diff options
Diffstat (limited to 'kernel')
33 files changed, 1139 insertions, 720 deletions
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index b3b02b9c4405..863e434a6020 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -729,7 +729,7 @@ static inline int nr_cpusets(void) * load balancing domains (sched domains) as specified by that partial * partition. * - * See "What is sched_load_balance" in Documentation/cgroup-v1/cpusets.rst + * See "What is sched_load_balance" in Documentation/admin-guide/cgroup-v1/cpusets.rst * for a background explanation of this. * * Does not return errors, on the theory that the callers of this diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 62fa5a82a065..9de232229063 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -129,15 +129,17 @@ setup_io_tlb_npages(char *str) } early_param("swiotlb", setup_io_tlb_npages); +static bool no_iotlb_memory; + unsigned long swiotlb_nr_tbl(void) { - return io_tlb_nslabs; + return unlikely(no_iotlb_memory) ? 0 : io_tlb_nslabs; } EXPORT_SYMBOL_GPL(swiotlb_nr_tbl); unsigned int swiotlb_max_segment(void) { - return max_segment; + return unlikely(no_iotlb_memory) ? 0 : max_segment; } EXPORT_SYMBOL_GPL(swiotlb_max_segment); @@ -160,8 +162,6 @@ unsigned long swiotlb_size_or_default(void) return size ? size : (IO_TLB_DEFAULT_SIZE); } -static bool no_iotlb_memory; - void swiotlb_print_info(void) { unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT; @@ -317,6 +317,14 @@ swiotlb_late_init_with_default_size(size_t default_size) return rc; } +static void swiotlb_cleanup(void) +{ + io_tlb_end = 0; + io_tlb_start = 0; + io_tlb_nslabs = 0; + max_segment = 0; +} + int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) { @@ -367,10 +375,7 @@ cleanup4: sizeof(int))); io_tlb_list = NULL; cleanup3: - io_tlb_end = 0; - io_tlb_start = 0; - io_tlb_nslabs = 0; - max_segment = 0; + swiotlb_cleanup(); return -ENOMEM; } @@ -394,10 +399,7 @@ void __init swiotlb_exit(void) memblock_free_late(io_tlb_start, PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); } - io_tlb_start = 0; - io_tlb_end = 0; - io_tlb_nslabs = 0; - max_segment = 0; + swiotlb_cleanup(); } /* @@ -546,7 +548,7 @@ not_found: if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n", size, io_tlb_nslabs, tmp_io_tlb_used); - return DMA_MAPPING_ERROR; + return (phys_addr_t)DMA_MAPPING_ERROR; found: io_tlb_used += nslots; spin_unlock_irqrestore(&io_tlb_lock, flags); @@ -664,7 +666,7 @@ bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr, /* Oh well, have to allocate and map a bounce buffer. */ *phys = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start), *phys, size, dir, attrs); - if (*phys == DMA_MAPPING_ERROR) + if (*phys == (phys_addr_t)DMA_MAPPING_ERROR) return false; /* Ensure that the address returned is DMA'ble */ diff --git a/kernel/events/core.c b/kernel/events/core.c index 785d708f8553..eea9d52b010c 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2553,6 +2553,9 @@ unlock: return ret; } +static bool exclusive_event_installable(struct perf_event *event, + struct perf_event_context *ctx); + /* * Attach a performance event to a context. * @@ -2567,6 +2570,8 @@ perf_install_in_context(struct perf_event_context *ctx, lockdep_assert_held(&ctx->mutex); + WARN_ON_ONCE(!exclusive_event_installable(event, ctx)); + if (event->cpu != -1) event->cpu = cpu; @@ -4360,7 +4365,7 @@ static int exclusive_event_init(struct perf_event *event) { struct pmu *pmu = event->pmu; - if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE)) + if (!is_exclusive_pmu(pmu)) return 0; /* @@ -4391,7 +4396,7 @@ static void exclusive_event_destroy(struct perf_event *event) { struct pmu *pmu = event->pmu; - if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE)) + if (!is_exclusive_pmu(pmu)) return; /* see comment in exclusive_event_init() */ @@ -4411,14 +4416,15 @@ static bool exclusive_event_match(struct perf_event *e1, struct perf_event *e2) return false; } -/* Called under the same ctx::mutex as perf_install_in_context() */ static bool exclusive_event_installable(struct