which should be reflected in the DT via the property, as described in Documentation/devicetree/bindings/mmc/mmc-spi-slot.txt. [1] https://sifive.cdn.prismic.io/sifive/6a06d6c0-6e66-49b5-8e9e-e68ce76f4192_hifive-unmatched-schematics-v3.pdf Signed-off-by: Bin Meng Fixes: d573b5558abb ("riscv: dts: add initial board data for the SiFive HiFive Unmatched") Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts index 4f66919215f6..3c796d64cf51 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts @@ -2,6 +2,7 @@ /* Copyright (c) 2020 SiFive, Inc */ #include "fu740-c000.dtsi" +#include #include /* Clock frequency (in Hz) of the PCB crystal for rtcclk */ @@ -223,6 +224,7 @@ spi-max-frequency = <20000000>; voltage-ranges = <3300 3300>; disable-wp; + gpios = <&gpio 15 GPIO_ACTIVE_LOW>; }; }; -- cgit v1.2.3 From 1b8d2789dad0005fd5e7d35dab26a8e1203fb6da Mon Sep 17 00:00:00 2001 From: Joe Thornber Date: Wed, 24 Nov 2021 12:07:39 -0500 Subject: dm btree remove: fix use after free in rebalance_children() Move dm_tm_unlock() after dm_tm_dec(). Cc: stable@vger.kernel.org Signed-off-by: Joe Thornber Signed-off-by: Mike Snitzer --- drivers/md/persistent-data/dm-btree-remove.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c index 70532335c7c7..cb670f16e98e 100644 --- a/drivers/md/persistent-data/dm-btree-remove.c +++ b/drivers/md/persistent-data/dm-btree-remove.c @@ -423,9 +423,9 @@ static int rebalance_children(struct shadow_spine *s, memcpy(n, dm_block_data(child), dm_bm_block_size(dm_tm_get_bm(info->tm))); - dm_tm_unlock(info->tm, child); dm_tm_dec(info->tm, dm_block_location(child)); + dm_tm_unlock(info->tm, child); return 0; } -- cgit v1.2.3 From 8979ead988d20887e563b77b16792594f76aa07a Mon Sep 17 00:00:00 2001 From: Janne Grunau Date: Mon, 22 Nov 2021 23:24:38 +0100 Subject: arm64: dts: apple: change ethernet0 device type to ethernet Fixes make dtbs_check errors for t8103-j274.dts due to missing pci properties. Fixes: e1bebf978151 ("arm64: dts: apple: j274: Expose PCI node for the Ethernet MAC address") Reviewed-by: Mark Kettenis Signed-off-by: Janne Grunau Tested-by: Hector Martin Signed-off-by: Hector Martin --- arch/arm64/boot/dts/apple/t8103-j274.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/apple/t8103-j274.dts b/arch/arm64/boot/dts/apple/t8103-j274.dts index 33a80f9501dc..02c36301e985 100644 --- a/arch/arm64/boot/dts/apple/t8103-j274.dts +++ b/arch/arm64/boot/dts/apple/t8103-j274.dts @@ -60,7 +60,7 @@ &port02 { bus-range = <3 3>; - ethernet0: pci@0,0 { + ethernet0: ethernet@0,0 { reg = <0x30000 0x0 0x0 0x0 0x0>; /* To be filled by the loader */ local-mac-address = [00 10 18 00 00 00]; -- cgit v1.2.3 From 48c06708e63e71b4395e4159797366aa03be10ff Mon Sep 17 00:00:00 2001 From: Maxime Bizon Date: Thu, 18 Nov 2021 12:58:24 +0100 Subject: mac80211: fix TCP performance on mesh interface sta is NULL for mesh point (resolved later), so sk pacing parameters were not applied. Signed-off-by: Maxime Bizon Link: https://lore.kernel.org/r/66f51659416ac35d6b11a313bd3ffe8b8a43dd55.camel@freebox.fr Signed-off-by: Johannes Berg --- net/mac80211/tx.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 278945e3e08a..51ec5f9bc2e0 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -4191,11 +4191,11 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, ieee80211_aggr_check(sdata, sta, skb); + sk_pacing_shift_update(skb->sk, sdata->local->hw.tx_sk_pacing_shift); + if (sta) { struct ieee80211_fast_tx *fast_tx; - sk_pacing_shift_update(skb->sk, sdata->local->hw.tx_sk_pacing_shift); - fast_tx = rcu_dereference(sta->fast_tx); if (fast_tx && -- cgit v1.2.3 From d5e568c3a4ec2ddd23e7dc5ad5b0c64e4f22981a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 22 Nov 2021 12:47:40 +0100 Subject: mac80211: track only QoS data frames for admission control For admission control, obviously all of that only works for QoS data frames, otherwise we cannot even access the QoS field in the header. Syzbot reported (see below) an uninitialized value here due to a status of a non-QoS nullfunc packet, which isn't even long enough to contain the QoS header. Fix this to only do anything for QoS data packets. Reported-by: syzbot+614e82b88a1a4973e534@syzkaller.appspotmail.com Fixes: 02219b3abca5 ("mac80211: add WMM admission control support") Link: https://lore.kernel.org/r/20211122124737.dad29e65902a.Ieb04587afacb27c14e0de93ec1bfbefb238cc2a0@changeid Signed-off-by: Johannes Berg --- net/mac80211/mlme.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 54ab0e1ef6ca..37f7d975f3da 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2452,11 +2452,18 @@ static void ieee80211_sta_tx_wmm_ac_notify(struct ieee80211_sub_if_data *sdata, u16 tx_time) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - u16 tid = ieee80211_get_tid(hdr); - int ac = ieee80211_ac_from_tid(tid); - struct ieee80211_sta_tx_tspec *tx_tspec = &ifmgd->tx_tspec[ac]; + u16 tid; + int ac; + struct ieee80211_sta_tx_tspec *tx_tspec; unsigned long now = jiffies; + if (!ieee80211_is_data_qos(hdr->frame_control)) + return; + + tid = ieee80211_get_tid(hdr); + ac = ieee80211_ac_from_tid(tid); + tx_tspec = &ifmgd->tx_tspec[ac]; + if (likely(!tx_tspec->admitted_time)) return; -- cgit v1.2.3 From 18688c80ad8a8dd50523dc9276e929932cac86d4 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Mon, 22 Nov 2021 21:43:23 +0100 Subject: mac80211: fix rate control for retransmitted frames Since retransmission clears info->control, rate control needs to be called again, otherwise the driver might crash due to invalid rates. Cc: stable@vger.kernel.org # 5.14+ Reported-by: Aaro Koskinen Reported-by: Robert W Fixes: 03c3911d2d67 ("mac80211: call ieee80211_tx_h_rate_ctrl() when dequeue") Signed-off-by: Felix Fietkau Tested-by: Aaro Koskinen Link: https://lore.kernel.org/r/20211122204323.9787-1-nbd@nbd.name Signed-off-by: Johannes Berg --- net/mac80211/tx.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 51ec5f9bc2e0..86a54df3aabd 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1822,15 +1822,15 @@ static int invoke_tx_handlers_late(struct ieee80211_tx_data *tx) struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); ieee80211_tx_result res = TX_CONTINUE; + if (!ieee80211_hw_check(&tx->local->hw, HAS_RATE_CONTROL)) + CALL_TXH(ieee80211_tx_h_rate_ctrl); + if (unlikely(info->flags & IEEE80211_TX_INTFL_RETRANSMISSION)) { __skb_queue_tail(&tx->skbs, tx->skb); tx->skb = NULL; goto txh_done; } - if (!ieee80211_hw_check(&tx->local->hw, HAS_RATE_CONTROL)) - CALL_TXH(ieee80211_tx_h_rate_ctrl); - CALL_TXH(ieee80211_tx_h_michael_mic_add); CALL_TXH(ieee80211_tx_h_sequence); CALL_TXH(ieee80211_tx_h_fragment); -- cgit v1.2.3 From 73111efacd3c6d9e644acca1d132566932be8af0 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Wed, 24 Nov 2021 10:40:24 +0100 Subject: mac80211: fix regression in SSN handling of addba tx Some drivers that do their own sequence number allocation (e.g. ath9k) rely on being able to modify params->ssn on starting tx ampdu sessions. This was broken by a change that modified it to use sta->tid_seq[tid] instead. Cc: stable@vger.kernel.org Fixes: 31d8bb4e07f8 ("mac80211: agg-tx: refactor sending addba") Reported-by: Eneas U de Queiroz Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20211124094024.43222-1-nbd@nbd.name Signed-off-by: Johannes Berg --- net/mac80211/agg-tx.c | 4 ++-- net/mac80211/sta_info.h | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 430a58587538..c1558dd2d244 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -480,8 +480,7 @@ static void ieee80211_send_addba_with_timeout(struct sta_info *sta, /* send AddBA request */ ieee80211_send_addba_request(sdata, sta->sta.addr, tid, - tid_tx->dialog_token, - sta->tid_seq[tid] >> 4, + tid_tx->dialog_token, tid_tx->ssn, buf_size, tid_tx->timeout); WARN_ON(test_and_set_bit(HT_AGG_STATE_SENT_ADDBA, &tid_tx->state)); @@ -523,6 +522,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) params.ssn = sta->tid_seq[tid] >> 4; ret = drv_ampdu_action(local, sdata, ¶ms); + tid_tx->ssn = params.ssn; if (ret == IEEE80211_AMPDU_TX_START_DELAY_ADDBA) { return; } else if (ret == IEEE80211_AMPDU_TX_START_IMMEDIATE) { diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index ba2796782008..e7443fc4669c 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -199,6 +199,7 @@ struct tid_ampdu_tx { u8 stop_initiator; bool tx_stop; u16 buf_size; + u16 ssn; u16 failed_bar_ssn; bool bar_pending; -- cgit v1.2.3 From 942bd1070c3a39d1302fc5db73d60c86e3033c81 Mon Sep 17 00:00:00 2001 From: Xing Song Date: Tue, 23 Nov 2021 11:31:23 +0800 Subject: mac80211: set up the fwd_skb->dev for mesh forwarding Mesh forwarding requires that the fwd_skb->dev is set up for TX handling, otherwise the following warning will be generated, so set it up for the pending frames. [ 72.835674 ] WARNING: CPU: 0 PID: 1193 at __skb_flow_dissect+0x284/0x1298 [ 72.842379 ] Modules linked in: ksmbd pppoe ppp_async l2tp_ppp ... [ 72.962020 ] CPU: 0 PID: 1193 Comm: kworker/u5:1 Tainted: P S 5.4.137 #0 [ 72.969938 ] Hardware name: MT7622_MT7531 RFB (DT) [ 72.974659 ] Workqueue: napi_workq napi_workfn [ 72.979025 ] pstate: 60000005 (nZCv daif -PAN -UAO) [ 72.983822 ] pc : __skb_flow_dissect+0x284/0x1298 [ 72.988444 ] lr : __skb_flow_dissect+0x54/0x1298 [ 72.992977 ] sp : ffffffc010c738c0 [ 72.996293 ] x29: ffffffc010c738c0 x28: 0000000000000000 [ 73.001615 ] x27: 000000000000ffc2 x26: ffffff800c2eb818 [ 73.006937 ] x25: ffffffc010a987c8 x24: 00000000000000ce [ 73.012259 ] x23: ffffffc010c73a28 x22: ffffffc010a99c60 [ 73.017581 ] x21: 000000000000ffc2 x20: ffffff80094da800 [ 73.022903 ] x19: 0000000000000000 x18: 0000000000000014 [ 73.028226 ] x17: 00000000084d16af x16: 00000000d1fc0bab [ 73.033548 ] x15: 00000000715f6034 x14: 000000009dbdd301 [ 73.038870 ] x13: 00000000ea4dcbc3 x12: 0000000000000040 [ 73.044192 ] x11: 000000000eb00ff0 x10: 0000000000000000 [ 73.049513 ] x9 : 000000000eb00073 x8 : 0000000000000088 [ 73.054834 ] x7 : 0000000000000000 x6 : 0000000000000001 [ 73.060155 ] x5 : 0000000000000000 x4 : 0000000000000000 [ 73.065476 ] x3 : ffffffc010a98000 x2 : 0000000000000000 [ 73.070797 ] x1 : 0000000000000000 x0 : 0000000000000000 [ 73.076120 ] Call trace: [ 73.078572 ] __skb_flow_dissect+0x284/0x1298 [ 73.082846 ] __skb_get_hash+0x7c/0x228 [ 73.086629 ] ieee80211_txq_may_transmit+0x7fc/0x17b8 [mac80211] [ 73.092564 ] ieee80211_tx_prepare_skb+0x20c/0x268 [mac80211] [ 73.098238 ] ieee80211_tx_pending+0x144/0x330 [mac80211] [ 73.103560 ] tasklet_action_common.isra.16+0xb4/0x158 [ 73.108618 ] tasklet_action+0x2c/0x38 [ 73.112286 ] __do_softirq+0x168/0x3b0 [ 73.115954 ] do_softirq.part.15+0x88/0x98 [ 73.119969 ] __local_bh_enable_ip+0xb0/0xb8 [ 73.124156 ] napi_workfn+0x58/0x90 [ 73.127565 ] process_one_work+0x20c/0x478 [ 73.131579 ] worker_thread+0x50/0x4f0 [ 73.135249 ] kthread+0x124/0x128 [ 73.138484 ] ret_from_fork+0x10/0x1c Signed-off-by: Xing Song Tested-By: Frank Wunderlich Link: https://lore.kernel.org/r/20211123033123.2684-1-xing.song@mediatek.com Signed-off-by: Johannes Berg --- net/mac80211/rx.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 9541a4c30aca..0544563ede52 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2944,6 +2944,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) if (!fwd_skb) goto out; + fwd_skb->dev = sdata->dev; fwd_hdr = (struct ieee80211_hdr *) fwd_skb->data; fwd_hdr->frame_control &= ~cpu_to_le16(IEEE80211_FCTL_RETRY); info = IEEE80211_SKB_CB(fwd_skb); -- cgit v1.2.3 From 8f9dcc29566626f683843ccac6113a12208315ca Mon Sep 17 00:00:00 2001 From: Ahmed Zaki Date: Sat, 2 Oct 2021 08:53:29 -0600 Subject: mac80211: fix a memory leak where sta_info is not freed The following is from a system that went OOM due to a memory leak: wlan0: Allocated STA 74:83:c2:64:0b:87 wlan0: Allocated STA 74:83:c2:64:0b:87 wlan0: IBSS finish 74:83:c2:64:0b:87 (---from ieee80211_ibss_add_sta) wlan0: Adding new IBSS station 74:83:c2:64:0b:87 wlan0: moving STA 74:83:c2:64:0b:87 to state 2 wlan0: moving STA 74:83:c2:64:0b:87 to state 3 wlan0: Inserted STA 74:83:c2:64:0b:87 wlan0: IBSS finish 74:83:c2:64:0b:87 (---from ieee80211_ibss_work) wlan0: Adding new IBSS station 74:83:c2:64:0b:87 wlan0: moving STA 74:83:c2:64:0b:87 to state 2 wlan0: moving STA 74:83:c2:64:0b:87 to state 3 . . wlan0: expiring inactive not authorized STA 74:83:c2:64:0b:87 wlan0: moving STA 74:83:c2:64:0b:87 to state 2 wlan0: moving STA 74:83:c2:64:0b:87 to state 1 wlan0: Removed STA 74:83:c2:64:0b:87 wlan0: Destroyed STA 74:83:c2:64:0b:87 The ieee80211_ibss_finish_sta() is called twice on the same STA from 2 different locations. On the second attempt, the allocated STA is not destroyed creating a kernel memory leak. This is happening because sta_info_insert_finish() does not call sta_info_free() the second time when the STA already exists (returns -EEXIST). Note that the caller sta_info_insert_rcu() assumes STA is destroyed upon errors. Same fix is applied to -ENOMEM. Signed-off-by: Ahmed Zaki Link: https://lore.kernel.org/r/20211002145329.3125293-1-anzaki@gmail.com [change the error path label to use the existing code] Signed-off-by: Johannes Berg --- net/mac80211/sta_info.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 51b49f0d3ad4..840ad1a860fa 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -644,13 +644,13 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) /* check if STA exists already */ if (sta_info_get_bss(sdata, sta->sta.addr)) { err = -EEXIST; - goto out_err; + goto out_cleanup; } sinfo = kzalloc(sizeof(struct station_info), GFP_KERNEL); if (!sinfo) { err = -ENOMEM; - goto out_err; + goto out_cleanup; } local->num_sta++; @@ -706,8 +706,8 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) out_drop_sta: local->num_sta--; synchronize_net(); + out_cleanup: cleanup_single_sta(sta); - out_err: mutex_unlock(&local->sta_mtx); kfree(sinfo); rcu_read_lock(); -- cgit v1.2.3 From 1dc2f2b81a6a9895da59f3915760f6c0c3074492 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 25 Nov 2021 18:33:16 -0800 Subject: hv: utils: add PTP_1588_CLOCK to Kconfig to fix build The hyperv utilities use PTP clock interfaces and should depend a a kconfig symbol such that they will be built as a loadable module or builtin so that linker errors do not happen. Prevents these build errors: ld: drivers/hv/hv_util.o: in function `hv_timesync_deinit': hv_util.c:(.text+0x37d): undefined reference to `ptp_clock_unregister' ld: drivers/hv/hv_util.o: in function `hv_timesync_init': hv_util.c:(.text+0x738): undefined reference to `ptp_clock_register' Fixes: 3716a49a81ba ("hv_utils: implement Hyper-V PTP source") Signed-off-by: Randy Dunlap Reported-by: kernel test robot Cc: Arnd Bergmann Cc: "K. Y. Srinivasan" Cc: Haiyang Zhang Cc: Stephen Hemminger Cc: Wei Liu Cc: Dexuan Cui Cc: linux-hyperv@vger.kernel.org Cc: Greg Kroah-Hartman Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20211126023316.25184-1-rdunlap@infradead.org Signed-off-by: Wei Liu --- drivers/hv/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig index dd12af20e467..0747a8f1fcee 100644 --- a/drivers/hv/Kconfig +++ b/drivers/hv/Kconfig @@ -19,6 +19,7 @@ config HYPERV_TIMER config HYPERV_UTILS tristate "Microsoft Hyper-V Utilities driver" depends on HYPERV && CONNECTOR && NLS + depends on PTP_1588_CLOCK_OPTIONAL help Select this option to enable the Hyper-V Utilities. -- cgit v1.2.3 From 3dc709e518b47386e6af937eaec37bb36539edfd Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Fri, 26 Nov 2021 12:11:53 +0800 Subject: powerpc/85xx: Fix oops when CONFIG_FSL_PMC=n When CONFIG_FSL_PMC is set to n, no value is assigned to cpu_up_prepare in the mpc85xx_pm_ops structure. As a result, oops is triggered in smp_85xx_start_cpu(). smp: Bringing up secondary CPUs ... kernel tried to execute user page (0) - exploit attempt? (uid: 0) BUG: Unable to handle kernel instruction fetch (NULL pointer?) Faulting instruction address: 0x00000000 Oops: Kernel access of bad area, sig: 11 [#1] ... NIP [00000000] 0x0 LR [c0021d2c] smp_85xx_kick_cpu+0xe8/0x568 Call Trace: [c1051da8] [c0021cb8] smp_85xx_kick_cpu+0x74/0x568 (unreliable) [c1051de8] [c0011460] __cpu_up+0xc0/0x228 [c1051e18] [c0031bbc] bringup_cpu+0x30/0x224 [c1051e48] [c0031f3c] cpu_up.constprop.0+0x180/0x33c [c1051e88] [c00322e8] bringup_nonboot_cpus+0x88/0xc8 [c1051eb8] [c07e67bc] smp_init+0x30/0x78 [c1051ed8] [c07d9e28] kernel_init_freeable+0x118/0x2a8 [c1051f18] [c00032d8] kernel_init+0x14/0x124 [c1051f38] [c0010278] ret_from_kernel_thread+0x14/0x1c Fixes: c45361abb918 ("powerpc/85xx: fix timebase sync issue when CONFIG_HOTPLUG_CPU=n") Reported-by: Martin Kennedy Signed-off-by: Xiaoming Ni Tested-by: Martin Kennedy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20211126041153.16926-1-nixiaoming@huawei.com --- arch/powerpc/platforms/85xx/smp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index 83f4a6389a28..d7081e9af65c 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -220,7 +220,7 @@ static int smp_85xx_start_cpu(int cpu) local_irq_save(flags); hard_irq_disable(); - if (qoriq_pm_ops) + if (qoriq_pm_ops && qoriq_pm_ops->cpu_up_prepare) qoriq_pm_ops->cpu_up_prepare(cpu); /* if cpu is not spinning, reset it */ @@ -292,7 +292,7 @@ static int smp_85xx_kick_cpu(int nr) booting_thread_hwid = cpu_thread_in_core(nr); primary = cpu_first_thread_sibling(nr); - if (qoriq_pm_ops) + if (qoriq_pm_ops && qoriq_pm_ops->cpu_up_prepare) qoriq_pm_ops->cpu_up_prepare(nr); /* -- cgit v1.2.3 From af9d3a2984dc3501acd612c657127517a1beaf9d Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 29 Nov 2021 09:19:49 +0100 Subject: mac80211: add docs for ssn in struct tid_ampdu_tx As pointed out by Stephen, add the missing docs. Reported-by: Stephen Rothwell Link: https://lore.kernel.org/r/20211129091948.1327ec82beab.Iecc5975406a3028d35c65ff8d2dec31a693888d3@changeid Signed-off-by: Johannes Berg --- net/mac80211/sta_info.h | 1 + 1 file changed, 1 insertion(+) diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index e7443fc4669c..379fd367197f 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -176,6 +176,7 @@ struct sta_info; * @failed_bar_ssn: ssn of the last failed BAR tx attempt * @bar_pending: BAR needs to be re-sent * @amsdu: support A-MSDU withing A-MDPU + * @ssn: starting sequence number of the session * * This structure's lifetime is managed by RCU, assignments to * the array holding it must hold the aggregation mutex. -- cgit v1.2.3 From 1eda919126b420fee6b8d546f7f728fbbd4b8f11 Mon Sep 17 00:00:00 2001 From: Finn Behrens Date: Sat, 27 Nov 2021 11:28:53 +0100 Subject: nl80211: reset regdom when reloading regdb Reload the regdom when the regulatory db is reloaded. Otherwise, the user had to change the regulatoy domain to a different one and then reset it to the correct one to have a new regulatory db take effect after a reload. Signed-off-by: Finn Behrens Link: https://lore.kernel.org/r/YaIIZfxHgqc/UTA7@gimli.kloenk.dev [edit commit message] Signed-off-by: Johannes Berg --- include/net/regulatory.h | 1 + net/wireless/reg.c | 27 +++++++++++++++++++++++++-- 2 files changed, 26 insertions(+), 2 deletions(-) diff --git a/include/net/regulatory.h b/include/net/regulatory.h index 47f06f6f5a67..0cf9335431e0 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -83,6 +83,7 @@ struct regulatory_request { enum nl80211_dfs_regions dfs_region; bool intersect; bool processed; + bool reload; enum environment_cap country_ie_env; struct list_head list; }; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index df87c7f3a049..61f1bf1bc4a7 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -133,6 +133,7 @@ static u32 reg_is_indoor_portid; static void restore_regulatory_settings(bool reset_user, bool cached); static void print_regdomain(const struct ieee80211_regdomain *rd); +static void reg_process_hint(struct regulatory_request *reg_request); static const struct ieee80211_regdomain *get_cfg80211_regdom(void) { @@ -1098,6 +1099,8 @@ int reg_reload_regdb(void) const struct firmware *fw; void *db; int err; + const struct ieee80211_regdomain *current_regdomain; + struct regulatory_request *request; err = request_firmware(&fw, "regulatory.db", ®_pdev->dev); if (err) @@ -1118,8 +1121,27 @@ int reg_reload_regdb(void) if (!IS_ERR_OR_NULL(regdb)) kfree(regdb); regdb = db; - rtnl_unlock(); + /* reset regulatory domain */ + current_regdomain = get_cfg80211_regdom(); + + request = kzalloc(sizeof(*request), GFP_KERNEL); + if (!request) { + err = -ENOMEM; + goto out_unlock; + } + + request->wiphy_idx = WIPHY_IDX_INVALID; + request->alpha2[0] = current_regdomain->alpha2[0]; + request->alpha2[1] = current_regdomain->alpha2[1]; + request->initiator = NL80211_USER_REG_HINT_USER; + request->user_reg_hint_type = NL80211_USER_REG_HINT_USER; + request->reload = true; + + reg_process_hint(request); + +out_unlock: + rtnl_unlock(); out: release_firmware(fw); return err; @@ -2690,7 +2712,8 @@ reg_process_hint_user(struct regulatory_request *user_request) treatment = __reg_process_hint_user(user_request); if (treatment == REG_REQ_IGNORE || - treatment == REG_REQ_ALREADY_SET) + (treatment == REG_REQ_ALREADY_SET && + !user_request->reload)) return REG_REQ_IGNORE; user_request->intersect = treatment == REG_REQ_INTERSECT; -- cgit v1.2.3 From 9d7482771fac8d8e38e763263f2ca0ca12dd22c6 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 24 Nov 2021 17:54:04 +0300 Subject: tee: amdtee: fix an IS_ERR() vs NULL bug The __get_free_pages() function does not return error pointers it returns NULL so fix this condition to avoid a NULL dereference. Fixes: 757cc3e9ff1d ("tee: add AMD-TEE driver") Signed-off-by: Dan Carpenter Acked-by: Rijo Thomas Signed-off-by: Jens Wiklander --- drivers/tee/amdtee/core.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/tee/amdtee/core.c b/drivers/tee/amdtee/core.c index da6b88e80dc0..297dc62bca29 100644 --- a/drivers/tee/amdtee/core.c +++ b/drivers/tee/amdtee/core.c @@ -203,9 +203,8 @@ static int copy_ta_binary(struct tee_context *ctx, void *ptr, void **ta, *ta_size = roundup(fw->size, PAGE_SIZE); *ta = (void *)__get_free_pages(GFP_KERNEL, get_order(*ta_size)); - if (IS_ERR(*ta)) { - pr_err("%s: get_free_pages failed 0x%llx\n", __func__, - (u64)*ta); + if (!*ta) { + pr_err("%s: get_free_pages failed\n", __func__); rc = -ENOMEM; goto rel_fw; } -- cgit v1.2.3 From c2584017f757da3c84a743b607d6cfc763ebcc2b Mon Sep 17 00:00:00 2001 From: Vyacheslav Bocharov Date: Thu, 25 Nov 2021 16:02:47 +0300 Subject: arm64: meson: fix dts for JetHub D1 Fix misplace of cpu_cooling_maps for JetHub D1, move it to right place. Fixes: 8e279fb29039 ("arm64: dts: meson-axg: add support for JetHub D1") Signed-off-by: Vyacheslav Bocharov Reviewed-by: Neil Armstrong Signed-off-by: Neil Armstrong Link: https://lore.kernel.org/r/20211125130246.1086627-1-adeep@lexina.in --- .../dts/amlogic/meson-axg-jethome-jethub-j100.dts | 30 +++++++++++----------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j100.dts b/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j100.dts index 52ebe371df26..561eec21b4de 100644 --- a/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j100.dts +++ b/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j100.dts @@ -134,23 +134,23 @@ type = "critical"; }; }; - }; - cpu_cooling_maps: cooling-maps { - map0 { - trip = <&cpu_passive>; - cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, - <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, - <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, - <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; - }; + cpu_cooling_maps: cooling-maps { + map0 { + trip = <&cpu_passive>; + cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; - map1 { - trip = <&cpu_hot>; - cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, - <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, - <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, - <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + map1 { + trip = <&cpu_hot>; + cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; }; }; }; -- cgit v1.2.3 From 5ad77b1272fce36604779efe6e2036c500e6fe7a Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Wed, 9 Jun 2021 22:20:09 +0200 Subject: arm64: meson: remove COMMON_CLK This reverts commit aea7a80ad5effd48f44a7a08c3903168be038a43. Selecting COMMON_CLK is not necessary, it is already selected by CONFIG_ARM64 Reported-by: Geert Uytterhoeven Signed-off-by: Jerome Brunet Reviewed-by: Kevin Hilman Signed-off-by: Neil Armstrong Link: https://lore.kernel.org/r/20210609202009.1424879-1-jbrunet@baylibre.com --- arch/arm64/Kconfig.platforms | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index 1aa8b7073218..54e3910e8b9b 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -161,7 +161,6 @@ config ARCH_MEDIATEK config ARCH_MESON bool "Amlogic Platforms" - select COMMON_CLK help This enables support for the arm64 based Amlogic SoCs such as the s905, S905X/D, S912, A113X/D or S905X/D2 -- cgit v1.2.3 From 4356fd6041877ef0c91a2f6051b59bb1a8961ca2 Mon Sep 17 00:00:00 2001 From: Janne Grunau Date: Mon, 22 Nov 2021 23:24:39 +0100 Subject: dt-bindings: i2c: apple,i2c: allow multiple compatibles The intention was to have a SoC-specific and base compatible string to allow forward compatibility and SoC specific quirks, Fixes: df7c4a8c1b47 ("dt-bindings: i2c: Add Apple I2C controller bindings") Signed-off-by: Janne Grunau Cc: Mark Kettenis Reviewed-by: Sven Peter Reviewed-by: Mark Kettenis Tested-by: Hector Martin Acked-by: Wolfram Sang Acked-by: Rob Herring Signed-off-by: Hector Martin --- Documentation/devicetree/bindings/i2c/apple,i2c.yaml | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/Documentation/devicetree/bindings/i2c/apple,i2c.yaml b/Documentation/devicetree/bindings/i2c/apple,i2c.yaml index 22fc8483256f..82b953181a52 100644 --- a/Documentation/devicetree/bindings/i2c/apple,i2c.yaml +++ b/Documentation/devicetree/bindings/i2c/apple,i2c.yaml @@ -20,9 +20,9 @@ allOf: properties: compatible: - enum: - - apple,t8103-i2c - - apple,i2c + items: + - const: apple,t8103-i2c + - const: apple,i2c reg: maxItems: 1 @@ -51,7 +51,7 @@ unevaluatedProperties: false examples: - | i2c@35010000 { - compatible = "apple,t8103-i2c"; + compatible = "apple,t8103-i2c", "apple,i2c"; reg = <0x35010000 0x4000>; interrupt-parent = <&aic>; interrupts = <0 627 4>; -- cgit v1.2.3 From 0668639eaf14813a39a8d3e0e6597d568581d4ea Mon Sep 17 00:00:00 2001 From: Janne Grunau Date: Mon, 22 Nov 2021 23:24:40 +0100 Subject: arm64: dts: apple: add #interrupt-cells property to pinctrl nodes Required for devices trying to use pinctrl devices as interrupt controller. Fixes: 0a8282b83119 ("arm64: apple: Add pinctrl nodes") Signed-off-by: Janne Grunau Cc: Mark Kettenis Reviewed-by: Sven Peter Reviewed-by: Mark Kettenis Tested-by: Hector Martin Signed-off-by: Hector Martin --- arch/arm64/boot/dts/apple/t8103.dtsi | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm64/boot/dts/apple/t8103.dtsi b/arch/arm64/boot/dts/apple/t8103.dtsi index fc8b2bb06ffe..c320c8baeb41 100644 --- a/arch/arm64/boot/dts/apple/t8103.dtsi +++ b/arch/arm64/boot/dts/apple/t8103.dtsi @@ -143,6 +143,7 @@ apple,npins = <212>; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&aic>; interrupts = , , @@ -169,6 +170,7 @@ apple,npins = <42>; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&aic>; interrupts = , , @@ -189,6 +191,7 @@ apple,npins = <23>; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&aic>; interrupts = , , @@ -209,6 +212,7 @@ apple,npins = <16>; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&aic>; interrupts = , , -- cgit v1.2.3 From 973e5245637accc4002843f6b888495a6a7762bc Mon Sep 17 00:00:00 2001 From: Hu Weiwen Date: Mon, 22 Nov 2021 22:22:12 +0800 Subject: ceph: fix duplicate increment of opened_inodes metric opened_inodes is incremented twice when the same inode is opened twice with O_RDONLY and O_WRONLY respectively. To reproduce, run this python script, then check the metrics: import os for _ in range(10000): fd_r = os.open('a', os.O_RDONLY) fd_w = os.open('a', os.O_WRONLY) os.close(fd_r) os.close(fd_w) Fixes: 1dd8d4708136 ("ceph: metrics for opened files, pinned caps and opened inodes") Signed-off-by: Hu Weiwen Reviewed-by: Xiubo Li Signed-off-by: Ilya Dryomov --- fs/ceph/caps.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index b9460b6fb76f..c447fa2e2d1f 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -4350,7 +4350,7 @@ void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count) { struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(ci->vfs_inode.i_sb); int bits = (fmode << 1) | 1; - bool is_opened = false; + bool already_opened = false; int i; if (count == 1) @@ -4358,19 +4358,19 @@ void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count) spin_lock(&ci->i_ceph_lock); for (i = 0; i < CEPH_FILE_MODE_BITS; i++) { - if (bits & (1 << i)) - ci->i_nr_by_mode[i] += count; - /* - * If any of the mode ref is larger than 1, + * If any of the mode ref is larger than 0, * that means it has been already opened by * others. Just skip checking the PIN ref. */ - if (i && ci->i_nr_by_mode[i] > 1) - is_opened = true; + if (i && ci->i_nr_by_mode[i]) + already_opened = true; + + if (bits & (1 << i)) + ci->i_nr_by_mode[i] += count; } - if (!is_opened) + if (!already_opened) percpu_counter_inc(&mdsc->metric.opened_inodes); spin_unlock(&ci->i_ceph_lock); } -- cgit v1.2.3 From e485d028bb1075d6167558b47f63e10713ad2034 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 23 Nov 2021 07:30:38 -0500 Subject: ceph: initialize i_size variable in ceph_sync_read Newer compilers seem to determine that this variable being uninitialized isn't a problem, but older compilers (from the RHEL8 era) seem to choke on it and complain that it could be used uninitialized. Go ahead and initialize the variable at declaration time to silence potential compiler warnings. Fixes: c3d8e0b5de48 ("ceph: return the real size read when it hits EOF") Signed-off-by: Jeff Layton Reviewed-by: Xiubo Li Signed-off-by: Ilya Dryomov --- fs/ceph/file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 02a0a0fd9ccd..b24442e27e4e 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -847,7 +847,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to, ssize_t ret; u64 off = iocb->ki_pos; u64 len = iov_iter_count(to); - u64 i_size; + u64 i_size = i_size_read(inode); dout("sync_read on file %p %llu~%u %s\n", file, off, (unsigned)len, (file->f_flags & O_DIRECT) ? "O_DIRECT" : ""); -- cgit v1.2.3 From ee2a095d3b24f300a5e11944d208801e928f108c Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Tue, 30 Nov 2021 19:20:34 +0800 Subject: ceph: initialize pathlen variable in reconnect_caps_cb The smatch static checker warned about an uninitialized symbol usage in this function, in the case where ceph_mdsc_build_path returns an error. It turns out that that case is harmless, but it just looks sketchy. Initialize the variable at declaration time, and remove the unneeded setting of it later. Fixes: a33f6432b3a6 ("ceph: encode inodes' parent/d_name in cap reconnect message") Reported-by: Dan Carpenter Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 250aad330a10..c30eefc0ac19 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3683,7 +3683,7 @@ static int reconnect_caps_cb(struct inode *inode, struct ceph_cap *cap, struct ceph_pagelist *pagelist = recon_state->pagelist; struct dentry *dentry; char *path; - int pathlen, err; + int pathlen = 0, err; u64 pathbase; u64 snap_follows; @@ -3703,7 +3703,6 @@ static int reconnect_caps_cb(struct inode *inode, struct ceph_cap *cap, } } else { path = NULL; - pathlen = 0; pathbase = 0; } -- cgit v1.2.3 From fd84bfdddd169c219c3a637889a8b87f70a072c2 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 29 Nov 2021 12:16:39 +0100 Subject: ceph: fix up non-directory creation in SGID directories Ceph always inherits the SGID bit if it is set on the parent inode, while the generic inode_init_owner does not do this in a few cases where it can create a possible security problem (cf. [1]). Update ceph to strip the SGID bit just as inode_init_owner would. This bug was detected by the mapped mount testsuite in [3]. The testsuite tests all core VFS functionality and semantics with and without mapped mounts. That is to say it functions as a generic VFS testsuite in addition to a mapped mount testsuite. While working on mapped mount support for ceph, SIGD inheritance was the only failing test for ceph after the port. The same bug was detected by the mapped mount testsuite in XFS in January 2021 (cf. [2]). [1]: commit 0fa3ecd87848 ("Fix up non-directory creation in SGID directories") [2]: commit 01ea173e103e ("xfs: fix up non-directory creation in SGID directories") [3]: https://git.kernel.org/fs/xfs/xfstests-dev.git Cc: stable@vger.kernel.org Signed-off-by: Christian Brauner Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/file.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/fs/ceph/file.c b/fs/ceph/file.c index b24442e27e4e..c138e8126286 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -605,13 +605,25 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry, in.cap.realm = cpu_to_le64(ci->i_snap_realm->ino); in.cap.flags = CEPH_CAP_FLAG_AUTH; in.ctime = in.mtime = in.atime = iinfo.btime; - in.mode = cpu_to_le32((u32)mode); in.truncate_seq = cpu_to_le32(1); in.truncate_size = cpu_to_le64(-1ULL); in.xattr_version = cpu_to_le64(1); in.uid = cpu_to_le32(from_kuid(&init_user_ns, current_fsuid())); - in.gid = cpu_to_le32(from_kgid(&init_user_ns, dir->i_mode & S_ISGID ? - dir->i_gid : current_fsgid())); + if (dir->i_mode & S_ISGID) { + in.gid = cpu_to_le32(from_kgid(&init_user_ns, dir->i_gid)); + + /* Directories always inherit the setgid bit. */ + if (S_ISDIR(mode)) + mode |= S_ISGID; + else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) && + !in_group_p(dir->i_gid) && + !capable_wrt_inode_uidgid(&init_user_ns, dir, CAP_FSETID)) + mode &= ~S_ISGID; + } else { + in.gid = cpu_to_le32(from_kgid(&init_user_ns, current_fsgid())); + } + in.mode = cpu_to_le32((u32)mode); + in.nlink = cpu_to_le32(1); in.max_size = cpu_to_le64(lo->stripe_unit); -- cgit v1.2.3 From cb25b11943cbcc5a34531129952870420f8be858 Mon Sep 17 00:00:00 2001 From: Dinh Nguyen Date: Mon, 1 Nov 2021 19:36:30 -0500 Subject: ARM: socfpga: dts: fix qspi node compatible The QSPI flash node needs to have the required "jedec,spi-nor" in the compatible string. Fixes: 1df99da8953 ("ARM: dts: socfpga: Enable QSPI in Arria10 devkit") Signed-off-by: Dinh Nguyen --- arch/arm/boot/dts/socfpga_arria10_socdk_qspi.dts | 2 +- arch/arm/boot/dts/socfpga_arria5_socdk.dts | 2 +- arch/arm/boot/dts/socfpga_cyclone5_socdk.dts | 2 +- arch/arm/boot/dts/socfpga_cyclone5_sockit.dts | 2 +- arch/arm/boot/dts/socfpga_cyclone5_socrates.dts | 2 +- arch/arm/boot/dts/socfpga_cyclone5_sodia.dts | 2 +- arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts | 4 ++-- 7 files changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/arm/boot/dts/socfpga_arria10_socdk_qspi.dts b/arch/arm/boot/dts/socfpga_arria10_socdk_qspi.dts index 2b645642b935..2a745522404d 100644 --- a/arch/arm/boot/dts/socfpga_arria10_socdk_qspi.dts +++ b/arch/arm/boot/dts/socfpga_arria10_socdk_qspi.dts @@ -12,7 +12,7 @@ flash0: n25q00@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q00aa"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; diff --git a/arch/arm/boot/dts/socfpga_arria5_socdk.dts b/arch/arm/boot/dts/socfpga_arria5_socdk.dts index 90e676e7019f..1b02d46496a8 100644 --- a/arch/arm/boot/dts/socfpga_arria5_socdk.dts +++ b/arch/arm/boot/dts/socfpga_arria5_socdk.dts @@ -119,7 +119,7 @@ flash: flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q256a"; + compatible = "micron,n25q256a", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; diff --git a/arch/arm/boot/dts/socfpga_cyclone5_socdk.dts b/arch/arm/boot/dts/socfpga_cyclone5_socdk.dts index 6f138b2b2616..51bb436784e2 100644 --- a/arch/arm/boot/dts/socfpga_cyclone5_socdk.dts +++ b/arch/arm/boot/dts/socfpga_cyclone5_socdk.dts @@ -124,7 +124,7 @@ flash0: n25q00@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q00"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <0>; /* chip select */ spi-max-frequency = <100000000>; diff --git a/arch/arm/boot/dts/socfpga_cyclone5_sockit.dts b/arch/arm/boot/dts/socfpga_cyclone5_sockit.dts index c155ff02eb6e..cae9ddd5ed38 100644 --- a/arch/arm/boot/dts/socfpga_cyclone5_sockit.dts +++ b/arch/arm/boot/dts/socfpga_cyclone5_sockit.dts @@ -169,7 +169,7 @@ flash: flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q00"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; diff --git a/arch/arm/boot/dts/socfpga_cyclone5_socrates.dts b/arch/arm/boot/dts/socfpga_cyclone5_socrates.dts index 8d5d3996f6f2..ca18b959e655 100644 --- a/arch/arm/boot/dts/socfpga_cyclone5_socrates.dts +++ b/arch/arm/boot/dts/socfpga_cyclone5_socrates.dts @@ -80,7 +80,7 @@ flash: flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q256a"; + compatible = "micron,n25q256a", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; m25p,fast-read; diff --git a/arch/arm/boot/dts/socfpga_cyclone5_sodia.dts b/arch/arm/boot/dts/socfpga_cyclone5_sodia.dts index 99a71757cdf4..3f7aa7bf0863 100644 --- a/arch/arm/boot/dts/socfpga_cyclone5_sodia.dts +++ b/arch/arm/boot/dts/socfpga_cyclone5_sodia.dts @@ -116,7 +116,7 @@ flash0: n25q512a@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q512a"; + compatible = "micron,n25q512a", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; diff --git a/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts b/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts index a060718758b6..25874e1b9c82 100644 --- a/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts +++ b/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts @@ -224,7 +224,7 @@ n25q128@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q128"; + compatible = "micron,n25q128", "jedec,spi-nor"; reg = <0>; /* chip select */ spi-max-frequency = <100000000>; m25p,fast-read; @@ -241,7 +241,7 @@ n25q00@1 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q00"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <1>; /* chip select */ spi-max-frequency = <100000000>; m25p,fast-read; -- cgit v1.2.3 From e5e6268f77badf18bd6ab435364cfe21c7396c31 Mon Sep 17 00:00:00 2001 From: Martin Kepplinger Date: Wed, 24 Nov 2021 09:37:03 +0100 Subject: arm64: dts: imx8mq: remove interconnect property from lcdif The mxsfb driver handling imx8mq lcdif doesn't yet request the interconnect bandwidth that's needed at runtime when the description is present in the DT node. So remove that description and bring it back when it's supported. Fixes: ad1abc8a03fd ("arm64: dts: imx8mq: Add interconnect for lcdif") Signed-off-by: Martin Kepplinger Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/imx8mq.dtsi | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi index 972766b67a15..71bf497f99c2 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi @@ -524,8 +524,6 @@ <&clk IMX8MQ_VIDEO_PLL1>, <&clk IMX8MQ_VIDEO_PLL1_OUT>; assigned-clock-rates = <0>, <0>, <0>, <594000000>; - interconnects = <&noc IMX8MQ_ICM_LCDIF &noc IMX8MQ_ICS_DRAM>; - interconnect-names = "dram"; status = "disabled"; port@0 { -- cgit v1.2.3 From 737e65c7956795b3553781fb7bc82fce1c39503f Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Wed, 24 Nov 2021 15:45:41 -0300 Subject: ARM: dts: imx6ull-pinfunc: Fix CSI_DATA07__ESAI_TX0 pad name According to the i.MX6ULL Reference Manual, pad CSI_DATA07 may have the ESAI_TX0 functionality, not ESAI_T0. Also, NXP's i.MX Config Tools 10.0 generates dtsi with the MX6ULL_PAD_CSI_DATA07__ESAI_TX0 naming, so fix it accordingly. There are no devicetree users in mainline that use the old name, so just remove the old entry. Fixes: c201369d4aa5 ("ARM: dts: imx6ull: add imx6ull support") Reported-by: George Makarov Signed-off-by: Fabio Estevam Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx6ull-pinfunc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/imx6ull-pinfunc.h b/arch/arm/boot/dts/imx6ull-pinfunc.h index eb025a9d4759..7328d4ef8559 100644 --- a/arch/arm/boot/dts/imx6ull-pinfunc.h +++ b/arch/arm/boot/dts/imx6ull-pinfunc.h @@ -82,6 +82,6 @@ #define MX6ULL_PAD_CSI_DATA04__ESAI_TX_FS 0x01F4 0x0480 0x0000 0x9 0x0 #define MX6ULL_PAD_CSI_DATA05__ESAI_TX_CLK 0x01F8 0x0484 0x0000 0x9 0x0 #define MX6ULL_PAD_CSI_DATA06__ESAI_TX5_RX0 0x01FC 0x0488 0x0000 0x9 0x0 -#define MX6ULL_PAD_CSI_DATA07__ESAI_T0 0x0200 0x048C 0x0000 0x9 0x0 +#define MX6ULL_PAD_CSI_DATA07__ESAI_TX0 0x0200 0x048C 0x0000 0x9 0x0 #endif /* __DTS_IMX6ULL_PINFUNC_H */ -- cgit v1.2.3 From 042b67799e2991e301df8269e166d8bc5944495e Mon Sep 17 00:00:00 2001 From: Adam Ford Date: Sun, 28 Nov 2021 06:50:07 -0600 Subject: soc: imx: imx8m-blk-ctrl: Fix imx8mm mipi reset Most of the blk-ctrl reset bits are found in one register, however there are two bits in offset 8 for pulling the MIPI DPHY out of reset and one of them needs to be set when IMX8MM_DISPBLK_PD_MIPI_CSI is brought out of reset or the MIPI_CSI hangs. Since MIPI_DSI is impacted, add the additional one for MIPI_DSI too. Fixes: 926e57c065df ("soc: imx: imx8m-blk-ctrl: add DISP blk-ctrl") Signed-off-by: Adam Ford Reviewed-by: Fabio Estevam Reviewed-by: Lucas Stach Reviewed-by: Laurent Pinchart Tested by: Tim Harvey Signed-off-by: Shawn Guo --- drivers/soc/imx/imx8m-blk-ctrl.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/drivers/soc/imx/imx8m-blk-ctrl.c b/drivers/soc/imx/imx8m-blk-ctrl.c index 519b3651d1d9..c2f076b56e24 100644 --- a/drivers/soc/imx/imx8m-blk-ctrl.c +++ b/drivers/soc/imx/imx8m-blk-ctrl.c @@ -17,6 +17,7 @@ #define BLK_SFT_RSTN 0x0 #define BLK_CLK_EN 0x4 +#define BLK_MIPI_RESET_DIV 0x8 /* Mini/Nano DISPLAY_BLK_CTRL only */ struct imx8m_blk_ctrl_domain; @@ -36,6 +37,15 @@ struct imx8m_blk_ctrl_domain_data { const char *gpc_name; u32 rst_mask; u32 clk_mask; + + /* + * i.MX8M Mini and Nano have a third DISPLAY_BLK_CTRL register + * which is used to control the reset for the MIPI Phy. + * Since it's only present in certain circumstances, + * an if-statement should be used before setting and clearing this + * register. + */ + u32 mipi_phy_rst_mask; }; #define DOMAIN_MAX_CLKS 3 @@ -78,6 +88,8 @@ static int imx8m_blk_ctrl_power_on(struct generic_pm_domain *genpd) /* put devices into reset */ regmap_clear_bits(bc->regmap, BLK_SFT_RSTN, data->rst_mask); + if (data->mipi_phy_rst_mask) + regmap_clear_bits(bc->regmap, BLK_MIPI_RESET_DIV, data->mipi_phy_rst_mask); /* enable upstream and blk-ctrl clocks to allow reset to propagate */ ret = clk_bulk_prepare_enable(data->num_clks, domain->clks); @@ -99,6 +111,8 @@ static int imx8m_blk_ctrl_power_on(struct generic_pm_domain *genpd) /* release reset */ regmap_set_bits(bc->regmap, BLK_SFT_RSTN, data->rst_mask); + if (data->mipi_phy_rst_mask) + regmap_set_bits(bc->regmap, BLK_MIPI_RESET_DIV, data->mipi_phy_rst_mask); /* disable upstream clocks */ clk_bulk_disable_unprepare(data->num_clks, domain->clks); @@ -120,6 +134,9 @@ static int imx8m_blk_ctrl_power_off(struct generic_pm_domain *genpd) struct imx8m_blk_ctrl *bc = domain->bc; /* put devices into reset and disable clocks */ + if (data->mipi_phy_rst_mask) + regmap_clear_bits(bc->regmap, BLK_MIPI_RESET_DIV, data->mipi_phy_rst_mask); + regmap_clear_bits(bc->regmap, BLK_SFT_RSTN, data->rst_mask); regmap_clear_bits(bc->regmap, BLK_CLK_EN, data->clk_mask); @@ -480,6 +497,7 @@ static const struct imx8m_blk_ctrl_domain_data imx8mm_disp_blk_ctl_domain_data[] .gpc_name = "mipi-dsi", .rst_mask = BIT(5), .clk_mask = BIT(8) | BIT(9), + .mipi_phy_rst_mask = BIT(17), }, [IMX8MM_DISPBLK_PD_MIPI_CSI] = { .name = "dispblk-mipi-csi", @@ -488,6 +506,7 @@ static const struct imx8m_blk_ctrl_domain_data imx8mm_disp_blk_ctl_domain_data[] .gpc_name = "mipi-csi", .rst_mask = BIT(3) | BIT(4), .clk_mask = BIT(10) | BIT(11), + .mipi_phy_rst_mask = BIT(16), }, }; -- cgit v1.2.3 From 06d59d626a0a49c7bfeae52aa6f793538209f2fc Mon Sep 17 00:00:00 2001 From: Kalle Valo Date: Wed, 1 Dec 2021 15:39:52 +0200 Subject: MAINTAINERS: update Kalle Valo's email I switched to using kvalo@kernel.org, update MAINTAINERS file. Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20211201133952.31744-1-kvalo@kernel.org --- MAINTAINERS | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 7a2345ce8521..22bea147c7d8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3056,7 +3056,7 @@ F: Documentation/devicetree/bindings/phy/phy-ath79-usb.txt F: drivers/phy/qualcomm/phy-ath79-usb.c ATHEROS ATH GENERIC UTILITIES -M: Kalle Valo +M: Kalle Valo L: linux-wireless@vger.kernel.org S: Supported F: drivers/net/wireless/ath/* @@ -3071,7 +3071,7 @@ W: https://wireless.wiki.kernel.org/en/users/Drivers/ath5k F: drivers/net/wireless/ath/ath5k/ ATHEROS ATH6KL WIRELESS DRIVER -M: Kalle Valo +M: Kalle Valo L: linux-wireless@vger.kernel.org S: Supported W: https://wireless.wiki.kernel.org/en/users/Drivers/ath6kl @@ -13238,7 +13238,7 @@ F: include/uapi/linux/if_* F: include/uapi/linux/netdevice.h NETWORKING DRIVERS (WIRELESS) -M: Kalle Valo +M: Kalle Valo L: linux-wireless@vger.kernel.org S: Maintained Q: http://patchwork.kernel.org/project/linux-wireless/list/ @@ -15694,7 +15694,7 @@ T: git git://linuxtv.org/anttip/media_tree.git F: drivers/media/tuners/qt1010* QUALCOMM ATHEROS ATH10K WIRELESS DRIVER -M: Kalle Valo +M: Kalle Valo L: ath10k@lists.infradead.org S: Supported W: https://wireless.wiki.kernel.org/en/users/Drivers/ath10k @@ -15702,7 +15702,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git F: drivers/net/wireless/ath/ath10k/ QUALCOMM ATHEROS ATH11K WIRELESS DRIVER -M: Kalle Valo +M: Kalle Valo L: ath11k@lists.infradead.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git @@ -15866,7 +15866,7 @@ F: Documentation/devicetree/bindings/media/*venus* F: drivers/media/platform/qcom/venus/ QUALCOMM WCN36XX WIRELESS DRIVER -M: Kalle Valo +M: Kalle Valo L: wcn36xx@lists.infradead.org S: Supported W: https://wireless.wiki.kernel.org/en/users/Drivers/wcn36xx -- cgit v1.2.3 From 54baf56eaa40aa5cdcd02b3c20d593e4e1211220 Mon Sep 17 00:00:00 2001 From: Mike Tipton Date: Mon, 8 Nov 2021 20:34:38 -0800 Subject: clk: Don't parent clks until the parent is fully registered Before commit fc0c209c147f ("clk: Allow parents to be specified without string names") child clks couldn't find their parent until the parent clk was added to a list in __clk_core_init(). After that commit, child clks can reference their parent clks directly via a clk_hw pointer, or they can lookup that clk_hw pointer via DT if the parent clk is registered with an OF clk provider. The common clk framework treats hw->core being non-NULL as "the clk is registered" per the logic within clk_core_fill_parent_index(): parent = entry->hw->core; /* * We have a direct reference but it isn't registered yet? * Orphan it and let clk_reparent() update the orphan status * when the parent is registered. */ if (!parent) Therefore we need to be extra careful to not set hw->core until the clk is fully registered with the clk framework. Otherwise we can get into a situation where a child finds a parent clk and we move the child clk off the orphan list when the parent isn't actually registered, wrecking our enable accounting and breaking critical clks. Consider the following scenario: CPU0 CPU1 ---- ---- struct clk_hw clkBad; struct clk_hw clkA; clkA.init.parent_hws = { &clkBad }; clk_hw_register(&clkA) clk_hw_register(&clkBad) ... __clk_register() hw->core = core ... __clk_register() __clk_core_init() clk_prepare_lock() __clk_init_parent() clk_core_get_parent_by_index() clk_core_fill_parent_index() if (entry->hw) { parent = entry->hw->core; At this point, 'parent' points to clkBad even though clkBad hasn't been fully registered yet. Ouch! A similar problem can happen if a clk controller registers orphan clks that are referenced in the DT node of another clk controller. Let's fix all this by only setting the hw->core pointer underneath the clk prepare lock in __clk_core_init(). This way we know that clk_core_fill_parent_index() can't see hw->core be non-NULL until the clk is fully registered. Fixes: fc0c209c147f ("clk: Allow parents to be specified without string names") Signed-off-by: Mike Tipton Link: https://lore.kernel.org/r/20211109043438.4639-1-quic_mdtipton@quicinc.com [sboyd@kernel.org: Reword commit text, update comment] Signed-off-by: Stephen Boyd --- drivers/clk/clk.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index f467d63bbf1e..566ee2c78709 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -3418,6 +3418,14 @@ static int __clk_core_init(struct clk_core *core) clk_prepare_lock(); + /* + * Set hw->core after grabbing the prepare_lock to synchronize with + * callers of clk_core_fill_parent_index() where we treat hw->core + * being NULL as the clk not being registered yet. This is crucial so + * that clks aren't parented until their parent is fully registered. + */ + core->hw->core = core; + ret = clk_pm_runtime_get(core); if (ret) goto unlock; @@ -3582,8 +3590,10 @@ static int __clk_core_init(struct clk_core *core) out: clk_pm_runtime_put(core); unlock: - if (ret) + if (ret) { hlist_del_init(&core->child_node); + core->hw->core = NULL; + } clk_prepare_unlock(); @@ -3847,7 +3857,6 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) core->num_parents = init->num_parents; core->min_rate = 0; core->max_rate = ULONG_MAX; - hw->core = core; ret = clk_core_populate_parent_map(core, init); if (ret) @@ -3865,7 +3874,7 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) goto fail_create_clk; } - clk_core_link_consumer(hw->core, hw->clk); + clk_core_link_consumer(core, hw->clk); ret = __clk_core_init(core); if (!ret) -- cgit v1.2.3 From 4ebd29f91629e69da7d57390cdc953772eee03ab Mon Sep 17 00:00:00 2001 From: Stephan Gerhold Date: Mon, 6 Dec 2021 12:38:28 +0100 Subject: soc: imx: Register SoC device only on i.MX boards At the moment, using the ARM32 multi_v7_defconfig always results in two SoCs being exposed in sysfs. This is wrong, as far as I'm aware the Qualcomm DragonBoard 410c does not actually make use of a i.MX SoC. :) qcom-db410c:/sys/devices/soc0$ grep . * family:Freescale i.MX machine:Qualcomm Technologies, Inc. APQ 8016 SBC revision:0.0 serial_number:0000000000000000 soc_id:Unknown qcom-db410c:/sys/devices/soc1$ grep . * family:Snapdragon machine:APQ8016 ... This happens because imx_soc_device_init() registers the soc device unconditionally, even when running on devices that do not make use of i.MX. Arnd already reported this more than a year ago and even suggested a fix similar to this commit, but for some reason it was never submitted. Fix it by checking if the "__mxc_cpu_type" variable was actually initialized by earlier platform code. On devices without i.MX it will simply stay 0. Cc: Peng Fan Fixes: d2199b34871b ("ARM: imx: use device_initcall for imx_soc_device_init") Reported-by: Arnd Bergmann Link: https://lore.kernel.org/r/CAK8P3a0hxO1TmK6oOMQ70AHSWJnP_CAq57YMOutrxkSYNjFeuw@mail.gmail.com/ Signed-off-by: Stephan Gerhold Reviewed-by: Fabio Estevam Reviewed-by: Peng Fan Signed-off-by: Shawn Guo --- drivers/soc/imx/soc-imx.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/soc/imx/soc-imx.c b/drivers/soc/imx/soc-imx.c index ac6d856ba228..77bc12039c3d 100644 --- a/drivers/soc/imx/soc-imx.c +++ b/drivers/soc/imx/soc-imx.c @@ -36,6 +36,10 @@ static int __init imx_soc_device_init(void) int ret; int i; + /* Return early if this is running on devices with different SoCs */ + if (!