April 2025 - Linux-stable-mirror

FAILED: patch "[PATCH] x86/tdx: Fix arch_safe_halt() execution for TDX VMs" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 9f98a4f4e7216dbe366010b4cdcab6b220f229c4 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025040845-quantum-situation-f9b0@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 9f98a4f4e7216dbe366010b4cdcab6b220f229c4 Mon Sep 17 00:00:00 2001 From: Vishal Annapurve <vannapurve(a)google.com> Date: Fri, 28 Feb 2025 01:44:15 +0000 Subject: [PATCH] x86/tdx: Fix arch_safe_halt() execution for TDX VMs Direct HLT instruction execution causes #VEs for TDX VMs which is routed to hypervisor via TDCALL. If HLT is executed in STI-shadow, resulting #VE handler will enable interrupts before TDCALL is routed to hypervisor leading to missed wakeup events, as current TDX spec doesn't expose interruptibility state information to allow #VE handler to selectively enable interrupts. Commit bfe6ed0c6727 ("x86/tdx: Add HLT support for TDX guests") prevented the idle routines from executing HLT instruction in STI-shadow. But it missed the paravirt routine which can be reached via this path as an example: kvm_wait() => safe_halt() => raw_safe_halt() => arch_safe_halt() => irq.safe_halt() => pv_native_safe_halt() To reliably handle arch_safe_halt() for TDX VMs, introduce explicit dependency on CONFIG_PARAVIRT and override paravirt halt()/safe_halt() routines with TDX-safe versions that execute direct TDCALL and needed interrupt flag updates. Executing direct TDCALL brings in additional benefit of avoiding HLT related #VEs altogether. As tested by Ryan Afranji: "Tested with the specjbb2015 benchmark. It has heavy lock contention which leads to many halt calls. TDX VMs suffered a poor score before this patchset. Verified the major performance improvement with this patchset applied." Fixes: bfe6ed0c6727 ("x86/tdx: Add HLT support for TDX guests") Signed-off-by: Vishal Annapurve <vannapurve(a)google.com> Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Reviewed-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> Tested-by: Ryan Afranji <afranji(a)google.com> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Brian Gerst <brgerst(a)gmail.com> Cc: Juergen Gross <jgross(a)suse.com> Cc: H. Peter Anvin <hpa(a)zytor.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/r/20250228014416.3925664-3-vannapurve@google.com diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 05b4eca156cf..f614c0522a0b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -878,6 +878,7 @@ config INTEL_TDX_GUEST depends on X86_64 && CPU_SUP_INTEL depends on X86_X2APIC depends on EFI_STUB + depends on PARAVIRT select ARCH_HAS_CC_PLATFORM select X86_MEM_ENCRYPT select X86_MCE diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index 7772b01ab738..aa0eb4057226 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -14,6 +14,7 @@ #include <asm/ia32.h> #include <asm/insn.h> #include <asm/insn-eval.h> +#include <asm/paravirt_types.h> #include <asm/pgtable.h> #include <asm/set_memory.h> #include <asm/traps.h> @@ -398,7 +399,7 @@ static int handle_halt(struct ve_info *ve) return ve_instr_len(ve); } -void __cpuidle tdx_safe_halt(void) +void __cpuidle tdx_halt(void) { const bool irq_disabled = false; @@ -409,6 +410,16 @@ void __cpuidle tdx_safe_halt(void) WARN_ONCE(1, "HLT instruction emulation failed\n"); } +static void __cpuidle tdx_safe_halt(void) +{ + tdx_halt(); + /* + * "__cpuidle" section doesn't support instrumentation, so stick + * with raw_* variant that avoids tracing hooks. + */ + raw_local_irq_enable(); +} + static int read_msr(struct pt_regs *regs, struct ve_info *ve) { struct tdx_module_args args = { @@ -1109,6 +1120,19 @@ void __init tdx_early_init(void) x86_platform.guest.enc_kexec_begin = tdx_kexec_begin; x86_platform.guest.enc_kexec_finish = tdx_kexec_finish; + /* + * Avoid "sti;hlt" execution in TDX guests as HLT induces a #VE that + * will enable interrupts before HLT TDCALL invocation if executed + * in STI-shadow, possibly resulting in missed wakeup events. + * + * Modify all possible HLT execution paths to use TDX specific routines + * that directly execute TDCALL and toggle the interrupt state as + * needed after TDCALL completion. This also reduces HLT related #VEs + * in addition to having a reliable halt logic execution. + */ + pv_ops.irq.safe_halt = tdx_safe_halt; + pv_ops.irq.halt = tdx_halt; + /* * TDX intercepts the RDMSR to read the X2APIC ID in the parallel * bringup low level code. That raises #VE which cannot be handled diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h index 65394aa9b49f..4a1922ec80cf 100644 --- a/arch/x86/include/asm/tdx.h +++ b/arch/x86/include/asm/tdx.h @@ -58,7 +58,7 @@ void tdx_get_ve_info(struct ve_info *ve); bool tdx_handle_virt_exception(struct pt_regs *regs, struct ve_info *ve); -void tdx_safe_halt(void); +void tdx_halt(void); bool tdx_early_handle_ve(struct pt_regs *regs); @@ -72,7 +72,7 @@ void __init tdx_dump_td_ctls(u64 td_ctls); #else static inline void tdx_early_init(void) { }; -static inline void tdx_safe_halt(void) { }; +static inline void tdx_halt(void) { }; static inline bool tdx_early_handle_ve(struct pt_regs *regs) { return false; } diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 91f6ff618852..962c3ce39323 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -939,7 +939,7 @@ void __init select_idle_routine(void) static_call_update(x86_idle, mwait_idle); } else if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) { pr_info("using TDX aware idle routine\n"); - static_call_update(x86_idle, tdx_safe_halt); + static_call_update(x86_idle, tdx_halt); } else { static_call_update(x86_idle, default_idle); }

