From: Uwe Kleine-König u.kleine-koenig@pengutronix.de

[ Upstream commit 7ef9651e9792b08eb310c6beb202cbc947f43cab ]

When a driver keeps a clock prepared (or enabled) during the whole lifetime of the driver, these helpers allow to simplify the drivers.

Reviewed-by: Jonathan Cameron Jonathan.Cameron@huawei.com Reviewed-by: Alexandru Ardelean aardelean@deviqon.com Signed-off-by: Uwe Kleine-König u.kleine-koenig@pengutronix.de Link: https://lore.kernel.org/r/20220520075737.758761-4-u.kleine-koenig@pengutroni... Signed-off-by: Stephen Boyd sboyd@kernel.org Stable-dep-of: 340cb392a038 ("memory: atmel-sdramc: Fix missing clk_disable_unprepare in atmel_ramc_probe()") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/clk/clk-devres.c | 27 ++++++++++ include/linux/clk.h | 109 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 136 insertions(+)

diff --git a/drivers/clk/clk-devres.c b/drivers/clk/clk-devres.c index c822f4ef1584..43ccd20e0298 100644 --- a/drivers/clk/clk-devres.c +++ b/drivers/clk/clk-devres.c @@ -66,12 +66,39 @@ struct clk *devm_clk_get(struct device *dev, const char *id) } EXPORT_SYMBOL(devm_clk_get);

+struct clk *devm_clk_get_prepared(struct device *dev, const char *id) +{ + return __devm_clk_get(dev, id, clk_get, clk_prepare, clk_unprepare); +} +EXPORT_SYMBOL_GPL(devm_clk_get_prepared); + +struct clk *devm_clk_get_enabled(struct device *dev, const char *id) +{ + return __devm_clk_get(dev, id, clk_get, + clk_prepare_enable, clk_disable_unprepare); +} +EXPORT_SYMBOL_GPL(devm_clk_get_enabled); + struct clk *devm_clk_get_optional(struct device *dev, const char *id) { return __devm_clk_get(dev, id, clk_get_optional, NULL, NULL); } EXPORT_SYMBOL(devm_clk_get_optional);

+struct clk *devm_clk_get_optional_prepared(struct device *dev, const char *id) +{ + return __devm_clk_get(dev, id, clk_get_optional, + clk_prepare, clk_unprepare); +} +EXPORT_SYMBOL_GPL(devm_clk_get_optional_prepared); + +struct clk *devm_clk_get_optional_enabled(struct device *dev, const char *id) +{ + return __devm_clk_get(dev, id, clk_get_optional, + clk_prepare_enable, clk_disable_unprepare); +} +EXPORT_SYMBOL_GPL(devm_clk_get_optional_enabled); + struct clk_bulk_devres { struct clk_bulk_data *clks; int num_clks; diff --git a/include/linux/clk.h b/include/linux/clk.h index 18b7b95a8253..87730337e28f 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -418,6 +418,47 @@ int __must_check devm_clk_bulk_get_all(struct device *dev, */ struct clk *devm_clk_get(struct device *dev, const char *id);

+/** + * devm_clk_get_prepared - devm_clk_get() + clk_prepare() + * @dev: device for clock "consumer" + * @id: clock consumer ID + * + * Context: May sleep. + * + * Return: a struct clk corresponding to the clock producer, or + * valid IS_ERR() condition containing errno. The implementation + * uses @dev and @id to determine the clock consumer, and thereby + * the clock producer. (IOW, @id may be identical strings, but + * clk_get may return different clock producers depending on @dev.) + * + * The returned clk (if valid) is prepared. Drivers must however assume + * that the clock is not enabled. + * + * The clock will automatically be unprepared and freed when the device + * is unbound from the bus. + */ +struct clk *devm_clk_get_prepared(struct device *dev, const char *id); + +/** + * devm_clk_get_enabled - devm_clk_get() + clk_prepare_enable() + * @dev: device for clock "consumer" + * @id: clock consumer ID + * + * Context: May sleep. + * + * Return: a struct clk corresponding to the clock producer, or + * valid IS_ERR() condition containing errno. The implementation + * uses @dev and @id to determine the clock consumer, and thereby + * the clock producer. (IOW, @id may be identical strings, but + * clk_get may return different clock producers depending on @dev.) + * + * The returned clk (if valid) is prepared and enabled. + * + * The clock will automatically be disabled, unprepared and freed + * when the device is unbound from the bus. + */ +struct clk *devm_clk_get_enabled(struct device *dev, const char *id); + /** * devm_clk_get_optional - lookup and obtain a managed reference to an optional * clock producer. @@ -429,6 +470,50 @@ struct clk *devm_clk_get(struct device *dev, const char *id); */ struct clk *devm_clk_get_optional(struct device *dev, const char *id);

+/** + * devm_clk_get_optional_prepared - devm_clk_get_optional() + clk_prepare() + * @dev: device for clock "consumer" + * @id: clock consumer ID + * + * Context: May sleep. + * + * Return: a struct clk corresponding to the clock producer, or + * valid IS_ERR() condition containing errno. The implementation + * uses @dev and @id to determine the clock consumer, and thereby + * the clock producer. If no such clk is found, it returns NULL + * which serves as a dummy clk. That's the only difference compared + * to devm_clk_get_prepared(). + * + * The returned clk (if valid) is prepared. Drivers must however + * assume that the clock is not enabled. + * + * The clock will automatically be unprepared and freed when the + * device is unbound from the bus. + */ +struct clk *devm_clk_get_optional_prepared(struct device *dev, const char *id); + +/** + * devm_clk_get_optional_enabled - devm_clk_get_optional() + + * clk_prepare_enable() + * @dev: device for clock "consumer" + * @id: clock consumer ID + * + * Context: May sleep. + * + * Return: a struct clk corresponding to the clock producer, or + * valid IS_ERR() condition containing errno. The implementation + * uses @dev and @id to determine the clock consumer, and thereby + * the clock producer. If no such clk is found, it returns NULL + * which serves as a dummy clk. That's the only difference compared + * to devm_clk_get_enabled(). + * + * The returned clk (if valid) is prepared and enabled. + * + * The clock will automatically be disabled, unprepared and freed + * when the device is unbound from the bus. + */ +struct clk *devm_clk_get_optional_enabled(struct device *dev, const char *id); + /** * devm_get_clk_from_child - lookup and obtain a managed reference to a * clock producer from child node. @@ -770,12 +855,36 @@ static inline struct clk *devm_clk_get(struct device *dev, const char *id) return NULL; }

+static inline struct clk *devm_clk_get_prepared(struct device *dev, + const char *id) +{ + return NULL; +} + +static inline struct clk *devm_clk_get_enabled(struct device *dev, + const char *id) +{ + return NULL; +} + static inline struct clk *devm_clk_get_optional(struct device *dev, const char *id) { return NULL; }

+static inline struct clk *devm_clk_get_optional_prepared(struct device *dev, + const char *id) +{ + return NULL; +} + +static inline struct clk *devm_clk_get_optional_enabled(struct device *dev, + const char *id) +{ + return NULL; +} + static inline int __must_check devm_clk_bulk_get(struct device *dev, int num_clks, struct clk_bulk_data *clks) {

From: Gaosheng Cui cuigaosheng1@huawei.com

[ Upstream commit cb8fd6f75775165390ededea8799b60d93d9fe3e ]

The clk_disable_unprepare() should be called in the error handling of devbus_get_timing_params() and of_platform_populate(), fix it by replacing devm_clk_get and clk_prepare_enable by devm_clk_get_enabled.

Fixes: e81b6abebc87 ("memory: add a driver for atmel ram controllers") Signed-off-by: Gaosheng Cui cuigaosheng1@huawei.com Link: https://lore.kernel.org/r/20221126044911.7226-1-cuigaosheng1@huawei.com Signed-off-by: Krzysztof Kozlowski krzysztof.kozlowski@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/memory/mvebu-devbus.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/memory/mvebu-devbus.c b/drivers/memory/mvebu-devbus.c index 095f8a3b2cfc..9bf477b000c0 100644 --- a/drivers/memory/mvebu-devbus.c +++ b/drivers/memory/mvebu-devbus.c @@ -282,10 +282,9 @@ static int mvebu_devbus_probe(struct platform_device *pdev) if (IS_ERR(devbus->base)) return PTR_ERR(devbus->base);

- clk = devm_clk_get(&pdev->dev, NULL); + clk = devm_clk_get_enabled(&pdev->dev, NULL); if (IS_ERR(clk)) return PTR_ERR(clk); - clk_prepare_enable(clk);

/* * Obtain clock period in picoseconds,

From: Fabio Estevam festevam@gmail.com

[ Upstream commit 94b2bec1b0e054b27b0a0b5f52a0cd55c83340f4 ]

Now that imx27 has been converted to a devicetree-only platform, retrieve the SYSCTRL base address from devicetree.

To keep devicetree compatibilty the SYSCTRL base address will be retrieved from the CCM base address plus an 0x800 offset.

This is not a problem as the imx27.dtsi describes the CCM register range as 0x1000.

Signed-off-by: Fabio Estevam festevam@gmail.com Acked-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Shawn Guo shawnguo@kernel.org Stable-dep-of: 87b30c4b0efb ("ARM: imx: add missing of_node_put()") Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/mach-imx/cpu-imx27.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/arch/arm/mach-imx/cpu-imx27.c b/arch/arm/mach-imx/cpu-imx27.c index a969aa71b60f..bf70e13bbe9e 100644 --- a/arch/arm/mach-imx/cpu-imx27.c +++ b/arch/arm/mach-imx/cpu-imx27.c @@ -9,6 +9,7 @@ */

#include <linux/io.h> +#include <linux/of_address.h> #include <linux/module.h>

#include "hardware.h" @@ -17,16 +18,23 @@ static int mx27_cpu_rev = -1; static int mx27_cpu_partnumber;

#define SYS_CHIP_ID 0x00 /* The offset of CHIP ID register */ +#define SYSCTRL_OFFSET 0x800 /* Offset from CCM base address */

static int mx27_read_cpu_rev(void) { + void __iomem *ccm_base; + struct device_node *np; u32 val; + + np = of_find_compatible_node(NULL, NULL, "fsl,imx27-ccm"); + ccm_base = of_iomap(np, 0); + BUG_ON(!ccm_base); /* * now we have access to the IO registers. As we need * the silicon revision very early we read it here to * avoid any further hooks */ - val = imx_readl(MX27_IO_ADDRESS(MX27_SYSCTRL_BASE_ADDR + SYS_CHIP_ID)); + val = imx_readl(ccm_base + SYSCTRL_OFFSET + SYS_CHIP_ID);

mx27_cpu_partnumber = (int)((val >> 12) & 0xFFFF);

From: Fabio Estevam festevam@gmail.com

[ Upstream commit f68ea682d1da77e0133a7726640c22836a900a67 ]

Now that imx35 has been converted to a devicetree-only platform, retrieve the IIM base address from devicetree.

Signed-off-by: Fabio Estevam festevam@gmail.com Acked-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Shawn Guo shawnguo@kernel.org Stable-dep-of: 87b30c4b0efb ("ARM: imx: add missing of_node_put()") Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/mach-imx/cpu-imx35.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/arch/arm/mach-imx/cpu-imx35.c b/arch/arm/mach-imx/cpu-imx35.c index ebb3cdabd506..80e7d8ab9f1b 100644 --- a/arch/arm/mach-imx/cpu-imx35.c +++ b/arch/arm/mach-imx/cpu-imx35.c @@ -5,6 +5,7 @@ * Copyright (c) 2009 Daniel Mack daniel@caiaq.de */ #include <linux/module.h> +#include <linux/of_address.h> #include <linux/io.h>

#include "hardware.h" @@ -14,9 +15,15 @@ static int mx35_cpu_rev = -1;

static int mx35_read_cpu_rev(void) { + void __iomem *iim_base; + struct device_node *np; u32 rev;

- rev = imx_readl(MX35_IO_ADDRESS(MX35_IIM_BASE_ADDR + MXC_IIMSREV)); + np = of_find_compatible_node(NULL, NULL, "fsl,imx35-iim"); + iim_base = of_iomap(np, 0); + BUG_ON(!iim_base); + + rev = imx_readl(iim_base + MXC_IIMSREV); switch (rev) { case 0x00: return IMX_CHIP_REVISION_1_0;

From: Jiasheng Jiang jiasheng@iscas.ac.cn

[ Upstream commit b3d40c3ec3dc4ad78017de6c3a38979f57aaaab8 ]

As the kcalloc may return NULL pointer, it should be better to check the ishtp_dma_tx_map before use in order to avoid NULL pointer dereference.

Fixes: 3703f53b99e4 ("HID: intel_ish-hid: ISH Transport layer") Signed-off-by: Jiasheng Jiang jiasheng@iscas.ac.cn Acked-by: Srinivas Pandruvada srinivas.pandruvada@linux.intel.com Signed-off-by: Jiri Kosina jkosina@suse.cz Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hid/intel-ish-hid/ishtp/dma-if.c | 10 ++++++++++ 1 file changed, 10 insertions(+)

diff --git a/drivers/hid/intel-ish-hid/ishtp/dma-if.c b/drivers/hid/intel-ish-hid/ishtp/dma-if.c index 40554c8daca0..00046cbfd4ed 100644 --- a/drivers/hid/intel-ish-hid/ishtp/dma-if.c +++ b/drivers/hid/intel-ish-hid/ishtp/dma-if.c @@ -104,6 +104,11 @@ void *ishtp_cl_get_dma_send_buf(struct ishtp_device *dev, int required_slots = (size / DMA_SLOT_SIZE) + 1 * (size % DMA_SLOT_SIZE != 0);

+ if (!dev->ishtp_dma_tx_map) { + dev_err(dev->devc, "Fail to allocate Tx map\n"); + return NULL; + } + spin_lock_irqsave(&dev->ishtp_dma_tx_lock, flags); for (i = 0; i <= (dev->ishtp_dma_num_slots - required_slots); i++) { free = 1; @@ -150,6 +155,11 @@ void ishtp_cl_release_dma_acked_mem(struct ishtp_device *dev, return; }

+ if (!dev->ishtp_dma_tx_map) { + dev_err(dev->devc, "Fail to allocate Tx map\n"); + return; + } + i = (msg_addr - dev->ishtp_host_dma_tx_buf) / DMA_SLOT_SIZE; spin_lock_irqsave(&dev->ishtp_dma_tx_lock, flags); for (j = 0; j < acked_slots; j++) {

From: Masahiro Yamada masahiroy@kernel.org

[ Upstream commit eaf2213ba563b2d74a1f2c13a6b258273f689802 ]

If *.conf.default is updated, builtin-policy.h should be rebuilt, but this does not work when compiled with O= option.

[Without this commit]

$ touch security/tomoyo/policy/exception_policy.conf.default $ make O=/tmp security/tomoyo/ make[1]: Entering directory '/tmp' GEN Makefile CALL /home/masahiro/ref/linux/scripts/checksyscalls.sh DESCEND objtool make[1]: Leaving directory '/tmp'

[With this commit]

$ touch security/tomoyo/policy/exception_policy.conf.default $ make O=/tmp security/tomoyo/ make[1]: Entering directory '/tmp' GEN Makefile CALL /home/masahiro/ref/linux/scripts/checksyscalls.sh DESCEND objtool POLICY security/tomoyo/builtin-policy.h CC security/tomoyo/common.o AR security/tomoyo/built-in.a make[1]: Leaving directory '/tmp'

$(srctree)/ is essential because $(wildcard ) does not follow VPATH.

Fixes: f02dee2d148b ("tomoyo: Do not generate empty policy files") Signed-off-by: Masahiro Yamada masahiroy@kernel.org Signed-off-by: Tetsuo Handa penguin-kernel@I-love.SAKURA.ne.jp Signed-off-by: Sasha Levin sashal@kernel.org --- security/tomoyo/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/security/tomoyo/Makefile b/security/tomoyo/Makefile index cca5a3012fee..221eaadffb09 100644 --- a/security/tomoyo/Makefile +++ b/security/tomoyo/Makefile @@ -10,7 +10,7 @@ endef quiet_cmd_policy = POLICY $@ cmd_policy = ($(call do_policy,profile); $(call do_policy,exception_policy); $(call do_policy,domain_policy); $(call do_policy,manager); $(call do_policy,stat)) >$@

-$(obj)/builtin-policy.h: $(wildcard $(obj)/policy/*.conf $(src)/policy/*.conf.default) FORCE +$(obj)/builtin-policy.h: $(wildcard $(obj)/policy/*.conf $(srctree)/$(src)/policy/*.conf.default) FORCE $(call if_changed,policy)

$(obj)/common.o: $(obj)/builtin-policy.h

From: Dean Luick dean.luick@cornelisnetworks.com

[ Upstream commit 0a0a6e80472c98947d73c3d13bcd7d101895f55d ]

A zero length user buffer makes no sense and the code does not handle it correctly. Instead, reject a zero length as invalid.

Fixes: 97736f36dbeb ("IB/hfi1: Validate page aligned for a given virtual addres") Signed-off-by: Dean Luick dean.luick@cornelisnetworks.com Signed-off-by: Dennis Dalessandro dennis.dalessandro@cornelisnetworks.com Link: https://lore.kernel.org/r/167328547120.1472310.6362802432127399257.stgit@awf... Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/hfi1/user_exp_rcv.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c index 4d732353379d..28f1b3c37a4f 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c @@ -325,6 +325,8 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,

if (!PAGE_ALIGNED(tinfo->vaddr)) return -EINVAL; + if (tinfo->length == 0) + return -EINVAL;

tidbuf = kzalloc(sizeof(*tidbuf), GFP_KERNEL); if (!tidbuf)

From: Dean Luick dean.luick@cornelisnetworks.com

[ Upstream commit e0c4a422f5246abefbf7c178ef99a1f2dc3c5f62 ]

Fix three error exit issues in expected receive setup. Re-arrange error exits to increase readability.

Issues and fixes: 1. Possible missed page unpin if tidlist copyout fails and not all pinned pages where made part of a TID. Fix: Unpin the unused pages.

2. Return success with unset return values tidcnt and length when no pages were pinned. Fix: Return -ENOSPC if no pages were pinned.

3. Return success with unset return values tidcnt and length when no rcvarray entries available. Fix: Return -ENOSPC if no rcvarray entries are available.

Fixes: 7e7a436ecb6e ("staging/hfi1: Add TID entry program function body") Fixes: 97736f36dbeb ("IB/hfi1: Validate page aligned for a given virtual addres") Fixes: f404ca4c7ea8 ("IB/hfi1: Refactor hfi_user_exp_rcv_setup() IOCTL") Signed-off-by: Dean Luick dean.luick@cornelisnetworks.com Signed-off-by: Dennis Dalessandro dennis.dalessandro@cornelisnetworks.com Link: https://lore.kernel.org/r/167328548150.1472310.1492305874804187634.stgit@awf... Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/hfi1/user_exp_rcv.c | 83 ++++++++++++++--------- 1 file changed, 50 insertions(+), 33 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c index 7623cb61ec4c..e7daa65589ab 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c @@ -337,15 +337,14 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd, tidbuf->psets = kcalloc(uctxt->expected_count, sizeof(*tidbuf->psets), GFP_KERNEL); if (!tidbuf->psets) { - kfree(tidbuf); - return -ENOMEM; + ret = -ENOMEM; + goto fail_release_mem; }

pinned = pin_rcv_pages(fd, tidbuf); if (pinned <= 0) { - kfree(tidbuf->psets); - kfree(tidbuf); - return pinned; + ret = (pinned < 0) ? pinned : -ENOSPC; + goto fail_unpin; }

/* Find sets of physically contiguous pages */ @@ -360,14 +359,16 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd, fd->tid_used += pageset_count; spin_unlock(&fd->tid_lock);

- if (!pageset_count) - goto bail; + if (!pageset_count) { + ret = -ENOSPC; + goto fail_unreserve; + }

ngroups = pageset_count / dd->rcv_entries.group_size; tidlist = kcalloc(pageset_count, sizeof(*tidlist), GFP_KERNEL); if (!tidlist) { ret = -ENOMEM; - goto nomem; + goto fail_unreserve; }

tididx = 0; @@ -463,44 +464,60 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd, } unlock: mutex_unlock(&uctxt->exp_mutex); -nomem: hfi1_cdbg(TID, "total mapped: tidpairs:%u pages:%u (%d)", tididx, mapped_pages, ret); + + /* fail if nothing was programmed, set error if none provided */ + if (tididx == 0) { + if (ret >= 0) + ret = -ENOSPC; + goto fail_unreserve; + } + /* adjust reserved tid_used to actual count */ spin_lock(&fd->tid_lock); fd->tid_used -= pageset_count - tididx; spin_unlock(&fd->tid_lock); - if (tididx) { - tinfo->tidcnt = tididx; - tinfo->length = mapped_pages * PAGE_SIZE;

- if (copy_to_user(u64_to_user_ptr(tinfo->tidlist), - tidlist, sizeof(tidlist[0]) * tididx)) { - /* - * On failure to copy to the user level, we need to undo - * everything done so far so we don't leak resources. - */ - tinfo->tidlist = (unsigned long)&tidlist; - hfi1_user_exp_rcv_clear(fd, tinfo); - tinfo->tidlist = 0; - ret = -EFAULT; - goto bail; - } + /* unpin all pages not covered by a TID */ + unpin_rcv_pages(fd, tidbuf, NULL, mapped_pages, pinned - mapped_pages, + false); + + tinfo->tidcnt = tididx; + tinfo->length = mapped_pages * PAGE_SIZE; + + if (copy_to_user(u64_to_user_ptr(tinfo->tidlist), + tidlist, sizeof(tidlist[0]) * tididx)) { + ret = -EFAULT; + goto fail_unprogram; }

- /* - * If not everything was mapped (due to insufficient RcvArray entries, - * for example), unpin all unmapped pages so we can pin them nex time. - */ - if (mapped_pages != pinned) - unpin_rcv_pages(fd, tidbuf, NULL, mapped_pages, - (pinned - mapped_pages), false); -bail: + kfree(tidbuf->pages); kfree(tidbuf->psets); + kfree(tidbuf); kfree(tidlist); + return 0; + +fail_unprogram: + /* unprogram, unmap, and unpin all allocated TIDs */ + tinfo->tidlist = (unsigned long)tidlist; + hfi1_user_exp_rcv_clear(fd, tinfo); + tinfo->tidlist = 0; + pinned = 0; /* nothing left to unpin */ + pageset_count = 0; /* nothing left reserved */ +fail_unreserve: + spin_lock(&fd->tid_lock); + fd->tid_used -= pageset_count; + spin_unlock(&fd->tid_lock); +fail_unpin: + if (pinned > 0) + unpin_rcv_pages(fd, tidbuf, NULL, 0, pinned, false); +fail_release_mem: kfree(tidbuf->pages); + kfree(tidbuf->psets); kfree(tidbuf); - return ret > 0 ? 0 : ret; + kfree(tidlist); + return ret; }

int hfi1_user_exp_rcv_clear(struct hfi1_filedata *fd,

From: Raju Rangoju Raju.Rangoju@amd.com

[ Upstream commit 579923d84b04abb6cd4cd1fd9974096a2dd1832b ]

There is difference in the TX Flow Control registers (TFCR) between the revisions of the hardware. The older revisions of hardware used to have single register per queue. Whereas, the newer revision of hardware (from ver 30H onwards) have one register per priority.

