diff options
Diffstat (limited to 'lib')
| -rw-r--r-- | lib/Kconfig.debug | 150 | ||||
| -rw-r--r-- | lib/btree.c | 10 | ||||
| -rw-r--r-- | lib/bug.c | 4 | ||||
| -rw-r--r-- | lib/debugobjects.c | 141 | ||||
| -rw-r--r-- | lib/dma-direct.c | 35 | ||||
| -rw-r--r-- | lib/ioremap.c | 6 | ||||
| -rw-r--r-- | lib/percpu-refcount.c | 2 | ||||
| -rw-r--r-- | lib/rhashtable.c | 4 | ||||
| -rw-r--r-- | lib/swiotlb.c | 77 | ||||
| -rw-r--r-- | lib/test_bpf.c | 6 | ||||
| -rw-r--r-- | lib/test_kmod.c | 2 | ||||
| -rw-r--r-- | lib/test_rhashtable.c | 134 |
12 files changed, 377 insertions, 194 deletions
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 6927c6d8d185..00eeff94b357 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1031,69 +1031,20 @@ config DEBUG_PREEMPT menu "Lock Debugging (spinlocks, mutexes, etc...)" -config DEBUG_RT_MUTEXES - bool "RT Mutex debugging, deadlock detection" - depends on DEBUG_KERNEL && RT_MUTEXES - help - This allows rt mutex semantics violations and rt mutex related - deadlocks (lockups) to be detected and reported automatically. - -config DEBUG_SPINLOCK - bool "Spinlock and rw-lock debugging: basic checks" - depends on DEBUG_KERNEL - select UNINLINE_SPIN_UNLOCK - help - Say Y here and build SMP to catch missing spinlock initialization - and certain other kinds of spinlock errors commonly made. This is - best used in conjunction with the NMI watchdog so that spinlock - deadlocks are also debuggable. - -config DEBUG_MUTEXES - bool "Mutex debugging: basic checks" - depends on DEBUG_KERNEL - help - This feature allows mutex semantics violations to be detected and - reported. - -config DEBUG_WW_MUTEX_SLOWPATH - bool "Wait/wound mutex debugging: Slowpath testing" - depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT - select DEBUG_LOCK_ALLOC - select DEBUG_SPINLOCK - select DEBUG_MUTEXES - help - This feature enables slowpath testing for w/w mutex users by - injecting additional -EDEADLK wound/backoff cases. Together with - the full mutex checks enabled with (CONFIG_PROVE_LOCKING) this - will test all possible w/w mutex interface abuse with the - exception of simply not acquiring all the required locks. - Note that this feature can introduce significant overhead, so - it really should not be enabled in a production or distro kernel, - even a debug kernel. If you are a driver writer, enable it. If - you are a distro, do not. - -config DEBUG_LOCK_ALLOC - bool "Lock debugging: detect incorrect freeing of live locks" - depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT - select DEBUG_SPINLOCK - select DEBUG_MUTEXES - select DEBUG_RT_MUTEXES if RT_MUTEXES - select LOCKDEP - help - This feature will check whether any held lock (spinlock, rwlock, - mutex or rwsem) is incorrectly freed by the kernel, via any of the - memory-freeing routines (kfree(), kmem_cache_free(), free_pages(), - vfree(), etc.), whether a live lock is incorrectly reinitialized via - spin_lock_init()/mutex_init()/etc., or whether there is any lock - held during task exit. +config LOCK_DEBUGGING_SUPPORT + bool + depends on TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT + default y config PROVE_LOCKING bool "Lock debugging: prove locking correctness" - depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT + depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT select LOCKDEP select DEBUG_SPINLOCK select DEBUG_MUTEXES select DEBUG_RT_MUTEXES if RT_MUTEXES + select DEBUG_RWSEMS if RWSEM_SPIN_ON_OWNER + select DEBUG_WW_MUTEX_SLOWPATH select DEBUG_LOCK_ALLOC select TRACE_IRQFLAGS default n @@ -1131,20 +1082,9 @@ config PROVE_LOCKING For more details, see Documentation/locking/lockdep-design.txt. -config LOCKDEP - bool - depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT - select STACKTRACE - select FRAME_POINTER if !MIPS && !PPC && !ARM_UNWIND && !S390 && !MICROBLAZE && !ARC && !X86 - select KALLSYMS - select KALLSYMS_ALL - -config LOCKDEP_SMALL - bool - config LOCK_STAT bool "Lock usage statistics" - depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT + depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT select LOCKDEP select DEBUG_SPINLOCK select DEBUG_MUTEXES @@ -1164,6 +1104,80 @@ config LOCK_STAT CONFIG_LOCK_STAT defines "contended" and "acquired" lock events. (CONFIG_LOCKDEP defines "acquire" and "release" events.) +config DEBUG_RT_MUTEXES + bool "RT Mutex debugging, deadlock detection" + depends on DEBUG_KERNEL && RT_MUTEXES + help + This allows rt mutex semantics violations and rt mutex related + deadlocks (lockups) to be detected and reported automatically. + +config DEBUG_SPINLOCK + bool "Spinlock and rw-lock debugging: basic checks" + depends on DEBUG_KERNEL + select UNINLINE_SPIN_UNLOCK + help + Say Y here and build SMP to catch missing spinlock initialization + and certain other kinds of spinlock errors commonly made. This is + best used in conjunction with the NMI watchdog so that spinlock + deadlocks are also debuggable. + +config DEBUG_MUTEXES + bool "Mutex debugging: basic checks" + depends on DEBUG_KERNEL + help + This feature allows mutex semantics violations to be detected and + reported. + +config DEBUG_WW_MUTEX_SLOWPATH + bool "Wait/wound mutex debugging: Slowpath testing" + depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT + select DEBUG_LOCK_ALLOC + select DEBUG_SPINLOCK + select DEBUG_MUTEXES + help + This feature enables slowpath testing for w/w mutex users by + injecting additional -EDEADLK wound/backoff cases. Together with + the full mutex checks enabled with (CONFIG_PROVE_LOCKING) this + will test all possible w/w mutex interface abuse with the + exception of simply not acquiring all the required locks. + Note that this feature can introduce significant overhead, so + it really should not be enabled in a production or distro kernel, + even a debug kernel. If you are a driver writer, enable it. If + you are a distro, do not. + +config DEBUG_RWSEMS + bool "RW Semaphore debugging: basic checks" + depends on DEBUG_KERNEL && RWSEM_SPIN_ON_OWNER + help + This debugging feature allows mismatched rw semaphore locks and unlocks + to be detected and reported. + +config DEBUG_LOCK_ALLOC + bool "Lock debugging: detect incorrect freeing of live locks" + depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT + select DEBUG_SPINLOCK + select DEBUG_MUTEXES + select DEBUG_RT_MUTEXES if RT_MUTEXES + select LOCKDEP + help + This feature will check whether any held lock (spinlock, rwlock, + mutex or rwsem) is incorrectly freed by the kernel, via any of the + memory-freeing routines (kfree(), kmem_cache_free(), free_pages(), + vfree(), etc.), whether a live lock is incorrectly reinitialized via + spin_lock_init()/mutex_init()/etc., or whether there is any lock + held during task exit. + +config LOCKDEP + bool + depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT + select STACKTRACE + select FRAME_POINTER if !MIPS && !PPC && !ARM_UNWIND && !S390 && !MICROBLAZE && !ARC && !X86 + select KALLSYMS + select KALLSYMS_ALL + +config LOCKDEP_SMALL + bool + config DEBUG_LOCKDEP bool "Lock dependency engine debugging" depends on DEBUG_KERNEL && LOCKDEP diff --git a/lib/btree.c b/lib/btree.c index f93a945274af..590facba2c50 100644 --- a/lib/btree.c +++ b/lib/btree.c @@ -3,7 +3,7 @@ * * As should be obvious for Linux kernel code, license is GPLv2 * - * Copyright (c) 2007-2008 Joern Engel <joern@logfs.org> + * Copyright (c) 2007-2008 Joern Engel <joern@purestorage.com> * Bits and pieces stolen from Peter Zijlstra's code, which is * Copyright 2007, Red Hat Inc. Peter Zijlstra * GPLv2 @@ -76,6 +76,8 @@ struct btree_geo btree_geo128 = { }; EXPORT_SYMBOL_GPL(btree_geo128); +#define MAX_KEYLEN (2 * LONG_PER_U64) + static struct kmem_cache *btree_cachep; void *btree_alloc(gfp_t gfp_mask, void *pool_data) @@ -313,7 +315,7 @@ void *btree_get_prev(struct btree_head *head, struct btree_geo *geo, { int i, height; unsigned long *node, *oldnode; - unsigned