- Linux-stable-mirror - lists.linaro.org

[PATCH v3 02/11] platform/x86/intel/pmt: crashlog binary file endpoint

by Michael J. Ruhl

Usage of the intel_pmt_read() for binary sysfs, requires an allocated endpoint struct. The crashlog driver does not allocate the endpoint. Without the ep, the crashlog usage causes the following NULL pointer exception: BUG: kernel NULL pointer dereference, address: 0000000000000000 Oops: Oops: 0000 [#1] SMP NOPTI RIP: 0010:intel_pmt_read+0x3b/0x70 [pmt_class] Code: Call Trace: <TASK> ? sysfs_kf_bin_read+0xc0/0xe0 kernfs_fop_read_iter+0xac/0x1a0 vfs_read+0x26d/0x350 ksys_read+0x6b/0xe0 __x64_sys_read+0x1d/0x30 x64_sys_call+0x1bc8/0x1d70 do_syscall_64+0x6d/0x110 Add the endpoint information to the crashlog driver to avoid the NULL pointer exception. Fixes: 416eeb2e1fc7 ("platform/x86/intel/pmt: telemetry: Export API to read telemetry") Cc: <stable(a)vger.kernel.org> Signed-off-by: Michael J. Ruhl <michael.j.ruhl(a)intel.com> --- drivers/platform/x86/intel/pmt/crashlog.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/platform/x86/intel/pmt/crashlog.c b/drivers/platform/x86/intel/pmt/crashlog.c index 6a9eb3c4b313..74ce199e59f0 100644 --- a/drivers/platform/x86/intel/pmt/crashlog.c +++ b/drivers/platform/x86/intel/pmt/crashlog.c @@ -252,6 +252,7 @@ static struct intel_pmt_namespace pmt_crashlog_ns = { .xa = &crashlog_array, .attr_grp = &pmt_crashlog_group, .pmt_header_decode = pmt_crashlog_header_decode, + .pmt_add_endpoint = intel_pmt_add_endpoint, }; /* @@ -262,8 +263,12 @@ static void pmt_crashlog_remove(struct auxiliary_device *auxdev) struct pmt_crashlog_priv *priv = auxiliary_get_drvdata(auxdev); int i; - for (i = 0; i < priv->num_entries; i++) - intel_pmt_dev_destroy(&priv->entry[i].entry, &pmt_crashlog_ns); + for (i = 0; i < priv->num_entries; i++) { + struct intel_pmt_entry *entry = &priv->entry[i].entry; + + intel_pmt_release_endpoint(entry->ep); + intel_pmt_dev_destroy(entry, &pmt_crashlog_ns); + } } static int pmt_crashlog_probe(struct auxiliary_device *auxdev, -- 2.49.0