perf_event *event, struct perf_event_context *ctx) { struct perf_event *iter_event; struct pmu *pmu = event->pmu; - if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE)) + lockdep_assert_held(&ctx->mutex); + + if (!is_exclusive_pmu(pmu)) return true; list_for_each_entry(iter_event, &ctx->event_list, event_entry) { @@ -4465,12 +4471,20 @@ static void _free_event(struct perf_event *event) if (event->destroy) event->destroy(event); - if (event->ctx) - put_ctx(event->ctx); - + /* + * Must be after ->destroy(), due to uprobe_perf_close() using + * hw.target. + */ if (event->hw.target) put_task_struct(event->hw.target); + /* + * perf_event_free_task() relies on put_ctx() being 'last', in particular + * all task references must be cleaned up. + */ + if (event->ctx) + put_ctx(event->ctx); + exclusive_event_destroy(event); module_put(event->pmu->module); @@ -4650,8 +4664,17 @@ again: mutex_unlock(&event->child_mutex); list_for_each_entry_safe(child, tmp, &free_list, child_list) { + void *var = &child->ctx->refcount; + list_del(&child->child_list); free_event(child); + + /* + * Wake any perf_event_free_task() waiting for this event to be + * freed. + */ + smp_mb(); /* pairs with wait_var_event() */ + wake_up_var(var); } no_ctx: @@ -10930,11 +10953,6 @@ SYSCALL_DEFINE5(perf_event_open, goto err_alloc; } - if ((pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) && group_leader) { - err = -EBUSY; - goto err_context; - } - /* * Look up the group leader (we will attach this event to it): */ @@ -11022,6 +11040,18 @@ SYSCALL_DEFINE5(perf_event_open, move_group = 0; } } + + /* + * Failure to create exclusive events returns -EBUSY. + */ + err = -EBUSY; + if (!exclusive_event_installable(group_leader, ctx)) + goto err_locked; + + for_each_sibling_event(sibling, group_leader) { + if (!exclusive_event_installable(sibling, ctx)) + goto err_locked; + } } else { mutex_lock(&ctx->mutex); } @@ -11058,9 +11088,6 @@ SYSCALL_DEFINE5(perf_event_open, * because we need to serialize with concurrent event creation. */ if (!exclusive_event_installable(event, ctx)) { - /* exclusive and group stuff are assumed mutually exclusive */ - WARN_ON_ONCE(move_group); - err = -EBUSY; goto err_locked; } @@ -11527,11 +11554,11 @@ static void perf_free_event(struct perf_event *event, } /* - * Free an unexposed, unused context as created by inheritance by - * perf_event_init_task below, used by fork() in case of fail. + * Free a context as created by inheritance by perf_event_init_task() below, + * used by fork() in case of fail. * - * Not all locks are strictly required, but take them anyway to be nice and - * help out with the lockdep assertions. + * Even though the task has never lived, the context and events have been + * exposed through the child_list, so we must take care tearing it all down. */ void perf_event_free_task(struct task_struct *task) { @@ -11561,7 +11588,23 @@ void perf_event_free_task(struct task_struct *task) perf_free_event(event, ctx); mutex_unlock(&ctx->mutex); - put_ctx(ctx); + + /* + * perf_event_release_kernel() could've stolen some of our + * child events and still have them on its free_list. In that + * case we must wait for these events to have been freed (in + * particular all their references to this task must've been + * dropped). + * + * Without this copy_process() will unconditionally free this + * task (irrespective of its reference count) and + * _free_event()'s put_task_struct(event->hw.target) will be a + * use-after-free. + * + * Wait for all events to drop their context reference. + */ + wait_var_event(&ctx->refcount, refcount_read(&ctx->refcount) == 1); + put_ctx(ctx); /* must be last */ } } diff --git a/kernel/fork.c b/kernel/fork.c index 8f3e2d97d771..d8ae0f1b4148 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -677,7 +677,6 @@ void __mmdrop(struct mm_struct *mm) WARN_ON_ONCE(mm == current->active_mm); mm_free_pgd(mm); destroy_context(mm); - hmm_mm_destroy(mm); mmu_notifier_mm_destroy(mm); check_mm(mm); put_user_ns(mm->user_ns); @@ -2406,6 +2405,16 @@ long _do_fork(struct