__mxc_cpu_type) + return 0; + if (of_machine_is_compatible("fsl,ls1021a")) return 0; -- cgit v1.2.3 From d599f714b73e4177dfdfe64fce09175568288ee9 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 3 Dec 2021 14:04:24 +0200 Subject: iwlwifi: mvm: don't crash on invalid rate w/o STA If we get to the WARN_ONCE(..., "Got a HT rate (...)", ...) here with a NULL sta, then we crash because mvmsta is bad and we try to dereference it. Fix that by printing -1 as the state if no station was given. Signed-off-by: Johannes Berg Fixes: 6761a718263a ("iwlwifi: mvm: add explicit check for non-data frames in get Tx rate") Signed-off-by: Luca Coelho Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/iwlwifi.20211203140410.1a1541d7dcb5.I606c746e11447fe168cf046376b70b04e278c3b4@changeid --- drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index bdd4ee432548..76e0b7b45980 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -269,17 +269,18 @@ static u32 iwl_mvm_get_tx_rate(struct iwl_mvm *mvm, u8 rate_plcp; u32 rate_flags = 0; bool is_cck; - struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); /* info->control is only relevant for non HW rate control */ if (!ieee80211_hw_check(mvm->hw, HAS_RATE_CONTROL)) { + struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); + /* HT rate doesn't make sense for a non data frame */ WARN_ONCE(info->control.rates[0].flags & IEEE80211_TX_RC_MCS && !ieee80211_is_data(fc), "Got a HT rate (flags:0x%x/mcs:%d/fc:0x%x/state:%d) for a non data frame\n", info->control.rates[0].flags, info->control.rates[0].idx, - le16_to_cpu(fc), mvmsta->sta_state); + le16_to_cpu(fc), sta ? mvmsta->sta_state : -1); rate_idx = info->control.rates[0].idx; } -- cgit v1.2.3 From efdbfa0ad03e764419378485d1b8f6e7706fb1a3 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 4 Dec 2021 18:38:33 +0100 Subject: iwlwifi: fix LED dependencies The dependencies for LED configuration are highly inconsistent and too complicated at the moment. One of the results is a randconfig failure I get very rarely when LEDS_CLASS is in a loadable module, but the wireless core is built-in: WARNING: unmet direct dependencies detected for MAC80211_LEDS Depends on [n]: NET [=y] && WIRELESS [=y] && MAC80211 [=y] && (LEDS_CLASS [=m]=y || LEDS_CLASS [=m]=MAC80211 [=y]) Selected by [m]: - IWLEGACY [=m] && NETDEVICES [=y] && WLAN [=y] && WLAN_VENDOR_INTEL [=y] - IWLWIFI_LEDS [=y] && NETDEVICES [=y] && WLAN [=y] && WLAN_VENDOR_INTEL [=y] && IWLWIFI [=m] && (LEDS_CLASS [=m]=y || LEDS_CLASS [=m]=IWLWIFI [=m]) && (IWLMVM [=m] || IWLDVM [=m]) aarch64-linux-ld: drivers/net/wireless/ath/ath5k/led.o: in function `ath5k_register_led': led.c:(.text+0x60): undefined reference to `led_classdev_register_ext' aarch64-linux-ld: drivers/net/wireless/ath/ath5k/led.o: in function `ath5k_unregister_leds': led.c:(.text+0x200): undefined reference to `led_classdev_unregister' For iwlwifi, the dependency is wrong, since this config prevents the MAC80211_LEDS code from being part of a built-in MAC80211 driver. For iwlegacy, this is worse because the driver tries to force-enable the other subsystems, which is both a layering violation and a bug because it will still fail with MAC80211=y and IWLEGACY=m, leading to LEDS_CLASS being a module as well. The actual link failure in the ath5k driver is a result of MAC80211_LEDS being enabled but not usable. With the Kconfig logic fixed in the Intel drivers, the ath5k driver works as expected again. Signed-off-by: Arnd Bergmann Acked-by: Luca Coelho Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20211204173848.873293-1-arnd@kernel.org --- drivers/net/wireless/intel/iwlegacy/Kconfig | 4 ++-- drivers/net/wireless/intel/iwlwifi/Kconfig | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/intel/iwlegacy/Kconfig b/drivers/net/wireless/intel/iwlegacy/Kconfig index 24fe3f63c321..7eacc8e58ee1 100644 --- a/drivers/net/wireless/intel/iwlegacy/Kconfig +++ b/drivers/net/wireless/intel/iwlegacy/Kconfig @@ -2,14 +2,13 @@ config IWLEGACY tristate select FW_LOADER - select NEW_LEDS - select LEDS_CLASS select LEDS_TRIGGERS select MAC80211_LEDS config IWL4965 tristate "Intel Wireless WiFi 4965AGN (iwl4965)" depends on PCI && MAC80211 + depends on LEDS_CLASS=y || LEDS_CLASS=MAC80211 select IWLEGACY help This option enables support for @@ -38,6 +37,7 @@ config IWL4965 config IWL3945 tristate "Intel PRO/Wireless 3945ABG/BG Network Connection (iwl3945)" depends on PCI && MAC80211 + depends on LEDS_CLASS=y || LEDS_CLASS=MAC80211 select IWLEGACY help Select to build the driver supporting the: diff --git a/drivers/net/wireless/intel/iwlwifi/Kconfig b/drivers/net/wireless/intel/iwlwifi/Kconfig index 1085afbefba8..418ae4f870ab 100644 --- a/drivers/net/wireless/intel/iwlwifi/Kconfig +++ b/drivers/net/wireless/intel/iwlwifi/Kconfig @@ -47,7 +47,7 @@ if IWLWIFI config IWLWIFI_LEDS bool - depends on LEDS_CLASS=y || LEDS_CLASS=IWLWIFI + depends on LEDS_CLASS=y || LEDS_CLASS=MAC80211 depends on IWLMVM || IWLDVM select LEDS_TRIGGERS select MAC80211_LEDS -- cgit v1.2.3 From c68115fc537518b8ff2c54b3e2984a60977affed Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 4 Dec 2021 18:38:34 +0100 Subject: brcmsmac: rework LED dependencies This is now the only driver that selects the LEDS_CLASS framework, which is normally user-selectable. While it doesn't strictly cause a bug, rework the Kconfig logic to be more consistent with what other drivers do, and only enable LED support in brcmsmac if the dependencies are all there, rather than using 'select' to enable what it needs. Signed-off-by: Arnd Bergmann Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20211204173848.873293-2-arnd@kernel.org --- drivers/net/wireless/broadcom/brcm80211/Kconfig | 14 +++++++++----- drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile | 2 +- drivers/net/wireless/broadcom/brcm80211/brcmsmac/led.h | 2 +- 3 files changed, 11 insertions(+), 7 deletions(-) diff --git a/drivers/net/wireless/broadcom/brcm80211/Kconfig b/drivers/net/wireless/broadcom/brcm80211/Kconfig index 5bf2318763c5..3a1a35b5672f 100644 --- a/drivers/net/wireless/broadcom/brcm80211/Kconfig +++ b/drivers/net/wireless/broadcom/brcm80211/Kconfig @@ -7,16 +7,20 @@ config BRCMSMAC depends on MAC80211 depends on BCMA_POSSIBLE select BCMA - select NEW_LEDS if BCMA_DRIVER_GPIO - select LEDS_CLASS if BCMA_DRIVER_GPIO select BRCMUTIL select FW_LOADER select CORDIC help This module adds support for PCIe wireless adapters based on Broadcom - IEEE802.11n SoftMAC chipsets. It also has WLAN led support, which will - be available if you select BCMA_DRIVER_GPIO. If you choose to build a - module, the driver will be called brcmsmac.ko. + IEEE802.11n SoftMAC chipsets. If you choose to build a module, the + driver will be called brcmsmac.ko. + +config BRCMSMAC_LEDS + def_bool BRCMSMAC && BCMA_DRIVER_GPIO && MAC80211_LEDS + help + The brcmsmac LED support depends on the presence of the + BCMA_DRIVER_GPIO driver, and it only works if LED support + is enabled and reachable from the driver module. source "drivers/net/wireless/broadcom/brcm80211/brcmfmac/Kconfig" diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile index 482d7737764d..090757730ba6 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile @@ -42,6 +42,6 @@ brcmsmac-y := \ brcms_trace_events.o \ debug.o -brcmsmac-$(CONFIG_BCMA_DRIVER_GPIO) += led.o +brcmsmac-$(CONFIG_BRCMSMAC_LEDS) += led.o obj-$(CONFIG_BRCMSMAC) += brcmsmac.o diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/led.h b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/led.h index d65f5c268fd7..2a5cbeb9e783 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/led.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/led.h @@ -24,7 +24,7 @@ struct brcms_led { struct gpio_desc *gpiod; }; -#ifdef CONFIG_BCMA_DRIVER_GPIO +#ifdef CONFIG_BRCMSMAC_LEDS void brcms_led_unregister(struct brcms_info *wl); int brcms_led_register(struct brcms_info *wl); #else -- cgit v1.2.3 From f7d55d2e439fa4430755d69a5d7ad16d43a5ebe6 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 4 Dec 2021 18:38:35 +0100 Subject: mt76: mt7921: fix build regression After mt7921s got added, there are two possible build problems: a) mt7921s does not get built at all if mt7921e is not also enabled b) there is a link error when mt7921e is a loadable module, but mt7921s configured as built-in: ERROR: modpost: "mt7921_mac_sta_add" [drivers/net/wireless/mediatek/mt76/mt7921/mt7921e.ko] undefined! ERROR: modpost: "mt7921_mac_sta_assoc" [drivers/net/wireless/mediatek/mt76/mt7921/mt7921e.ko] undefined! ERROR: modpost: "mt7921_mac_sta_remove" [drivers/net/wireless/mediatek/mt76/mt7921/mt7921e.ko] undefined! ERROR: modpost: "mt7921_mac_write_txwi" [drivers/net/wireless/mediatek/mt76/mt7921/mt7921e.ko] undefined! ERROR: modpost: "mt7921_mcu_drv_pmctrl" [drivers/net/wireless/mediatek/mt76/mt7921/mt7921e.ko] undefined! ERROR: modpost: "mt7921_mcu_fill_message" [drivers/net/wireless/mediatek/mt76/mt7921/mt7921e.ko] undefined! ERROR: modpost: "mt7921_mcu_parse_response" [drivers/net/wireless/mediatek/mt76/mt7921/mt7921e.ko] undefined! ERROR: modpost: "mt7921_ops" [drivers/net/wireless/mediatek/mt76/mt7921/mt7921e.ko] undefined! ERROR: modpost: "mt7921_queue_rx_skb" [drivers/net/wireless/mediatek/mt76/mt7921/mt7921e.ko] undefined! ERROR: modpost: "mt7921_update_channel" [drivers/net/wireless/mediatek/mt76/mt7921/mt7921e.ko] undefined! Fix both by making sure that Kbuild enters the subdirectory when either one is enabled. Fixes: 48fab5bbef40 ("mt76: mt7921: introduce mt7921s support") Signed-off-by: Arnd Bergmann Acked-by: Felix Fietkau Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20211204173848.873293-3-arnd@kernel.org --- drivers/net/wireless/mediatek/mt76/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile index 79ab850a45a2..c78ae4b89761 100644 --- a/drivers/net/wireless/mediatek/mt76/Makefile +++ b/drivers/net/wireless/mediatek/mt76/Makefile @@ -34,4 +34,4 @@ obj-$(CONFIG_MT76x2_COMMON) += mt76x2/ obj-$(CONFIG_MT7603E) += mt7603/ obj-$(CONFIG_MT7615_COMMON) += mt7615/ obj-$(CONFIG_MT7915E) += mt7915/ -obj-$(CONFIG_MT7921E) += mt7921/ +obj-$(CONFIG_MT7921_COMMON) += mt7921/ -- cgit v1.2.3 From ff9f9c6e74848170fcb45c8403c80d661484c8c9 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 8 Dec 2021 13:33:07 +0300 Subject: vduse: fix memory corruption in vduse_dev_ioctl() The "config.offset" comes from the user. There needs to a check to prevent it being out of bounds. The "config.offset" and "dev->config_size" variables are both type u32. So if the offset if out of bounds then the "dev->config_size - config.offset" subtraction results in a very high u32 value. The out of bounds offset can result in memory corruption. Fixes: c8a6153b6c59 ("vduse: Introduce VDUSE - vDPA Device in Userspace") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/20211208103307.GA3778@kili Signed-off-by: Michael S. Tsirkin Cc: stable@vger.kernel.org --- drivers/vdpa/vdpa_user/vduse_dev.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index c9204c62f339..1a206f95d73a 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -975,7 +975,8 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, break; ret = -EINVAL; - if (config.length == 0 || + if (config.offset > dev->config_size || + config.length == 0 || config.length > dev->config_size - config.offset) break; -- cgit v1.2.3 From 3ed21c1451a14d139e1ceb18f2fa70865ce3195a Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 8 Dec 2021 13:33:37 +0300 Subject: vdpa: check that offsets are within bounds In this function "c->off" is a u32 and "size" is a long. On 64bit systems if "c->off" is greater than "size" then "size - c->off" is a negative and we always return -E2BIG. But on 32bit systems the subtraction is type promoted to a high positive u32 value and basically any "c->len" is accepted. Fixes: 4c8cf31885f6 ("vhost: introduce vDPA-based backend") Reported-by: Xie Yongji Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/20211208103337.GA4047@kili Signed-off-by: Michael S. Tsirkin Cc: stable@vger.kernel.org --- drivers/vhost/vdpa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 29cced1cd277..e3c4f059b21a 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -197,7 +197,7 @@ static int vhost_vdpa_config_validate(struct vhost_vdpa *v, struct vdpa_device *vdpa = v->vdpa; long size = vdpa->config->get_config_size(vdpa); - if (c->len == 0) + if (c->len == 0 || c->off > size) return -EINVAL; if (c->len > size - c->off) -- cgit v1.2.3 From dc1db0060c02d119fd4196924eff2d1129e9a442 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 8 Dec 2021 18:09:56 +0300 Subject: vduse: check that offset is within bounds in get_config() This condition checks "len" but it does not check "offset" and that could result in an out of bounds read if "offset > dev->config_size". The problem is that since both variables are unsigned the "dev->config_size - offset" subtraction would result in a very high unsigned value. I think these checks might not be necessary because "len" and "offset" are supposed to already have been validated using the vhost_vdpa_config_validate() function. But I do not know the code perfectly, and I like to be safe. Fixes: c8a6153b6c59 ("vduse: Introduce VDUSE - vDPA Device in Userspace") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/20211208150956.GA29160@kili Signed-off-by: Michael S. Tsirkin Cc: stable@vger.kernel.org --- drivers/vdpa/vdpa_user/vduse_dev.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 1a206f95d73a..eddcb64a910a 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -655,7 +655,8 @@ static void vduse_vdpa_get_config(struct vdpa_device *vdpa, unsigned int offset, { struct vduse_dev *dev = vdpa_to_vduse(vdpa); - if (len > dev->config_size - offset) + if (offset > dev->config_size || + len > dev->config_size - offset) return; memcpy(buf, dev->config + offset, len); -- cgit v1.2.3 From 27d9839f17940e8edc475df616bbd9cf7ede8d05 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 6 Dec 2021 09:50:18 +0100 Subject: virtio: always enter drivers/virtio/ When neither VIRTIO_PCI_LIB nor VIRTIO are enabled, but the alibaba vdpa driver is, the kernel runs into a link error because the legacy virtio module never gets built: x86_64-linux-ld: drivers/vdpa/alibaba/eni_vdpa.o: in function `eni_vdpa_set_features': eni_vdpa.c:(.text+0x23f): undefined reference to `vp_legacy_set_features' x86_64-linux-ld: drivers/vdpa/alibaba/eni_vdpa.o: in function `eni_vdpa_set_vq_state': eni_vdpa.c:(.text+0x2fe): undefined reference to `vp_legacy_get_queue_enable' x86_64-linux-ld: drivers/vdpa/alibaba/eni_vdpa.o: in function `eni_vdpa_set_vq_address': eni_vdpa.c:(.text+0x376): undefined reference to `vp_legacy_set_queue_address' x86_64-linux-ld: drivers/vdpa/alibaba/eni_vdpa.o: in function `eni_vdpa_set_vq_ready': eni_vdpa.c:(.text+0x3b4): undefined reference to `vp_legacy_set_queue_address' x86_64-linux-ld: drivers/vdpa/alibaba/eni_vdpa.o: in function `eni_vdpa_free_irq': eni_vdpa.c:(.text+0x460): undefined reference to `vp_legacy_queue_vector' x86_64-linux-ld: eni_vdpa.c:(.text+0x4b7): undefined reference to `vp_legacy_config_vector' x86_64-linux-ld: drivers/vdpa/alibaba/eni_vdpa.o: in function `eni_vdpa_reset': When VIRTIO_PCI_LIB was added, it was correctly added to drivers/Makefile as well, but for the legacy module, this is missing. Solve this by always entering drivers/virtio during the build and letting its Makefile take care of the individual options, rather than having a separate line for each sub-option. Fixes: 64b9f64f80a6 ("vdpa: introduce virtio pci driver") Fixes: e85087beedca ("eni_vdpa: add vDPA driver for Alibaba ENI") Fixes: d89c8169bd70 ("virtio-pci: introduce legacy device module") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20211206085034.2836099-1-arnd@kernel.org Signed-off-by: Michael S. Tsirkin --- drivers/Makefile | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/Makefile b/drivers/Makefile index be5d40ae1488..a110338c860c 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -41,8 +41,7 @@ obj-$(CONFIG_DMADEVICES) += dma/ # SOC specific infrastructure drivers. obj-y += soc/ -obj-$(CONFIG_VIRTIO) += virtio/ -obj-$(CONFIG_VIRTIO_PCI_LIB) += virtio/ +obj-y += virtio/ obj-$(CONFIG_VDPA) += vdpa/ obj-$(CONFIG_XEN) += xen/ -- cgit v1.2.3 From 817fc978b5a29b039db0418a91072b31c9aab152 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 1 Dec 2021 11:20:18 +0000 Subject: virtio_ring: Fix querying of maximum DMA mapping size for virtio device virtio_max_dma_size() returns the maximum DMA mapping size of the virtio device by querying dma_max_mapping_size() for the device when the DMA API is in use for the vring. Unfortunately, the device passed is initialised by register_virtio_device() and does not inherit the DMA configuration from its parent, resulting in SWIOTLB errors when bouncing is enabled and the default 256K mapping limit (IO_TLB_SEGSIZE) is not respected: | virtio-pci 0000:00:01.0: swiotlb buffer is full (sz: 294912 bytes), total 1024 (slots), used 725 (slots) Follow the pattern used elsewhere in the virtio_ring code when calling into the DMA layer and pass the parent device to dma_max_mapping_size() instead. Cc: Marc Zyngier Cc: Quentin Perret Cc: "Michael S. Tsirkin" Cc: Jason Wang Signed-off-by: Will Deacon Link: https://lore.kernel.org/r/20211201112018.25276-1-will@kernel.org Acked-by: Jason Wang Tested-by: Suzuki K Poulose Fixes: e6d6dd6c875e ("virtio: Introduce virtio_max_dma_size()") Cc: Joerg Roedel Cc: Konrad Rzeszutek Wilk Cc: Christoph Hellwig Cc: Robin Murphy Signed-off-by: Steven Price Signed-off-by: Suzuki K Poulose Cc: stable@vger.kernel.org Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_ring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 6d2614e34470..028b05d44546 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -268,7 +268,7 @@ size_t virtio_max_dma_size(struct virtio_device *vdev) size_t max_segment_size = SIZE_MAX; if (vring_use_dma_api(vdev)) - max_segment_size = dma_max_mapping_size(&vdev->dev); + max_segment_size = dma_max_mapping_size(vdev->dev.parent); return max_segment_size; } -- cgit v1.2.3 From 1db8f5fc2e5c66a5c51e1f6488e0ba7d45c29ae4 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Thu, 25 Nov 2021 20:18:23 -0500 Subject: virtio/vsock: fix the transport to work with VMADDR_CID_ANY The VMADDR_CID_ANY flag used by a socket means that the socket isn't bound to any specific CID. For example, a host vsock server may want to be bound with VMADDR_CID_ANY, so that a guest vsock client can connect to the host server with CID=VMADDR_CID_HOST (i.e. 2), and meanwhile, a host vsock client can connect to the same local server with CID=VMADDR_CID_LOCAL (i.e. 1). The current implementation sets the destination socket's svm_cid to a fixed CID value after the first client's connection, which isn't an expected operation. For example, if the guest client first connects to the host server, the server's svm_cid gets set to VMADDR_CID_HOST, then other host clients won't be able to connect to the server anymore. Reproduce steps: 1. Run the host server: socat VSOCK-LISTEN:1234,fork - 2. Run a guest client to connect to the host server: socat - VSOCK-CONNECT:2:1234 3. Run a host client to connect to the host server: socat - VSOCK-CONNECT:1:1234 Without this patch, step 3. above fails to connect, and socat complains "socat[1720] E connect(5, AF=40 cid:1 port:1234, 16): Connection reset by peer". With this patch, the above works well. Fixes: c0cfa2d8a788 ("vsock: add multi-transports support") Signed-off-by: Wei Wang Link: https://lore.kernel.org/r/20211126011823.1760-1-wei.w.wang@intel.com Signed-off-by: Michael S. Tsirkin Reviewed-by: Stefano Garzarella --- net/vmw_vsock/virtio_transport_common.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 59ee1be5a6dd..ec2c2afbf0d0 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1299,7 +1299,8 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, space_available = virtio_transport_space_update(sk, pkt); /* Update CID in case it has changed after a transport reset event */ - vsk->local_addr.svm_cid = dst.svm_cid; + if (vsk->local_addr.svm_cid != VMADDR_CID_ANY) + vsk->local_addr.svm_cid = dst.svm_cid; if (space_available) sk->sk_write_space(sk); -- cgit v1.2.3 From bb47620be322c5e9e372536cb6b54e17b3a00258 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 30 Nov 2021 06:29:49 +0200 Subject: vdpa: Consider device id larger than 31 virtio device id value can be more than 31. Hence, use BIT_ULL in assignment. Fixes: 33b347503f01 ("vdpa: Define vdpa mgmt device, ops and a netlink interface") Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Parav Pandit Acked-by: Jason Wang Link: https://lore.kernel.org/r/20211130042949.88958-1-parav@nvidia.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 7332a74a4b00..09bbe53c3ac4 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -404,7 +404,8 @@ static int vdpa_mgmtdev_fill(const struct vdpa_mgmt_dev *mdev, struct sk_buff *m goto msg_err; while (mdev->id_table[i].device) { - supported_classes |= BIT(mdev->id_table[i].device); + if (mdev->id_table[i].device <= 63) + supported_classes |= BIT_ULL(mdev->id_table[i].device); i++; } -- cgit v1.2.3 From 09d97da660ff77df20984496aa0abcd6b88819f2 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Wed, 8 Dec 2021 17:27:19 +0800 Subject: MIPS: Only define pci_remap_iospace() for Ralink After commit 9f76779f2418 ("MIPS: implement architecture-specific 'pci_remap_iospace()'"), there exists the following warning on the Loongson64 platform: loongson-pci 1a000000.pci: IO 0x0018020000..0x001803ffff -> 0x0000020000 loongson-pci 1a000000.pci: MEM 0x0040000000..0x007fffffff -> 0x0040000000 ------------[ cut here ]------------ WARNING: CPU: 2 PID: 1 at arch/mips/pci/pci-generic.c:55 pci_remap_iospace+0x84/0x90 resource start address is not zero ... Call Trace: [] show_stack+0x40/0x120 [] dump_stack_lvl+0x58/0x74 [] __warn+0xe0/0x110 [] warn_slowpath_fmt+0xa4/0xd0 [] pci_remap_iospace+0x84/0x90 [] devm_pci_remap_iospace+0x5c/0xb8 [] devm_of_pci_bridge_init+0x178/0x1f8 [] devm_pci_alloc_host_bridge+0x78/0x98 [] loongson_pci_probe+0x34/0x160 [] platform_probe+0x6c/0xe0 [] really_probe+0xbc/0x340 [] __driver_probe_device+0x98/0x110 [] driver_probe_device+0x50/0x118 [] __driver_attach+0x80/0x118 [] bus_for_each_dev+0x80/0xc8 [] bus_add_driver+0x130/0x210 [] driver_register+0x8c/0x150 [] do_one_initcall+0x54/0x288 [] kernel_init_freeable+0x27c/0x2e4 [] kernel_init+0x2c/0x134 [] ret_from_kernel_thread+0x14/0x1c ---[ end trace e4a0efe10aa5cce6 ]--- loongson-pci 1a000000.pci: error -19: failed to map resource [io 0x20000-0x3ffff] We can see that the resource start address is 0x0000020000, because the ISA Bridge used the zero address which is defined in the dts file arch/mips/boot/dts/loongson/ls7a-pch.dtsi: ISA Bridge: /bus@10000000/isa@18000000 IO 0x0000000018000000..0x000000001801ffff -> 0x0000000000000000 Based on the above analysis, the architecture-specific pci_remap_iospace() is not suitable for Loongson64, we should only define pci_remap_iospace() for Ralink on MIPS based on the commit background. Fixes: 9f76779f2418 ("MIPS: implement architecture-specific 'pci_remap_iospace()'") Suggested-by: Thomas Bogendoerfer Signed-off-by: Tiezhu Yang Tested-by: Sergio Paracuellos Acked-by: Sergio Paracuellos Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/mach-ralink/spaces.h | 2 ++ arch/mips/include/asm/pci.h | 4 ---- arch/mips/pci/pci-generic.c | 2 ++ 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/mips/include/asm/mach-ralink/spaces.h b/arch/mips/include/asm/mach-ralink/spaces.h index 05d14c21c417..f7af11ea2d61 100644 --- a/arch/mips/include/asm/mach-ralink/spaces.h +++ b/arch/mips/include/asm/mach-ralink/spaces.h @@ -6,5 +6,7 @@ #define PCI_IOSIZE SZ_64K #define IO_SPACE_LIMIT (PCI_IOSIZE - 1) +#define pci_remap_iospace pci_remap_iospace + #include #endif diff --git a/arch/mips/include/asm/pci.h b/arch/mips/include/asm/pci.h index 421231f55935..9ffc8192adae 100644 --- a/arch/mips/include/asm/pci.h +++ b/arch/mips/include/asm/pci.h @@ -20,10 +20,6 @@ #include #include -#ifdef CONFIG_PCI_DRIVERS_GENERIC -#define pci_remap_iospace pci_remap_iospace -#endif - #ifdef CONFIG_PCI_DRIVERS_LEGACY /* diff --git a/arch/mips/pci/pci-generic.c b/arch/mips/pci/pci-generic.c index 18eb8a453a86..d2d68bac3d25 100644 --- a/arch/mips/pci/pci-generic.c +++ b/arch/mips/pci/pci-generic.c @@ -47,6 +47,7 @@ void pcibios_fixup_bus(struct pci_bus *bus) pci_read_bridge_bases(bus); } +#ifdef pci_remap_iospace int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr) { unsigned long vaddr; @@ -60,3 +61,4 @@ int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr) set_io_port_base(vaddr); return 0; } +#endif -- cgit v1.2.3 From 842470c4e211f284a224842849b1fa81b130c154 Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Wed, 20 Oct 2021 18:57:40 +0200 Subject: Revert "drm/fb-helper: improve DRM fbdev emulation device names" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit b3484d2b03e4c940a9598aa841a52d69729c582a. That change attempted to improve the DRM drivers fbdev emulation device names to avoid having confusing names like "simpledrmdrmfb" in /proc/fb. But unfortunately, there are user-space programs such as pm-utils that match against the fbdev names and so broke after the mentioned commit. Since the names in /proc/fb are used by tools that consider it an uAPI, let's restore the old names even when this lead to silly names like the one mentioned above. Fixes: b3484d2b03e4 ("drm/fb-helper: improve DRM fbdev emulation device names") Reported-by: Johannes Stezenbach Signed-off-by: Javier Martinez Canillas Reviewed-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20211020165740.3011927-1-javierm@redhat.com --- drivers/gpu/drm/drm_fb_helper.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 8e7a124d6c5a..22bf690910b2 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -1743,7 +1743,13 @@ void drm_fb_helper_fill_info(struct fb_info *info, sizes->fb_width, sizes->fb_height); info->par = fb_helper; - snprintf(info->fix.id, sizeof(info->fix.id), "%s", + /* + * The DRM drivers fbdev emulation device name can be confusing if the + * driver name also has a "drm" suffix on it. Leading to names such as + * "simpledrmdrmfb" in /proc/fb. Unfortunately, it's an uAPI and can't + * be changed due user-space tools (e.g: pm-utils) matching against it. + */ + snprintf(info->fix.id, sizeof(info->fix.id), "%sdrmfb", fb_helper->dev->driver->name); } -- cgit v1.2.3 From 92816e2629808726af015c7f5b14adc8e4f8b147 Mon Sep 17 00:00:00 2001 From: Jie2x Zhou Date: Thu, 9 Dec 2021 10:02:30 +0800 Subject: selftests: net: Correct ping6 expected rc from 2 to 1 ./fcnal-test.sh -v -t ipv6_ping TEST: ping out, VRF bind - ns-B IPv6 LLA [FAIL] TEST: ping out, VRF bind - multicast IP [FAIL] ping6 is failing as it should. COMMAND: ip netns exec ns-A /bin/ping6 -c1 -w1 fe80::7c4c:bcff:fe66:a63a%red strace of ping6 shows it is failing with '1', so change the expected rc from 2 to 1. Fixes: c0644e71df33 ("selftests: Add ipv6 ping tests to fcnal-test") Reported-by: kernel test robot Suggested-by: David Ahern Signed-off-by: Jie2x Zhou Link: https://lore.kernel.org/r/20211209020230.37270-1-jie2x.zhou@intel.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/fcnal-test.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index a1da013d847b..29cc72d7c3d0 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -2191,7 +2191,7 @@ ipv6_ping_vrf() log_start show_hint "Fails since VRF device does not support linklocal or multicast" run_cmd ${ping6} -c1 -w1 ${a} - log_test_addr ${a} $? 2 "ping out, VRF bind" + log_test_addr ${a} $? 1 "ping out, VRF bind" done for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} ${MCAST}%${NSA_DEV} -- cgit v1.2.3 From edce10ee21f3916f5da34e55bbc03103c604ba70 Mon Sep 17 00:00:00 2001 From: Philipp Rudo Date: Wed, 8 Dec 2021 14:07:40 +0100 Subject: s390/kexec_file: print some more error messages Be kind and give some more information on what went wrong. Signed-off-by: Philipp Rudo Link: https://lore.kernel.org/r/20211208130741.5821-2-prudo@redhat.com Signed-off-by: Heiko Carstens --- arch/s390/kernel/machine_kexec_file.c | 27 ++++++++++++++++++++++++--- 1 file changed, 24 insertions(+), 3 deletions(-) diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c index 9975ad200d74..a8bfa7c8cbba 100644 --- a/arch/s390/kernel/machine_kexec_file.c +++ b/arch/s390/kernel/machine_kexec_file.c @@ -7,6 +7,8 @@ * Author(s): Philipp Rudo */ +#define pr_fmt(fmt) "kexec: " fmt + #include #include #include @@ -290,9 +292,16 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, const Elf_Shdr *relsec, const Elf_Shdr *symtab) { + const char *strtab, *name, *shstrtab; + const Elf_Shdr *sechdrs; Elf_Rela *relas; int i, r_type; + /* String & section header string table */ + sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff; + strtab = (char *)pi->ehdr + sechdrs[symtab->sh_link].sh_offset; + shstrtab = (char *)pi->ehdr + sechdrs[pi->ehdr->e_shstrndx].sh_offset; + relas = (void *)pi->ehdr + relsec->sh_offset; for (i = 0; i < relsec->sh_size / sizeof(*relas); i++) { @@ -304,15 +313,27 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, sym = (void *)pi->ehdr + symtab->sh_offset; sym += ELF64_R_SYM(relas[i].r_info); - if (sym->st_shndx == SHN_UNDEF) + if (sym->st_name) + name = strtab + sym->st_name; + else + name = shstrtab + sechdrs[sym->st_shndx].sh_name; + + if (sym->st_shndx == SHN_UNDEF) { + pr_err("Undefined symbol: %s\n", name); return -ENOEXEC; + } - if (sym->st_shndx == SHN_COMMON) + if (sym->st_shndx == SHN_COMMON) { + pr_err("symbol '%s' in common section\n", name); return -ENOEXEC; + } if (sym->st_shndx >= pi->ehdr->e_shnum && - sym->st_shndx != SHN_ABS) + sym->st_shndx != SHN_ABS) { + pr_err("Invalid section %d for symbol %s\n", + sym->st_shndx, name); return -ENOEXEC; + } loc = pi->purgatory_buf; loc += section->sh_offset; -- cgit v1.2.3 From 41967a37b8eedfee15b81406a9f3015be90d3980 Mon Sep 17 00:00:00 2001 From: Philipp Rudo Date: Wed, 8 Dec 2021 14:07:41 +0100 Subject: s390/kexec_file: fix error handling when applying relocations arch_kexec_apply_relocations_add currently ignores all errors returned by arch_kexec_do_relocs. This means that every unknown relocation is silently skipped causing unpredictable behavior while the relocated code runs. Fix this by checking for errors and fail kexec_file_load if an unknown relocation type is encountered. The problem was found after gcc changed its behavior and used R_390_PLT32DBL relocations for brasl instruction and relied on ld to resolve the relocations in the final link in case direct calls are possible. As the purgatory code is only linked partially (option -r) ld didn't resolve the relocations leaving them for arch_kexec_do_relocs. But arch_kexec_do_relocs doesn't know how to handle R_390_PLT32DBL relocations so they were silently skipped. This ultimately caused an endless loop in the purgatory as the brasl instructions kept branching to itself. Fixes: 71406883fd35 ("s390/kexec_file: Add kexec_file_load system call") Reported-by: Tao Liu Signed-off-by: Philipp Rudo Link: https://lore.kernel.org/r/20211208130741.5821-3-prudo@redhat.com Signed-off-by: Heiko Carstens --- arch/s390/kernel/machine_kexec_file.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c index a8bfa7c8cbba..876cdd3c994e 100644 --- a/arch/s390/kernel/machine_kexec_file.c +++ b/arch/s390/kernel/machine_kexec_file.c @@ -296,6 +296,7 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, const Elf_Shdr *sechdrs; Elf_Rela *relas; int i, r_type; + int ret; /* String & section header string table */ sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff; @@ -347,7 +348,11 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, addr = section->sh_addr + relas[i].r_offset; r_type = ELF64_R_TYPE(relas[i].r_info); - arch_kexec_do_relocs(r_type, loc, val, addr); + ret = arch_kexec_do_relocs(r_type, loc, val, addr); + if (ret) { + pr_err("Unknown rela relocation: %d\n", r_type); + return -ENOEXEC; + } } return 0; } -- cgit v1.2.3 From ac8fc6af1ab62b2e5d57ddadc8bd4c9433c49a72 Mon Sep 17 00:00:00 2001 From: Jerome Marchand Date: Wed, 8 Dec 2021 16:15:03 +0100 Subject: s390/ftrace: remove preempt_disable()/preempt_enable() pair It looks like commit ce5e48036c9e76a2 ("ftrace: disable preemption when recursion locked") missed a spot in kprobe_ftrace_handler() in arch/s390/kernel/ftrace.c. Remove the superfluous preempt_disable/enable_notrace() there too. Fixes: ce5e48036c9e76a2 ("ftrace: disable preemption when recursion locked") Signed-off-by: Jerome Marchand Link: https://lore.kernel.org/r/20211208151503.1510381-1-jmarchan@redhat.com Signed-off-by: Heiko Carstens --- arch/s390/kernel/ftrace.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 5510c7d10ddc..21d62d8b6b9a 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -290,7 +290,6 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, return; regs = ftrace_get_regs(fregs); - preempt_disable_notrace(); p = get_kprobe((kprobe_opcode_t *)ip); if (unlikely(!p) || kprobe_disabled(p)) goto out; @@ -318,7 +317,6 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, } __this_cpu_write(current_kprobe, NULL); out: - preempt_enable_notrace(); ftrace_test_recursion_unlock(bit); } NOKPROBE_SYMBOL(kprobe_ftrace_handler); -- cgit v1.2.3 From abf0e8e4ef25478a4390115e6a953d589d1f9ffd Mon Sep 17 00:00:00 2001 From: Alexander Egorenkov Date: Thu, 9 Dec 2021 08:38:17 +0100 Subject: s390/kexec: handle R_390_PLT32DBL rela in arch_kexec_apply_relocations_add() Starting with gcc 11.3, the C compiler will generate PLT-relative function calls even if they are local and do not require it. Later on during linking, the linker will replace all PLT-relative calls to local functions with PC-relative ones. Unfortunately, the purgatory code of kexec/kdump is not being linked as a regular executable or shared library would have been, and therefore, all PLT-relative addresses remain in the generated purgatory object code unresolved. This leads to the situation where the purgatory code is being executed during kdump with all PLT-relative addresses unresolved. And this results in endless loops within the purgatory code. Furthermore, the clang C compiler has always behaved like described above and this commit should fix kdump for kernels built with the latter. Because the purgatory code is no regular executable or shared library, contains only calls to local functions and has no PLT, all R_390_PLT32DBL relocation entries can be resolved just like a R_390_PC32DBL one. * https://refspecs.linuxfoundation.org/ELF/zSeries/lzsabi0_zSeries/x1633.html#AEN1699 Relocation entries of purgatory code generated with gcc 11.3 ------------------------------------------------------------ $ readelf -r linux/arch/s390/purgatory/purgatory.o Relocation section '.rela.text' at offset 0x370 contains 5 entries: Offset Info Type Sym. Value Sym. Name + Addend 00000000005c 000c00000013 R_390_PC32DBL 0000000000000000 purgatory_sha_regions + 2 00000000007a 000d00000014 R_390_PLT32DBL 0000000000000000 sha256_update + 2 00000000008c 000e00000014 R_390_PLT32DBL 0000000000000000 sha256_final + 2 000000000092 000800000013 R_390_PC32DBL 0000000000000000 .LC0 + 2 0000000000a0 000f00000014 R_390_PLT32DBL 0000000000000000 memcmp + 2 Relocation entries of purgatory code generated with gcc 11.2 ------------------------------------------------------------ $ readelf -r linux/arch/s390/purgatory/purgatory.o Relocation section '.rela.text' at offset 0x368 contains 5 entries: Offset Info Type Sym. Value Sym. Name + Addend 00000000005c 000c00000013 R_390_PC32DBL 0000000000000000 purgatory_sha_regions + 2 00000000007a 000d00000013 R_390_PC32DBL 0000000000000000 sha256_update + 2 00000000008c 000e00000013 R_390_PC32DBL 0000000000000000 sha256_final + 2 000000000092 000800000013 R_390_PC32DBL 0000000000000000 .LC0 + 2 0000000000a0 000f00000013 R_390_PC32DBL 0000000000000000 memcmp + 2 Signed-off-by: Alexander Egorenkov Reported-by: Tao Liu Suggested-by: Philipp Rudo Reviewed-by: Philipp Rudo Cc: Link: https://lore.kernel.org/r/20211209073817.82196-1-egorenar@linux.ibm.com Signed-off-by: Heiko Carstens --- arch/s390/kernel/machine_kexec_file.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c index 876cdd3c994e..8f43575a4dd3 100644 --- a/arch/s390/kernel/machine_kexec_file.c +++ b/arch/s390/kernel/machine_kexec_file.c @@ -348,6 +348,10 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, addr = section->sh_addr + relas[i].r_offset; r_type = ELF64_R_TYPE(relas[i].r_info); + + if (r_type == R_390_PLT32DBL) + r_type = R_390_PC32DBL; + ret = arch_kexec_do_relocs(r_type, loc, val, addr); if (ret) { pr_err("Unknown rela relocation: %d\n", r_type); -- cgit v1.2.3 From 5dcf0c3084eb098bbb702f2f5ee55666047997d4 Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Thu, 9 Dec 2021 15:21:06 +0100 Subject: s390: enable switchdev support in defconfig The HiperSockets Converged Interface (HSCI) introduced with commit 4e20e73e631a ("s390/qeth: Switchdev event handler") requires CONFIG_SWITCHDEV=y to be usable. Similarly when using Linux controlled SR-IOV capable PF devices with the mlx5_core driver CONFIG_SWITCHDEV=y as well as CONFIG_MLX5_ESWITCH=y are necessary to actually get link on the created VFs. So let's add these to the defconfig to make both types of devices usable. Note also that these options are already enabled in most current distribution kernels. Signed-off-by: Niklas Schnelle Signed-off-by: Heiko Carstens --- arch/s390/configs/debug_defconfig | 2 ++ arch/s390/configs/defconfig | 2 ++ 2 files changed, 4 insertions(+) diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index b626bc6e0eaf..e45cc27716de 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -117,6 +117,7 @@ CONFIG_UNIX=y CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m +CONFIG_NET_SWITCHDEV=y CONFIG_SMC=m CONFIG_SMC_DIAG=m CONFIG_INET=y @@ -511,6 +512,7 @@ CONFIG_NLMON=m CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m CONFIG_MLX5_CORE_EN=y +CONFIG_MLX5_ESWITCH=y # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_MICROCHIP is not set # CONFIG_NET_VENDOR_MICROSEMI is not set diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 0056cab27372..1c750bfca2d8 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -109,6 +109,7 @@ CONFIG_UNIX=y CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m +CONFIG_NET_SWITCHDEV=y CONFIG_SMC=m CONFIG_SMC_DIAG=m CONFIG_INET=y @@ -502,6 +503,7 @@ CONFIG_NLMON=m CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m CONFIG_MLX5_CORE_EN=y +CONFIG_MLX5_ESWITCH=y # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_MICROCHIP is not set # CONFIG_NET_VENDOR_MICROSEMI is not set -- cgit v1.2.3 From ab443c53916730862cec202078d36fd4008bea79 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 10 Dec 2021 06:20:46 -0800 Subject: sch_cake: do not call cake_destroy() from cake_init() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit qdiscs are not supposed to call their own destroy() method from init(), because core stack already does that. syzbot was able to trigger use after free: DEBUG_LOCKS_WARN_ON(lock->magic != lock) WARNING: CPU: 0 PID: 21902 at kernel/locking/mutex.c:586 __mutex_lock_common kernel/locking/mutex.c:586 [inline] WARNING: CPU: 0 PID: 21902 at kernel/locking/mutex.c:586 __mutex_lock+0x9ec/0x12f0 kernel/locking/mutex.c:740 Modules linked in: CPU: 0 PID: 21902 Comm: syz-executor189 Not tainted 5.16.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__mutex_lock_common kernel/locking/mutex.c:586 [inline] RIP: 0010:__mutex_lock+0x9ec/0x12f0 kernel/locking/mutex.c:740 Code: 08 84 d2 0f 85 19 08 00 00 8b 05 97 38 4b 04 85 c0 0f 85 27 f7 ff ff 48 c7 c6 20 00 ac 89 48 c7 c7 a0 fe ab 89 e8 bf 76 ba ff <0f> 0b e9 0d f7 ff ff 48 8b 44 24 40 48 8d b8 c8 08 00 00 48 89 f8 RSP: 0018:ffffc9000627f290 EFLAGS: 00010282 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: ffff88802315d700 RSI: ffffffff815f1db8 RDI: fffff52000c4fe44 RBP: ffff88818f28e000 R08: 0000000000000000 R09: 0000000000000000 R10: ffffffff815ebb5e R11: 0000000000000000 R12: 0000000000000000 R13: dffffc0000000000 R14: ffffc9000627f458 R15: 0000000093c30000 FS: 0000555556abc400(0000) GS:ffff8880b9c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fda689c3303 CR3: 000000001cfbb000 CR4: 0000000000350ef0 Call Trace: tcf_chain0_head_change_cb_del+0x2e/0x3d0 net/sched/cls_api.c:810 tcf_block_put_ext net/sched/cls_api.c:1381 [inline] tcf_block_put_ext net/sched/cls_api.c:1376 [inline] tcf_block_put+0xbc/0x130 net/sched/cls_api.c:1394 cake_destroy+0x3f/0x80 net/sched/sch_cake.c:2695 qdisc_create.constprop.0+0x9da/0x10f0 net/sched/sch_api.c:1293 tc_modify_qdisc+0x4c5/0x1980 net/sched/sch_api.c:1660 rtnetlink_rcv_msg+0x413/0xb80 net/core/rtnetlink.c:5571 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2496 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x533/0x7d0 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x904/0xdf0 net/netlink/af_netlink.c:1921 sock_sendmsg_nosec net/socket.c:704 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:724 ____sys_sendmsg+0x6e8/0x810 net/socket.c:2409 ___sys_sendmsg+0xf3/0x170 net/socket.c:2463 __sys_sendmsg+0xe5/0x1b0 net/socket.c:2492 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f1bb06badb9 Code: Unable to access opcode bytes at RIP 0x7f1bb06bad8f. RSP: 002b:00007fff3012a658 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f1bb06badb9 RDX: 0000000000000000 RSI: 00000000200007c0 RDI: 0000000000000003 RBP: 0000000000000000 R08: 0000000000000003 R09: 0000000000000003 R10: 0000000000000003 R11: 0000000000000246 R12: 00007fff3012a688 R13: 00007fff3012a6a0 R14: 00007fff3012a6e0 R15: 00000000000013c2 Fixes: 046f6fd5daef ("sched: Add Common Applications Kept Enhanced (cake) qdisc") Signed-off-by: Eric Dumazet Reported-by: syzbot Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/r/20211210142046.698336-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- net/sched/sch_cake.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 3c2300d14468..857aaebd49f4 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -2736,7 +2736,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, q->tins = kvcalloc(CAKE_MAX_TINS, sizeof(struct cake_tin_data), GFP_KERNEL); if (!q->tins) - goto nomem; + return -ENOMEM; for (i = 0; i < CAKE_MAX_TINS; i++) { struct cake_tin_data *b = q->tins + i; @@ -2766,10 +2766,6 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, q->min_netlen = ~0; q->min_adjlen = ~0; return 0; - -nomem: - cake_destroy(sch); - return -ENOMEM; } static int cake_dump(struct Qdisc *sch, struct sk_buff *skb) -- cgit v1.2.3 From 345e004d023343d38088fdfea39688aa11e06ccf Mon Sep 17 00:00:00 2001 From: Paul Chaignon Date: Fri, 10 Dec 2021 00:46:31 +0100 Subject: bpf: Fix incorrect state pruning for <8B spill/fill Commit 354e8f1970f8 ("bpf: Support <8-byte scalar spill and refill") introduced support in the verifier to track <8B spill/fills of scalars. The backtracking logic for the precision bit was however skipping spill/fills of less than 8B. That could cause state pruning to consider two states equivalent when they shouldn't be. As an example, consider the following bytecode snippet: 0: r7 = r1 1: call bpf_get_prandom_u32 2: r6 = 2 3: if r0 == 0 goto pc+1 4: r6 = 3 ... 8: [state pruning point] ... /* u32 spill/fill */ 10: *(u32 *)(r10 - 8) = r6 11: r8 = *(u32 *)(r10 - 8) 12: r0 = 0 13: if r8 == 3 goto pc+1 14: r0 = 1 15: exit The verifier first walks the path with R6=3. Given the support for <8B spill/fills, at instruction 13, it knows the condition is true and skips instruction 14. At that point, the backtracking logic kicks in but stops at the fill instruction since it only propagates the precision bit for 8B spill/fill. When the verifier then walks the path with R6=2, it will consider it safe at instruction 8 because R6 is not marked as needing precision. Instruction 14 is thus never walked and is then incorrectly removed as 'dead code'. It's also possible to lead the verifier to accept e.g. an out-of-bound memory access instead of causing an incorrect dead code elimination. This regression was found via Cilium's bpf-next CI where it was causing a conntrack map update to be silently skipped because the code had been removed by the verifier. This commit fixes it by enabling support for <8B spill/fills in the bactracking logic. In case of a <8B spill/fill, the full 8B stack slot will be marked as needing precision. Then, in __mark_chain_precision, any tracked register spilled in a marked slot will itself be marked as needing precision, regardless of the spill size. This logic makes two assumptions: (1) only 8B-aligned spill/fill are tracked and (2) spilled registers are only tracked if the spill and fill sizes are equal. Commit ef979017b837 ("bpf: selftest: Add verifier tests for <8-byte scalar spill and refill") covers the first assumption and the next commit in this patchset covers the second. Fixes: 354e8f1970f8 ("bpf: Support <8-byte scalar spill and refill") Signed-off-by: Paul Chaignon Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f3001937bbb9..f2f1ed34cfe9 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2379,8 +2379,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, */ if (insn->src_reg != BPF_REG_FP) return 0; - if (BPF_SIZE(insn->code) != BPF_DW) - return 0; /* dreg = *(u64 *)[fp - off] was a fill from the stack. * that [fp - off] slot contains scalar that needs to be @@ -2403,8 +2401,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, /* scalars can only be spilled into stack */ if (insn->dst_reg != BPF_REG_FP) return 0; - if (BPF_SIZE(insn->code) != BPF_DW) - return 0; spi = (-insn->off - 1) / BPF_REG_SIZE; if (spi >= 64) { verbose(env, "BUG spi %d\n", spi); -- cgit v1.2.3 From 0be2516f865f5a876837184a8385163ff64a5889 Mon Sep 17 00:00:00 2001 From: Paul Chaignon Date: Fri, 10 Dec 2021 00:47:00 +0100 Subject: selftests/bpf: Tests for state pruning with u32 spill/fill This patch adds tests for the verifier's tracking for spilled, <8B registers. The first two test cases ensure the verifier doesn't incorrectly prune states in case of <8B spill/fills. The last one simply checks that a filled u64 register is marked unknown if the register spilled in the same slack slot was less than 8B. The map value access at the end of the first program is only incorrect for the path R6=32. If the precision bit for register R8 isn't backtracked through the u32 spill/fill, the R6=32 path is pruned at instruction 9 and the program is incorrectly accepted. The second program is a variation of the same with u32 spills and a u64 fill. The additional instructions to introduce the first pruning point may be a bit fragile as they depend on the heuristics for pruning points in the verifier (currently at least 8 instructions and 2 jumps). If the heuristics are changed, the pruning point may move (e.g., to the subsequent jump) or disappear, which would cause the test to always pass. Signed-off-by: Paul Chaignon Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/verifier/search_pruning.c | 71 ++++++++++++++++++++++ tools/testing/selftests/bpf/verifier/spill_fill.c | 32 ++++++++++ 2 files changed, 103 insertions(+) diff --git a/tools/testing/selftests/bpf/verifier/search_pruning.c b/tools/testing/selftests/bpf/verifier/search_pruning.c index 7e50cb80873a..682519769fe3 100644 --- a/tools/testing/selftests/bpf/verifier/search_pruning.c +++ b/tools/testing/selftests/bpf/verifier/search_pruning.c @@ -132,6 +132,77 @@ .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, +{ + "precision tracking for u32 spill/fill", + .insns = { + BPF_MOV64_REG(BPF_REG_7, BPF_REG_1), + BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32), + BPF_MOV32_IMM(BPF_REG_6, 32), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_MOV32_IMM(BPF_REG_6, 4), + /* Additional insns to introduce a pruning point. */ + BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_3, 0), + /* u32 spill/fill */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_6, -8), + BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_10, -8), + /* out-of-bound map value access for r6=32 */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_8), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 15 }, + .result = REJECT, + .errstr = "R0 min value is outside of the allowed memory range", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "precision tracking for u32 spills, u64 fill", + .insns = { + BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV32_IMM(BPF_REG_7, 0xffffffff), + /* Additional insns to introduce a pruning point. */ + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_ALU32_IMM(BPF_DIV, BPF_REG_3, 0), + /* u32 spills, u64 fill */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_6, -4), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_8, BPF_REG_10, -8), + /* if r8 != X goto pc+1 r8 known in fallthrough branch */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_8, 0xffffffff, 1), + BPF_MOV64_IMM(BPF_REG_3, 1), + /* if r8 == X goto pc+1 condition always true on first + * traversal, so starts backtracking to mark r8 as requiring + * precision. r7 marked as needing precision. r6 not marked + * since it's not tracked. + */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_8, 0xffffffff, 1), + /* fails if r8 correctly marked unknown after fill. */ + BPF_ALU32_IMM(BPF_DIV, BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "div by zero", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, { "allocated_stack", .insns = { diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c index 7ab3de108761..6c907144311f 100644 --- a/tools/testing/selftests/bpf/verifier/spill_fill.c +++ b/tools/testing/selftests/bpf/verifier/spill_fill.c @@ -175,6 +175,38 @@ .errstr = "invalid access to packet", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, +{ + "Spill u32 const scalars. Refill as u64. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + /* r6 = 0 */ + BPF_MOV32_IMM(BPF_REG_6, 0), + /* r7 = 20 */ + BPF_MOV32_IMM(BPF_REG_7, 20), + /* *(u32 *)(r10 -4) = r6 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_6, -4), + /* *(u32 *)(r10 -8) = r7 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, -8), + /* r4 = *(u64 *)(r10 -8) */ + BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -8), + /* r0 = r2 */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=65535 */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), + /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv,umax=65535 */ + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv20 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, { "Spill a u32 const scalar. Refill as u16 from fp-6. Offset to skb->data", .insns = { -- cgit v1.2.3 From bcd0f93353326954817a4f9fa55ec57fb38acbb0 Mon Sep 17 00:00:00 2001 From: Hangyu Hua Date: Thu, 9 Dec 2021 16:28:39 +0800 Subject: phonet: refcount leak in pep_sock_accep sock_hold(sk) is invoked in pep_sock_accept(), but __sock_put(sk) is not invoked in subsequent failure branches(pep_accept_conn() != 0). Signed-off-by: Hangyu Hua Link: https://lore.kernel.org/r/20211209082839.33985-1-hbh25y@gmail.com Signed-off-by: Jakub Kicinski --- net/phonet/pep.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/phonet/pep.c b/net/phonet/pep.c index a1525916885a..b4f90afb0638 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -868,6 +868,7 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp, err = pep_accept_conn(newsk, skb); if (err) { + __sock_put(sk); sock_put(newsk); newsk = NULL; goto drop; -- cgit v1.2.3 From 71ddeac8cd1d217744a0e060ff520e147c9328d1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 9 Dec 2021 10:50:58 -0800 Subject: inet_diag: fix kernel-infoleak for UDP sockets KMSAN reported a kernel-infoleak [1], that can exploited by unpriv users. After analysis it turned out UDP was not initializing r->idiag_expires. Other users of inet_sk_diag_fill() might make the same mistake in the future, so fix this in inet_sk_diag_fill(). [1] BUG: KMSAN: kernel-infoleak in instrument_copy_to_user include/linux/instrumented.h:121 [inline] BUG: KMSAN: kernel-infoleak in copyout lib/iov_iter.c:156 [inline] BUG: KMSAN: kernel-infoleak in _copy_to_iter+0x69d/0x25c0 lib/iov_iter.c:670 instrument_copy_to_user include/linux/instrumented.h:121 [inline] copyout lib/iov_iter.c:156 [inline] _copy_to_iter+0x69d/0x25c0 lib/iov_iter.c:670 copy_to_iter include/linux/uio.h:155 [inline] simple_copy_to_iter+0xf3/0x140 net/core/datagram.c:519 __skb_datagram_iter+0x2cb/0x1280 net/core/datagram.c:425 skb_copy_datagram_iter+0xdc/0x270 net/core/datagram.c:533 skb_copy_datagram_msg include/linux/skbuff.h:3657 [inline] netlink_recvmsg+0x660/0x1c60 net/netlink/af_netlink.c:1974 sock_recvmsg_nosec net/socket.c:944 [inline] sock_recvmsg net/socket.c:962 [inline] sock_read_iter+0x5a9/0x630 net/socket.c:1035 call_read_iter include/linux/fs.h:2156 [inline] new_sync_read fs/read_write.c:400 [inline] vfs_read+0x1631/0x1980 fs/read_write.c:481 ksys_read+0x28c/0x520 fs/read_write.c:619 __do_sys_read fs/read_write.c:629 [inline] __se_sys_read fs/read_write.c:627 [inline] __x64_sys_read+0xdb/0x120 fs/read_write.c:627 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x54/0xd0 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x44/0xae Uninit was created at: slab_post_alloc_hook mm/slab.h:524 [inline] slab_alloc_node mm/slub.c:3251 [inline] __kmalloc_node_track_caller+0xe0c/0x1510 mm/slub.c:4974 kmalloc_reserve net/core/skbuff.c:354 [inline] __alloc_skb+0x545/0xf90 net/core/skbuff.c:426 alloc_skb include/linux/skbuff.h:1126 [inline] netlink_dump+0x3d5/0x16a0 net/netlink/af_netlink.c:2245 __netlink_dump_start+0xd1c/0xee0 net/netlink/af_netlink.c:2370 netlink_dump_start include/linux/netlink.h:254 [inline] inet_diag_handler_cmd+0x2e7/0x400 net/ipv4/inet_diag.c:1343 sock_diag_rcv_msg+0x24a/0x620 netlink_rcv_skb+0x447/0x800 net/netlink/af_netlink.c:2491 sock_diag_rcv+0x63/0x80 net/core/sock_diag.c:276 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x1095/0x1360 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x16f3/0x1870 net/netlink/af_netlink.c:1916 sock_sendmsg_nosec net/socket.c:704 [inline] sock_sendmsg net/socket.c:724 [inline] sock_write_iter+0x594/0x690 net/socket.c:1057 do_iter_readv_writev+0xa7f/0xc70 do_iter_write+0x52c/0x1500 fs/read_write.c:851 vfs_writev fs/read_write.c:924 [inline] do_writev+0x63f/0xe30 fs/read_write.c:967 __do_sys_writev fs/read_write.c:1040 [inline] __se_sys_writev fs/read_write.c:1037 [inline] __x64_sys_writev+0xe5/0x120 fs/read_write.c:1037 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x54/0xd0 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x44/0xae Bytes 68-71 of 312 are uninitialized Memory access of size 312 starts at ffff88812ab54000 Data copied to user address 0000000020001440 CPU: 1 PID: 6365 Comm: syz-executor801 Not tainted 5.16.