6.1.37-rc1 review

@@ -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:

@@ -2404,7 +2404,8 @@ do_mas_align_munmap(struct ma_state *mas
 			break;
 		}
 		mas_set_range(&mas_detach, next->vm_start, next->vm_end - 1);
-		if (mas_store_gfp(&mas_detach, next, GFP_KERNEL))
+		error = mas_store_gfp(&mas_detach, next, GFP_KERNEL);
+		if (error)
 			goto munmap_gather_failed;
 		if (next->vm_flags & VM_LOCKED)
 			locked_vm += vma_pages(next);

@@ -2456,6 +2457,7 @@ do_mas_align_munmap(struct ma_state *mas
 		mas_set_range(mas, start, end - 1);
 	}
 #endif
+	/* Point of no return */
 	mas_store_prealloc(mas, NULL);
 
 	mm->locked_vm -= locked_vm;

@@ -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);

@@ -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);

@@ -319,6 +319,32 @@ static inline void copy_user_highpage(st
 
 #endif
 
+#ifdef copy_mc_to_kernel
+static inline int copy_mc_user_highpage(struct page *to, struct page *from,
+					unsigned long vaddr, struct vm_area_struct *vma)
+{
+	unsigned long ret;
+	char *vfrom, *vto;
+
+	vfrom = kmap_local_page(from);
+	vto = kmap_local_page(to);
+	ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE);
+	if (!ret)
+		kmsan_unpoison_memory(page_address(to), PAGE_SIZE);
+	kunmap_local(vto);
+	kunmap_local(vfrom);
+
+	return ret;
+}
+#else
+static inline int copy_mc_user_highpage(struct page *to, struct page *from,
+					unsigned long vaddr, struct vm_area_struct *vma)
+{
+	copy_user_highpage(to, from, vaddr, vma);
+	return 0;
+}
+#endif
+
 #ifndef __HAVE_ARCH_COPY_HIGHPAGE
 
 static inline void copy_highpage(struct page *to, struct page *from)

@@ -2843,10 +2843,16 @@ static inline int pte_unmap_same(struct
 	return same;
 }
 
-static inline bool __wp_page_copy_user(struct page *dst, struct page *src,
-				       struct vm_fault *vmf)
+/*
+ * Return:
+ *	0:		copied succeeded
+ *	-EHWPOISON:	copy failed due to hwpoison in source page
+ *	-EAGAIN:	copied failed (some other reason)
+ */
+static inline int __wp_page_copy_user(struct page *dst, struct page *src,
+				      struct vm_fault *vmf)
 {
-	bool ret;
+	int ret;
 	void *kaddr;
 	void __user *uaddr;
 	bool locked = false;

@@ -2855,8 +2861,9 @@ static inline bool __wp_page_copy_user(s
 	unsigned long addr = vmf->address;
 
 	if (likely(src)) {
-		copy_user_highpage(dst, src, addr, vma);
-		return true;
+		if (copy_mc_user_highpage(dst, src, addr, vma))
+			return -EHWPOISON;
+		return 0;
 	}
 
 	/*

@@ -2883,7 +2890,7 @@ static inline bool __wp_page_copy_user(s
 			 * and update local tlb only
 			 */
 			update_mmu_tlb(vma, addr, vmf->pte);
-			ret = false;
+			ret = -EAGAIN;
 			goto pte_unlock;
 		}
 

@@ -2908,7 +2915,7 @@ static inline bool __wp_page_copy_user(s
 		if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) {
 			/* The PTE changed under us, update local tlb */
 			update_mmu_tlb(vma, addr, vmf->pte);
-			ret = false;
+			ret = -EAGAIN;
 			goto pte_unlock;
 		}
 

@@ -2927,7 +2934,7 @@ warn:
 		}
 	}
 
-	ret = true;
+	ret = 0;
 
 pte_unlock:
 	if (locked)

@@ -3099,6 +3106,7 @@ static vm_fault_t wp_page_copy(struct vm
 	pte_t entry;
 	int page_copied = 0;
 	struct mmu_notifier_range range;
+	int ret;
 
 	delayacct_wpcopy_start();
 

@@ -3116,19 +3124,21 @@ static vm_fault_t wp_page_copy(struct vm
 		if (!new_page)
 			goto oom;
 
-		if (!__wp_page_copy_user(new_page, old_page, vmf)) {
+		ret = __wp_page_copy_user(new_page, old_page, vmf);
+		if (ret) {
 			/*
 			 * COW failed, if the fault was solved by other,
 			 * it's fine. If not, userspace would re-fault on
 			 * the same address and we will handle the fault
 			 * from the second attempt.
+			 * The -EHWPOISON case will not be retried.
 			 */
 			put_page(new_page);
 			if (old_page)
 				put_page(old_page);
 
 			delayacct_wpcopy_end();
-			return 0;
+			return ret == -EHWPOISON ? VM_FAULT_HWPOISON : 0;
 		}
 		kmsan_copy_page_meta(new_page, old_page);
 	}

@@ -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;

@@ -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;
 	}
 

@@ -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;
 	}

@@ -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 */

@@ -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

110 lines not on this page · raw message

@@ -748,6 +748,7 @@ 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();

@@ -762,7 +763,7 @@ 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

@@ -776,7 +777,7 @@ 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();
 
 	/*

@@ -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)

@@ -99,6 +99,17 @@ 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);