2 weeks, 6 days

1
0
0 0

FAILED: patch "[PATCH] x86/paravirt: Move halt paravirt calls under CONFIG_PARAVIRT" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 22cc5ca5de52bbfc36a7d4a55323f91fb4492264 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025040828-overreach-yummy-48f0@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 22cc5ca5de52bbfc36a7d4a55323f91fb4492264 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" <kirill.shutemov(a)linux.intel.com> Date: Fri, 28 Feb 2025 01:44:14 +0000 Subject: [PATCH] x86/paravirt: Move halt paravirt calls under CONFIG_PARAVIRT CONFIG_PARAVIRT_XXL is mainly defined/used by XEN PV guests. For other VM guest types, features supported under CONFIG_PARAVIRT are self sufficient. CONFIG_PARAVIRT mainly provides support for TLB flush operations and time related operations. For TDX guest as well, paravirt calls under CONFIG_PARVIRT meets most of its requirement except the need of HLT and SAFE_HLT paravirt calls, which is currently defined under CONFIG_PARAVIRT_XXL. Since enabling CONFIG_PARAVIRT_XXL is too bloated for TDX guest like platforms, move HLT and SAFE_HLT paravirt calls under CONFIG_PARAVIRT. Moving HLT and SAFE_HLT paravirt calls are not fatal and should not break any functionality for current users of CONFIG_PARAVIRT. Fixes: bfe6ed0c6727 ("x86/tdx: Add HLT support for TDX guests") Co-developed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy(a)linux.intel.com> Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy(a)linux.intel.com> Signed-off-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> Signed-off-by: Vishal Annapurve <vannapurve(a)google.com> Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Reviewed-by: Andi Kleen <ak(a)linux.intel.com> Reviewed-by: Tony Luck <tony.luck(a)intel.com> Reviewed-by: Juergen Gross <jgross(a)suse.com> Tested-by: Ryan Afranji <afranji(a)google.com> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Brian Gerst <brgerst(a)gmail.com> Cc: H. Peter Anvin <hpa(a)zytor.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: stable(a)kernel.org Link: https://lore.kernel.org/r/20250228014416.3925664-2-vannapurve@google.com diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index abb8374c9ff7..9a9b21b78905 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -76,6 +76,28 @@ static __always_inline void native_local_irq_restore(unsigned long flags) #endif +#ifndef CONFIG_PARAVIRT +#ifndef __ASSEMBLY__ +/* + * Used in the idle loop; sti takes one instruction cycle + * to complete: + */ +static __always_inline void arch_safe_halt(void) +{ + native_safe_halt(); +} + +/* + * Used when interrupts are already enabled or to + * shutdown the processor: + */ +static __always_inline void halt(void) +{ + native_halt(); +} +#endif /* __ASSEMBLY__ */ +#endif /* CONFIG_PARAVIRT */ + #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else @@ -97,24 +119,6 @@ static __always_inline void arch_local_irq_enable(void) native_irq_enable(); } -/* - * Used in the idle loop; sti takes one instruction cycle - * to complete: - */ -static __always_inline void arch_safe_halt(void) -{ - native_safe_halt(); -} - -/* - * Used when interrupts are already enabled or to - * shutdown the processor: - */ -static __always_inline void halt(void) -{ - native_halt(); -} - /* * For spinlocks, etc: */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index bed346bfac89..c4c23190925c 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -102,6 +102,16 @@ static inline void notify_page_enc_status_changed(unsigned long pfn, PVOP_VCALL3(mmu.notify_page_enc_status_changed, pfn, npages, enc); } +static __always_inline void arch_safe_halt(void) +{ + PVOP_VCALL0(irq.safe_halt); +} + +static inline void halt(void) +{ + PVOP_VCALL0(irq.halt); +} + #ifdef CONFIG_PARAVIRT_XXL static inline void load_sp0(unsigned long sp0) { @@ -165,16 +175,6 @@ static inline void __write_cr4(unsigned long x) PVOP_VCALL1(cpu.write_cr4, x); } -static __always_inline void arch_safe_halt(void) -{ - PVOP_VCALL0(irq.safe_halt); -} - -static inline void halt(void) -{ - PVOP_VCALL0(irq.halt); -} - static inline u64 paravirt_read_msr(unsigned msr) { return PVOP_CALL1(u64, cpu.read_msr, msr); diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 62912023b46f..631c306ce1ff 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -120,10 +120,9 @@ struct pv_irq_ops { struct paravirt_callee_save save_fl; struct paravirt_callee_save irq_disable; struct paravirt_callee_save irq_enable; - +#endif void (*safe_halt)(void); void (*halt)(void); -#endif } __no_randomize_layout; struct pv_mmu_ops { diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 97925632c28e..1ccd05d8999f 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -75,6 +75,11 @@ void paravirt_set_sched_clock(u64 (*func)(void)) static_call_update(pv_sched_clock, func); } +static noinstr void pv_native_safe_halt(void) +{ + native_safe_halt(); +} + #ifdef CONFIG_PARAVIRT_XXL static noinstr void pv_native_write_cr2(unsigned long val) { @@ -100,11 +105,6 @@ static noinstr void pv_native_set_debugreg(int regno, unsigned long val) { native_set_debugreg(regno, val); } - -static noinstr void pv_native_safe_halt(void) -{ - native_safe_halt(); -} #endif struct pv_info pv_info = { @@ -161,9 +161,11 @@ struct paravirt_patch_template pv_ops = { .irq.save_fl = __PV_IS_CALLEE_SAVE(pv_native_save_fl), .irq.irq_disable = __PV_IS_CALLEE_SAVE(pv_native_irq_disable), .irq.irq_enable = __PV_IS_CALLEE_SAVE(pv_native_irq_enable), +#endif /* CONFIG_PARAVIRT_XXL */ + + /* Irq HLT ops. */ .irq.safe_halt = pv_native_safe_halt, .irq.halt = native_halt, -#endif /* CONFIG_PARAVIRT_XXL */ /* Mmu ops. */ .mmu.flush_tlb_user = native_flush_tlb_local,

