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. ] Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/mmap.c | 29 +++++++++++------------------ 1 file changed, 11 insertions(+), 18 deletions(-)

--- a/mm/mmap.c +++ b/mm/mmap.c @@ -2280,19 +2280,6 @@ int split_vma(struct vma_iterator *vmi, return __split_vma(vmi, 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_vmi_align_munmap() - munmap the aligned region from @start to @end. * @vmi: The vma iterator @@ -2314,6 +2301,7 @@ do_vmi_align_munmap(struct vma_iterator 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, vmi->mas.tree->ma_flags & MT_FLAGS_LOCK_MASK); mt_set_external_lock(&mt_detach, &mm->mmap_lock); @@ -2359,9 +2347,11 @@ do_vmi_align_munmap(struct vma_iterator if (error) goto end_split_failed; } - 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 @@ -2407,10 +2397,12 @@ do_vmi_align_munmap(struct vma_iterator } #endif /* Point of no return */ + error = -ENOMEM; vma_iter_set(vmi, start); if (vma_iter_clear_gfp(vmi, start, end, GFP_KERNEL)) - return -ENOMEM; + goto clear_tree_failed;

+ mm->locked_vm -= locked_vm; mm->map_count -= count; /* * Do not downgrade mmap_lock if we are next to VM_GROWSDOWN or @@ -2440,8 +2432,9 @@ do_vmi_align_munmap(struct vma_iterator validate_mm(mm); return downgrade ? 1 : 0;

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

From: Borislav Petkov (AMD) bp@alien8.de

commit a32b0f0db3f396f1c9be2fe621e77c09ec3d8e7d upstream.

Do the same as early loading - load on both threads.

Signed-off-by: Borislav Petkov (AMD) bp@alien8.de Cc: stable@kernel.org Link: https://lore.kernel.org/r/20230605141332.25948-1-bp@alien8.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/cpu/microcode/amd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -705,7 +705,7 @@ static enum ucode_state apply_microcode_ rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);

/* need to apply patch? */ - if (rev >= mc_amd->hdr.patch_id) { + if (rev > mc_amd->hdr.patch_id) { ret = UCODE_OK; goto out; }

From: Tony Battersby tonyb@cybernetics.com

commit 9b040453d4440659f33dc6f0aa26af418ebfe70b upstream.

stop_this_cpu() tests CPUID leaf 0x8000001f::EAX unconditionally. Intel CPUs return the content of the highest supported leaf when a non-existing leaf is read, while AMD CPUs return all zeros for unsupported leafs.

So the result of the test on Intel CPUs is lottery.

While harmless it's incorrect and causes the conditional wbinvd() to be issued where not required.

Check whether the leaf is supported before reading it.

[ tglx: Adjusted changelog ]

Fixes: 08f253ec3767 ("x86/cpu: Clear SME feature flag when not in use") Signed-off-by: Tony Battersby tonyb@cybernetics.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Mario Limonciello mario.limonciello@amd.com Reviewed-by: Borislav Petkov (AMD) bp@alien8.de Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/3817d810-e0f1-8ef8-0bbd-663b919ca49b@cybernetics.c... Link: https://lore.kernel.org/r/20230615193330.322186388@linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/process.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

--- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -756,6 +756,7 @@ struct cpumask cpus_stop_mask;

void __noreturn stop_this_cpu(void *dummy) { + struct cpuinfo_x86 *c = this_cpu_ptr(&cpu_info); unsigned int cpu = smp_processor_id();

local_irq_disable(); @@ -770,7 +771,7 @@ void __noreturn stop_this_cpu(void *dumm */ set_cpu_online(cpu, false); disable_local_APIC(); - mcheck_cpu_clear(this_cpu_ptr(&cpu_info)); + mcheck_cpu_clear(c);

/* * Use wbinvd on processors that support SME. This provides support @@ -784,7 +785,7 @@ void __noreturn stop_this_cpu(void *dumm * Test the CPUID bit directly because the machine might've cleared * X86_FEATURE_SME due to cmdline options. */ - if (cpuid_eax(0x8000001f) & BIT(0)) + if (c->extended_cpuid_level >= 0x8000001f && (cpuid_eax(0x8000001f) & BIT(0))) native_wbinvd();

/*

From: Thomas Gleixner tglx@linutronix.de

commit f9c9987bf52f4e42e940ae217333ebb5a4c3b506 upstream.

Monitoring idletask::thread_info::flags in mwait_play_dead() has been an obvious choice as all what is needed is a cache line which is not written by other CPUs.