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 3c4d05c80567 ("inet_diag: Introduce the inet socket dumping routine") Signed-off-by: Eric Dumazet Reported-by: syzbot Link: https://lore.kernel.org/r/20211209185058.53917-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- net/ipv4/inet_diag.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index c8fa6e7f7d12..581b5b2d72a5 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -261,6 +261,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, r->idiag_state = sk->sk_state; r->idiag_timer = 0; r->idiag_retrans = 0; + r->idiag_expires = 0; if (inet_diag_msg_attrs_fill(sk, skb, r, ext, sk_user_ns(NETLINK_CB(cb->skb).sk), @@ -314,9 +315,6 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, r->idiag_retrans = icsk->icsk_probes_out; r->idiag_expires = jiffies_delta_to_msecs(sk->sk_timer.expires - jiffies); - } else { - r->idiag_timer = 0; - r->idiag_expires = 0; } if ((ext & (1 << (INET_DIAG_INFO - 1))) && handler->idiag_info_size) { -- cgit v1.2.3 From 94f2a444f28a649926c410eb9a38afb13a83ebe0 Mon Sep 17 00:00:00 2001 From: Daniele Palmas Date: Fri, 10 Dec 2021 10:57:22 +0100 Subject: net: usb: qmi_wwan: add Telit 0x1070 composition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add the following Telit FN990 composition: 0x1070: tty, adb, rmnet, tty, tty, tty, tty Signed-off-by: Daniele Palmas Acked-by: Bjørn Mork Link: https://lore.kernel.org/r/20211210095722.22269-1-dnlplm@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/usb/qmi_wwan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 86b814e99224..f510e8219470 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1358,6 +1358,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)}, /* Telit LE922A */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)}, /* Telit FN980 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1060, 2)}, /* Telit LN920 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x1070, 2)}, /* Telit FN990 */ {QMI_FIXED_INTF(0x1bc7, 0x1100, 3)}, /* Telit ME910 */ {QMI_FIXED_INTF(0x1bc7, 0x1101, 3)}, /* Telit ME910 dual modem */ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ -- cgit v1.2.3 From ee60e626d536da4c710b3634afe68fe7c6d69b59 Mon Sep 17 00:00:00 2001 From: Filip Pokryvka Date: Fri, 10 Dec 2021 18:50:32 +0100 Subject: netdevsim: don't overwrite read only ethtool parms Ethtool ring feature has _max_pending attributes read-only. Set only read-write attributes in nsim_set_ringparam. This patch is useful, if netdevsim device is set-up using NetworkManager, because NetworkManager sends 0 as MAX values, as it is pointless to retrieve them in extra call, because they should be read-only. Then, the device is left in incosistent state (value > MAX). Fixes: a7fc6db099b5 ("netdevsim: support ethtool ring and coalesce settings") Signed-off-by: Filip Pokryvka Link: https://lore.kernel.org/r/20211210175032.411872-1-fpokryvk@redhat.com Signed-off-by: Jakub Kicinski --- drivers/net/netdevsim/ethtool.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c index 0ab6a40be611..a6a713b31aad 100644 --- a/drivers/net/netdevsim/ethtool.c +++ b/drivers/net/netdevsim/ethtool.c @@ -77,7 +77,10 @@ static int nsim_set_ringparam(struct net_device *dev, { struct netdevsim *ns = netdev_priv(dev); - memcpy(&ns->ethtool.ring, ring, sizeof(ns->ethtool.ring)); + ns->ethtool.ring.rx_pending = ring->rx_pending; + ns->ethtool.ring.rx_jumbo_pending = ring->rx_jumbo_pending; + ns->ethtool.ring.rx_mini_pending = ring->rx_mini_pending; + ns->ethtool.ring.tx_pending = ring->tx_pending; return 0; } -- cgit v1.2.3 From 3748939bce3fc7a15ef07161826507fbe410bb7a Mon Sep 17 00:00:00 2001 From: Po-Hsu Lin Date: Fri, 10 Dec 2021 15:25:23 +0800 Subject: selftests: icmp_redirect: pass xfail=0 to log_test() If any sub-test in this icmp_redirect.sh is failing but not expected to fail. The script will complain: ./icmp_redirect.sh: line 72: [: 1: unary operator expected This is because when the sub-test is not expected to fail, we won't pass any value for the xfail local variable in log_test() and thus it's empty. Fix this by passing 0 as the 4th variable to log_test() for non-xfail cases. v2: added fixes tag Fixes: 0a36a75c6818 ("selftests: icmp_redirect: support expected failures") Signed-off-by: Po-Hsu Lin Signed-off-by: David S. Miller --- tools/testing/selftests/net/icmp_redirect.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/icmp_redirect.sh b/tools/testing/selftests/net/icmp_redirect.sh index ecbf57f264ed..7b9d6e31b8e7 100755 --- a/tools/testing/selftests/net/icmp_redirect.sh +++ b/tools/testing/selftests/net/icmp_redirect.sh @@ -311,7 +311,7 @@ check_exception() ip -netns h1 ro get ${H1_VRF_ARG} ${H2_N2_IP} | \ grep -E -v 'mtu|redirected' | grep -q "cache" fi - log_test $? 0 "IPv4: ${desc}" + log_test $? 0 "IPv4: ${desc}" 0 # No PMTU info for test "redirect" and "mtu exception plus redirect" if [ "$with_redirect" = "yes" ] && [ "$desc" != "redirect exception plus mtu" ]; then -- cgit v1.2.3 From 27cbf64a766e86f068ce6214f04c00ceb4db1af4 Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Fri, 10 Dec 2021 21:09:33 +0800 Subject: net: hns3: fix use-after-free bug in hclgevf_send_mbx_msg Currently, the hns3_remove function firstly uninstall client instance, and then uninstall acceletion engine device. The netdevice is freed in client instance uninstall process, but acceletion engine device uninstall process still use it to trace runtime information. This causes a use after free problem. So fixes it by check the instance register state to avoid use after free. Fixes: d8355240cf8f ("net: hns3: add trace event support for PF/VF mailbox") Signed-off-by: Jie Wang Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c index fdc66fae0960..c5ac6ecf36e1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c @@ -114,7 +114,8 @@ int hclgevf_send_mbx_msg(struct hclgevf_dev *hdev, memcpy(&req->msg, send_msg, sizeof(struct hclge_vf_to_pf_msg)); - trace_hclge_vf_mbx_send(hdev, req); + if (test_bit(HCLGEVF_STATE_NIC_REGISTERED, &hdev->state)) + trace_hclge_vf_mbx_send(hdev, req); /* synchronous send */ if (need_resp) { -- cgit v1.2.3 From 6dde452bceca3f2ed2b33bc46a16ff5682a03a2e Mon Sep 17 00:00:00 2001 From: Yufeng Mo Date: Fri, 10 Dec 2021 21:09:34 +0800 Subject: net: hns3: fix race condition in debugfs When multiple threads concurrently access the debugfs content, data and pointer exceptions may occur. Therefore, mutex lock protection is added for debugfs. Fixes: 5e69ea7ee2a6 ("net: hns3: refactor the debugfs process") Signed-off-by: Yufeng Mo Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hnae3.h | 2 ++ drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 20 ++++++++++++++------ 2 files changed, 16 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 3f7a9a4c59d5..63f5abcc6bf4 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -839,6 +839,8 @@ struct hnae3_handle { u8 netdev_flags; struct dentry *hnae3_dbgfs; + /* protects concurrent contention between debugfs commands */ + struct mutex dbgfs_lock; /* Network interface message level enabled bits */ u32 msg_enable; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 081295bff765..c381f8af67f0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -1226,6 +1226,7 @@ static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer, if (ret) return ret; + mutex_lock(&handle->dbgfs_lock); save_buf = &hns3_dbg_cmd[index].buf; if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) || @@ -1238,15 +1239,15 @@ static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer, read_buf = *save_buf; } else { read_buf = kvzalloc(hns3_dbg_cmd[index].buf_len, GFP_KERNEL); - if (!read_buf) - return -ENOMEM; + if (!read_buf) { + ret = -ENOMEM; + goto out; + } /* save the buffer addr until the last read operation */ *save_buf = read_buf; - } - /* get data ready for the first time to read */ - if (!*ppos) { + /* get data ready for the first time to read */ ret = hns3_dbg_read_cmd(dbg_data, hns3_dbg_cmd[index].cmd, read_buf, hns3_dbg_cmd[index].buf_len); if (ret) @@ -1255,8 +1256,10 @@ static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer, size = simple_read_from_buffer(buffer, count, ppos, read_buf, strlen(read_buf)); - if (size > 0) + if (size > 0) { + mutex_unlock(&handle->dbgfs_lock); return size; + } out: /* free the buffer for the last read operation */ @@ -1265,6 +1268,7 @@ out: *save_buf = NULL; } + mutex_unlock(&handle->dbgfs_lock); return ret; } @@ -1337,6 +1341,8 @@ int hns3_dbg_init(struct hnae3_handle *handle) debugfs_create_dir(hns3_dbg_dentry[i].name, handle->hnae3_dbgfs); + mutex_init(&handle->dbgfs_lock); + for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++) { if ((hns3_dbg_cmd[i].cmd == HNAE3_DBG_CMD_TM_NODES && ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2) || @@ -1363,6 +1369,7 @@ int hns3_dbg_init(struct hnae3_handle *handle) return 0; out: + mutex_destroy(&handle->dbgfs_lock); debugfs_remove_recursive(handle->hnae3_dbgfs); handle->hnae3_dbgfs = NULL; return ret; @@ -1378,6 +1385,7 @@ void hns3_dbg_uninit(struct hnae3_handle *handle) hns3_dbg_cmd[i].buf = NULL; } + mutex_destroy(&handle->dbgfs_lock); debugfs_remove_recursive(handle->hnae3_dbgfs); handle->hnae3_dbgfs = NULL; } -- cgit v1.2.3 From 7e0147592b5c4f9e2eb8c54a7857a56d4863f74e Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sat, 11 Dec 2021 10:11:30 -0700 Subject: selftests: Add duplicate config only for MD5 VRF tests Commit referenced below added configuration in the default VRF that duplicates a VRF to check MD5 passwords are properly used and fail when expected. That config should not be added all the time as it can cause tests to pass that should not (by matching on default VRF setup when it should not). Move the duplicate setup to a function that is only called for the MD5 tests and add a cleanup function to remove it after the MD5 tests. Fixes: 5cad8bce26e0 ("fcnal-test: Add TCP MD5 tests for VRF") Signed-off-by: David Ahern Signed-off-by: David S. Miller --- tools/testing/selftests/net/fcnal-test.sh | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 29cc72d7c3d0..dd7437dd2680 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -455,6 +455,22 @@ cleanup() ip netns del ${NSC} >/dev/null 2>&1 } +cleanup_vrf_dup() +{ + ip link del ${NSA_DEV2} >/dev/null 2>&1 + ip netns pids ${NSC} | xargs kill 2>/dev/null + ip netns del ${NSC} >/dev/null 2>&1 +} + +setup_vrf_dup() +{ + # some VRF tests use ns-C which has the same config as + # ns-B but for a device NOT in the VRF + create_ns ${NSC} "-" "-" + connect_ns ${NSA} ${NSA_DEV2} ${NSA_IP}/24 ${NSA_IP6}/64 \ + ${NSC} ${NSC_DEV} ${NSB_IP}/24 ${NSB_IP6}/64 +} + setup() { local with_vrf=${1} @@ -484,12 +500,6 @@ setup() ip -netns ${NSB} ro add ${VRF_IP}/32 via ${NSA_IP} dev ${NSB_DEV} ip -netns ${NSB} -6 ro add ${VRF_IP6}/128 via ${NSA_IP6} dev ${NSB_DEV} - - # some VRF tests use ns-C which has the same config as - # ns-B but for a device NOT in the VRF - create_ns ${NSC} "-" "-" - connect_ns ${NSA} ${NSA_DEV2} ${NSA_IP}/24 ${NSA_IP6}/64 \ - ${NSC} ${NSC_DEV} ${NSB_IP}/24 ${NSB_IP6}/64 else ip -netns ${NSA} ro add ${NSB_LO_IP}/32 via ${NSB_IP} dev ${NSA_DEV} ip -netns ${NSA} ro add ${NSB_LO_IP6}/128 via ${NSB_IP6} dev ${NSA_DEV} @@ -1240,7 +1250,9 @@ ipv4_tcp_vrf() log_test_addr ${a} $? 1 "Global server, local connection" # run MD5 tests + setup_vrf_dup ipv4_tcp_md5 + cleanup_vrf_dup # # enable VRF global server @@ -2719,7 +2731,9 @@ ipv6_tcp_vrf() log_test_addr ${a} $? 1 "Global server, local connection" # run MD5 tests + setup_vrf_dup ipv6_tcp_md5 + cleanup_vrf_dup # # enable VRF global server -- cgit v1.2.3 From 0f108ae4452025fef529671998f6c7f1c4526790 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sat, 11 Dec 2021 10:21:08 -0700 Subject: selftests: Fix raw socket bind tests with VRF Commit referenced below added negative socket bind tests for VRF. The socket binds should fail since the address to bind to is in a VRF yet the socket is not bound to the VRF or a device within it. Update the expected return code to check for 1 (bind failure) so the test passes when the bind fails as expected. Add a 'show_hint' comment to explain why the bind is expected to fail. Fixes: 75b2b2b3db4c ("selftests: Add ipv4 address bind tests to fcnal-test") Reported-by: Li Zhijian Signed-off-by: David Ahern Signed-off-by: David S. Miller --- tools/testing/selftests/net/fcnal-test.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index dd7437dd2680..4340477863d3 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -1810,8 +1810,9 @@ ipv4_addr_bind_vrf() for a in ${NSA_IP} ${VRF_IP} do log_start + show_hint "Socket not bound to VRF, but address is in VRF" run_cmd nettest -s -R -P icmp -l ${a} -b - log_test_addr ${a} $? 0 "Raw socket bind to local address" + log_test_addr ${a} $? 1 "Raw socket bind to local address" log_start run_cmd nettest -s -R -P icmp -l ${a} -I ${NSA_DEV} -b -- cgit v1.2.3 From 28a2686c185e84b6aa6a4d9c9a972360eb7ca266 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sat, 11 Dec 2021 11:26:16 -0700 Subject: selftests: Fix IPv6 address bind tests IPv6 allows binding a socket to a device then binding to an address not on the device (__inet6_bind -> ipv6_chk_addr with strict flag not set). Update the bind tests to reflect legacy behavior. Fixes: 34d0302ab861 ("selftests: Add ipv6 address bind tests to fcnal-test") Reported-by: Li Zhijian Signed-off-by: David Ahern Signed-off-by: David S. Miller --- tools/testing/selftests/net/fcnal-test.sh | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 4340477863d3..ad2982b72e02 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -3429,11 +3429,14 @@ ipv6_addr_bind_novrf() run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b log_test_addr ${a} $? 0 "TCP socket bind to local address after device bind" + # Sadly, the kernel allows binding a socket to a device and then + # binding to an address not on the device. So this test passes + # when it really should not a=${NSA_LO_IP6} log_start - show_hint "Should fail with 'Cannot assign requested address'" + show_hint "Tecnically should fail since address is not on device but kernel allows" run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b - log_test_addr ${a} $? 1 "TCP socket bind to out of scope local address" + log_test_addr ${a} $? 0 "TCP socket bind to out of scope local address" } ipv6_addr_bind_vrf() @@ -3474,10 +3477,15 @@ ipv6_addr_bind_vrf() run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b log_test_addr ${a} $? 0 "TCP socket bind to local address with device bind" + # Sadly, the kernel allows binding a socket to a device and then + # binding to an address not on the device. The only restriction + # is that the address is valid in the L3 domain. So this test + # passes when it really should not a=${VRF_IP6} log_start + show_hint "Tecnically should fail since address is not on device but kernel allows" run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b - log_test_addr ${a} $? 1 "TCP socket bind to VRF address with device bind" + log_test_addr ${a} $? 0 "TCP socket bind to VRF address with device bind" a=${NSA_LO_IP6} log_start -- cgit v1.2.3 From c9b12b59e2ea4c3c7cedec7efb071b649652f3a9 Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Mon, 6 Dec 2021 11:50:16 +0100 Subject: s390/entry: fix duplicate tracking of irq nesting level In the current code, when exiting from idle, rcu_irq_enter() is called twice during irq entry: irq_entry_enter()-> rcu_irq_enter() irq_enter() -> rcu_irq_enter() This may lead to wrong results from rcu_is_cpu_rrupt_from_idle() because of a wrong dynticks nmi nesting count. Fix this by only calling irq_enter_rcu(). Cc: # 5.12+ Reported-by: Mark Rutland Fixes: 56e62a737028 ("s390: convert to generic entry") Signed-off-by: Sven Schnelle Signed-off-by: Heiko Carstens --- arch/s390/kernel/irq.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index 0df83ecaa2e0..cb7099682340 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -138,7 +138,7 @@ void noinstr do_io_irq(struct pt_regs *regs) struct pt_regs *old_regs = set_irq_regs(regs); int from_idle; - irq_enter(); + irq_enter_rcu(); if (user_mode(regs)) { update_timer_sys(); @@ -158,7 +158,8 @@ void noinstr do_io_irq(struct pt_regs *regs) do_irq_async(regs, IO_INTERRUPT); } while (MACHINE_IS_LPAR && irq_pending(regs)); - irq_exit(); + irq_exit_rcu(); + set_irq_regs(old_regs); irqentry_exit(regs, state); @@ -172,7 +173,7 @@ void noinstr do_ext_irq(struct pt_regs *regs) struct pt_regs *old_regs = set_irq_regs(regs); int from_idle; - irq_enter(); + irq_enter_rcu(); if (user_mode(regs)) { update_timer_sys(); @@ -190,7 +191,7 @@ void noinstr do_ext_irq(struct pt_regs *regs) do_irq_async(regs, EXT_INTERRUPT); - irq_exit(); + irq_exit_rcu(); set_irq_regs(old_regs); irqentry_exit(regs, state); -- cgit v1.2.3 From 85bf17b28f97ca2749968d8786dc423db320d9c2 Mon Sep 17 00:00:00 2001 From: Jerome Marchand Date: Fri, 10 Dec 2021 10:38:27 +0100 Subject: recordmcount.pl: look for jgnop instruction as well as bcrl on s390 On s390, recordmcount.pl is looking for "bcrl 0," instructions in the objdump -d outpout. However since binutils 2.37, objdump -d display "jgnop " for the same instruction. Update the mcount_regex so that it accepts both. Signed-off-by: Jerome Marchand Reviewed-by: Miroslav Benes Acked-by: Steven Rostedt (VMware) Cc: Link: https://lore.kernel.org/r/20211210093827.1623286-1-jmarchan@redhat.com Signed-off-by: Heiko Carstens --- scripts/recordmcount.pl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index 7d631aaa0ae1..52a000b057a5 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -219,7 +219,7 @@ if ($arch eq "x86_64") { } elsif ($arch eq "s390" && $bits == 64) { if ($cc =~ /-DCC_USING_HOTPATCH/) { - $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*c0 04 00 00 00 00\\s*brcl\\s*0,[0-9a-f]+ <([^\+]*)>\$"; + $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*c0 04 00 00 00 00\\s*(bcrl\\s*0,|jgnop\\s*)[0-9a-f]+ <([^\+]*)>\$"; $mcount_adjust = 0; } $alignment = 8; -- cgit v1.2.3 From 80936d68665be88dc3bf60884a71f2694eb6b1f1 Mon Sep 17 00:00:00 2001 From: Vignesh Raghavendra Date: Thu, 9 Dec 2021 23:39:56 +0530 Subject: dmaengine: ti: k3-udma: Fix smatch warnings Smatch reports below warnings [1] wrt dereferencing rm_res when it can potentially be ERR_PTR(). This is possible when entire range is allocated to Linux Fix this case by making sure, there is no deference of rm_res when its ERR_PTR(). [1]: drivers/dma/ti/k3-udma.c:4524 udma_setup_resources() error: 'rm_res' dereferencing possible ERR_PTR() drivers/dma/ti/k3-udma.c:4537 udma_setup_resources() error: 'rm_res' dereferencing possible ERR_PTR() drivers/dma/ti/k3-udma.c:4681 bcdma_setup_resources() error: 'rm_res' dereferencing possible ERR_PTR() drivers/dma/ti/k3-udma.c:4696 bcdma_setup_resources() error: 'rm_res' dereferencing possible ERR_PTR() drivers/dma/ti/k3-udma.c:4711 bcdma_setup_resources() error: 'rm_res' dereferencing possible ERR_PTR() drivers/dma/ti/k3-udma.c:4848 pktdma_setup_resources() error: 'rm_res' dereferencing possible ERR_PTR() drivers/dma/ti/k3-udma.c:4861 pktdma_setup_resources() error: 'rm_res' dereferencing possible ERR_PTR() Reported-by: Nishanth Menon Signed-off-by: Vignesh Raghavendra Acked-by: Peter Ujfalusi Link: https://lore.kernel.org/r/20211209180957.29036-1-vigneshr@ti.com Signed-off-by: Vinod Koul --- drivers/dma/ti/k3-udma.c | 157 ++++++++++++++++++++++++++++++++--------------- 1 file changed, 107 insertions(+), 50 deletions(-) diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index 041d8e32d630..6e56d1cef5ee 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -4534,45 +4534,60 @@ static int udma_setup_resources(struct udma_dev *ud) rm_res = tisci_rm->rm_ranges[RM_RANGE_TCHAN]; if (IS_ERR(rm_res)) { bitmap_zero(ud->tchan_map, ud->tchan_cnt); + irq_res.sets = 1; } else { bitmap_fill(ud->tchan_map, ud->tchan_cnt); for (i = 0; i < rm_res->sets; i++) udma_mark_resource_ranges(ud, ud->tchan_map, &rm_res->desc[i], "tchan"); + irq_res.sets = rm_res->sets; } - irq_res.sets = rm_res->sets; /* rchan and matching default flow ranges */ rm_res = tisci_rm->rm_ranges[RM_RANGE_RCHAN]; if (IS_ERR(rm_res)) { bitmap_zero(ud->rchan_map, ud->rchan_cnt); + irq_res.sets++; } else { bitmap_fill(ud->rchan_map, ud->rchan_cnt); for (i = 0; i < rm_res->sets; i++) udma_mark_resource_ranges(ud, ud->rchan_map, &rm_res->desc[i], "rchan"); + irq_res.sets += rm_res->sets; } - irq_res.sets += rm_res->sets; irq_res.desc = kcalloc(irq_res.sets, sizeof(*irq_res.desc), GFP_KERNEL); + if (!irq_res.desc) + return -ENOMEM; rm_res = tisci_rm->rm_ranges[RM_RANGE_TCHAN]; - for (i = 0; i < rm_res->sets; i++) { - irq_res.desc[i].start = rm_res->desc[i].start; - irq_res.desc[i].num = rm_res->desc[i].num; - irq_res.desc[i].start_sec = rm_res->desc[i].start_sec; - irq_res.desc[i].num_sec = rm_res->desc[i].num_sec; + if (IS_ERR(rm_res)) { + irq_res.desc[0].start = 0; + irq_res.desc[0].num = ud->tchan_cnt; + i = 1; + } else { + for (i = 0; i < rm_res->sets; i++) { + irq_res.desc[i].start = rm_res->desc[i].start; + irq_res.desc[i].num = rm_res->desc[i].num; + irq_res.desc[i].start_sec = rm_res->desc[i].start_sec; + irq_res.desc[i].num_sec = rm_res->desc[i].num_sec; + } } rm_res = tisci_rm->rm_ranges[RM_RANGE_RCHAN]; - for (j = 0; j < rm_res->sets; j++, i++) { - if (rm_res->desc[j].num) { - irq_res.desc[i].start = rm_res->desc[j].start + - ud->soc_data->oes.udma_rchan; - irq_res.desc[i].num = rm_res->desc[j].num; - } - if (rm_res->desc[j].num_sec) { - irq_res.desc[i].start_sec = rm_res->desc[j].start_sec + - ud->soc_data->oes.udma_rchan; - irq_res.desc[i].num_sec = rm_res->desc[j].num_sec; + if (IS_ERR(rm_res)) { + irq_res.desc[i].start = 0; + irq_res.desc[i].num = ud->rchan_cnt; + } else { + for (j = 0; j < rm_res->sets; j++, i++) { + if (rm_res->desc[j].num) { + irq_res.desc[i].start = rm_res->desc[j].start + + ud->soc_data->oes.udma_rchan; + irq_res.desc[i].num = rm_res->desc[j].num; + } + if (rm_res->desc[j].num_sec) { + irq_res.desc[i].start_sec = rm_res->desc[j].start_sec + + ud->soc_data->oes.udma_rchan; + irq_res.desc[i].num_sec = rm_res->desc[j].num_sec; + } } } ret = ti_sci_inta_msi_domain_alloc_irqs(ud->dev, &irq_res); @@ -4690,14 +4705,15 @@ static int bcdma_setup_resources(struct udma_dev *ud) rm_res = tisci_rm->rm_ranges[RM_RANGE_BCHAN]; if (IS_ERR(rm_res)) { bitmap_zero(ud->bchan_map, ud->bchan_cnt); + irq_res.sets++; } else { bitmap_fill(ud->bchan_map, ud->bchan_cnt); for (i = 0; i < rm_res->sets; i++) udma_mark_resource_ranges(ud, ud->bchan_map, &rm_res->desc[i], "bchan"); + irq_res.sets += rm_res->sets; } - irq_res.sets += rm_res->sets; } /* tchan ranges */ @@ -4705,14 +4721,15 @@ static int bcdma_setup_resources(struct udma_dev *ud) rm_res = tisci_rm->rm_ranges[RM_RANGE_TCHAN]; if (IS_ERR(rm_res)) { bitmap_zero(ud->tchan_map, ud->tchan_cnt); + irq_res.sets += 2; } else { bitmap_fill(ud->tchan_map, ud->tchan_cnt); for (i = 0; i < rm_res->sets; i++) udma_mark_resource_ranges(ud, ud->tchan_map, &rm_res->desc[i], "tchan"); + irq_res.sets += rm_res->sets * 2; } - irq_res.sets += rm_res->sets * 2; } /* rchan ranges */ @@ -4720,47 +4737,72 @@ static int bcdma_setup_resources(struct udma_dev *ud) rm_res = tisci_rm->rm_ranges[RM_RANGE_RCHAN]; if (IS_ERR(rm_res)) { bitmap_zero(ud->rchan_map, ud->rchan_cnt); + irq_res.sets += 2; } else { bitmap_fill(ud->rchan_map, ud->rchan_cnt); for (i = 0; i < rm_res->sets; i++) udma_mark_resource_ranges(ud, ud->rchan_map, &rm_res->desc[i], "rchan"); + irq_res.sets += rm_res->sets * 2; } - irq_res.sets += rm_res->sets * 2; } irq_res.desc = kcalloc(irq_res.sets, sizeof(*irq_res.desc), GFP_KERNEL); + if (!irq_res.desc) + return -ENOMEM; if (ud->bchan_cnt) { rm_res = tisci_rm->rm_ranges[RM_RANGE_BCHAN]; - for (i = 0; i < rm_res->sets; i++) { - irq_res.desc[i].start = rm_res->desc[i].start + - oes->bcdma_bchan_ring; - irq_res.desc[i].num = rm_res->desc[i].num; + if (IS_ERR(rm_res)) { + irq_res.desc[0].start = oes->bcdma_bchan_ring; + irq_res.desc[0].num = ud->bchan_cnt; + i = 1; + } else { + for (i = 0; i < rm_res->sets; i++) { + irq_res.desc[i].start = rm_res->desc[i].start + + oes->bcdma_bchan_ring; + irq_res.desc[i].num = rm_res->desc[i].num; + } } } if (ud->tchan_cnt) { rm_res = tisci_rm->rm_ranges[RM_RANGE_TCHAN]; - for (j = 0; j < rm_res->sets; j++, i += 2) { - irq_res.desc[i].start = rm_res->desc[j].start + - oes->bcdma_tchan_data; - irq_res.desc[i].num = rm_res->desc[j].num; - - irq_res.desc[i + 1].start = rm_res->desc[j].start + - oes->bcdma_tchan_ring; - irq_res.desc[i + 1].num = rm_res->desc[j].num; + if (IS_ERR(rm_res)) { + irq_res.desc[i].start = oes->bcdma_tchan_data; + irq_res.desc[i].num = ud->tchan_cnt; + irq_res.desc[i + 1].start = oes->bcdma_tchan_ring; + irq_res.desc[i + 1].num = ud->tchan_cnt; + i += 2; + } else { + for (j = 0; j < rm_res->sets; j++, i += 2) { + irq_res.desc[i].start = rm_res->desc[j].start + + oes->bcdma_tchan_data; + irq_res.desc[i].num = rm_res->desc[j].num; + + irq_res.desc[i + 1].start = rm_res->desc[j].start + + oes->bcdma_tchan_ring; + irq_res.desc[i + 1].num = rm_res->desc[j].num; + } } } if (ud->rchan_cnt) { rm_res = tisci_rm->rm_ranges[RM_RANGE_RCHAN]; - for (j = 0; j < rm_res->sets; j++, i += 2) { - irq_res.desc[i].start = rm_res->desc[j].start + - oes->bcdma_rchan_data; - irq_res.desc[i].num = rm_res->desc[j].num; - - irq_res.desc[i + 1].start = rm_res->desc[j].start + - oes->bcdma_rchan_ring; - irq_res.desc[i + 1].num = rm_res->desc[j].num; + if (IS_ERR(rm_res)) { + irq_res.desc[i].start = oes->bcdma_rchan_data; + irq_res.desc[i].num = ud->rchan_cnt; + irq_res.desc[i + 1].start = oes->bcdma_rchan_ring; + irq_res.desc[i + 1].num = ud->rchan_cnt; + i += 2; + } else { + for (j = 0; j < rm_res->sets; j++, i += 2) { + irq_res.desc[i].start = rm_res->desc[j].start + + oes->bcdma_rchan_data; + irq_res.desc[i].num = rm_res->desc[j].num; + + irq_res.desc[i + 1].start = rm_res->desc[j].start + + oes->bcdma_rchan_ring; + irq_res.desc[i + 1].num = rm_res->desc[j].num; + } } } @@ -4858,39 +4900,54 @@ static int pktdma_setup_resources(struct udma_dev *ud) if (IS_ERR(rm_res)) { /* all rflows are assigned exclusively to Linux */ bitmap_zero(ud->rflow_in_use, ud->rflow_cnt); + irq_res.sets = 1; } else { bitmap_fill(ud->rflow_in_use, ud->rflow_cnt); for (i = 0; i < rm_res->sets; i++) udma_mark_resource_ranges(ud, ud->rflow_in_use, &rm_res->desc[i], "rflow"); + irq_res.sets = rm_res->sets; } - irq_res.sets = rm_res->sets; /* tflow ranges */ rm_res = tisci_rm->rm_ranges[RM_RANGE_TFLOW]; if (IS_ERR(rm_res)) { /* all tflows are assigned exclusively to Linux */ bitmap_zero(ud->tflow_map, ud->tflow_cnt); + irq_res.sets++; } else { bitmap_fill(ud->tflow_map, ud->tflow_cnt); for (i = 0; i < rm_res->sets; i++) udma_mark_resource_ranges(ud, ud->tflow_map, &rm_res->desc[i], "tflow"); + irq_res.sets += rm_res->sets; } - irq_res.sets += rm_res->sets; irq_res.desc = kcalloc(irq_res.sets, sizeof(*irq_res.desc), GFP_KERNEL); + if (!irq_res.desc) + return -ENOMEM; rm_res = tisci_rm->rm_ranges[RM_RANGE_TFLOW]; - for (i = 0; i < rm_res->sets; i++) { - irq_res.desc[i].start = rm_res->desc[i].start + - oes->pktdma_tchan_flow; - irq_res.desc[i].num = rm_res->desc[i].num; + if (IS_ERR(rm_res)) { + irq_res.desc[0].start = oes->pktdma_tchan_flow; + irq_res.desc[0].num = ud->tflow_cnt; + i = 1; + } else { + for (i = 0; i < rm_res->sets; i++) { + irq_res.desc[i].start = rm_res->desc[i].start + + oes->pktdma_tchan_flow; + irq_res.desc[i].num = rm_res->desc[i].num; + } } rm_res = tisci_rm->rm_ranges[RM_RANGE_RFLOW]; - for (j = 0; j < rm_res->sets; j++, i++) { - irq_res.desc[i].start = rm_res->desc[j].start + - oes->pktdma_rchan_flow; - irq_res.desc[i].num = rm_res->desc[j].num; + if (IS_ERR(rm_res)) { + irq_res.desc[i].start = oes->pktdma_rchan_flow; + irq_res.desc[i].num = ud->rflow_cnt; + } else { + for (j = 0; j < rm_res->sets; j++, i++) { + irq_res.desc[i].start = rm_res->desc[j].start + + oes->pktdma_rchan_flow; + irq_res.desc[i].num = rm_res->desc[j].num; + } } ret = ti_sci_inta_msi_domain_alloc_irqs(ud->dev, &irq_res); kfree(irq_res.desc); -- cgit v1.2.3 From 8affd8a4b5ce356c8900cfb037674f3a4a11fbdb Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 8 Dec 2021 10:01:27 -0700 Subject: dmaengine: idxd: fix missed completion on abort path Ming reported that with the abort path of the descriptor submission, there can be a window where a completed descriptor can be missed to be completed by the irq completion thread: CPU A CPU B Submit (successful) Submit (fail) irq_process_work_list() // empty llist_abort_desc() // remove all descs from pending list irq_process_pending_llist() // empty exit idxd_wq_thread() with no processing Add opportunistic descriptor completion in the abort path in order to remove the missed completion. Fixes: 6b4b87f2c31a ("dmaengine: idxd: fix submission race window") Reported-by: Ming Li Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/163898288714.443911.16084982766671976640.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/submit.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c index de76fb4abac2..83452fbbb168 100644 --- a/drivers/dma/idxd/submit.c +++ b/drivers/dma/idxd/submit.c @@ -106,6 +106,7 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie, { struct idxd_desc *d, *t, *found = NULL; struct llist_node *head; + LIST_HEAD(flist); desc->completion->status = IDXD_COMP_DESC_ABORT; /* @@ -120,7 +121,11 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie, found = desc; continue; } - list_add_tail(&desc->list, &ie->work_list); + + if (d->completion->status) + list_add_tail(&d->list, &flist); + else + list_add_tail(&d->list, &ie->work_list); } } @@ -130,6 +135,17 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie, if (found) complete_desc(found, IDXD_COMPLETE_ABORT); + + /* + * complete_desc() will return desc to allocator and the desc can be + * acquired by a different process and the desc->list can be modified. + * Delete desc from list so the list trasversing does not get corrupted + * by the other process. + */ + list_for_each_entry_safe(d, t, &flist, list) { + list_del_init(&d->list); + complete_desc(d, IDXD_COMPLETE_NORMAL); + } } int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc) -- cgit v1.2.3 From 822c9f2b833c53fc67e8adf6f63ecc3ea24d502c Mon Sep 17 00:00:00 2001 From: Alyssa Ross Date: Thu, 25 Nov 2021 15:44:38 +0000 Subject: dmaengine: st_fdma: fix MODULE_ALIAS modprobe can't handle spaces in aliases. Fixes: 6b4cd727eaf1 ("dmaengine: st_fdma: Add STMicroelectronics FDMA engine driver support") Signed-off-by: Alyssa Ross Link: https://lore.kernel.org/r/20211125154441.2626214-1-hi@alyssa.is Signed-off-by: Vinod Koul --- drivers/dma/st_fdma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/dma/st_fdma.c b/drivers/dma/st_fdma.c index 962b6e05287b..d95c421877fb 100644 --- a/drivers/dma/st_fdma.c +++ b/drivers/dma/st_fdma.c @@ -874,4 +874,4 @@ MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("STMicroelectronics FDMA engine driver"); MODULE_AUTHOR("Ludovic.barre "); MODULE_AUTHOR("Peter Griffin "); -MODULE_ALIAS("platform: " DRIVER_NAME); +MODULE_ALIAS("platform:" DRIVER_NAME); -- cgit v1.2.3 From 5cf06065bd1f7b94fbb80e7eeb033899f77ab5ba Mon Sep 17 00:00:00 2001 From: Alejandro Concepcion-Rodriguez Date: Sun, 12 Dec 2021 16:06:02 +0000 Subject: drm: simpledrm: fix wrong unit with pixel clock Pixel clock has to be set in kHz. Signed-off-by: Alejandro Concepcion-Rodriguez Fixes: 11e8f5fd223b ("drm: Add simpledrm driver") Signed-off-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/6f8554ef-1305-0dda-821c-f7d2e5644a48@acoro.eu --- drivers/gpu/drm/tiny/simpledrm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/tiny/simpledrm.c b/drivers/gpu/drm/tiny/simpledrm.c index 481b48bde047..5a6e89825bc2 100644 --- a/drivers/gpu/drm/tiny/simpledrm.c +++ b/drivers/gpu/drm/tiny/simpledrm.c @@ -458,7 +458,7 @@ static struct drm_display_mode simpledrm_mode(unsigned int width, { struct drm_display_mode mode = { SIMPLEDRM_MODE(width, height) }; - mode.clock = 60 /* Hz */ * mode.hdisplay * mode.vdisplay; + mode.clock = mode.hdisplay * mode.vdisplay * 60 / 1000 /* kHz */; drm_mode_set_name(&mode); return mode; -- cgit v1.2.3 From c062f2a0b04d86c5b8c9d973bea43493eaca3d32 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Fri, 10 Dec 2021 17:42:47 +0100 Subject: net/sched: sch_ets: don't remove idle classes from the round-robin list Shuang reported that the following script: 1) tc qdisc add dev ddd0 handle 10: parent 1: ets bands 8 strict 4 priomap 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 2) mausezahn ddd0 -A 10.10.10.1 -B 10.10.10.2 -c 0 -a own -b 00:c1:a0:c1:a0:00 -t udp & 3) tc qdisc change dev ddd0 handle 10: ets bands 4 strict 2 quanta 2500 2500 priomap 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 crashes systematically when line 2) is commented: list_del corruption, ffff8e028404bd30->next is LIST_POISON1 (dead000000000100) ------------[ cut here ]------------ kernel BUG at lib/list_debug.c:47! invalid opcode: 0000 [#1] PREEMPT SMP NOPTI CPU: 0 PID: 954 Comm: tc Not tainted 5.16.0-rc4+ #478 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 RIP: 0010:__list_del_entry_valid.cold.1+0x12/0x47 Code: fe ff 0f 0b 48 89 c1 4c 89 c6 48 c7 c7 08 42 1b 87 e8 1d c5 fe ff 0f 0b 48 89 fe 48 89 c2 48 c7 c7 98 42 1b 87 e8 09 c5 fe ff <0f> 0b 48 c7 c7 48 43 1b 87 e8 fb c4 fe ff 0f 0b 48 89 f2 48 89 fe RSP: 0018:ffffae46807a3888 EFLAGS: 00010246 RAX: 000000000000004e RBX: 0000000000000007 RCX: 0000000000000202 RDX: 0000000000000000 RSI: ffffffff871ac536 RDI: 00000000ffffffff RBP: ffffae46807a3a10 R08: 0000000000000000 R09: c0000000ffff7fff R10: 0000000000000001 R11: ffffae46807a36a8 R12: ffff8e028404b800 R13: ffff8e028404bd30 R14: dead000000000100 R15: ffff8e02fafa2400 FS: 00007efdc92e4480(0000) GS:ffff8e02fb600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000682f48 CR3: 00000001058be000 CR4: 0000000000350ef0 Call Trace: ets_qdisc_change+0x58b/0xa70 [sch_ets] tc_modify_qdisc+0x323/0x880 rtnetlink_rcv_msg+0x169/0x4a0 netlink_rcv_skb+0x50/0x100 netlink_unicast+0x1a5/0x280 netlink_sendmsg+0x257/0x4d0 sock_sendmsg+0x5b/0x60 ____sys_sendmsg+0x1f2/0x260 ___sys_sendmsg+0x7c/0xc0 __sys_sendmsg+0x57/0xa0 do_syscall_64+0x3a/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7efdc8031338 Code: 89 02 48 c7 c0 ff ff ff ff eb b5 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 8d 05 25 43 2c 00 8b 00 85 c0 75 17 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 58 c3 0f 1f 80 00 00 00 00 41 54 41 89 d4 55 RSP: 002b:00007ffdf1ce9828 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000061b37a97 RCX: 00007efdc8031338 RDX: 0000000000000000 RSI: 00007ffdf1ce9890 RDI: 0000000000000003 RBP: 0000000000000000 R08: 0000000000000001 R09: 000000000078a940 R10: 000000000000000c R11: 0000000000000246 R12: 0000000000000001 R13: 0000000000688880 R14: 0000000000000000 R15: 0000000000000000 Modules linked in: sch_ets sch_tbf dummy rfkill iTCO_wdt iTCO_vendor_support intel_rapl_msr intel_rapl_common joydev pcspkr i2c_i801 virtio_balloon i2c_smbus lpc_ich ip_tables xfs libcrc32c crct10dif_pclmul crc32_pclmul crc32c_intel serio_raw ghash_clmulni_intel ahci libahci libata virtio_blk virtio_console virtio_net net_failover failover sunrpc dm_mirror dm_region_hash dm_log dm_mod [last unloaded: sch_ets] ---[ end trace f35878d1912655c2 ]--- RIP: 0010:__list_del_entry_valid.cold.1+0x12/0x47 Code: fe ff 0f 0b 48 89 c1 4c 89 c6 48 c7 c7 08 42 1b 87 e8 1d c5 fe ff 0f 0b 48 89 fe 48 89 c2 48 c7 c7 98 42 1b 87 e8 09 c5 fe ff <0f> 0b 48 c7 c7 48 43 1b 87 e8 fb c4 fe ff 0f 0b 48 89 f2 48 89 fe RSP: 0018:ffffae46807a3888 EFLAGS: 00010246 RAX: 000000000000004e RBX: 0000000000000007 RCX: 0000000000000202 RDX: 0000000000000000 RSI: ffffffff871ac536 RDI: 00000000ffffffff RBP: ffffae46807a3a10 R08: 0000000000000000 R09: c0000000ffff7fff R10: 0000000000000001 R11: ffffae46807a36a8 R12: ffff8e028404b800 R13: ffff8e028404bd30 R14: dead000000000100 R15: ffff8e02fafa2400 FS: 00007efdc92e4480(0000) GS:ffff8e02fb600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000682f48 CR3: 00000001058be000 CR4: 0000000000350ef0 Kernel panic - not syncing: Fatal exception in interrupt Kernel Offset: 0x4e00000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]--- we can remove 'q->classes[i].alist' only if DRR class 'i' was part of the active list. In the ETS scheduler DRR classes belong to that list only if the queue length is greater than zero: we need to test for non-zero value of 'q->classes[i].qdisc->q.qlen' before removing from the list, similarly to what has been done elsewhere in the ETS code. Fixes: de6d25924c2a ("net/sched: sch_ets: don't peek at classes beyond 'nbands'") Reported-by: Shuang Li Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- net/sched/sch_ets.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index e007fc75ef2f..d73393493553 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -666,9 +666,9 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, } } for (i = q->nbands; i < oldbands; i++) { - qdisc_tree_flush_backlog(q->classes[i].qdisc); - if (i >= q->nstrict) + if (i >= q->nstrict && q->classes[i].qdisc->q.qlen) list_del(&q->classes[i].alist); + qdisc_tree_flush_backlog(q->classes[i].qdisc); } q->nstrict = nstrict; memcpy(q->prio2band, priomap, sizeof(priomap)); -- cgit v1.2.3 From 865ed67ab955428b9aa771d8b4f1e4fb7fd08945 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Thu, 9 Dec 2021 12:04:56 +0000 Subject: firmware: arm_scpi: Fix string overflow in SCPI genpd driver Without the bound checks for scpi_pd->name, it could result in the buffer overflow when copying the SCPI device name from the corresponding device tree node as the name string is set at maximum size of 30. Let us fix it by using devm_kasprintf so that the string buffer is allocated dynamically. Fixes: 8bec4337ad40 ("firmware: scpi: add device power domain support using genpd") Reported-by: Pedro Batista Signed-off-by: Sudeep Holla Cc: stable@vger.kernel.org Cc: Cristian Marussi Link: https://lore.kernel.org/r/20211209120456.696879-1-sudeep.holla@arm.com' Signed-off-by: Arnd Bergmann --- drivers/firmware/scpi_pm_domain.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/firmware/scpi_pm_domain.c b/drivers/firmware/scpi_pm_domain.c index 51201600d789..800673910b51 100644 --- a/drivers/firmware/scpi_pm_domain.c +++ b/drivers/firmware/scpi_pm_domain.c @@ -16,7 +16,6 @@ struct scpi_pm_domain { struct generic_pm_domain genpd; struct scpi_ops *ops; u32 domain; - char name[30]; }; /* @@ -110,8 +109,13 @@ static int scpi_pm_domain_probe(struct platform_device *pdev) scpi_pd->domain = i; scpi_pd->ops = scpi_ops; - sprintf(scpi_pd->name, "%pOFn.%d", np, i); - scpi_pd->genpd.name = scpi_pd->name; + scpi_pd->genpd.name = devm_kasprintf(dev, GFP_KERNEL, + "%pOFn.%d", np, i); + if (!scpi_pd->genpd.name) { + dev_err(dev, "Failed to allocate genpd name:%pOFn.%d\n", + np, i); + continue; + } scpi_pd->genpd.power_off = scpi_pd_power_off; scpi_pd->genpd.power_on = scpi_pd_power_on; -- cgit v1.2.3 From 890d5b40908bfd1a79be018d2d297cf9df60f4ee Mon Sep 17 00:00:00 2001 From: Marian Postevca Date: Sat, 4 Dec 2021 23:49:12 +0200 Subject: usb: gadget: u_ether: fix race in setting MAC address in setup phase When listening for notifications through netlink of a new interface being registered, sporadically, it is possible for the MAC to be read as zero. The zero MAC address lasts a short period of time and then switches to a valid random MAC address. This causes problems for netd in Android, which assumes that the interface is malfunctioning and will not use it. In the good case we get this log: InterfaceController::getCfg() ifName usb0 hwAddr 92:a8:f0:73:79:5b ipv4Addr 0.0.0.0 flags 0x1002 In the error case we get these logs: InterfaceController::getCfg() ifName usb0 hwAddr 00:00:00:00:00:00 ipv4Addr 0.0.0.0 flags 0x1002 netd : interfaceGetCfg("usb0") netd : interfaceSetCfg() -> ServiceSpecificException (99, "[Cannot assign requested address] : ioctl() failed") The reason for the issue is the order in which the interface is setup, it is first registered through register_netdev() and after the MAC address is set. Fixed by first setting the MAC address of the net_device and after that calling register_netdev(). Fixes: bcd4a1c40bee885e ("usb: gadget: u_ether: construct with default values and add setters/getters") Cc: stable@vger.kernel.org Signed-off-by: Marian Postevca Link: https://lore.kernel.org/r/20211204214912.17627-1-posteuca@mutex.one Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/u_ether.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c index e0ad5aed6ac9..6f5d45ef2e39 100644 --- a/drivers/usb/gadget/function/u_ether.c +++ b/drivers/usb/gadget/function/u_ether.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "u_ether.h" @@ -863,19 +864,23 @@ int gether_register_netdev(struct net_device *net) { struct eth_dev *dev; struct usb_gadget *g; - struct sockaddr sa; int status; if (!net->dev.parent) return -EINVAL; dev = netdev_priv(net); g = dev->gadget; + + net->addr_assign_type = NET_ADDR_RANDOM; + eth_hw_addr_set(net, dev->dev_mac); + status = register_netdev(net); if (status < 0) { dev_dbg(&g->dev, "register_netdev failed, %d\n", status); return status; } else { INFO(dev, "HOST MAC %pM\n", dev->host_mac); + INFO(dev, "MAC %pM\n", dev->dev_mac); /* two kinds of host-initiated state changes: * - iff DATA transfer is active, carrier is "on" @@ -883,15 +888,6 @@ int gether_register_netdev(struct net_device *net) */ netif_carrier_off(net); } - sa.sa_family = net->type; - memcpy(sa.sa_data, dev->dev_mac, ETH_ALEN); - rtnl_lock(); - status = dev_set_mac_address(net, &sa, NULL); - rtnl_unlock(); - if (status) - pr_warn("cannot set self ethernet address: %d\n", status); - else - INFO(dev, "MAC %pM\n", dev->dev_mac); return status; } -- cgit v1.2.3 From ccc14c6cfd346e85c3ecb970975afd5132763437 Mon Sep 17 00:00:00 2001 From: Chunfeng Yun Date: Thu, 9 Dec 2021 10:54:22 +0800 Subject: usb: xhci-mtk: fix list_del warning when enable list debug There is warning of 'list_del corruption' when enable list debug (CONFIG_DEBUG_LIST=y), fix it by using list_del_init() Fixes: 4ce186665e7c ("usb: xhci-mtk: Do not use xhci's virt_dev in drop_endpoint") Cc: stable Signed-off-by: Chunfeng Yun Link: https://lore.kernel.org/r/20211209025422.17108-1-chunfeng.yun@mediatek.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-mtk-sch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-mtk-sch.c b/drivers/usb/host/xhci-mtk-sch.c index 1edef7527c11..edbfa82c6565 100644 --- a/drivers/usb/host/xhci-mtk-sch.c +++ b/drivers/usb/host/xhci-mtk-sch.c @@ -781,7 +781,7 @@ int xhci_mtk_check_bandwidth(struct usb_hcd *hcd, struct usb_device *udev) ret = xhci_check_bandwidth(hcd, udev); if (!ret) - INIT_LIST_HEAD(&mtk->bw_ep_chk_list); + list_del_init(&mtk->bw_ep_chk_list); return ret; } -- cgit v1.2.3 From 16f00d969afe60e233c1a91af7ac840df60d3536 Mon Sep 17 00:00:00 2001 From: Pawel Laszczak Date: Fri, 10 Dec 2021 12:29:45 +0100 Subject: usb: cdnsp: Fix incorrect calling of cdnsp_died function Patch restrict calling of cdnsp_died function during removing modules or software disconnect. This function was called because after transition controller to HALT state the driver starts handling the deferred interrupt. In this case such interrupt can be simple ignored. Fixes: 3d82904559f4 ("usb: cdnsp: cdns3 Add main part of Cadence USBSSP DRD Driver") cc: Reviewed-by: Peter Chen Signed-off-by: Pawel Laszczak Link: https://lore.kernel.org/r/20211210112945.660-1-pawell@gli-login.cadence.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/cdns3/cdnsp-ring.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c index 1b1438457fb0..e1ac6c398bd3 100644 --- a/drivers/usb/cdns3/cdnsp-ring.c +++ b/drivers/usb/cdns3/cdnsp-ring.c @@ -1523,7 +1523,14 @@ irqreturn_t cdnsp_thread_irq_handler(int irq, void *data) spin_lock_irqsave(&pdev->lock, flags); if (pdev->cdnsp_state & (CDNSP_STATE_HALTED | CDNSP_STATE_DYING)) { - cdnsp_died(pdev); + /* + * While removing or stopping driver there may still be deferred + * not handled interrupt which should not be treated as error. + * Driver should simply ignore it. + */ + if (pdev->gadget_driver) + cdnsp_died(pdev); + spin_unlock_irqrestore(&pdev->lock, flags); return IRQ_HANDLED; } -- cgit v1.2.3 From 50931ba27d1665c8b038cd1d16c5869301f32fd6 Mon Sep 17 00:00:00 2001 From: Pawel Laszczak Date: Mon, 13 Dec 2021 06:06:09 +0100 Subject: usb: cdnsp: Fix issue in cdnsp_log_ep trace event Patch fixes incorrect order of __entry->stream_id and __entry->state parameters in TP_printk macro. Fixes: 3d82904559f4 ("usb: cdnsp: cdns3 Add main part of Cadence USBSSP DRD Driver") cc: Reviewed-by: Peter Chen Signed-off-by: Pawel Laszczak Link: https://lore.kernel.org/r/20211213050609.22640-1-pawell@gli-login.cadence.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/cdns3/cdnsp-trace.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/usb/cdns3/cdnsp-trace.h b/drivers/usb/cdns3/cdnsp-trace.h index 6a2571c6aa9e..5983dfb99653 100644 --- a/drivers/usb/cdns3/cdnsp-trace.h +++ b/drivers/usb/cdns3/cdnsp-trace.h @@ -57,9 +57,9 @@ DECLARE_EVENT_CLASS(cdnsp_log_ep, __entry->first_prime_det = pep->stream_info.first_prime_det; __entry->drbls_count = pep->stream_info.drbls_count; ), - TP_printk("%s: SID: %08x ep state: %x stream: enabled: %d num %d " + TP_printk("%s: SID: %08x, ep state: %x, stream: enabled: %d num %d " "tds %d, first prime: %d drbls %d", - __get_str(name), __entry->state, __entry->stream_id, + __get_str(name), __entry->stream_id, __entry->state, __entry->enabled, __entry->num_streams, __entry->td_count, __entry->first_prime_det, __entry->drbls_count) ); -- cgit v1.2.3 From 99ea221f2e2f2743314e348b25c1e2574b467528 Mon Sep 17 00:00:00 2001 From: Pawel Laszczak Date: Tue, 7 Dec 2021 10:18:38 +0100 Subject: usb: cdnsp: Fix incorrect status for control request Patch fixes incorrect status for control request. Without this fix all usb_request objects were returned to upper drivers with usb_reqest->status field set to -EINPROGRESS. Fixes: 3d82904559f4 ("usb: cdnsp: cdns3 Add main part of Cadence USBSSP DRD Driver") cc: Reported-by: Ken (Jian) He Reviewed-by: Peter Chen Signed-off-by: Pawel Laszczak Link: https://lore.kernel.org/r/20211207091838.39572-1-pawell@gli-login.cadence.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/cdns3/cdnsp-ring.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c index e1ac6c398bd3..e45c3d6e1536 100644 --- a/drivers/usb/cdns3/cdnsp-ring.c +++ b/drivers/usb/cdns3/cdnsp-ring.c @@ -1029,6 +1029,8 @@ static void cdnsp_process_ctrl_td(struct cdnsp_device *pdev, return; } + *status = 0; + cdnsp_finish_td(pdev, td, event, pep, status); } -- cgit v1.2.3 From ab8eb798ddabddb2944401bf31ead9671cb97d95 Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Sat, 11 Dec 2021 14:01:53 +0000 Subject: net: bcmgenet: Fix NULL vs IS_ERR() checking The phy_attach() function does not return NULL. It returns error pointers. Signed-off-by: Miaoqian Lin Acked-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/genet/bcmmii.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 5f259641437a..c888ddee1fc4 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -589,9 +589,9 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv) * Internal or external PHY with MDIO access */ phydev = phy_attach(priv->dev, phy_name, pd->phy_interface); - if (!phydev) { + if (IS_ERR(phydev)) { dev_err(kdev, "failed to register PHY device\n"); - return -ENODEV; + return PTR_ERR(phydev); } } else { /* -- cgit v1.2.3 From a8d13611b4a7b1b20d17bf2b9a89a3efcabde56c Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Sat, 11 Dec 2021 14:30:31 -0500 Subject: selftests/net: toeplitz: fix udp option Tiny fix. Option -u ("use udp") does not take an argument. It can cause the next argument to silently be ignored. Fixes: 5ebfb4cc3048 ("selftests/net: toeplitz test") Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- tools/testing/selftests/net/toeplitz.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/toeplitz.c b/tools/testing/selftests/net/toeplitz.c index 710ac956bdb3..c5489341cfb8 100644 --- a/tools/testing/selftests/net/toeplitz.c +++ b/tools/testing/selftests/net/toeplitz.c @@ -498,7 +498,7 @@ static void parse_opts(int argc, char **argv) bool have_toeplitz = false; int index, c; - while ((c = getopt_long(argc, argv, "46C:d:i:k:r:stT:u:v", long_options, &index)) != -1) { + while ((c = getopt_long(argc, argv, "46C:d:i:k:r:stT:uv", long_options, &index)) != -1) { switch (c) { case '4': cfg_family = AF_INET; -- cgit v1.2.3 From 9d591fc028b6bddb38c6585874f331267cbdadae Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Sat, 11 Dec 2021 23:51:41 +0100 Subject: net: dsa: mv88e6xxx: Unforce speed & duplex in mac_link_down() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 64d47d50be7a ("net: dsa: mv88e6xxx: configure interface settings in mac_config") removed forcing of speed and duplex from mv88e6xxx_mac_config(), where the link is forced down, and left it only in mv88e6xxx_mac_link_up(), by which time link is unforced. It seems that (at least on 88E6190) when changing cmode to 2500base-x, if the link is not forced down, but the speed or duplex are still forced, the forcing of new settings for speed & duplex doesn't take in mv88e6xxx_mac_link_up(). Fix this by unforcing speed & duplex in mv88e6xxx_mac_link_down(). Fixes: 64d47d50be7a ("net: dsa: mv88e6xxx: configure interface settings in mac_config") Signed-off-by: Marek Behún Reviewed-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 14f87f6ac479..cd8462d1e27c 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -768,6 +768,10 @@ static void mv88e6xxx_mac_link_down(struct dsa_switch *ds, int port, if ((!mv88e6xxx_port_ppu_updates(chip, port) || mode == MLO_AN_FIXED) && ops->port_sync_link) err = ops->port_sync_link(chip, port, mode, false); + + if (!err && ops->port_set_speed_duplex) + err = ops->port_set_speed_duplex(chip, port, SPEED_UNFORCED, + DUPLEX_UNFORCED); mv88e6xxx_reg_unlock(chip); if (err) -- cgit v1.2.3 From 71da1aec215290e249d09c44c768df859f3a3bba Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Mon, 13 Dec 2021 16:36:00 +0800 Subject: selftest/net/forwarding: declare NETIFS p9 p10 The recent GRE selftests defined NUM_NETIFS=10. If the users copy forwarding.config.sample to forwarding.config directly, they will get error "Command line is not complete" when run the GRE tests, because create_netif_veth() failed with no interface name defined. Fix it by extending the NETIFS with p9 and p10. Fixes: 2800f2485417 ("selftests: forwarding: Test multipath hashing on inner IP pkts for GRE tunnel") Signed-off-by: Hangbin Liu Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- tools/testing/selftests/net/forwarding/forwarding.config.sample | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample index bf17e485684f..b0980a2efa31 100644 --- a/tools/testing/selftests/net/forwarding/forwarding.config.sample +++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample @@ -13,6 +13,8 @@ NETIFS[p5]=veth4 NETIFS[p6]=veth5 NETIFS[p7]=veth6 NETIFS[p8]=veth7 +NETIFS[p9]=veth8 +NETIFS[p10]=veth9 # Port that does not have a cable connected. NETIF_NO_CABLE=eth8 -- cgit v1.2.3 From be565ec71d1d59438bed0c7ed0a252a327e0b0ef Mon Sep 17 00:00:00 2001 From: Wang Qing Date: Mon, 13 Dec 2021 01:44:36 -0800 Subject: net: ethernet: ti: add missing of_node_put before return Fix following coccicheck warning: WARNING: Function "for_each_child_of_node" should have of_node_put() before return. Early exits from for_each_child_of_node should decrement the node reference counter. Signed-off-by: Wang Qing Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/am65-cpsw-nuss.c | 29 ++++++++++++++++++++--------- 1 file changed, 20 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index c092cb61416a..ffbbda8f4d41 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1844,13 +1844,14 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) if (ret < 0) { dev_err(dev, "%pOF error reading port_id %d\n", port_np, ret); - return ret; + goto of_node_put; } if (!port_id || port_id > common->port_num) { dev_err(dev, "%pOF has invalid port_id %u %s\n", port_np, port_id, port_np->name); - return -EINVAL; + ret = -EINVAL; + goto of_node_put; } port = am65_common_get_port(common, port_id); @@ -1866,8 +1867,10 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) (AM65_CPSW_NU_FRAM_PORT_OFFSET * (port_id - 1)); port->slave.mac_sl = cpsw_sl_get("am65", dev, port->port_base); - if (IS_ERR(port->slave.mac_sl)) - return PTR_ERR(port->slave.mac_sl); + if (IS_ERR(port->slave.mac_sl)) { + ret = PTR_ERR(port->slave.mac_sl); + goto of_node_put; + } port->disabled = !of_device_is_available(port_np); if (port->disabled) { @@ -1880,7 +1883,7 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) ret = PTR_ERR(port->slave.ifphy); dev_err(dev, "%pOF error retrieving port phy: %d\n", port_np, ret); - return ret; + goto of_node_put; } port->slave.mac_only = @@ -1889,10 +1892,12 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) /* get phy/link info */ if (of_phy_is_fixed_link(port_np)) { ret = of_phy_register_fixed_link(port_np); - if (ret) - return dev_err_probe(dev, ret, + if (ret) { + ret = dev_err_probe(dev, ret, "failed to register fixed-link phy %pOF\n", port_np); + goto of_node_put; + } port->slave.phy_node = of_node_get(port_np); } else { port->slave.phy_node = @@ -1902,14 +1907,15 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) if (!port->slave.phy_node) { dev_err(dev, "slave[%d] no phy found\n", port_id); - return -ENODEV; + ret = -ENODEV; + goto of_node_put; } ret = of_get_phy_mode(port_np, &port->slave.phy_if); if (ret) { dev_err(dev, "%pOF read phy-mode err %d\n", port_np, ret); - return ret; + goto of_node_put; } ret = of_get_mac_address(port_np, port->slave.mac_addr); @@ -1932,6 +1938,11 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) } return 0; + +of_node_put: + of_node_put(port_np); + of_node_put(node); + return ret; } static void am65_cpsw_pcpu_stats_free(void *data) -- cgit v1.2.3 From d33dae51645c0d837e587000f3131118fcd6bf5e Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Mon, 13 Dec 2021 11:05:13 +0000 Subject: net: phy: add a note about refcounting Recently, a patch has been submitted to "fix" the refcounting for a DT node in of_mdiobus_link_mdiodev(). This is not a leaked refcount. The refcount is passed to the new device. Sadly, coccicheck identifies this location as a leaked refcount, which means we're likely to keep getting patches to "fix" this. However, fixing this will cause breakage. Add a comment to state that the lack of of_node_put() here is intentional. Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/mdio_bus.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index c204067f1890..c198722e4871 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -460,6 +460,9 @@ static void of_mdiobus_link_mdiodev(struct mii_bus *bus, if (addr == mdiodev->addr) { device_set_node(dev, of_fwnode_handle(child)); + /* The refcount on "child" is passed to the mdio + * device. Do _not_ use of_node_put(child) here. + */ return; } } -- cgit v1.2.3 From 884d2b845477cd0a18302444dc20fe2d9a01743e Mon Sep 17 00:00:00 2001 From: David Wu Date: Mon, 13 Dec 2021 19:15:15 +0800 Subject: net: stmmac: Add GFP_DMA32 for rx buffers if no 64 capability Use page_pool_alloc_pages instead of page_pool_dev_alloc_pages, which can give the gfp parameter, in the case of not supporting 64-bit width, using 32-bit address memory can reduce a copy from swiotlb. Signed-off-by: David Wu Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index da8306f60730..8ded4be08b00 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1461,16 +1461,20 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p, { struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; struct stmmac_rx_buffer *buf = &rx_q->buf_pool[i]; + gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); + + if (priv->dma_cap.addr64 <= 32) + gfp |= GFP_DMA32; if (!buf->page) { - buf->page = page_pool_dev_alloc_pages(rx_q->page_pool); + buf->page = page_pool_alloc_pages(rx_q->page_pool, gfp); if (!buf->page) return -ENOMEM; buf->page_offset = stmmac_rx_offset(priv); } if (priv->sph && !buf->sec_page) { - buf->sec_page = page_pool_dev_alloc_pages(rx_q->page_pool); + buf->sec_page = page_pool_alloc_pages(rx_q->page_pool, gfp); if (!buf->sec_page) return -ENOMEM; @@ -4482,6 +4486,10 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; int dirty = stmmac_rx_dirty(priv, queue); unsigned int entry = rx_q->dirty_rx; + gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); + + if (priv->dma_cap.addr64 <= 32) + gfp |= GFP_DMA32; while (dirty-- > 0) { struct stmmac_rx_buffer *buf = &rx_q->buf_pool[entry]; @@ -4494,13 +4502,13 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) p = rx_q->dma_rx + entry; if (!buf->page) { - buf->page = page_pool_dev_alloc_pages(rx_q->page_pool); + buf->page = page_pool_alloc_pages(rx_q->page_pool, gfp); if (!buf->page) break; } if (priv->sph && !buf->sec_page) { - buf->sec_page = page_pool_dev_alloc_pages(rx_q->page_pool); + buf->sec_page = page_pool_alloc_pages(rx_q->page_pool, gfp); if (!buf->sec_page) break; -- cgit v1.2.3 From d800c65c2d4eccebb27ffb7808e842d5b533823c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 13 Dec 2021 09:04:01 -0700 Subject: io-wq: drop wqe lock before creating new worker We have two io-wq creation paths: - On queue enqueue - When a worker goes to sleep The latter invokes worker creation with the wqe->lock held, but that can run into problems if we end up exiting and need to cancel the queued work. syzbot caught this: ============================================ WARNING: possible recursive locking detected 5.16.0-rc4-syzkaller #0 Not tainted -------------------------------------------- iou-wrk-6468/6471 is trying to acquire lock: ffff88801aa98018 (&wqe->lock){+.+.}-{2:2}, at: io_worker_cancel_cb+0xb7/0x210 fs/io-wq.c:187 but task is already holding lock: ffff88801aa98018 (&wqe->lock){+.+.}-{2:2}, at: io_wq_worker_sleeping+0xb6/0x140 fs/io-wq.c:700 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&wqe->lock); lock(&wqe->lock); *** DEADLOCK *** May be due to missing lock nesting notation 1 lock held by iou-wrk-6468/6471: #0: ffff88801aa98018 (&wqe->lock){+.+.}-{2:2}, at: io_wq_worker_sleeping+0xb6/0x140 fs/io-wq.c:700 stack backtrace: CPU: 1 PID: 6471 Comm: iou-wrk-6468 Not tainted 5.16.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1dc/0x2d8 lib/dump_stack.c:106 print_deadlock_bug kernel/locking/lockdep.c:2956 [inline] check_deadlock kernel/locking/lockdep.c:2999 [inline] validate_chain+0x5984/0x8240 kernel/locking/lockdep.c:3788 __lock_acquire+0x1382/0x2b00 kernel/locking/lockdep.c:5027 lock_acquire+0x19f/0x4d0 kernel/locking/lockdep.c:5637 __raw_spin_lock include/linux/spinlock_api_smp.h:133 [inline] _raw_spin_lock+0x2a/0x40 kernel/locking/spinlock.c:154 io_worker_cancel_cb+0xb7/0x210 fs/io-wq.c:187 io_wq_cancel_tw_create fs/io-wq.c:1220 [inline] io_queue_worker_create+0x3cf/0x4c0 fs/io-wq.c:372 io_wq_worker_sleeping+0xbe/0x140 fs/io-wq.c:701 sched_submit_work kernel/sched/core.c:6295 [inline] schedule+0x67/0x1f0 kernel/sched/core.c:6323 schedule_timeout+0xac/0x300 kernel/time/timer.c:1857 wait_woken+0xca/0x1b0 kernel/sched/wait.c:460 unix_msg_wait_data net/unix/unix_bpf.c:32 [inline] unix_bpf_recvmsg+0x7f9/0xe20 net/unix/unix_bpf.c:77 unix_stream_recvmsg+0x214/0x2c0 net/unix/af_unix.c:2832 sock_recvmsg_nosec net/socket.c:944 [inline] sock_recvmsg net/socket.c:962 [inline] sock_read_iter+0x3a7/0x4d0 net/socket.c:1035 call_read_iter include/linux/fs.h:2156 [inline] io_iter_do_read fs/io_uring.c:3501 [inline] io_read fs/io_uring.c:3558 [inline] io_issue_sqe+0x144c/0x9590 fs/io_uring.c:6671 io_wq_submit_work+0x2d8/0x790 fs/io_uring.c:6836 io_worker_handle_work+0x808/0xdd0 fs/io-wq.c:574 io_wqe_worker+0x395/0x870 fs/io-wq.c:630 ret_from_fork+0x1f/0x30 We can safely drop the lock before doing work creation, making the two contexts the same in that regard. Reported-by: syzbot+b18b8be69df33a3918e9@syzkaller.appspotmail.com Fixes: 71a85387546e ("io-wq: check for wq exit after adding new worker task_work") Signed-off-by: Jens Axboe --- fs/io-wq.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/io-wq.c b/fs/io-wq.c index 8d2bb818a3bb..5c4f582d6549 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -395,7 +395,9 @@ static void io_wqe_dec_running(struct io_worker *worker) if (atomic_dec_and_test(&acct->nr_running) && io_acct_run_queue(acct)) { atomic_inc(&acct->nr_running); atomic_inc(&wqe->wq->worker_refs); + raw_spin_unlock(&wqe->lock); io_queue_worker_create(worker, acct, create_worker_cb); + raw_spin_lock(&wqe->lock); } } -- cgit v1.2.3 From bc2f39a6252ee40d9bfc2743d4437d420aec5f6e Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 10 Nov 2021 11:13:50 +0300 Subject: iavf: missing unlocks in iavf_watchdog_task() This code was re-organized and there some unlocks missing now. Fixes: 898ef1cb1cb2 ("iavf: Combine init and watchdog state machines") Signed-off-by: Dan Carpenter Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index cfdbf8c08d18..884a19c51543 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2046,6 +2046,7 @@ static void iavf_watchdog_task(struct work_struct *work) } adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; + mutex_unlock(&adapter->crit_lock); queue_delayed_work(iavf_wq, &adapter->watchdog_task, msecs_to_jiffies(10)); @@ -2076,9 +2077,8 @@ static void iavf_watchdog_task(struct work_struct *work) iavf_detect_recover_hung(&adapter->vsi); break; case __IAVF_REMOVE: - mutex_unlock(&adapter->crit_lock); - return; default: + mutex_unlock(&adapter->crit_lock); return; } -- cgit v1.2.3 From fe523d7c9a8332855376ad5eb1aa301091129ba4 Mon Sep 17 00:00:00 2001 From: Stefan Assmann Date: Wed, 1 Dec 2021 09:14:34 +0100 Subject: iavf: do not override the adapter state in the watchdog task (again) The watchdog task incorrectly changes the state to __IAVF_RESETTING, instead of letting the reset task take care of that. This was already resolved by commit 22c8fd71d3a5 ("iavf: do not override the adapter state in the watchdog task") but the problem was reintroduced by the recent code refactoring in commit 45eebd62999d ("iavf: Refactor iavf state machine tracking"). Fixes: 45eebd62999d ("iavf: Refactor iavf state machine tracking") Signed-off-by: Stefan Assmann Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf_main.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 884a19c51543..4e7c04047f91 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2085,7 +2085,6 @@ static void iavf_watchdog_task(struct work_struct *work) /* check for hw reset */ reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK; if (!reg_val) { - iavf_change_state(adapter, __IAVF_RESETTING); adapter->flags |= IAVF_FLAG_RESET_PENDING; adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; -- cgit v1.2.3 From e386dfc56f837da66d00a078e5314bc8382fab83 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 10 Dec 2021 14:00:15 -0800 Subject: fget: clarify and improve __fget_files() implementation Commit 054aa8d439b9 ("fget: check that the fd still exists after getting a ref to it") fixed a race with getting a reference to a file just as it was being closed. It was a fairly minimal patch, and I didn't think re-checking the file pointer lookup would be a measurable overhead, since it was all right there and cached. But I was wrong, as pointed out by the kernel test robot. The 'poll2' case of the will-it-scale.per_thread_ops benchmark regressed quite noticeably. Admittedly it seems to be a very artificial test: doing "poll()" system calls on regular files in a very tight loop in multiple threads. That means that basically all the time is spent just looking up file descriptors without ever doing anything useful with them (not that doing 'poll()' on a regular file is useful to begin with). And as a result it shows the extra "re-check fd" cost as a sore thumb. Happily, the regression is fixable by just writing the code to loook up the fd to be better and clearer. There's still a cost to verify the file pointer, but now it's basically in the noise even for that benchmark that does nothing else - and the code is more understandable and has better comments too. [ Side note: this patch is also a classic case of one that looks very messy with the default greedy Myers diff - it's much more legible with either the patience of histogram diff algorithm ] Link: https://lore.kernel.org/lkml/20211210053743.GA36420@xsang-OptiPlex-9020/ Link: https://lore.kernel.org/lkml/20211213083154.GA20853@linux.intel.com/ Reported-by: kernel test robot Tested-by: Carel Si Cc: Jann Horn Cc: Miklos Szeredi Signed-off-by: Linus Torvalds --- fs/file.c | 72 +++++++++++++++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 56 insertions(+), 16 deletions(-) diff --git a/fs/file.c b/fs/file.c index ad4a8bf3cf10..97d212a9b814 100644 --- a/fs/file.c +++ b/fs/file.c @@ -841,28 +841,68 @@ void do_close_on_exec(struct files_struct *files) spin_unlock(&files->file_lock); } -static struct file *__fget_files(struct files_struct *files, unsigned int fd, - fmode_t mask, unsigned int refs) +static inline struct file *__fget_files_rcu(struct files_struct *files, + unsigned int fd, fmode_t mask, unsigned int refs) { - struct file *file; + for (;;) { + struct file *file; + struct fdtable *fdt = rcu_dereference_raw(files->fdt); + struct file __rcu **fdentry; - rcu_read_lock(); -loop: - file = files_lookup_fd_rcu(files, fd); - if (file) { - /* File object ref couldn't be taken. - * dup2() atomicity guarantee is the reason - * we loop to catch the new file (or NULL pointer) + if (unlikely(fd >= fdt->max_fds)) + return NULL; + + fdentry = fdt->fd + array_index_nospec(fd, fdt->max_fds); + file = rcu_dereference_raw(*fdentry); + if (unlikely(!file)) + return NULL; + + if (unlikely(file->f_mode & mask)) + return NULL; + + /* + * Ok, we have a file pointer. However, because we do + * this all locklessly under RCU, we may be racing with + * that file being closed. + * + * Such a race can take two forms: + * + * (a) the file ref already went down to zero, + * and get_file_rcu_many() fails. Just try + * again: */ - if (file->f_mode & mask) - file = NULL; - else if (!get_file_rcu_many(file, refs)) - goto loop; - else if (files_lookup_fd_raw(files, fd) != file) { + if (unlikely(!get_file_rcu_many(file, refs))) + continue; + + /* + * (b) the file table entry has changed under us. + * Note that we don't need to re-check the 'fdt->fd' + * pointer having changed, because it always goes + * hand-in-hand with 'fdt'. + * + * If so, we need to put our refs and try again. + */ + if (unlikely(rcu_dereference_raw(files->fdt) != fdt) || + unlikely(rcu_dereference_raw(*fdentry) != file)) { fput_many(file, refs); - goto loop; + continue; } + + /* + * Ok, we have a ref to the file, and checked that it + * still exists. + */ + return file; } +} + +static struct file *__fget_files(struct files_struct *files, unsigned int fd, + fmode_t mask, unsigned int refs) +{ + struct file *file; + + rcu_read_lock(); + file = __fget_files_rcu(files, fd, mask, refs); rcu_read_unlock(); return file; -- cgit v1.2.3 From aa50faff4416c869b52dff68a937c84d29e12f4b Mon Sep 17 00:00:00 2001 From: Sergio Paracuellos Date: Wed, 1 Dec 2021 22:34:02 +0100 Subject: PCI: mt7621: Convert driver into 'bool' The driver is not ready yet to be compiled as a module since it depends on some symbols not exported on MIPS. We have the following current problems: Building mips:allmodconfig ... failed -------------- Error log: ERROR: modpost: missing MODULE_LICENSE() in drivers/pci/controller/pcie-mt7621.o ERROR: modpost: "mips_cm_unlock_other" [drivers/pci/controller/pcie-mt7621.ko] undefined! ERROR: modpost: "mips_cpc_base" [drivers/pci/controller/pcie-mt7621.ko] undefined! ERROR: modpost: "mips_cm_lock_other" [drivers/pci/controller/pcie-mt7621.ko] undefined! ERROR: modpost: "mips_cm_is64" [drivers/pci/controller/pcie-mt7621.ko] undefined! ERROR: modpost: "mips_gcr_base" [drivers/pci/controller/pcie-mt7621.ko] undefined! Temporarily move from 'tristate' to 'bool' until a better solution is ready. Also RALINK is redundant because SOC_MT7621 already depends on it. Hence, simplify condition. Fixes: 2bdd5238e756 ("PCI: mt7621: Add MediaTek MT7621 PCIe host controller driver"). Signed-off-by: Sergio Paracuellos Reviewed-and-Tested-by: Guenter Roeck Signed-off-by: Linus Torvalds --- drivers/pci/controller/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig index 93b141110537..7fc5135ffbbf 100644 --- a/drivers/pci/controller/Kconfig +++ b/drivers/pci/controller/Kconfig @@ -332,8 +332,8 @@ config PCIE_APPLE If unsure, say Y if you have an Apple Silicon system. config PCIE_MT7621 - tristate "MediaTek MT7621 PCIe Controller" - depends on (RALINK && SOC_MT7621) || (MIPS && COMPILE_TEST) + bool "MediaTek MT7621 PCIe Controller" + depends on SOC_MT7621 || (MIPS && COMPILE_TEST) select PHY_MT7621_PCI default SOC_MT7621 help -- cgit v1.2.3 From b0cdc5dbcf2ba0d99785da5aabf1b17943805b8a Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Sat, 11 Dec 2021 17:11:12 +0100 Subject: mptcp: never allow the PM to close a listener subflow Currently, when deleting an endpoint the netlink PM treverses all the local MPTCP sockets, regardless of their status. If an MPTCP listener socket is bound to the IP matching the delete endpoint, the listener TCP socket will be closed. That is unexpected, the PM should only affect data subflows. Additionally, syzbot was able to trigger a NULL ptr dereference due to the above: general protection fault, probably for non-canonical address 0xdffffc0000000003: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000018-0x000000000000001f] CPU: 1 PID: 6550 Comm: syz-executor122 Not tainted 5.16.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__lock_acquire+0xd7d/0x54a0 kernel/locking/lockdep.c:4897 Code: 0f 0e 41 be 01 00 00 00 0f 86 c8 00 00 00 89 05 69 cc 0f 0e e9 bd 00 00 00 48 b8 00 00 00 00 00 fc ff df 48 89 da 48 c1 ea 03 <80> 3c 02 00 0f 85 f3 2f 00 00 48 81 3b 20 75 17 8f 0f 84 52 f3 ff RSP: 0018:ffffc90001f2f818 EFLAGS: 00010016 RAX: dffffc0000000000 RBX: 0000000000000018 RCX: 0000000000000000 RDX: 0000000000000003 RSI: 0000000000000000 RDI: 0000000000000001 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000001 R10: 0000000000000000 R11: 000000000000000a R12: 0000000000000000 R13: ffff88801b98d700 R14: 0000000000000000 R15: 0000000000000001 FS: 00007f177cd3d700(0000) GS:ffff8880b9d00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f177cd1b268 CR3: 000000001dd55000 CR4: 0000000000350ee0 Call Trace: lock_acquire kernel/locking/lockdep.c:5637 [inline] lock_acquire+0x1ab/0x510 kernel/locking/lockdep.c:5602 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline] _raw_spin_lock_irqsave+0x39/0x50 kernel/locking/spinlock.c:162 finish_wait+0xc0/0x270 kernel/sched/wait.c:400 inet_csk_wait_for_connect net/ipv4/inet_connection_sock.c:464 [inline] inet_csk_accept+0x7de/0x9d0 net/ipv4/inet_connection_sock.c:497 mptcp_accept+0xe5/0x500 net/mptcp/protocol.c:2865 inet_accept+0xe4/0x7b0 net/ipv4/af_inet.c:739 mptcp_stream_accept+0x2e7/0x10e0 net/mptcp/protocol.c:3345 do_accept+0x382/0x510 net/socket.c:1773 __sys_accept4_file+0x7e/0xe0 net/socket.c:1816 __sys_accept4+0xb0/0x100 net/socket.c:1846 __do_sys_accept net/socket.c:1864 [inline] __se_sys_accept net/socket.c:1861 [inline] __x64_sys_accept+0x71/0xb0 net/socket.c:1861 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f177cd8b8e9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 b1 14 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f177cd3d308 EFLAGS: 00000246 ORIG_RAX: 000000000000002b RAX: ffffffffffffffda RBX: 00007f177ce13408 RCX: 00007f177cd8b8e9 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000003 RBP: 00007f177ce13400 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f177ce1340c R13: 00007f177cde1004 R14: 6d705f706374706d R15: 0000000000022000 Fix the issue explicitly skipping MPTCP socket in TCP_LISTEN status. Reported-and-tested-by: syzbot+e4d843bb96a9431e6331@syzkaller.appspotmail.com Reviewed-by: Mat Martineau Fixes: 740d798e8767 ("mptcp: remove id 0 address") Signed-off-by: Paolo Abeni Link: https://lore.kernel.org/r/ebc7594cdd420d241fb2172ddb8542ba64717657.1639238695.git.pabeni@redhat.com Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 7b96be1e9f14..f523051f5aef 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -700,6 +700,9 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, msk_owned_by_me(msk); + if (sk->sk_state == TCP_LISTEN) + return; + if (!rm_list->nr) return; -- cgit v1.2.3 From 2fe24343922e0428fb68674a4fae099171141bc7 Mon Sep 17 00:00:00 2001 From: John Garry Date: Mon, 13 Dec 2021 18:10:48 +0800 Subject: scsi: pm8001: Fix phys_to_virt() usage on dma_addr_t The driver supports a "direct" mode of operation, where the SMP req frame is directly copied into the command payload (and vice-versa for the SMP resp). To get at the SMP req frame data in the scatterlist the driver uses phys_to_virt() on the DMA mapped memory dma_addr_t . This is broken, and subsequently crashes as follows when an IOMMU is enabled: Unable to handle kernel paging request at virtual address ffff0000fcebfb00 ... pc : pm80xx_chip_smp_req+0x2d0/0x3d0 lr : pm80xx_chip_smp_req+0xac/0x3d0 pm80xx_chip_smp_req+0x2d0/0x3d0 pm8001_task_exec.constprop.0+0x368/0x520 pm8001_queue_command+0x1c/0x30 smp_execute_task_sg+0xdc/0x204 sas_discover_expander.part.0+0xac/0x6cc sas_discover_root_expander+0x8c/0x150 sas_discover_domain+0x3ac/0x6a0 process_one_work+0x1d0/0x354 worker_thread+0x13c/0x470 kthread+0x17c/0x190 ret_from_fork+0x10/0x20 Code: 371806e1 910006d6 6b16033f 54000249 (38766b05) ---[ end trace b91d59aaee98ea2d ]--- note: kworker/u192:0[7] exited with preempt_count 1 Instead use kmap_atomic(). -- Difference to v1: - use kmap_atomic() in both locations Difference to v2: - add whitespace around arithmetic (Damien) Link: https://lore.kernel.org/r/1639390248-213603-1-git-send-email-john.garry@huawei.com Reviewed-by: Damien Le Moal Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- drivers/scsi/pm8001/pm80xx_hwi.c | 38 +++++++++++++++++++++----------------- 1 file changed, 21 insertions(+), 17 deletions(-) diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c index b9f6d83ff380..2101fc5761c3 100644 --- a/drivers/scsi/pm8001/pm80xx_hwi.c +++ b/drivers/scsi/pm8001/pm80xx_hwi.c @@ -3053,7 +3053,6 @@ mpi_smp_completion(struct pm8001_hba_info *pm8001_ha, void *piomb) struct smp_completion_resp *psmpPayload; struct task_status_struct *ts; struct pm8001_device *pm8001_dev; - char *pdma_respaddr = NULL; psmpPayload = (struct smp_completion_resp *)(piomb + 4); status = le32_to_cpu(psmpPayload->status); @@ -3080,19 +3079,23 @@ mpi_smp_completion(struct pm8001_hba_info *pm8001_ha, void *piomb) if (pm8001_dev) atomic_dec(&pm8001_dev->running_req); if (pm8001_ha->smp_exp_mode == SMP_DIRECT) { + struct scatterlist *sg_resp = &t->smp_task.smp_resp; + u8 *payload; + void *to; + pm8001_dbg(pm8001_ha, IO, "DIRECT RESPONSE Length:%d\n", param); - pdma_respaddr = (char *)(phys_to_virt(cpu_to_le64 - ((u64)sg_dma_address - (&t->smp_task.smp_resp)))); + to = kmap_atomic(sg_page(sg_resp)); + payload = to + sg_resp->offset; for (i = 0; i < param; i++) { - *(pdma_respaddr+i) = psmpPayload->_r_a[i]; + *(payload + i) = psmpPayload->_r_a[i]; pm8001_dbg(pm8001_ha, IO, "SMP Byte%d DMA data 0x%x psmp 0x%x\n", - i, *(pdma_respaddr + i), + i, *(payload + i), psmpPayload->_r_a[i]); } + kunmap_atomic(to); } break; case IO_ABORTED: @@ -4236,14 +4239,14 @@ static int pm80xx_chip_smp_req(struct pm8001_hba_info *pm8001_ha, struct sas_task *task = ccb->task; struct domain_device *dev = task->dev; struct pm8001_device *pm8001_dev = dev->lldd_dev; - struct scatterlist *sg_req, *sg_resp; + struct scatterlist *sg_req, *sg_resp, *smp_req; u32 req_len, resp_len; struct smp_req smp_cmd; u32 opc; struct inbound_queue_table *circularQ; - char *preq_dma_addr = NULL; - __le64 tmp_addr; u32 i, length; + u8 *payload; + u8 *to; memset(&smp_cmd, 0, sizeof(smp_cmd)); /* @@ -4280,8 +4283,9 @@ static int pm80xx_chip_smp_req(struct pm8001_hba_info *pm8001_ha, pm8001_ha->smp_exp_mode = SMP_INDIRECT; - tmp_addr = cpu_to_le64((u64)sg_dma_address(&task->smp_task.smp_req)); - preq_dma_addr = (char *)phys_to_virt(tmp_addr); + smp_req = &task->smp_task.smp_req; + to = kmap_atomic(sg_page(smp_req)); + payload = to + smp_req->offset; /* INDIRECT MODE command settings. Use DMA */ if (pm8001_ha->smp_exp_mode == SMP_INDIRECT) { @@ -4289,7 +4293,7 @@ static int pm80xx_chip_smp_req(struct pm8001_hba_info *pm8001_ha, /* for SPCv indirect mode. Place the top 4 bytes of * SMP Request header here. */ for (i = 0; i < 4; i++) - smp_cmd.smp_req16[i] = *(preq_dma_addr + i); + smp_cmd.smp_req16[i] = *(payload + i); /* exclude top 4 bytes for SMP req header */ smp_cmd.long_smp_req.long_req_addr = cpu_to_le64((u64)sg_dma_address @@ -4320,20 +4324,20 @@ static int pm80xx_chip_smp_req(struct pm8001_hba_info *pm8001_ha, pm8001_dbg(pm8001_ha, IO, "SMP REQUEST DIRECT MODE\n"); for (i = 0; i < length; i++) if (i < 16) { - smp_cmd.smp_req16[i] = *(preq_dma_addr+i); + smp_cmd.smp_req16[i] = *(payload + i); pm8001_dbg(pm8001_ha, IO, "Byte[%d]:%x (DMA data:%x)\n", i, smp_cmd.smp_req16[i], - *(preq_dma_addr)); + *(payload)); } else { - smp_cmd.smp_req[i] = *(preq_dma_addr+i); + smp_cmd.smp_req[i] = *(payload + i); pm8001_dbg(pm8001_ha, IO, "Byte[%d]:%x (DMA data:%x)\n", i, smp_cmd.smp_req[i], - *(preq_dma_addr)); + *(payload)); } } - + kunmap_atomic(to); build_smp_cmd(pm8001_dev->device_id, smp_cmd.tag, &smp_cmd, pm8001_ha->smp_exp_mode, length); rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &smp_cmd, -- cgit v1.2.3 From fea3fdf975dd9f3e5248afaab8fe023db313f005 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Tue, 14 Dec 2021 09:41:26 +0800 Subject: drm/ast: potential dereference of null pointer The return value of kzalloc() needs to be checked. To avoid use of null pointer '&ast_state->base' in case of the failure of alloc. Fixes: f0adbc382b8b ("drm/ast: Allocate initial CRTC state of the correct size") Signed-off-by: Jiasheng Jiang Signed-off-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20211214014126.2211535-1-jiasheng@iscas.ac.cn --- drivers/gpu/drm/ast/ast_mode.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index 1e30eaeb0e1b..d5c98f79d58d 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -1121,7 +1121,10 @@ static void ast_crtc_reset(struct drm_crtc *crtc) if (crtc->state) crtc->funcs->atomic_destroy_state(crtc, crtc->state); - __drm_atomic_helper_crtc_reset(crtc, &ast_state->base); + if (ast_state) + __drm_atomic_helper_crtc_reset(crtc, &ast_state->base); + else + __drm_atomic_helper_crtc_reset(crtc, NULL); } static struct drm_crtc_state * -- cgit v1.2.3 From 83b67041f3eaf33f98a075249aa7f4c7617c2f85 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 26 Nov 2021 10:43:48 +0100 Subject: USB: serial: cp210x: fix CP2105 GPIO registration When generalising GPIO support and adding support for CP2102N, the GPIO registration for some CP2105 devices accidentally broke. Specifically, when all the pins of a port are in "modem" mode, and thus unavailable for GPIO use, the GPIO chip would now be registered without having initialised the number of GPIO lines. This would in turn be rejected by gpiolib and some errors messages would be printed (but importantly probe would still succeed). Fix this by initialising the number of GPIO lines before registering the GPIO chip. Note that as for the other device types, and as when all CP2105 pins are muxed for LED function, the GPIO chip is registered also when no pins are available for GPIO use. Reported-by: Maarten Brock Link: https://lore.kernel.org/r/5eb560c81d2ea1a2b4602a92d9f48a89@vanmierlo.com Fixes: c8acfe0aadbe ("USB: serial: cp210x: implement GPIO support for CP2102N") Cc: stable@vger.kernel.org # 4.19 Cc: Karoly Pados Link: https://lore.kernel.org/r/20211126094348.31698-1-johan@kernel.org Reviewed-by: Greg Kroah-Hartman Tested-by: Maarten Brock Signed-off-by: Johan Hovold --- drivers/usb/serial/cp210x.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 7705328034ca..8a60c0d56863 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -1635,6 +1635,8 @@ static int cp2105_gpioconf_init(struct usb_serial *serial) /* 2 banks of GPIO - One for the pins taken from each serial port */ if (intf_num == 0) { + priv->gc.ngpio = 2; + if (mode.eci == CP210X_PIN_MODE_MODEM) { /* mark all GPIOs of this interface as reserved */ priv->gpio_altfunc = 0xff; @@ -1645,8 +1647,9 @@ static int cp2105_gpioconf_init(struct usb_serial *serial) priv->gpio_pushpull = (u8)((le16_to_cpu(config.gpio_mode) & CP210X_ECI_GPIO_MODE_MASK) >> CP210X_ECI_GPIO_MODE_OFFSET); - priv->gc.ngpio = 2; } else if (intf_num == 1) { + priv->gc.ngpio = 3; + if (mode.sci == CP210X_PIN_MODE_MODEM) { /* mark all GPIOs of this interface as reserved */ priv->gpio_altfunc = 0xff; @@ -1657,7 +1660,6 @@ static int cp2105_gpioconf_init(struct usb_serial *serial) priv->gpio_pushpull = (u8)((le16_to_cpu(config.gpio_mode) & CP210X_SCI_GPIO_MODE_MASK) >> CP210X_SCI_GPIO_MODE_OFFSET); - priv->gc.ngpio = 3; } else { return -ENODEV; } -- cgit v1.2.3 From 2b503c8598d1b232e7fc7526bce9326d92331541 Mon Sep 17 00:00:00 2001 From: Daniele Palmas Date: Fri, 10 Dec 2021 11:07:14 +0100 Subject: USB: serial: option: add Telit FN990 compositions Add the following Telit FN990 compositions: 0x1070: tty, adb, rmnet, tty, tty, tty, tty 0x1071: tty, adb, mbim, tty, tty, tty, tty 0x1072: rndis, tty, adb, tty, tty, tty, tty 0x1073: tty, adb, ecm, tty, tty, tty, tty Signed-off-by: Daniele Palmas Link: https://lore.kernel.org/r/20211210100714.22587-1-dnlplm@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 546fce4617a8..42420bfc983c 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1219,6 +1219,14 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1063, 0xff), /* Telit LN920 (ECM) */ .driver_info = NCTRL(0) | RSVD(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1070, 0xff), /* Telit FN990 (rmnet) */ + .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1071, 0xff), /* Telit FN990 (MBIM) */ + .driver_info = NCTRL(0) | RSVD(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1072, 0xff), /* Telit FN990 (RNDIS) */ + .driver_info = NCTRL(2) | RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1073, 0xff), /* Telit FN990 (ECM) */ + .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), -- cgit v1.2.3 From 53b3495273282aa844c4613d19c3b30558c70c84 Mon Sep 17 00:00:00 2001 From: Harshit Mogalapalli Date: Thu, 9 Dec 2021 20:41:24 -0800 Subject: drm/i915/display: Fix an unsigned subtraction which can never be negative. smatch warning: drivers/gpu/drm/i915/display/intel_dmc.c:601 parse_dmc_fw() warn: unsigned 'fw->size - offset' is never less than zero Firmware size is size_t and offset is u32. So the subtraction is unsigned which can never be less than zero. Fixes: 3d5928a168a9 ("drm/i915/xelpd: Pipe A DMC plugging") Signed-off-by: Harshit Mogalapalli Reviewed-by: Lucas De Marchi Signed-off-by: Lucas De Marchi Link: https://patchwork.freedesktop.org/patch/msgid/20211210044129.12422-1-harshit.m.mogalapalli@oracle.com (cherry picked from commit 87bb2a410dcfb617b88e4695edf4beb6336dc314) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/display/intel_dmc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c index 2dc9d632969d..aef69522f0be 100644 --- a/drivers/gpu/drm/i915/display/intel_dmc.c +++ b/drivers/gpu/drm/i915/display/intel_dmc.c @@ -596,7 +596,7 @@ static void parse_dmc_fw(struct drm_i915_private *dev_priv, continue; offset = readcount + dmc->dmc_info[id].dmc_offset * 4; - if (fw->size - offset < 0) { + if (offset > fw->size) { drm_err(&dev_priv->drm, "Reading beyond the fw_size\n"); continue; } -- cgit v1.2.3 From 1fe98f5690c4219d419ea9cc190f94b3401cf324 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Thu, 2 Dec 2021 13:45:33 +0100 Subject: mac80211: send ADDBA requests using the tid/queue of the aggregation session Sending them out on a different queue can cause a race condition where a number of packets in the queue may be discarded by the receiver, because the ADDBA request is sent too early. This affects any driver with software A-MPDU setup which does not allocate packet seqno in hardware on tx, regardless of whether iTXQ is used or not. The only driver I've seen that explicitly deals with this issue internally is mwl8k. Cc: stable@vger.kernel.org Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20211202124533.80388-1-nbd@nbd.name Signed-off-by: Johannes Berg --- net/mac80211/agg-tx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index c1558dd2d244..58761ca7da3c 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -106,7 +106,7 @@ static void ieee80211_send_addba_request(struct ieee80211_sub_if_data *sdata, mgmt->u.action.u.addba_req.start_seq_num = cpu_to_le16(start_seq_num << 4); - ieee80211_tx_skb(sdata, skb); + ieee80211_tx_skb_tid(sdata, skb, tid); } void ieee80211_send_bar(struct ieee80211_vif *vif, u8 *ra, u16 tid, u16 ssn) -- cgit v1.2.3 From 37d33114240ede043c42463a6347f68ed72d6904 Mon Sep 17 00:00:00 2001 From: Finn Behrens Date: Wed, 1 Dec 2021 13:49:18 +0100 Subject: nl80211: remove reload flag from regulatory_request This removes the previously unused reload flag, which was introduced in 1eda919126b4. The request is handled as NL80211_REGDOM_SET_BY_CORE, which is parsed unconditionally. Reported-by: kernel test robot Reported-by: Nathan Chancellor Fixes: 1eda919126b4 ("nl80211: reset regdom when reloading regdb") Link: https://lore.kernel.org/all/YaZuKYM5bfWe2Urn@archlinux-ax161/ Signed-off-by: Finn Behrens Reviewed-by: Nathan Chancellor Link: https://lore.kernel.org/r/YadvTolO8rQcNCd/@gimli.kloenk.dev Signed-off-by: Johannes Berg --- include/net/regulatory.h | 1 - net/wireless/reg.c | 6 ++---- 2 files changed, 2 insertions(+), 5 deletions(-) diff --git a/include/net/regulatory.h b/include/net/regulatory.h index 0cf9335431e0..47f06f6f5a67 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -83,7 +83,6 @@ struct regulatory_request { enum nl80211_dfs_regions dfs_region; bool intersect; bool processed; - bool reload; enum environment_cap country_ie_env; struct list_head list; }; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 61f1bf1bc4a7..8148a3b5f607 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1134,9 +1134,8 @@ int reg_reload_regdb(void) request->wiphy_idx = WIPHY_IDX_INVALID; request->alpha2[0] = current_regdomain->alpha2[0]; request->alpha2[1] = current_regdomain->alpha2[1]; - request->initiator = NL80211_USER_REG_HINT_USER; + request->initiator = NL80211_REGDOM_SET_BY_CORE; request->user_reg_hint_type = NL80211_USER_REG_HINT_USER; - request->reload = true; reg_process_hint(request); @@ -2712,8 +2711,7 @@ reg_process_hint_user(struct regulatory_request *user_request) treatment = __reg_process_hint_user(user_request); if (treatment == REG_REQ_IGNORE || - (treatment == REG_REQ_ALREADY_SET && - !user_request->reload)) + treatment == REG_REQ_ALREADY_SET) return REG_REQ_IGNORE; user_request->intersect = treatment == REG_REQ_INTERSECT; -- cgit v1.2.3 From 06c41bda0ea14aa7fba932a9613c4ee239682cf0 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 2 Dec 2021 15:26:25 +0200 Subject: mac80211: agg-tx: don't schedule_and_wake_txq() under sta->lock When we call ieee80211_agg_start_txq(), that will in turn call schedule_and_wake_txq(). Called from ieee80211_stop_tx_ba_cb() this is done under sta->lock, which leads to certain circular lock dependencies, as reported by Chris Murphy: https://lore.kernel.org/r/CAJCQCtSXJ5qA4bqSPY=oLRMbv-irihVvP7A2uGutEbXQVkoNaw@mail.gmail.com In general, ieee80211_agg_start_txq() is usually not called with sta->lock held, only in this one place. But it's always called with sta->ampdu_mlme.mtx held, and that's therefore clearly sufficient. Change ieee80211_stop_tx_ba_cb() to also call it without the sta->lock held, by factoring it out of ieee80211_remove_tid_tx() (which is only called in this one place). This breaks the locking chain and makes it less likely that we'll have similar locking chain problems in the future. Fixes: ba8c3d6f16a1 ("mac80211: add an intermediate software queue implementation") Reported-by: Chris Murphy Signed-off-by: Johannes Berg Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20211202152554.f519884c8784.I555fef8e67d93fff3d9a304886c4a9f8b322e591@changeid Signed-off-by: Johannes Berg --- net/mac80211/agg-tx.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 58761ca7da3c..74a878f213d3 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -9,7 +9,7 @@ * Copyright 2007, Michael Wu * Copyright 2007-2010, Intel Corporation * Copyright(c) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2020 Intel Corporation + * Copyright (C) 2018 - 2021 Intel Corporation */ #include @@ -213,6 +213,8 @@ ieee80211_agg_start_txq(struct sta_info *sta, int tid, bool enable) struct ieee80211_txq *txq = sta->sta.txq[tid]; struct txq_info *txqi; + lockdep_assert_held(&sta->ampdu_mlme.mtx); + if (!txq) return; @@ -290,7 +292,6 @@ static void ieee80211_remove_tid_tx(struct sta_info *sta, int tid) ieee80211_assign_tid_tx(sta, tid, NULL); ieee80211_agg_splice_finish(sta->sdata, tid); - ieee80211_agg_start_txq(sta, tid, false); kfree_rcu(tid_tx, rcu_head); } @@ -889,6 +890,7 @@ void ieee80211_stop_tx_ba_cb(struct sta_info *sta, int tid, { struct ieee80211_sub_if_data *sdata = sta->sdata; bool send_delba = false; + bool start_txq = false; ht_dbg(sdata, "Stopping Tx BA session for %pM tid %d\n", sta->sta.addr, tid); @@ -906,10 +908,14 @@ void ieee80211_stop_tx_ba_cb(struct sta_info *sta, int tid, send_delba = true; ieee80211_remove_tid_tx(sta, tid); + start_txq = true; unlock_sta: spin_unlock_bh(&sta->lock); + if (start_txq) + ieee80211_agg_start_txq(sta, tid, false); + if (send_delba) ieee80211_send_delba(sdata, sta->sta.addr, tid, WLAN_BACK_INITIATOR, WLAN_REASON_QSTA_NOT_USE); -- cgit v1.2.3 From e08ebd6d7b90ae81f21425ca39136f5b2272580f Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Thu, 2 Dec 2021 15:28:54 +0200 Subject: cfg80211: Acquire wiphy mutex on regulatory work The function cfg80211_reg_can_beacon_relax() expects wiphy mutex to be held when it is being called. However, when reg_leave_invalid_chans() is called the mutex is not held. Fix it by acquiring the lock before calling the function. Fixes: a05829a7222e ("cfg80211: avoid holding the RTNL when calling the driver") Signed-off-by: Ilan Peer Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20211202152831.527686cda037.I40ad9372a47cbad53b4aae7b5a6ccc0dc3fddf8b@changeid Signed-off-by: Johannes Berg --- net/wireless/reg.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 8148a3b5f607..f8f01a3e020b 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2359,6 +2359,7 @@ static bool reg_wdev_chan_valid(struct wiphy *wiphy, struct wireless_dev *wdev) struct cfg80211_chan_def chandef = {}; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); enum nl80211_iftype iftype; + bool ret; wdev_lock(wdev); iftype = wdev->iftype; @@ -2408,7 +2409,11 @@ static bool reg_wdev_chan_valid(struct wiphy *wiphy, struct wireless_dev *wdev) case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: case NL80211_IFTYPE_ADHOC: - return cfg80211_reg_can_beacon_relax(wiphy, &chandef, iftype); + wiphy_lock(wiphy); + ret = cfg80211_reg_can_beacon_relax(wiphy, &chandef, iftype); + wiphy_unlock(wiphy); + + return ret; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: return cfg80211_chandef_usable(wiphy, &chandef, -- cgit v1.2.3 From 768c0b19b50665e337c96858aa2b7928d6dcf756 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sat, 11 Dec 2021 20:10:24 +0100 Subject: mac80211: validate extended element ID is present Before attempting to parse an extended element, verify that the extended element ID is present. Fixes: 41cbb0f5a295 ("mac80211: add support for HE") Reported-by: syzbot+59bdff68edce82e393b6@syzkaller.appspotmail.com Link: https://lore.kernel.org/r/20211211201023.f30a1b128c07.I5cacc176da94ba316877c6e10fe3ceec8b4dbd7d@changeid Cc: stable@vger.kernel.org Signed-off-by: Johannes Berg --- net/mac80211/util.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 43df2f0c5db9..6c2934854d3c 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -943,7 +943,12 @@ static void ieee80211_parse_extension_element(u32 *crc, struct ieee802_11_elems *elems) { const void *data = elem->data + 1; - u8 len = elem->datalen - 1; + u8 len; + + if (!elem->datalen) + return; + + len = elem->datalen - 1; switch (elem->data[0]) { case WLAN_EID_EXT_HE_MU_EDCA: -- cgit v1.2.3 From 511ab0c1dfb260a6b17b8771109e8d63474473a7 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 29 Nov 2021 15:32:46 +0200 Subject: mac80211: fix lookup when adding AddBA extension element We should be doing the HE capabilities lookup based on the full interface type so if P2P doesn't have HE but client has it doesn't get confused. Fix that. Fixes: 2ab45876756f ("mac80211: add support for the ADDBA extension element") Signed-off-by: Johannes Berg Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20211129152938.010fc1d61137.If3a468145f29d670cb00a693bed559d8290ba693@changeid Signed-off-by: Johannes Berg --- net/mac80211/agg-rx.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 470ff0ce3dc7..7d2925bb966e 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -9,7 +9,7 @@ * Copyright 2007, Michael Wu * Copyright 2007-2010, Intel Corporation * Copyright(c) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ /** @@ -191,7 +191,8 @@ static void ieee80211_add_addbaext(struct ieee80211_sub_if_data *sdata, sband = ieee80211_get_sband(sdata); if (!sband) return; - he_cap = ieee80211_get_he_iftype_cap(sband, sdata->vif.type); + he_cap = ieee80211_get_he_iftype_cap(sband, + ieee80211_vif_type_p2p(&sdata->vif)); if (!he_cap) return; -- cgit v1.2.3 From f22d981386d12d1513bd2720fb4387b469124d4b Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Mon, 29 Nov 2021 15:32:45 +0200 Subject: mac80211: Fix the size used for building probe request Instead of using the hard-coded value of '100' use the correct scan IEs length as calculated during HW registration to mac80211. Signed-off-by: Ilan Peer Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20211129152938.0a82d6891719.I8ded1f2e0bccb9e71222c945666bcd86537f2e35@changeid Signed-off-by: Johannes Berg --- net/mac80211/util.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 6c2934854d3c..fe2903b84ceb 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2068,7 +2068,7 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, chandef.chan = chan; skb = ieee80211_probereq_get(&local->hw, src, ssid, ssid_len, - 100 + ie_len); + local->scan_ies_len + ie_len); if (!skb) return NULL; -- cgit v1.2.3 From 4dde3c3627b52ca515a34f6f4de3898224aa1dd3 Mon Sep 17 00:00:00 2001 From: Mordechay Goodstein Date: Mon, 29 Nov 2021 15:32:42 +0200 Subject: mac80211: update channel context before station state Currently channel context is updated only after station got an update about new assoc state, this results in station using the old channel context. Fix this by moving the update channel context before updating station, enabling the driver to immediately use the updated channel context in the new assoc state. Signed-off-by: Mordechay Goodstein Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20211129152938.1c80c17ffd8a.I94ae31378b363c1182cfdca46c4b7e7165cff984@changeid Signed-off-by: Johannes Berg --- net/mac80211/sta_info.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 840ad1a860fa..537535a88990 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -667,6 +667,15 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) list_add_tail_rcu(&sta->list, &local->sta_list); + /* update channel context before notifying the driver about state + * change, this enables driver using the updated channel context right away. + */ + if (sta->sta_state >= IEEE80211_STA_ASSOC) { + ieee80211_recalc_min_chandef(sta->sdata); + if (!sta->sta.support_p2p_ps) + ieee80211_recalc_p2p_go_ps_allowed(sta->sdata); + } + /* notify driver */ err = sta_info_insert_drv_state(local, sdata, sta); if (err) @@ -674,12 +683,6 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) set_sta_flag(sta, WLAN_STA_INSERTED); - if (sta->sta_state >= IEEE80211_STA_ASSOC) { - ieee80211_recalc_min_chandef(sta->sdata); - if (!sta->sta.support_p2p_ps) - ieee80211_recalc_p2p_go_ps_allowed(sta->sdata); - } - /* accept BA sessions now */ clear_sta_flag(sta, WLAN_STA_BLOCK_BA); -- cgit v1.2.3 From db7205af049d230e7e0abf61c1e74c1aab40f390 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 29 Nov 2021 15:32:39 +0200 Subject: mac80211: mark TX-during-stop for TX in in_reconfig Mark TXQs as having seen transmit while they were stopped if we bail out of drv_wake_tx_queue() due to reconfig, so that the queue wake after this will make them catch up. This is particularly necessary for when TXQs are used for management packets since those TXQs won't see a lot of traffic that'd make them catch up later. Cc: stable@vger.kernel.org Fixes: 4856bfd23098 ("mac80211: do not call driver wake_tx_queue op during reconfig") Signed-off-by: Johannes Berg Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20211129152938.4573a221c0e1.I0d1d5daea3089be3fc0dccc92991b0f8c5677f0c@changeid Signed-off-by: Johannes Berg --- net/mac80211/driver-ops.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index cd3731cbf6c6..c336267f4599 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1219,8 +1219,11 @@ static inline void drv_wake_tx_queue(struct ieee80211_local *local, { struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->txq.vif); - if (local->in_reconfig) + /* In reconfig don't transmit now, but mark for waking later */ + if (local->in_reconfig) { + set_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txq->flags); return; + } if (!check_sdata_in_driver(sdata)) return; -- cgit v1.2.3 From 13dee10b30c058ee2c58c5da00339cc0d4201aa6 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 29 Nov 2021 15:32:40 +0200 Subject: mac80211: do drv_reconfig_complete() before restarting all When we reconfigure, the driver might do some things to complete the reconfiguration. It's strange and could be broken in some cases because we restart other works (e.g. remain-on-channel and TX) before this happens, yet only start queues later. Change this to do the reconfig complete when reconfiguration is actually complete, not when we've already started doing other things again. For iwlwifi, this should fix a race where the reconfig can race with TX, for ath10k and ath11k that also use this it won't make a difference because they just start queues there, and mac80211 also stopped the queues and will restart them later as before. Signed-off-by: Johannes Berg Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20211129152938.cab99f22fe19.Iefe494687f15fd85f77c1b989d1149c8efdfdc36@changeid Signed-off-by: Johannes Berg --- net/mac80211/util.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/net/mac80211/util.c b/net/mac80211/util.c index fe2903b84ceb..0e4e1956bcea 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2651,6 +2651,13 @@ int ieee80211_reconfig(struct ieee80211_local *local) mutex_unlock(&local->sta_mtx); } + /* + * If this is for hw restart things are still running. + * We may want to change that later, however. + */ + if (local->open_count && (!suspended || reconfig_due_to_wowlan)) + drv_reconfig_complete(local, IEEE80211_RECONFIG_TYPE_RESTART); + if (local->in_reconfig) { local->in_reconfig = false; barrier(); @@ -2669,13 +2676,6 @@ int ieee80211_reconfig(struct ieee80211_local *local) IEEE80211_QUEUE_STOP_REASON_SUSPEND, false); - /* - * If this is for hw restart things are still running. - * We may want to change that later, however. - */ - if (local->open_count && (!suspended || reconfig_due_to_wowlan)) - drv_reconfig_complete(local, IEEE80211_RECONFIG_TYPE_RESTART); - if (!suspended) return 0; -- cgit v1.2.3 From 8734b41b3efe0fc6082c1937b0e88556c396dc96 Mon Sep 17 00:00:00 2001 From: Russell Currey Date: Tue, 23 Nov 2021 18:15:20 +1000 Subject: powerpc/module_64: Fix livepatching for RO modules Livepatching a loaded module involves applying relocations through apply_relocate_add(), which attempts to write to read-only memory when CONFIG_STRICT_MODULE_RWX=y. Work around this by performing these writes through the text poke area by using patch_instruction(). R_PPC_REL24 is the only relocation type generated by the kpatch-build userspace tool or klp-convert kernel tree that I observed applying a relocation to a post-init module. A more comprehensive solution is planned, but using patch_instruction() for R_PPC_REL24 on should serve as a sufficient fix. This does have a performance impact, I observed ~15% overhead in module_load() on POWER8 bare metal with checksum verification off. Fixes: c35717c71e98 ("powerpc: Set ARCH_HAS_STRICT_MODULE_RWX") Cc: stable@vger.kernel.org # v5.14+ Reported-by: Joe Lawrence Signed-off-by: Russell Currey Tested-by: Joe Lawrence [mpe: Check return codes from patch_instruction()] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20211214121248.777249-1-mpe@ellerman.id.au --- arch/powerpc/kernel/module_64.c | 42 +++++++++++++++++++++++++++++++++-------- 1 file changed, 34 insertions(+), 8 deletions(-) diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 6baa676e7cb6..5d77d3f5fbb5 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -422,11 +422,17 @@ static inline int create_stub(const Elf64_Shdr *sechdrs, const char *name) { long reladdr; + func_desc_t desc; + int i; if (is_mprofile_ftrace_call(name)) return create_ftrace_stub(entry, addr, me); - memcpy(entry->jump, ppc64_stub_insns, sizeof(ppc64_stub_insns)); + for (i = 0; i < sizeof(ppc64_stub_insns) / sizeof(u32); i++) { + if (patch_instruction(&entry->jump[i], + ppc_inst(ppc64_stub_insns[i]))) + return 0; + } /* Stub uses address relative to r2. */ reladdr = (unsigned long)entry - my_r2(sechdrs, me); @@ -437,10 +443,24 @@ static inline int create_stub(const Elf64_Shdr *sechdrs, } pr_debug("Stub %p get data from reladdr %li\n", entry, reladdr); - entry->jump[0] |= PPC_HA(reladdr); - entry->jump[1] |= PPC_LO(reladdr); - entry->funcdata = func_desc(addr); - entry->magic = STUB_MAGIC; + if (patch_instruction(&entry->jump[0], + ppc_inst(entry->jump[0] | PPC_HA(reladdr)))) + return 0; + + if (patch_instruction(&entry->jump[1], + ppc_inst(entry->jump[1] | PPC_LO(reladdr)))) + return 0; + + // func_desc_t is 8 bytes if ABIv2, else 16 bytes + desc = func_desc(addr); + for (i = 0; i < sizeof(func_desc_t) / sizeof(u32); i++) { + if (patch_instruction(((u32 *)&entry->funcdata) + i, + ppc_inst(((u32 *)(&desc))[i]))) + return 0; + } + + if (patch_instruction(&entry->magic, ppc_inst(STUB_MAGIC))) + return 0; return 1; } @@ -495,8 +515,11 @@ static int restore_r2(const char *name, u32 *instruction, struct module *me) me->name, *instruction, instruction); return 0; } + /* ld r2,R2_STACK_OFFSET(r1) */ - *instruction = PPC_INST_LD_TOC; + if (patch_instruction(instruction, ppc_inst(PPC_INST_LD_TOC))) + return 0; + return 1; } @@ -636,9 +659,12 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, } /* Only replace bits 2 through 26 */ - *(uint32_t *)location - = (*(uint32_t *)location & ~0x03fffffc) + value = (*(uint32_t *)location & ~0x03fffffc) | (value & 0x03fffffc); + + if (patch_instruction((u32 *)location, ppc_inst(value))) + return -EFAULT; + break; case R_PPC64_REL64: -- cgit v1.2.3 From 83dbf898a2d45289be875deb580e93050ba67529 Mon Sep 17 00:00:00 2001 From: Stefan Roese Date: Tue, 14 Dec 2021 12:49:32 +0100 Subject: PCI/MSI: Mask MSI-X vectors only on success MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Masking all unused MSI-X entries is done to ensure that a crash kernel starts from a clean slate, which correponds to the reset state of the device as defined in the PCI-E specificion 3.0 and later: Vector Control for MSI-X Table Entries -------------------------------------- "00: Mask bit: When this bit is set, the function is prohibited from sending a message using this MSI-X Table entry. ... This bit’s state after reset is 1 (entry is masked)." A Marvell NVME device fails to deliver MSI interrupts after trying to enable MSI-X interrupts due to that masking. It seems to take the MSI-X mask bits into account even when MSI-X is disabled. While not specification compliant, this can be cured by moving the masking into the success path, so that the MSI-X table entries stay in device reset state when the MSI-X setup fails. [ tglx: Move it into the success path, add comment and amend changelog ] Fixes: aa8092c1d1f1 ("PCI/MSI: Mask all unused MSI-X entries") Signed-off-by: Stefan Roese Signed-off-by: Thomas Gleixner Cc: linux-pci@vger.kernel.org Cc: Bjorn Helgaas Cc: Michal Simek Cc: Marek Vasut Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20211210161025.3287927-1-sr@denx.de --- drivers/pci/msi.