2 weeks, 6 days

1
0
0 0

FAILED: patch "[PATCH] x86/mce: use is_copy_from_user() to determine copy-from-user" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 1a15bb8303b6b104e78028b6c68f76a0d4562134 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025040811-capable-unblock-8997@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 1a15bb8303b6b104e78028b6c68f76a0d4562134 Mon Sep 17 00:00:00 2001 From: Shuai Xue <xueshuai(a)linux.alibaba.com> Date: Wed, 12 Mar 2025 19:28:50 +0800 Subject: [PATCH] x86/mce: use is_copy_from_user() to determine copy-from-user context Patch series "mm/hwpoison: Fix regressions in memory failure handling", v4. ## 1. What am I trying to do: This patchset resolves two critical regressions related to memory failure handling that have appeared in the upstream kernel since version 5.17, as compared to 5.10 LTS. - copyin case: poison found in user page while kernel copying from user space - instr case: poison found while instruction fetching in user space ## 2. What is the expected outcome and why - For copyin case: Kernel can recover from poison found where kernel is doing get_user() or copy_from_user() if those places get an error return and the kernel return -EFAULT to the process instead of crashing. More specifily, MCE handler checks the fixup handler type to decide whether an in kernel #MC can be recovered. When EX_TYPE_UACCESS is found, the PC jumps to recovery code specified in _ASM_EXTABLE_FAULT() and return a -EFAULT to user space. - For instr case: If a poison found while instruction fetching in user space, full recovery is possible. User process takes #PF, Linux allocates a new page and fills by reading from storage. ## 3. What actually happens and why - For copyin case: kernel panic since v5.17 Commit 4c132d1d844a ("x86/futex: Remove .fixup usage") introduced a new extable fixup type, EX_TYPE_EFAULT_REG, and later patches updated the extable fixup type for copy-from-user operations, changing it from EX_TYPE_UACCESS to EX_TYPE_EFAULT_REG. It breaks previous EX_TYPE_UACCESS handling when posion found in get_user() or copy_from_user(). - For instr case: user process is killed by a SIGBUS signal due to #CMCI and #MCE race When an uncorrected memory error is consumed there is a race between the CMCI from the memory controller reporting an uncorrected error with a UCNA signature, and the core reporting and SRAR signature machine check when the data is about to be consumed. ### Background: why *UN*corrected errors tied to *C*MCI in Intel platform [1] Prior to Icelake memory controllers reported patrol scrub events that detected a previously unseen uncorrected error in memory by signaling a broadcast machine check with an SRAO (Software Recoverable Action Optional) signature in the machine check bank. This was overkill because it's not an urgent problem that no core is on the verge of consuming that bad data. It's also found that multi SRAO UCE may cause nested MCE interrupts and finally become an IERR. Hence, Intel downgrades the machine check bank signature of patrol scrub from SRAO to UCNA (Uncorrected, No Action required), and signal changed to #CMCI. Just to add to the confusion, Linux does take an action (in uc_decode_notifier()) to try to offline the page despite the UC*NA* signature name. ### Background: why #CMCI and #MCE race when poison is consuming in Intel platform [1] Having decided that CMCI/UCNA is the best action for patrol scrub errors, the memory controller uses it for reads too. But the memory controller is executing asynchronously from the core, and can't tell the difference between a "real" read and a speculative read. So it will do CMCI/UCNA if an error is found in any read. Thus: 1) Core is clever and thinks address A is needed soon, issues a speculative read. 2) Core finds it is going to use address A soon after sending the read request 3) The CMCI from the memory controller is in a race with MCE from the core that will soon try to retire the load from address A. Quite often (because speculation has got better) the CMCI from the memory controller is delivered before the core is committed to the instruction reading address A, so the interrupt is taken, and Linux offlines the page (marking it as poison). ## Why user process is killed for instr case Commit 046545a661af ("mm/hwpoison: fix error page recovered but reported "not recovered"") tries to fix noise message "Memory error not recovered" and skips duplicate SIGBUSs due to the race. But it also introduced a bug that kill_accessing_process() return -EHWPOISON for instr case, as result, kill_me_maybe() send a SIGBUS to user process. # 4. The fix, in my opinion, should be: - For copyin case: The key point is whether the error context is in a read from user memory. We do not care about the ex-type if we know its a MOV reading from userspace. is_copy_from_user() return true when both of the following two checks are true: - the current instruction is copy - source address is user memory If copy_user is true, we set m->kflags |= MCE_IN_KERNEL_COPYIN | MCE_IN_KERNEL_RECOV; Then do_machine_check() will try fixup_exception() first. - For instr case: let kill_accessing_process() return 0 to prevent a SIGBUS. - For patch 3: The return value of memory_failure() is quite important while discussed instr case regression with Tony and Miaohe for patch 2, so add comment about the return value. This patch (of 3): Commit 4c132d1d844a ("x86/futex: Remove .fixup usage") introduced a new extable fixup type, EX_TYPE_EFAULT_REG, and commit 4c132d1d844a ("x86/futex: Remove .fixup usage") updated the extable fixup type for copy-from-user operations, changing it from EX_TYPE_UACCESS to EX_TYPE_EFAULT_REG. The error context for copy-from-user operations no longer functions as an in-kernel recovery context. Consequently, the error context for copy-from-user operations no longer functions as an in-kernel recovery context, resulting in kernel panics with the message: "Machine check: Data load in unrecoverable area of kernel." To address this, it is crucial to identify if an error context involves a read operation from user memory. The function is_copy_from_user() can be utilized to determine: - the current operation is copy - when reading user memory When these conditions are met, is_copy_from_user() will return true, confirming that it is indeed a direct copy from user memory. This check is essential for correctly handling the context of errors in these operations without relying on the extable fixup types that previously allowed for in-kernel recovery. So, use is_copy_from_user() to determine if a context is copy user directly. Link: https://lkml.kernel.org/r/20250312112852.82415-1-xueshuai@linux.alibaba.com Link: https://lkml.kernel.org/r/20250312112852.82415-2-xueshuai@linux.alibaba.com Fixes: 4c132d1d844a ("x86/futex: Remove .fixup usage") Signed-off-by: Shuai Xue <xueshuai(a)linux.alibaba.com> Suggested-by: Peter Zijlstra <peterz(a)infradead.org> Acked-by: Borislav Petkov (AMD) <bp(a)alien8.de> Tested-by: Tony Luck <tony.luck(a)intel.com> Cc: Baolin Wang <baolin.wang(a)linux.alibaba.com> Cc: Borislav Betkov <bp(a)alien8.de> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Josh Poimboeuf <jpoimboe(a)kernel.org> Cc: Miaohe Lin <linmiaohe(a)huawei.com> Cc: Naoya Horiguchi <nao.horiguchi(a)gmail.com> Cc: Ruidong Tian <tianruidong(a)linux.alibaba.com> Cc: Thomas Gleinxer <tglx(a)linutronix.de> Cc: Yazen Ghannam <yazen.ghannam(a)amd.com> Cc: Jane Chu <jane.chu(a)oracle.com> Cc: Jarkko Sakkinen <jarkko(a)kernel.org> Cc: Jonathan Cameron <Jonathan.Cameron(a)huawei.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index dac4d64dfb2a..2235a7477436 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -300,13 +300,12 @@ static noinstr int error_context(struct mce *m, struct pt_regs *regs) copy_user = is_copy_from_user(regs); instrumentation_end(); - switch (fixup_type) { - case EX_TYPE_UACCESS: - if (!copy_user) - return IN_KERNEL; - m->kflags |= MCE_IN_KERNEL_COPYIN; - fallthrough; + if (copy_user) { + m->kflags |= MCE_IN_KERNEL_COPYIN | MCE_IN_KERNEL_RECOV; + return IN_KERNEL_RECOV; + } + switch (fixup_type) { case EX_TYPE_FAULT_MCE_SAFE: case EX_TYPE_DEFAULT_MCE_SAFE: m->kflags |= MCE_IN_KERNEL_RECOV;

