- Kernel - mailweb.openeuler.org

[PATCH] Add the limit on page cache
by wenzhiwei 27 Oct '21

27 Oct '21

kylin inclusion category: feature bugfix: https://gitee.com/openeuler-competition/summer-2021/issues/I3EIMT?from=proj… CVE: NA -------------------------------------------------- In some atomic operation scenarios, such as interrupt context, it is not possible to sleep. Therefore, when memory allocation in this scenario, it will not enter the direct_reclaim link, and will not even wake up the kswapd process. For example, in the soft interrupt processing function of the network card receiving packets, there may be a phenomenon that the page cache is too occupied and the remaining memory of the system is insufficient, and the memory cannot be allocated for the received data packet, and the packet is directly lost. This is the problem to be solved by the page cache limit. The page cache limit is mainly used to detect whether the page cache exceeds the upper limit we set (/proc/sys/vm/pagecache_limit_ratio) when the page cache is added to the application (that is, when the add_to_page_cache_lru function is called) Provides 3 /proc interfaces, respectively: echo x > /proc/sys/vm/pagecache_limit_ratio（0 < x < 100）:Enable page cache limit function x means limit the percentage of page cache to the total system memory /proc/sys/vm/pagecache_limit_ignore_dirty :Whether to ignore dirty pages when calculating the memory occupied by the page cache. The default value is 1, which means ignore. Because the recycling of dirty pages is time-consuming. /proc/sys/vm/pagecache_limit_async:1 means asynchronous recycling, 0 means synchronous recycling signed-off-by: wen zhiwei <wenzhiwei(a)kylinos.cn> Signed-off-by: wenzhiwei <wenzhiwei(a)kylinos.cn> --- include/linux/memcontrol.h | 7 +- include/linux/mmzone.h | 7 + include/linux/swap.h | 15 + include/trace/events/vmscan.h | 28 +- kernel/sysctl.c | 139 ++++++++ mm/filemap.c | 2 + mm/page_alloc.c | 52 +++ mm/vmscan.c | 650 ++++++++++++++++++++++++++++++++-- mm/workingset.c | 1 + 9 files changed, 862 insertions(+), 39 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 71a5b589bddb..731a2cd2ea86 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -50,6 +50,7 @@ enum memcg_memory_event { struct mem_cgroup_reclaim_cookie { pg_data_t *pgdat; + int priority; unsigned int generation; }; @@ -492,8 +493,7 @@ mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid) * @node combination. This can be the node lruvec, if the memory * controller is disabled. */ -static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, - struct pglist_data *pgdat) +static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, struct pglist_data *pgdat) { struct mem_cgroup_per_node *mz; struct lruvec *lruvec; @@ -1066,8 +1066,7 @@ static inline void mem_cgroup_migrate(struct page *old, struct page *new) { } -static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, - struct pglist_data *pgdat) +static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, struct pglist_data *pgdat) { return &pgdat->__lruvec; } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 82fceef88448..d3c5258e5d0d 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -445,6 +445,13 @@ struct zone { * changes. */ long lowmem_reserve[MAX_NR_ZONES]; + /* + * This atomic counter is set when there is pagecache limit + * reclaim going on on this particular zone. Other potential + * reclaiers should back off to prevent from heavy lru_lock + * bouncing. + */ + atomic_t pagecache_reclaim; #ifdef CONFIG_NEED_MULTIPLE_NODES int node; diff --git a/include/linux/swap.h b/include/linux/swap.h index 9b708c0288bc..b9329e575836 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -377,6 +377,21 @@ extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, unsigned long *nr_scanned); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; + +#define ADDITIONAL_RECLAIM_RATIO 2 +extern unsigned long pagecache_over_limit(void); +extern void shrink_page_cache(gfp_t mask, struct page *page); +extern unsigned long vm_pagecache_limit_pages; +extern unsigned long vm_pagecache_limit_reclaim_pages; +extern int unsigned vm_pagecache_limit_ratio; +extern int vm_pagecache_limit_reclaim_ratio; +extern unsigned int vm_pagecache_ignore_dirty; +extern unsigned long pagecache_over_limit(void); +extern unsigned int vm_pagecache_limit_async; +extern int kpagecache_limitd_run(void); +extern void kpagecache_limitd_stop(void); +extern unsigned int vm_pagecache_ignore_slab; + extern int remove_mapping(struct address_space *mapping, struct page *page); extern unsigned long reclaim_pages(struct list_head *page_list); diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 2070df64958e..3bfe47a85f6f 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -183,48 +183,48 @@ DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_softlimit_re #endif /* CONFIG_MEMCG */ TRACE_EVENT(mm_shrink_slab_start, - TP_PROTO(struct shrinker *shr, struct shrink_control *sc, - long nr_objects_to_shrink, unsigned long cache_items, - unsigned long long delta, unsigned long total_scan, - int priority), - - TP_ARGS(shr, sc, nr_objects_to_shrink, cache_items, delta, total_scan, - priority), + TP_PROTO(struct shrinker *shr, struct shrink_control *sc, + long nr_objects_to_shrink,unsigned long pgs_scanned, + unsigned long lru_pgs, unsigned long cache_items, + unsigned long long delta, unsigned long total_scan), + TP_ARGS(shr, sc, nr_objects_to_shrink,pgs_scanned, lru_pgs, cache_items, delta, total_scan), TP_STRUCT__entry( __field(struct shrinker *, shr) __field(void *, shrink) __field(int, nid) __field(long, nr_objects_to_shrink) __field(gfp_t, gfp_flags) + __field(unsigned long, pgs_scanned) + __field(unsigned long, lru_pgs) __field(unsigned long, cache_items) __field(unsigned long long, delta) __field(unsigned long, total_scan) - __field(int, priority) ), TP_fast_assign( - __entry->shr = shr; + __entry->shr = shr; __entry->shrink = shr->scan_objects; __entry->nid = sc->nid; __entry->nr_objects_to_shrink = nr_objects_to_shrink; __entry->gfp_flags = sc->gfp_mask; + __entry->pgs_scanned = pgs_scanned; + __entry->lru_pgs = lru_pgs; __entry->cache_items = cache_items; __entry->delta = delta; __entry->total_scan = total_scan; - __entry->priority = priority; ), - - TP_printk("%pS %p: nid: %d objects to shrink %ld gfp_flags %s cache items %ld delta %lld total_scan %ld priority %d", +TP_printk("%pF %p: nid: %d objects to shrink %ld gfp_flags %s pgs_scanned %ld lru_pgs %ld cache items %ld delta %lld total_scan %ld", __entry->shrink, __entry->shr, __entry->nid, __entry->nr_objects_to_shrink, show_gfp_flags(__entry->gfp_flags), + __entry->pgs_scanned, + __entry->lru_pgs, __entry->cache_items, __entry->delta, - __entry->total_scan, - __entry->priority) + __entry->total_scan) ); TRACE_EVENT(mm_shrink_slab_end, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c7ca58de3b1b..4ef436cdfdad 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -111,6 +111,7 @@ static int sixty = 60; #endif +static int zero; static int __maybe_unused neg_one = -1; static int __maybe_unused two = 2; static int __maybe_unused four = 4; @@ -648,6 +649,68 @@ static int do_proc_dointvec(struct ctl_table *table, int write, return __do_proc_dointvec(table->data, table, write, buffer, lenp, ppos, conv, data); } +int setup_pagecache_limit(void) +{ + /* reclaim $ADDITIONAL_RECLAIM_PAGES more than limit. */ + vm_pagecache_limit_reclaim_ratio = vm_pagecache_limit_ratio + ADDITIONAL_RECLAIM_RATIO; + + if (vm_pagecache_limit_reclaim_ratio > 100) + vm_pagecache_limit_reclaim_ratio = 100; + if (vm_pagecache_limit_ratio == 0) + vm_pagecache_limit_reclaim_ratio = 0; + + vm_pagecache_limit_pages = vm_pagecache_limit_ratio * totalram_pages() / 100; + vm_pagecache_limit_reclaim_pages = vm_pagecache_limit_reclaim_ratio * totalram_pages() / 100; + return 0; +} + +static int pc_limit_proc_dointvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (write && !ret) + ret = setup_pagecache_limit(); + return ret; +} +static int pc_reclaim_limit_proc_dointvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int pre_reclaim_ratio = vm_pagecache_limit_reclaim_ratio; + int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + + if (write && vm_pagecache_limit_ratio == 0) + return -EINVAL; + + if (write && !ret) { + if (vm_pagecache_limit_reclaim_ratio - vm_pagecache_limit_ratio < ADDITIONAL_RECLAIM_RATIO) { + vm_pagecache_limit_reclaim_ratio = pre_reclaim_ratio; + return -EINVAL; + } + vm_pagecache_limit_reclaim_pages = vm_pagecache_limit_reclaim_ratio * totalram_pages() / 100; + } + return ret; +} +static int pc_limit_async_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + + if (write && vm_pagecache_limit_ratio == 0) + return -EINVAL; + + if (write && !ret) { + if (vm_pagecache_limit_async > 0) { + if (kpagecache_limitd_run()) { + vm_pagecache_limit_async = 0; + return -EINVAL; + } + } + else { + kpagecache_limitd_stop(); + } + } + return ret; +} static int do_proc_douintvec_w(unsigned int *tbl_data, struct ctl_table *table, @@ -2711,6 +2774,14 @@ static struct ctl_table kern_table[] = { }, { } }; +static int pc_limit_proc_dointvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); + +static int pc_reclaim_limit_proc_dointvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); + +static int pc_limit_async_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); static struct ctl_table vm_table[] = { { @@ -2833,6 +2904,74 @@ static struct ctl_table vm_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = &two_hundred, }, + { + .procname = "pagecache_limit_ratio", + .data = &vm_pagecache_limit_ratio, + .maxlen = sizeof(vm_pagecache_limit_ratio), + .mode = 0644, + .proc_handler = &pc_limit_proc_dointvec, + .extra1 = &zero, + .extra2 = &one_hundred, + }, + { + .procname = "pagecache_limit_reclaim_ratio", + .data = &vm_pagecache_limit_reclaim_ratio, + .maxlen = sizeof(vm_pagecache_limit_reclaim_ratio), + .mode = 0644, + .proc_handler = &pc_reclaim_limit_proc_dointvec, + .extra1 = &zero, + .extra2 = &one_hundred, + }, + { + .procname = "pagecache_limit_ignore_dirty", + .data = &vm_pagecache_ignore_dirty, + .maxlen = sizeof(vm_pagecache_ignore_dirty), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#ifdef CONFIG_SHRINK_PAGECACHE + { + .procname = "cache_reclaim_s", + .data = &vm_cache_reclaim_s, + .maxlen = sizeof(vm_cache_reclaim_s), + .mode = 0644, + .proc_handler = cache_reclaim_sysctl_handler, + .extra1 = &vm_cache_reclaim_s_min, + .extra2 = &vm_cache_reclaim_s_max, + }, + { + .procname = "cache_reclaim_weight", + .data = &vm_cache_reclaim_weight, + .maxlen = sizeof(vm_cache_reclaim_weight), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &vm_cache_reclaim_weight_min, + .extra2 = &vm_cache_reclaim_weight_max, + }, + { + .procname = "cache_reclaim_enable", + .data = &vm_cache_reclaim_enable, + .maxlen = sizeof(vm_cache_reclaim_enable), + .mode = 0644, + .proc_handler = cache_reclaim_enable_handler, + .extra1 = &zero, + .extra2 = &one, + }, + { + .procname = "pagecache_limit_async", + .data = &vm_pagecache_limit_async, + .maxlen = sizeof(vm_pagecache_limit_async), + .mode = 0644, + .proc_handler = &pc_limit_async_handler, + }, + { + .procname = "pagecache_limit_ignore_slab", + .data = &vm_pagecache_ignore_slab, + .maxlen = sizeof(vm_pagecache_ignore_slab), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif #ifdef CONFIG_HUGETLB_PAGE { .procname = "nr_hugepages", diff --git a/mm/filemap.c b/mm/filemap.c index ef611eb34aa7..808d4f02b5a5 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -922,6 +922,8 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, { void *shadow = NULL; int ret; + if (unlikely(vm_pagecache_limit_pages) && pagecache_over_limit() > 0) + shrink_page_cache(gfp_mask, page); __SetPageLocked(page); ret = __add_to_page_cache_locked(page, mapping, offset, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 71afec177233..08feba42d3d7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8933,6 +8933,58 @@ void zone_pcp_reset(struct zone *zone) local_irq_restore(flags); } +/* Returns a number that's positive if the pagecache is above + * the set limit*/ +unsigned long pagecache_over_limit() +{ + unsigned long should_reclaim_pages = 0; + unsigned long overlimit_pages = 0; + unsigned long delta_pages = 0; + unsigned long pgcache_lru_pages = 0; + /* We only want to limit unmapped and non-shmem page cache pages; + * normally all shmem pages are mapped as well*/ + unsigned long pgcache_pages = global_node_page_state(NR_FILE_PAGES) + - max_t(unsigned long, + global_node_page_state(NR_FILE_MAPPED), + global_node_page_state(NR_SHMEM)); + /* We certainly can't free more than what's on the LRU lists + * minus the dirty ones*/ + if (vm_pagecache_ignore_slab) + pgcache_lru_pages = global_node_page_state(NR_ACTIVE_FILE) + + global_node_page_state(NR_INACTIVE_FILE); + else + pgcache_lru_pages = global_node_page_state(NR_ACTIVE_FILE) + + global_node_page_state(NR_INACTIVE_FILE) + + global_node_page_state(NR_SLAB_RECLAIMABLE_B) + + global_node_page_state(NR_SLAB_UNRECLAIMABLE_B); + + if (vm_pagecache_ignore_dirty != 0) + pgcache_lru_pages -= global_node_page_state(NR_FILE_DIRTY) / vm_pagecache_ignore_dirty; + /* Paranoia */ + if (unlikely(pgcache_lru_pages > LONG_MAX)) + return 0; + + /* Limit it to 94% of LRU (not all there might be unmapped) */ + pgcache_lru_pages -= pgcache_lru_pages/16; + if (vm_pagecache_ignore_slab) + pgcache_pages = min_t(unsigned long, pgcache_pages, pgcache_lru_pages); + else + pgcache_pages = pgcache_lru_pages; + + /* + *delta_pages: we should reclaim at least 2% more pages than overlimit_page, values get from + * /proc/vm/pagecache_limit_reclaim_pages + *should_reclaim_pages: the real pages we will reclaim, but it should less than pgcache_pages; + */ + if (pgcache_pages > vm_pagecache_limit_pages) { + overlimit_pages = pgcache_pages - vm_pagecache_limit_pages; + delta_pages = vm_pagecache_limit_reclaim_pages - vm_pagecache_limit_pages; + should_reclaim_pages = min_t(unsigned long, delta_pages, vm_pagecache_limit_pages) + overlimit_pages; + return should_reclaim_pages; + } + return 0; +} + #ifdef CONFIG_MEMORY_HOTREMOVE /* * All pages in the range must be in a single zone, must not contain holes, diff --git a/mm/vmscan.c b/mm/vmscan.c index 23f8a5242de7..1fe2c74a1c10 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -175,6 +175,39 @@ struct scan_control { */ int vm_swappiness = 60; +/* + * The total number of pages which are beyond the high watermark within all + * zones. + */ +unsigned long vm_pagecache_limit_pages __read_mostly = 0; +unsigned long vm_pagecache_limit_reclaim_pages = 0; +unsigned int vm_pagecache_limit_ratio __read_mostly = 0; +int vm_pagecache_limit_reclaim_ratio __read_mostly = 0; +unsigned int vm_pagecache_ignore_dirty __read_mostly = 1; + +unsigned long vm_total_pages; +static struct task_struct *kpclimitd = NULL; +unsigned int vm_pagecache_ignore_slab __read_mostly = 1; +unsigned int vm_pagecache_limit_async __read_mostly = 0; + +#ifdef CONFIG_SHRINK_PAGECACHE +unsigned long vm_cache_limit_ratio; +unsigned long vm_cache_limit_ratio_min; +unsigned long vm_cache_limit_ratio_max; +unsigned long vm_cache_limit_mbytes __read_mostly; +unsigned long vm_cache_limit_mbytes_min; +unsigned long vm_cache_limit_mbytes_max; +static bool kpclimitd_context = false; +int vm_cache_reclaim_s __read_mostly; +int vm_cache_reclaim_s_min; +int vm_cache_reclaim_s_max; +int vm_cache_reclaim_weight __read_mostly; +int vm_cache_reclaim_weight_min; +int vm_cache_reclaim_weight_max; +int vm_cache_reclaim_enable; +static DEFINE_PER_CPU(struct delayed_work, vmscan_work); +#endif + static void set_task_reclaim_state(struct task_struct *task, struct reclaim_state *rs) { @@ -187,10 +220,12 @@ static void set_task_reclaim_state(struct task_struct *task, task->reclaim_state = rs; } +static bool kpclimitd_context = false; static LIST_HEAD(shrinker_list); static DECLARE_RWSEM(shrinker_rwsem); #ifdef CONFIG_MEMCG +static DEFINE_IDR(shrinker_idr); static int shrinker_nr_max; /* The shrinker_info is expanded in a batch of BITS_PER_LONG */ @@ -346,7 +381,6 @@ void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) } } -static DEFINE_IDR(shrinker_idr); static int prealloc_memcg_shrinker(struct shrinker *shrinker) { @@ -646,7 +680,9 @@ EXPORT_SYMBOL(unregister_shrinker); #define SHRINK_BATCH 128 static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, - struct shrinker *shrinker, int priority) + struct shrinker *shrinker, + unsigned long nr_scanned, + unsigned long nr_eligible) { unsigned long freed = 0; unsigned long long delta; @@ -670,8 +706,10 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, nr = xchg_nr_deferred(shrinker, shrinkctl); if (shrinker->seeks) { - delta = freeable >> priority; - delta *= 4; + //delta = freeable >> priority; + //delta *= 4; + delta = (4 * nr_scanned) / shrinker->seeks; + delta *= freeable; do_div(delta, shrinker->seeks); } else { /* @@ -682,12 +720,12 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, delta = freeable / 2; } - total_scan = nr >> priority; + total_scan = nr; total_scan += delta; total_scan = min(total_scan, (2 * freeable)); trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, - freeable, delta, total_scan, priority); + freeable, delta, total_scan, nr_scanned,nr_eligible); /* * Normally, we should not scan less than batch_size objects in one @@ -744,7 +782,7 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, #ifdef CONFIG_MEMCG static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, - struct mem_cgroup *memcg, int priority) + struct mem_cgroup *memcg, unsigned long nr_scanned, unsigned long nr_eligible) { struct shrinker_info *info; unsigned long ret, freed = 0; @@ -780,7 +818,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, !(shrinker->flags & SHRINKER_NONSLAB)) continue; - ret = do_shrink_slab(&sc, shrinker, priority); + ret = do_shrink_slab(&sc, shrinker, nr_scanned, nr_eligible); if (ret == SHRINK_EMPTY) { clear_bit(i, info->map); /* @@ -799,7 +837,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, * set_bit() do_shrink_slab() */ smp_mb__after_atomic(); - ret = do_shrink_slab(&sc, shrinker, priority); + ret = do_shrink_slab(&sc, shrinker, nr_scanned, nr_eligible); if (ret == SHRINK_EMPTY) ret = 0; else @@ -846,7 +884,8 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, */ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, - int priority) + unsigned long nr_scanned, + unsigned long nr_eligible) { unsigned long ret, freed = 0; struct shrinker *shrinker; @@ -859,7 +898,8 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, * oom. */ if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) - return shrink_slab_memcg(gfp_mask, nid, memcg, priority); + return 0; + // return shrink_slab_memcg(gfp_mask, nid, memcg, priority); if (!down_read_trylock(&shrinker_rwsem)) goto out; @@ -871,7 +911,14 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, .memcg = memcg, }; - ret = do_shrink_slab(&sc, shrinker, priority); + if (memcg_kmem_enabled() && + !!memcg != !!(shrinker->flags & SHRINKER_MEMCG_AWARE)) + continue; + + if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) + sc.nid = 0; + + ret = do_shrink_slab(&sc, shrinker, nr_scanned, nr_eligible); if (ret == SHRINK_EMPTY) ret = 0; freed += ret; @@ -905,7 +952,7 @@ void drop_slab_node(int nid) freed = 0; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { - freed += shrink_slab(GFP_KERNEL, nid, memcg, 0); + freed += shrink_slab(GFP_KERNEL, nid, memcg, 1000,1000); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); } while (freed > 10); } @@ -2369,7 +2416,7 @@ unsigned long reclaim_pages(struct list_head *page_list) EXPORT_SYMBOL_GPL(reclaim_pages); static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, - struct lruvec *lruvec, struct scan_control *sc) + struct lruvec *lruvec, struct mem_cgroup *memcg, struct scan_control *sc) { if (is_active_lru(lru)) { if (sc->may_deactivate & (1 << is_file_lru(lru))) @@ -2683,7 +2730,7 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) nr[lru] -= nr_to_scan; nr_reclaimed += shrink_list(lru, nr_to_scan, - lruvec, sc); + lruvec, NULL, sc); } } @@ -2836,7 +2883,7 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); unsigned long reclaimed; unsigned long scanned; - + unsigned long lru_pages; /* * This loop can become CPU-bound when target memcgs * aren't eligible for reclaim - either because they @@ -2873,7 +2920,8 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) shrink_lruvec(lruvec, sc); shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, - sc->priority); + sc->nr_scanned - scanned, + lru_pages); /* Record the group's reclaim efficiency */ vmpressure(sc->gfp_mask, memcg, false, @@ -3202,6 +3250,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat) { + struct mem_cgroup *memcg; struct lruvec *target_lruvec; unsigned long refaults; @@ -3273,8 +3322,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, if (cgroup_reclaim(sc)) { struct lruvec *lruvec; - lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, - zone->zone_pgdat); + lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, zone->zone_pgdat); clear_bit(LRUVEC_CONGESTED, &lruvec->flags); } } @@ -3745,6 +3793,8 @@ static bool kswapd_shrink_node(pg_data_t *pgdat, return sc->nr_scanned >= sc->nr_to_reclaim; } +static void __shrink_page_cache(gfp_t mask); + /* * For kswapd, balance_pgdat() will reclaim pages across a node from zones * that are eligible for use by the caller until at least one zone is @@ -4208,6 +4258,27 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, wake_up_interruptible(&pgdat->kswapd_wait); } +/* + * The reclaimable count would be mostly accurate. + * The less reclaimable pages may be + * - mlocked pages, which will be moved to unevictable list when encountered + * - mapped pages, which may require several travels to be reclaimed + * - dirty pages, which is not "instantly" reclaimable + */ + +static unsigned long global_reclaimable_pages(void) +{ + int nr; + + nr = global_node_page_state(NR_ACTIVE_FILE) + + global_node_page_state(NR_INACTIVE_FILE); + + if (get_nr_swap_pages() > 0) + nr += global_node_page_state(NR_ACTIVE_ANON) + + global_node_page_state(NR_INACTIVE_ANON); + return nr; +} + #ifdef CONFIG_HIBERNATION /* * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of @@ -4246,6 +4317,498 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) return nr_reclaimed; } #endif /* CONFIG_HIBERNATION */ +/* + * Returns non-zero if the lock has been acquired, false if somebody + * else is holding the lock. + */ +static int pagecache_reclaim_lock_zone(struct zone *zone) +{ + return atomic_add_unless(&zone->pagecache_reclaim, 1, 1); +} + +static void pagecache_reclaim_unlock_zone(struct zone *zone) +{ + BUG_ON(atomic_dec_return(&zone->pagecache_reclaim)); +} + +/* + * Potential page cache reclaimers who are not able to take + * reclaim lock on any zone are sleeping on this waitqueue. + * So this is basically a congestion wait queue for them. + */ +DECLARE_WAIT_QUEUE_HEAD(pagecache_reclaim_wq); +DECLARE_WAIT_QUEUE_HEAD(kpagecache_limitd_wq); + +/* + * Similar to shrink_zone but it has a different consumer - pagecache limit + * so we cannot reuse the original function - and we do not want to clobber + * that code path so we have to live with this code duplication. + * + * In short this simply scans through the given lru for all cgroups for the + * give zone. + * + * returns true if we managed to cumulatively reclaim (via nr_reclaimed) + * the given nr_to_reclaim pages, false otherwise. The caller knows that + * it doesn't have to touch other zones if the target was hit already. + * + * DO NOT USE OUTSIDE of shrink_all_zones unless you have a really really + * really good reason. + */ + +static bool shrink_zone_per_memcg(struct zone *zone, enum lru_list lru, + unsigned long nr_to_scan, unsigned long nr_to_reclaim, + unsigned long *nr_reclaimed, struct scan_control *sc) +{ + struct mem_cgroup *root = sc->target_mem_cgroup; + struct mem_cgroup *memcg; + struct mem_cgroup_reclaim_cookie reclaim = { + .pgdat = zone->zone_pgdat, + .priority = sc->priority, + }; + + memcg = mem_cgroup_iter(root, NULL, &reclaim); + do { + struct lruvec *lruvec; + + lruvec = mem_cgroup_lruvec(memcg, zone->zone_pgdat); + *nr_reclaimed += shrink_list(lru, nr_to_scan, lruvec, memcg, sc); + if (*nr_reclaimed >= nr_to_reclaim) { + mem_cgroup_iter_break(root, memcg); + return true; + } + memcg = mem_cgroup_iter(root, memcg, &reclaim); + } while (memcg); + + return false; +} +/* + * Tries to reclaim 'nr_pages' pages from LRU lists system-wide, for given + * pass. + * + * For pass > 3 we also try to shrink the LRU lists that contain a few pages + * + * Returns the number of scanned zones. + */ +static int shrink_all_zones(unsigned long nr_pages, int pass, + struct scan_control *sc) +{ + struct zone *zone; + unsigned long nr_reclaimed = 0; + unsigned int nr_locked_zones = 0; + DEFINE_WAIT(wait); + + prepare_to_wait(&pagecache_reclaim_wq, &wait, TASK_INTERRUPTIBLE); + + for_each_populated_zone(zone) { + enum lru_list lru; + + /* + * Back off if somebody is already reclaiming this zone + * for the pagecache reclaim. + */ + if (!pagecache_reclaim_lock_zone(zone)) + continue; + + + /* + * This reclaimer might scan a zone so it will never + * sleep on pagecache_reclaim_wq + */ + finish_wait(&pagecache_reclaim_wq, &wait); + nr_locked_zones++; + + for_each_evictable_lru(lru) { + enum zone_stat_item ls = NR_ZONE_LRU_BASE + lru; + unsigned long lru_pages = zone_page_state(zone, ls); + + /* For pass = 0, we don't shrink the active list */ + if (pass == 0 && (lru == LRU_ACTIVE_ANON || + lru == LRU_ACTIVE_FILE)) + continue; + + /* Original code relied on nr_saved_scan which is no + * longer present so we are just considering LRU pages. + * This means that the zone has to have quite large + * LRU list for default priority and minimum nr_pages + * size (8*SWAP_CLUSTER_MAX). In the end we will tend + * to reclaim more from large zones wrt. small. + * This should be OK because shrink_page_cache is called + * when we are getting to short memory condition so + * LRUs tend to be large. + */ + if (((lru_pages >> sc->priority) + 1) >= nr_pages || pass >= 3) { + unsigned long nr_to_scan; + + nr_to_scan = min(nr_pages, lru_pages); + + /* + * A bit of a hack but the code has always been + * updating sc->nr_reclaimed once per shrink_all_zones + * rather than accumulating it for all calls to shrink + * lru. This costs us an additional argument to + * shrink_zone_per_memcg but well... + * + * Let's stick with this for bug-to-bug compatibility + */ + while (nr_to_scan > 0) { + /* shrink_list takes lru_lock with IRQ off so we + * should be careful about really huge nr_to_scan + */ + unsigned long batch = min_t(unsigned long, nr_to_scan, SWAP_CLUSTER_MAX); + + if (shrink_zone_per_memcg(zone, lru, + batch, nr_pages, &nr_reclaimed, sc)) { + pagecache_reclaim_unlock_zone(zone); + goto out_wakeup; + } + nr_to_scan -= batch; + } + } + } + pagecache_reclaim_unlock_zone(zone); + } + /* + * We have to go to sleep because all the zones are already reclaimed. + * One of the reclaimer will wake us up or __shrink_page_cache will + * do it if there is nothing to be done. + */ + if (!nr_locked_zones) { + if (!kpclimitd_context) + schedule(); + finish_wait(&pagecache_reclaim_wq, &wait); + goto out; + } + +out_wakeup: + wake_up_interruptible(&pagecache_reclaim_wq); + sc->nr_reclaimed += nr_reclaimed; +out: + return nr_locked_zones; +} + +/* + * Function to shrink the page cache + * + * This function calculates the number of pages (nr_pages) the page + * cache is over its limit and shrinks the page cache accordingly. + * + * The maximum number of pages, the page cache shrinks in one call of + * this function is limited to SWAP_CLUSTER_MAX pages. Therefore it may + * require a number of calls to actually reach the vm_pagecache_limit_kb. + * + * This function is similar to shrink_all_memory, except that it may never + * swap out mapped pages and only does four passes. + */ +static void __shrink_page_cache(gfp_t mask) +{ + unsigned long ret = 0; + int pass = 0; + struct reclaim_state reclaim_state; + struct scan_control sc = { + .gfp_mask = mask, + .may_swap = 0, + .may_unmap = 0, + .may_writepage = 0, + .target_mem_cgroup = NULL, + .reclaim_idx = MAX_NR_ZONES, + }; + struct reclaim_state *old_rs = current->reclaim_state; + long nr_pages; + + /* We might sleep during direct reclaim so make atomic context + * is certainly a bug. + */ + BUG_ON(!(mask & __GFP_RECLAIM)); + +retry: + /* How many pages are we over the limit?*/ + nr_pages = pagecache_over_limit(); + + /* + * Return early if there's no work to do. + * Wake up reclaimers that couldn't scan any zone due to congestion. + * There is apparently nothing to do so they do not have to sleep. + * This makes sure that no sleeping reclaimer will stay behind. + * Allow breaching the limit if the task is on the way out. + */ + if (nr_pages <= 0 || fatal_signal_pending(current)) { + wake_up_interruptible(&pagecache_reclaim_wq); + goto out; + } + + /* But do a few at least */ + nr_pages = max_t(unsigned long, nr_pages, 8*SWAP_CLUSTER_MAX); + + current->reclaim_state = &reclaim_state; + + /* + * Shrink the LRU in 4 passes: + * 0 = Reclaim from inactive_list only (fast) + * 1 = Reclaim from active list but don't reclaim mapped and dirtied (not that fast) + * 2 = Reclaim from active list but don't reclaim mapped (2nd pass) + * it may reclaim dirtied if vm_pagecache_ignore_dirty = 0 + * 3 = same as pass 2, but it will reclaim some few pages , detail in shrink_all_zones + */ + for (; pass <= 3; pass++) { + for (sc.priority = DEF_PRIORITY; sc.priority >= 0; sc.priority--) { + unsigned long nr_to_scan = nr_pages - ret; + struct mem_cgroup *memcg = NULL; + int nid; + + sc.nr_scanned = 0; + + /* + * No zone reclaimed because of too many reclaimers. Retry whether + * there is still something to do + */ + if (!shrink_all_zones(nr_to_scan, pass, &sc)) + goto retry; + + ret += sc.nr_reclaimed; + if (ret >= nr_pages) + goto out; + + reclaim_state.reclaimed_slab = 0; + for_each_online_node(nid) { + do { + shrink_slab(mask, nid, memcg, sc.nr_scanned, + global_reclaimable_pages()); + } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); + } + ret += reclaim_state.reclaimed_slab; + + if (ret >= nr_pages) + goto out; + + } + if (pass == 1) { + if (vm_pagecache_ignore_dirty == 1 || + (mask & (__GFP_IO | __GFP_FS)) != (__GFP_IO | __GFP_FS) ) + break; + else + sc.may_writepage = 1; + } + } + +out: + current->reclaim_state = old_rs; +} + +#ifdef CONFIG_SHRINK_PAGECACHE +static unsigned long __shrink_page_cache(gfp_t mask) +{ + struct scan_control sc = { + .gfp_mask = current_gfp_context(mask), + .reclaim_idx = gfp_zone(mask), + .may_writepage = !laptop_mode, + .nr_to_reclaim = SWAP_CLUSTER_MAX * + (unsigned long)vm_cache_reclaim_weight, + .may_unmap = 1, + .may_swap = 1, + .order = 0, + .priority = DEF_PRIORITY, + .target_mem_cgroup = NULL, + .nodemask = NULL, + }; + + struct zonelist *zonelist = node_zonelist(numa_node_id(), mask); + + return do_try_to_free_pages(zonelist, &sc); +} + + +static void shrink_page_cache_work(struct work_struct *w); +static void shrink_shepherd(struct work_struct *w); +static DECLARE_DEFERRABLE_WORK(shepherd, shrink_shepherd); + +static void shrink_shepherd(struct work_struct *w) +{ + int cpu; + + get_online_cpus(); + + for_each_online_cpu(cpu) { + struct delayed_work *work = &per_cpu(vmscan_work, cpu); + + if (!delayed_work_pending(work) && vm_cache_reclaim_enable) + queue_delayed_work_on(cpu, system_wq, work, 0); + } + + put_online_cpus(); + + /* we want all kernel thread to stop */ + if (vm_cache_reclaim_enable) { + if (vm_cache_reclaim_s == 0) + schedule_delayed_work(&shepherd, + round_jiffies_relative(120 * HZ)); + else + schedule_delayed_work(&shepherd, + round_jiffies_relative((unsigned long) + vm_cache_reclaim_s * HZ)); + } +} +static void shrink_shepherd_timer(void) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct delayed_work *work = &per_cpu(vmscan_work, cpu); + + INIT_DEFERRABLE_WORK(work, shrink_page_cache_work); + } + + schedule_delayed_work(&shepherd, + round_jiffies_relative((unsigned long)vm_cache_reclaim_s * HZ)); +} + +unsigned long shrink_page_cache(gfp_t mask) +{ + unsigned long nr_pages; + + /* We reclaim the highmem zone too, it is useful for 32bit arch */ + nr_pages = __shrink_page_cache(mask | __GFP_HIGHMEM); + + return nr_pages; +} +static void shrink_page_cache_work(struct work_struct *w) +{ + struct delayed_work *work = to_delayed_work(w); + unsigned long nr_pages; + + /* + * if vm_cache_reclaim_enable or vm_cache_reclaim_s is zero, + * we do not shrink page cache again. + */ + if (vm_cache_reclaim_s == 0 || !vm_cache_reclaim_enable) + return; + + /* It should wait more time if we hardly reclaim the page cache */ + nr_pages = shrink_page_cache(GFP_KERNEL); + if ((nr_pages < SWAP_CLUSTER_MAX) && vm_cache_reclaim_enable) + queue_delayed_work_on(smp_processor_id(), system_wq, work, + round_jiffies_relative(120 * HZ)); +} + +static void shrink_page_cache_init(void) +{ + vm_cache_limit_ratio = 0; + vm_cache_limit_ratio_min = 0; + vm_cache_limit_ratio_max = 100; + vm_cache_limit_mbytes = 0; + vm_cache_limit_mbytes_min = 0; + vm_cache_limit_mbytes_max = totalram_pages >> (20 - PAGE_SHIFT); + vm_cache_reclaim_s = 0; + vm_cache_reclaim_s_min = 0; + vm_cache_reclaim_s_max = 43200; + vm_cache_reclaim_weight = 1; + vm_cache_reclaim_weight_min = 1; + vm_cache_reclaim_weight_max = 100; + vm_cache_reclaim_enable = 1; + + shrink_shepherd_timer(); +} + +static int kswapd_cpu_down_prep(unsigned int cpu) +{ + cancel_delayed_work_sync(&per_cpu(vmscan_work, cpu)); + + return 0; +} +int cache_reclaim_enable_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) +{ + int ret; + + ret = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (ret) + return ret; + + if (write) + schedule_delayed_work(&shepherd, round_jiffies_relative((unsigned long)vm_cache_reclaim_s * HZ)); + + return 0; +} + +int cache_reclaim_sysctl_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) +{ + int ret; + + ret = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (ret) + return ret; + + if (write) + mod_delayed_work(system_wq, &shepherd, + round_jiffies_relative( + (unsigned long)vm_cache_reclaim_s * HZ)); + + return ret; +} +#endif + +static int kpagecache_limitd(void *data) +{ + DEFINE_WAIT(wait); + kpclimitd_context = true; + + /* + * make sure all work threads woken up, when switch to async mode + */ + if (waitqueue_active(&pagecache_reclaim_wq)) + wake_up_interruptible(&pagecache_reclaim_wq); + + for ( ; ; ) { + __shrink_page_cache(GFP_KERNEL); + prepare_to_wait(&kpagecache_limitd_wq, &wait, TASK_INTERRUPTIBLE); + + if (!kthread_should_stop()) + schedule(); + else { + finish_wait(&kpagecache_limitd_wq, &wait); + break; + } + finish_wait(&kpagecache_limitd_wq, &wait); + } + kpclimitd_context = false; + return 0; +} + +static void wakeup_kpclimitd(gfp_t mask) +{ + if (!waitqueue_active(&kpagecache_limitd_wq)) + return; + wake_up_interruptible(&kpagecache_limitd_wq); +} + +void shrink_page_cache(gfp_t mask, struct page *page) +{ + if (0 == vm_pagecache_limit_async) + __shrink_page_cache(mask); + else + wakeup_kpclimitd(mask); +} + +/* It's optimal to keep kswapds on the same CPUs as their memory, but + not required for correctness. So if the last cpu in a node goes + away, we get changed to run anywhere: as the first one comes back, + restore their cpu bindings. */ +static int kswapd_cpu_online(unsigned int cpu) +{ + int nid; + + for_each_node_state(nid, N_MEMORY) { + pg_data_t *pgdat = NODE_DATA(nid); + const struct cpumask *mask; + + mask = cpumask_of_node(pgdat->node_id); + + if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids) + /* One of our CPUs online: restore mask */ + set_cpus_allowed_ptr(pgdat->kswapd, mask); + } + return 0; +} /* * This kswapd start function will be called by init and node-hot-add. @@ -4286,16 +4849,61 @@ void kswapd_stop(int nid) static int __init kswapd_init(void) { - int nid; + /*int nid; swap_setup(); for_each_node_state(nid, N_MEMORY) kswapd_run(nid); - return 0; + return 0;*/ + int nid, ret; + + swap_setup(); + for_each_node_state(nid, N_MEMORY) + kswapd_run(nid); +#ifdef CONFIG_SHRINK_PAGECACHE + ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "mm/vmscan:online", kswapd_cpu_online, + kswapd_cpu_down_prep); +#else + ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "mm/vmscan:online", kswapd_cpu_online, + NULL); +#endif + WARN_ON(ret < 0); +#ifdef CONFIG_SHRINK_PAGECACHE + shrink_page_cache_init(); +#endif + return 0; + } module_init(kswapd_init) +int kpagecache_limitd_run(void) +{ + int ret = 0; + + if (kpclimitd) + return 0; + + kpclimitd = kthread_run(kpagecache_limitd, NULL, "kpclimitd"); + if (IS_ERR(kpclimitd)) { + pr_err("Failed to start kpagecache_limitd thread\n"); + ret = PTR_ERR(kpclimitd); + kpclimitd = NULL; + } + return ret; + +} + +void kpagecache_limitd_stop(void) +{ + if (kpclimitd) { + kthread_stop(kpclimitd); + kpclimitd = NULL; + } +} + #ifdef CONFIG_NUMA /* * Node reclaim mode diff --git a/mm/workingset.c b/mm/workingset.c index bba4380405b4..9a5ad145b9bd 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -253,6 +253,7 @@ void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages) void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg) { struct pglist_data *pgdat = page_pgdat(page); + struct mem_cgroup *memcg = page_memcg(page); unsigned long eviction; struct lruvec *lruvec; int memcgid; -- 2.30.0

1 0

[PATCH kernel-4.19] drivers/txgbe: fix buffer not null terminated by strncpy in txgbe_ethtool.c
by shenzijun 26 Oct '21

26 Oct '21

From: 沈子俊 <shenzijun(a)kylinos.cn> kylin inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4AG3E?from=project-issue CVE: NA --------------------------------------------------- change copy size in the function strncpy(). Signed-off-by: 沈子俊 <shenzijun(a)kylinos.cn> --- drivers/net/ethernet/netswift/txgbe/txgbe_ethtool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/netswift/txgbe/txgbe_ethtool.c b/drivers/net/ethernet/netswift/txgbe/txgbe_ethtool.c index 5cb8ef61e04b..9af9f19fb491 100644 --- a/drivers/net/ethernet/netswift/txgbe/txgbe_ethtool.c +++ b/drivers/net/ethernet/netswift/txgbe/txgbe_ethtool.c @@ -1040,7 +1040,7 @@ static void txgbe_get_drvinfo(struct net_device *netdev, strncpy(drvinfo->version, txgbe_driver_version, sizeof(drvinfo->version) - 1); strncpy(drvinfo->fw_version, adapter->eeprom_id, - sizeof(drvinfo->fw_version)); + sizeof(drvinfo->fw_version) - 1); strncpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info) - 1); if (adapter->num_tx_queues <= TXGBE_NUM_RX_QUEUES) { -- 2.30.0

1 0

[PATCH openEuler-1.0-LTS] blk-mq: complete req in softirq context in case of single queue
by Yang Yingliang 26 Oct '21

26 Oct '21

From: Ming Lei <ming.lei(a)redhat.com> mainline inclusion from mainline-4.20-rc1 commit 36e765392e48e0322222347c4d21078c0b94758c category: bugfix bugzilla: 175585 CVE: NA ------------------------------------------------- Lot of controllers may have only one irq vector for completing IO request. And usually affinity of the only irq vector is all possible CPUs, however, on most of ARCH, there may be only one specific CPU for handling this interrupt. So if all IOs are completed in hardirq context, it is inevitable to degrade IO performance because of increased irq latency. This patch tries to address this issue by allowing to complete request in softirq context, like the legacy IO path. IOPS is observed as ~13%+ in the following randread test on raid0 over virtio-scsi. mdadm --create --verbose /dev/md0 --level=0 --chunk=1024 --raid-devices=8 /dev/sdb /dev/sdc /dev/sdd /dev/sde /dev/sdf /dev/sdg /dev/sdh /dev/sdi fio --time_based --name=benchmark --runtime=30 --filename=/dev/md0 --nrfiles=1 --ioengine=libaio --iodepth=32 --direct=1 --invalidate=1 --verify=0 --verify_fatal=0 --numjobs=32 --rw=randread --blocksize=4k Cc: Dongli Zhang <dongli.zhang(a)oracle.com> Cc: Zach Marano <zmarano(a)google.com> Cc: Christoph Hellwig <hch(a)lst.de> Cc: Bart Van Assche <bvanassche(a)acm.org> Cc: Jianchao Wang <jianchao.w.wang(a)oracle.com> Signed-off-by: Ming Lei <ming.lei(a)redhat.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Lihong Kou <koulihong(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-mq.c | 14 ++++++++++++++ block/blk-softirq.c | 5 ++--- 2 files changed, 16 insertions(+), 3 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index 7106c94ea58fe..55c81dcafbdc2 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -600,6 +600,20 @@ void blk_mq_force_complete_rq(struct request *rq) if (rq->internal_tag != -1) blk_mq_sched_completed_request(rq); + /* + * Most of single queue controllers, there is only one irq vector + * for handling IO completion, and the only irq's affinity is set + * as all possible CPUs. On most of ARCHs, this affinity means the + * irq is handled on one specific CPU. + * + * So complete IO reqeust in softirq context in case of single queue + * for not degrading IO performance by irqsoff latency. + */ + if (rq->q->nr_hw_queues == 1) { + __blk_complete_request(rq); + return; + } + if (!test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) { rq->q->softirq_done_fn(rq); return; diff --git a/block/blk-softirq.c b/block/blk-softirq.c index 15c1f5e12eb89..e47a2f751884d 100644 --- a/block/blk-softirq.c +++ b/block/blk-softirq.c @@ -97,8 +97,8 @@ static int blk_softirq_cpu_dead(unsigned int cpu) void __blk_complete_request(struct request *req) { - int ccpu, cpu; struct request_queue *q = req->q; + int cpu, ccpu = q->mq_ops ? req->mq_ctx->cpu : req->cpu; unsigned long flags; bool shared = false; @@ -110,8 +110,7 @@ void __blk_complete_request(struct request *req) /* * Select completion CPU */ - if (req->cpu != -1) { - ccpu = req->cpu; + if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) && ccpu != -1) { if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags)) shared = cpus_share_cache(cpu, ccpu); } else -- 2.25.1

1 0

[PATCH kernel-4.19] blk-mq: complete req in softirq context in case of single queue
by Yang Yingliang 26 Oct '21