kernel_clone_args *args) return nr; } +bool legacy_clone_args_valid(const struct kernel_clone_args *kargs) +{ + /* clone(CLONE_PIDFD) uses parent_tidptr to return a pidfd */ + if ((kargs->flags & CLONE_PIDFD) && + (kargs->flags & CLONE_PARENT_SETTID)) + return false; + + return true; +} + #ifndef CONFIG_HAVE_COPY_THREAD_TLS /* For compatibility with architectures that call do_fork directly rather than * using the syscall entry points below. */ @@ -2417,6 +2426,7 @@ long do_fork(unsigned long clone_flags, { struct kernel_clone_args args = { .flags = (clone_flags & ~CSIGNAL), + .pidfd = parent_tidptr, .child_tid = child_tidptr, .parent_tid = parent_tidptr, .exit_signal = (clone_flags & CSIGNAL), @@ -2424,6 +2434,9 @@ long do_fork(unsigned long clone_flags, .stack_size = stack_size, }; + if (!legacy_clone_args_valid(&args)) + return -EINVAL; + return _do_fork(&args); } #endif @@ -2505,8 +2518,7 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, .tls = tls, }; - /* clone(CLONE_PIDFD) uses parent_tidptr to return a pidfd */ - if ((clone_flags & CLONE_PIDFD) && (clone_flags & CLONE_PARENT_SETTID)) + if (!legacy_clone_args_valid(&args)) return -EINVAL; return _do_fork(&args); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 9f5433a52488..9873fc627d61 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2276,6 +2276,7 @@ static int __init init_kprobes(void) init_test_probes(); return err; } +subsys_initcall(init_kprobes); #ifdef CONFIG_DEBUG_FS static void report_probe(struct seq_file *pi, struct kprobe *p, @@ -2588,5 +2589,3 @@ static int __init debugfs_kprobe_init(void) late_initcall(debugfs_kprobe_init); #endif /* CONFIG_DEBUG_FS */ - -module_init(init_kprobes); diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index 9c49ec645d8b..65b6a1600c8f 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -210,6 +210,7 @@ static int lockdep_stats_show(struct seq_file *m, void *v) nr_hardirq_read_safe = 0, nr_hardirq_read_unsafe = 0, sum_forward_deps = 0; +#ifdef CONFIG_PROVE_LOCKING list_for_each_entry(class, &all_lock_classes, lock_entry) { if (class->usage_mask == 0) @@ -241,13 +242,13 @@ static int lockdep_stats_show(struct seq_file *m, void *v) if (class->usage_mask & LOCKF_ENABLED_HARDIRQ_READ) nr_hardirq_read_unsafe++; -#ifdef CONFIG_PROVE_LOCKING sum_forward_deps += lockdep_count_forward_deps(class); -#endif } #ifdef CONFIG_DEBUG_LOCKDEP DEBUG_LOCKS_WARN_ON(debug_atomic_read(nr_unused_locks) != nr_unused); #endif + +#endif seq_printf(m, " lock-classes: %11lu [max: %lu]\n", nr_lock_classes, MAX_LOCKDEP_KEYS); seq_printf(m, " direct dependencies: %11lu [max: %lu]\n", diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 0c601ae072b3..edd1c082dbf5 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -16,7 +16,7 @@ * by Steven Rostedt, based on work by Gregory Haskins, Peter Morreale * and Sven Dietrich. * - * Also see Documentation/locking/mutex-design.txt. + * Also see Documentation/locking/mutex-design.rst. */ #include <linux/mutex.h> #include <linux/ww_mutex.h> diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 38fbf9fa7f1b..fa83d36e30c6 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -9,7 +9,7 @@ * Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt * Copyright (C) 2006 Esben Nielsen * - * See Documentation/locking/rt-mutex-design.txt for details. + * See Documentation/locking/rt-mutex-design.rst for details. */ #include <linux/spinlock.h> #include <linux/export.h> diff --git a/kernel/memremap.c b/kernel/memremap.c index 6e1970719dc2..6ee03a816d67 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -11,41 +11,39 @@ #include <linux/types.h> #include <linux/wait_bit.h> #include <linux/xarray.h> -#include <linux/hmm.h> static DEFINE_XARRAY(pgmap_array); #define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1) #define SECTION_SIZE (1UL << PA_SECTION_SHIFT) -#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) -vm_fault_t device_private_entry_fault(struct vm_area_struct *vma, - unsigned long addr, - swp_entry_t entry, - unsigned int flags, - pmd_t *pmdp) +#ifdef