2 weeks, 6 days

1
0
0 0

FAILED: patch "[PATCH] x86/mce: use is_copy_from_user() to determine copy-from-user" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 1a15bb8303b6b104e78028b6c68f76a0d4562134 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025040808-ammonia-petal-1583@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 1a15bb8303b6b104e78028b6c68f76a0d4562134 Mon Sep 17 00:00:00 2001 From: Shuai Xue <xueshuai(a)linux.alibaba.com> Date: Wed, 12 Mar 2025 19:28:50 +0800 Subject: [PATCH] x86/mce: use is_copy_from_user() to determine copy-from-user context Patch series "mm/hwpoison: Fix regressions in memory failure handling", v4. ## 1. What am I trying to do: This patchset resolves two critical regressions related to memory failure handling that have appeared in the upstream kernel since version 5.17, as compared to 5.10 LTS. - copyin case: poison found in user page while kernel copying from user space - instr case: poison found while instruction fetching in user space ## 2. What is the expected outcome and why - For copyin case: Kernel can recover from poison found where kernel is doing get_user() or copy_from_user() if those places get an error return and the kernel return -EFAULT to the process instead of crashing. More specifily, MCE handler checks the fixup handler type to decide whether an in kernel #MC can be recovered. When EX_TYPE_UACCESS is found, the PC jumps to recovery code specified in _ASM_EXTABLE_FAULT() and return a -EFAULT to user space. - For instr case: If a poison found while instruction fetching in user space, full recovery is possible. User process takes #PF, Linux allocates a new page and fills by reading from storage. ## 3. What actually happens and why - For copyin case: kernel panic since v5.17 Commit 4c132d1d844a ("x86/futex: Remove .fixup usage") introduced a new extable fixup type, EX_TYPE_EFAULT_REG, and later patches updated the extable fixup type for copy-from-user operations, changing it from EX_TYPE_UACCESS to EX_TYPE_EFAULT_REG. It breaks previous EX_TYPE_UACCESS handling when posion found in get_user() or copy_from_user(). - For instr case: user process is killed by a SIGBUS signal due to #CMCI and #MCE race When an uncorrected memory error is consumed there is a race between the CMCI from the memory controller reporting an uncorrected error with a UCNA signature, and the core reporting and SRAR signature machine check when the data is about to be consumed. ### Background: why *UN*corrected errors tied to *C*MCI in Intel platform [1] Prior to Icelake memory controllers reported patrol scrub events that detected a previously unseen uncorrected error in memory by signaling a broadcast machine check with an SRAO (Software Recoverable Action Optional) signature in the machine check bank. This was overkill because it's not an urgent problem that no core is on the verge of consuming that bad data. It's also found that multi SRAO UCE may cause nested MCE interrupts and finally become an IERR. Hence, Intel downgrades the machine check bank signature of patrol scrub from SRAO to UCNA (Uncorrected, No Action required), and signal changed to #CMCI. Just to add to the confusion, Linux does take an action (in uc_decode_notifier()) to try to offline the page despite the UC*NA* signature name. ### Background: why #CMCI and #MCE race when poison is consuming in Intel platform [1] Having decided that CMCI/UCNA is the best action for patrol scrub errors, the memory controller uses it for reads too. But the memory controller is executing asynchronously from the core, and can't tell the difference between a "real" read and a speculative read. So it will do CMCI/UCNA if an error is found in any read. Thus: 1) Core is clever and thinks address A is needed soon, issues a speculative read. 2) Core finds it is going to use address A soon after sending the read request 3) The CMCI from the memory controller is in a race with MCE from the core that will soon try to retire the load from address A. Quite often (because speculation has got better) the CMCI from the memory controller is delivered before the core is committed to the instruction reading address A, so the interrupt is taken, and Linux offlines the page (marking it as poison). ## Why user process is killed for instr case Commit 046545a661af ("mm/hwpoison: fix error page recovered but reported "not recovered"") tries to fix noise message "Memory error not recovered" and skips duplicate SIGBUSs due to the race. But it also introduced a bug that kill_accessing_process() return -EHWPOISON for instr case, as result, kill_me_maybe() send a SIGBUS to user process. # 4. The fix, in my opinion, should be: - For copyin case: The key point is whether the error context is in a read from user memory. We do not care about the ex-type if we know its a MOV reading from userspace. is_copy_from_user() return true when both of the following two checks are true: - the current instruction is copy - source address is user memory If copy_user is true, we set m->kflags |= MCE_IN_KERNEL_COPYIN | MCE_IN_KERNEL_RECOV; Then do_machine_check() will try fixup_exception() first. - For instr case: let kill_accessing_process() return 0 to prevent a SIGBUS. - For patch 3: The return value of memory_failure() is quite important while discussed instr case regression with Tony and Miaohe for patch 2, so add comment about the return value. This patch (of 3): Commit 4c132d1d844a ("x86/futex: Remove .fixup usage") introduced a new extable fixup type, EX_TYPE_EFAULT_REG, and commit 4c132d1d844a ("x86/futex: Remove .fixup usage") updated the extable fixup type for copy-from-user operations, changing it from EX_TYPE_UACCESS to EX_TYPE_EFAULT_REG. The error context for copy-from-user operations no longer functions as an in-kernel recovery context. Consequently, the error context for copy-from-user operations no longer functions as an in-kernel recovery context, resulting in kernel panics with the message: "Machine check: Data load in unrecoverable area of kernel." To address this, it is crucial to identify if an error context involves a read operation from user memory. The function is_copy_from_user() can be utilized to determine: - the current operation is copy - when reading user memory When these conditions are met, is_copy_from_user() will return true, confirming that it is indeed a direct copy from user memory. This check is essential for correctly handling the context of errors in these operations without relying on the extable fixup types that previously allowed for in-kernel recovery. So, use is_copy_from_user() to determine if a context is copy user directly. Link: https://lkml.kernel.org/r/20250312112852.82415-1-xueshuai@linux.alibaba.com Link: https://lkml.kernel.org/r/20250312112852.82415-2-xueshuai@linux.alibaba.com Fixes: 4c132d1d844a ("x86/futex: Remove .fixup usage") Signed-off-by: Shuai Xue <xueshuai(a)linux.alibaba.com> Suggested-by: Peter Zijlstra <peterz(a)infradead.org> Acked-by: Borislav Petkov (AMD) <bp(a)alien8.de> Tested-by: Tony Luck <tony.luck(a)intel.com> Cc: Baolin Wang <baolin.wang(a)linux.alibaba.com> Cc: Borislav Betkov <bp(a)alien8.de> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Josh Poimboeuf <jpoimboe(a)kernel.org> Cc: Miaohe Lin <linmiaohe(a)huawei.com> Cc: Naoya Horiguchi <nao.horiguchi(a)gmail.com> Cc: Ruidong Tian <tianruidong(a)linux.alibaba.com> Cc: Thomas Gleinxer <tglx(a)linutronix.de> Cc: Yazen Ghannam <yazen.ghannam(a)amd.com> Cc: Jane Chu <jane.chu(a)oracle.com> Cc: Jarkko Sakkinen <jarkko(a)kernel.org> Cc: Jonathan Cameron <Jonathan.Cameron(a)huawei.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index dac4d64dfb2a..2235a7477436 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -300,13 +300,12 @@ static noinstr int error_context(struct mce *m, struct pt_regs *regs) copy_user = is_copy_from_user(regs); instrumentation_end(); - switch (fixup_type) { - case EX_TYPE_UACCESS: - if (!copy_user) - return IN_KERNEL; - m->kflags |= MCE_IN_KERNEL_COPYIN; - fallthrough; + if (copy_user) { + m->kflags |= MCE_IN_KERNEL_COPYIN | MCE_IN_KERNEL_RECOV; + return IN_KERNEL_RECOV; + } + switch (fixup_type) { case EX_TYPE_FAULT_MCE_SAFE: case EX_TYPE_DEFAULT_MCE_SAFE: m->kflags |= MCE_IN_KERNEL_RECOV;

