October 2024 - Linux-stable-mirror

[PATCH 03/13] media: dvbdev: prevent the risk of out of memory access

by Mauro Carvalho Chehab

The dvbdev contains a static variable used to store dvb minors. The behavior of it depends if CONFIG_DVB_DYNAMIC_MINORS is set or not. When not set, dvb_register_device() won't check for boundaries, as it will rely that a previous call to dvb_register_adapter() would already be enforcing it. On a similar way, dvb_device_open() uses the assumption that the register functions already did the needed checks. This can be fragile if some device ends using different calls. This also generate warnings on static check analysers. So, add explicit guards to prevent potential risk of OOM issues. Fixes: 5dd3f3071070 ("V4L/DVB (9361): Dynamic DVB minor allocation") Cc: stable(a)vger.kernel.org Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei(a)kernel.org> --- drivers/media/dvb-core/dvbdev.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c index b43695bc51e7..14f323fbada7 100644 --- a/drivers/media/dvb-core/dvbdev.c +++ b/drivers/media/dvb-core/dvbdev.c @@ -86,10 +86,15 @@ static DECLARE_RWSEM(minor_rwsem); static int dvb_device_open(struct inode *inode, struct file *file) { struct dvb_device *dvbdev; + unsigned int minor = iminor(inode); + + if (minor >= MAX_DVB_MINORS) + return -ENODEV; mutex_lock(&dvbdev_mutex); down_read(&minor_rwsem); - dvbdev = dvb_minors[iminor(inode)]; + + dvbdev = dvb_minors[minor]; if (dvbdev && dvbdev->fops) { int err = 0; @@ -525,7 +530,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, for (minor = 0; minor < MAX_DVB_MINORS; minor++) if (!dvb_minors[minor]) break; - if (minor == MAX_DVB_MINORS) { + if (minor >= MAX_DVB_MINORS) { if (new_node) { list_del(&new_node->list_head); kfree(dvbdevfops); @@ -540,6 +545,14 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, } #else minor = nums2minor(adap->num, type, id); + if (minor >= MAX_DVB_MINORS) { + dvb_media_device_free(dvbdev); + list_del(&dvbdev->list_head); + kfree(dvbdev); + *pdvbdev = NULL; + mutex_unlock(&dvbdev_register_lock); + return ret; + } #endif dvbdev->minor = minor; dvb_minors[minor] = dvb_device_get(dvbdev); -- 2.47.0

6 months, 1 week

1
0
0 0

[PATCH v2] x86/stackprotector: Work around strict Clang TLS symbol requirements

by Ard Biesheuvel

From: Ard Biesheuvel <ardb(a)kernel.org> GCC and Clang both implement stack protector support based on Thread Local Storage (TLS) variables, and this is used in the kernel to implement per-task stack cookies, by copying a task's stack cookie into a per-CPU variable every time it is scheduled in. Both now also implement -mstack-protector-guard-symbol=, which permits the TLS variable to be specified directly. This is useful because it will allow us to move away from using a fixed offset of 40 bytes into the per-CPU area on x86_64, which requires a lot of special handling in the per-CPU code and the runtime relocation code. However, while GCC is rather lax in its implementation of this command line option, Clang actually requires that the provided symbol name refers to a TLS variable (i.e., one declared with __thread), although it also permits the variable to be undeclared entirely, in which case it will use an implicit declaration of the right type. The upshot of this is that Clang will emit the correct references to the stack cookie variable in most cases, e.g., 10d: 64 a1 00 00 00 00 mov %fs:0x0,%eax 10f: R_386_32 __stack_chk_guard However, if a non-TLS definition of the symbol in question is visible in the same compilation unit (which amounts to the whole of vmlinux if LTO is enabled), it will drop the per-CPU prefix and emit a load from a bogus address. Work around this by using a symbol name that never occurs in C code, and emit it as an alias in the linker script. Fixes: 3fb0fdb3bbe7 ("x86/stackprotector/32: Make the canary into a regular percpu variable") Cc: <stable(a)vger.kernel.org> Cc: Fangrui Song <i(a)maskray.me> Cc: Brian Gerst <brgerst(a)gmail.com> Cc: Uros Bizjak <ubizjak(a)gmail.com> Cc: Nathan Chancellor <nathan(a)kernel.org> Cc: Andy Lutomirski <luto(a)kernel.org> Link: https://github.com/ClangBuiltLinux/linux/issues/1854 Signed-off-by: Ard Biesheuvel <ardb(a)kernel.org> --- v2: add declaration of alias to asm-prototypes.h, but expose it only to genksyms arch/x86/Makefile | 5 +++-- arch/x86/entry/entry.S | 16 ++++++++++++++++ arch/x86/include/asm/asm-prototypes.h | 3 +++ arch/x86/kernel/cpu/common.c | 2 ++ arch/x86/kernel/vmlinux.lds.S | 3 +++ 5 files changed, 27 insertions(+), 2 deletions(-) diff --git a/arch/x86/Makefile b/arch/x86/Makefile index cd75e78a06c1..5b773b34768d 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -142,9 +142,10 @@ ifeq ($(CONFIG_X86_32),y) ifeq ($(CONFIG_STACKPROTECTOR),y) ifeq ($(CONFIG_SMP),y) - KBUILD_CFLAGS += -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard + KBUILD_CFLAGS += -mstack-protector-guard-reg=fs \ + -mstack-protector-guard-symbol=__ref_stack_chk_guard else - KBUILD_CFLAGS += -mstack-protector-guard=global + KBUILD_CFLAGS += -mstack-protector-guard=global endif endif else diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S index d9feadffa972..a503e6d535f8 100644 --- a/arch/x86/entry/entry.S +++ b/arch/x86/entry/entry.S @@ -46,3 +46,19 @@ EXPORT_SYMBOL_GPL(mds_verw_sel); .popsection THUNK warn_thunk_thunk, __warn_thunk + +#ifndef CONFIG_X86_64 +/* + * Clang's implementation of TLS stack cookies requires the variable in + * question to be a TLS variable. If the variable happens to be defined as an + * ordinary variable with external linkage in the same compilation unit (which + * amounts to the whole of vmlinux with LTO enabled), Clang will drop the + * segment register prefix from the references, resulting in broken code. Work + * around this by avoiding the symbol used in -mstack-protector-guard-symbol= + * entirely in the C code, and use an alias emitted by the linker script + * instead. + */ +#ifdef CONFIG_STACKPROTECTOR +EXPORT_SYMBOL(__ref_stack_chk_guard); +#endif +#endif diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 25466c4d2134..3674006e3974 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -20,3 +20,6 @@ extern void cmpxchg8b_emu(void); #endif +#if defined(__GENKSYMS__) && defined(CONFIG_STACKPROTECTOR) +extern unsigned long __ref_stack_chk_guard; +#endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 07a34d723505..ba83f54dfaa8 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -2085,8 +2085,10 @@ void syscall_init(void) #ifdef CONFIG_STACKPROTECTOR DEFINE_PER_CPU(unsigned long, __stack_chk_guard); +#ifndef CONFIG_SMP EXPORT_PER_CPU_SYMBOL(__stack_chk_guard); #endif +#endif #endif /* CONFIG_X86_64 */ diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 2b7c8c14c6fd..a80ad2bf8da4 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -490,6 +490,9 @@ SECTIONS . = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE), "kernel image bigger than KERNEL_IMAGE_SIZE"); +/* needed for Clang - see arch/x86/entry/entry.S */ +PROVIDE(__ref_stack_chk_guard = __stack_chk_guard); + #ifdef CONFIG_X86_64 /* * Per-cpu symbols which need to be offset from __per_cpu_load -- 2.47.0.rc0.187.ge670bccf7e-goog