@@ -1746,10 +1757,10 @@ 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 ||

@@ -1784,13 +1795,6 @@ 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) {

@@ -1802,9 +1806,9 @@ 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);
 

@@ -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);

@@ -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.
 	 *

93 lines not on this page · raw message

@@ -1079,8 +1079,9 @@ wait_free_buffer:
 		if (err)
 			goto err_event_drop;
 
-		if (sk->sk_err)
-			return -sk->sk_err;
+		err = sock_error(sk);
+		if (err)
+			return err;
 	}
 
 	return size;

@@ -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)

72 lines not on this page · raw message

@@ -1932,6 +1932,8 @@ void unmap_mapping_pages(struct address_
 		pgoff_t start, pgoff_t nr, bool even_cows);
 void unmap_mapping_range(struct address_space *mapping,
 		loff_t const holebegin, loff_t const holelen, int even_cows);
+struct vm_area_struct *lock_mm_and_find_vma(struct mm_struct *mm,
+		unsigned long address, struct pt_regs *regs);
 #else
 static inline vm_fault_t handle_mm_fault(struct vm_area_struct *vma,
 					 unsigned long address, unsigned int flags,

127 lines not on this page · raw message

@@ -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);
 }
 
 /*

79 lines not on this page · raw message

55 lines not on this page · raw message

@@ -99,21 +99,13 @@ static void __do_page_fault(struct pt_re
 
 	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 (write) {

@@ -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))) {

88 lines not on this page · raw message

@@ -2045,7 +2045,7 @@ int expand_downwards(struct vm_area_stru
 	int error = 0;
 
 	address &= PAGE_MASK;
-	if (address < mmap_min_addr)
+	if (address < mmap_min_addr || address < FIRST_USER_ADDRESS)
 		return -EPERM;
 
 	/* Enforce stack_guard_gap */

@@ -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;
 

@@ -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)

@@ -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;
 	}
 

@@ -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;

@@ -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;
 

@@ -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) {

@@ -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;

@@ -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;
 

@@ -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;

@@ -33,19 +33,11 @@ int copro_handle_mm_fault(struct mm_stru
 	if (mm->pgd == NULL)
 		return -EFAULT;
 
-	mmap_read_lock(mm);
-	ret = -EFAULT;
-	vma = find_vma(mm, ea);
+	vma = lock_mm_and_find_vma(mm, ea, NULL);
 	if (!vma)
-		goto out_unlock;
-
-	if (ea < vma->vm_start) {
-		if (!(vma->vm_flags & VM_GROWSDOWN))
-			goto out_unlock;
-		if (expand_stack(vma, ea))
-			goto out_unlock;
-	}
+		return -EFAULT;
 
+	ret = -EFAULT;
 	is_write = dsisr & DSISR_ISSTORE;
 	if (is_write) {
 		if (!(vma->vm_flags & VM_WRITE))

@@ -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;
 

@@ -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;
 

@@ -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,

@@ -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:

112 lines not on this page · raw message

@@ -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;
 }

@@ -198,34 +198,39 @@ static struct page *get_arg_page(struct
 		int write)
 {
 	struct page *page;
+	struct vm_area_struct *vma = bprm->vma;
+	struct mm_struct *mm = bprm->mm;
 	int ret;
-	unsigned int gup_flags = FOLL_FORCE;
 
-#ifdef CONFIG_STACK_GROWSUP
-	if (write) {
-		/* We claim to hold the lock - nobody to race with */
-		ret = expand_downwards(bprm->vma, pos, true);
-		if (ret < 0)
+	/*
+	 * Avoid relying on expanding the stack down in GUP (which
+	 * does not work for STACK_GROWSUP anyway), and just do it
+	 * by hand ahead of time.
+	 */
+	if (write && pos < vma->vm_start) {
+		mmap_write_lock(mm);
+		ret = expand_downwards(vma, pos, true);
+		if (unlikely(ret < 0)) {
+			mmap_write_unlock(mm);
 			return NULL;
-	}
-#endif
-
-	if (write)
-		gup_flags |= FOLL_WRITE;
+		}
+		mmap_write_downgrade(mm);
+	} else
+		mmap_read_lock(mm);
 
 	/*
 	 * We are doing an exec().  'current' is the process
-	 * doing the exec and bprm->mm is the new process's mm.
+	 * doing the exec and 'mm' is the new process's mm.
 	 */
-	mmap_read_lock(bprm->mm);
-	ret = get_user_pages_remote(bprm->mm, pos, 1, gup_flags,
+	ret = get_user_pages_remote(mm, pos, 1,
+			write ? FOLL_WRITE : 0,
 			&page, NULL, NULL);
-	mmap_read_unlock(bprm->mm);
+	mmap_read_unlock(mm);
 	if (ret <= 0)
 		return NULL;
 
 	if (write)
-		acct_arg_size(bprm, vma_pages(bprm->vma));
+		acct_arg_size(bprm, vma_pages(vma));
 
 	return page;
 }

@@ -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))
 	{

@@ -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;

@@ -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;

@@ -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

@@ -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;
 			}

@@ -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;
 	}
 
 	/*

@@ -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);

@@ -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;

@@ -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;
 

@@ -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;

@@ -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;

@@ -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;
 

@@ -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,

@@ -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))

@@ -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;

192 lines not on this page · raw message

@@ -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

@@ -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;

@@ -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);

@@ -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;

@@ -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 {

@@ -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 */

@@ -1028,12 +1028,7 @@ 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);

@@ -1049,12 +1044,7 @@ 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);