From: "Liam R. Howlett" Liam.Howlett@oracle.com

commit 606c812eb1d5b5fb0dd9e330ca94b52d7c227830 upstream

The error unrolling was leaving the VMAs detached in many cases and leaving the locked_vm statistic altered, and skipping the unrolling entirely in the case of the vma tree write failing.

Fix the error path by re-attaching the detached VMAs and adding the necessary goto for the failed vma tree write, and fix the locked_vm statistic by only updating after the vma tree write succeeds.

Fixes: 763ecb035029 ("mm: remove the vma linked list") Reported-by: Vegard Nossum vegard.nossum@oracle.com Signed-off-by: Liam R. Howlett Liam.Howlett@oracle.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org [ dwmw2: Strictly, the original patch wasn't *re-attaching* the detached VMAs. They *were* still attached but just had the 'detached' flag set, which is an optimisation. Which doesn't exist in 6.3, so drop that. Also drop the call to vma_start_write() which came in with the per-VMA locking in 6.4. ] [ dwmw2 (6.1): It's do_mas_align_munmap() here. And has two call sites for the now-removed munmap_sidetree() function. Inline them both rather then trying to backport various dependencies with potentially subtle interactions. ] Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/mmap.c | 33 ++++++++++++++------------------- 1 file changed, 14 insertions(+), 19 deletions(-)

--- a/mm/mmap.c +++ b/mm/mmap.c @@ -2311,19 +2311,6 @@ int split_vma(struct mm_struct *mm, stru return __split_vma(mm, vma, addr, new_below); }

-static inline int munmap_sidetree(struct vm_area_struct *vma, - struct ma_state *mas_detach) -{ - mas_set_range(mas_detach, vma->vm_start, vma->vm_end - 1); - if (mas_store_gfp(mas_detach, vma, GFP_KERNEL)) - return -ENOMEM; - - if (vma->vm_flags & VM_LOCKED) - vma->vm_mm->locked_vm -= vma_pages(vma); - - return 0; -} - /* * do_mas_align_munmap() - munmap the aligned region from @start to @end. * @mas: The maple_state, ideally set up to alter the correct tree location. @@ -2345,6 +2332,7 @@ do_mas_align_munmap(struct ma_state *mas struct maple_tree mt_detach; int count = 0; int error = -ENOMEM; + unsigned long locked_vm = 0; MA_STATE(mas_detach, &mt_detach, 0, 0); mt_init_flags(&mt_detach, mas->tree->ma_flags & MT_FLAGS_LOCK_MASK); mt_set_external_lock(&mt_detach, &mm->mmap_lock); @@ -2403,18 +2391,23 @@ do_mas_align_munmap(struct ma_state *mas

mas_set(mas, end); split = mas_prev(mas, 0); - error = munmap_sidetree(split, &mas_detach); + mas_set_range(&mas_detach, split->vm_start, split->vm_end - 1); + error = mas_store_gfp(&mas_detach, split, GFP_KERNEL); if (error) - goto munmap_sidetree_failed; + goto munmap_gather_failed; + if (next->vm_flags & VM_LOCKED) + locked_vm += vma_pages(split);

count++; if (vma == next) vma = split; break; } - error = munmap_sidetree(next, &mas_detach); - if (error) - goto munmap_sidetree_failed; + mas_set_range(&mas_detach, next->vm_start, next->vm_end - 1); + if (mas_store_gfp(&mas_detach, next, GFP_KERNEL)) + goto munmap_gather_failed; + if (next->vm_flags & VM_LOCKED) + locked_vm += vma_pages(next);

count++; #ifdef CONFIG_DEBUG_VM_MAPLE_TREE @@ -2464,6 +2457,8 @@ do_mas_align_munmap(struct ma_state *mas } #endif mas_store_prealloc(mas, NULL); + + mm->locked_vm -= locked_vm; mm->map_count -= count; /* * Do not downgrade mmap_lock if we are next to VM_GROWSDOWN or @@ -2490,7 +2485,7 @@ do_mas_align_munmap(struct ma_state *mas return downgrade ? 1 : 0;

userfaultfd_error: -munmap_sidetree_failed: +munmap_gather_failed: end_split_failed: __mt_destroy(&mt_detach); start_split_failed:

From: Paolo Abeni pabeni@redhat.com

commit 57fc0f1ceaa4016354cf6f88533e20b56190e41a upstream.

The MPTCP protocol access the listener subflow in a lockless manner in a couple of places (poll, diag). That works only if the msk itself leaves the listener status only after that the subflow itself has been closed/disconnected. Otherwise we risk deadlock in diag, as reported by Christoph.

Address the issue ensuring that the first subflow (the listener one) is always disconnected before updating the msk socket status.

Reported-by: Christoph Paasch cpaasch@apple.com Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/407 Fixes: b29fcfb54cd7 ("mptcp: full disconnect implementation") Cc: stable@vger.kernel.org Signed-off-by: Paolo Abeni pabeni@redhat.com Reviewed-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/mptcp/pm_netlink.c | 1 + net/mptcp/protocol.c | 26 ++++++++++++++++++++------ 2 files changed, 21 insertions(+), 6 deletions(-)

--- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1039,6 +1039,7 @@ static int mptcp_pm_nl_create_listen_soc return err; }

+ inet_sk_state_store(newsk, TCP_LISTEN); err = kernel_listen(ssock, backlog); if (err) { pr_warn("kernel_listen error, err=%d", err); --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2400,12 +2400,6 @@ static void __mptcp_close_ssk(struct soc kfree_rcu(subflow, rcu); } else { /* otherwise tcp will dispose of the ssk and subflow ctx */ - if (ssk->sk_state == TCP_LISTEN) { - tcp_set_state(ssk, TCP_CLOSE); - mptcp_subflow_queue_clean(sk, ssk); - inet_csk_listen_stop(ssk); - } - __tcp_close(ssk, 0);

/* close acquired an extra ref */ @@ -2939,6 +2933,24 @@ static __poll_t mptcp_check_readable(str return EPOLLIN | EPOLLRDNORM; }

+static void mptcp_check_listen_stop(struct sock *sk) +{ + struct sock *ssk; + + if (inet_sk_state_load(sk) != TCP_LISTEN) + return; + + ssk = mptcp_sk(sk)->first; + if (WARN_ON_ONCE(!ssk || inet_sk_state_load(ssk) != TCP_LISTEN)) + return; + + lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); + mptcp_subflow_queue_clean(sk, ssk); + inet_csk_listen_stop(ssk); + tcp_set_state(ssk, TCP_CLOSE); + release_sock(ssk); +} + bool __mptcp_close(struct sock *sk, long timeout) { struct mptcp_subflow_context *subflow; @@ -2949,6 +2961,7 @@ bool __mptcp_close(struct sock *sk, long WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);

if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) { + mptcp_check_listen_stop(sk); inet_sk_state_store(sk, TCP_CLOSE); goto cleanup; } @@ -3062,6 +3075,7 @@ static int mptcp_disconnect(struct sock if (msk->fastopening) return -EBUSY;

+ mptcp_check_listen_stop(sk); inet_sk_state_store(sk, TCP_CLOSE);

mptcp_stop_timer(sk);

From: Tony Luck tony.luck@intel.com

commit d302c2398ba269e788a4f37ae57c07a7fcabaa42 upstream.

Cannot call memory_failure() directly from the fault handler because mmap_lock (and others) are held.

It is important, but not urgent, to mark the source page as h/w poisoned and unmap it from other tasks.

Use memory_failure_queue() to request a call to memory_failure() for the page with the error.

Also provide a stub version for CONFIG_MEMORY_FAILURE=n

Link: https://lkml.kernel.org/r/20221021200120.175753-3-tony.luck@intel.com Signed-off-by: Tony Luck tony.luck@intel.com Reviewed-by: Miaohe Lin linmiaohe@huawei.com Cc: Christophe Leroy christophe.leroy@csgroup.eu Cc: Dan Williams dan.j.williams@intel.com Cc: Matthew Wilcox (Oracle) willy@infradead.org Cc: Michael Ellerman mpe@ellerman.id.au Cc: Naoya Horiguchi naoya.horiguchi@nec.com Cc: Nicholas Piggin npiggin@gmail.com Cc: Shuai Xue xueshuai@linux.alibaba.com Signed-off-by: Andrew Morton akpm@linux-foundation.org [ Due to missing commits e591ef7d96d6e ("mm,hwpoison,hugetlb,memory_hotplug: hotremove memory section with hwpoisoned hugepage") 5033091de814a ("mm/hwpoison: introduce per-memory_block hwpoison counter") The impact of e591ef7d96d6e is its introduction of an additional flag in __get_huge_page_for_hwpoison() that serves as an indication a hwpoisoned hugetlb page should have its migratable bit cleared. The impact of 5033091de814a is contexual. Resolve by ignoring both missing commits. - jane] Signed-off-by: Jane Chu jane.chu@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/mm.h | 5 ++++- mm/memory.c | 4 +++- 2 files changed, 7 insertions(+), 2 deletions(-)

--- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3295,7 +3295,6 @@ enum mf_flags { int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, unsigned long count, int mf_flags); extern int memory_failure(unsigned long pfn, int flags); -extern void memory_failure_queue(unsigned long pfn, int flags); extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); extern int sysctl_memory_failure_early_kill; @@ -3304,8 +3303,12 @@ extern void shake_page(struct page *p); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); #ifdef CONFIG_MEMORY_FAILURE +extern void memory_failure_queue(unsigned long pfn, int flags); extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags); #else +static inline void memory_failure_queue(unsigned long pfn, int flags) +{ +} static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags) { return 0; --- a/mm/memory.c +++ b/mm/memory.c @@ -2861,8 +2861,10 @@ static inline int __wp_page_copy_user(st unsigned long addr = vmf->address;

if (likely(src)) { - if (copy_mc_user_highpage(dst, src, addr, vma)) + if (copy_mc_user_highpage(dst, src, addr, vma)) { + memory_failure_queue(page_to_pfn(src), 0); return -EHWPOISON; + } return 0; }

From: Thomas Gleixner tglx@linutronix.de

commit 1f5e7eb7868e42227ac426c96d437117e6e06e8e upstream.