CONFIG_DEV_PAGEMAP_OPS +DEFINE_STATIC_KEY_FALSE(devmap_managed_key); +EXPORT_SYMBOL(devmap_managed_key); +static atomic_t devmap_managed_enable; + +static void devmap_managed_enable_put(void *data) { - struct page *page = device_private_entry_to_page(entry); - struct hmm_devmem *devmem; + if (atomic_dec_and_test(&devmap_managed_enable)) + static_branch_disable(&devmap_managed_key); +} - devmem = container_of(page->pgmap, typeof(*devmem), pagemap); +static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap) +{ + if (!pgmap->ops || !pgmap->ops->page_free) { + WARN(1, "Missing page_free method\n"); + return -EINVAL; + } - /* - * The page_fault() callback must migrate page back to system memory - * so that CPU can access it. This might fail for various reasons - * (device issue, device was unsafely unplugged, ...). When such - * error conditions happen, the callback must return VM_FAULT_SIGBUS. - * - * Note that because memory cgroup charges are accounted to the device - * memory, this should never fail because of memory restrictions (but - * allocation of regular system page might still fail because we are - * out of memory). - * - * There is a more in-depth description of what that callback can and - * cannot do, in include/linux/memremap.h - */ - return devmem->page_fault(vma, addr, page, flags, pmdp); + if (atomic_inc_return(&devmap_managed_enable) == 1) + static_branch_enable(&devmap_managed_key); + return devm_add_action_or_reset(dev, devmap_managed_enable_put, NULL); } -#endif /* CONFIG_DEVICE_PRIVATE */ +#else +static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap) +{ + return -EINVAL; +} +#endif /* CONFIG_DEV_PAGEMAP_OPS */ static void pgmap_array_delete(struct resource *res) { @@ -56,14 +54,8 @@ static void pgmap_array_delete(struct resource *res) static unsigned long pfn_first(struct dev_pagemap *pgmap) { - const struct resource *res = &pgmap->res; - struct vmem_altmap *altmap = &pgmap->altmap; - unsigned long pfn; - - pfn = res->start >> PAGE_SHIFT; - if (pgmap->altmap_valid) - pfn += vmem_altmap_offset(altmap); - return pfn; + return PHYS_PFN(pgmap->res.start) + + vmem_altmap_offset(pgmap_altmap(pgmap)); } static unsigned long pfn_end(struct dev_pagemap *pgmap) @@ -83,59 +75,81 @@ static unsigned long pfn_next(unsigned long pfn) #define for_each_device_pfn(pfn, map) \ for (pfn = pfn_first(map); pfn < pfn_end(map); pfn = pfn_next(pfn)) +static void dev_pagemap_kill(struct dev_pagemap *pgmap) +{ + if (pgmap->ops && pgmap->ops->kill) + pgmap->ops->kill(pgmap); + else + percpu_ref_kill(pgmap->ref); +} + +static void dev_pagemap_cleanup(struct dev_pagemap *pgmap) +{ + if (pgmap->ops && pgmap->ops->cleanup) { + pgmap->ops->cleanup(pgmap); + } else { + wait_for_completion(&pgmap->done); + percpu_ref_exit(pgmap->ref); + } +} + static void devm_memremap_pages_release(void *data) { struct dev_pagemap *pgmap = data; struct device *dev = pgmap->dev; struct resource *res = &pgmap->res; - resource_size_t align_start, align_size; unsigned long pfn; int nid; - pgmap->kill(pgmap->ref); + dev_pagemap_kill(pgmap); for_each_device_pfn(pfn, pgmap) put_page(pfn_to_page(pfn)); - pgmap->cleanup(pgmap->ref); + dev_pagemap_cleanup(pgmap); /* pages are dead and unused, undo the arch mapping */ - align_start = res->start & ~(SECTION_SIZE - 1); - align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) - - align_start; - - nid = page_to_nid(pfn_to_page(align_start >> PAGE_SHIFT)); + nid = page_to_nid(pfn_to_page(PHYS_PFN(res->start))); mem_hotplug_begin(); if (pgmap->type == MEMORY_DEVICE_PRIVATE) { - pfn = align_start >> PAGE_SHIFT; + pfn = PHYS_PFN(res->start); __remove_pages(page_zone(pfn_to_page(pfn)), pfn, - align_size >> PAGE_SHIFT, NULL); + PHYS_PFN(resource_size(res)), NULL); } else { - arch_remove_memory(nid, align_start, align_size, - pgmap->altmap_valid ? &pgmap->altmap : NULL); - kasan_remove_zero_shadow(__va(align_start), align_size); + arch_remove_memory(nid, res->start, resource_size(res), + pgmap_altmap(pgmap)); + kasan_remove_zero_shadow(__va(res->start), resource_size(res)); } mem_hotplug_done(); - untrack_pfn(NULL, PHYS_PFN(align_start), align_size); + untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res)); pgmap_array_delete(res); dev_WARN_ONCE(dev, pgmap->altmap.alloc, "%s: failed to free all reserved pages\n", __func__); } +static void dev_pagemap_percpu_release(struct percpu_ref *ref) +{ + struct dev_pagemap *pgmap = + container_of(ref, struct dev_pagemap, internal_ref); + + complete(&pgmap->done); +} + /** * devm_memremap_pages - remap and provide memmap backing for the given resource * @dev: hosting device for @res * @pgmap: pointer to a struct dev_pagemap * * Notes: - * 1/ At a minimum the res, ref and type members of @pgmap must be initialized + * 1/ At a minimum the res and type members of @pgmap must be initialized * by the caller before passing it to this function * - * 2/ The altmap field may optionally be initialized, in which case altmap_valid - * must be set to true + * 2/ The altmap field may optionally be initialized, in which case + * PGMAP_ALTMAP_VALID must be set in pgmap->flags. * - * 3/ pgmap->ref must be 'live' on entry and will be killed and reaped - * at devm_memremap_pages_release() time, or if this routine fails. + * 3/ The ref field may optionally be provided, in which pgmap->ref must be + * 'live' on entry and will be killed and reaped at + * devm_memremap_pages_release() time, or if this routine fails. * * 4/ res is expected to be a host memory range that could feasibly be * treated as a "System RAM" range, i.e. not a device mmio range, but @@ -143,31 +157,69 @@ static void devm_memremap_pages_release(void *data) */ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) { - resource_size_t align_start, align_size, align_end; - struct vmem_altmap *altmap = pgmap->altmap_valid ? - &pgmap->altmap : NULL; struct resource *res = &pgmap->res; struct dev_pagemap *conflict_pgmap; struct mhp_restrictions restrictions = { /* * We do not want any optional features only our own memmap - */ - .altmap = altmap, + */ + .altmap = pgmap_altmap(pgmap), }; pgprot_t pgprot = PAGE_KERNEL; int error, nid, is_ram; + bool need_devmap_managed = true; + + switch (pgmap->type) { + case MEMORY_DEVICE_PRIVATE: + if (!IS_ENABLED(CONFIG_DEVICE_PRIVATE)) { + WARN(1, "Device private memory not supported\n"); + return ERR_PTR(-EINVAL); + } + if (!pgmap->ops || !pgmap->ops->migrate_to_ram) { + WARN(1, "Missing migrate_to_ram method\n"); + return ERR_PTR(-EINVAL); + } + break; + case MEMORY_DEVICE_FS_DAX: + if (!IS_ENABLED(CONFIG_ZONE_DEVICE) || + IS_ENABLED(CONFIG_FS_DAX_LIMITED)) { + WARN(1, "File system DAX not supported\n"); + return ERR_PTR(-EINVAL); + } + break; + case MEMORY_DEVICE_DEVDAX: + case MEMORY_DEVICE_PCI_P2PDMA: + need_devmap_managed = false; + break; + default: + WARN(1, "Invalid pgmap type %d\n", pgmap->type); + break; + } + + if (!pgmap->ref) { + if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup)) + return ERR_PTR(-EINVAL); - if (!pgmap->ref || !pgmap->kill || !pgmap->cleanup) { - WARN(1, "Missing reference count teardown definition\n"); - return ERR_PTR(-EINVAL); + init_completion(&pgmap->done); + error = percpu_ref_init(&pgmap->internal_ref, + dev_pagemap_percpu_release, 0, GFP_KERNEL); + if (error) + return ERR_PTR(error); + pgmap->ref = &pgmap->internal_ref; + } else { + if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) { + WARN(1, "Missing reference count teardown definition\n"); + return ERR_PTR(-EINVAL); + } } - align_start = res->start & ~(SECTION_SIZE - 1); - align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) - - align_start; - align_end = align_start + align_size - 1; + if (need_devmap_managed) { + error = devmap_managed_enable_get(dev, pgmap); + if (error) + return ERR_PTR(error); + } - conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_start), NULL); + conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->start), NULL); if (conflict_pgmap) { dev_WARN(dev, "Conflicting mapping in same section\n"); put_dev_pagemap(conflict_pgmap); @@ -175,7 +227,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) goto