1 day, 3 hours

2
1
0 0

[PATCH v3 01/11] platform/x86/intel: refactor endpoint usage

by Michael J. Ruhl

The use of an endpoint has introduced a dependency in all class/pmt drivers to have an endpoint allocated. The telemetry driver has this allocation, the crashlog does not. The current usage is very telemetry focused, but should be common code. With this in mind: rename the struct telemetry_endpoint to struct class_endpoint, refactor the common endpoint code to be in the class.c module Fixes: 416eeb2e1fc7 ("platform/x86/intel/pmt: telemetry: Export API to read telemetry") Cc: <stable(a)vger.kernel.org> Signed-off-by: Michael J. Ruhl <michael.j.ruhl(a)intel.com> --- drivers/platform/x86/intel/pmc/core.c | 3 +- drivers/platform/x86/intel/pmc/core.h | 4 +- drivers/platform/x86/intel/pmc/core_ssram.c | 2 +- drivers/platform/x86/intel/pmt/class.c | 45 ++++++++++++++++++ drivers/platform/x86/intel/pmt/class.h | 21 +++++++-- drivers/platform/x86/intel/pmt/telemetry.c | 51 ++++----------------- drivers/platform/x86/intel/pmt/telemetry.h | 23 ++++------ 7 files changed, 84 insertions(+), 65 deletions(-) diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c index 7a1d11f2914f..805f56665d1d 100644 --- a/drivers/platform/x86/intel/pmc/core.c +++ b/drivers/platform/x86/intel/pmc/core.c @@ -29,6 +29,7 @@ #include <asm/tsc.h> #include "core.h" +#include "../pmt/class.h" #include "../pmt/telemetry.h" /* Maximum number of modes supported by platfoms that has low power mode capability */ @@ -1198,7 +1199,7 @@ int get_primary_reg_base(struct pmc *pmc) void pmc_core_punit_pmt_init(struct pmc_dev *pmcdev, u32 guid) { - struct telem_endpoint *ep; + struct class_endpoint *ep; struct pci_dev *pcidev; pcidev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(10, 0)); diff --git a/drivers/platform/x86/intel/pmc/core.h b/drivers/platform/x86/intel/pmc/core.h index 945a1c440cca..1c12ea7c3ce3 100644 --- a/drivers/platform/x86/intel/pmc/core.h +++ b/drivers/platform/x86/intel/pmc/core.h @@ -16,7 +16,7 @@ #include <linux/bits.h> #include <linux/platform_device.h> -struct telem_endpoint; +struct class_endpoint; #define SLP_S0_RES_COUNTER_MASK GENMASK(31, 0) @@ -432,7 +432,7 @@ struct pmc_dev { bool has_die_c6; u32 die_c6_offset; - struct telem_endpoint *punit_ep; + struct class_endpoint *punit_ep; struct pmc_info *regmap_list; }; diff --git a/drivers/platform/x86/intel/pmc/core_ssram.c b/drivers/platform/x86/intel/pmc/core_ssram.c index 739569803017..3e670fc380a5 100644 --- a/drivers/platform/x86/intel/pmc/core_ssram.c +++ b/drivers/platform/x86/intel/pmc/core_ssram.c @@ -42,7 +42,7 @@ static u32 pmc_core_find_guid(struct pmc_info *list, const struct pmc_reg_map *m static int pmc_core_get_lpm_req(struct pmc_dev *pmcdev, struct pmc *pmc) { - struct telem_endpoint *ep; + struct class_endpoint *ep; const u8 *lpm_indices; int num_maps, mode_offset = 0; int ret, mode; diff --git a/drivers/platform/x86/intel/pmt/class.c b/drivers/platform/x86/intel/pmt/class.c index 7233b654bbad..bba552131bc2 100644 --- a/drivers/platform/x86/intel/pmt/class.c +++ b/drivers/platform/x86/intel/pmt/class.c @@ -76,6 +76,47 @@ int pmt_telem_read_mmio(struct pci_dev *pdev, struct pmt_callbacks *cb, u32 guid } EXPORT_SYMBOL_NS_GPL(pmt_telem_read_mmio, "INTEL_PMT"); +/* Called when all users unregister and the device is removed */ +static void pmt_class_ep_release(struct kref *kref) +{ + struct class_endpoint *ep; + + ep = container_of(kref, struct class_endpoint, kref); + kfree(ep); +} + +void intel_pmt_release_endpoint(struct class_endpoint *ep) +{ + kref_put(&ep->kref, pmt_class_ep_release); +} +EXPORT_SYMBOL_NS_GPL(intel_pmt_release_endpoint, "INTEL_PMT"); + +int intel_pmt_add_endpoint(struct intel_vsec_device *ivdev, + struct intel_pmt_entry *entry) +{ + struct class_endpoint *ep; + + ep = kzalloc(sizeof(*ep), GFP_KERNEL); + if (!ep) + return -ENOMEM; + + ep->pcidev = ivdev->pcidev; + ep->header.access_type = entry->header.access_type; + ep->header.guid = entry->header.guid; + ep->header.base_offset = entry->header.base_offset; + ep->header.size = entry->header.size; + ep->base = entry->base; + ep->present = true; + ep->cb = ivdev->priv_data; + + /* Endpoint lifetimes are managed by kref, not devres */ + kref_init(&ep->kref); + + entry->ep = ep; + + return 0; +} +EXPORT_SYMBOL_NS_GPL(intel_pmt_add_endpoint, "INTEL_PMT"); /* * sysfs */ @@ -97,6 +138,10 @@ intel_pmt_read(struct file *filp, struct kobject *kobj, if (count > entry->size - off) count = entry->size - off; + /* verify endpoint is available */ + if (!entry->ep) + return -ENODEV; + count = pmt_telem_read_mmio(entry->ep->pcidev, entry->cb, entry->header.guid, buf, entry->base, off, count); diff --git a/drivers/platform/x86/intel/pmt/class.h b/drivers/platform/x86/intel/pmt/class.h index b2006d57779d..d2d8f9e31c9d 100644 --- a/drivers/platform/x86/intel/pmt/class.h +++ b/drivers/platform/x86/intel/pmt/class.h @@ -9,8 +9,6 @@ #include <linux/err.h> #include <linux/io.h> -#include "telemetry.h" - /* PMT access types */ #define ACCESS_BARID 2 #define ACCESS_LOCAL 3 @@ -19,11 +17,19 @@ #define GET_BIR(v) ((v) & GENMASK(2, 0)) #define GET_ADDRESS(v) ((v) & GENMASK(31, 3)) +struct kref; struct pci_dev; -struct telem_endpoint { +struct class_header { + u8 access_type; + u16 size; + u32 guid; + u32 base_offset; +}; + +struct class_endpoint { struct pci_dev *pcidev; - struct telem_header header; + struct class_header header; struct pmt_callbacks *cb; void __iomem *base; bool present; @@ -38,7 +44,7 @@ struct intel_pmt_header { }; struct intel_pmt_entry { - struct telem_endpoint *ep; + struct class_endpoint *ep; struct intel_pmt_header header; struct bin_attribute pmt_bin_attr; struct kobject *kobj; @@ -69,4 +75,9 @@ int intel_pmt_dev_create(struct intel_pmt_entry *entry, struct intel_vsec_device *dev, int idx); void intel_pmt_dev_destroy(struct intel_pmt_entry *entry, struct intel_pmt_namespace *ns); + +int intel_pmt_add_endpoint(struct intel_vsec_device *ivdev, + struct intel_pmt_entry *entry); +void intel_pmt_release_endpoint(struct class_endpoint *ep); + #endif diff --git a/drivers/platform/x86/intel/pmt/telemetry.c b/drivers/platform/x86/intel/pmt/telemetry.c index ac3a9bdf5601..27d09867e6a3 100644 --- a/drivers/platform/x86/intel/pmt/telemetry.c +++ b/drivers/platform/x86/intel/pmt/telemetry.c @@ -18,6 +18,7 @@ #include <linux/overflow.h> #include "class.h" +#include "telemetry.h" #define TELEM_SIZE_OFFSET 0x0 #define TELEM_GUID_OFFSET 0x4 @@ -93,48 +94,14 @@ static int pmt_telem_header_decode(struct intel_pmt_entry *entry, return 0; } -static int pmt_telem_add_endpoint(struct intel_vsec_device *ivdev, - struct intel_pmt_entry *entry) -{ - struct telem_endpoint *ep; - - /* Endpoint lifetimes are managed by kref, not devres */ - entry->ep = kzalloc(sizeof(*(entry->ep)), GFP_KERNEL); - if (!entry->ep) - return -ENOMEM; - - ep = entry->ep; - ep->pcidev = ivdev->pcidev; - ep->header.access_type = entry->header.access_type; - ep->header.guid = entry->header.guid; - ep->header.base_offset = entry->header.base_offset; - ep->header.size = entry->header.size; - ep->base = entry->base; - ep->present = true; - ep->cb = ivdev->priv_data; - - kref_init(&ep->kref); - - return 0; -} - static DEFINE_XARRAY_ALLOC(telem_array); static struct intel_pmt_namespace pmt_telem_ns = { .name = "telem", .xa = &telem_array, .pmt_header_decode = pmt_telem_header_decode, - .pmt_add_endpoint = pmt_telem_add_endpoint, + .pmt_add_endpoint = intel_pmt_add_endpoint, }; -/* Called when all users unregister and the device is removed */ -static void pmt_telem_ep_release(struct kref *kref) -{ - struct telem_endpoint *ep; - - ep = container_of(kref, struct telem_endpoint, kref); - kfree(ep); -} - unsigned long pmt_telem_get_next_endpoint(unsigned long start) { struct intel_pmt_entry *entry; @@ -155,7 +122,7 @@ unsigned long pmt_telem_get_next_endpoint(unsigned long start) } EXPORT_SYMBOL_NS_GPL(pmt_telem_get_next_endpoint, "INTEL_PMT_TELEMETRY"); -struct telem_endpoint *pmt_telem_register_endpoint(int devid) +struct class_endpoint *pmt_telem_register_endpoint(int devid) { struct intel_pmt_entry *entry; unsigned long index = devid; @@ -174,9 +141,9 @@ struct telem_endpoint *pmt_telem_register_endpoint(int devid) } EXPORT_SYMBOL_NS_GPL(pmt_telem_register_endpoint, "INTEL_PMT_TELEMETRY"); -void pmt_telem_unregister_endpoint(struct telem_endpoint *ep) +void pmt_telem_unregister_endpoint(struct class_endpoint *ep) { - kref_put(&ep->kref, pmt_telem_ep_release); + intel_pmt_release_endpoint(ep); } EXPORT_SYMBOL_NS_GPL(pmt_telem_unregister_endpoint, "INTEL_PMT_TELEMETRY"); @@ -206,7 +173,7 @@ int pmt_telem_get_endpoint_info(int devid, struct telem_endpoint_info *info) } EXPORT_SYMBOL_NS_GPL(pmt_telem_get_endpoint_info, "INTEL_PMT_TELEMETRY"); -int pmt_telem_read(struct telem_endpoint *ep, u32 id, u64 *data, u32 count) +int pmt_telem_read(struct class_endpoint *ep, u32 id, u64 *data, u32 count) { u32 offset, size; @@ -226,7 +193,7 @@ int pmt_telem_read(struct telem_endpoint *ep, u32 id, u64 *data, u32 count) } EXPORT_SYMBOL_NS_GPL(pmt_telem_read, "INTEL_PMT_TELEMETRY"); -int pmt_telem_read32(struct telem_endpoint *ep, u32 id, u32 *data, u32 count) +int pmt_telem_read32(struct class_endpoint *ep, u32 id, u32 *data, u32 count) { u32 offset, size; @@ -245,7 +212,7 @@ int pmt_telem_read32(struct telem_endpoint *ep, u32 id, u32 *data, u32 count) } EXPORT_SYMBOL_NS_GPL(pmt_telem_read32, "INTEL_PMT_TELEMETRY"); -struct telem_endpoint * +struct class_endpoint * pmt_telem_find_and_register_endpoint(struct pci_dev *pcidev, u32 guid, u16 pos) { int devid = 0; @@ -279,7 +246,7 @@ static void pmt_telem_remove(struct auxiliary_device *auxdev) for (i = 0; i < priv->num_entries; i++) { struct intel_pmt_entry *entry = &priv->entry[i]; - kref_put(&entry->ep->kref, pmt_telem_ep_release); + pmt_telem_unregister_endpoint(entry->ep); intel_pmt_dev_destroy(entry, &pmt_telem_ns); } mutex_unlock(&ep_lock); diff --git a/drivers/platform/x86/intel/pmt/telemetry.h b/drivers/platform/x86/intel/pmt/telemetry.h index d45af5512b4e..e987dd32a58a 100644 --- a/drivers/platform/x86/intel/pmt/telemetry.h +++ b/drivers/platform/x86/intel/pmt/telemetry.h @@ -2,6 +2,8 @@ #ifndef _TELEMETRY_H #define _TELEMETRY_H +#include "class.h" + /* Telemetry types */ #define PMT_TELEM_TELEMETRY 0 #define PMT_TELEM_CRASHLOG 1 @@ -9,16 +11,9 @@ struct telem_endpoint; struct pci_dev; -struct telem_header { - u8 access_type; - u16 size; - u32 guid; - u32 base_offset; -}; - struct telem_endpoint_info { struct pci_dev *pdev; - struct telem_header header; + struct class_header header; }; /** @@ -47,7 +42,7 @@ unsigned long pmt_telem_get_next_endpoint(unsigned long start); * * endpoint - On success returns pointer to the telemetry endpoint * * -ENXIO - telemetry endpoint not found */ -struct telem_endpoint *pmt_telem_register_endpoint(int devid); +struct class_endpoint *pmt_telem_register_endpoint(int devid); /** * pmt_telem_unregister_endpoint() - Unregister a telemetry endpoint @@ -55,7 +50,7 @@ struct telem_endpoint *pmt_telem_register_endpoint(int devid); * * Decrements the kref usage counter for the endpoint. */ -void pmt_telem_unregister_endpoint(struct telem_endpoint *ep); +void pmt_telem_unregister_endpoint(struct class_endpoint *ep); /** * pmt_telem_get_endpoint_info() - Get info for an endpoint from its devid @@ -80,8 +75,8 @@ int pmt_telem_get_endpoint_info(int devid, struct telem_endpoint_info *info); * * endpoint - On success returns pointer to the telemetry endpoint * * -ENXIO - telemetry endpoint not found */ -struct telem_endpoint *pmt_telem_find_and_register_endpoint(struct pci_dev *pcidev, - u32 guid, u16 pos); +struct class_endpoint *pmt_telem_find_and_register_endpoint(struct pci_dev *pcidev, + u32 guid, u16 pos); /** * pmt_telem_read() - Read qwords from counter sram using sample id @@ -101,7 +96,7 @@ struct telem_endpoint *pmt_telem_find_and_register_endpoint(struct pci_dev *pcid * * -EPIPE - The device was removed during the read. Data written * but should be considered invalid. */ -int pmt_telem_read(struct telem_endpoint *ep, u32 id, u64 *data, u32 count); +int pmt_telem_read(struct class_endpoint *ep, u32 id, u64 *data, u32 count); /** * pmt_telem_read32() - Read qwords from counter sram using sample id @@ -121,6 +116,6 @@ int pmt_telem_read(struct telem_endpoint *ep, u32 id, u64 *data, u32 count); * * -EPIPE - The device was removed during the read. Data written * but should be considered invalid. */ -int pmt_telem_read32(struct telem_endpoint *ep, u32 id, u32 *data, u32 count); +int pmt_telem_read32(struct class_endpoint *ep, u32 id, u32 *data, u32 count); #endif -- 2.49.0