2 weeks, 6 days

1
0
0 0

FAILED: patch "[PATCH] x86/mce: use is_copy_from_user() to determine copy-from-user" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 1a15bb8303b6b104e78028b6c68f76a0d4562134 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025040805-enlisted-regular-7bac@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 1a15bb8303b6b104e78028b6c68f76a0d4562134 Mon Sep 17 00:00:00 2001 From: Shuai Xue <xueshuai(a)linux.alibaba.com> Date: Wed, 12 Mar 2025 19:28:50 +0800 Subject: [PATCH] x86/mce: use is_copy_from_user() to determine copy-from-user context Patch series "mm/hwpoison: Fix regressions in memory failure handling", v4. ## 1. What am I trying to do: This patchset resolves two critical regressions related to memory failure handling that have appeared in the upstream kernel since version 5.17, as compared to 5.10 LTS. - copyin case: poison found in user page while kernel copying from user space - instr case: poison found while instruction fetching in user space ## 2. What is the expected outcome and why - For copyin case: Kernel can recover from poison found where kernel is doing get_user() or copy_from_user() if those places get an error return and the kernel return -EFAULT to the process instead of crashing. More specifily, MCE handler checks the fixup handler type to decide whether an in kernel #MC can be recovered. When EX_TYPE_UACCESS is found, the PC jumps to recovery code specified in _ASM_EXTABLE_FAULT() and return a -EFAULT to user space. - For instr case: If a poison found while instruction fetching in user space, full recovery is possible. User process takes #PF, Linux allocates a new page and fills by reading from storage. ## 3. What actually happens and why - For copyin case: kernel panic since v5.17 Commit 4c132d1d844a ("x86/futex: Remove .fixup usage") introduced a new extable fixup type, EX_TYPE_EFAULT_REG, and later patches updated the extable fixup type for copy-from-user operations, changing it from EX_TYPE_UACCESS to EX_TYPE_EFAULT_REG. It breaks previous EX_TYPE_UACCESS handling when posion found in get_user() or copy_from_user(). - For instr case: user process is killed by a SIGBUS signal due to #CMCI and #MCE race When an uncorrected memory error is consumed there is a race between the CMCI from the memory controller reporting an uncorrected error with a UCNA signature, and the core reporting and SRAR signature machine check when the data is about to be consumed. ### Background: why *UN*corrected errors tied to *C*MCI in Intel platform [1] Prior to Icelake memory controllers reported patrol scrub events that detected a previously unseen uncorrected error in memory by signaling a broadcast machine check with an SRAO (Software Recoverable Action Optional) signature in the machine check bank. This was overkill because it's not an urgent problem that no core is on the verge of consuming that bad data. It's also found that multi SRAO UCE may cause nested MCE interrupts and finally become an IERR. Hence, Intel downgrades the machine check bank signature of patrol scrub from SRAO to UCNA (Uncorrected, No Action required), and signal changed to #CMCI. Just to add to the confusion, Linux does take an action (in uc_decode_notifier()) to try to offline the page despite the UC*NA* signature name. ### Background: why #CMCI and #MCE race when poison is consuming in Intel platform [1] Having decided that CMCI/UCNA is the best action for patrol scrub errors, the memory controller uses it for reads too. But the memory controller is executing asynchronously from the core, and can't tell the difference between a "real" read and a speculative read. So it will do CMCI/UCNA if an error is found in any read. Thus: 1) Core is clever and thinks address A is needed soon, issues a speculative read. 2) Core finds it is going to use address A soon after sending the read request 3) The CMCI from the memory controller is in a race with MCE from the core that will soon try to retire the load from address A. Quite often (because speculation has got better) the CMCI from the memory controller is delivered before the core is committed