Tony reported intermittent lockups on poweroff. His analysis identified the wbinvd() in stop_this_cpu() as the culprit. This was added to ensure that on SME enabled machines a kexec() does not leave any stale data in the caches when switching from encrypted to non-encrypted mode or vice versa.

That wbinvd() is conditional on the SME feature bit which is read directly from CPUID. But that readout does not check whether the CPUID leaf is available or not. If it's not available the CPU will return the value of the highest supported leaf instead. Depending on the content the "SME" bit might be set or not.

That's incorrect but harmless. Making the CPUID readout conditional makes the observed hangs go away, but it does not fix the underlying problem:

CPU0 CPU1

stop_other_cpus() send_IPIs(REBOOT); stop_this_cpu() while (num_online_cpus() > 1); set_online(false); proceed... -> hang wbinvd()

WBINVD is an expensive operation and if multiple CPUs issue it at the same time the resulting delays are even larger.

But CPU0 already observed num_online_cpus() going down to 1 and proceeds which causes the system to hang.

This issue exists independent of WBINVD, but the delays caused by WBINVD make it more prominent.

Make this more robust by adding a cpumask which is initialized to the online CPU mask before sending the IPIs and CPUs clear their bit in stop_this_cpu() after the WBINVD completed. Check for that cpumask to become empty in stop_other_cpus() instead of watching num_online_cpus().

The cpumask cannot plug all holes either, but it's better than a raw counter and allows to restrict the NMI fallback IPI to be sent only the CPUs which have not reported within the timeout window.

Fixes: 08f253ec3767 ("x86/cpu: Clear SME feature flag when not in use") Reported-by: Tony Battersby tonyb@cybernetics.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Borislav Petkov (AMD) bp@alien8.de Reviewed-by: Ashok Raj ashok.raj@intel.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/3817d810-e0f1-8ef8-0bbd-663b919ca49b@cybernetics... Link: https://lore.kernel.org/r/87h6r770bv.ffs@tglx Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/cpu.h | 2 + arch/x86/kernel/process.c | 23 +++++++++++++++- arch/x86/kernel/smp.c | 62 +++++++++++++++++++++++++++++---------------- 3 files changed, 64 insertions(+), 23 deletions(-)

--- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -96,4 +96,6 @@ static inline bool intel_cpu_signatures_

extern u64 x86_read_arch_cap_msr(void);

+extern struct cpumask cpus_stop_mask; + #endif /* _ASM_X86_CPU_H */ --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -744,13 +744,23 @@ bool xen_set_default_idle(void) } #endif

+struct cpumask cpus_stop_mask; + void __noreturn stop_this_cpu(void *dummy) { + unsigned int cpu = smp_processor_id(); + local_irq_disable(); + /* - * Remove this CPU: + * Remove this CPU from the online mask and disable it + * unconditionally. This might be redundant in case that the reboot + * vector was handled late and stop_other_cpus() sent an NMI. + * + * According to SDM and APM NMIs can be accepted even after soft + * disabling the local APIC. */ - set_cpu_online(smp_processor_id(), false); + set_cpu_online(cpu, false); disable_local_APIC(); mcheck_cpu_clear(this_cpu_ptr(&cpu_info));

@@ -768,6 +778,15 @@ void __noreturn stop_this_cpu(void *dumm */ if (cpuid_eax(0x8000001f) & BIT(0)) native_wbinvd(); + + /* + * This brings a cache line back and dirties it, but + * native_stop_other_cpus() will overwrite cpus_stop_mask after it + * observed that all CPUs reported stop. This write will invalidate + * the related cache line on this CPU. + */ + cpumask_clear_cpu(cpu, &cpus_stop_mask); + for (;;) { /* * Use native_halt() so that memory contents don't change --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -27,6 +27,7 @@ #include <asm/mmu_context.h> #include <asm/proto.h> #include <asm/apic.h> +#include <asm/cpu.h> #include <asm/idtentry.h> #include <asm/nmi.h> #include <asm/mce.h> @@ -146,31 +147,43 @@ static int register_stop_handler(void)

static void native_stop_other_cpus(int wait) { - unsigned long flags; - unsigned long timeout; + unsigned int cpu = smp_processor_id(); + unsigned long flags, timeout;

if (reboot_force) return;

- /* - * Use an own vector here because smp_call_function - * does lots of things not suitable in a panic situation. - */ + /* Only proceed if this is the first CPU to reach this code */ + if (atomic_cmpxchg(&stopping_cpu, -1, cpu) != -1) + return;

/* - * We start by using the REBOOT_VECTOR irq. - * The irq is treated as a sync point to allow critical - * regions of code on other cpus to release their spin locks - * and re-enable irqs. Jumping straight to an NMI might - * accidentally cause deadlocks with further shutdown/panic - * code. By syncing, we give the cpus up to one second to - * finish their work before we force them off with the NMI. + * 1) Send an IPI on the reboot vector to all other CPUs. + * + * The other CPUs should react on it after leaving critical + * sections and re-enabling interrupts. They might still hold + * locks, but there is nothing which can be done about that. + * + * 2) Wait for all other CPUs to report that they reached the + * HLT loop in stop_this_cpu() + * + * 3) If #2 timed out send an NMI to the CPUs which did not + * yet report + * + * 4) Wait for all other CPUs to report that they reached the + * HLT loop in stop_this_cpu() + * + * #3 can obviously race against a CPU reaching the HLT loop late. + * That CPU will have reported already and the "have all CPUs + * reached HLT" condition will be true despite the fact that the + * other CPU is still handling the NMI. Again, there is no + * protection against that as "disabled" APICs still respond to + * NMIs. */ - if (num_online_cpus() > 1) { - /* did someone beat us here? */ - if (atomic_cmpxchg(&stopping_cpu, -1, safe_smp_processor_id()) != -1) - return; + cpumask_copy(&cpus_stop_mask, cpu_online_mask); + cpumask_clear_cpu(cpu, &cpus_stop_mask);

+ if (!cpumask_empty(&cpus_stop_mask)) { /* sync above data before sending IRQ */ wmb();

@@ -183,12 +196,12 @@ static void native_stop_other_cpus(int w * CPUs reach shutdown state. */ timeout = USEC_PER_SEC; - while (num_online_cpus() > 1 && timeout--) + while (!cpumask_empty(&cpus_stop_mask) && timeout--) udelay(1); }

/* if the REBOOT_VECTOR didn't work, try with the NMI */ - if (num_online_cpus() > 1) { + if (!cpumask_empty(&cpus_stop_mask)) { /* * If NMI IPI is enabled, try to register the stop handler * and send the IPI. In any case try to wait for the other @@ -200,7 +213,8 @@ static void native_stop_other_cpus(int w

pr_emerg("Shutting down cpus with NMI\n");

- apic_send_IPI_allbutself(NMI_VECTOR); + for_each_cpu(cpu, &cpus_stop_mask) + apic->send_IPI(cpu, NMI_VECTOR); } /* * Don't wait longer than 10 ms if the caller didn't @@ -208,7 +222,7 @@ static void native_stop_other_cpus(int w * one or more CPUs do not reach shutdown state. */ timeout = USEC_PER_MSEC * 10; - while (num_online_cpus() > 1 && (wait || timeout--)) + while (!cpumask_empty(&cpus_stop_mask) && (wait || timeout--)) udelay(1); }

@@ -216,6 +230,12 @@ static void native_stop_other_cpus(int w disable_local_APIC(); mcheck_cpu_clear(this_cpu_ptr(&cpu_info)); local_irq_restore(flags); + + /* + * Ensure that the cpus_stop_mask cache lines are invalidated on + * the other CPUs. See comment vs. SME in stop_this_cpu(). + */ + cpumask_clear(&cpus_stop_mask); }

/*

From: Thomas Gleixner tglx@linutronix.de

commit 2affa6d6db28855e6340b060b809c23477aa546e upstream.

The wmb()s before sending the IPIs are not synchronizing anything.

If at all then the apic IPI functions have to provide or act as appropriate barriers.

Remove these cargo cult barriers which have no explanation of what they are synchronizing.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Borislav Petkov (AMD) bp@alien8.de Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615193330.378358382@linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/smp.c | 6 ------ 1 file changed, 6 deletions(-)

--- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -184,9 +184,6 @@ static void native_stop_other_cpus(int w cpumask_clear_cpu(cpu, &cpus_stop_mask);

if (!cpumask_empty(&cpus_stop_mask)) { - /* sync above data before sending IRQ */ - wmb(); - apic_send_IPI_allbutself(REBOOT_VECTOR);

/* @@ -208,9 +205,6 @@ static void native_stop_other_cpus(int w * CPUs to stop. */ if (!smp_no_nmi_ipi && !register_stop_handler()) { - /* Sync above data before sending IRQ */ - wmb(); - pr_emerg("Shutting down cpus with NMI\n");

for_each_cpu(cpu, &cpus_stop_mask)

From: Thomas Gleixner tglx@linutronix.de

commit d7893093a7417527c0d73c9832244e65c9d0114f upstream.

TLDR: It's a mess.

When kexec() is executed on a system with offline CPUs, which are parked in mwait_play_dead() it can end up in a triple fault during the bootup of the kexec kernel or cause hard to diagnose data corruption.

The reason is that kexec() eventually overwrites the previous kernel's text, page tables, data and stack. If it writes to the cache line which is monitored by a previously offlined CPU, MWAIT resumes execution and ends up executing the wrong text, dereferencing overwritten page tables or corrupting the kexec kernels data.

Cure this by bringing the offlined CPUs out of MWAIT into HLT.

Write to the monitored cache line of each offline CPU, which makes MWAIT resume execution. The written control word tells the offlined CPUs to issue HLT, which does not have the MWAIT problem.