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 48e3f4e47b29..6748cf9d7d90 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -722,9 +722,6 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, goto out_disable; } - /* Ensure that all table entries are masked. */ - msix_mask_all(base, tsize); - ret = msix_setup_entries(dev, base, entries, nvec, affd); if (ret) goto out_disable; @@ -751,6 +748,16 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, /* Set MSI-X enabled bits and unmask the function */ pci_intx_for_msi(dev, 0); dev->msix_enabled = 1; + + /* + * Ensure that all table entries are masked to prevent + * stale entries from firing in a crash kernel. + * + * Done late to deal with a broken Marvell NVME device + * which takes the MSI-X mask bits into account even + * when MSI-X is disabled, which prevents MSI delivery. + */ + msix_mask_all(base, tsize); pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0); pcibios_free_irq(dev); -- cgit v1.2.3 From 94185adbfad56815c2c8401e16d81bdb74a79201 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 14 Dec 2021 12:42:14 +0100 Subject: PCI/MSI: Clear PCI_MSIX_FLAGS_MASKALL on error PCI_MSIX_FLAGS_MASKALL is set in the MSI-X control register at MSI-X interrupt setup time. It's cleared on success, but the error handling path only clears the PCI_MSIX_FLAGS_ENABLE bit. That's incorrect as the reset state of the PCI_MSIX_FLAGS_MASKALL bit is zero. That can be observed via lspci: Capabilities: [b0] MSI-X: Enable- Count=67 Masked+ Clear the bit in the error path to restore the reset state. Fixes: 438553958ba1 ("PCI/MSI: Enable and mask MSI-X early") Reported-by: Stefan Roese Signed-off-by: Thomas Gleixner Tested-by: Stefan Roese Cc: linux-pci@vger.kernel.org Cc: Bjorn Helgaas Cc: Michal Simek Cc: Marek Vasut Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/87tufevoqx.ffs@tglx --- drivers/pci/msi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 6748cf9d7d90..d84cf30bb279 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -784,7 +784,7 @@ out_free: free_msi_irqs(dev); out_disable: - pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0); + pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE, 0); return ret; } -- cgit v1.2.3 From aeb7c75cb77478fdbf821628e9c95c4baa9adc63 Mon Sep 17 00:00:00 2001 From: Ong Boon Leong Date: Sat, 11 Dec 2021 22:51:34 +0800 Subject: net: stmmac: fix tc flower deletion for VLAN priority Rx steering To replicate the issue:- 1) Add 1 flower filter for VLAN Priority based frame steering:- $ IFDEVNAME=eth0 $ tc qdisc add dev $IFDEVNAME ingress $ tc qdisc add dev $IFDEVNAME root mqprio num_tc 8 \ map 0 1 2 3 4 5 6 7 0 0 0 0 0 0 0 0 \ queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 hw 0 $ tc filter add dev $IFDEVNAME parent ffff: protocol 802.1Q \ flower vlan_prio 0 hw_tc 0 2) Get the 'pref' id $ tc filter show dev $IFDEVNAME ingress 3) Delete a specific tc flower record (say pref 49151) $ tc filter del dev $IFDEVNAME parent ffff: pref 49151 From dmesg, we will observe kernel NULL pointer ooops [ 197.170464] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 197.171367] #PF: supervisor read access in kernel mode [ 197.171367] #PF: error_code(0x0000) - not-present page [ 197.171367] PGD 0 P4D 0 [ 197.171367] Oops: 0000 [#1] PREEMPT SMP NOPTI [ 197.171367] RIP: 0010:tc_setup_cls+0x20b/0x4a0 [stmmac] [ 197.171367] Call Trace: [ 197.171367] [ 197.171367] ? __stmmac_disable_all_queues+0xa8/0xe0 [stmmac] [ 197.171367] stmmac_setup_tc_block_cb+0x70/0x110 [stmmac] [ 197.171367] tc_setup_cb_destroy+0xb3/0x180 [ 197.171367] fl_hw_destroy_filter+0x94/0xc0 [cls_flower] The above issue is due to previous incorrect implementation of tc_del_vlan_flow(), shown below, that uses flow_cls_offload_flow_rule() to get struct flow_rule *rule which is no longer valid for tc filter delete operation. struct flow_rule *rule = flow_cls_offload_flow_rule(cls); struct flow_dissector *dissector = rule->match.dissector; So, to ensure tc_del_vlan_flow() deletes the right VLAN cls record for earlier configured RX queue (configured by hw_tc) in tc_add_vlan_flow(), this patch introduces stmmac_rfs_entry as driver-side flow_cls_offload record for 'RX frame steering' tc flower, currently used for VLAN priority. The implementation has taken consideration for future extension to include other type RX frame steering such as EtherType based. v2: - Clean up overly extensive backtrace and rewrite git message to better explain the kernel NULL pointer issue. Fixes: 0e039f5cf86c ("net: stmmac: add RX frame steering based on VLAN priority in tc flower") Tested-by: Kurt Kanzenbach Signed-off-by: Ong Boon Leong Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac.h | 17 +++++ drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c | 86 +++++++++++++++++++++---- 2 files changed, 90 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 5f129733aabd..873b9e3e5da2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -172,6 +172,19 @@ struct stmmac_flow_entry { int is_l4; }; +/* Rx Frame Steering */ +enum stmmac_rfs_type { + STMMAC_RFS_T_VLAN, + STMMAC_RFS_T_MAX, +}; + +struct stmmac_rfs_entry { + unsigned long cookie; + int in_use; + int type; + int tc; +}; + struct stmmac_priv { /* Frequently used values are kept adjacent for cache effect */ u32 tx_coal_frames[MTL_MAX_TX_QUEUES]; @@ -289,6 +302,10 @@ struct stmmac_priv { struct stmmac_tc_entry *tc_entries; unsigned int flow_entries_max; struct stmmac_flow_entry *flow_entries; + unsigned int rfs_entries_max[STMMAC_RFS_T_MAX]; + unsigned int rfs_entries_cnt[STMMAC_RFS_T_MAX]; + unsigned int rfs_entries_total; + struct stmmac_rfs_entry *rfs_entries; /* Pulse Per Second output */ struct stmmac_pps_cfg pps[STMMAC_PPS_MAX]; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 1c4ea0b1b845..d0a2b289f460 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -232,11 +232,33 @@ static int tc_setup_cls_u32(struct stmmac_priv *priv, } } +static int tc_rfs_init(struct stmmac_priv *priv) +{ + int i; + + priv->rfs_entries_max[STMMAC_RFS_T_VLAN] = 8; + + for (i = 0; i < STMMAC_RFS_T_MAX; i++) + priv->rfs_entries_total += priv->rfs_entries_max[i]; + + priv->rfs_entries = devm_kcalloc(priv->device, + priv->rfs_entries_total, + sizeof(*priv->rfs_entries), + GFP_KERNEL); + if (!priv->rfs_entries) + return -ENOMEM; + + dev_info(priv->device, "Enabled RFS Flow TC (entries=%d)\n", + priv->rfs_entries_total); + + return 0; +} + static int tc_init(struct stmmac_priv *priv) { struct dma_features *dma_cap = &priv->dma_cap; unsigned int count; - int i; + int ret, i; if (dma_cap->l3l4fnum) { priv->flow_entries_max = dma_cap->l3l4fnum; @@ -250,10 +272,14 @@ static int tc_init(struct stmmac_priv *priv) for (i = 0; i < priv->flow_entries_max; i++) priv->flow_entries[i].idx = i; - dev_info(priv->device, "Enabled Flow TC (entries=%d)\n", + dev_info(priv->device, "Enabled L3L4 Flow TC (entries=%d)\n", priv->flow_entries_max); } + ret = tc_rfs_init(priv); + if (ret) + return -ENOMEM; + if (!priv->plat->fpe_cfg) { priv->plat->fpe_cfg = devm_kzalloc(priv->device, sizeof(*priv->plat->fpe_cfg), @@ -607,16 +633,45 @@ static int tc_del_flow(struct stmmac_priv *priv, return ret; } +static struct stmmac_rfs_entry *tc_find_rfs(struct stmmac_priv *priv, + struct flow_cls_offload *cls, + bool get_free) +{ + int i; + + for (i = 0; i < priv->rfs_entries_total; i++) { + struct stmmac_rfs_entry *entry = &priv->rfs_entries[i]; + + if (entry->cookie == cls->cookie) + return entry; + if (get_free && entry->in_use == false) + return entry; + } + + return NULL; +} + #define VLAN_PRIO_FULL_MASK (0x07) static int tc_add_vlan_flow(struct stmmac_priv *priv, struct flow_cls_offload *cls) { + struct stmmac_rfs_entry *entry = tc_find_rfs(priv, cls, false); struct flow_rule *rule = flow_cls_offload_flow_rule(cls); struct flow_dissector *dissector = rule->match.dissector; int tc = tc_classid_to_hwtc(priv->dev, cls->classid); struct flow_match_vlan match; + if (!entry) { + entry = tc_find_rfs(priv, cls, true); + if (!entry) + return -ENOENT; + } + + if (priv->rfs_entries_cnt[STMMAC_RFS_T_VLAN] >= + priv->rfs_entries_max[STMMAC_RFS_T_VLAN]) + return -ENOENT; + /* Nothing to do here */ if (!dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_VLAN)) return -EINVAL; @@ -638,6 +693,12 @@ static int tc_add_vlan_flow(struct stmmac_priv *priv, prio = BIT(match.key->vlan_priority); stmmac_rx_queue_prio(priv, priv->hw, prio, tc); + + entry->in_use = true; + entry->cookie = cls->cookie; + entry->tc = tc; + entry->type = STMMAC_RFS_T_VLAN; + priv->rfs_entries_cnt[STMMAC_RFS_T_VLAN]++; } return 0; @@ -646,20 +707,19 @@ static int tc_add_vlan_flow(struct stmmac_priv *priv, static int tc_del_vlan_flow(struct stmmac_priv *priv, struct flow_cls_offload *cls) { - struct flow_rule *rule = flow_cls_offload_flow_rule(cls); - struct flow_dissector *dissector = rule->match.dissector; - int tc = tc_classid_to_hwtc(priv->dev, cls->classid); + struct stmmac_rfs_entry *entry = tc_find_rfs(priv, cls, false); - /* Nothing to do here */ - if (!dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_VLAN)) - return -EINVAL; + if (!entry || !entry->in_use || entry->type != STMMAC_RFS_T_VLAN) + return -ENOENT; - if (tc < 0) { - netdev_err(priv->dev, "Invalid traffic class\n"); - return -EINVAL; - } + stmmac_rx_queue_prio(priv, priv->hw, 0, entry->tc); + + entry->in_use = false; + entry->cookie = 0; + entry->tc = 0; + entry->type = 0; - stmmac_rx_queue_prio(priv, priv->hw, 0, tc); + priv->rfs_entries_cnt[STMMAC_RFS_T_VLAN]--; return 0; } -- cgit v1.2.3 From 166b6a46b78bf8b9559a6620c3032f9fe492e082 Mon Sep 17 00:00:00 2001 From: Baowen Zheng Date: Mon, 13 Dec 2021 15:46:04 +0100 Subject: flow_offload: return EOPNOTSUPP for the unsupported mpls action type We need to return EOPNOTSUPP for the unsupported mpls action type when setup the flow action. In the original implement, we will return 0 for the unsupported mpls action type, actually we do not setup it and the following actions to the flow action entry. Fixes: 9838b20a7fb2 ("net: sched: take rtnl lock in tc_setup_flow_action()") Signed-off-by: Baowen Zheng Signed-off-by: Simon Horman Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- net/sched/cls_api.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 2ef8f5a6205a..e54f0a42270c 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3687,6 +3687,7 @@ int tc_setup_flow_action(struct flow_action *flow_action, entry->mpls_mangle.ttl = tcf_mpls_ttl(act); break; default: + err = -EOPNOTSUPP; goto err_out_locked; } } else if (is_tcf_skbedit_ptype(act)) { -- cgit v1.2.3 From 5f9562ebe710c307adc5f666bf1a2162ee7977c0 Mon Sep 17 00:00:00 2001 From: Hangyu Hua Date: Tue, 14 Dec 2021 18:46:59 +0800 Subject: rds: memory leak in __rds_conn_create() __rds_conn_create() did not release conn->c_path when loop_trans != 0 and trans->t_prefer_loopback != 0 and is_outgoing == 0. Fixes: aced3ce57cd3 ("RDS tcp loopback connection can hang") Signed-off-by: Hangyu Hua Reviewed-by: Sharath Srinivasan Signed-off-by: David S. Miller --- net/rds/connection.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/rds/connection.c b/net/rds/connection.c index a3bc4b54d491..b4cc699c5fad 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -253,6 +253,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, * should end up here, but if it * does, reset/destroy the connection. */ + kfree(conn->c_path); kmem_cache_free(rds_conn_slab, conn); conn = ERR_PTR(-EOPNOTSUPP); goto out; -- cgit v1.2.3 From b442f2ea84624873d538e4c5986d7c0d40883a47 Mon Sep 17 00:00:00 2001 From: Danielle Ratson Date: Tue, 14 Dec 2021 12:21:36 +0200 Subject: mlxsw: spectrum_router: Consolidate MAC profiles when possible Currently, when setting a router interface (RIF) MAC address while the MAC profile is not shared with other RIFs, the profile is edited so that the new MAC address is assigned to it. This does not take into account a situation in which the new MAC address already matches an existing MAC profile. In that situation, two MAC profiles will be occupied even though they hold MAC addresses from the same profile. In order to prevent that, add a check to ensure that editing a MAC profile takes place only when the new MAC address does not match an existing profile. Fixes: 605d25cd782a6 ("mlxsw: spectrum_router: Add RIF MAC profiles support") Reported-by: Maksym Yaremchuk Tested-by: Maksym Yaremchuk Signed-off-by: Danielle Ratson Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 217e3b351dfe..c34833ff1dde 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -8494,7 +8494,8 @@ mlxsw_sp_rif_mac_profile_replace(struct mlxsw_sp *mlxsw_sp, u8 mac_profile; int err; - if (!mlxsw_sp_rif_mac_profile_is_shared(rif)) + if (!mlxsw_sp_rif_mac_profile_is_shared(rif) && + !mlxsw_sp_rif_mac_profile_find(mlxsw_sp, new_mac)) return mlxsw_sp_rif_mac_profile_edit(rif, new_mac); err = mlxsw_sp_rif_mac_profile_get(mlxsw_sp, new_mac, -- cgit v1.2.3 From 20617717cd219d3c1f798cd13dbce1bcd86a6ece Mon Sep 17 00:00:00 2001 From: Danielle Ratson Date: Tue, 14 Dec 2021 12:21:37 +0200 Subject: selftests: mlxsw: Add a test case for MAC profiles consolidation Add a test case to cover the bug fixed by the previous patch. Edit the MAC address of one netdev so that it matches the MAC address of the second netdev. Verify that the two MAC profiles were consolidated by testing that the MAC profiles occupancy decreased by one. Signed-off-by: Danielle Ratson Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- .../drivers/net/mlxsw/rif_mac_profiles_occ.sh | 30 ++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_mac_profiles_occ.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_mac_profiles_occ.sh index b513f64d9092..026a126f584d 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/rif_mac_profiles_occ.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/rif_mac_profiles_occ.sh @@ -72,6 +72,35 @@ rif_mac_profile_replacement_test() ip link set $h1.10 address $h1_10_mac } +rif_mac_profile_consolidation_test() +{ + local count=$1; shift + local h1_20_mac + + RET=0 + + if [[ $count -eq 1 ]]; then + return + fi + + h1_20_mac=$(mac_get $h1.20) + + # Set the MAC of $h1.20 to that of $h1.10 and confirm that they are + # using the same MAC profile. + ip link set $h1.20 address 00:11:11:11:11:11 + check_err $? + + occ=$(devlink -j resource show $DEVLINK_DEV \ + | jq '.[][][] | select(.name=="rif_mac_profiles") |.["occ"]') + + [[ $occ -eq $((count - 1)) ]] + check_err $? "MAC profile occupancy did not decrease" + + log_test "RIF MAC profile consolidation" + + ip link set $h1.20 address $h1_20_mac +} + rif_mac_profile_shared_replacement_test() { local count=$1; shift @@ -104,6 +133,7 @@ rif_mac_profile_edit_test() create_max_rif_mac_profiles $count rif_mac_profile_replacement_test + rif_mac_profile_consolidation_test $count rif_mac_profile_shared_replacement_test $count } -- cgit v1.2.3 From edaa26334c117a584add6053f48d63a988d25a6e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 13 Dec 2021 14:14:43 -1000 Subject: iocost: Fix divide-by-zero on donation from low hweight cgroup The donation calculation logic assumes that the donor has non-zero after-donation hweight, so the lowest active hweight a donating cgroup can have is 2 so that it can donate 1 while keeping the other 1 for itself. Earlier, we only donated from cgroups with sizable surpluses so this condition was always true. However, with the precise donation algorithm implemented, f1de2439ec43 ("blk-iocost: revamp donation amount determination") made the donation amount calculation exact enabling even low hweight cgroups to donate. This means that in rare occasions, a cgroup with active hweight of 1 can enter donation calculation triggering the following warning and then a divide-by-zero oops. WARNING: CPU: 4 PID: 0 at block/blk-iocost.c:1928 transfer_surpluses.cold+0x0/0x53 [884/94867] ... RIP: 0010:transfer_surpluses.cold+0x0/0x53 Code: 92 ff 48 c7 c7 28 d1 ab b5 65 48 8b 34 25 00 ae 01 00 48 81 c6 90 06 00 00 e8 8b 3f fe ff 48 c7 c0 ea ff ff ff e9 95 ff 92 ff <0f> 0b 48 c7 c7 30 da ab b5 e8 71 3f fe ff 4c 89 e8 4d 85 ed 74 0 4 ... Call Trace: ioc_timer_fn+0x1043/0x1390 call_timer_fn+0xa1/0x2c0 __run_timers.part.0+0x1ec/0x2e0 run_timer_softirq+0x35/0x70 ... iocg: invalid donation weights in /a/b: active=1 donating=1 after=0 Fix it by excluding cgroups w/ active hweight < 2 from donating. Excluding these extreme low hweight donations shouldn't affect work conservation in any meaningful way. Signed-off-by: Tejun Heo Fixes: f1de2439ec43 ("blk-iocost: revamp donation amount determination") Cc: stable@vger.kernel.org # v5.10+ Link: https://lore.kernel.org/r/Ybfh86iSvpWKxhVM@slm.duckdns.org Signed-off-by: Jens Axboe --- block/blk-iocost.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/block/blk-iocost.c b/block/blk-iocost.c index a5b37cc65b17..769b64394298 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -2311,7 +2311,14 @@ static void ioc_timer_fn(struct timer_list *timer) hwm = current_hweight_max(iocg); new_hwi = hweight_after_donation(iocg, old_hwi, hwm, usage, &now); - if (new_hwi < hwm) { + /* + * Donation calculation assumes hweight_after_donation + * to be positive, a condition that a donor w/ hwa < 2 + * can't meet. Don't bother with donation if hwa is + * below 2. It's not gonna make a meaningful difference + * anyway. + */ + if (new_hwi < hwm && hwa >= 2) { iocg->hweight_donating = hwa; iocg->hweight_after_donation = new_hwi; list_add(&iocg->surplus_list, &surpluses); -- cgit v1.2.3 From bd0687c18e635b63233dc87f38058cd728802ab4 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Tue, 14 Dec 2021 11:26:07 +0100 Subject: xsk: Do not sleep in poll() when need_wakeup set Do not sleep in poll() when the need_wakeup flag is set. When this flag is set, the application needs to explicitly wake up the driver with a syscall (poll, recvmsg, sendmsg, etc.) to guarantee that Rx and/or Tx processing will be processed promptly. But the current code in poll(), sleeps first then wakes up the driver. This means that no driver processing will occur (baring any interrupts) until the timeout has expired. Fix this by checking the need_wakeup flag first and if set, wake the driver and return to the application. Only if need_wakeup is not set should the process sleep if there is a timeout set in the poll() call. Fixes: 77cd0d7b3f25 ("xsk: add support for need_wakeup flag in AF_XDP rings") Reported-by: Keith Wiles Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Acked-by: Maciej Fijalkowski Link: https://lore.kernel.org/bpf/20211214102607.7677-1-magnus.karlsson@gmail.com --- net/xdp/xsk.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index f16074eb53c7..7a466ea962c5 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -677,8 +677,6 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, struct xdp_sock *xs = xdp_sk(sk); struct xsk_buff_pool *pool; - sock_poll_wait(file, sock, wait); - if (unlikely(!xsk_is_bound(xs))) return mask; @@ -690,6 +688,8 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, else /* Poll needs to drive Tx also in copy mode */ __xsk_sendmsg(sk); + } else { + sock_poll_wait(file, sock, wait); } if (xs->rx && !xskq_prod_is_empty(xs->rx)) -- cgit v1.2.3 From f7abc4c8df8c7930d0b9c56d9abee9a1fca635e9 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Tue, 14 Dec 2021 07:18:00 +0530 Subject: selftests/bpf: Fix OOB write in test_verifier The commit referenced below added fixup_map_timer support (to create a BPF map containing timers), but failed to increase the size of the map_fds array, leading to out of bounds write. Fix this by changing MAX_NR_MAPS to 22. Fixes: e60e6962c503 ("selftests/bpf: Add tests for restricted helpers") Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20211214014800.78762-1-memxor@gmail.com --- tools/testing/selftests/bpf/test_verifier.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 465ef3f112c0..d3bf83d5c6cf 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -54,7 +54,7 @@ #define MAX_INSNS BPF_MAXINSNS #define MAX_TEST_INSNS 1000000 #define MAX_FIXUPS 8 -#define MAX_NR_MAPS 21 +#define MAX_NR_MAPS 22 #define MAX_TEST_RUNS 8 #define POINTER_VALUE 0xcafe4all #define TEST_DATA_LEN 64 -- cgit v1.2.3 From f35838a6930296fc1988764cfa54cb3f705c0665 Mon Sep 17 00:00:00 2001 From: Jianglei Nie Date: Thu, 9 Dec 2021 14:56:31 +0800 Subject: btrfs: fix memory leak in __add_inode_ref() Line 1169 (#3) allocates a memory chunk for victim_name by kmalloc(), but when the function returns in line 1184 (#4) victim_name allocated by line 1169 (#3) is not freed, which will lead to a memory leak. There is a similar snippet of code in this function as allocating a memory chunk for victim_name in line 1104 (#1) as well as releasing the memory in line 1116 (#2). We should kfree() victim_name when the return value of backref_in_log() is less than zero and before the function returns in line 1184 (#4). 1057 static inline int __add_inode_ref(struct btrfs_trans_handle *trans, 1058 struct btrfs_root *root, 1059 struct btrfs_path *path, 1060 struct btrfs_root *log_root, 1061 struct btrfs_inode *dir, 1062 struct btrfs_inode *inode, 1063 u64 inode_objectid, u64 parent_objectid, 1064 u64 ref_index, char *name, int namelen, 1065 int *search_done) 1066 { 1104 victim_name = kmalloc(victim_name_len, GFP_NOFS); // #1: kmalloc (victim_name-1) 1105 if (!victim_name) 1106 return -ENOMEM; 1112 ret = backref_in_log(log_root, &search_key, 1113 parent_objectid, victim_name, 1114 victim_name_len); 1115 if (ret < 0) { 1116 kfree(victim_name); // #2: kfree (victim_name-1) 1117 return ret; 1118 } else if (!ret) { 1169 victim_name = kmalloc(victim_name_len, GFP_NOFS); // #3: kmalloc (victim_name-2) 1170 if (!victim_name) 1171 return -ENOMEM; 1180 ret = backref_in_log(log_root, &search_key, 1181 parent_objectid, victim_name, 1182 victim_name_len); 1183 if (ret < 0) { 1184 return ret; // #4: missing kfree (victim_name-2) 1185 } else if (!ret) { 1241 return 0; 1242 } Fixes: d3316c8233bb ("btrfs: Properly handle backref_in_log retval") CC: stable@vger.kernel.org # 5.10+ Reviewed-by: Qu Wenruo Reviewed-by: Filipe Manana Signed-off-by: Jianglei Nie Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 3e6f14e13918..8778401665c3 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1181,6 +1181,7 @@ again: parent_objectid, victim_name, victim_name_len); if (ret < 0) { + kfree(victim_name); return ret; } else if (!ret) { ret = -ENOENT; -- cgit v1.2.3 From 33fab972497ae66822c0b6846d4f9382938575b6 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 10 Dec 2021 19:02:18 +0000 Subject: btrfs: fix double free of anon_dev after failure to create subvolume When creating a subvolume, at create_subvol(), we allocate an anonymous device and later call btrfs_get_new_fs_root(), which in turn just calls btrfs_get_root_ref(). There we call btrfs_init_fs_root() which assigns the anonymous device to the root, but if after that call there's an error, when we jump to 'fail' label, we call btrfs_put_root(), which frees the anonymous device and then returns an error that is propagated back to create_subvol(). Than create_subvol() frees the anonymous device again. When this happens, if the anonymous device was not reallocated after the first time it was freed with btrfs_put_root(), we get a kernel message like the following: (...) [13950.282466] BTRFS: error (device dm-0) in create_subvol:663: errno=-5 IO failure [13950.283027] ida_free called for id=65 which is not allocated. [13950.285974] BTRFS info (device dm-0): forced readonly (...) If the anonymous device gets reallocated by another btrfs filesystem or any other kernel subsystem, then bad things can happen. So fix this by setting the root's anonymous device to 0 at btrfs_get_root_ref(), before we call btrfs_put_root(), if an error happened. Fixes: 2dfb1e43f57dd3 ("btrfs: preallocate anon block device at first phase of snapshot creation") CC: stable@vger.kernel.org # 5.10+ Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 847aabb30676..28449ca66dbd 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1732,6 +1732,14 @@ again: } return root; fail: + /* + * If our caller provided us an anonymous device, then it's his + * responsability to free it in case we fail. So we have to set our + * root's anon_dev to 0 to avoid a double free, once by btrfs_put_root() + * and once again by our caller. + */ + if (anon_dev) + root->anon_dev = 0; btrfs_put_root(root); return ERR_PTR(ret); } -- cgit v1.2.3 From 1b2e5e5c7feabb4f3041f637b96494944da6aeff Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 14 Dec 2021 11:29:01 +0000 Subject: btrfs: fix missing last dir item offset update when logging directory When logging a directory, once we finish processing a leaf that is full of dir items, if we find the next leaf was not modified in the current transaction, we grab the first key of that next leaf and log it as to mark the end of a key range boundary. However we did not update the value of ctx->last_dir_item_offset, which tracks the offset of the last logged key. This can result in subsequent logging of the same directory in the current transaction to not realize that key was already logged, and then add it to the middle of a batch that starts with a lower key, resulting later in a leaf with one key that is duplicated and at non-consecutive slots. When that happens we get an error later when writing out the leaf, reporting that there is a pair of keys in wrong order. The report is something like the following: Dec 13 21:44:50 kernel: BTRFS critical (device dm-0): corrupt leaf: root=18446744073709551610 block=118444032 slot=21, bad key order, prev (704687 84 4146773349) current (704687 84 1063561078) Dec 13 21:44:50 kernel: BTRFS info (device dm-0): leaf 118444032 gen 91449 total ptrs 39 free space 546 owner 18446744073709551610 Dec 13 21:44:50 kernel: item 0 key (704687 1 0) itemoff 3835 itemsize 160 Dec 13 21:44:50 kernel: inode generation 35532 size 1026 mode 40755 Dec 13 21:44:50 kernel: item 1 key (704687 12 704685) itemoff 3822 itemsize 13 Dec 13 21:44:50 kernel: item 2 key (704687 24 3817753667) itemoff 3736 itemsize 86 Dec 13 21:44:50 kernel: item 3 key (704687 60 0) itemoff 3728 itemsize 8 Dec 13 21:44:50 kernel: item 4 key (704687 72 0) itemoff 3720 itemsize 8 Dec 13 21:44:50 kernel: item 5 key (704687 84 140445108) itemoff 3666 itemsize 54 Dec 13 21:44:50 kernel: dir oid 704793 type 1 Dec 13 21:44:50 kernel: item 6 key (704687 84 298800632) itemoff 3599 itemsize 67 Dec 13 21:44:50 kernel: dir oid 707849 type 2 Dec 13 21:44:50 kernel: item 7 key (704687 84 476147658) itemoff 3532 itemsize 67 Dec 13 21:44:50 kernel: dir oid 707901 type 2 Dec 13 21:44:50 kernel: item 8 key (704687 84 633818382) itemoff 3471 itemsize 61 Dec 13 21:44:50 kernel: dir oid 704694 type 2 Dec 13 21:44:50 kernel: item 9 key (704687 84 654256665) itemoff 3403 itemsize 68 Dec 13 21:44:50 kernel: dir oid 707841 type 1 Dec 13 21:44:50 kernel: item 10 key (704687 84 995843418) itemoff 3331 itemsize 72 Dec 13 21:44:50 kernel: dir oid 2167736 type 1 Dec 13 21:44:50 kernel: item 11 key (704687 84 1063561078) itemoff 3278 itemsize 53 Dec 13 21:44:50 kernel: dir oid 704799 type 2 Dec 13 21:44:50 kernel: item 12 key (704687 84 1101156010) itemoff 3225 itemsize 53 Dec 13 21:44:50 kernel: dir oid 704696 type 1 Dec 13 21:44:50 kernel: item 13 key (704687 84 2521936574) itemoff 3173 itemsize 52 Dec 13 21:44:50 kernel: dir oid 704704 type 2 Dec 13 21:44:50 kernel: item 14 key (704687 84 2618368432) itemoff 3112 itemsize 61 Dec 13 21:44:50 kernel: dir oid 704738 type 1 Dec 13 21:44:50 kernel: item 15 key (704687 84 2676316190) itemoff 3046 itemsize 66 Dec 13 21:44:50 kernel: dir oid 2167729 type 1 Dec 13 21:44:50 kernel: item 16 key (704687 84 3319104192) itemoff 2986 itemsize 60 Dec 13 21:44:50 kernel: dir oid 704745 type 2 Dec 13 21:44:50 kernel: item 17 key (704687 84 3908046265) itemoff 2929 itemsize 57 Dec 13 21:44:50 kernel: dir oid 2167734 type 1 Dec 13 21:44:50 kernel: item 18 key (704687 84 3945713089) itemoff 2857 itemsize 72 Dec 13 21:44:50 kernel: dir oid 2167730 type 1 Dec 13 21:44:50 kernel: item 19 key (704687 84 4077169308) itemoff 2795 itemsize 62 Dec 13 21:44:50 kernel: dir oid 704688 type 1 Dec 13 21:44:50 kernel: item 20 key (704687 84 4146773349) itemoff 2727 itemsize 68 Dec 13 21:44:50 kernel: dir oid 707892 type 1 Dec 13 21:44:50 kernel: item 21 key (704687 84 1063561078) itemoff 2674 itemsize 53 Dec 13 21:44:50 kernel: dir oid 704799 type 2 Dec 13 21:44:50 kernel: item 22 key (704687 96 2) itemoff 2612 itemsize 62 Dec 13 21:44:50 kernel: item 23 key (704687 96 6) itemoff 2551 itemsize 61 Dec 13 21:44:50 kernel: item 24 key (704687 96 7) itemoff 2498 itemsize 53 Dec 13 21:44:50 kernel: item 25 key (704687 96 12) itemoff 2446 itemsize 52 Dec 13 21:44:50 kernel: item 26 key (704687 96 14) itemoff 2385 itemsize 61 Dec 13 21:44:50 kernel: item 27 key (704687 96 18) itemoff 2325 itemsize 60 Dec 13 21:44:50 kernel: item 28 key (704687 96 24) itemoff 2271 itemsize 54 Dec 13 21:44:50 kernel: item 29 key (704687 96 28) itemoff 2218 itemsize 53 Dec 13 21:44:50 kernel: item 30 key (704687 96 62) itemoff 2150 itemsize 68 Dec 13 21:44:50 kernel: item 31 key (704687 96 66) itemoff 2083 itemsize 67 Dec 13 21:44:50 kernel: item 32 key (704687 96 75) itemoff 2015 itemsize 68 Dec 13 21:44:50 kernel: item 33 key (704687 96 79) itemoff 1948 itemsize 67 Dec 13 21:44:50 kernel: item 34 key (704687 96 82) itemoff 1882 itemsize 66 Dec 13 21:44:50 kernel: item 35 key (704687 96 83) itemoff 1810 itemsize 72 Dec 13 21:44:50 kernel: item 36 key (704687 96 85) itemoff 1753 itemsize 57 Dec 13 21:44:50 kernel: item 37 key (704687 96 87) itemoff 1681 itemsize 72 Dec 13 21:44:50 kernel: item 38 key (704694 1 0) itemoff 1521 itemsize 160 Dec 13 21:44:50 kernel: inode generation 35534 size 30 mode 40755 Dec 13 21:44:50 kernel: BTRFS error (device dm-0): block=118444032 write time tree block corruption detected So fix that by adding the missing update of ctx->last_dir_item_offset with the offset of the boundary key. Reported-by: Chris Murphy Link: https://lore.kernel.org/linux-btrfs/CAJCQCtT+RSzpUjbMq+UfzNUMe1X5+1G+DnAGbHC=OZ=iRS24jg@mail.gmail.com/ Fixes: dc2872247ec0ca ("btrfs: keep track of the last logged keys when logging a directory") Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 8778401665c3..6993dcdba6f1 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3978,6 +3978,7 @@ search: goto done; } if (btrfs_header_generation(path->nodes[0]) != trans->transid) { + ctx->last_dir_item_offset = min_key.offset; ret = overwrite_item(trans, log, dst_path, path->nodes[0], path->slots[0], &min_key); -- cgit v1.2.3 From 0013881c1145d36bf26165bb70fdd7560a5507a3 Mon Sep 17 00:00:00 2001 From: Karol Kolacinski Date: Thu, 4 Nov 2021 14:52:11 +0100 Subject: ice: Use div64_u64 instead of div_u64 in adjfine Change the division in ice_ptp_adjfine from div_u64 to div64_u64. div_u64 is used when the divisor is 32 bit but in this case incval is 64 bit and it caused incorrect calculations and incval adjustments. Fixes: 06c16d89d2cb ("ice: register 1588 PTP clock device object for E810 devices") Signed-off-by: Karol Kolacinski Tested-by: Gurucharan G Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_ptp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index bf7247c6f58e..ad7cabe7932f 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -705,7 +705,7 @@ static int ice_ptp_adjfine(struct ptp_clock_info *info, long scaled_ppm) scaled_ppm = -scaled_ppm; } - while ((u64)scaled_ppm > div_u64(U64_MAX, incval)) { + while ((u64)scaled_ppm > div64_u64(U64_MAX, incval)) { /* handle overflow by scaling down the scaled_ppm and * the divisor, losing some precision */ -- cgit v1.2.3 From 37e738b6fdb14529534dca441e0222313688fde3 Mon Sep 17 00:00:00 2001 From: Karol Kolacinski Date: Tue, 16 Nov 2021 13:07:14 +0100 Subject: ice: Don't put stale timestamps in the skb The driver has to check if it does not accidentally put the timestamp in the SKB before previous timestamp gets overwritten. Timestamp values in the PHY are read only and do not get cleared except at hardware reset or when a new timestamp value is captured. The cached_tstamp field is used to detect the case where a new timestamp has not yet been captured, ensuring that we avoid sending stale timestamp data to the stack. Fixes: ea9b847cda64 ("ice: enable transmit timestamps for E810 devices") Signed-off-by: Karol Kolacinski Tested-by: Gurucharan G Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_ptp.c | 11 ++++------- drivers/net/ethernet/intel/ice/ice_ptp.h | 6 ++++++ 2 files changed, 10 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index ad7cabe7932f..442b031b0edc 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -1540,19 +1540,16 @@ static void ice_ptp_tx_tstamp_work(struct kthread_work *work) if (err) continue; - /* Check if the timestamp is valid */ - if (!(raw_tstamp & ICE_PTP_TS_VALID)) + /* Check if the timestamp is invalid or stale */ + if (!(raw_tstamp & ICE_PTP_TS_VALID) || + raw_tstamp == tx->tstamps[idx].cached_tstamp) continue; - /* clear the timestamp register, so that it won't show valid - * again when re-used. - */ - ice_clear_phy_tstamp(hw, tx->quad, phy_idx); - /* The timestamp is valid, so we'll go ahead and clear this * index and then send the timestamp up to the stack. */ spin_lock(&tx->lock); + tx->tstamps[idx].cached_tstamp = raw_tstamp; clear_bit(idx, tx->in_use); skb = tx->tstamps[idx].skb; tx->tstamps[idx].skb = NULL; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index f71ad317d6c8..53c15fc9d996 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -55,15 +55,21 @@ struct ice_perout_channel { * struct ice_tx_tstamp - Tracking for a single Tx timestamp * @skb: pointer to the SKB for this timestamp request * @start: jiffies when the timestamp was first requested + * @cached_tstamp: last read timestamp * * This structure tracks a single timestamp request. The SKB pointer is * provided when initiating a request. The start time is used to ensure that * we discard old requests that were not fulfilled within a 2 second time * window. + * Timestamp values in the PHY are read only and do not get cleared except at + * hardware reset or when a new timestamp value is captured. The cached_tstamp + * field is used to detect the case where a new timestamp has not yet been + * captured, ensuring that we avoid sending stale timestamp data to the stack. */ struct ice_tx_tstamp { struct sk_buff *skb; unsigned long start; + u64 cached_tstamp; }; /** -- cgit v1.2.3 From 6c3118c32129b4197999a8928ba776bcabd0f5c4 Mon Sep 17 00:00:00 2001 From: "Chang S. Bae" Date: Fri, 10 Dec 2021 14:55:03 -0800 Subject: signal: Skip the altstack update when not needed == Background == Support for large, "dynamic" fpstates was recently merged. This included code to ensure that sigaltstacks are sufficiently sized for these large states. A new lock was added to remove races between enabling large features and setting up sigaltstacks. == Problem == The new lock (sigaltstack_lock()) is acquired in the sigreturn path before restoring the old sigaltstack. Unfortunately, contention on the new lock causes a measurable signal handling performance regression [1]. However, the common case is that no *changes* are made to the sigaltstack state at sigreturn. == Solution == do_sigaltstack() acquires sigaltstack_lock() and is used for both sys_sigaltstack() and restoring the sigaltstack in sys_sigreturn(). Check for changes to the sigaltstack before taking the lock. If no changes were made, return before acquiring the lock. This removes lock contention from the common-case sigreturn path. [1] https://lore.kernel.org/lkml/20211207012128.GA16074@xsang-OptiPlex-9020/ Fixes: 3aac3ebea08f ("x86/signal: Implement sigaltstack size validation") Reported-by: kernel test robot Signed-off-by: Chang S. Bae Signed-off-by: Dave Hansen Reviewed-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20211210225503.12734-1-chang.seok.bae@intel.com --- kernel/signal.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/kernel/signal.c b/kernel/signal.c index a629b11bf3e0..dfcee3888b00 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -4185,6 +4185,15 @@ do_sigaltstack (const stack_t *ss, stack_t *oss, unsigned long sp, ss_mode != 0)) return -EINVAL; + /* + * Return before taking any locks if no actual + * sigaltstack changes were requested. + */ + if (t->sas_ss_sp == (unsigned long)ss_sp && + t->sas_ss_size == ss_size && + t->sas_ss_flags == ss_flags) + return 0; + sigaltstack_lock(); if (ss_mode == SS_DISABLE) { ss_size = 0; -- cgit v1.2.3 From f3a8076eb28cae1553958c629aecec479394bbe2 Mon Sep 17 00:00:00 2001 From: Le Ma Date: Sat, 4 Dec 2021 18:59:08 +0800 Subject: drm/amdgpu: correct register access for RLC_JUMP_TABLE_RESTORE should count on GC IP base address Signed-off-by: Le Ma Signed-off-by: Hawking Zhang Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index b305fd39874f..edb3e3b08eed 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -3070,8 +3070,8 @@ static void gfx_v9_0_init_pg(struct amdgpu_device *adev) AMD_PG_SUPPORT_CP | AMD_PG_SUPPORT_GDS | AMD_PG_SUPPORT_RLC_SMU_HS)) { - WREG32(mmRLC_JUMP_TABLE_RESTORE, - adev->gfx.rlc.cp_table_gpu_addr >> 8); + WREG32_SOC15(GC, 0, mmRLC_JUMP_TABLE_RESTORE, + adev->gfx.rlc.cp_table_gpu_addr >> 8); gfx_v9_0_init_gfx_power_gating(adev); } } -- cgit v1.2.3 From 841933d5b8aa853abe68e63827f68f50fab37226 Mon Sep 17 00:00:00 2001 From: Hawking Zhang Date: Sat, 4 Dec 2021 19:22:12 +0800 Subject: drm/amdgpu: don't override default ECO_BITs setting Leave this bit as hardware default setting Signed-off-by: Hawking Zhang Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c | 1 - drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c | 1 - drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c | 1 - drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c | 1 - drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c | 1 - drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c | 1 - drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c | 1 - drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c | 2 -- 8 files changed, 9 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c index 480e41847d7c..ec4d5e15b766 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c @@ -162,7 +162,6 @@ static void gfxhub_v1_0_init_tlb_regs(struct amdgpu_device *adev) ENABLE_ADVANCED_DRIVER_MODEL, 1); tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, SYSTEM_APERTURE_UNMAPPED_ACCESS, 0); - tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0); tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, MTYPE, MTYPE_UC);/* XXX for emulation. */ tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ATC_EN, 1); diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c index 14c1c1a297dd..6e0ace2fbfab 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c @@ -196,7 +196,6 @@ static void gfxhub_v2_0_init_tlb_regs(struct amdgpu_device *adev) ENABLE_ADVANCED_DRIVER_MODEL, 1); tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL, SYSTEM_APERTURE_UNMAPPED_ACCESS, 0); - tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0); tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL, MTYPE, MTYPE_UC); /* UC, uncached */ diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c index e80d1dc43079..b4eddf6e98a6 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c @@ -197,7 +197,6 @@ static void gfxhub_v2_1_init_tlb_regs(struct amdgpu_device *adev) ENABLE_ADVANCED_DRIVER_MODEL, 1); tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL, SYSTEM_APERTURE_UNMAPPED_ACCESS, 0); - tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0); tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL, MTYPE, MTYPE_UC); /* UC, uncached */ diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c index a99953833820..b3bede1dc41d 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c @@ -145,7 +145,6 @@ static void mmhub_v1_0_init_tlb_regs(struct amdgpu_device *adev) ENABLE_ADVANCED_DRIVER_MODEL, 1); tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, SYSTEM_APERTURE_UNMAPPED_ACCESS, 0); - tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0); tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, MTYPE, MTYPE_UC);/* XXX for emulation. */ tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ATC_EN, 1); diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c index f80a14a1b82d..f5f7181f9af5 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c @@ -165,7 +165,6 @@ static void mmhub_v1_7_init_tlb_regs(struct amdgpu_device *adev) ENABLE_ADVANCED_DRIVER_MODEL, 1); tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, SYSTEM_APERTURE_UNMAPPED_ACCESS, 0); - tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0); tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, MTYPE, MTYPE_UC);/* XXX for emulation. */ tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ATC_EN, 1); diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c index 25f8e93e5ec3..3718ff610ab2 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c @@ -267,7 +267,6 @@ static void mmhub_v2_0_init_tlb_regs(struct amdgpu_device *adev) ENABLE_ADVANCED_DRIVER_MODEL, 1); tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL, SYSTEM_APERTURE_UNMAPPED_ACCESS, 0); - tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0); tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL, MTYPE, MTYPE_UC); /* UC, uncached */ diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c index a11d60ec6321..9e16da28505a 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c @@ -194,7 +194,6 @@ static void mmhub_v2_3_init_tlb_regs(struct amdgpu_device *adev) ENABLE_ADVANCED_DRIVER_MODEL, 1); tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL, SYSTEM_APERTURE_UNMAPPED_ACCESS, 0); - tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0); tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL, MTYPE, MTYPE_UC); /* UC, uncached */ diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c index c4ef822bbe8c..ff49eeaf7882 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c @@ -189,8 +189,6 @@ static void mmhub_v9_4_init_tlb_regs(struct amdgpu_device *adev, int hubid) ENABLE_ADVANCED_DRIVER_MODEL, 1); tmp = REG_SET_FIELD(tmp, VMSHAREDVC0_MC_VM_MX_L1_TLB_CNTL, SYSTEM_APERTURE_UNMAPPED_ACCESS, 0); - tmp = REG_SET_FIELD(tmp, VMSHAREDVC0_MC_VM_MX_L1_TLB_CNTL, - ECO_BITS, 0); tmp = REG_SET_FIELD(tmp, VMSHAREDVC0_MC_VM_MX_L1_TLB_CNTL, MTYPE, MTYPE_UC);/* XXX for emulation. */ tmp = REG_SET_FIELD(tmp, VMSHAREDVC0_MC_VM_MX_L1_TLB_CNTL, -- cgit v1.2.3 From dcd10d879a9d1d4e929d374c2f24aba8fac3252b Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Thu, 9 Dec 2021 12:13:53 -0600 Subject: drm/amd/pm: fix reading SMU FW version from amdgpu_firmware_info on YC This value does not get cached into adev->pm.fw_version during startup for smu13 like it does for other SMU like smu12. Signed-off-by: Mario Limonciello Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index 35145db6eedf..19a5d2c39c8d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -198,6 +198,7 @@ int smu_v13_0_check_fw_status(struct smu_context *smu) int smu_v13_0_check_fw_version(struct smu_context *smu) { + struct amdgpu_device *adev = smu->adev; uint32_t if_version = 0xff, smu_version = 0xff; uint16_t smu_major; uint8_t smu_minor, smu_debug; @@ -210,6 +211,8 @@ int smu_v13_0_check_fw_version(struct smu_context *smu) smu_major = (smu_version >> 16) & 0xffff; smu_minor = (smu_version >> 8) & 0xff; smu_debug = (smu_version >> 0) & 0xff; + if (smu->is_apu) + adev->pm.fw_version = smu_version; switch (smu->adev->ip_versions[MP1_HWIP][0]) { case IP_VERSION(13, 0, 2): -- cgit v1.2.3 From 7e4d2f30df3fb48f75ce9e96867d42bdddab83ac Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Fri, 10 Dec 2021 15:03:59 -0800 Subject: drm/amd/display: Set exit_optimized_pwr_state for DCN31 [Why] SMU now respects the PHY refclk disable request from driver. This causes a hang during hotplug when PHY refclk was disabled because it's not being re-enabled and the transmitter control starts on dc_link_detect. [How] We normally would re-enable the clk with exit_optimized_pwr_state but this is only set on DCN21 and DCN301. Set it for dcn31 as well. This fixes DMCUB timeouts in the PHY. Fixes: 64b1d0e8d500 ("drm/amd/display: Add DCN3.1 HWSEQ") Reviewed-by: Eric Yang Acked-by: Pavle Kotarac Tested-by: Daniel Wheeler Signed-off-by: Nicholas Kazlauskas Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c index 05335a8c3c2d..4f6e639e9353 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c @@ -101,6 +101,7 @@ static const struct hw_sequencer_funcs dcn31_funcs = { .z10_restore = dcn31_z10_restore, .z10_save_init = dcn31_z10_save_init, .set_disp_pattern_generator = dcn30_set_disp_pattern_generator, + .exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state, .update_visual_confirm_color = dcn20_update_visual_confirm_color, }; -- cgit v1.2.3 From 791255ca9fbe38042cfd55df5deb116dc11fef18 Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Fri, 10 Dec 2021 15:04:05 -0800 Subject: drm/amd/display: Reset DMCUB before HW init [Why] If the firmware wasn't reset by PSP or HW and is currently running then the firmware will hang or perform underfined behavior when we modify its firmware state underneath it. [How] Reset DMCUB before setting up cache windows and performing HW init. Reviewed-by: Aurabindo Jayamohanan Pillai Acked-by: Pavle Kotarac Tested-by: Daniel Wheeler Signed-off-by: Nicholas Kazlauskas Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 122dae1a1813..e727f1dd2a9a 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1051,6 +1051,11 @@ static int dm_dmub_hw_init(struct amdgpu_device *adev) return 0; } + /* Reset DMCUB if it was previously running - before we overwrite its memory. */ + status = dmub_srv_hw_reset(dmub_srv); + if (status != DMUB_STATUS_OK) + DRM_WARN("Error resetting DMUB HW: %d\n", status); + hdr = (const struct dmcub_firmware_header_v1_0 *)dmub_fw->data; fw_inst_const = dmub_fw->data + -- cgit v1.2.3 From 17c65d6fca844ee72a651944d8ce721e9040bf70 Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Mon, 13 Dec 2021 14:38:38 +0800 Subject: drm/amdgpu: correct the wrong cached state for GMC on PICASSO Pair the operations did in GMC ->hw_init and ->hw_fini. That can help to maintain correct cached state for GMC and avoid unintention gate operation dropping due to wrong cached state. BugLink: https://gitlab.freedesktop.org/drm/amd/-/issues/1828 Signed-off-by: Evan Quan Acked-by: Guchun Chen Reviewed-by: Mario Limonciello Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 8 ++++++++ drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c | 8 ++++---- drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c | 7 ++++++- 3 files changed, 18 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index cb82404df534..d84523cf5f75 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1808,6 +1808,14 @@ static int gmc_v9_0_hw_fini(void *handle) return 0; } + /* + * Pair the operations did in gmc_v9_0_hw_init and thus maintain + * a correct cached state for GMC. Otherwise, the "gate" again + * operation on S3 resuming will fail due to wrong cached state. + */ + if (adev->mmhub.funcs->update_power_gating) + adev->mmhub.funcs->update_power_gating(adev, false); + amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0); amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c index b3bede1dc41d..1da2ec692057 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c @@ -301,10 +301,10 @@ static void mmhub_v1_0_update_power_gating(struct amdgpu_device *adev, if (amdgpu_sriov_vf(adev)) return; - if (enable && adev->pg_flags & AMD_PG_SUPPORT_MMHUB) { - amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GMC, true); - - } + if (adev->pg_flags & AMD_PG_SUPPORT_MMHUB) + amdgpu_dpm_set_powergating_by_smu(adev, + AMD_IP_BLOCK_TYPE_GMC, + enable); } static int mmhub_v1_0_gart_enable(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c index 8d796ed3b7d1..619f8d305292 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c @@ -1328,7 +1328,12 @@ static int pp_set_powergating_by_smu(void *handle, pp_dpm_powergate_vce(handle, gate); break; case AMD_IP_BLOCK_TYPE_GMC: - pp_dpm_powergate_mmhub(handle); + /* + * For now, this is only used on PICASSO. + * And only "gate" operation is supported. + */ + if (gate) + pp_dpm_powergate_mmhub(handle); break; case AMD_IP_BLOCK_TYPE_GFX: ret = pp_dpm_powergate_gfx(handle, gate); -- cgit v1.2.3 From aa464957f7e660abd554f2546a588f6533720e21 Mon Sep 17 00:00:00 2001 From: Lang Yu Date: Tue, 14 Dec 2021 15:25:54 +0800 Subject: drm/amd/pm: fix a potential gpu_metrics_table memory leak Memory is allocated for gpu_metrics_table in renoir_init_smc_tables(), but not freed in int smu_v12_0_fini_smc_tables(). Free it! Fixes: 95868b85764a ("drm/amd/powerplay: add Renoir support for gpu metrics export") Signed-off-by: Lang Yu Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c index d60b8c5e8715..43028f2cd28b 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c @@ -191,6 +191,9 @@ int smu_v12_0_fini_smc_tables(struct smu_context *smu) kfree(smu_table->watermarks_table); smu_table->watermarks_table = NULL; + kfree(smu_table->gpu_metrics_table); + smu_table->gpu_metrics_table = NULL; + return 0; } -- cgit v1.2.3 From 404cd9a22150f24acf23a8df2ad0c094ba379f57 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 14 Dec 2021 15:16:01 -0800 Subject: mptcp: remove tcp ulp setsockopt support TCP_ULP setsockopt cannot be used for mptcp because its already used internally to plumb subflow (tcp) sockets to the mptcp layer. syzbot managed to trigger a crash for mptcp connections that are in fallback mode: KASAN: null-ptr-deref in range [0x0000000000000020-0x0000000000000027] CPU: 1 PID: 1083 Comm: syz-executor.3 Not tainted 5.16.0-rc2-syzkaller #0 RIP: 0010:tls_build_proto net/tls/tls_main.c:776 [inline] [..] __tcp_set_ulp net/ipv4/tcp_ulp.c:139 [inline] tcp_set_ulp+0x428/0x4c0 net/ipv4/tcp_ulp.c:160 do_tcp_setsockopt+0x455/0x37c0 net/ipv4/tcp.c:3391 mptcp_setsockopt+0x1b47/0x2400 net/mptcp/sockopt.c:638 Remove support for TCP_ULP setsockopt. Fixes: d9e4c1291810 ("mptcp: only admit explicitly supported sockopt") Reported-by: syzbot+1fd9b69cde42967d1add@syzkaller.appspotmail.com Signed-off-by: Florian Westphal Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- net/mptcp/sockopt.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 0f1e661c2032..f8efd478ac97 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -525,7 +525,6 @@ static bool mptcp_supported_sockopt(int level, int optname) case TCP_NODELAY: case TCP_THIN_LINEAR_TIMEOUTS: case TCP_CONGESTION: - case TCP_ULP: case TCP_CORK: case TCP_KEEPIDLE: case TCP_KEEPINTVL: -- cgit v1.2.3 From d6692b3b97bdc165d150f4c1505751a323a80717 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 14 Dec 2021 15:16:02 -0800 Subject: mptcp: clear 'kern' flag from fallback sockets The mptcp ULP extension relies on sk->sk_sock_kern being set correctly: It prevents setsockopt(fd, IPPROTO_TCP, TCP_ULP, "mptcp", 6); from working for plain tcp sockets (any userspace-exposed socket). But in case of fallback, accept() can return a plain tcp sk. In such case, sk is still tagged as 'kernel' and setsockopt will work. This will crash the kernel, The subflow extension has a NULL ctx->conn mptcp socket: BUG: KASAN: null-ptr-deref in subflow_data_ready+0x181/0x2b0 Call Trace: tcp_data_ready+0xf8/0x370 [..] Fixes: cf7da0d66cc1 ("mptcp: Create SUBFLOW socket for incoming connections") Signed-off-by: Florian Westphal Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index c82a76d2d0bf..6dc1ff07994c 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2879,7 +2879,7 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, */ if (WARN_ON_ONCE(!new_mptcp_sock)) { tcp_sk(newsk)->is_mptcp = 0; - return newsk; + goto out; } /* acquire the 2nd reference for the owning socket */ @@ -2891,6 +2891,8 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK); } +out: + newsk->sk_kern_sock = kern; return newsk; } -- cgit v1.2.3 From 3d79e3756ca90f7a6087b77b62c1d9c0801e0820 Mon Sep 17 00:00:00 2001 From: Maxim Galaganov Date: Tue, 14 Dec 2021 15:16:03 -0800 Subject: mptcp: fix deadlock in __mptcp_push_pending() __mptcp_push_pending() may call mptcp_flush_join_list() with subflow socket lock held. If such call hits mptcp_sockopt_sync_all() then subsequently __mptcp_sockopt_sync() could try to lock the subflow socket for itself, causing a deadlock. sysrq: Show Blocked State task:ss-server state:D stack: 0 pid: 938 ppid: 1 flags:0x00000000 Call Trace: __schedule+0x2d6/0x10c0 ? __mod_memcg_state+0x4d/0x70 ? csum_partial+0xd/0x20 ? _raw_spin_lock_irqsave+0x26/0x50 schedule+0x4e/0xc0 __lock_sock+0x69/0x90 ? do_wait_intr_irq+0xa0/0xa0 __lock_sock_fast+0x35/0x50 mptcp_sockopt_sync_all+0x38/0xc0 __mptcp_push_pending+0x105/0x200 mptcp_sendmsg+0x466/0x490 sock_sendmsg+0x57/0x60 __sys_sendto+0xf0/0x160 ? do_wait_intr_irq+0xa0/0xa0 ? fpregs_restore_userregs+0x12/0xd0 __x64_sys_sendto+0x20/0x30 do_syscall_64+0x38/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f9ba546c2d0 RSP: 002b:00007ffdc3b762d8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 00007f9ba56c8060 RCX: 00007f9ba546c2d0 RDX: 000000000000077a RSI: 0000000000e5e180 RDI: 0000000000000234 RBP: 0000000000cc57f0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f9ba56c8060 R13: 0000000000b6ba60 R14: 0000000000cc7840 R15: 41d8685b1d7901b8 Fix the issue by using __mptcp_flush_join_list() instead of plain mptcp_flush_join_list() inside __mptcp_push_pending(), as suggested by Florian. The sockopt sync will be deferred to the workqueue. Fixes: 1b3e7ede1365 ("mptcp: setsockopt: handle SO_KEEPALIVE and SO_PRIORITY") Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/244 Suggested-by: Florian Westphal Reviewed-by: Florian Westphal Signed-off-by: Maxim Galaganov Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 6dc1ff07994c..54613f5b7521 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1524,7 +1524,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags) int ret = 0; prev_ssk = ssk; - mptcp_flush_join_list(msk); + __mptcp_flush_join_list(msk); ssk = mptcp_subflow_get_send(msk); /* First check. If the ssk has changed since -- cgit v1.2.3 From 6813b1928758ce64fabbb8ef157f994b7c2235fa Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Tue, 14 Dec 2021 15:16:04 -0800 Subject: mptcp: add missing documented NL params 'loc_id' and 'rem_id' are set in all events linked to subflows but those were missing in the events description in the comments. Fixes: b911c97c7dc7 ("mptcp: add netlink event support") Signed-off-by: Matthieu Baerts Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index c8cc46f80a16..f106a3941cdf 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -136,19 +136,21 @@ struct mptcp_info { * MPTCP_EVENT_REMOVED: token, rem_id * An address has been lost by the peer. * - * MPTCP_EVENT_SUB_ESTABLISHED: token, family, saddr4 | saddr6, - * daddr4 | daddr6, sport, dport, backup, - * if_idx [, error] + * MPTCP_EVENT_SUB_ESTABLISHED: token, family, loc_id, rem_id, + * saddr4 | saddr6, daddr4 | daddr6, sport, + * dport, backup, if_idx [, error] * A new subflow has been established. 