But there is a use case where a "dead" CPU needs to be brought out of MWAIT: kexec().

This is required as kexec() can overwrite text, pagetables, stacks and the monitored cacheline of the original kernel. The latter causes MWAIT to resume execution which obviously causes havoc on the kexec kernel which results usually in triple faults.

Use a dedicated per CPU storage to prepare for that.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Ashok Raj ashok.raj@intel.com Reviewed-by: Borislav Petkov (AMD) bp@alien8.de Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230615193330.434553750@linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/smpboot.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-)

--- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -101,6 +101,17 @@ EXPORT_PER_CPU_SYMBOL(cpu_die_map); DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); EXPORT_PER_CPU_SYMBOL(cpu_info);

+struct mwait_cpu_dead { + unsigned int control; + unsigned int status; +}; + +/* + * Cache line aligned data for mwait_play_dead(). Separate on purpose so + * that it's unlikely to be touched by other CPUs. + */ +static DEFINE_PER_CPU_ALIGNED(struct mwait_cpu_dead, mwait_cpu_dead); + /* Logical package management. We might want to allocate that dynamically */ unsigned int __max_logical_packages __read_mostly; EXPORT_SYMBOL(__max_logical_packages); @@ -1750,10 +1761,10 @@ EXPORT_SYMBOL_GPL(cond_wakeup_cpu0); */ static inline void mwait_play_dead(void) { + struct mwait_cpu_dead *md = this_cpu_ptr(&mwait_cpu_dead); unsigned int eax, ebx, ecx, edx; unsigned int highest_cstate = 0; unsigned int highest_subcstate = 0; - void *mwait_ptr; int i;

if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || @@ -1788,13 +1799,6 @@ static inline void mwait_play_dead(void) (highest_subcstate - 1); }

- /* - * This should be a memory location in a cache line which is - * unlikely to be touched by other processors. The actual - * content is immaterial as it is not actually modified in any way. - */ - mwait_ptr = &current_thread_info()->flags; - wbinvd();

while (1) { @@ -1806,9 +1810,9 @@ static inline void mwait_play_dead(void) * case where we return around the loop. */ mb(); - clflush(mwait_ptr); + clflush(md); mb(); - __monitor(mwait_ptr, 0, 0); + __monitor(md, 0, 0); mb(); __mwait(eax, 0);

From: Wyes Karny wyes.karny@amd.com

commit f4aad639302a07454dcb23b408dcadf8a9efb031 upstream.

amd-pstate passive mode driver is hyphenated. So make amd-pstate active mode driver consistent with that rename "amd_pstate_epp" to "amd-pstate-epp".

Fixes: ffa5096a7c33 ("cpufreq: amd-pstate: implement Pstate EPP support for the AMD processors") Cc: All applicable stable@vger.kernel.org Reviewed-by: Gautham R. Shenoy gautham.shenoy@amd.com Signed-off-by: Wyes Karny wyes.karny@amd.com Acked-by: Huang Rui ray.huang@amd.com Reviewed-by: Perry Yuan Perry.Yuan@amd.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/cpufreq/amd-pstate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -1272,7 +1272,7 @@ static struct cpufreq_driver amd_pstate_ .online = amd_pstate_epp_cpu_online, .suspend = amd_pstate_epp_suspend, .resume = amd_pstate_epp_resume, - .name = "amd_pstate_epp", + .name = "amd-pstate-epp", .attr = amd_pstate_epp_attr, };

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 @@ -4287,11 +4287,13 @@ 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; }

@@ -4448,7 +4450,6 @@ 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: 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 @@ -5247,8 +5247,7 @@ 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) @@ -5272,8 +5271,7 @@ 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: 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 @@ -263,6 +263,7 @@ 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 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 @@ -119,6 +119,7 @@ config RISCV select HAVE_SYSCALL_TRACEPOINTS 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; @@ -286,23 +295,10 @@ 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; }

@@ -310,7 +306,6 @@ 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: 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 @@ -29,6 +29,7 @@ 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)) @@ -192,6 +184,7 @@ 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_REGS_AND_STACK_ACCESS_API 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;

@@ -143,6 +132,7 @@ 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 @@ -125,6 +125,7 @@ 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 @@ -169,22 +169,18 @@ 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)) @@ -321,17 +312,9 @@ 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)) @@ -350,6 +333,7 @@ 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)) { force_sig_fault(SIGSEGV, code, (void *) address); return;