26 Oct '21

From: Ming Lei <ming.lei(a)redhat.com> mainline inclusion from mainline-4.20-rc1 commit 36e765392e48e0322222347c4d21078c0b94758c category: bugfix bugzilla: 175585 CVE: NA ------------------------------------------------- Lot of controllers may have only one irq vector for completing IO request. And usually affinity of the only irq vector is all possible CPUs, however, on most of ARCH, there may be only one specific CPU for handling this interrupt. So if all IOs are completed in hardirq context, it is inevitable to degrade IO performance because of increased irq latency. This patch tries to address this issue by allowing to complete request in softirq context, like the legacy IO path. IOPS is observed as ~13%+ in the following randread test on raid0 over virtio-scsi. mdadm --create --verbose /dev/md0 --level=0 --chunk=1024 --raid-devices=8 /dev/sdb /dev/sdc /dev/sdd /dev/sde /dev/sdf /dev/sdg /dev/sdh /dev/sdi fio --time_based --name=benchmark --runtime=30 --filename=/dev/md0 --nrfiles=1 --ioengine=libaio --iodepth=32 --direct=1 --invalidate=1 --verify=0 --verify_fatal=0 --numjobs=32 --rw=randread --blocksize=4k Cc: Dongli Zhang <dongli.zhang(a)oracle.com> Cc: Zach Marano <zmarano(a)google.com> Cc: Christoph Hellwig <hch(a)lst.de> Cc: Bart Van Assche <bvanassche(a)acm.org> Cc: Jianchao Wang <jianchao.w.wang(a)oracle.com> Signed-off-by: Ming Lei <ming.lei(a)redhat.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Lihong Kou <koulihong(a)huawei.com> Reviewed-by: Tao Hou <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-mq.c | 14 ++++++++++++++ block/blk-softirq.c | 5 ++--- 2 files changed, 16 insertions(+), 3 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index be1e2ad4631aa..52a04f6ffeea2 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -603,6 +603,20 @@ void blk_mq_force_complete_rq(struct request *rq) if (rq->internal_tag != -1) blk_mq_sched_completed_request(rq); + /* + * Most of single queue controllers, there is only one irq vector + * for handling IO completion, and the only irq's affinity is set + * as all possible CPUs. On most of ARCHs, this affinity means the + * irq is handled on one specific CPU. + * + * So complete IO reqeust in softirq context in case of single queue + * for not degrading IO performance by irqsoff latency. + */ + if (rq->q->nr_hw_queues == 1) { + __blk_complete_request(rq); + return; + } + if (!test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) { rq->q->softirq_done_fn(rq); return; diff --git a/block/blk-softirq.c b/block/blk-softirq.c index 15c1f5e12eb89..e47a2f751884d 100644 --- a/block/blk-softirq.c +++ b/block/blk-softirq.c @@ -97,8 +97,8 @@ static int blk_softirq_cpu_dead(unsigned int cpu) void __blk_complete_request(struct request *req) { - int ccpu, cpu; struct request_queue *q = req->q; + int cpu, ccpu = q->mq_ops ? req->mq_ctx->cpu : req->cpu; unsigned long flags; bool shared = false; @@ -110,8 +110,7 @@ void __blk_complete_request(struct request *req) /* * Select completion CPU */ - if (req->cpu != -1) { - ccpu = req->cpu; + if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) && ccpu != -1) { if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags)) shared = cpus_share_cache(cpu, ccpu); } else -- 2.25.1

1 0

[PATCH kernel-4.19 1/8] ovl: simplify setting of origin for index lookup
by Yang Yingliang 26 Oct '21

26 Oct '21

From: Vivek Goyal <vgoyal(a)redhat.com> mainline inclusion from mainline-v5.8-rc1 commit 59fb20138a9b5249a4176d5bbc5c670a97343061 category: bugfix bugzilla: NA CVE: NA ------------------------------------------------- overlayfs can keep index of copied up files and directories and it seems to serve two primary puroposes. For regular files, it avoids breaking lower hardlinks over copy up. For directories it seems to be used for various error checks. During ovl_lookup(), we lookup for index using lower dentry in many a cases. That lower dentry is called "origin" and following is a summary of current logic. If there is no upperdentry, always lookup for index using lower dentry. For regular files it helps avoiding breaking hard links over copyup and for directories it seems to be just error checks. If there is an upperdentry, then there are 3 possible cases. - For directories, lower dentry is found using two ways. One is regular path based lookup in lower layers and second is using ORIGIN xattr on upper dentry. First verify that path based lookup lower dentry matches the one pointed by upper ORIGIN xattr. If yes, use this verified origin for index lookup. - For regular files (non-metacopy), there is no path based lookup in lower layers as lookup stops once we find upper dentry. So there is no origin verification. If there is ORIGIN xattr present on upper, use that to lookup index otherwise don't. - For regular metacopy files, again lower dentry is found using path based lookup as well as ORIGIN xattr on upper. Path based lookup is continued in this case to find lower data dentry for metacopy upper. So like directories we only use verified origin. If ORIGIN xattr is not present (Either because lower did not support file handles or because this is hardlink copied up with index=off), then don't use path lookup based lower dentry as origin. This is same as regular non-metacopy file case. Suggested-by: Amir Goldstein <amir73il(a)gmail.com> Signed-off-by: Vivek Goyal <vgoyal(a)redhat.com> Reviewed-by: Amir Goldstein <amir73il(a)gmail.com> Signed-off-by: Miklos Szeredi <mszeredi(a)redhat.com> Signed-off-by: Zheng Liang <zhengliang6(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/overlayfs/namei.c | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index 145bfdde53feb..968ad757c578e 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -1014,25 +1014,30 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, } stack = origin_path; ctr = 1; + origin = origin_path->dentry; origin_path = NULL; } /* - * Lookup index by lower inode and verify it matches upper inode. - * We only trust dir index if we verified that lower dir matches - * origin, otherwise dir index entries may be inconsistent and we - * ignore them. + * Always lookup index if there is no-upperdentry. * - * For non-dir upper metacopy dentry, we already set "origin" if we - * verified that lower matched upper origin. If upper origin was - * not present (because lower layer did not support fh encode/decode), - * or indexing is not enabled, do not set "origin" and skip looking up - * index. This case should be handled in same way as a non-dir upper - * without ORIGIN is handled. + * For the case of upperdentry, we have set origin by now if it + * needed to be set. There are basically three cases. + * + * For directories, lookup index by lower inode and verify it matches + * upper inode. We only trust dir index if we verified that lower dir + * matches origin, otherwise dir index entries may be inconsistent + * and we ignore them. + * + * For regular upper, we already set origin if upper had ORIGIN + * xattr. There is no verification though as there is no path + * based dentry lookup in lower in this case. + * + * For metacopy upper, we set a verified origin already if index + * is enabled and if upper had an ORIGIN xattr. * - * Always lookup index of non-dir non-metacopy and non-upper. */ - if (ctr && (!upperdentry || (!d.is_dir && !metacopy))) + if (!upperdentry && ctr) origin = stack[0].dentry; if (origin && ovl_indexdir(dentry->d_sb) && -- 2.25.1

1 7

Re: [PATCH openEuler-21.03] USB: f_ncm: ncm_bitrate (speed) is unsigned
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:03, xjx00 写道: > From: Maciej Żenczykowski <maze(a)google.com> > > stable inclusion > from stable-v5.10.44 > commit 0f5a20b1fd9da3ac9f7c6edcad522712ca694d5c > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=358 > CVE: NA > > ------------------------------------------------- > > commit 3370139745853f7826895293e8ac3aec1430508e upstream. > > [ 190.544755] configfs-gadget gadget: notify speed -44967296 > > This is because 4250000000 - 2**32 is -44967296. > > Fixes: 9f6ce4240a2b ("usb: gadget: f_ncm.c added") > Cc: Brooke Basile <brookebasile(a)gmail.com> > Cc: Bryan O'Donoghue <bryan.odonoghue(a)linaro.org> > Cc: Felipe Balbi <balbi(a)kernel.org> > Cc: Lorenzo Colitti <lorenzo(a)google.com> > Cc: Yauheni Kaliuta <yauheni.kaliuta(a)nokia.com> > Cc: Linux USB Mailing List <linux-usb(a)vger.kernel.org> > Acked-By: Lorenzo Colitti <lorenzo(a)google.com> > Signed-off-by: Maciej Żenczykowski <maze(a)google.com> > Cc: stable <stable(a)vger.kernel.org> > Link: https://lore.kernel.org/r/20210608005344.3762668-1-zenczykowski@gmail.com > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: xjx00 <xjxyklwx(a)126.com> > --- > drivers/usb/gadget/function/f_ncm.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c > index 019bea8e09cc..0d23c6c11a13 100644 > --- a/drivers/usb/gadget/function/f_ncm.c > +++ b/drivers/usb/gadget/function/f_ncm.c > @@ -583,7 +583,7 @@ static void ncm_do_notify(struct f_ncm *ncm) > data[0] = cpu_to_le32(ncm_bitrate(cdev->gadget)); > data[1] = data[0]; > > - DBG(cdev, "notify speed %d\n", ncm_bitrate(cdev->gadget)); > + DBG(cdev, "notify speed %u\n", ncm_bitrate(cdev->gadget)); > ncm->notify_state = NCM_NOTIFY_CONNECT; > break; > }

2 1

Re: [PATCH openEuler-21.03] ALSA: firewire-lib: fix the context to call snd_pcm_stop_xrun()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 21:17, lihao 写道: > From: Takashi Sakamoto <o-takashi(a)sakamocchi.jp> > > stable inclusion > from stable-v5.10.44 > commit 98f842951f8aa222e8a8453e6dbce6c056e9984f > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=430 > CVE: NA > > ------------------------------------------------- > > commit 9981b20a5e3694f4625ab5a1ddc98ce7503f6d12 upstream. > > In the workqueue to queue wake-up event, isochronous context is not > processed, thus it's useless to check context for the workqueue to switch > status of runtime for PCM substream to XRUN. On the other hand, in > software IRQ context of 1394 OHCI, it's needed. > > This commit fixes the bug introduced when tasklet was replaced with > workqueue. > > Cc: <stable(a)vger.kernel.org> > Fixes: 2b3d2987d800 ("ALSA: firewire: Replace tasklet with work") > Signed-off-by: Takashi Sakamoto <o-takashi(a)sakamocchi.jp> > Link: https://lore.kernel.org/r/20210605091054.68866-1-o-takashi@sakamocchi.jp > Signed-off-by: Takashi Iwai <tiwai(a)suse.de> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: lihao <380525608(a)qq.com> > --- > sound/firewire/amdtp-stream.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c > index e0faa6601966..5805c5de39fb 100644 > --- a/sound/firewire/amdtp-stream.c > +++ b/sound/firewire/amdtp-stream.c > @@ -804,7 +804,7 @@ static void generate_pkt_descs(struct amdtp_stream *s, struct pkt_desc *descs, > static inline void cancel_stream(struct amdtp_stream *s) > { > s->packet_index = -1; > - if (current_work() == &s->period_work) > + if (in_interrupt()) > amdtp_stream_pcm_abort(s); > WRITE_ONCE(s->pcm_buffer_pointer, SNDRV_PCM_POS_XRUN); > }

1 0

Re: [PATCH openEuler-21.03] drm/msm/a6xx: avoid shadow NULL reference in failure path
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:02, lzb 写道: > From: Jonathan Marek <jonathan(a)marek.ca> > > stable inclusion > from stable-v5.10.44 > commit fd681a8c7ac8f649a0718f6cbf2fe75d0587c9a2 > bugzilla: > CVE: NA > > https://bugzilla.openeuler.org/show_bug.cgi?id=472-------------------------… > > commit ce86c239e4d218ae6040bec18e6d19a58edb8b7c upstream. > > If a6xx_hw_init() fails before creating the shadow_bo, the a6xx_pm_suspend > code referencing it will crash. Change the condition to one that avoids > this problem (note: creation of shadow_bo is behind this same condition) > > Fixes: e8b0b994c3a5 ("drm/msm/a6xx: Clear shadow on suspend") > Signed-off-by: Jonathan Marek <jonathan(a)marek.ca> > Reviewed-by: Akhil P Oommen <akhilpo(a)codeaurora.org> > Link: https://lore.kernel.org/r/20210513171431.18632-6-jonathan@marek.ca > Signed-off-by: Rob Clark <robdclark(a)chromium.org> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: lzb <zbliancs(a)qq.com> > --- > drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c > index 722c2fe3bfd5..7061ba457c5b 100644 > --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c > +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c > @@ -1055,7 +1055,7 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu) > if (ret) > return ret; > > - if (adreno_gpu->base.hw_apriv || a6xx_gpu->has_whereami) > + if (a6xx_gpu->shadow_bo) > for (i = 0; i < gpu->nr_rings; i++) > a6xx_gpu->shadow[i] = 0; >

1 0

Re: [PATCH openEuler-21.03] sched/fair: Make sure to update tg contrib for blocked load
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:09, wjy 写道: > From: Vincent Guittot <vincent.guittot(a)linaro.org> > > stable inclusion > from stable-v5.10.44 > commit 32e22db8b25ea165bd9e446c7f92b089c8568eaf > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=379 > CVE: NA > > ------------------------------------------------- > > commit 02da26ad5ed6ea8680e5d01f20661439611ed776 upstream. > > During the update of fair blocked load (__update_blocked_fair()), we > update the contribution of the cfs in tg->load_avg if cfs_rq's pelt > has decayed. Nevertheless, the pelt values of a cfs_rq could have > been recently updated while propagating the change of a child. In this > case, cfs_rq's pelt will not decayed because it has already been > updated and we don't update tg->load_avg. > > __update_blocked_fair > ... > for_each_leaf_cfs_rq_safe: child cfs_rq > update cfs_rq_load_avg() for child cfs_rq > ... > update_load_avg(cfs_rq_of(se), se, 0) > ... > update cfs_rq_load_avg() for parent cfs_rq > -propagation of child's load makes parent cfs_rq->load_sum > becoming null > -UPDATE_TG is not set so it doesn't update parent > cfs_rq->tg_load_avg_contrib > .. > for_each_leaf_cfs_rq_safe: parent cfs_rq > update cfs_rq_load_avg() for parent cfs_rq > - nothing to do because parent cfs_rq has already been updated > recently so cfs_rq->tg_load_avg_contrib is not updated > ... > parent cfs_rq is decayed > list_del_leaf_cfs_rq parent cfs_rq > - but it still contibutes to tg->load_avg > > we must set UPDATE_TG flags when propagting pending load to the parent > > Fixes: 039ae8bcf7a5 ("sched/fair: Fix O(nr_cgroups) in the load balancing path") > Reported-by: Odin Ugedal <odin(a)uged.al> > Signed-off-by: Vincent Guittot <vincent.guittot(a)linaro.org> > Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> > Reviewed-by: Odin Ugedal <odin(a)uged.al> > Link: https://lkml.kernel.org/r/20210527122916.27683-3-vincent.guittot@linaro.org > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: wjy <464310675(a)qq.com> > --- > kernel/sched/fair.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c > index 1ad0e52487f6..43497d88a330 100644 > --- a/kernel/sched/fair.c > +++ b/kernel/sched/fair.c > @@ -7961,7 +7961,7 @@ static bool __update_blocked_fair(struct rq *rq, bool *done) > /* Propagate pending load changes to the parent, if any: */ > se = cfs_rq->tg->se[cpu]; > if (se && !skip_blocked_update(se)) > - update_load_avg(cfs_rq_of(se), se, 0); > + update_load_avg(cfs_rq_of(se), se, UPDATE_TG); > > /* > * There can be a lot of idle CPU cgroups. Don't let fully

1 0

Re: [PATCH openEuler-21.03] NFSv4: Fix second deadlock in nfs4_evict_inode()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:13, wyp 写道: > From: Trond Myklebust <trond.myklebust(a)hammerspace.com> > > stable inclusion > from stable-v5.10.44 > commit d973bd0d6e7f9b4ea976cc619e8d6e0d235b9056 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=462 > CVE: NA > > ------------------------------------------------- > > commit c3aba897c6e67fa464ec02b1f17911577d619713 upstream. > > If the inode is being evicted but has to return a layout first, then > that too can cause a deadlock in the corner case where the server > reboots. > > Signed-off-by: Trond Myklebust <trond.myklebust(a)hammerspace.com> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: Hang <haihangyiyuan(a)163.com> > Reviewed-by: Jian Cheng <cj.chengjian(a)huawei.com> > Signed-off-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> > --- > fs/nfs/nfs4proc.c | 9 +++++++-- > 1 file changed, 7 insertions(+), 2 deletions(-) > > diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c > index c92d6ff0fcea..eedcbe6832fb 100644 > --- a/fs/nfs/nfs4proc.c > +++ b/fs/nfs/nfs4proc.c > @@ -9619,15 +9619,20 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync) > &task_setup_data.rpc_client, &msg); > > dprintk("--> %s\n", __func__); > + lrp->inode = nfs_igrab_and_active(lrp->args.inode); > if (!sync) { > - lrp->inode = nfs_igrab_and_active(lrp->args.inode); > if (!lrp->inode) { > nfs4_layoutreturn_release(lrp); > return -EAGAIN; > } > task_setup_data.flags |= RPC_TASK_ASYNC; > } > - nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, 0); > + if (!lrp->inode) > + nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, > + 1); > + else > + nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, > + 0); > task = rpc_run_task(&task_setup_data); > if (IS_ERR(task)) > return PTR_ERR(task);

1 0

Re: [PATCH openEuler-21.03] net: mdiobus: get rid of a BUG_ON()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:15, gpj 写道: > From: Dan Carpenter <dan.carpenter(a)oracle.com> > > stable inclusion > from stable-v5.10.44 > commit be23c4af3d8a1b986fe9b43b8966797653a76ca4 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=341 > CVE: NA > > -------------------------------- > > [ Upstream commit 1dde47a66d4fb181830d6fa000e5ea86907b639e ] > > We spotted a bug recently during a review where a driver was > unregistering a bus that wasn't registered, which would trigger this > BUG_ON(). Let's handle that situation more gracefully, and just print > a warning and return. > > Reported-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> > Reviewed-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Reviewed-by: Andrew Lunn <andrew(a)lunn.ch> > Signed-off-by: David S. Miller <davem(a)davemloft.net> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: wangqing <wangqing(a)uniontech.com> > Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> > Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> > --- > drivers/net/phy/mdio_bus.c | 3 ++- > 1 file changed, 2 insertions(+), 1 deletion(-) > > diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c > index 757e950fb745..b848439fa837 100644 > --- a/drivers/net/phy/mdio_bus.c > +++ b/drivers/net/phy/mdio_bus.c > @@ -608,7 +608,8 @@ void mdiobus_unregister(struct mii_bus *bus) > struct mdio_device *mdiodev; > int i; > > - BUG_ON(bus->state != MDIOBUS_REGISTERED); > + if (WARN_ON_ONCE(bus->state != MDIOBUS_REGISTERED)) > + return; > bus->state = MDIOBUS_UNREGISTERED; > > for (i = 0; i < PHY_MAX_ADDR; i++) {

1 0

Re: [PATCH openEuler-21.03] net: mdiobus: get rid of a BUG_ON()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:18, dqh 写道: > From: Dan Carpenter <dan.carpenter(a)oracle.com> > > stable inclusion > from stable-v5.10.44 > commit be23c4af3d8a1b986fe9b43b8966797653a76ca4 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=341 > CVE: NA > > -------------------------------- > > [ Upstream commit 1dde47a66d4fb181830d6fa000e5ea86907b639e ] > > We spotted a bug recently during a review where a driver was > unregistering a bus that wasn't registered, which would trigger this > BUG_ON(). Let's handle that situation more gracefully, and just print > a warning and return. > > Reported-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> > Reviewed-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Reviewed-by: Andrew Lunn <andrew(a)lunn.ch> > Signed-off-by: David S. Miller <davem(a)davemloft.net> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: wangqing <wangqing(a)uniontech.com> > Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> > Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> > --- > drivers/net/phy/mdio_bus.c | 3 ++- > 1 file changed, 2 insertions(+), 1 deletion(-) > > diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c > index 757e950fb745..b848439fa837 100644 > --- a/drivers/net/phy/mdio_bus.c > +++ b/drivers/net/phy/mdio_bus.c > @@ -608,7 +608,8 @@ void mdiobus_unregister(struct mii_bus *bus) > struct mdio_device *mdiodev; > int i; > > - BUG_ON(bus->state != MDIOBUS_REGISTERED); > + if (WARN_ON_ONCE(bus->state != MDIOBUS_REGISTERED)) > + return; > bus->state = MDIOBUS_UNREGISTERED; > > for (i = 0; i < PHY_MAX_ADDR; i++) {

1 0

Re: [PATCH openEuler-21.03] spi: Cleanup on failure of initial setup
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:18, dqh 写道: > From: Lukas Wunner <lukas(a)wunner.de> > > stable inclusion > from stable-v5.10.44 > commit fa05ba61967ad051f5f2b7c4f39d6c56719c9900 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=470 > CVE: NA > > ------------------------------------------------- > > [ Upstream commit 2ec6f20b33eb4f62ab90bdcd620436c883ec3af6 ] > > Commit c7299fea6769 ("spi: Fix spi device unregister flow") changed the > SPI core's behavior if the ->setup() hook returns an error upon adding > an spi_device: Before, the ->cleanup() hook was invoked to free any > allocations that were made by ->setup(). With the commit, that's no > longer the case, so the ->setup() hook is expected to free the > allocations itself. > > I've identified 5 drivers which depend on the old behavior and am fixing > them up hereinafter: spi-bitbang.c spi-fsl-spi.c spi-omap-uwire.c > spi-omap2-mcspi.c spi-pxa2xx.c > > Importantly, ->setup() is not only invoked on spi_device *addition*: > It may subsequently be called to *change* SPI parameters. If changing > these SPI parameters fails, freeing memory allocations would be wrong. > That should only be done if the spi_device is finally destroyed. > I am therefore using a bool "initial_setup" in 4 of the affected drivers > to differentiate between the invocation on *adding* the spi_device and > any subsequent invocations: spi-bitbang.c spi-fsl-spi.c spi-omap-uwire.c > spi-omap2-mcspi.c > > In spi-pxa2xx.c, it seems the ->setup() hook can only fail on spi_device > addition, not any subsequent calls. It therefore doesn't need the bool. > > It's worth noting that 5 other drivers already perform a cleanup if the > ->setup() hook fails. Before c7299fea6769, they caused a double-free > if ->setup() failed on spi_device addition. Since the commit, they're > fine. These drivers are: spi-mpc512x-psc.c spi-pl022.c spi-s3c64xx.c > spi-st-ssc4.c spi-tegra114.c > > (spi-pxa2xx.c also already performs a cleanup, but only in one of > several error paths.) > > Fixes: c7299fea6769 ("spi: Fix spi device unregister flow") > Signed-off-by: Lukas Wunner <lukas(a)wunner.de> > Cc: Saravana Kannan <saravanak(a)google.com> > Acked-by: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com> # pxa2xx > Link: https://lore.kernel.org/r/f76a0599469f265b69c371538794101fa37b5536.16221493… > Signed-off-by: Mark Brown <broonie(a)kernel.org> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: dqh <1486653795(a)qq.com> > --- > drivers/spi/spi-bitbang.c | 18 ++++++++++++++---- > drivers/spi/spi-fsl-spi.c | 4 ++++ > drivers/spi/spi-omap-uwire.c | 9 ++++++++- > drivers/spi/spi-omap2-mcspi.c | 33 ++++++++++++++++++++------------- > drivers/spi/spi-pxa2xx.c | 9 ++++++++- > 5 files changed, 54 insertions(+), 19 deletions(-) > > diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c > index 1a7352abd878..3d8948a17095 100644 > --- a/drivers/spi/spi-bitbang.c > +++ b/drivers/spi/spi-bitbang.c > @@ -181,6 +181,8 @@ int spi_bitbang_setup(struct spi_device *spi) > { > struct spi_bitbang_cs *cs = spi->controller_state; > struct spi_bitbang *bitbang; > + bool initial_setup = false; > + int retval; > > bitbang = spi_master_get_devdata(spi->master); > > @@ -189,22 +191,30 @@ int spi_bitbang_setup(struct spi_device *spi) > if (!cs) > return -ENOMEM; > spi->controller_state = cs; > + initial_setup = true; > } > > /* per-word shift register access, in hardware or bitbanging */ > cs->txrx_word = bitbang->txrx_word[spi->mode & (SPI_CPOL|SPI_CPHA)]; > - if (!cs->txrx_word) > - return -EINVAL; > + if (!cs->txrx_word) { > + retval = -EINVAL; > + goto err_free; > + } > > if (bitbang->setup_transfer) { > - int retval = bitbang->setup_transfer(spi, NULL); > + retval = bitbang->setup_transfer(spi, NULL); > if (retval < 0) > - return retval; > + goto err_free; > } > > dev_dbg(&spi->dev, "%s, %u nsec/bit\n", __func__, 2 * cs->nsecs); > > return 0; > + > +err_free: > + if (initial_setup) > + kfree(cs); > + return retval; > } > EXPORT_SYMBOL_GPL(spi_bitbang_setup); > > diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c > index d0e5aa18b7ba..bdf94cc7be1a 100644 > --- a/drivers/spi/spi-fsl-spi.c > +++ b/drivers/spi/spi-fsl-spi.c > @@ -440,6 +440,7 @@ static int fsl_spi_setup(struct spi_device *spi) > { > struct mpc8xxx_spi *mpc8xxx_spi; > struct fsl_spi_reg __iomem *reg_base; > + bool initial_setup = false; > int retval; > u32 hw_mode; > struct spi_mpc8xxx_cs *cs = spi_get_ctldata(spi); > @@ -452,6 +453,7 @@ static int fsl_spi_setup(struct spi_device *spi) > if (!cs) > return -ENOMEM; > spi_set_ctldata(spi, cs); > + initial_setup = true; > } > mpc8xxx_spi = spi_master_get_devdata(spi->master); > > @@ -475,6 +477,8 @@ static int fsl_spi_setup(struct spi_device *spi) > retval = fsl_spi_setup_transfer(spi, NULL); > if (retval < 0) { > cs->hw_mode = hw_mode; /* Restore settings */ > + if (initial_setup) > + kfree(cs); > return retval; > } > > diff --git a/drivers/spi/spi-omap-uwire.c b/drivers/spi/spi-omap-uwire.c > index 71402f71ddd8..df28c6664aba 100644 > --- a/drivers/spi/spi-omap-uwire.c > +++ b/drivers/spi/spi-omap-uwire.c > @@ -424,15 +424,22 @@ static int uwire_setup_transfer(struct spi_device *spi, struct spi_transfer *t) > static int uwire_setup(struct spi_device *spi) > { > struct uwire_state *ust = spi->controller_state; > + bool initial_setup = false; > + int status; > > if (ust == NULL) { > ust = kzalloc(sizeof(*ust), GFP_KERNEL); > if (ust == NULL) > return -ENOMEM; > spi->controller_state = ust; > + initial_setup = true; > } > > - return uwire_setup_transfer(spi, NULL); > + status = uwire_setup_transfer(spi, NULL); > + if (status && initial_setup) > + kfree(ust); > + > + return status; > } > > static void uwire_cleanup(struct spi_device *spi) > diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c > index d4c9510af393..3596bbe4b776 100644 > --- a/drivers/spi/spi-omap2-mcspi.c > +++ b/drivers/spi/spi-omap2-mcspi.c > @@ -1032,8 +1032,22 @@ static void omap2_mcspi_release_dma(struct spi_master *master) > } > } > > +static void omap2_mcspi_cleanup(struct spi_device *spi) > +{ > + struct omap2_mcspi_cs *cs; > + > + if (spi->controller_state) { > + /* Unlink controller state from context save list */ > + cs = spi->controller_state; > + list_del(&cs->node); > + > + kfree(cs); > + } > +} > + > static int omap2_mcspi_setup(struct spi_device *spi) > { > + bool initial_setup = false; > int ret; > struct omap2_mcspi *mcspi = spi_master_get_devdata(spi->master); > struct omap2_mcspi_regs *ctx = &mcspi->ctx; > @@ -1051,35 +1065,28 @@ static int omap2_mcspi_setup(struct spi_device *spi) > spi->controller_state = cs; > /* Link this to context save list */ > list_add_tail(&cs->node, &ctx->cs); > + initial_setup = true; > } > > ret = pm_runtime_get_sync(mcspi->dev); > if (ret < 0) { > pm_runtime_put_noidle(mcspi->dev); > + if (initial_setup) > + omap2_mcspi_cleanup(spi); > > return ret; > } > > ret = omap2_mcspi_setup_transfer(spi, NULL); > + if (ret && initial_setup) > + omap2_mcspi_cleanup(spi); > + > pm_runtime_mark_last_busy(mcspi->dev); > pm_runtime_put_autosuspend(mcspi->dev); > > return ret; > } > > -static void omap2_mcspi_cleanup(struct spi_device *spi) > -{ > - struct omap2_mcspi_cs *cs; > - > - if (spi->controller_state) { > - /* Unlink controller state from context save list */ > - cs = spi->controller_state; > - list_del(&cs->node); > - > - kfree(cs); > - } > -} > - > static irqreturn_t omap2_mcspi_irq_handler(int irq, void *data) > { > struct omap2_mcspi *mcspi = data; > diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c > index d6b534d38e5d..56a62095ec8c 100644 > --- a/drivers/spi/spi-pxa2xx.c > +++ b/drivers/spi/spi-pxa2xx.c > @@ -1254,6 +1254,8 @@ static int setup_cs(struct spi_device *spi, struct chip_data *chip, > chip->gpio_cs_inverted = spi->mode & SPI_CS_HIGH; > > err = gpiod_direction_output(gpiod, !chip->gpio_cs_inverted); > + if (err) > + gpiod_put(chip->gpiod_cs); > } > > return err; > @@ -1267,6 +1269,7 @@ static int setup(struct spi_device *spi) > struct driver_data *drv_data = > spi_controller_get_devdata(spi->controller); > uint tx_thres, tx_hi_thres, rx_thres; > + int err; > > switch (drv_data->ssp_type) { > case QUARK_X1000_SSP: > @@ -1413,7 +1416,11 @@ static int setup(struct spi_device *spi) > if (drv_data->ssp_type == CE4100_SSP) > return 0; > > - return setup_cs(spi, chip, chip_info); > + err = setup_cs(spi, chip, chip_info); > + if (err) > + kfree(chip); > + > + return err; > } > > static void cleanup(struct spi_device *spi)

1 0

Re: [PATCH openEuler-21.03] usb: chipidea: udc: assign interrupt number to USB gadget structure
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:19, chensiyan96 写道: > From: Li Jun <jun.li(a)nxp.com> > > stable inclusion > from stable-v5.10.44 > commit 2e2145ccfbcb0dd38d8423681d22b595ca735846 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=376 > CVE: NA > > ------------------------------------------------- > > [ Upstream commit 9e3927f6373da54cb17e17f4bd700907e1123d2f ] > > Chipidea also need sync interrupt before unbind the udc while > gadget remove driver, otherwise setup irq handling may happen > while unbind, see below dump generated from android function > switch stress test: > > [ 4703.503056] android_work: sent uevent USB_STATE=CONNECTED > [ 4703.514642] android_work: sent uevent USB_STATE=DISCONNECTED > [ 4703.651339] android_work: sent uevent USB_STATE=CONNECTED > [ 4703.661806] init: Control message: Processed ctl.stop for 'adbd' from pid: 561 (system_server) > [ 4703.673469] init: processing action (init.svc.adbd=stopped) from (/system/etc/init/hw/init.usb.configfs.rc:14) > [ 4703.676451] Unable to handle kernel read from unreadable memory at virtual address 0000000000000090 > [ 4703.676454] Mem abort info: > [ 4703.676458] ESR = 0x96000004 > [ 4703.676461] EC = 0x25: DABT (current EL), IL = 32 bits > [ 4703.676464] SET = 0, FnV = 0 > [ 4703.676466] EA = 0, S1PTW = 0 > [ 4703.676468] Data abort info: > [ 4703.676471] ISV = 0, ISS = 0x00000004 > [ 4703.676473] CM = 0, WnR = 0 > [ 4703.676478] user pgtable: 4k pages, 48-bit VAs, pgdp=000000004a867000 > [ 4703.676481] [0000000000000090] pgd=0000000000000000, p4d=0000000000000000 > [ 4703.676503] Internal error: Oops: 96000004 [#1] PREEMPT SMP > [ 4703.758297] Modules linked in: synaptics_dsx_i2c moal(O) mlan(O) > [ 4703.764327] CPU: 0 PID: 235 Comm: lmkd Tainted: G W O 5.10.9-00001-g3f5fd8487c38-dirty #63 > [ 4703.773720] Hardware name: NXP i.MX8MNano EVK board (DT) > [ 4703.779033] pstate: 60400085 (nZCv daIf +PAN -UAO -TCO BTYPE=--) > [ 4703.785046] pc : _raw_write_unlock_bh+0xc0/0x2c8 > [ 4703.789667] lr : android_setup+0x4c/0x168 > [ 4703.793676] sp : ffff80001256bd80 > [ 4703.796989] x29: ffff80001256bd80 x28: 00000000000000a8 > [ 4703.802304] x27: ffff800012470000 x26: ffff80006d923000 > [ 4703.807616] x25: ffff800012471000 x24: ffff00000b091140 > [ 4703.812929] x23: ffff0000077dbd38 x22: ffff0000077da490 > [ 4703.818242] x21: ffff80001256be30 x20: 0000000000000000 > [ 4703.823554] x19: 0000000000000080 x18: ffff800012561048 > [ 4703.828867] x17: 0000000000000000 x16: 0000000000000039 > [ 4703.834180] x15: ffff8000106ad258 x14: ffff80001194c277 > [ 4703.839493] x13: 0000000000003934 x12: 0000000000000000 > [ 4703.844805] x11: 0000000000000000 x10: 0000000000000001 > [ 4703.850117] x9 : 0000000000000000 x8 : 0000000000000090 > [ 4703.855429] x7 : 6f72646e61203a70 x6 : ffff8000124f2450 > [ 4703.860742] x5 : ffffffffffffffff x4 : 0000000000000009 > [ 4703.866054] x3 : ffff8000108a290c x2 : ffff00007fb3a9c8 > [ 4703.871367] x1 : 0000000000000000 x0 : 0000000000000090 > [ 4703.876681] Call trace: > [ 4703.879129] _raw_write_unlock_bh+0xc0/0x2c8 > [ 4703.883397] android_setup+0x4c/0x168 > [ 4703.887059] udc_irq+0x824/0xa9c > [ 4703.890287] ci_irq+0x124/0x148 > [ 4703.893429] __handle_irq_event_percpu+0x84/0x268 > [ 4703.898131] handle_irq_event+0x64/0x14c > [ 4703.902054] handle_fasteoi_irq+0x110/0x210 > [ 4703.906236] __handle_domain_irq+0x8c/0xd4 > [ 4703.910332] gic_handle_irq+0x6c/0x124 > [ 4703.914081] el1_irq+0xdc/0x1c0 > [ 4703.917221] _raw_spin_unlock_irq+0x20/0x54 > [ 4703.921405] finish_task_switch+0x84/0x224 > [ 4703.925502] __schedule+0x4a4/0x734 > [ 4703.928990] schedule+0xa0/0xe8 > [ 4703.932132] do_notify_resume+0x150/0x184 > [ 4703.936140] work_pending+0xc/0x40c > [ 4703.939633] Code: d5384613 521b0a69 d5184609 f9800111 (885ffd01) > [ 4703.945732] ---[ end trace ba5c1875ae49d53c ]--- > [ 4703.950350] Kernel panic - not syncing: Oops: Fatal exception in interrupt > [ 4703.957223] SMP: stopping secondary CPUs > [ 4703.961151] Kernel Offset: disabled > [ 4703.964638] CPU features: 0x0240002,2000200c > [ 4703.968905] Memory Limit: none > [ 4703.971963] Rebooting in 5 seconds.. > > Tested-by: faqiang.zhu <faqiang.zhu(a)nxp.com> > Signed-off-by: Li Jun <jun.li(a)nxp.com> > Link: https://lore.kernel.org/r/1620989984-7653-1-git-send-email-jun.li@nxp.com > Signed-off-by: Peter Chen <peter.chen(a)kernel.org> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: chensiyan96 <3225973902(a)qq.com> > --- > drivers/usb/chipidea/udc.c | 1 + > 1 file changed, 1 insertion(+) > > diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c > index 60ea932afe2b..5f35cdd2cf1d 100644 > --- a/drivers/usb/chipidea/udc.c > +++ b/drivers/usb/chipidea/udc.c > @@ -2055,6 +2055,7 @@ static int udc_start(struct ci_hdrc *ci) > ci->gadget.name = ci->platdata->name; > ci->gadget.otg_caps = otg_caps; > ci->gadget.sg_supported = 1; > + ci->gadget.irq = ci->irq; > > if (ci->platdata->flags & CI_HDRC_REQUIRES_ALIGNED_DMA) > ci->gadget.quirk_avoids_skb_reserve = 1;

1 0

Re: [PATCH openEuler-21.03] net: mdiobus: get rid of a BUG_ON()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:25, ZhuoliHuang 写道: > From: Dan Carpenter <dan.carpenter(a)oracle.com> > > stable inclusion > from stable-v5.10.44 > commit be23c4af3d8a1b986fe9b43b8966797653a76ca4 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=341 > CVE: NA > > -------------------------------- > > [ Upstream commit 1dde47a66d4fb181830d6fa000e5ea86907b639e ] > > We spotted a bug recently during a review where a driver was > unregistering a bus that wasn't registered, which would trigger this > BUG_ON(). Let's handle that situation more gracefully, and just print > a warning and return. > > Reported-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> > Reviewed-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Reviewed-by: Andrew Lunn <andrew(a)lunn.ch> > Signed-off-by: David S. Miller <davem(a)davemloft.net> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: wangqing <wangqing(a)uniontech.com> > Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> > Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> > --- > drivers/net/phy/mdio_bus.c | 3 ++- > 1 file changed, 2 insertions(+), 1 deletion(-) > > diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c > index 757e950fb745..b848439fa837 100644 > --- a/drivers/net/phy/mdio_bus.c > +++ b/drivers/net/phy/mdio_bus.c > @@ -608,7 +608,8 @@ void mdiobus_unregister(struct mii_bus *bus) > struct mdio_device *mdiodev; > int i; > > - BUG_ON(bus->state != MDIOBUS_REGISTERED); > + if (WARN_ON_ONCE(bus->state != MDIOBUS_REGISTERED)) > + return; > bus->state = MDIOBUS_UNREGISTERED; > > for (i = 0; i < PHY_MAX_ADDR; i++) {

1 0

Re: [PATCH openEuler-21.03] net: mdiobus: get rid of a BUG_ON()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:26, lihao 写道: > From: Dan Carpenter <dan.carpenter(a)oracle.com> > > stable inclusion > from stable-v5.10.44 > commit be23c4af3d8a1b986fe9b43b8966797653a76ca4 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=341 > CVE: NA > > -------------------------------- > > [ Upstream commit 1dde47a66d4fb181830d6fa000e5ea86907b639e ] > > We spotted a bug recently during a review where a driver was > unregistering a bus that wasn't registered, which would trigger this > BUG_ON(). Let's handle that situation more gracefully, and just print > a warning and return. > > Reported-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> > Reviewed-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Reviewed-by: Andrew Lunn <andrew(a)lunn.ch> > Signed-off-by: David S. Miller <davem(a)davemloft.net> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: wangqing <wangqing(a)uniontech.com> > Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> > Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> > --- > drivers/net/phy/mdio_bus.c | 3 ++- > 1 file changed, 2 insertions(+), 1 deletion(-) > > diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c > index 757e950fb745..b848439fa837 100644 > --- a/drivers/net/phy/mdio_bus.c > +++ b/drivers/net/phy/mdio_bus.c > @@ -608,7 +608,8 @@ void mdiobus_unregister(struct mii_bus *bus) > struct mdio_device *mdiodev; > int i; > > - BUG_ON(bus->state != MDIOBUS_REGISTERED); > + if (WARN_ON_ONCE(bus->state != MDIOBUS_REGISTERED)) > + return; > bus->state = MDIOBUS_UNREGISTERED; > > for (i = 0; i < PHY_MAX_ADDR; i++) {

1 0

Re: [PATCH openEuler-21.03] net: mdiobus: get rid of a BUG_ON()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:27, zanderzhao 写道: > From: Dan Carpenter <dan.carpenter(a)oracle.com> > > stable inclusion > from stable-v5.10.44 > commit be23c4af3d8a1b986fe9b43b8966797653a76ca4 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=341 > CVE: NA > > -------------------------------- > > [ Upstream commit 1dde47a66d4fb181830d6fa000e5ea86907b639e ] > > We spotted a bug recently during a review where a driver was > unregistering a bus that wasn't registered, which would trigger this > BUG_ON(). Let's handle that situation more gracefully, and just print > a warning and return. > > Reported-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> > Reviewed-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Reviewed-by: Andrew Lunn <andrew(a)lunn.ch> > Signed-off-by: David S. Miller <davem(a)davemloft.net> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: wangqing <wangqing(a)uniontech.com> > Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> > Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> > --- > drivers/net/phy/mdio_bus.c | 3 ++- > 1 file changed, 2 insertions(+), 1 deletion(-) > > diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c > index 757e950fb745..b848439fa837 100644 > --- a/drivers/net/phy/mdio_bus.c > +++ b/drivers/net/phy/mdio_bus.c > @@ -608,7 +608,8 @@ void mdiobus_unregister(struct mii_bus *bus) > struct mdio_device *mdiodev; > int i; > > - BUG_ON(bus->state != MDIOBUS_REGISTERED); > + if (WARN_ON_ONCE(bus->state != MDIOBUS_REGISTERED)) > + return; > bus->state = MDIOBUS_UNREGISTERED; > > for (i = 0; i < PHY_MAX_ADDR; i++) {

1 0

Re: [PATCH openEuler-21.03] scsi: core: Fix failure handling of scsi_add_host_with_dma()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:32, dongenyang 写道: > From: Ming Lei <ming.lei(a)redhat.com> > > stable inclusion > from stable-v5.10.44 > commit 146446a43b3dbaa3a58364ef99fd606b3f324832 > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=361 > CVE: NA > > ------------------------------------------------- > > commit 3719f4ff047e20062b8314c23ec3cab84d74c908 upstream. > > When scsi_add_host_with_dma() returns failure, the caller will call > scsi_host_put(shost) to release everything allocated for this host > instance. Consequently we can't also free allocated stuff in > scsi_add_host_with_dma(), otherwise we will end up with a double free. > > Strictly speaking, host resource allocations should have been done in > scsi_host_alloc(). However, the allocations may need information which is > not yet provided by the driver when that function is called. So leave the > allocations where they are but rely on host device's release handler to > free resources. > > Link: https://lore.kernel.org/r/20210602133029.2864069-3-ming.lei@redhat.com > Cc: Bart Van Assche <bvanassche(a)acm.org> > Cc: John Garry <john.garry(a)huawei.com> > Cc: Hannes Reinecke <hare(a)suse.de> > Tested-by: John Garry <john.garry(a)huawei.com> > Reviewed-by: Bart Van Assche <bvanassche(a)acm.org> > Reviewed-by: John Garry <john.garry(a)huawei.com> > Reviewed-by: Hannes Reinecke <hare(a)suse.de> > Signed-off-by: Ming Lei <ming.lei(a)redhat.com> > Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: dongenyang <sdlpdey(a)163.com> > --- > drivers/scsi/hosts.c | 14 ++++++-------- > 1 file changed, 6 insertions(+), 8 deletions(-) > > diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c > index 2f162603876f..85ec3cce43f1 100644 > --- a/drivers/scsi/hosts.c > +++ b/drivers/scsi/hosts.c > @@ -278,23 +278,22 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev, > > if (!shost->work_q) { > error = -EINVAL; > - goto out_free_shost_data; > + goto out_del_dev; > } > } > > error = scsi_sysfs_add_host(shost); > if (error) > - goto out_destroy_host; > + goto out_del_dev; > > scsi_proc_host_add(shost); > scsi_autopm_put_host(shost); > return error; > > - out_destroy_host: > - if (shost->work_q) > - destroy_workqueue(shost->work_q); > - out_free_shost_data: > - kfree(shost->shost_data); > + /* > + * Any host allocation in this function will be freed in > + * scsi_host_dev_release(). > + */ > out_del_dev: > device_del(&shost->shost_dev); > out_del_gendev: > @@ -304,7 +303,6 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev, > pm_runtime_disable(&shost->shost_gendev); > pm_runtime_set_suspended(&shost->shost_gendev); > pm_runtime_put_noidle(&shost->shost_gendev); > - scsi_mq_destroy_tags(shost); > fail: > return error; > }

1 0

Re: [PATCH openEuler-21.03] USB: f_ncm: ncm_bitrate (speed) is unsigned
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 17:32, xjx00 写道: > From: Maciej Żenczykowski <maze(a)google.com> > > stable inclusion > from stable-v5.10.44 > commit 0f5a20b1fd9da3ac9f7c6edcad522712ca694d5c > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=358 > CVE: NA > > ------------------------------------------------- > > commit 3370139745853f7826895293e8ac3aec1430508e upstream. > > [ 190.544755] configfs-gadget gadget: notify speed -44967296 > > This is because 4250000000 - 2**32 is -44967296. > > Fixes: 9f6ce4240a2b ("usb: gadget: f_ncm.c added") > Cc: Brooke Basile <brookebasile(a)gmail.com> > Cc: Bryan O'Donoghue <bryan.odonoghue(a)linaro.org> > Cc: Felipe Balbi <balbi(a)kernel.org> > Cc: Lorenzo Colitti <lorenzo(a)google.com> > Cc: Yauheni Kaliuta <yauheni.kaliuta(a)nokia.com> > Cc: Linux USB Mailing List <linux-usb(a)vger.kernel.org> > Acked-By: Lorenzo Colitti <lorenzo(a)google.com> > Signed-off-by: Maciej Żenczykowski <maze(a)google.com> > Cc: stable <stable(a)vger.kernel.org> > Link: https://lore.kernel.org/r/20210608005344.3762668-1-zenczykowski@gmail.com > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: xjx00 <xjxyklwx(a)126.com> > --- > drivers/usb/gadget/function/f_ncm.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c > index 019bea8e09cc..0d23c6c11a13 100644 > --- a/drivers/usb/gadget/function/f_ncm.c > +++ b/drivers/usb/gadget/function/f_ncm.c > @@ -583,7 +583,7 @@ static void ncm_do_notify(struct f_ncm *ncm) > data[0] = cpu_to_le32(ncm_bitrate(cdev->gadget)); > data[1] = data[0]; > > - DBG(cdev, "notify speed %d\n", ncm_bitrate(cdev->gadget)); > + DBG(cdev, "notify speed %u\n", ncm_bitrate(cdev->gadget)); > ncm->notify_state = NCM_NOTIFY_CONNECT; > break; > }