'error' should not be set. * - * MPTCP_EVENT_SUB_CLOSED: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport, backup, if_idx [, error] + * MPTCP_EVENT_SUB_CLOSED: token, family, loc_id, rem_id, saddr4 | saddr6, + * daddr4 | daddr6, sport, dport, backup, if_idx + * [, error] * A subflow has been closed. An error (copy of sk_err) could be set if an * error has been detected for this subflow. * - * MPTCP_EVENT_SUB_PRIORITY: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport, backup, if_idx [, error] - * The priority of a subflow has changed. 'error' should not be set. + * MPTCP_EVENT_SUB_PRIORITY: token, family, loc_id, rem_id, saddr4 | saddr6, + * daddr4 | daddr6, sport, dport, backup, if_idx + * [, error] + * The priority of a subflow has changed. 'error' should not be set. */ enum mptcp_event_type { MPTCP_EVENT_UNSPEC = 0, -- cgit v1.2.3 From cb2ac2912a9ca7d3d26291c511939a41361d2d83 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 14 Dec 2021 07:03:24 -0700 Subject: block: reduce kblockd_mod_delayed_work_on() CPU consumption Dexuan reports that he's seeing spikes of very heavy CPU utilization when running 24 disks and using the 'none' scheduler. This happens off the sched restart path, because SCSI requires the queue to be restarted async, and hence we're hammering on mod_delayed_work_on() to ensure that the work item gets run appropriately. Avoid hammering on the timer and just use queue_work_on() if no delay has been specified. Reported-and-tested-by: Dexuan Cui Link: https://lore.kernel.org/linux-block/BYAPR21MB1270C598ED214C0490F47400BF719@BYAPR21MB1270.namprd21.prod.outlook.com/ Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/block/blk-core.c b/block/blk-core.c index 1378d084c770..c1833f95cb97 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1484,6 +1484,8 @@ EXPORT_SYMBOL(kblockd_schedule_work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay) { + if (!delay) + return queue_work_on(cpu, kblockd_workqueue, &dwork->work); return mod_delayed_work_on(cpu, kblockd_workqueue, dwork, delay); } EXPORT_SYMBOL(kblockd_mod_delayed_work_on); -- cgit v1.2.3 From aa97f6cdb7e92909e17c8ca63e622fcb81d57a57 Mon Sep 17 00:00:00 2001 From: Lin Feng Date: Fri, 12 Nov 2021 13:36:29 +0800 Subject: bcache: fix NULL pointer reference in cached_dev_detach_finish Commit 0259d4498ba4 ("bcache: move calc_cached_dev_sectors to proper place on backing device detach") tries to fix calc_cached_dev_sectors when bcache device detaches, but now we have: cached_dev_detach_finish ... bcache_device_detach(&dc->disk); ... closure_put(&d->c->caching); d->c = NULL; [*explicitly set dc->disk.c to NULL*] list_move(&dc->list, &uncached_devices); calc_cached_dev_sectors(dc->disk.c); [*passing a NULL pointer*] ... Upper codeflows shows how bug happens, this patch fix the problem by caching dc->disk.c beforehand, and cache_set won't be freed under us because c->caching closure at least holds a reference count and closure callback __cache_set_unregister only being called by bch_cache_set_stop which using closure_queue(&c->caching), that means c->caching closure callback for destroying cache_set won't be trigger by previous closure_put(&d->c->caching). So at this stage(while cached_dev_detach_finish is calling) it's safe to access cache_set dc->disk.c. Fixes: 0259d4498ba4 ("bcache: move calc_cached_dev_sectors to proper place on backing device detach") Signed-off-by: Lin Feng Signed-off-by: Coly Li Link: https://lore.kernel.org/r/20211112053629.3437-2-colyli@suse.de Signed-off-by: Jens Axboe --- drivers/md/bcache/super.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 86b9e355c583..140f35dc0c45 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1139,6 +1139,7 @@ static void cancel_writeback_rate_update_dwork(struct cached_dev *dc) static void cached_dev_detach_finish(struct work_struct *w) { struct cached_dev *dc = container_of(w, struct cached_dev, detach); + struct cache_set *c = dc->disk.c; BUG_ON(!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags)); BUG_ON(refcount_read(&dc->count)); @@ -1156,7 +1157,7 @@ static void cached_dev_detach_finish(struct work_struct *w) bcache_device_detach(&dc->disk); list_move(&dc->list, &uncached_devices); - calc_cached_dev_sectors(dc->disk.c); + calc_cached_dev_sectors(c); clear_bit(BCACHE_DEV_DETACHING, &dc->disk.flags); clear_bit(BCACHE_DEV_UNLINK_DONE, &dc->disk.flags); -- cgit v1.2.3 From 7d3baf0afa3aa9102d6a521a8e4c41888bb79882 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 7 Dec 2021 12:51:56 +0000 Subject: bpf: Fix kernel address leakage in atomic fetch The change in commit 37086bfdc737 ("bpf: Propagate stack bounds to registers in atomics w/ BPF_FETCH") around check_mem_access() handling is buggy since this would allow for unprivileged users to leak kernel pointers. For example, an atomic fetch/and with -1 on a stack destination which holds a spilled pointer will migrate the spilled register type into a scalar, which can then be exported out of the program (since scalar != pointer) by dumping it into a map value. The original implementation of XADD was preventing this situation by using a double call to check_mem_access() one with BPF_READ and a subsequent one with BPF_WRITE, in both cases passing -1 as a placeholder value instead of register as per XADD semantics since it didn't contain a value fetch. The BPF_READ also included a check in check_stack_read_fixed_off() which rejects the program if the stack slot is of __is_pointer_value() if dst_regno < 0. The latter is to distinguish whether we're dealing with a regular stack spill/ fill or some arithmetical operation which is disallowed on non-scalars, see also 6e7e63cbb023 ("bpf: Forbid XADD on spilled pointers for unprivileged users") for more context on check_mem_access() and its handling of placeholder value -1. One minimally intrusive option to fix the leak is for the BPF_FETCH case to initially check the BPF_READ case via check_mem_access() with -1 as register, followed by the actual load case with non-negative load_reg to propagate stack bounds to registers. Fixes: 37086bfdc737 ("bpf: Propagate stack bounds to registers in atomics w/ BPF_FETCH") Reported-by: Acked-by: Brendan Jackman Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f2f1ed34cfe9..53d39db3b0fa 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4584,13 +4584,19 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i load_reg = -1; } - /* check whether we can read the memory */ + /* Check whether we can read the memory, with second call for fetch + * case to simulate the register fill. + */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, - BPF_SIZE(insn->code), BPF_READ, load_reg, true); + BPF_SIZE(insn->code), BPF_READ, -1, true); + if (!err && load_reg >= 0) + err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, + BPF_SIZE(insn->code), BPF_READ, load_reg, + true); if (err) return err; - /* check whether we can write into the same memory */ + /* Check whether we can write into the same memory. */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, -1, true); if (err) -- cgit v1.2.3 From 180486b430f4e22cc00a478163d942804baae4b5 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 7 Dec 2021 10:07:04 +0000 Subject: bpf, selftests: Add test case for atomic fetch on spilled pointer Test whether unprivileged would be able to leak the spilled pointer either by exporting the returned value from the atomic{32,64} operation or by reading and exporting the value from the stack after the atomic operation took place. Note that for unprivileged, the below atomic cmpxchg test case named "Dest pointer in r0 - succeed" is failing. The reason is that in the dst memory location (r10 -8) there is the spilled register r10: 0: R1=ctx(id=0,off=0,imm=0) R10=fp0 0: (bf) r0 = r10 1: R0_w=fp0 R1=ctx(id=0,off=0,imm=0) R10=fp0 1: (7b) *(u64 *)(r10 -8) = r0 2: R0_w=fp0 R1=ctx(id=0,off=0,imm=0) R10=fp0 fp-8_w=fp 2: (b7) r1 = 0 3: R0_w=fp0 R1_w=invP0 R10=fp0 fp-8_w=fp 3: (db) r0 = atomic64_cmpxchg((u64 *)(r10 -8), r0, r1) 4: R0_w=fp0 R1_w=invP0 R10=fp0 fp-8_w=mmmmmmmm 4: (79) r1 = *(u64 *)(r0 -8) 5: R0_w=fp0 R1_w=invP(id=0) R10=fp0 fp-8_w=mmmmmmmm 5: (b7) r0 = 0 6: R0_w=invP0 R1_w=invP(id=0) R10=fp0 fp-8_w=mmmmmmmm 6: (95) exit However, allowing this case for unprivileged is a bit useless given an update with a new pointer will fail anyway: 0: R1=ctx(id=0,off=0,imm=0) R10=fp0 0: (bf) r0 = r10 1: R0_w=fp0 R1=ctx(id=0,off=0,imm=0) R10=fp0 1: (7b) *(u64 *)(r10 -8) = r0 2: R0_w=fp0 R1=ctx(id=0,off=0,imm=0) R10=fp0 fp-8_w=fp 2: (db) r0 = atomic64_cmpxchg((u64 *)(r10 -8), r0, r10) R10 leaks addr into mem Acked-by: Brendan Jackman Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/verifier/atomic_cmpxchg.c | 23 ++++++ .../testing/selftests/bpf/verifier/atomic_fetch.c | 94 ++++++++++++++++++++++ 2 files changed, 117 insertions(+) diff --git a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c index c22dc83a41fd..0ffc69f602af 100644 --- a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c +++ b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c @@ -156,4 +156,27 @@ BPF_EXIT_INSN(), }, .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "leaking pointer from stack off -8", +}, +{ + "Dest pointer in r0 - succeed, check 2", + .insns = { + /* r0 = &val */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_10), + /* val = r0; */ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + /* r5 = &val */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_10), + /* r0 = atomic_cmpxchg(&val, r0, r5); */ + BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, BPF_REG_10, BPF_REG_5, -8), + /* r1 = *r0 */ + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8), + /* exit(0); */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R5 leaks addr into mem", }, diff --git a/tools/testing/selftests/bpf/verifier/atomic_fetch.c b/tools/testing/selftests/bpf/verifier/atomic_fetch.c index 3bc9ff7a860b..5bf03fb4fa2b 100644 --- a/tools/testing/selftests/bpf/verifier/atomic_fetch.c +++ b/tools/testing/selftests/bpf/verifier/atomic_fetch.c @@ -1,3 +1,97 @@ +{ + "atomic dw/fetch and address leakage of (map ptr & -1) via stack slot", + .insns = { + BPF_LD_IMM64(BPF_REG_1, -1), + BPF_LD_MAP_FD(BPF_REG_8, 0), + BPF_LD_MAP_FD(BPF_REG_9, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_9, 0), + BPF_ATOMIC_OP(BPF_DW, BPF_AND | BPF_FETCH, BPF_REG_2, BPF_REG_1, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_2, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_8), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_9, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 2, 4 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "leaking pointer from stack off -8", +}, +{ + "atomic dw/fetch and address leakage of (map ptr & -1) via returned value", + .insns = { + BPF_LD_IMM64(BPF_REG_1, -1), + BPF_LD_MAP_FD(BPF_REG_8, 0), + BPF_LD_MAP_FD(BPF_REG_9, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_9, 0), + BPF_ATOMIC_OP(BPF_DW, BPF_AND | BPF_FETCH, BPF_REG_2, BPF_REG_1, 0), + BPF_MOV64_REG(BPF_REG_9, BPF_REG_1), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_8), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_9, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 2, 4 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "leaking pointer from stack off -8", +}, +{ + "atomic w/fetch and address leakage of (map ptr & -1) via stack slot", + .insns = { + BPF_LD_IMM64(BPF_REG_1, -1), + BPF_LD_MAP_FD(BPF_REG_8, 0), + BPF_LD_MAP_FD(BPF_REG_9, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_9, 0), + BPF_ATOMIC_OP(BPF_W, BPF_AND | BPF_FETCH, BPF_REG_2, BPF_REG_1, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_2, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_8), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_9, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 2, 4 }, + .result = REJECT, + .errstr = "invalid size of register fill", +}, +{ + "atomic w/fetch and address leakage of (map ptr & -1) via returned value", + .insns = { + BPF_LD_IMM64(BPF_REG_1, -1), + BPF_LD_MAP_FD(BPF_REG_8, 0), + BPF_LD_MAP_FD(BPF_REG_9, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_9, 0), + BPF_ATOMIC_OP(BPF_W, BPF_AND | BPF_FETCH, BPF_REG_2, BPF_REG_1, 0), + BPF_MOV64_REG(BPF_REG_9, BPF_REG_1), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_8), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_9, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 2, 4 }, + .result = REJECT, + .errstr = "invalid size of register fill", +}, #define __ATOMIC_FETCH_OP_TEST(src_reg, dst_reg, operand1, op, operand2, expect) \ { \ "atomic fetch " #op ", src=" #dst_reg " dst=" #dst_reg, \ -- cgit v1.2.3 From a82fe085f344ef20b452cd5f481010ff96b5c4cd Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 7 Dec 2021 11:02:02 +0000 Subject: bpf: Fix kernel address leakage in atomic cmpxchg's r0 aux reg The implementation of BPF_CMPXCHG on a high level has the following parameters: .-[old-val] .-[new-val] BPF_R0 = cmpxchg{32,64}(DST_REG + insn->off, BPF_R0, SRC_REG) `-[mem-loc] `-[old-val] Given a BPF insn can only have two registers (dst, src), the R0 is fixed and used as an auxilliary register for input (old value) as well as output (returning old value from memory location). While the verifier performs a number of safety checks, it misses to reject unprivileged programs where R0 contains a pointer as old value. Through brute-forcing it takes about ~16sec on my machine to leak a kernel pointer with BPF_CMPXCHG. The PoC is basically probing for kernel addresses by storing the guessed address into the map slot as a scalar, and using the map value pointer as R0 while SRC_REG has a canary value to detect a matching address. Fix it by checking R0 for pointers, and reject if that's the case for unprivileged programs. Fixes: 5ffa25502b5a ("bpf: Add instructions for atomic_[cmp]xchg") Reported-by: Ryota Shiga (Flatt Security) Acked-by: Brendan Jackman Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 53d39db3b0fa..2d48159b58bd 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4547,9 +4547,16 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i if (insn->imm == BPF_CMPXCHG) { /* Check comparison of R0 with memory location */ - err = check_reg_arg(env, BPF_REG_0, SRC_OP); + const u32 aux_reg = BPF_REG_0; + + err = check_reg_arg(env, aux_reg, SRC_OP); if (err) return err; + + if (is_pointer_value(env, aux_reg)) { + verbose(env, "R%d leaks addr into mem\n", aux_reg); + return -EACCES; + } } if (is_pointer_value(env, insn->src_reg)) { -- cgit v1.2.3 From e523102cb719cbad1673b6aa2a4d5c1fa6f13799 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 13 Dec 2021 22:25:23 +0000 Subject: bpf, selftests: Update test case for atomic cmpxchg on r0 with pointer Fix up unprivileged test case results for 'Dest pointer in r0' verifier tests given they now need to reject R0 containing a pointer value, and add a couple of new related ones with 32bit cmpxchg as well. root@foo:~/bpf/tools/testing/selftests/bpf# ./test_verifier #0/u invalid and of negative number OK #0/p invalid and of negative number OK [...] #1268/p XDP pkt read, pkt_meta' <= pkt_data, bad access 1 OK #1269/p XDP pkt read, pkt_meta' <= pkt_data, bad access 2 OK #1270/p XDP pkt read, pkt_data <= pkt_meta', good access OK #1271/p XDP pkt read, pkt_data <= pkt_meta', bad access 1 OK #1272/p XDP pkt read, pkt_data <= pkt_meta', bad access 2 OK Summary: 1900 PASSED, 0 SKIPPED, 0 FAILED Acked-by: Brendan Jackman Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/verifier/atomic_cmpxchg.c | 67 +++++++++++++++++++++- 1 file changed, 65 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c index 0ffc69f602af..b39665f33524 100644 --- a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c +++ b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c @@ -138,6 +138,8 @@ BPF_EXIT_INSN(), }, .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R0 leaks addr into mem", }, { "Dest pointer in r0 - succeed", @@ -157,7 +159,7 @@ }, .result = ACCEPT, .result_unpriv = REJECT, - .errstr_unpriv = "leaking pointer from stack off -8", + .errstr_unpriv = "R0 leaks addr into mem", }, { "Dest pointer in r0 - succeed, check 2", @@ -178,5 +180,66 @@ }, .result = ACCEPT, .result_unpriv = REJECT, - .errstr_unpriv = "R5 leaks addr into mem", + .errstr_unpriv = "R0 leaks addr into mem", +}, +{ + "Dest pointer in r0 - succeed, check 3", + .insns = { + /* r0 = &val */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_10), + /* val = r0; */ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + /* r5 = &val */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_10), + /* r0 = atomic_cmpxchg(&val, r0, r5); */ + BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, BPF_REG_10, BPF_REG_5, -8), + /* exit(0); */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid size of register fill", + .errstr_unpriv = "R0 leaks addr into mem", +}, +{ + "Dest pointer in r0 - succeed, check 4", + .insns = { + /* r0 = &val */ + BPF_MOV32_REG(BPF_REG_0, BPF_REG_10), + /* val = r0; */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -8), + /* r5 = &val */ + BPF_MOV32_REG(BPF_REG_5, BPF_REG_10), + /* r0 = atomic_cmpxchg(&val, r0, r5); */ + BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, BPF_REG_10, BPF_REG_5, -8), + /* r1 = *r10 */ + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, -8), + /* exit(0); */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R10 partial copy of pointer", +}, +{ + "Dest pointer in r0 - succeed, check 5", + .insns = { + /* r0 = &val */ + BPF_MOV32_REG(BPF_REG_0, BPF_REG_10), + /* val = r0; */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -8), + /* r5 = &val */ + BPF_MOV32_REG(BPF_REG_5, BPF_REG_10), + /* r0 = atomic_cmpxchg(&val, r0, r5); */ + BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, BPF_REG_10, BPF_REG_5, -8), + /* r1 = *r0 */ + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, -8), + /* exit(0); */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "R0 invalid mem access", + .errstr_unpriv = "R10 partial copy of pointer", }, -- cgit v1.2.3 From 651740a502411793327e2f0741104749c4eedcd1 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 13 Dec 2021 14:22:33 -0500 Subject: btrfs: check WRITE_ERR when trying to read an extent buffer Filipe reported a hang when we have errors on btrfs. This turned out to be a side-effect of my fix c2e39305299f01 ("btrfs: clear extent buffer uptodate when we fail to write it") which made it so we clear EXTENT_BUFFER_UPTODATE on an eb when we fail to write it out. Below is a paste of Filipe's analysis he got from using drgn to debug the hang """ btree readahead code calls read_extent_buffer_pages(), sets ->io_pages to a value while writeback of all pages has not yet completed: --> writeback for the first 3 pages finishes, we clear EXTENT_BUFFER_UPTODATE from eb on the first page when we get an error. --> at this point eb->io_pages is 1 and we cleared Uptodate bit from the first 3 pages --> read_extent_buffer_pages() does not see EXTENT_BUFFER_UPTODATE() so it continues, it's able to lock the pages since we obviously don't hold the pages locked during writeback --> read_extent_buffer_pages() then computes 'num_reads' as 3, and sets eb->io_pages to 3, since only the first page does not have Uptodate bit set at this point --> writeback for the remaining page completes, we ended decrementing eb->io_pages by 1, resulting in eb->io_pages == 2, and therefore never calling end_extent_buffer_writeback(), so EXTENT_BUFFER_WRITEBACK remains in the eb's flags --> of course, when the read bio completes, it doesn't and shouldn't call end_extent_buffer_writeback() --> we should clear EXTENT_BUFFER_UPTODATE only after all pages of the eb finished writeback? or maybe make the read pages code wait for writeback of all pages of the eb to complete before checking which pages need to be read, touch ->io_pages, submit read bio, etc writeback bit never cleared means we can hang when aborting a transaction, at: btrfs_cleanup_one_transaction() btrfs_destroy_marked_extents() wait_on_extent_buffer_writeback() """ This is a problem because our writes are not synchronized with reads in any way. We clear the UPTODATE flag and then we can easily come in and try to read the EB while we're still waiting on other bio's to complete. We have two options here, we could lock all the pages, and then check to see if eb->io_pages != 0 to know if we've already got an outstanding write on the eb. Or we can simply check to see if we have WRITE_ERR set on this extent buffer. We set this bit _before_ we clear UPTODATE, so if the read gets triggered because we aren't UPTODATE because of a write error we're guaranteed to have WRITE_ERR set, and in this case we can simply return -EIO. This will fix the reported hang. Reported-by: Filipe Manana Fixes: c2e39305299f01 ("btrfs: clear extent buffer uptodate when we fail to write it") CC: stable@vger.kernel.org # 5.4+ Reviewed-by: Filipe Manana Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/extent_io.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 3258b6f01e85..9234d96a7fd5 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -6611,6 +6611,14 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num) if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) return 0; + /* + * We could have had EXTENT_BUFFER_UPTODATE cleared by the write + * operation, which could potentially still be in flight. In this case + * we simply want to return an error. + */ + if (unlikely(test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags))) + return -EIO; + if (eb->fs_info->sectorsize < PAGE_SIZE) return read_extent_buffer_subpage(eb, wait, mirror_num); -- cgit v1.2.3 From 7a1636089acfee7562fe79aff7d1b4c57869896d Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 13 Dec 2021 08:45:12 +0000 Subject: btrfs: fix invalid delayed ref after subvolume creation failure When creating a subvolume, at ioctl.c:create_subvol(), if we fail to insert the new root's root item into the root tree, we are freeing the metadata extent we reserved for the new root to prevent a metadata extent leak, as we don't abort the transaction at that point (since there is nothing at that point that is irreversible). However we allocated the metadata extent for the new root which we are creating for the new subvolume, so its delayed reference refers to the ID of this new root. But when we free the metadata extent we pass the root of the subvolume where the new subvolume is located to btrfs_free_tree_block() - this is incorrect because this will generate a delayed reference that refers to the ID of the parent subvolume's root, and not to ID of the new root. This results in a failure when running delayed references that leads to a transaction abort and a trace like the following: [3868.738042] RIP: 0010:__btrfs_free_extent+0x709/0x950 [btrfs] [3868.739857] Code: 68 0f 85 e6 fb ff (...) [3868.742963] RSP: 0018:ffffb0e9045cf910 EFLAGS: 00010246 [3868.743908] RAX: 00000000fffffffe RBX: 00000000fffffffe RCX: 0000000000000002 [3868.745312] RDX: 00000000fffffffe RSI: 0000000000000002 RDI: ffff90b0cd793b88 [3868.746643] RBP: 000000000e5d8000 R08: 0000000000000000 R09: ffff90b0cd793b88 [3868.747979] R10: 0000000000000002 R11: 00014ded97944d68 R12: 0000000000000000 [3868.749373] R13: ffff90b09afe4a28 R14: 0000000000000000 R15: ffff90b0cd793b88 [3868.750725] FS: 00007f281c4a8b80(0000) GS:ffff90b3ada00000(0000) knlGS:0000000000000000 [3868.752275] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [3868.753515] CR2: 00007f281c6a5000 CR3: 0000000108a42006 CR4: 0000000000370ee0 [3868.754869] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [3868.756228] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [3868.757803] Call Trace: [3868.758281] [3868.758655] ? btrfs_merge_delayed_refs+0x178/0x1c0 [btrfs] [3868.759827] __btrfs_run_delayed_refs+0x2b1/0x1250 [btrfs] [3868.761047] btrfs_run_delayed_refs+0x86/0x210 [btrfs] [3868.762069] ? lock_acquired+0x19f/0x420 [3868.762829] btrfs_commit_transaction+0x69/0xb20 [btrfs] [3868.763860] ? _raw_spin_unlock+0x29/0x40 [3868.764614] ? btrfs_block_rsv_release+0x1c2/0x1e0 [btrfs] [3868.765870] create_subvol+0x1d8/0x9a0 [btrfs] [3868.766766] btrfs_mksubvol+0x447/0x4c0 [btrfs] [3868.767669] ? preempt_count_add+0x49/0xa0 [3868.768444] __btrfs_ioctl_snap_create+0x123/0x190 [btrfs] [3868.769639] ? _copy_from_user+0x66/0xa0 [3868.770391] btrfs_ioctl_snap_create_v2+0xbb/0x140 [btrfs] [3868.771495] btrfs_ioctl+0xd1e/0x35c0 [btrfs] [3868.772364] ? __slab_free+0x10a/0x360 [3868.773198] ? rcu_read_lock_sched_held+0x12/0x60 [3868.774121] ? lock_release+0x223/0x4a0 [3868.774863] ? lock_acquired+0x19f/0x420 [3868.775634] ? rcu_read_lock_sched_held+0x12/0x60 [3868.776530] ? trace_hardirqs_on+0x1b/0xe0 [3868.777373] ? _raw_spin_unlock_irqrestore+0x3e/0x60 [3868.778280] ? kmem_cache_free+0x321/0x3c0 [3868.779011] ? __x64_sys_ioctl+0x83/0xb0 [3868.779718] __x64_sys_ioctl+0x83/0xb0 [3868.780387] do_syscall_64+0x3b/0xc0 [3868.781059] entry_SYSCALL_64_after_hwframe+0x44/0xae [3868.781953] RIP: 0033:0x7f281c59e957 [3868.782585] Code: 3c 1c 48 f7 d8 4c (...) [3868.785867] RSP: 002b:00007ffe1f83e2b8 EFLAGS: 00000202 ORIG_RAX: 0000000000000010 [3868.787198] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f281c59e957 [3868.788450] RDX: 00007ffe1f83e2c0 RSI: 0000000050009418 RDI: 0000000000000003 [3868.789748] RBP: 00007ffe1f83f300 R08: 0000000000000000 R09: 00007ffe1f83fe36 [3868.791214] R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000000003 [3868.792468] R13: 0000000000000003 R14: 00007ffe1f83e2c0 R15: 00000000000003cc [3868.793765] [3868.794037] irq event stamp: 0 [3868.794548] hardirqs last enabled at (0): [<0000000000000000>] 0x0 [3868.795670] hardirqs last disabled at (0): [] copy_process+0x934/0x2040 [3868.797086] softirqs last enabled at (0): [] copy_process+0x934/0x2040 [3868.798309] softirqs last disabled at (0): [<0000000000000000>] 0x0 [3868.799284] ---[ end trace be24c7002fe27747 ]--- [3868.799928] BTRFS info (device dm-0): leaf 241188864 gen 1268 total ptrs 214 free space 469 owner 2 [3868.801133] BTRFS info (device dm-0): refs 2 lock_owner 225627 current 225627 [3868.802056] item 0 key (237436928 169 0) itemoff 16250 itemsize 33 [3868.802863] extent refs 1 gen 1265 flags 2 [3868.803447] ref#0: tree block backref root 1610 (...) [3869.064354] item 114 key (241008640 169 0) itemoff 12488 itemsize 33 [3869.065421] extent refs 1 gen 1268 flags 2 [3869.066115] ref#0: tree block backref root 1689 (...) [3869.403834] BTRFS error (device dm-0): unable to find ref byte nr 241008640 parent 0 root 1622 owner 0 offset 0 [3869.405641] BTRFS: error (device dm-0) in __btrfs_free_extent:3076: errno=-2 No such entry [3869.407138] BTRFS: error (device dm-0) in btrfs_run_delayed_refs:2159: errno=-2 No such entry Fix this by passing the new subvolume's root ID to btrfs_free_tree_block(). This requires changing the root argument of btrfs_free_tree_block() from struct btrfs_root * to a u64, since at this point during the subvolume creation we have not yet created the struct btrfs_root for the new subvolume, and btrfs_free_tree_block() only needs a root ID and nothing else from a struct btrfs_root. This was triggered by test case generic/475 from fstests. Fixes: 67addf29004c5b ("btrfs: fix metadata extent leak after failure to create subvolume") CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Nikolay Borisov Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/ctree.c | 17 +++++++++-------- fs/btrfs/ctree.h | 7 ++++++- fs/btrfs/extent-tree.c | 13 +++++++------ fs/btrfs/free-space-tree.c | 4 ++-- fs/btrfs/ioctl.c | 9 +++++---- fs/btrfs/qgroup.c | 3 ++- 6 files changed, 31 insertions(+), 22 deletions(-) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 74c8e18f3720..64599625c7d7 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -462,8 +462,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, BUG_ON(ret < 0); rcu_assign_pointer(root->node, cow); - btrfs_free_tree_block(trans, root, buf, parent_start, - last_ref); + btrfs_free_tree_block(trans, btrfs_root_id(root), buf, + parent_start, last_ref); free_extent_buffer(buf); add_root_to_dirty_list(root); } else { @@ -484,8 +484,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, return ret; } } - btrfs_free_tree_block(trans, root, buf, parent_start, - last_ref); + btrfs_free_tree_block(trans, btrfs_root_id(root), buf, + parent_start, last_ref); } if (unlock_orig) btrfs_tree_unlock(buf); @@ -926,7 +926,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, free_extent_buffer(mid); root_sub_used(root, mid->len); - btrfs_free_tree_block(trans, root, mid, 0, 1); + btrfs_free_tree_block(trans, btrfs_root_id(root), mid, 0, 1); /* once for the root ptr */ free_extent_buffer_stale(mid); return 0; @@ -985,7 +985,8 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, btrfs_tree_unlock(right); del_ptr(root, path, level + 1, pslot + 1); root_sub_used(root, right->len); - btrfs_free_tree_block(trans, root, right, 0, 1); + btrfs_free_tree_block(trans, btrfs_root_id(root), right, + 0, 1); free_extent_buffer_stale(right); right = NULL; } else { @@ -1030,7 +1031,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, btrfs_tree_unlock(mid); del_ptr(root, path, level + 1, pslot); root_sub_used(root, mid->len); - btrfs_free_tree_block(trans, root, mid, 0, 1); + btrfs_free_tree_block(trans, btrfs_root_id(root), mid, 0, 1); free_extent_buffer_stale(mid); mid = NULL; } else { @@ -4031,7 +4032,7 @@ static noinline void btrfs_del_leaf(struct btrfs_trans_handle *trans, root_sub_used(root, leaf->len); atomic_inc(&leaf->refs); - btrfs_free_tree_block(trans, root, leaf, 0, 1); + btrfs_free_tree_block(trans, btrfs_root_id(root), leaf, 0, 1); free_extent_buffer_stale(leaf); } /* diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 7553e9dc5f93..5fe5eccb3c87 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2257,6 +2257,11 @@ static inline bool btrfs_root_dead(const struct btrfs_root *root) return (root->root_item.flags & cpu_to_le64(BTRFS_ROOT_SUBVOL_DEAD)) != 0; } +static inline u64 btrfs_root_id(const struct btrfs_root *root) +{ + return root->root_key.objectid; +} + /* struct btrfs_root_backup */ BTRFS_SETGET_STACK_FUNCS(backup_tree_root, struct btrfs_root_backup, tree_root, 64); @@ -2719,7 +2724,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, u64 empty_size, enum btrfs_lock_nesting nest); void btrfs_free_tree_block(struct btrfs_trans_handle *trans, - struct btrfs_root *root, + u64 root_id, struct extent_buffer *buf, u64 parent, int last_ref); int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index fc4895e6a62c..25ef6e3fd306 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3275,20 +3275,20 @@ out_delayed_unlock: } void btrfs_free_tree_block(struct btrfs_trans_handle *trans, - struct btrfs_root *root, + u64 root_id, struct extent_buffer *buf, u64 parent, int last_ref) { - struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_ref generic_ref = { 0 }; int ret; btrfs_init_generic_ref(&generic_ref, BTRFS_DROP_DELAYED_REF, buf->start, buf->len, parent); btrfs_init_tree_ref(&generic_ref, btrfs_header_level(buf), - root->root_key.objectid, 0, false); + root_id, 0, false); - if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { + if (root_id != BTRFS_TREE_LOG_OBJECTID) { btrfs_ref_tree_mod(fs_info, &generic_ref); ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, NULL); BUG_ON(ret); /* -ENOMEM */ @@ -3298,7 +3298,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, struct btrfs_block_group *cache; bool must_pin = false; - if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { + if (root_id != BTRFS_TREE_LOG_OBJECTID) { ret = check_ref_cleanup(trans, buf->start); if (!ret) { btrfs_redirty_list_add(trans->transaction, buf); @@ -5472,7 +5472,8 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans, goto owner_mismatch; } - btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1); + btrfs_free_tree_block(trans, btrfs_root_id(root), eb, parent, + wc->refs[level] == 1); out: wc->refs[level] = 0; wc->flags[level] = 0; diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index a33bca94d133..3abec44c6255 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -1256,8 +1256,8 @@ int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info) btrfs_tree_lock(free_space_root->node); btrfs_clean_tree_block(free_space_root->node); btrfs_tree_unlock(free_space_root->node); - btrfs_free_tree_block(trans, free_space_root, free_space_root->node, - 0, 1); + btrfs_free_tree_block(trans, btrfs_root_id(free_space_root), + free_space_root->node, 0, 1); btrfs_put_root(free_space_root); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 1b85d98df66b..a7533416370a 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -617,11 +617,12 @@ static noinline int create_subvol(struct user_namespace *mnt_userns, * Since we don't abort the transaction in this case, free the * tree block so that we don't leak space and leave the * filesystem in an inconsistent state (an extent item in the - * extent tree without backreferences). Also no need to have - * the tree block locked since it is not in any tree at this - * point, so no other task can find it and use it. + * extent tree with a backreference for a root that does not + * exists). Also no need to have the tree block locked since it + * is not in any tree at this point, so no other task can find + * it and use it. */ - btrfs_free_tree_block(trans, root, leaf, 0, 1); + btrfs_free_tree_block(trans, objectid, leaf, 0, 1); free_extent_buffer(leaf); goto fail; } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index db680f5be745..6c037f1252b7 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1219,7 +1219,8 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) btrfs_tree_lock(quota_root->node); btrfs_clean_tree_block(quota_root->node); btrfs_tree_unlock(quota_root->node); - btrfs_free_tree_block(trans, quota_root, quota_root->node, 0, 1); + btrfs_free_tree_block(trans, btrfs_root_id(quota_root), + quota_root->node, 0, 1); btrfs_put_root(quota_root); -- cgit v1.2.3 From 212a58fda9b9077e0efc20200a4feb76afacfd95 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 13 Dec 2021 08:45:13 +0000 Subject: btrfs: fix warning when freeing leaf after subvolume creation failure When creating a subvolume, at ioctl.c:create_subvol(), if we fail to insert the root item for the new subvolume into the root tree, we can trigger the following warning: [78961.741046] WARNING: CPU: 0 PID: 4079814 at fs/btrfs/extent-tree.c:3357 btrfs_free_tree_block+0x2af/0x310 [btrfs] [78961.743344] Modules linked in: [78961.749440] dm_snapshot dm_thin_pool (...) [78961.773648] CPU: 0 PID: 4079814 Comm: fsstress Not tainted 5.16.0-rc4-btrfs-next-108 #1 [78961.775198] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [78961.777266] RIP: 0010:btrfs_free_tree_block+0x2af/0x310 [btrfs] [78961.778398] Code: 17 00 48 85 (...) [78961.781067] RSP: 0018:ffffaa4001657b28 EFLAGS: 00010202 [78961.781877] RAX: 0000000000000213 RBX: ffff897f8a796910 RCX: 0000000000000000 [78961.782780] RDX: 0000000000000000 RSI: 0000000011004000 RDI: 00000000ffffffff [78961.783764] RBP: ffff8981f490e800 R08: 0000000000000001 R09: 0000000000000000 [78961.784740] R10: 0000000000000000 R11: 0000000000000001 R12: ffff897fc963fcc8 [78961.785665] R13: 0000000000000001 R14: ffff898063548000 R15: ffff898063548000 [78961.786620] FS: 00007f31283c6b80(0000) GS:ffff8982ace00000(0000) knlGS:0000000000000000 [78961.787717] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [78961.788598] CR2: 00007f31285c3000 CR3: 000000023fcc8003 CR4: 0000000000370ef0 [78961.789568] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [78961.790585] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [78961.791684] Call Trace: [78961.792082] [78961.792359] create_subvol+0x5d1/0x9a0 [btrfs] [78961.793054] btrfs_mksubvol+0x447/0x4c0 [btrfs] [78961.794009] ? preempt_count_add+0x49/0xa0 [78961.794705] __btrfs_ioctl_snap_create+0x123/0x190 [btrfs] [78961.795712] ? _copy_from_user+0x66/0xa0 [78961.796382] btrfs_ioctl_snap_create_v2+0xbb/0x140 [btrfs] [78961.797392] btrfs_ioctl+0xd1e/0x35c0 [btrfs] [78961.798172] ? __slab_free+0x10a/0x360 [78961.798820] ? rcu_read_lock_sched_held+0x12/0x60 [78961.799664] ? lock_release+0x223/0x4a0 [78961.800321] ? lock_acquired+0x19f/0x420 [78961.800992] ? rcu_read_lock_sched_held+0x12/0x60 [78961.801796] ? trace_hardirqs_on+0x1b/0xe0 [78961.802495] ? _raw_spin_unlock_irqrestore+0x3e/0x60 [78961.803358] ? kmem_cache_free+0x321/0x3c0 [78961.804071] ? __x64_sys_ioctl+0x83/0xb0 [78961.804711] __x64_sys_ioctl+0x83/0xb0 [78961.805348] do_syscall_64+0x3b/0xc0 [78961.805969] entry_SYSCALL_64_after_hwframe+0x44/0xae [78961.806830] RIP: 0033:0x7f31284bc957 [78961.807517] Code: 3c 1c 48 f7 d8 (...) This is because we are calling btrfs_free_tree_block() on an extent buffer that is dirty. Fix that by cleaning the extent buffer, with btrfs_clean_tree_block(), before freeing it. This was triggered by test case generic/475 from fstests. Fixes: 67addf29004c5b ("btrfs: fix metadata extent leak after failure to create subvolume") CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Nikolay Borisov Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a7533416370a..8a442b59eee0 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -618,10 +618,11 @@ static noinline int create_subvol(struct user_namespace *mnt_userns, * tree block so that we don't leak space and leave the * filesystem in an inconsistent state (an extent item in the * extent tree with a backreference for a root that does not - * exists). Also no need to have the tree block locked since it - * is not in any tree at this point, so no other task can find - * it and use it. + * exists). */ + btrfs_tree_lock(leaf); + btrfs_clean_tree_block(leaf); + btrfs_tree_unlock(leaf); btrfs_free_tree_block(trans, objectid, leaf, 0, 1); free_extent_buffer(leaf); goto fail; -- cgit v1.2.3 From 4989d4a0aed3fb30f5b48787a689d7090de6f86d Mon Sep 17 00:00:00 2001 From: Shin'ichiro Kawasaki Date: Wed, 15 Dec 2021 19:38:43 +0900 Subject: btrfs: fix missing blkdev_put() call in btrfs_scan_one_device() The function btrfs_scan_one_device() calls blkdev_get_by_path() and blkdev_put() to get and release its target block device. However, when btrfs_sb_log_location_bdev() fails, blkdev_put() is not called and the block device is left without clean up. This triggered failure of fstests generic/085. Fix the failure path of btrfs_sb_log_location_bdev() to call blkdev_put(). Fixes: 12659251ca5df ("btrfs: implement log-structured superblock for ZONED mode") CC: stable@vger.kernel.org # 5.15+ Reviewed-by: Nikolay Borisov Signed-off-by: Shin'ichiro Kawasaki Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/volumes.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index cc80f2a97a0b..b4da58fd0e1a 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1370,8 +1370,10 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags, bytenr_orig = btrfs_sb_offset(0); ret = btrfs_sb_log_location_bdev(bdev, 0, READ, &bytenr); - if (ret) - return ERR_PTR(ret); + if (ret) { + device = ERR_PTR(ret); + goto error_bdev_put; + } disk_super = btrfs_read_disk_super(bdev, bytenr, bytenr_orig); if (IS_ERR(disk_super)) { -- cgit v1.2.3 From a7083763619f7485ccdade160deb81737cf2732f Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Fri, 10 Dec 2021 09:55:29 -0700 Subject: soc/tegra: fuse: Fix bitwise vs. logical OR warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A new warning in clang points out two instances where boolean expressions are being used with a bitwise OR instead of logical OR: drivers/soc/tegra/fuse/speedo-tegra20.c:72:9: warning: use of bitwise '|' with boolean operands [-Wbitwise-instead-of-logical] reg = tegra_fuse_read_spare(i) | ^~~~~~~~~~~~~~~~~~~~~~~~~~ || drivers/soc/tegra/fuse/speedo-tegra20.c:72:9: note: cast one or both operands to int to silence this warning drivers/soc/tegra/fuse/speedo-tegra20.c:87:9: warning: use of bitwise '|' with boolean operands [-Wbitwise-instead-of-logical] reg = tegra_fuse_read_spare(i) | ^~~~~~~~~~~~~~~~~~~~~~~~~~ || drivers/soc/tegra/fuse/speedo-tegra20.c:87:9: note: cast one or both operands to int to silence this warning 2 warnings generated. The motivation for the warning is that logical operations short circuit while bitwise operations do not. In this instance, tegra_fuse_read_spare() is not semantically returning a boolean, it is returning a bit value. Use u32 for its return type so that it can be used with either bitwise or boolean operators without any warnings. Fixes: 25cd5a391478 ("ARM: tegra: Add speedo-based process identification") Link: https://github.com/ClangBuiltLinux/linux/issues/1488 Suggested-by: MichaÅ‚ MirosÅ‚aw Signed-off-by: Nathan Chancellor Reviewed-by: Nick Desaulniers Signed-off-by: Thierry Reding --- drivers/soc/tegra/fuse/fuse-tegra.c | 2 +- drivers/soc/tegra/fuse/fuse.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/soc/tegra/fuse/fuse-tegra.c b/drivers/soc/tegra/fuse/fuse-tegra.c index f2151815db58..e714ed3b61bc 100644 --- a/drivers/soc/tegra/fuse/fuse-tegra.c +++ b/drivers/soc/tegra/fuse/fuse-tegra.c @@ -320,7 +320,7 @@ static struct platform_driver tegra_fuse_driver = { }; builtin_platform_driver(tegra_fuse_driver); -bool __init tegra_fuse_read_spare(unsigned int spare) +u32 __init tegra_fuse_read_spare(unsigned int spare) { unsigned int offset = fuse->soc->info->spare + spare * 4; diff --git a/drivers/soc/tegra/fuse/fuse.h b/drivers/soc/tegra/fuse/fuse.h index de58feba0435..ecff0c08e959 100644 --- a/drivers/soc/tegra/fuse/fuse.h +++ b/drivers/soc/tegra/fuse/fuse.h @@ -65,7 +65,7 @@ struct tegra_fuse { void tegra_init_revision(void); void tegra_init_apbmisc(void); -bool __init tegra_fuse_read_spare(unsigned int spare); +u32 __init tegra_fuse_read_spare(unsigned int spare); u32 __init tegra_fuse_read_early(unsigned int offset); u8 tegra_get_major_rev(void); -- cgit v1.2.3 From f08adf5add9a071160c68bb2a61d697f39ab0758 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 14 Dec 2021 19:46:21 +0100 Subject: USB: gadget: bRequestType is a bitfield, not a enum Szymon rightly pointed out that the previous check for the endpoint direction in bRequestType was not looking at only the bit involved, but rather the whole value. Normally this is ok, but for some request types, bits other than bit 8 could be set and the check for the endpoint length could not stall correctly. Fix that up by only checking the single bit. Fixes: 153a2d7e3350 ("USB: gadget: detect too-big endpoint 0 requests") Cc: Felipe Balbi Reported-by: Szymon Heidrich Link: https://lore.kernel.org/r/20211214184621.385828-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/composite.c | 6 +++--- drivers/usb/gadget/legacy/dbgp.c | 6 +++--- drivers/usb/gadget/legacy/inode.c | 6 +++--- 3 files changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index 284eea9f6e4d..3789c329183c 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -1680,14 +1680,14 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) u8 endp; if (w_length > USB_COMP_EP0_BUFSIZ) { - if (ctrl->bRequestType == USB_DIR_OUT) { - goto done; - } else { + if (ctrl->bRequestType & USB_DIR_IN) { /* Cast away the const, we are going to overwrite on purpose. */ __le16 *temp = (__le16 *)&ctrl->wLength; *temp = cpu_to_le16(USB_COMP_EP0_BUFSIZ); w_length = USB_COMP_EP0_BUFSIZ; + } else { + goto done; } } diff --git a/drivers/usb/gadget/legacy/dbgp.c b/drivers/usb/gadget/legacy/dbgp.c index 355bc7dab9d5..6bcbad382580 100644 --- a/drivers/usb/gadget/legacy/dbgp.c +++ b/drivers/usb/gadget/legacy/dbgp.c @@ -346,14 +346,14 @@ static int dbgp_setup(struct usb_gadget *gadget, u16 len = 0; if (length > DBGP_REQ_LEN) { - if (ctrl->bRequestType == USB_DIR_OUT) { - return err; - } else { + if (ctrl->bRequestType & USB_DIR_IN) { /* Cast away the const, we are going to overwrite on purpose. */ __le16 *temp = (__le16 *)&ctrl->wLength; *temp = cpu_to_le16(DBGP_REQ_LEN); length = DBGP_REQ_LEN; + } else { + return err; } } diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 63150e3889ef..3b58f4fc0a80 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -1334,14 +1334,14 @@ gadgetfs_setup (struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) u16 w_length = le16_to_cpu(ctrl->wLength); if (w_length > RBUF_SIZE) { - if (ctrl->bRequestType == USB_DIR_OUT) { - return value; - } else { + if (ctrl->bRequestType & USB_DIR_IN) { /* Cast away the const, we are going to overwrite on purpose. */ __le16 *temp = (__le16 *)&ctrl->wLength; *temp = cpu_to_le16(RBUF_SIZE); w_length = RBUF_SIZE; + } else { + return value; } } -- cgit v1.2.3 From fac6bf87c55f7f0733efb0375565fb6a50cf2caf Mon Sep 17 00:00:00 2001 From: Amelie Delaunay Date: Tue, 7 Dec 2021 13:45:10 +0100 Subject: usb: dwc2: fix STM ID/VBUS detection startup delay in dwc2_driver_probe When activate_stm_id_vb_detection is enabled, ID and Vbus detection relies on sensing comparators. This detection needs time to stabilize. A delay was already applied in dwc2_resume() when reactivating the detection, but it wasn't done in dwc2_probe(). This patch adds delay after enabling STM ID/VBUS detection. Then, ID state is good when initializing gadget and host, and avoid to get a wrong Connector ID Status Change interrupt. Fixes: a415083a11cc ("usb: dwc2: add support for STM32MP15 SoCs USB OTG HS and FS") Cc: stable Acked-by: Minas Harutyunyan Signed-off-by: Amelie Delaunay Link: https://lore.kernel.org/r/20211207124510.268841-1-amelie.delaunay@foss.st.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc2/platform.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c index c8f18f3ba9e3..c331a5128c2c 100644 --- a/drivers/usb/dwc2/platform.c +++ b/drivers/usb/dwc2/platform.c @@ -575,6 +575,9 @@ static int dwc2_driver_probe(struct platform_device *dev) ggpio |= GGPIO_STM32_OTG_GCCFG_IDEN; ggpio |= GGPIO_STM32_OTG_GCCFG_VBDEN; dwc2_writel(hsotg, ggpio, GGPIO); + + /* ID/VBUS detection startup time */ + usleep_range(5000, 7000); } retval = dwc2_drd_init(hsotg); -- cgit v1.2.3 From f4b3ee3c85551d2d343a3ba159304066523f730f Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Thu, 9 Dec 2021 11:46:07 -0500 Subject: audit: improve robustness of the audit queue handling If the audit daemon were ever to get stuck in a stopped state the kernel's kauditd_thread() could get blocked attempting to send audit records to the userspace audit daemon. With the kernel thread blocked it is possible that the audit queue could grow unbounded as certain audit record generating events must be exempt from the queue limits else the system enter a deadlock state. This patch resolves this problem by lowering the kernel thread's socket sending timeout from MAX_SCHEDULE_TIMEOUT to HZ/10 and tweaks the kauditd_send_queue() function to better manage the various audit queues when connection problems occur between the kernel and the audit daemon. With this patch, the backlog may temporarily grow beyond the defined limits when the audit daemon is stopped and the system is under heavy audit pressure, but kauditd_thread() will continue to make progress and drain the queues as it would for other connection problems. For example, with the audit daemon put into a stopped state and the system configured to audit every syscall it was still possible to shutdown the system without a kernel panic, deadlock, etc.; granted, the system was slow to shutdown but that is to be expected given the extreme pressure of recording every syscall. The timeout value of HZ/10 was chosen primarily through experimentation and this developer's "gut feeling". There is likely no one perfect value, but as this scenario is limited in scope (root privileges would be needed to send SIGSTOP to the audit daemon), it is likely not worth exposing this as a tunable at present. This can always be done at a later date if it proves necessary. Cc: stable@vger.kernel.org Fixes: 5b52330bbfe63 ("audit: fix auditd/kernel connection state tracking") Reported-by: Gaosheng Cui Tested-by: Gaosheng Cui Reviewed-by: Richard Guy Briggs Signed-off-by: Paul Moore --- kernel/audit.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) diff --git a/kernel/audit.c b/kernel/audit.c index 121d37e700a6..4cebadb5f30d 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -718,7 +718,7 @@ static int kauditd_send_queue(struct sock *sk, u32 portid, { int rc = 0; struct sk_buff *skb; - static unsigned int failed = 0; + unsigned int failed = 0; /* NOTE: kauditd_thread takes care of all our locking, we just use * the netlink info passed to us (e.g. sk and portid) */ @@ -735,32 +735,30 @@ static int kauditd_send_queue(struct sock *sk, u32 portid, continue; } +retry: /* grab an extra skb reference in case of error */ skb_get(skb); rc = netlink_unicast(sk, skb, portid, 0); if (rc < 0) { - /* fatal failure for our queue flush attempt? */ + /* send failed - try a few times unless fatal error */ if (++failed >= retry_limit || rc == -ECONNREFUSED || rc == -EPERM) { - /* yes - error processing for the queue */ sk = NULL; if (err_hook) (*err_hook)(skb); - if (!skb_hook) - goto out; - /* keep processing with the skb_hook */ + if (rc == -EAGAIN) + rc = 0; + /* continue to drain the queue */ continue; } else - /* no - requeue to preserve ordering */ - skb_queue_head(queue, skb); + goto retry; } else { - /* it worked - drop the extra reference and continue */ + /* skb sent - drop the extra reference and continue */ consume_skb(skb); failed = 0; } } -out: return (rc >= 0 ? 0 : rc); } @@ -1609,7 +1607,8 @@ static int __net_init audit_net_init(struct net *net) audit_panic("cannot initialize netlink socket in namespace"); return -ENOMEM; } - aunet->sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; + /* limit the timeout in case auditd is blocked/stopped */ + aunet->sk->sk_sndtimeo = HZ / 10; return 0; } -- cgit v1.2.3 From 584af82154f56e6b2740160fcc84a2966d969e15 Mon Sep 17 00:00:00 2001 From: Karen Sornek Date: Tue, 31 Aug 2021 13:16:35 +0200 Subject: igb: Fix removal of unicast MAC filters of VFs Move checking condition of VF MAC filter before clearing or adding MAC filter to VF to prevent potential blackout caused by removal of necessary and working VF's MAC filter. Fixes: 1b8b062a99dc ("igb: add VF trust infrastructure") Signed-off-by: Karen Sornek Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igb/igb_main.