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: 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 @@ -320,10 +320,10 @@ 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 @@ -204,7 +204,8 @@ 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; } @@ -852,7 +853,7 @@ int setup_arg_pages(struct linux_binprm stack_base = vma->vm_end - 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 @@ -3065,11 +3065,13 @@ 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 @@ -3170,6 +3172,8 @@ 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 @@ -5336,7 +5336,7 @@ 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 @@ -1898,7 +1898,8 @@ 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; @@ -1922,6 +1923,8 @@ 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)) @@ -1991,7 +1994,8 @@ 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); @@ -2005,10 +2009,13 @@ 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, GFP_KERNEL)) @@ -2087,13 +2094,14 @@ 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;

@@ -2101,20 +2109,25 @@ 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; @@ -2125,10 +2138,8 @@ 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); @@ -2136,6 +2147,11 @@ 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 @@ -643,7 +643,8 @@ 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.

Tested-by: Vegard Nossum vegard.nossum@oracle.com Tested-by: John Paul Adrian Glaubitz glaubitz@physik.fu-berlin.de # ia64 Tested-by: Frank Scheiner frank.scheiner@web.de # ia64 Signed-off-by: Linus Torvalds torvalds@linux-foundation.org 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/iommu-sva.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: */ @@ -177,35 +179,9 @@ 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 @@ -196,10 +197,12 @@ 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;

@@ -347,17 +351,13 @@ 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;

@@ -449,7 +449,7 @@ 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; @@ -485,7 +485,7 @@ 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);

/* @@ -494,7 +494,6 @@ 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 @@ -433,8 +433,9 @@ 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.. @@ -487,8 +488,9 @@ 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/iommu-sva.c +++ b/drivers/iommu/iommu-sva.c @@ -203,7 +203,7 @@ iommu_sva_handle_iopf(struct iommu_fault

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 @@ -322,7 +322,7 @@ 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 @@ -210,7 +210,7 @@ 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; @@ -858,7 +858,7 @@ int setup_arg_pages(struct linux_binprm stack_base = vma->vm_end - 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 @@ -3065,18 +3065,11 @@ 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); @@ -3171,9 +3164,8 @@ 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 @@ -1096,7 +1096,7 @@ 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, @@ -1265,8 +1265,8 @@ 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 @@ -5336,7 +5336,7 @@ 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: @@ -5620,6 +5620,14 @@ 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 @@ -1898,8 +1898,7 @@ 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; @@ -1923,8 +1922,6 @@ 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)) @@ -1993,15 +1990,18 @@ 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; @@ -2014,8 +2014,6 @@ 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, GFP_KERNEL)) @@ -2094,14 +2092,12 @@ 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;

@@ -2111,23 +2107,21 @@ 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; @@ -2139,7 +2133,7 @@ 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); @@ -2147,12 +2141,91 @@ 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 @@ -631,24 +631,20 @@ 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: Zhang Shurong zhang_shurong@foxmail.com

commit c2d22806aecb24e2de55c30a06e5d6eb297d161d upstream.

There is a potential OOB read at fast_imageblit, for "colortab[(*src >> 4)]" can become a negative value due to "const char *s = image->data, *src". This change makes sure the index for colortab always positive or zero.

Similar commit: https://patchwork.kernel.org/patch/11746067

Potential bug report: https://groups.google.com/g/syzkaller-bugs/c/9ubBXKeKXf4/m/k-QXy4UgAAAJ

Signed-off-by: Zhang Shurong zhang_shurong@foxmail.com Cc: stable@vger.kernel.org Signed-off-by: Helge Deller deller@gmx.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/video/fbdev/core/sysimgblt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/video/fbdev/core/sysimgblt.c +++ b/drivers/video/fbdev/core/sysimgblt.c @@ -189,7 +189,7 @@ static void fast_imageblit(const struct u32 fgx = fgcolor, bgx = bgcolor, bpp = p->var.bits_per_pixel; u32 ppw = 32/bpp, spitch = (image->width + 7)/8; u32 bit_mask, eorx, shift; - const char *s = image->data, *src; + const u8 *s = image->data, *src; u32 *dst; const u32 *tab; size_t tablen;

From: Jason Gerecke jason.gerecke@wacom.com

commit 9a6c0e28e215535b2938c61ded54603b4e5814c5 upstream.

Code which interacts with timestamps needs to use the ktime_t type returned by functions like ktime_get. The int type does not offer enough space to store these values, and attempting to use it is a recipe for problems. In this particular case, overflows would occur when calculating/storing timestamps leading to incorrect values being reported to userspace. In some cases these bad timestamps cause input handling in userspace to appear hung.