1 0

Re: [PATCH openEuler-21.03] gpio: wcd934x: Fix shift-out-of-bounds error
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 20:18, zcj 写道: > From: Srinivas Kandagatla <srinivas.kandagatla(a)linaro.org> > > stable inclusion > from stable-v5.10.44 > commit e0b518a2eb44d8a74c19e50f79a8ed393e96d634 > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=463 > CVE: NA > > ------------------------------------------------- > > commit dbec64b11c65d74f31427e2b9d5746fbf17bf840 upstream. > > bit-mask for pins 0 to 4 is BIT(0) to BIT(4) however we ended up with BIT(n - 1) > which is not right, and this was caught by below usban check > > UBSAN: shift-out-of-bounds in drivers/gpio/gpio-wcd934x.c:34:14 > > Fixes: 59c324683400 ("gpio: wcd934x: Add support to wcd934x gpio controller") > Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla(a)linaro.org> > Reviewed-by: Andy Shevchenko <andy.shevchenko(a)gmail.com> > Reviewed-by: Bjorn Andersson <bjorn.andersson(a)linaro.org> > Signed-off-by: Bartosz Golaszewski <bgolaszewski(a)baylibre.com> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: zcj <2459770937(a)qq.com> > --- > drivers/gpio/gpio-wcd934x.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/gpio/gpio-wcd934x.c b/drivers/gpio/gpio-wcd934x.c > index 1cbce5990855..97e6caedf1f3 100644 > --- a/drivers/gpio/gpio-wcd934x.c > +++ b/drivers/gpio/gpio-wcd934x.c > @@ -7,7 +7,7 @@ > #include <linux/slab.h> > #include <linux/of_device.h> > > -#define WCD_PIN_MASK(p) BIT(p - 1) > +#define WCD_PIN_MASK(p) BIT(p) > #define WCD_REG_DIR_CTL_OFFSET 0x42 > #define WCD_REG_VAL_CTL_OFFSET 0x43 > #define WCD934X_NPINS 5

1 0

Re: [PATCH openEuler-21.03] regulator: fan53880: Fix missing n_voltages setting
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 20:49, lantianbaiyun 写道: > From: Axel Lin <axel.lin(a)ingics.com> > > stable inclusion > from stable-v5.10.44 > commit 5a5f5cfb5f0996d65eae3cc034513d90f4be6783 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=401 > CVE: NA > > ------------------------------------------------- > > commit 34991ee96fd8477479dd15adadceb6b28b30d9b0 upstream. > > Fixes: e6dea51e2d41 ("regulator: fan53880: Add initial support") > Signed-off-by: Axel Lin <axel.lin(a)ingics.com> > Acked-by: Christoph Fritz <chf.fritz(a)googlemail.com> > Link: https://lore.kernel.org/r/20210517105325.1227393-1-axel.lin@ingics.com > Signed-off-by: Mark Brown <broonie(a)kernel.org> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: lantianbaiyun <lianyi21(a)mails.ucas.ac.cn> > --- > drivers/regulator/fan53880.c | 3 +++ > 1 file changed, 3 insertions(+) > > diff --git a/drivers/regulator/fan53880.c b/drivers/regulator/fan53880.c > index e83eb4fb1876..1684faf82ed2 100644 > --- a/drivers/regulator/fan53880.c > +++ b/drivers/regulator/fan53880.c > @@ -51,6 +51,7 @@ static const struct regulator_ops fan53880_ops = { > REGULATOR_LINEAR_RANGE(800000, 0xf, 0x73, 25000), \ > }, \ > .n_linear_ranges = 2, \ > + .n_voltages = 0x74, \ > .vsel_reg = FAN53880_LDO ## _num ## VOUT, \ > .vsel_mask = 0x7f, \ > .enable_reg = FAN53880_ENABLE, \ > @@ -76,6 +77,7 @@ static const struct regulator_desc fan53880_regulators[] = { > REGULATOR_LINEAR_RANGE(600000, 0x1f, 0xf7, 12500), > }, > .n_linear_ranges = 2, > + .n_voltages = 0xf8, > .vsel_reg = FAN53880_BUCKVOUT, > .vsel_mask = 0x7f, > .enable_reg = FAN53880_ENABLE, > @@ -95,6 +97,7 @@ static const struct regulator_desc fan53880_regulators[] = { > REGULATOR_LINEAR_RANGE(3000000, 0x4, 0x70, 25000), > }, > .n_linear_ranges = 2, > + .n_voltages = 0x71, > .vsel_reg = FAN53880_BOOSTVOUT, > .vsel_mask = 0x7f, > .enable_reg = FAN53880_ENABLE_BOOST,

1 0

Re: [PATCH openEuler-21.03] NFSv4: Fix second deadlock in nfs4_evict_inode()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 20:55, smilezhangs 写道: > From: Trond Myklebust <trond.myklebust(a)hammerspace.com> > > stable inclusion > from stable-v5.10.44 > commit d973bd0d6e7f9b4ea976cc619e8d6e0d235b9056 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=462 > CVE: NA > > ------------------------------------------------- > > commit c3aba897c6e67fa464ec02b1f17911577d619713 upstream. > > If the inode is being evicted but has to return a layout first, then > that too can cause a deadlock in the corner case where the server > reboots. > > Signed-off-by: Trond Myklebust <trond.myklebust(a)hammerspace.com> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: Hang <haihangyiyuan(a)163.com> > Reviewed-by: Jian Cheng <cj.chengjian(a)huawei.com> > Signed-off-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> > --- > fs/nfs/nfs4proc.c | 9 +++++++-- > 1 file changed, 7 insertions(+), 2 deletions(-) > > diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c > index c92d6ff0fcea..eedcbe6832fb 100644 > --- a/fs/nfs/nfs4proc.c > +++ b/fs/nfs/nfs4proc.c > @@ -9619,15 +9619,20 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync) > &task_setup_data.rpc_client, &msg); > > dprintk("--> %s\n", __func__); > + lrp->inode = nfs_igrab_and_active(lrp->args.inode); > if (!sync) { > - lrp->inode = nfs_igrab_and_active(lrp->args.inode); > if (!lrp->inode) { > nfs4_layoutreturn_release(lrp); > return -EAGAIN; > } > task_setup_data.flags |= RPC_TASK_ASYNC; > } > - nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, 0); > + if (!lrp->inode) > + nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, > + 1); > + else > + nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, > + 0); > task = rpc_run_task(&task_setup_data); > if (IS_ERR(task)) > return PTR_ERR(task);

1 0

Re: [PATCH openEuler-21.03] net/nfc/rawsock.c: fix a permission check bug
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 21:10, lf 写道: > From: Jeimon <jjjinmeng.zhou(a)gmail.com> > > stable inclusion > from stable-v5.10.44 > commit 1e5cab50208c8fb7351b798cb1d569debfeb994a > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=371 > CVE: NA > > ------------------------------------------------- > > [ Upstream commit 8ab78863e9eff11910e1ac8bcf478060c29b379e ] > > The function rawsock_create() calls a privileged function sk_alloc(), which requires a ns-aware check to check net->user_ns, i.e., ns_capable(). However, the original code checks the init_user_ns using capable(). So we replace the capable() with ns_capable(). > > Signed-off-by: Jeimon <jjjinmeng.zhou(a)gmail.com> > Signed-off-by: David S. Miller <davem(a)davemloft.net> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: lf <15042944259(a)163.com> > --- > net/nfc/rawsock.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c > index 9c7eb8455ba8..5f1d438a0a23 100644 > --- a/net/nfc/rawsock.c > +++ b/net/nfc/rawsock.c > @@ -329,7 +329,7 @@ static int rawsock_create(struct net *net, struct socket *sock, > return -ESOCKTNOSUPPORT; > > if (sock->type == SOCK_RAW) { > - if (!capable(CAP_NET_RAW)) > + if (!ns_capable(net->user_ns, CAP_NET_RAW)) > return -EPERM; > sock->ops = &rawsock_raw_ops; > } else {

1 0

Re: [PATCH openEuler-21.03] net: mdiobus: get rid of a BUG_ON()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 21:09, lf 写道: > From: Dan Carpenter <dan.carpenter(a)oracle.com> > > stable inclusion > from stable-v5.10.44 > commit be23c4af3d8a1b986fe9b43b8966797653a76ca4 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=341 > CVE: NA > > -------------------------------- > > [ Upstream commit 1dde47a66d4fb181830d6fa000e5ea86907b639e ] > > We spotted a bug recently during a review where a driver was > unregistering a bus that wasn't registered, which would trigger this > BUG_ON(). Let's handle that situation more gracefully, and just print > a warning and return. > > Reported-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> > Reviewed-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Reviewed-by: Andrew Lunn <andrew(a)lunn.ch> > Signed-off-by: David S. Miller <davem(a)davemloft.net> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: wangqing <wangqing(a)uniontech.com> > Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> > Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> > --- > drivers/net/phy/mdio_bus.c | 3 ++- > 1 file changed, 2 insertions(+), 1 deletion(-) > > diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c > index 757e950fb745..b848439fa837 100644 > --- a/drivers/net/phy/mdio_bus.c > +++ b/drivers/net/phy/mdio_bus.c > @@ -608,7 +608,8 @@ void mdiobus_unregister(struct mii_bus *bus) > struct mdio_device *mdiodev; > int i; > > - BUG_ON(bus->state != MDIOBUS_REGISTERED); > + if (WARN_ON_ONCE(bus->state != MDIOBUS_REGISTERED)) > + return; > bus->state = MDIOBUS_UNREGISTERED; > > for (i = 0; i < PHY_MAX_ADDR; i++) {

1 0

Re: [PATCH openEuler-21.03] Revert "ACPI: sleep: Put the FACS table after using it"
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 21:18, ws 写道: > From: Zhang Rui <rui.zhang(a)intel.com> > > stable inclusion > from stable-v5.10.44 > commit afd87792db355282c4608356b98bb2dd650a6885 > Bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=438 > CVE: NA > > ------------------------------------------------- > > commit f1ffa9d4cccc8fdf6c03fb1b3429154d22037988 upstream. > > Commit 95722237cb2a ("ACPI: sleep: Put the FACS table after using it") > puts the FACS table during initialization. > > But the hardware signature bits in the FACS table need to be accessed, > after every hibernation, to compare with the original hardware > signature. > > So there is no reason to release the FACS table mapping after > initialization. > > This reverts commit 95722237cb2ae4f7b73471058cdb19e8f4057c93. > > An alternative solution is to use acpi_gbl_FACS variable instead, which > is mapped by the ACPICA core and never released. > > Link: https://bugzilla.kernel.org/show_bug.cgi?id=212277 > Reported-by: Stephan Hohe <sth.dev(a)tejp.de> > Signed-off-by: Zhang Rui <rui.zhang(a)intel.com> > Cc: 5.8+ <stable(a)vger.kernel.org> # 5.8+ > Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: ws <3045672234(a)qq.com> > --- > drivers/acpi/sleep.c | 4 +--- > 1 file changed, 1 insertion(+), 3 deletions(-) > > diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c > index aff13bf4d947..31c9d0c8ae11 100644 > --- a/drivers/acpi/sleep.c > +++ b/drivers/acpi/sleep.c > @@ -1290,10 +1290,8 @@ static void acpi_sleep_hibernate_setup(void) > return; > > acpi_get_table(ACPI_SIG_FACS, 1, (struct acpi_table_header **)&facs); > - if (facs) { > + if (facs) > s4_hardware_signature = facs->hardware_signature; > - acpi_put_table((struct acpi_table_header *)facs); > - } > } > #else /* !CONFIG_HIBERNATION */ > static inline void acpi_sleep_hibernate_setup(void) {}

1 0

Re: [PATCH openEuler-21.03] net: mdiobus: get rid of a BUG_ON()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 21:27, lcr 写道: > From: Dan Carpenter <dan.carpenter(a)oracle.com> > > stable inclusion > from stable-v5.10.44 > commit be23c4af3d8a1b986fe9b43b8966797653a76ca4 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=341 > CVE: NA > > -------------------------------- > > [ Upstream commit 1dde47a66d4fb181830d6fa000e5ea86907b639e ] > > We spotted a bug recently during a review where a driver was > unregistering a bus that wasn't registered, which would trigger this > BUG_ON(). Let's handle that situation more gracefully, and just print > a warning and return. > > Reported-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> > Reviewed-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Reviewed-by: Andrew Lunn <andrew(a)lunn.ch> > Signed-off-by: David S. Miller <davem(a)davemloft.net> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: wangqing <wangqing(a)uniontech.com> > Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> > Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> > --- > drivers/net/phy/mdio_bus.c | 3 ++- > 1 file changed, 2 insertions(+), 1 deletion(-) > > diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c > index 757e950fb745..b848439fa837 100644 > --- a/drivers/net/phy/mdio_bus.c > +++ b/drivers/net/phy/mdio_bus.c > @@ -608,7 +608,8 @@ void mdiobus_unregister(struct mii_bus *bus) > struct mdio_device *mdiodev; > int i; > > - BUG_ON(bus->state != MDIOBUS_REGISTERED); > + if (WARN_ON_ONCE(bus->state != MDIOBUS_REGISTERED)) > + return; > bus->state = MDIOBUS_UNREGISTERED; > > for (i = 0; i < PHY_MAX_ADDR; i++) {

1 0

Re: [PATCH openEuler-21.03] RDMA/mlx4: Do not map the core_clock page to user space unless enabled
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 21:27, gaodawei 写道: > From: Shay Drory <shayd(a)nvidia.com> > > stable inclusion > from stable-v5.10.44 > commit cb1aa1da04882d1860f733e24aeebdbbc85724d7 > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=454 > CVE: NA > > ------------------------------------------------- > > commit 404e5a12691fe797486475fe28cc0b80cb8bef2c upstream. > > Currently when mlx4 maps the hca_core_clock page to the user space there > are read-modifiable registers, one of which is semaphore, on this page as > well as the clock counter. If user reads the wrong offset, it can modify > the semaphore and hang the device. > > Do not map the hca_core_clock page to the user space unless the device has > been put in a backwards compatibility mode to support this feature. > > After this patch, mlx4 core_clock won't be mapped to user space on the > majority of existing devices and the uverbs device time feature in > ibv_query_rt_values_ex() will be disabled. > > Fixes: 52033cfb5aab ("IB/mlx4: Add mmap call to map the hardware clock") > Link: https://lore.kernel.org/r/9632304e0d6790af84b3b706d8c18732bc0d5e27.16227263… > Signed-off-by: Shay Drory <shayd(a)nvidia.com> > Signed-off-by: Leon Romanovsky <leonro(a)nvidia.com> > Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: gaodawei <810789471(a)qq.com> > --- > drivers/infiniband/hw/mlx4/main.c | 5 +---- > drivers/net/ethernet/mellanox/mlx4/fw.c | 3 +++ > drivers/net/ethernet/mellanox/mlx4/fw.h | 1 + > drivers/net/ethernet/mellanox/mlx4/main.c | 6 ++++++ > include/linux/mlx4/device.h | 1 + > 5 files changed, 12 insertions(+), 4 deletions(-) > > diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c > index cd0fba6b0964..7b11aff8a5ea 100644 > --- a/drivers/infiniband/hw/mlx4/main.c > +++ b/drivers/infiniband/hw/mlx4/main.c > @@ -580,12 +580,9 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, > props->cq_caps.max_cq_moderation_count = MLX4_MAX_CQ_COUNT; > props->cq_caps.max_cq_moderation_period = MLX4_MAX_CQ_PERIOD; > > - if (!mlx4_is_slave(dev->dev)) > - err = mlx4_get_internal_clock_params(dev->dev, &clock_params); > - > if (uhw->outlen >= resp.response_length + sizeof(resp.hca_core_clock_offset)) { > resp.response_length += sizeof(resp.hca_core_clock_offset); > - if (!err && !mlx4_is_slave(dev->dev)) { > + if (!mlx4_get_internal_clock_params(dev->dev, &clock_params)) { > resp.comp_mask |= MLX4_IB_QUERY_DEV_RESP_MASK_CORE_CLOCK_OFFSET; > resp.hca_core_clock_offset = clock_params.offset % PAGE_SIZE; > } > diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c > index f6cfec81ccc3..dc4ac1a2b6b6 100644 > --- a/drivers/net/ethernet/mellanox/mlx4/fw.c > +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c > @@ -823,6 +823,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) > #define QUERY_DEV_CAP_MAD_DEMUX_OFFSET 0xb0 > #define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_BASE_OFFSET 0xa8 > #define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_RANGE_OFFSET 0xac > +#define QUERY_DEV_CAP_MAP_CLOCK_TO_USER 0xc1 > #define QUERY_DEV_CAP_QP_RATE_LIMIT_NUM_OFFSET 0xcc > #define QUERY_DEV_CAP_QP_RATE_LIMIT_MAX_OFFSET 0xd0 > #define QUERY_DEV_CAP_QP_RATE_LIMIT_MIN_OFFSET 0xd2 > @@ -841,6 +842,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) > > if (mlx4_is_mfunc(dev)) > disable_unsupported_roce_caps(outbox); > + MLX4_GET(field, outbox, QUERY_DEV_CAP_MAP_CLOCK_TO_USER); > + dev_cap->map_clock_to_user = field & 0x80; > MLX4_GET(field, outbox, QUERY_DEV_CAP_RSVD_QP_OFFSET); > dev_cap->reserved_qps = 1 << (field & 0xf); > MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_QP_OFFSET); > diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h > index 8f020f26ebf5..cf64e54eecb0 100644 > --- a/drivers/net/ethernet/mellanox/mlx4/fw.h > +++ b/drivers/net/ethernet/mellanox/mlx4/fw.h > @@ -131,6 +131,7 @@ struct mlx4_dev_cap { > u32 health_buffer_addrs; > struct mlx4_port_cap port_cap[MLX4_MAX_PORTS + 1]; > bool wol_port[MLX4_MAX_PORTS + 1]; > + bool map_clock_to_user; > }; > > struct mlx4_func_cap { > diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c > index c326b434734e..00c84656b2e7 100644 > --- a/drivers/net/ethernet/mellanox/mlx4/main.c > +++ b/drivers/net/ethernet/mellanox/mlx4/main.c > @@ -498,6 +498,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) > } > } > > + dev->caps.map_clock_to_user = dev_cap->map_clock_to_user; > dev->caps.uar_page_size = PAGE_SIZE; > dev->caps.num_uars = dev_cap->uar_size / PAGE_SIZE; > dev->caps.local_ca_ack_delay = dev_cap->local_ca_ack_delay; > @@ -1948,6 +1949,11 @@ int mlx4_get_internal_clock_params(struct mlx4_dev *dev, > if (mlx4_is_slave(dev)) > return -EOPNOTSUPP; > > + if (!dev->caps.map_clock_to_user) { > + mlx4_dbg(dev, "Map clock to user is not supported.\n"); > + return -EOPNOTSUPP; > + } > + > if (!params) > return -EINVAL; > > diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h > index 06e066e04a4b..eb8169c03d89 100644 > --- a/include/linux/mlx4/device.h > +++ b/include/linux/mlx4/device.h > @@ -631,6 +631,7 @@ struct mlx4_caps { > bool wol_port[MLX4_MAX_PORTS + 1]; > struct mlx4_rate_limit_caps rl_caps; > u32 health_buffer_addrs; > + bool map_clock_to_user; > }; > > struct mlx4_buf_list {

1 0

Re: [PATCH openEuler-21.03] NFSv4: Fix second deadlock in nfs4_evict_inode()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 21:31, smilezhangs 写道: > From: Trond Myklebust <trond.myklebust(a)hammerspace.com> > > stable inclusion > from stable-v5.10.44 > commit d973bd0d6e7f9b4ea976cc619e8d6e0d235b9056 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=462 > CVE: NA > > ------------------------------------------------- > > commit c3aba897c6e67fa464ec02b1f17911577d619713 upstream. > > If the inode is being evicted but has to return a layout first, then > that too can cause a deadlock in the corner case where the server > reboots. > > Signed-off-by: Trond Myklebust <trond.myklebust(a)hammerspace.com> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: Hang <haihangyiyuan(a)163.com> > Reviewed-by: Jian Cheng <cj.chengjian(a)huawei.com> > Signed-off-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> > --- > fs/nfs/nfs4proc.c | 9 +++++++-- > 1 file changed, 7 insertions(+), 2 deletions(-) > > diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c > index c92d6ff0fcea..eedcbe6832fb 100644 > --- a/fs/nfs/nfs4proc.c > +++ b/fs/nfs/nfs4proc.c > @@ -9619,15 +9619,20 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync) > &task_setup_data.rpc_client, &msg); > > dprintk("--> %s\n", __func__); > + lrp->inode = nfs_igrab_and_active(lrp->args.inode); > if (!sync) { > - lrp->inode = nfs_igrab_and_active(lrp->args.inode); > if (!lrp->inode) { > nfs4_layoutreturn_release(lrp); > return -EAGAIN; > } > task_setup_data.flags |= RPC_TASK_ASYNC; > } > - nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, 0); > + if (!lrp->inode) > + nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, > + 1); > + else > + nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, > + 0); > task = rpc_run_task(&task_setup_data); > if (IS_ERR(task)) > return PTR_ERR(task);

1 0

Re: [PATCH openEuler-21.03] scsi: core: Only put parent device if host state differs from SHOST_CREATED
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 21:37, yangshuo 写道: > From: Ming Lei <ming.lei(a)redhat.com> > > stable inclusion > from stable-v5.10.44 > commit 5b537408f2733d510060e72596befa44c3435cb6 > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=403 > CVE: NA > > ------------------------------------------------- > > commit 1e0d4e6225996f05271de1ebcb1a7c9381af0b27 upstream. > > get_device(shost->shost_gendev.parent) is called after host state has > switched to SHOST_RUNNING. scsi_host_dev_release() shouldn't release the > parent device if host state is still SHOST_CREATED. > > Link: https://lore.kernel.org/r/20210602133029.2864069-5-ming.lei@redhat.com > Cc: Bart Van Assche <bvanassche(a)acm.org> > Cc: John Garry <john.garry(a)huawei.com> > Cc: Hannes Reinecke <hare(a)suse.de> > Tested-by: John Garry <john.garry(a)huawei.com> > Reviewed-by: John Garry <john.garry(a)huawei.com> > Signed-off-by: Ming Lei <ming.lei(a)redhat.com> > Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: yangshuo <look4polaris(a)163.com> > --- > drivers/scsi/hosts.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c > index 2f162603876f..f1b7061aa0d9 100644 > --- a/drivers/scsi/hosts.c > +++ b/drivers/scsi/hosts.c > @@ -345,7 +345,7 @@ static void scsi_host_dev_release(struct device *dev) > > ida_simple_remove(&host_index_ida, shost->host_no); > > - if (parent) > + if (shost->shost_state != SHOST_CREATED) > put_device(parent); > kfree(shost); > }

1 0

Re: [PATCH openEuler-21.03] dm verity: fix require_signatures module_param permissions
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 22:40, huangzhuoli 写道: > From: John Keeping <john(a)metanate.com> > > stable inclusion > from stable-v5.10.44 > commit 90547d5db50bcb2705709e420e0af51535109113 > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=426 > CVE: NA > > ------------------------------------------------- > > [ Upstream commit 0c1f3193b1cdd21e7182f97dc9bca7d284d18a15 ] > > The third parameter of module_param() is permissions for the sysfs node > but it looks like it is being used as the initial value of the parameter > here. In fact, false here equates to omitting the file from sysfs and > does not affect the value of require_signatures. > > Making the parameter writable is not simple because going from > false->true is fine but it should not be possible to remove the > requirement to verify a signature. But it can be useful to inspect the > value of this parameter from userspace, so change the permissions to > make a read-only file in sysfs. > > Signed-off-by: John Keeping <john(a)metanate.com> > Signed-off-by: Mike Snitzer <snitzer(a)redhat.com> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: huangzhuoli <bioagr_huangzl(a)163.com> > --- > drivers/md/dm-verity-verify-sig.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/md/dm-verity-verify-sig.c b/drivers/md/dm-verity-verify-sig.c > index 614e43db93aa..919154ae4cae 100644 > --- a/drivers/md/dm-verity-verify-sig.c > +++ b/drivers/md/dm-verity-verify-sig.c > @@ -15,7 +15,7 @@ > #define DM_VERITY_VERIFY_ERR(s) DM_VERITY_ROOT_HASH_VERIFICATION " " s > > static bool require_signatures; > -module_param(require_signatures, bool, false); > +module_param(require_signatures, bool, 0444); > MODULE_PARM_DESC(require_signatures, > "Verify the roothash of dm-verity hash tree"); >

1 0

Re: [PATCH openEuler-21.03] dm verity: fix require_signatures module_param permissions
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 22:40, huangzhuoli 写道: > From: John Keeping <john(a)metanate.com> > > stable inclusion > from stable-v5.10.44 > commit 90547d5db50bcb2705709e420e0af51535109113 > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=426 > CVE: NA > > ------------------------------------------------- > > [ Upstream commit 0c1f3193b1cdd21e7182f97dc9bca7d284d18a15 ] > > The third parameter of module_param() is permissions for the sysfs node > but it looks like it is being used as the initial value of the parameter > here. In fact, false here equates to omitting the file from sysfs and > does not affect the value of require_signatures. > > Making the parameter writable is not simple because going from > false->true is fine but it should not be possible to remove the > requirement to verify a signature. But it can be useful to inspect the > value of this parameter from userspace, so change the permissions to > make a read-only file in sysfs. > > Signed-off-by: John Keeping <john(a)metanate.com> > Signed-off-by: Mike Snitzer <snitzer(a)redhat.com> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: huangzhuoli <bioagr_huangzl(a)163.com> > --- > drivers/md/dm-verity-verify-sig.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/md/dm-verity-verify-sig.c b/drivers/md/dm-verity-verify-sig.c > index 614e43db93aa..919154ae4cae 100644 > --- a/drivers/md/dm-verity-verify-sig.c > +++ b/drivers/md/dm-verity-verify-sig.c > @@ -15,7 +15,7 @@ > #define DM_VERITY_VERIFY_ERR(s) DM_VERITY_ROOT_HASH_VERIFICATION " " s > > static bool require_signatures; > -module_param(require_signatures, bool, false); > +module_param(require_signatures, bool, 0444); > MODULE_PARM_DESC(require_signatures, > "Verify the roothash of dm-verity hash tree"); >

1 0

Re: [PATCH openEuler-21.03] ALSA: seq: Fix race of snd_seq_timer_open()
by chengjian (D) 26 Oct '21

26 Oct '21

您好，感谢参与 openEuler kernel 开发您的 signed-off-by 没有加。另外您的邮箱用户名可能不正确：显示为 yourname。在 2021/10/23 23:05, yourname 写道: > From: Takashi Iwai <tiwai(a)suse.de> > > stable inclusion > from stable-v5.10.44 > commit bd7d88b0874f82f7b29d1a53e574cedaf23166ba > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=445 > CVE: NA > > ------------------------------------------------- > > commit 83e197a8414c0ba545e7e3916ce05f836f349273 upstream. > > The timer instance per queue is exclusive, and snd_seq_timer_open() > should have managed the concurrent accesses. It looks as if it's > checking the already existing timer instance at the beginning, but > it's not right, because there is no protection, hence any later > concurrent call of snd_seq_timer_open() may override the timer > instance easily. This may result in UAF, as the leftover timer > instance can keep running while the queue itself gets closed, as > spotted by syzkaller recently. > > For avoiding the race, add a proper check at the assignment of > tmr->timeri again, and return -EBUSY if it's been already registered. > > Reported-by: syzbot+ddc1260a83ed1cbf6fb5(a)syzkaller.appspotmail.com > Cc: <stable(a)vger.kernel.org> > Link: https://lore.kernel.org/r/000000000000dce34f05c42f110c@google.com > Link: https://lore.kernel.org/r/20210610152059.24633-1-tiwai@suse.de > Signed-off-by: Takashi Iwai <tiwai(a)suse.de> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: yourname <625267121(a)qq.com> > --- > sound/core/seq/seq_timer.c | 10 +++++++++- > 1 file changed, 9 insertions(+), 1 deletion(-) > > diff --git a/sound/core/seq/seq_timer.c b/sound/core/seq/seq_timer.c > index 1645e4142e30..9863be6fd43e 100644 > --- a/sound/core/seq/seq_timer.c > +++ b/sound/core/seq/seq_timer.c > @@ -297,8 +297,16 @@ int snd_seq_timer_open(struct snd_seq_queue *q) > return err; > } > spin_lock_irq(&tmr->lock); > - tmr->timeri = t; > + if (tmr->timeri) > + err = -EBUSY; > + else > + tmr->timeri = t; > spin_unlock_irq(&tmr->lock); > + if (err < 0) { > + snd_timer_close(t); > + snd_timer_instance_free(t); > + return err; > + } > return 0; > } >

1 0

Re: [PATCH openEuler-21.03] net: mdiobus: get rid of a BUG_ON()
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/23 23:05, yourname 写道: > From: Dan Carpenter <dan.carpenter(a)oracle.com> > > stable inclusion > from stable-v5.10.44 > commit be23c4af3d8a1b986fe9b43b8966797653a76ca4 > bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=341 > CVE: NA > > -------------------------------- > > [ Upstream commit 1dde47a66d4fb181830d6fa000e5ea86907b639e ] > > We spotted a bug recently during a review where a driver was > unregistering a bus that wasn't registered, which would trigger this > BUG_ON(). Let's handle that situation more gracefully, and just print > a warning and return. > > Reported-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> > Reviewed-by: Russell King (Oracle) <rmk+kernel(a)armlinux.org.uk> > Reviewed-by: Andrew Lunn <andrew(a)lunn.ch> > Signed-off-by: David S. Miller <davem(a)davemloft.net> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > Signed-off-by: wangqing <wangqing(a)uniontech.com> > Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> > Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> 您好，感谢参与 openEuler kernel 开发您的 signed-off-by 没有加。另外您的邮箱用户名可能不正确：显示为 yourname。 > drivers/net/phy/mdio_bus.c | 3 ++- > 1 file changed, 2 insertions(+), 1 deletion(-) > > diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c > index 757e950fb745..b848439fa837 100644 > --- a/drivers/net/phy/mdio_bus.c > +++ b/drivers/net/phy/mdio_bus.c > @@ -608,7 +608,8 @@ void mdiobus_unregister(struct mii_bus *bus) > struct mdio_device *mdiodev; > int i; > > - BUG_ON(bus->state != MDIOBUS_REGISTERED); > + if (WARN_ON_ONCE(bus->state != MDIOBUS_REGISTERED)) > + return; > bus->state = MDIOBUS_UNREGISTERED; > > for (i = 0; i < PHY_MAX_ADDR; i++) {

1 0

[PATCH openEuler-21.03] usb: gadget: f_fs: Ensure io_completion_wq is idle during unbind
by liuhao 26 Oct '21

26 Oct '21

From: Wesley Cheng <wcheng(a)codeaurora.org> stable inclusion from stable-v5.10.44 commit 5cead896962d8b25dee8a8efc85b076572732b86 bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=406 CVE: NA ------------------------------------------------- commit 6fc1db5e6211e30fbb1cee8d7925d79d4ed2ae14 upstream. During unbind, ffs_func_eps_disable() will be executed, resulting in completion callbacks for any pending USB requests. When using AIO, irrespective of the completion status, io_data work is queued to io_completion_wq to evaluate and handle the completed requests. Since work runs asynchronously to the unbind() routine, there can be a scenario where the work runs after the USB gadget has been fully removed, resulting in accessing of a resource which has been already freed. (i.e. usb_ep_free_request() accessing the USB ep structure) Explicitly drain the io_completion_wq, instead of relying on the destroy_workqueue() (in ffs_data_put()) to make sure no pending completion work items are running. Signed-off-by: Wesley Cheng <wcheng(a)codeaurora.org> Cc: stable <stable(a)vger.kernel.org> Link: https://lore.kernel.org/r/1621644261-1236-1-git-send-email-wcheng@codeauror… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: liuhao <qq1107732331(a)qq.com> --- drivers/usb/gadget/function/f_fs.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index ffe67d836b0c..7df180b110af 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -3566,6 +3566,9 @@ static void ffs_func_unbind(struct usb_configuration *c, ffs->func = NULL; } + /* Drain any pending AIO completions */ + drain_workqueue(ffs->io_completion_wq); + if (!--opts->refcnt) functionfs_unbind(ffs); -- 2.23.0

2 1

Re: [PATCH openEuler-21.03] NFSv4: nfs4_proc_set_acl needs to restore NFS_CAP_UIDGID_NOMAP on error.
by chengjian (D) 26 Oct '21

26 Oct '21

Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> 在 2021/10/24 16:58, wangyongpan 写道: > From: Dai Ngo <dai.ngo(a)oracle.com> > > stable inclusion > from stable-v5.10.44 > commit 6e13b9bc66f0e34238aa7b9486a0575177fb7955 > bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=414 > CVE: NA > > ------------------------------------------------- > > commit f8849e206ef52b584cd9227255f4724f0cc900bb upstream. > > Currently if __nfs4_proc_set_acl fails with NFS4ERR_BADOWNER it > re-enables the idmapper by clearing NFS_CAP_UIDGID_NOMAP before > retrying again. The NFS_CAP_UIDGID_NOMAP remains cleared even if > the retry fails. This causes problem for subsequent setattr > requests for v4 server that does not have idmapping configured. > > This patch modifies nfs4_proc_set_acl to detect NFS4ERR_BADOWNER > and NFS4ERR_BADNAME and skips the retry, since the kernel isn't > involved in encoding the ACEs, and return -EINVAL. > > Steps to reproduce the problem: > > # mount -o vers=4.1,sec=sys server:/export/test /tmp/mnt > # touch /tmp/mnt/file1 > # chown 99 /tmp/mnt/file1 > # nfs4_setfacl -a A::unknown.user@xyz.com:wrtncy /tmp/mnt/file1 > Failed setxattr operation: Invalid argument > # chown 99 /tmp/mnt/file1 > chown: changing ownership of ‘/tmp/mnt/file1’: Invalid argument > # umount /tmp/mnt > # mount -o vers=4.1,sec=sys server:/export/test /tmp/mnt > # chown 99 /tmp/mnt/file1 > # > > v2: detect NFS4ERR_BADOWNER and NFS4ERR_BADNAME and skip retry > in nfs4_proc_set_acl. > Signed-off-by: Dai Ngo <dai.ngo(a)oracle.com> > Signed-off-by: Trond Myklebust <trond.myklebust(a)hammerspace.com> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Signed-off-by: wangyongpan <1071630525(a)qq.com> > --- > fs/nfs/nfs4proc.c | 8 ++++++++ > 1 file changed, 8 insertions(+) > > diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c > index eedcbe6832fb..f387b34bc5e5 100644 > --- a/fs/nfs/nfs4proc.c > +++ b/fs/nfs/nfs4proc.c > @@ -5942,6 +5942,14 @@ static int nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen > do { > err = __nfs4_proc_set_acl(inode, buf, buflen); > trace_nfs4_set_acl(inode, err); > + if (err == -NFS4ERR_BADOWNER || err == -NFS4ERR_BADNAME) { > + /* > + * no need to retry since the kernel > + * isn't involved in encoding the ACEs. > + */ > + err = -EINVAL; > + break; > + } > err = nfs4_handle_exception(NFS_SERVER(inode), err, > &exception); > } while (exception.retry);

1 0

[PATCH kernel-5.10] Add a kcpuid tool to show raw CPU features
by zhangyue 26 Oct '21