1 day, 4 hours

3
2
0 0

[PATCH RESEND 3/3] HID: wacom: fix kobject reference count leak

by Qasim Ijaz

When sysfs_create_files() fails in wacom_initialize_remotes() the error is returned and the cleanup action will not have been registered yet. As a result the kobject��s refcount is never dropped, so the kobject can never be freed leading to a reference leak. Fix this by calling kobject_put() before returning. Fixes: 83e6b40e2de6 ("HID: wacom: EKR: have the wacom resources dynamically allocated") Acked-by: Ping Cheng <ping.cheng(a)wacom.com> Cc: stable(a)vger.kernel.org Signed-off-by: Qasim Ijaz <qasdev00(a)gmail.com> --- drivers/hid/wacom_sys.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index 58cbd43a37e9..1257131b1e34 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -2059,6 +2059,7 @@ static int wacom_initialize_remotes(struct wacom *wacom) hid_err(wacom->hdev, "cannot create sysfs group err: %d\n", error); kfifo_free(&remote->remote_fifo); + kobject_put(remote->remote_dir); return error; } -- 2.39.5

1 day, 4 hours

1
0
0 0

[PATCH RESEND 2/3] HID: wacom: fix memory leak on sysfs attribute creation failure

by Qasim Ijaz

When sysfs_create_files() fails during wacom_initialize_remotes() the fifo buffer is not freed leading to a memory leak. Fix this by calling kfifo_free() before returning. Fixes: 83e6b40e2de6 ("HID: wacom: EKR: have the wacom resources dynamically allocated") Reviewed-by: Ping Cheng <ping.cheng(a)wacom.com> Cc: stable(a)vger.kernel.org Signed-off-by: Qasim Ijaz <qasdev00(a)gmail.com> --- drivers/hid/wacom_sys.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index ec5282bc69d6..58cbd43a37e9 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -2058,6 +2058,7 @@ static int wacom_initialize_remotes(struct wacom *wacom) if (error) { hid_err(wacom->hdev, "cannot create sysfs group err: %d\n", error); + kfifo_free(&remote->remote_fifo); return error; } -- 2.39.5

1 day, 4 hours

1
0
0 0

[PATCH RESEND 1/3] HID: wacom: fix memory leak on kobject creation failure

by Qasim Ijaz

During wacom_initialize_remotes() a fifo buffer is allocated with kfifo_alloc() and later a cleanup action is registered during devm_add_action_or_reset() to clean it up. However if the code fails to create a kobject and register it with sysfs the code simply returns -ENOMEM before the cleanup action is registered leading to a memory leak. Fix this by ensuring the fifo is freed when the kobject creation and registration process fails. Fixes: 83e6b40e2de6 ("HID: wacom: EKR: have the wacom resources dynamically allocated") Reviewed-by: Ping Cheng <ping.cheng(a)wacom.com> Cc: stable(a)vger.kernel.org Signed-off-by: Qasim Ijaz <qasdev00(a)gmail.com> --- drivers/hid/wacom_sys.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index eaf099b2efdb..ec5282bc69d6 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -2048,8 +2048,10 @@ static int wacom_initialize_remotes(struct wacom *wacom) remote->remote_dir = kobject_create_and_add("wacom_remote", &wacom->hdev->dev.kobj); - if (!remote->remote_dir) + if (!remote->remote_dir) { + kfifo_free(&remote->remote_fifo); return -ENOMEM; + } error = sysfs_create_files(remote->remote_dir, remote_unpair_attrs); -- 2.39.5

1 day, 4 hours

1
0
0 0

[PATCH] dmaengine: mediatek: Fix a flag reuse error in mtk_cqdma_tx_status()

by Qiu-ji Chen

Fixed a flag reuse bug in the mtk_cqdma_tx_status() function. Fixes: 157ae5ffd76a ("dmaengine: mediatek: Fix a possible deadlock error in mtk_cqdma_tx_status()") Cc: stable(a)vger.kernel.org Reported-by: kernel test robot <lkp(a)intel.com> Closes: https://lore.kernel.org/oe-kbuild-all/202505270641.MStzJUfU-lkp@intel.com/ Signed-off-by: Qiu-ji Chen <chenqiuji666(a)gmail.com> --- drivers/dma/mediatek/mtk-cqdma.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/dma/mediatek/mtk-cqdma.c b/drivers/dma/mediatek/mtk-cqdma.c index 47c8adfdc155..f7b870d2ca90 100644 --- a/drivers/dma/mediatek/mtk-cqdma.c +++ b/drivers/dma/mediatek/mtk-cqdma.c @@ -441,18 +441,19 @@ static enum dma_status mtk_cqdma_tx_status(struct dma_chan *c, struct mtk_cqdma_vdesc *cvd; struct virt_dma_desc *vd; enum dma_status ret; - unsigned long flags; + unsigned long pc_flags; + unsigned long vc_flags; size_t bytes = 0; ret = dma_cookie_status(c, cookie, txstate); if (ret == DMA_COMPLETE || !txstate) return ret; - spin_lock_irqsave(&cvc->pc->lock, flags); - spin_lock_irqsave(&cvc->vc.lock, flags); + spin_lock_irqsave(&cvc->pc->lock, pc_flags); + spin_lock_irqsave(&cvc->vc.lock, vc_flags); vd = mtk_cqdma_find_active_desc(c, cookie); - spin_unlock_irqrestore(&cvc->vc.lock, flags); - spin_unlock_irqrestore(&cvc->pc->lock, flags); + spin_unlock_irqrestore(&cvc->vc.lock, vc_flags); + spin_unlock_irqrestore(&cvc->pc->lock, pc_flags); if (vd) { cvd = to_cqdma_vdesc(vd); -- 2.34.1

1 day, 5 hours

2
4
0 0

[PATCH 6.15.y] pinctrl: mediatek: eint: Fix invalid pointer dereference for v1 platforms