Update the driver to use the TFCR based on the reported version of the hardware.

Fixes: c5aa9e3b8156 ("amd-xgbe: Initial AMD 10GbE platform driver") Co-developed-by: Ajith Nayak Ajith.Nayak@amd.com Signed-off-by: Ajith Nayak Ajith.Nayak@amd.com Signed-off-by: Raju Rangoju Raju.Rangoju@amd.com Acked-by: Shyam Sundar S K Shyam-sundar.S-k@amd.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/amd/xgbe/xgbe-dev.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index d5fd49dd25f3..decc1c09a031 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -524,19 +524,28 @@ static void xgbe_disable_vxlan(struct xgbe_prv_data *pdata) netif_dbg(pdata, drv, pdata->netdev, "VXLAN acceleration disabled\n"); }

+static unsigned int xgbe_get_fc_queue_count(struct xgbe_prv_data *pdata) +{ + unsigned int max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES; + + /* From MAC ver 30H the TFCR is per priority, instead of per queue */ + if (XGMAC_GET_BITS(pdata->hw_feat.version, MAC_VR, SNPSVER) >= 0x30) + return max_q_count; + else + return min_t(unsigned int, pdata->tx_q_count, max_q_count); +} + static int xgbe_disable_tx_flow_control(struct xgbe_prv_data *pdata) { - unsigned int max_q_count, q_count; unsigned int reg, reg_val; - unsigned int i; + unsigned int i, q_count;

/* Clear MTL flow control */ for (i = 0; i < pdata->rx_q_count; i++) XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQOMR, EHFC, 0);

/* Clear MAC flow control */ - max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES; - q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count); + q_count = xgbe_get_fc_queue_count(pdata); reg = MAC_Q0TFCR; for (i = 0; i < q_count; i++) { reg_val = XGMAC_IOREAD(pdata, reg); @@ -553,9 +562,8 @@ static int xgbe_enable_tx_flow_control(struct xgbe_prv_data *pdata) { struct ieee_pfc *pfc = pdata->pfc; struct ieee_ets *ets = pdata->ets; - unsigned int max_q_count, q_count; unsigned int reg, reg_val; - unsigned int i; + unsigned int i, q_count;

/* Set MTL flow control */ for (i = 0; i < pdata->rx_q_count; i++) { @@ -579,8 +587,7 @@ static int xgbe_enable_tx_flow_control(struct xgbe_prv_data *pdata) }

/* Set MAC flow control */ - max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES; - q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count); + q_count = xgbe_get_fc_queue_count(pdata); reg = MAC_Q0TFCR; for (i = 0; i < q_count; i++) { reg_val = XGMAC_IOREAD(pdata, reg);

From: Luis Gerhorst gerhorst@cs.fau.de

[ Upstream commit e4f4db47794c9f474b184ee1418f42e6a07412b6 ]

To mitigate Spectre v4, 2039f26f3aca ("bpf: Fix leakage due to insufficient speculative store bypass mitigation") inserts lfence instructions after 1) initializing a stack slot and 2) spilling a pointer to the stack.

However, this does not cover cases where a stack slot is first initialized with a pointer (subject to sanitization) but then overwritten with a scalar (not subject to sanitization because the slot was already initialized). In this case, the second write may be subject to speculative store bypass (SSB) creating a speculative pointer-as-scalar type confusion. This allows the program to subsequently leak the numerical pointer value using, for example, a branch-based cache side channel.

To fix this, also sanitize scalars if they write a stack slot that previously contained a pointer. Assuming that pointer-spills are only generated by LLVM on register-pressure, the performance impact on most real-world BPF programs should be small.

The following unprivileged BPF bytecode drafts a minimal exploit and the mitigation:

[...] // r6 = 0 or 1 (skalar, unknown user input) // r7 = accessible ptr for side channel // r10 = frame pointer (fp), to be leaked // r9 = r10 # fp alias to encourage ssb *(u64 *)(r9 - 8) = r10 // fp[-8] = ptr, to be leaked // lfence added here because of pointer spill to stack. // // Ommitted: Dummy bpf_ringbuf_output() here to train alias predictor // for no r9-r10 dependency. // *(u64 *)(r10 - 8) = r6 // fp[-8] = scalar, overwrites ptr // 2039f26f3aca: no lfence added because stack slot was not STACK_INVALID, // store may be subject to SSB // // fix: also add an lfence when the slot contained a ptr // r8 = *(u64 *)(r9 - 8) // r8 = architecturally a scalar, speculatively a ptr // // leak ptr using branch-based cache side channel: r8 &= 1 // choose bit to leak if r8 == 0 goto SLOW // no mispredict // architecturally dead code if input r6 is 0, // only executes speculatively iff ptr bit is 1 r8 = *(u64 *)(r7 + 0) # encode bit in cache (0: slow, 1: fast) SLOW: [...]

After running this, the program can time the access to *(r7 + 0) to determine whether the chosen pointer bit was 0 or 1. Repeat this 64 times to recover the whole address on amd64.

In summary, sanitization can only be skipped if one scalar is overwritten with another scalar. Scalar-confusion due to speculative store bypass can not lead to invalid accesses because the pointer bounds deducted during verification are enforced using branchless logic. See 979d63d50c0c ("bpf: prevent out of bounds speculation on pointer arithmetic") for details.

Do not make the mitigation depend on !env->allow_{uninit_stack,ptr_leaks} because speculative leaks are likely unexpected if these were enabled. For example, leaking the address to a protected log file may be acceptable while disabling the mitigation might unintentionally leak the address into the cached-state of a map that is accessible to unprivileged processes.

Fixes: 2039f26f3aca ("bpf: Fix leakage due to insufficient speculative store bypass mitigation") Signed-off-by: Luis Gerhorst gerhorst@cs.fau.de Signed-off-by: Daniel Borkmann daniel@iogearbox.net Acked-by: Henriette Hofmeier henriette.hofmeier@rub.de Link: https://lore.kernel.org/bpf/edc95bad-aada-9cfc-ffe2-fa9bb206583c@cs.fau.de Link: https://lore.kernel.org/bpf/20230109150544.41465-1-gerhorst@cs.fau.de Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/bpf/verifier.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 32b32ecad770..ca7e05ddbb46 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1924,7 +1924,9 @@ static int check_stack_write(struct bpf_verifier_env *env, bool sanitize = reg && is_spillable_regtype(reg->type);

for (i = 0; i < size; i++) { - if (state->stack[spi].slot_type[i] == STACK_INVALID) { + u8 type = state->stack[spi].slot_type[i]; + + if (type != STACK_MISC && type != STACK_ZERO) { sanitize = true; break; }

From: Jisoo Jang jisoo.jang@yonsei.ac.kr

[ Upstream commit 4bb4db7f3187c6e3de6b229ffc87cdb30a2d22b6 ]

Fix a use-after-free that occurs in kfree_skb() called from local_cleanup(). This could happen when killing nfc daemon (e.g. neard) after detaching an nfc device. When detaching an nfc device, local_cleanup() called from nfc_llcp_unregister_device() frees local->rx_pending and decreases local->ref by kref_put() in nfc_llcp_local_put(). In the terminating process, nfc daemon releases all sockets and it leads to decreasing local->ref. After the last release of local->ref, local_cleanup() called from local_release() frees local->rx_pending again, which leads to the bug.

Setting local->rx_pending to NULL in local_cleanup() could prevent use-after-free when local_cleanup() is called twice.

Found by a modified version of syzkaller.

BUG: KASAN: use-after-free in kfree_skb()

Call Trace: dump_stack_lvl (lib/dump_stack.c:106) print_address_description.constprop.0.cold (mm/kasan/report.c:306) kasan_check_range (mm/kasan/generic.c:189) kfree_skb (net/core/skbuff.c:955) local_cleanup (net/nfc/llcp_core.c:159) nfc_llcp_local_put.part.0 (net/nfc/llcp_core.c:172) nfc_llcp_local_put (net/nfc/llcp_core.c:181) llcp_sock_destruct (net/nfc/llcp_sock.c:959) __sk_destruct (net/core/sock.c:2133) sk_destruct (net/core/sock.c:2181) __sk_free (net/core/sock.c:2192) sk_free (net/core/sock.c:2203) llcp_sock_release (net/nfc/llcp_sock.c:646) __sock_release (net/socket.c:650) sock_close (net/socket.c:1365) __fput (fs/file_table.c:306) task_work_run (kernel/task_work.c:179) ptrace_notify (kernel/signal.c:2354) syscall_exit_to_user_mode_prepare (kernel/entry/common.c:278) syscall_exit_to_user_mode (kernel/entry/common.c:296) do_syscall_64 (arch/x86/entry/common.c:86) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:106)

Allocated by task 4719: kasan_save_stack (mm/kasan/common.c:45) __kasan_slab_alloc (mm/kasan/common.c:325) slab_post_alloc_hook (mm/slab.h:766) kmem_cache_alloc_node (mm/slub.c:3497) __alloc_skb (net/core/skbuff.c:552) pn533_recv_response (drivers/nfc/pn533/usb.c:65) __usb_hcd_giveback_urb (drivers/usb/core/hcd.c:1671) usb_giveback_urb_bh (drivers/usb/core/hcd.c:1704) tasklet_action_common.isra.0 (kernel/softirq.c:797) __do_softirq (kernel/softirq.c:571)

Freed by task 1901: kasan_save_stack (mm/kasan/common.c:45) kasan_set_track (mm/kasan/common.c:52) kasan_save_free_info (mm/kasan/genericdd.c:518) __kasan_slab_free (mm/kasan/common.c:236) kmem_cache_free (mm/slub.c:3809) kfree_skbmem (net/core/skbuff.c:874) kfree_skb (net/core/skbuff.c:931) local_cleanup (net/nfc/llcp_core.c:159) nfc_llcp_unregister_device (net/nfc/llcp_core.c:1617) nfc_unregister_device (net/nfc/core.c:1179) pn53x_unregister_nfc (drivers/nfc/pn533/pn533.c:2846) pn533_usb_disconnect (drivers/nfc/pn533/usb.c:579) usb_unbind_interface (drivers/usb/core/driver.c:458) device_release_driver_internal (drivers/base/dd.c:1279) bus_remove_device (drivers/base/bus.c:529) device_del (drivers/base/core.c:3665) usb_disable_device (drivers/usb/core/message.c:1420) usb_disconnect (drivers/usb/core.c:2261) hub_event (drivers/usb/core/hub.c:5833) process_one_work (arch/x86/include/asm/jump_label.h:27 include/linux/jump_label.h:212 include/trace/events/workqueue.h:108 kernel/workqueue.c:2281) worker_thread (include/linux/list.h:282 kernel/workqueue.c:2423) kthread (kernel/kthread.c:319) ret_from_fork (arch/x86/entry/entry_64.S:301)

Fixes: 3536da06db0b ("NFC: llcp: Clean local timers and works when removing a device") Signed-off-by: Jisoo Jang jisoo.jang@yonsei.ac.kr Link: https://lore.kernel.org/r/20230111131914.3338838-1-jisoo.jang@yonsei.ac.kr Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/nfc/llcp_core.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index cc997518f79d..edadebb3efd2 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -159,6 +159,7 @@ static void local_cleanup(struct nfc_llcp_local *local) cancel_work_sync(&local->rx_work); cancel_work_sync(&local->timeout_work); kfree_skb(local->rx_pending); + local->rx_pending = NULL; del_timer_sync(&local->sdreq_timer); cancel_work_sync(&local->sdreq_timeout_work); nfc_llcp_free_sdp_tlv_list(&local->pending_sdreqs);

From: Marek Vasut marex@denx.de

[ Upstream commit 8e88a0feebb241cab0253698b2f7358b6ebec802 ]

Always configure GPIO pins which are used as interrupt source as INPUTs. In case the default pin configuration is OUTPUT, or the prior stage does configure the pins as OUTPUT, then Linux will not reconfigure the pin as INPUT and no interrupts are received.

Always configure the interrupt source GPIO pin as input to fix the above case.

Reviewed-by: Linus Walleij linus.walleij@linaro.org Fixes: 07bd1a6cc7cbb ("MXC arch: Add gpio support for the whole platform") Signed-off-by: Marek Vasut marex@denx.de Signed-off-by: Bartosz Golaszewski bartosz.golaszewski@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpio/gpio-mxc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-mxc.c b/drivers/gpio/gpio-mxc.c index c77d474185f3..2e4b6b176875 100644 --- a/drivers/gpio/gpio-mxc.c +++ b/drivers/gpio/gpio-mxc.c @@ -229,7 +229,7 @@ static int gpio_set_irq_type(struct irq_data *d, u32 type)

writel(1 << gpio_idx, port->base + GPIO_ISR);

- return 0; + return port->gc.direction_input(&port->gc, gpio_idx); }

static void mxc_flip_edge(struct mxc_gpio_port *port, u32 gpio)

From: Eric Dumazet edumazet@google.com

[ Upstream commit 3a415d59c1dbec9d772dbfab2d2520d98360caae ]

syzbot reported a nasty crash [1] in net_tx_action() which made little sense until we got a repro.

This repro installs a taprio qdisc, but providing an invalid TCA_RATE attribute.

qdisc_create() has to destroy the just initialized taprio qdisc, and taprio_destroy() is called.

However, the hrtimer used by taprio had already fired, therefore advance_sched() called __netif_schedule().

Then net_tx_action was trying to use a destroyed qdisc.

We can not undo the __netif_schedule(), so we must wait until one cpu serviced the qdisc before we can proceed.

Many thanks to Alexander Potapenko for his help.

[1] BUG: KMSAN: uninit-value in queued_spin_trylock include/asm-generic/qspinlock.h:94 [inline] BUG: KMSAN: uninit-value in do_raw_spin_trylock include/linux/spinlock.h:191 [inline] BUG: KMSAN: uninit-value in __raw_spin_trylock include/linux/spinlock_api_smp.h:89 [inline] BUG: KMSAN: uninit-value in _raw_spin_trylock+0x92/0xa0 kernel/locking/spinlock.c:138 queued_spin_trylock include/asm-generic/qspinlock.h:94 [inline] do_raw_spin_trylock include/linux/spinlock.h:191 [inline] __raw_spin_trylock include/linux/spinlock_api_smp.h:89 [inline] _raw_spin_trylock+0x92/0xa0 kernel/locking/spinlock.c:138 spin_trylock include/linux/spinlock.h:359 [inline] qdisc_run_begin include/net/sch_generic.h:187 [inline] qdisc_run+0xee/0x540 include/net/pkt_sched.h:125 net_tx_action+0x77c/0x9a0 net/core/dev.c:5086 __do_softirq+0x1cc/0x7fb kernel/softirq.c:571 run_ksoftirqd+0x2c/0x50 kernel/softirq.c:934 smpboot_thread_fn+0x554/0x9f0 kernel/smpboot.c:164 kthread+0x31b/0x430 kernel/kthread.c:376 ret_from_fork+0x1f/0x30

Uninit was created at: slab_post_alloc_hook mm/slab.h:732 [inline] slab_alloc_node mm/slub.c:3258 [inline] __kmalloc_node_track_caller+0x814/0x1250 mm/slub.c:4970 kmalloc_reserve net/core/skbuff.c:358 [inline] __alloc_skb+0x346/0xcf0 net/core/skbuff.c:430 alloc_skb include/linux/skbuff.h:1257 [inline] nlmsg_new include/net/netlink.h:953 [inline] netlink_ack+0x5f3/0x12b0 net/netlink/af_netlink.c:2436 netlink_rcv_skb+0x55d/0x6c0 net/netlink/af_netlink.c:2507 rtnetlink_rcv+0x30/0x40 net/core/rtnetlink.c:6108 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0xf3b/0x1270 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x1288/0x1440 net/netlink/af_netlink.c:1921 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] ____sys_sendmsg+0xabc/0xe90 net/socket.c:2482 ___sys_sendmsg+0x2a1/0x3f0 net/socket.c:2536 __sys_sendmsg net/socket.c:2565 [inline] __do_sys_sendmsg net/socket.c:2574 [inline] __se_sys_sendmsg net/socket.c:2572 [inline] __x64_sys_sendmsg+0x367/0x540 net/socket.c:2572 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd

CPU: 0 PID: 13 Comm: ksoftirqd/0 Not tainted 6.0.0-rc2-syzkaller-47461-gac3859c02d7f #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/22/2022

Fixes: 5a781ccbd19e ("tc: Add support for configuring the taprio scheduler") Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: Eric Dumazet edumazet@google.com Cc: Alexander Potapenko glider@google.com Cc: Vinicius Costa Gomes vinicius.gomes@intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/sch_generic.h | 7 +++++++ net/sched/sch_taprio.c | 3 +++ 2 files changed, 10 insertions(+)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 1ee396ce0eda..e8034756cbf8 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -1334,4 +1334,11 @@ static inline void skb_tc_reinsert(struct sk_buff *skb, struct tcf_result *res) qstats_overlimit_inc(res->qstats); }

+/* Make sure qdisc is no longer in SCHED state. */ +static inline void qdisc_synchronize(const struct Qdisc *q) +{ + while (test_bit(__QDISC_STATE_SCHED, &q->state)) + msleep(1); +} + #endif diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 506ebae1f72c..4278a466cb50 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1622,6 +1622,8 @@ static void taprio_reset(struct Qdisc *sch) int i;

hrtimer_cancel(&q->advance_timer); + qdisc_synchronize(sch); + if (q->qdiscs) { for (i = 0; i < dev->num_tx_queues && q->qdiscs[i]; i++) qdisc_reset(q->qdiscs[i]); @@ -1644,6 +1646,7 @@ static void taprio_destroy(struct Qdisc *sch) * happens in qdisc_create(), after taprio_init() has been called. */ hrtimer_cancel(&q->advance_timer); + qdisc_synchronize(sch);

taprio_disable_offload(dev, q, NULL);

From: Jakub Sitnicki jakub@cloudflare.com

[ Upstream commit b68777d54fac21fc833ec26ea1a2a84f975ab035 ]

sk->sk_user_data has multiple users, which are not compatible with each other. Writers must synchronize by grabbing the sk->sk_callback_lock.

l2tp currently fails to grab the lock when modifying the underlying tunnel socket fields. Fix it by adding appropriate locking.