Link: https://gitlab.freedesktop.org/libinput/libinput/-/issues/901 Fixes: 17d793f3ed53 ("HID: wacom: insert timestamp to packed Bluetooth (BT) events") CC: stable@vger.kernel.org Signed-off-by: Jason Gerecke jason.gerecke@wacom.com Reviewed-by: Benjamin Tissoires benjamin.tissoires@redhat.com Link: https://lore.kernel.org/r/20230608213828.2108-1-jason.gerecke@wacom.com Signed-off-by: Benjamin Tissoires bentiss@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/hid/wacom_wac.c | 6 +++--- drivers/hid/wacom_wac.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-)

--- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -1309,7 +1309,7 @@ static void wacom_intuos_pro2_bt_pen(str struct input_dev *pen_input = wacom->pen_input; unsigned char *data = wacom->data; int number_of_valid_frames = 0; - int time_interval = 15000000; + ktime_t time_interval = 15000000; ktime_t time_packet_received = ktime_get(); int i;

@@ -1343,7 +1343,7 @@ static void wacom_intuos_pro2_bt_pen(str if (number_of_valid_frames) { if (wacom->hid_data.time_delayed) time_interval = ktime_get() - wacom->hid_data.time_delayed; - time_interval /= number_of_valid_frames; + time_interval = div_u64(time_interval, number_of_valid_frames); wacom->hid_data.time_delayed = time_packet_received; }

@@ -1354,7 +1354,7 @@ static void wacom_intuos_pro2_bt_pen(str bool range = frame[0] & 0x20; bool invert = frame[0] & 0x10; int frames_number_reversed = number_of_valid_frames - i - 1; - int event_timestamp = time_packet_received - frames_number_reversed * time_interval; + ktime_t event_timestamp = time_packet_received - frames_number_reversed * time_interval;

if (!valid) continue; --- a/drivers/hid/wacom_wac.h +++ b/drivers/hid/wacom_wac.h @@ -324,7 +324,7 @@ struct hid_data { int ps_connected; bool pad_input_event_flag; unsigned short sequence_number; - int time_delayed; + ktime_t time_delayed; };

struct wacom_remote_data {

From: Ricardo Cañuelo ricardo.canuelo@collabora.com

commit 86edac7d3888c715fe3a81bd61f3617ecfe2e1dd upstream.

This reverts commit f05c7b7d9ea9477fcc388476c6f4ade8c66d2d26.

That change was causing a regression in the generic-adc-thermal-probed bootrr test as reported in the kernelci-results list [1]. A proper rework will take longer, so revert it for now.

[1] https://groups.io/g/kernelci-results/message/42660

Fixes: f05c7b7d9ea9 ("thermal/drivers/mediatek: Use devm_of_iomap to avoid resource leak in mtk_thermal_probe") Signed-off-by: Ricardo Cañuelo ricardo.canuelo@collabora.com Suggested-by: AngeloGioacchino Del Regno angelogioacchino.delregno@collabora.com Reviewed-by: AngeloGioacchino Del Regno angelogioacchino.delregno@collabora.com Signed-off-by: Daniel Lezcano daniel.lezcano@linaro.org Link: https://lore.kernel.org/r/20230525121811.3360268-1-ricardo.canuelo@collabora... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/thermal/mediatek/auxadc_thermal.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-)

--- a/drivers/thermal/mediatek/auxadc_thermal.c +++ b/drivers/thermal/mediatek/auxadc_thermal.c @@ -1142,12 +1142,7 @@ static int mtk_thermal_probe(struct plat return -ENODEV; }

- auxadc_base = devm_of_iomap(&pdev->dev, auxadc, 0, NULL); - if (IS_ERR(auxadc_base)) { - of_node_put(auxadc); - return PTR_ERR(auxadc_base); - } - + auxadc_base = of_iomap(auxadc, 0); auxadc_phys_base = of_get_phys_base(auxadc);

of_node_put(auxadc); @@ -1163,12 +1158,7 @@ static int mtk_thermal_probe(struct plat return -ENODEV; }

- apmixed_base = devm_of_iomap(&pdev->dev, apmixedsys, 0, NULL); - if (IS_ERR(apmixed_base)) { - of_node_put(apmixedsys); - return PTR_ERR(apmixed_base); - } - + apmixed_base = of_iomap(apmixedsys, 0); apmixed_phys_base = of_get_phys_base(apmixedsys);

of_node_put(apmixedsys);