by Uwe Kleine-König

From: Nícolas F. R. A. Prado <nfraprado(a)collabora.com> commit 1c9977b263475373b31bbf86af94a5c9ae2be42c upstream. Commit 3ef9f710efcb ("pinctrl: mediatek: Add EINT support for multiple addresses") introduced an access to the 'soc' field of struct mtk_pinctrl in mtk_eint_do_init() and for that an include of pinctrl-mtk-common-v2.h. However, pinctrl drivers relying on the v1 common driver include pinctrl-mtk-common.h instead, which provides another definition of struct mtk_pinctrl that does not contain an 'soc' field. Since mtk_eint_do_init() can be called both by v1 and v2 drivers, it will now try to dereference an invalid pointer when called on v1 platforms. This has been observed on Genio 350 EVK (MT8365), which crashes very early in boot (the kernel trace can only be seen with earlycon). In order to fix this, since 'struct mtk_pinctrl' was only needed to get a 'struct mtk_eint_pin', make 'struct mtk_eint_pin' a parameter of mtk_eint_do_init() so that callers need to supply it, removing mtk_eint_do_init()'s dependency on any particular 'struct mtk_pinctrl'. Fixes: 3ef9f710efcb ("pinctrl: mediatek: Add EINT support for multiple addresses") Suggested-by: AngeloGioacchino Del Regno <angelogioacchino.delregno(a)collabora.com> Signed-off-by: Nícolas F. R. A. Prado <nfraprado(a)collabora.com> Link: https://lore.kernel.org/20250520-genio-350-eint-null-ptr-deref-fix-v2-1-6a3… Signed-off-by: Linus Walleij <linus.walleij(a)linaro.org> [ukleinek: backport to 6.15.y] Signed-off-by: Uwe Kleine-König <u.kleine-koenig(a)baylibre.com> --- Hello, would be great to have this in 6.15. Further backporting isn't needed as 3ef9f710efcb == v6.15-rc1~106^2 isn't in 6.14. This patch fixes booting on mt8365-evk (and probably a few more machines based on mediatek SoCs. There was an easy conflict with 86dee87f4b2e6ac119b03810e58723d0b27787a4 in drivers/pinctrl/mediatek/mtk-eint.c. Thanks Uwe drivers/pinctrl/mediatek/mtk-eint.c | 26 ++++++++----------- drivers/pinctrl/mediatek/mtk-eint.h | 5 ++-- .../pinctrl/mediatek/pinctrl-mtk-common-v2.c | 2 +- drivers/pinctrl/mediatek/pinctrl-mtk-common.c | 2 +- 4 files changed, 16 insertions(+), 19 deletions(-) diff --git a/drivers/pinctrl/mediatek/mtk-eint.c b/drivers/pinctrl/mediatek/mtk-eint.c index b4eb2beab691..c516c34aaaf6 100644 --- a/drivers/pinctrl/mediatek/mtk-eint.c +++ b/drivers/pinctrl/mediatek/mtk-eint.c @@ -22,7 +22,6 @@ #include <linux/platform_device.h> #include "mtk-eint.h" -#include "pinctrl-mtk-common-v2.h" #define MTK_EINT_EDGE_SENSITIVE 0 #define MTK_EINT_LEVEL_SENSITIVE 1 @@ -505,10 +504,9 @@ int mtk_eint_find_irq(struct mtk_eint *eint, unsigned long eint_n) } EXPORT_SYMBOL_GPL(mtk_eint_find_irq); -int mtk_eint_do_init(struct mtk_eint *eint) +int mtk_eint_do_init(struct mtk_eint *eint, struct mtk_eint_pin *eint_pin) { unsigned int size, i, port, inst = 0; - struct mtk_pinctrl *hw = (struct mtk_pinctrl *)eint->pctl; /* If clients don't assign a specific regs, let's use generic one */ if (!eint->regs) @@ -519,7 +517,15 @@ int mtk_eint_do_init(struct mtk_eint *eint) if (!eint->base_pin_num) return -ENOMEM; - if (eint->nbase == 1) { + if (eint_pin) { + eint->pins = eint_pin; + for (i = 0; i < eint->hw->ap_num; i++) { + inst = eint->pins[i].instance; + if (inst >= eint->nbase) + continue; + eint->base_pin_num[inst]++; + } + } else { size = eint->hw->ap_num * sizeof(struct mtk_eint_pin); eint->pins = devm_kmalloc(eint->dev, size, GFP_KERNEL); if (!eint->pins) @@ -533,16 +539,6 @@ int mtk_eint_do_init(struct mtk_eint *eint) } } - if (hw && hw->soc && hw->soc->eint_pin) { - eint->pins = hw->soc->eint_pin; - for (i = 0; i < eint->hw->ap_num; i++) { - inst = eint->pins[i].instance; - if (inst >= eint->nbase) - continue; - eint->base_pin_num[inst]++; - } - } - eint->pin_list = devm_kmalloc(eint->dev, eint->nbase * sizeof(u16 *), GFP_KERNEL); if (!eint->pin_list) goto err_pin_list; @@ -610,7 +606,7 @@ int mtk_eint_do_init(struct mtk_eint *eint) err_wake_mask: devm_kfree(eint->dev, eint->pin_list); err_pin_list: - if (eint->nbase == 1) + if (!eint_pin) devm_kfree(eint->dev, eint->pins); err_pins: devm_kfree(eint->dev, eint->base_pin_num); diff --git a/drivers/pinctrl/mediatek/mtk-eint.h b/drivers/pinctrl/mediatek/mtk-eint.h index f7f58cca0d5e..23801d4b636f 100644 --- a/drivers/pinctrl/mediatek/mtk-eint.h +++ b/drivers/pinctrl/mediatek/mtk-eint.h @@ -88,7 +88,7 @@ struct mtk_eint { }; #if IS_ENABLED(CONFIG_EINT_MTK) -int mtk_eint_do_init(struct mtk_eint *eint); +int mtk_eint_do_init(struct mtk_eint *eint, struct mtk_eint_pin *eint_pin); int mtk_eint_do_suspend(struct mtk_eint *eint); int mtk_eint_do_resume(struct mtk_eint *eint); int mtk_eint_set_debounce(struct mtk_eint *eint, unsigned long eint_n, @@ -96,7 +96,8 @@ int mtk_eint_set_debounce(struct mtk_eint *eint, unsigned long eint_n, int mtk_eint_find_irq(struct mtk_eint *eint, unsigned long eint_n); #else -static inline int mtk_eint_do_init(struct mtk_eint *eint) +static inline int mtk_eint_do_init(struct mtk_eint *eint, + struct mtk_eint_pin *eint_pin) { return -EOPNOTSUPP; } diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c index d1556b75d9ef..ba13558bfcd7 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c +++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c @@ -416,7 +416,7 @@ int mtk_build_eint(struct mtk_pinctrl *hw, struct platform_device *pdev) hw->eint->pctl = hw; hw->eint->gpio_xlate = &mtk_eint_xt; - ret = mtk_eint_do_init(hw->eint); + ret = mtk_eint_do_init(hw->eint, hw->soc->eint_pin); if (ret) goto err_free_eint; diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c index 8596f3541265..7289648eaa02 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c +++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c @@ -1039,7 +1039,7 @@ static int mtk_eint_init(struct mtk_pinctrl *pctl, struct platform_device *pdev) pctl->eint->pctl = pctl; pctl->eint->gpio_xlate = &mtk_eint_xt; - return mtk_eint_do_init(pctl->eint); + return mtk_eint_do_init(pctl->eint, NULL); } /* This is used as a common probe function */ -- 2.47.2