26 Oct '21

From: Feng Tang <feng.tang(a)intel.com> mainline inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4CMMB?from=project-issue CVE: NA ------------------------------------ End users frequently want to know what features their processor supports, independent of what the kernel supports. /proc/cpuinfo is great. It is omnipresent and since it is provided by the kernel it is always as up to date as the kernel. But, it could be ambiguous about processor features which can be disabled by the kernel at boot-time or compile-time. There are some user space tools showing more raw features, but they are not bound with kernel, and go with distros. Many end users are still using old distros with new kernels (upgraded by themselves), and may not upgrade the distros only to get a newer tool. So here arise the need for a new tool, which * shows raw CPU features read from the CPUID instruction * will be easier to update compared to existing userspace tooling (perhaps distributed like perf) * inherits "modern" kernel development process, in contrast to some of the existing userspace CPUID tools which are still being developed without git and distributed in tarballs from non-https sites. * Can produce output consistent with /proc/cpuinfo to make comparison easier. The CPUID leaf definitions are kept in an .csv file which allows for updating only that file to add support for new feature leafs. This is based on prototype code from Borislav Petkov (http://sr71.net/~dave/intel/stupid-cpuid.c) [ bp: - Massage, add #define _GNU_SOURCE to fix implicit declaration of function ‘strcasestr' warning - remove superfluous newlines - fallback to cpuid.csv in the current dir if none found - fix typos - move comments over the lines instead of sideways. ] Originally-from: Borislav Petkov <bp(a)alien8.de> Suggested-by: Dave Hansen <dave.hansen(a)intel.com> Suggested-by: Borislav Petkov <bp(a)alien8.de> Signed-off-by: Feng Tang <feng.tang(a)intel.com> Signed-off-by: Borislav Petkov <bp(a)suse.de> Signed-off-by: zhangyue <zhangyue1(a)kylinos.cn> --- tools/arch/x86/kcpuid/Makefile | 24 ++ tools/arch/x86/kcpuid/cpuid.csv | 400 +++++++++++++++++++ tools/arch/x86/kcpuid/kcpuid.c | 657 ++++++++++++++++++++++++++++++++ 3 files changed, 1081 insertions(+) create mode 100644 tools/arch/x86/kcpuid/Makefile create mode 100644 tools/arch/x86/kcpuid/cpuid.csv create mode 100644 tools/arch/x86/kcpuid/kcpuid.c diff --git a/tools/arch/x86/kcpuid/Makefile b/tools/arch/x86/kcpuid/Makefile new file mode 100644 index 000000000000..a2f1e855092c --- /dev/null +++ b/tools/arch/x86/kcpuid/Makefile @@ -0,0 +1,24 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for x86/kcpuid tool + +kcpuid : kcpuid.c + +CFLAGS = -Wextra + +BINDIR ?= /usr/sbin + +HWDATADIR ?= /usr/share/misc/ + +override CFLAGS += -O2 -Wall -I../../../include + +%: %.c + $(CC) $(CFLAGS) -o $@ $< $(LDFLAGS) + +.PHONY : clean +clean : + @rm -f kcpuid + +install : kcpuid + install -d $(DESTDIR)$(BINDIR) + install -m 755 -p kcpuid $(DESTDIR)$(BINDIR)/kcpuid + install -m 444 -p cpuid.csv $(HWDATADIR)/cpuid.csv diff --git a/tools/arch/x86/kcpuid/cpuid.csv b/tools/arch/x86/kcpuid/cpuid.csv new file mode 100644 index 000000000000..e422fad9a98e --- /dev/null +++ b/tools/arch/x86/kcpuid/cpuid.csv @@ -0,0 +1,400 @@ +# The basic row format is: +# LEAF, SUBLEAF, register_name, bits, short_name, long_description + +# Leaf 00H + 0, 0, EAX, 31:0, max_basic_leafs, Max input value for supported subleafs + +# Leaf 01H + 1, 0, EAX, 3:0, stepping, Stepping ID + 1, 0, EAX, 7:4, model, Model + 1, 0, EAX, 11:8, family, Family ID + 1, 0, EAX, 13:12, processor, Processor Type + 1, 0, EAX, 19:16, model_ext, Extended Model ID + 1, 0, EAX, 27:20, family_ext, Extended Family ID + + 1, 0, EBX, 7:0, brand, Brand Index + 1, 0, EBX, 15:8, clflush_size, CLFLUSH line size (value * 8) in bytes + 1, 0, EBX, 23:16, max_cpu_id, Maxim number of addressable logic cpu in this package + 1, 0, EBX, 31:24, apic_id, Initial APIC ID + + 1, 0, ECX, 0, sse3, Streaming SIMD Extensions 3(SSE3) + 1, 0, ECX, 1, pclmulqdq, PCLMULQDQ instruction supported + 1, 0, ECX, 2, dtes64, DS area uses 64-bit layout + 1, 0, ECX, 3, mwait, MONITOR/MWAIT supported + 1, 0, ECX, 4, ds_cpl, CPL Qualified Debug Store which allows for branch message storage qualified by CPL + 1, 0, ECX, 5, vmx, Virtual Machine Extensions supported + 1, 0, ECX, 6, smx, Safer Mode Extension supported + 1, 0, ECX, 7, eist, Enhanced Intel SpeedStep Technology + 1, 0, ECX, 8, tm2, Thermal Monitor 2 + 1, 0, ECX, 9, ssse3, Supplemental Streaming SIMD Extensions 3 (SSSE3) + 1, 0, ECX, 10, l1_ctx_id, L1 data cache could be set to either adaptive mode or shared mode (check IA32_MISC_ENABLE bit 24 definition) + 1, 0, ECX, 11, sdbg, IA32_DEBUG_INTERFACE MSR for silicon debug supported + 1, 0, ECX, 12, fma, FMA extensions using YMM state supported + 1, 0, ECX, 13, cmpxchg16b, 'CMPXCHG16B - Compare and Exchange Bytes' supported + 1, 0, ECX, 14, xtpr_update, xTPR Update Control supported + 1, 0, ECX, 15, pdcm, Perfmon and Debug Capability present + 1, 0, ECX, 17, pcid, Process-Context Identifiers feature present + 1, 0, ECX, 18, dca, Prefetching data from a memory mapped device supported + 1, 0, ECX, 19, sse4_1, SSE4.1 feature present + 1, 0, ECX, 20, sse4_2, SSE4.2 feature present + 1, 0, ECX, 21, x2apic, x2APIC supported + 1, 0, ECX, 22, movbe, MOVBE instruction supported + 1, 0, ECX, 23, popcnt, POPCNT instruction supported + 1, 0, ECX, 24, tsc_deadline_timer, LAPIC supports one-shot operation using a TSC deadline value + 1, 0, ECX, 25, aesni, AESNI instruction supported + 1, 0, ECX, 26, xsave, XSAVE/XRSTOR processor extended states (XSETBV/XGETBV/XCR0) + 1, 0, ECX, 27, osxsave, OS has set CR4.OSXSAVE bit to enable XSETBV/XGETBV/XCR0 + 1, 0, ECX, 28, avx, AVX instruction supported + 1, 0, ECX, 29, f16c, 16-bit floating-point conversion instruction supported + 1, 0, ECX, 30, rdrand, RDRAND instruction supported + + 1, 0, EDX, 0, fpu, x87 FPU on chip + 1, 0, EDX, 1, vme, Virtual-8086 Mode Enhancement + 1, 0, EDX, 2, de, Debugging Extensions + 1, 0, EDX, 3, pse, Page Size Extensions + 1, 0, EDX, 4, tsc, Time Stamp Counter + 1, 0, EDX, 5, msr, RDMSR and WRMSR Support + 1, 0, EDX, 6, pae, Physical Address Extensions + 1, 0, EDX, 7, mce, Machine Check Exception + 1, 0, EDX, 8, cx8, CMPXCHG8B instr + 1, 0, EDX, 9, apic, APIC on Chip + 1, 0, EDX, 11, sep, SYSENTER and SYSEXIT instrs + 1, 0, EDX, 12, mtrr, Memory Type Range Registers + 1, 0, EDX, 13, pge, Page Global Bit + 1, 0, EDX, 14, mca, Machine Check Architecture + 1, 0, EDX, 15, cmov, Conditional Move Instrs + 1, 0, EDX, 16, pat, Page Attribute Table + 1, 0, EDX, 17, pse36, 36-Bit Page Size Extension + 1, 0, EDX, 18, psn, Processor Serial Number + 1, 0, EDX, 19, clflush, CLFLUSH instr +# 1, 0, EDX, 20, + 1, 0, EDX, 21, ds, Debug Store + 1, 0, EDX, 22, acpi, Thermal Monitor and Software Controlled Clock Facilities + 1, 0, EDX, 23, mmx, Intel MMX Technology + 1, 0, EDX, 24, fxsr, XSAVE and FXRSTOR Instrs + 1, 0, EDX, 25, sse, SSE + 1, 0, EDX, 26, sse2, SSE2 + 1, 0, EDX, 27, ss, Self Snoop + 1, 0, EDX, 28, hit, Max APIC IDs + 1, 0, EDX, 29, tm, Thermal Monitor +# 1, 0, EDX, 30, + 1, 0, EDX, 31, pbe, Pending Break Enable + +# Leaf 02H +# cache and TLB descriptor info + +# Leaf 03H +# Precessor Serial Number, introduced on Pentium III, not valid for +# latest models + +# Leaf 04H +# thread/core and cache topology + 4, 0, EAX, 4:0, cache_type, Cache type like instr/data or unified + 4, 0, EAX, 7:5, cache_level, Cache Level (starts at 1) + 4, 0, EAX, 8, cache_self_init, Cache Self Initialization + 4, 0, EAX, 9, fully_associate, Fully Associative cache +# 4, 0, EAX, 13:10, resvd, resvd + 4, 0, EAX, 25:14, max_logical_id, Max number of addressable IDs for logical processors sharing the cache + 4, 0, EAX, 31:26, max_phy_id, Max number of addressable IDs for processors in phy package + + 4, 0, EBX, 11:0, cache_linesize, Size of a cache line in bytes + 4, 0, EBX, 21:12, cache_partition, Physical Line partitions + 4, 0, EBX, 31:22, cache_ways, Ways of associativity + 4, 0, ECX, 31:0, cache_sets, Number of Sets - 1 + 4, 0, EDX, 0, c_wbinvd, 1 means WBINVD/INVD is not ganranteed to act upon lower level caches of non-originating threads sharing this cache + 4, 0, EDX, 1, c_incl, Whether cache is inclusive of lower cache level + 4, 0, EDX, 2, c_comp_index, Complex Cache Indexing + +# Leaf 05H +# MONITOR/MWAIT + 5, 0, EAX, 15:0, min_mon_size, Smallest monitor line size in bytes + 5, 0, EBX, 15:0, max_mon_size, Largest monitor line size in bytes + 5, 0, ECX, 0, mwait_ext, Enum of Monitor-Mwait extensions supported + 5, 0, ECX, 1, mwait_irq_break, Largest monitor line size in bytes + 5, 0, EDX, 3:0, c0_sub_stats, Number of C0* sub C-states supported using MWAIT + 5, 0, EDX, 7:4, c1_sub_stats, Number of C1* sub C-states supported using MWAIT + 5, 0, EDX, 11:8, c2_sub_stats, Number of C2* sub C-states supported using MWAIT + 5, 0, EDX, 15:12, c3_sub_stats, Number of C3* sub C-states supported using MWAIT + 5, 0, EDX, 19:16, c4_sub_stats, Number of C4* sub C-states supported using MWAIT + 5, 0, EDX, 23:20, c5_sub_stats, Number of C5* sub C-states supported using MWAIT + 5, 0, EDX, 27:24, c6_sub_stats, Number of C6* sub C-states supported using MWAIT + 5, 0, EDX, 31:28, c7_sub_stats, Number of C7* sub C-states supported using MWAIT + +# Leaf 06H +# Thermal & Power Management + + 6, 0, EAX, 0, dig_temp, Digital temperature sensor supported + 6, 0, EAX, 1, turbo, Intel Turbo Boost + 6, 0, EAX, 2, arat, Always running APIC timer +# 6, 0, EAX, 3, resv, Reserved + 6, 0, EAX, 4, pln, Power limit notifications supported + 6, 0, EAX, 5, ecmd, Clock modulation duty cycle extension supported + 6, 0, EAX, 6, ptm, Package thermal management supported + 6, 0, EAX, 7, hwp, HWP base register + 6, 0, EAX, 8, hwp_notify, HWP notification + 6, 0, EAX, 9, hwp_act_window, HWP activity window + 6, 0, EAX, 10, hwp_energy, HWP energy performance preference + 6, 0, EAX, 11, hwp_pkg_req, HWP package level request +# 6, 0, EAX, 12, resv, Reserved + 6, 0, EAX, 13, hdc, HDC base registers supported + 6, 0, EAX, 14, turbo3, Turbo Boost Max 3.0 + 6, 0, EAX, 15, hwp_cap, Highest Performance change supported + 6, 0, EAX, 16, hwp_peci, HWP PECI override is supported + 6, 0, EAX, 17, hwp_flex, Flexible HWP is supported + 6, 0, EAX, 18, hwp_fast, Fast access mode for the IA32_HWP_REQUEST MSR is supported +# 6, 0, EAX, 19, resv, Reserved + 6, 0, EAX, 20, hwp_ignr, Ignoring Idle Logical Processor HWP request is supported + + 6, 0, EBX, 3:0, therm_irq_thresh, Number of Interrupt Thresholds in Digital Thermal Sensor + 6, 0, ECX, 0, aperfmperf, Presence of IA32_MPERF and IA32_APERF + 6, 0, ECX, 3, energ_bias, Performance-energy bias preference supported + +# Leaf 07H +# ECX == 0 +# AVX512 refers to https://en.wikipedia.org/wiki/AVX-512 +# XXX: Do we really need to enumerate each and every AVX512 sub features + + 7, 0, EBX, 0, fsgsbase, RDFSBASE/RDGSBASE/WRFSBASE/WRGSBASE supported + 7, 0, EBX, 1, tsc_adjust, TSC_ADJUST MSR supported + 7, 0, EBX, 2, sgx, Software Guard Extensions + 7, 0, EBX, 3, bmi1, BMI1 + 7, 0, EBX, 4, hle, Hardware Lock Elision + 7, 0, EBX, 5, avx2, AVX2 +# 7, 0, EBX, 6, fdp_excp_only, x87 FPU Data Pointer updated only on x87 exceptions + 7, 0, EBX, 7, smep, Supervisor-Mode Execution Prevention + 7, 0, EBX, 8, bmi2, BMI2 + 7, 0, EBX, 9, rep_movsb, Enhanced REP MOVSB/STOSB + 7, 0, EBX, 10, invpcid, INVPCID instruction + 7, 0, EBX, 11, rtm, Restricted Transactional Memory + 7, 0, EBX, 12, rdt_m, Intel RDT Monitoring capability + 7, 0, EBX, 13, depc_fpu_cs_ds, Deprecates FPU CS and FPU DS + 7, 0, EBX, 14, mpx, Memory Protection Extensions + 7, 0, EBX, 15, rdt_a, Intel RDT Allocation capability + 7, 0, EBX, 16, avx512f, AVX512 Foundation instr + 7, 0, EBX, 17, avx512dq, AVX512 Double and Quadword AVX512 instr + 7, 0, EBX, 18, rdseed, RDSEED instr + 7, 0, EBX, 19, adx, ADX instr + 7, 0, EBX, 20, smap, Supervisor Mode Access Prevention + 7, 0, EBX, 21, avx512ifma, AVX512 Integer Fused Multiply Add +# 7, 0, EBX, 22, resvd, resvd + 7, 0, EBX, 23, clflushopt, CLFLUSHOPT instr + 7, 0, EBX, 24, clwb, CLWB instr + 7, 0, EBX, 25, intel_pt, Intel Processor Trace instr + 7, 0, EBX, 26, avx512pf, Prefetch + 7, 0, EBX, 27, avx512er, AVX512 Exponent Reciproca instr + 7, 0, EBX, 28, avx512cd, AVX512 Conflict Detection instr + 7, 0, EBX, 29, sha, Intel Secure Hash Algorithm Extensions instr + 7, 0, EBX, 26, avx512bw, AVX512 Byte & Word instr + 7, 0, EBX, 28, avx512vl, AVX512 Vector Length Extentions (VL) + 7, 0, ECX, 0, prefetchwt1, X + 7, 0, ECX, 1, avx512vbmi, AVX512 Vector Byte Manipulation Instructions + 7, 0, ECX, 2, umip, User-mode Instruction Prevention + + 7, 0, ECX, 3, pku, Protection Keys for User-mode pages + 7, 0, ECX, 4, ospke, CR4 PKE set to enable protection keys +# 7, 0, ECX, 16:5, resvd, resvd + 7, 0, ECX, 21:17, mawau, The value of MAWAU used by the BNDLDX and BNDSTX instructions in 64-bit mode + 7, 0, ECX, 22, rdpid, RDPID and IA32_TSC_AUX +# 7, 0, ECX, 29:23, resvd, resvd + 7, 0, ECX, 30, sgx_lc, SGX Launch Configuration +# 7, 0, ECX, 31, resvd, resvd + +# Leaf 08H +# + + +# Leaf 09H +# Direct Cache Access (DCA) information + 9, 0, ECX, 31:0, dca_cap, The value of IA32_PLATFORM_DCA_CAP + +# Leaf 0AH +# Architectural Performance Monitoring +# +# Do we really need to print out the PMU related stuff? +# Does normal user really care about it? +# + 0xA, 0, EAX, 7:0, pmu_ver, Performance Monitoring Unit version + 0xA, 0, EAX, 15:8, pmu_gp_cnt_num, Numer of general-purose PMU counters per logical CPU + 0xA, 0, EAX, 23:16, pmu_cnt_bits, Bit wideth of PMU counter + 0xA, 0, EAX, 31:24, pmu_ebx_bits, Length of EBX bit vector to enumerate PMU events + + 0xA, 0, EBX, 0, pmu_no_core_cycle_evt, Core cycle event not available + 0xA, 0, EBX, 1, pmu_no_instr_ret_evt, Instruction retired event not available + 0xA, 0, EBX, 2, pmu_no_ref_cycle_evt, Reference cycles event not available + 0xA, 0, EBX, 3, pmu_no_llc_ref_evt, Last-level cache reference event not available + 0xA, 0, EBX, 4, pmu_no_llc_mis_evt, Last-level cache misses event not available + 0xA, 0, EBX, 5, pmu_no_br_instr_ret_evt, Branch instruction retired event not available + 0xA, 0, EBX, 6, pmu_no_br_mispredict_evt, Branch mispredict retired event not available + + 0xA, 0, ECX, 4:0, pmu_fixed_cnt_num, Performance Monitoring Unit version + 0xA, 0, ECX, 12:5, pmu_fixed_cnt_bits, Numer of PMU counters per logical CPU + +# Leaf 0BH +# Extended Topology Enumeration Leaf +# + + 0xB, 0, EAX, 4:0, id_shift, Number of bits to shift right on x2APIC ID to get a unique topology ID of the next level type + 0xB, 0, EBX, 15:0, cpu_nr, Number of logical processors at this level type + 0xB, 0, ECX, 15:8, lvl_type, 0-Invalid 1-SMT 2-Core + 0xB, 0, EDX, 31:0, x2apic_id, x2APIC ID the current logical processor + + +# Leaf 0DH +# Processor Extended State + + 0xD, 0, EAX, 0, x87, X87 state + 0xD, 0, EAX, 1, sse, SSE state + 0xD, 0, EAX, 2, avx, AVX state + 0xD, 0, EAX, 4:3, mpx, MPX state + 0xD, 0, EAX, 7:5, avx512, AVX-512 state + 0xD, 0, EAX, 9, pkru, PKRU state + + 0xD, 0, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0 + 0xD, 0, ECX, 31:0, max_sz_xsave, Maximum size (bytes) of the XSAVE/XRSTOR save area + + 0xD, 1, EAX, 0, xsaveopt, XSAVEOPT available + 0xD, 1, EAX, 1, xsavec, XSAVEC and compacted form supported + 0xD, 1, EAX, 2, xgetbv, XGETBV supported + 0xD, 1, EAX, 3, xsaves, XSAVES/XRSTORS and IA32_XSS supported + + 0xD, 1, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0 + 0xD, 1, ECX, 8, pt, PT state + 0xD, 1, ECX, 11, cet_usr, CET user state + 0xD, 1, ECX, 12, cet_supv, CET supervisor state + 0xD, 1, ECX, 13, hdc, HDC state + 0xD, 1, ECX, 16, hwp, HWP state + +# Leaf 0FH +# Intel RDT Monitoring + + 0xF, 0, EBX, 31:0, rmid_range, Maximum range (zero-based) of RMID within this physical processor of all types + 0xF, 0, EDX, 1, l3c_rdt_mon, L3 Cache RDT Monitoring supported + + 0xF, 1, ECX, 31:0, rmid_range, Maximum range (zero-based) of RMID of this types + 0xF, 1, EDX, 0, l3c_ocp_mon, L3 Cache occupancy Monitoring supported + 0xF, 1, EDX, 1, l3c_tbw_mon, L3 Cache Total Bandwidth Monitoring supported + 0xF, 1, EDX, 2, l3c_lbw_mon, L3 Cache Local Bandwidth Monitoring supported + +# Leaf 10H +# Intel RDT Allocation + + 0x10, 0, EBX, 1, l3c_rdt_alloc, L3 Cache Allocation supported + 0x10, 0, EBX, 2, l2c_rdt_alloc, L2 Cache Allocation supported + 0x10, 0, EBX, 3, mem_bw_alloc, Memory Bandwidth Allocation supported + + +# Leaf 12H +# SGX Capability +# +# Some detailed SGX features not added yet + + 0x12, 0, EAX, 0, sgx1, L3 Cache Allocation supported + 0x12, 1, EAX, 0, sgx2, L3 Cache Allocation supported + + +# Leaf 14H +# Intel Processor Tracer +# + +# Leaf 15H +# Time Stamp Counter and Nominal Core Crystal Clock Information + + 0x15, 0, EAX, 31:0, tsc_denominator, The denominator of the TSC/”core crystal clock” ratio + 0x15, 0, EBX, 31:0, tsc_numerator, The numerator of the TSC/”core crystal clock” ratio + 0x15, 0, ECX, 31:0, nom_freq, Nominal frequency of the core crystal clock in Hz + +# Leaf 16H +# Processor Frequency Information + + 0x16, 0, EAX, 15:0, cpu_base_freq, Processor Base Frequency in MHz + 0x16, 0, EBX, 15:0, cpu_max_freq, Maximum Frequency in MHz + 0x16, 0, ECX, 15:0, bus_freq, Bus (Reference) Frequency in MHz + +# Leaf 17H +# System-On-Chip Vendor Attribute + + 0x17, 0, EAX, 31:0, max_socid, Maximum input value of supported sub-leaf + 0x17, 0, EBX, 15:0, soc_vid, SOC Vendor ID + 0x17, 0, EBX, 16, std_vid, SOC Vendor ID is assigned via an industry standard scheme + 0x17, 0, ECX, 31:0, soc_pid, SOC Project ID assigned by vendor + 0x17, 0, EDX, 31:0, soc_sid, SOC Stepping ID + +# Leaf 18H +# Deterministic Address Translation Parameters + + +# Leaf 19H +# Key Locker Leaf + + +# Leaf 1AH +# Hybrid Information + + 0x1A, 0, EAX, 31:24, core_type, 20H-Intel_Atom 40H-Intel_Core + + +# Leaf 1FH +# V2 Extended Topology - A preferred superset to leaf 0BH + + +# According to SDM +# 40000000H - 4FFFFFFFH is invalid range + + +# Leaf 80000001H +# Extended Processor Signature and Feature Bits + +0x80000001, 0, ECX, 0, lahf_lm, LAHF/SAHF available in 64-bit mode +0x80000001, 0, ECX, 5, lzcnt, LZCNT +0x80000001, 0, ECX, 8, prefetchw, PREFETCHW + +0x80000001, 0, EDX, 11, sysret, SYSCALL/SYSRET supported +0x80000001, 0, EDX, 20, exec_dis, Execute Disable Bit available +0x80000001, 0, EDX, 26, 1gb_page, 1GB page supported +0x80000001, 0, EDX, 27, rdtscp, RDTSCP and IA32_TSC_AUX are available +#0x80000001, 0, EDX, 29, 64b, 64b Architecture supported + +# Leaf 80000002H/80000003H/80000004H +# Processor Brand String + +# Leaf 80000005H +# Reserved + +# Leaf 80000006H +# Extended L2 Cache Features + +0x80000006, 0, ECX, 7:0, clsize, Cache Line size in bytes +0x80000006, 0, ECX, 15:12, l2c_assoc, L2 Associativity +0x80000006, 0, ECX, 31:16, csize, Cache size in 1K units + + +# Leaf 80000007H + +0x80000007, 0, EDX, 8, nonstop_tsc, Invariant TSC available + + +# Leaf 80000008H + +0x80000008, 0, EAX, 7:0, phy_adr_bits, Physical Address Bits +0x80000008, 0, EAX, 15:8, lnr_adr_bits, Linear Address Bits +0x80000007, 0, EBX, 9, wbnoinvd, WBNOINVD + +# 0x8000001E +# EAX: Extended APIC ID +0x8000001E, 0, EAX, 31:0, extended_apic_id, Extended APIC ID +# EBX: Core Identifiers +0x8000001E, 0, EBX, 7:0, core_id, Identifies the logical core ID +0x8000001E, 0, EBX, 15:8, threads_per_core, The number of threads per core is threads_per_core + 1 +# ECX: Node Identifiers +0x8000001E, 0, ECX, 7:0, node_id, Node ID +0x8000001E, 0, ECX, 10:8, nodes_per_processor, Nodes per processor { 0: 1 node, else reserved } + +# 8000001F: AMD Secure Encryption +0x8000001F, 0, EAX, 0, sme, Secure Memory Encryption +0x8000001F, 0, EAX, 1, sev, Secure Encrypted Virtualization +0x8000001F, 0, EAX, 2, vmpgflush, VM Page Flush MSR +0x8000001F, 0, EAX, 3, seves, SEV Encrypted State +0x8000001F, 0, EBX, 5:0, c-bit, Page table bit number used to enable memory encryption +0x8000001F, 0, EBX, 11:6, mem_encrypt_physaddr_width, Reduction of physical address space in bits with SME enabled +0x8000001F, 0, ECX, 31:0, num_encrypted_guests, Maximum ASID value that may be used for an SEV-enabled guest +0x8000001F, 0, EDX, 31:0, minimum_sev_asid, Minimum ASID value that must be used for an SEV-enabled, SEV-ES-disabled guest \ No newline at end of file diff --git a/tools/arch/x86/kcpuid/kcpuid.c b/tools/arch/x86/kcpuid/kcpuid.c new file mode 100644 index 000000000000..936a3a2aad04 --- /dev/null +++ b/tools/arch/x86/kcpuid/kcpuid.c @@ -0,0 +1,657 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <stdio.h> +#include <stdbool.h> +#include <stdlib.h> +#include <string.h> +#include <getopt.h> + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) + +typedef unsigned int u32; +typedef unsigned long long u64; + +char *def_csv = "/usr/share/misc/cpuid.csv"; +char *user_csv; + + +/* Cover both single-bit flag and multiple-bits fields */ +struct bits_desc { + /* start and end bits */ + int start, end; + /* 0 or 1 for 1-bit flag */ + int value; + char simp[32]; + char detail[256]; +}; + +/* descriptor info for eax/ebx/ecx/edx */ +struct reg_desc { + /* number of valid entries */ + int nr; + struct bits_desc descs[32]; +}; + +enum { + R_EAX = 0, + R_EBX, + R_ECX, + R_EDX, + NR_REGS +}; + +struct subleaf { + u32 index; + u32 sub; + u32 eax, ebx, ecx, edx; + struct reg_desc info[NR_REGS]; +}; + +/* Represent one leaf (basic or extended) */ +struct cpuid_func { + /* + * Array of subleafs for this func, if there is no subleafs + * then the leafs[0] is the main leaf + */ + struct subleaf *leafs; + int nr; +}; + +struct cpuid_range { + /* array of main leafs */ + struct cpuid_func *funcs; + /* number of valid leafs */ + int nr; + bool is_ext; +}; + +/* + * basic: basic functions range: [0... ] + * ext: extended functions range: [0x80000000... ] + */ +struct cpuid_range *leafs_basic, *leafs_ext; + +static int num_leafs; +static bool is_amd; +static bool show_details; +static bool show_raw; +static bool show_flags_only = true; +static u32 user_index = 0xFFFFFFFF; +static u32 user_sub = 0xFFFFFFFF; +static int flines; + +static inline void cpuid(u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) +{ + /* ecx is often an input as well as an output. */ + asm volatile("cpuid" + : "=a" (*eax), + "=b" (*ebx), + "=c" (*ecx), + "=d" (*edx) + : "0" (*eax), "2" (*ecx)); +} + +static inline bool has_subleafs(u32 f) +{ + if (f == 0x7 || f == 0xd) + return true; + + if (is_amd) { + if (f == 0x8000001d) + return true; + return false; + } + + switch (f) { + case 0x4: + case 0xb: + case 0xf: + case 0x10: + case 0x14: + case 0x18: + case 0x1f: + return true; + default: + return false; + } +} + +static void leaf_print_raw(struct subleaf *leaf) +{ + if (has_subleafs(leaf->index)) { + if (leaf->sub == 0) + printf("0x%08x: subleafs:\n", leaf->index); + + printf(" %2d: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n", + leaf->sub, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx); + } else { + printf("0x%08x: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n", + leaf->index, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx); + } +} + +/* Return true is the input eax/ebx/ecx/edx are all zero */ +static bool cpuid_store(struct cpuid_range *range, u32 f, int subleaf, + u32 a, u32 b, u32 c, u32 d) +{ + struct cpuid_func *func; + struct subleaf *leaf; + int s = 0; + + if (a == 0 && b == 0 && c == 0 && d == 0) + return true; + + /* + * Cut off vendor-prefix from CPUID function as we're using it as an + * index into ->funcs. + */ + func = &range->funcs[f & 0xffff]; + + if (!func->leafs) { + func->leafs = malloc(sizeof(struct subleaf)); + if (!func->leafs) + perror("malloc func leaf"); + + func->nr = 1; + } else { + s = func->nr; + func->leafs = realloc(func->leafs, (s + 1) * sizeof(*leaf)); + if (!func->leafs) + perror("realloc f->leafs"); + + func->nr++; + } + + leaf = &func->leafs[s]; + + leaf->index = f; + leaf->sub = subleaf; + leaf->eax = a; + leaf->ebx = b; + leaf->ecx = c; + leaf->edx = d; + + return false; +} + +static void raw_dump_range(struct cpuid_range *range) +{ + u32 f; + int i; + + printf("%s Leafs :\n", range->is_ext ? "Extended" : "Basic"); + printf("================\n"); + + for (f = 0; (int)f < range->nr; f++) { + struct cpuid_func *func = &range->funcs[f]; + u32 index = f; + + if (range->is_ext) + index += 0x80000000; + + /* Skip leaf without valid items */ + if (!func->nr) + continue; + + /* First item is the main leaf, followed by all subleafs */ + for (i = 0; i < func->nr; i++) + leaf_print_raw(&func->leafs[i]); + } +} + +#define MAX_SUBLEAF_NUM 32 +struct cpuid_range *setup_cpuid_range(u32 input_eax) +{ + u32 max_func, idx_func; + int subleaf; + struct cpuid_range *range; + u32 eax, ebx, ecx, edx; + u32 f = input_eax; + int max_subleaf; + bool allzero; + + eax = input_eax; + ebx = ecx = edx = 0; + + cpuid(&eax, &ebx, &ecx, &edx); + max_func = eax; + idx_func = (max_func & 0xffff) + 1; + + range = malloc(sizeof(struct cpuid_range)); + if (!range) + perror("malloc range"); + + if (input_eax & 0x80000000) + range->is_ext = true; + else + range->is_ext = false; + + range->funcs = malloc(sizeof(struct cpuid_func) * idx_func); + if (!range->funcs) + perror("malloc range->funcs"); + + range->nr = idx_func; + memset(range->funcs, 0, sizeof(struct cpuid_func) * idx_func); + + for (; f <= max_func; f++) { + eax = f; + subleaf = ecx = 0; + + cpuid(&eax, &ebx, &ecx, &edx); + allzero = cpuid_store(range, f, subleaf, eax, ebx, ecx, edx); + if (allzero) + continue; + num_leafs++; + + if (!has_subleafs(f)) + continue; + + max_subleaf = MAX_SUBLEAF_NUM; + + /* + * Some can provide the exact number of subleafs, + * others have to be tried (0xf) + */ + if (f == 0x7 || f == 0x14 || f == 0x17 || f == 0x18) + max_subleaf = (eax & 0xff) + 1; + + if (f == 0xb) + max_subleaf = 2; + + for (subleaf = 1; subleaf < max_subleaf; subleaf++) { + eax = f; + ecx = subleaf; + + cpuid(&eax, &ebx, &ecx, &edx); + allzero = cpuid_store(range, f, subleaf, + eax, ebx, ecx, edx); + if (allzero) + continue; + num_leafs++; + } + + } + + return range; +} + +/* + * The basic row format for cpuid.csv is + * LEAF,SUBLEAF,register_name,bits,short name,long description + * + * like: + * 0, 0, EAX, 31:0, max_basic_leafs, Max input value for supported subleafs + * 1, 0, ECX, 0, sse3, Streaming SIMD Extensions 3(SSE3) + */ +static int parse_line(char *line) +{ + char *str; + int i; + struct cpuid_range *range; + struct cpuid_func *func; + struct subleaf *leaf; + u32 index; + u32 sub; + char buffer[512]; + char *buf; + /* + * Tokens: + * 1. leaf + * 2. subleaf + * 3. register + * 4. bits + * 5. short name + * 6. long detail + */ + char *tokens[6]; + struct reg_desc *reg; + struct bits_desc *bdesc; + int reg_index; + char *start, *end; + + /* Skip comments and NULL line */ + if (line[0] == '#' || line[0] == '\n') + return 0; + + strncpy(buffer, line, 511); + buffer[511] = 0; + str = buffer; + for (i = 0; i < 5; i++) { + tokens[i] = strtok(str, ","); + if (!tokens[i]) + goto err_exit; + str = NULL; + } + tokens[5] = strtok(str, "\n"); + if (!tokens[5]) + goto err_exit; + + /* index/main-leaf */ + index = strtoull(tokens[0], NULL, 0); + + if (index & 0x80000000) + range = leafs_ext; + else + range = leafs_basic; + + index &= 0x7FFFFFFF; + /* Skip line parsing for non-existing indexes */ + if ((int)index >= range->nr) + return -1; + + func = &range->funcs[index]; + + /* Return if the index has no valid item on this platform */ + if (!func->nr) + return 0; + + /* subleaf */ + sub = strtoul(tokens[1], NULL, 0); + if ((int)sub > func->nr) + return -1; + + leaf = &func->leafs[sub]; + buf = tokens[2]; + + if (strcasestr(buf, "EAX")) + reg_index = R_EAX; + else if (strcasestr(buf, "EBX")) + reg_index = R_EBX; + else if (strcasestr(buf, "ECX")) + reg_index = R_ECX; + else if (strcasestr(buf, "EDX")) + reg_index = R_EDX; + else + goto err_exit; + + reg = &leaf->info[reg_index]; + bdesc = &reg->descs[reg->nr++]; + + /* bit flag or bits field */ + buf = tokens[3]; + + end = strtok(buf, ":"); + bdesc->end = strtoul(end, NULL, 0); + bdesc->start = bdesc->end; + + /* start != NULL means it is bit fields */ + start = strtok(NULL, ":"); + if (start) + bdesc->start = strtoul(start, NULL, 0); + + strcpy(bdesc->simp, tokens[4]); + strcpy(bdesc->detail, tokens[5]); + return 0; + +err_exit: + printf("Warning: wrong line format:\n"); + printf("\tline[%d]: %s\n", flines, line); + return -1; +} + +/* Parse csv file, and construct the array of all leafs and subleafs */ +static void parse_text(void) +{ + FILE *file; + char *filename, *line = NULL; + size_t len = 0; + int ret; + + if (show_raw) + return; + + filename = user_csv ? user_csv : def_csv; + file = fopen(filename, "r"); + if (!file) { + /* Fallback to a csv in the same dir */ + file = fopen("./cpuid.csv", "r"); + } + + if (!file) { + printf("Fail to open '%s'\n", filename); + return; + } + + while (1) { + ret = getline(&line, &len, file); + flines++; + if (ret > 0) + parse_line(line); + + if (feof(file)) + break; + } + + fclose(file); +} + + +/* Decode every eax/ebx/ecx/edx */ +static void decode_bits(u32 value, struct reg_desc *rdesc) +{ + struct bits_desc *bdesc; + int start, end, i; + u32 mask; + + for (i = 0; i < rdesc->nr; i++) { + bdesc = &rdesc->descs[i]; + + start = bdesc->start; + end = bdesc->end; + if (start == end) { + /* single bit flag */ + if (value & (1 << start)) + printf("\t%-20s %s%s\n", + bdesc->simp, + show_details ? "-" : "", + show_details ? bdesc->detail : "" + ); + } else { + /* bit fields */ + if (show_flags_only) + continue; + + mask = ((u64)1 << (end - start + 1)) - 1; + printf("\t%-20s\t: 0x%-8x\t%s%s\n", + bdesc->simp, + (value >> start) & mask, + show_details ? "-" : "", + show_details ? bdesc->detail : "" + ); + } + } +} + +static void show_leaf(struct subleaf *leaf) +{ + if (!leaf) + return; + + if (show_raw) + leaf_print_raw(leaf); + + decode_bits(leaf->eax, &leaf->info[R_EAX]); + decode_bits(leaf->ebx, &leaf->info[R_EBX]); + decode_bits(leaf->ecx, &leaf->info[R_ECX]); + decode_bits(leaf->edx, &leaf->info[R_EDX]); +} + +static void show_func(struct cpuid_func *func) +{ + int i; + + if (!func) + return; + + for (i = 0; i < func->nr; i++) + show_leaf(&func->leafs[i]); +} + +static void show_range(struct cpuid_range *range) +{ + int i; + + for (i = 0; i < range->nr; i++) + show_func(&range->funcs[i]); +} + +static inline struct cpuid_func *index_to_func(u32 index) +{ + struct cpuid_range *range; + + range = (index & 0x80000000) ? leafs_ext : leafs_basic; + index &= 0x7FFFFFFF; + + if (((index & 0xFFFF) + 1) > (u32)range->nr) { + printf("ERR: invalid input index (0x%x)\n", index); + return NULL; + } + return &range->funcs[index]; +} + +static void show_info(void) +{ + struct cpuid_func *func; + + if (show_raw) { + /* Show all of the raw output of 'cpuid' instr */ + raw_dump_range(leafs_basic); + raw_dump_range(leafs_ext); + return; + } + + if (user_index != 0xFFFFFFFF) { + /* Only show specific leaf/subleaf info */ + func = index_to_func(user_index); + if (!func) + return; + + /* Dump the raw data also */ + show_raw = true; + + if (user_sub != 0xFFFFFFFF) { + if (user_sub + 1 <= (u32)func->nr) { + show_leaf(&func->leafs[user_sub]); + return; + } + + printf("ERR: invalid input subleaf (0x%x)\n", user_sub); + } + + show_func(func); + return; + } + + printf("CPU features:\n=============\n\n"); + show_range(leafs_basic); + show_range(leafs_ext); +} + +static void setup_platform_cpuid(void) +{ + u32 eax, ebx, ecx, edx; + + /* Check vendor */ + eax = ebx = ecx = edx = 0; + cpuid(&eax, &ebx, &ecx, &edx); + + /* "htuA" */ + if (ebx == 0x68747541) + is_amd = true; + + /* Setup leafs for the basic and extended range */ + leafs_basic = setup_cpuid_range(0x0); + leafs_ext = setup_cpuid_range(0x80000000); +} + +static void usage(void) +{ + printf("kcpuid [-abdfhr] [-l leaf] [-s subleaf]\n" + "\t-a|--all Show both bit flags and complex bit fields info\n" + "\t-b|--bitflags Show boolean flags only\n" + "\t-d|--detail Show details of the flag/fields (default)\n" + "\t-f|--flags Specify the cpuid csv file\n" + "\t-h|--help Show usage info\n" + "\t-l|--leaf=index Specify the leaf you want to check\n" + "\t-r|--raw Show raw cpuid data\n" + "\t-s|--subleaf=sub Specify the subleaf you want to check\n" + ); +} + +static struct option opts[] = { + { "all", no_argument, NULL, 'a' }, /* show both bit flags and fields */ + { "bitflags", no_argument, NULL, 'b' }, /* only show bit flags, default on */ + { "detail", no_argument, NULL, 'd' }, /* show detail descriptions */ + { "file", required_argument, NULL, 'f' }, /* use user's cpuid file */ + { "help", no_argument, NULL, 'h'}, /* show usage */ + { "leaf", required_argument, NULL, 'l'}, /* only check a specific leaf */ + { "raw", no_argument, NULL, 'r'}, /* show raw CPUID leaf data */ + { "subleaf", required_argument, NULL, 's'}, /* check a specific subleaf */ + { NULL, 0, NULL, 0 } +}; + +static int parse_options(int argc, char *argv[]) +{ + int c; + + while ((c = getopt_long(argc, argv, "abdf:hl:rs:", + opts, NULL)) != -1) + switch (c) { + case 'a': + show_flags_only = false; + break; + case 'b': + show_flags_only = true; + break; + case 'd': + show_details = true; + break; + case 'f': + user_csv = optarg; + break; + case 'h': + usage(); + exit(1); + break; + case 'l': + /* main leaf */ + user_index = strtoul(optarg, NULL, 0); + break; + case 'r': + show_raw = true; + break; + case 's': + /* subleaf */ + user_sub = strtoul(optarg, NULL, 0); + break; + default: + printf("%s: Invalid option '%c'\n", argv[0], optopt); + return -1; + } + + return 0; +} + +/* + * Do 4 things in turn: + * 1. Parse user options + * 2. Parse and store all the CPUID leaf data supported on this platform + * 2. Parse the csv file, while skipping leafs which are not available + * on this platform + * 3. Print leafs info based on user options + */ +int main(int argc, char *argv[]) +{ + if (parse_options(argc, argv)) + return -1; + + /* Setup the cpuid leafs of current platform */ + setup_platform_cpuid(); + + /* Read and parse the 'cpuid.csv' */ + parse_text(); + + show_info(); + return 0; +} \ No newline at end of file -- 2.30.0

1 0

[PATCH kernel-5.10] Add a kcpuid tool to show raw CPU features
by zhangyue 26 Oct '21

26 Oct '21

From: Feng Tang <feng.tang(a)intel.com> mainline inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4CMMB?from=project-issue CVE: NA ------------------------------------ End users frequently want to know what features their processor supports, independent of what the kernel supports. /proc/cpuinfo is great. It is omnipresent and since it is provided by the kernel it is always as up to date as the kernel. But, it could be ambiguous about processor features which can be disabled by the kernel at boot-time or compile-time. There are some user space tools showing more raw features, but they are not bound with kernel, and go with distros. Many end users are still using old distros with new kernels (upgraded by themselves), and may not upgrade the distros only to get a newer tool. So here arise the need for a new tool, which * shows raw CPU features read from the CPUID instruction * will be easier to update compared to existing userspace tooling (perhaps distributed like perf) * inherits "modern" kernel development process, in contrast to some of the existing userspace CPUID tools which are still being developed without git and distributed in tarballs from non-https sites. * Can produce output consistent with /proc/cpuinfo to make comparison easier. The CPUID leaf definitions are kept in an .csv file which allows for updating only that file to add support for new feature leafs. This is based on prototype code from Borislav Petkov (http://sr71.net/~dave/intel/stupid-cpuid.c) [ bp: - Massage, add #define _GNU_SOURCE to fix implicit declaration of function ‘strcasestr' warning - remove superfluous newlines - fallback to cpuid.csv in the current dir if none found - fix typos - move comments over the lines instead of sideways. ] Originally-from: Borislav Petkov <bp(a)alien8.de> Suggested-by: Dave Hansen <dave.hansen(a)intel.com> Suggested-by: Borislav Petkov <bp(a)alien8.de> Signed-off-by: Feng Tang <feng.tang(a)intel.com> Signed-off-by: Borislav Petkov <bp(a)suse.de> Signed-off-by: zhangyue <zhangyue1(a)kylinos.cn> --- tools/arch/x86/kcpuid/Makefile | 24 ++ tools/arch/x86/kcpuid/cpuid.csv | 400 +++++++++++++++++++ tools/arch/x86/kcpuid/kcpuid.c | 657 ++++++++++++++++++++++++++++++++ 3 files changed, 1081 insertions(+) create mode 100644 tools/arch/x86/kcpuid/Makefile create mode 100644 tools/arch/x86/kcpuid/cpuid.csv create mode 100644 tools/arch/x86/kcpuid/kcpuid.c diff --git a/tools/arch/x86/kcpuid/Makefile b/tools/arch/x86/kcpuid/Makefile new file mode 100644 index 000000000000..a2f1e855092c --- /dev/null +++ b/tools/arch/x86/kcpuid/Makefile @@ -0,0 +1,24 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for x86/kcpuid tool + +kcpuid : kcpuid.c + +CFLAGS = -Wextra + +BINDIR ?= /usr/sbin + +HWDATADIR ?= /usr/share/misc/ + +override CFLAGS += -O2 -Wall -I../../../include + +%: %.c + $(CC) $(CFLAGS) -o $@ $< $(LDFLAGS) + +.PHONY : clean +clean : + @rm -f kcpuid + +install : kcpuid + install -d $(DESTDIR)$(BINDIR) + install -m 755 -p kcpuid $(DESTDIR)$(BINDIR)/kcpuid + install -m 444 -p cpuid.csv $(HWDATADIR)/cpuid.csv diff --git a/tools/arch/x86/kcpuid/cpuid.csv b/tools/arch/x86/kcpuid/cpuid.csv new file mode 100644 index 000000000000..e422fad9a98e --- /dev/null +++ b/tools/arch/x86/kcpuid/cpuid.csv @@ -0,0 +1,400 @@ +# The basic row format is: +# LEAF, SUBLEAF, register_name, bits, short_name, long_description + +# Leaf 00H + 0, 0, EAX, 31:0, max_basic_leafs, Max input value for supported subleafs + +# Leaf 01H + 1, 0, EAX, 3:0, stepping, Stepping ID + 1, 0, EAX, 7:4, model, Model + 1, 0, EAX, 11:8, family, Family ID + 1, 0, EAX, 13:12, processor, Processor Type + 1, 0, EAX, 19:16, model_ext, Extended Model ID + 1, 0, EAX, 27:20, family_ext, Extended Family ID + + 1, 0, EBX, 7:0, brand, Brand Index + 1, 0, EBX, 15:8, clflush_size, CLFLUSH line size (value * 8) in bytes + 1, 0, EBX, 23:16, max_cpu_id, Maxim number of addressable logic cpu in this package + 1, 0, EBX, 31:24, apic_id, Initial APIC ID + + 1, 0, ECX, 0, sse3, Streaming SIMD Extensions 3(SSE3) + 1, 0, ECX, 1, pclmulqdq, PCLMULQDQ instruction supported + 1, 0, ECX, 2, dtes64, DS area uses 64-bit layout + 1, 0, ECX, 3, mwait, MONITOR/MWAIT supported + 1, 0, ECX, 4, ds_cpl, CPL Qualified Debug Store which allows for branch message storage qualified by CPL + 1, 0, ECX, 5, vmx, Virtual Machine Extensions supported + 1, 0, ECX, 6, smx, Safer Mode Extension supported + 1, 0, ECX, 7, eist, Enhanced Intel SpeedStep Technology + 1, 0, ECX, 8, tm2, Thermal Monitor 2 + 1, 0, ECX, 9, ssse3, Supplemental Streaming SIMD Extensions 3 (SSSE3) + 1, 0, ECX, 10, l1_ctx_id, L1 data cache could be set to either adaptive mode or shared mode (check IA32_MISC_ENABLE bit 24 definition) + 1, 0, ECX, 11, sdbg, IA32_DEBUG_INTERFACE MSR for silicon debug supported + 1, 0, ECX, 12, fma, FMA extensions using YMM state supported + 1, 0, ECX, 13, cmpxchg16b, 'CMPXCHG16B - Compare and Exchange Bytes' supported + 1, 0, ECX, 14, xtpr_update, xTPR Update Control supported + 1, 0, ECX, 15, pdcm, Perfmon and Debug Capability present + 1, 0, ECX, 17, pcid, Process-Context Identifiers feature present + 1, 0, ECX, 18, dca, Prefetching data from a memory mapped device supported + 1, 0, ECX, 19, sse4_1, SSE4.1 feature present + 1, 0, ECX, 20, sse4_2, SSE4.2 feature present + 1, 0, ECX, 21, x2apic, x2APIC supported + 1, 0, ECX, 22, movbe, MOVBE instruction supported + 1, 0, ECX, 23, popcnt, POPCNT instruction supported + 1, 0, ECX, 24, tsc_deadline_timer, LAPIC supports one-shot operation using a TSC deadline value + 1, 0, ECX, 25, aesni, AESNI instruction supported + 1, 0, ECX, 26, xsave, XSAVE/XRSTOR processor extended states (XSETBV/XGETBV/XCR0) + 1, 0, ECX, 27, osxsave, OS has set CR4.OSXSAVE bit to enable XSETBV/XGETBV/XCR0 + 1, 0, ECX, 28, avx, AVX instruction supported + 1, 0, ECX, 29, f16c, 16-bit floating-point conversion instruction supported + 1, 0, ECX, 30, rdrand, RDRAND instruction supported + + 1, 0, EDX, 0, fpu, x87 FPU on chip + 1, 0, EDX, 1, vme, Virtual-8086 Mode Enhancement + 1, 0, EDX, 2, de, Debugging Extensions + 1, 0, EDX, 3, pse, Page Size Extensions + 1, 0, EDX, 4, tsc, Time Stamp Counter + 1, 0, EDX, 5, msr, RDMSR and WRMSR Support + 1, 0, EDX, 6, pae, Physical Address Extensions + 1, 0, EDX, 7, mce, Machine Check Exception + 1, 0, EDX, 8, cx8, CMPXCHG8B instr + 1, 0, EDX, 9, apic, APIC on Chip + 1, 0, EDX, 11, sep, SYSENTER and SYSEXIT instrs + 1, 0, EDX, 12, mtrr, Memory Type Range Registers + 1, 0, EDX, 13, pge, Page Global Bit + 1, 0, EDX, 14, mca, Machine Check Architecture + 1, 0, EDX, 15, cmov, Conditional Move Instrs + 1, 0, EDX, 16, pat, Page Attribute Table + 1, 0, EDX, 17, pse36, 36-Bit Page Size Extension + 1, 0, EDX, 18, psn, Processor Serial Number + 1, 0, EDX, 19, clflush, CLFLUSH instr +# 1, 0, EDX, 20, + 1, 0, EDX, 21, ds, Debug Store + 1, 0, EDX, 22, acpi, Thermal Monitor and Software Controlled Clock Facilities + 1, 0, EDX, 23, mmx, Intel MMX Technology + 1, 0, EDX, 24, fxsr, XSAVE and FXRSTOR Instrs + 1, 0, EDX, 25, sse, SSE + 1, 0, EDX, 26, sse2, SSE2 + 1, 0, EDX, 27, ss, Self Snoop + 1, 0, EDX, 28, hit, Max APIC IDs + 1, 0, EDX, 29, tm, Thermal Monitor +# 1, 0, EDX, 30, + 1, 0, EDX, 31, pbe, Pending Break Enable + +# Leaf 02H +# cache and TLB descriptor info + +# Leaf 03H +# Precessor Serial Number, introduced on Pentium III, not valid for +# latest models + +# Leaf 04H +# thread/core and cache topology + 4, 0, EAX, 4:0, cache_type, Cache type like instr/data or unified + 4, 0, EAX, 7:5, cache_level, Cache Level (starts at 1) + 4, 0, EAX, 8, cache_self_init, Cache Self Initialization + 4, 0, EAX, 9, fully_associate, Fully Associative cache +# 4, 0, EAX, 13:10, resvd, resvd + 4, 0, EAX, 25:14, max_logical_id, Max number of addressable IDs for logical processors sharing the cache + 4, 0, EAX, 31:26, max_phy_id, Max number of addressable IDs for processors in phy package + + 4, 0, EBX, 11:0, cache_linesize, Size of a cache line in bytes + 4, 0, EBX, 21:12, cache_partition, Physical Line partitions + 4, 0, EBX, 31:22, cache_ways, Ways of associativity + 4, 0, ECX, 31:0, cache_sets, Number of Sets - 1 + 4, 0, EDX, 0, c_wbinvd, 1 means WBINVD/INVD is not ganranteed to act upon lower level caches of non-originating threads sharing this cache + 4, 0, EDX, 1, c_incl, Whether cache is inclusive of lower cache level + 4, 0, EDX, 2, c_comp_index, Complex Cache Indexing + +# Leaf 05H +# MONITOR/MWAIT + 5, 0, EAX, 15:0, min_mon_size, Smallest monitor line size in bytes + 5, 0, EBX, 15:0, max_mon_size, Largest monitor line size in bytes + 5, 0, ECX, 0, mwait_ext, Enum of Monitor-Mwait extensions supported + 5, 0, ECX, 1, mwait_irq_break, Largest monitor line size in bytes + 5, 0, EDX, 3:0, c0_sub_stats, Number of C0* sub C-states supported using MWAIT + 5, 0, EDX, 7:4, c1_sub_stats, Number of C1* sub C-states supported using MWAIT + 5, 0, EDX, 11:8, c2_sub_stats, Number of C2* sub C-states supported using MWAIT + 5, 0, EDX, 15:12, c3_sub_stats, Number of C3* sub C-states supported using MWAIT + 5, 0, EDX, 19:16, c4_sub_stats, Number of C4* sub C-states supported using MWAIT + 5, 0, EDX, 23:20, c5_sub_stats, Number of C5* sub C-states supported using MWAIT + 5, 0, EDX, 27:24, c6_sub_stats, Number of C6* sub C-states supported using MWAIT + 5, 0, EDX, 31:28, c7_sub_stats, Number of C7* sub C-states supported using MWAIT + +# Leaf 06H +# Thermal & Power Management + + 6, 0, EAX, 0, dig_temp, Digital temperature sensor supported + 6, 0, EAX, 1, turbo, Intel Turbo Boost + 6, 0, EAX, 2, arat, Always running APIC timer +# 6, 0, EAX, 3, resv, Reserved + 6, 0, EAX, 4, pln, Power limit notifications supported + 6, 0, EAX, 5, ecmd, Clock modulation duty cycle extension supported + 6, 0, EAX, 6, ptm, Package thermal management supported + 6, 0, EAX, 7, hwp, HWP base register + 6, 0, EAX, 8, hwp_notify, HWP notification + 6, 0, EAX, 9, hwp_act_window, HWP activity window + 6, 0, EAX, 10, hwp_energy, HWP energy performance preference + 6, 0, EAX, 11, hwp_pkg_req, HWP package level request +# 6, 0, EAX, 12, resv, Reserved + 6, 0, EAX, 13, hdc, HDC base registers supported + 6, 0, EAX, 14, turbo3, Turbo Boost Max 3.0 + 6, 0, EAX, 15, hwp_cap, Highest Performance change supported + 6, 0, EAX, 16, hwp_peci, HWP PECI override is supported + 6, 0, EAX, 17, hwp_flex, Flexible HWP is supported + 6, 0, EAX, 18, hwp_fast, Fast access mode for the IA32_HWP_REQUEST MSR is supported +# 6, 0, EAX, 19, resv, Reserved + 6, 0, EAX, 20, hwp_ignr, Ignoring Idle Logical Processor HWP request is supported + + 6, 0, EBX, 3:0, therm_irq_thresh, Number of Interrupt Thresholds in Digital Thermal Sensor + 6, 0, ECX, 0, aperfmperf, Presence of IA32_MPERF and IA32_APERF + 6, 0, ECX, 3, energ_bias, Performance-energy bias preference supported + +# Leaf 07H +# ECX == 0 +# AVX512 refers to https://en.wikipedia.org/wiki/AVX-512 +# XXX: Do we really need to enumerate each and every AVX512 sub features + + 7, 0, EBX, 0, fsgsbase, RDFSBASE/RDGSBASE/WRFSBASE/WRGSBASE supported + 7, 0, EBX, 1, tsc_adjust, TSC_ADJUST MSR supported + 7, 0, EBX, 2, sgx, Software Guard Extensions + 7, 0, EBX, 3, bmi1, BMI1 + 7, 0, EBX, 4, hle, Hardware Lock Elision + 7, 0, EBX, 5, avx2, AVX2 +# 7, 0, EBX, 6, fdp_excp_only, x87 FPU Data Pointer updated only on x87 exceptions + 7, 0, EBX, 7, smep, Supervisor-Mode Execution Prevention + 7, 0, EBX, 8, bmi2, BMI2 + 7, 0, EBX, 9, rep_movsb, Enhanced REP MOVSB/STOSB + 7, 0, EBX, 10, invpcid, INVPCID instruction + 7, 0, EBX, 11, rtm, Restricted Transactional Memory + 7, 0, EBX, 12, rdt_m, Intel RDT Monitoring capability + 7, 0, EBX, 13, depc_fpu_cs_ds, Deprecates FPU CS and FPU DS + 7, 0, EBX, 14, mpx, Memory Protection Extensions + 7, 0, EBX, 15, rdt_a, Intel RDT Allocation capability + 7, 0, EBX, 16, avx512f, AVX512 Foundation instr + 7, 0, EBX, 17, avx512dq, AVX512 Double and Quadword AVX512 instr + 7, 0, EBX, 18, rdseed, RDSEED instr + 7, 0, EBX, 19, adx, ADX instr + 7, 0, EBX, 20, smap, Supervisor Mode Access Prevention + 7, 0, EBX, 21, avx512ifma, AVX512 Integer Fused Multiply Add +# 7, 0, EBX, 22, resvd, resvd + 7, 0, EBX, 23, clflushopt, CLFLUSHOPT instr + 7, 0, EBX, 24, clwb, CLWB instr + 7, 0, EBX, 25, intel_pt, Intel Processor Trace instr + 7, 0, EBX, 26, avx512pf, Prefetch + 7, 0, EBX, 27, avx512er, AVX512 Exponent Reciproca instr + 7, 0, EBX, 28, avx512cd, AVX512 Conflict Detection instr + 7, 0, EBX, 29, sha, Intel Secure Hash Algorithm Extensions instr + 7, 0, EBX, 26, avx512bw, AVX512 Byte & Word instr + 7, 0, EBX, 28, avx512vl, AVX512 Vector Length Extentions (VL) + 7, 0, ECX, 0, prefetchwt1, X + 7, 0, ECX, 1, avx512vbmi, AVX512 Vector Byte Manipulation Instructions + 7, 0, ECX, 2, umip, User-mode Instruction Prevention + + 7, 0, ECX, 3, pku, Protection Keys for User-mode pages + 7, 0, ECX, 4, ospke, CR4 PKE set to enable protection keys +# 7, 0, ECX, 16:5, resvd, resvd + 7, 0, ECX, 21:17, mawau, The value of MAWAU used by the BNDLDX and BNDSTX instructions in 64-bit mode + 7, 0, ECX, 22, rdpid, RDPID and IA32_TSC_AUX +# 7, 0, ECX, 29:23, resvd, resvd + 7, 0, ECX, 30, sgx_lc, SGX Launch Configuration +# 7, 0, ECX, 31, resvd, resvd + +# Leaf 08H +# + + +# Leaf 09H +# Direct Cache Access (DCA) information + 9, 0, ECX, 31:0, dca_cap, The value of IA32_PLATFORM_DCA_CAP + +# Leaf 0AH +# Architectural Performance Monitoring +# +# Do we really need to print out the PMU related stuff? +# Does normal user really care about it? +# + 0xA, 0, EAX, 7:0, pmu_ver, Performance Monitoring Unit version + 0xA, 0, EAX, 15:8, pmu_gp_cnt_num, Numer of general-purose PMU counters per logical CPU + 0xA, 0, EAX, 23:16, pmu_cnt_bits, Bit wideth of PMU counter + 0xA, 0, EAX, 31:24, pmu_ebx_bits, Length of EBX bit vector to enumerate PMU events + + 0xA, 0, EBX, 0, pmu_no_core_cycle_evt, Core cycle event not available + 0xA, 0, EBX, 1, pmu_no_instr_ret_evt, Instruction retired event not available + 0xA, 0, EBX, 2, pmu_no_ref_cycle_evt, Reference cycles event not available + 0xA, 0, EBX, 3, pmu_no_llc_ref_evt, Last-level cache reference event not available + 0xA, 0, EBX, 4, pmu_no_llc_mis_evt, Last-level cache misses event not available + 0xA, 0, EBX, 5, pmu_no_br_instr_ret_evt, Branch instruction retired event not available + 0xA, 0, EBX, 6, pmu_no_br_mispredict_evt, Branch mispredict retired event not available + + 0xA, 0, ECX, 4:0, pmu_fixed_cnt_num, Performance Monitoring Unit version + 0xA, 0, ECX, 12:5, pmu_fixed_cnt_bits, Numer of PMU counters per logical CPU + +# Leaf 0BH +# Extended Topology Enumeration Leaf +# + + 0xB, 0, EAX, 4:0, id_shift, Number of bits to shift right on x2APIC ID to get a unique topology ID of the next level type + 0xB, 0, EBX, 15:0, cpu_nr, Number of logical processors at this level type + 0xB, 0, ECX, 15:8, lvl_type, 0-Invalid 1-SMT 2-Core + 0xB, 0, EDX, 31:0, x2apic_id, x2APIC ID the current logical processor + + +# Leaf 0DH +# Processor Extended State + + 0xD, 0, EAX, 0, x87, X87 state + 0xD, 0, EAX, 1, sse, SSE state + 0xD, 0, EAX, 2, avx, AVX state + 0xD, 0, EAX, 4:3, mpx, MPX state + 0xD, 0, EAX, 7:5, avx512, AVX-512 state + 0xD, 0, EAX, 9, pkru, PKRU state + + 0xD, 0, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0 + 0xD, 0, ECX, 31:0, max_sz_xsave, Maximum size (bytes) of the XSAVE/XRSTOR save area + + 0xD, 1, EAX, 0, xsaveopt, XSAVEOPT available + 0xD, 1, EAX, 1, xsavec, XSAVEC and compacted form supported + 0xD, 1, EAX, 2, xgetbv, XGETBV supported + 0xD, 1, EAX, 3, xsaves, XSAVES/XRSTORS and IA32_XSS supported + + 0xD, 1, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0 + 0xD, 1, ECX, 8, pt, PT state + 0xD, 1, ECX, 11, cet_usr, CET user state + 0xD, 1, ECX, 12, cet_supv, CET supervisor state + 0xD, 1, ECX, 13, hdc, HDC state + 0xD, 1, ECX, 16, hwp, HWP state + +# Leaf 0FH +# Intel RDT Monitoring + + 0xF, 0, EBX, 31:0, rmid_range, Maximum range (zero-based) of RMID within this physical processor of all types + 0xF, 0, EDX, 1, l3c_rdt_mon, L3 Cache RDT Monitoring supported + + 0xF, 1, ECX, 31:0, rmid_range, Maximum range (zero-based) of RMID of this types + 0xF, 1, EDX, 0, l3c_ocp_mon, L3 Cache occupancy Monitoring supported + 0xF, 1, EDX, 1, l3c_tbw_mon, L3 Cache Total Bandwidth Monitoring supported + 0xF, 1, EDX, 2, l3c_lbw_mon, L3 Cache Local Bandwidth Monitoring supported + +# Leaf 10H +# Intel RDT Allocation + + 0x10, 0, EBX, 1, l3c_rdt_alloc, L3 Cache Allocation supported + 0x10, 0, EBX, 2, l2c_rdt_alloc, L2 Cache Allocation supported + 0x10, 0, EBX, 3, mem_bw_alloc, Memory Bandwidth Allocation supported + + +# Leaf 12H +# SGX Capability +# +# Some detailed SGX features not added yet + + 0x12, 0, EAX, 0, sgx1, L3 Cache Allocation supported + 0x12, 1, EAX, 0, sgx2, L3 Cache Allocation supported + + +# Leaf 14H +# Intel Processor Tracer +# + +# Leaf 15H +# Time Stamp Counter and Nominal Core Crystal Clock Information + + 0x15, 0, EAX, 31:0, tsc_denominator, The denominator of the TSC/”core crystal clock” ratio + 0x15, 0, EBX, 31:0, tsc_numerator, The numerator of the TSC/”core crystal clock” ratio + 0x15, 0, ECX, 31:0, nom_freq, Nominal frequency of the core crystal clock in Hz + +# Leaf 16H +# Processor Frequency Information + + 0x16, 0, EAX, 15:0, cpu_base_freq, Processor Base Frequency in MHz + 0x16, 0, EBX, 15:0, cpu_max_freq, Maximum Frequency in MHz + 0x16, 0, ECX, 15:0, bus_freq, Bus (Reference) Frequency in MHz + +# Leaf 17H +# System-On-Chip Vendor Attribute + + 0x17, 0, EAX, 31:0, max_socid, Maximum input value of supported sub-leaf + 0x17, 0, EBX, 15:0, soc_vid, SOC Vendor ID + 0x17, 0, EBX, 16, std_vid, SOC Vendor ID is assigned via an industry standard scheme + 0x17, 0, ECX, 31:0, soc_pid, SOC Project ID assigned by vendor + 0x17, 0, EDX, 31:0, soc_sid, SOC Stepping ID + +# Leaf 18H +# Deterministic Address Translation Parameters + + +# Leaf 19H +# Key Locker Leaf + + +# Leaf 1AH +# Hybrid Information + + 0x1A, 0, EAX, 31:24, core_type, 20H-Intel_Atom 40H-Intel_Core + + +# Leaf 1FH +# V2 Extended Topology - A preferred superset to leaf 0BH + + +# According to SDM +# 40000000H - 4FFFFFFFH is invalid range + + +# Leaf 80000001H +# Extended Processor Signature and Feature Bits + +0x80000001, 0, ECX, 0, lahf_lm, LAHF/SAHF available in 64-bit mode +0x80000001, 0, ECX, 5, lzcnt, LZCNT +0x80000001, 0, ECX, 8, prefetchw, PREFETCHW + +0x80000001, 0, EDX, 11, sysret, SYSCALL/SYSRET supported +0x80000001, 0, EDX, 20, exec_dis, Execute Disable Bit available +0x80000001, 0, EDX, 26, 1gb_page, 1GB page supported +0x80000001, 0, EDX, 27, rdtscp, RDTSCP and IA32_TSC_AUX are available +#0x80000001, 0, EDX, 29, 64b, 64b Architecture supported + +# Leaf 80000002H/80000003H/80000004H +# Processor Brand String + +# Leaf 80000005H +# Reserved + +# Leaf 80000006H +# Extended L2 Cache Features + +0x80000006, 0, ECX, 7:0, clsize, Cache Line size in bytes +0x80000006, 0, ECX, 15:12, l2c_assoc, L2 Associativity +0x80000006, 0, ECX, 31:16, csize, Cache size in 1K units + + +# Leaf 80000007H + +0x80000007, 0, EDX, 8, nonstop_tsc, Invariant TSC available + + +# Leaf 80000008H + +0x80000008, 0, EAX, 7:0, phy_adr_bits, Physical Address Bits +0x80000008, 0, EAX, 15:8, lnr_adr_bits, Linear Address Bits +0x80000007, 0, EBX, 9, wbnoinvd, WBNOINVD + +# 0x8000001E +# EAX: Extended APIC ID +0x8000001E, 0, EAX, 31:0, extended_apic_id, Extended APIC ID +# EBX: Core Identifiers +0x8000001E, 0, EBX, 7:0, core_id, Identifies the logical core ID +0x8000001E, 0, EBX, 15:8, threads_per_core, The number of threads per core is threads_per_core + 1 +# ECX: Node Identifiers +0x8000001E, 0, ECX, 7:0, node_id, Node ID +0x8000001E, 0, ECX, 10:8, nodes_per_processor, Nodes per processor { 0: 1 node, else reserved } + +# 8000001F: AMD Secure Encryption +0x8000001F, 0, EAX, 0, sme, Secure Memory Encryption +0x8000001F, 0, EAX, 1, sev, Secure Encrypted Virtualization +0x8000001F, 0, EAX, 2, vmpgflush, VM Page Flush MSR +0x8000001F, 0, EAX, 3, seves, SEV Encrypted State +0x8000001F, 0, EBX, 5:0, c-bit, Page table bit number used to enable memory encryption +0x8000001F, 0, EBX, 11:6, mem_encrypt_physaddr_width, Reduction of physical address space in bits with SME enabled +0x8000001F, 0, ECX, 31:0, num_encrypted_guests, Maximum ASID value that may be used for an SEV-enabled guest +0x8000001F, 0, EDX, 31:0, minimum_sev_asid, Minimum ASID value that must be used for an SEV-enabled, SEV-ES-disabled guest \ No newline at end of file diff --git a/tools/arch/x86/kcpuid/kcpuid.c b/tools/arch/x86/kcpuid/kcpuid.c new file mode 100644 index 000000000000..936a3a2aad04 --- /dev/null +++ b/tools/arch/x86/kcpuid/kcpuid.c @@ -0,0 +1,657 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <stdio.h> +#include <stdbool.h> +#include <stdlib.h> +#include <string.h> +#include <getopt.h> + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) + +typedef unsigned int u32; +typedef unsigned long long u64; + +char *def_csv = "/usr/share/misc/cpuid.csv"; +char *user_csv; + + +/* Cover both single-bit flag and multiple-bits fields */ +struct bits_desc { + /* start and end bits */ + int start, end; + /* 0 or 1 for 1-bit flag */ + int value; + char simp[32]; + char detail[256]; +}; + +/* descriptor info for eax/ebx/ecx/edx */ +struct reg_desc { + /* number of valid entries */ + int nr; + struct bits_desc descs[32]; +}; + +enum { + R_EAX = 0, + R_EBX, + R_ECX, + R_EDX, + NR_REGS +}; + +struct subleaf { + u32 index; + u32 sub; + u32 eax, ebx, ecx, edx; + struct reg_desc info[NR_REGS]; +}; + +/* Represent one leaf (basic or extended) */ +struct cpuid_func { + /* + * Array of subleafs for this func, if there is no subleafs + * then the leafs[0] is the main leaf + */ + struct subleaf *leafs; + int nr; +}; + +struct cpuid_range { + /* array of main leafs */ + struct cpuid_func *funcs; + /* number of valid leafs */ + int nr; + bool is_ext; +}; + +/* + * basic: basic functions range: [0... ] + * ext: extended functions range: [0x80000000... ] + */ +struct cpuid_range *leafs_basic, *leafs_ext; + +static int num_leafs; +static bool is_amd; +static bool show_details; +static bool show_raw; +static bool show_flags_only = true; +static u32 user_index = 0xFFFFFFFF; +static u32 user_sub = 0xFFFFFFFF; +static int flines; + +static inline void cpuid(u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) +{ + /* ecx is often an input as well as an output. */ + asm volatile("cpuid" + : "=a" (*eax), + "=b" (*ebx), + "=c" (*ecx), + "=d" (*edx) + : "0" (*eax), "2" (*ecx)); +} + +static inline bool has_subleafs(u32 f) +{ + if (f == 0x7 || f == 0xd) + return true; + + if (is_amd) { + if (f == 0x8000001d) + return true; + return false; + } + + switch (f) { + case 0x4: + case 0xb: + case 0xf: + case 0x10: + case 0x14: + case 0x18: + case 0x1f: + return true; + default: + return false; + } +} + +static void leaf_print_raw(struct subleaf *leaf) +{ + if (has_subleafs(leaf->index)) { + if (leaf->sub == 0) + printf("0x%08x: subleafs:\n", leaf->index); + + printf(" %2d: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n", + leaf->sub, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx); + } else { + printf("0x%08x: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n", + leaf->index, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx); + } +} + +/* Return true is the input eax/ebx/ecx/edx are all zero */ +static bool cpuid_store(struct cpuid_range *range, u32 f, int subleaf, + u32 a, u32 b, u32 c, u32 d) +{ + struct cpuid_func *func; + struct subleaf *leaf; + int s = 0; + + if (a == 0 && b == 0 && c == 0 && d == 0) + return true; + + /* + * Cut off vendor-prefix from CPUID function as we're using it as an + * index into ->funcs. + */ + func = &range->funcs[f & 0xffff]; + + if (!func->leafs) { + func->leafs = malloc(sizeof(struct subleaf)); + if (!func->leafs) + perror("malloc func leaf"); + + func->nr = 1; + } else { + s = func->nr; + func->leafs = realloc(func->leafs, (s + 1) * sizeof(*leaf)); + if (!func->leafs) + perror("realloc f->leafs"); + + func->nr++; + } + + leaf = &func->leafs[s]; + + leaf->index = f; + leaf->sub = subleaf; + leaf->eax = a; + leaf->ebx = b; + leaf->ecx = c; + leaf->edx = d; + + return false; +} + +static void raw_dump_range(struct cpuid_range *range) +{ + u32 f; + int i; + + printf("%s Leafs :\n", range->is_ext ? "Extended" : "Basic"); + printf("================\n"); + + for (f = 0; (int)f < range->nr; f++) { + struct cpuid_func *func = &range->funcs[f]; + u32 index = f; + + if (range->is_ext) + index += 0x80000000; + + /* Skip leaf without valid items */ + if (!func->nr) + continue; + + /* First item is the main leaf, followed by all subleafs */ + for (i = 0; i < func->nr; i++) + leaf_print_raw(&func->leafs[i]); + } +} + +#define MAX_SUBLEAF_NUM 32 +struct cpuid_range *setup_cpuid_range(u32 input_eax) +{ + u32 max_func, idx_func; + int subleaf; + struct cpuid_range *range; + u32 eax, ebx, ecx, edx; + u32 f = input_eax; + int max_subleaf; + bool allzero; + + eax = input_eax; + ebx = ecx = edx = 0; + + cpuid(&eax, &ebx, &ecx, &edx); + max_func = eax; + idx_func = (max_func & 0xffff) + 1; + + range = malloc(sizeof(struct cpuid_range)); + if (!range) + perror("malloc range"); + + if (input_eax & 0x80000000) + range->is_ext = true; + else + range->is_ext = false; + + range->funcs = malloc(sizeof(struct cpuid_func) * idx_func); + if (!range->funcs) + perror("malloc range->funcs"); + + range->nr = idx_func; + memset(range->funcs, 0, sizeof(struct cpuid_func) * idx_func); + + for (; f <= max_func; f++) { + eax = f; + subleaf = ecx = 0; + + cpuid(&eax, &ebx, &ecx, &edx); + allzero = cpuid_store(range, f, subleaf, eax, ebx, ecx, edx); + if (allzero) + continue; + num_leafs++; + + if (!has_subleafs(f)) + continue; + + max_subleaf = MAX_SUBLEAF_NUM; + + /* + * Some can provide the exact number of subleafs, + * others have to be tried (0xf) + */ + if (f == 0x7 || f == 0x14 || f == 0x17 || f == 0x18) + max_subleaf = (eax & 0xff) + 1; + + if (f == 0xb) + max_subleaf = 2; + + for (subleaf = 1; subleaf < max_subleaf; subleaf++) { + eax = f; + ecx = subleaf; + + cpuid(&eax, &ebx, &ecx, &edx); + allzero = cpuid_store(range, f, subleaf, + eax, ebx, ecx, edx); + if (allzero) + continue; + num_leafs++; + } + + } + + return range; +} + +/* + * The basic row format for cpuid.csv is + * LEAF,SUBLEAF,register_name,bits,short name,long description + * + * like: + * 0, 0, EAX, 31:0, max_basic_leafs, Max input value for supported subleafs + * 1, 0, ECX, 0, sse3, Streaming SIMD Extensions 3(SSE3) + */ +static int parse_line(char *line) +{ + char *str; + int i; + struct cpuid_range *range; + struct cpuid_func *func; + struct subleaf *leaf; + u32 index; + u32 sub; + char buffer[512]; + char *buf; + /* + * Tokens: + * 1. leaf + * 2. subleaf + * 3. register + * 4. bits + * 5. short name + * 6. long detail + */ + char *tokens[6]; + struct reg_desc *reg; + struct bits_desc *bdesc; + int reg_index; + char *start, *end; + + /* Skip comments and NULL line */ + if (line[0] == '#' || line[0] == '\n') + return 0; + + strncpy(buffer, line, 511); + buffer[511] = 0; + str = buffer; + for (i = 0; i < 5; i++) { + tokens[i] = strtok(str, ","); + if (!tokens[i]) + goto err_exit; + str = NULL; + } + tokens[5] = strtok(str, "\n"); + if (!tokens[5]) + goto err_exit; + + /* index/main-leaf */ + index = strtoull(tokens[0], NULL, 0); + + if (index & 0x80000000) + range = leafs_ext; + else + range = leafs_basic; + + index &= 0x7FFFFFFF; + /* Skip line parsing for non-existing indexes */ + if ((int)index >= range->nr) + return -1; + + func = &range->funcs[index]; + + /* Return if the index has no valid item on this platform */ + if (!func->nr) + return 0; + + /* subleaf */ + sub = strtoul(tokens[1], NULL, 0); + if ((int)sub > func->nr) + return -1; + + leaf = &func->leafs[sub]; + buf = tokens[2]; + + if (strcasestr(buf, "EAX")) + reg_index = R_EAX; + else if (strcasestr(buf, "EBX")) + reg_index = R_EBX; + else if (strcasestr(buf, "ECX")) + reg_index = R_ECX; + else if (strcasestr(buf, "EDX")) + reg_index = R_EDX; + else + goto err_exit; + + reg = &leaf->info[reg_index]; + bdesc = &reg->descs[reg->nr++]; + + /* bit flag or bits field */ + buf = tokens[3]; + + end = strtok(buf, ":"); + bdesc->end = strtoul(end, NULL, 0); + bdesc->start = bdesc->end; + + /* start != NULL means it is bit fields */ + start = strtok(NULL, ":"); + if (start) + bdesc->start = strtoul(start, NULL, 0); + + strcpy(bdesc->simp, tokens[4]); + strcpy(bdesc->detail, tokens[5]); + return 0; + +err_exit: + printf("Warning: wrong line format:\n"); + printf("\tline[%d]: %s\n", flines, line); + return -1; +} + +/* Parse csv file, and construct the array of all leafs and subleafs */ +static void parse_text(void) +{ + FILE *file; + char *filename, *line = NULL; + size_t len = 0; + int ret; + + if (show_raw) + return; + + filename = user_csv ? user_csv : def_csv; + file = fopen(filename, "r"); + if (!file) { + /* Fallback to a csv in the same dir */ + file = fopen("./cpuid.csv", "r"); + } + + if (!file) { + printf("Fail to open '%s'\n", filename); + return; + } + + while (1) { + ret = getline(&line, &len, file); + flines++; + if (ret > 0) + parse_line(line); + + if (feof(file)) + break; + } + + fclose(file); +} + + +/* Decode every eax/ebx/ecx/edx */ +static void decode_bits(u32 value, struct reg_desc *rdesc) +{ + struct bits_desc *bdesc; + int start, end, i; + u32 mask; + + for (i = 0; i < rdesc->nr; i++) { + bdesc = &rdesc->descs[i]; + + start = bdesc->start; + end = bdesc->end; + if (start == end) { + /* single bit flag */ + if (value & (1 << start)) + printf("\t%-20s %s%s\n", + bdesc->simp, + show_details ? "-" : "", + show_details ? bdesc->detail : "" + ); + } else { + /* bit fields */ + if (show_flags_only) + continue; + + mask = ((u64)1 << (end - start + 1)) - 1; + printf("\t%-20s\t: 0x%-8x\t%s%s\n", + bdesc->simp, + (value >> start) & mask, + show_details ? "-" : "", + show_details ? bdesc->detail : "" + ); + } + } +} + +static void show_leaf(struct subleaf *leaf) +{ + if (!leaf) + return; + + if (show_raw) + leaf_print_raw(leaf); + + decode_bits(leaf->eax, &leaf->info[R_EAX]); + decode_bits(leaf->ebx, &leaf->info[R_EBX]); + decode_bits(leaf->ecx, &leaf->info[R_ECX]); + decode_bits(leaf->edx, &leaf->info[R_EDX]); +} + +static void show_func(struct cpuid_func *func) +{ + int i; + + if (!func) + return; + + for (i = 0; i < func->nr; i++) + show_leaf(&func->leafs[i]); +} + +static void show_range(struct cpuid_range *range) +{ + int i; + + for (i = 0; i < range->nr; i++) + show_func(&range->funcs[i]); +} + +static inline struct cpuid_func *index_to_func(u32 index) +{ + struct cpuid_range *range; + + range = (index & 0x80000000) ? leafs_ext : leafs_basic; + index &= 0x7FFFFFFF; + + if (((index & 0xFFFF) + 1) > (u32)range->nr) { + printf("ERR: invalid input index (0x%x)\n", index); + return NULL; + } + return &range->funcs[index]; +} + +static void show_info(void) +{ + struct cpuid_func *func; + + if (show_raw) { + /* Show all of the raw output of 'cpuid' instr */ + raw_dump_range(leafs_basic); + raw_dump_range(leafs_ext); + return; + } + + if (user_index != 0xFFFFFFFF) { + /* Only show specific leaf/subleaf info */ + func = index_to_func(user_index); + if (!func) + return; + + /* Dump the raw data also */ + show_raw = true; + + if (user_sub != 0xFFFFFFFF) { + if (user_sub + 1 <= (u32)func->nr) { + show_leaf(&func->leafs[user_sub]); + return; + } + + printf("ERR: invalid input subleaf (0x%x)\n", user_sub); + } + + show_func(func); + return; + } + + printf("CPU features:\n=============\n\n"); + show_range(leafs_basic); + show_range(leafs_ext); +} + +static void setup_platform_cpuid(void) +{ + u32 eax, ebx, ecx, edx; + + /* Check vendor */ + eax = ebx = ecx = edx = 0; + cpuid(&eax, &ebx, &ecx, &edx); + + /* "htuA" */ + if (ebx == 0x68747541) + is_amd = true; + + /* Setup leafs for the basic and extended range */ + leafs_basic = setup_cpuid_range(0x0); + leafs_ext = setup_cpuid_range(0x80000000); +} + +static void usage(void) +{ + printf("kcpuid [-abdfhr] [-l leaf] [-s subleaf]\n" + "\t-a|--all Show both bit flags and complex bit fields info\n" + "\t-b|--bitflags Show boolean flags only\n" + "\t-d|--detail Show details of the flag/fields (default)\n" + "\t-f|--flags Specify the cpuid csv file\n" + "\t-h|--help Show usage info\n" + "\t-l|--leaf=index Specify the leaf you want to check\n" + "\t-r|--raw Show raw cpuid data\n" + "\t-s|--subleaf=sub Specify the subleaf you want to check\n" + ); +} + +static struct option opts[] = { + { "all", no_argument, NULL, 'a' }, /* show both bit flags and fields */ + { "bitflags", no_argument, NULL, 'b' }, /* only show bit flags, default on */ + { "detail", no_argument, NULL, 'd' }, /* show detail descriptions */ + { "file", required_argument, NULL, 'f' }, /* use user's cpuid file */ + { "help", no_argument, NULL, 'h'}, /* show usage */ + { "leaf", required_argument, NULL, 'l'}, /* only check a specific leaf */ + { "raw", no_argument, NULL, 'r'}, /* show raw CPUID leaf data */ + { "subleaf", required_argument, NULL, 's'}, /* check a specific subleaf */ + { NULL, 0, NULL, 0 } +}; + +static int parse_options(int argc, char *argv[]) +{ + int c; + + while ((c = getopt_long(argc, argv, "abdf:hl:rs:", + opts, NULL)) != -1) + switch (c) { + case 'a': + show_flags_only = false; + break; + case 'b': + show_flags_only = true; + break; + case 'd': + show_details = true; + break; + case 'f': + user_csv = optarg; + break; + case 'h': + usage(); + exit(1); + break; + case 'l': + /* main leaf */ + user_index = strtoul(optarg, NULL, 0); + break; + case 'r': + show_raw = true; + break; + case 's': + /* subleaf */ + user_sub = strtoul(optarg, NULL, 0); + break; + default: + printf("%s: Invalid option '%c'\n", argv[0], optopt); + return -1; + } + + return 0; +} + +/* + * Do 4 things in turn: + * 1. Parse user options + * 2. Parse and store all the CPUID leaf data supported on this platform + * 2. Parse the csv file, while skipping leafs which are not available + * on this platform + * 3. Print leafs info based on user options + */ +int main(int argc, char *argv[]) +{ + if (parse_options(argc, argv)) + return -1; + + /* Setup the cpuid leafs of current platform */ + setup_platform_cpuid(); + + /* Read and parse the 'cpuid.csv' */ + parse_text(); + + show_info(); + return 0; +} \ No newline at end of file -- 2.30.0

1 0

[PATCH kernel-5.10] Add a kcpuid tool to show raw CPU features
by zhangyue 25 Oct '21

25 Oct '21

From: Feng Tang <feng.tang(a)intel.com> mainline inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4CMMB?from=project-issue CVE: NA ------------------------------------ End users frequently want to know what features their processor supports, independent of what the kernel supports. /proc/cpuinfo is great. It is omnipresent and since it is provided by the kernel it is always as up to date as the kernel. But, it could be ambiguous about processor features which can be disabled by the kernel at boot-time or compile-time. There are some user space tools showing more raw features, but they are not bound with kernel, and go with distros. Many end users are still using old distros with new kernels (upgraded by themselves), and may not upgrade the distros only to get a newer tool. So here arise the need for a new tool, which * shows raw CPU features read from the CPUID instruction * will be easier to update compared to existing userspace tooling (perhaps distributed like perf) * inherits "modern" kernel development process, in contrast to some of the existing userspace CPUID tools which are still being developed without git and distributed in tarballs from non-https sites. * Can produce output consistent with /proc/cpuinfo to make comparison easier. The CPUID leaf definitions are kept in an .csv file which allows for updating only that file to add support for new feature leafs. This is based on prototype code from Borislav Petkov (http://sr71.net/~dave/intel/stupid-cpuid.c) [ bp: - Massage, add #define _GNU_SOURCE to fix implicit declaration of function ‘strcasestr' warning - remove superfluous newlines - fallback to cpuid.csv in the current dir if none found - fix typos - move comments over the lines instead of sideways. ] Originally-from: Borislav Petkov <bp(a)alien8.de> Suggested-by: Dave Hansen <dave.hansen(a)intel.com> Suggested-by: Borislav Petkov <bp(a)alien8.de> Signed-off-by: Feng Tang <feng.tang(a)intel.com> Signed-off-by: Borislav Petkov <bp(a)suse.de> Signed-off-by: zhangyue <zhangyue1(a)kylinos.cn> --- tools/arch/x86/kcpuid/Makefile | 24 ++ tools/arch/x86/kcpuid/cpuid.csv | 400 +++++++++++++++++++ tools/arch/x86/kcpuid/kcpuid.c | 657 ++++++++++++++++++++++++++++++++ 3 files changed, 1081 insertions(+) create mode 100644 tools/arch/x86/kcpuid/Makefile create mode 100644 tools/arch/x86/kcpuid/cpuid.csv create mode 100644 tools/arch/x86/kcpuid/kcpuid.c diff --git a/tools/arch/x86/kcpuid/Makefile b/tools/arch/x86/kcpuid/Makefile new file mode 100644 index 000000000000..a2f1e855092c --- /dev/null +++ b/tools/arch/x86/kcpuid/Makefile @@ -0,0 +1,24 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for x86/kcpuid tool + +kcpuid : kcpuid.c + +CFLAGS = -Wextra + +BINDIR ?= /usr/sbin + +HWDATADIR ?= /usr/share/misc/ + +override CFLAGS += -O2 -Wall -I../../../include + +%: %.c + $(CC) $(CFLAGS) -o $@ $< $(LDFLAGS) + +.PHONY : clean +clean : + @rm -f kcpuid + +install : kcpuid + install -d $(DESTDIR)$(BINDIR) + install -m 755 -p kcpuid $(DESTDIR)$(BINDIR)/kcpuid + install -m 444 -p cpuid.csv $(HWDATADIR)/cpuid.csv diff --git a/tools/arch/x86/kcpuid/cpuid.csv b/tools/arch/x86/kcpuid/cpuid.csv new file mode 100644 index 000000000000..e422fad9a98e --- /dev/null +++ b/tools/arch/x86/kcpuid/cpuid.csv @@ -0,0 +1,400 @@ +# The basic row format is: +# LEAF, SUBLEAF, register_name, bits, short_name, long_description + +# Leaf 00H + 0, 0, EAX, 31:0, max_basic_leafs, Max input value for supported subleafs + +# Leaf 01H + 1, 0, EAX, 3:0, stepping, Stepping ID + 1, 0, EAX, 7:4, model, Model + 1, 0, EAX, 11:8, family, Family ID + 1, 0, EAX, 13:12, processor, Processor Type + 1, 0, EAX, 19:16, model_ext, Extended Model ID + 1, 0, EAX, 27:20, family_ext, Extended Family ID + + 1, 0, EBX, 7:0, brand, Brand Index + 1, 0, EBX, 15:8, clflush_size, CLFLUSH line size (value * 8) in bytes + 1, 0, EBX, 23:16, max_cpu_id, Maxim number of addressable logic cpu in this package + 1, 0, EBX, 31:24, apic_id, Initial APIC ID + + 1, 0, ECX, 0, sse3, Streaming SIMD Extensions 3(SSE3) + 1, 0, ECX, 1, pclmulqdq, PCLMULQDQ instruction supported + 1, 0, ECX, 2, dtes64, DS area uses 64-bit layout + 1, 0, ECX, 3, mwait, MONITOR/MWAIT supported + 1, 0, ECX, 4, ds_cpl, CPL Qualified Debug Store which allows for branch message storage qualified by CPL + 1, 0, ECX, 5, vmx, Virtual Machine Extensions supported + 1, 0, ECX, 6, smx, Safer Mode Extension supported + 1, 0, ECX, 7, eist, Enhanced Intel SpeedStep Technology + 1, 0, ECX, 8, tm2, Thermal Monitor 2 + 1, 0, ECX, 9, ssse3, Supplemental Streaming SIMD Extensions 3 (SSSE3) + 1, 0, ECX, 10, l1_ctx_id, L1 data cache could be set to either adaptive mode or shared mode (check IA32_MISC_ENABLE bit 24 definition) + 1, 0, ECX, 11, sdbg, IA32_DEBUG_INTERFACE MSR for silicon debug supported + 1, 0, ECX, 12, fma, FMA extensions using YMM state supported + 1, 0, ECX, 13, cmpxchg16b, 'CMPXCHG16B - Compare and Exchange Bytes' supported + 1, 0, ECX, 14, xtpr_update, xTPR Update Control supported + 1, 0, ECX, 15, pdcm, Perfmon and Debug Capability present + 1, 0, ECX, 17, pcid, Process-Context Identifiers feature present + 1, 0, ECX, 18, dca, Prefetching data from a memory mapped device supported + 1, 0, ECX, 19, sse4_1, SSE4.1 feature present + 1, 0, ECX, 20, sse4_2, SSE4.2 feature present + 1, 0, ECX, 21, x2apic, x2APIC supported + 1, 0, ECX, 22, movbe, MOVBE instruction supported + 1, 0, ECX, 23, popcnt, POPCNT instruction supported + 1, 0, ECX, 24, tsc_deadline_timer, LAPIC supports one-shot operation using a TSC deadline value + 1, 0, ECX, 25, aesni, AESNI instruction supported + 1, 0, ECX, 26, xsave, XSAVE/XRSTOR processor extended states (XSETBV/XGETBV/XCR0) + 1, 0, ECX, 27, osxsave, OS has set CR4.OSXSAVE bit to enable XSETBV/XGETBV/XCR0 + 1, 0, ECX, 28, avx, AVX instruction supported + 1, 0, ECX, 29, f16c, 16-bit floating-point conversion instruction supported + 1, 0, ECX, 30, rdrand, RDRAND instruction supported + + 1, 0, EDX, 0, fpu, x87 FPU on chip + 1, 0, EDX, 1, vme, Virtual-8086 Mode Enhancement + 1, 0, EDX, 2, de, Debugging Extensions + 1, 0, EDX, 3, pse, Page Size Extensions + 1, 0, EDX, 4, tsc, Time Stamp Counter + 1, 0, EDX, 5, msr, RDMSR and WRMSR Support + 1, 0, EDX, 6, pae, Physical Address Extensions + 1, 0, EDX, 7, mce, Machine Check Exception + 1, 0, EDX, 8, cx8, CMPXCHG8B instr + 1, 0, EDX, 9, apic, APIC on Chip + 1, 0, EDX, 11, sep, SYSENTER and SYSEXIT instrs + 1, 0, EDX, 12, mtrr, Memory Type Range Registers + 1, 0, EDX, 13, pge, Page Global Bit + 1, 0, EDX, 14, mca, Machine Check Architecture + 1, 0, EDX, 15, cmov, Conditional Move Instrs + 1, 0, EDX, 16, pat, Page Attribute Table + 1, 0, EDX, 17, pse36, 36-Bit Page Size Extension + 1, 0, EDX, 18, psn, Processor Serial Number + 1, 0, EDX, 19, clflush, CLFLUSH instr +# 1, 0, EDX, 20, + 1, 0, EDX, 21, ds, Debug Store + 1, 0, EDX, 22, acpi, Thermal Monitor and Software Controlled Clock Facilities + 1, 0, EDX, 23, mmx, Intel MMX Technology + 1, 0, EDX, 24, fxsr, XSAVE and FXRSTOR Instrs + 1, 0, EDX, 25, sse, SSE + 1, 0, EDX, 26, sse2, SSE2 + 1, 0, EDX, 27, ss, Self Snoop + 1, 0, EDX, 28, hit, Max APIC IDs + 1, 0, EDX, 29, tm, Thermal Monitor +# 1, 0, EDX, 30, + 1, 0, EDX, 31, pbe, Pending Break Enable + +# Leaf 02H +# cache and TLB descriptor info + +# Leaf 03H +# Precessor Serial Number, introduced on Pentium III, not valid for +# latest models + +# Leaf 04H +# thread/core and cache topology + 4, 0, EAX, 4:0, cache_type, Cache type like instr/data or unified + 4, 0, EAX, 7:5, cache_level, Cache Level (starts at 1) + 4, 0, EAX, 8, cache_self_init, Cache Self Initialization + 4, 0, EAX, 9, fully_associate, Fully Associative cache +# 4, 0, EAX, 13:10, resvd, resvd + 4, 0, EAX, 25:14, max_logical_id, Max number of addressable IDs for logical processors sharing the cache + 4, 0, EAX, 31:26, max_phy_id, Max number of addressable IDs for processors in phy package + + 4, 0, EBX, 11:0, cache_linesize, Size of a cache line in bytes + 4, 0, EBX, 21:12, cache_partition, Physical Line partitions + 4, 0, EBX, 31:22, cache_ways, Ways of associativity + 4, 0, ECX, 31:0, cache_sets, Number of Sets - 1 + 4, 0, EDX, 0, c_wbinvd, 1 means WBINVD/INVD is not ganranteed to act upon lower level caches of non-originating threads sharing this cache + 4, 0, EDX, 1, c_incl, Whether cache is inclusive of lower cache level + 4, 0, EDX, 2, c_comp_index, Complex Cache Indexing + +# Leaf 05H +# MONITOR/MWAIT + 5, 0, EAX, 15:0, min_mon_size, Smallest monitor line size in bytes + 5, 0, EBX, 15:0, max_mon_size, Largest monitor line size in bytes + 5, 0, ECX, 0, mwait_ext, Enum of Monitor-Mwait extensions supported + 5, 0, ECX, 1, mwait_irq_break, Largest monitor line size in bytes + 5, 0, EDX, 3:0, c0_sub_stats, Number of C0* sub C-states supported using MWAIT + 5, 0, EDX, 7:4, c1_sub_stats, Number of C1* sub C-states supported using MWAIT + 5, 0, EDX, 11:8, c2_sub_stats, Number of C2* sub C-states supported using MWAIT + 5, 0, EDX, 15:12, c3_sub_stats, Number of C3* sub C-states supported using MWAIT + 5, 0, EDX, 19:16, c4_sub_stats, Number of C4* sub C-states supported using MWAIT + 5, 0, EDX, 23:20, c5_sub_stats, Number of C5* sub C-states supported using MWAIT + 5, 0, EDX, 27:24, c6_sub_stats, Number of C6* sub C-states supported using MWAIT + 5, 0, EDX, 31:28, c7_sub_stats, Number of C7* sub C-states supported using MWAIT + +# Leaf 06H +# Thermal & Power Management + + 6, 0, EAX, 0, dig_temp, Digital temperature sensor supported + 6, 0, EAX, 1, turbo, Intel Turbo Boost + 6, 0, EAX, 2, arat, Always running APIC timer +# 6, 0, EAX, 3, resv, Reserved + 6, 0, EAX, 4, pln, Power limit notifications supported + 6, 0, EAX, 5, ecmd, Clock modulation duty cycle extension supported + 6, 0, EAX, 6, ptm, Package thermal management supported + 6, 0, EAX, 7, hwp, HWP base register + 6, 0, EAX, 8, hwp_notify, HWP notification + 6, 0, EAX, 9, hwp_act_window, HWP activity window + 6, 0, EAX, 10, hwp_energy, HWP energy performance preference + 6, 0, EAX, 11, hwp_pkg_req, HWP package level request +# 6, 0, EAX, 12, resv, Reserved + 6, 0, EAX, 13, hdc, HDC base registers supported + 6, 0, EAX, 14, turbo3, Turbo Boost Max 3.0 + 6, 0, EAX, 15, hwp_cap, Highest Performance change supported + 6, 0, EAX, 16, hwp_peci, HWP PECI override is supported + 6, 0, EAX, 17, hwp_flex, Flexible HWP is supported + 6, 0, EAX, 18, hwp_fast, Fast access mode for the IA32_HWP_REQUEST MSR is supported +# 6, 0, EAX, 19, resv, Reserved + 6, 0, EAX, 20, hwp_ignr, Ignoring Idle Logical Processor HWP request is supported + + 6, 0, EBX, 3:0, therm_irq_thresh, Number of Interrupt Thresholds in Digital Thermal Sensor + 6, 0, ECX, 0, aperfmperf, Presence of IA32_MPERF and IA32_APERF + 6, 0, ECX, 3, energ_bias, Performance-energy bias preference supported + +# Leaf 07H +# ECX == 0 +# AVX512 refers to https://en.wikipedia.org/wiki/AVX-512 +# XXX: Do we really need to enumerate each and every AVX512 sub features + + 7, 0, EBX, 0, fsgsbase, RDFSBASE/RDGSBASE/WRFSBASE/WRGSBASE supported + 7, 0, EBX, 1, tsc_adjust, TSC_ADJUST MSR supported + 7, 0, EBX, 2, sgx, Software Guard Extensions + 7, 0, EBX, 3, bmi1, BMI1 + 7, 0, EBX, 4, hle, Hardware Lock Elision + 7, 0, EBX, 5, avx2, AVX2 +# 7, 0, EBX, 6, fdp_excp_only, x87 FPU Data Pointer updated only on x87 exceptions + 7, 0, EBX, 7, smep, Supervisor-Mode Execution Prevention + 7, 0, EBX, 8, bmi2, BMI2 + 7, 0, EBX, 9, rep_movsb, Enhanced REP MOVSB/STOSB + 7, 0, EBX, 10, invpcid, INVPCID instruction + 7, 0, EBX, 11, rtm, Restricted Transactional Memory + 7, 0, EBX, 12, rdt_m, Intel RDT Monitoring capability + 7, 0, EBX, 13, depc_fpu_cs_ds, Deprecates FPU CS and FPU DS + 7, 0, EBX, 14, mpx, Memory Protection Extensions + 7, 0, EBX, 15, rdt_a, Intel RDT Allocation capability + 7, 0, EBX, 16, avx512f, AVX512 Foundation instr + 7, 0, EBX, 17, avx512dq, AVX512 Double and Quadword AVX512 instr + 7, 0, EBX, 18, rdseed, RDSEED instr + 7, 0, EBX, 19, adx, ADX instr + 7, 0, EBX, 20, smap, Supervisor Mode Access Prevention + 7, 0, EBX, 21, avx512ifma, AVX512 Integer Fused Multiply Add +# 7, 0, EBX, 22, resvd, resvd + 7, 0, EBX, 23, clflushopt, CLFLUSHOPT instr + 7, 0, EBX, 24, clwb, CLWB instr + 7, 0, EBX, 25, intel_pt, Intel Processor Trace instr + 7, 0, EBX, 26, avx512pf, Prefetch + 7, 0, EBX, 27, avx512er, AVX512 Exponent Reciproca instr + 7, 0, EBX, 28, avx512cd, AVX512 Conflict Detection instr + 7, 0, EBX, 29, sha, Intel Secure Hash Algorithm Extensions instr + 7, 0, EBX, 26, avx512bw, AVX512 Byte & Word instr + 7, 0, EBX, 28, avx512vl, AVX512 Vector Length Extentions (VL) + 7, 0, ECX, 0, prefetchwt1, X + 7, 0, ECX, 1, avx512vbmi, AVX512 Vector Byte Manipulation Instructions + 7, 0, ECX, 2, umip, User-mode Instruction Prevention + + 7, 0, ECX, 3, pku, Protection Keys for User-mode pages + 7, 0, ECX, 4, ospke, CR4 PKE set to enable protection keys +# 7, 0, ECX, 16:5, resvd, resvd + 7, 0, ECX, 21:17, mawau, The value of MAWAU used by the BNDLDX and BNDSTX instructions in 64-bit mode + 7, 0, ECX, 22, rdpid, RDPID and IA32_TSC_AUX +# 7, 0, ECX, 29:23, resvd, resvd + 7, 0, ECX, 30, sgx_lc, SGX Launch Configuration +# 7, 0, ECX, 31, resvd, resvd + +# Leaf 08H +# + + +# Leaf 09H +# Direct Cache Access (DCA) information + 9, 0, ECX, 31:0, dca_cap, The value of IA32_PLATFORM_DCA_CAP + +# Leaf 0AH +# Architectural Performance Monitoring +# +# Do we really need to print out the PMU related stuff? +# Does normal user really care about it? +# + 0xA, 0, EAX, 7:0, pmu_ver, Performance Monitoring Unit version + 0xA, 0, EAX, 15:8, pmu_gp_cnt_num, Numer of general-purose PMU counters per logical CPU + 0xA, 0, EAX, 23:16, pmu_cnt_bits, Bit wideth of PMU counter + 0xA, 0, EAX, 31:24, pmu_ebx_bits, Length of EBX bit vector to enumerate PMU events + + 0xA, 0, EBX, 0, pmu_no_core_cycle_evt, Core cycle event not available + 0xA, 0, EBX, 1, pmu_no_instr_ret_evt, Instruction retired event not available + 0xA, 0, EBX, 2, pmu_no_ref_cycle_evt, Reference cycles event not available + 0xA, 0, EBX, 3, pmu_no_llc_ref_evt, Last-level cache reference event not available + 0xA, 0, EBX, 4, pmu_no_llc_mis_evt, Last-level cache misses event not available + 0xA, 0, EBX, 5, pmu_no_br_instr_ret_evt, Branch instruction retired event not available + 0xA, 0, EBX, 6, pmu_no_br_mispredict_evt, Branch mispredict retired event not available + + 0xA, 0, ECX, 4:0, pmu_fixed_cnt_num, Performance Monitoring Unit version + 0xA, 0, ECX, 12:5, pmu_fixed_cnt_bits, Numer of PMU counters per logical CPU + +# Leaf 0BH +# Extended Topology Enumeration Leaf +# + + 0xB, 0, EAX, 4:0, id_shift, Number of bits to shift right on x2APIC ID to get a unique topology ID of the next level type + 0xB, 0, EBX, 15:0, cpu_nr, Number of logical processors at this level type + 0xB, 0, ECX, 15:8, lvl_type, 0-Invalid 1-SMT 2-Core + 0xB, 0, EDX, 31:0, x2apic_id, x2APIC ID the current logical processor + + +# Leaf 0DH +# Processor Extended State + + 0xD, 0, EAX, 0, x87, X87 state + 0xD, 0, EAX, 1, sse, SSE state + 0xD, 0, EAX, 2, avx, AVX state + 0xD, 0, EAX, 4:3, mpx, MPX state + 0xD, 0, EAX, 7:5, avx512, AVX-512 state + 0xD, 0, EAX, 9, pkru, PKRU state + + 0xD, 0, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0 + 0xD, 0, ECX, 31:0, max_sz_xsave, Maximum size (bytes) of the XSAVE/XRSTOR save area + + 0xD, 1, EAX, 0, xsaveopt, XSAVEOPT available + 0xD, 1, EAX, 1, xsavec, XSAVEC and compacted form supported + 0xD, 1, EAX, 2, xgetbv, XGETBV supported + 0xD, 1, EAX, 3, xsaves, XSAVES/XRSTORS and IA32_XSS supported + + 0xD, 1, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0 + 0xD, 1, ECX, 8, pt, PT state + 0xD, 1, ECX, 11, cet_usr, CET user state + 0xD, 1, ECX, 12, cet_supv, CET supervisor state + 0xD, 1, ECX, 13, hdc, HDC state + 0xD, 1, ECX, 16, hwp, HWP state + +# Leaf 0FH +# Intel RDT Monitoring + + 0xF, 0, EBX, 31:0, rmid_range, Maximum range (zero-based) of RMID within this physical processor of all types + 0xF, 0, EDX, 1, l3c_rdt_mon, L3 Cache RDT Monitoring supported + + 0xF, 1, ECX, 31:0, rmid_range, Maximum range (zero-based) of RMID of this types + 0xF, 1, EDX, 0, l3c_ocp_mon, L3 Cache occupancy Monitoring supported + 0xF, 1, EDX, 1, l3c_tbw_mon, L3 Cache Total Bandwidth Monitoring supported + 0xF, 1, EDX, 2, l3c_lbw_mon, L3 Cache Local Bandwidth Monitoring supported + +# Leaf 10H +# Intel RDT Allocation + + 0x10, 0, EBX, 1, l3c_rdt_alloc, L3 Cache Allocation supported + 0x10, 0, EBX, 2, l2c_rdt_alloc, L2 Cache Allocation supported + 0x10, 0, EBX, 3, mem_bw_alloc, Memory Bandwidth Allocation supported + + +# Leaf 12H +# SGX Capability +# +# Some detailed SGX features not added yet + + 0x12, 0, EAX, 0, sgx1, L3 Cache Allocation supported + 0x12, 1, EAX, 0, sgx2, L3 Cache Allocation supported + + +# Leaf 14H +# Intel Processor Tracer +# + +# Leaf 15H +# Time Stamp Counter and Nominal Core Crystal Clock Information + + 0x15, 0, EAX, 31:0, tsc_denominator, The denominator of the TSC/”core crystal clock” ratio + 0x15, 0, EBX, 31:0, tsc_numerator, The numerator of the TSC/”core crystal clock” ratio + 0x15, 0, ECX, 31:0, nom_freq, Nominal frequency of the core crystal clock in Hz + +# Leaf 16H +# Processor Frequency Information + + 0x16, 0, EAX, 15:0, cpu_base_freq, Processor Base Frequency in MHz + 0x16, 0, EBX, 15:0, cpu_max_freq, Maximum Frequency in MHz + 0x16, 0, ECX, 15:0, bus_freq, Bus (Reference) Frequency in MHz + +# Leaf 17H +# System-On-Chip Vendor Attribute + + 0x17, 0, EAX, 31:0, max_socid, Maximum input value of supported sub-leaf + 0x17, 0, EBX, 15:0, soc_vid, SOC Vendor ID + 0x17, 0, EBX, 16, std_vid, SOC Vendor ID is assigned via an industry standard scheme + 0x17, 0, ECX, 31:0, soc_pid, SOC Project ID assigned by vendor + 0x17, 0, EDX, 31:0, soc_sid, SOC Stepping ID + +# Leaf 18H +# Deterministic Address Translation Parameters + + +# Leaf 19H +# Key Locker Leaf + + +# Leaf 1AH +# Hybrid Information + + 0x1A, 0, EAX, 31:24, core_type, 20H-Intel_Atom 40H-Intel_Core + + +# Leaf 1FH +# V2 Extended Topology - A preferred superset to leaf 0BH + + +# According to SDM +# 40000000H - 4FFFFFFFH is invalid range + + +# Leaf 80000001H +# Extended Processor Signature and Feature Bits + +0x80000001, 0, ECX, 0, lahf_lm, LAHF/SAHF available in 64-bit mode +0x80000001, 0, ECX, 5, lzcnt, LZCNT +0x80000001, 0, ECX, 8, prefetchw, PREFETCHW + +0x80000001, 0, EDX, 11, sysret, SYSCALL/SYSRET supported +0x80000001, 0, EDX, 20, exec_dis, Execute Disable Bit available +0x80000001, 0, EDX, 26, 1gb_page, 1GB page supported +0x80000001, 0, EDX, 27, rdtscp, RDTSCP and IA32_TSC_AUX are available +#0x80000001, 0, EDX, 29, 64b, 64b Architecture supported + +# Leaf 80000002H/80000003H/80000004H +# Processor Brand String + +# Leaf 80000005H +# Reserved + +# Leaf 80000006H +# Extended L2 Cache Features + +0x80000006, 0, ECX, 7:0, clsize, Cache Line size in bytes +0x80000006, 0, ECX, 15:12, l2c_assoc, L2 Associativity +0x80000006, 0, ECX, 31:16, csize, Cache size in 1K units + + +# Leaf 80000007H + +0x80000007, 0, EDX, 8, nonstop_tsc, Invariant TSC available + + +# Leaf 80000008H + +0x80000008, 0, EAX, 7:0, phy_adr_bits, Physical Address Bits +0x80000008, 0, EAX, 15:8, lnr_adr_bits, Linear Address Bits +0x80000007, 0, EBX, 9, wbnoinvd, WBNOINVD + +# 0x8000001E +# EAX: Extended APIC ID +0x8000001E, 0, EAX, 31:0, extended_apic_id, Extended APIC ID +# EBX: Core Identifiers +0x8000001E, 0, EBX, 7:0, core_id, Identifies the logical core ID +0x8000001E, 0, EBX, 15:8, threads_per_core, The number of threads per core is threads_per_core + 1 +# ECX: Node Identifiers +0x8000001E, 0, ECX, 7:0, node_id, Node ID +0x8000001E, 0, ECX, 10:8, nodes_per_processor, Nodes per processor { 0: 1 node, else reserved } + +# 8000001F: AMD Secure Encryption +0x8000001F, 0, EAX, 0, sme, Secure Memory Encryption +0x8000001F, 0, EAX, 1, sev, Secure Encrypted Virtualization +0x8000001F, 0, EAX, 2, vmpgflush, VM Page Flush MSR +0x8000001F, 0, EAX, 3, seves, SEV Encrypted State +0x8000001F, 0, EBX, 5:0, c-bit, Page table bit number used to enable memory encryption +0x8000001F, 0, EBX, 11:6, mem_encrypt_physaddr_width, Reduction of physical address space in bits with SME enabled +0x8000001F, 0, ECX, 31:0, num_encrypted_guests, Maximum ASID value that may be used for an SEV-enabled guest +0x8000001F, 0, EDX, 31:0, minimum_sev_asid, Minimum ASID value that must be used for an SEV-enabled, SEV-ES-disabled guest \ No newline at end of file diff --git a/tools/arch/x86/kcpuid/kcpuid.c b/tools/arch/x86/kcpuid/kcpuid.c new file mode 100644 index 000000000000..936a3a2aad04 --- /dev/null +++ b/tools/arch/x86/kcpuid/kcpuid.c @@ -0,0 +1,657 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <stdio.h> +#include <stdbool.h> +#include <stdlib.h> +#include <string.h> +#include <getopt.h> + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) + +typedef unsigned int u32; +typedef unsigned long long u64; + +char *def_csv = "/usr/share/misc/cpuid.csv"; +char *user_csv; + + +/* Cover both single-bit flag and multiple-bits fields */ +struct bits_desc { + /* start and end bits */ + int start, end; + /* 0 or 1 for 1-bit flag */ + int value; + char simp[32]; + char detail[256]; +}; + +/* descriptor info for eax/ebx/ecx/edx */ +struct reg_desc { + /* number of valid entries */ + int nr; + struct bits_desc descs[32]; +}; + +enum { + R_EAX = 0, + R_EBX, + R_ECX, + R_EDX, + NR_REGS +}; + +struct subleaf { + u32 index; + u32 sub; + u32 eax, ebx, ecx, edx; + struct reg_desc info[NR_REGS]; +}; + +/* Represent one leaf (basic or extended) */ +struct cpuid_func { + /* + * Array of subleafs for this func, if there is no subleafs + * then the leafs[0] is the main leaf + */ + struct subleaf *leafs; + int nr; +}; + +struct cpuid_range { + /* array of main leafs */ + struct cpuid_func *funcs; + /* number of valid leafs */ + int nr; + bool is_ext; +}; + +/* + * basic: basic functions range: [0... ] + * ext: extended functions range: [0x80000000... ] + */ +struct cpuid_range *leafs_basic, *leafs_ext; + +static int num_leafs; +static bool is_amd; +static bool show_details; +static bool show_raw; +static bool show_flags_only = true; +static u32 user_index = 0xFFFFFFFF; +static u32 user_sub = 0xFFFFFFFF; +static int flines; + +static inline void cpuid(u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) +{ + /* ecx is often an input as well as an output. */ + asm volatile("cpuid" + : "=a" (*eax), + "=b" (*ebx), + "=c" (*ecx), + "=d" (*edx) + : "0" (*eax), "2" (*ecx)); +} + +static inline bool has_subleafs(u32 f) +{ + if (f == 0x7 || f == 0xd) + return true; + + if (is_amd) { + if (f == 0x8000001d) + return true; + return false; + } + + switch (f) { + case 0x4: + case 0xb: + case 0xf: + case 0x10: + case 0x14: + case 0x18: + case 0x1f: + return true; + default: + return false; + } +} + +static void leaf_print_raw(struct subleaf *leaf) +{ + if (has_subleafs(leaf->index)) { + if (leaf->sub == 0) + printf("0x%08x: subleafs:\n", leaf->index); + + printf(" %2d: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n", + leaf->sub, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx); + } else { + printf("0x%08x: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n", + leaf->index, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx); + } +} + +/* Return true is the input eax/ebx/ecx/edx are all zero */ +static bool cpuid_store(struct cpuid_range *range, u32 f, int subleaf, + u32 a, u32 b, u32 c, u32 d) +{ + struct cpuid_func *func; + struct subleaf *leaf; + int s = 0; + + if (a == 0 && b == 0 && c == 0 && d == 0) + return true; + + /* + * Cut off vendor-prefix from CPUID function as we're using it as an + * index into ->funcs. + */ + func = &range->funcs[f & 0xffff]; + + if (!func->leafs) { + func->leafs = malloc(sizeof(struct subleaf)); + if (!func->leafs) + perror("malloc func leaf"); + + func->nr = 1; + } else { + s = func->nr; + func->leafs = realloc(func->leafs, (s + 1) * sizeof(*leaf)); + if (!func->leafs) + perror("realloc f->leafs"); + + func->nr++; + } + + leaf = &func->leafs[s]; + + leaf->index = f; + leaf->sub = subleaf; + leaf->eax = a; + leaf->ebx = b; + leaf->ecx = c; + leaf->edx = d; + + return false; +} + +static void raw_dump_range(struct cpuid_range *range) +{ + u32 f; + int i; + + printf("%s Leafs :\n", range->is_ext ? "Extended" : "Basic"); + printf("================\n"); + + for (f = 0; (int)f < range->nr; f++) { + struct cpuid_func *func = &range->funcs[f]; + u32 index = f; + + if (range->is_ext) + index += 0x80000000; + + /* Skip leaf without valid items */ + if (!func->nr) + continue; + + /* First item is the main leaf, followed by all subleafs */ + for (i = 0; i < func->nr; i++) + leaf_print_raw(&func->leafs[i]); + } +} + +#define MAX_SUBLEAF_NUM 32 +struct cpuid_range *setup_cpuid_range(u32 input_eax) +{ + u32 max_func, idx_func; + int subleaf; + struct cpuid_range *range; + u32 eax, ebx, ecx, edx; + u32 f = input_eax; + int max_subleaf; + bool allzero; + + eax = input_eax; + ebx = ecx = edx = 0; + + cpuid(&eax, &ebx, &ecx, &edx); + max_func = eax; + idx_func = (max_func & 0xffff) + 1; + + range = malloc(sizeof(struct cpuid_range)); + if (!range) + perror("malloc range"); + + if (input_eax & 0x80000000) + range->is_ext = true; + else + range->is_ext = false; + + range->funcs = malloc(sizeof(struct cpuid_func) * idx_func); + if (!range->funcs) + perror("malloc range->funcs"); + + range->nr = idx_func; + memset(range->funcs, 0, sizeof(struct cpuid_func) * idx_func); + + for (; f <= max_func; f++) { + eax = f; + subleaf = ecx = 0; + + cpuid(&eax, &ebx, &ecx, &edx); + allzero = cpuid_store(range, f, subleaf, eax, ebx, ecx, edx); + if (allzero) + continue; + num_leafs++; + + if (!has_subleafs(f)) + continue; + + max_subleaf = MAX_SUBLEAF_NUM; + + /* + * Some can provide the exact number of subleafs, + * others have to be tried (0xf) + */ + if (f == 0x7 || f == 0x14 || f == 0x17 || f == 0x18) + max_subleaf = (eax & 0xff) + 1; + + if (f == 0xb) + max_subleaf = 2; + + for (subleaf = 1; subleaf < max_subleaf; subleaf++) { + eax = f; + ecx = subleaf; + + cpuid(&eax, &ebx, &ecx, &edx); + allzero = cpuid_store(range, f, subleaf, + eax, ebx, ecx, edx); + if (allzero) + continue; + num_leafs++; + } + + } + + return range; +} + +/* + * The basic row format for cpuid.csv is + * LEAF,SUBLEAF,register_name,bits,short name,long description + * + * like: + * 0, 0, EAX, 31:0, max_basic_leafs, Max input value for supported subleafs + * 1, 0, ECX, 0, sse3, Streaming SIMD Extensions 3(SSE3) + */ +static int parse_line(char *line) +{ + char *str; + int i; + struct cpuid_range *range; + struct cpuid_func *func; + struct subleaf *leaf; + u32 index; + u32 sub; + char buffer[512]; + char *buf; + /* + * Tokens: + * 1. leaf + * 2. subleaf + * 3. register + * 4. bits + * 5. short name + * 6. long detail + */ + char *tokens[6]; + struct reg_desc *reg; + struct bits_desc *bdesc; + int reg_index; + char *start, *end; + + /* Skip comments and NULL line */ + if (line[0] == '#' || line[0] == '\n') + return 0; + + strncpy(buffer, line, 511); + buffer[511] = 0; + str = buffer; + for (i = 0; i < 5; i++) { + tokens[i] = strtok(str, ","); + if (!tokens[i]) + goto err_exit; + str = NULL; + } + tokens[5] = strtok(str, "\n"); + if (!tokens[5]) + goto err_exit; + + /* index/main-leaf */ + index = strtoull(tokens[0], NULL, 0); + + if (index & 0x80000000) + range = leafs_ext; + else + range = leafs_basic; + + index &= 0x7FFFFFFF; + /* Skip line parsing for non-existing indexes */ + if ((int)index >= range->nr) + return -1; + + func = &range->funcs[index]; + + /* Return if the index has no valid item on this platform */ + if (!func->nr) + return 0; + + /* subleaf */ + sub = strtoul(tokens[1], NULL, 0); + if ((int)sub > func->nr) + return -1; + + leaf = &func->leafs[sub]; + buf = tokens[2]; + + if (strcasestr(buf, "EAX")) + reg_index = R_EAX; + else if (strcasestr(buf, "EBX")) + reg_index = R_EBX; + else if (strcasestr(buf, "ECX")) + reg_index = R_ECX; + else if (strcasestr(buf, "EDX")) + reg_index = R_EDX; + else + goto err_exit; + + reg = &leaf->info[reg_index]; + bdesc = &reg->descs[reg->nr++]; + + /* bit flag or bits field */ + buf = tokens[3]; + + end = strtok(buf, ":"); + bdesc->end = strtoul(end, NULL, 0); + bdesc->start = bdesc->end; + + /* start != NULL means it is bit fields */ + start = strtok(NULL, ":"); + if (start) + bdesc->start = strtoul(start, NULL, 0); + + strcpy(bdesc->simp, tokens[4]); + strcpy(bdesc->detail, tokens[5]); + return 0; + +err_exit: + printf("Warning: wrong line format:\n"); + printf("\tline[%d]: %s\n", flines, line); + return -1; +} + +/* Parse csv file, and construct the array of all leafs and subleafs */ +static void parse_text(void) +{ + FILE *file; + char *filename, *line = NULL; + size_t len = 0; + int ret; + + if (show_raw) + return; + + filename = user_csv ? user_csv : def_csv; + file = fopen(filename, "r"); + if (!file) { + /* Fallback to a csv in the same dir */ + file = fopen("./cpuid.csv", "r"); + } + + if (!file) { + printf("Fail to open '%s'\n", filename); + return; + } + + while (1) { + ret = getline(&line, &len, file); + flines++; + if (ret > 0) + parse_line(line); + + if (feof(file)) + break; + } + + fclose(file); +} + + +/* Decode every eax/ebx/ecx/edx */ +static void decode_bits(u32 value, struct reg_desc *rdesc) +{ + struct bits_desc *bdesc; + int start, end, i; + u32 mask; + + for (i = 0; i < rdesc->nr; i++) { + bdesc = &rdesc->descs[i]; + + start = bdesc->start; + end = bdesc->end; + if (start == end) { + /* single bit flag */ + if (value & (1 << start)) + printf("\t%-20s %s%s\n", + bdesc->simp, + show_details ? "-" : "", + show_details ? bdesc->detail : "" + ); + } else { + /* bit fields */ + if (show_flags_only) + continue; + + mask = ((u64)1 << (end - start + 1)) - 1; + printf("\t%-20s\t: 0x%-8x\t%s%s\n", + bdesc->simp, + (value >> start) & mask, + show_details ? "-" : "", + show_details ? bdesc->detail : "" + ); + } + } +} + +static void show_leaf(struct subleaf *leaf) +{ + if (!leaf) + return; + + if (show_raw) + leaf_print_raw(leaf); + + decode_bits(leaf->eax, &leaf->info[R_EAX]); + decode_bits(leaf->ebx, &leaf->info[R_EBX]); + decode_bits(leaf->ecx, &leaf->info[R_ECX]); + decode_bits(leaf->edx, &leaf->info[R_EDX]); +} + +static void show_func(struct cpuid_func *func) +{ + int i; + + if (!func) + return; + + for (i = 0; i < func->nr; i++) + show_leaf(&func->leafs[i]); +} + +static void show_range(struct cpuid_range *range) +{ + int i; + + for (i = 0; i < range->nr; i++) + show_func(&range->funcs[i]); +} + +static inline struct cpuid_func *index_to_func(u32 index) +{ + struct cpuid_range *range; + + range = (index & 0x80000000) ? leafs_ext : leafs_basic; + index &= 0x7FFFFFFF; + + if (((index & 0xFFFF) + 1) > (u32)range->nr) { + printf("ERR: invalid input index (0x%x)\n", index); + return NULL; + } + return &range->funcs[index]; +} + +static void show_info(void) +{ + struct cpuid_func *func; + + if (show_raw) { + /* Show all of the raw output of 'cpuid' instr */ + raw_dump_range(leafs_basic); + raw_dump_range(leafs_ext); + return; + } + + if (user_index != 0xFFFFFFFF) { + /* Only show specific leaf/subleaf info */ + func = index_to_func(user_index); + if (!func) + return; + + /* Dump the raw data also */ + show_raw = true; + + if (user_sub != 0xFFFFFFFF) { + if (user_sub + 1 <= (u32)func->nr) { + show_leaf(&func->leafs[user_sub]); + return; + } + + printf("ERR: invalid input subleaf (0x%x)\n", user_sub); + } + + show_func(func); + return; + } + + printf("CPU features:\n=============\n\n"); + show_range(leafs_basic); + show_range(leafs_ext); +} + +static void setup_platform_cpuid(void) +{ + u32 eax, ebx, ecx, edx; + + /* Check vendor */ + eax = ebx = ecx = edx = 0; + cpuid(&eax, &ebx, &ecx, &edx); + + /* "htuA" */ + if (ebx == 0x68747541) + is_amd = true; + + /* Setup leafs for the basic and extended range */ + leafs_basic = setup_cpuid_range(0x0); + leafs_ext = setup_cpuid_range(0x80000000); +} + +static void usage(void) +{ + printf("kcpuid [-abdfhr] [-l leaf] [-s subleaf]\n" + "\t-a|--all Show both bit flags and complex bit fields info\n" + "\t-b|--bitflags Show boolean flags only\n" + "\t-d|--detail Show details of the flag/fields (default)\n" + "\t-f|--flags Specify the cpuid csv file\n" + "\t-h|--help Show usage info\n" + "\t-l|--leaf=index Specify the leaf you want to check\n" + "\t-r|--raw Show raw cpuid data\n" + "\t-s|--subleaf=sub Specify the subleaf you want to check\n" + ); +} + +static struct option opts[] = { + { "all", no_argument, NULL, 'a' }, /* show both bit flags and fields */ + { "bitflags", no_argument, NULL, 'b' }, /* only show bit flags, default on */ + { "detail", no_argument, NULL, 'd' }, /* show detail descriptions */ + { "file", required_argument, NULL, 'f' }, /* use user's cpuid file */ + { "help", no_argument, NULL, 'h'}, /* show usage */ + { "leaf", required_argument, NULL, 'l'}, /* only check a specific leaf */ + { "raw", no_argument, NULL, 'r'}, /* show raw CPUID leaf data */ + { "subleaf", required_argument, NULL, 's'}, /* check a specific subleaf */ + { NULL, 0, NULL, 0 } +}; + +static int parse_options(int argc, char *argv[]) +{ + int c; + + while ((c = getopt_long(argc, argv, "abdf:hl:rs:", + opts, NULL)) != -1) + switch (c) { + case 'a': + show_flags_only = false; + break; + case 'b': + show_flags_only = true; + break; + case 'd': + show_details = true; + break; + case 'f': + user_csv = optarg; + break; + case 'h': + usage(); + exit(1); + break; + case 'l': + /* main leaf */ + user_index = strtoul(optarg, NULL, 0); + break; + case 'r': + show_raw = true; + break; + case 's': + /* subleaf */ + user_sub = strtoul(optarg, NULL, 0); + break; + default: + printf("%s: Invalid option '%c'\n", argv[0], optopt); + return -1; + } + + return 0; +} + +/* + * Do 4 things in turn: + * 1. Parse user options + * 2. Parse and store all the CPUID leaf data supported on this platform + * 2. Parse the csv file, while skipping leafs which are not available + * on this platform + * 3. Print leafs info based on user options + */ +int main(int argc, char *argv[]) +{ + if (parse_options(argc, argv)) + return -1; + + /* Setup the cpuid leafs of current platform */ + setup_platform_cpuid(); + + /* Read and parse the 'cpuid.csv' */ + parse_text(); + + show_info(); + return 0; +} \ No newline at end of file -- 2.30.0

1 0

[PATCH] Add a kcpuid tool to show raw CPU features
by zhangyue 25 Oct '21

25 Oct '21

From: Feng Tang <feng.tang(a)intel.com> mainline inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4CMMB?from=project-issue CVE: NA ------------------------------------ End users frequently want to know what features their processor supports, independent of what the kernel supports. /proc/cpuinfo is great. It is omnipresent and since it is provided by the kernel it is always as up to date as the kernel. But, it could be ambiguous about processor features which can be disabled by the kernel at boot-time or compile-time. There are some user space tools showing more raw features, but they are not bound with kernel, and go with distros. Many end users are still using old distros with new kernels (upgraded by themselves), and may not upgrade the distros only to get a newer tool. So here arise the need for a new tool, which * shows raw CPU features read from the CPUID instruction * will be easier to update compared to existing userspace tooling (perhaps distributed like perf) * inherits "modern" kernel development process, in contrast to some of the existing userspace CPUID tools which are still being developed without git and distributed in tarballs from non-https sites. * Can produce output consistent with /proc/cpuinfo to make comparison easier. The CPUID leaf definitions are kept in an .csv file which allows for updating only that file to add support for new feature leafs. This is based on prototype code from Borislav Petkov (http://sr71.net/~dave/intel/stupid-cpuid.c) [ bp: - Massage, add #define _GNU_SOURCE to fix implicit declaration of function ‘strcasestr' warning - remove superfluous newlines - fallback to cpuid.csv in the current dir if none found - fix typos - move comments over the lines instead of sideways. ] Originally-from: Borislav Petkov <bp(a)alien8.de> Suggested-by: Dave Hansen <dave.hansen(a)intel.com> Suggested-by: Borislav Petkov <bp(a)alien8.de> Signed-off-by: Feng Tang <feng.tang(a)intel.com> Signed-off-by: Borislav Petkov <bp(a)suse.de> Signed-off-by: zhangyue <zhangyue1(a)kylinos.cn> --- tools/arch/x86/kcpuid/Makefile | 24 ++ tools/arch/x86/kcpuid/cpuid.csv | 400 +++++++++++++++++++ tools/arch/x86/kcpuid/kcpuid.c | 657 ++++++++++++++++++++++++++++++++ 3 files changed, 1081 insertions(+) create mode 100644 tools/arch/x86/kcpuid/Makefile create mode 100644 tools/arch/x86/kcpuid/cpuid.csv create mode 100644 tools/arch/x86/kcpuid/kcpuid.c diff --git a/tools/arch/x86/kcpuid/Makefile b/tools/arch/x86/kcpuid/Makefile new file mode 100644 index 000000000000..a2f1e855092c --- /dev/null +++ b/tools/arch/x86/kcpuid/Makefile @@ -0,0 +1,24 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for x86/kcpuid tool + +kcpuid : kcpuid.c + +CFLAGS = -Wextra + +BINDIR ?= /usr/sbin + +HWDATADIR ?= /usr/share/misc/ + +override CFLAGS += -O2 -Wall -I../../../include + +%: %.c + $(CC) $(CFLAGS) -o $@ $< $(LDFLAGS) + +.PHONY : clean +clean : + @rm -f kcpuid + +install : kcpuid + install -d $(DESTDIR)$(BINDIR) + install -m 755 -p kcpuid $(DESTDIR)$(BINDIR)/kcpuid + install -m 444 -p cpuid.csv $(HWDATADIR)/cpuid.csv diff --git a/tools/arch/x86/kcpuid/cpuid.csv b/tools/arch/x86/kcpuid/cpuid.csv new file mode 100644 index 000000000000..e422fad9a98e --- /dev/null +++ b/tools/arch/x86/kcpuid/cpuid.csv @@ -0,0 +1,400 @@ +# The basic row format is: +# LEAF, SUBLEAF, register_name, bits, short_name, long_description + +# Leaf 00H + 0, 0, EAX, 31:0, max_basic_leafs, Max input value for supported subleafs + +# Leaf 01H + 1, 0, EAX, 3:0, stepping, Stepping ID + 1, 0, EAX, 7:4, model, Model + 1, 0, EAX, 11:8, family, Family ID + 1, 0, EAX, 13:12, processor, Processor Type + 1, 0, EAX, 19:16, model_ext, Extended Model ID + 1, 0, EAX, 27:20, family_ext, Extended Family ID + + 1, 0, EBX, 7:0, brand, Brand Index + 1, 0, EBX, 15:8, clflush_size, CLFLUSH line size (value * 8) in bytes + 1, 0, EBX, 23:16, max_cpu_id, Maxim number of addressable logic cpu in this package + 1, 0, EBX, 31:24, apic_id, Initial APIC ID + + 1, 0, ECX, 0, sse3, Streaming SIMD Extensions 3(SSE3) + 1, 0, ECX, 1, pclmulqdq, PCLMULQDQ instruction supported + 1, 0, ECX, 2, dtes64, DS area uses 64-bit layout + 1, 0, ECX, 3, mwait, MONITOR/MWAIT supported + 1, 0, ECX, 4, ds_cpl, CPL Qualified Debug Store which allows for branch message storage qualified by CPL + 1, 0, ECX, 5, vmx, Virtual Machine Extensions supported + 1, 0, ECX, 6, smx, Safer Mode Extension supported + 1, 0, ECX, 7, eist, Enhanced Intel SpeedStep Technology + 1, 0, ECX, 8, tm2, Thermal Monitor 2 + 1, 0, ECX, 9, ssse3, Supplemental Streaming SIMD Extensions 3 (SSSE3) + 1, 0, ECX, 10, l1_ctx_id, L1 data cache could be set to either adaptive mode or shared mode (check IA32_MISC_ENABLE bit 24 definition) + 1, 0, ECX, 11, sdbg, IA32_DEBUG_INTERFACE MSR for silicon debug supported + 1, 0, ECX, 12, fma, FMA extensions using YMM state supported + 1, 0, ECX, 13, cmpxchg16b, 'CMPXCHG16B - Compare and Exchange Bytes' supported + 1, 0, ECX, 14, xtpr_update, xTPR Update Control supported + 1, 0, ECX, 15, pdcm, Perfmon and Debug Capability present + 1, 0, ECX, 17, pcid, Process-Context Identifiers feature present + 1, 0, ECX, 18, dca, Prefetching data from a memory mapped device supported + 1, 0, ECX, 19, sse4_1, SSE4.1 feature present + 1, 0, ECX, 20, sse4_2, SSE4.2 feature present + 1, 0, ECX, 21, x2apic, x2APIC supported + 1, 0, ECX, 22, movbe, MOVBE instruction supported + 1, 0, ECX, 23, popcnt, POPCNT instruction supported + 1, 0, ECX, 24, tsc_deadline_timer, LAPIC supports one-shot operation using a TSC deadline value + 1, 0, ECX, 25, aesni, AESNI instruction supported + 1, 0, ECX, 26, xsave, XSAVE/XRSTOR processor extended states (XSETBV/XGETBV/XCR0) + 1, 0, ECX, 27, osxsave, OS has set CR4.OSXSAVE bit to enable XSETBV/XGETBV/XCR0 + 1, 0, ECX, 28, avx, AVX instruction supported + 1, 0, ECX, 29, f16c, 16-bit floating-point conversion instruction supported + 1, 0, ECX, 30, rdrand, RDRAND instruction supported + + 1, 0, EDX, 0, fpu, x87 FPU on chip + 1, 0, EDX, 1, vme, Virtual-8086 Mode Enhancement + 1, 0, EDX, 2, de, Debugging Extensions + 1, 0, EDX, 3, pse, Page Size Extensions + 1, 0, EDX, 4, tsc, Time Stamp Counter + 1, 0, EDX, 5, msr, RDMSR and WRMSR Support + 1, 0, EDX, 6, pae, Physical Address Extensions + 1, 0, EDX, 7, mce, Machine Check Exception + 1, 0, EDX, 8, cx8, CMPXCHG8B instr + 1, 0, EDX, 9, apic, APIC on Chip + 1, 0, EDX, 11, sep, SYSENTER and SYSEXIT instrs + 1, 0, EDX, 12, mtrr, Memory Type Range Registers + 1, 0, EDX, 13, pge, Page Global Bit + 1, 0, EDX, 14, mca, Machine Check Architecture + 1, 0, EDX, 15, cmov, Conditional Move Instrs + 1, 0, EDX, 16, pat, Page Attribute Table + 1, 0, EDX, 17, pse36, 36-Bit Page Size Extension + 1, 0, EDX, 18, psn, Processor Serial Number + 1, 0, EDX, 19, clflush, CLFLUSH instr +# 1, 0, EDX, 20, + 1, 0, EDX, 21, ds, Debug Store + 1, 0, EDX, 22, acpi, Thermal Monitor and Software Controlled Clock Facilities + 1, 0, EDX, 23, mmx, Intel MMX Technology + 1, 0, EDX, 24, fxsr, XSAVE and FXRSTOR Instrs + 1, 0, EDX, 25, sse, SSE + 1, 0, EDX, 26, sse2, SSE2 + 1, 0, EDX, 27, ss, Self Snoop + 1, 0, EDX, 28, hit, Max APIC IDs + 1, 0, EDX, 29, tm, Thermal Monitor +# 1, 0, EDX, 30, + 1, 0, EDX, 31, pbe, Pending Break Enable + +# Leaf 02H +# cache and TLB descriptor info + +# Leaf 03H +# Precessor Serial Number, introduced on Pentium III, not valid for +# latest models + +# Leaf 04H +# thread/core and cache topology + 4, 0, EAX, 4:0, cache_type, Cache type like instr/data or unified + 4, 0, EAX, 7:5, cache_level, Cache Level (starts at 1) + 4, 0, EAX, 8, cache_self_init, Cache Self Initialization + 4, 0, EAX, 9, fully_associate, Fully Associative cache +# 4, 0, EAX, 13:10, resvd, resvd + 4, 0, EAX, 25:14, max_logical_id, Max number of addressable IDs for logical processors sharing the cache + 4, 0, EAX, 31:26, max_phy_id, Max number of addressable IDs for processors in phy package + + 4, 0, EBX, 11:0, cache_linesize, Size of a cache line in bytes + 4, 0, EBX, 21:12, cache_partition, Physical Line partitions + 4, 0, EBX, 31:22, cache_ways, Ways of associativity + 4, 0, ECX, 31:0, cache_sets, Number of Sets - 1 + 4, 0, EDX, 0, c_wbinvd, 1 means WBINVD/INVD is not ganranteed to act upon lower level caches of non-originating threads sharing this cache + 4, 0, EDX, 1, c_incl, Whether cache is inclusive of lower cache level + 4, 0, EDX, 2, c_comp_index, Complex Cache Indexing + +# Leaf 05H +# MONITOR/MWAIT + 5, 0, EAX, 15:0, min_mon_size, Smallest monitor line size in bytes + 5, 0, EBX, 15:0, max_mon_size, Largest monitor line size in bytes + 5, 0, ECX, 0, mwait_ext, Enum of Monitor-Mwait extensions supported + 5, 0, ECX, 1, mwait_irq_break, Largest monitor line size in bytes + 5, 0, EDX, 3:0, c0_sub_stats, Number of C0* sub C-states supported using MWAIT + 5, 0, EDX, 7:4, c1_sub_stats, Number of C1* sub C-states supported using MWAIT + 5, 0, EDX, 11:8, c2_sub_stats, Number of C2* sub C-states supported using MWAIT + 5, 0, EDX, 15:12, c3_sub_stats, Number of C3* sub C-states supported using MWAIT + 5, 0, EDX, 19:16, c4_sub_stats, Number of C4* sub C-states supported using MWAIT + 5, 0, EDX, 23:20, c5_sub_stats, Number of C5* sub C-states supported using MWAIT + 5, 0, EDX, 27:24, c6_sub_stats, Number of C6* sub C-states supported using MWAIT + 5, 0, EDX, 31:28, c7_sub_stats, Number of C7* sub C-states supported using MWAIT + +# Leaf 06H +# Thermal & Power Management + + 6, 0, EAX, 0, dig_temp, Digital temperature sensor supported + 6, 0, EAX, 1, turbo, Intel Turbo Boost + 6, 0, EAX, 2, arat, Always running APIC timer +# 6, 0, EAX, 3, resv, Reserved + 6, 0, EAX, 4, pln, Power limit notifications supported + 6, 0, EAX, 5, ecmd, Clock modulation duty cycle extension supported + 6, 0, EAX, 6, ptm, Package thermal management supported + 6, 0, EAX, 7, hwp, HWP base register + 6, 0, EAX, 8, hwp_notify, HWP notification + 6, 0, EAX, 9, hwp_act_window, HWP activity window + 6, 0, EAX, 10, hwp_energy, HWP energy performance preference + 6, 0, EAX, 11, hwp_pkg_req, HWP package level request +# 6, 0, EAX, 12, resv, Reserved + 6, 0, EAX, 13, hdc, HDC base registers supported + 6, 0, EAX, 14, turbo3, Turbo Boost Max 3.0 + 6, 0, EAX, 15, hwp_cap, Highest Performance change supported + 6, 0, EAX, 16, hwp_peci, HWP PECI override is supported + 6, 0, EAX, 17, hwp_flex, Flexible HWP is supported + 6, 0, EAX, 18, hwp_fast, Fast access mode for the IA32_HWP_REQUEST MSR is supported +# 6, 0, EAX, 19, resv, Reserved + 6, 0, EAX, 20, hwp_ignr, Ignoring Idle Logical Processor HWP request is supported + + 6, 0, EBX, 3:0, therm_irq_thresh, Number of Interrupt Thresholds in Digital Thermal Sensor + 6, 0, ECX, 0, aperfmperf, Presence of IA32_MPERF and IA32_APERF + 6, 0, ECX, 3, energ_bias, Performance-energy bias preference supported + +# Leaf 07H +# ECX == 0 +# AVX512 refers to https://en.wikipedia.org/wiki/AVX-512 +# XXX: Do we really need to enumerate each and every AVX512 sub features + + 7, 0, EBX, 0, fsgsbase, RDFSBASE/RDGSBASE/WRFSBASE/WRGSBASE supported + 7, 0, EBX, 1, tsc_adjust, TSC_ADJUST MSR supported + 7, 0, EBX, 2, sgx, Software Guard Extensions + 7, 0, EBX, 3, bmi1, BMI1 + 7, 0, EBX, 4, hle, Hardware Lock Elision + 7, 0, EBX, 5, avx2, AVX2 +# 7, 0, EBX, 6, fdp_excp_only, x87 FPU Data Pointer updated only on x87 exceptions + 7, 0, EBX, 7, smep, Supervisor-Mode Execution Prevention + 7, 0, EBX, 8, bmi2, BMI2 + 7, 0, EBX, 9, rep_movsb, Enhanced REP MOVSB/STOSB + 7, 0, EBX, 10, invpcid, INVPCID instruction + 7, 0, EBX, 11, rtm, Restricted Transactional Memory + 7, 0, EBX, 12, rdt_m, Intel RDT Monitoring capability + 7, 0, EBX, 13, depc_fpu_cs_ds, Deprecates FPU CS and FPU DS + 7, 0, EBX, 14, mpx, Memory Protection Extensions + 7, 0, EBX, 15, rdt_a, Intel RDT Allocation capability + 7, 0, EBX, 16, avx512f, AVX512 Foundation instr + 7, 0, EBX, 17, avx512dq, AVX512 Double and Quadword AVX512 instr + 7, 0, EBX, 18, rdseed, RDSEED instr + 7, 0, EBX, 19, adx, ADX instr + 7, 0, EBX, 20, smap, Supervisor Mode Access Prevention + 7, 0, EBX, 21, avx512ifma, AVX512 Integer Fused Multiply Add +# 7, 0, EBX, 22, resvd, resvd + 7, 0, EBX, 23, clflushopt, CLFLUSHOPT instr + 7, 0, EBX, 24, clwb, CLWB instr + 7, 0, EBX, 25, intel_pt, Intel Processor Trace instr + 7, 0, EBX, 26, avx512pf, Prefetch + 7, 0, EBX, 27, avx512er, AVX512 Exponent Reciproca instr + 7, 0, EBX, 28, avx512cd, AVX512 Conflict Detection instr + 7, 0, EBX, 29, sha, Intel Secure Hash Algorithm Extensions instr + 7, 0, EBX, 26, avx512bw, AVX512 Byte & Word instr + 7, 0, EBX, 28, avx512vl, AVX512 Vector Length Extentions (VL) + 7, 0, ECX, 0, prefetchwt1, X + 7, 0, ECX, 1, avx512vbmi, AVX512 Vector Byte Manipulation Instructions + 7, 0, ECX, 2, umip, User-mode Instruction Prevention + + 7, 0, ECX, 3, pku, Protection Keys for User-mode pages + 7, 0, ECX, 4, ospke, CR4 PKE set to enable protection keys +# 7, 0, ECX, 16:5, resvd, resvd + 7, 0, ECX, 21:17, mawau, The value of MAWAU used by the BNDLDX and BNDSTX instructions in 64-bit mode + 7, 0, ECX, 22, rdpid, RDPID and IA32_TSC_AUX +# 7, 0, ECX, 29:23, resvd, resvd + 7, 0, ECX, 30, sgx_lc, SGX Launch Configuration +# 7, 0, ECX, 31, resvd, resvd + +# Leaf 08H +# + + +# Leaf 09H +# Direct Cache Access (DCA) information + 9, 0, ECX, 31:0, dca_cap, The value of IA32_PLATFORM_DCA_CAP + +# Leaf 0AH +# Architectural Performance Monitoring +# +# Do we really need to print out the PMU related stuff? +# Does normal user really care about it? +# + 0xA, 0, EAX, 7:0, pmu_ver, Performance Monitoring Unit version + 0xA, 0, EAX, 15:8, pmu_gp_cnt_num, Numer of general-purose PMU counters per logical CPU + 0xA, 0, EAX, 23:16, pmu_cnt_bits, Bit wideth of PMU counter + 0xA, 0, EAX, 31:24, pmu_ebx_bits, Length of EBX bit vector to enumerate PMU events + + 0xA, 0, EBX, 0, pmu_no_core_cycle_evt, Core cycle event not available + 0xA, 0, EBX, 1, pmu_no_instr_ret_evt, Instruction retired event not available + 0xA, 0, EBX, 2, pmu_no_ref_cycle_evt, Reference cycles event not available + 0xA, 0, EBX, 3, pmu_no_llc_ref_evt, Last-level cache reference event not available + 0xA, 0, EBX, 4, pmu_no_llc_mis_evt, Last-level cache misses event not available + 0xA, 0, EBX, 5, pmu_no_br_instr_ret_evt, Branch instruction retired event not available + 0xA, 0, EBX, 6, pmu_no_br_mispredict_evt, Branch mispredict retired event not available + + 0xA, 0, ECX, 4:0, pmu_fixed_cnt_num, Performance Monitoring Unit version + 0xA, 0, ECX, 12:5, pmu_fixed_cnt_bits, Numer of PMU counters per logical CPU + +# Leaf 0BH +# Extended Topology Enumeration Leaf +# + + 0xB, 0, EAX, 4:0, id_shift, Number of bits to shift right on x2APIC ID to get a unique topology ID of the next level type + 0xB, 0, EBX, 15:0, cpu_nr, Number of logical processors at this level type + 0xB, 0, ECX, 15:8, lvl_type, 0-Invalid 1-SMT 2-Core + 0xB, 0, EDX, 31:0, x2apic_id, x2APIC ID the current logical processor + + +# Leaf 0DH +# Processor Extended State + + 0xD, 0, EAX, 0, x87, X87 state + 0xD, 0, EAX, 1, sse, SSE state + 0xD, 0, EAX, 2, avx, AVX state + 0xD, 0, EAX, 4:3, mpx, MPX state + 0xD, 0, EAX, 7:5, avx512, AVX-512 state + 0xD, 0, EAX, 9, pkru, PKRU state + + 0xD, 0, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0 + 0xD, 0, ECX, 31:0, max_sz_xsave, Maximum size (bytes) of the XSAVE/XRSTOR save area + + 0xD, 1, EAX, 0, xsaveopt, XSAVEOPT available + 0xD, 1, EAX, 1, xsavec, XSAVEC and compacted form supported + 0xD, 1, EAX, 2, xgetbv, XGETBV supported + 0xD, 1, EAX, 3, xsaves, XSAVES/XRSTORS and IA32_XSS supported + + 0xD, 1, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0 + 0xD, 1, ECX, 8, pt, PT state + 0xD, 1, ECX, 11, cet_usr, CET user state + 0xD, 1, ECX, 12, cet_supv, CET supervisor state + 0xD, 1, ECX, 13, hdc, HDC state + 0xD, 1, ECX, 16, hwp, HWP state + +# Leaf 0FH +# Intel RDT Monitoring + + 0xF, 0, EBX, 31:0, rmid_range, Maximum range (zero-based) of RMID within this physical processor of all types + 0xF, 0, EDX, 1, l3c_rdt_mon, L3 Cache RDT Monitoring supported + + 0xF, 1, ECX, 31:0, rmid_range, Maximum range (zero-based) of RMID of this types + 0xF, 1, EDX, 0, l3c_ocp_mon, L3 Cache occupancy Monitoring supported + 0xF, 1, EDX, 1, l3c_tbw_mon, L3 Cache Total Bandwidth Monitoring supported + 0xF, 1, EDX, 2, l3c_lbw_mon, L3 Cache Local Bandwidth Monitoring supported + +# Leaf 10H +# Intel RDT Allocation + + 0x10, 0, EBX, 1, l3c_rdt_alloc, L3 Cache Allocation supported + 0x10, 0, EBX, 2, l2c_rdt_alloc, L2 Cache Allocation supported + 0x10, 0, EBX, 3, mem_bw_alloc, Memory Bandwidth Allocation supported + + +# Leaf 12H +# SGX Capability +# +# Some detailed SGX features not added yet + + 0x12, 0, EAX, 0, sgx1, L3 Cache Allocation supported + 0x12, 1, EAX, 0, sgx2, L3 Cache Allocation supported + + +# Leaf 14H +# Intel Processor Tracer +# + +# Leaf 15H +# Time Stamp Counter and Nominal Core Crystal Clock Information + + 0x15, 0, EAX, 31:0, tsc_denominator, The denominator of the TSC/”core crystal clock” ratio + 0x15, 0, EBX, 31:0, tsc_numerator, The numerator of the TSC/”core crystal clock” ratio + 0x15, 0, ECX, 31:0, nom_freq, Nominal frequency of the core crystal clock in Hz + +# Leaf 16H +# Processor Frequency Information + + 0x16, 0, EAX, 15:0, cpu_base_freq, Processor Base Frequency in MHz + 0x16, 0, EBX, 15:0, cpu_max_freq, Maximum Frequency in MHz + 0x16, 0, ECX, 15:0, bus_freq, Bus (Reference) Frequency in MHz + +# Leaf 17H +# System-On-Chip Vendor Attribute + + 0x17, 0, EAX, 31:0, max_socid, Maximum input value of supported sub-leaf + 0x17, 0, EBX, 15:0, soc_vid, SOC Vendor ID + 0x17, 0, EBX, 16, std_vid, SOC Vendor ID is assigned via an industry standard scheme + 0x17, 0, ECX, 31:0, soc_pid, SOC Project ID assigned by vendor + 0x17, 0, EDX, 31:0, soc_sid, SOC Stepping ID + +# Leaf 18H +# Deterministic Address Translation Parameters + + +# Leaf 19H +# Key Locker Leaf + + +# Leaf 1AH +# Hybrid Information + + 0x1A, 0, EAX, 31:24, core_type, 20H-Intel_Atom 40H-Intel_Core + + +# Leaf 1FH +# V2 Extended Topology - A preferred superset to leaf 0BH + + +# According to SDM +# 40000000H - 4FFFFFFFH is invalid range + + +# Leaf 80000001H +# Extended Processor Signature and Feature Bits + +0x80000001, 0, ECX, 0, lahf_lm, LAHF/SAHF available in 64-bit mode +0x80000001, 0, ECX, 5, lzcnt, LZCNT +0x80000001, 0, ECX, 8, prefetchw, PREFETCHW + +0x80000001, 0, EDX, 11, sysret, SYSCALL/SYSRET supported +0x80000001, 0, EDX, 20, exec_dis, Execute Disable Bit available +0x80000001, 0, EDX, 26, 1gb_page, 1GB page supported +0x80000001, 0, EDX, 27, rdtscp, RDTSCP and IA32_TSC_AUX are available +#0x80000001, 0, EDX, 29, 64b, 64b Architecture supported + +# Leaf 80000002H/80000003H/80000004H +# Processor Brand String + +# Leaf 80000005H +# Reserved + +# Leaf 80000006H +# Extended L2 Cache Features + +0x80000006, 0, ECX, 7:0, clsize, Cache Line size in bytes +0x80000006, 0, ECX, 15:12, l2c_assoc, L2 Associativity +0x80000006, 0, ECX, 31:16, csize, Cache size in 1K units + + +# Leaf 80000007H + +0x80000007, 0, EDX, 8, nonstop_tsc, Invariant TSC available + + +# Leaf 80000008H + +0x80000008, 0, EAX, 7:0, phy_adr_bits, Physical Address Bits +0x80000008, 0, EAX, 15:8, lnr_adr_bits, Linear Address Bits +0x80000007, 0, EBX, 9, wbnoinvd, WBNOINVD + +# 0x8000001E +# EAX: Extended APIC ID +0x8000001E, 0, EAX, 31:0, extended_apic_id, Extended APIC ID +# EBX: Core Identifiers +0x8000001E, 0, EBX, 7:0, core_id, Identifies the logical core ID +0x8000001E, 0, EBX, 15:8, threads_per_core, The number of threads per core is threads_per_core + 1 +# ECX: Node Identifiers +0x8000001E, 0, ECX, 7:0, node_id, Node ID +0x8000001E, 0, ECX, 10:8, nodes_per_processor, Nodes per processor { 0: 1 node, else reserved } + +# 8000001F: AMD Secure Encryption +0x8000001F, 0, EAX, 0, sme, Secure Memory Encryption +0x8000001F, 0, EAX, 1, sev, Secure Encrypted Virtualization +0x8000001F, 0, EAX, 2, vmpgflush, VM Page Flush MSR +0x8000001F, 0, EAX, 3, seves, SEV Encrypted State +0x8000001F, 0, EBX, 5:0, c-bit, Page table bit number used to enable memory encryption +0x8000001F, 0, EBX, 11:6, mem_encrypt_physaddr_width, Reduction of physical address space in bits with SME enabled +0x8000001F, 0, ECX, 31:0, num_encrypted_guests, Maximum ASID value that may be used for an SEV-enabled guest +0x8000001F, 0, EDX, 31:0, minimum_sev_asid, Minimum ASID value that must be used for an SEV-enabled, SEV-ES-disabled guest \ No newline at end of file diff --git a/tools/arch/x86/kcpuid/kcpuid.c b/tools/arch/x86/kcpuid/kcpuid.c new file mode 100644 index 000000000000..936a3a2aad04 --- /dev/null +++ b/tools/arch/x86/kcpuid/kcpuid.c @@ -0,0 +1,657 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <stdio.h> +#include <stdbool.h> +#include <stdlib.h> +#include <string.h> +#include <getopt.h> + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) + +typedef unsigned int u32; +typedef unsigned long long u64; + +char *def_csv = "/usr/share/misc/cpuid.csv"; +char *user_csv; + + +/* Cover both single-bit flag and multiple-bits fields */ +struct bits_desc { + /* start and end bits */ + int start, end; + /* 0 or 1 for 1-bit flag */ + int value; + char simp[32]; + char detail[256]; +}; + +/* descriptor info for eax/ebx/ecx/edx */ +struct reg_desc { + /* number of valid entries */ + int nr; + struct bits_desc descs[32]; +}; + +enum { + R_EAX = 0, + R_EBX, + R_ECX, + R_EDX, + NR_REGS +}; + +struct subleaf { + u32 index; + u32 sub; + u32 eax, ebx, ecx, edx; + struct reg_desc info[NR_REGS]; +}; + +/* Represent one leaf (basic or extended) */ +struct cpuid_func { + /* + * Array of subleafs for this func, if there is no subleafs + * then the leafs[0] is the main leaf + */ + struct subleaf *leafs; + int nr; +}; + +struct cpuid_range { + /* array of main leafs */ + struct cpuid_func *funcs; + /* number of valid leafs */ + int nr; + bool is_ext; +}; + +/* + * basic: basic functions range: [0... ] + * ext: extended functions range: [0x80000000... ] + */ +struct cpuid_range *leafs_basic, *leafs_ext; + +static int num_leafs; +static bool is_amd; +static bool show_details; +static bool show_raw; +static bool show_flags_only = true; +static u32 user_index = 0xFFFFFFFF; +static u32 user_sub = 0xFFFFFFFF; +static int flines; + +static inline void cpuid(u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) +{ + /* ecx is often an input as well as an output. */ + asm volatile("cpuid" + : "=a" (*eax), + "=b" (*ebx), + "=c" (*ecx), + "=d" (*edx) + : "0" (*eax), "2" (*ecx)); +} + +static inline bool has_subleafs(u32 f) +{ + if (f == 0x7 || f == 0xd) + return true; + + if (is_amd) { + if (f == 0x8000001d) + return true; + return false; + } + + switch (f) { + case 0x4: + case 0xb: + case 0xf: + case 0x10: + case 0x14: + case 0x18: + case 0x1f: + return true; + default: + return false; + } +} + +static void leaf_print_raw(struct subleaf *leaf) +{ + if (has_subleafs(leaf->index)) { + if (leaf->sub == 0) + printf("0x%08x: subleafs:\n", leaf->index); + + printf(" %2d: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n", + leaf->sub, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx); + } else { + printf("0x%08x: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n", + leaf->index, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx); + } +} + +/* Return true is the input eax/ebx/ecx/edx are all zero */ +static bool cpuid_store(struct cpuid_range *range, u32 f, int subleaf, + u32 a, u32 b, u32 c, u32 d) +{ + struct cpuid_func *func; + struct subleaf *leaf; + int s = 0; + + if (a == 0 && b == 0 && c == 0 && d == 0) + return true; + + /* + * Cut off vendor-prefix from CPUID function as we're using it as an + * index into ->funcs. + */ + func = &range->funcs[f & 0xffff]; + + if (!func->leafs) { + func->leafs = malloc(sizeof(struct subleaf)); + if (!func->leafs) + perror("malloc func leaf"); + + func->nr = 1; + } else { + s = func->nr; + func->leafs = realloc(func->leafs, (s + 1) * sizeof(*leaf)); + if (!func->leafs) + perror("realloc f->leafs"); + + func->nr++; + } + + leaf = &func->leafs[s]; + + leaf->index = f; + leaf->sub = subleaf; + leaf->eax = a; + leaf->ebx = b; + leaf->ecx = c; + leaf->edx = d; + + return false; +} + +static void raw_dump_range(struct cpuid_range *range) +{ + u32 f; + int i; + + printf("%s Leafs :\n", range->is_ext ? "Extended" : "Basic"); + printf("================\n"); + + for (f = 0; (int)f < range->nr; f++) { + struct cpuid_func *func = &range->funcs[f]; + u32 index = f; + + if (range->is_ext) + index += 0x80000000; + + /* Skip leaf without valid items */ + if (!func->nr) + continue; + + /* First item is the main leaf, followed by all subleafs */ + for (i = 0; i < func->nr; i++) + leaf_print_raw(&func->leafs[i]); + } +} + +#define MAX_SUBLEAF_NUM 32 +struct cpuid_range *setup_cpuid_range(u32 input_eax) +{ + u32 max_func, idx_func; + int subleaf; + struct cpuid_range *range; + u32 eax, ebx, ecx, edx; + u32 f = input_eax; + int max_subleaf; + bool allzero; + + eax = input_eax; + ebx = ecx = edx = 0; + + cpuid(&eax, &ebx, &ecx, &edx); + max_func = eax; + idx_func = (max_func & 0xffff) + 1; + + range = malloc(sizeof(struct cpuid_range)); + if (!range) + perror("malloc range"); + + if (input_eax & 0x80000000) + range->is_ext = true; + else + range->is_ext = false; + + range->funcs = malloc(sizeof(struct cpuid_func) * idx_func); + if (!range->funcs) + perror("malloc range->funcs"); + + range->nr = idx_func; + memset(range->funcs, 0, sizeof(struct cpuid_func) * idx_func); + + for (; f <= max_func; f++) { + eax = f; + subleaf = ecx = 0; + + cpuid(&eax, &ebx, &ecx, &edx); + allzero = cpuid_store(range, f, subleaf, eax, ebx, ecx, edx); + if (allzero) + continue; + num_leafs++; + + if (!has_subleafs(f)) + continue; + + max_subleaf = MAX_SUBLEAF_NUM; + + /* + * Some can provide the exact number of subleafs, + * others have to be tried (0xf) + */ + if (f == 0x7 || f == 0x14 || f == 0x17 || f == 0x18) + max_subleaf = (eax & 0xff) + 1; + + if (f == 0xb) + max_subleaf = 2; + + for (subleaf = 1; subleaf < max_subleaf; subleaf++) { + eax = f; + ecx = subleaf; + + cpuid(&eax, &ebx, &ecx, &edx); + allzero = cpuid_store(range, f, subleaf, + eax, ebx, ecx, edx); + if (allzero) + continue; + num_leafs++; + } + + } + + return range; +} + +/* + * The basic row format for cpuid.csv is + * LEAF,SUBLEAF,register_name,bits,short name,long description + * + * like: + * 0, 0, EAX, 31:0, max_basic_leafs, Max input value for supported subleafs + * 1, 0, ECX, 0, sse3, Streaming SIMD Extensions 3(SSE3) + */ +static int parse_line(char *line) +{ + char *str; + int i; + struct cpuid_range *range; + struct cpuid_func *func; + struct subleaf *leaf; + u32 index; + u32 sub; + char buffer[512]; + char *buf; + /* + * Tokens: + * 1. leaf + * 2. subleaf + * 3. register + * 4. bits + * 5. short name + * 6. long detail + */ + char *tokens[6]; + struct reg_desc *reg; + struct bits_desc *bdesc; + int reg_index; + char *start, *end; + + /* Skip comments and NULL line */ + if (line[0] == '#' || line[0] == '\n') + return 0; + + strncpy(buffer, line, 511); + buffer[511] = 0; + str = buffer; + for (i = 0; i < 5; i++) { + tokens[i] = strtok(str, ","); + if (!tokens[i]) + goto err_exit; + str = NULL; + } + tokens[5] = strtok(str, "\n"); + if (!tokens[5]) + goto err_exit; + + /* index/main-leaf */ + index = strtoull(tokens[0], NULL, 0); + + if (index & 0x80000000) + range = leafs_ext; + else + range = leafs_basic; + + index &= 0x7FFFFFFF; + /* Skip line parsing for non-existing indexes */ + if ((int)index >= range->nr) + return -1; + + func = &range->funcs[index]; + + /* Return if the index has no valid item on this platform */ + if (!func->nr) + return 0; + + /* subleaf */ + sub = strtoul(tokens[1], NULL, 0); + if ((int)sub > func->nr) + return -1; + + leaf = &func->leafs[sub]; + buf = tokens[2]; + + if (strcasestr(buf, "EAX")) + reg_index = R_EAX; + else if (strcasestr(buf, "EBX")) + reg_index = R_EBX; + else if (strcasestr(buf, "ECX")) + reg_index = R_ECX; + else if (strcasestr(buf, "EDX")) + reg_index = R_EDX; + else + goto err_exit; + + reg = &leaf->info[reg_index]; + bdesc = &reg->descs[reg->nr++]; + + /* bit flag or bits field */ + buf = tokens[3]; + + end = strtok(buf, ":"); + bdesc->end = strtoul(end, NULL, 0); + bdesc->start = bdesc->end; + + /* start != NULL means it is bit fields */ + start = strtok(NULL, ":"); + if (start) + bdesc->start = strtoul(start, NULL, 0); + + strcpy(bdesc->simp, tokens[4]); + strcpy(bdesc->detail, tokens[5]); + return 0; + +err_exit: + printf("Warning: wrong line format:\n"); + printf("\tline[%d]: %s\n", flines, line); + return -1; +} + +/* Parse csv file, and construct the array of all leafs and subleafs */ +static void parse_text(void) +{ + FILE *file; + char *filename, *line = NULL; + size_t len = 0; + int ret; + + if (show_raw) + return; + + filename = user_csv ? user_csv : def_csv; + file = fopen(filename, "r"); + if (!file) { + /* Fallback to a csv in the same dir */ + file = fopen("./cpuid.csv", "r"); + } + + if (!file) { + printf("Fail to open '%s'\n", filename); + return; + } + + while (1) { + ret = getline(&line, &len, file); + flines++; + if (ret > 0) + parse_line(line); + + if (feof(file)) + break; + } + + fclose(file); +} + + +/* Decode every eax/ebx/ecx/edx */ +static void decode_bits(u32 value, struct reg_desc *rdesc) +{ + struct bits_desc *bdesc; + int start, end, i; + u32 mask; + + for (i = 0; i < rdesc->nr; i++) { + bdesc = &rdesc->descs[i]; + + start = bdesc->start; + end = bdesc->end; + if (start == end) { + /* single bit flag */ + if (value & (1 << start)) + printf("\t%-20s %s%s\n", + bdesc->simp, + show_details ? "-" : "", + show_details ? bdesc->detail : "" + ); + } else { + /* bit fields */ + if (show_flags_only) + continue; + + mask = ((u64)1 << (end - start + 1)) - 1; + printf("\t%-20s\t: 0x%-8x\t%s%s\n", + bdesc->simp, + (value >> start) & mask, + show_details ? "-" : "", + show_details ? bdesc->detail : "" + ); + } + } +} + +static void show_leaf(struct subleaf *leaf) +{ + if (!leaf) + return; + + if (show_raw) + leaf_print_raw(leaf); + + decode_bits(leaf->eax, &leaf->info[R_EAX]); + decode_bits(leaf->ebx, &leaf->info[R_EBX]); + decode_bits(leaf->ecx, &leaf->info[R_ECX]); + decode_bits(leaf->edx, &leaf->info[R_EDX]); +} + +static void show_func(struct cpuid_func *func) +{ + int i; + + if (!func) + return; + + for (i = 0; i < func->nr; i++) + show_leaf(&func->leafs[i]); +} + +static void show_range(struct cpuid_range *range) +{ + int i; + + for (i = 0; i < range->nr; i++) + show_func(&range->funcs[i]); +} + +static inline struct cpuid_func *index_to_func(u32 index) +{ + struct cpuid_range *range; + + range = (index & 0x80000000) ? leafs_ext : leafs_basic; + index &= 0x7FFFFFFF; + + if (((index & 0xFFFF) + 1) > (u32)range->nr) { + printf("ERR: invalid input index (0x%x)\n", index); + return NULL; + } + return &range->funcs[index]; +} + +static void show_info(void) +{ + struct cpuid_func *func; + + if (show_raw) { + /* Show all of the raw output of 'cpuid' instr */ + raw_dump_range(leafs_basic); + raw_dump_range(leafs_ext); + return; + } + + if (user_index != 0xFFFFFFFF) { + /* Only show specific leaf/subleaf info */ + func = index_to_func(user_index); + if (!func) + return; + + /* Dump the raw data also */ + show_raw = true; + + if (user_sub != 0xFFFFFFFF) { + if (user_sub + 1 <= (u32)func->nr) { + show_leaf(&func->leafs[user_sub]); + return; + } + + printf("ERR: invalid input subleaf (0x%x)\n", user_sub); + } + + show_func(func); + return; + } + + printf("CPU features:\n=============\n\n"); + show_range(leafs_basic); + show_range(leafs_ext); +} + +static void setup_platform_cpuid(void) +{ + u32 eax, ebx, ecx, edx; + + /* Check vendor */ + eax = ebx = ecx = edx = 0; + cpuid(&eax, &ebx, &ecx, &edx); + + /* "htuA" */ + if (ebx == 0x68747541) + is_amd = true; + + /* Setup leafs for the basic and extended range */ + leafs_basic = setup_cpuid_range(0x0); + leafs_ext = setup_cpuid_range(0x80000000); +} + +static void usage(void) +{ + printf("kcpuid [-abdfhr] [-l leaf] [-s subleaf]\n" + "\t-a|--all Show both bit flags and complex bit fields info\n" + "\t-b|--bitflags Show boolean flags only\n" + "\t-d|--detail Show details of the flag/fields (default)\n" + "\t-f|--flags Specify the cpuid csv file\n" + "\t-h|--help Show usage info\n" + "\t-l|--leaf=index Specify the leaf you want to check\n" + "\t-r|--raw Show raw cpuid data\n" + "\t-s|--subleaf=sub Specify the subleaf you want to check\n" + ); +} + +static struct option opts[] = { + { "all", no_argument, NULL, 'a' }, /* show both bit flags and fields */ + { "bitflags", no_argument, NULL, 'b' }, /* only show bit flags, default on */ + { "detail", no_argument, NULL, 'd' }, /* show detail descriptions */ + { "file", required_argument, NULL, 'f' }, /* use user's cpuid file */ + { "help", no_argument, NULL, 'h'}, /* show usage */ + { "leaf", required_argument, NULL, 'l'}, /* only check a specific leaf */ + { "raw", no_argument, NULL, 'r'}, /* show raw CPUID leaf data */ + { "subleaf", required_argument, NULL, 's'}, /* check a specific subleaf */ + { NULL, 0, NULL, 0 } +}; + +static int parse_options(int argc, char *argv[]) +{ + int c; + + while ((c = getopt_long(argc, argv, "abdf:hl:rs:", + opts, NULL)) != -1) + switch (c) { + case 'a': + show_flags_only = false; + break; + case 'b': + show_flags_only = true; + break; + case 'd': + show_details = true; + break; + case 'f': + user_csv = optarg; + break; + case 'h': + usage(); + exit(1); + break; + case 'l': + /* main leaf */ + user_index = strtoul(optarg, NULL, 0); + break; + case 'r': + show_raw = true; + break; + case 's': + /* subleaf */ + user_sub = strtoul(optarg, NULL, 0); + break; + default: + printf("%s: Invalid option '%c'\n", argv[0], optopt); + return -1; + } + + return 0; +} + +/* + * Do 4 things in turn: + * 1. Parse user options + * 2. Parse and store all the CPUID leaf data supported on this platform + * 2. Parse the csv file, while skipping leafs which are not available + * on this platform + * 3. Print leafs info based on user options + */ +int main(int argc, char *argv[]) +{ + if (parse_options(argc, argv)) + return -1; + + /* Setup the cpuid leafs of current platform */ + setup_platform_cpuid(); + + /* Read and parse the 'cpuid.csv' */ + parse_text(); + + show_info(); + return 0; +} \ No newline at end of file -- 2.30.0

1 0

[PATCH kernel-4.19 1/3] net: hns3: use ae_dev->ops->reset_event to do reset.
by Yang Yingliang 25 Oct '21

25 Oct '21

From: Yonglong Liu <liuyonglong(a)huawei.com> driver inclusion category: bugfix bugzilla: NA CVE: NA ---------------------------- IT products want to know whether a reset is happened, so need to use ae_dev->ops->reset_event to notify them. Signed-off-by: Yonglong Liu <liuyonglong(a)huawei.com> Reviewed-by: li yongxin <liyongxin1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 98a1d3d2870a9..8507eb60450fe 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -3933,6 +3933,7 @@ static void hclge_set_def_reset_request(struct hnae3_ae_dev *ae_dev, static void hclge_reset_timer(struct timer_list *t) { struct hclge_dev *hdev = from_timer(hdev, t, reset_timer); + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); /* if default_reset_request has no value, it means that this reset * request has already be handled, so just return here @@ -3942,7 +3943,9 @@ static void hclge_reset_timer(struct timer_list *t) dev_info(&hdev->pdev->dev, "triggering reset in reset timer\n"); - hclge_reset_event(hdev->pdev, NULL); + + if (ae_dev->ops->reset_event) + ae_dev->ops->reset_event(hdev->pdev, NULL); } static bool hclge_reset_end(struct hnae3_handle *handle, bool done) -- 2.25.1

1 2

[PATCH kernel-4.19] media: firewire: firedtv-avc: fix a buffer overflow in avc_ca_pmt()
by Yang Yingliang 25 Oct '21

25 Oct '21

From: Dan Carpenter <dan.carpenter(a)oracle.com> mainline inclusion from mainline-v5.16 commit 35d2969ea3c7d32aee78066b1f3cf61a0d935a4e category: bugfix bugzilla: NA CVE: CVE-2021-42739 ------------------------------------------------- The bounds checking in avc_ca_pmt() is not strict enough. It should be checking "read_pos + 4" because it's reading 5 bytes. If the "es_info_length" is non-zero then it reads a 6th byte so there needs to be an additional check for that. I also added checks for the "write_pos". I don't think these are required because "read_pos" and "write_pos" are tied together so checking one ought to be enough. But they make the code easier to understand for me. The check on write_pos is: if (write_pos + 4 >= sizeof(c->operand) - 4) { The first "+ 4" is because we're writing 5 bytes and the last " - 4" is to leave space for the CRC. The other problem is that "length" can be invalid. It comes from "data_length" in fdtv_ca_pmt(). Cc: stable(a)vger.kernel.org Reported-by: Luo Likang <luolikang(a)nsfocus.com> Signed-off-by: Dan Carpenter <dan.carpenter(a)oracle.com> Signed-off-by: Hans Verkuil <hverkuil-cisco(a)xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei(a)kernel.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/media/firewire/firedtv-avc.c | 14 +++++++++++--- drivers/media/firewire/firedtv-ci.c | 2 ++ 2 files changed, 13 insertions(+), 3 deletions(-) diff --git a/drivers/media/firewire/firedtv-avc.c b/drivers/media/firewire/firedtv-avc.c index 3ef5df1648d77..8c31cf90c5907 100644 --- a/drivers/media/firewire/firedtv-avc.c +++ b/drivers/media/firewire/firedtv-avc.c @@ -1169,7 +1169,11 @@ int avc_ca_pmt(struct firedtv *fdtv, char *msg, int length) read_pos += program_info_length; write_pos += program_info_length; } - while (read_pos < length) { + while (read_pos + 4 < length) { + if (write_pos + 4 >= sizeof(c->operand) - 4) { + ret = -EINVAL; + goto out; + } c->operand[write_pos++] = msg[read_pos++]; c->operand[write_pos++] = msg[read_pos++]; c->operand[write_pos++] = msg[read_pos++]; @@ -1181,13 +1185,17 @@ int avc_ca_pmt(struct firedtv *fdtv, char *msg, int length) c->operand[write_pos++] = es_info_length >> 8; c->operand[write_pos++] = es_info_length & 0xff; if (es_info_length > 0) { + if (read_pos >= length) { + ret = -EINVAL; + goto out; + } pmt_cmd_id = msg[read_pos++]; if (pmt_cmd_id != 1 && pmt_cmd_id != 4) dev_err(fdtv->device, "invalid pmt_cmd_id %d at stream level\n", pmt_cmd_id); - if (es_info_length > sizeof(c->operand) - 4 - - write_pos) { + if (es_info_length > sizeof(c->operand) - 4 - write_pos || + es_info_length > length - read_pos) { ret = -EINVAL; goto out; } diff --git a/drivers/media/firewire/firedtv-ci.c b/drivers/media/firewire/firedtv-ci.c index 8dc5a7495abee..14f779812d250 100644 --- a/drivers/media/firewire/firedtv-ci.c +++ b/drivers/media/firewire/firedtv-ci.c @@ -138,6 +138,8 @@ static int fdtv_ca_pmt(struct firedtv *fdtv, void *arg) } else { data_length = msg->msg[3]; } + if (data_length > sizeof(msg->msg) - data_pos) + return -EINVAL; return avc_ca_pmt(fdtv, &msg->msg[data_pos], data_length); } -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] GPIO : support ascend gpio driver
by Yang Yingliang 25 Oct '21

25 Oct '21

From: wuhuaye <wuhuaye(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4DLVR CVE: NA ------------------------------------------------- Hi everyone， This patch add some special gpio register configuration. It is necessary to configure some gpio register when gpio-dwapb function is enable in Ascend platform. Signed-off-by: wuhuaye <wuhuaye(a)huawei.com> Reviewed-by: Ding Tianhong <dingtianhong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/mm/init.c | 17 ++++++++++ drivers/gpio/gpio-dwapb.c | 66 ++++++++++++++++++++++++++++++++++++++- 2 files changed, 82 insertions(+), 1 deletion(-) diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 5449ae2d26bee..55fc6a0206796 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -941,6 +941,12 @@ __setup("keepinitrd", keepinitrd_setup); void ascend_enable_all_features(void) { +#ifdef CONFIG_GPIO_DWAPB + extern bool enable_ascend_gpio_dwapb; + + enable_ascend_gpio_dwapb = true; +#endif + if (IS_ENABLED(CONFIG_ASCEND_DVPP_MMAP)) enable_mmap_dvpp = 1; @@ -974,6 +980,17 @@ static int __init ascend_enable_setup(char *__unused) } early_param("ascend_enable_all", ascend_enable_setup); + +static int __init ascend_mini_enable_setup(char *s) +{ +#ifdef CONFIG_GPIO_DWAPB + extern bool enable_ascend_mini_gpio_dwapb; + + enable_ascend_mini_gpio_dwapb = true; +#endif + return 1; +} +__setup("ascend_mini_enable", ascend_mini_enable_setup); #endif diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c index 044888fd96a1f..2cdbb4a11075f 100644 --- a/drivers/gpio/gpio-dwapb.c +++ b/drivers/gpio/gpio-dwapb.c @@ -50,6 +50,9 @@ #define GPIO_EXT_PORTB 0x54 #define GPIO_EXT_PORTC 0x58 #define GPIO_EXT_PORTD 0x5c +#define GPIO_INTCOMB_MASK 0xffc +#define GPIO_INT_MASK_REG 0x3804 +#define MEM_PERI_SUBCTRL_IOBASE 0x1 #define DWAPB_MAX_PORTS 4 #define GPIO_EXT_PORT_STRIDE 0x04 /* register stride 32 bits */ @@ -64,6 +67,8 @@ #define GPIO_INTSTATUS_V2 0x3c #define GPIO_PORTA_EOI_V2 0x40 +bool enable_ascend_mini_gpio_dwapb; +bool enable_ascend_gpio_dwapb; struct dwapb_gpio; #ifdef CONFIG_PM_SLEEP @@ -77,10 +82,11 @@ struct dwapb_context { u32 int_type; u32 int_pol; u32 int_deb; + u32 int_comb_mask; u32 wake_en; }; #endif - +static void __iomem *peri_subctrl_base_addr; struct dwapb_gpio_port { struct gpio_chip gc; bool is_registered; @@ -232,6 +238,11 @@ static void dwapb_irq_enable(struct irq_data *d) val = dwapb_read(gpio, GPIO_INTEN); val |= BIT(d->hwirq); dwapb_write(gpio, GPIO_INTEN, val); + if (enable_ascend_gpio_dwapb) { + val = dwapb_read(gpio, GPIO_INTMASK); + val &= ~BIT(d->hwirq); + dwapb_write(gpio, GPIO_INTMASK, val); + } spin_unlock_irqrestore(&gc->bgpio_lock, flags); } @@ -244,6 +255,11 @@ static void dwapb_irq_disable(struct irq_data *d) u32 val; spin_lock_irqsave(&gc->bgpio_lock, flags); + if (enable_ascend_gpio_dwapb) { + val = dwapb_read(gpio, GPIO_INTMASK); + val |= BIT(d->hwirq); + dwapb_write(gpio, GPIO_INTMASK, val); + } val = dwapb_read(gpio, GPIO_INTEN); val &= ~BIT(d->hwirq); dwapb_write(gpio, GPIO_INTEN, val); @@ -393,6 +409,7 @@ static void dwapb_configure_irqs(struct dwapb_gpio *gpio, unsigned int hwirq, ngpio = gc->ngpio; struct irq_chip_type *ct; int err, i; + u32 val; gpio->domain = irq_domain_create_linear(fwnode, ngpio, &irq_generic_chip_ops, gpio); @@ -470,6 +487,12 @@ static void dwapb_configure_irqs(struct dwapb_gpio *gpio, irq_create_mapping(gpio->domain, hwirq); port->gc.to_irq = dwapb_gpio_to_irq; + + if (enable_ascend_gpio_dwapb) { + val = dwapb_read(gpio, GPIO_INTCOMB_MASK); + val |= BIT(0); + dwapb_write(gpio, GPIO_INTCOMB_MASK, val); + } } static void dwapb_irq_teardown(struct dwapb_gpio *gpio) @@ -478,6 +501,7 @@ static void dwapb_irq_teardown(struct dwapb_gpio *gpio) struct gpio_chip *gc = &port->gc; unsigned int ngpio = gc->ngpio; irq_hw_number_t hwirq; + u32 val; if (!gpio->domain) return; @@ -487,6 +511,12 @@ static void dwapb_irq_teardown(struct dwapb_gpio *gpio) irq_domain_remove(gpio->domain); gpio->domain = NULL; + + if (enable_ascend_gpio_dwapb) { + val = dwapb_read(gpio, GPIO_INTCOMB_MASK); + val &= ~BIT(0); + dwapb_write(gpio, GPIO_INTCOMB_MASK, val); + } } static int dwapb_gpio_add_port(struct dwapb_gpio *gpio, @@ -660,6 +690,22 @@ static int dwapb_gpio_probe(struct platform_device *pdev) int err; struct device *dev = &pdev->dev; struct dwapb_platform_data *pdata = dev_get_platdata(dev); + struct device_node *np = dev->of_node; + unsigned int value; + + if (enable_ascend_mini_gpio_dwapb && enable_ascend_gpio_dwapb) { + peri_subctrl_base_addr = of_iomap(np, MEM_PERI_SUBCTRL_IOBASE); + if (!peri_subctrl_base_addr) { + dev_err(&pdev->dev, "sysctrl iomap not find!\n"); + } else { + dev_dbg(&pdev->dev, "sysctrl iomap find!\n"); + value = readl(peri_subctrl_base_addr + + GPIO_INT_MASK_REG); + value &= ~1UL; + writel(value, peri_subctrl_base_addr + + GPIO_INT_MASK_REG); + } + } if (!pdata) { pdata = dwapb_gpio_get_pdata(dev); @@ -742,6 +788,10 @@ static int dwapb_gpio_remove(struct platform_device *pdev) reset_control_assert(gpio->rst); clk_disable_unprepare(gpio->clk); + if ((peri_subctrl_base_addr != NULL) && enable_ascend_mini_gpio_dwapb && + enable_ascend_gpio_dwapb) + iounmap(peri_subctrl_base_addr); + return 0; } @@ -778,6 +828,9 @@ static int dwapb_gpio_suspend(struct device *dev) ctx->int_pol = dwapb_read(gpio, GPIO_INT_POLARITY); ctx->int_type = dwapb_read(gpio, GPIO_INTTYPE_LEVEL); ctx->int_deb = dwapb_read(gpio, GPIO_PORTA_DEBOUNCE); + if (enable_ascend_gpio_dwapb) + ctx->int_comb_mask = + dwapb_read(gpio, GPIO_INTCOMB_MASK); /* Mask out interrupts */ dwapb_write(gpio, GPIO_INTMASK, @@ -798,6 +851,7 @@ static int dwapb_gpio_resume(struct device *dev) struct gpio_chip *gc = &gpio->ports[0].gc; unsigned long flags; int i; + unsigned int value; if (!IS_ERR(gpio->clk)) clk_prepare_enable(gpio->clk); @@ -826,6 +880,9 @@ static int dwapb_gpio_resume(struct device *dev) dwapb_write(gpio, GPIO_PORTA_DEBOUNCE, ctx->int_deb); dwapb_write(gpio, GPIO_INTEN, ctx->int_en); dwapb_write(gpio, GPIO_INTMASK, ctx->int_mask); + if (enable_ascend_gpio_dwapb) + dwapb_write(gpio, + GPIO_INTCOMB_MASK, ctx->int_comb_mask); /* Clear out spurious interrupts */ dwapb_write(gpio, GPIO_PORTA_EOI, 0xffffffff); @@ -833,6 +890,13 @@ static int dwapb_gpio_resume(struct device *dev) } spin_unlock_irqrestore(&gc->bgpio_lock, flags); + if ((peri_subctrl_base_addr != NULL) && enable_ascend_mini_gpio_dwapb && + enable_ascend_gpio_dwapb) { + value = readl(peri_subctrl_base_addr + GPIO_INT_MASK_REG); + value &= ~1UL; + writel(value, peri_subctrl_base_addr + GPIO_INT_MASK_REG); + } + return 0; } #endif -- 2.25.1

1 0

[PATCH kernel-4.19] GPIO : support ascend gpio driver
by Yang Yingliang 25 Oct '21

25 Oct '21

From: wuhuaye <wuhuaye(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4DLVR CVE: NA ------------------------------------------------- Hi everyone， This patch add some special gpio register configuration. It is necessary to configure some gpio register when gpio-dwapb function is enable in Ascend platform. Signed-off-by: wuhuaye <wuhuaye(a)huawei.com> Reviewed-by: Ding Tianhong <dingtianhong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/mm/init.c | 17 ++++++++++ drivers/gpio/gpio-dwapb.c | 66 ++++++++++++++++++++++++++++++++++++++- 2 files changed, 82 insertions(+), 1 deletion(-) diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 2399a257eaf33..8cdf92626c2c6 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -944,6 +944,12 @@ __setup("keepinitrd", keepinitrd_setup); void ascend_enable_all_features(void) { +#ifdef CONFIG_GPIO_DWAPB + extern bool enable_ascend_gpio_dwapb; + + enable_ascend_gpio_dwapb = true; +#endif + if (IS_ENABLED(CONFIG_ASCEND_DVPP_MMAP)) enable_mmap_dvpp = 1; @@ -981,6 +987,17 @@ static int __init ascend_enable_setup(char *__unused) } early_param("ascend_enable_all", ascend_enable_setup); + +static int __init ascend_mini_enable_setup(char *s) +{ +#ifdef CONFIG_GPIO_DWAPB + extern bool enable_ascend_mini_gpio_dwapb; + + enable_ascend_mini_gpio_dwapb = true; +#endif + return 1; +} +__setup("ascend_mini_enable", ascend_mini_enable_setup); #endif diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c index 2a56efced7988..4c332f0ed8524 100644 --- a/drivers/gpio/gpio-dwapb.c +++ b/drivers/gpio/gpio-dwapb.c @@ -50,6 +50,9 @@ #define GPIO_EXT_PORTB 0x54 #define GPIO_EXT_PORTC 0x58 #define GPIO_EXT_PORTD 0x5c +#define GPIO_INTCOMB_MASK 0xffc +#define GPIO_INT_MASK_REG 0x3804 +#define MEM_PERI_SUBCTRL_IOBASE 0x1 #define DWAPB_DRIVER_NAME "gpio-dwapb" #define DWAPB_MAX_PORTS 4 @@ -66,6 +69,8 @@ #define GPIO_INTSTATUS_V2 0x3c #define GPIO_PORTA_EOI_V2 0x40 +bool enable_ascend_mini_gpio_dwapb; +bool enable_ascend_gpio_dwapb; struct dwapb_gpio; #ifdef CONFIG_PM_SLEEP @@ -79,10 +84,11 @@ struct dwapb_context { u32 int_type; u32 int_pol; u32 int_deb; + u32 int_comb_mask; u32 wake_en; }; #endif - +static void __iomem *peri_subctrl_base_addr; struct dwapb_gpio_port { struct gpio_chip gc; bool is_registered; @@ -234,6 +240,11 @@ static void dwapb_irq_enable(struct irq_data *d) val = dwapb_read(gpio, GPIO_INTEN); val |= BIT(d->hwirq); dwapb_write(gpio, GPIO_INTEN, val); + if (enable_ascend_gpio_dwapb) { + val = dwapb_read(gpio, GPIO_INTMASK); + val &= ~BIT(d->hwirq); + dwapb_write(gpio, GPIO_INTMASK, val); + } spin_unlock_irqrestore(&gc->bgpio_lock, flags); } @@ -246,6 +257,11 @@ static void dwapb_irq_disable(struct irq_data *d) u32 val; spin_lock_irqsave(&gc->bgpio_lock, flags); + if (enable_ascend_gpio_dwapb) { + val = dwapb_read(gpio, GPIO_INTMASK); + val |= BIT(d->hwirq); + dwapb_write(gpio, GPIO_INTMASK, val); + } val = dwapb_read(gpio, GPIO_INTEN); val &= ~BIT(d->hwirq); dwapb_write(gpio, GPIO_INTEN, val); @@ -395,6 +411,7 @@ static void dwapb_configure_irqs(struct dwapb_gpio *gpio, unsigned int hwirq, ngpio = gc->ngpio; struct irq_chip_type *ct; int err, i; + u32 val; gpio->domain = irq_domain_create_linear(fwnode, ngpio, &irq_generic_chip_ops, gpio); @@ -472,6 +489,12 @@ static void dwapb_configure_irqs(struct dwapb_gpio *gpio, irq_create_mapping(gpio->domain, hwirq); port->gc.to_irq = dwapb_gpio_to_irq; + + if (enable_ascend_gpio_dwapb) { + val = dwapb_read(gpio, GPIO_INTCOMB_MASK); + val |= BIT(0); + dwapb_write(gpio, GPIO_INTCOMB_MASK, val); + } } static void dwapb_irq_teardown(struct dwapb_gpio *gpio) @@ -480,6 +503,7 @@ static void dwapb_irq_teardown(struct dwapb_gpio *gpio) struct gpio_chip *gc = &port->gc; unsigned int ngpio = gc->ngpio; irq_hw_number_t hwirq; + u32 val; if (!gpio->domain) return; @@ -489,6 +513,12 @@ static void dwapb_irq_teardown(struct dwapb_gpio *gpio) irq_domain_remove(gpio->domain); gpio->domain = NULL; + + if (enable_ascend_gpio_dwapb) { + val = dwapb_read(gpio, GPIO_INTCOMB_MASK); + val &= ~BIT(0); + dwapb_write(gpio, GPIO_INTCOMB_MASK, val); + } } static int dwapb_gpio_add_port(struct dwapb_gpio *gpio, @@ -669,6 +699,22 @@ static int dwapb_gpio_probe(struct platform_device *pdev) int err; struct device *dev = &pdev->dev; struct dwapb_platform_data *pdata = dev_get_platdata(dev); + struct device_node *np = dev->of_node; + unsigned int value; + + if (enable_ascend_mini_gpio_dwapb && enable_ascend_gpio_dwapb) { + peri_subctrl_base_addr = of_iomap(np, MEM_PERI_SUBCTRL_IOBASE); + if (!peri_subctrl_base_addr) { + dev_err(&pdev->dev, "sysctrl iomap not find!\n"); + } else { + dev_dbg(&pdev->dev, "sysctrl iomap find!\n"); + value = readl(peri_subctrl_base_addr + + GPIO_INT_MASK_REG); + value &= ~1UL; + writel(value, peri_subctrl_base_addr + + GPIO_INT_MASK_REG); + } + } if (!pdata) { pdata = dwapb_gpio_get_pdata(dev); @@ -751,6 +797,10 @@ static int dwapb_gpio_remove(struct platform_device *pdev) reset_control_assert(gpio->rst); clk_disable_unprepare(gpio->clk); + if ((peri_subctrl_base_addr != NULL) && enable_ascend_mini_gpio_dwapb && + enable_ascend_gpio_dwapb) + iounmap(peri_subctrl_base_addr); + return 0; } @@ -787,6 +837,9 @@ static int dwapb_gpio_suspend(struct device *dev) ctx->int_pol = dwapb_read(gpio, GPIO_INT_POLARITY); ctx->int_type = dwapb_read(gpio, GPIO_INTTYPE_LEVEL); ctx->int_deb = dwapb_read(gpio, GPIO_PORTA_DEBOUNCE); + if (enable_ascend_gpio_dwapb) + ctx->int_comb_mask = + dwapb_read(gpio, GPIO_INTCOMB_MASK); /* Mask out interrupts */ dwapb_write(gpio, GPIO_INTMASK, @@ -807,6 +860,7 @@ static int dwapb_gpio_resume(struct device *dev) struct gpio_chip *gc = &gpio->ports[0].gc; unsigned long flags; int i; + unsigned int value; if (!IS_ERR(gpio->clk)) clk_prepare_enable(gpio->clk); @@ -835,6 +889,9 @@ static int dwapb_gpio_resume(struct device *dev) dwapb_write(gpio, GPIO_PORTA_DEBOUNCE, ctx->int_deb); dwapb_write(gpio, GPIO_INTEN, ctx->int_en); dwapb_write(gpio, GPIO_INTMASK, ctx->int_mask); + if (enable_ascend_gpio_dwapb) + dwapb_write(gpio, + GPIO_INTCOMB_MASK, ctx->int_comb_mask); /* Clear out spurious interrupts */ dwapb_write(gpio, GPIO_PORTA_EOI, 0xffffffff); @@ -842,6 +899,13 @@ static int dwapb_gpio_resume(struct device *dev) } spin_unlock_irqrestore(&gc->bgpio_lock, flags); + if ((peri_subctrl_base_addr != NULL) && enable_ascend_mini_gpio_dwapb && + enable_ascend_gpio_dwapb) { + value = readl(peri_subctrl_base_addr + GPIO_INT_MASK_REG); + value &= ~1UL; + writel(value, peri_subctrl_base_addr + GPIO_INT_MASK_REG); + } + return 0; } #endif -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 1/9] iommu/arm-smmu-v3: Add support to configure mpam in STE/CD context
by Yang Yingliang 25 Oct '21

25 Oct '21

From: Xingang Wang <wangxingang5(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I49RB2 CVE: NA ------------------------------------------------- To support limiting qos of device, the partid and pmg need to be set into the SMMU STE/CD context. This introduce support of SMMU mpam feature and add interface to set mpam configuration in STE/CD. Signed-off-by: Xingang Wang <wangxingang5(a)huawei.com> Signed-off-by: Rui Zhu <zhurui3(a)huawei.com> Reviewed-by: Yingtai Xie <xieyingtai(a)huawei.com> Reviewed-by: Zhen Lei <thunder.leizhen(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/iommu/arm-smmu-v3-context.c | 25 +++++ drivers/iommu/arm-smmu-v3.c | 151 ++++++++++++++++++++++++++++ include/linux/ascend_smmu.h | 9 ++ 3 files changed, 185 insertions(+) create mode 100644 include/linux/ascend_smmu.h diff --git a/drivers/iommu/arm-smmu-v3-context.c b/drivers/iommu/arm-smmu-v3-context.c index 2351de86d31f1..b30a93e076608 100644 --- a/drivers/iommu/arm-smmu-v3-context.c +++ b/drivers/iommu/arm-smmu-v3-context.c @@ -66,6 +66,9 @@ #define CTXDESC_CD_1_TTB0_MASK GENMASK_ULL(51, 4) +#define CTXDESC_CD_5_PARTID_MASK GENMASK_ULL(47, 32) +#define CTXDESC_CD_5_PMG_MASK GENMASK_ULL(55, 48) + /* Convert between AArch64 (CPU) TCR format and SMMU CD format */ #define ARM_SMMU_TCR2CD(tcr, fld) FIELD_PREP(CTXDESC_CD_0_TCR_##fld, \ FIELD_GET(ARM64_TCR_##fld, tcr)) @@ -563,6 +566,28 @@ static int arm_smmu_set_cd(struct iommu_pasid_table_ops *ops, int pasid, return arm_smmu_write_ctx_desc(tbl, pasid, cd); } +int arm_smmu_set_cd_mpam(struct iommu_pasid_table_ops *ops, + int ssid, int partid, int pmg) +{ + struct arm_smmu_cd_tables *tbl = pasid_ops_to_tables(ops); + u64 val; + __le64 *cdptr = arm_smmu_get_cd_ptr(tbl, ssid); + + if (!cdptr) + return -ENOMEM; + + val = le64_to_cpu(cdptr[5]); + val &= ~CTXDESC_CD_5_PARTID_MASK; + val |= FIELD_PREP(CTXDESC_CD_5_PARTID_MASK, partid); + val &= ~CTXDESC_CD_5_PMG_MASK; + val |= FIELD_PREP(CTXDESC_CD_5_PMG_MASK, pmg); + WRITE_ONCE(cdptr[5], cpu_to_le64(val)); + + iommu_pasid_flush(&tbl->pasid, ssid, true); + + return 0; +} + static void arm_smmu_clear_cd(struct iommu_pasid_table_ops *ops, int pasid, struct iommu_pasid_entry *entry) { diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 6731b47558f4d..c282fc129222f 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -88,6 +88,10 @@ #define IDR1_SSIDSIZE GENMASK(10, 6) #define IDR1_SIDSIZE GENMASK(5, 0) +#define ARM_SMMU_IDR3 0xc +#define IDR3_MPAM (1 << 7) +#define ARM_SMMU_IDR3_CFG 0x140C + #define ARM_SMMU_IDR5 0x14 #define IDR5_STALL_MAX GENMASK(31, 16) #define IDR5_GRAN64K (1 << 6) @@ -186,6 +190,10 @@ #define ARM_SMMU_PRIQ_IRQ_CFG1 0xd8 #define ARM_SMMU_PRIQ_IRQ_CFG2 0xdc +#define ARM_SMMU_MPAMIDR 0x130 +#define MPAMIDR_PMG_MAX GENMASK(23, 16) +#define MPAMIDR_PARTID_MAX GENMASK(15, 0) + /* Common MSI config fields */ #define MSI_CFG0_ADDR_MASK GENMASK_ULL(51, 2) #define MSI_CFG2_SH GENMASK(5, 4) @@ -250,6 +258,7 @@ #define STRTAB_STE_1_S1COR GENMASK_ULL(5, 4) #define STRTAB_STE_1_S1CSH GENMASK_ULL(7, 6) +#define STRTAB_STE_1_S1MPAM (1UL << 26) #define STRTAB_STE_1_S1STALLD (1UL << 27) #define STRTAB_STE_1_EATS GENMASK_ULL(29, 28) @@ -273,6 +282,11 @@ #define STRTAB_STE_3_S2TTB_MASK GENMASK_ULL(51, 4) +#define STRTAB_STE_4_PARTID_MASK GENMASK_ULL(31, 16) + +#define STRTAB_STE_5_MPAM_NS (1UL << 8) +#define STRTAB_STE_5_PMG_MASK GENMASK_ULL(7, 0) + /* Command queue */ #define CMDQ_ENT_SZ_SHIFT 4 #define CMDQ_ENT_DWORDS ((1 << CMDQ_ENT_SZ_SHIFT) >> 3) @@ -634,6 +648,7 @@ struct arm_smmu_device { #define ARM_SMMU_FEAT_SVA (1 << 17) #define ARM_SMMU_FEAT_HA (1 << 18) #define ARM_SMMU_FEAT_HD (1 << 19) +#define ARM_SMMU_FEAT_MPAM (1 << 20) u32 features; #define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) @@ -672,6 +687,9 @@ struct arm_smmu_device { struct mutex streams_mutex; struct iopf_queue *iopf_queue; + + unsigned int mpam_partid_max; + unsigned int mpam_pmg_max; }; struct arm_smmu_stream { @@ -3977,6 +3995,25 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) if (smmu->sid_bits <= STRTAB_SPLIT) smmu->features &= ~ARM_SMMU_FEAT_2_LVL_STRTAB; + /* IDR3 */ + reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3); + + if (!(reg & IDR3_MPAM)) { + reg |= FIELD_PREP(IDR3_MPAM, 1); + writel(reg, smmu->base + ARM_SMMU_IDR3_CFG); + reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3); + if (!(reg & IDR3_MPAM)) + dev_warn(smmu->dev, "enable smmu mpam failed\n"); + } + + if (reg & IDR3_MPAM) { + reg = readl_relaxed(smmu->base + ARM_SMMU_MPAMIDR); + smmu->mpam_partid_max = FIELD_GET(MPAMIDR_PARTID_MAX, reg); + smmu->mpam_pmg_max = FIELD_GET(MPAMIDR_PMG_MAX, reg); + if (smmu->mpam_partid_max || smmu->mpam_pmg_max) + smmu->features |= ARM_SMMU_FEAT_MPAM; + } + /* IDR5 */ reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5); @@ -4124,6 +4161,120 @@ static unsigned long arm_smmu_resource_size(struct arm_smmu_device *smmu) return SZ_128K; } +static int arm_smmu_set_ste_mpam(struct arm_smmu_device *smmu, + int sid, int partid, int pmg, int s1mpam) +{ + u64 val; + __le64 *ste; + + if (!arm_smmu_sid_in_range(smmu, sid)) + return -ERANGE; + + /* get ste ptr */ + ste = arm_smmu_get_step_for_sid(smmu, sid); + + /* write s1mpam to ste */ + val = le64_to_cpu(ste[1]); + val &= ~STRTAB_STE_1_S1MPAM; + val |= FIELD_PREP(STRTAB_STE_1_S1MPAM, s1mpam); + WRITE_ONCE(ste[1], cpu_to_le64(val)); + + val = le64_to_cpu(ste[4]); + val &= ~STRTAB_STE_4_PARTID_MASK; + val |= FIELD_PREP(STRTAB_STE_4_PARTID_MASK, partid); + WRITE_ONCE(ste[4], cpu_to_le64(val)); + + val = le64_to_cpu(ste[5]); + val &= ~STRTAB_STE_5_PMG_MASK; + val |= FIELD_PREP(STRTAB_STE_5_PMG_MASK, pmg); + WRITE_ONCE(ste[5], cpu_to_le64(val)); + + arm_smmu_sync_ste_for_sid(smmu, sid); + + return 0; +} + +int arm_smmu_set_cd_mpam(struct iommu_pasid_table_ops *ops, + int ssid, int partid, int pmg); + +static int arm_smmu_set_mpam(struct arm_smmu_device *smmu, + int sid, int ssid, int partid, int pmg, int s1mpam) +{ + struct arm_smmu_master_data *master = arm_smmu_find_master(smmu, sid); + struct arm_smmu_s1_cfg *cfg = master ? master->ste.s1_cfg : NULL; + struct arm_smmu_domain *domain = master ? master->domain : NULL; + int ret; + + struct arm_smmu_cmdq_ent prefetch_cmd = { + .opcode = CMDQ_OP_PREFETCH_CFG, + .prefetch = { + .sid = sid, + }, + }; + + if (!(smmu->features & ARM_SMMU_FEAT_MPAM)) + return -ENODEV; + + if (WARN_ON(!domain)) + return -EINVAL; + + if (WARN_ON(!cfg)) + return -EINVAL; + + if (WARN_ON(ssid >= (1 << master->ssid_bits))) + return -E2BIG; + + if (partid > smmu->mpam_partid_max || pmg > smmu->mpam_pmg_max) { + dev_err(smmu->dev, + "mpam rmid out of range: partid[0, %d] pmg[0, %d]\n", + smmu->mpam_partid_max, smmu->mpam_pmg_max); + return -ERANGE; + } + + ret = arm_smmu_set_ste_mpam(smmu, sid, partid, pmg, s1mpam); + if (ret < 0) { + dev_err(smmu->dev, "set ste mpam configuration error %d\n", + ret); + return ret; + } + + /* do not modify cd table which owned by guest */ + if (domain->stage == ARM_SMMU_DOMAIN_NESTED) { + dev_err(smmu->dev, + "mpam: smmu cd is owned by guest, not modified\n"); + return 0; + } + + ret = arm_smmu_set_cd_mpam(cfg->ops, ssid, partid, pmg); + if (s1mpam && ret < 0) { + dev_err(smmu->dev, "set cd mpam configuration error %d\n", + ret); + return ret; + } + + /* It's likely that we'll want to use the new STE soon */ + if (!(smmu->options & ARM_SMMU_OPT_SKIP_PREFETCH)) + arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd); + + dev_info(smmu->dev, "partid %d, pmg %d\n", partid, pmg); + + return 0; +} + +/** + * arm_smmu_set_dev_mpam() - Set mpam configuration to SMMU STE/CD + */ +int arm_smmu_set_dev_mpam(struct device *dev, int ssid, int partid, int pmg, + int s1mpam) +{ + struct arm_smmu_master_data *master = dev->iommu_fwspec->iommu_priv; + struct arm_smmu_device *smmu = master->domain->smmu; + int sid = master->streams->id; + + return arm_smmu_set_mpam(smmu, sid, ssid, partid, pmg, s1mpam); +} +EXPORT_SYMBOL(arm_smmu_set_dev_mpam); + static int arm_smmu_device_probe(struct platform_device *pdev) { int irq, ret; diff --git a/include/linux/ascend_smmu.h b/include/linux/ascend_smmu.h new file mode 100644 index 0000000000000..bd0edd25057e1 --- /dev/null +++ b/include/linux/ascend_smmu.h @@ -0,0 +1,9 @@ +#ifndef __LINUX_ASCEND_SMMU_H +#define __LINUX_ASCEND_SMMU_H + +#include <linux/device.h> + +extern int arm_smmu_set_dev_mpam(struct device *dev, int ssid, int partid, + int pmg, int s1mpam); + +#endif /* __LINUX_ASCEND_SMMU_H */ -- 2.25.1

1 8

[PATCH kernel-4.19 1/9] iommu/arm-smmu-v3: Add support to configure mpam in STE/CD context
by Yang Yingliang 25 Oct '21

25 Oct '21

From: Xingang Wang <wangxingang5(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I49RB2 CVE: NA ------------------------------------------------- To support limiting qos of device, the partid and pmg need to be set into the SMMU STE/CD context. This introduce support of SMMU mpam feature and add interface to set mpam configuration in STE/CD. Signed-off-by: Xingang Wang <wangxingang5(a)huawei.com> Signed-off-by: Rui Zhu <zhurui3(a)huawei.com> Reviewed-by: Yingtai Xie <xieyingtai(a)huawei.com> Reviewed-by: Zhen Lei <thunder.leizhen(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/iommu/arm-smmu-v3-context.c | 25 +++++ drivers/iommu/arm-smmu-v3.c | 151 ++++++++++++++++++++++++++++ include/linux/ascend_smmu.h | 9 ++ 3 files changed, 185 insertions(+) create mode 100644 include/linux/ascend_smmu.h diff --git a/drivers/iommu/arm-smmu-v3-context.c b/drivers/iommu/arm-smmu-v3-context.c index 2351de86d31f1..b30a93e076608 100644 --- a/drivers/iommu/arm-smmu-v3-context.c +++ b/drivers/iommu/arm-smmu-v3-context.c @@ -66,6 +66,9 @@ #define CTXDESC_CD_1_TTB0_MASK GENMASK_ULL(51, 4) +#define CTXDESC_CD_5_PARTID_MASK GENMASK_ULL(47, 32) +#define CTXDESC_CD_5_PMG_MASK GENMASK_ULL(55, 48) + /* Convert between AArch64 (CPU) TCR format and SMMU CD format */ #define ARM_SMMU_TCR2CD(tcr, fld) FIELD_PREP(CTXDESC_CD_0_TCR_##fld, \ FIELD_GET(ARM64_TCR_##fld, tcr)) @@ -563,6 +566,28 @@ static int arm_smmu_set_cd(struct iommu_pasid_table_ops *ops, int pasid, return arm_smmu_write_ctx_desc(tbl, pasid, cd); } +int arm_smmu_set_cd_mpam(struct iommu_pasid_table_ops *ops, + int ssid, int partid, int pmg) +{ + struct arm_smmu_cd_tables *tbl = pasid_ops_to_tables(ops); + u64 val; + __le64 *cdptr = arm_smmu_get_cd_ptr(tbl, ssid); + + if (!cdptr) + return -ENOMEM; + + val = le64_to_cpu(cdptr[5]); + val &= ~CTXDESC_CD_5_PARTID_MASK; + val |= FIELD_PREP(CTXDESC_CD_5_PARTID_MASK, partid); + val &= ~CTXDESC_CD_5_PMG_MASK; + val |= FIELD_PREP(CTXDESC_CD_5_PMG_MASK, pmg); + WRITE_ONCE(cdptr[5], cpu_to_le64(val)); + + iommu_pasid_flush(&tbl->pasid, ssid, true); + + return 0; +} + static void arm_smmu_clear_cd(struct iommu_pasid_table_ops *ops, int pasid, struct iommu_pasid_entry *entry) { diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 8b5083c3e0a16..6634d596f7efc 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -88,6 +88,10 @@ #define IDR1_SSIDSIZE GENMASK(10, 6) #define IDR1_SIDSIZE GENMASK(5, 0) +#define ARM_SMMU_IDR3 0xc +#define IDR3_MPAM (1 << 7) +#define ARM_SMMU_IDR3_CFG 0x140C + #define ARM_SMMU_IDR5 0x14 #define IDR5_STALL_MAX GENMASK(31, 16) #define IDR5_GRAN64K (1 << 6) @@ -186,6 +190,10 @@ #define ARM_SMMU_PRIQ_IRQ_CFG1 0xd8 #define ARM_SMMU_PRIQ_IRQ_CFG2 0xdc +#define ARM_SMMU_MPAMIDR 0x130 +#define MPAMIDR_PMG_MAX GENMASK(23, 16) +#define MPAMIDR_PARTID_MAX GENMASK(15, 0) + /* Common MSI config fields */ #define MSI_CFG0_ADDR_MASK GENMASK_ULL(51, 2) #define MSI_CFG2_SH GENMASK(5, 4) @@ -250,6 +258,7 @@ #define STRTAB_STE_1_S1COR GENMASK_ULL(5, 4) #define STRTAB_STE_1_S1CSH GENMASK_ULL(7, 6) +#define STRTAB_STE_1_S1MPAM (1UL << 26) #define STRTAB_STE_1_S1STALLD (1UL << 27) #define STRTAB_STE_1_EATS GENMASK_ULL(29, 28) @@ -273,6 +282,11 @@ #define STRTAB_STE_3_S2TTB_MASK GENMASK_ULL(51, 4) +#define STRTAB_STE_4_PARTID_MASK GENMASK_ULL(31, 16) + +#define STRTAB_STE_5_MPAM_NS (1UL << 8) +#define STRTAB_STE_5_PMG_MASK GENMASK_ULL(7, 0) + /* Command queue */ #define CMDQ_ENT_SZ_SHIFT 4 #define CMDQ_ENT_DWORDS ((1 << CMDQ_ENT_SZ_SHIFT) >> 3) @@ -634,6 +648,7 @@ struct arm_smmu_device { #define ARM_SMMU_FEAT_SVA (1 << 17) #define ARM_SMMU_FEAT_HA (1 << 18) #define ARM_SMMU_FEAT_HD (1 << 19) +#define ARM_SMMU_FEAT_MPAM (1 << 20) u32 features; #define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) @@ -672,6 +687,9 @@ struct arm_smmu_device { struct mutex streams_mutex; struct iopf_queue *iopf_queue; + + unsigned int mpam_partid_max; + unsigned int mpam_pmg_max; }; struct arm_smmu_stream { @@ -3980,6 +3998,25 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) if (smmu->sid_bits <= STRTAB_SPLIT) smmu->features &= ~ARM_SMMU_FEAT_2_LVL_STRTAB; + /* IDR3 */ + reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3); + + if (!(reg & IDR3_MPAM)) { + reg |= FIELD_PREP(IDR3_MPAM, 1); + writel(reg, smmu->base + ARM_SMMU_IDR3_CFG); + reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3); + if (!(reg & IDR3_MPAM)) + dev_warn(smmu->dev, "enable smmu mpam failed\n"); + } + + if (reg & IDR3_MPAM) { + reg = readl_relaxed(smmu->base + ARM_SMMU_MPAMIDR); + smmu->mpam_partid_max = FIELD_GET(MPAMIDR_PARTID_MAX, reg); + smmu->mpam_pmg_max = FIELD_GET(MPAMIDR_PMG_MAX, reg); + if (smmu->mpam_partid_max || smmu->mpam_pmg_max) + smmu->features |= ARM_SMMU_FEAT_MPAM; + } + /* IDR5 */ reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5); @@ -4127,6 +4164,120 @@ static unsigned long arm_smmu_resource_size(struct arm_smmu_device *smmu) return SZ_128K; } +static int arm_smmu_set_ste_mpam(struct arm_smmu_device *smmu, + int sid, int partid, int pmg, int s1mpam) +{ + u64 val; + __le64 *ste; + + if (!arm_smmu_sid_in_range(smmu, sid)) + return -ERANGE; + + /* get ste ptr */ + ste = arm_smmu_get_step_for_sid(smmu, sid); + + /* write s1mpam to ste */ + val = le64_to_cpu(ste[1]); + val &= ~STRTAB_STE_1_S1MPAM; + val |= FIELD_PREP(STRTAB_STE_1_S1MPAM, s1mpam); + WRITE_ONCE(ste[1], cpu_to_le64(val)); + + val = le64_to_cpu(ste[4]); + val &= ~STRTAB_STE_4_PARTID_MASK; + val |= FIELD_PREP(STRTAB_STE_4_PARTID_MASK, partid); + WRITE_ONCE(ste[4], cpu_to_le64(val)); + + val = le64_to_cpu(ste[5]); + val &= ~STRTAB_STE_5_PMG_MASK; + val |= FIELD_PREP(STRTAB_STE_5_PMG_MASK, pmg); + WRITE_ONCE(ste[5], cpu_to_le64(val)); + + arm_smmu_sync_ste_for_sid(smmu, sid); + + return 0; +} + +int arm_smmu_set_cd_mpam(struct iommu_pasid_table_ops *ops, + int ssid, int partid, int pmg); + +static int arm_smmu_set_mpam(struct arm_smmu_device *smmu, + int sid, int ssid, int partid, int pmg, int s1mpam) +{ + struct arm_smmu_master_data *master = arm_smmu_find_master(smmu, sid); + struct arm_smmu_s1_cfg *cfg = master ? master->ste.s1_cfg : NULL; + struct arm_smmu_domain *domain = master ? master->domain : NULL; + int ret; + + struct arm_smmu_cmdq_ent prefetch_cmd = { + .opcode = CMDQ_OP_PREFETCH_CFG, + .prefetch = { + .sid = sid, + }, + }; + + if (!(smmu->features & ARM_SMMU_FEAT_MPAM)) + return -ENODEV; + + if (WARN_ON(!domain)) + return -EINVAL; + + if (WARN_ON(!cfg)) + return -EINVAL; + + if (WARN_ON(ssid >= (1 << master->ssid_bits))) + return -E2BIG; + + if (partid > smmu->mpam_partid_max || pmg > smmu->mpam_pmg_max) { + dev_err(smmu->dev, + "mpam rmid out of range: partid[0, %d] pmg[0, %d]\n", + smmu->mpam_partid_max, smmu->mpam_pmg_max); + return -ERANGE; + } + + ret = arm_smmu_set_ste_mpam(smmu, sid, partid, pmg, s1mpam); + if (ret < 0) { + dev_err(smmu->dev, "set ste mpam configuration error %d\n", + ret); + return ret; + } + + /* do not modify cd table which owned by guest */ + if (domain->stage == ARM_SMMU_DOMAIN_NESTED) { + dev_err(smmu->dev, + "mpam: smmu cd is owned by guest, not modified\n"); + return 0; + } + + ret = arm_smmu_set_cd_mpam(cfg->ops, ssid, partid, pmg); + if (s1mpam && ret < 0) { + dev_err(smmu->dev, "set cd mpam configuration error %d\n", + ret); + return ret; + } + + /* It's likely that we'll want to use the new STE soon */ + if (!(smmu->options & ARM_SMMU_OPT_SKIP_PREFETCH)) + arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd); + + dev_info(smmu->dev, "partid %d, pmg %d\n", partid, pmg); + + return 0; +} + +/** + * arm_smmu_set_dev_mpam() - Set mpam configuration to SMMU STE/CD + */ +int arm_smmu_set_dev_mpam(struct device *dev, int ssid, int partid, int pmg, + int s1mpam) +{ + struct arm_smmu_master_data *master = dev->iommu_fwspec->iommu_priv; + struct arm_smmu_device *smmu = master->domain->smmu; + int sid = master->streams->id; + + return arm_smmu_set_mpam(smmu, sid, ssid, partid, pmg, s1mpam); +} +EXPORT_SYMBOL(arm_smmu_set_dev_mpam); + static int arm_smmu_device_probe(struct platform_device *pdev) { int irq, ret; diff --git a/include/linux/ascend_smmu.h b/include/linux/ascend_smmu.h new file mode 100644 index 0000000000000..bd0edd25057e1 --- /dev/null +++ b/include/linux/ascend_smmu.h @@ -0,0 +1,9 @@ +#ifndef __LINUX_ASCEND_SMMU_H +#define __LINUX_ASCEND_SMMU_H + +#include <linux/device.h> + +extern int arm_smmu_set_dev_mpam(struct device *dev, int ssid, int partid, + int pmg, int s1mpam); + +#endif /* __LINUX_ASCEND_SMMU_H */ -- 2.25.1

1 8

[PATCH openEuler-1.0-LTS 0/6] Fix the problem that the number of tcp timeout retransmissions is lost
by jiazhenyuan 25 Oct '21

25 Oct '21

From: Jiazhenyuan <jiazhenyuan(a)uniontech.com> issue: https://gitee.com/openeuler/kernel/issues/I4AFRJ?from=project-issue jiazhenyuan (6): tcp: switch tcp and sch_fq to new earliest departure time net_sched: sch_fq: ensure maxrate fq parameter applies to EDT flows From 9efdda4e3abed13f0903b7b6e4d4c2102019440a Mon Sep 17 00:00:00 2001 From: Eric Dumazet <edumazet(a)google.com> Date: Sat, 24 Nov 2018 09:12:24 -0800 Subject: [PATCH] tcp: address problems caused by EDT misshaps From 7ae189759cc48cf8b54beebff566e9fd2d4e7d7c Mon Sep 17 00:00:00 2001 From: Yuchung Cheng <ycheng(a)google.com> Date: Wed, 16 Jan 2019 15:05:30 -0800 Subject: [PATCH] tcp: always set retrans_stamp on recovery From 01a523b071618abbc634d1958229fe3bd2dfa5fa Mon Sep 17 00:00:00 2001 From: Yuchung Cheng <ycheng(a)google.com> Date: Wed, 16 Jan 2019 15:05:32 -0800 Subject: [PATCH] tcp: create a helper to model exponential backoff From 3256a2d6ab1f71f9a1bd2d7f6f18eb8108c48d17 Mon Sep 17 00:00:00 2001 From: Eric Dumazet <edumazet(a)google.com> Date: Mon, 30 Sep 2019 15:44:44 -0700 Subject: [PATCH] tcp: adjust rto_base in retransmits_timed_out() net/ipv4/tcp_bbr.c | 7 +++-- net/ipv4/tcp_input.c | 17 +++++++----- net/ipv4/tcp_output.c | 29 ++++++++++++++------ net/ipv4/tcp_timer.c | 64 ++++++++++++++++++++----------------------- net/sched/sch_fq.c | 46 ++++++++++++++++++------------- 5 files changed, 92 insertions(+), 71 deletions(-) -- 2.27.0

2 7

[PATCH openEuler-1.0-LTS] nvme-rdma: destroy cm id before destroy qp to avoid use after free
by Yang Yingliang 25 Oct '21

25 Oct '21

From: Ruozhu Li <liruozhu(a)huawei.com> mainline inclusion from mainline-v5.15-rc2 commit 9817d763dbe15327b9b3ff4404fa6f27f927e744 category: bugfix bugzilla: NA CVE: NA Link: https://gitee.com/openeuler/kernel/issues/I1WGZE We got a panic when host received a rej cm event soon after a connect error cm event. When host get connect error cm event, it will destroy qp immediately. But cm_id is still valid then.Another cm event rise here, try to access the qp which was destroyed.Then we got a kernel panic blow: [87816.777089] [20473] ib_cm:cm_rep_handler:2343: cm_rep_handler: Stale connection. local_comm_id -154357094, remote_comm_id -1133609861 [87816.777223] [20473] ib_cm:cm_init_qp_rtr_attr:4162: cm_init_qp_rtr_attr: local_id -1150387077, cm_id_priv->id.state: 13 [87816.777225] [20473] rdma_cm:cma_rep_recv:1871: RDMA CM: CONNECT_ERROR: failed to handle reply. status -22 [87816.777395] [20473] ib_cm:ib_send_cm_rej:2781: ib_send_cm_rej: local_id -1150387077, cm_id->state: 13 [87816.777398] [20473] nvme_rdma:nvme_rdma_cm_handler:1718: nvme nvme278: connect error (6): status -22 id 00000000c3809aff [87816.801155] [20473] nvme_rdma:nvme_rdma_cm_handler:1742: nvme nvme278: CM error event 6 [87816.801160] [20473] rdma_cm:cma_ib_handler:1947: RDMA CM: REJECTED: consumer defined [87816.801163] nvme nvme278: rdma connection establishment failed (-104) [87816.801168] BUG: unable to handle kernel NULL pointer dereference at 0000000000000370 [87816.801201] RIP: 0010:_ib_modify_qp+0x6e/0x3a0 [ib_core] [87816.801215] Call Trace: [87816.801223] cma_modify_qp_err+0x52/0x80 [rdma_cm] [87816.801228] ? __dynamic_pr_debug+0x8a/0xb0 [87816.801232] cma_ib_handler+0x25a/0x2f0 [rdma_cm] [87816.801235] cm_process_work+0x60/0xe0 [ib_cm] [87816.801238] cm_work_handler+0x13b/0x1b97 [ib_cm] [87816.801243] ? __switch_to_asm+0x35/0x70 [87816.801244] ? __switch_to_asm+0x41/0x70 [87816.801246] ? __switch_to_asm+0x35/0x70 [87816.801248] ? __switch_to_asm+0x41/0x70 [87816.801252] ? __switch_to+0x8c/0x480 [87816.801254] ? __switch_to_asm+0x41/0x70 [87816.801256] ? __switch_to_asm+0x35/0x70 [87816.801259] process_one_work+0x1a7/0x3b0 [87816.801263] worker_thread+0x30/0x390 [87816.801266] ? create_worker+0x1a0/0x1a0 [87816.801268] kthread+0x112/0x130 [87816.801270] ? kthread_flush_work_fn+0x10/0x10 [87816.801272] ret_from_fork+0x35/0x40 ------------------------------------------------- We should always destroy cm_id before destroy qp to avoid to get cma event after qp was destroyed, which may lead to use after free. In RDMA connection establishment error flow, don't destroy qp in cm event handler.Just report cm_error to upper level, qp will be destroy in nvme_rdma_alloc_queue() after destroy cm id. Signed-off-by: Ruozhu Li <liruozhu(a)huawei.com> Reviewed-by: Max Gurtovoy <mgurtovoy(a)nvidia.com> Signed-off-by: Christoph Hellwig <hch(a)lst.de> Conflicts: drivers/nvme/host/rdma.c [lrz: adjust context] Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/nvme/host/rdma.c | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index b8e0d637ddcfc..049edb9ed1858 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -575,8 +575,8 @@ static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue) if (!test_and_clear_bit(NVME_RDMA_Q_ALLOCATED, &queue->flags)) return; - nvme_rdma_destroy_queue_ib(queue); rdma_destroy_id(queue->cm_id); + nvme_rdma_destroy_queue_ib(queue); mutex_destroy(&queue->queue_lock); } @@ -1509,14 +1509,10 @@ static int nvme_rdma_conn_established(struct nvme_rdma_queue *queue) for (i = 0; i < queue->queue_size; i++) { ret = nvme_rdma_post_recv(queue, &queue->rsp_ring[i]); if (ret) - goto out_destroy_queue_ib; + return ret; } return 0; - -out_destroy_queue_ib: - nvme_rdma_destroy_queue_ib(queue); - return ret; } static int nvme_rdma_conn_rejected(struct nvme_rdma_queue *queue, @@ -1608,14 +1604,10 @@ static int nvme_rdma_route_resolved(struct nvme_rdma_queue *queue) if (ret) { dev_err(ctrl->ctrl.device, "rdma_connect failed (%d).\n", ret); - goto out_destroy_queue_ib; + return ret; } return 0; - -out_destroy_queue_ib: - nvme_rdma_destroy_queue_ib(queue); - return ret; } static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, @@ -1646,8 +1638,6 @@ static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, case RDMA_CM_EVENT_ROUTE_ERROR: case RDMA_CM_EVENT_CONNECT_ERROR: case RDMA_CM_EVENT_UNREACHABLE: - nvme_rdma_destroy_queue_ib(queue); - /* fall through */ case RDMA_CM_EVENT_ADDR_ERROR: dev_dbg(queue->ctrl->ctrl.device, "CM error event %d\n", ev->event); -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] arm64: Errata: fix kabi changed by cpu_errata
by Yang Yingliang 25 Oct '21

25 Oct '21

From: Weilong Chen <chenweilong(a)huawei.com> ascend inclusion category: feature bugzilla: 46922 CVE: NA ------------------------------------- Patch "cache: Workaround HiSilicon Taishan DC CVAU" breaks the kabi symbols: cpu_hwcaps cpu_hwcap_keys Fix by using CONFIG_HISILICON_ERRATUM_1980005 to protect it. Signed-off-by: Weilong Chen <chenweilong(a)huawei.com> Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/include/asm/cpucaps.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index d6c863d2cf984..69515f9077e34 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -56,8 +56,12 @@ #define ARM64_WORKAROUND_1463225 35 #define ARM64_HAS_CRC32 36 #define ARM64_SSBS 37 +#ifdef CONFIG_HISILICON_ERRATUM_1980005 #define ARM64_WORKAROUND_HISILICON_1980005 38 #define ARM64_NCAPS 39 +#else +#define ARM64_NCAPS 38 +#endif #endif /* __ASM_CPUCAPS_H */ -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 01/45] af_unix: fix garbage collect vs MSG_PEEK
by Yang Yingliang 25 Oct '21

25 Oct '21

From: Miklos Szeredi <mszeredi(a)redhat.com> stable inclusion from linux-4.19.200 commit 1dabafa9f61118b1377fde424d9a94bf8dbf2813 -------------------------------- commit cbcf01128d0a92e131bd09f1688fe032480b65ca upstream. unix_gc() assumes that candidate sockets can never gain an external reference (i.e. be installed into an fd) while the unix_gc_lock is held. Except for MSG_PEEK this is guaranteed by modifying inflight count under the unix_gc_lock. MSG_PEEK does not touch any variable protected by unix_gc_lock (file count is not), yet it needs to be serialized with garbage collection. Do this by locking/unlocking unix_gc_lock: 1) increment file count 2) lock/unlock barrier to make sure incremented file count is visible to garbage collection 3) install file into fd This is a lock barrier (unlike smp_mb()) that ensures that garbage collection is run completely before or completely after the barrier. Cc: <stable(a)vger.kernel.org> Signed-off-by: Miklos Szeredi <mszeredi(a)redhat.com> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/unix/af_unix.c | 51 ++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 49 insertions(+), 2 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 337c4797ab167..98c253afa0db2 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1517,6 +1517,53 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer) return err; } +static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + scm->fp = scm_fp_dup(UNIXCB(skb).fp); + + /* + * Garbage collection of unix sockets starts by selecting a set of + * candidate sockets which have reference only from being in flight + * (total_refs == inflight_refs). This condition is checked once during + * the candidate collection phase, and candidates are marked as such, so + * that non-candidates can later be ignored. While inflight_refs is + * protected by unix_gc_lock, total_refs (file count) is not, hence this + * is an instantaneous decision. + * + * Once a candidate, however, the socket must not be reinstalled into a + * file descriptor while the garbage collection is in progress. + * + * If the above conditions are met, then the directed graph of + * candidates (*) does not change while unix_gc_lock is held. + * + * Any operations that changes the file count through file descriptors + * (dup, close, sendmsg) does not change the graph since candidates are + * not installed in fds. + * + * Dequeing a candidate via recvmsg would install it into an fd, but + * that takes unix_gc_lock to decrement the inflight count, so it's + * serialized with garbage collection. + * + * MSG_PEEK is special in that it does not change the inflight count, + * yet does install the socket into an fd. The following lock/unlock + * pair is to ensure serialization with garbage collection. It must be + * done between incrementing the file count and installing the file into + * an fd. + * + * If garbage collection starts after the barrier provided by the + * lock/unlock, then it will see the elevated refcount and not mark this + * as a candidate. If a garbage collection is already in progress + * before the file count was incremented, then the lock/unlock pair will + * ensure that garbage collection is finished before progressing to + * installing the fd. + * + * (*) A -> B where B is on the queue of A or B is on the queue of C + * which is on the queue of listening socket A. + */ + spin_lock(&unix_gc_lock); + spin_unlock(&unix_gc_lock); +} + static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds) { int err = 0; @@ -2142,7 +2189,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, sk_peek_offset_fwd(sk, size); if (UNIXCB(skb).fp) - scm.fp = scm_fp_dup(UNIXCB(skb).fp); + unix_peek_fds(&scm, skb); } err = (flags & MSG_TRUNC) ? skb->len - skip : size; @@ -2383,7 +2430,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, /* It is questionable, see note in unix_dgram_recvmsg. */ if (UNIXCB(skb).fp) - scm.fp = scm_fp_dup(UNIXCB(skb).fp); + unix_peek_fds(&scm, skb); sk_peek_offset_fwd(sk, chunk); -- 2.25.1

1 44

[PATCH kernel-4.19 1/9] iommu/arm-smmu-v3: Add support to configure mpam in STE/CD context
by Yang Yingliang 22 Oct '21

22 Oct '21

From: Xingang Wang <wangxingang5(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I49RB2 CVE: NA ------------------------------------------------- To support limiting qos of device, the partid and pmg need to be set into the SMMU STE/CD context. This introduce support of SMMU mpam feature and add interface to set mpam configuration in STE/CD. Signed-off-by: Xingang Wang <wangxingang5(a)huawei.com> Signed-off-by: Rui Zhu <zhurui3(a)huawei.com> Reviewed-by: Yingtai Xie <xieyingtai(a)huawei.com> Reviewed-by: Zhen Lei <thunder.leizhen(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/iommu/arm-smmu-v3-context.c | 25 +++++ drivers/iommu/arm-smmu-v3.c | 151 ++++++++++++++++++++++++++++ include/linux/ascend_smmu.h | 9 ++ 3 files changed, 185 insertions(+) create mode 100644 include/linux/ascend_smmu.h diff --git a/drivers/iommu/arm-smmu-v3-context.c b/drivers/iommu/arm-smmu-v3-context.c index 2351de86d31f1..b30a93e076608 100644 --- a/drivers/iommu/arm-smmu-v3-context.c +++ b/drivers/iommu/arm-smmu-v3-context.c @@ -66,6 +66,9 @@ #define CTXDESC_CD_1_TTB0_MASK GENMASK_ULL(51, 4) +#define CTXDESC_CD_5_PARTID_MASK GENMASK_ULL(47, 32) +#define CTXDESC_CD_5_PMG_MASK GENMASK_ULL(55, 48) + /* Convert between AArch64 (CPU) TCR format and SMMU CD format */ #define ARM_SMMU_TCR2CD(tcr, fld) FIELD_PREP(CTXDESC_CD_0_TCR_##fld, \ FIELD_GET(ARM64_TCR_##fld, tcr)) @@ -563,6 +566,28 @@ static int arm_smmu_set_cd(struct iommu_pasid_table_ops *ops, int pasid, return arm_smmu_write_ctx_desc(tbl, pasid, cd); } +int arm_smmu_set_cd_mpam(struct iommu_pasid_table_ops *ops, + int ssid, int partid, int pmg) +{ + struct arm_smmu_cd_tables *tbl = pasid_ops_to_tables(ops); + u64 val; + __le64 *cdptr = arm_smmu_get_cd_ptr(tbl, ssid); + + if (!cdptr) + return -ENOMEM; + + val = le64_to_cpu(cdptr[5]); + val &= ~CTXDESC_CD_5_PARTID_MASK; + val |= FIELD_PREP(CTXDESC_CD_5_PARTID_MASK, partid); + val &= ~CTXDESC_CD_5_PMG_MASK; + val |= FIELD_PREP(CTXDESC_CD_5_PMG_MASK, pmg); + WRITE_ONCE(cdptr[5], cpu_to_le64(val)); + + iommu_pasid_flush(&tbl->pasid, ssid, true); + + return 0; +} + static void arm_smmu_clear_cd(struct iommu_pasid_table_ops *ops, int pasid, struct iommu_pasid_entry *entry) { diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 8b5083c3e0a16..6634d596f7efc 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -88,6 +88,10 @@ #define IDR1_SSIDSIZE GENMASK(10, 6) #define IDR1_SIDSIZE GENMASK(5, 0) +#define ARM_SMMU_IDR3 0xc +#define IDR3_MPAM (1 << 7) +#define ARM_SMMU_IDR3_CFG 0x140C + #define ARM_SMMU_IDR5 0x14 #define IDR5_STALL_MAX GENMASK(31, 16) #define IDR5_GRAN64K (1 << 6) @@ -186,6 +190,10 @@ #define ARM_SMMU_PRIQ_IRQ_CFG1 0xd8 #define ARM_SMMU_PRIQ_IRQ_CFG2 0xdc +#define ARM_SMMU_MPAMIDR 0x130 +#define MPAMIDR_PMG_MAX GENMASK(23, 16) +#define MPAMIDR_PARTID_MAX GENMASK(15, 0) + /* Common MSI config fields */ #define MSI_CFG0_ADDR_MASK GENMASK_ULL(51, 2) #define MSI_CFG2_SH GENMASK(5, 4) @@ -250,6 +258,7 @@ #define STRTAB_STE_1_S1COR GENMASK_ULL(5, 4) #define STRTAB_STE_1_S1CSH GENMASK_ULL(7, 6) +#define STRTAB_STE_1_S1MPAM (1UL << 26) #define STRTAB_STE_1_S1STALLD (1UL << 27) #define STRTAB_STE_1_EATS GENMASK_ULL(29, 28) @@ -273,6 +282,11 @@ #define STRTAB_STE_3_S2TTB_MASK GENMASK_ULL(51, 4) +#define STRTAB_STE_4_PARTID_MASK GENMASK_ULL(31, 16) + +#define STRTAB_STE_5_MPAM_NS (1UL << 8) +#define STRTAB_STE_5_PMG_MASK GENMASK_ULL(7, 0) + /* Command queue */ #define CMDQ_ENT_SZ_SHIFT 4 #define CMDQ_ENT_DWORDS ((1 << CMDQ_ENT_SZ_SHIFT) >> 3) @@ -634,6 +648,7 @@ struct arm_smmu_device { #define ARM_SMMU_FEAT_SVA (1 << 17) #define ARM_SMMU_FEAT_HA (1 << 18) #define ARM_SMMU_FEAT_HD (1 << 19) +#define ARM_SMMU_FEAT_MPAM (1 << 20) u32 features; #define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) @@ -672,6 +687,9 @@ struct arm_smmu_device { struct mutex streams_mutex; struct iopf_queue *iopf_queue; + + unsigned int mpam_partid_max; + unsigned int mpam_pmg_max; }; struct arm_smmu_stream { @@ -3980,6 +3998,25 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) if (smmu->sid_bits <= STRTAB_SPLIT) smmu->features &= ~ARM_SMMU_FEAT_2_LVL_STRTAB; + /* IDR3 */ + reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3); + + if (!(reg & IDR3_MPAM)) { + reg |= FIELD_PREP(IDR3_MPAM, 1); + writel(reg, smmu->base + ARM_SMMU_IDR3_CFG); + reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3); + if (!(reg & IDR3_MPAM)) + dev_warn(smmu->dev, "enable smmu mpam failed\n"); + } + + if (reg & IDR3_MPAM) { + reg = readl_relaxed(smmu->base + ARM_SMMU_MPAMIDR); + smmu->mpam_partid_max = FIELD_GET(MPAMIDR_PARTID_MAX, reg); + smmu->mpam_pmg_max = FIELD_GET(MPAMIDR_PMG_MAX, reg); + if (smmu->mpam_partid_max || smmu->mpam_pmg_max) + smmu->features |= ARM_SMMU_FEAT_MPAM; + } + /* IDR5 */ reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5); @@ -4127,6 +4164,120 @@ static unsigned long arm_smmu_resource_size(struct arm_smmu_device *smmu) return SZ_128K; } +static int arm_smmu_set_ste_mpam(struct arm_smmu_device *smmu, + int sid, int partid, int pmg, int s1mpam) +{ + u64 val; + __le64 *ste; + + if (!arm_smmu_sid_in_range(smmu, sid)) + return -ERANGE; + + /* get ste ptr */ + ste = arm_smmu_get_step_for_sid(smmu, sid); + + /* write s1mpam to ste */ + val = le64_to_cpu(ste[1]); + val &= ~STRTAB_STE_1_S1MPAM; + val |= FIELD_PREP(STRTAB_STE_1_S1MPAM, s1mpam); + WRITE_ONCE(ste[1], cpu_to_le64(val)); + + val = le64_to_cpu(ste[4]); + val &= ~STRTAB_STE_4_PARTID_MASK; + val |= FIELD_PREP(STRTAB_STE_4_PARTID_MASK, partid); + WRITE_ONCE(ste[4], cpu_to_le64(val)); + + val = le64_to_cpu(ste[5]); + val &= ~STRTAB_STE_5_PMG_MASK; + val |= FIELD_PREP(STRTAB_STE_5_PMG_MASK, pmg); + WRITE_ONCE(ste[5], cpu_to_le64(val)); + + arm_smmu_sync_ste_for_sid(smmu, sid); + + return 0; +} + +int arm_smmu_set_cd_mpam(struct iommu_pasid_table_ops *ops, + int ssid, int partid, int pmg); + +static int arm_smmu_set_mpam(struct arm_smmu_device *smmu, + int sid, int ssid, int partid, int pmg, int s1mpam) +{ + struct arm_smmu_master_data *master = arm_smmu_find_master(smmu, sid); + struct arm_smmu_s1_cfg *cfg = master ? master->ste.s1_cfg : NULL; + struct arm_smmu_domain *domain = master ? master->domain : NULL; + int ret; + + struct arm_smmu_cmdq_ent prefetch_cmd = { + .opcode = CMDQ_OP_PREFETCH_CFG, + .prefetch = { + .sid = sid, + }, + }; + + if (!(smmu->features & ARM_SMMU_FEAT_MPAM)) + return -ENODEV; + + if (WARN_ON(!domain)) + return -EINVAL; + + if (WARN_ON(!cfg)) + return -EINVAL; + + if (WARN_ON(ssid >= (1 << master->ssid_bits))) + return -E2BIG; + + if (partid > smmu->mpam_partid_max || pmg > smmu->mpam_pmg_max) { + dev_err(smmu->dev, + "mpam rmid out of range: partid[0, %d] pmg[0, %d]\n", + smmu->mpam_partid_max, smmu->mpam_pmg_max); + return -ERANGE; + } + + ret = arm_smmu_set_ste_mpam(smmu, sid, partid, pmg, s1mpam); + if (ret < 0) { + dev_err(smmu->dev, "set ste mpam configuration error %d\n", + ret); + return ret; + } + + /* do not modify cd table which owned by guest */ + if (domain->stage == ARM_SMMU_DOMAIN_NESTED) { + dev_err(smmu->dev, + "mpam: smmu cd is owned by guest, not modified\n"); + return 0; + } + + ret = arm_smmu_set_cd_mpam(cfg->ops, ssid, partid, pmg); + if (s1mpam && ret < 0) { + dev_err(smmu->dev, "set cd mpam configuration error %d\n", + ret); + return ret; + } + + /* It's likely that we'll want to use the new STE soon */ + if (!(smmu->options & ARM_SMMU_OPT_SKIP_PREFETCH)) + arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd); + + dev_info(smmu->dev, "partid %d, pmg %d\n", partid, pmg); + + return 0; +} + +/** + * arm_smmu_set_dev_mpam() - Set mpam configuration to SMMU STE/CD + */ +int arm_smmu_set_dev_mpam(struct device *dev, int ssid, int partid, int pmg, + int s1mpam) +{ + struct arm_smmu_master_data *master = dev->iommu_fwspec->iommu_priv; + struct arm_smmu_device *smmu = master->domain->smmu; + int sid = master->streams->id; + + return arm_smmu_set_mpam(smmu, sid, ssid, partid, pmg, s1mpam); +} +EXPORT_SYMBOL(arm_smmu_set_dev_mpam); + static int arm_smmu_device_probe(struct platform_device *pdev) { int irq, ret; diff --git a/include/linux/ascend_smmu.h b/include/linux/ascend_smmu.h new file mode 100644 index 0000000000000..bd0edd25057e1 --- /dev/null +++ b/include/linux/ascend_smmu.h @@ -0,0 +1,9 @@ +#ifndef __LINUX_ASCEND_SMMU_H +#define __LINUX_ASCEND_SMMU_H + +#include <linux/device.h> + +extern int arm_smmu_set_dev_mpam(struct device *dev, int ssid, int partid, + int pmg, int s1mpam); + +#endif /* __LINUX_ASCEND_SMMU_H */ -- 2.25.1

1 8