That does not help, if a stray NMI, MCE or SMI hits the offlined CPUs as those make it come out of HLT.

A follow up change will put them into INIT, which protects at least against NMI and SMI.

Fixes: ea53069231f9 ("x86, hotplug: Use mwait to offline a processor, fix the legacy case") Reported-by: Ashok Raj ashok.raj@intel.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Tested-by: Ashok Raj ashok.raj@intel.com Reviewed-by: Ashok Raj ashok.raj@intel.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615193330.492257119@linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/smp.h | 2 + arch/x86/kernel/smp.c | 5 +++ arch/x86/kernel/smpboot.c | 59 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 66 insertions(+)

--- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -132,6 +132,8 @@ void wbinvd_on_cpu(int cpu); int wbinvd_on_all_cpus(void); void cond_wakeup_cpu0(void);

+void smp_kick_mwait_play_dead(void); + void native_smp_send_reschedule(int cpu); void native_send_call_func_ipi(const struct cpumask *mask); void native_send_call_func_single_ipi(int cpu); --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -21,6 +21,7 @@ #include <linux/interrupt.h> #include <linux/cpu.h> #include <linux/gfp.h> +#include <linux/kexec.h>

#include <asm/mtrr.h> #include <asm/tlbflush.h> @@ -157,6 +158,10 @@ static void native_stop_other_cpus(int w if (atomic_cmpxchg(&stopping_cpu, -1, cpu) != -1) return;

+ /* For kexec, ensure that offline CPUs are out of MWAIT and in HLT */ + if (kexec_in_progress) + smp_kick_mwait_play_dead(); + /* * 1) Send an IPI on the reboot vector to all other CPUs. * --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -53,6 +53,7 @@ #include <linux/tboot.h> #include <linux/gfp.h> #include <linux/cpuidle.h> +#include <linux/kexec.h> #include <linux/numa.h> #include <linux/pgtable.h> #include <linux/overflow.h> @@ -104,6 +105,9 @@ struct mwait_cpu_dead { unsigned int status; };

+#define CPUDEAD_MWAIT_WAIT 0xDEADBEEF +#define CPUDEAD_MWAIT_KEXEC_HLT 0x4A17DEAD + /* * Cache line aligned data for mwait_play_dead(). Separate on purpose so * that it's unlikely to be touched by other CPUs. @@ -166,6 +170,10 @@ static void smp_callin(void) { int cpuid;

+ /* Mop up eventual mwait_play_dead() wreckage */ + this_cpu_write(mwait_cpu_dead.status, 0); + this_cpu_write(mwait_cpu_dead.control, 0); + /* * If waken up by an INIT in an 82489DX configuration * cpu_callout_mask guarantees we don't get here before @@ -1795,6 +1803,10 @@ static inline void mwait_play_dead(void) (highest_subcstate - 1); }

+ /* Set up state for the kexec() hack below */ + md->status = CPUDEAD_MWAIT_WAIT; + md->control = CPUDEAD_MWAIT_WAIT; + wbinvd();

while (1) { @@ -1812,10 +1824,57 @@ static inline void mwait_play_dead(void) mb(); __mwait(eax, 0);

+ if (READ_ONCE(md->control) == CPUDEAD_MWAIT_KEXEC_HLT) { + /* + * Kexec is about to happen. Don't go back into mwait() as + * the kexec kernel might overwrite text and data including + * page tables and stack. So mwait() would resume when the + * monitor cache line is written to and then the CPU goes + * south due to overwritten text, page tables and stack. + * + * Note: This does _NOT_ protect against a stray MCE, NMI, + * SMI. They will resume execution at the instruction + * following the HLT instruction and run into the problem + * which this is trying to prevent. + */ + WRITE_ONCE(md->status, CPUDEAD_MWAIT_KEXEC_HLT); + while(1) + native_halt(); + } + cond_wakeup_cpu0(); } }

+/* + * Kick all "offline" CPUs out of mwait on kexec(). See comment in + * mwait_play_dead(). + */ +void smp_kick_mwait_play_dead(void) +{ + u32 newstate = CPUDEAD_MWAIT_KEXEC_HLT; + struct mwait_cpu_dead *md; + unsigned int cpu, i; + + for_each_cpu_andnot(cpu, cpu_present_mask, cpu_online_mask) { + md = per_cpu_ptr(&mwait_cpu_dead, cpu); + + /* Does it sit in mwait_play_dead() ? */ + if (READ_ONCE(md->status) != CPUDEAD_MWAIT_WAIT) + continue; + + /* Wait up to 5ms */ + for (i = 0; READ_ONCE(md->status) != newstate && i < 1000; i++) { + /* Bring it out of mwait */ + WRITE_ONCE(md->control, newstate); + udelay(5); + } + + if (READ_ONCE(md->status) != newstate) + pr_err_once("CPU%u is stuck in mwait_play_dead()\n", cpu); + } +} + void hlt_play_dead(void) { if (__this_cpu_read(cpu_info.x86) >= 4)

From: Peng Zhang zhangpeng.00@bytedance.com

commit cd00dd2585c4158e81fdfac0bbcc0446afbad26d upstream.

Check the write offset end bounds before using it as the offset into the pivot array. This avoids a possible out-of-bounds access on the pivot array if the write extends to the last slot in the node, in which case the node maximum should be used as the end pivot.

akpm: this doesn't affect any current callers, but new users of mapletree may encounter this problem if backported into earlier kernels, so let's fix it in -stable kernels in case of this.

Link: https://lkml.kernel.org/r/20230506024752.2550-1-zhangpeng.00@bytedance.com Fixes: 54a611b60590 ("Maple Tree: add new data structure") Signed-off-by: Peng Zhang zhangpeng.00@bytedance.com Reviewed-by: Liam R. Howlett Liam.Howlett@oracle.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- lib/maple_tree.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-)

--- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -4281,11 +4281,13 @@ done:

static inline void mas_wr_end_piv(struct ma_wr_state *wr_mas) { - while ((wr_mas->mas->last > wr_mas->end_piv) && - (wr_mas->offset_end < wr_mas->node_end)) - wr_mas->end_piv = wr_mas->pivots[++wr_mas->offset_end]; + while ((wr_mas->offset_end < wr_mas->node_end) && + (wr_mas->mas->last > wr_mas->pivots[wr_mas->offset_end])) + wr_mas->offset_end++;

- if (wr_mas->mas->last > wr_mas->end_piv) + if (wr_mas->offset_end < wr_mas->node_end) + wr_mas->end_piv = wr_mas->pivots[wr_mas->offset_end]; + else wr_mas->end_piv = wr_mas->mas->max; }

@@ -4442,7 +4444,6 @@ static inline void *mas_wr_store_entry(s }

/* At this point, we are at the leaf node that needs to be altered. */ - wr_mas->end_piv = wr_mas->r_max; mas_wr_end_piv(wr_mas);

if (!wr_mas->entry)

From: Linus Torvalds torvalds@linux-foundation.org

commit eda0047296a16d65a7f2bc60a408f70d178b2014 upstream.

This is done as a separate patch from introducing the new lock_mm_and_find_vma() helper, because while it's an obvious change, it's not what x86 used to do in this area.

We already abort the page fault on fatal signals anyway, so why should we wait for the mmap lock only to then abort later? With the new helper function that returns without the lock held on failure anyway, this is particularly easy and straightforward.

Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Samuel Mendoza-Jonas samjonas@amazon.com Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/memory.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)

--- a/mm/memory.c +++ b/mm/memory.c @@ -5275,8 +5275,7 @@ static inline bool get_mmap_lock_careful return false; }

- mmap_read_lock(mm); - return true; + return !mmap_read_lock_killable(mm); }

static inline bool mmap_upgrade_trylock(struct mm_struct *mm) @@ -5300,8 +5299,7 @@ static inline bool upgrade_mmap_lock_car if (!search_exception_tables(ip)) return false; } - mmap_write_lock(mm); - return true; + return !mmap_write_lock_killable(mm); }

/*

From: Michael Ellerman mpe@ellerman.id.au

commit e6fe228c4ffafdfc970cf6d46883a1f481baf7ea upstream.

Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Samuel Mendoza-Jonas samjonas@amazon.com Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/Kconfig | 1 + arch/powerpc/mm/fault.c | 41 ++++------------------------------------- 2 files changed, 5 insertions(+), 37 deletions(-)

--- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -257,6 +257,7 @@ config PPC select IRQ_DOMAIN select IRQ_FORCED_THREADING select KASAN_VMALLOC if KASAN && MODULES + select LOCK_MM_AND_FIND_VMA select MMU_GATHER_PAGE_SIZE select MMU_GATHER_RCU_TABLE_FREE select MMU_GATHER_MERGE_VMAS --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -84,11 +84,6 @@ static int __bad_area(struct pt_regs *re return __bad_area_nosemaphore(regs, address, si_code); }

-static noinline int bad_area(struct pt_regs *regs, unsigned long address) -{ - return __bad_area(regs, address, SEGV_MAPERR); -} - static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address, struct vm_area_struct *vma) { @@ -481,40 +476,12 @@ static int ___do_page_fault(struct pt_re * we will deadlock attempting to validate the fault against the * address space. Luckily the kernel only validly references user * space from well defined areas of code, which are listed in the - * exceptions table. - * - * As the vast majority of faults will be valid we will only perform - * the source reference check when there is a possibility of a deadlock. - * Attempt to lock the address space, if we cannot we then validate the - * source. If this is invalid we can skip the address space check, - * thus avoiding the deadlock. - */ - if (unlikely(!mmap_read_trylock(mm))) { - if (!is_user && !search_exception_tables(regs->nip)) - return bad_area_nosemaphore(regs, address); - + * exceptions table. lock_mm_and_find_vma() handles that logic. + */ retry: - mmap_read_lock(mm); - } else { - /* - * The above down_read_trylock() might have succeeded in - * which case we'll have missed the might_sleep() from - * down_read(): - */ - might_sleep(); - } - - vma = find_vma(mm, address); + vma = lock_mm_and_find_vma(mm, address, regs); if (unlikely(!vma)) - return bad_area(regs, address); - - if (unlikely(vma->vm_start > address)) { - if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) - return bad_area(regs, address); - - if (unlikely(expand_stack(vma, address))) - return bad_area(regs, address); - } + return bad_area_nosemaphore(regs, address);

if (unlikely(access_pkey_error(is_write, is_exec, (error_code & DSISR_KEYFAULT), vma)))

From: Ben Hutchings ben@decadent.org.uk

commit 7267ef7b0b77f4ed23b7b3c87d8eca7bd9c2d007 upstream.

Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Linus Torvalds torvalds@linux-foundation.org [6.1: Kconfig context] Signed-off-by: Samuel Mendoza-Jonas samjonas@amazon.com Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/riscv/Kconfig | 1 + arch/riscv/mm/fault.c | 31 +++++++++++++------------------ 2 files changed, 14 insertions(+), 18 deletions(-)

--- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -114,6 +114,7 @@ config RISCV select HAVE_RSEQ select IRQ_DOMAIN select IRQ_FORCED_THREADING + select LOCK_MM_AND_FIND_VMA select MODULES_USE_ELF_RELA if MODULES select MODULE_SECTIONS if MODULES select OF --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -83,13 +83,13 @@ static inline void mm_fault_error(struct BUG(); }

-static inline void bad_area(struct pt_regs *regs, struct mm_struct *mm, int code, unsigned long addr) +static inline void +bad_area_nosemaphore(struct pt_regs *regs, int code, unsigned long addr) { /* * Something tried to access memory that isn't in our memory map. * Fix it, but check if it's kernel or user first. */ - mmap_read_unlock(mm); /* User mode accesses just cause a SIGSEGV */ if (user_mode(regs)) { do_trap(regs, SIGSEGV, code, addr); @@ -99,6 +99,15 @@ static inline void bad_area(struct pt_re no_context(regs, addr); }

+static inline void +bad_area(struct pt_regs *regs, struct mm_struct *mm, int code, + unsigned long addr) +{ + mmap_read_unlock(mm); + + bad_area_nosemaphore(regs, code, addr); +} + static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long addr) { pgd_t *pgd, *pgd_k; @@ -281,23 +290,10 @@ asmlinkage void do_page_fault(struct pt_ else if (cause == EXC_INST_PAGE_FAULT) flags |= FAULT_FLAG_INSTRUCTION; retry: - mmap_read_lock(mm); - vma = find_vma(mm, addr); + vma = lock_mm_and_find_vma(mm, addr, regs); if (unlikely(!vma)) { tsk->thread.bad_cause = cause; - bad_area(regs, mm, code, addr); - return; - } - if (likely(vma->vm_start <= addr)) - goto good_area; - if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) { - tsk->thread.bad_cause = cause; - bad_area(regs, mm, code, addr); - return; - } - if (unlikely(expand_stack(vma, addr))) { - tsk->thread.bad_cause = cause; - bad_area(regs, mm, code, addr); + bad_area_nosemaphore(regs, code, addr); return; }

@@ -305,7 +301,6 @@ retry: * Ok, we have a good vm_area for this memory access, so * we can handle it. */ -good_area: code = SEGV_ACCERR;

if (unlikely(access_error(cause, vma))) {

From: Linus Torvalds torvalds@linux-foundation.org

commit a050ba1e7422f2cc60ff8bfde3f96d34d00cb585 upstream.

This does the simple pattern conversion of alpha, arc, csky, hexagon, loongarch, nios2, sh, sparc32, and xtensa to the lock_mm_and_find_vma() helper. They all have the regular fault handling pattern without odd special cases.

The remaining architectures all have something that keeps us from a straightforward conversion: ia64 and parisc have stacks that can grow both up as well as down (and ia64 has special address region checks).

And m68k, microblaze, openrisc, sparc64, and um end up having extra rules about only expanding the stack down a limited amount below the user space stack pointer. That is something that x86 used to do too (long long ago), and it probably could just be skipped, but it still makes the conversion less than trivial.

Note that this conversion was done manually and with the exception of alpha without any build testing, because I have a fairly limited cross- building environment. The cases are all simple, and I went through the changes several times, but...

Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Samuel Mendoza-Jonas samjonas@amazon.com Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/alpha/Kconfig | 1 + arch/alpha/mm/fault.c | 13 +++---------- arch/arc/Kconfig | 1 + arch/arc/mm/fault.c | 11 +++-------- arch/csky/Kconfig | 1 + arch/csky/mm/fault.c | 22 +++++----------------- arch/hexagon/Kconfig | 1 + arch/hexagon/mm/vm_fault.c | 18 ++++-------------- arch/loongarch/Kconfig | 1 + arch/loongarch/mm/fault.c | 16 ++++++---------- arch/nios2/Kconfig | 1 + arch/nios2/mm/fault.c | 17 ++--------------- arch/sh/Kconfig | 1 + arch/sh/mm/fault.c | 17 ++--------------- arch/sparc/Kconfig | 1 + arch/sparc/mm/fault_32.c | 32 ++++++++------------------------ arch/xtensa/Kconfig | 1 + arch/xtensa/mm/fault.c | 14 +++----------- 18 files changed, 45 insertions(+), 124 deletions(-)

--- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -28,6 +28,7 @@ config ALPHA select GENERIC_SMP_IDLE_THREAD select HAVE_ARCH_AUDITSYSCALL select HAVE_MOD_ARCH_SPECIFIC + select LOCK_MM_AND_FIND_VMA select MODULES_USE_ELF_RELA select ODD_RT_SIGACTION select OLD_SIGSUSPEND --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -119,20 +119,12 @@ do_page_fault(unsigned long address, uns flags |= FAULT_FLAG_USER; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); retry: - mmap_read_lock(mm); - vma = find_vma(mm, address); + vma = lock_mm_and_find_vma(mm, address, regs); if (!vma) - goto bad_area; - if (vma->vm_start <= address) - goto good_area; - if (!(vma->vm_flags & VM_GROWSDOWN)) - goto bad_area; - if (expand_stack(vma, address)) - goto bad_area; + goto bad_area_nosemaphore;

/* Ok, we have a good vm_area for this memory access, so we can handle it. */ - good_area: si_code = SEGV_ACCERR; if (cause < 0) { if (!(vma->vm_flags & VM_EXEC)) @@ -189,6 +181,7 @@ retry: bad_area: mmap_read_unlock(mm);

+ bad_area_nosemaphore: if (user_mode(regs)) goto do_sigsegv;

--- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -41,6 +41,7 @@ config ARC select HAVE_PERF_EVENTS select HAVE_SYSCALL_TRACEPOINTS select IRQ_DOMAIN + select LOCK_MM_AND_FIND_VMA select MODULES_USE_ELF_RELA select OF select OF_EARLY_FLATTREE --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -113,15 +113,9 @@ void do_page_fault(unsigned long address

perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); retry: - mmap_read_lock(mm); - - vma = find_vma(mm, address); + vma = lock_mm_and_find_vma(mm, address, regs); if (!vma) - goto bad_area; - if (unlikely(address < vma->vm_start)) { - if (!(vma->vm_flags & VM_GROWSDOWN) || expand_stack(vma, address)) - goto bad_area; - } + goto bad_area_nosemaphore;

/* * vm_area is good, now check permissions for this memory access @@ -161,6 +155,7 @@ retry: bad_area: mmap_read_unlock(mm);

+bad_area_nosemaphore: /* * Major/minor page fault accounting * (in case of retry we only land here once) --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -96,6 +96,7 @@ config CSKY select HAVE_RSEQ select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS + select LOCK_MM_AND_FIND_VMA select MAY_HAVE_SPARSE_IRQ select MODULES_USE_ELF_RELA if MODULES select OF --- a/arch/csky/mm/fault.c +++ b/arch/csky/mm/fault.c @@ -97,13 +97,12 @@ static inline void mm_fault_error(struct BUG(); }

-static inline void bad_area(struct pt_regs *regs, struct mm_struct *mm, int code, unsigned long addr) +static inline void bad_area_nosemaphore(struct pt_regs *regs, struct mm_struct *mm, int code, unsigned long addr) { /* * Something tried to access memory that isn't in our memory map. * Fix it, but check if it's kernel or user first. */ - mmap_read_unlock(mm); /* User mode accesses just cause a SIGSEGV */ if (user_mode(regs)) { do_trap(regs, SIGSEGV, code, addr); @@ -238,20 +237,9 @@ asmlinkage void do_page_fault(struct pt_ if (is_write(regs)) flags |= FAULT_FLAG_WRITE; retry: - mmap_read_lock(mm); - vma = find_vma(mm, addr); + vma = lock_mm_and_find_vma(mm, address, regs); if (unlikely(!vma)) { - bad_area(regs, mm, code, addr); - return; - } - if (likely(vma->vm_start <= addr)) - goto good_area; - if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) { - bad_area(regs, mm, code, addr); - return; - } - if (unlikely(expand_stack(vma, addr))) { - bad_area(regs, mm, code, addr); + bad_area_nosemaphore(regs, mm, code, addr); return; }

@@ -259,11 +247,11 @@ retry: * Ok, we have a good vm_area for this memory access, so * we can handle it. */ -good_area: code = SEGV_ACCERR;

if (unlikely(access_error(regs, vma))) { - bad_area(regs, mm, code, addr); + mmap_read_unlock(mm); + bad_area_nosemaphore(regs, mm, code, addr); return; }

--- a/arch/hexagon/Kconfig +++ b/arch/hexagon/Kconfig @@ -28,6 +28,7 @@ config HEXAGON select GENERIC_SMP_IDLE_THREAD select STACKTRACE_SUPPORT select GENERIC_CLOCKEVENTS_BROADCAST + select LOCK_MM_AND_FIND_VMA select MODULES_USE_ELF_RELA select GENERIC_CPU_DEVICES select ARCH_WANT_LD_ORPHAN_WARN --- a/arch/hexagon/mm/vm_fault.c +++ b/arch/hexagon/mm/vm_fault.c @@ -57,21 +57,10 @@ void do_page_fault(unsigned long address

perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); retry: - mmap_read_lock(mm); - vma = find_vma(mm, address); - if (!vma) - goto bad_area; + vma = lock_mm_and_find_vma(mm, address, regs); + if (unlikely(!vma)) + goto bad_area_nosemaphore;

- if (vma->vm_start <= address) - goto good_area; - - if (!(vma->vm_flags & VM_GROWSDOWN)) - goto bad_area; - - if (expand_stack(vma, address)) - goto bad_area; - -good_area: /* Address space is OK. Now check access rights. */ si_code = SEGV_ACCERR;

@@ -140,6 +129,7 @@ good_area: bad_area: mmap_read_unlock(mm);

+bad_area_nosemaphore: if (user_mode(regs)) { force_sig_fault(SIGSEGV, si_code, (void __user *)address); return; --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -107,6 +107,7 @@ config LOONGARCH select HAVE_VIRT_CPU_ACCOUNTING_GEN if !SMP select IRQ_FORCED_THREADING select IRQ_LOONGARCH_CPU + select LOCK_MM_AND_FIND_VMA select MMU_GATHER_MERGE_VMAS if MMU select MODULES_USE_ELF_RELA if MODULES select NEED_PER_CPU_EMBED_FIRST_CHUNK --- a/arch/loongarch/mm/fault.c +++ b/arch/loongarch/mm/fault.c @@ -166,22 +166,18 @@ static void __kprobes __do_page_fault(st

perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); retry: - mmap_read_lock(mm); - vma = find_vma(mm, address); - if (!vma) - goto bad_area; - if (vma->vm_start <= address) - goto good_area; - if (!(vma->vm_flags & VM_GROWSDOWN)) - goto bad_area; - if (!expand_stack(vma, address)) - goto good_area; + vma = lock_mm_and_find_vma(mm, address, regs); + if (unlikely(!vma)) + goto bad_area_nosemaphore; + goto good_area; + /* * Something tried to access memory that isn't in our memory map.. * Fix it, but check if it's kernel or user first.. */ bad_area: mmap_read_unlock(mm); +bad_area_nosemaphore: do_sigsegv(regs, write, address, si_code); return;

--- a/arch/nios2/Kconfig +++ b/arch/nios2/Kconfig @@ -16,6 +16,7 @@ config NIOS2 select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_KGDB select IRQ_DOMAIN + select LOCK_MM_AND_FIND_VMA select MODULES_USE_ELF_RELA select OF select OF_EARLY_FLATTREE --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -86,27 +86,14 @@ asmlinkage void do_page_fault(struct pt_

perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);

- if (!mmap_read_trylock(mm)) { - if (!user_mode(regs) && !search_exception_tables(regs->ea)) - goto bad_area_nosemaphore; retry: - mmap_read_lock(mm); - } - - vma = find_vma(mm, address); + vma = lock_mm_and_find_vma(mm, address, regs); if (!vma) - goto bad_area; - if (vma->vm_start <= address) - goto good_area; - if (!(vma->vm_flags & VM_GROWSDOWN)) - goto bad_area; - if (expand_stack(vma, address)) - goto bad_area; + goto bad_area_nosemaphore; /* * Ok, we have a good vm_area for this memory access, so * we can handle it.. */ -good_area: code = SEGV_ACCERR;

switch (cause) { --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -56,6 +56,7 @@ config SUPERH select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS select IRQ_FORCED_THREADING + select LOCK_MM_AND_FIND_VMA select MODULES_USE_ELF_RELA select NEED_SG_DMA_LENGTH select NO_DMA if !MMU && !DMA_COHERENT --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -439,21 +439,9 @@ asmlinkage void __kprobes do_page_fault( }

retry: - mmap_read_lock(mm); - - vma = find_vma(mm, address); + vma = lock_mm_and_find_vma(mm, address, regs); if (unlikely(!vma)) { - bad_area(regs, error_code, address); - return; - } - if (likely(vma->vm_start <= address)) - goto good_area; - if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) { - bad_area(regs, error_code, address); - return; - } - if (unlikely(expand_stack(vma, address))) { - bad_area(regs, error_code, address); + bad_area_nosemaphore(regs, error_code, address); return; }

@@ -461,7 +449,6 @@ retry: * Ok, we have a good vm_area for this memory access, so * we can handle it.. */ -good_area: if (unlikely(access_error(error_code, vma))) { bad_area_access_error(regs, error_code, address); return; --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -56,6 +56,7 @@ config SPARC32 select DMA_DIRECT_REMAP select GENERIC_ATOMIC64 select HAVE_UID16 + select LOCK_MM_AND_FIND_VMA select OLD_SIGACTION select ZONE_DMA

--- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -143,28 +143,19 @@ asmlinkage void do_sparc_fault(struct pt if (pagefault_disabled() || !mm) goto no_context;

+ if (!from_user && address >= PAGE_OFFSET) + goto no_context; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);

retry: - mmap_read_lock(mm); - - if (!from_user && address >= PAGE_OFFSET) - goto bad_area; - - vma = find_vma(mm, address); + vma = lock_mm_and_find_vma(mm, address, regs); if (!vma) - goto bad_area; - if (vma->vm_start <= address) - goto good_area; - if (!(vma->vm_flags & VM_GROWSDOWN)) - goto bad_area; - if (expand_stack(vma, address)) - goto bad_area; + goto bad_area_nosemaphore; /* * Ok, we have a good vm_area for this memory access, so * we can handle it.. */ -good_area: code = SEGV_ACCERR; if (write) { if (!(vma->vm_flags & VM_WRITE)) @@ -318,17 +309,9 @@ static void force_user_fault(unsigned lo

code = SEGV_MAPERR;

- mmap_read_lock(mm); - vma = find_vma(mm, address); + vma = lock_mm_and_find_vma(mm, address, regs); if (!vma) - goto bad_area; - if (vma->vm_start <= address) - goto good_area; - if (!(vma->vm_flags & VM_GROWSDOWN)) - goto bad_area; - if (expand_stack(vma, address)) - goto bad_area; -good_area: + goto bad_area_nosemaphore; code = SEGV_ACCERR; if (write) { if (!(vma->vm_flags & VM_WRITE)) @@ -347,6 +330,7 @@ good_area: return; bad_area: mmap_read_unlock(mm); +bad_area_nosemaphore: __do_fault_siginfo(code, SIGSEGV, tsk->thread.kregs, address); return;

--- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -49,6 +49,7 @@ config XTENSA select HAVE_SYSCALL_TRACEPOINTS select HAVE_VIRT_CPU_ACCOUNTING_GEN select IRQ_DOMAIN + select LOCK_MM_AND_FIND_VMA select MODULES_USE_ELF_RELA select PERF_USE_VMALLOC select TRACE_IRQFLAGS_SUPPORT --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -130,23 +130,14 @@ void do_page_fault(struct pt_regs *regs) perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);

retry: - mmap_read_lock(mm); - vma = find_vma(mm, address); - + vma = lock_mm_and_find_vma(mm, address, regs); if (!vma) - goto bad_area; - if (vma->vm_start <= address) - goto good_area; - if (!(vma->vm_flags & VM_GROWSDOWN)) - goto bad_area; - if (expand_stack(vma, address)) - goto bad_area; + goto bad_area_nosemaphore;

/* Ok, we have a good vm_area for this memory access, so * we can handle it.. */

-good_area: code = SEGV_ACCERR;

if (is_write) { @@ -205,6 +196,7 @@ good_area: */ bad_area: mmap_read_unlock(mm); +bad_area_nosemaphore: if (user_mode(regs)) { current->thread.bad_vaddr = address; current->thread.error_code = is_write;

From: "Liam R. Howlett" Liam.Howlett@oracle.com

commit f440fa1ac955e2898893f9301568435eb5cdfc4b upstream.

Make calls to extend_vma() and find_extend_vma() fail if the write lock is required.

To avoid making this a flag-day event, this still allows the old read-locking case for the trivial situations, and passes in a flag to say "is it write-locked". That way write-lockers can say "yes, I'm being careful", and legacy users will continue to work in all the common cases until they have been fully converted to the new world order.

Co-Developed-by: Matthew Wilcox (Oracle) willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) willy@infradead.org Signed-off-by: Liam R. Howlett Liam.Howlett@oracle.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Samuel Mendoza-Jonas samjonas@amazon.com Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/binfmt_elf.c | 6 +++--- fs/exec.c | 5 +++-- include/linux/mm.h | 10 +++++++--- mm/memory.c | 2 +- mm/mmap.c | 50 +++++++++++++++++++++++++++++++++----------------- mm/nommu.c | 3 ++- 6 files changed, 49 insertions(+), 27 deletions(-)

--- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -315,10 +315,10 @@ create_elf_tables(struct linux_binprm *b * Grow the stack manually; some architectures have a limit on how * far ahead a user-space access may be in order to grow the stack. */ - if (mmap_read_lock_killable(mm)) + if (mmap_write_lock_killable(mm)) return -EINTR; - vma = find_extend_vma(mm, bprm->p); - mmap_read_unlock(mm); + vma = find_extend_vma_locked(mm, bprm->p, true); + mmap_write_unlock(mm); if (!vma) return -EFAULT;

--- a/fs/exec.c +++ b/fs/exec.c @@ -203,7 +203,8 @@ static struct page *get_arg_page(struct

#ifdef CONFIG_STACK_GROWSUP if (write) { - ret = expand_downwards(bprm->vma, pos); + /* We claim to hold the lock - nobody to race with */ + ret = expand_downwards(bprm->vma, pos, true); if (ret < 0) return NULL; } @@ -854,7 +855,7 @@ int setup_arg_pages(struct linux_binprm stack_base = vma->vm_start - stack_expand; #endif current->mm->start_stack = bprm->p; - ret = expand_stack(vma, stack_base); + ret = expand_stack_locked(vma, stack_base, true); if (ret) ret = -EFAULT;

--- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2810,11 +2810,13 @@ extern vm_fault_t filemap_page_mkwrite(s

extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ -extern int expand_stack(struct vm_area_struct *vma, unsigned long address); +int expand_stack_locked(struct vm_area_struct *vma, unsigned long address, + bool write_locked); +#define expand_stack(vma,addr) expand_stack_locked(vma,addr,false)

/* CONFIG_STACK_GROWSUP still needs to grow downwards at some places */ -extern int expand_downwards(struct vm_area_struct *vma, - unsigned long address); +int expand_downwards(struct vm_area_struct *vma, unsigned long address, + bool write_locked); #if VM_GROWSUP extern int expand_upwards(struct vm_area_struct *vma, unsigned long address); #else @@ -2915,6 +2917,8 @@ unsigned long change_prot_numa(struct vm #endif

struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr); +struct vm_area_struct *find_extend_vma_locked(struct mm_struct *, + unsigned long addr, bool write_locked); int remap_pfn_range(struct vm_area_struct *, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t); int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr, --- a/mm/memory.c +++ b/mm/memory.c @@ -5364,7 +5364,7 @@ struct vm_area_struct *lock_mm_and_find_ goto fail; }

- if (expand_stack(vma, addr)) + if (expand_stack_locked(vma, addr, true)) goto fail;

success: --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1945,7 +1945,8 @@ static int acct_stack_growth(struct vm_a * PA-RISC uses this for its stack; IA64 for its Register Backing Store. * vma is the last one with address > vma->vm_end. Have to extend vma. */ -int expand_upwards(struct vm_area_struct *vma, unsigned long address) +int expand_upwards(struct vm_area_struct *vma, unsigned long address, + bool write_locked) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *next; @@ -1969,6 +1970,8 @@ int expand_upwards(struct vm_area_struct if (gap_addr < address || gap_addr > TASK_SIZE) gap_addr = TASK_SIZE;

+ if (!write_locked) + return -EAGAIN; next = find_vma_intersection(mm, vma->vm_end, gap_addr); if (next && vma_is_accessible(next)) { if (!(next->vm_flags & VM_GROWSUP)) @@ -2037,7 +2040,8 @@ int expand_upwards(struct vm_area_struct /* * vma is the first one with address < vma->vm_start. Have to extend vma. */ -int expand_downwards(struct vm_area_struct *vma, unsigned long address) +int expand_downwards(struct vm_area_struct *vma, unsigned long address, + bool write_locked) { struct mm_struct *mm = vma->vm_mm; MA_STATE(mas, &mm->mm_mt, vma->vm_start, vma->vm_start); @@ -2051,10 +2055,13 @@ int expand_downwards(struct vm_area_stru /* Enforce stack_guard_gap */ prev = mas_prev(&mas, 0); /* Check that both stack segments have the same anon_vma? */ - if (prev && !(prev->vm_flags & VM_GROWSDOWN) && - vma_is_accessible(prev)) { - if (address - prev->vm_end < stack_guard_gap) + if (prev) { + if (!(prev->vm_flags & VM_GROWSDOWN) && + vma_is_accessible(prev) && + (address - prev->vm_end < stack_guard_gap)) return -ENOMEM; + if (!write_locked && (prev->vm_end == address)) + return -EAGAIN; }

if (mas_preallocate(&mas, vma, GFP_KERNEL)) @@ -2132,13 +2139,14 @@ static int __init cmdline_parse_stack_gu __setup("stack_guard_gap=", cmdline_parse_stack_guard_gap);

#ifdef CONFIG_STACK_GROWSUP -int expand_stack(struct vm_area_struct *vma, unsigned long address) +int expand_stack_locked(struct vm_area_struct *vma, unsigned long address, + bool write_locked) { - return expand_upwards(vma, address); + return expand_upwards(vma, address, write_locked); }

-struct vm_area_struct * -find_extend_vma(struct mm_struct *mm, unsigned long addr) +struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, + unsigned long addr, bool write_locked) { struct vm_area_struct *vma, *prev;

@@ -2146,20 +2154,25 @@ find_extend_vma(struct mm_struct *mm, un vma = find_vma_prev(mm, addr, &prev); if (vma && (vma->vm_start <= addr)) return vma; - if (!prev || expand_stack(prev, addr)) + if (!prev) + return NULL; + if (expand_stack_locked(prev, addr, write_locked)) return NULL; if (prev->vm_flags & VM_LOCKED) populate_vma_page_range(prev, addr, prev->vm_end, NULL); return prev; } #else -int expand_stack(struct vm_area_struct *vma, unsigned long address) +int expand_stack_locked(struct vm_area_struct *vma, unsigned long address, + bool write_locked) { - return expand_downwards(vma, address); + if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) + return -EINVAL; + return expand_downwards(vma, address, write_locked); }

-struct vm_area_struct * -find_extend_vma(struct mm_struct *mm, unsigned long addr) +struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, + unsigned long addr, bool write_locked) { struct vm_area_struct *vma; unsigned long start; @@ -2170,10 +2183,8 @@ find_extend_vma(struct mm_struct *mm, un return NULL; if (vma->vm_start <= addr) return vma; - if (!(vma->vm_flags & VM_GROWSDOWN)) - return NULL; start = vma->vm_start; - if (expand_stack(vma, addr)) + if (expand_stack_locked(vma, addr, write_locked)) return NULL; if (vma->vm_flags & VM_LOCKED) populate_vma_page_range(vma, addr, start, NULL); @@ -2181,6 +2192,11 @@ find_extend_vma(struct mm_struct *mm, un } #endif

+struct vm_area_struct *find_extend_vma(struct mm_struct *mm, + unsigned long addr) +{ + return find_extend_vma_locked(mm, addr, false); +} EXPORT_SYMBOL_GPL(find_extend_vma);

/* --- a/mm/nommu.c +++ b/mm/nommu.c @@ -694,7 +694,8 @@ struct vm_area_struct *find_extend_vma(s * expand a stack to a given address * - not supported under NOMMU conditions */ -int expand_stack(struct vm_area_struct *vma, unsigned long address) +int expand_stack_locked(struct vm_area_struct *vma, unsigned long address, + bool write_locked) { return -ENOMEM; }

From: Linus Torvalds torvalds@linux-foundation.org

commit 8d7071af890768438c14db6172cc8f9f4d04e184 upstream

This finishes the job of always holding the mmap write lock when extending the user stack vma, and removes the 'write_locked' argument from the vm helper functions again.

For some cases, we just avoid expanding the stack at all: drivers and page pinning really shouldn't be extending any stacks. Let's see if any strange users really wanted that.

It's worth noting that architectures that weren't converted to the new lock_mm_and_find_vma() helper function are left using the legacy "expand_stack()" function, but it has been changed to drop the mmap_lock and take it for writing while expanding the vma. This makes it fairly straightforward to convert the remaining architectures.

As a result of dropping and re-taking the lock, the calling conventions for this function have also changed, since the old vma may no longer be valid. So it will now return the new vma if successful, and NULL - and the lock dropped - if the area could not be extended.

Signed-off-by: Linus Torvalds torvalds@linux-foundation.org [6.1: Patch drivers/iommu/io-pgfault.c instead] Signed-off-by: Samuel Mendoza-Jonas samjonas@amazon.com Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/ia64/mm/fault.c | 36 ++---------- arch/m68k/mm/fault.c | 9 ++- arch/microblaze/mm/fault.c | 5 + arch/openrisc/mm/fault.c | 5 + arch/parisc/mm/fault.c | 23 +++----- arch/s390/mm/fault.c | 5 + arch/sparc/mm/fault_64.c | 8 +- arch/um/kernel/trap.c | 11 ++- drivers/iommu/amd/iommu_v2.c | 4 - drivers/iommu/io-pgfault.c | 2 fs/binfmt_elf.c | 2 fs/exec.c | 4 - include/linux/mm.h | 16 +---- mm/gup.c | 6 +- mm/memory.c | 10 +++ mm/mmap.c | 121 ++++++++++++++++++++++++++++++++++--------- mm/nommu.c | 18 ++---- 17 files changed, 169 insertions(+), 116 deletions(-)

--- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -110,10 +110,12 @@ retry: * register backing store that needs to expand upwards, in * this case vma will be null, but prev_vma will ne non-null */ - if (( !vma && prev_vma ) || (address < vma->vm_start) ) - goto check_expansion; + if (( !vma && prev_vma ) || (address < vma->vm_start) ) { + vma = expand_stack(mm, address); + if (!vma) + goto bad_area_nosemaphore; + }

- good_area: code = SEGV_ACCERR;

/* OK, we've got a good vm_area for this memory area. Check the access permissions: */ @@ -174,35 +176,9 @@ retry: mmap_read_unlock(mm); return;

- check_expansion: - if (!(prev_vma && (prev_vma->vm_flags & VM_GROWSUP) && (address == prev_vma->vm_end))) { - if (!vma) - goto bad_area; - if (!(vma->vm_flags & VM_GROWSDOWN)) - goto bad_area; - if (REGION_NUMBER(address) != REGION_NUMBER(vma->vm_start) - || REGION_OFFSET(address) >= RGN_MAP_LIMIT) - goto bad_area; - if (expand_stack(vma, address)) - goto bad_area; - } else { - vma = prev_vma; - if (REGION_NUMBER(address) != REGION_NUMBER(vma->vm_start) - || REGION_OFFSET(address) >= RGN_MAP_LIMIT) - goto bad_area; - /* - * Since the register backing store is accessed sequentially, - * we disallow growing it by more than a page at a time. - */ - if (address > vma->vm_end + PAGE_SIZE - sizeof(long)) - goto bad_area; - if (expand_upwards(vma, address)) - goto bad_area; - } - goto good_area; - bad_area: mmap_read_unlock(mm); + bad_area_nosemaphore: if ((isr & IA64_ISR_SP) || ((isr & IA64_ISR_NA) && (isr & IA64_ISR_CODE_MASK) == IA64_ISR_CODE_LFETCH)) { --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -105,8 +105,9 @@ retry: if (address + 256 < rdusp()) goto map_err; } - if (expand_stack(vma, address)) - goto map_err; + vma = expand_stack(mm, address); + if (!vma) + goto map_err_nosemaphore;

/* * Ok, we have a good vm_area for this memory access, so @@ -193,10 +194,12 @@ bus_err: goto send_sig;

map_err: + mmap_read_unlock(mm); +map_err_nosemaphore: current->thread.signo = SIGSEGV; current->thread.code = SEGV_MAPERR; current->thread.faddr = address; - goto send_sig; + return send_fault_sig(regs);

acc_err: current->thread.signo = SIGSEGV; --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -192,8 +192,9 @@ retry: && (kernel_mode(regs) || !store_updates_sp(regs))) goto bad_area; } - if (expand_stack(vma, address)) - goto bad_area; + vma = expand_stack(mm, address); + if (!vma) + goto bad_area_nosemaphore;

good_area: code = SEGV_ACCERR; --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -127,8 +127,9 @@ retry: if (address + PAGE_SIZE < regs->sp) goto bad_area; } - if (expand_stack(vma, address)) - goto bad_area; + vma = expand_stack(mm, address); + if (!vma) + goto bad_area_nosemaphore;

/* * Ok, we have a good vm_area for this memory access, so --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -288,15 +288,19 @@ void do_page_fault(struct pt_regs *regs, retry: mmap_read_lock(mm); vma = find_vma_prev(mm, address, &prev_vma); - if (!vma || address < vma->vm_start) - goto check_expansion; + if (!vma || address < vma->vm_start) { + if (!prev || !(prev->vm_flags & VM_GROWSUP)) + goto bad_area; + vma = expand_stack(mm, address); + if (!vma) + goto bad_area_nosemaphore; + } + /* * Ok, we have a good vm_area for this memory access. We still need to * check the access permissions. */

-good_area: - if ((vma->vm_flags & acc_type) != acc_type) goto bad_area;

@@ -342,17 +346,13 @@ good_area: mmap_read_unlock(mm); return;

-check_expansion: - vma = prev_vma; - if (vma && (expand_stack(vma, address) == 0)) - goto good_area; - /* * Something tried to access memory that isn't in our memory map.. */ bad_area: mmap_read_unlock(mm);

+bad_area_nosemaphore: if (user_mode(regs)) { int signo, si_code;

@@ -444,7 +444,7 @@ handle_nadtlb_fault(struct pt_regs *regs { unsigned long insn = regs->iir; int breg, treg, xreg, val = 0; - struct vm_area_struct *vma, *prev_vma; + struct vm_area_struct *vma; struct task_struct *tsk; struct mm_struct *mm; unsigned long address; @@ -480,7 +480,7 @@ handle_nadtlb_fault(struct pt_regs *regs /* Search for VMA */ address = regs->ior; mmap_read_lock(mm); - vma = find_vma_prev(mm, address, &prev_vma); + vma = vma_lookup(mm, address); mmap_read_unlock(mm);

/* @@ -489,7 +489,6 @@ handle_nadtlb_fault(struct pt_regs *regs */ acc_type = (insn & 0x40) ? VM_WRITE : VM_READ; if (vma - && address >= vma->vm_start && (vma->vm_flags & acc_type) == acc_type) val = 1; } --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -429,8 +429,9 @@ retry: if (unlikely(vma->vm_start > address)) { if (!(vma->vm_flags & VM_GROWSDOWN)) goto out_up; - if (expand_stack(vma, address)) - goto out_up; + vma = expand_stack(mm, address); + if (!vma) + goto out; }

/* --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -383,8 +383,9 @@ continue_fault: goto bad_area; } } - if (expand_stack(vma, address)) - goto bad_area; + vma = expand_stack(mm, address); + if (!vma) + goto bad_area_nosemaphore; /* * Ok, we have a good vm_area for this memory access, so * we can handle it.. @@ -482,8 +483,9 @@ exit_exception: * Fix it, but check if it's kernel or user first.. */ bad_area: - insn = get_fault_insn(regs, insn); mmap_read_unlock(mm); +bad_area_nosemaphore: + insn = get_fault_insn(regs, insn);

handle_kernel_fault: do_kernel_fault(regs, si_code, fault_code, insn, address); --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -47,14 +47,15 @@ retry: vma = find_vma(mm, address); if (!vma) goto out; - else if (vma->vm_start <= address) + if (vma->vm_start <= address) goto good_area; - else if (!(vma->vm_flags & VM_GROWSDOWN)) + if (!(vma->vm_flags & VM_GROWSDOWN)) goto out; - else if (is_user && !ARCH_IS_STACKGROW(address)) - goto out; - else if (expand_stack(vma, address)) + if (is_user && !ARCH_IS_STACKGROW(address)) goto out; + vma = expand_stack(mm, address); + if (!vma) + goto out_nosemaphore;

good_area: *code_out = SEGV_ACCERR; --- a/drivers/iommu/amd/iommu_v2.c +++ b/drivers/iommu/amd/iommu_v2.c @@ -485,8 +485,8 @@ static void do_fault(struct work_struct flags |= FAULT_FLAG_REMOTE;

mmap_read_lock(mm); - vma = find_extend_vma(mm, address); - if (!vma || address < vma->vm_start) + vma = vma_lookup(mm, address); + if (!vma) /* failed to get a vma in the right range */ goto out;

--- a/drivers/iommu/io-pgfault.c +++ b/drivers/iommu/io-pgfault.c @@ -89,7 +89,7 @@ iopf_handle_single(struct iopf_fault *io

mmap_read_lock(mm);

- vma = find_extend_vma(mm, prm->addr); + vma = vma_lookup(mm, prm->addr); if (!vma) /* Unmapped area */ goto out_put_mm; --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -317,7 +317,7 @@ create_elf_tables(struct linux_binprm *b */ if (mmap_write_lock_killable(mm)) return -EINTR; - vma = find_extend_vma_locked(mm, bprm->p, true); + vma = find_extend_vma_locked(mm, bprm->p); mmap_write_unlock(mm); if (!vma) return -EFAULT; --- a/fs/exec.c +++ b/fs/exec.c @@ -209,7 +209,7 @@ static struct page *get_arg_page(struct */ if (write && pos < vma->vm_start) { mmap_write_lock(mm); - ret = expand_downwards(vma, pos, true); + ret = expand_downwards(vma, pos); if (unlikely(ret < 0)) { mmap_write_unlock(mm); return NULL; @@ -860,7 +860,7 @@ int setup_arg_pages(struct linux_binprm stack_base = vma->vm_start - stack_expand; #endif current->mm->start_stack = bprm->p; - ret = expand_stack_locked(vma, stack_base, true); + ret = expand_stack_locked(vma, stack_base); if (ret) ret = -EFAULT;

--- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2810,18 +2810,11 @@ extern vm_fault_t filemap_page_mkwrite(s

extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ -int expand_stack_locked(struct vm_area_struct *vma, unsigned long address, - bool write_locked); -#define expand_stack(vma,addr) expand_stack_locked(vma,addr,false) +int expand_stack_locked(struct vm_area_struct *vma, unsigned long address); +struct vm_area_struct *expand_stack(struct mm_struct * mm, unsigned long addr);

/* CONFIG_STACK_GROWSUP still needs to grow downwards at some places */ -int expand_downwards(struct vm_area_struct *vma, unsigned long address, - bool write_locked); -#if VM_GROWSUP -extern int expand_upwards(struct vm_area_struct *vma, unsigned long address); -#else - #define expand_upwards(vma, address) (0) -#endif +int expand_downwards(struct vm_area_struct *vma, unsigned long address);

/* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr); @@ -2916,9 +2909,8 @@ unsigned long change_prot_numa(struct vm unsigned long start, unsigned long end); #endif

-struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr); struct vm_area_struct *find_extend_vma_locked(struct mm_struct *, - unsigned long addr, bool write_locked); + unsigned long addr); int remap_pfn_range(struct vm_area_struct *, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t); int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr, --- a/mm/gup.c +++ b/mm/gup.c @@ -1182,7 +1182,7 @@ static long __get_user_pages(struct mm_s

/* first iteration or cross vma bound */ if (!vma || start >= vma->vm_end) { - vma = find_extend_vma(mm, start); + vma = vma_lookup(mm, start); if (!vma && in_gate_area(mm, start)) { ret = get_gate_page(mm, start & PAGE_MASK, gup_flags, &vma, @@ -1351,8 +1351,8 @@ int fixup_user_fault(struct mm_struct *m fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

retry: - vma = find_extend_vma(mm, address); - if (!vma || address < vma->vm_start) + vma = vma_lookup(mm, address); + if (!vma) return -EFAULT;

if (!vma_permits_fault(vma, fault_flags)) --- a/mm/memory.c +++ b/mm/memory.c @@ -5364,7 +5364,7 @@ struct vm_area_struct *lock_mm_and_find_ goto fail; }

- if (expand_stack_locked(vma, addr, true)) + if (expand_stack_locked(vma, addr)) goto fail;

success: @@ -5648,6 +5648,14 @@ int __access_remote_vm(struct mm_struct if (mmap_read_lock_killable(mm)) return 0;

+ /* We might need to expand the stack to access it */ + vma = vma_lookup(mm, addr); + if (!vma) { + vma = expand_stack(mm, addr); + if (!vma) + return 0; + } + /* ignore errors, just check how much was successfully transferred */ while (len) { int bytes, ret, offset; --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1945,8 +1945,7 @@ static int acct_stack_growth(struct vm_a * PA-RISC uses this for its stack; IA64 for its Register Backing Store. * vma is the last one with address > vma->vm_end. Have to extend vma. */ -int expand_upwards(struct vm_area_struct *vma, unsigned long address, - bool write_locked) +static int expand_upwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *next; @@ -1970,8 +1969,6 @@ int expand_upwards(struct vm_area_struct if (gap_addr < address || gap_addr > TASK_SIZE) gap_addr = TASK_SIZE;

- if (!write_locked) - return -EAGAIN; next = find_vma_intersection(mm, vma->vm_end, gap_addr); if (next && vma_is_accessible(next)) { if (!(next->vm_flags & VM_GROWSUP)) @@ -2039,15 +2036,18 @@ int expand_upwards(struct vm_area_struct

/* * vma is the first one with address < vma->vm_start. Have to extend vma. + * mmap_lock held for writing. */ -int expand_downwards(struct vm_area_struct *vma, unsigned long address, - bool write_locked) +int expand_downwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; MA_STATE(mas, &mm->mm_mt, vma->vm_start, vma->vm_start); struct vm_area_struct *prev; int error = 0;

+ if (!(vma->vm_flags & VM_GROWSDOWN)) + return -EFAULT; + address &= PAGE_MASK; if (address < mmap_min_addr || address < FIRST_USER_ADDRESS) return -EPERM; @@ -2060,8 +2060,6 @@ int expand_downwards(struct vm_area_stru vma_is_accessible(prev) && (address - prev->vm_end < stack_guard_gap)) return -ENOMEM; - if (!write_locked && (prev->vm_end == address)) - return -EAGAIN; }

if (mas_preallocate(&mas, vma, GFP_KERNEL)) @@ -2139,14 +2137,12 @@ static int __init cmdline_parse_stack_gu __setup("stack_guard_gap=", cmdline_parse_stack_guard_gap);

#ifdef CONFIG_STACK_GROWSUP -int expand_stack_locked(struct vm_area_struct *vma, unsigned long address, - bool write_locked) +int expand_stack_locked(struct vm_area_struct *vma, unsigned long address) { - return expand_upwards(vma, address, write_locked); + return expand_upwards(vma, address); }

-struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, - unsigned long addr, bool write_locked) +struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma, *prev;

@@ -2156,23 +2152,21 @@ struct vm_area_struct *find_extend_vma_l return vma; if (!prev) return NULL; - if (expand_stack_locked(prev, addr, write_locked)) + if (expand_stack_locked(prev, addr)) return NULL; if (prev->vm_flags & VM_LOCKED) populate_vma_page_range(prev, addr, prev->vm_end, NULL); return prev; } #else -int expand_stack_locked(struct vm_area_struct *vma, unsigned long address, - bool write_locked) +int expand_stack_locked(struct vm_area_struct *vma, unsigned long address) { if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) return -EINVAL; - return expand_downwards(vma, address, write_locked); + return expand_downwards(vma, address); }

-struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, - unsigned long addr, bool write_locked) +struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma; unsigned long start; @@ -2184,7 +2178,7 @@ struct vm_area_struct *find_extend_vma_l if (vma->vm_start <= addr) return vma; start = vma->vm_start; - if (expand_stack_locked(vma, addr, write_locked)) + if (expand_stack_locked(vma, addr)) return NULL; if (vma->vm_flags & VM_LOCKED) populate_vma_page_range(vma, addr, start, NULL); @@ -2192,12 +2186,91 @@ struct vm_area_struct *find_extend_vma_l } #endif

-struct vm_area_struct *find_extend_vma(struct mm_struct *mm, - unsigned long addr) +/* + * IA64 has some horrid mapping rules: it can expand both up and down, + * but with various special rules. + * + * We'll get rid of this architecture eventually, so the ugliness is + * temporary. + */ +#ifdef CONFIG_IA64 +static inline bool vma_expand_ok(struct vm_area_struct *vma, unsigned long addr) +{ + return REGION_NUMBER(addr) == REGION_NUMBER(vma->vm_start) && + REGION_OFFSET(addr) < RGN_MAP_LIMIT; +} + +/* + * IA64 stacks grow down, but there's a special register backing store + * that can grow up. Only sequentially, though, so the new address must + * match vm_end. + */ +static inline int vma_expand_up(struct vm_area_struct *vma, unsigned long addr) +{ + if (!vma_expand_ok(vma, addr)) + return -EFAULT; + if (vma->vm_end != (addr & PAGE_MASK)) + return -EFAULT; + return expand_upwards(vma, addr); +} + +static inline bool vma_expand_down(struct vm_area_struct *vma, unsigned long addr) +{ + if (!vma_expand_ok(vma, addr)) + return -EFAULT; + return expand_downwards(vma, addr); +} + +#elif defined(CONFIG_STACK_GROWSUP) + +#define vma_expand_up(vma,addr) expand_upwards(vma, addr) +#define vma_expand_down(vma, addr) (-EFAULT) + +#else + +#define vma_expand_up(vma,addr) (-EFAULT) +#define vma_expand_down(vma, addr) expand_downwards(vma, addr) + +#endif + +/* + * expand_stack(): legacy interface for page faulting. Don't use unless + * you have to. + * + * This is called with the mm locked for reading, drops the lock, takes + * the lock for writing, tries to look up a vma again, expands it if + * necessary, and downgrades the lock to reading again. + * + * If no vma is found or it can't be expanded, it returns NULL and has + * dropped the lock. + */ +struct vm_area_struct *expand_stack(struct mm_struct *mm, unsigned long addr) { - return find_extend_vma_locked(mm, addr, false); + struct vm_area_struct *vma, *prev; + + mmap_read_unlock(mm); + if (mmap_write_lock_killable(mm)) + return NULL; + + vma = find_vma_prev(mm, addr, &prev); + if (vma && vma->vm_start <= addr) + goto success; + + if (prev && !vma_expand_up(prev, addr)) { + vma = prev; + goto success; + } + + if (vma && !vma_expand_down(vma, addr)) + goto success; + + mmap_write_unlock(mm); + return NULL; + +success: + mmap_write_downgrade(mm); + return vma; } -EXPORT_SYMBOL_GPL(find_extend_vma);

/* * Ok - we have the memory areas we should free on a maple tree so release them, --- a/mm/nommu.c +++ b/mm/nommu.c @@ -682,24 +682,20 @@ struct vm_area_struct *find_vma(struct m EXPORT_SYMBOL(find_vma);

/* - * find a VMA - * - we don't extend stack VMAs under NOMMU conditions - */ -struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr) -{ - return find_vma(mm, addr); -} - -/* * expand a stack to a given address * - not supported under NOMMU conditions */ -int expand_stack_locked(struct vm_area_struct *vma, unsigned long address, - bool write_locked) +int expand_stack_locked(struct vm_area_struct *vma, unsigned long addr) { return -ENOMEM; }

+struct vm_area_struct *expand_stack(struct mm_struct *mm, unsigned long addr) +{ + mmap_read_unlock(mm); + return NULL; +} + /* * look up the first VMA exactly that exactly matches addr * - should be called with mm->mmap_lock at least held readlocked

From: Ludvig Michaelsson ludvig.michaelsson@yubico.com

commit 944ee77dc6ec7b0afd8ec70ffc418b238c92f12b upstream.

The hidraw_open() function increments the hidraw device reference counter. The counter has no dedicated synchronization mechanism, resulting in a potential data race when concurrently opening a device.

The race is a regression introduced by commit 8590222e4b02 ("HID: hidraw: Replace hidraw device table mutex with a rwsem"). While minors_rwsem is intended to protect the hidraw_table itself, by instead acquiring the lock for writing, the reference counter is also protected. This is symmetrical to hidraw_release().

Link: https://github.com/systemd/systemd/issues/27947 Fixes: 8590222e4b02 ("HID: hidraw: Replace hidraw device table mutex with a rwsem") Cc: stable@vger.kernel.org Signed-off-by: Ludvig Michaelsson ludvig.michaelsson@yubico.com Link: https://lore.kernel.org/r/20230621-hidraw-race-v1-1-a58e6ac69bab@yubico.com Signed-off-by: Benjamin Tissoires benjamin.tissoires@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/hid/hidraw.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)

--- a/drivers/hid/hidraw.c +++ b/drivers/hid/hidraw.c @@ -272,7 +272,12 @@ static int hidraw_open(struct inode *ino goto out; }

- down_read(&minors_rwsem); + /* + * Technically not writing to the hidraw_table but a write lock is + * required to protect the device refcount. This is symmetrical to + * hidraw_release(). + */ + down_write(&minors_rwsem); if (!hidraw_table[minor] || !hidraw_table[minor]->exist) { err = -ENODEV; goto out_unlock; @@ -301,7 +306,7 @@ static int hidraw_open(struct inode *ino spin_unlock_irqrestore(&hidraw_table[minor]->list_lock, flags); file->private_data = list; out_unlock: - up_read(&minors_rwsem); + up_write(&minors_rwsem); out: if (err < 0) kfree(list);

From: Mike Hommey mh@glandium.org

commit 5fe251112646d8626818ea90f7af325bab243efa upstream.

commit 498ba2069035 ("HID: logitech-hidpp: Don't restart communication if not necessary") put restarting communication behind that flag, and this was apparently necessary on the T651, but the flag was not set for it.

Fixes: 498ba2069035 ("HID: logitech-hidpp: Don't restart communication if not necessary") Cc: stable@vger.kernel.org Signed-off-by: Mike Hommey mh@glandium.org Link: https://lore.kernel.org/r/20230617230957.6mx73th4blv7owqk@glandium.org Signed-off-by: Benjamin Tissoires benjamin.tissoires@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/hid/hid-logitech-hidpp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -4348,7 +4348,7 @@ static const struct hid_device_id hidpp_ { /* wireless touchpad T651 */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_T651), - .driver_data = HIDPP_QUIRK_CLASS_WTP }, + .driver_data = HIDPP_QUIRK_CLASS_WTP | HIDPP_QUIRK_DELAYED_INIT }, { /* Mouse Logitech Anywhere MX */ LDJ_DEVICE(0x1017), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_1P0 }, { /* Mouse logitech M560 */