err_array; } - conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_end), NULL); + conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->end), NULL); if (conflict_pgmap) { dev_WARN(dev, "Conflicting mapping in same section\n"); put_dev_pagemap(conflict_pgmap); @@ -183,7 +235,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) goto err_array; } - is_ram = region_intersects(align_start, align_size, + is_ram = region_intersects(res->start, resource_size(res), IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); if (is_ram != REGION_DISJOINT) { @@ -204,8 +256,8 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) if (nid < 0) nid = numa_mem_id(); - error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(align_start), 0, - align_size); + error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(res->start), 0, + resource_size(res)); if (error) goto err_pfn_remap; @@ -223,16 +275,16 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) * arch_add_memory(). */ if (pgmap->type == MEMORY_DEVICE_PRIVATE) { - error = add_pages(nid, align_start >> PAGE_SHIFT, - align_size >> PAGE_SHIFT, &restrictions); + error = add_pages(nid, PHYS_PFN(res->start), + PHYS_PFN(resource_size(res)), &restrictions); } else { - error = kasan_add_zero_shadow(__va(align_start), align_size); + error = kasan_add_zero_shadow(__va(res->start), resource_size(res)); if (error) { mem_hotplug_done(); goto err_kasan; } - error = arch_add_memory(nid, align_start, align_size, + error = arch_add_memory(nid, res->start, resource_size(res), &restrictions); } @@ -240,8 +292,8 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) struct zone *zone; zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE]; - move_pfn_range_to_zone(zone, align_start >> PAGE_SHIFT, - align_size >> PAGE_SHIFT, altmap); + move_pfn_range_to_zone(zone, PHYS_PFN(res->start), + PHYS_PFN(resource_size(res)), restrictions.altmap); } mem_hotplug_done(); @@ -253,8 +305,8 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) * to allow us to do the work while not holding the hotplug lock. */ memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE], - align_start >> PAGE_SHIFT, - align_size >> PAGE_SHIFT, pgmap); + PHYS_PFN(res->start), + PHYS_PFN(resource_size(res)), pgmap); percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap)); error = devm_add_action_or_reset(dev, devm_memremap_pages_release, @@ -265,15 +317,14 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) return __va(res->start); err_add_memory: - kasan_remove_zero_shadow(__va(align_start), align_size); + kasan_remove_zero_shadow(__va(res->start), resource_size(res)); err_kasan: - untrack_pfn(NULL, PHYS_PFN(align_start), align_size); + untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res)); err_pfn_remap: pgmap_array_delete(res); err_array: - pgmap->kill(pgmap->ref); - pgmap->cleanup(pgmap->ref); - + dev_pagemap_kill(pgmap); + dev_pagemap_cleanup(pgmap); return ERR_PTR(error); } EXPORT_SYMBOL_GPL(devm_memremap_pages); @@ -287,7 +338,9 @@ EXPORT_SYMBOL_GPL(devm_memunmap_pages); unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) { /* number of pfns from base where pfn_to_page() is valid */ - return altmap->reserve + altmap->free; + if (altmap) + return altmap->reserve + altmap->free; + return 0; } void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) @@ -329,28 +382,6 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn, EXPORT_SYMBOL_GPL(get_dev_pagemap); #ifdef CONFIG_DEV_PAGEMAP_OPS -DEFINE_STATIC_KEY_FALSE(devmap_managed_key); -EXPORT_SYMBOL(devmap_managed_key); -static atomic_t devmap_enable; - -/* - * Toggle the static key for ->page_free() callbacks when dev_pagemap - * pages go idle. - */ -void dev_pagemap_get_ops(void) -{ - if (atomic_inc_return(&devmap_enable) == 1) - static_branch_enable(&devmap_managed_key); -} -EXPORT_SYMBOL_GPL(dev_pagemap_get_ops); - -void dev_pagemap_put_ops(void) -{ - if (atomic_dec_and_test(&devmap_enable)) - static_branch_disable(&devmap_managed_key); -} -EXPORT_SYMBOL_GPL(dev_pagemap_put_ops); - < |