We err on the side of safety and grab the sk_callback_lock also inside the sk_destruct callback overridden by l2tp, even though there should be no refs allowing access to the sock at the time when sk_destruct gets called.

v4: - serialize write to sk_user_data in l2tp sk_destruct

v3: - switch from sock lock to sk_callback_lock - document write-protection for sk_user_data

v2: - update Fixes to point to origin of the bug - use real names in Reported/Tested-by tags

Cc: Tom Parkin tparkin@katalix.com Fixes: 3557baabf280 ("[L2TP]: PPP over L2TP driver core") Reported-by: Haowei Yan g1042620637@gmail.com Signed-off-by: Jakub Sitnicki jakub@cloudflare.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/sock.h | 2 +- net/l2tp/l2tp_core.c | 19 +++++++++++++------ 2 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h index f508e86a2021..5fa255b1e0a6 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -300,7 +300,7 @@ struct bpf_sk_storage; * @sk_tskey: counter to disambiguate concurrent tstamp requests * @sk_zckey: counter to order MSG_ZEROCOPY notifications * @sk_socket: Identd and reporting IO signals - * @sk_user_data: RPC layer private data + * @sk_user_data: RPC layer private data. Write-protected by @sk_callback_lock. * @sk_frag: cached page frag * @sk_peek_off: current peek_offset value * @sk_send_head: front of stuff to transmit diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index a0ec61f2295b..0e0f3e96b80e 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1171,8 +1171,10 @@ static void l2tp_tunnel_destruct(struct sock *sk) }

/* Remove hooks into tunnel socket */ + write_lock_bh(&sk->sk_callback_lock); sk->sk_destruct = tunnel->old_sk_destruct; sk->sk_user_data = NULL; + write_unlock_bh(&sk->sk_callback_lock);

/* Call the original destructor */ if (sk->sk_destruct) @@ -1491,16 +1493,18 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, sock = sockfd_lookup(tunnel->fd, &ret); if (!sock) goto err; - - ret = l2tp_validate_socket(sock->sk, net, tunnel->encap); - if (ret < 0) - goto err_sock; }

+ sk = sock->sk; + write_lock(&sk->sk_callback_lock); + + ret = l2tp_validate_socket(sk, net, tunnel->encap); + if (ret < 0) + goto err_sock; + tunnel->l2tp_net = net; pn = l2tp_pernet(net);

- sk = sock->sk; sock_hold(sk); tunnel->sock = sk;

@@ -1526,7 +1530,7 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,

setup_udp_tunnel_sock(net, sock, &udp_cfg); } else { - sk->sk_user_data = tunnel; + rcu_assign_sk_user_data(sk, tunnel); }

tunnel->old_sk_destruct = sk->sk_destruct; @@ -1538,6 +1542,7 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, if (tunnel->fd >= 0) sockfd_put(sock);

+ write_unlock(&sk->sk_callback_lock); return 0;

err_sock: @@ -1545,6 +1550,8 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, sock_release(sock); else sockfd_put(sock); + + write_unlock(&sk->sk_callback_lock); err: return ret; }

From: Szymon Heidrich szymon.heidrich@gmail.com

[ Upstream commit ecf7cf8efb59789e2b21d2f9ab926142579092b2 ]

Packet len computed as difference of length word extracted from skb data and four may result in a negative value. In such case processing of the buffer should be interrupted rather than setting sr_skb->len to an unexpectedly large value (due to cast from signed to unsigned integer) and passing sr_skb to usbnet_skb_return.

Fixes: e9da0b56fe27 ("sr9700: sanity check for packet length") Signed-off-by: Szymon Heidrich szymon.heidrich@gmail.com Link: https://lore.kernel.org/r/20230114182326.30479-1-szymon.heidrich@gmail.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/sr9700.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c index fce6713e970b..811c8751308c 100644 --- a/drivers/net/usb/sr9700.c +++ b/drivers/net/usb/sr9700.c @@ -410,7 +410,7 @@ static int sr9700_rx_fixup(struct usbnet *dev, struct sk_buff *skb) /* ignore the CRC length */ len = (skb->data[1] | (skb->data[2] << 8)) - 4;

- if (len > ETH_FRAME_LEN || len > skb->len) + if (len > ETH_FRAME_LEN || len > skb->len || len < 0) return 0;

/* the last packet of current skb */

From: Pietro Borrello borrello@diag.uniroma1.it

[ Upstream commit b12fece4c64857e5fab4290bf01b2e0317a88456 ]

Add a check for empty report_list in hid_validate_values(). The missing check causes a type confusion when issuing a list_entry() on an empty report_list. The problem is caused by the assumption that the device must have valid report_list. While this will be true for all normal HID devices, a suitably malicious device can violate the assumption.

Fixes: 1b15d2e5b807 ("HID: core: fix validation of report id 0") Signed-off-by: Pietro Borrello borrello@diag.uniroma1.it Signed-off-by: Jiri Kosina jkosina@suse.cz Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hid/hid-core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index eda96c92977b..2888bd5502f3 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -981,8 +981,8 @@ struct hid_report *hid_validate_values(struct hid_device *hid, * Validating on id 0 means we should examine the first * report in the list. */ - report = list_entry( - hid->report_enum[type].report_list.next, + report = list_first_entry_or_null( + &hid->report_enum[type].report_list, struct hid_report, list); } else { report = hid->report_enum[type].report_id_hash[id];

From: Heiner Kallweit hkallweit1@gmail.com

[ Upstream commit 1f3bd64ad921f051254591fbed04fd30b306cde6 ]

In a number of cases the driver assigns a default value of -1 to priv->plat->phy_addr. This may result in calling mdiobus_get_phy() with addr parameter being -1. Therefore check for this scenario and bail out before calling mdiobus_get_phy().

Fixes: 42e87024f727 ("net: stmmac: Fix case when PHY handle is not present") Signed-off-by: Heiner Kallweit hkallweit1@gmail.com Link: https://lore.kernel.org/r/669f9671-ecd1-a41b-2727-7b73e3003985@gmail.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 9931724c4727..3079e5254666 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -998,6 +998,11 @@ static int stmmac_init_phy(struct net_device *dev) int addr = priv->plat->phy_addr; struct phy_device *phydev;

+ if (addr < 0) { + netdev_err(priv->dev, "no phy found\n"); + return -ENODEV; + } + phydev = mdiobus_get_phy(priv->mii, addr); if (!phydev) { netdev_err(priv->dev, "no phy at addr %d\n", addr);

From: Udipto Goswami quic_ugoswami@quicinc.com

[ Upstream commit 6a19da111057f69214b97c62fb0ac59023970850 ]

While performing fast composition switch, there is a possibility that the process of ffs_ep0_write/ffs_ep0_read get into a race condition due to ep0req being freed up from functionfs_unbind.

Consider the scenario that the ffs_ep0_write calls the ffs_ep0_queue_wait by taking a lock &ffs->ev.waitq.lock. However, the functionfs_unbind isn't bounded so it can go ahead and mark the ep0req to NULL, and since there is no NULL check in ffs_ep0_queue_wait we will end up in use-after-free.

Fix this by making a serialized execution between the two functions using a mutex_lock(ffs->mutex).

Fixes: ddf8abd25994 ("USB: f_fs: the FunctionFS driver") Signed-off-by: Udipto Goswami quic_ugoswami@quicinc.com Tested-by: Krishna Kurapati quic_kriskura@quicinc.com Link: https://lore.kernel.org/r/20221215052906.8993-2-quic_ugoswami@quicinc.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/usb/gadget/function/f_fs.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 5fd4fc49aef9..3b7323233b39 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -278,6 +278,9 @@ static int __ffs_ep0_queue_wait(struct ffs_data *ffs, char *data, size_t len) struct usb_request *req = ffs->ep0req; int ret;

+ if (!req) + return -EINVAL; + req->zero = len < le16_to_cpu(ffs->ev.setup.wLength);

spin_unlock_irq(&ffs->ev.waitq.lock); @@ -1900,10 +1903,12 @@ static void functionfs_unbind(struct ffs_data *ffs) ENTER();

if (!WARN_ON(!ffs->gadget)) { + mutex_lock(&ffs->mutex); usb_ep_free_request(ffs->gadget->ep0, ffs->ep0req); ffs->ep0req = NULL; ffs->gadget = NULL; clear_bit(FFS_FL_BOUND, &ffs->flags); + mutex_unlock(&ffs->mutex); ffs_data_put(ffs); } }

From: Randy Dunlap rdunlap@infradead.org

[ Upstream commit 2c1e1b949024989e20907b84e11a731a50778416 ]

Eliminate anonymous module_init() and module_exit(), which can lead to confusion or ambiguity when reading System.map, crashes/oops/bugs, or an initcall_debug log.

Give each of these init and exit functions unique driver-specific names to eliminate the anonymous names.

Example 1: (System.map) ffffffff832fc78c t init ffffffff832fc79e t init ffffffff832fc8f8 t init

Example 2: (initcall_debug log) calling init+0x0/0x12 @ 1 initcall init+0x0/0x12 returned 0 after 15 usecs calling init+0x0/0x60 @ 1 initcall init+0x0/0x60 returned 0 after 2 usecs calling init+0x0/0x9a @ 1 initcall init+0x0/0x9a returned 0 after 74 usecs

Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Signed-off-by: Randy Dunlap rdunlap@infradead.org Cc: Eli Cohen eli@mellanox.com Cc: Saeed Mahameed saeedm@nvidia.com Cc: Leon Romanovsky leon@kernel.org Cc: linux-rdma@vger.kernel.org Reviewed-by: Ira Weiny ira.weiny@intel.com Reviewed-by: Leon Romanovsky leonro@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index f2657cd3ffa4..83ee9429e7c6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1640,7 +1640,7 @@ static void mlx5_core_verify_params(void) } }

-static int __init init(void) +static int __init mlx5_init(void) { int err;

@@ -1665,7 +1665,7 @@ static int __init init(void) return err; }

-static void __exit cleanup(void) +static void __exit mlx5_cleanup(void) { #ifdef CONFIG_MLX5_CORE_EN mlx5e_cleanup(); @@ -1674,5 +1674,5 @@ static void __exit cleanup(void) mlx5_unregister_debugfs(); }

-module_init(init); -module_exit(cleanup); +module_init(mlx5_init); +module_exit(mlx5_cleanup);

From: Koba Ko koba.ko@canonical.com

[ Upstream commit f3dc1b3b4750851a94212dba249703dd0e50bb20 ]

The first time dma_chan_get() is called for a channel the channel client_count is incorrectly incremented twice for public channels, first in balance_ref_count(), and again prior to returning. This results in an incorrect client count which will lead to the channel resources not being freed when they should be. A simple test of repeated module load and unload of async_tx on a Dell Power Edge R7425 also shows this resulting in a kref underflow warning.

[ 124.329662] async_tx: api initialized (async) [ 129.000627] async_tx: api initialized (async) [ 130.047839] ------------[ cut here ]------------ [ 130.052472] refcount_t: underflow; use-after-free. [ 130.057279] WARNING: CPU: 3 PID: 19364 at lib/refcount.c:28 refcount_warn_saturate+0xba/0x110 [ 130.065811] Modules linked in: async_tx(-) rfkill intel_rapl_msr intel_rapl_common amd64_edac edac_mce_amd ipmi_ssif kvm_amd dcdbas kvm mgag200 drm_shmem_helper acpi_ipmi irqbypass drm_kms_helper ipmi_si syscopyarea sysfillrect rapl pcspkr ipmi_devintf sysimgblt fb_sys_fops k10temp i2c_piix4 ipmi_msghandler acpi_power_meter acpi_cpufreq vfat fat drm fuse xfs libcrc32c sd_mod t10_pi sg ahci crct10dif_pclmul libahci crc32_pclmul crc32c_intel ghash_clmulni_intel igb megaraid_sas i40e libata i2c_algo_bit ccp sp5100_tco dca dm_mirror dm_region_hash dm_log dm_mod [last unloaded: async_tx] [ 130.117361] CPU: 3 PID: 19364 Comm: modprobe Kdump: loaded Not tainted 5.14.0-185.el9.x86_64 #1 [ 130.126091] Hardware name: Dell Inc. PowerEdge R7425/02MJ3T, BIOS 1.18.0 01/17/2022 [ 130.133806] RIP: 0010:refcount_warn_saturate+0xba/0x110 [ 130.139041] Code: 01 01 e8 6d bd 55 00 0f 0b e9 72 9d 8a 00 80 3d 26 18 9c 01 00 75 85 48 c7 c7 f8 a3 03 9d c6 05 16 18 9c 01 01 e8 4a bd 55 00 <0f> 0b e9 4f 9d 8a 00 80 3d 01 18 9c 01 00 0f 85 5e ff ff ff 48 c7 [ 130.157807] RSP: 0018:ffffbf98898afe68 EFLAGS: 00010286 [ 130.163036] RAX: 0000000000000000 RBX: ffff9da06028e598 RCX: 0000000000000000 [ 130.170172] RDX: ffff9daf9de26480 RSI: ffff9daf9de198a0 RDI: ffff9daf9de198a0 [ 130.177316] RBP: ffff9da7cddf3970 R08: 0000000000000000 R09: 00000000ffff7fff [ 130.184459] R10: ffffbf98898afd00 R11: ffffffff9d9e8c28 R12: ffff9da7cddf1970 [ 130.191596] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 [ 130.198739] FS: 00007f646435c740(0000) GS:ffff9daf9de00000(0000) knlGS:0000000000000000 [ 130.206832] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 130.212586] CR2: 00007f6463b214f0 CR3: 00000008ab98c000 CR4: 00000000003506e0 [ 130.219729] Call Trace: [ 130.222192] <TASK> [ 130.224305] dma_chan_put+0x10d/0x110 [ 130.227988] dmaengine_put+0x7a/0xa0 [ 130.231575] __do_sys_delete_module.constprop.0+0x178/0x280 [ 130.237157] ? syscall_trace_enter.constprop.0+0x145/0x1d0 [ 130.242652] do_syscall_64+0x5c/0x90 [ 130.246240] ? exc_page_fault+0x62/0x150 [ 130.250178] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 130.255243] RIP: 0033:0x7f6463a3f5ab [ 130.258830] Code: 73 01 c3 48 8b 0d 75 a8 1b 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 b8 b0 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 45 a8 1b 00 f7 d8 64 89 01 48 [ 130.277591] RSP: 002b:00007fff22f972c8 EFLAGS: 00000206 ORIG_RAX: 00000000000000b0 [ 130.285164] RAX: ffffffffffffffda RBX: 000055b6786edd40 RCX: 00007f6463a3f5ab [ 130.292303] RDX: 0000000000000000 RSI: 0000000000000800 RDI: 000055b6786edda8 [ 130.299443] RBP: 000055b6786edd40 R08: 0000000000000000 R09: 0000000000000000 [ 130.306584] R10: 00007f6463b9eac0 R11: 0000000000000206 R12: 000055b6786edda8 [ 130.313731] R13: 0000000000000000 R14: 000055b6786edda8 R15: 00007fff22f995f8 [ 130.320875] </TASK> [ 130.323081] ---[ end trace eff7156d56b5cf25 ]---

cat /sys/class/dma/dma0chan*/in_use would get the wrong result. 2 2 2

Fixes: d2f4f99db3e9 ("dmaengine: Rework dma_chan_get") Signed-off-by: Koba Ko koba.ko@canonical.com Reviewed-by: Jie Hai haijie1@huawei.com Test-by: Jie Hai haijie1@huawei.com Reviewed-by: Jerry Snitselaar jsnitsel@redhat.com Reviewed-by: Dave Jiang dave.jiang@intel.com Tested-by: Joel Savitz jsavitz@redhat.com Link: https://lore.kernel.org/r/20221201030050.978595-1-koba.ko@canonical.com Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/dmaengine.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index 4b604086b1b3..a8996faa85a9 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -212,7 +212,8 @@ static int dma_chan_get(struct dma_chan *chan) /* The channel is already in use, update client count */ if (chan->client_count) { __module_get(owner); - goto out; + chan->client_count++; + return 0; }

if (!try_module_get(owner)) @@ -225,11 +226,11 @@ static int dma_chan_get(struct dma_chan *chan) goto err_out; }

+ chan->client_count++; + if (!dma_has_cap(DMA_PRIVATE, chan->device->cap_mask)) balance_ref_count(chan);

-out: - chan->client_count++; return 0;

err_out:

From: Pietro Borrello borrello@diag.uniroma1.it

[ Upstream commit 3782c0d6edf658b71354a64d60aa7a296188fc90 ]

betopff_init() only checks the total sum of the report counts for each report field to be at least 4, but hid_betopff_play() expects 4 report fields. A device advertising an output report with one field and 4 report counts would pass the check but crash the kernel with a NULL pointer dereference in hid_betopff_play().

Fixes: 52cd7785f3cd ("HID: betop: add drivers/hid/hid-betopff.c") Signed-off-by: Pietro Borrello borrello@diag.uniroma1.it Signed-off-by: Jiri Kosina jkosina@suse.cz Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hid/hid-betopff.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/hid/hid-betopff.c b/drivers/hid/hid-betopff.c index 467d789f9bc2..25ed7b9a917e 100644 --- a/drivers/hid/hid-betopff.c +++ b/drivers/hid/hid-betopff.c @@ -60,7 +60,6 @@ static int betopff_init(struct hid_device *hid) struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list; struct input_dev *dev; - int field_count = 0; int error; int i, j;

@@ -86,19 +85,21 @@ static int betopff_init(struct hid_device *hid) * ----------------------------------------- * Do init them with default value. */ + if (report->maxfield < 4) { + hid_err(hid, "not enough fields in the report: %d\n", + report->maxfield); + return -ENODEV; + } for (i = 0; i < report->maxfield; i++) { + if (report->field[i]->report_count < 1) { + hid_err(hid, "no values in the field\n"); + return -ENODEV; + } for (j = 0; j < report->field[i]->report_count; j++) { report->field[i]->value[j] = 0x00; - field_count++; } }

- if (field_count < 4) { - hid_err(hid, "not enough fields in the report: %d\n", - field_count); - return -ENODEV; - } - betopff = kzalloc(sizeof(*betopff), GFP_KERNEL); if (!betopff) return -ENOMEM;

From: Swati Agarwal swati.agarwal@xilinx.com

[ Upstream commit 91df7751eb890e970afc08f50b8f0fa5ea39e03d ]

Add missing cleanup in devm_platform_ioremap_resource(). When probe fails remove dma channel resources and disable clocks in accordance with the order of resources allocated .

Signed-off-by: Swati Agarwal swati.agarwal@xilinx.com Link: https://lore.kernel.org/r/20220817061125.4720-2-swati.agarwal@xilinx.com Signed-off-by: Vinod Koul vkoul@kernel.org Stable-dep-of: 596b53ccc36a ("dmaengine: xilinx_dma: call of_node_put() when breaking out of for_each_child_of_node()") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/xilinx/xilinx_dma.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index 8a7606bc326a..7b60248be725 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -2652,9 +2652,10 @@ static int xilinx_dma_probe(struct platform_device *pdev)

/* Request and map I/O memory */ xdev->regs = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(xdev->regs)) - return PTR_ERR(xdev->regs); - + if (IS_ERR(xdev->regs)) { + err = PTR_ERR(xdev->regs); + goto disable_clks; + } /* Retrieve the DMA engine properties from the device tree */ xdev->max_buffer_len = GENMASK(XILINX_DMA_MAX_TRANS_LEN_MAX - 1, 0);

@@ -2747,7 +2748,7 @@ static int xilinx_dma_probe(struct platform_device *pdev) for_each_child_of_node(node, child) { err = xilinx_dma_child_probe(xdev, child); if (err < 0) - goto disable_clks; + goto error; }

if (xdev->dma_config->dmatype == XDMA_TYPE_VDMA) { @@ -2780,12 +2781,12 @@ static int xilinx_dma_probe(struct platform_device *pdev)

return 0;

-disable_clks: - xdma_disable_allclks(xdev); error: for (i = 0; i < xdev->nr_channels; i++) if (xdev->chan[i]) xilinx_dma_chan_remove(xdev->chan[i]); +disable_clks: + xdma_disable_allclks(xdev);

return err; }

From: Jason Xing kernelxing@tencent.com

[ Upstream commit 3f4ca5fafc08881d7a57daa20449d171f2887043 ]

While one cpu is working on looking up the right socket from ehash table, another cpu is done deleting the request socket and is about to add (or is adding) the big socket from the table. It means that we could miss both of them, even though it has little chance.

Let me draw a call trace map of the server side. CPU 0 CPU 1 ----- ----- tcp_v4_rcv() syn_recv_sock() inet_ehash_insert() -> sk_nulls_del_node_init_rcu(osk) __inet_lookup_established() -> __sk_nulls_add_node_rcu(sk, list)

Notice that the CPU 0 is receiving the data after the final ack during 3-way shakehands and CPU 1 is still handling the final ack.

Why could this be a real problem? This case is happening only when the final ack and the first data receiving by different CPUs. Then the server receiving data with ACK flag tries to search one proper established socket from ehash table, but apparently it fails as my map shows above. After that, the server fetches a listener socket and then sends a RST because it finds a ACK flag in the skb (data), which obeys RST definition in RFC 793.