long *retry_key = NULL, key[geo->keylen]; + unsigned long *retry_key = NULL, key[MAX_KEYLEN]; if (keyzero(geo, __key)) return NULL; @@ -639,8 +641,8 @@ EXPORT_SYMBOL_GPL(btree_remove); int btree_merge(struct btree_head *target, struct btree_head *victim, struct btree_geo *geo, gfp_t gfp) { - unsigned long key[geo->keylen]; - unsigned long dup[geo->keylen]; + unsigned long key[MAX_KEYLEN]; + unsigned long dup[MAX_KEYLEN]; void *val; int err; diff --git a/lib/bug.c b/lib/bug.c index c1b0fad31b10..1077366f496b 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -150,6 +150,8 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs) return BUG_TRAP_TYPE_NONE; bug = find_bug(bugaddr); + if (!bug) + return BUG_TRAP_TYPE_NONE; file = NULL; line = 0; @@ -191,7 +193,7 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs) if (file) pr_crit("kernel BUG at %s:%u!\n", file, line); else - pr_crit("Kernel BUG at %p [verbose debug info unavailable]\n", + pr_crit("Kernel BUG at %pB [verbose debug info unavailable]\n", (void *)bugaddr); return BUG_TRAP_TYPE_BUG; diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 2f5349c6e81a..994be4805cec 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -42,14 +42,18 @@ static struct debug_obj obj_static_pool[ODEBUG_POOL_SIZE] __initdata; static DEFINE_RAW_SPINLOCK(pool_lock); static HLIST_HEAD(obj_pool); +static HLIST_HEAD(obj_to_free); static int obj_pool_min_free = ODEBUG_POOL_SIZE; static int obj_pool_free = ODEBUG_POOL_SIZE; static int obj_pool_used; static int obj_pool_max_used; +/* The number of objs on the global free list */ +static int obj_nr_tofree; static struct kmem_cache *obj_cache; static int debug_objects_maxchain __read_mostly; +static int __maybe_unused debug_objects_maxchecked __read_mostly; static int debug_objects_fixups __read_mostly; static int debug_objects_warnings __read_mostly; static int debug_objects_enabled __read_mostly @@ -96,12 +100,32 @@ static const char *obj_states[ODEBUG_STATE_MAX] = { static void fill_pool(void) { gfp_t gfp = GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN; - struct debug_obj *new; + struct debug_obj *new, *obj; unsigned long flags; if (likely(obj_pool_free >= debug_objects_pool_min_level)) return; + /* + * Reuse objs from the global free list; they will be reinitialized + * when allocating. + */ + while (obj_nr_tofree && (obj_pool_free < obj_pool_min_free)) { + raw_spin_lock_irqsave(&pool_lock, flags); + /* + * Recheck with the lock held as the worker thread might have + * won the race and freed the global free list already. + */ + if (obj_nr_tofree) { + obj = hlist_entry(obj_to_free.first, typeof(*obj), node); + hlist_del(&obj->node); + obj_nr_tofree--; + hlist_add_head(&obj->node, &obj_pool); + obj_pool_free++; + } + raw_spin_unlock_irqrestore(&pool_lock, flags); + } + if (unlikely(!obj_cache)) return; @@ -177,62 +201,76 @@ alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr) * workqueue function to free objects. * * To reduce contention on the global pool_lock, the actual freeing of - * debug objects will be delayed if the pool_lock is busy. We also free - * the objects in a batch of 4 for each lock/unlock cycle. + * debug objects will be delayed if the pool_lock is busy. */ -#define ODEBUG_FREE_BATCH 4 - static void free_obj_work(struct work_struct *work) { - struct debug_obj *objs[ODEBUG_FREE_BATCH]; + struct hlist_node *tmp; + struct debug_obj *obj; unsigned long flags; - int i; + HLIST_HEAD(tofree); if (!raw_spin_trylock_irqsave(&pool_lock, flags)) return; - while (obj_pool_free >= debug_objects_pool_size + ODEBUG_FREE_BATCH) { - for (i = 0; i < ODEBUG_FREE_BATCH; i++) { - objs[i] = hlist_entry(obj_pool.first, - typeof(*objs[0]), node); - hlist_del(&objs[i]->node); - } - obj_pool_free -= ODEBUG_FREE_BATCH; - debug_objects_freed += ODEBUG_FREE_BATCH; - /* - * We release pool_lock across kmem_cache_free() to - * avoid contention on pool_lock. - */ - raw_spin_unlock_irqrestore(&pool_lock, flags); - for (i = 0; i < ODEBUG_FREE_BATCH; i++) - kmem_cache_free(obj_cache, objs[i]); - if (!raw_spin_trylock_irqsave(&pool_lock, flags)) - return; + /* + * The objs on the pool list might be allocated before the work is + * run, so recheck if pool list it full or not, if not fill pool + * list from the global free list + */ + while (obj_nr_tofree && obj_pool_free < debug_objects_pool_size) { + obj = hlist_entry(obj_to_free.first, typeof(*obj), node); + hlist_del(&obj->node); + hlist_add_head(&obj->node, &obj_pool); + obj_pool_free++; + obj_nr_tofree--; + } + + /* + * Pool list is already full and there are still objs on the free + * list. Move remaining free objs to a temporary list to free the + * memory outside the pool_lock held region. + */ + if (obj_nr_tofree) { + hlist_move_list(&obj_to_free, &tofree); + debug_objects_freed += obj_nr_tofree; + obj_nr_tofree = 0; } raw_spin_unlock_irqrestore(&pool_lock, flags); + + hlist_for_each_entry_safe(obj, tmp, &tofree, node) { + hlist_del(&obj->node); + kmem_cache_free(obj_cache, obj); + } } -/* - * Put the object back into the pool and schedule work to free objects - * if necessary. - */ -static void free_object(struct debug_obj *obj) +static bool __free_object(struct debug_obj *obj) { unsigned long flags; - int sched = 0; + bool work; raw_spin_lock_irqsave(&pool_lock, flags); - /* - * schedule work when the pool is filled and the cache is - * initialized: - */ - if (obj_pool_free > debug_objects_pool_size && obj_cache) - sched = 1; - hlist_add_head(&obj->node, &obj_pool); - obj_pool_free++; + work = (obj_pool_free > debug_objects_pool_size) && obj_cache; obj_pool_used--; + + if (work) { + obj_nr_tofree++; + hlist_add_head(&obj->node, &obj_to_free); + } else { + obj_pool_free++; + hlist_add_head(&obj->node, &obj_pool); + } raw_spin_unlock_irqrestore(&pool_lock, flags); - if (sched) + return work; +} + +/* + * Put the object back into the pool and schedule work to free objects + * if necessary. + */ +static void free_object(struct debug_obj *obj) +{ + if (__free_object(obj)) schedule_work(&debug_obj_work); } @@ -714,13 +752,13 @@ EXPORT_SYMBOL_GPL(debug_object_active_state); static void __debug_check_no_obj_freed(const void *address, unsigned long size) { unsigned long flags, oaddr, saddr, eaddr, paddr, chunks; - struct hlist_node *tmp; - HLIST_HEAD(freelist); struct debug_obj_descr *descr; enum debug_obj_state state; struct debug_bucket *db; + struct hlist_node *tmp; struct debug_obj *obj; - int cnt; + int cnt, objs_checked = 0; + bool work = false; saddr = (unsigned long) address; eaddr = saddr + size; @@ -751,21 +789,24 @@ repeat: goto repeat; default: hlist_del(&obj->node); - hlist_add_head(&obj->node, &freelist); + work |= __free_object(obj); break; } } raw_spin_unlock_irqrestore(&db->lock, flags); - /* Now free them */ - hlist_for_each_entry_safe(obj, tmp, &freelist, node) { - hlist_del(&obj->node); - free_object(obj); - } - if (cnt > debug_objects_maxchain) debug_objects_maxchain = cnt; + + objs_checked += cnt; } + + if (objs_checked > debug_objects_maxchecked) + debug_objects_maxchecked = objs_checked; + + /* Schedule work to actually kmem_cache_free() objects */ + if (work) + schedule_work(&debug_obj_work); } void debug_check_no_obj_freed(const void *address, unsigned long size) @@ -780,12 +821,14 @@ void debug_check_no_obj_freed(const void *address, unsigned long size) static int debug_stats_show(struct seq_file *m, void *v) { seq_printf(m, "max_chain :%d\n", debug_objects_maxchain); + seq_printf(m, "max_checked :%d\n", debug_objects_maxchecked); seq_printf(m, "warnings :%d\n", debug_objects_warnings); seq_printf(m, "fixups :%d\n", debug_objects_fixups); seq_printf(m, "pool_free :%d\n", obj_pool_free); seq_printf(m, "pool_min_free :%d\n", obj_pool_min_free); seq_printf(m, "pool_used :%d\n", obj_pool_used); seq_printf(m, "pool_max_used :%d\n", obj_pool_max_used); + seq_printf(m, "on_free_list :%d\n", obj_nr_tofree); seq_printf(m, "objs_allocated:%d\n", debug_objects_allocated); seq_printf(m, "objs_freed :%d\n", debug_objects_freed); return 0; diff --git a/lib/dma-direct.c b/lib/dma-direct.c index c9e8e21cb334..c0bba30fef0a 100644 --- a/lib/dma-direct.c +++ b/lib/dma-direct.c @@ -9,6 +9,7 @@ #include <linux/scatterlist.h> #include <linux/dma-contiguous.h> #include <linux/pfn.h> +#include <linux/set_memory.h> #define DIRECT_MAPPING_ERROR 0 @@ -20,6 +21,14 @@ #define ARCH_ZONE_DMA_BITS 24 #endif +/* + * For AMD SEV all DMA must be to unencrypted addresses. + */ +static inline bool force_dma_unencrypted(void) +{ + return sev_active(); +} + static bool check_addr(struct device *dev, dma_addr_t dma_addr, size_t size, const char *caller) @@ -37,7 +46,9 @@ check_addr(struct device *dev, dma_addr_t dma_addr, size_t size, static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) { - return phys_to_dma(dev, phys) + size - 1 <= dev->coherent_dma_mask; + dma_addr_t addr = force_dma_unencrypted() ? + __phys_to_dma(dev, phys) : phys_to_dma(dev, phys); + return addr + size - 1 <= dev->coherent_dma_mask; } void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, @@ -46,6 +57,10 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; int page_order = get_order(size); struct page *page = NULL; + void *ret; + + /* we always manually zero the memory once we are done: */ + gfp &= ~__GFP_ZERO; /* GFP_DMA32 and GFP_DMA are no ops without the corresponding zones: */ if (dev->coherent_dma_mask <= DMA_BIT_MASK(ARCH_ZONE_DMA_BITS)) @@ -78,10 +93,15 @@ again: if (!page) return NULL; - - *dma_handle = phys_to_dma(dev, page_to_phys(page)); - memset(page_address(page), 0, size); - return page_address(page); + ret = page_address(page); + if (force_dma_unencrypted()) { + set_memory_decrypted((unsigned long)ret, 1 << page_order); + *dma_handle = __phys_to_dma(dev, page_to_phys(page)); + } else { + *dma_handle = phys_to_dma(dev, page_to_phys(page)); + } + memset(ret, 0, size); + return ret; } /* @@ -92,9 +112,12 @@ void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs) { unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; + unsigned int page_order = get_order(size); + if (force_dma_unencrypted()) + set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order); if (!dma_release_from_contiguous(dev, virt_to_page(cpu_addr), count)) - free_pages((unsigned long)cpu_addr, get_order(size)); + free_pages((unsigned long)cpu_addr, page_order); } static dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, diff --git a/lib/ioremap.c b/lib/ioremap.c index b808a390e4c3..54e5bbaa3200 100644 --- a/lib/ioremap.c +++ b/lib/ioremap.c @@ -91,7 +91,8 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr, if (ioremap_pmd_enabled() && ((next - addr) == PMD_SIZE) && - IS_ALIGNED(phys_addr + addr, PMD_SIZE)) { + IS_ALIGNED(phys_addr + addr, PMD_SIZE) && + pmd_free_pte_page(pmd)) { if (pmd_set_huge(pmd, phys_addr + addr, prot)) continue; } @@ -117,7 +118,8 @@ static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr, if (ioremap_pud_enabled() && ((next - addr) == PUD_SIZE) && - IS_ALIGNED(phys_addr + addr, PUD_SIZE)) { + IS_ALIGNED(phys_addr + addr, PUD_SIZE) && + pud_free_pmd_page(pud)) { if (pud_set_huge(pud, phys_addr + addr, prot)) continue; } diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c index 30e7dd88148b..9f96fa7bc000 100644 --- a/lib/percpu-refcount.c +++ b/lib/percpu-refcount.c @@ -322,6 +322,8 @@ EXPORT_SYMBOL_GPL(percpu_ref_switch_to_percpu); * This function normally doesn't block and can be called from any context * but it may block if @confirm_kill is specified and @ref is in the * process of switching to atomic mode by percpu_ref_switch_to_atomic(). + * + * There are no implied RCU grace periods between kill and release. */ void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill) diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 3825c30aaa36..47de025b6245 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -506,8 +506,10 @@ static void *rhashtable_lookup_one(struct rhashtable *ht, if (!key || (ht->p.obj_cmpfn ? ht->p.obj_cmpfn(&arg, rht_obj(ht, head)) : - rhashtable_compare(&arg, rht_obj(ht, head)))) + rhashtable_compare(&arg, rht_obj(ht, head)))) { + pprev = &head->next; continue; + } if (!ht->rhlist) return rht_obj(ht, head); diff --git a/lib/swiotlb.c b/lib/swiotlb.c index c43ec2271469..47aeb04c1997 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -31,6 +31,7 @@ #include <linux/gfp.h> #include <linux/scatterlist.h> #include <linux/mem_encrypt.h> +#include <linux/set_memory.h> #include <asm/io.h> #include <asm/dma.h> @@ -156,22 +157,6 @@ unsigned long swiotlb_size_or_default(void) return size ? size : (IO_TLB_DEFAULT_SIZE); } -void __weak swiotlb_set_mem_attributes(void *vaddr, unsigned long size) { } - -/* For swiotlb, clear memory encryption mask from dma addresses */ -static dma_addr_t swiotlb_phys_to_dma(struct device *hwdev, - phys_addr_t address) -{ - return __sme_clr(phys_to_dma(hwdev, address)); -} - -/* Note that this doesn't work with highmem page */ -static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev, - volatile void *address) -{ - return phys_to_dma(hwdev, virt_to_phys(address)); -} - static bool no_iotlb_memory; void swiotlb_print_info(void) @@ -209,12 +194,12 @@ void __init swiotlb_update_mem_attributes(void) vaddr = phys_to_virt(io_tlb_start); bytes = PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT); - swiotlb_set_mem_attributes(vaddr, bytes); + set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT); memset(vaddr, 0, bytes); vaddr = phys_to_virt(io_tlb_overflow_buffer); bytes = PAGE_ALIGN(io_tlb_overflow); - swiotlb_set_mem_attributes(vaddr, bytes); + set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT); memset(vaddr, 0, bytes); } @@ -355,7 +340,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) io_tlb_start = virt_to_phys(tlb); io_tlb_end = io_tlb_start + bytes; - swiotlb_set_mem_attributes(tlb, bytes); + set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT); memset(tlb, 0, bytes); /* @@ -366,7 +351,8 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) if (!v_overflow_buffer) goto cleanup2; - swiotlb_set_mem_attributes(v_overflow_buffer, io_tlb_overflow); + set_memory_decrypted((unsigned long)v_overflow_buffer, + io_tlb_overflow >> PAGE_SHIFT); memset(v_overflow_buffer, 0, io_tlb_overflow); io_tlb_overflow_buffer = virt_to_phys(v_overflow_buffer); @@ -622,7 +608,7 @@ map_single(struct device *hwdev, phys_addr_t phys, size_t size, return SWIOTLB_MAP_ERROR; } - start_dma_addr = swiotlb_phys_to_dma(hwdev, io_tlb_start); + start_dma_addr = __phys_to_dma(hwdev, io_tlb_start); return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size, dir, attrs); } @@ -706,6 +692,7 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, } } +#ifdef CONFIG_DMA_DIRECT_OPS static inline bool dma_coherent_ok(struct device *dev, dma_addr_t addr, size_t size) { @@ -726,12 +713,12 @@ swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle, goto out_warn; phys_addr = swiotlb_tbl_map_single(dev, - swiotlb_phys_to_dma(dev, io_tlb_start), + __phys_to_dma(dev, io_tlb_start), 0, size, DMA_FROM_DEVICE, 0); if (phys_addr == SWIOTLB_MAP_ERROR) goto out_warn; - *dma_handle = swiotlb_phys_to_dma(dev, phys_addr); + *dma_handle = __phys_to_dma(dev, phys_addr); if (dma_coherent_ok(dev, *dma_handle, size)) goto out_unmap; @@ -759,28 +746,6 @@ out_warn: return NULL; } -void * -swiotlb_alloc_coherent(struct device *hwdev, size_t size, - dma_addr_t *dma_handle, gfp_t flags) -{ - int order = get_order(size); - unsigned long attrs = (flags & __GFP_NOWARN) ? DMA_ATTR_NO_WARN : 0; - void *ret; - - ret = (void *)__get_free_pages(flags, order); - if (ret) { - *dma_handle = swiotlb_virt_to_bus(hwdev, ret); - if (dma_coherent_ok(hwdev, *dma_handle, size)) { - memset(ret, 0, size); - return ret; - } - free_pages((unsigned long)ret, order); - } - - return swiotlb_alloc_buffer(hwdev, size, dma_handle, attrs); -} -EXPORT_SYMBOL(swiotlb_alloc_coherent); - static bool swiotlb_free_buffer(struct device *dev, size_t size, dma_addr_t dma_addr) { @@ -799,15 +764,7 @@ static bool swiotlb_free_buffer(struct device *dev, size_t size, DMA_ATTR_SKIP_CPU_SYNC); return true; } - -void -swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr, - dma_addr_t dev_addr) -{ - if (!swiotlb_free_buffer(hwdev, size, dev_addr)) - free_pages((unsigned long)vaddr, get_order(size)); -} -EXPORT_SYMBOL(swiotlb_free_coherent); +#endif static void swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir, @@ -867,10 +824,10 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, map = map_single(dev, phys, size, dir, attrs); if (map == SWIOTLB_MAP_ERROR) { swiotlb_full(dev, size, dir, 1); - return swiotlb_phys_to_dma(dev, io_tlb_overflow_buffer); + return __phys_to_dma(dev, io_tlb_overflow_buffer); } - dev_addr = swiotlb_phys_to_dma(dev, map); + dev_addr = __phys_to_dma(dev, map); /* Ensure that the address returned is DMA'ble */ if (dma_capable(dev, dev_addr, size)) @@ -879,7 +836,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, attrs |= DMA_ATTR_SKIP_CPU_SYNC; swiotlb_tbl_unmap_single(dev, map, size, dir, attrs); - return swiotlb_phys_to_dma(dev, io_tlb_overflow_buffer); + return __phys_to_dma(dev, io_tlb_overflow_buffer); } /* @@ -1009,7 +966,7 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, sg_dma_len(sgl) = 0; return 0; } - sg->dma_address = swiotlb_phys_to_dma(hwdev, map); + sg->dma_address = __phys_to_dma(hwdev, map); } else sg->dma_address = dev_addr; sg_dma_len(sg) = sg->length; @@ -1073,7 +1030,7 @@ swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, int swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr) { - return (dma_addr == swiotlb_phys_to_dma(hwdev, io_tlb_overflow_buffer)); + return (dma_addr == __phys_to_dma(hwdev, io_tlb_overflow_buffer)); } /* @@ -1085,7 +1042,7 @@ swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr) int swiotlb_dma_supported(struct device *hwdev, u64 mask) { - return swiotlb_phys_to_dma(hwdev, io_tlb_end - 1) <= mask; + return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask; } #ifdef CONFIG_DMA_DIRECT_OPS diff --git a/lib/test_bpf.c b/lib/test_bpf.c index b4e22345963f..3e9335493fe4 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -24,10 +24,11 @@ #include <linux/if_vlan.h> #include <linux/random.h> #include <linux/highmem.h> +#include <linux/sched.h> /* General test specific settings */ #define MAX_SUBTESTS 3 -#define MAX_TESTRUNS 10000 +#define MAX_TESTRUNS 1000 #define MAX_DATA 128 #define MAX_INSNS 512 #define MAX_K 0xffffFFFF @@ -5466,7 +5467,7 @@ static struct bpf_test tests[] = { { "BPF_MAXINSNS: Jump, gap, jump, ...", { }, -#ifdef CONFIG_BPF_JIT_ALWAYS_ON +#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_X86) CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL, #else CLASSIC | FLAG_NO_DATA, @@ -6582,6 +6583,7 @@ static __init int test_bpf(void) struct bpf_prog *fp; int err; + cond_resched(); if (exclude_test(i)) continue; diff --git a/lib/test_kmod.c b/lib/test_kmod.c index e372b97eee13..0e5b7a61460b 100644 --- a/lib/test_kmod.c +++ b/lib/test_kmod.c @@ -1141,7 +1141,7 @@ static struct kmod_test_device *register_test_dev_kmod(void) mutex_lock(®_dev_mutex); /* int should suffice for number of devices, test for wrap */ - if (unlikely(num_test_devs + 1) < 0) { + if (num_test_devs + 1 == INT_MAX) { pr_err("reached limit of number of test devices\n"); goto out; } diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index 76d3667fdea2..f4000c137dbe 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -79,6 +79,21 @@ struct thread_data { struct test_obj *objs; }; +static u32 my_hashfn(const void *data, u32 len, u32 seed) +{ + const struct test_obj_rhl *obj = data; + + return (obj->value.id % 10) << RHT_HASH_RESERVED_SPACE; +} + +static int my_cmpfn(struct rhashtable_compare_arg *arg, const void *obj) +{ + const struct test_obj_rhl *test_obj = obj; + const struct test_obj_val *val = arg->key; + + return test_obj->value.id - val->id; +} + static struct rhashtable_params test_rht_params = { .head_offset = offsetof(struct test_obj, node), .key_offset = offsetof(struct test_obj, value), @@ -87,6 +102,17 @@ static struct rhashtable_params test_rht_params = { .nulls_base = (3U << RHT_BASE_SHIFT), }; +static struct rhashtable_params test_rht_params_dup = { + .head_offset = offsetof(struct test_obj_rhl, list_node), + .key_offset = offsetof(struct test_obj_rhl, value), + .key_len = sizeof(struct test_obj_val), + .hashfn = jhash, + .obj_hashfn = my_hashfn, + .obj_cmpfn = my_cmpfn, + .nelem_hint = 128, + .automatic_shrinking = false, +}; + static struct semaphore prestart_sem; static struct semaphore startup_sem = __SEMAPHORE_INITIALIZER(startup_sem, 0); @@ -465,6 +491,112 @@ static int __init test_rhashtable_max(struct test_obj *array, return err; } +static unsigned int __init print_ht(struct rhltable *rhlt) +{ + struct rhashtable *ht; + const struct bucket_table *tbl; + char buff[512] = ""; + unsigned int i, cnt = 0; + + ht = &rhlt->ht; + tbl = rht_dereference(ht->tbl, ht); + for (i = 0; i < tbl->size; i++) { + struct rhash_head *pos, *next; + struct test_obj_rhl *p; + + pos = rht_dereference(tbl->buckets[i], ht); + next = !rht_is_a_nulls(pos) ? rht_dereference(pos->next, ht) : NULL; + + if (!rht_is_a_nulls(pos)) { + sprintf(buff, "%s\nbucket[%d] -> ", buff, i); + } + + while (!rht_is_a_nulls(pos)) { + struct rhlist_head *list = container_of(pos, struct rhlist_head, rhead); + sprintf(buff, "%s[[", buff); + do { + pos = &list->rhead; + list = rht_dereference(list->next, ht); + p = rht_obj(ht, pos); + + sprintf(buff, "%s val %d (tid=%d)%s", buff, p->value.id, p->value.tid, + list? ", " : " "); + cnt++; + } while (list); + + pos = next, + next = !rht_is_a_nulls(pos) ? + rht_dereference(pos->next, ht) : NULL; + + sprintf(buff, "%s]]%s", buff, !rht_is_a_nulls(pos) ? " -> " : ""); + } + } + printk(KERN_ERR "\n---- ht: ----%s\n-------------\n", buff); + + return cnt; +} + +static int __init test_insert_dup(struct test_obj_rhl *rhl_test_objects, + int cnt, bool slow) +{ + struct rhltable rhlt; + unsigned int i, ret; + const char *key; + int err = 0; + + err = rhltable_init(&rhlt, &test_rht_params_dup); + if (WARN_ON(err)) + return err; + + for (i = 0; i < cnt; i++) { + rhl_test_objects[i].value.tid = i; + key = rht_obj(&rhlt.ht, &rhl_test_objects[i].list_node.rhead); + key += test_rht_params_dup.key_offset; + + if (slow) { + err = PTR_ERR(rhashtable_insert_slow(&rhlt.ht, key, + &rhl_test_objects[i].list_node.rhead)); + if (err == -EAGAIN) + err = 0; + } else + err = rhltable_insert(&rhlt, + &rhl_test_objects[i].list_node, + test_rht_params_dup); + if (WARN(err, "error %d on element %d/%d (%s)\n", err, i, cnt, slow? "slow" : "fast")) + goto skip_print; + } + + ret = print_ht(&rhlt); + WARN(ret != cnt, "missing rhltable elements (%d != %d, %s)\n", ret, cnt, slow? "slow" : "fast"); + +skip_print: + rhltable_destroy(&rhlt); + + return 0; +} + +static int __init test_insert_duplicates_run(void) +{ + struct test_obj_rhl rhl_test_objects[3] = {}; + + pr_info("test inserting duplicates\n"); + + /* two different values that map to same bucket */ + rhl_test_objects[0].value.id = 1; + rhl_test_objects[1].value.id = 21; + + /* and another duplicate with same as [0] value + * which will be second on the bucket list */ + rhl_test_objects[2].value.id = rhl_test_objects[0].value.id; + + test_insert_dup(rhl_test_objects, 2, false); + test_insert_dup(rhl_test_objects, 3, false); + test_insert_dup(rhl_test_objects, 2, true); + test_insert_dup(rhl_test_objects, 3, true); + + return 0; +} + static int thread_lookup_test(struct thread_data *tdata) { unsigned int entries = tdata->entries; @@ -613,6 +745,8 @@ static int __init test_rht_init(void) do_div(total_time, runs); pr_info("Average test time: %llu\n", total_time); + test_insert_duplicates_run(); + if (!tcount) return 0; |