1 day, 6 hours

1
0
0 0

[for-linus][PATCH 2/3] ring-buffer: Fix buffer locking in ring_buffer_subbuf_order_set()

by Steven Rostedt

From: Dmitry Antipov <dmantipov(a)yandex.ru> Enlarge the critical section in ring_buffer_subbuf_order_set() to ensure that error handling takes place with per-buffer mutex held, thus preventing list corruption and other concurrency-related issues. Cc: stable(a)vger.kernel.org Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Tzvetomir Stoyanov <tz.stoyanov(a)gmail.com> Link: https://lore.kernel.org/20250606112242.1510605-1-dmantipov@yandex.ru Reported-by: syzbot+05d673e83ec640f0ced9(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=05d673e83ec640f0ced9 Fixes: f9b94daa542a8 ("ring-buffer: Set new size of the ring buffer sub page") Signed-off-by: Dmitry Antipov <dmantipov(a)yandex.ru> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- kernel/trace/ring_buffer.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index e24509bd0af5..00fc38d70e86 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -6795,7 +6795,7 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) old_size = buffer->subbuf_size; /* prevent another thread from changing buffer sizes */ - mutex_lock(&buffer->mutex); + guard(mutex)(&buffer->mutex); atomic_inc(&buffer->record_disabled); /* Make sure all commits have finished */ @@ -6900,7 +6900,6 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) } atomic_dec(&buffer->record_disabled); - mutex_unlock(&buffer->mutex); return 0; @@ -6909,7 +6908,6 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) buffer->subbuf_size = old_size; atomic_dec(&buffer->record_disabled); - mutex_unlock(&buffer->mutex); for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; -- 2.47.2

1 day, 6 hours

1
0
0 0

[for-linus][PATCH 1/3] tracing: Fix regression of filter waiting a long time on RCU synchronization

by Steven Rostedt

From: Steven Rostedt <rostedt(a)goodmis.org> When faultable trace events were added, a trace event may no longer use normal RCU to synchronize but instead used synchronize_rcu_tasks_trace(). This synchronization takes a much longer time to synchronize. The filter logic would free the filters by calling tracepoint_synchronize_unregister() after it unhooked the filter strings and before freeing them. With this function now calling synchronize_rcu_tasks_trace() this increased the time to free a filter tremendously. On a PREEMPT_RT system, it was even more noticeable. # time trace-cmd record -p function sleep 1 [..] real 2m29.052s user 0m0.244s sys 0m20.136s As trace-cmd would clear out all the filters before recording, it could take up to 2 minutes to do a recording of "sleep 1". To find out where the issues was: ~# trace-cmd sqlhist -e -n sched_stack select start.prev_state as state, end.next_comm as comm, TIMESTAMP_DELTA_USECS as delta, start.STACKTRACE as stack from sched_switch as start join sched_switch as end on start.prev_pid = end.next_pid Which will produce the following commands (and -e will also execute them): echo 's:sched_stack s64 state; char comm[16]; u64 delta; unsigned long stack[];' >> /sys/kernel/tracing/dynamic_events echo 'hist:keys=prev_pid:__arg_18057_2=prev_state,__arg_18057_4=common_timestamp.usecs,__arg_18057_7=common_stacktrace' >> /sys/kernel/tracing/events/sched/sched_switch/trigger echo 'hist:keys=next_pid:__state_18057_1=$__arg_18057_2,__comm_18057_3=next_comm,__delta_18057_5=common_timestamp.usecs-$__arg_18057_4,__stack_18057_6=$__arg_18057_7:onmatch(sched.sched_switch).trace(sched_stack,$__state_18057_1,$__comm_18057_3,$__delta_18057_5,$__stack_18057_6)' >> /sys/kernel/tracing/events/sched/sched_switch/trigger The above creates a synthetic event that creates a stack trace when a task schedules out and records it with the time it scheduled back in. Basically the time a task is off the CPU. It also records the state of the task when it left the CPU (running, blocked, sleeping, etc). It also saves the comm of the task as "comm" (needed for the next command). ~# echo 'hist:keys=state,stack.stacktrace:vals=delta:sort=state,delta if comm == "trace-cmd" && state & 3' > /sys/kernel/tracing/events/synthetic/sched_stack/trigger The above creates a histogram with buckets per state, per stack, and the value of the total time it was off the CPU for that stack trace. It filters on tasks with "comm == trace-cmd" and only the sleeping and blocked states (1 - sleeping, 2 - blocked). ~# trace-cmd record -p function sleep 1 ~# cat /sys/kernel/tracing/events/synthetic/sched_stack/hist | tail -18 { state: 2, stack.stacktrace __schedule+0x1545/0x3700 schedule+0xe2/0x390 schedule_timeout+0x175/0x200 wait_for_completion_state+0x294/0x440 __wait_rcu_gp+0x247/0x4f0 synchronize_rcu_tasks_generic+0x151/0x230 apply_subsystem_event_filter+0xa2b/0x1300 subsystem_filter_write+0x67/0xc0 vfs_write+0x1e2/0xeb0 ksys_write+0xff/0x1d0 do_syscall_64+0x7b/0x420 entry_SYSCALL_64_after_hwframe+0x76/0x7e } hitcount: 237 delta: 99756288 <<--------------- Delta is 99 seconds! Totals: Hits: 525 Entries: 21 Dropped: 0 This shows that this particular trace waited for 99 seconds on synchronize_rcu_tasks() in apply_subsystem_event_filter(). In fact, there's a lot of places in the filter code that spends a lot of time waiting for synchronize_rcu_tasks_trace() in order to free the filters. Add helper functions that will use call_rcu*() variants to asynchronously free the filters. This brings the timings back to normal: # time trace-cmd record -p function sleep 1 [..] real 0m14.681s user 0m0.335s sys 0m28.616s And the histogram also shows this: ~# cat /sys/kernel/tracing/events/synthetic/sched_stack/hist | tail -21 { state: 2, stack.stacktrace __schedule+0x1545/0x3700 schedule+0xe2/0x390 schedule_timeout+0x175/0x200 wait_for_completion_state+0x294/0x440 __wait_rcu_gp+0x247/0x4f0 synchronize_rcu_normal+0x3db/0x5c0 tracing_reset_online_cpus+0x8f/0x1e0 tracing_open+0x335/0x440 do_dentry_open+0x4c6/0x17a0 vfs_open+0x82/0x360 path_openat+0x1a36/0x2990 do_filp_open+0x1c5/0x420 do_sys_openat2+0xed/0x180 __x64_sys_openat+0x108/0x1d0 do_syscall_64+0x7b/0x420 } hitcount: 2 delta: 77044 Totals: Hits: 55 Entries: 28 Dropped: 0 Where the total waiting time of synchronize_rcu_tasks_trace() is 77 milliseconds. Cc: stable(a)vger.kernel.org Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: "Paul E. McKenney" <paulmck(a)kernel.org> Cc: "Kiszka, Jan" <jan.kiszka(a)siemens.com> Cc: "Ziegler, Andreas" <ziegler.andreas(a)siemens.com> Cc: "MOESSBAUER, Felix" <felix.moessbauer(a)siemens.com> Link: https://lore.kernel.org/20250605161701.35f7989a@gandalf.local.home Reported-by: "Flot, Julien" <julien.flot(a)siemens.com> Tested-by: Julien Flot <julien.flot(a)siemens.com> Fixes: a363d27cdbc2 ("tracing: Allow system call tracepoints to handle page faults") Closes: https://lore.kernel.org/all/240017f656631c7dd4017aa93d91f41f653788ea.camel@… Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- kernel/trace/trace_events_filter.c | 164 ++++++++++++++++++++++------- 1 file changed, 127 insertions(+), 37 deletions(-) diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 2048560264bb..3ff782d6b522 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1335,6 +1335,74 @@ static void filter_free_subsystem_preds(struct trace_subsystem_dir *dir, } } +struct filter_list { + struct list_head list; + struct event_filter *filter; +}; + +struct filter_head { + struct list_head list; + struct rcu_head rcu; +}; + + +static void free_filter_list(struct rcu_head *rhp) +{ + struct filter_head *filter_list = container_of(rhp, struct filter_head, rcu); + struct filter_list *filter_item, *tmp; + + list_for_each_entry_safe(filter_item, tmp, &filter_list->list, list) { + __free_filter(filter_item->filter); + list_del(&filter_item->list); + kfree(filter_item); + } + kfree(filter_list); +} + +static void free_filter_list_tasks(struct rcu_head *rhp) +{ + call_rcu(rhp, free_filter_list); +} + +/* + * The tracepoint_synchronize_unregister() is a double rcu call. + * It calls synchronize_rcu_tasks_trace() followed by synchronize_rcu(). + * Instead of waiting for it, simply call these via the call_rcu*() + * variants. + */ +static void delay_free_filter(struct filter_head *head) +{ + call_rcu_tasks_trace(&head->rcu, free_filter_list_tasks); +} + +static void try_delay_free_filter(struct event_filter *filter) +{ + struct filter_head *head; + struct filter_list *item; + + head = kmalloc(sizeof(*head), GFP_KERNEL); + if (!head) + goto free_now; + + INIT_LIST_HEAD(&head->list); + + item = kmalloc(sizeof(*item), GFP_KERNEL); + if (!item) { + kfree(head); + goto free_now; + } + + item->filter = filter; + list_add_tail(&item->list, &head->list); + delay_free_filter(head); + return; + + free_now: + /* Make sure the filter is not being used */ + tracepoint_synchronize_unregister(); + __free_filter(filter); +} + static inline void __free_subsystem_filter(struct trace_event_file *file) { __free_filter(file->filter); @@ -1342,15 +1410,53 @@ static inline void __free_subsystem_filter(struct trace_event_file *file) } static void filter_free_subsystem_filters(struct trace_subsystem_dir *dir, - struct trace_array *tr) + struct trace_array *tr, + struct event_filter *filter) { struct trace_event_file *file; + struct filter_head *head; + struct filter_list *item; + + head = kmalloc(sizeof(*head), GFP_KERNEL); + if (!head) + goto free_now; + + INIT_LIST_HEAD(&head->list); + + item = kmalloc(sizeof(*item), GFP_KERNEL); + if (!item) { + kfree(head); + goto free_now; + } + + item->filter = filter; + list_add_tail(&item->list, &head->list); list_for_each_entry(file, &tr->events, list) { if (file->system != dir) continue; - __free_subsystem_filter(file); + item = kmalloc(sizeof(*item), GFP_KERNEL); + if (!item) + goto free_now; + item->filter = file->filter; + list_add_tail(&item->list, &head->list); + file->filter = NULL; + } + + delay_free_filter(head); + return; + free_now: + tracepoint_synchronize_unregister(); + + if (head) + free_filter_list(&head->rcu); + + list_for_each_entry(file, &tr->events, list) { + if (file->system != dir || !file->filter) + continue; + __free_filter(file->filter); } + __free_filter(filter); } int filter_assign_type(const char *type) @@ -2131,11 +2237,6 @@ static inline void event_clear_filter(struct trace_event_file *file) RCU_INIT_POINTER(file->filter, NULL); } -struct filter_list { - struct list_head list; - struct event_filter *filter; -}; - static int process_system_preds(struct trace_subsystem_dir *dir, struct trace_array *tr, struct filter_parse_error *pe, @@ -2144,11 +2245,16 @@ static int process_system_preds(struct trace_subsystem_dir *dir, struct trace_event_file *file; struct filter_list *filter_item; struct event_filter *filter = NULL; - struct filter_list *tmp; - LIST_HEAD(filter_list); + struct filter_head *filter_list; bool fail = true; int err; + filter_list = kmalloc(sizeof(*filter_list), GFP_KERNEL); + if (!filter_list) + return -ENOMEM; + + INIT_LIST_HEAD(&filter_list->list); + list_for_each_entry(file, &tr->events, list) { if (file->system != dir) @@ -2175,7 +2281,7 @@ static int process_system_preds(struct trace_subsystem_dir *dir, if (!filter_item) goto fail_mem; - list_add_tail(&filter_item->list, &filter_list); + list_add_tail(&filter_item->list, &filter_list->list); /* * Regardless of if this returned an error, we still * replace the filter for the call. @@ -2195,31 +2301,22 @@ static int process_system_preds(struct trace_subsystem_dir *dir, * Do a synchronize_rcu() and to ensure all calls are * done with them before we free them. */ - tracepoint_synchronize_unregister(); - list_for_each_entry_safe(filter_item, tmp, &filter_list, list) { - __free_filter(filter_item->filter); - list_del(&filter_item->list); - kfree(filter_item); - } + delay_free_filter(filter_list); return 0; fail: /* No call succeeded */ - list_for_each_entry_safe(filter_item, tmp, &filter_list, list) { - list_del(&filter_item->list); - kfree(filter_item); - } + free_filter_list(&filter_list->rcu); parse_error(pe, FILT_ERR_BAD_SUBSYS_FILTER, 0); return -EINVAL; fail_mem: __free_filter(filter); + /* If any call succeeded, we still need to sync */ if (!fail) - tracepoint_synchronize_unregister(); - list_for_each_entry_safe(filter_item, tmp, &filter_list, list) { - __free_filter(filter_item->filter); - list_del(&filter_item->list); - kfree(filter_item); - } + delay_free_filter(filter_list); + else + free_filter_list(&filter_list->rcu); + return -ENOMEM; } @@ -2361,9 +2458,7 @@ int apply_event_filter(struct trace_event_file *file, char *filter_string) event_clear_filter(file); - /* Make sure the filter is not being used */ - tracepoint_synchronize_unregister(); - __free_filter(filter); + try_delay_free_filter(filter); return 0; } @@ -2387,11 +2482,8 @@ int apply_event_filter(struct trace_event_file *file, char *filter_string) event_set_filter(file, filter); - if (tmp) { - /* Make sure the call is done with the filter */ - tracepoint_synchronize_unregister(); - __free_filter(tmp); - } + if (tmp) + try_delay_free_filter(tmp); } return err; @@ -2417,9 +2509,7 @@ int apply_subsystem_event_filter(struct trace_subsystem_dir *dir, filter = system->filter; system->filter = NULL; /* Ensure all filters are no longer used */ - tracepoint_synchronize_unregister(); - filter_free_subsystem_filters(dir, tr); - __free_filter(filter); + filter_free_subsystem_filters(dir, tr, filter); return 0; } -- 2.47.2