to the instruction reading address A, so the interrupt is taken, and Linux offlines the page (marking it as poison). ## Why user process is killed for instr case Commit 046545a661af ("mm/hwpoison: fix error page recovered but reported "not recovered"") tries to fix noise message "Memory error not recovered" and skips duplicate SIGBUSs due to the race. But it also introduced a bug that kill_accessing_process() return -EHWPOISON for instr case, as result, kill_me_maybe() send a SIGBUS to user process. # 4. The fix, in my opinion, should be: - For copyin case: The key point is whether the error context is in a read from user memory. We do not care about the ex-type if we know its a MOV reading from userspace. is_copy_from_user() return true when both of the following two checks are true: - the current instruction is copy - source address is user memory If copy_user is true, we set m->kflags |= MCE_IN_KERNEL_COPYIN | MCE_IN_KERNEL_RECOV; Then do_machine_check() will try fixup_exception() first. - For instr case: let kill_accessing_process() return 0 to prevent a SIGBUS. - For patch 3: The return value of memory_failure() is quite important while discussed instr case regression with Tony and Miaohe for patch 2, so add comment about the return value. This patch (of 3): Commit 4c132d1d844a ("x86/futex: Remove .fixup usage") introduced a new extable fixup type, EX_TYPE_EFAULT_REG, and commit 4c132d1d844a ("x86/futex: Remove .fixup usage") updated the extable fixup type for copy-from-user operations, changing it from EX_TYPE_UACCESS to EX_TYPE_EFAULT_REG. The error context for copy-from-user operations no longer functions as an in-kernel recovery context. Consequently, the error context for copy-from-user operations no longer functions as an in-kernel recovery context, resulting in kernel panics with the message: "Machine check: Data load in unrecoverable area of kernel." To address this, it is crucial to identify if an error context involves a read operation from user memory. The function is_copy_from_user() can be utilized to determine: - the current operation is copy - when reading user memory When these conditions are met, is_copy_from_user() will return true, confirming that it is indeed a direct copy from user memory. This check is essential for correctly handling the context of errors in these operations without relying on the extable fixup types that previously allowed for in-kernel recovery. So, use is_copy_from_user() to determine if a context is copy user directly. Link: https://lkml.kernel.org/r/20250312112852.82415-1-xueshuai@linux.alibaba.com Link: https://lkml.kernel.org/r/20250312112852.82415-2-xueshuai@linux.alibaba.com Fixes: 4c132d1d844a ("x86/futex: Remove .fixup usage") Signed-off-by: Shuai Xue <xueshuai(a)linux.alibaba.com> Suggested-by: Peter Zijlstra <peterz(a)infradead.org> Acked-by: Borislav Petkov (AMD) <bp(a)alien8.de> Tested-by: Tony Luck <tony.luck(a)intel.com> Cc: Baolin Wang <baolin.wang(a)linux.alibaba.com> Cc: Borislav Betkov <bp(a)alien8.de> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Josh Poimboeuf <jpoimboe(a)kernel.org> Cc: Miaohe Lin <linmiaohe(a)huawei.com> Cc: Naoya Horiguchi <nao.horiguchi(a)gmail.com> Cc: Ruidong Tian <tianruidong(a)linux.alibaba.com> Cc: Thomas Gleinxer <tglx(a)linutronix.de> Cc: Yazen Ghannam <yazen.ghannam(a)amd.com> Cc: Jane Chu <jane.chu(a)oracle.com> Cc: Jarkko Sakkinen <jarkko(a)kernel.org> Cc: Jonathan Cameron <Jonathan.Cameron(a)huawei.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index dac4d64dfb2a..2235a7477436 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -300,13 +300,12 @@ static noinstr int error_context(struct mce *m, struct pt_regs *regs) copy_user = is_copy_from_user(regs); instrumentation_end(); - switch (fixup_type) { - case EX_TYPE_UACCESS: - if (!copy_user) - return IN_KERNEL; - m->kflags |= MCE_IN_KERNEL_COPYIN; - fallthrough; + if (copy_user) { + m->kflags |= MCE_IN_KERNEL_COPYIN | MCE_IN_KERNEL_RECOV; + return IN_KERNEL_RECOV; + } + switch (fixup_type) { case EX_TYPE_FAULT_MCE_SAFE: case EX_TYPE_DEFAULT_MCE_SAFE: m->kflags |= MCE_IN_KERNEL_RECOV;