Besides, Eric pointed out there's one more race condition where it handles tw socket hashdance. Only by adding to the tail of the list before deleting the old one can we avoid the race if the reader has already begun the bucket traversal and it would possibly miss the head.

Many thanks to Eric for great help from beginning to end.

Fixes: 5e0724d027f0 ("tcp/dccp: fix hashdance race for passive sessions") Suggested-by: Eric Dumazet edumazet@google.com Signed-off-by: Jason Xing kernelxing@tencent.com Reviewed-by: Eric Dumazet edumazet@google.com Reviewed-by: Kuniyuki Iwashima kuniyu@amazon.com Link: https://lore.kernel.org/lkml/20230112065336.41034-1-kerneljasonxing@gmail.co... Link: https://lore.kernel.org/r/20230118015941.1313-1-kerneljasonxing@gmail.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/inet_hashtables.c | 17 +++++++++++++++-- net/ipv4/inet_timewait_sock.c | 8 ++++---- 2 files changed, 19 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 25334aa3da04..33292983b8cf 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -536,8 +536,20 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) spin_lock(lock); if (osk) { WARN_ON_ONCE(sk->sk_hash != osk->sk_hash); - ret = sk_nulls_del_node_init_rcu(osk); - } else if (found_dup_sk) { + ret = sk_hashed(osk); + if (ret) { + /* Before deleting the node, we insert a new one to make + * sure that the look-up-sk process would not miss either + * of them and that at least one node would exist in ehash + * table all the time. Otherwise there's a tiny chance + * that lookup process could find nothing in ehash table. + */ + __sk_nulls_add_node_tail_rcu(sk, list); + sk_nulls_del_node_init_rcu(osk); + } + goto unlock; + } + if (found_dup_sk) { *found_dup_sk = inet_ehash_lookup_by_sk(sk, list); if (*found_dup_sk) ret = false; @@ -546,6 +558,7 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) if (ret) __sk_nulls_add_node_rcu(sk, list);

+unlock: spin_unlock(lock);

return ret; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index c411c87ae865..a00102d7c7fd 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -81,10 +81,10 @@ void inet_twsk_put(struct inet_timewait_sock *tw) } EXPORT_SYMBOL_GPL(inet_twsk_put);

-static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw, - struct hlist_nulls_head *list) +static void inet_twsk_add_node_tail_rcu(struct inet_timewait_sock *tw, + struct hlist_nulls_head *list) { - hlist_nulls_add_head_rcu(&tw->tw_node, list); + hlist_nulls_add_tail_rcu(&tw->tw_node, list); }

static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw, @@ -120,7 +120,7 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,

spin_lock(lock);

- inet_twsk_add_node_rcu(tw, &ehead->chain); + inet_twsk_add_node_tail_rcu(tw, &ehead->chain);

/* Step 3: Remove SK from hash chain */ if (__sk_nulls_del_node_init_rcu(sk))

From: Yang Yingliang yangyingliang@huawei.com

[ Upstream commit 36225a7c72e9e3e1ce4001b6ce72849f5c9a2d3b ]

I got the following WARNING message while removing driver(ds2482):

------------[ cut here ]------------ do not call blocking ops when !TASK_RUNNING; state=1 set at [<000000002d50bfb6>] w1_process+0x9e/0x1d0 [wire] WARNING: CPU: 0 PID: 262 at kernel/sched/core.c:9817 __might_sleep+0x98/0xa0 CPU: 0 PID: 262 Comm: w1_bus_master1 Tainted: G N 6.1.0-rc3+ #307 RIP: 0010:__might_sleep+0x98/0xa0 Call Trace: exit_signals+0x6c/0x550 do_exit+0x2b4/0x17e0 kthread_exit+0x52/0x60 kthread+0x16d/0x1e0 ret_from_fork+0x1f/0x30

The state of task is set to TASK_INTERRUPTIBLE in loop in w1_process(), set it to TASK_RUNNING when it breaks out of the loop to avoid the warning.

Fixes: 3c52e4e62789 ("W1: w1_process, block or sleep") Signed-off-by: Yang Yingliang yangyingliang@huawei.com Link: https://lore.kernel.org/r/20221205101558.3599162-1-yangyingliang@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/w1/w1.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c index 9a9c6f54304e..2a7970a10533 100644 --- a/drivers/w1/w1.c +++ b/drivers/w1/w1.c @@ -1160,8 +1160,10 @@ int w1_process(void *data) */ mutex_unlock(&dev->list_mutex);

- if (kthread_should_stop()) + if (kthread_should_stop()) { + __set_current_state(TASK_RUNNING); break; + }

/* Only sleep when the search is active. */ if (dev->search_count) {

From: Rakesh Sankaranarayanan rakesh.sankaranarayanan@microchip.com

[ Upstream commit 6c977c5c2e4c5d8ad1b604724cc344e38f96fe9b ]

ALU table entry 2 register in KSZ9477 have bit positions reserved for forwarding port map. This field is referred in ksz9477_fdb_del() for clearing forward port map and alu table.

But current fdb_del refer ALU table entry 3 register for accessing forward port map. Update ksz9477_fdb_del() to get forward port map from correct alu table entry register.

With this bug, issue can be observed while deleting static MAC entries. Delete any specific MAC entry using "bridge fdb del" command. This should clear all the specified MAC entries. But it is observed that entries with self static alone are retained.

Tested on LAN9370 EVB since ksz9477_fdb_del() is used common across LAN937x and KSZ series.

Fixes: b987e98e50ab ("dsa: add DSA switch driver for Microchip KSZ9477") Signed-off-by: Rakesh Sankaranarayanan rakesh.sankaranarayanan@microchip.com Reviewed-by: Vladimir Oltean olteanv@gmail.com Link: https://lore.kernel.org/r/20230118174735.702377-1-rakesh.sankaranarayanan@mi... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/microchip/ksz9477.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index c66e78b2870d..ba2dc01e0f6b 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -682,10 +682,10 @@ static int ksz9477_port_fdb_del(struct dsa_switch *ds, int port, ksz_read32(dev, REG_SW_ALU_VAL_D, &alu_table[3]);

/* clear forwarding port */ - alu_table[2] &= ~BIT(port); + alu_table[1] &= ~BIT(port);

/* if there is no port to forward, clear table */ - if ((alu_table[2] & ALU_V_PORT_MAP) == 0) { + if ((alu_table[1] & ALU_V_PORT_MAP) == 0) { alu_table[0] = 0; alu_table[1] = 0; alu_table[2] = 0;

From: Sumit Gupta sumitg@nvidia.com

[ Upstream commit 01c5bb0cc2a39fbc56ff9a5ef28b79447f0c2351 ]

Tegra234 platform uses the tegra194-cpufreq driver, so add it to the blocklist in cpufreq-dt-platdev driver to avoid the cpufreq driver registration from there.

Signed-off-by: Sumit Gupta sumitg@nvidia.com Signed-off-by: Viresh Kumar viresh.kumar@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/cpufreq/cpufreq-dt-platdev.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index 1200842c3da4..5d28553b69f5 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -126,6 +126,7 @@ static const struct of_device_id blacklist[] __initconst = {

{ .compatible = "nvidia,tegra124", }, { .compatible = "nvidia,tegra210", }, + { .compatible = "nvidia,tegra234", },

{ .compatible = "qcom,apq8096", }, { .compatible = "qcom,msm8996", },

From: Patrick Thompson ptf@google.com

[ Upstream commit 0688773f0710528e1ab302c3d6317e269f2e2e6e ]

Panel is 800x1280 but mounted on a detachable form factor sideways.

Signed-off-by: Patrick Thompson ptf@google.com Signed-off-by: Daniel Vetter daniel.vetter@ffwll.ch Link: https://patchwork.freedesktop.org/patch/msgid/20221220205826.178008-1-ptf@go... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/drm_panel_orientation_quirks.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index ca0fefeaab20..ce739ba45c55 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -272,6 +272,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad D330-10IGM"), }, .driver_data = (void *)&lcd1200x1920_rightside_up, + }, { /* Lenovo Ideapad D330-10IGL (HD) */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad D330-10IGL"), + }, + .driver_data = (void *)&lcd800x1280_rightside_up, }, { /* Lenovo Yoga Book X90F / X91F / X91L */ .matches = { /* Non exact match to match all versions */

From: Miles Chen miles.chen@mediatek.com

[ Upstream commit 08f0adb193c008de640fde34a2e00a666c01d77c ]

Use NULL for NULL pointer to fix the following sparse warning: drivers/cpufreq/armada-37xx-cpufreq.c:448:32: sparse: warning: Using plain integer as NULL pointer

Signed-off-by: Miles Chen miles.chen@mediatek.com Signed-off-by: Viresh Kumar viresh.kumar@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/cpufreq/armada-37xx-cpufreq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c index 2de7fd18f66a..f0be8a43ec49 100644 --- a/drivers/cpufreq/armada-37xx-cpufreq.c +++ b/drivers/cpufreq/armada-37xx-cpufreq.c @@ -443,7 +443,7 @@ static int __init armada37xx_cpufreq_driver_init(void) return -ENODEV; }

- clk = clk_get(cpu_dev, 0); + clk = clk_get(cpu_dev, NULL); if (IS_ERR(clk)) { dev_err(cpu_dev, "Cannot get clock for CPU0\n"); return PTR_ERR(clk);

From: Mark Brown broonie@kernel.org

[ Upstream commit 242fc66ae6e1e2b8519daacc7590a73cd0e8a6e4 ]

The fsl-asoc-card AC'97 support currently tries to route to Playback and Capture widgets provided by the AC'97 CODEC. This doesn't work since the generic AC'97 driver registers with an "AC97" at the front of the stream and hence widget names, update to reflect reality. It's not clear to me if or how this ever worked.

Acked-by: Shengjiu Wang shengjiu.wang@gmail.com Signed-off-by: Mark Brown broonie@kernel.org Link: https://lore.kernel.org/r/20230106-asoc-udoo-probe-v1-2-a5d7469d4f67@kernel.... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/fsl/fsl-asoc-card.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c index d78eb9f9d24c..db663e7d17a4 100644 --- a/sound/soc/fsl/fsl-asoc-card.c +++ b/sound/soc/fsl/fsl-asoc-card.c @@ -112,8 +112,8 @@ static const struct snd_soc_dapm_route audio_map[] = {

static const struct snd_soc_dapm_route audio_map_ac97[] = { /* 1st half -- Normal DAPM routes */ - {"Playback", NULL, "CPU AC97 Playback"}, - {"CPU AC97 Capture", NULL, "Capture"}, + {"AC97 Playback", NULL, "CPU AC97 Playback"}, + {"CPU AC97 Capture", NULL, "AC97 Capture"}, /* 2nd half -- ASRC DAPM routes */ {"CPU AC97 Playback", NULL, "ASRC-Playback"}, {"ASRC-Capture", NULL, "CPU AC97 Capture"},

From: Heiko Carstens hca@linux.ibm.com

[ Upstream commit 42400d99e9f0728c17240edb9645637ead40f6b9 ]

Use READ_ONCE() before cmpxchg() to prevent that the compiler generates code that fetches the to be compared old value several times from memory.

Reviewed-by: Christian Borntraeger borntraeger@linux.ibm.com Acked-by: Christian Borntraeger borntraeger@linux.ibm.com Reviewed-by: Claudio Imbrenda imbrenda@linux.ibm.com Link: https://lore.kernel.org/r/20230109145456.2895385-1-hca@linux.ibm.com Signed-off-by: Heiko Carstens hca@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/s390/kvm/interrupt.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 8be5750fe5ac..a180fe54dc68 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -81,8 +81,9 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id) struct esca_block *sca = vcpu->kvm->arch.sca; union esca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union esca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl; + union esca_sigp_ctrl new_val = {0}, old_val;

+ old_val = READ_ONCE(*sigp_ctrl); new_val.scn = src_id; new_val.c = 1; old_val.c = 0; @@ -93,8 +94,9 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id) struct bsca_block *sca = vcpu->kvm->arch.sca; union bsca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union bsca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl; + union bsca_sigp_ctrl new_val = {0}, old_val;

+ old_val = READ_ONCE(*sigp_ctrl); new_val.scn = src_id; new_val.c = 1; old_val.c = 0; @@ -124,16 +126,18 @@ static void sca_clear_ext_call(struct kvm_vcpu *vcpu) struct esca_block *sca = vcpu->kvm->arch.sca; union esca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union esca_sigp_ctrl old = *sigp_ctrl; + union esca_sigp_ctrl old;

+ old = READ_ONCE(*sigp_ctrl); expect = old.value; rc = cmpxchg(&sigp_ctrl->value, old.value, 0); } else { struct bsca_block *sca = vcpu->kvm->arch.sca; union bsca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union bsca_sigp_ctrl old = *sigp_ctrl; + union bsca_sigp_ctrl old;

+ old = READ_ONCE(*sigp_ctrl); expect = old.value; rc = cmpxchg(&sigp_ctrl->value, old.value, 0); }

From: Michael Klein m.klein@mvz-labor-lb.de

[ Upstream commit 36c2b9d6710427f802494ba070621cb415198293 ]

Add touchscreen info for the CSL Panther Tab HD.

Signed-off-by: Michael Klein m.klein@mvz-labor-lb.de Link: https://lore.kernel.org/r/20221220121103.uiwn5l7fii2iggct@LLGMVZLB-0037 Reviewed-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/platform/x86/touchscreen_dmi.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+)

diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 515c66ca1aec..61cb1a4a8257 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -169,6 +169,23 @@ static const struct ts_dmi_data connect_tablet9_data = { .properties = connect_tablet9_props, };

+static const struct property_entry csl_panther_tab_hd_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 1), + PROPERTY_ENTRY_U32("touchscreen-min-y", 20), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1980), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1526), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-csl-panther-tab-hd.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + { } +}; + +static const struct ts_dmi_data csl_panther_tab_hd_data = { + .acpi_name = "MSSL1680:00", + .properties = csl_panther_tab_hd_props, +}; + static const struct property_entry cube_iwork8_air_props[] = { PROPERTY_ENTRY_U32("touchscreen-min-x", 1), PROPERTY_ENTRY_U32("touchscreen-min-y", 3), @@ -721,6 +738,14 @@ static const struct dmi_system_id touchscreen_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Tablet 9"), }, }, + { + /* CSL Panther Tab HD */ + .driver_data = (void *)&csl_panther_tab_hd_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "CSL Computer GmbH & Co. KG"), + DMI_MATCH(DMI_PRODUCT_NAME, "CSL Panther Tab HD"), + }, + }, { /* CUBE iwork8 Air */ .driver_data = (void *)&cube_iwork8_air_data,

From: Mateusz Guzik mjguzik@gmail.com

[ Upstream commit f5fe24ef17b5fbe6db49534163e77499fb10ae8c ]

On the x86-64 architecture even a failing cmpxchg grants exclusive access to the cacheline, making it preferable to retry the failed op immediately instead of stalling with the pause instruction.

To illustrate the impact, below are benchmark results obtained by running various will-it-scale tests on top of the 6.2-rc3 kernel and Cascade Lake (2 sockets * 24 cores * 2 threads) CPU.

All results in ops/s. Note there is some variance in re-runs, but the code is consistently faster when contention is present.

open3 ("Same file open/close"): proc stock no-pause 1 805603 814942 (+%1) 2 1054980 1054781 (-0%) 8 1544802 1822858 (+18%) 24 1191064 2199665 (+84%) 48 851582 1469860 (+72%) 96 609481 1427170 (+134%)

fstat2 ("Same file fstat"): proc stock no-pause 1 3013872 3047636 (+1%) 2 4284687 4400421 (+2%) 8 3257721 5530156 (+69%) 24 2239819 5466127 (+144%) 48 1701072 5256609 (+209%) 96 1269157 6649326 (+423%)

Additionally, a kernel with a private patch to help access() scalability: access2 ("Same file access"):

proc stock patched patched +nopause 24 2378041 2005501 5370335 (-15% / +125%)

That is, fixing the problems in access itself *reduces* scalability after the cacheline ping-pong only happens in lockref with the pause instruction.

Note that fstat and access benchmarks are not currently integrated into will-it-scale, but interested parties can find them in pull requests to said project.

Code at hand has a rather tortured history. First modification showed up in commit d472d9d98b46 ("lockref: Relax in cmpxchg loop"), written with Itanium in mind. Later it got patched up to use an arch-dependent macro to stop doing it on s390 where it caused a significant regression. Said macro had undergone revisions and was ultimately eliminated later, going back to cpu_relax.

While I intended to only remove cpu_relax for x86-64, I got the following comment from Linus:

I would actually prefer just removing it entirely and see if somebody else hollers. You have the numbers to prove it hurts on real hardware, and I don't think we have any numbers to the contrary.

So I think it's better to trust the numbers and remove it as a failure, than say "let's just remove it on x86-64 and leave everybody else with the potentially broken code"

Additionally, Will Deacon (maintainer of the arm64 port, one of the architectures previously benchmarked):

So, from the arm64 side of the fence, I'm perfectly happy just removing the cpu_relax() calls from lockref.

As such, come back full circle in history and whack it altogether.

Signed-off-by: Mateusz Guzik mjguzik@gmail.com Link: https://lore.kernel.org/all/CAGudoHHx0Nqg6DE70zAVA75eV-HXfWyhVMWZ-aSeOofkA_=... Acked-by: Tony Luck tony.luck@intel.com # ia64 Acked-by: Nicholas Piggin npiggin@gmail.com # powerpc Acked-by: Will Deacon will@kernel.org # arm64 Acked-by: Peter Zijlstra peterz@infradead.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- lib/lockref.c | 1 - 1 file changed, 1 deletion(-)

diff --git a/lib/lockref.c b/lib/lockref.c index 5b34bbd3eba8..81ac5f355242 100644 --- a/lib/lockref.c +++ b/lib/lockref.c @@ -24,7 +24,6 @@ } \ if (!--retry) \ break; \ - cpu_relax(); \ } \ } while (0)

From: Haibo Chen haibo.chen@nxp.com

[ Upstream commit 16e40e5b1e3c6646fd90d0c3186703d209216f03 ]

In current code, we add 1ms dealy after each tuning command for standard tuning method. Adding this 1ms dealy is because USDHC default check the CMD CRC and DATA line. If detect the CMD CRC, USDHC standard tuning IC logic do not wait for the tuning data sending out by the card, trigger the buffer read ready interrupt immediately, and step to next cycle. So when next time the new tuning command send out by USDHC, card may still not send out the tuning data of the upper command，then some eMMC cards may stuck, can't response to any command, block the whole tuning procedure.

If do not check the CMD CRC for tuning, then do not has this issue. USDHC will wait for the tuning data of each tuning command and check them. If the tuning data pass the check, it also means the CMD line also okay for tuning.

So this patch disable the CMD CRC check for tuning, save some time for the whole tuning procedure.

Signed-off-by: Haibo Chen haibo.chen@nxp.com Link: https://lore.kernel.org/r/1590488522-9292-2-git-send-email-haibo.chen@nxp.co... Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Stable-dep-of: 1e336aa0c025 ("mmc: sdhci-esdhc-imx: correct the tuning start tap and step setting") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/mmc/host/sdhci-esdhc-imx.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index 22bb5499f515..453ac2b6910c 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -89,6 +89,7 @@ /* NOTE: the minimum valid tuning start tap for mx6sl is 1 */ #define ESDHC_TUNING_START_TAP_DEFAULT 0x1 #define ESDHC_TUNING_START_TAP_MASK 0x7f +#define ESDHC_TUNING_CMD_CRC_CHECK_DISABLE (1 << 7) #define ESDHC_TUNING_STEP_MASK 0x00070000 #define ESDHC_TUNING_STEP_SHIFT 16

@@ -1246,6 +1247,18 @@ static void sdhci_esdhc_imx_hwinit(struct sdhci_host *host) tmp |= imx_data->boarddata.tuning_step << ESDHC_TUNING_STEP_SHIFT; } + + /* Disable the CMD CRC check for tuning, if not, need to + * add some delay after every tuning command, because + * hardware standard tuning logic will directly go to next + * step once it detect the CMD CRC error, will not wait for + * the card side to finally send out the tuning data, trigger + * the buffer read ready interrupt immediately. If usdhc send + * the next tuning command some eMMC card will stuck, can't + * response, block the tuning procedure or the first command + * after the whole tuning procedure always can't get any response. + */ + tmp |= ESDHC_TUNING_CMD_CRC_CHECK_DISABLE; writel(tmp, host->ioaddr + ESDHC_TUNING_CTRL); } else if (imx_data->socdata->flags & ESDHC_FLAG_MAN_TUNING) { /* @@ -1587,8 +1600,6 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev) if (err) goto disable_ahb_clk;

- host->tuning_delay = 1; - sdhci_esdhc_imx_hwinit(host);

err = sdhci_add_host(host);

This reverts commit 4de1a5af1be3daa8177473904dfde03b53298785.