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index fd54d3ef890b..b597b8bfb910 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -7648,6 +7648,20 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf, struct vf_mac_filter *entry = NULL; int ret = 0; + if ((vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) && + !vf_data->trusted) { + dev_warn(&pdev->dev, + "VF %d requested MAC filter but is administratively denied\n", + vf); + return -EINVAL; + } + if (!is_valid_ether_addr(addr)) { + dev_warn(&pdev->dev, + "VF %d attempted to set invalid MAC filter\n", + vf); + return -EINVAL; + } + switch (info) { case E1000_VF_MAC_FILTER_CLR: /* remove all unicast MAC filters related to the current VF */ @@ -7661,20 +7675,6 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf, } break; case E1000_VF_MAC_FILTER_ADD: - if ((vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) && - !vf_data->trusted) { - dev_warn(&pdev->dev, - "VF %d requested MAC filter but is administratively denied\n", - vf); - return -EINVAL; - } - if (!is_valid_ether_addr(addr)) { - dev_warn(&pdev->dev, - "VF %d attempted to set invalid MAC filter\n", - vf); - return -EINVAL; - } - /* try to find empty slot in the list */ list_for_each(pos, &adapter->vf_macs.l) { entry = list_entry(pos, struct vf_mac_filter, l); -- cgit v1.2.3 From b6d335a60dc624c0d279333b22c737faa765b028 Mon Sep 17 00:00:00 2001 From: Letu Ren Date: Sat, 13 Nov 2021 11:42:34 +0800 Subject: igbvf: fix double free in `igbvf_probe` In `igbvf_probe`, if register_netdev() fails, the program will go to label err_hw_init, and then to label err_ioremap. In free_netdev() which is just below label err_ioremap, there is `list_for_each_entry_safe` and `netif_napi_del` which aims to delete all entries in `dev->napi_list`. The program has added an entry `adapter->rx_ring->napi` which is added by `netif_napi_add` in igbvf_alloc_queues(). However, adapter->rx_ring has been freed below label err_hw_init. So this a UAF. In terms of how to patch the problem, we can refer to igbvf_remove() and delete the entry before `adapter->rx_ring`. The KASAN logs are as follows: [ 35.126075] BUG: KASAN: use-after-free in free_netdev+0x1fd/0x450 [ 35.127170] Read of size 8 at addr ffff88810126d990 by task modprobe/366 [ 35.128360] [ 35.128643] CPU: 1 PID: 366 Comm: modprobe Not tainted 5.15.0-rc2+ #14 [ 35.129789] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 [ 35.131749] Call Trace: [ 35.132199] dump_stack_lvl+0x59/0x7b [ 35.132865] print_address_description+0x7c/0x3b0 [ 35.133707] ? free_netdev+0x1fd/0x450 [ 35.134378] __kasan_report+0x160/0x1c0 [ 35.135063] ? free_netdev+0x1fd/0x450 [ 35.135738] kasan_report+0x4b/0x70 [ 35.136367] free_netdev+0x1fd/0x450 [ 35.137006] igbvf_probe+0x121d/0x1a10 [igbvf] [ 35.137808] ? igbvf_vlan_rx_add_vid+0x100/0x100 [igbvf] [ 35.138751] local_pci_probe+0x13c/0x1f0 [ 35.139461] pci_device_probe+0x37e/0x6c0 [ 35.165526] [ 35.165806] Allocated by task 366: [ 35.166414] ____kasan_kmalloc+0xc4/0xf0 [ 35.167117] foo_kmem_cache_alloc_trace+0x3c/0x50 [igbvf] [ 35.168078] igbvf_probe+0x9c5/0x1a10 [igbvf] [ 35.168866] local_pci_probe+0x13c/0x1f0 [ 35.169565] pci_device_probe+0x37e/0x6c0 [ 35.179713] [ 35.179993] Freed by task 366: [ 35.180539] kasan_set_track+0x4c/0x80 [ 35.181211] kasan_set_free_info+0x1f/0x40 [ 35.181942] ____kasan_slab_free+0x103/0x140 [ 35.182703] kfree+0xe3/0x250 [ 35.183239] igbvf_probe+0x1173/0x1a10 [igbvf] [ 35.184040] local_pci_probe+0x13c/0x1f0 Fixes: d4e0fe01a38a0 (igbvf: add new driver to support 82576 virtual functions) Reported-by: Zheyu Ma Signed-off-by: Letu Ren Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igbvf/netdev.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 74ccd622251a..4d988da68394 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -2859,6 +2859,7 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; err_hw_init: + netif_napi_del(&adapter->rx_ring->napi); kfree(adapter->tx_ring); kfree(adapter->rx_ring); err_sw_init: -- cgit v1.2.3 From 0182d1f3fa640888a2ed7e3f6df2fdb10adee7c8 Mon Sep 17 00:00:00 2001 From: Sasha Neftin Date: Tue, 2 Nov 2021 09:20:06 +0200 Subject: igc: Fix typo in i225 LTR functions The LTR maximum value was incorrectly written using the scale from the LTR minimum value. This would cause incorrect values to be sent, in cases where the initial calculation lead to different min/max scales. Fixes: 707abf069548 ("igc: Add initial LTR support") Suggested-by: Dima Ruinskiy Signed-off-by: Sasha Neftin Tested-by: Nechama Kraus Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igc/igc_i225.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igc/igc_i225.c b/drivers/net/ethernet/intel/igc/igc_i225.c index b2ef9fde97b3..b6807e16eea9 100644 --- a/drivers/net/ethernet/intel/igc/igc_i225.c +++ b/drivers/net/ethernet/intel/igc/igc_i225.c @@ -636,7 +636,7 @@ s32 igc_set_ltr_i225(struct igc_hw *hw, bool link) ltrv = rd32(IGC_LTRMAXV); if (ltr_max != (ltrv & IGC_LTRMAXV_LTRV_MASK)) { ltrv = IGC_LTRMAXV_LSNP_REQ | ltr_max | - (scale_min << IGC_LTRMAXV_SCALE_SHIFT); + (scale_max << IGC_LTRMAXV_SCALE_SHIFT); wr32(IGC_LTRMAXV, ltrv); } } -- cgit v1.2.3 From 271225fd57c2f1e0b3f8826df51be6c634affefe Mon Sep 17 00:00:00 2001 From: Robert Schlabbach Date: Tue, 26 Oct 2021 02:24:48 +0200 Subject: ixgbe: Document how to enable NBASE-T support Commit a296d665eae1 ("ixgbe: Add ethtool support to enable 2.5 and 5.0 Gbps support") introduced suppression of the advertisement of NBASE-T speeds by default, according to Todd Fujinaka to accommodate customers with network switches which could not cope with advertised NBASE-T speeds, as posted in the E1000-devel mailing list: https://sourceforge.net/p/e1000/mailman/message/37106269/ However, the suppression was not documented at all, nor was how to enable NBASE-T support. Properly document the NBASE-T suppression and how to enable NBASE-T support. Fixes: a296d665eae1 ("ixgbe: Add ethtool support to enable 2.5 and 5.0 Gbps support") Reported-by: Robert Schlabbach Signed-off-by: Robert Schlabbach Signed-off-by: Tony Nguyen --- .../networking/device_drivers/ethernet/intel/ixgbe.rst | 16 ++++++++++++++++ drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 4 ++++ 2 files changed, 20 insertions(+) diff --git a/Documentation/networking/device_drivers/ethernet/intel/ixgbe.rst b/Documentation/networking/device_drivers/ethernet/intel/ixgbe.rst index f1d5233e5e51..0a233b17c664 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/ixgbe.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/ixgbe.rst @@ -440,6 +440,22 @@ NOTE: For 82599-based network connections, if you are enabling jumbo frames in a virtual function (VF), jumbo frames must first be enabled in the physical function (PF). The VF MTU setting cannot be larger than the PF MTU. +NBASE-T Support +--------------- +The ixgbe driver supports NBASE-T on some devices. However, the advertisement +of NBASE-T speeds is suppressed by default, to accommodate broken network +switches which cannot cope with advertised NBASE-T speeds. Use the ethtool +command to enable advertising NBASE-T speeds on devices which support it:: + + ethtool -s eth? advertise 0x1800000001028 + +On Linux systems with INTERFACES(5), this can be specified as a pre-up command +in /etc/network/interfaces so that the interface is always brought up with +NBASE-T support, e.g.:: + + iface eth? inet dhcp + pre-up ethtool -s eth? advertise 0x1800000001028 || true + Generic Receive Offload, aka GRO -------------------------------- The driver supports the in-kernel software implementation of GRO. GRO has diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 0f9f022260d7..45e2ec4d264d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -5531,6 +5531,10 @@ static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw) if (!speed && hw->mac.ops.get_link_capabilities) { ret = hw->mac.ops.get_link_capabilities(hw, &speed, &autoneg); + /* remove NBASE-T speeds from default autonegotiation + * to accommodate broken network switches in the field + * which cannot cope with advertised NBASE-T speeds + */ speed &= ~(IXGBE_LINK_SPEED_5GB_FULL | IXGBE_LINK_SPEED_2_5GB_FULL); } -- cgit v1.2.3 From 1cef171abd39102dcc862c6bfbf7f954f4f1f66f Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 15 Dec 2021 12:31:51 -0500 Subject: dm integrity: fix data corruption due to improper use of bvec_kmap_local Commit 25058d1c725c ("dm integrity: use bvec_kmap_local in __journal_read_write") didn't account for __journal_read_write() later adding the biovec's bv_offset. As such using bvec_kmap_local() caused the start of the biovec to be skipped. Trivial test that illustrates data corruption: # integritysetup format /dev/pmem0 # integritysetup open /dev/pmem0 integrityroot # mkfs.xfs /dev/mapper/integrityroot ... bad magic number bad magic number Metadata corruption detected at xfs_sb block 0x0/0x1000 libxfs_writebufr: write verifer failed on xfs_sb bno 0x0/0x1000 releasing dirty buffer (bulk) to free list! Fix this by using kmap_local_page() instead of bvec_kmap_local() in __journal_read_write(). Fixes: 25058d1c725c ("dm integrity: use bvec_kmap_local in __journal_read_write") Reported-by: Tony Asleson Reviewed-by: Heinz Mauelshagen Signed-off-by: Mike Snitzer --- drivers/md/dm-integrity.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 6319deccbe09..7af242de3202 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -1963,7 +1963,7 @@ static bool __journal_read_write(struct dm_integrity_io *dio, struct bio *bio, n_sectors -= bv.bv_len >> SECTOR_SHIFT; bio_advance_iter(bio, &bio->bi_iter, bv.bv_len); retry_kmap: - mem = bvec_kmap_local(&bv); + mem = kmap_local_page(bv.bv_page); if (likely(dio->op == REQ_OP_WRITE)) flush_dcache_page(bv.bv_page); -- cgit v1.2.3 From bf0a375055bd1afbbf02a0ef45f7655da7b71317 Mon Sep 17 00:00:00 2001 From: Cyril Novikov Date: Mon, 1 Nov 2021 18:39:36 -0700 Subject: ixgbe: set X550 MDIO speed before talking to PHY The MDIO bus speed must be initialized before talking to the PHY the first time in order to avoid talking to it using a speed that the PHY doesn't support. This fixes HW initialization error -17 (IXGBE_ERR_PHY_ADDR_INVALID) on Denverton CPUs (a.k.a. the Atom C3000 family) on ports with a 10Gb network plugged in. On those devices, HLREG0[MDCSPD] resets to 1, which combined with the 10Gb network results in a 24MHz MDIO speed, which is apparently too fast for the connected PHY. PHY register reads over MDIO bus return garbage, leading to initialization failure. Reproduced with Linux kernel 4.19 and 5.15-rc7. Can be reproduced using the following setup: * Use an Atom C3000 family system with at least one X552 LAN on the SoC * Disable PXE or other BIOS network initialization if possible (the interface must not be initialized before Linux boots) * Connect a live 10Gb Ethernet cable to an X550 port * Power cycle (not reset, doesn't always work) the system and boot Linux * Observe: ixgbe interfaces w/ 10GbE cables plugged in fail with error -17 Fixes: e84db7272798 ("ixgbe: Introduce function to control MDIO speed") Signed-off-by: Cyril Novikov Reviewed-by: Andrew Lunn Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 9724ffb16518..e4b50c7781ff 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -3405,6 +3405,9 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw) /* flush pending Tx transactions */ ixgbe_clear_tx_pending(hw); + /* set MDIO speed before talking to the PHY in case it's the 1st time */ + ixgbe_set_mdio_speed(hw); + /* PHY ops must be identified and initialized prior to reset */ status = hw->phy.ops.init(hw); if (status == IXGBE_ERR_SFP_NOT_SUPPORTED || -- cgit v1.2.3 From 1ee33b1ca2b8dabfcc17198ffd049a6b55674a86 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Wed, 15 Dec 2021 20:52:40 +0900 Subject: tty: n_hdlc: make n_hdlc_tty_wakeup() asynchronous syzbot is reporting that an unprivileged user who logged in from tty console can crash the system using a reproducer shown below [1], for n_hdlc_tty_wakeup() is synchronously calling n_hdlc_send_frames(). ---------- #include #include int main(int argc, char *argv[]) { const int disc = 0xd; ioctl(1, TIOCSETD, &disc); while (1) { ioctl(1, TCXONC, 0); write(1, "", 1); ioctl(1, TCXONC, 1); /* Kernel panic - not syncing: scheduling while atomic */ } } ---------- Linus suspected that "struct tty_ldisc"->ops->write_wakeup() must not sleep, and Jiri confirmed it from include/linux/tty_ldisc.h. Thus, defer n_hdlc_send_frames() from n_hdlc_tty_wakeup() to a WQ context like net/nfc/nci/uart.c does. Link: https://syzkaller.appspot.com/bug?extid=5f47a8cea6a12b77a876 [1] Reported-by: syzbot Cc: stable Analyzed-by: Fabio M. De Francesco Suggested-by: Linus Torvalds Confirmed-by: Jiri Slaby Reviewed-by: Fabio M. De Francesco Signed-off-by: Tetsuo Handa Link: https://lore.kernel.org/r/40de8b7e-a3be-4486-4e33-1b1d1da452f8@i-love.sakura.ne.jp Signed-off-by: Greg Kroah-Hartman --- drivers/tty/n_hdlc.c | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c index 7e0884ecc74f..23ba1fc99df8 100644 --- a/drivers/tty/n_hdlc.c +++ b/drivers/tty/n_hdlc.c @@ -140,6 +140,8 @@ struct n_hdlc { struct n_hdlc_buf_list rx_buf_list; struct n_hdlc_buf_list tx_free_buf_list; struct n_hdlc_buf_list rx_free_buf_list; + struct work_struct write_work; + struct tty_struct *tty_for_write_work; }; /* @@ -154,6 +156,7 @@ static struct n_hdlc_buf *n_hdlc_buf_get(struct n_hdlc_buf_list *list); /* Local functions */ static struct n_hdlc *n_hdlc_alloc(void); +static void n_hdlc_tty_write_work(struct work_struct *work); /* max frame size for memory allocations */ static int maxframe = 4096; @@ -210,6 +213,8 @@ static void n_hdlc_tty_close(struct tty_struct *tty) wake_up_interruptible(&tty->read_wait); wake_up_interruptible(&tty->write_wait); + cancel_work_sync(&n_hdlc->write_work); + n_hdlc_free_buf_list(&n_hdlc->rx_free_buf_list); n_hdlc_free_buf_list(&n_hdlc->tx_free_buf_list); n_hdlc_free_buf_list(&n_hdlc->rx_buf_list); @@ -241,6 +246,8 @@ static int n_hdlc_tty_open(struct tty_struct *tty) return -ENFILE; } + INIT_WORK(&n_hdlc->write_work, n_hdlc_tty_write_work); + n_hdlc->tty_for_write_work = tty; tty->disc_data = n_hdlc; tty->receive_room = 65536; @@ -334,6 +341,20 @@ check_again: goto check_again; } /* end of n_hdlc_send_frames() */ +/** + * n_hdlc_tty_write_work - Asynchronous callback for transmit wakeup + * @work: pointer to work_struct + * + * Called when low level device driver can accept more send data. + */ +static void n_hdlc_tty_write_work(struct work_struct *work) +{ + struct n_hdlc *n_hdlc = container_of(work, struct n_hdlc, write_work); + struct tty_struct *tty = n_hdlc->tty_for_write_work; + + n_hdlc_send_frames(n_hdlc, tty); +} /* end of n_hdlc_tty_write_work() */ + /** * n_hdlc_tty_wakeup - Callback for transmit wakeup * @tty: pointer to associated tty instance data @@ -344,7 +365,7 @@ static void n_hdlc_tty_wakeup(struct tty_struct *tty) { struct n_hdlc *n_hdlc = tty->disc_data; - n_hdlc_send_frames(n_hdlc, tty); + schedule_work(&n_hdlc->write_work); } /* end of n_hdlc_tty_wakeup() */ /** -- cgit v1.2.3 From 6c33ff728812aa18792afffaf2c9873b898e7512 Mon Sep 17 00:00:00 2001 From: "Ji-Ze Hong (Peter Hong)" Date: Wed, 15 Dec 2021 15:58:35 +0800 Subject: serial: 8250_fintek: Fix garbled text for console Commit fab8a02b73eb ("serial: 8250_fintek: Enable high speed mode on Fintek F81866") introduced support to use high baudrate with Fintek SuperIO UARTs. It'll change clocksources when the UART probed. But when user add kernel parameter "console=ttyS0,115200 console=tty0" to make the UART as console output, the console will output garbled text after the following kernel message. [ 3.681188] Serial: 8250/16550 driver, 32 ports, IRQ sharing enabled The issue is occurs in following step: probe_setup_port() -> fintek_8250_goto_highspeed() It change clocksource from 115200 to 921600 with wrong time, it should change clocksource in set_termios() not in probed. The following 3 patches are implemented change clocksource in fintek_8250_set_termios(). Commit 58178914ae5b ("serial: 8250_fintek: UART dynamic clocksource on Fintek F81216H") Commit 195638b6d44f ("serial: 8250_fintek: UART dynamic clocksource on Fintek F81866") Commit 423d9118c624 ("serial: 8250_fintek: Add F81966 Support") Due to the high baud rate had implemented above 3 patches and the patch Commit fab8a02b73eb ("serial: 8250_fintek: Enable high speed mode on Fintek F81866") is bugged, So this patch will remove it. Fixes: fab8a02b73eb ("serial: 8250_fintek: Enable high speed mode on Fintek F81866") Signed-off-by: Ji-Ze Hong (Peter Hong) Link: https://lore.kernel.org/r/20211215075835.2072-1-hpeter+linux_kernel@gmail.com Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_fintek.c | 20 -------------------- 1 file changed, 20 deletions(-) diff --git a/drivers/tty/serial/8250/8250_fintek.c b/drivers/tty/serial/8250/8250_fintek.c index 31c9e83ea3cb..251f0018ae8c 100644 --- a/drivers/tty/serial/8250/8250_fintek.c +++ b/drivers/tty/serial/8250/8250_fintek.c @@ -290,25 +290,6 @@ static void fintek_8250_set_max_fifo(struct fintek_8250 *pdata) } } -static void fintek_8250_goto_highspeed(struct uart_8250_port *uart, - struct fintek_8250 *pdata) -{ - sio_write_reg(pdata, LDN, pdata->index); - - switch (pdata->pid) { - case CHIP_ID_F81966: - case CHIP_ID_F81866: /* set uart clock for high speed serial mode */ - sio_write_mask_reg(pdata, F81866_UART_CLK, - F81866_UART_CLK_MASK, - F81866_UART_CLK_14_769MHZ); - - uart->port.uartclk = 921600 * 16; - break; - default: /* leave clock speed untouched */ - break; - } -} - static void fintek_8250_set_termios(struct uart_port *port, struct ktermios *termios, struct ktermios *old) @@ -430,7 +411,6 @@ static int probe_setup_port(struct fintek_8250 *pdata, fintek_8250_set_irq_mode(pdata, level_mode); fintek_8250_set_max_fifo(pdata); - fintek_8250_goto_highspeed(uart, pdata); fintek_8250_exit_key(addr[i]); -- cgit v1.2.3 From f886d4fbb7c97b8f5f447c92d2dab99c841803c0 Mon Sep 17 00:00:00 2001 From: Nehal Bakulchandra Shah Date: Wed, 15 Dec 2021 15:02:16 +0530 Subject: usb: xhci: Extend support for runtime power management for AMD's Yellow carp. AMD's Yellow Carp platform has few more XHCI controllers, enable the runtime power management support for the same. Signed-off-by: Nehal Bakulchandra Shah Cc: stable Link: https://lore.kernel.org/r/20211215093216.1839065-1-Nehal-Bakulchandra.shah@amd.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-pci.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 92adf6107864..3af017883231 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -71,6 +71,8 @@ #define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_4 0x161e #define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_5 0x15d6 #define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_6 0x15d7 +#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_7 0x161c +#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_8 0x161f #define PCI_DEVICE_ID_ASMEDIA_1042_XHCI 0x1042 #define PCI_DEVICE_ID_ASMEDIA_1042A_XHCI 0x1142 @@ -330,7 +332,9 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_3 || pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_4 || pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_5 || - pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_6)) + pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_6 || + pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_7 || + pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_8)) xhci->quirks |= XHCI_DEFAULT_PM_RUNTIME_ALLOW; if (xhci->quirks & XHCI_RESET_ON_RESUME) -- cgit v1.2.3 From 0ad3bd562bb91853b9f42bda145b5db6255aee90 Mon Sep 17 00:00:00 2001 From: Jimmy Wang Date: Tue, 14 Dec 2021 09:26:50 +0800 Subject: USB: NO_LPM quirk Lenovo USB-C to Ethernet Adapher(RTL8153-04) This device doesn't work well with LPM, losing connectivity intermittently. Disable LPM to resolve the issue. Reviewed-by: Signed-off-by: Jimmy Wang Cc: stable Link: https://lore.kernel.org/r/20211214012652.4898-1-wangjm221@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/quirks.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 019351c0b52c..d3c14b5ed4a1 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -434,6 +434,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x1532, 0x0116), .driver_info = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL }, + /* Lenovo USB-C to Ethernet Adapter RTL8153-04 */ + { USB_DEVICE(0x17ef, 0x720c), .driver_info = USB_QUIRK_NO_LPM }, + /* Lenovo Powered USB-C Travel Hub (4X90S92381, RTL8153 GigE) */ { USB_DEVICE(0x17ef, 0x721e), .driver_info = USB_QUIRK_NO_LPM }, -- cgit v1.2.3 From 4c4e162d9cf38528c4f13df09d5755cbc06f6c77 Mon Sep 17 00:00:00 2001 From: Pawel Laszczak Date: Tue, 14 Dec 2021 05:55:27 +0100 Subject: usb: cdnsp: Fix lack of spin_lock_irqsave/spin_lock_restore Patch puts content of cdnsp_gadget_pullup function inside spin_lock_irqsave and spin_lock_restore section. This construction is required here to keep the data consistency, otherwise some data can be changed e.g. from interrupt context. Fixes: 3d82904559f4 ("usb: cdnsp: cdns3 Add main part of Cadence USBSSP DRD Driver") Reported-by: Ken (Jian) He cc: Signed-off-by: Pawel Laszczak -- Changelog: v2: - added disable_irq/enable_irq as sugester by Peter Chen drivers/usb/cdns3/cdnsp-gadget.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) Reviewed-by: Peter Chen Link: https://lore.kernel.org/r/20211214045527.26823-1-pawell@gli-login.cadence.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/cdns3/cdnsp-gadget.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c index 27df0c697897..e85bf768c66d 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.c +++ b/drivers/usb/cdns3/cdnsp-gadget.c @@ -1541,15 +1541,27 @@ static int cdnsp_gadget_pullup(struct usb_gadget *gadget, int is_on) { struct cdnsp_device *pdev = gadget_to_cdnsp(gadget); struct cdns *cdns = dev_get_drvdata(pdev->dev); + unsigned long flags; trace_cdnsp_pullup(is_on); + /* + * Disable events handling while controller is being + * enabled/disabled. + */ + disable_irq(cdns->dev_irq); + spin_lock_irqsave(&pdev->lock, flags); + if (!is_on) { cdnsp_reset_device(pdev); cdns_clear_vbus(cdns); } else { cdns_set_vbus(cdns); } + + spin_unlock_irqrestore(&pdev->lock, flags); + enable_irq(cdns->dev_irq); + return 0; } -- cgit v1.2.3 From ca4d8344a72b91fb9d4c8bfbc22204b4c09c5d8f Mon Sep 17 00:00:00 2001 From: Xu Yang Date: Thu, 9 Dec 2021 18:15:07 +0800 Subject: usb: typec: tcpm: fix tcpm unregister port but leave a pending timer In current design, when the tcpm port is unregisterd, the kthread_worker will be destroyed in the last step. Inside the kthread_destroy_worker(), the worker will flush all the works and wait for them to end. However, if one of the works calls hrtimer_start(), this hrtimer will be pending until timeout even though tcpm port is removed. Once the hrtimer timeout, many strange kernel dumps appear. Thus, we can first complete kthread_destroy_worker(), then cancel all the hrtimers. This will guarantee that no hrtimer is pending at the end. Fixes: 3ed8e1c2ac99 ("usb: typec: tcpm: Migrate workqueue to RT priority for processing events") cc: Reviewed-by: Guenter Roeck Acked-by: Heikki Krogerus Signed-off-by: Xu Yang Link: https://lore.kernel.org/r/20211209101507.499096-1-xu.yang_2@nxp.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/tcpm.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 6010b9901126..59d4fa2443f2 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -324,6 +324,7 @@ struct tcpm_port { bool attached; bool connected; + bool registered; bool pd_supported; enum typec_port_type port_type; @@ -6291,7 +6292,8 @@ static enum hrtimer_restart state_machine_timer_handler(struct hrtimer *timer) { struct tcpm_port *port = container_of(timer, struct tcpm_port, state_machine_timer); - kthread_queue_work(port->wq, &port->state_machine); + if (port->registered) + kthread_queue_work(port->wq, &port->state_machine); return HRTIMER_NORESTART; } @@ -6299,7 +6301,8 @@ static enum hrtimer_restart vdm_state_machine_timer_handler(struct hrtimer *time { struct tcpm_port *port = container_of(timer, struct tcpm_port, vdm_state_machine_timer); - kthread_queue_work(port->wq, &port->vdm_state_machine); + if (port->registered) + kthread_queue_work(port->wq, &port->vdm_state_machine); return HRTIMER_NORESTART; } @@ -6307,7 +6310,8 @@ static enum hrtimer_restart enable_frs_timer_handler(struct hrtimer *timer) { struct tcpm_port *port = container_of(timer, struct tcpm_port, enable_frs_timer); - kthread_queue_work(port->wq, &port->enable_frs); + if (port->registered) + kthread_queue_work(port->wq, &port->enable_frs); return HRTIMER_NORESTART; } @@ -6315,7 +6319,8 @@ static enum hrtimer_restart send_discover_timer_handler(struct hrtimer *timer) { struct tcpm_port *port = container_of(timer, struct tcpm_port, send_discover_timer); - kthread_queue_work(port->wq, &port->send_discover_work); + if (port->registered) + kthread_queue_work(port->wq, &port->send_discover_work); return HRTIMER_NORESTART; } @@ -6403,6 +6408,7 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc) typec_port_register_altmodes(port->typec_port, &tcpm_altmode_ops, port, port->port_altmode, ALTMODE_DISCOVERY_MAX); + port->registered = true; mutex_lock(&port->lock); tcpm_init(port); @@ -6424,6 +6430,9 @@ void tcpm_unregister_port(struct tcpm_port *port) { int i; + port->registered = false; + kthread_destroy_worker(port->wq); + hrtimer_cancel(&port->send_discover_timer); hrtimer_cancel(&port->enable_frs_timer); hrtimer_cancel(&port->vdm_state_machine_timer); @@ -6435,7 +6444,6 @@ void tcpm_unregister_port(struct tcpm_port *port) typec_unregister_port(port->typec_port); usb_role_switch_put(port->role_sw); tcpm_debugfs_exit(port); - kthread_destroy_worker(port->wq); } EXPORT_SYMBOL_GPL(tcpm_unregister_port); -- cgit v1.2.3 From 972ce7e3801e790bb348bfe98be1ab65af15bacd Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Wed, 15 Dec 2021 12:58:31 +0200 Subject: dpaa2-eth: fix ethtool statistics Unfortunately, with the blamed commit I also added a side effect in the ethtool stats shown. Because I added two more fields in the per channel structure without verifying if its size is used in any way, part of the ethtool statistics were off by 2. Fix this by not looking up the size of the structure but instead on a fixed value kept in a macro. Fixes: fc398bec0387 ("net: dpaa2: add adaptive interrupt coalescing") Signed-off-by: Ioana Ciornei Link: https://lore.kernel.org/r/20211215105831.290070-1-ioana.ciornei@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h | 2 ++ drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h index 2085844227fe..e54e70ebdd05 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h @@ -388,6 +388,8 @@ struct dpaa2_eth_ch_stats { __u64 bytes_per_cdan; }; +#define DPAA2_ETH_CH_STATS 7 + /* Maximum number of queues associated with a DPNI */ #define DPAA2_ETH_MAX_TCS 8 #define DPAA2_ETH_MAX_RX_QUEUES_PER_TC 16 diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index adb8ce5306ee..3fdbf87dccb1 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c @@ -278,7 +278,7 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev, /* Per-channel stats */ for (k = 0; k < priv->num_channels; k++) { ch_stats = &priv->channel[k]->stats; - for (j = 0; j < sizeof(*ch_stats) / sizeof(__u64) - 1; j++) + for (j = 0; j < DPAA2_ETH_CH_STATS; j++) *((__u64 *)data + i + j) += *((__u64 *)ch_stats + j); } i += j; -- cgit v1.2.3 From 481221775d53d6215a6e5e9ce1cce6d2b4ab9a46 Mon Sep 17 00:00:00 2001 From: Haimin Zhang Date: Wed, 15 Dec 2021 19:15:30 +0800 Subject: netdevsim: Zero-initialize memory for new map's value in function nsim_bpf_map_alloc Zero-initialize memory for new map's value in function nsim_bpf_map_alloc since it may cause a potential kernel information leak issue, as follows: 1. nsim_bpf_map_alloc calls nsim_map_alloc_elem to allocate elements for a new map. 2. nsim_map_alloc_elem uses kmalloc to allocate map's value, but doesn't zero it. 3. A user application can use IOCTL BPF_MAP_LOOKUP_ELEM to get specific element's information in the map. 4. The kernel function map_lookup_elem will call bpf_map_copy_value to get the information allocated at step-2, then use copy_to_user to copy to the user buffer. This can only leak information for an array map. Fixes: 395cacb5f1a0 ("netdevsim: bpf: support fake map offload") Suggested-by: Jakub Kicinski Acked-by: Jakub Kicinski Signed-off-by: Haimin Zhang Link: https://lore.kernel.org/r/20211215111530.72103-1-tcs.kernel@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/netdevsim/bpf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index 90aafb56f140..a43820212932 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -514,6 +514,7 @@ nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap) goto err_free; key = nmap->entry[i].key; *key = i; + memset(nmap->entry[i].value, 0, offmap->map.value_size); } } -- cgit v1.2.3 From ec6af094ea28f0f2dda1a6a33b14cd57e36a9755 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Wed, 15 Dec 2021 09:39:37 -0500 Subject: net/packet: rx_owner_map depends on pg_vec Packet sockets may switch ring versions. Avoid misinterpreting state between versions, whose fields share a union. rx_owner_map is only allocated with a packet ring (pg_vec) and both are swapped together. If pg_vec is NULL, meaning no packet ring was allocated, then neither was rx_owner_map. And the field may be old state from a tpacket_v3. Fixes: 61fad6816fc1 ("net/packet: tpacket_rcv: avoid a producer race condition") Reported-by: Syzbot Signed-off-by: Willem de Bruijn Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20211215143937.106178-1-willemdebruijn.kernel@gmail.com Signed-off-by: Jakub Kicinski --- net/packet/af_packet.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 46943a18a10d..76c2dca7f0a5 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -4492,9 +4492,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, } out_free_pg_vec: - bitmap_free(rx_owner_map); - if (pg_vec) + if (pg_vec) { + bitmap_free(rx_owner_map); free_pg_vec(pg_vec, order, req->tp_block_nr); + } out: return err; } -- cgit v1.2.3 From ef8a0f6eab1ca5d1a75c242c5c7b9d386735fa0a Mon Sep 17 00:00:00 2001 From: Greg Jesionowski Date: Tue, 14 Dec 2021 15:10:27 -0700 Subject: net: usb: lan78xx: add Allied Telesis AT29M2-AF This adds the vendor and product IDs for the AT29M2-AF which is a lan7801-based device. Signed-off-by: Greg Jesionowski Link: https://lore.kernel.org/r/20211214221027.305784-1-jesionowskigreg@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/usb/lan78xx.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 8cd265fc1fd9..075f8abde5cd 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -76,6 +76,8 @@ #define LAN7801_USB_PRODUCT_ID (0x7801) #define LAN78XX_EEPROM_MAGIC (0x78A5) #define LAN78XX_OTP_MAGIC (0x78F3) +#define AT29M2AF_USB_VENDOR_ID (0x07C9) +#define AT29M2AF_USB_PRODUCT_ID (0x0012) #define MII_READ 1 #define MII_WRITE 0 @@ -4734,6 +4736,10 @@ static const struct usb_device_id products[] = { /* LAN7801 USB Gigabit Ethernet Device */ USB_DEVICE(LAN78XX_USB_VENDOR_ID, LAN7801_USB_PRODUCT_ID), }, + { + /* ATM2-AF USB Gigabit Ethernet Device */ + USB_DEVICE(AT29M2AF_USB_VENDOR_ID, AT29M2AF_USB_PRODUCT_ID), + }, {}, }; MODULE_DEVICE_TABLE(usb, products); -- cgit v1.2.3 From 0546b224cc7717cc8a2db076b0bb069a9c430794 Mon Sep 17 00:00:00 2001 From: John Keeping Date: Tue, 14 Dec 2021 19:10:09 +0000 Subject: net: stmmac: dwmac-rk: fix oob read in rk_gmac_setup KASAN reports an out-of-bounds read in rk_gmac_setup on the line: while (ops->regs[i]) { This happens for most platforms since the regs flexible array member is empty, so the memory after the ops structure is being read here. It seems that mostly this happens to contain zero anyway, so we get lucky and everything still works. To avoid adding redundant data to nearly all the ops structures, add a new flag to indicate whether the regs field is valid and avoid this loop when it is not. Fixes: 3bb3d6b1c195 ("net: stmmac: Add RK3566/RK3568 SoC support") Signed-off-by: John Keeping Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 6924a6aacbd5..c469abc91fa1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -33,6 +33,7 @@ struct rk_gmac_ops { void (*set_rgmii_speed)(struct rk_priv_data *bsp_priv, int speed); void (*set_rmii_speed)(struct rk_priv_data *bsp_priv, int speed); void (*integrated_phy_powerup)(struct rk_priv_data *bsp_priv); + bool regs_valid; u32 regs[]; }; @@ -1092,6 +1093,7 @@ static const struct rk_gmac_ops rk3568_ops = { .set_to_rmii = rk3568_set_to_rmii, .set_rgmii_speed = rk3568_set_gmac_speed, .set_rmii_speed = rk3568_set_gmac_speed, + .regs_valid = true, .regs = { 0xfe2a0000, /* gmac0 */ 0xfe010000, /* gmac1 */ @@ -1383,7 +1385,7 @@ static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev, * to be distinguished. */ res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (res) { + if (res && ops->regs_valid) { int i = 0; while (ops->regs[i]) { -- cgit v1.2.3 From 407ecd1bd726f240123f704620d46e285ff30dd9 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Wed, 15 Dec 2021 22:37:31 +0800 Subject: sfc_ef100: potential dereference of null pointer The return value of kmalloc() needs to be checked. To avoid use in efx_nic_update_stats() in case of the failure of alloc. Fixes: b593b6f1b492 ("sfc_ef100: statistics gathering") Signed-off-by: Jiasheng Jiang Reported-by: kernel test robot Signed-off-by: David S. Miller --- drivers/net/ethernet/sfc/ef100_nic.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/sfc/ef100_nic.c b/drivers/net/ethernet/sfc/ef100_nic.c index 6aa81229b68a..e77a5cb4e40d 100644 --- a/drivers/net/ethernet/sfc/ef100_nic.c +++ b/drivers/net/ethernet/sfc/ef100_nic.c @@ -609,6 +609,9 @@ static size_t ef100_update_stats(struct efx_nic *efx, ef100_common_stat_mask(mask); ef100_ethtool_stat_mask(mask); + if (!mc_stats) + return 0; + efx_nic_copy_stats(efx, mc_stats); efx_nic_update_stats(ef100_stat_desc, EF100_STAT_COUNT, mask, stats, mc_stats, false); -- cgit v1.2.3 From e08cdf63049b711099efff0811273449083bb958 Mon Sep 17 00:00:00 2001 From: Andrey Eremeev Date: Wed, 15 Dec 2021 20:30:32 +0300 Subject: dsa: mv88e6xxx: fix debug print for SPEED_UNFORCED Debug print uses invalid check to detect if speed is unforced: (speed != SPEED_UNFORCED) should be used instead of (!speed). Found by Linux Verification Center (linuxtesting.org) with SVACE. Signed-off-by: Andrey Eremeev Fixes: 96a2b40c7bd3 ("net: dsa: mv88e6xxx: add port's MAC speed setter") Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/port.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index d9817b20ea64..ab41619a809b 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -283,7 +283,7 @@ static int mv88e6xxx_port_set_speed_duplex(struct mv88e6xxx_chip *chip, if (err) return err; - if (speed) + if (speed != SPEED_UNFORCED) dev_dbg(chip->dev, "p%d: Speed set to %d Mbps\n", port, speed); else dev_dbg(chip->dev, "p%d: Speed unforced\n", port); @@ -516,7 +516,7 @@ int mv88e6393x_port_set_speed_duplex(struct mv88e6xxx_chip *chip, int port, if (err) return err; - if (speed) + if (speed != SPEED_UNFORCED) dev_dbg(chip->dev, "p%d: Speed set to %d Mbps\n", port, speed); else dev_dbg(chip->dev, "p%d: Speed unforced\n", port); -- cgit v1.2.3 From 053c9e18c6f9cf82242ef35ac21cae1842725714 Mon Sep 17 00:00:00 2001 From: Wenliang Wang Date: Thu, 16 Dec 2021 11:11:35 +0800 Subject: virtio_net: fix rx_drops stat for small pkts We found the stat of rx drops for small pkts does not increment when build_skb fail, it's not coherent with other mode's rx drops stat. Signed-off-by: Wenliang Wang Acked-by: Jason Wang Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 55db6a336f7e..b107835242ad 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -733,7 +733,7 @@ static struct sk_buff *receive_small(struct net_device *dev, pr_debug("%s: rx error: len %u exceeds max size %d\n", dev->name, len, GOOD_PACKET_LEN); dev->stats.rx_length_errors++; - goto err_len; + goto err; } if (likely(!vi->xdp_enabled)) { @@ -825,10 +825,8 @@ static struct sk_buff *receive_small(struct net_device *dev, skip_xdp: skb = build_skb(buf, buflen); - if (!skb) { - put_page(page); + if (!skb) goto err; - } skb_reserve(skb, headroom - delta); skb_put(skb, len); if (!xdp_prog) { @@ -839,13 +837,12 @@ skip_xdp: if (metasize) skb_metadata_set(skb, metasize); -err: return skb; err_xdp: rcu_read_unlock(); stats->xdp_drops++; -err_len: +err: stats->drops++; put_page(page); xdp_xmit: -- cgit v1.2.3 From 8a03ef676ade55182f9b05115763aeda6dc08159 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Thu, 16 Dec 2021 11:28:25 +0200 Subject: net: Fix double 0x prefix print in SKB dump When printing netdev features %pNF already takes care of the 0x prefix, remove the explicit one. Fixes: 6413139dfc64 ("skbuff: increase verbosity when dumping skb data") Signed-off-by: Gal Pressman Signed-off-by: David S. Miller --- net/core/skbuff.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index ba2f38246f07..909db87d7383 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -832,7 +832,7 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) ntohs(skb->protocol), skb->pkt_type, skb->skb_iif); if (dev) - printk("%sdev name=%s feat=0x%pNF\n", + printk("%sdev name=%s feat=%pNF\n", level, dev->name, &dev->features); if (sk) printk("%ssk family=%hu type=%u proto=%u\n", -- cgit v1.2.3 From 5c15b3123f65f8fbb1b445d9a7e8812e0e435df2 Mon Sep 17 00:00:00 2001 From: "D. Wythe" Date: Wed, 15 Dec 2021 20:29:21 +0800 Subject: net/smc: Prevent smc_release() from long blocking MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In nginx/wrk benchmark, there's a hung problem with high probability on case likes that: (client will last several minutes to exit) server: smc_run nginx client: smc_run wrk -c 10000 -t 1 http://server Client hangs with the following backtrace: 0 [ffffa7ce8Of3bbf8] __schedule at ffffffff9f9eOd5f 1 [ffffa7ce8Of3bc88] schedule at ffffffff9f9eløe6 2 [ffffa7ce8Of3bcaO] schedule_timeout at ffffffff9f9e3f3c 3 [ffffa7ce8Of3bd2O] wait_for_common at ffffffff9f9el9de 4 [ffffa7ce8Of3bd8O] __flush_work at ffffffff9fOfeOl3 5 [ffffa7ce8øf3bdfO] smc_release at ffffffffcO697d24 [smc] 6 [ffffa7ce8Of3be2O] __sock_release at ffffffff9f8O2e2d 7 [ffffa7ce8Of3be4ø] sock_close at ffffffff9f8ø2ebl 8 [ffffa7ce8øf3be48] __fput at ffffffff9f334f93 9 [ffffa7ce8Of3be78] task_work_run at ffffffff9flOlff5 10 [ffffa7ce8Of3beaO] do_exit at ffffffff9fOe5Ol2 11 [ffffa7ce8Of3bflO] do_group_exit at ffffffff9fOe592a 12 [ffffa7ce8Of3bf38] __x64_sys_exit_group at ffffffff9fOe5994 13 [ffffa7ce8Of3bf4O] do_syscall_64 at ffffffff9f9d4373 14 [ffffa7ce8Of3bfsO] entry_SYSCALL_64_after_hwframe at ffffffff9fa0007c This issue dues to flush_work(), which is used to wait for smc_connect_work() to finish in smc_release(). Once lots of smc_connect_work() was pending or all executing work dangling, smc_release() has to block until one worker comes to free, which is equivalent to wait another smc_connnect_work() to finish. In order to fix this, There are two changes: 1. For those idle smc_connect_work(), cancel it from the workqueue; for executing smc_connect_work(), waiting for it to finish. For that purpose, replace flush_work() with cancel_work_sync(). 2. Since smc_connect() hold a reference for passive closing, if smc_connect_work() has been cancelled, release the reference. Fixes: 24ac3a08e658 ("net/smc: rebuild nonblocking connect") Reported-by: Tony Lu Tested-by: Dust Li Reviewed-by: Dust Li Reviewed-by: Tony Lu Signed-off-by: D. Wythe Acked-by: Karsten Graul Link: https://lore.kernel.org/r/1639571361-101128-1-git-send-email-alibuda@linux.alibaba.com Signed-off-by: Jakub Kicinski --- net/smc/af_smc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 230072f9ec48..1c9289f56dc4 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -194,7 +194,9 @@ static int smc_release(struct socket *sock) /* cleanup for a dangling non-blocking connect */ if (smc->connect_nonblock && sk->sk_state == SMC_INIT) tcp_abort(smc->clcsock->sk, ECONNABORTED); - flush_work(&smc->connect_work); + + if (cancel_work_sync(&smc->connect_work)) + sock_put(&smc->sk); /* sock_hold in smc_connect for passive closing */ if (sk->sk_state == SMC_LISTEN) /* smc_close_non_accepted() is called and acquires -- cgit v1.2.3 From 8b8e6e782456f1ce02a7ae914bbd5b1053f0b034 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 15 Dec 2021 12:24:49 -0800 Subject: net: systemport: Add global locking for descriptor lifecycle The descriptor list is a shared resource across all of the transmit queues, and the locking mechanism used today only protects concurrency across a given transmit queue between the transmit and reclaiming. This creates an opportunity for the SYSTEMPORT hardware to work on corrupted descriptors if we have multiple producers at once which is the case when using multiple transmit queues. This was particularly noticeable when using multiple flows/transmit queues and it showed up in interesting ways in that UDP packets would get a correct UDP header checksum being calculated over an incorrect packet length. Similarly TCP packets would get an equally correct checksum computed by the hardware over an incorrect packet length. The SYSTEMPORT hardware maintains an internal descriptor list that it re-arranges when the driver produces a new descriptor anytime it writes to the WRITE_PORT_{HI,LO} registers, there is however some delay in the hardware to re-organize its descriptors and it is possible that concurrent TX queues eventually break this internal allocation scheme to the point where the length/status part of the descriptor gets used for an incorrect data buffer. The fix is to impose a global serialization for all TX queues in the short section where we are writing to the WRITE_PORT_{HI,LO} registers which solves the corruption even with multiple concurrent TX queues being used. Fixes: 80105befdb4b ("net: systemport: add Broadcom SYSTEMPORT Ethernet MAC driver") Signed-off-by: Florian Fainelli Link: https://lore.kernel.org/r/20211215202450.4086240-1-f.fainelli@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bcmsysport.c | 5 ++++- drivers/net/ethernet/broadcom/bcmsysport.h | 1 + 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 40933bf5a710..60dde29974bf 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1309,11 +1309,11 @@ static netdev_tx_t bcm_sysport_xmit(struct sk_buff *skb, struct bcm_sysport_priv *priv = netdev_priv(dev); struct device *kdev = &priv->pdev->dev; struct bcm_sysport_tx_ring *ring; + unsigned long flags, desc_flags; struct bcm_sysport_cb *cb; struct netdev_queue *txq; u32 len_status, addr_lo; unsigned int skb_len; - unsigned long flags; dma_addr_t mapping; u16 queue; int ret; @@ -1373,8 +1373,10 @@ static netdev_tx_t bcm_sysport_xmit(struct sk_buff *skb, ring->desc_count--; /* Ports are latched, so write upper address first */ + spin_lock_irqsave(&priv->desc_lock, desc_flags); tdma_writel(priv, len_status, TDMA_WRITE_PORT_HI(ring->index)); tdma_writel(priv, addr_lo, TDMA_WRITE_PORT_LO(ring->index)); + spin_unlock_irqrestore(&priv->desc_lock, desc_flags); /* Check ring space and update SW control flow */ if (ring->desc_count == 0) @@ -2013,6 +2015,7 @@ static int bcm_sysport_open(struct net_device *dev) } /* Initialize both hardware and software ring */ + spin_lock_init(&priv->desc_lock); for (i = 0; i < dev->num_tx_queues; i++) { ret = bcm_sysport_init_tx_ring(priv, i); if (ret) { diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h index 984f76e74b43..16b73bb9acc7 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.h +++ b/drivers/net/ethernet/broadcom/bcmsysport.h @@ -711,6 +711,7 @@ struct bcm_sysport_priv { int wol_irq; /* Transmit rings */ + spinlock_t desc_lock; struct bcm_sysport_tx_ring *tx_rings; /* Receive queue */ -- cgit v1.2.3 From e28587cc491ef0f3c51258fdc87fbc386b1d4c59 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Dec 2021 03:17:41 -0800 Subject: sit: do not call ipip6_dev_free() from sit_init_net() ipip6_dev_free is sit dev->priv_destructor, already called by register_netdevice() if something goes wrong. Alternative would be to make ipip6_dev_free() robust against multiple invocations, but other drivers do not implement this strategy. syzbot reported: dst_release underflow WARNING: CPU: 0 PID: 5059 at net/core/dst.c:173 dst_release+0xd8/0xe0 net/core/dst.c:173 Modules linked in: CPU: 1 PID: 5059 Comm: syz-executor.4 Not tainted 5.16.0-rc5-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:dst_release+0xd8/0xe0 net/core/dst.c:173 Code: 4c 89 f2 89 d9 31 c0 5b 41 5e 5d e9 da d5 44 f9 e8 1d 90 5f f9 c6 05 87 48 c6 05 01 48 c7 c7 80 44 99 8b 31 c0 e8 e8 67 29 f9 <0f> 0b eb 85 0f 1f 40 00 53 48 89 fb e8 f7 8f 5f f9 48 83 c3 a8 48 RSP: 0018:ffffc9000aa5faa0 EFLAGS: 00010246 RAX: d6894a925dd15a00 RBX: 00000000ffffffff RCX: 0000000000040000 RDX: ffffc90005e19000 RSI: 000000000003ffff RDI: 0000000000040000 RBP: 0000000000000000 R08: ffffffff816a1f42 R09: ffffed1017344f2c R10: ffffed1017344f2c R11: 0000000000000000 R12: 0000607f462b1358 R13: 1ffffffff1bfd305 R14: ffffe8ffffcb1358 R15: dffffc0000000000 FS: 00007f66c71a2700(0000) GS:ffff8880b9a00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f88aaed5058 CR3: 0000000023e0f000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: dst_cache_destroy+0x107/0x1e0 net/core/dst_cache.c:160 ipip6_dev_free net/ipv6/sit.c:1414 [inline] sit_init_net+0x229/0x550 net/ipv6/sit.c:1936 ops_init+0x313/0x430 net/core/net_namespace.c:140 setup_net+0x35b/0x9d0 net/core/net_namespace.c:326 copy_net_ns+0x359/0x5c0 net/core/net_namespace.c:470 create_new_namespaces+0x4ce/0xa00 kernel/nsproxy.c:110 unshare_nsproxy_namespaces+0x11e/0x180 kernel/nsproxy.c:226 ksys_unshare+0x57d/0xb50 kernel/fork.c:3075 __do_sys_unshare kernel/fork.c:3146 [inline] __se_sys_unshare kernel/fork.c:3144 [inline] __x64_sys_unshare+0x34/0x40 kernel/fork.c:3144 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f66c882ce99 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f66c71a2168 EFLAGS: 00000246 ORIG_RAX: 0000000000000110 RAX: ffffffffffffffda RBX: 00007f66c893ff60 RCX: 00007f66c882ce99 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000048040200 RBP: 00007f66c8886ff1 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fff6634832f R14: 00007f66c71a2300 R15: 0000000000022000 Fixes: cf124db566e6 ("net: Fix inconsistent teardown and release of private netdev state.") Signed-off-by: Eric Dumazet Reported-by: syzbot Link: https://lore.kernel.org/r/20211216111741.1387540-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- net/ipv6/sit.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 1b57ee36d668..8a3618a30632 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1933,7 +1933,6 @@ static int __net_init sit_init_net(struct net *net) return 0; err_reg_dev: - ipip6_dev_free(sitn->fb_tunnel_dev); free_netdev(sitn->fb_tunnel_dev); err_alloc_dev: return err; -- cgit v1.2.3 From 1744a22ae948799da7927b53ec97ccc877ff9d61 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 14 Dec 2021 09:22:12 +0000 Subject: afs: Fix mmap Fix afs_add_open_map() to check that the vnode isn't already on the list when it adds it. It's possible that afs_drop_open_mmap() decremented the cb_nr_mmap counter, but hadn't yet got into the locked section to remove it. Also vnode->cb_mmap_link should be initialised, so fix that too. Fixes: 6e0e99d58a65 ("afs: Fix mmap coherency vs 3rd-party changes") Reported-by: kafs-testing+fedora34_64checkkafs-build-300@auristor.com Suggested-by: Marc Dionne Signed-off-by: David Howells Tested-by: kafs-testing+fedora34_64checkkafs-build-300@auristor.com cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/686465.1639435380@warthog.procyon.org.uk/ # v1 Signed-off-by: Linus Torvalds --- fs/afs/file.c | 5 +++-- fs/afs/super.c | 1 + 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/afs/file.c b/fs/afs/file.c index cb6ad61eec3b..afe4b803f84b 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -514,8 +514,9 @@ static void afs_add_open_mmap(struct afs_vnode *vnode) if (atomic_inc_return(&vnode->cb_nr_mmap) == 1) { down_write(&vnode->volume->cell->fs_open_mmaps_lock); - list_add_tail(&vnode->cb_mmap_link, - &vnode->volume->cell->fs_open_mmaps); + if (list_empty(&vnode->cb_mmap_link)) + list_add_tail(&vnode->cb_mmap_link, + &vnode->volume->cell->fs_open_mmaps); up_write(&vnode->volume->cell->fs_open_mmaps_lock); } diff --git a/fs/afs/super.c b/fs/afs/super.c index d110def8aa8e..34c68724c98b 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -667,6 +667,7 @@ static void afs_i_init_once(void *_vnode) INIT_LIST_HEAD(&vnode->pending_locks); INIT_LIST_HEAD(&vnode->granted_locks); INIT_DELAYED_WORK(&vnode->lock_work, afs_lock_work); + INIT_LIST_HEAD(&vnode->cb_mmap_link); seqlock_init(&vnode->cb_lock); } -- cgit v1.2.3 From 9c5d89bc10551f1aecd768b00fca3339a7b8c8ee Mon Sep 17 00:00:00 2001 From: Lakshmi Ramasubramanian Date: Thu, 9 Dec 2021 17:01:21 -0800 Subject: arm64: kexec: Fix missing error code 'ret' warning in load_other_segments() Since commit ac10be5cdbfa ("arm64: Use common of_kexec_alloc_and_setup_fdt()"), smatch reports the following warning: arch/arm64/kernel/machine_kexec_file.c:152 load_other_segments() warn: missing error code 'ret' Return code is not set to an error code in load_other_segments() when of_kexec_alloc_and_setup_fdt() call returns a NULL dtb. This results in status success (return code set to 0) being returned from load_other_segments(). Set return code to -EINVAL if of_kexec_alloc_and_setup_fdt() returns NULL dtb. Signed-off-by: Lakshmi Ramasubramanian Reported-by: kernel test robot Reported-by: Dan Carpenter Fixes: ac10be5cdbfa ("arm64: Use common of_kexec_alloc_and_setup_fdt()") Link: https://lore.kernel.org/r/20211210010121.101823-1-nramas@linux.microsoft.com Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/kernel/machine_kexec_file.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index 63634b4d72c1..59c648d51848 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -149,6 +149,7 @@ int load_other_segments(struct kimage *image, initrd_len, cmdline, 0); if (!dtb) { pr_err("Preparing for new dtb failed\n"); + ret = -EINVAL; goto out_err; } -- cgit v1.2.3 From 3cf2b61eb06765e27fec6799292d9fb46d0b7e60 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 15 Dec 2021 22:02:19 +0000 Subject: bpf: Fix signed bounds propagation after mov32 For the case where both s32_{min,max}_value bounds are positive, the __reg_assign_32_into_64() directly propagates them to their 64 bit counterparts, otherwise it pessimises them into [0,u32_max] universe and tries to refine them later on by learning through the tnum as per comment in mentioned function. However, that does not always happen, for example, in mov32 operation we call zext_32_to_64(dst_reg) which invokes the __reg_assign_32_into_64() as is without subsequent bounds update as elsewhere thus no refinement based on tnum takes place. Thus, not calling into the __update_reg_bounds() / __reg_deduce_bounds() / __reg_bound_offset() triplet as we do, for example, in case of ALU ops via adjust_scalar_min_max_vals(), will lead to more pessimistic bounds when dumping the full register state: Before fix: 0: (b4) w0 = -1 1: R0_w=invP4294967295 (id=0,imm=ffffffff, smin_value=4294967295,smax_value=4294967295, umin_value=4294967295,umax_value=4294967295, var_off=(0xffffffff; 0x0), s32_min_value=-1,s32_max_value=-1, u32_min_value=-1,u32_max_value=-1) 1: (bc) w0 = w0 2: R0_w=invP4294967295 (id=0,imm=ffffffff, smin_value=0,smax_value=4294967295, umin_value=4294967295,umax_value=4294967295, var_off=(0xffffffff; 0x0), s32_min_value=-1,s32_max_value=-1, u32_min_value=-1,u32_max_value=-1) Technically, the smin_value=0 and smax_value=4294967295 bounds are not incorrect, but given the register is still a constant, they break assumptions about const scalars that smin_value == smax_value and umin_value == umax_value. After fix: 0: (b4) w0 = -1 1: R0_w=invP4294967295 (id=0,imm=ffffffff, smin_value=4294967295,smax_value=4294967295, umin_value=4294967295,umax_value=4294967295, var_off=(0xffffffff; 0x0), s32_min_value=-1,s32_max_value=-1, u32_min_value=-1,u32_max_value=-1) 1: (bc) w0 = w0 2: R0_w=invP4294967295 (id=0,imm=ffffffff, smin_value=4294967295,smax_value=4294967295, umin_value=4294967295,umax_value=4294967295, var_off=(0xffffffff; 0x0), s32_min_value=-1,s32_max_value=-1, u32_min_value=-1,u32_max_value=-1) Without the smin_value == smax_value and umin_value == umax_value invariant being intact for const scalars, it is possible to leak out kernel pointers from unprivileged user space if the latter is enabled. For example, when such registers are involved in pointer arithmtics, then adjust_ptr_min_max_vals() will taint the destination register into an unknown scalar, and the latter can be exported and stored e.g. into a BPF map value. Fixes: 3f50f132d840 ("bpf: Verifier, do explicit ALU32 bounds tracking") Reported-by: Kuee K1r0a Signed-off-by: Daniel Borkmann Reviewed-by: John Fastabend Acked-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 2d48159b58bd..0872b6c9fb33 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8317,6 +8317,10 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) insn->dst_reg); } zext_32_to_64(dst_reg); + + __update_reg_bounds(dst_reg); + __reg_deduce_bounds(dst_reg); + __reg_bound_offset(dst_reg); } } else { /* case: R = imm -- cgit v1.2.3 From e572ff80f05c33cd0cb4860f864f5c9c044280b6 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 15 Dec 2021 22:28:48 +0000 Subject: bpf: Make 32->64 bounds propagation slightly more robust Make the bounds propagation in __reg_assign_32_into_64() slightly more robust and readable by aligning it similarly as we did back in the __reg_combine_64_into_32() counterpart. Meaning, only propagate or pessimize them as a smin/smax pair. Signed-off-by: Daniel Borkmann Reviewed-by: John Fastabend Acked-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 0872b6c9fb33..b532f1058d35 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1366,22 +1366,28 @@ static void __reg_bound_offset(struct bpf_reg_state *reg) reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off); } +static bool __reg32_bound_s64(s32 a) +{ + return a >= 0 && a <= S32_MAX; +} + static void __reg_assign_32_into_64(struct bpf_reg_state *reg) { reg->umin_value = reg->u32_min_value; reg->umax_value = reg->u32_max_value; - /* Attempt to pull 32-bit signed bounds into 64-bit bounds - * but must be positive otherwise set to worse case bounds - * and refine later from tnum. + + /* Attempt to pull 32-bit signed bounds into 64-bit bounds but must + * be positive otherwise set to worse case bounds and refine later + * from tnum. */ - if (reg->s32_min_value >= 0 && reg->s32_max_value >= 0) - reg->smax_value = reg->s32_max_value; - else - reg->smax_value = U32_MAX; - if (reg->s32_min_value >= 0) + if (__reg32_bound_s64(reg->s32_min_value) && + __reg32_bound_s64(reg->s32_max_value)) { reg->smin_value = reg->s32_min_value; - else + reg->smax_value = reg->s32_max_value; + } else { reg->smin_value = 0; + reg->smax_value = U32_MAX; + } } static void __reg_combine_32_into_64(struct bpf_reg_state *reg) -- cgit v1.2.3 From b1a7288dedc6caf9023f2676b4f5ed34cf0d4029 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 15 Dec 2021 23:48:54 +0000 Subject: bpf, selftests: Add test case trying to taint map value pointer Add a test case which tries to taint map value pointer arithmetic into a unknown scalar with subsequent export through the map. Before fix: # ./test_verifier 1186 #1186/u map access: trying to leak tained dst reg FAIL Unexpected success to load! verification time 24 usec stack depth 8 processed 15 insns (limit 1000000) max_states_per_insn 0 total_states 1 peak_states 1 mark_read 1 #1186/p map access: trying to leak tained dst reg FAIL Unexpected success to load! verification time 8 usec stack depth 8 processed 15 insns (limit 1000000) max_states_per_insn 0 total_states 1 peak_states 1 mark_read 1 Summary: 0 PASSED, 0 SKIPPED, 2 FAILED After fix: # ./test_verifier 1186 #1186/u map access: trying to leak tained dst reg OK #1186/p map access: trying to leak tained dst reg OK Summary: 2 PASSED, 0 SKIPPED, 0 FAILED Signed-off-by: Daniel Borkmann Reviewed-by: John Fastabend Acked-by: Alexei Starovoitov --- .../selftests/bpf/verifier/value_ptr_arith.c | 23 ++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index 2debba4e8a3a..4d347bc53aa2 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -1077,6 +1077,29 @@ .errstr = "R0 invalid mem access 'inv'", .errstr_unpriv = "R0 pointer -= pointer prohibited", }, +{ + "map access: trying to leak tained dst reg", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_MOV32_IMM(BPF_REG_1, 0xFFFFFFFF), + BPF_MOV32_REG(BPF_REG_1, BPF_REG_1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1), + BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 4 }, + .result = REJECT, + .errstr = "math between map_value pointer and 4294967295 is not allowed", +}, { "32bit pkt_ptr -= scalar", .insns = { -- cgit v1.2.3 From 433956e91200734d09958673a56df02d00a917c2 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 15 Dec 2021 18:38:30 -0800 Subject: bpf: Fix extable fixup offset. The prog - start_of_ldx is the offset before the faulting ldx to the location after it, so this will be used to adjust pt_regs->ip for jumping over it and continuing, and with old temp it would have been fixed up to the wrong offset, causing crash. Fixes: 4c5de127598e ("bpf: Emit explicit NULL pointer checks for PROBE_LDX instructions.") Signed-off-by: Alexei Starovoitov Reviewed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann --- arch/x86/net/bpf_jit_comp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 726700fabca6..fa58681db45e 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1305,7 +1305,7 @@ st: if (is_imm8(insn->off)) * End result: x86 insn "mov rbx, qword ptr [rax+0x14]" * of 4 bytes will be ignored and rbx will be zero inited. */ - ex->fixup = (prog - temp) | (reg2pt_regs[dst_reg] << 8); + ex->fixup = (prog - start_of_ldx) | (reg2pt_regs[dst_reg] << 8); } break; -- cgit v1.2.3 From 588a25e92458c6efeb7a261d5ca5726f5de89184 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 14 Dec 2021 19:25:13 -0800 Subject: bpf: Fix extable address check. The verifier checks that PTR_TO_BTF_ID pointer is either valid or NULL, but it cannot distinguish IS_ERR pointer from valid one. When offset is added to IS_ERR pointer it may become small positive value which is a user address that is not handled by extable logic and has to be checked for at the runtime. Tighten BPF_PROBE_MEM pointer check code to prevent this case. Fixes: 4c5de127598e ("bpf: Emit explicit NULL pointer checks for PROBE_LDX instructions.") Reported-by: Lorenzo Fontana Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: Daniel Borkmann --- arch/x86/net/bpf_jit_comp.c | 49 ++++++++++++++++++++++++++++++++++++++------- 1 file changed, 42 insertions(+), 7 deletions(-) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index fa58681db45e..bafe36e69227 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1252,19 +1252,54 @@ st: if (is_imm8(insn->off)) case BPF_LDX | BPF_MEM | BPF_DW: case BPF_LDX | BPF_PROBE_MEM | BPF_DW: if (BPF_MODE(insn->code) == BPF_PROBE_MEM) { - /* test src_reg, src_reg */ - maybe_emit_mod(&prog, src_reg, src_reg, true); /* always 1 byte */ - EMIT2(0x85, add_2reg(0xC0, src_reg, src_reg)); - /* jne start_of_ldx */ - EMIT2(X86_JNE, 0); + /* Though the verifier prevents negative insn->off in BPF_PROBE_MEM + * add abs(insn->off) to the limit to make sure that negative + * offset won't be an issue. + * insn->off is s16, so it won't affect valid pointers. + */ + u64 limit = TASK_SIZE_MAX + PAGE_SIZE + abs(insn->off); + u8 *end_of_jmp1, *end_of_jmp2; + + /* Conservatively check that src_reg + insn->off is a kernel address: + * 1. src_reg + insn->off >= limit + * 2. src_reg + insn->off doesn't become small positive. + * Cannot do src_reg + insn->off >= limit in one branch, + * since it needs two spare registers, but JIT has only one. + */ + + /* movabsq r11, limit */ + EMIT2(add_1mod(0x48, AUX_REG), add_1reg(0xB8, AUX_REG)); + EMIT((u32)limit, 4); + EMIT(limit >> 32, 4); + /* cmp src_reg, r11 */ + maybe_emit_mod(&prog, src_reg, AUX_REG, true); + EMIT2(0x39, add_2reg(0xC0, src_reg, AUX_REG)); + /* if unsigned '<' goto end_of_jmp2 */ + EMIT2(X86_JB, 0); + end_of_jmp1 = prog; + + /* mov r11, src_reg */ + emit_mov_reg(&prog, true, AUX_REG, src_reg); + /* add r11, insn->off */ + maybe_emit_1mod(&prog, AUX_REG, true); + EMIT2_off32(0x81, add_1reg(0xC0, AUX_REG), insn->off); + /* jmp if not carry to start_of_ldx + * Otherwise ERR_PTR(-EINVAL) + 128 will be the user addr + * that has to be rejected. + */ + EMIT2(0x73 /* JNC */, 0); + end_of_jmp2 = prog; + /* xor dst_reg, dst_reg */ emit_mov_imm32(&prog, false, dst_reg, 0); /* jmp byte_after_ldx */ EMIT2(0xEB, 0); - /* populate jmp_offset for JNE above */ - temp[4] = prog - temp - 5 /* sizeof(test + jne) */; + /* populate jmp_offset for JB above to jump to xor dst_reg */ + end_of_jmp1[-1] = end_of_jmp2 - end_of_jmp1; + /* populate jmp_offset for JNC above to jump to start_of_ldx */ start_of_ldx = prog; + end_of_jmp2[-1] = start_of_ldx - end_of_jmp2; } emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off); if (BPF_MODE(insn->code) == BPF_PROBE_MEM) { -- cgit v1.2.3 From 7edc3fcbf9a2b2e3df53c9656a9f85bf807affac Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 15 Dec 2021 12:35:34 -0800 Subject: selftest/bpf: Add a test that reads various addresses. Add a function to bpf_testmod that returns invalid kernel and user addresses. Then attach an fexit program to that function that tries to read memory through these addresses. This logic checks that bpf_probe_read_kernel and BPF_PROBE_MEM logic is sane. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: Daniel Borkmann --- .../testing/selftests/bpf/bpf_testmod/bpf_testmod.c | 20 ++++++++++++++++++++ .../testing/selftests/bpf/progs/test_module_attach.c | 12 ++++++++++++ 2 files changed, 32 insertions(+) diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 5d52ea2768df..df3b292a8ffe 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -33,6 +33,22 @@ noinline int bpf_testmod_loop_test(int n) return sum; } +__weak noinline struct file *bpf_testmod_return_ptr(int arg) +{ + static struct file f = {}; + + switch (arg) { + case 1: return (void *)EINVAL; /* user addr */ + case 2: return (void *)0xcafe4a11; /* user addr */ + case 3: return (void *)-EINVAL; /* canonical, but invalid */ + case 4: return (void *)(1ull << 60); /* non-canonical and invalid */ + case 5: return (void *)~(1ull << 30); /* trigger extable */ + case 6: return &f; /* valid addr */ + case 7: return (void *)((long)&f | 1); /* kernel tricks */ + default: return NULL; + } +} + noinline ssize_t bpf_testmod_test_read(struct file *file, struct kobject *kobj, struct bin_attribute *bin_attr, @@ -43,6 +59,10 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj, .off = off, .len = len, }; + int i = 1; + + while (bpf_testmod_return_ptr(i)) + i++; /* This is always true. Use the check to make sure the compiler * doesn't remove bpf_testmod_loop_test. diff --git a/tools/testing/selftests/bpf/progs/test_module_attach.c b/tools/testing/selftests/bpf/progs/test_module_attach.c index b36857093f71..50ce16d02da7 100644 --- a/tools/testing/selftests/bpf/progs/test_module_attach.c +++ b/tools/testing/selftests/bpf/progs/test_module_attach.c @@ -87,6 +87,18 @@ int BPF_PROG(handle_fexit, return 0; } +SEC("fexit/bpf_testmod_return_ptr") +int BPF_PROG(handle_fexit_ret, int arg, struct file *ret) +{ + long buf = 0; + + bpf_probe_read_kernel(&buf, 8, ret); + bpf_probe_read_kernel(&buf, 8, (char *)ret + 256); + *(volatile long long *)ret; + *(volatile int *)&ret->f_mode; + return 0; +} + __u32 fmod_ret_read_sz = 0; SEC("fmod_ret/bpf_testmod_test_read") -- cgit v1.2.3 From c2fcbf81c332b42382a0c439bfe2414a241e4f5b Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 16 Dec 2021 11:16:30 -0800 Subject: bpf, selftests: Fix racing issue in btf_skc_cls_ingress test The libbpf CI reported occasional failure in btf_skc_cls_ingress: test_syncookie:FAIL:Unexpected syncookie states gen_cookie:80326634 recv_cookie:0 bpf prog error at line 97 "error at line 97" means the bpf prog cannot find the listening socket when the final ack is received. It then skipped processing the syncookie in the final ack which then led to "recv_cookie:0". The problem is the userspace program did not do accept() and went ahead to close(listen_fd) before the kernel (and the bpf prog) had a chance to process the final ack. The fix is to add accept() call so that the userspace will wait for the kernel to finish processing the final ack first before close()-ing everything. Fixes: 9a856cae2217 ("bpf: selftest: Add test_btf_skc_cls_ingress") Reported-by: Andrii Nakryiko Signed-off-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20211216191630.466151-1-kafai@fb.com --- .../selftests/bpf/prog_tests/btf_skc_cls_ingress.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c index 762f6a9da8b5..664ffc0364f4 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c @@ -90,7 +90,7 @@ static void print_err_line(void) static void test_conn(void) { - int listen_fd = -1, cli_fd = -1, err; + int listen_fd = -1, cli_fd = -1, srv_fd = -1, err; socklen_t addrlen = sizeof(srv_sa6); int srv_port; @@ -112,6 +112,10 @@ static void test_conn(void) if (CHECK_FAIL(cli_fd == -1)) goto done; + srv_fd = accept(listen_fd, NULL, NULL); + if (CHECK_FAIL(srv_fd == -1)) + goto done; + if (CHECK(skel->bss->listen_tp_sport != srv_port || skel->bss->req_sk_sport != srv_port, "Unexpected sk src port", @@ -134,11 +138,13 @@ done: close(listen_fd); if (cli_fd != -1) close(cli_fd); + if (srv_fd != -1) + close(srv_fd); } static void test_syncookie(void) { - int listen_fd = -1, cli_fd = -1, err; + int listen_fd = -1, cli_fd = -1, srv_fd = -1, err; socklen_t addrlen = sizeof(srv_sa6); int srv_port; @@ -161,6 +167,10 @@ static void test_syncookie(void) if (CHECK_FAIL(cli_fd == -1)) goto done; + srv_fd = accept(listen_fd, NULL, NULL); + if (CHECK_FAIL(srv_fd == -1)) + goto done; + if (CHECK(skel->bss->listen_tp_sport != srv_port, "Unexpected tp src port", "listen_tp_sport:%u expected:%u\n", @@ -188,6 +198,8 @@ done: close(listen_fd); if (cli_fd != -1) close(cli_fd); + if (srv_fd != -1) + close(srv_fd); } struct test { -- cgit v1.2.3 From cc274ae7763d9700a56659f3228641d7069e7a3f Mon Sep 17 00:00:00 2001 From: Scott Mayhew Date: Wed, 15 Dec 2021 16:28:40 -0500 Subject: selinux: fix sleeping function called from invalid context selinux_sb_mnt_opts_compat() is called via sget_fc() under the sb_lock spinlock, so it can't use GFP_KERNEL allocations: [ 868.565200] BUG: sleeping function called from invalid context at include/linux/sched/mm.h:230 [ 868.568246] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 4914, name: mount.nfs [ 868.569626] preempt_count: 1, expected: 0 [ 868.570215] RCU nest depth: 0, expected: 0 [ 868.570809] Preemption disabled at: [ 868.570810] [<0000000000000000>] 0x0 [ 868.571848] CPU: 1 PID: 4914 Comm: mount.nfs Kdump: loaded Tainted: G W 5.16.0-rc5.2585cf9dfa #1 [ 868.573273] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.14.0-4.fc34 04/01/2014 [ 868.574478] Call Trace: [ 868.574844] [ 868.575156] dump_stack_lvl+0x34/0x44 [ 868.575692] __might_resched.cold+0xd6/0x10f [ 868.576308] slab_pre_alloc_hook.constprop.0+0x89/0xf0 [ 868.577046] __kmalloc_track_caller+0x72/0x420 [ 868.577684] ? security_context_to_sid_core+0x48/0x2b0 [ 868.578569] kmemdup_nul+0x22/0x50 [ 868.579108] security_context_to_sid_core+0x48/0x2b0 [ 868.579854] ? _nfs4_proc_pathconf+0xff/0x110 [nfsv4] [ 868.580742] ? nfs_reconfigure+0x80/0x80 [nfs] [ 868.581355] security_context_str_to_sid+0x36/0x40 [ 868.581960] selinux_sb_mnt_opts_compat+0xb5/0x1e0 [ 868.582550] ? nfs_reconfigure+0x80/0x80 [nfs] [ 868.583098] security_sb_mnt_opts_compat+0x2a/0x40 [ 868.583676] nfs_compare_super+0x113/0x220 [nfs] [ 868.584249] ? nfs_try_mount_request+0x210/0x210 [nfs] [ 868.584879] sget_fc+0xb5/0x2f0 [ 868.585267] nfs_get_tree_common+0x91/0x4a0 [nfs] [ 868.585834] vfs_get_tree+0x25/0xb0 [ 868.586241] fc_mount+0xe/0x30 [ 868.586605] do_nfs4_mount+0x130/0x380 [nfsv4] [ 868.587160] nfs4_try_get_tree+0x47/0xb0 [nfsv4] [ 868.587724] vfs_get_tree+0x25/0xb0 [ 868.588193] do_new_mount+0x176/0x310 [ 868.588782] __x64_sys_mount+0x103/0x140 [ 868.589388] do_syscall_64+0x3b/0x90 [ 868.589935] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 868.590699] RIP: 0033:0x7f2b371c6c4e [ 868.591239] Code: 48 8b 0d dd 71 0e 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d aa 71 0e 00 f7 d8 64 89 01 48 [ 868.593810] RSP: 002b:00007ffc83775d88 EFLAGS: 00000246 ORIG_RAX: 00000000000000a5 [ 868.594691] RAX: ffffffffffffffda RBX: 00007ffc83775f10 RCX: 00007f2b371c6c4e [ 868.595504] RDX: 0000555d517247a0 RSI: 0000555d51724700 RDI: 0000555d51724540 [ 868.596317] RBP: 00007ffc83775f10 R08: 0000555d51726890 R09: 0000555d51726890 [ 868.597162] R10: 0000000000000000 R11: 0000000000000246 R12: 0000555d51726890 [ 868.598005] R13: 0000000000000003 R14: 0000555d517246e0 R15: 0000555d511ac925 [ 868.598826] Cc: stable@vger.kernel.org Fixes: 69c4a42d72eb ("lsm,selinux: add new hook to compare new mount to an existing mount") Signed-off-by: Scott Mayhew [PM: cleanup/line-wrap the backtrace] Signed-off-by: Paul Moore --- security/selinux/hooks.c | 33 +++++++++++++++++++-------------- 1 file changed, 19 insertions(+), 14 deletions(-) diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 62d30c0a30c2..1afc06ffd969 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -611,10 +611,11 @@ static int bad_option(struct superblock_security_struct *sbsec, char flag, return 0; } -static int parse_sid(struct super_block *sb, const char *s, u32 *sid) +static int parse_sid(struct super_block *sb, const char *s, u32 *sid, + gfp_t gfp) { int rc = security_context_str_to_sid(&selinux_state, s, - sid, GFP_KERNEL); + sid, gfp); if (rc) pr_warn("SELinux: security_context_str_to_sid" "(%s) failed for (dev %s, type %s) errno=%d\n", @@ -685,7 +686,8 @@ static int selinux_set_mnt_opts(struct super_block *sb, */ if (opts) { if (opts->fscontext) { - rc = parse_sid(sb, opts->fscontext, &fscontext_sid); + rc = parse_sid(sb, opts->fscontext, &fscontext_sid, + GFP_KERNEL); if (rc) goto out; if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, @@ -694,7 +696,8 @@ static int selinux_set_mnt_opts(struct super_block *sb, sbsec->flags |= FSCONTEXT_MNT; } if (opts->context) { - rc = parse_sid(sb, opts->context, &context_sid); + rc = parse_sid(sb, opts->context, &context_sid, + GFP_KERNEL); if (rc) goto out; if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, @@ -703,7 +706,8 @@ static int selinux_set_mnt_opts(struct super_block *sb, sbsec->flags |= CONTEXT_MNT; } if (opts->rootcontext) { - rc = parse_sid(sb, opts->rootcontext, &rootcontext_sid); + rc = parse_sid(sb, opts->rootcontext, &rootcontext_sid, + GFP_KERNEL); if (rc) goto out; if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, @@ -712,7 +716,8 @@ static int selinux_set_mnt_opts(struct super_block *sb, sbsec->flags |= ROOTCONTEXT_MNT; } if (opts->defcontext) { - rc = parse_sid(sb, opts->defcontext, &defcontext_sid); + rc = parse_sid(sb, opts->defcontext, &defcontext_sid, + GFP_KERNEL); if (rc) goto out; if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, @@ -2702,14 +2707,14 @@ static int selinux_sb_mnt_opts_compat(struct super_block *sb, void *mnt_opts) return (sbsec->flags & SE_MNTMASK) ? 1 : 0; if (opts->fscontext) { - rc = parse_sid(sb, opts->fscontext, &sid); + rc = parse_sid(sb, opts->fscontext, &sid, GFP_NOWAIT); if (rc) return 1; if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, sid)) return 1; } if (opts->context) { - rc = parse_sid(sb, opts->context, &sid); + rc = parse_sid(sb, opts->context, &sid, GFP_NOWAIT); if (rc) return 1; if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, sid)) @@ -2719,14 +2724,14 @@ static int selinux_sb_mnt_opts_compat(struct super_block *sb, void *mnt_opts) struct inode_security_struct *root_isec; root_isec = backing_inode_security(sb->s_root); - rc = parse_sid(sb, opts->rootcontext, &sid); + rc = parse_sid(sb, opts->rootcontext, &sid, GFP_NOWAIT); if (rc) return 1; if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, sid)) return 1; } if (opts->defcontext) { - rc = parse_sid(sb, opts->defcontext, &sid); + rc = parse_sid(sb, opts->defcontext, &sid, GFP_NOWAIT); if (rc) return 1; if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, sid)) @@ -2749,14 +2754,14 @@ static int selinux_sb_remount(struct super_block *sb, void *mnt_opts) return 0; if (opts->fscontext) { - rc = parse_sid(sb, opts->fscontext, &sid); + rc = parse_sid(sb, opts->fscontext, &sid, GFP_KERNEL); if (rc) return rc; if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, sid)) goto out_bad_option; } if (opts->context) { - rc = parse_sid(sb, opts->context, &sid); + rc = parse_sid(sb, opts->context, &sid, GFP_KERNEL); if (rc) return rc; if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, sid)) @@ -2765,14 +2770,14 @@ static int selinux_sb_remount(struct super_block *sb, void *mnt_opts) if (opts->rootcontext) { struct inode_security_struct *root_isec; root_isec = backing_inode_security(sb->s_root); - rc = parse_sid(sb, opts->rootcontext, &sid); + rc = parse_sid(sb, opts->rootcontext, &sid, GFP_KERNEL); if (rc) return rc; if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, sid)) goto out_bad_option; } if (opts->defcontext) { - rc = parse_sid(sb, opts->defcontext, &sid); + rc = parse_sid(sb, opts->defcontext, &sid, GFP_KERNEL); if (rc) return rc; if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, sid)) -- cgit v1.2.3 From 5da5231bb47864e5dd6c6731151e98b6ee498827 Mon Sep 17 00:00:00 2001 From: George Kennedy Date: Tue, 14 Dec 2021 09:45:10 -0500 Subject: libata: if T_LENGTH is zero, dma direction should be DMA_NONE Avoid data corruption by rejecting pass-through commands where T_LENGTH is zero (No data is transferred) and the dma direction is not DMA_NONE. Cc: Reported-by: syzkaller Signed-off-by: George Kennedy Signed-off-by: Damien Le Moal --- drivers/ata/libata-scsi.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 1b84d5526d77..313e9475507b 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -2859,8 +2859,19 @@ static unsigned int ata_scsi_pass_thru(struct ata_queued_cmd *qc) goto invalid_fld; } - if (ata_is_ncq(tf->protocol) && (cdb[2 + cdb_offset] & 0x3) == 0) - tf->protocol = ATA_PROT_NCQ_NODATA; + if ((cdb[2 + cdb_offset] & 0x3) == 0) { + /* + * When T_LENGTH is zero (No data is transferred), dir should + * be DMA_NONE. + */ + if (scmd->sc_data_direction != DMA_NONE) { + fp = 2 + cdb_offset; + goto invalid_fld; + } + + if (ata_is_ncq(tf->protocol)) + tf->protocol = ATA_PROT_NCQ_NODATA; + } /* enable LBA */ tf->flags |= ATA_TFLAG_LBA; -- cgit v1.2.3 From ea81b91e4e256b0bb75d47ad3a5c230b2171a005 Mon Sep 17 00:00:00 2001 From: Vincent Pelletier Date: Tue, 16 Nov 2021 23:57:37 +0000 Subject: riscv: dts: sifive unmatched: Name gpio lines Follow the pin descriptions given in the version 3 of the board schematics. Signed-off-by: Vincent Pelletier Signed-off-by: Palmer Dabbelt --- arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts index 3c796d64cf51..f8648ee1785a 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts @@ -247,4 +247,8 @@ &gpio { status = "okay"; + gpio-line-names = "J29.1", "PMICNTB", "PMICSHDN", "J8.1", "J8.3", + "PCIe_PWREN", "THERM", "UBRDG_RSTN", "PCIe_PERSTN", + "ULPI_RSTN", "J8.2", "UHUB_RSTN", "GEMGXL_RST", "J8.4", + "EN_VDD_SD", "SD_CD"; }; -- cgit v1.2.3 From 8120393b74b31bbaf293f59896de6b0d50febc48 Mon Sep 17 00:00:00 2001 From: Vincent Pelletier Date: Tue, 16 Nov 2021 23:57:38 +0000 Subject: riscv: dts: sifive unmatched: Expose the board ID eeprom Mark it as read-only as it is factory-programmed with identifying information, and no executable nor configuration: - eth MAC address - board model (PCB version, BoM version) - board serial number Accidental modification would cause misidentification which could brick the board, so marking read-only seem like both a safe and non-constraining choice. Signed-off-by: Vincent Pelletier Signed-off-by: Palmer Dabbelt --- arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts index f8648ee1785a..d1f2289e529b 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts @@ -59,6 +59,16 @@ interrupts = <6 IRQ_TYPE_LEVEL_LOW>; }; + eeprom@54 { + compatible = "microchip,24c02", "atmel,24c02"; + reg = <0x54>; + vcc-supply = <&vdd_bpro>; + label = "board-id"; + pagesize = <16>; + read-only; + size = <256>; + }; + pmic@58 { compatible = "dlg,da9063"; reg = <0x58>; -- cgit v1.2.3 From cd29cc8ad2540a4f9a0a3e174394d39e648ef941 Mon Sep 17 00:00:00 2001 From: Vincent Pelletier Date: Tue, 16 Nov 2021 23:57:39 +0000 Subject: riscv: dts: sifive unmatched: Expose the PMIC sub-functions These sub-functions are available in the chip revision on this board, so expose them. Signed-off-by: Vincent Pelletier Signed-off-by: Palmer Dabbelt --- arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts index d1f2289e529b..91b3e76b2bb2 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts @@ -76,6 +76,18 @@ interrupts = <1 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; + onkey { + compatible = "dlg,da9063-onkey"; + }; + + rtc { + compatible = "dlg,da9063-rtc"; + }; + + wdt { + compatible = "dlg,da9063-watchdog"; + }; + regulators { vdd_bcore1: bcore1 { regulator-min-microvolt = <900000>; -- cgit v1.2.3 From ad931d9b3b2e21586de8e6b34346d0a30c13721d Mon Sep 17 00:00:00 2001 From: Vincent Pelletier Date: Tue, 16 Nov 2021 23:57:41 +0000 Subject: riscv: dts: sifive unmatched: Fix regulator for board rev3 The existing values are rejected by the da9063 regulator driver, as they are unachievable with the declared chip setup (non-merged vcore and bmem are unable to provide the declared curent). Fix voltages to match rev3 schematics, which also matches their boot-up configuration within the chip's available precision. Declare bcore1/bcore2 and bmem/bio as merged. Set ldo09 and ldo10 as always-on as their consumers are not declared but exist. Drop ldo current limits as there is no current limit feature for these regulators in the DA9063. Fixes warnings like: DA9063_LDO3: Operation of current configuration missing Signed-off-by: Vincent Pelletier Signed-off-by: Palmer Dabbelt --- .../riscv/boot/dts/sifive/hifive-unmatched-a00.dts | 84 +++++++--------------- 1 file changed, 24 insertions(+), 60 deletions(-) diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts index 91b3e76b2bb2..58de5a312fc9 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts @@ -89,47 +89,31 @@ }; regulators { - vdd_bcore1: bcore1 { - regulator-min-microvolt = <900000>; - regulator-max-microvolt = <900000>; - regulator-min-microamp = <5000000>; - regulator-max-microamp = <5000000>; - regulator-always-on; - }; - - vdd_bcore2: bcore2 { - regulator-min-microvolt = <900000>; - regulator-max-microvolt = <900000>; - regulator-min-microamp = <5000000>; - regulator-max-microamp = <5000000>; + vdd_bcore: bcores-merged { + regulator-min-microvolt = <1050000>; + regulator-max-microvolt = <1050000>; + regulator-min-microamp = <4800000>; + regulator-max-microamp = <4800000>; regulator-always-on; }; vdd_bpro: bpro { regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; - regulator-min-microamp = <2500000>; - regulator-max-microamp = <2500000>; + regulator-min-microamp = <2400000>; + regulator-max-microamp = <2400000>; regulator-always-on; }; vdd_bperi: bperi { - regulator-min-microvolt = <1050000>; - regulator-max-microvolt = <1050000>; + regulator-min-microvolt = <1060000>; + regulator-max-microvolt = <1060000>; regulator-min-microamp = <1500000>; regulator-max-microamp = <1500000>; regulator-always-on; }; - vdd_bmem: bmem { - regulator-min-microvolt = <1200000>; - regulator-max-microvolt = <1200000>; - regulator-min-microamp = <3000000>; - regulator-max-microamp = <3000000>; - regulator-always-on; - }; - - vdd_bio: bio { + vdd_bmem_bio: bmem-bio-merged { regulator-min-microvolt = <1200000>; regulator-max-microvolt = <1200000>; regulator-min-microamp = <3000000>; @@ -140,86 +124,66 @@ vdd_ldo1: ldo1 { regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; - regulator-min-microamp = <100000>; - regulator-max-microamp = <100000>; regulator-always-on; }; vdd_ldo2: ldo2 { regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; - regulator-min-microamp = <200000>; - regulator-max-microamp = <200000>; regulator-always-on; }; vdd_ldo3: ldo3 { - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; - regulator-min-microamp = <200000>; - regulator-max-microamp = <200000>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; regulator-always-on; }; vdd_ldo4: ldo4 { - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; - regulator-min-microamp = <200000>; - regulator-max-microamp = <200000>; + regulator-min-microvolt = <2500000>; + regulator-max-microvolt = <2500000>; regulator-always-on; }; vdd_ldo5: ldo5 { - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; - regulator-min-microamp = <100000>; - regulator-max-microamp = <100000>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; regulator-always-on; }; vdd_ldo6: ldo6 { - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - regulator-min-microamp = <200000>; - regulator-max-microamp = <200000>; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; regulator-always-on; }; vdd_ldo7: ldo7 { - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; - regulator-min-microamp = <200000>; - regulator-max-microamp = <200000>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; regulator-always-on; }; vdd_ldo8: ldo8 { - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; - regulator-min-microamp = <200000>; - regulator-max-microamp = <200000>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; regulator-always-on; }; vdd_ld09: ldo9 { regulator-min-microvolt = <1050000>; regulator-max-microvolt = <1050000>; - regulator-min-microamp = <200000>; - regulator-max-microamp = <200000>; + regulator-always-on; }; vdd_ldo10: ldo10 { regulator-min-microvolt = <1000000>; regulator-max-microvolt = <1000000>; - regulator-min-microamp = <300000>; - regulator-max-microamp = <300000>; + regulator-always-on; }; vdd_ldo11: ldo11 { regulator-min-microvolt = <2500000>; regulator-max-microvolt = <2500000>; - regulator-min-microamp = <300000>; - regulator-max-microamp = <300000>; regulator-always-on; }; }; -- cgit v1.2.3 From f6f7fbb89bf8dc9132fde55cfe67483138eea880 Mon Sep 17 00:00:00 2001 From: Vincent Pelletier Date: Tue, 16 Nov 2021 23:57:42 +0000 Subject: riscv: dts: sifive unmatched: Link the tmp451 with its power supply Fixes the following probe warning: lm90 0-004c: Looking up vcc-supply from device tree lm90 0-004c: Looking up vcc-supply property in node /soc/i2c@10030000/temperature-sensor@4c failed lm90 0-004c: supply vcc not found, using dummy regulator Signed-off-by: Vincent Pelletier Signed-off-by: Palmer Dabbelt --- arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts index 58de5a312fc9..6bfa1f24d3de 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts @@ -55,6 +55,7 @@ temperature-sensor@4c { compatible = "ti,tmp451"; reg = <0x4c>; + vcc-supply = <&vdd_bpro>; interrupt-parent = <&gpio>; interrupts = <6 IRQ_TYPE_LEVEL_LOW>; }; -- cgit v1.2.3 From 8ffea2599f63fdbee968b894eab78170abf3ec2c Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Fri, 17 Dec 2021 15:15:45 +0900 Subject: zonefs: add MODULE_ALIAS_FS Add MODULE_ALIAS_FS() to load the module automatically when you do "mount -t zonefs". Fixes: 8dcc1a9d90c1 ("fs: New zonefs file system") Cc: stable # 5.6+ Signed-off-by: Naohiro Aota Reviewed-by: Johannes Thumshirn Signed-off-by: Damien Le Moal --- fs/zonefs/super.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 259ee2bda492..b76dfb310ab6 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -1787,5 +1787,6 @@ static void __exit zonefs_exit(void) MODULE_AUTHOR("Damien Le Moal"); MODULE_DESCRIPTION("Zone file system for zoned block devices"); MODULE_LICENSE("GPL"); +MODULE_ALIAS_FS("zonefs"); module_init(zonefs_init); module_exit(zonefs_exit); -- cgit v1.2.3 From bce472f90952cc8be03dded25c4aa109d27e5924 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 17 Dec 2021 16:41:17 +0900 Subject: MAITAINERS: Change zonefs maintainer email address Update my email address from damien.lemoal@wdc.com to damien.lemoal@opensource.wdc.com. Signed-off-by: Damien Le Moal --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 13f9a84a617e..d01ae22c55f8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -21059,7 +21059,7 @@ S: Maintained F: arch/x86/kernel/cpu/zhaoxin.c ZONEFS FILESYSTEM -M: Damien Le Moal +M: Damien Le Moal M: Naohiro Aota R: Johannes Thumshirn L: linux-fsdevel@vger.kernel.org -- cgit v1.2.3 From c4d936efa46d8ea183df16c0f3fa4423327da51d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 17 Dec 2021 16:24:30 +0100 Subject: Revert "usb: early: convert to readl_poll_timeout_atomic()" This reverts commit 796eed4b2342c9d6b26c958e92af91253a2390e1. This change causes boot lockups when using "arlyprintk=xdbc" because ktime can not be used at this point in time in the boot process. Also, it is not needed for very small delays like this. Reported-by: Mathias Nyman Reported-by: Peter Zijlstra Cc: Jann Horn Cc: Chunfeng Yun Fixes: 796eed4b2342 ("usb: early: convert to readl_poll_timeout_atomic()") Link: https://lore.kernel.org/r/c2b5c9bb-1b75-bf56-3754-b5b18812d65e@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/early/xhci-dbc.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/usb/early/xhci-dbc.c b/drivers/usb/early/xhci-dbc.c index 933d77ad0a64..4502108069cd 100644 --- a/drivers/usb/early/xhci-dbc.c +++ b/drivers/usb/early/xhci-dbc.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include @@ -136,9 +135,17 @@ static int handshake(void __iomem *ptr, u32 mask, u32 done, int wait, int delay) { u32 result; - return readl_poll_timeout_atomic(ptr, result, - ((result & mask) == done), - delay, wait); + /* Can not use readl_poll_timeout_atomic() for early boot things */ + do { + result = readl(ptr); + result &= mask; + if (result == done) + return 0; + udelay(delay); + wait -= delay; + } while (wait > 0); + + return -ETIMEDOUT; } static void __init xdbc_bios_handoff(void) -- cgit v1.2.3 From 4e8c11b6b3f0b6a283e898344f154641eda94266 Mon Sep 17 00:00:00 2001 From: Yu Liao Date: Mon, 13 Dec 2021 21:57:27 +0800 Subject: timekeeping: Really make sure wall_to_monotonic isn't positive Even after commit e1d7ba873555 ("time: Always make sure wall_to_monotonic isn't positive") it is still possible to make wall_to_monotonic positive by running the following code: int main(void) { struct timespec time; clock_gettime(CLOCK_MONOTONIC, &time); time.tv_nsec = 0; clock_settime(CLOCK_REALTIME, &time); return 0; } The reason is that the second parameter of timespec64_compare(), ts_delta, may be unnormalized because the delta is calculated with an open coded substraction which causes the comparison of tv_sec to yield the wrong result: wall_to_monotonic = { .tv_sec = -10, .tv_nsec = 900000000 } ts_delta = { .tv_sec = -9, .tv_nsec = -900000000 } That makes timespec64_compare() claim that wall_to_monotonic < ts_delta, but actually the result should be wall_to_monotonic > ts_delta. After normalization, the result of timespec64_compare() is correct because the tv_sec comparison is not longer misleading: wall_to_monotonic = { .tv_sec = -10, .tv_nsec = 900000000 } ts_delta = { .tv_sec = -10, .tv_nsec = 100000000 } Use timespec64_sub() to ensure that ts_delta is normalized, which fixes the issue. Fixes: e1d7ba873555 ("time: Always make sure wall_to_monotonic isn't positive") Signed-off-by: Yu Liao Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20211213135727.1656662-1-liaoyu15@huawei.com --- kernel/time/timekeeping.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index b348749a9fc6..dcdcb85121e4 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1306,8 +1306,7 @@ int do_settimeofday64(const struct timespec64 *ts) timekeeping_forward_now(tk); xt = tk_xtime(tk); - ts_delta.tv_sec = ts->tv_sec - xt.tv_sec; - ts_delta.tv_nsec = ts->tv_nsec - xt.tv_nsec; + ts_delta = timespec64_sub(*ts, xt); if (timespec64_compare(&tk->wall_to_monotonic, &ts_delta) > 0) { ret = -EINVAL; -- cgit v1.2.3 From b774302e885697dde027825f8de9beb985d037bd Mon Sep 17 00:00:00 2001 From: Shyam Prasad N Date: Wed, 8 Dec 2021 16:33:19 +0000 Subject: cifs: ignore resource_id while getting fscache super cookie We have a cyclic dependency between fscache super cookie and root inode cookie. The super cookie relies on tcon->resource_id, which gets populated from the root inode number. However, fetching the root inode initializes inode cookie as a child of super cookie, which is yet to be populated. resource_id is only used as auxdata to check the validity of super cookie. We can completely avoid setting resource_id to remove the circular dependency. Since vol creation time and vol serial numbers are used for auxdata, we should be fine. Additionally, there will be auxiliary data check for each inode cookie as well. Fixes: 5bf91ef03d98 ("cifs: wait for tcon resource_id before getting fscache super") CC: David Howells Signed-off-by: Shyam Prasad N Signed-off-by: Steve French --- fs/cifs/connect.c | 7 +++++++ fs/cifs/inode.c | 13 ------------- 2 files changed, 7 insertions(+), 13 deletions(-) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 18448dbd762a..1060164b984a 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -3064,6 +3064,13 @@ static int mount_get_conns(struct mount_ctx *mnt_ctx) (cifs_sb->ctx->rsize > server->ops->negotiate_rsize(tcon, ctx))) cifs_sb->ctx->rsize = server->ops->negotiate_rsize(tcon, ctx); + /* + * The cookie is initialized from volume info returned above. + * Inside cifs_fscache_get_super_cookie it checks + * that we do not get super cookie twice. + */ + cifs_fscache_get_super_cookie(tcon); + out: mnt_ctx->server = server; mnt_ctx->ses = ses; diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 96d083db1737..279622e4eb1c 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1356,11 +1356,6 @@ iget_no_retry: goto out; } -#ifdef CONFIG_CIFS_FSCACHE - /* populate tcon->resource_id */ - tcon->resource_id = CIFS_I(inode)->uniqueid; -#endif - if (rc && tcon->pipe) { cifs_dbg(FYI, "ipc connection - fake read inode\n"); spin_lock(&inode->i_lock); @@ -1375,14 +1370,6 @@ iget_no_retry: iget_failed(inode); inode = ERR_PTR(rc); } - - /* - * The cookie is initialized from volume info returned above. - * Inside cifs_fscache_get_super_cookie it checks - * that we do not get super cookie twice. - */ - cifs_fscache_get_super_cookie(tcon); - out: kfree(path); free_xid(xid); -- cgit v1.2.3 From a31080899d5fdafcccf7f39dd214a814a2c82626 Mon Sep 17 00:00:00 2001 From: Thiago Rafael Becker Date: Fri, 17 Dec 2021 15:20:22 -0300 Subject: cifs: sanitize multiple delimiters in prepath mount.cifs can pass a device with multiple delimiters in it. This will cause rename(2) to fail with ENOENT. V2: - Make sanitize_path more readable. - Fix multiple delimiters between UNC and prepath. - Avoid a memory leak if a bad user starts putting a lot of delimiters in the path on purpose. BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=2031200 Fixes: 24e0a1eff9e2 ("cifs: switch to new mount api") Cc: stable@vger.kernel.org # 5.11+ Acked-by: Ronnie Sahlberg Signed-off-by: Thiago Rafael Becker Signed-off-by: Steve French --- fs/cifs/fs_context.c | 38 +++++++++++++++++++++++++++++++++++++- 1 file changed, 37 insertions(+), 1 deletion(-) diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c index 6a179ae753c1..e3ed25dc6f3f 100644 --- a/fs/cifs/fs_context.c +++ b/fs/cifs/fs_context.c @@ -434,6 +434,42 @@ out: return rc; } +/* + * Remove duplicate path delimiters. Windows is supposed to do that + * but there are some bugs that prevent rename from working if there are + * multiple delimiters. + * + * Returns a sanitized duplicate of @path. The caller is responsible for + * cleaning up the original. + */ +#define IS_DELIM(c) ((c) == '/' || (c) == '\\') +static char *sanitize_path(char *path) +{ + char *cursor1 = path, *cursor2 = path; + + /* skip all prepended delimiters */ + while (IS_DELIM(*cursor1)) + cursor1++; + + /* copy the first letter */ + *cursor2 = *cursor1; + + /* copy the remainder... */ + while (*(cursor1++)) { + /* ... skipping all duplicated delimiters */ + if (IS_DELIM(*cursor1) && IS_DELIM(*cursor2)) + continue; + *(++cursor2) = *cursor1; + } + + /* if the last character is a delimiter, skip it */ + if (IS_DELIM(*(cursor2 - 1))) + cursor2--; + + *(cursor2) = '\0'; + return kstrdup(path, GFP_KERNEL); +} + /* * Parse a devname into substrings and populate the ctx->UNC and ctx->prepath * fields with the result. Returns 0 on success and an error otherwise @@ -493,7 +529,7 @@ smb3_parse_devname(const char *devname, struct smb3_fs_context *ctx) if (!*pos) return 0; - ctx->prepath = kstrdup(pos, GFP_KERNEL); + ctx->prepath = sanitize_path(pos); if (!ctx->prepath) return -ENOMEM; -- cgit v1.2.3 From 8f556a326c93213927e683fc32bbf5be1b62540a Mon Sep 17 00:00:00 2001 From: Zqiang Date: Fri, 17 Dec 2021 15:42:07 +0800 Subject: locking/rtmutex: Fix incorrect condition in rtmutex_spin_on_owner() Optimistic spinning needs to be terminated when the spinning waiter is not longer the top waiter on the lock, but the condition is negated. It terminates if the waiter is the top waiter, which is defeating the whole purpose. Fixes: c3123c431447 ("locking/rtmutex: Dont dereference waiter lockless") Signed-off-by: Zqiang Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20211217074207.77425-1-qiang1.zhang@intel.com --- kernel/locking/rtmutex.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 0c6a48dfcecb..1f25a4d7de27 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1380,7 +1380,7 @@ static bool rtmutex_spin_on_owner(struct rt_mutex_base *lock, * - the VCPU on which owner runs is preempted */ if (!owner->on_cpu || need_resched() || - rt_mutex_waiter_is_top_waiter(lock, waiter) || + !rt_mutex_waiter_is_top_waiter(lock, waiter) || vcpu_is_preempted(task_cpu(owner))) { res = false; break; -- cgit v1.2.3 From 0a515a06c5ebfa46fee3ac519e418f801e718da4 Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Sun, 12 Dec 2021 06:25:02 +0000 Subject: perf expr: Fix missing check for return value of hashmap__new() The hashmap__new() function may return ERR_PTR(-ENOMEM) when malloc() fails, add IS_ERR() checking for ctx->ids. Signed-off-by: Miaoqian Lin Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20211212062504.25841-1-linmq006@gmail.com [ s/kfree()/free()/ and add missing linux/err.h include ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/expr.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index 1d532b9fed29..254601060b39 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -12,6 +12,7 @@ #include "expr-bison.h" #include "expr-flex.h" #include "smt.h" +#include #include #include #include @@ -299,6 +300,10 @@ struct expr_parse_ctx *expr__ctx_new(void) return NULL; ctx->ids = hashmap__new(key_hash, key_equal, NULL); + if (IS_ERR(ctx->ids)) { + free(ctx); + return NULL; + } ctx->runtime = 0; return ctx; -- cgit v1.2.3 From 0c8e32fe48f549eef27c8c6b0a63530f83c3a643 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 13 Dec 2021 10:48:28 +0200 Subject: perf inject: Fix segfault due to close without open The fixed commit attempts to close inject.output even if it was never opened e.g. $ perf record uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.002 MB perf.data (7 samples) ] $ perf inject -i perf.data --vm-time-correlation=dry-run Segmentation fault (core dumped) $ gdb --quiet perf Reading symbols from perf... (gdb) r inject -i perf.data --vm-time-correlation=dry-run Starting program: /home/ahunter/bin/perf inject -i perf.data --vm-time-correlation=dry-run [Thread debugging using libthread_db enabled] Using host libthread_db library "/lib/x86_64-linux-gnu/libthread_db.so.1". Program received signal SIGSEGV, Segmentation fault. 0x00007eff8afeef5b in _IO_new_fclose (fp=0x0) at iofclose.c:48 48 iofclose.c: No such file or directory. (gdb) bt #0 0x00007eff8afeef5b in _IO_new_fclose (fp=0x0) at iofclose.c:48 #1 0x0000557fc7b74f92 in perf_data__close (data=data@entry=0x7ffcdafa6578) at util/data.c:376 #2 0x0000557fc7a6b807 in cmd_inject (argc=, argv=) at builtin-inject.c:1085 #3 0x0000557fc7ac4783 in run_builtin (p=0x557fc8074878 , argc=4, argv=0x7ffcdafb6a60) at perf.c:313 #4 0x0000557fc7a25d5c in handle_internal_command (argv=, argc=) at perf.c:365 #5 run_argv (argcp=, argv=) at perf.c:409 #6 main (argc=4, argv=0x7ffcdafb6a60) at perf.c:539 (gdb) Fixes: 02e6246f5364d526 ("perf inject: Close inject.output on exit") Signed-off-by: Adrian Hunter Tested-by: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Namhyung Kim Cc: Riccardo Mancini Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/20211213084829.114772-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-inject.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index b9d6306cc14e..af70f1c72052 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -1078,7 +1078,8 @@ out_delete: zstd_fini(&(inject.session->zstd_data)); perf_session__delete(inject.session); out_close_output: - perf_data__close(&inject.output); + if (!inject.in_place_update) + perf_data__close(&inject.output); free(inject.itrace_synth_opts.vm_tm_corr_args); return ret; } -- cgit v1.2.3 From c271a55b0c6029fed0cac909fa57999a11467132 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 13 Dec 2021 10:48:29 +0200 Subject: perf inject: Fix segfault due to perf_data__fd() without open The fixed commit attempts to get the output file descriptor even if the file was never opened e.g. $ perf record uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.002 MB perf.data (7 samples) ] $ perf inject -i perf.data --vm-time-correlation=dry-run Segmentation fault (core dumped) $ gdb --quiet perf Reading symbols from perf... (gdb) r inject -i perf.data --vm-time-correlation=dry-run Starting program: /home/ahunter/bin/perf inject -i perf.data --vm-time-correlation=dry-run [Thread debugging using libthread_db enabled] Using host libthread_db library "/lib/x86_64-linux-gnu/libthread_db.so.1". Program received signal SIGSEGV, Segmentation fault. __GI___fileno (fp=0x0) at fileno.c:35 35 fileno.c: No such file or directory. (gdb) bt #0 __GI___fileno (fp=0x0) at fileno.c:35 #1 0x00005621e48dd987 in perf_data__fd (data=0x7fff4c68bd08) at util/data.h:72 #2 perf_data__fd (data=0x7fff4c68bd08) at util/data.h:69 #3 cmd_inject (argc=, argv=0x7fff4c69c1f0) at builtin-inject.c:1017 #4 0x00005621e4936783 in run_builtin (p=0x5621e4ee6878 , argc=4, argv=0x7fff4c69c1f0) at perf.c:313 #5 0x00005621e4897d5c in handle_internal_command (argv=, argc=) at perf.c:365 #6 run_argv (argcp=, argv=) at perf.c:409 #7 main (argc=4, argv=0x7fff4c69c1f0) at perf.c:539 (gdb) Fixes: 0ae03893623dd1dd ("perf tools: Pass a fd to perf_file_header__read_pipe()") Signed-off-by: Adrian Hunter Tested-by: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Namhyung Kim Cc: Riccardo Mancini Cc: stable@vger.kernel.org Link: http://lore.kernel.org/lkml/20211213084829.114772-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-inject.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index af70f1c72052..409b721666cb 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -755,12 +755,16 @@ static int parse_vm_time_correlation(const struct option *opt, const char *str, return inject->itrace_synth_opts.vm_tm_corr_args ? 0 : -ENOMEM; } +static int output_fd(struct perf_inject *inject) +{ + return inject->in_place_update ? -1 : perf_data__fd(&inject->output); +} + static int __cmd_inject(struct perf_inject *inject) { int ret = -EINVAL; struct perf_session *session = inject->session; - struct perf_data *data_out = &inject->output; - int fd = inject->in_place_update ? -1 : perf_data__fd(data_out); + int fd = output_fd(inject); u64 output_data_offset; signal(SIGINT, sig_handler); @@ -1015,7 +1019,7 @@ int cmd_inject(int argc, const char **argv) } inject.session = __perf_session__new(&data, repipe, - perf_data__fd(&inject.output), + output_fd(&inject), &inject.tool); if (IS_ERR(inject.session)) { ret = PTR_ERR(inject.session); -- cgit v1.2.3 From 87959fa16cfbcf76245c11559db1940069621274 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 19 Dec 2021 07:58:44 -0700 Subject: Revert "block: reduce kblockd_mod_delayed_work_on() CPU consumption" This reverts commit cb2ac2912a9ca7d3d26291c511939a41361d2d83. Alex and the kernel test robot report that this causes a significant performance regression with BFQ. I can reproduce that result, so let's revert this one as we're close to -rc6 and we there's no point in trying to rush a fix. Link: https://lore.kernel.org/linux-block/1639853092.524jxfaem2.none@localhost/ Link: https://lore.kernel.org/lkml/20211219141852.GH14057@xsang-OptiPlex-9020/ Reported-by: Alex Xu (Hello71) Reported-by: kernel test robot Signed-off-by: Jens Axboe --- block/blk-core.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index c1833f95cb97..1378d084c770 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1484,8 +1484,6 @@ EXPORT_SYMBOL(kblockd_schedule_work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay) { - if (!delay) - return queue_work_on(cpu, kblockd_workqueue, &dwork->work); return mod_delayed_work_on(cpu, kblockd_workqueue, dwork, delay); } EXPORT_SYMBOL(kblockd_mod_delayed_work_on); -- cgit v1.2.3 From 1aa2abb33a419090c7c87d4ae842a6347078ee12 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Thu, 16 Dec 2021 17:52:13 +0100 Subject: KVM: x86: Drop guest CPUID check for host initiated writes to MSR_IA32_PERF_CAPABILITIES The ability to write to MSR_IA32_PERF_CAPABILITIES from the host should not depend on guest visible CPUID entries, even if just to allow creating/restoring guest MSRs and CPUIDs in any sequence. Fixes: 27461da31089 ("KVM: x86/pmu: Support full width counting") Suggested-by: Sean Christopherson Signed-off-by: Vitaly Kuznetsov Message-Id: <20211216165213.338923-3-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0cf1082455df..9a2972fdae82 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3413,7 +3413,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated) return 1; - if (guest_cpuid_has(vcpu, X86_FEATURE_PDCM) && kvm_get_msr_feature(&msr_ent)) + if (kvm_get_msr_feature(&msr_ent)) return 1; if (data & ~msr_ent.data) return 1; -- cgit v1.2.3 From 0b091a43d704997789c6d812b02167c8f5f9f061 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Thu, 16 Dec 2021 17:52:12 +0100 Subject: KVM: selftests: vmx_pmu_msrs_test: Drop tests mangling guest visible CPUIDs Host initiated writes to MSR_IA32_PERF_CAPABILITIES should not depend on guest visible CPUIDs and (incorrect) KVM logic implementing it is about to change. Also, KVM_SET_CPUID{,2} after KVM_RUN is now forbidden and causes test to fail. Reported-by: kernel test robot Fixes: feb627e8d6f6 ("KVM: x86: Forbid KVM_SET_CPUID{,2} after KVM_RUN") Signed-off-by: Vitaly Kuznetsov Message-Id: <20211216165213.338923-2-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/x86_64/vmx_pmu_msrs_test.c | 17 ----------------- 1 file changed, 17 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_msrs_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_msrs_test.c index 23051d84b907..2454a1f2ca0c 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_msrs_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_msrs_test.c @@ -110,22 +110,5 @@ int main(int argc, char *argv[]) ret = _vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_LBR_FMT); TEST_ASSERT(ret == 0, "Bad PERF_CAPABILITIES didn't fail."); - /* testcase 4, set capabilities when we don't have PDCM bit */ - entry_1_0->ecx &= ~X86_FEATURE_PDCM; - vcpu_set_cpuid(vm, VCPU_ID, cpuid); - ret = _vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); - TEST_ASSERT(ret == 0, "Bad PERF_CAPABILITIES didn't fail."); - - /* testcase 5, set capabilities when we don't have PMU version bits */ - entry_1_0->ecx |= X86_FEATURE_PDCM; - eax.split.version_id = 0; - entry_1_0->ecx = eax.full; - vcpu_set_cpuid(vm, VCPU_ID, cpuid); - ret = _vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_FW_WRITES); - TEST_ASSERT(ret == 0, "Bad PERF_CAPABILITIES didn't fail."); - - vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, 0); - ASSERT_EQ(vcpu_get_msr(vm, VCPU_ID, MSR_IA32_PERF_CAPABILITIES), 0); - kvm_vm_free(vm); } -- cgit v1.2.3 From 18c841e1f4112d3fb742aca3429e84117fcb1e1c Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 9 Dec 2021 06:05:46 +0000 Subject: KVM: x86: Retry page fault if MMU reload is pending and root has no sp Play nice with a NULL shadow page when checking for an obsolete root in the page fault handler by flagging the page fault as stale if there's no shadow page associated with the root and KVM_REQ_MMU_RELOAD is pending. Invalidating memslots, which is the only case where _all_ roots need to be reloaded, requests all vCPUs to reload their MMUs while holding mmu_lock for lock. The "special" roots, e.g. pae_root when KVM uses PAE paging, are not backed by a shadow page. Running with TDP disabled or with nested NPT explodes spectaculary due to dereferencing a NULL shadow page pointer. Skip the KVM_REQ_MMU_RELOAD check if there is a valid shadow page for the root. Zapping shadow pages in response to guest activity, e.g. when the guest frees a PGD, can trigger KVM_REQ_MMU_RELOAD even if the current vCPU isn't using the affected root. I.e. KVM_REQ_MMU_RELOAD can be seen with a completely valid root shadow page. This is a bit of a moot point as KVM currently unloads all roots on KVM_REQ_MMU_RELOAD, but that will be cleaned up in the future. Fixes: a955cad84cda ("KVM: x86/mmu: Retry page fault if root is invalidated by memslot update") Cc: stable@vger.kernel.org Cc: Maxim Levitsky Signed-off-by: Sean Christopherson Message-Id: <20211209060552.2956723-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index e2e1d012df22..fcdf3f8bb59a 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3987,7 +3987,21 @@ out_retry: static bool is_page_fault_stale(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, int mmu_seq) { - if (is_obsolete_sp(vcpu->kvm, to_shadow_page(vcpu->arch.mmu->root_hpa))) + struct kvm_mmu_page *sp = to_shadow_page(vcpu->arch.mmu->root_hpa); + + /* Special roots, e.g. pae_root, are not backed by shadow pages. */ + if (sp && is_obsolete_sp(vcpu->kvm, sp)) + return true; + + /* + * Roots without an associated shadow page are considered invalid if + * there is a pending request to free obsolete roots. The request is + * only a hint that the current root _may_ be obsolete and needs to be + * reloaded, e.g. if the guest frees a PGD that KVM is tracking as a + * previous root, then __kvm_mmu_prepare_zap_page() signals all vCPUs + * to reload even if no vCPU is actively using the root. + */ + if (!sp && kvm_test_request(KVM_REQ_MMU_RELOAD, vcpu)) return true; return fault->slot && -- cgit v1.2.3 From a7904a538933c525096ca2ccde1e60d0ee62c08e Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 19 Dec 2021 14:14:33 -0800 Subject: Linux 5.16-rc6 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 765115c99655..d85f1ff79f5c 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 16 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Gobble Gobble # *DOCUMENTATION* -- cgit v1.2.3