6 months, 1 week

4
4
0 0

[PATCH 1/2] dt-bindings: pinctrl: samsung: Fix interrupt constraint for variants with fallbacks

by Krzysztof Kozlowski

Commit 904140fa4553 ("dt-bindings: pinctrl: samsung: use Exynos7 fallbacks for newer wake-up controllers") added samsung,exynos7-wakeup-eint fallback to some compatibles, so the intention in the if:then: conditions was to handle the cases: 1. Single Exynos7 compatible or Exynos5433+Exynos7 or Exynos7885+Exynos7: only one interrupt 2. Exynos850+Exynos7: no interrupts This was not implemented properly however and if:then: block matches only single Exynos5433 or Exynos7885 compatibles, which do not exist in DTS anymore, so basically is a no-op and no enforcement on number of interrupts is made by the binding. Fix the if:then: condition so interrupts in the Exynos5433 and Exynos7885 wake-up pin controller will be properly constrained. Fixes: 904140fa4553 ("dt-bindings: pinctrl: samsung: use Exynos7 fallbacks for newer wake-up controllers") Cc: <stable(a)vger.kernel.org> Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski(a)linaro.org> --- Cc: Igor Belwon <igor.belwon(a)mentallysanemainliners.org> --- .../samsung,pinctrl-wakeup-interrupt.yaml | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml index 91516fedc872..49cb2b1a3d28 100644 --- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml +++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml @@ -92,14 +92,17 @@ allOf: - if: properties: compatible: - # Match without "contains", to skip newer variants which are still - # compatible with samsung,exynos7-wakeup-eint - enum: - - samsung,s5pv210-wakeup-eint - - samsung,exynos4210-wakeup-eint - - samsung,exynos5433-wakeup-eint - - samsung,exynos7-wakeup-eint - - samsung,exynos7885-wakeup-eint + oneOf: + # Match without "contains", to skip newer variants which are still + # compatible with samsung,exynos7-wakeup-eint + - enum: + - samsung,exynos4210-wakeup-eint + - samsung,exynos7-wakeup-eint + - samsung,s5pv210-wakeup-eint + - contains: + enum: + - samsung,exynos5433-wakeup-eint + - samsung,exynos7885-wakeup-eint then: properties: interrupts: -- 2.43.0