Signed-off-by: Sasha Levin sashal@kernel.org --- .../bpf/prog_tests/jeq_infer_not_null.c | 9 ---- .../bpf/progs/jeq_infer_not_null_fail.c | 42 ------------------- 2 files changed, 51 deletions(-) delete mode 100644 tools/testing/selftests/bpf/prog_tests/jeq_infer_not_null.c delete mode 100644 tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c

diff --git a/tools/testing/selftests/bpf/prog_tests/jeq_infer_not_null.c b/tools/testing/selftests/bpf/prog_tests/jeq_infer_not_null.c deleted file mode 100644 index 3add34df5767..000000000000 --- a/tools/testing/selftests/bpf/prog_tests/jeq_infer_not_null.c +++ /dev/null @@ -1,9 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -#include <test_progs.h> -#include "jeq_infer_not_null_fail.skel.h" - -void test_jeq_infer_not_null(void) -{ - RUN_TESTS(jeq_infer_not_null_fail); -} diff --git a/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c b/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c deleted file mode 100644 index f46965053acb..000000000000 --- a/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c +++ /dev/null @@ -1,42 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -#include "vmlinux.h" -#include <bpf/bpf_helpers.h> -#include "bpf_misc.h" - -char _license[] SEC("license") = "GPL"; - -struct { - __uint(type, BPF_MAP_TYPE_HASH); - __uint(max_entries, 1); - __type(key, u64); - __type(value, u64); -} m_hash SEC(".maps"); - -SEC("?raw_tp") -__failure __msg("R8 invalid mem access 'map_value_or_null") -int jeq_infer_not_null_ptr_to_btfid(void *ctx) -{ - struct bpf_map *map = (struct bpf_map *)&m_hash; - struct bpf_map *inner_map = map->inner_map_meta; - u64 key = 0, ret = 0, *val; - - val = bpf_map_lookup_elem(map, &key); - /* Do not mark ptr as non-null if one of them is - * PTR_TO_BTF_ID (R9), reject because of invalid - * access to map value (R8). - * - * Here, we need to inline those insns to access - * R8 directly, since compiler may use other reg - * once it figures out val==inner_map. - */ - asm volatile("r8 = %[val];\n" - "r9 = %[inner_map];\n" - "if r8 != r9 goto +1;\n" - "%[ret] = *(u64 *)(r8 +0);\n" - : [ret] "+r"(ret) - : [inner_map] "r"(inner_map), [val] "r"(val) - : "r8", "r9"); - - return ret; -}

From: Dongliang Mu mudongliangabcd@gmail.com

commit 81dedaf10c20959bdf5624f9783f408df26ba7a4 upstream.

Since the commit c3d98ea08291 ("VFS: Don't use save/replace_mount_options if not using generic_show_options") eliminates replace_mount_options in reiserfs_remount, but does not handle the allocated new_opts, it will cause memory leak in the reiserfs_remount.

Because new_opts is useless in reiserfs_mount, so we fix this bug by removing the useless new_opts in reiserfs_remount.

Fixes: c3d98ea08291 ("VFS: Don't use save/replace_mount_options if not using generic_show_options") Link: https://lore.kernel.org/r/20211027143445.4156459-1-mudongliangabcd@gmail.com Signed-off-by: Dongliang Mu mudongliangabcd@gmail.com Signed-off-by: Jan Kara jack@suse.cz Signed-off-by: Fedor Pchelkin pchelkin@ispras.ru Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/reiserfs/super.c | 6 ------ 1 file changed, 6 deletions(-)

--- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -1437,7 +1437,6 @@ static int reiserfs_remount(struct super unsigned long safe_mask = 0; unsigned int commit_max_age = (unsigned int)-1; struct reiserfs_journal *journal = SB_JOURNAL(s); - char *new_opts; int err; char *qf_names[REISERFS_MAXQUOTAS]; unsigned int qfmt = 0; @@ -1445,10 +1444,6 @@ static int reiserfs_remount(struct super int i; #endif

- new_opts = kstrdup(arg, GFP_KERNEL); - if (arg && !new_opts) - return -ENOMEM; - sync_filesystem(s); reiserfs_write_lock(s);

@@ -1599,7 +1594,6 @@ out_ok_unlocked: out_err_unlock: reiserfs_write_unlock(s); out_err: - kfree(new_opts); return err; }

From: Archie Pusaka apusaka@chromium.org

commit 97dfaf073f5881c624856ef293be307b6166115c upstream.

If a command is already sent, we take care of freeing it, but we also need to cancel the timeout as well.

Signed-off-by: Archie Pusaka apusaka@chromium.org Reviewed-by: Abhishek Pandit-Subedi abhishekpandit@google.com Signed-off-by: Luiz Augusto von Dentz luiz.von.dentz@intel.com Signed-off-by: Fedor Pchelkin pchelkin@ispras.ru Signed-off-by: Sasha Levin sashal@kernel.org --- net/bluetooth/hci_core.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index e5e1c139f211..eb5b2f45deec 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1582,6 +1582,7 @@ static int hci_dev_do_open(struct hci_dev *hdev) hdev->flush(hdev);

if (hdev->sent_cmd) { + cancel_delayed_work_sync(&hdev->cmd_timer); kfree_skb(hdev->sent_cmd); hdev->sent_cmd = NULL; }

From: Petr Pavlu petr.pavlu@suse.com

commit 0254127ab977e70798707a7a2b757c9f3c971210 upstream.

During a system boot, it can happen that the kernel receives a burst of requests to insert the same module but loading it eventually fails during its init call. For instance, udev can make a request to insert a frequency module for each individual CPU when another frequency module is already loaded which causes the init function of the new module to return an error.

Since commit 6e6de3dee51a ("kernel/module.c: Only return -EEXIST for modules that have finished loading"), the kernel waits for modules in MODULE_STATE_GOING state to finish unloading before making another attempt to load the same module.

This creates unnecessary work in the described scenario and delays the boot. In the worst case, it can prevent udev from loading drivers for other devices and might cause timeouts of services waiting on them and subsequently a failed boot.

This patch attempts a different solution for the problem 6e6de3dee51a was trying to solve. Rather than waiting for the unloading to complete, it returns a different error code (-EBUSY) for modules in the GOING state. This should avoid the error situation that was described in 6e6de3dee51a (user space attempting to load a dependent module because the -EEXIST error code would suggest to user space that the first module had been loaded successfully), while avoiding the delay situation too.

This has been tested on linux-next since December 2022 and passes all kmod selftests except test 0009 with module compression enabled but it has been confirmed that this issue has existed and has gone unnoticed since prior to this commit and can also be reproduced without module compression with a simple usleep(5000000) on tools/modprobe.c [0]. These failures are caused by hitting the kernel mod_concurrent_max and can happen either due to a self inflicted kernel module auto-loead DoS somehow or on a system with large CPU count and each CPU count incorrectly triggering many module auto-loads. Both of those issues need to be fixed in-kernel.

[0] https://lore.kernel.org/all/Y9A4fiobL6IHp%2F%2FP@bombadil.infradead.org/

Fixes: 6e6de3dee51a ("kernel/module.c: Only return -EEXIST for modules that have finished loading") Co-developed-by: Martin Wilck mwilck@suse.com Signed-off-by: Martin Wilck mwilck@suse.com Signed-off-by: Petr Pavlu petr.pavlu@suse.com Cc: stable@vger.kernel.org Reviewed-by: Petr Mladek pmladek@suse.com [mcgrof: enhance commit log with testing and kmod test result interpretation ] Signed-off-by: Luis Chamberlain mcgrof@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/module.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-)

--- a/kernel/module.c +++ b/kernel/module.c @@ -3654,7 +3654,8 @@ static bool finished_loading(const char sched_annotate_sleep(); mutex_lock(&module_mutex); mod = find_module_all(name, strlen(name), true); - ret = !mod || mod->state == MODULE_STATE_LIVE; + ret = !mod || mod->state == MODULE_STATE_LIVE + || mod->state == MODULE_STATE_GOING; mutex_unlock(&module_mutex);

return ret; @@ -3820,20 +3821,35 @@ static int add_unformed_module(struct mo

mod->state = MODULE_STATE_UNFORMED;

-again: mutex_lock(&module_mutex); old = find_module_all(mod->name, strlen(mod->name), true); if (old != NULL) { - if (old->state != MODULE_STATE_LIVE) { + if (old->state == MODULE_STATE_COMING + || old->state == MODULE_STATE_UNFORMED) { /* Wait in case it fails to load. */ mutex_unlock(&module_mutex); err = wait_event_interruptible(module_wq, finished_loading(mod->name)); if (err) goto out_unlocked; - goto again; + + /* The module might have gone in the meantime. */ + mutex_lock(&module_mutex); + old = find_module_all(mod->name, strlen(mod->name), + true); } - err = -EEXIST; + + /* + * We are here only when the same module was being loaded. Do + * not try to load it again right now. It prevents long delays + * caused by serialized module load failures. It might happen + * when more devices of the same type trigger load of + * a particular module. + */ + if (old && old->state == MODULE_STATE_LIVE) + err = -EEXIST; + else + err = -EBUSY; goto out; } mod_update_bounds(mod);

From: Natalia Petrova n.petrova@fintech.ru

commit 8b152e9150d07a885f95e1fd401fc81af202d9a4 upstream.

Function 'create_hist_field' is called recursively at trace_events_hist.c:1954 and can return NULL-value that's why we have to check it to avoid null pointer dereference.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Link: https://lkml.kernel.org/r/20230111120409.4111-1-n.petrova@fintech.ru

Cc: stable@vger.kernel.org Fixes: 30350d65ac56 ("tracing: Add variable support to hist triggers") Signed-off-by: Natalia Petrova n.petrova@fintech.ru Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/trace_events_hist.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -2552,6 +2552,8 @@ static struct hist_field *create_hist_fi unsigned long fl = flags & ~HIST_FIELD_FL_LOG2; hist_field->fn = hist_field_log2; hist_field->operands[0] = create_hist_field(hist_data, field, fl, NULL); + if (!hist_field->operands[0]) + goto free; hist_field->size = hist_field->operands[0]->size; hist_field->type = kstrdup(hist_field->operands[0]->type, GFP_KERNEL); if (!hist_field->type)

From: David Howells dhowells@redhat.com

commit b7ab9161cf5ddc42a288edf9d1a61f3bdffe17c7 upstream.

In smbd_destroy(), clear the server->smbd_conn pointer after freeing the smbd_connection struct that it points to so that reconnection doesn't get confused.

Fixes: 8ef130f9ec27 ("CIFS: SMBD: Implement function to destroy a SMB Direct connection") Cc: stable@vger.kernel.org Reviewed-by: Paulo Alcantara (SUSE) pc@cjr.nz Acked-by: Tom Talpey tom@talpey.com Signed-off-by: David Howells dhowells@redhat.com Cc: Long Li longli@microsoft.com Cc: Pavel Shilovsky piastryyy@gmail.com Cc: Ronnie Sahlberg lsahlber@redhat.com Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/cifs/smbdirect.c | 1 + 1 file changed, 1 insertion(+)

--- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -1478,6 +1478,7 @@ void smbd_destroy(struct TCP_Server_Info destroy_workqueue(info->workqueue); log_rdma_event(INFO, "rdma session destroyed\n"); kfree(info); + server->smbd_conn = NULL; }

/*

From: Srinivas Pandruvada srinivas.pandruvada@linux.intel.com

commit 6757a7abe47bcb12cb2d45661067e182424b0ee3 upstream.

Trip temperatures are read using ACPI methods and stored in the memory during zone initializtion and when the firmware sends a notification for change. This trip temperature is returned when the thermal core calls via callback get_trip_temp().

But it is possible that while updating the memory copy of the trips when the firmware sends a notification for change, thermal core is reading the trip temperature via the callback get_trip_temp(). This may return invalid trip temperature.

To address this add a mutex to protect the invalid temperature reads in the callback get_trip_temp() and int340x_thermal_read_trips().

Fixes: 5fbf7f27fa3d ("Thermal/int340x: Add common thermal zone handler") Signed-off-by: Srinivas Pandruvada srinivas.pandruvada@linux.intel.com Cc: 5.0+ stable@vger.kernel.org # 5.0+ Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c | 18 +++++++++-- drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h | 1 2 files changed, 16 insertions(+), 3 deletions(-)

--- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c +++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c @@ -43,11 +43,13 @@ static int int340x_thermal_get_trip_temp int trip, int *temp) { struct int34x_thermal_zone *d = zone->devdata; - int i; + int i, ret = 0;

if (d->override_ops && d->override_ops->get_trip_temp) return d->override_ops->get_trip_temp(zone, trip, temp);

+ mutex_lock(&d->trip_mutex); + if (trip < d->aux_trip_nr) *temp = d->aux_trips[trip]; else if (trip == d->crt_trip_id) @@ -65,10 +67,12 @@ static int int340x_thermal_get_trip_temp } } if (i == INT340X_THERMAL_MAX_ACT_TRIP_COUNT) - return -EINVAL; + ret = -EINVAL; }

- return 0; + mutex_unlock(&d->trip_mutex); + + return ret; }

static int int340x_thermal_get_trip_type(struct thermal_zone_device *zone, @@ -173,6 +177,8 @@ int int340x_thermal_read_trips(struct in int trip_cnt = int34x_zone->aux_trip_nr; int i;

+ mutex_lock(&int34x_zone->trip_mutex); + int34x_zone->crt_trip_id = -1; if (!int340x_thermal_get_trip_config(int34x_zone->adev->handle, "_CRT", &int34x_zone->crt_temp)) @@ -200,6 +206,8 @@ int int340x_thermal_read_trips(struct in int34x_zone->act_trips[i].valid = true; }

+ mutex_unlock(&int34x_zone->trip_mutex); + return trip_cnt; } EXPORT_SYMBOL_GPL(int340x_thermal_read_trips); @@ -223,6 +231,8 @@ struct int34x_thermal_zone *int340x_ther if (!int34x_thermal_zone) return ERR_PTR(-ENOMEM);

+ mutex_init(&int34x_thermal_zone->trip_mutex); + int34x_thermal_zone->adev = adev; int34x_thermal_zone->override_ops = override_ops;

@@ -269,6 +279,7 @@ err_thermal_zone: acpi_lpat_free_conversion_table(int34x_thermal_zone->lpat_table); kfree(int34x_thermal_zone->aux_trips); err_trip_alloc: + mutex_destroy(&int34x_thermal_zone->trip_mutex); kfree(int34x_thermal_zone); return ERR_PTR(ret); } @@ -280,6 +291,7 @@ void int340x_thermal_zone_remove(struct thermal_zone_device_unregister(int34x_thermal_zone->zone); acpi_lpat_free_conversion_table(int34x_thermal_zone->lpat_table); kfree(int34x_thermal_zone->aux_trips); + mutex_destroy(&int34x_thermal_zone->trip_mutex); kfree(int34x_thermal_zone); } EXPORT_SYMBOL_GPL(int340x_thermal_zone_remove); --- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h +++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h @@ -32,6 +32,7 @@ struct int34x_thermal_zone { struct thermal_zone_device_ops *override_ops; void *priv_data; struct acpi_lpat_conversion_table *lpat_table; + struct mutex trip_mutex; };

struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *,

From: Manivannan Sadhasivam manivannan.sadhasivam@linaro.org

commit cec669ff716cc83505c77b242aecf6f7baad869d upstream.

The EDAC drivers may optionally pass the poll_msec value. Use that value if available, else fall back to 1000ms.

[ bp: Touchups. ]

Fixes: e27e3dac6517 ("drivers/edac: add edac_device class") Reported-by: Luca Weiss luca.weiss@fairphone.com Signed-off-by: Manivannan Sadhasivam manivannan.sadhasivam@linaro.org Signed-off-by: Borislav Petkov (AMD) bp@alien8.de Tested-by: Steev Klimaszewski steev@kali.org # Thinkpad X13s Tested-by: Andrew Halaney ahalaney@redhat.com # sa8540p-ride Cc: stable@vger.kernel.org # 4.9 Link: https://lore.kernel.org/r/COZYL8MWN97H.MROQ391BGA09@otso Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/edac/edac_device.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-)

--- a/drivers/edac/edac_device.c +++ b/drivers/edac/edac_device.c @@ -34,6 +34,9 @@ static DEFINE_MUTEX(device_ctls_mutex); static LIST_HEAD(edac_device_list);

+/* Default workqueue processing interval on this instance, in msecs */ +#define DEFAULT_POLL_INTERVAL 1000 + #ifdef CONFIG_EDAC_DEBUG static void edac_device_dump_device(struct edac_device_ctl_info *edac_dev) { @@ -366,7 +369,7 @@ static void edac_device_workq_function(s * whole one second to save timers firing all over the period * between integral seconds */ - if (edac_dev->poll_msec == 1000) + if (edac_dev->poll_msec == DEFAULT_POLL_INTERVAL) edac_queue_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay)); else edac_queue_work(&edac_dev->work, edac_dev->delay); @@ -396,7 +399,7 @@ static void edac_device_workq_setup(stru * timers firing on sub-second basis, while they are happy * to fire together on the 1 second exactly */ - if (edac_dev->poll_msec == 1000) + if (edac_dev->poll_msec == DEFAULT_POLL_INTERVAL) edac_queue_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay)); else edac_queue_work(&edac_dev->work, edac_dev->delay); @@ -430,7 +433,7 @@ void edac_device_reset_delay_period(stru edac_dev->delay = msecs_to_jiffies(msec);

/* See comment in edac_device_workq_setup() above */ - if (edac_dev->poll_msec == 1000) + if (edac_dev->poll_msec == DEFAULT_POLL_INTERVAL) edac_mod_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay)); else edac_mod_work(&edac_dev->work, edac_dev->delay); @@ -472,11 +475,7 @@ int edac_device_add_device(struct edac_d /* This instance is NOW RUNNING */ edac_dev->op_state = OP_RUNNING_POLL;

- /* - * enable workq processing on this instance, - * default = 1000 msec - */ - edac_device_workq_setup(edac_dev, 1000); + edac_device_workq_setup(edac_dev, edac_dev->poll_msec ?: DEFAULT_POLL_INTERVAL); } else { edac_dev->op_state = OP_RUNNING_INTERRUPT; }

From: Eric Dumazet edumazet@google.com

[ Upstream commit f0950402e8c76e7dcb08563f1b4e8000fbc62455 ]

Most netlink attributes are parsed and validated from __nla_validate_parse() or validate_nla()

u16 type = nla_type(nla);

if (type == 0 || type > maxtype) { /* error or continue */ }

@type is then used as an array index and can be used as a Spectre v1 gadget.

array_index_nospec() can be used to prevent leaking content of kernel memory to malicious users.

This should take care of vast majority of netlink uses, but an audit is needed to take care of others where validation is not yet centralized in core netlink functions.

Fixes: bfa83a9e03cf ("[NETLINK]: Type-safe netlink messages/attributes interface") Signed-off-by: Eric Dumazet edumazet@google.com Link: https://lore.kernel.org/r/20230119110150.2678537-1-edumazet@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- lib/nlattr.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/lib/nlattr.c b/lib/nlattr.c index 0d84f79cb4b5..b5ce5e46c06e 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -10,6 +10,7 @@ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/jiffies.h> +#include <linux/nospec.h> #include <linux/skbuff.h> #include <linux/string.h> #include <linux/types.h> @@ -169,6 +170,7 @@ static int validate_nla(const struct nlattr *nla, int maxtype, if (type <= 0 || type > maxtype) return 0;

+ type = array_index_nospec(type, maxtype + 1); pt = &policy[type];

BUG_ON(pt->type > NLA_TYPE_MAX); @@ -377,6 +379,7 @@ static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype, } continue; } + type = array_index_nospec(type, maxtype + 1); if (policy) { int err = validate_nla(nla, maxtype, policy, validate, extack);

From: Pablo Neira Ayuso pablo@netfilter.org

[ Upstream commit 5d235d6ce75c12a7fdee375eb211e4116f7ab01b ]

Skip interference with an ongoing transaction, do not perform garbage collection on inactive elements. Reset annotated previous end interval if the expired element is marked as busy (control plane removed the element right before expiration).

Fixes: 8d8540c4f5e0 ("netfilter: nft_set_rbtree: add timeout support") Reviewed-by: Stefano Brivio sbrivio@redhat.com Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nft_set_rbtree.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index ee7c29e0a9d7..093eea02f9d2 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -389,23 +389,37 @@ static void nft_rbtree_gc(struct work_struct *work) struct nft_rbtree *priv; struct rb_node *node; struct nft_set *set; + struct net *net; + u8 genmask;

priv = container_of(work, struct nft_rbtree, gc_work.work); set = nft_set_container_of(priv); + net = read_pnet(&set->net); + genmask = nft_genmask_cur(net);

write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { rbe = rb_entry(node, struct nft_rbtree_elem, node);

+ if (!nft_set_elem_active(&rbe->ext, genmask)) + continue; + + /* elements are reversed in the rbtree for historical reasons, + * from highest to lowest value, that is why end element is + * always visited before the start element. + */ if (nft_rbtree_interval_end(rbe)) { rbe_end = rbe; continue; } if (!nft_set_elem_expired(&rbe->ext)) continue; - if (nft_set_elem_mark_busy(&rbe->ext)) + + if (nft_set_elem_mark_busy(&rbe->ext)) { + rbe_end = NULL; continue; + }

if (rbe_prev) { rb_erase(&rbe_prev->node, &priv->root);

From: Eric Dumazet edumazet@google.com

[ Upstream commit 004db64d185a5f23dfb891d7701e23713b2420ee ]

netlink_getname(), netlink_sendmsg() and netlink_getsockbyportid() can read nlk->dst_portid and nlk->dst_group while another thread is changing them.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netlink/af_netlink.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index f6b985877d9c..d398623d8275 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1081,8 +1081,9 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,

if (addr->sa_family == AF_UNSPEC) { sk->sk_state = NETLINK_UNCONNECTED; - nlk->dst_portid = 0; - nlk->dst_group = 0; + /* dst_portid and dst_group can be read locklessly */ + WRITE_ONCE(nlk->dst_portid, 0); + WRITE_ONCE(nlk->dst_group, 0); return 0; } if (addr->sa_family != AF_NETLINK) @@ -1104,8 +1105,9 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,

if (err == 0) { sk->sk_state = NETLINK_CONNECTED; - nlk->dst_portid = nladdr->nl_pid; - nlk->dst_group = ffs(nladdr->nl_groups); + /* dst_portid and dst_group can be read locklessly */ + WRITE_ONCE(nlk->dst_portid, nladdr->nl_pid); + WRITE_ONCE(nlk->dst_group, ffs(nladdr->nl_groups)); }

return err; @@ -1122,8 +1124,9 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr, nladdr->nl_pad = 0;

if (peer) { - nladdr->nl_pid = nlk->dst_portid; - nladdr->nl_groups = netlink_group_mask(nlk->dst_group); + /* Paired with WRITE_ONCE() in netlink_connect() */ + nladdr->nl_pid = READ_ONCE(nlk->dst_portid); + nladdr->nl_groups = netlink_group_mask(READ_ONCE(nlk->dst_group)); } else { /* Paired with WRITE_ONCE() in netlink_insert() */ nladdr->nl_pid = READ_ONCE(nlk->portid); @@ -1153,8 +1156,9 @@ static struct sock *netlink_getsockbyportid(struct sock *ssk, u32 portid)

/* Don't bother queuing skb if kernel socket has no input function */ nlk = nlk_sk(sock); + /* dst_portid can be changed in netlink_connect() */ if (sock->sk_state == NETLINK_CONNECTED && - nlk->dst_portid != nlk_sk(ssk)->portid) { + READ_ONCE(nlk->dst_portid) != nlk_sk(ssk)->portid) { sock_put(sock); return ERR_PTR(-ECONNREFUSED); } @@ -1890,8 +1894,9 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) goto out; netlink_skb_flags |= NETLINK_SKB_DST; } else { - dst_portid = nlk->dst_portid; - dst_group = nlk->dst_group; + /* Paired with WRITE_ONCE() in netlink_connect() */ + dst_portid = READ_ONCE(nlk->dst_portid); + dst_group = READ_ONCE(nlk->dst_group); }

/* Paired with WRITE_ONCE() in netlink_insert() */

From: Eric Dumazet edumazet@google.com

[ Upstream commit 1d1d63b612801b3f0a39b7d4467cad0abd60e5c8 ]

if (!type) continue; if (type > RTAX_MAX) return -EINVAL; ... metrics[type - 1] = val;

@type being used as an array index, we need to prevent cpu speculation or risk leaking kernel memory content.

Fixes: 6cf9dfd3bd62 ("net: fib: move metrics parsing to a helper") Signed-off-by: Eric Dumazet edumazet@google.com Link: https://lore.kernel.org/r/20230120133040.3623463-1-edumazet@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/metrics.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c index 3205d5f7c8c9..4966ac2aaf87 100644 --- a/net/ipv4/metrics.c +++ b/net/ipv4/metrics.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only #include <linux/netlink.h> +#include <linux/nospec.h> #include <linux/rtnetlink.h> #include <linux/types.h> #include <net/ip.h> @@ -28,6 +29,7 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, return -EINVAL; }

+ type = array_index_nospec(type, RTAX_MAX + 1); if (type == RTAX_CC_ALGO) { char tmp[TCP_CA_NAME_MAX];

From: Sriram Yagnaraman sriram.yagnaraman@est.tech

[ Upstream commit a9993591fa94246b16b444eea55d84c54608282a ]

RFC 9260, Sec 8.5.1 states that for ABORT/SHUTDOWN_COMPLETE, the chunk MUST be accepted if the vtag of the packet matches its own tag and the T bit is not set OR if it is set to its peer's vtag and the T bit is set in chunk flags. Otherwise the packet MUST be silently dropped.

Update vtag verification for ABORT/SHUTDOWN_COMPLETE based on the above description.

Fixes: 9fb9cbb1082d ("[NETFILTER]: Add nf_conntrack subsystem.") Signed-off-by: Sriram Yagnaraman sriram.yagnaraman@est.tech Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_conntrack_proto_sctp.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 7626f3e1c70a..72d0aa603cd6 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -412,22 +412,29 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, for_each_sctp_chunk (skb, sch, _sch, offset, dataoff, count) { /* Special cases of Verification tag check (Sec 8.5.1) */ if (sch->type == SCTP_CID_INIT) { - /* Sec 8.5.1 (A) */ + /* (A) vtag MUST be zero */ if (sh->vtag != 0) goto out_unlock; } else if (sch->type == SCTP_CID_ABORT) { - /* Sec 8.5.1 (B) */ - if (sh->vtag != ct->proto.sctp.vtag[dir] && - sh->vtag != ct->proto.sctp.vtag[!dir]) + /* (B) vtag MUST match own vtag if T flag is unset OR + * MUST match peer's vtag if T flag is set + */ + if ((!(sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[dir]) || + ((sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[!dir])) goto out_unlock; } else if (sch->type == SCTP_CID_SHUTDOWN_COMPLETE) { - /* Sec 8.5.1 (C) */ - if (sh->vtag != ct->proto.sctp.vtag[dir] && - sh->vtag != ct->proto.sctp.vtag[!dir] && - sch->flags & SCTP_CHUNK_FLAG_T) + /* (C) vtag MUST match own vtag if T flag is unset OR + * MUST match peer's vtag if T flag is set + */ + if ((!(sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[dir]) || + ((sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[!dir])) goto out_unlock; } else if (sch->type == SCTP_CID_COOKIE_ECHO) { - /* Sec 8.5.1 (D) */ + /* (D) vtag must be same as init_vtag as found in INIT_ACK */ if (sh->vtag != ct->proto.sctp.vtag[dir]) goto out_unlock; } else if (sch->type == SCTP_CID_HEARTBEAT) {

From: Eric Dumazet edumazet@google.com

[ Upstream commit ea4fdbaa2f7798cb25adbe4fd52ffc6356f097bb ]

As reported by syzbot and hinted by Vinicius, I should not have added a qdisc_synchronize() call in taprio_reset()

taprio_reset() can be called with qdisc spinlock held (and BH disabled) as shown in included syzbot report [1].

Only taprio_destroy() needed this synchronization, as explained in the blamed commit changelog.

[1]

BUG: scheduling while atomic: syz-executor150/5091/0x00000202 2 locks held by syz-executor150/5091: Modules linked in: Preemption disabled at: [<0000000000000000>] 0x0 Kernel panic - not syncing: scheduling while atomic: panic_on_warn set ... CPU: 1 PID: 5091 Comm: syz-executor150 Not tainted 6.2.0-rc3-syzkaller-00219-g010a74f52203 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/12/2023 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd1/0x138 lib/dump_stack.c:106 panic+0x2cc/0x626 kernel/panic.c:318 check_panic_on_warn.cold+0x19/0x35 kernel/panic.c:238 __schedule_bug.cold+0xd5/0xfe kernel/sched/core.c:5836 schedule_debug kernel/sched/core.c:5865 [inline] __schedule+0x34e4/0x5450 kernel/sched/core.c:6500 schedule+0xde/0x1b0 kernel/sched/core.c:6682 schedule_timeout+0x14e/0x2a0 kernel/time/timer.c:2167 schedule_timeout_uninterruptible kernel/time/timer.c:2201 [inline] msleep+0xb6/0x100 kernel/time/timer.c:2322 qdisc_synchronize include/net/sch_generic.h:1295 [inline] taprio_reset+0x93/0x270 net/sched/sch_taprio.c:1703 qdisc_reset+0x10c/0x770 net/sched/sch_generic.c:1022 dev_reset_queue+0x92/0x130 net/sched/sch_generic.c:1285 netdev_for_each_tx_queue include/linux/netdevice.h:2464 [inline] dev_deactivate_many+0x36d/0x9f0 net/sched/sch_generic.c:1351 dev_deactivate+0xed/0x1b0 net/sched/sch_generic.c:1374 qdisc_graft+0xe4a/0x1380 net/sched/sch_api.c:1080 tc_modify_qdisc+0xb6b/0x19a0 net/sched/sch_api.c:1689 rtnetlink_rcv_msg+0x43e/0xca0 net/core/rtnetlink.c:6141 netlink_rcv_skb+0x165/0x440 net/netlink/af_netlink.c:2564 netlink_unicast_kernel net/netlink/af_netlink.c:1330 [inline] netlink_unicast+0x547/0x7f0 net/netlink/af_netlink.c:1356 netlink_sendmsg+0x91b/0xe10 net/netlink/af_netlink.c:1932 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg+0xd3/0x120 net/socket.c:734 ____sys_sendmsg+0x712/0x8c0 net/socket.c:2476 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2530 __sys_sendmsg+0xf7/0x1c0 net/socket.c:2559 do_syscall_x64 arch/x86/entry/common.c:50 [inline]

Fixes: 3a415d59c1db ("net/sched: sch_taprio: fix possible use-after-free") Link: https://lore.kernel.org/netdev/167387581653.2747.13878941339893288655.git-pa... Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: Eric Dumazet edumazet@google.com Cc: Vinicius Costa Gomes vinicius.gomes@intel.com Link: https://lore.kernel.org/r/20230123084552.574396-1-edumazet@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/sch_taprio.c | 1 - 1 file changed, 1 deletion(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 4278a466cb50..b7bd8c3e3158 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1622,7 +1622,6 @@ static void taprio_reset(struct Qdisc *sch) int i;

hrtimer_cancel(&q->advance_timer); - qdisc_synchronize(sch);

if (q->qdiscs) { for (i = 0; i < dev->num_tx_queues && q->qdiscs[i]; i++)

From: Yoshihiro Shimoda yoshihiro.shimoda.uh@renesas.com

[ Upstream commit f3c07758c9007a6bfff5290d9e19d3c41930c897 ]

Since this driver enables the interrupt by RIC2_QFE1, this driver should clear the interrupt flag if it happens. Otherwise, the interrupt causes to hang the system.

Note that this also fix a minor coding style (a comment indentation) around the fixed code.

Fixes: c156633f1353 ("Renesas Ethernet AVB driver proper") Signed-off-by: Yoshihiro Shimoda yoshihiro.shimoda.uh@renesas.com Reviewed-by: Sergey Shtylyov s.shtylyov@omp.ru Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/renesas/ravb_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 3fd5155bdd5f..231a1295c470 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -736,14 +736,14 @@ static void ravb_error_interrupt(struct net_device *ndev) ravb_write(ndev, ~(EIS_QFS | EIS_RESERVED), EIS); if (eis & EIS_QFS) { ris2 = ravb_read(ndev, RIS2); - ravb_write(ndev, ~(RIS2_QFF0 | RIS2_RFFF | RIS2_RESERVED), + ravb_write(ndev, ~(RIS2_QFF0 | RIS2_QFF1 | RIS2_RFFF | RIS2_RESERVED), RIS2);

/* Receive Descriptor Empty int */ if (ris2 & RIS2_QFF0) priv->stats[RAVB_BE].rx_over_errors++;

- /* Receive Descriptor Empty int */ + /* Receive Descriptor Empty int */ if (ris2 & RIS2_QFF1) priv->stats[RAVB_NC].rx_over_errors++;

From: David Christensen drc@linux.vnet.ibm.com

[ Upstream commit 6c4ca03bd890566d873e3593b32d034bf2f5a087 ]

During EEH error injection testing, a deadlock was encountered in the tg3 driver when tg3_io_error_detected() was attempting to cancel outstanding reset tasks:

crash> foreach UN bt ... PID: 159 TASK: c0000000067c6000 CPU: 8 COMMAND: "eehd" ... #5 [c00000000681f990] __cancel_work_timer at c00000000019fd18 #6 [c00000000681fa30] tg3_io_error_detected at c00800000295f098 [tg3] #7 [c00000000681faf0] eeh_report_error at c00000000004e25c ...

PID: 290 TASK: c000000036e5f800 CPU: 6 COMMAND: "kworker/6:1" ... #4 [c00000003721fbc0] rtnl_lock at c000000000c940d8 #5 [c00000003721fbe0] tg3_reset_task at c008000002969358 [tg3] #6 [c00000003721fc60] process_one_work at c00000000019e5c4 ...

PID: 296 TASK: c000000037a65800 CPU: 21 COMMAND: "kworker/21:1" ... #4 [c000000037247bc0] rtnl_lock at c000000000c940d8 #5 [c000000037247be0] tg3_reset_task at c008000002969358 [tg3] #6 [c000000037247c60] process_one_work at c00000000019e5c4 ...

PID: 655 TASK: c000000036f49000 CPU: 16 COMMAND: "kworker/16:2" ...:1

#4 [c0000000373ebbc0] rtnl_lock at c000000000c940d8 #5 [c0000000373ebbe0] tg3_reset_task at c008000002969358 [tg3] #6 [c0000000373ebc60] process_one_work at c00000000019e5c4 ...

Code inspection shows that both tg3_io_error_detected() and tg3_reset_task() attempt to acquire the RTNL lock at the beginning of their code blocks. If tg3_reset_task() should happen to execute between the times when tg3_io_error_deteced() acquires the RTNL lock and tg3_reset_task_cancel() is called, a deadlock will occur.

Moving tg3_reset_task_cancel() call earlier within the code block, prior to acquiring RTNL, prevents this from happening, but also exposes another deadlock issue where tg3_reset_task() may execute AFTER tg3_io_error_detected() has executed:

crash> foreach UN bt PID: 159 TASK: c0000000067d2000 CPU: 9 COMMAND: "eehd" ... #4 [c000000006867a60] rtnl_lock at c000000000c940d8 #5 [c000000006867a80] tg3_io_slot_reset at c0080000026c2ea8 [tg3] #6 [c000000006867b00] eeh_report_reset at c00000000004de88 ... PID: 363 TASK: c000000037564000 CPU: 6 COMMAND: "kworker/6:1" ... #3 [c000000036c1bb70] msleep at c000000000259e6c #4 [c000000036c1bba0] napi_disable at c000000000c6b848 #5 [c000000036c1bbe0] tg3_reset_task at c0080000026d942c [tg3] #6 [c000000036c1bc60] process_one_work at c00000000019e5c4 ...

This issue can be avoided by aborting tg3_reset_task() if EEH error recovery is already in progress.

Fixes: db84bf43ef23 ("tg3: tg3_reset_task() needs to use rtnl_lock to synchronize") Signed-off-by: David Christensen drc@linux.vnet.ibm.com Reviewed-by: Pavan Chebbi pavan.chebbi@broadcom.com Link: https://lore.kernel.org/r/20230124185339.225806-1-drc@linux.vnet.ibm.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/broadcom/tg3.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index a9962474d551..d0cd86af29d9 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -11195,7 +11195,7 @@ static void tg3_reset_task(struct work_struct *work) rtnl_lock(); tg3_full_lock(tp, 0);

- if (!netif_running(tp->dev)) { + if (tp->pcierr_recovery || !netif_running(tp->dev)) { tg3_flag_clear(tp, RESET_TASK_PENDING); tg3_full_unlock(tp); rtnl_unlock(); @@ -18187,6 +18187,9 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,

netdev_info(netdev, "PCI I/O error detected\n");

+ /* Want to make sure that the reset task doesn't run */ + tg3_reset_task_cancel(tp); + rtnl_lock();

/* Could be second call or maybe we don't have netdev yet */ @@ -18203,9 +18206,6 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,

tg3_timer_stop(tp);

- /* Want to make sure that the reset task doesn't run */ - tg3_reset_task_cancel(tp); - netif_device_detach(netdev);

/* Clean up software state, even if MMIO is blocked */

From: Andrew Lunn andrew@lunn.ch

[ Upstream commit 232e15e1d7ddb191c28248cb681f4544c0ff1c54 ]

This header file is currently included into the ethernet driver via a relative path into the PHY subsystem. This is bad practice, and causes issues for the upcoming move of the MDIO driver. Move the header file into include/linux to clean this up.

v2: Move header to include/linux/mdio

Reviewed-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: Andrew Lunn andrew@lunn.ch Signed-off-by: David S. Miller davem@davemloft.net Stable-dep-of: 7083df59abbc ("net: mdio-mux-meson-g12a: force internal PHY off on mux switch") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/apm/xgene/xgene_enet_main.h | 2 +- drivers/net/phy/mdio-xgene.c | 2 +- {drivers/net/phy => include/linux/mdio}/mdio-xgene.h | 0 3 files changed, 2 insertions(+), 2 deletions(-) rename {drivers/net/phy => include/linux/mdio}/mdio-xgene.h (100%)

diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h index 18f4923b1723..6a253f81c555 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h @@ -18,6 +18,7 @@ #include <linux/of_platform.h> #include <linux/of_net.h> #include <linux/of_mdio.h> +#include <linux/mdio/mdio-xgene.h> #include <linux/module.h> #include <net/ip.h> #include <linux/prefetch.h> @@ -26,7 +27,6 @@ #include "xgene_enet_hw.h" #include "xgene_enet_cle.h" #include "xgene_enet_ring2.h" -#include "../../../phy/mdio-xgene.h"

#define XGENE_DRV_VERSION "v1.0" #define ETHER_MIN_PACKET 64 diff --git a/drivers/net/phy/mdio-xgene.c b/drivers/net/phy/mdio-xgene.c index 34990eaa3298..461207cdf5d6 100644 --- a/drivers/net/phy/mdio-xgene.c +++ b/drivers/net/phy/mdio-xgene.c @@ -11,6 +11,7 @@ #include <linux/efi.h> #include <linux/if_vlan.h> #include <linux/io.h> +#include <linux/mdio/mdio-xgene.h> #include <linux/module.h> #include <linux/of_platform.h> #include <linux/of_net.h> @@ -18,7 +19,6 @@ #include <linux/prefetch.h> #include <linux/phy.h> #include <net/ip.h> -#include "mdio-xgene.h"

static bool xgene_mdio_status;

diff --git a/drivers/net/phy/mdio-xgene.h b/include/linux/mdio/mdio-xgene.h similarity index 100% rename from drivers/net/phy/mdio-xgene.h rename to include/linux/mdio/mdio-xgene.h

From: Dmitry Torokhov dmitry.torokhov@gmail.com

commit 3c44e2b6cde674797b76e76d3a903a63ce8a18bb upstream.

This reverts commit ac5408991ea6b06e29129b4d4861097c4c3e0d59 because it causes loss of keyboard on HP 15-da1xxx.

Fixes: ac5408991ea6 ("Input: synaptics - switch touchpad on HP Laptop 15-da3001TU to RMI mode") Reported-by: Jiri Slaby jirislaby@kernel.org Link: https://lore.kernel.org/r/824effa5-8b9a-c28a-82bb-9b0ab24623e1@kernel.org Bugzilla: https://bugzilla.suse.com/show_bug.cgi?id=1206358 Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov dmitry.torokhov@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/input/mouse/synaptics.c | 1 - 1 file changed, 1 deletion(-)

--- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -189,7 +189,6 @@ static const char * const smbus_pnp_ids[ "SYN3221", /* HP 15-ay000 */ "SYN323d", /* HP Spectre X360 13-w013dx */ "SYN3257", /* HP Envy 13-ad105ng */ - "SYN3286", /* HP Laptop 15-da3001TU */ NULL };

From: Christoph Hellwig hch@lst.de

commit 57e95e4670d1126c103305bcf34a9442f49f6d6a upstream.

Don't use a WARN_ON when printing a potentially user triggered condition. Also don't print the partno when the block device name already includes it, and use the %pg specifier to simplify printing the block device name.

Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Chaitanya Kulkarni kch@nvidia.com Reviewed-by: Johannes Thumshirn johannes.thumshirn@wdc.com Link: https://lore.kernel.org/r/20220304180105.409765-2-hch@lst.de Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Fedor Pchelkin pchelkin@ispras.ru Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- block/blk-core.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-)

--- a/block/blk-core.c +++ b/block/blk-core.c @@ -793,10 +793,7 @@ static inline bool bio_check_ro(struct b

if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) return false; - - WARN_ONCE(1, - "generic_make_request: Trying to write " - "to read-only block-device %s (partno %d)\n", + pr_warn("Trying to write to read-only block-device %s (partno %d)\n", bio_devname(bio, b), part->partno); /* Older lvm-tools actually trigger this */ return false;

From: Sriram Yagnaraman sriram.yagnaraman@est.tech

commit a44b7651489f26271ac784b70895e8a85d0cebf4 upstream.

An SCTP endpoint can start an association through a path and tear it down over another one. That means the initial path will not see the shutdown sequence, and the conntrack entry will remain in ESTABLISHED state for 5 days.

By merging the HEARTBEAT_ACKED and ESTABLISHED states into one ESTABLISHED state, there remains no difference between a primary or secondary path. The timeout for the merged ESTABLISHED state is set to 210 seconds (hb_interval * max_path_retrans + rto_max). So, even if a path doesn't see the shutdown sequence, it will expire in a reasonable amount of time.

With this change in place, there is now more than one state from which we can transition to ESTABLISHED, COOKIE_ECHOED and HEARTBEAT_SENT, so handle the setting of ASSURED bit whenever a state change has happened and the new state is ESTABLISHED. Removed the check for dir==REPLY since the transition to ESTABLISHED can happen only in the reply direction.

Fixes: 9fb9cbb1082d ("[NETFILTER]: Add nf_conntrack subsystem.") Signed-off-by: Sriram Yagnaraman sriram.yagnaraman@est.tech Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/uapi/linux/netfilter/nf_conntrack_sctp.h | 2 include/uapi/linux/netfilter/nfnetlink_cttimeout.h | 2 net/netfilter/nf_conntrack_proto_sctp.c | 93 ++++++++------------- net/netfilter/nf_conntrack_standalone.c | 8 - 4 files changed, 41 insertions(+), 64 deletions(-)

--- a/include/uapi/linux/netfilter/nf_conntrack_sctp.h +++ b/include/uapi/linux/netfilter/nf_conntrack_sctp.h @@ -15,7 +15,7 @@ enum sctp_conntrack { SCTP_CONNTRACK_SHUTDOWN_RECD, SCTP_CONNTRACK_SHUTDOWN_ACK_SENT, SCTP_CONNTRACK_HEARTBEAT_SENT, - SCTP_CONNTRACK_HEARTBEAT_ACKED, + SCTP_CONNTRACK_HEARTBEAT_ACKED, /* no longer used */ SCTP_CONNTRACK_MAX };

--- a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h +++ b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h @@ -94,7 +94,7 @@ enum ctattr_timeout_sctp { CTA_TIMEOUT_SCTP_SHUTDOWN_RECD, CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT, CTA_TIMEOUT_SCTP_HEARTBEAT_SENT, - CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED, + CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED, /* no longer used */ __CTA_TIMEOUT_SCTP_MAX }; #define CTA_TIMEOUT_SCTP_MAX (__CTA_TIMEOUT_SCTP_MAX - 1) --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -27,22 +27,16 @@ #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_timeout.h>

-/* FIXME: Examine ipfilter's timeouts and conntrack transitions more - closely. They're more complex. --RR - - And so for me for SCTP :D -Kiran */ - static const char *const sctp_conntrack_names[] = { - "NONE", - "CLOSED", - "COOKIE_WAIT", - "COOKIE_ECHOED", - "ESTABLISHED", - "SHUTDOWN_SENT", - "SHUTDOWN_RECD", - "SHUTDOWN_ACK_SENT", - "HEARTBEAT_SENT", - "HEARTBEAT_ACKED", + [SCTP_CONNTRACK_NONE] = "NONE", + [SCTP_CONNTRACK_CLOSED] = "CLOSED", + [SCTP_CONNTRACK_COOKIE_WAIT] = "COOKIE_WAIT", + [SCTP_CONNTRACK_COOKIE_ECHOED] = "COOKIE_ECHOED", + [SCTP_CONNTRACK_ESTABLISHED] = "ESTABLISHED", + [SCTP_CONNTRACK_SHUTDOWN_SENT] = "SHUTDOWN_SENT", + [SCTP_CONNTRACK_SHUTDOWN_RECD] = "SHUTDOWN_RECD", + [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = "SHUTDOWN_ACK_SENT", + [SCTP_CONNTRACK_HEARTBEAT_SENT] = "HEARTBEAT_SENT", };

#define SECS * HZ @@ -54,12 +48,11 @@ static const unsigned int sctp_timeouts[ [SCTP_CONNTRACK_CLOSED] = 10 SECS, [SCTP_CONNTRACK_COOKIE_WAIT] = 3 SECS, [SCTP_CONNTRACK_COOKIE_ECHOED] = 3 SECS, - [SCTP_CONNTRACK_ESTABLISHED] = 5 DAYS, + [SCTP_CONNTRACK_ESTABLISHED] = 210 SECS, [SCTP_CONNTRACK_SHUTDOWN_SENT] = 300 SECS / 1000, [SCTP_CONNTRACK_SHUTDOWN_RECD] = 300 SECS / 1000, [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS, [SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS, - [SCTP_CONNTRACK_HEARTBEAT_ACKED] = 210 SECS, };

#define SCTP_FLAG_HEARTBEAT_VTAG_FAILED 1 @@ -73,7 +66,6 @@ static const unsigned int sctp_timeouts[ #define sSR SCTP_CONNTRACK_SHUTDOWN_RECD #define sSA SCTP_CONNTRACK_SHUTDOWN_ACK_SENT #define sHS SCTP_CONNTRACK_HEARTBEAT_SENT -#define sHA SCTP_CONNTRACK_HEARTBEAT_ACKED #define sIV SCTP_CONNTRACK_MAX

/* @@ -96,9 +88,6 @@ SHUTDOWN_ACK_SENT - We have seen a SHUTD CLOSED - We have seen a SHUTDOWN_COMPLETE chunk in the direction of the SHUTDOWN chunk. Connection is closed. HEARTBEAT_SENT - We have seen a HEARTBEAT in a new flow. -HEARTBEAT_ACKED - We have seen a HEARTBEAT-ACK in the direction opposite to - that of the HEARTBEAT chunk. Secondary connection is - established. */

/* TODO @@ -115,33 +104,33 @@ cookie echoed to closed. static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { { /* ORIGINAL */ -/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ -/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA}, -/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA}, -/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, -/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS}, -/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA, sHA}, -/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't have Stale cookie*/ -/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* 5.2.4 - Big TODO */ -/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't come in orig dir */ -/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL, sHA}, -/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA}, -/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA} +/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */ +/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW}, +/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL}, +/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, +/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL}, +/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA}, +/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't have Stale cookie*/ +/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL},/* 5.2.4 - Big TODO */ +/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */ +/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL}, +/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, +/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, }, { /* REPLY */ -/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ -/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* INIT in sCL Big TODO */ -/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA}, -/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL}, -/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR}, -/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA}, -/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV, sHA}, -/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* Can't come in reply dir */ -/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV, sHA}, -/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV, sHA}, -/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA}, -/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA} +/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */ +/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* INIT in sCL Big TODO */ +/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV}, +/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV}, +/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV}, +/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV}, +/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV}, +/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */ +/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV}, +/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV}, +/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, +/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sES}, } };

@@ -508,8 +497,12 @@ int nf_conntrack_sctp_packet(struct nf_c }

ct->proto.sctp.state = new_state; - if (old_state != new_state) + if (old_state != new_state) { nf_conntrack_event_cache(IPCT_PROTOINFO, ct); + if (new_state == SCTP_CONNTRACK_ESTABLISHED && + !test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) + nf_conntrack_event_cache(IPCT_ASSURED, ct); + } } spin_unlock_bh(&ct->lock);

@@ -523,14 +516,6 @@ int nf_conntrack_sctp_packet(struct nf_c

nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]);

- if (old_state == SCTP_CONNTRACK_COOKIE_ECHOED && - dir == IP_CT_DIR_REPLY && - new_state == SCTP_CONNTRACK_ESTABLISHED) { - pr_debug("Setting assured bit\n"); - set_bit(IPS_ASSURED_BIT, &ct->status); - nf_conntrack_event_cache(IPCT_ASSURED, ct); - } - return NF_ACCEPT;

out_unlock: --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -581,7 +581,6 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_RECD, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_SENT, - NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED, #endif #ifdef CONFIG_NF_CT_PROTO_DCCP NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST, @@ -851,12 +850,6 @@ static struct ctl_table nf_ct_sysctl_tab .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED] = { - .procname = "nf_conntrack_sctp_timeout_heartbeat_acked", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, #endif #ifdef CONFIG_NF_CT_PROTO_DCCP [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST] = { @@ -985,7 +978,6 @@ static void nf_conntrack_standalone_init XASSIGN(SHUTDOWN_RECD, sn); XASSIGN(SHUTDOWN_ACK_SENT, sn); XASSIGN(HEARTBEAT_SENT, sn); - XASSIGN(HEARTBEAT_ACKED, sn); #undef XASSIGN #endif }

From: Uwe Kleine-König u.kleine-koenig@pengutronix.de

commit 8b3d743fc9e2542822826890b482afabf0e7522a upstream.

The release function is called with a pointer to the memory returned by devres_alloc(). I was confused about that by the code before the generalization that used a struct clk **ptr.

Reported-by: Marek Szyprowski m.szyprowski@samsung.com Fixes: abae8e57e49a ("clk: generalize devm_clk_get() a bit") Signed-off-by: Uwe Kleine-König u.kleine-koenig@pengutronix.de Link: https://lore.kernel.org/r/20220620171815.114212-1-u.kleine-koenig@pengutroni... Tested-by: Marek Szyprowski m.szyprowski@samsung.com Tested-by: Linux Kernel Functional Testing lkft@linaro.org Signed-off-by: Stephen Boyd sboyd@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/clk/clk-devres.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/clk/clk-devres.c +++ b/drivers/clk/clk-devres.c @@ -11,7 +11,7 @@ struct devm_clk_state {

static void devm_clk_release(struct device *dev, void *res) { - struct devm_clk_state *state = *(struct devm_clk_state **)res; + struct devm_clk_state *state = res;

if (state->exit) state->exit(state->clk);

From: Geert Uytterhoeven geert+renesas@glider.be

[ Upstream commit f78985f9f58380eec37f82c8a2c765aa7670fc29 ]

"make dtbs_check":

arch/arm/boot/dts/imx53-ppd.dtb: i2c-switch@70: $nodename:0: 'i2c-switch@70' does not match '^(i2c-?)?mux' From schema: Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.yaml arch/arm/boot/dts/imx53-ppd.dtb: i2c-switch@70: Unevaluated properties are not allowed ('#address-cells', '#size-cells', 'i2c@0', 'i2c@1', 'i2c@2', 'i2c@3', 'i2c@4', 'i2c@5', 'i2c@6', 'i2c@7' were unexpected) From schema: Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.yaml

Fix this by renaming the PCA9547 node to "i2c-mux", to match the I2C bus multiplexer/switch DT bindings and the Generic Names Recommendation in the Devicetree Specification.

Signed-off-by: Geert Uytterhoeven geert+renesas@glider.be Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/imx53-ppd.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/boot/dts/imx53-ppd.dts b/arch/arm/boot/dts/imx53-ppd.dts index c80d1700e094..c01dc571b55c 100644 --- a/arch/arm/boot/dts/imx53-ppd.dts +++ b/arch/arm/boot/dts/imx53-ppd.dts @@ -461,7 +461,7 @@ &i2c1 { scl-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; status = "okay";

- i2c-switch@70 { + i2c-mux@70 { compatible = "nxp,pca9547"; #address-cells = <1>; #size-cells = <0>;

From: Yu Kuai yukuai3@huawei.com

[ Upstream commit e3ff8887e7db757360f97634e0d6f4b8e27a8c46 ]

If the policy defines pd_online_fn(), it should be called after pd_init_fn(), like blkg_create().

Signed-off-by: Yu Kuai yukuai3@huawei.com Acked-by: Tejun Heo tj@kernel.org Link: https://lore.kernel.org/r/20230103112833.2013432-1-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- block/blk-cgroup.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index dde8d0acfb34..cd085a0e5e4a 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1445,6 +1445,10 @@ int blkcg_activate_policy(struct request_queue *q, list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) pol->pd_init_fn(blkg->pd[pol->plid]);

+ if (pol->pd_online_fn) + list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) + pol->pd_online_fn(blkg->pd[pol->plid]); + __set_bit(pol->plid, q->blkcg_pols); ret = 0;

From: Xiaoming Ni nixiaoming@huawei.com

commit 3ddd9a808cee7284931312f2f3e854c9617f44b2 upstream.

Patch series "sysctl: first set of kernel/sysctl cleanups", v2.

Finally had time to respin the series of the work we had started last year on cleaning up the kernel/sysct.c kitchen sink. People keeps stuffing their sysctls in that file and this creates a maintenance burden. So this effort is aimed at placing sysctls where they actually belong.

I'm going to split patches up into series as there is quite a bit of work.

This first set adds register_sysctl_init() for uses of registerting a sysctl on the init path, adds const where missing to a few places, generalizes common values so to be more easy to share, and starts the move of a few kernel/sysctl.c out where they belong.

The majority of rework on v2 in this first patch set is 0-day fixes. Eric Biederman's feedback is later addressed in subsequent patch sets.

I'll only post the first two patch sets for now. We can address the rest once the first two patch sets get completely reviewed / Acked.

This patch (of 9):

The kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain.

To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic.

Today though folks heavily rely on tables on kernel/sysctl.c so they can easily just extend this table with their needed sysctls. In order to help users move their sysctls out we need to provide a helper which can be used during code initialization.

We special-case the initialization use of register_sysctl() since it *is* safe to fail, given all that sysctls do is provide a dynamic interface to query or modify at runtime an existing variable. So the use case of register_sysctl() on init should *not* stop if the sysctls don't end up getting registered. It would be counter productive to stop boot if a simple sysctl registration failed.

Provide a helper for init then, and document the recommended init levels to use for callers of this routine. We will later use this in subsequent patches to start slimming down kernel/sysctl.c tables and moving sysctl registration to the code which actually needs these sysctls.

[mcgrof@kernel.org: major commit log and documentation rephrasing also moved to fs/proc/proc_sysctl.c ]

Link: https://lkml.kernel.org/r/20211123202347.818157-1-mcgrof@kernel.org Link: https://lkml.kernel.org/r/20211123202347.818157-2-mcgrof@kernel.org Signed-off-by: Xiaoming Ni nixiaoming@huawei.com Signed-off-by: Luis Chamberlain mcgrof@kernel.org Reviewed-by: Kees Cook keescook@chromium.org Cc: Iurii Zaikin yzaikin@google.com Cc: "Eric W. Biederman" ebiederm@xmission.com Cc: Peter Zijlstra peterz@infradead.org Cc: Greg Kroah-Hartman gregkh@linuxfoundation.org Cc: Paul Turner pjt@google.com Cc: Andy Shevchenko andriy.shevchenko@linux.intel.com Cc: Sebastian Reichel sre@kernel.org Cc: Tetsuo Handa penguin-kernel@I-love.SAKURA.ne.jp Cc: Petr Mladek pmladek@suse.com Cc: Sergey Senozhatsky senozhatsky@chromium.org Cc: Qing Wang wangqing@vivo.com Cc: Benjamin LaHaise bcrl@kvack.org Cc: Al Viro viro@zeniv.linux.org.uk Cc: Jan Kara jack@suse.cz Cc: Amir Goldstein amir73il@gmail.com Cc: Stephen Kitt steve@sk2.org Cc: Antti Palosaari crope@iki.fi Cc: Arnd Bergmann arnd@arndb.de Cc: Benjamin Herrenschmidt benh@kernel.crashing.org Cc: Clemens Ladisch clemens@ladisch.de Cc: David Airlie airlied@linux.ie Cc: Jani Nikula jani.nikula@linux.intel.com Cc: Joel Becker jlbec@evilplan.org Cc: Joonas Lahtinen joonas.lahtinen@linux.intel.com Cc: Joseph Qi joseph.qi@linux.alibaba.com Cc: Julia Lawall julia.lawall@inria.fr Cc: Lukas Middendorf kernel@tuxforce.de Cc: Mark Fasheh mark@fasheh.com Cc: Phillip Potter phil@philpotter.co.uk Cc: Rodrigo Vivi rodrigo.vivi@intel.com Cc: Douglas Gilbert dgilbert@interlog.com Cc: James E.J. Bottomley jejb@linux.ibm.com Cc: Jani Nikula jani.nikula@intel.com Cc: John Ogness john.ogness@linutronix.de Cc: Martin K. Petersen martin.petersen@oracle.com Cc: "Rafael J. Wysocki" rafael@kernel.org Cc: Steven Rostedt (VMware) rostedt@goodmis.org Cc: Suren Baghdasaryan surenb@google.com Cc: "Theodore Ts'o" tytso@mit.edu Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Eric Biggers ebiggers@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/proc/proc_sysctl.c | 33 +++++++++++++++++++++++++++++++++ include/linux/sysctl.h | 3 +++ 2 files changed, 36 insertions(+)

diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index d80989b6c344..f4264dd4ea31 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -14,6 +14,7 @@ #include <linux/mm.h> #include <linux/module.h> #include <linux/bpf-cgroup.h> +#include <linux/kmemleak.h> #include "internal.h"

static const struct dentry_operations proc_sys_dentry_operations; @@ -1397,6 +1398,38 @@ struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *tab } EXPORT_SYMBOL(register_sysctl);

+/** + * __register_sysctl_init() - register sysctl table to path + * @path: path name for sysctl base + * @table: This is the sysctl table that needs to be registered to the path + * @table_name: The name of sysctl table, only used for log printing when + * registration fails + * + * The sysctl interface is used by userspace to query or modify at runtime + * a predefined value set on a variable. These variables however have default + * values pre-set. Code which depends on these variables will always work even + * if register_sysctl() fails. If register_sysctl() fails you'd just loose the + * ability to query or modify the sysctls dynamically at run time. Chances of + * register_sysctl() failing on init are extremely low, and so for both reasons + * this function does not return any error as it is used by initialization code. + * + * Context: Can only be called after your respective sysctl base path has been + * registered. So for instance, most base directories are registered early on + * init before init levels are processed through proc_sys_init() and + * sysctl_init(). + */ +void __init __register_sysctl_init(const char *path, struct ctl_table *table, + const char *table_name) +{ + struct ctl_table_header *hdr = register_sysctl(path, table); + + if (unlikely(!hdr)) { + pr_err("failed when register_sysctl %s to %s\n", table_name, path); + return; + } + kmemleak_not_leak(hdr); +} + static char *append_path(const char *path, char *pos, const char *name) { int namelen; diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 6df477329b76..aa615a0863f5 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -208,6 +208,9 @@ struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, void unregister_sysctl_table(struct ctl_table_header * table);

extern int sysctl_init(void); +extern void __register_sysctl_init(const char *path, struct ctl_table *table, + const char *table_name); +#define register_sysctl_init(path, table) __register_sysctl_init(path, table, #table)

extern struct ctl_table sysctl_mount_point[];

From: David Gow davidgow@google.com

commit be4f1ae978ffe98cc95ec49ceb95386fb4474974 upstream.

KASAN errors will currently trigger a panic when panic_on_warn is set. This renders kasan_multishot useless, as further KASAN errors won't be reported if the kernel has already paniced. By making kasan_multishot disable this behaviour for KASAN errors, we can still have the benefits of panic_on_warn for non-KASAN warnings, yet be able to use kasan_multishot.

This is particularly important when running KASAN tests, which need to trigger multiple KASAN errors: previously these would panic the system if panic_on_warn was set, now they can run (and will panic the system should non-KASAN warnings show up).

Signed-off-by: David Gow davidgow@google.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Tested-by: Andrey Konovalov andreyknvl@google.com Reviewed-by: Andrey Konovalov andreyknvl@google.com Reviewed-by: Brendan Higgins brendanhiggins@google.com Cc: Andrey Ryabinin aryabinin@virtuozzo.com Cc: Dmitry Vyukov dvyukov@google.com Cc: Ingo Molnar mingo@redhat.com Cc: Juri Lelli juri.lelli@redhat.com Cc: Patricia Alfonso trishalfonso@google.com Cc: Peter Zijlstra a.p.zijlstra@chello.nl Cc: Shuah Khan shuah@kernel.org Cc: Vincent Guittot vincent.guittot@linaro.org Link: https://lkml.kernel.org/r/20200915035828.570483-6-davidgow@google.com Link: https://lkml.kernel.org/r/20200910070331.3358048-6-davidgow@google.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Eric Biggers ebiggers@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- mm/kasan/report.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 621782100eaa..a05ff1922d49 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -92,7 +92,7 @@ static void end_report(unsigned long *flags) pr_err("==================================================================\n"); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); spin_unlock_irqrestore(&report_lock, *flags); - if (panic_on_warn) + if (panic_on_warn && !test_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags)) panic("panic_on_warn set ...\n"); kasan_enable_current(); }

From: Eric W. Biederman ebiederm@xmission.com

commit 1fb466dff904e4a72282af336f2c355f011eec61 upstream.