2 weeks, 6 days

1
0
0 0

FAILED: patch "[PATCH] LoongArch: BPF: Don't override subprog's return value" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 60f3caff1492e5b8616b9578c4bedb5c0a88ed14 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025040845-repeater-uninvited-9d3b@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 60f3caff1492e5b8616b9578c4bedb5c0a88ed14 Mon Sep 17 00:00:00 2001 From: Hengqi Chen <hengqi.chen(a)gmail.com> Date: Sun, 30 Mar 2025 16:31:09 +0800 Subject: [PATCH] LoongArch: BPF: Don't override subprog's return value The verifier test `calls: div by 0 in subprog` triggers a panic at the ld.bu instruction. The ld.bu insn is trying to load byte from memory address returned by the subprog. The subprog actually set the correct address at the a5 register (dedicated register for BPF return values). But at commit 73c359d1d356 ("LoongArch: BPF: Sign-extend return values") we also sign extended a5 to the a0 register (return value in LoongArch). For function call insn, we later propagate the a0 register back to a5 register. This is right for native calls but wrong for bpf2bpf calls which expect zero-extended return value in a5 register. So only move a0 to a5 for native calls (i.e. non-BPF_PSEUDO_CALL). Cc: stable(a)vger.kernel.org Fixes: 73c359d1d356 ("LoongArch: BPF: Sign-extend return values") Signed-off-by: Hengqi Chen <hengqi.chen(a)gmail.com> Signed-off-by: Huacai Chen <chenhuacai(a)loongson.cn> diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index a06bf89fed67..fa1500d4aa3e 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -907,7 +907,10 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext move_addr(ctx, t1, func_addr); emit_insn(ctx, jirl, LOONGARCH_GPR_RA, t1, 0); - move_reg(ctx, regmap[BPF_REG_0], LOONGARCH_GPR_A0); + + if (insn->src_reg != BPF_PSEUDO_CALL) + move_reg(ctx, regmap[BPF_REG_0], LOONGARCH_GPR_A0); + break; /* tail call */

2 weeks, 6 days

1
0
0 0

Re: Patch "wifi: mac80211: remove debugfs dir for virtual monitor" has been added to the 6.13-stable tree

by Alexander Wetzel

On 4/7/25 17:25, Sasha Levin wrote: > This is a note to let you know that I've just added the patch titled > > wifi: mac80211: remove debugfs dir for virtual monitor > > to the 6.13-stable tree which can be found at: > http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… > > The filename of the patch is: > wifi-mac80211-remove-debugfs-dir-for-virtual-monitor.patch > and it can be found in the queue-6.13 subdirectory. > > If you, or anyone else, feels it should not be added to the stable tree, > please let <stable(a)vger.kernel.org> know about it. > The commit here is causing a sparse warning. Please always add commit 861d0445e72e ("wifi: mac80211: Fix sparse warning for monitor_sdata") when you backport this patch to avoid that. (So far I got the backport notification for 6.12 and 6.13.) It's also no big deal when you decide to not backport this patch. > > > commit 193bafe31a2a08b5631a98ecf148fa0d18e94b0d > Author: Alexander Wetzel <Alexander(a)wetzel-home.de> > Date: Tue Feb 4 17:42:40 2025 +0100 > > wifi: mac80211: remove debugfs dir for virtual monitor > > [ Upstream commit 646262c71aca87bb66945933abe4e620796d6c5a ] > > Don't call ieee80211_debugfs_recreate_netdev() for virtual monitor > interface when deleting it. > > The virtual monitor interface shouldn't have debugfs entries and trying > to update them will *create* them on deletion. > > And when the virtual monitor interface is created/destroyed multiple > times we'll get warnings about debugfs name conflicts. > > Signed-off-by: Alexander Wetzel <Alexander(a)wetzel-home.de> > Link: https://patch.msgid.link/20250204164240.370153-1-Alexander@wetzel-home.de > Signed-off-by: Johannes Berg <johannes.berg(a)intel.com> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > > diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c > index 299d38e9e8630..2fc60e1e77a55 100644 > --- a/net/mac80211/driver-ops.c > +++ b/net/mac80211/driver-ops.c > @@ -116,8 +116,14 @@ void drv_remove_interface(struct ieee80211_local *local, > > sdata->flags &= ~IEEE80211_SDATA_IN_DRIVER; > > - /* Remove driver debugfs entries */ > - ieee80211_debugfs_recreate_netdev(sdata, sdata->vif.valid_links); > + /* > + * Remove driver debugfs entries. > + * The virtual monitor interface doesn't get a debugfs > + * entry, so it's exempt here. > + */ > + if (sdata != local->monitor_sdata) > + ieee80211_debugfs_recreate_netdev(sdata, > + sdata->vif.valid_links); > > trace_drv_remove_interface(local, sdata); > local->ops->remove_interface(&local->hw, &sdata->vif); > diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c > index 806dffa48ef92..04b3626387309 100644 > --- a/net/mac80211/iface.c > +++ b/net/mac80211/iface.c > @@ -1212,16 +1212,17 @@ void ieee80211_del_virtual_monitor(struct ieee80211_local *local) > return; > } > > - RCU_INIT_POINTER(local->monitor_sdata, NULL); > - mutex_unlock(&local->iflist_mtx); > - > - synchronize_net(); > - > + clear_bit(SDATA_STATE_RUNNING, &sdata->state); > ieee80211_link_release_channel(&sdata->deflink); > > if (ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) > drv_remove_interface(local, sdata); > > + RCU_INIT_POINTER(local->monitor_sdata, NULL); > + mutex_unlock(&local->iflist_mtx); > + > + synchronize_net(); > + > kfree(sdata); > } >

2 weeks, 6 days

2
1
0 0

[PATCH v7] staging: rtl8723bs: Add error handling for sd_read()

by Wentao Liang

The sdio_read32() calls sd_read(), but does not handle the error if sd_read() fails. This could lead to subsequent operations processing invalid data. A proper implementation can be found in sdio_readN(), which has an error handling for the sd_read(). Add error handling for the sd_read() to free tmpbuf and return error code if sd_read() fails. This ensure that the memcpy() is only performed when the read operation is successful. Since none of the callers check for the errors, there is no need to return the error code propagated from sd_read(). Returning SDIO_ERR_VAL32 might be a better choice, which is a specialized error code for SDIO. Another problem of returning propagated error code is that the error code is a s32 type value, which is not fit with the u32 type return value of the sdio_read32(). An practical option would be to go through all the callers and add error handling, which need to pass a pointer to u32 *val and return zero on success or negative on failure. It is not a better choice since will cost unnecessary effort on the error code. The other opion is to replace sd_read() by sd_read32(), which return an u32 type error code that can be directly used as the return value of sdio_read32(). But, it is also a bad choice to use sd_read32() in a alignment failed branch. Fixes: 554c0a3abf21 ("staging: Add rtl8723bs sdio wifi driver") Cc: stable(a)vger.kernel.org # v4.12+ Signed-off-by: Wentao Liang <vulab(a)iscas.ac.cn> --- v7: Fix error code and add patch explanation v6: Fix improper code to propagate error code v5: Fix error code v4: Add change log and fix error code v3: Add Cc flag v2: Change code to initialize val drivers/staging/rtl8723bs/hal/sdio_ops.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/staging/rtl8723bs/hal/sdio_ops.c b/drivers/staging/rtl8723bs/hal/sdio_ops.c index 21e9f1858745..d79d41727042 100644 --- a/drivers/staging/rtl8723bs/hal/sdio_ops.c +++ b/drivers/staging/rtl8723bs/hal/sdio_ops.c @@ -185,7 +185,12 @@ static u32 sdio_read32(struct intf_hdl *intfhdl, u32 addr) return SDIO_ERR_VAL32; ftaddr &= ~(u16)0x3; - sd_read(intfhdl, ftaddr, 8, tmpbuf); + err = sd_read(intfhdl, ftaddr, 8, tmpbuf); + if (err) { + kfree(tmpbuf); + return SDIO_ERR_VAL32; + } + memcpy(&le_tmp, tmpbuf + shift, 4); val = le32_to_cpu(le_tmp); -- 2.42.0.windows.2

2 weeks, 6 days

2
1
0 0

[PATCH v3] platform/x86: thinkpad-acpi: Add error check for tpacpi_check_quirks

by Wentao Liang

In tpacpi_battery_init(), the return value of tpacpi_check_quirks() needs to be checked. The battery should not be hooked if there is no matched battery information in quirk table. Add an error check and return -ENODEV immediately if the device fail the check. Fixes: 1a32ebb26ba9 ("platform/x86: thinkpad_acpi: Support battery quirk") Cc: stable(a)vger.kernel.org Signed-off-by: Wentao Liang <vulab(a)iscas.ac.cn> --- v3: Fix error code v2: Fix double assignment error drivers/platform/x86/thinkpad_acpi.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 2cfb2ac3f465..ab538bf53716 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -9974,6 +9974,8 @@ static int __init tpacpi_battery_init(struct ibm_init_struct *ibm) tp_features.battery_force_primary = tpacpi_check_quirks( battery_quirk_table, ARRAY_SIZE(battery_quirk_table)); + if (!tp_features.battery_force_primary) + return -ENODEV; battery_hook_register(&battery_hook); return 0; -- 2.42.0.windows.2

2 weeks, 6 days

2
1
0 0

[PATCH 6.6.y] drm/amd/display: Check link_index before accessing dc->links[]

by jianqi.ren.cn＠windriver.com

From: Alex Hung <alex.hung(a)amd.com> [ Upstream commit 8aa2864044b9d13e95fe224f32e808afbf79ecdf ] [WHY & HOW] dc->links[] has max size of MAX_LINKS and NULL is return when trying to access with out-of-bound index. This fixes 3 OVERRUN and 1 RESOURCE_LEAK issues reported by Coverity. Reviewed-by: Harry Wentland <harry.wentland(a)amd.com> Acked-by: Tom Chung <chiahsuan.chung(a)amd.com> Signed-off-by: Alex Hung <alex.hung(a)amd.com> Tested-by: Daniel Wheeler <daniel.wheeler(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> [The macro MAX_LINKS is introduced by Commit 60df5628144b ("drm/amd/display: handle invalid connector indices") after 6.10. So here we still use the original array length MAX_PIPES * 2] Signed-off-by: Jianqi Ren <jianqi.ren.cn(a)windriver.com> Signed-off-by: He Zhe <zhe.he(a)windriver.com> --- Verified the build test --- drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c index f365773d5714..e9b3c1c7a931 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c @@ -37,6 +37,9 @@ #include "dce/dce_i2c.h" struct dc_link *dc_get_link_at_index(struct dc *dc, uint32_t link_index) { + if (link_index >= (MAX_PIPES * 2)) + return NULL; + return dc->links[link_index]; } -- 2.34.1

2 weeks, 6 days

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror April 2025