6 months, 1 week

3
3
0 0

[PATCH v2] mpi3mr: Validating SAS port assignments

by Ranjan Kumar

Sanity on phy_mask was added by Tomas through [1]. It causes warning messages when >64 phys are detected (expander can have >64 phys) and devices connected to phys greater than 64 are dropped. phy_mask bitmap is only needed for controller phys(not required for expander phys).Controller phys can go maximum up to 64 and u64 is good enough to contain phy_mask bitmap. To suppress those warnings and allow devices to be discovered as before the [1], restrict the phy_mask setting and lowest phy setting only to the controller phys. [1]:https://git.kernel.org/pub/scm/linux/kernel/git/mkp/scsi.git/commit/ drivers/scsi/mpi3mr?h=6.12/ scsi-queue&id=3668651def2c1622904e58b0280ee93121f2b10b Fixes: 3668651def2c ("mpi3mr: Sanitise num_phys") Cc: stable(a)vger.kernel.org Reported-by: kernel test robot <lkp(a)intel.com> Closes: https://lore.kernel.org/oe-kbuild-all/202410051943.Mp9o5DlF-lkp@intel.com/ Reported-by: Alexander Motin <mav(a)ixsystems.com> Signed-off-by: Ranjan Kumar <ranjan.kumar(a)broadcom.com> --- drivers/scsi/mpi3mr/mpi3mr.h | 4 +-- drivers/scsi/mpi3mr/mpi3mr_transport.c | 42 +++++++++++++++++--------- 2 files changed, 29 insertions(+), 17 deletions(-) diff --git a/drivers/scsi/mpi3mr/mpi3mr.h b/drivers/scsi/mpi3mr/mpi3mr.h index dc2cdd5f0311..3822efe349e1 100644 --- a/drivers/scsi/mpi3mr/mpi3mr.h +++ b/drivers/scsi/mpi3mr/mpi3mr.h @@ -541,8 +541,8 @@ struct mpi3mr_hba_port { * @port_list: List of ports belonging to a SAS node * @num_phys: Number of phys associated with port * @marked_responding: used while refresing the sas ports - * @lowest_phy: lowest phy ID of current sas port - * @phy_mask: phy_mask of current sas port + * @lowest_phy: lowest phy ID of current sas port, valid for controller port + * @phy_mask: phy_mask of current sas port, valid for controller port * @hba_port: HBA port entry * @remote_identify: Attached device identification * @rphy: SAS transport layer rphy object diff --git a/drivers/scsi/mpi3mr/mpi3mr_transport.c b/drivers/scsi/mpi3mr/mpi3mr_transport.c index ccd23def2e0c..0ba9e6a6a13c 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_transport.c +++ b/drivers/scsi/mpi3mr/mpi3mr_transport.c @@ -590,12 +590,13 @@ static enum sas_linkrate mpi3mr_convert_phy_link_rate(u8 link_rate) * @mrioc: Adapter instance reference * @mr_sas_port: Internal Port object * @mr_sas_phy: Internal Phy object + * @host_node: Flag to indicate this is a host_node * * Return: None. */ static void mpi3mr_delete_sas_phy(struct mpi3mr_ioc *mrioc, struct mpi3mr_sas_port *mr_sas_port, - struct mpi3mr_sas_phy *mr_sas_phy) + struct mpi3mr_sas_phy *mr_sas_phy, u8 host_node) { u64 sas_address = mr_sas_port->remote_identify.sas_address; @@ -605,9 +606,13 @@ static void mpi3mr_delete_sas_phy(struct mpi3mr_ioc *mrioc, list_del(&mr_sas_phy->port_siblings); mr_sas_port->num_phys--; - mr_sas_port->phy_mask &= ~(1 << mr_sas_phy->phy_id); - if (mr_sas_port->lowest_phy == mr_sas_phy->phy_id) - mr_sas_port->lowest_phy = ffs(mr_sas_port->phy_mask) - 1; + + if (host_node) { + mr_sas_port->phy_mask &= ~(1 << mr_sas_phy->phy_id); + + if (mr_sas_port->lowest_phy == mr_sas_phy->phy_id) + mr_sas_port->lowest_phy = ffs(mr_sas_port->phy_mask) - 1; + } sas_port_delete_phy(mr_sas_port->port, mr_sas_phy->phy); mr_sas_phy->phy_belongs_to_port = 0; } @@ -617,12 +622,13 @@ static void mpi3mr_delete_sas_phy(struct mpi3mr_ioc *mrioc, * @mrioc: Adapter instance reference * @mr_sas_port: Internal Port object * @mr_sas_phy: Internal Phy object + * @host_node: Flag to indicate this is a host_node * * Return: None. */ static void mpi3mr_add_sas_phy(struct mpi3mr_ioc *mrioc, struct mpi3mr_sas_port *mr_sas_port, - struct mpi3mr_sas_phy *mr_sas_phy) + struct mpi3mr_sas_phy *mr_sas_phy, u8 host_node) { u64 sas_address = mr_sas_port->remote_identify.sas_address; @@ -632,9 +638,12 @@ static void mpi3mr_add_sas_phy(struct mpi3mr_ioc *mrioc, list_add_tail(&mr_sas_phy->port_siblings, &mr_sas_port->phy_list); mr_sas_port->num_phys++; - mr_sas_port->phy_mask |= (1 << mr_sas_phy->phy_id); - if (mr_sas_phy->phy_id < mr_sas_port->lowest_phy) - mr_sas_port->lowest_phy = ffs(mr_sas_port->phy_mask) - 1; + if (host_node) { + mr_sas_port->phy_mask |= (1 << mr_sas_phy->phy_id); + + if (mr_sas_phy->phy_id < mr_sas_port->lowest_phy) + mr_sas_port->lowest_phy = ffs(mr_sas_port->phy_mask) - 1; + } sas_port_add_phy(mr_sas_port->port, mr_sas_phy->phy); mr_sas_phy->phy_belongs_to_port = 1; } @@ -675,7 +684,7 @@ static void mpi3mr_add_phy_to_an_existing_port(struct mpi3mr_ioc *mrioc, if (srch_phy == mr_sas_phy) return; } - mpi3mr_add_sas_phy(mrioc, mr_sas_port, mr_sas_phy); + mpi3mr_add_sas_phy(mrioc, mr_sas_port, mr_sas_phy, mr_sas_node->host_node); return; } } @@ -736,7 +745,7 @@ static void mpi3mr_del_phy_from_an_existing_port(struct mpi3mr_ioc *mrioc, mpi3mr_delete_sas_port(mrioc, mr_sas_port); else mpi3mr_delete_sas_phy(mrioc, mr_sas_port, - mr_sas_phy); + mr_sas_phy, mr_sas_node->host_node); return; } } @@ -1028,7 +1037,7 @@ mpi3mr_alloc_hba_port(struct mpi3mr_ioc *mrioc, u16 port_id) /** * mpi3mr_get_hba_port_by_id - find hba port by id * @mrioc: Adapter instance reference - * @port_id - Port ID to search + * @port_id: Port ID to search * * Return: mpi3mr_hba_port reference for the matched port */ @@ -1367,7 +1376,8 @@ static struct mpi3mr_sas_port *mpi3mr_sas_port_add(struct mpi3mr_ioc *mrioc, mpi3mr_sas_port_sanity_check(mrioc, mr_sas_node, mr_sas_port->remote_identify.sas_address, hba_port); - if (mr_sas_node->num_phys >= sizeof(mr_sas_port->phy_mask) * 8) + if (mr_sas_node->host_node && mr_sas_node->num_phys >= + sizeof(mr_sas_port->phy_mask) * 8) ioc_info(mrioc, "max port count %u could be too high\n", mr_sas_node->num_phys); @@ -1377,7 +1387,7 @@ static struct mpi3mr_sas_port *mpi3mr_sas_port_add(struct mpi3mr_ioc *mrioc, (mr_sas_node->phy[i].hba_port != hba_port)) continue; - if (i >= sizeof(mr_sas_port->phy_mask) * 8) { + if (mr_sas_node->host_node && (i >= sizeof(mr_sas_port->phy_mask) * 8)) { ioc_warn(mrioc, "skipping port %u, max allowed value is %zu\n", i, sizeof(mr_sas_port->phy_mask) * 8); goto out_fail; @@ -1385,7 +1395,8 @@ static struct mpi3mr_sas_port *mpi3mr_sas_port_add(struct mpi3mr_ioc *mrioc, list_add_tail(&mr_sas_node->phy[i].port_siblings, &mr_sas_port->phy_list); mr_sas_port->num_phys++; - mr_sas_port->phy_mask |= (1 << i); + if (mr_sas_node->host_node) + mr_sas_port->phy_mask |= (1 << i); } if (!mr_sas_port->num_phys) { @@ -1394,7 +1405,8 @@ static struct mpi3mr_sas_port *mpi3mr_sas_port_add(struct mpi3mr_ioc *mrioc, goto out_fail; } - mr_sas_port->lowest_phy = ffs(mr_sas_port->phy_mask) - 1; + if (mr_sas_node->host_node) + mr_sas_port->lowest_phy = ffs(mr_sas_port->phy_mask) - 1; if (mr_sas_port->remote_identify.device_type == SAS_END_DEVICE) { tgtdev = mpi3mr_get_tgtdev_by_addr(mrioc, -- 2.31.1

6 months, 1 week

2
1
0 0

[tip: x86/urgent] x86/apic: Always explicitly disarm TSC-deadline timer

by tip-bot2 for Zhang Rui

The following commit has been merged into the x86/urgent branch of tip: Commit-ID: ffd95846c6ec6cf1f93da411ea10d504036cab42 Gitweb: https://git.kernel.org/tip/ffd95846c6ec6cf1f93da411ea10d504036cab42 Author: Zhang Rui <rui.zhang(a)intel.com> AuthorDate: Tue, 15 Oct 2024 14:15:22 +08:00 Committer: Dave Hansen <dave.hansen(a)linux.intel.com> CommitterDate: Tue, 15 Oct 2024 05:45:18 -07:00 x86/apic: Always explicitly disarm TSC-deadline timer New processors have become pickier about the local APIC timer state before entering low power modes. These low power modes are used (for example) when you close your laptop lid and suspend. If you put your laptop in a bag and it is not in this low power mode, it is likely to get quite toasty while it quickly sucks the battery dry. The problem boils down to some CPUs' inability to power down until the CPU recognizes that the local APIC timer is shut down. The current kernel code works in one-shot and periodic modes but does not work for deadline mode. Deadline mode has been the supported and preferred mode on Intel CPUs for over a decade and uses an MSR to drive the timer instead of an APIC register. Disable the TSC Deadline timer in lapic_timer_shutdown() by writing to MSR_IA32_TSC_DEADLINE when in TSC-deadline mode. Also avoid writing to the initial-count register (APIC_TMICT) which is ignored in TSC-deadline mode. Note: The APIC_LVTT|=APIC_LVT_MASKED operation should theoretically be enough to tell the hardware that the timer will not fire in any of the timer modes. But mitigating AMD erratum 411[1] also requires clearing out APIC_TMICT. Solely setting APIC_LVT_MASKED is also ineffective in practice on Intel Lunar Lake systems, which is the motivation for this change. 1. 411 Processor May Exit Message-Triggered C1E State Without an Interrupt if Local APIC Timer Reaches Zero - https://www.amd.com/content/dam/amd/en/documents/archived-tech-docs/revisio… Fixes: 279f1461432c ("x86: apic: Use tsc deadline for oneshot when available") Suggested-by: Dave Hansen <dave.hansen(a)intel.com> Signed-off-by: Zhang Rui <rui.zhang(a)intel.com> Signed-off-by: Dave Hansen <dave.hansen(a)linux.intel.com> Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> Tested-by: Srinivas Pandruvada <srinivas.pandruvada(a)linux.intel.com> Tested-by: Todd Brandt <todd.e.brandt(a)intel.com> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/all/20241015061522.25288-1-rui.zhang%40intel.com --- arch/x86/kernel/apic/apic.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 6513c53..c5fb28e 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -440,7 +440,19 @@ static int lapic_timer_shutdown(struct clock_event_device *evt) v = apic_read(APIC_LVTT); v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR); apic_write(APIC_LVTT, v); - apic_write(APIC_TMICT, 0); + + /* + * Setting APIC_LVT_MASKED (above) should be enough to tell + * the hardware that this timer will never fire. But AMD + * erratum 411 and some Intel CPU behavior circa 2024 say + * otherwise. Time for belt and suspenders programming: mask + * the timer _and_ zero the counter registers: + */ + if (v & APIC_LVT_TIMER_TSCDEADLINE) + wrmsrl(MSR_IA32_TSC_DEADLINE, 0); + else + apic_write(APIC_TMICT, 0); + return 0; }

6 months, 1 week

1
0
0 0

+ fork-only-invoke-khugepaged-ksm-hooks-if-no-error.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: fork: only invoke khugepaged, ksm hooks if no error has been added to the -mm mm-hotfixes-unstable branch. Its filename is fork-only-invoke-khugepaged-ksm-hooks-if-no-error.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Subject: fork: only invoke khugepaged, ksm hooks if no error Date: Tue, 15 Oct 2024 18:56:06 +0100 There is no reason to invoke these hooks early against an mm that is in an incomplete state. The change in commit d24062914837 ("fork: use __mt_dup() to duplicate maple tree in dup_mmap()") makes this more pertinent as we may be in a state where entries in the maple tree are not yet consistent. Their placement early in dup_mmap() only appears to have been meaningful for early error checking, and since functionally it'd require a very small allocation to fail (in practice 'too small to fail') that'd only occur in the most dire circumstances, meaning the fork would fail or be OOM'd in any case. Since both khugepaged and KSM tracking are there to provide optimisations to memory performance rather than critical functionality, it doesn't really matter all that much if, under such dire memory pressure, we fail to register an mm with these. As a result, we follow the example of commit d2081b2bf819 ("mm: khugepaged: make khugepaged_enter() void function") and make ksm_fork() a void function also. We only expose the mm to these functions once we are done with them and only if no error occurred in the fork operation. Link: https://lkml.kernel.org/r/e0cb8b840c9d1d5a6e84d4f8eff5f3f2022aa10c.17290143… Fixes: d24062914837 ("fork: use __mt_dup() to duplicate maple tree in dup_mmap()") Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Reported-by: Jann Horn <jannh(a)google.com> Reviewed-by: Liam R. Howlett <Liam.Howlett(a)Oracle.com> Reviewed-by: Vlastimil Babka <vbabka(a)suse.cz> Reviewed-by: Jann Horn <jannh(a)google.com> Cc: Alexander Viro <viro(a)zeniv.linux.org.uk> Cc: Christian Brauner <brauner(a)kernel.org> Cc: Jan Kara <jack(a)suse.cz> Cc: Linus Torvalds <torvalds(a)linuxfoundation.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/ksm.h | 10 ++++------ kernel/fork.c | 7 ++----- 2 files changed, 6 insertions(+), 11 deletions(-) --- a/include/linux/ksm.h~fork-only-invoke-khugepaged-ksm-hooks-if-no-error +++ a/include/linux/ksm.h @@ -54,12 +54,11 @@ static inline long mm_ksm_zero_pages(str return atomic_long_read(&mm->ksm_zero_pages); } -static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) +static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { + /* Adding mm to ksm is best effort on fork. */ if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) - return __ksm_enter(mm); - - return 0; + __ksm_enter(mm); } static inline int ksm_execve(struct mm_struct *mm) @@ -107,9 +106,8 @@ static inline int ksm_disable(struct mm_ return 0; } -static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) +static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { - return 0; } static inline int ksm_execve(struct mm_struct *mm) --- a/kernel/fork.c~fork-only-invoke-khugepaged-ksm-hooks-if-no-error +++ a/kernel/fork.c @@ -653,11 +653,6 @@ static __latent_entropy int dup_mmap(str mm->exec_vm = oldmm->exec_vm; mm->stack_vm = oldmm->stack_vm; - retval = ksm_fork(mm, oldmm); - if (retval) - goto out; - khugepaged_fork(mm, oldmm); - /* Use __mt_dup() to efficiently build an identical maple tree. */ retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL); if (unlikely(retval)) @@ -760,6 +755,8 @@ loop_out: vma_iter_free(&vmi); if (!retval) { mt_set_in_rcu(vmi.mas.tree); + ksm_fork(mm, oldmm); + khugepaged_fork(mm, oldmm); } else if (mpnt) { /* * The entire maple tree has already been duplicated. If the _ Patches currently in -mm which might be from lorenzo.stoakes(a)oracle.com are mm-mmap-correct-error-handling-in-mmap_region.patch maple_tree-correct-tree-corruption-on-spanning-store.patch maple_tree-add-regression-test-for-spanning-store-bug.patch maintainers-add-memory-mapping-vma-co-maintainers.patch fork-do-not-invoke-uffd-on-fork-if-error-occurs.patch fork-only-invoke-khugepaged-ksm-hooks-if-no-error.patch selftests-mm-add-pkey_sighandler_xx-hugetlb_dio-to-gitignore.patch mm-refactor-mm_access-to-not-return-null.patch mm-refactor-mm_access-to-not-return-null-fix.patch mm-madvise-unrestrict-process_madvise-for-current-process.patch maple_tree-do-not-hash-pointers-on-dump-in-debug-mode.patch

6 months, 1 week

1
0
0 0

+ fork-do-not-invoke-uffd-on-fork-if-error-occurs.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: fork: do not invoke uffd on fork if error occurs has been added to the -mm mm-hotfixes-unstable branch. Its filename is fork-do-not-invoke-uffd-on-fork-if-error-occurs.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Subject: fork: do not invoke uffd on fork if error occurs Date: Tue, 15 Oct 2024 18:56:05 +0100 Patch series "fork: do not expose incomplete mm on fork". During fork we may place the virtual memory address space into an inconsistent state before the fork operation is complete. In addition, we may encounter an error during the fork operation that indicates that the virtual memory address space is invalidated. As a result, we should not be exposing it in any way to external machinery that might interact with the mm or VMAs, machinery that is not designed to deal with incomplete state. We specifically update the fork logic to defer khugepaged and ksm to the end of the operation and only to be invoked if no error arose, and disallow uffd from observing fork events should an error have occurred. This patch (of 2): Currently on fork we expose the virtual address space of a process to userland unconditionally if uffd is registered in VMAs, regardless of whether an error arose in the fork. This is performed in dup_userfaultfd_complete() which is invoked unconditionally, and performs two duties - invoking registered handlers for the UFFD_EVENT_FORK event via dup_fctx(), and clearing down userfaultfd_fork_ctx objects established in dup_userfaultfd(). This is problematic, because the virtual address space may not yet be correctly initialised if an error arose. The change in commit d24062914837 ("fork: use __mt_dup() to duplicate maple tree in dup_mmap()") makes this more pertinent as we may be in a state where entries in the maple tree are not yet consistent. We address this by, on fork error, ensuring that we roll back state that we would otherwise expect to clean up through the event being handled by userland and perform the memory freeing duty otherwise performed by dup_userfaultfd_complete(). We do this by implementing a new function, dup_userfaultfd_fail(), which performs the same loop, only decrementing reference counts. Note that we perform mmgrab() on the parent and child mm's, however userfaultfd_ctx_put() will mmdrop() this once the reference count drops to zero, so we will avoid memory leaks correctly here. Link: https://lkml.kernel.org/r/cover.1729014377.git.lorenzo.stoakes@oracle.com Link: https://lkml.kernel.org/r/d3691d58bb58712b6fb3df2be441d175bd3cdf07.17290143… Fixes: d24062914837 ("fork: use __mt_dup() to duplicate maple tree in dup_mmap()") Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Reported-by: Jann Horn <jannh(a)google.com> Reviewed-by: Jann Horn <jannh(a)google.com> Reviewed-by: Liam R. Howlett <Liam.Howlett(a)Oracle.com> Cc: Alexander Viro <viro(a)zeniv.linux.org.uk> Cc: Christian Brauner <brauner(a)kernel.org> Cc: Jan Kara <jack(a)suse.cz> Cc: Linus Torvalds <torvalds(a)linuxfoundation.org> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/userfaultfd.c | 28 ++++++++++++++++++++++++++++ include/linux/userfaultfd_k.h | 5 +++++ kernel/fork.c | 5 ++++- 3 files changed, 37 insertions(+), 1 deletion(-) --- a/fs/userfaultfd.c~fork-do-not-invoke-uffd-on-fork-if-error-occurs +++ a/fs/userfaultfd.c @@ -692,6 +692,34 @@ void dup_userfaultfd_complete(struct lis } } +void dup_userfaultfd_fail(struct list_head *fcs) +{ + struct userfaultfd_fork_ctx *fctx, *n; + + /* + * An error has occurred on fork, we will tear memory down, but have + * allocated memory for fctx's and raised reference counts for both the + * original and child contexts (and on the mm for each as a result). + * + * These would ordinarily be taken care of by a user handling the event, + * but we are no longer doing so, so manually clean up here. + * + * mm tear down will take care of cleaning up VMA contexts. + */ + list_for_each_entry_safe(fctx, n, fcs, list) { + struct userfaultfd_ctx *octx = fctx->orig; + struct userfaultfd_ctx *ctx = fctx->new; + + atomic_dec(&octx->mmap_changing); + VM_BUG_ON(atomic_read(&octx->mmap_changing) < 0); + userfaultfd_ctx_put(octx); + userfaultfd_ctx_put(ctx); + + list_del(&fctx->list); + kfree(fctx); + } +} + void mremap_userfaultfd_prep(struct vm_area_struct *vma, struct vm_userfaultfd_ctx *vm_ctx) { --- a/include/linux/userfaultfd_k.h~fork-do-not-invoke-uffd-on-fork-if-error-occurs +++ a/include/linux/userfaultfd_k.h @@ -249,6 +249,7 @@ static inline bool vma_can_userfault(str extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); extern void dup_userfaultfd_complete(struct list_head *); +void dup_userfaultfd_fail(struct list_head *); extern void mremap_userfaultfd_prep(struct vm_area_struct *, struct vm_userfaultfd_ctx *); @@ -351,6 +352,10 @@ static inline void dup_userfaultfd_compl { } +static inline void dup_userfaultfd_fail(struct list_head *l) +{ +} + static inline void mremap_userfaultfd_prep(struct vm_area_struct *vma, struct vm_userfaultfd_ctx *ctx) { --- a/kernel/fork.c~fork-do-not-invoke-uffd-on-fork-if-error-occurs +++ a/kernel/fork.c @@ -775,7 +775,10 @@ out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); mmap_write_unlock(oldmm); - dup_userfaultfd_complete(&uf); + if (!retval) + dup_userfaultfd_complete(&uf); + else + dup_userfaultfd_fail(&uf); fail_uprobe_end: uprobe_end_dup_mmap(); return retval; _ Patches currently in -mm which might be from lorenzo.stoakes(a)oracle.com are mm-mmap-correct-error-handling-in-mmap_region.patch maple_tree-correct-tree-corruption-on-spanning-store.patch maple_tree-add-regression-test-for-spanning-store-bug.patch maintainers-add-memory-mapping-vma-co-maintainers.patch fork-do-not-invoke-uffd-on-fork-if-error-occurs.patch fork-only-invoke-khugepaged-ksm-hooks-if-no-error.patch selftests-mm-add-pkey_sighandler_xx-hugetlb_dio-to-gitignore.patch mm-refactor-mm_access-to-not-return-null.patch mm-refactor-mm_access-to-not-return-null-fix.patch mm-madvise-unrestrict-process_madvise-for-current-process.patch maple_tree-do-not-hash-pointers-on-dump-in-debug-mode.patch

6 months, 1 week

1
0
0 0

+ nilfs2-fix-kernel-bug-due-to-missing-clearing-of-buffer-delay-flag.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: nilfs2: fix kernel bug due to missing clearing of buffer delay flag has been added to the -mm mm-hotfixes-unstable branch. Its filename is nilfs2-fix-kernel-bug-due-to-missing-clearing-of-buffer-delay-flag.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Subject: nilfs2: fix kernel bug due to missing clearing of buffer delay flag Date: Wed, 16 Oct 2024 06:32:07 +0900 Syzbot reported that after nilfs2 reads a corrupted file system image and degrades to read-only, the BUG_ON check for the buffer delay flag in submit_bh_wbc() may fail, causing a kernel bug. This is because the buffer delay flag is not cleared when clearing the buffer state flags to discard a page/folio or a buffer head. So, fix this. This became necessary when the use of nilfs2's own page clear routine was expanded. This state inconsistency does not occur if the buffer is written normally by log writing. Link: https://lkml.kernel.org/r/20241015213300.7114-1-konishi.ryusuke@gmail.com Fixes: 8c26c4e2694a ("nilfs2: fix issue with flush kernel thread after remount in RO mode because of driver's internal error or metadata corruption") Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: syzbot+985ada84bf055a575c07(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=985ada84bf055a575c07 Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/nilfs2/page.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) --- a/fs/nilfs2/page.c~nilfs2-fix-kernel-bug-due-to-missing-clearing-of-buffer-delay-flag +++ a/fs/nilfs2/page.c @@ -77,7 +77,8 @@ void nilfs_forget_buffer(struct buffer_h const unsigned long clear_bits = (BIT(BH_Uptodate) | BIT(BH_Dirty) | BIT(BH_Mapped) | BIT(BH_Async_Write) | BIT(BH_NILFS_Volatile) | - BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected)); + BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected) | + BIT(BH_Delay)); lock_buffer(bh); set_mask_bits(&bh->b_state, clear_bits, 0); @@ -406,7 +407,8 @@ void nilfs_clear_folio_dirty(struct foli const unsigned long clear_bits = (BIT(BH_Uptodate) | BIT(BH_Dirty) | BIT(BH_Mapped) | BIT(BH_Async_Write) | BIT(BH_NILFS_Volatile) | - BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected)); + BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected) | + BIT(BH_Delay)); bh = head; do { _ Patches currently in -mm which might be from konishi.ryusuke(a)gmail.com are nilfs2-propagate-directory-read-errors-from-nilfs_find_entry.patch nilfs2-fix-kernel-bug-due-to-missing-clearing-of-buffer-delay-flag.patch

6 months, 1 week

1
0
0 0

Re: [PATCH 5.15 000/691] 5.15.168-rc1 review

by Richard Narron

Builds and runs fine on x86_64 and x86 (Slackware 15.0) Richard Narron

6 months, 1 week

1
0
0 0

[PATCH v6 4/5] tpm: Allocate chip->auth in tpm2_start_auth_session()

by Jarkko Sakkinen

Move allocation of chip->auth to tpm2_start_auth_session() so that the field can be used as flag to tell whether auth session is active or not. Cc: stable(a)vger.kernel.org # v6.10+ Fixes: 699e3efd6c64 ("tpm: Add HMAC session start and end functions") Signed-off-by: Jarkko Sakkinen <jarkko(a)kernel.org> --- v5: - No changes. v4: - Change to bug. v3: - No changes. v2: - A new patch. --- drivers/char/tpm/tpm2-sessions.c | 43 +++++++++++++++++++------------- 1 file changed, 25 insertions(+), 18 deletions(-) diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c index 9ffd3da35d21..78d344607b53 100644 --- a/drivers/char/tpm/tpm2-sessions.c +++ b/drivers/char/tpm/tpm2-sessions.c @@ -484,7 +484,8 @@ static void tpm2_KDFe(u8 z[EC_PT_SZ], const char *str, u8 *pt_u, u8 *pt_v, sha256_final(&sctx, out); } -static void tpm_buf_append_salt(struct tpm_buf *buf, struct tpm_chip *chip) +static void tpm_buf_append_salt(struct tpm_buf *buf, struct tpm_chip *chip, + struct tpm2_auth *auth) { struct crypto_kpp *kpp; struct kpp_request *req; @@ -543,7 +544,7 @@ static void tpm_buf_append_salt(struct tpm_buf *buf, struct tpm_chip *chip) sg_set_buf(&s[0], chip->null_ec_key_x, EC_PT_SZ); sg_set_buf(&s[1], chip->null_ec_key_y, EC_PT_SZ); kpp_request_set_input(req, s, EC_PT_SZ*2); - sg_init_one(d, chip->auth->salt, EC_PT_SZ); + sg_init_one(d, auth->salt, EC_PT_SZ); kpp_request_set_output(req, d, EC_PT_SZ); crypto_kpp_compute_shared_secret(req); kpp_request_free(req); @@ -554,8 +555,7 @@ static void tpm_buf_append_salt(struct tpm_buf *buf, struct tpm_chip *chip) * This works because KDFe fully consumes the secret before it * writes the salt */ - tpm2_KDFe(chip->auth->salt, "SECRET", x, chip->null_ec_key_x, - chip->auth->salt); + tpm2_KDFe(auth->salt, "SECRET", x, chip->null_ec_key_x, auth->salt); out: crypto_free_kpp(kpp); @@ -854,6 +854,8 @@ int tpm_buf_check_hmac_response(struct tpm_chip *chip, struct tpm_buf *buf, /* manually close the session if it wasn't consumed */ tpm2_flush_context(chip, auth->handle); memzero_explicit(auth, sizeof(*auth)); + kfree(auth); + chip->auth = NULL; } else { /* reset for next use */ auth->session = TPM_HEADER_SIZE; @@ -882,6 +884,8 @@ void tpm2_end_auth_session(struct tpm_chip *chip) tpm2_flush_context(chip, auth->handle); memzero_explicit(auth, sizeof(*auth)); + kfree(auth); + chip->auth = NULL; } EXPORT_SYMBOL(tpm2_end_auth_session); @@ -970,25 +974,29 @@ static int tpm2_load_null(struct tpm_chip *chip, u32 *null_key) */ int tpm2_start_auth_session(struct tpm_chip *chip) { + struct tpm2_auth *auth; struct tpm_buf buf; - struct tpm2_auth *auth = chip->auth; - int rc; u32 null_key; + int rc; - if (!auth) { - dev_warn_once(&chip->dev, "auth session is not active\n"); + if (chip->auth) { + dev_warn_once(&chip->dev, "auth session is active\n"); return 0; } + auth = kzalloc(sizeof(*auth), GFP_KERNEL); + if (!auth) + return -ENOMEM; + rc = tpm2_load_null(chip, &null_key); if (rc) - goto out; + goto err; auth->session = TPM_HEADER_SIZE; rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_START_AUTH_SESS); if (rc) - goto out; + goto err; /* salt key handle */ tpm_buf_append_u32(&buf, null_key); @@ -1000,7 +1008,7 @@ int tpm2_start_auth_session(struct tpm_chip *chip) tpm_buf_append(&buf, auth->our_nonce, sizeof(auth->our_nonce)); /* append encrypted salt and squirrel away unencrypted in auth */ - tpm_buf_append_salt(&buf, chip); + tpm_buf_append_salt(&buf, chip, auth); /* session type (HMAC, audit or policy) */ tpm_buf_append_u8(&buf, TPM2_SE_HMAC); @@ -1021,10 +1029,13 @@ int tpm2_start_auth_session(struct tpm_chip *chip) tpm_buf_destroy(&buf); - if (rc) - goto out; + if (rc == TPM2_RC_SUCCESS) { + chip->auth = auth; + return 0; + } - out: +err: + kfree(auth); return rc; } EXPORT_SYMBOL(tpm2_start_auth_session); @@ -1375,10 +1386,6 @@ int tpm2_sessions_init(struct tpm_chip *chip) if (rc) return rc; - chip->auth = kmalloc(sizeof(*chip->auth), GFP_KERNEL); - if (!chip->auth) - return -ENOMEM; - return rc; } EXPORT_SYMBOL(tpm2_sessions_init); -- 2.47.0

6 months, 1 week

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror October 2024