Recently the kbuild robot reported two new errors:

...

lib/kunit/kunit-example-test.o: warning: objtool: .text.unlikely: unexpected end of section arch/x86/kernel/dumpstack.o: warning: objtool: oops_end() falls through to next function show_opcodes()

I don't know why they did not occur in my test setup but after digging it I realized I had accidentally dropped a comma in tools/objtool/check.c when I renamed rewind_stack_do_exit to rewind_stack_and_make_dead.

Add that comma back to fix objtool errors.

Link: https://lkml.kernel.org/r/202112140949.Uq5sFKR1-lkp@intel.com Fixes: 0e25498f8cd4 ("exit: Add and use make_task_dead.") Reported-by: kernel test robot lkp@intel.com Signed-off-by: "Eric W. Biederman" ebiederm@xmission.com Signed-off-by: Eric Biggers ebiggers@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/objtool/check.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 14be7d261ae7..dfd67243faac 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -144,7 +144,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "fortify_panic", "usercopy_abort", "machine_real_restart", - "rewind_stack_and_make_dead" + "rewind_stack_and_make_dead", "cpu_bringup_and_idle", };

From: Nathan Chancellor nathan@kernel.org

commit ab4ababdf77ccc56c7301c751dff49c79709c51c upstream.

When building ARCH=h8300 defconfig:

arch/h8300/kernel/traps.c: In function 'die': arch/h8300/kernel/traps.c:109:2: error: implicit declaration of function 'make_dead_task' [-Werror=implicit-function-declaration] 109 | make_dead_task(SIGSEGV); | ^~~~~~~~~~~~~~

arch/h8300/mm/fault.c: In function 'do_page_fault': arch/h8300/mm/fault.c:54:2: error: implicit declaration of function 'make_dead_task' [-Werror=implicit-function-declaration] 54 | make_dead_task(SIGKILL); | ^~~~~~~~~~~~~~

The function's name is make_task_dead(), change it so there is no more build error.

Additionally, include linux/sched/task.h in arch/h8300/kernel/traps.c to avoid the same error because do_exit()'s declaration is in kernel.h but make_task_dead()'s is in task.h, which is not included in traps.c.

Fixes: 0e25498f8cd4 ("exit: Add and use make_task_dead.") Signed-off-by: Nathan Chancellor nathan@kernel.org Link: https://lkml.kernel.org/r/20211227184851.2297759-3-nathan@kernel.org Signed-off-by: Eric W. Biederman ebiederm@xmission.com Signed-off-by: Eric Biggers ebiggers@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/h8300/kernel/traps.c | 3 ++- arch/h8300/mm/fault.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/h8300/kernel/traps.c b/arch/h8300/kernel/traps.c index a284c126f07a..090adaee4b84 100644 --- a/arch/h8300/kernel/traps.c +++ b/arch/h8300/kernel/traps.c @@ -17,6 +17,7 @@ #include <linux/types.h> #include <linux/sched.h> #include <linux/sched/debug.h> +#include <linux/sched/task.h> #include <linux/mm_types.h> #include <linux/kernel.h> #include <linux/errno.h> @@ -110,7 +111,7 @@ void die(const char *str, struct pt_regs *fp, unsigned long err) dump(fp);

spin_unlock_irq(&die_lock); - make_dead_task(SIGSEGV); + make_task_dead(SIGSEGV); }

static int kstack_depth_to_print = 24; diff --git a/arch/h8300/mm/fault.c b/arch/h8300/mm/fault.c index a8d8fc63780e..573825c3cb70 100644 --- a/arch/h8300/mm/fault.c +++ b/arch/h8300/mm/fault.c @@ -52,7 +52,7 @@ asmlinkage int do_page_fault(struct pt_regs *regs, unsigned long address, printk(" at virtual address %08lx\n", address); if (!user_mode(regs)) die("Oops", regs, error_code); - make_dead_task(SIGKILL); + make_task_dead(SIGKILL);

return 1; }

From: Randy Dunlap rdunlap@infradead.org

commit dbecf9b8b8ce580f4e11afed9d61e8aa294cddd2 upstream.

In linux-next, IA64_MCA_RECOVERY uses the (new) function make_task_dead(), which is not exported for use by modules. Instead of exporting it for one user, convert IA64_MCA_RECOVERY to be a bool Kconfig symbol.

In a config file from "kernel test robot lkp@intel.com" for a different problem, this linker error was exposed when CONFIG_IA64_MCA_RECOVERY=m.

Fixes this build error:

ERROR: modpost: "make_task_dead" [arch/ia64/kernel/mca_recovery.ko] undefined!

Link: https://lkml.kernel.org/r/20220124213129.29306-1-rdunlap@infradead.org Fixes: 0e25498f8cd4 ("exit: Add and use make_task_dead.") Signed-off-by: Randy Dunlap rdunlap@infradead.org Suggested-by: Christoph Hellwig hch@infradead.org Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: "Eric W. Biederman" ebiederm@xmission.com Cc: Tony Luck tony.luck@intel.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Eric Biggers ebiggers@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/ia64/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 16714477eef4..6a6036f16abe 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -360,7 +360,7 @@ config ARCH_PROC_KCORE_TEXT depends on PROC_KCORE

config IA64_MCA_RECOVERY - tristate "MCA recovery from errors other than TLB." + bool "MCA recovery from errors other than TLB."

config PERFMON bool "Performance monitor support"

From: Kees Cook keescook@chromium.org

commit 9db89b41117024f80b38b15954017fb293133364 upstream.

Since Oops count is now tracked and is a fairly interesting signal, add the entry /sys/kernel/oops_count to expose it to userspace.

Cc: "Eric W. Biederman" ebiederm@xmission.com Cc: Jann Horn jannh@google.com Cc: Arnd Bergmann arnd@arndb.de Reviewed-by: Luis Chamberlain mcgrof@kernel.org Signed-off-by: Kees Cook keescook@chromium.org Link: https://lore.kernel.org/r/20221117234328.594699-3-keescook@chromium.org Signed-off-by: Eric Biggers ebiggers@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../ABI/testing/sysfs-kernel-oops_count | 6 +++++ kernel/exit.c | 22 +++++++++++++++++-- 2 files changed, 26 insertions(+), 2 deletions(-) create mode 100644 Documentation/ABI/testing/sysfs-kernel-oops_count

diff --git a/Documentation/ABI/testing/sysfs-kernel-oops_count b/Documentation/ABI/testing/sysfs-kernel-oops_count new file mode 100644 index 000000000000..156cca9dbc96 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-oops_count @@ -0,0 +1,6 @@ +What: /sys/kernel/oops_count +Date: November 2022 +KernelVersion: 6.2.0 +Contact: Linux Kernel Hardening List linux-hardening@vger.kernel.org +Description: + Shows how many times the system has Oopsed since last boot. diff --git a/kernel/exit.c b/kernel/exit.c index 4236970aa438..48ac68ebab72 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -63,6 +63,7 @@ #include <linux/random.h> #include <linux/rcuwait.h> #include <linux/compat.h> +#include <linux/sysfs.h>

#include <linux/uaccess.h> #include <asm/unistd.h> @@ -96,6 +97,25 @@ static __init int kernel_exit_sysctls_init(void) late_initcall(kernel_exit_sysctls_init); #endif

+static atomic_t oops_count = ATOMIC_INIT(0); + +#ifdef CONFIG_SYSFS +static ssize_t oops_count_show(struct kobject *kobj, struct kobj_attribute *attr, + char *page) +{ + return sysfs_emit(page, "%d\n", atomic_read(&oops_count)); +} + +static struct kobj_attribute oops_count_attr = __ATTR_RO(oops_count); + +static __init int kernel_exit_sysfs_init(void) +{ + sysfs_add_file_to_group(kernel_kobj, &oops_count_attr.attr, NULL); + return 0; +} +late_initcall(kernel_exit_sysfs_init); +#endif + static void __unhash_process(struct task_struct *p, bool group_dead) { nr_threads--; @@ -893,8 +913,6 @@ EXPORT_SYMBOL_GPL(do_exit);

void __noreturn make_task_dead(int signr) { - static atomic_t oops_count = ATOMIC_INIT(0); - /* * Take the task off the cpu after something catastrophic has * happened.

From: Kees Cook keescook@chromium.org

commit 79cc1ba7badf9e7a12af99695a557e9ce27ee967 upstream.

Several run-time checkers (KASAN, UBSAN, KFENCE, KCSAN, sched) roll their own warnings, and each check "panic_on_warn". Consolidate this into a single function so that future instrumentation can be added in a single location.

Cc: Marco Elver elver@google.com Cc: Dmitry Vyukov dvyukov@google.com Cc: Ingo Molnar mingo@redhat.com Cc: Peter Zijlstra peterz@infradead.org Cc: Juri Lelli juri.lelli@redhat.com Cc: Vincent Guittot vincent.guittot@linaro.org Cc: Dietmar Eggemann dietmar.eggemann@arm.com Cc: Steven Rostedt rostedt@goodmis.org Cc: Ben Segall bsegall@google.com Cc: Mel Gorman mgorman@suse.de Cc: Daniel Bristot de Oliveira bristot@redhat.com Cc: Valentin Schneider vschneid@redhat.com Cc: Andrey Ryabinin ryabinin.a.a@gmail.com Cc: Alexander Potapenko glider@google.com Cc: Andrey Konovalov andreyknvl@gmail.com Cc: Vincenzo Frascino vincenzo.frascino@arm.com Cc: Andrew Morton akpm@linux-foundation.org Cc: David Gow davidgow@google.com Cc: tangmeng tangmeng@uniontech.com Cc: Jann Horn jannh@google.com Cc: Shuah Khan skhan@linuxfoundation.org Cc: Petr Mladek pmladek@suse.com Cc: "Paul E. McKenney" paulmck@kernel.org Cc: Sebastian Andrzej Siewior bigeasy@linutronix.de Cc: "Guilherme G. Piccoli" gpiccoli@igalia.com Cc: Tiezhu Yang yangtiezhu@loongson.cn Cc: kasan-dev@googlegroups.com Cc: linux-mm@kvack.org Reviewed-by: Luis Chamberlain mcgrof@kernel.org Signed-off-by: Kees Cook keescook@chromium.org Reviewed-by: Marco Elver elver@google.com Reviewed-by: Andrey Konovalov andreyknvl@gmail.com Link: https://lore.kernel.org/r/20221117234328.594699-4-keescook@chromium.org Signed-off-by: Eric Biggers ebiggers@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/kernel.h | 1 + kernel/panic.c | 9 +++++++-- kernel/sched/core.c | 3 +-- mm/kasan/report.c | 4 ++-- 4 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 77c86a2236da..1fdb251947ed 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -321,6 +321,7 @@ extern long (*panic_blink)(int state); __printf(1, 2) void panic(const char *fmt, ...) __noreturn __cold; void nmi_panic(struct pt_regs *regs, const char *msg); +void check_panic_on_warn(const char *origin); extern void oops_enter(void); extern void oops_exit(void); void print_oops_end_marker(void); diff --git a/kernel/panic.c b/kernel/panic.c index 5e2b764ff5d5..7e4900eb25ac 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -156,6 +156,12 @@ static void panic_print_sys_info(void) ftrace_dump(DUMP_ALL); }

+void check_panic_on_warn(const char *origin) +{ + if (panic_on_warn) + panic("%s: panic_on_warn set ...\n", origin); +} + /** * panic - halt the system * @fmt: The text string to print @@ -581,8 +587,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint, if (args) vprintk(args->fmt, args->args);

- if (panic_on_warn) - panic("panic_on_warn set ...\n"); + check_panic_on_warn("kernel");

print_modules();

diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 06b686ef36e6..8ab239fd1c8d 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3964,8 +3964,7 @@ static noinline void __schedule_bug(struct task_struct *prev) print_ip_sym(preempt_disable_ip); pr_cont("\n"); } - if (panic_on_warn) - panic("scheduling while atomic\n"); + check_panic_on_warn("scheduling while atomic");

dump_stack(); add_taint(TAINT_WARN, LOCKDEP_STILL_OK); diff --git a/mm/kasan/report.c b/mm/kasan/report.c index a05ff1922d49..4d87df96acc1 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -92,8 +92,8 @@ static void end_report(unsigned long *flags) pr_err("==================================================================\n"); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); spin_unlock_irqrestore(&report_lock, *flags); - if (panic_on_warn && !test_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags)) - panic("panic_on_warn set ...\n"); + if (!test_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags)) + check_panic_on_warn("KASAN"); kasan_enable_current(); }

From: Kees Cook keescook@chromium.org

commit 8b05aa26336113c4cea25f1c333ee8cd4fc212a6 upstream.

Since Warn count is now tracked and is a fairly interesting signal, add the entry /sys/kernel/warn_count to expose it to userspace.

Cc: Petr Mladek pmladek@suse.com Cc: Andrew Morton akpm@linux-foundation.org Cc: tangmeng tangmeng@uniontech.com Cc: "Guilherme G. Piccoli" gpiccoli@igalia.com Cc: Sebastian Andrzej Siewior bigeasy@linutronix.de Cc: Tiezhu Yang yangtiezhu@loongson.cn Reviewed-by: Luis Chamberlain mcgrof@kernel.org Signed-off-by: Kees Cook keescook@chromium.org Link: https://lore.kernel.org/r/20221117234328.594699-6-keescook@chromium.org Signed-off-by: Eric Biggers ebiggers@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../ABI/testing/sysfs-kernel-warn_count | 6 +++++ kernel/panic.c | 22 +++++++++++++++++-- 2 files changed, 26 insertions(+), 2 deletions(-) create mode 100644 Documentation/ABI/testing/sysfs-kernel-warn_count

diff --git a/Documentation/ABI/testing/sysfs-kernel-warn_count b/Documentation/ABI/testing/sysfs-kernel-warn_count new file mode 100644 index 000000000000..08f083d2fd51 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-warn_count @@ -0,0 +1,6 @@ +What: /sys/kernel/oops_count +Date: November 2022 +KernelVersion: 6.2.0 +Contact: Linux Kernel Hardening List linux-hardening@vger.kernel.org +Description: + Shows how many times the system has Warned since last boot. diff --git a/kernel/panic.c b/kernel/panic.c index 8f72305dd501..2c118645e740 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -31,6 +31,7 @@ #include <linux/bug.h> #include <linux/ratelimit.h> #include <linux/debugfs.h> +#include <linux/sysfs.h> #include <asm/sections.h>

#define PANIC_TIMER_STEP 100 @@ -81,6 +82,25 @@ static __init int kernel_panic_sysctls_init(void) late_initcall(kernel_panic_sysctls_init); #endif

+static atomic_t warn_count = ATOMIC_INIT(0); + +#ifdef CONFIG_SYSFS +static ssize_t warn_count_show(struct kobject *kobj, struct kobj_attribute *attr, + char *page) +{ + return sysfs_emit(page, "%d\n", atomic_read(&warn_count)); +} + +static struct kobj_attribute warn_count_attr = __ATTR_RO(warn_count); + +static __init int kernel_panic_sysfs_init(void) +{ + sysfs_add_file_to_group(kernel_kobj, &warn_count_attr.attr, NULL); + return 0; +} +late_initcall(kernel_panic_sysfs_init); +#endif + static long no_blink(int state) { return 0; @@ -179,8 +199,6 @@ static void panic_print_sys_info(void)

void check_panic_on_warn(const char *origin) { - static atomic_t warn_count = ATOMIC_INIT(0); - if (panic_on_warn) panic("%s: panic_on_warn set ...\n", origin);

From: Kees Cook keescook@chromium.org

commit 7535b832c6399b5ebfc5b53af5c51dd915ee2538 upstream.

Use a temporary variable to take full advantage of READ_ONCE() behavior. Without this, the report (and even the test) might be out of sync with the initial test.

Reported-by: Peter Zijlstra peterz@infradead.org Link: https://lore.kernel.org/lkml/Y5x7GXeluFmZ8E0E@hirez.programming.kicks-ass.ne... Fixes: 9fc9e278a5c0 ("panic: Introduce warn_limit") Fixes: d4ccd54d28d3 ("exit: Put an upper limit on how often we can oops") Cc: "Eric W. Biederman" ebiederm@xmission.com Cc: Jann Horn jannh@google.com Cc: Arnd Bergmann arnd@arndb.de Cc: Petr Mladek pmladek@suse.com Cc: Andrew Morton akpm@linux-foundation.org Cc: Luis Chamberlain mcgrof@kernel.org Cc: Marco Elver elver@google.com Cc: tangmeng tangmeng@uniontech.com Cc: Sebastian Andrzej Siewior bigeasy@linutronix.de Cc: Tiezhu Yang yangtiezhu@loongson.cn Signed-off-by: Kees Cook keescook@chromium.org Signed-off-by: Eric Biggers ebiggers@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/exit.c | 6 ++++-- kernel/panic.c | 7 +++++-- 2 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/kernel/exit.c b/kernel/exit.c index 381282fb756c..563bdaa76694 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -917,6 +917,7 @@ void __noreturn make_task_dead(int signr) * Take the task off the cpu after something catastrophic has * happened. */ + unsigned int limit;

/* * Every time the system oopses, if the oops happens while a reference @@ -928,8 +929,9 @@ void __noreturn make_task_dead(int signr) * To make sure this can't happen, place an upper bound on how often the * kernel may oops without panic(). */ - if (atomic_inc_return(&oops_count) >= READ_ONCE(oops_limit) && oops_limit) - panic("Oopsed too often (kernel.oops_limit is %d)", oops_limit); + limit = READ_ONCE(oops_limit); + if (atomic_inc_return(&oops_count) >= limit && limit) + panic("Oopsed too often (kernel.oops_limit is %d)", limit);

do_exit(signr); } diff --git a/kernel/panic.c b/kernel/panic.c index 2c118645e740..cef79466f941 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -199,12 +199,15 @@ static void panic_print_sys_info(void)

void check_panic_on_warn(const char *origin) { + unsigned int limit; + if (panic_on_warn) panic("%s: panic_on_warn set ...\n", origin);

- if (atomic_inc_return(&warn_count) >= READ_ONCE(warn_limit) && warn_limit) + limit = READ_ONCE(warn_limit); + if (atomic_inc_return(&warn_count) >= limit && limit) panic("%s: system warned too often (kernel.warn_limit is %d)", - origin, warn_limit); + origin, limit); }

/**

From: Soenke Huster soenke.huster@eknoes.de

commit 3afee2118132e93e5f6fa636dfde86201a860ab3 upstream.

This event is just specified for SCO and eSCO link types. On the reception of a HCI_Synchronous_Connection_Complete for a BDADDR of an existing LE connection, LE link type and a status that triggers the second case of the packet processing a NULL pointer dereference happens, as conn->link is NULL.

Signed-off-by: Soenke Huster soenke.huster@eknoes.de Signed-off-by: Luiz Augusto von Dentz luiz.von.dentz@intel.com Signed-off-by: Ovidiu Panait ovidiu.panait@eng.windriver.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/bluetooth/hci_event.c | 13 +++++++++++++ 1 file changed, 13 insertions(+)

--- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -4177,6 +4177,19 @@ static void hci_sync_conn_complete_evt(s struct hci_ev_sync_conn_complete *ev = (void *) skb->data; struct hci_conn *conn;

+ switch (ev->link_type) { + case SCO_LINK: + case ESCO_LINK: + break; + default: + /* As per Core 5.3 Vol 4 Part E 7.7.35 (p.2219), Link_Type + * for HCI_Synchronous_Connection_Complete is limited to + * either SCO or eSCO + */ + bt_dev_err(hdev, "Ignoring connect complete event for invalid link type"); + return; + } + BT_DBG("%s status 0x%2.2x", hdev->name, ev->status);

hci_dev_lock(hdev);

From: Greg Kroah-Hartman gregkh@linuxfoundation.org

This reverts commit bcebcb11fcbc744de1add88601c51cca8b4e762c which is commit 9181f40fb2952fd59ecb75e7158620c9c669eee3 upstream.

The backport to 5.4.y causes problems, as reported by Harshit, so revert it for now and wait for a working backport to be added.

Reported-by: Harshit Mogalapalli harshit.m.mogalapalli@oracle.com Link: https://lore.kernel.org/r/4d2928e1-c836-b817-3dc2-3fe9adcaf2d6@oracle.com Cc: Zhang Xiaoxu zhangxiaoxu5@huawei.com Cc: Trond Myklebust trond.myklebust@hammerspace.com Cc: Sasha Levin sashal@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sunrpc/xprtrdma/verbs.c | 1 - 1 file changed, 1 deletion(-)

--- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1037,7 +1037,6 @@ out4: kfree(req->rl_sendbuf); out3: kfree(req->rl_rdmabuf); - rpcrdma_regbuf_free(req->rl_sendbuf); out2: kfree(req); out1: