diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c index 0618827f73fe3e1814c09f643be09a4f76178b2e..c5c61ccbd8ce9161c5abe6490efe1f8c53c5bfdd 100644 --- a/drivers/base/cacheinfo.c +++ b/drivers/base/cacheinfo.c @@ -58,7 +58,7 @@ bool last_level_cache_is_valid(unsigned int cpu) { struct cacheinfo *llc; - if (!cache_leaves(cpu)) + if (!cache_leaves(cpu) || !per_cpu_cacheinfo(cpu)) return false; llc = per_cpu_cacheinfo_idx(cpu, cache_leaves(cpu) - 1); @@ -511,11 +511,9 @@ int __weak populate_cache_leaves(unsigned int cpu) return -ENOENT; } -static inline -int allocate_cache_info(int cpu) +static inline int allocate_cache_info(int cpu) { - per_cpu_cacheinfo(cpu) = kcalloc(cache_leaves(cpu), - sizeof(struct cacheinfo), GFP_ATOMIC); + per_cpu_cacheinfo(cpu) = kcalloc(cache_leaves(cpu), sizeof(struct cacheinfo), GFP_ATOMIC); if (!per_cpu_cacheinfo(cpu)) { cache_leaves(cpu) = 0; return -ENOMEM; @@ -587,7 +585,11 @@ static inline int init_level_allocate_ci(unsigned int cpu) */ ci_cacheinfo(cpu)->early_ci_levels = false; - if (cache_leaves(cpu) <= early_leaves) + /* + * Some architectures (e.g., x86) do not use early initialization. + * Allocate memory now in such case. + */ + if (cache_leaves(cpu) <= early_leaves && per_cpu_cacheinfo(cpu)) return 0; kfree(per_cpu_cacheinfo(cpu)); diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index 659112da47b6926108abca3a356a715a7cd411fe..a0dbdfd8a68f7e92c60745b1d969f9b04b8c3ddf 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -163,10 +163,9 @@ static void mtk_drm_crtc_destroy(struct drm_crtc *crtc) mtk_mutex_put(mtk_crtc->mutex); #if IS_REACHABLE(CONFIG_MTK_CMDQ) - mtk_drm_cmdq_pkt_destroy(&mtk_crtc->cmdq_handle); - if (mtk_crtc->cmdq_client.chan) { mbox_free_channel(mtk_crtc->cmdq_client.chan); + mtk_drm_cmdq_pkt_destroy(&mtk_crtc->cmdq_handle); mtk_crtc->cmdq_client.chan = NULL; } #endif diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 9d724d228b831ceb44b59eb0c98767a372ccaec4..bc7c5cd385969549871d6440687779136bfb4a9e 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -3736,8 +3736,8 @@ int ionic_lif_register(struct ionic_lif *lif) /* only register LIF0 for now */ err = register_netdev(lif->netdev); if (err) { - dev_err(lif->ionic->dev, "Cannot register net device, aborting\n"); - ionic_lif_unregister_phc(lif); + dev_err(lif->ionic->dev, "Cannot register net device: %d, aborting\n", err); + ionic_lif_unregister(lif); return err; } diff --git a/include/linux/mman.h b/include/linux/mman.h index bcb201ab7a412e02254f98e51d830cfef1c31c06..8ddca62d6460bd461b8afff731bb64a5203b822a 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -188,16 +188,31 @@ static inline bool arch_memory_deny_write_exec_supported(void) * * d) mmap(PROT_READ | PROT_EXEC) * mmap(PROT_READ | PROT_EXEC | PROT_BTI) + * + * This is only applicable if the user has set the Memory-Deny-Write-Execute + * (MDWE) protection mask for the current process. + * + * @old specifies the VMA flags the VMA originally possessed, and @new the ones + * we propose to set. + * + * Return: false if proposed change is OK, true if not ok and should be denied. */ -static inline bool map_deny_write_exec(struct vm_area_struct *vma, unsigned long vm_flags) +static inline bool map_deny_write_exec(unsigned long old, unsigned long new) { + /* If MDWE is disabled, we have nothing to deny. */ if (!test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) return false; - if ((vm_flags & VM_EXEC) && (vm_flags & VM_WRITE)) + /* If the new VMA is not executable, we have nothing to deny. */ + if (!(new & VM_EXEC)) + return false; + + /* Under MDWE we do not accept newly writably executable VMAs... */ + if (new & VM_WRITE) return true; - if (!(vma->vm_flags & VM_EXEC) && (vm_flags & VM_EXEC)) + /* ...nor previously non-executable VMAs becoming executable. */ + if (!(old & VM_EXEC)) return true; return false; diff --git a/kernel/kcsan/debugfs.c b/kernel/kcsan/debugfs.c index 1d1d1b0e424897d1c9ba750d046f7e535b3b724d..f4623910fb1f232744947bbe1fc333348759a516 100644 --- a/kernel/kcsan/debugfs.c +++ b/kernel/kcsan/debugfs.c @@ -46,14 +46,8 @@ static struct { int used; /* number of elements used */ bool sorted; /* if elements are sorted */ bool whitelist; /* if list is a blacklist or whitelist */ -} report_filterlist = { - .addrs = NULL, - .size = 8, /* small initial size */ - .used = 0, - .sorted = false, - .whitelist = false, /* default is blacklist */ -}; -static DEFINE_SPINLOCK(report_filterlist_lock); +} report_filterlist; +static DEFINE_RAW_SPINLOCK(report_filterlist_lock); /* * The microbenchmark allows benchmarking KCSAN core runtime only. To run @@ -110,7 +104,7 @@ bool kcsan_skip_report_debugfs(unsigned long func_addr) return false; func_addr -= offset; /* Get function start */ - spin_lock_irqsave(&report_filterlist_lock, flags); + raw_spin_lock_irqsave(&report_filterlist_lock, flags); if (report_filterlist.used == 0) goto out; @@ -127,7 +121,7 @@ bool kcsan_skip_report_debugfs(unsigned long func_addr) ret = !ret; out: - spin_unlock_irqrestore(&report_filterlist_lock, flags); + raw_spin_unlock_irqrestore(&report_filterlist_lock, flags); return ret; } @@ -135,9 +129,9 @@ static void set_report_filterlist_whitelist(bool whitelist) { unsigned long flags; - spin_lock_irqsave(&report_filterlist_lock, flags); + raw_spin_lock_irqsave(&report_filterlist_lock, flags); report_filterlist.whitelist = whitelist; - spin_unlock_irqrestore(&report_filterlist_lock, flags); + raw_spin_unlock_irqrestore(&report_filterlist_lock, flags); } /* Returns 0 on success, error-code otherwise. */ @@ -145,6 +139,9 @@ static ssize_t insert_report_filterlist(const char *func) { unsigned long flags; unsigned long addr = kallsyms_lookup_name(func); + unsigned long *delay_free = NULL; + unsigned long *new_addrs = NULL; + size_t new_size = 0; ssize_t ret = 0; if (!addr) { @@ -152,32 +149,33 @@ static ssize_t insert_report_filterlist(const char *func) return -ENOENT; } - spin_lock_irqsave(&report_filterlist_lock, flags); +retry_alloc: + /* + * Check if we need an allocation, and re-validate under the lock. Since + * the report_filterlist_lock is a raw, cannot allocate under the lock. + */ + if (data_race(report_filterlist.used == report_filterlist.size)) { + new_size = (report_filterlist.size ?: 4) * 2; + delay_free = new_addrs = kmalloc_array(new_size, sizeof(unsigned long), GFP_KERNEL); + if (!new_addrs) + return -ENOMEM; + } - if (report_filterlist.addrs == NULL) { - /* initial allocation */ - report_filterlist.addrs = - kmalloc_array(report_filterlist.size, - sizeof(unsigned long), GFP_ATOMIC); - if (report_filterlist.addrs == NULL) { - ret = -ENOMEM; - goto out; - } - } else if (report_filterlist.used == report_filterlist.size) { - /* resize filterlist */ - size_t new_size = report_filterlist.size * 2; - unsigned long *new_addrs = - krealloc(report_filterlist.addrs, - new_size * sizeof(unsigned long), GFP_ATOMIC); - - if (new_addrs == NULL) { - /* leave filterlist itself untouched */ - ret = -ENOMEM; - goto out; + raw_spin_lock_irqsave(&report_filterlist_lock, flags); + if (report_filterlist.used == report_filterlist.size) { + /* Check we pre-allocated enough, and retry if not. */ + if (report_filterlist.used >= new_size) { + raw_spin_unlock_irqrestore(&report_filterlist_lock, flags); + kfree(new_addrs); /* kfree(NULL) is safe */ + delay_free = new_addrs = NULL; + goto retry_alloc; } + if (report_filterlist.used) + memcpy(new_addrs, report_filterlist.addrs, report_filterlist.used * sizeof(unsigned long)); + delay_free = report_filterlist.addrs; /* free the old list */ + report_filterlist.addrs = new_addrs; /* switch to the new list */ report_filterlist.size = new_size; - report_filterlist.addrs = new_addrs; } /* Note: deduplicating should be done in userspace. */ @@ -185,9 +183,9 @@ static ssize_t insert_report_filterlist(const char *func) kallsyms_lookup_name(func); report_filterlist.sorted = false; -out: - spin_unlock_irqrestore(&report_filterlist_lock, flags); + raw_spin_unlock_irqrestore(&report_filterlist_lock, flags); + kfree(delay_free); return ret; } @@ -204,13 +202,13 @@ static int show_info(struct seq_file *file, void *v) } /* show filter functions, and filter type */ - spin_lock_irqsave(&report_filterlist_lock, flags); + raw_spin_lock_irqsave(&report_filterlist_lock, flags); seq_printf(file, "\n%s functions: %s\n", report_filterlist.whitelist ? "whitelisted" : "blacklisted", report_filterlist.used == 0 ? "none" : ""); for (i = 0; i < report_filterlist.used; ++i) seq_printf(file, " %ps\n", (void *)report_filterlist.addrs[i]); - spin_unlock_irqrestore(&report_filterlist_lock, flags); + raw_spin_unlock_irqrestore(&report_filterlist_lock, flags); return 0; } diff --git a/mm/mmap.c b/mm/mmap.c index dfa3d2bfe289101325e6e69ef46a054020ea15f3..e68ace34716f6c4c3ff9b4b1d178bab06cccf5e9 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2900,7 +2900,7 @@ static unsigned long __mmap_region(struct mm_struct *mm, vma_set_anonymous(vma); } - if (map_deny_write_exec(vma, vma->vm_flags)) { + if (map_deny_write_exec(vma->vm_flags, vma->vm_flags)) { error = -EACCES; goto close_and_free_vma; } diff --git a/mm/mprotect.c b/mm/mprotect.c index ed0e21a053398e4a13da4cd6dd63a286721b9b48..ed08f87e39c44e8f5f7149c2f2eb2acace593dd3 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -793,7 +793,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len, break; } - if (map_deny_write_exec(vma, newflags)) { + if (map_deny_write_exec(vma->vm_flags, newflags)) { error = -EACCES; break; } diff --git a/mm/nommu.c b/mm/nommu.c index 8c6686176ebdcb7334736a18fe8024646b35add8..10b42c531e0cf656146335132a93cdee83f6d930 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -582,7 +582,7 @@ static int delete_vma_from_mm(struct vm_area_struct *vma) VMA_ITERATOR(vmi, vma->vm_mm, vma->vm_start); vma_iter_config(&vmi, vma->vm_start, vma->vm_end); - if (vma_iter_prealloc(&vmi, vma)) { + if (vma_iter_prealloc(&vmi, NULL)) { pr_warn("Allocation of vma tree for process %d failed\n", current->pid); return -ENOMEM; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 36cd38df06140f01c03413e74e8dc90bc1c4df81..a58453ed565cd320141c86d9fae97d5cfd42173a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1076,12 +1076,27 @@ __always_inline bool free_pages_prepare(struct page *page, bool skip_kasan_poison = should_skip_kasan_poison(page); bool init = want_init_on_free(); bool compound = PageCompound(page); + struct folio *folio = page_folio(page); VM_BUG_ON_PAGE(PageTail(page), page); trace_mm_page_free(page, order); kmsan_free_page(page, order); + /* + * In rare cases, when truncation or holepunching raced with + * munlock after VM_LOCKED was cleared, Mlocked may still be + * found set here. This does not indicate a problem, unless + * "unevictable_pgs_cleared" appears worryingly large. + */ + if (unlikely(folio_test_mlocked(folio))) { + long nr_pages = folio_nr_pages(folio); + + __folio_clear_mlocked(folio); + zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages); + count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages); + } + if (unlikely(PageHWPoison(page)) && !order) { /* * Do not let hwpoison pages hit pcplists/buddy diff --git a/mm/swap.c b/mm/swap.c index 9bc530395949b7797f395106611b506a9d8ab9b4..3e5f88baf61ee867ce923d75f413ca8946ed9ab8 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -82,20 +82,6 @@ static void __page_cache_release(struct folio *folio, struct lruvec **lruvecp, lruvec_del_folio(*lruvecp, folio); __folio_clear_lru_flags(folio); } - - /* - * In rare cases, when truncation or holepunching raced with - * munlock after VM_LOCKED was cleared, Mlocked may still be - * found set here. This does not indicate a problem, unless - * "unevictable_pgs_cleared" appears worryingly large. - */ - if (unlikely(folio_test_mlocked(folio))) { - long nr_pages = folio_nr_pages(folio); - - __folio_clear_mlocked(folio); - zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages); - count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages); - } } /*