1 day, 6 hours

1
0
0 0

[PATCH 0/2] mm/memory: fix memory tearing on threaded fork

by Jann Horn

The first patch is a fix with an explanation of the issue, you should read that first. The second patch adds a comment to document the rules because figuring this out from scratch causes brain pain. Accidentally hitting this issue and getting negative consequences from it would require several stars to line up just right; but if someone out there is using a malloc() implementation that uses lockless data structures across threads or such, this could actually be a problem. In case someone wants a testcase, here's a very artificial one: ``` #include <pthread.h> #include <err.h> #include <stdio.h> #include <unistd.h> #include <sys/syscall.h> #include <sys/uio.h> #include <sys/mman.h> #include <sys/wait.h> #include <linux/io_uring.h> #define SYSCHK(x) ({ \ typeof(x) __res = (x); \ if (__res == (typeof(x))-1) \ err(1, "SYSCHK(" #x ")"); \ __res; \ }) #define NUM_SQ_PAGES 4 static int uring_init(struct io_uring_sqe **sqesp, void **cqesp) { struct io_uring_sqe *sqes = SYSCHK(mmap(NULL, NUM_SQ_PAGES*0x1000, PROT_READ|PROT_WRITE, MAP_SHARED|MAP_ANONYMOUS, -1, 0)); void *cqes = SYSCHK(mmap(NULL, NUM_SQ_PAGES*0x1000, PROT_READ|PROT_WRITE, MAP_SHARED|MAP_ANONYMOUS, -1, 0)); *(volatile unsigned int *)(cqes+4) = 64 * NUM_SQ_PAGES; struct io_uring_params params = { .flags = IORING_SETUP_NO_MMAP|IORING_SETUP_NO_SQARRAY, .sq_off = { .user_addr = (unsigned long)sqes }, .cq_off = { .user_addr = (unsigned long)cqes } }; int uring_fd = SYSCHK(syscall(__NR_io_uring_setup, /*entries=*/10, &params)); if (sqesp) *sqesp = sqes; if (cqesp) *cqesp = cqes; return uring_fd; } static char *bufmem[0x3000] __attribute__((aligned(0x1000))); static void *thread_fn(void *dummy) { unsigned long i = 0; while (1) { *(volatile unsigned long *)(bufmem + 0x0000) = i; *(volatile unsigned long *)(bufmem + 0x0f00) = i; *(volatile unsigned long *)(bufmem + 0x1000) = i; *(volatile unsigned long *)(bufmem + 0x1f00) = i; *(volatile unsigned long *)(bufmem + 0x2000) = i; *(volatile unsigned long *)(bufmem + 0x2f00) = i; i++; } } int main(void) { #if 1 int uring_fd = uring_init(NULL, NULL); struct iovec reg_iov = { .iov_base = bufmem, .iov_len = 0x2000 }; SYSCHK(syscall(__NR_io_uring_register, uring_fd, IORING_REGISTER_BUFFERS, &reg_iov, 1)); #endif pthread_t thread; if (pthread_create(&thread, NULL, thread_fn, NULL)) errx(1, "pthread_create"); sleep(1); int child = SYSCHK(fork()); if (child == 0) { printf("bufmem values:\n"); printf(" 0x0000: 0x%lx\n", *(volatile unsigned long *)(bufmem + 0x0000)); printf(" 0x0f00: 0x%lx\n", *(volatile unsigned long *)(bufmem + 0x0f00)); printf(" 0x1000: 0x%lx\n", *(volatile unsigned long *)(bufmem + 0x1000)); printf(" 0x1f00: 0x%lx\n", *(volatile unsigned long *)(bufmem + 0x1f00)); printf(" 0x2000: 0x%lx\n", *(volatile unsigned long *)(bufmem + 0x2000)); printf(" 0x2f00: 0x%lx\n", *(volatile unsigned long *)(bufmem + 0x2f00)); return 0; } int wstatus; SYSCHK(wait(&wstatus)); return 0; } ``` Without this series, the child will usually print results that are apart by more than 1, which is not a state that ever occurred in the parent; in my opinion, that counts as a bug. If you change the "#if 1" to "#if 0", the bug won't manifest. Signed-off-by: Jann Horn <jannh(a)google.com> --- Jann Horn (2): mm/memory: ensure fork child sees coherent memory snapshot mm/memory: Document how we make a coherent memory snapshot kernel/fork.c | 34 ++++++++++++++++++++++++++++++++++ mm/memory.c | 18 ++++++++++++++++++ 2 files changed, 52 insertions(+) --- base-commit: 8477ab143069c6b05d6da4a8184ded8b969240f5 change-id: 20250530-fork-tearing-71da211a50cf -- Jann Horn <jannh(a)google.com>

1 day, 7 hours

5
17
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror