From: Trond Myklebust trondmy@gmail.com

commit 9542e6a643fc69d528dfb3303f145719c61d3050 upstream.

Ensure that if the filecache laundrette gets stuck, it only affects the knfsd instances of one container.

The notifier callbacks can be called from various contexts so avoid using synchonous filesystem operations that might deadlock.

Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: J. Bruce Fields bfields@redhat.com Cc: Khazhy Kumykov khazhy@google.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/nfsd/filecache.c | 238 +++++++++++++++++++++++++++++++++++++++++++--------- fs/nfsd/filecache.h | 2 fs/nfsd/nfssvc.c | 9 + 3 files changed, 207 insertions(+), 42 deletions(-)

--- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -44,6 +44,17 @@ struct nfsd_fcache_bucket {

static DEFINE_PER_CPU(unsigned long, nfsd_file_cache_hits);

+struct nfsd_fcache_disposal { + struct list_head list; + struct work_struct work; + struct net *net; + spinlock_t lock; + struct list_head freeme; + struct rcu_head rcu; +}; + +struct workqueue_struct *nfsd_filecache_wq __read_mostly; + static struct kmem_cache *nfsd_file_slab; static struct kmem_cache *nfsd_file_mark_slab; static struct nfsd_fcache_bucket *nfsd_file_hashtbl; @@ -52,32 +63,21 @@ static long nfsd_file_lru_flags; static struct fsnotify_group *nfsd_file_fsnotify_group; static atomic_long_t nfsd_filecache_count; static struct delayed_work nfsd_filecache_laundrette; +static DEFINE_SPINLOCK(laundrette_lock); +static LIST_HEAD(laundrettes);

-enum nfsd_file_laundrette_ctl { - NFSD_FILE_LAUNDRETTE_NOFLUSH = 0, - NFSD_FILE_LAUNDRETTE_MAY_FLUSH -}; +static void nfsd_file_gc(void);

static void -nfsd_file_schedule_laundrette(enum nfsd_file_laundrette_ctl ctl) +nfsd_file_schedule_laundrette(void) { long count = atomic_long_read(&nfsd_filecache_count);

if (count == 0 || test_bit(NFSD_FILE_SHUTDOWN, &nfsd_file_lru_flags)) return;

- /* Be more aggressive about scanning if over the threshold */ - if (count > NFSD_FILE_LRU_THRESHOLD) - mod_delayed_work(system_wq, &nfsd_filecache_laundrette, 0); - else - schedule_delayed_work(&nfsd_filecache_laundrette, NFSD_LAUNDRETTE_DELAY); - - if (ctl == NFSD_FILE_LAUNDRETTE_NOFLUSH) - return; - - /* ...and don't delay flushing if we're out of control */ - if (count >= NFSD_FILE_LRU_LIMIT) - flush_delayed_work(&nfsd_filecache_laundrette); + queue_delayed_work(system_wq, &nfsd_filecache_laundrette, + NFSD_LAUNDRETTE_DELAY); }

static void @@ -316,7 +316,9 @@ nfsd_file_put(struct nfsd_file *nf)

set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags); if (nfsd_file_put_noref(nf) == 1 && is_hashed && unused) - nfsd_file_schedule_laundrette(NFSD_FILE_LAUNDRETTE_MAY_FLUSH); + nfsd_file_schedule_laundrette(); + if (atomic_long_read(&nfsd_filecache_count) >= NFSD_FILE_LRU_LIMIT) + nfsd_file_gc(); }

struct nfsd_file * @@ -357,6 +359,58 @@ nfsd_file_dispose_list_sync(struct list_ flush_delayed_fput(); }

+static void +nfsd_file_list_remove_disposal(struct list_head *dst, + struct nfsd_fcache_disposal *l) +{ + spin_lock(&l->lock); + list_splice_init(&l->freeme, dst); + spin_unlock(&l->lock); +} + +static void +nfsd_file_list_add_disposal(struct list_head *files, struct net *net) +{ + struct nfsd_fcache_disposal *l; + + rcu_read_lock(); + list_for_each_entry_rcu(l, &laundrettes, list) { + if (l->net == net) { + spin_lock(&l->lock); + list_splice_tail_init(files, &l->freeme); + spin_unlock(&l->lock); + queue_work(nfsd_filecache_wq, &l->work); + break; + } + } + rcu_read_unlock(); +} + +static void +nfsd_file_list_add_pernet(struct list_head *dst, struct list_head *src, + struct net *net) +{ + struct nfsd_file *nf, *tmp; + + list_for_each_entry_safe(nf, tmp, src, nf_lru) { + if (nf->nf_net == net) + list_move_tail(&nf->nf_lru, dst); + } +} + +static void +nfsd_file_dispose_list_delayed(struct list_head *dispose) +{ + LIST_HEAD(list); + struct nfsd_file *nf; + + while(!list_empty(dispose)) { + nf = list_first_entry(dispose, struct nfsd_file, nf_lru); + nfsd_file_list_add_pernet(&list, dispose, nf->nf_net); + nfsd_file_list_add_disposal(&list, nf->nf_net); + } +} + /* * Note this can deadlock with nfsd_file_cache_purge. */ @@ -403,17 +457,40 @@ out_skip: return LRU_SKIP; }

-static void -nfsd_file_lru_dispose(struct list_head *head) +static unsigned long +nfsd_file_lru_walk_list(struct shrink_control *sc) { + LIST_HEAD(head); struct nfsd_file *nf; + unsigned long ret;

- list_for_each_entry(nf, head, nf_lru) { + if (sc) + ret = list_lru_shrink_walk(&nfsd_file_lru, sc, + nfsd_file_lru_cb, &head); + else + ret = list_lru_walk(&nfsd_file_lru, + nfsd_file_lru_cb, + &head, LONG_MAX); + list_for_each_entry(nf, &head, nf_lru) { spin_lock(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock); nfsd_file_do_unhash(nf); spin_unlock(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock); } - nfsd_file_dispose_list(head); + nfsd_file_dispose_list_delayed(&head); + return ret; +} + +static void +nfsd_file_gc(void) +{ + nfsd_file_lru_walk_list(NULL); +} + +static void +nfsd_file_gc_worker(struct work_struct *work) +{ + nfsd_file_gc(); + nfsd_file_schedule_laundrette(); }

static unsigned long @@ -425,12 +502,7 @@ nfsd_file_lru_count(struct shrinker *s, static unsigned long nfsd_file_lru_scan(struct shrinker *s, struct shrink_control *sc) { - LIST_HEAD(head); - unsigned long ret; - - ret = list_lru_shrink_walk(&nfsd_file_lru, sc, nfsd_file_lru_cb, &head); - nfsd_file_lru_dispose(&head); - return ret; + return nfsd_file_lru_walk_list(sc); }

static struct shrinker nfsd_file_shrinker = { @@ -492,7 +564,7 @@ nfsd_file_close_inode(struct inode *inod

__nfsd_file_close_inode(inode, hashval, &dispose); trace_nfsd_file_close_inode(inode, hashval, !list_empty(&dispose)); - nfsd_file_dispose_list(&dispose); + nfsd_file_dispose_list_delayed(&dispose); }

/** @@ -508,16 +580,11 @@ static void nfsd_file_delayed_close(struct work_struct *work) { LIST_HEAD(head); + struct nfsd_fcache_disposal *l = container_of(work, + struct nfsd_fcache_disposal, work);

- list_lru_walk(&nfsd_file_lru, nfsd_file_lru_cb, &head, LONG_MAX); - - if (test_and_clear_bit(NFSD_FILE_LRU_RESCAN, &nfsd_file_lru_flags)) - nfsd_file_schedule_laundrette(NFSD_FILE_LAUNDRETTE_NOFLUSH); - - if (!list_empty(&head)) { - nfsd_file_lru_dispose(&head); - flush_delayed_fput(); - } + nfsd_file_list_remove_disposal(&head, l); + nfsd_file_dispose_list(&head); }

static int @@ -578,6 +645,10 @@ nfsd_file_cache_init(void) if (nfsd_file_hashtbl) return 0;

+ nfsd_filecache_wq = alloc_workqueue("nfsd_filecache", 0, 0); + if (!nfsd_filecache_wq) + goto out; + nfsd_file_hashtbl = kcalloc(NFSD_FILE_HASH_SIZE, sizeof(*nfsd_file_hashtbl), GFP_KERNEL); if (!nfsd_file_hashtbl) { @@ -631,7 +702,7 @@ nfsd_file_cache_init(void) spin_lock_init(&nfsd_file_hashtbl[i].nfb_lock); }

- INIT_DELAYED_WORK(&nfsd_filecache_laundrette, nfsd_file_delayed_close); + INIT_DELAYED_WORK(&nfsd_filecache_laundrette, nfsd_file_gc_worker); out: return ret; out_notifier: @@ -647,6 +718,8 @@ out_err: nfsd_file_mark_slab = NULL; kfree(nfsd_file_hashtbl); nfsd_file_hashtbl = NULL; + destroy_workqueue(nfsd_filecache_wq); + nfsd_filecache_wq = NULL; goto out; }

@@ -685,6 +758,88 @@ nfsd_file_cache_purge(struct net *net) } }

+static struct nfsd_fcache_disposal * +nfsd_alloc_fcache_disposal(struct net *net) +{ + struct nfsd_fcache_disposal *l; + + l = kmalloc(sizeof(*l), GFP_KERNEL); + if (!l) + return NULL; + INIT_WORK(&l->work, nfsd_file_delayed_close); + l->net = net; + spin_lock_init(&l->lock); + INIT_LIST_HEAD(&l->freeme); + return l; +} + +static void +nfsd_free_fcache_disposal(struct nfsd_fcache_disposal *l) +{ + rcu_assign_pointer(l->net, NULL); + cancel_work_sync(&l->work); + nfsd_file_dispose_list(&l->freeme); + kfree_rcu(l, rcu); +} + +static void +nfsd_add_fcache_disposal(struct nfsd_fcache_disposal *l) +{ + spin_lock(&laundrette_lock); + list_add_tail_rcu(&l->list, &laundrettes); + spin_unlock(&laundrette_lock); +} + +static void +nfsd_del_fcache_disposal(struct nfsd_fcache_disposal *l) +{ + spin_lock(&laundrette_lock); + list_del_rcu(&l->list); + spin_unlock(&laundrette_lock); +} + +static int +nfsd_alloc_fcache_disposal_net(struct net *net) +{ + struct nfsd_fcache_disposal *l; + + l = nfsd_alloc_fcache_disposal(net); + if (!l) + return -ENOMEM; + nfsd_add_fcache_disposal(l); + return 0; +} + +static void +nfsd_free_fcache_disposal_net(struct net *net) +{ + struct nfsd_fcache_disposal *l; + + rcu_read_lock(); + list_for_each_entry_rcu(l, &laundrettes, list) { + if (l->net != net) + continue; + nfsd_del_fcache_disposal(l); + rcu_read_unlock(); + nfsd_free_fcache_disposal(l); + return; + } + rcu_read_unlock(); +} + +int +nfsd_file_cache_start_net(struct net *net) +{ + return nfsd_alloc_fcache_disposal_net(net); +} + +void +nfsd_file_cache_shutdown_net(struct net *net) +{ + nfsd_file_cache_purge(net); + nfsd_free_fcache_disposal_net(net); +} + void nfsd_file_cache_shutdown(void) { @@ -711,6 +866,8 @@ nfsd_file_cache_shutdown(void) nfsd_file_mark_slab = NULL; kfree(nfsd_file_hashtbl); nfsd_file_hashtbl = NULL; + destroy_workqueue(nfsd_filecache_wq); + nfsd_filecache_wq = NULL; }

static bool @@ -880,7 +1037,8 @@ open_file: nfsd_file_hashtbl[hashval].nfb_maxcount = max(nfsd_file_hashtbl[hashval].nfb_maxcount, nfsd_file_hashtbl[hashval].nfb_count); spin_unlock(&nfsd_file_hashtbl[hashval].nfb_lock); - atomic_long_inc(&nfsd_filecache_count); + if (atomic_long_inc_return(&nfsd_filecache_count) >= NFSD_FILE_LRU_THRESHOLD) + nfsd_file_gc();

nf->nf_mark = nfsd_file_mark_find_or_create(nf); if (nf->nf_mark) --- a/fs/nfsd/filecache.h +++ b/fs/nfsd/filecache.h @@ -51,6 +51,8 @@ struct nfsd_file { int nfsd_file_cache_init(void); void nfsd_file_cache_purge(struct net *); void nfsd_file_cache_shutdown(void); +int nfsd_file_cache_start_net(struct net *net); +void nfsd_file_cache_shutdown_net(struct net *net); void nfsd_file_put(struct nfsd_file *nf); struct nfsd_file *nfsd_file_get(struct nfsd_file *nf); void nfsd_file_close_inode_sync(struct inode *inode); --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -394,13 +394,18 @@ static int nfsd_startup_net(int nrservs, nn->lockd_up = 1; }

- ret = nfs4_state_start_net(net); + ret = nfsd_file_cache_start_net(net); if (ret) goto out_lockd; + ret = nfs4_state_start_net(net); + if (ret) + goto out_filecache;

nn->nfsd_net_up = true; return 0;

+out_filecache: + nfsd_file_cache_shutdown_net(net); out_lockd: if (nn->lockd_up) { lockd_down(net); @@ -415,7 +420,7 @@ static void nfsd_shutdown_net(struct net { struct nfsd_net *nn = net_generic(net, nfsd_net_id);

- nfsd_file_cache_purge(net); + nfsd_file_cache_shutdown_net(net); nfs4_state_shutdown_net(net); if (nn->lockd_up) { lockd_down(net);

From: Tadeusz Struk tadeusz.struk@linaro.org

commit 5e34af4142ffe68f01c8a9acae83300f8911e20c upstream.

Syzbot found a kernel bug in the ipv6 stack: LINK: https://syzkaller.appspot.com/bug?id=205d6f11d72329ab8d62a610c44c5e7e2541558... The reproducer triggers it by sending a crafted message via sendmmsg() call, which triggers skb_over_panic, and crashes the kernel:

skbuff: skb_over_panic: text:ffffffff84647fb4 len:65575 put:65575 head:ffff888109ff0000 data:ffff888109ff0088 tail:0x100af end:0xfec0 dev:<NULL>

Update the check that prevents an invalid packet with MTU equal to the fregment header size to eat up all the space for payload.

The reproducer can be found here: LINK: https://syzkaller.appspot.com/text?tag=ReproC&x=1648c83fb00000

Reported-by: syzbot+e223cf47ec8ae183f2a0@syzkaller.appspotmail.com Signed-off-by: Tadeusz Struk tadeusz.struk@linaro.org Acked-by: Willem de Bruijn willemb@google.com Link: https://lore.kernel.org/r/20220310232538.1044947-1-tadeusz.struk@linaro.org Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/ip6_output.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1429,8 +1429,8 @@ static int __ip6_append_data(struct sock sizeof(struct frag_hdr) : 0) + rt->rt6i_nfheader_len;

- if (mtu < fragheaderlen || - ((mtu - fragheaderlen) & ~7) + fragheaderlen < sizeof(struct frag_hdr)) + if (mtu <= fragheaderlen || + ((mtu - fragheaderlen) & ~7) + fragheaderlen <= sizeof(struct frag_hdr)) goto emsgsize;

maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen -

From: Tadeusz Struk tstruk@gmail.com

commit 2e8e4c8f6673247e22efc7985ce5497accd16f88 upstream.

When an invalid (non existing) handle is used in a TPM command, that uses the resource manager interface (/dev/tpmrm0) the resource manager tries to load it from its internal cache, but fails and the tpm_dev_transmit returns an -EINVAL error to the caller. The existing async handler doesn't handle these error cases currently and the condition in the poll handler never returns mask with EPOLLIN set. The result is that the poll call blocks and the application gets stuck until the user_read_timer wakes it up after 120 sec. Change the tpm_dev_async_work function to handle error conditions returned from tpm_dev_transmit they are also reflected in the poll mask and a correct error code could passed back to the caller.

Cc: Jarkko Sakkinen jarkko@kernel.org Cc: Jason Gunthorpe jgg@ziepe.ca Cc: linux-integrity@vger.kernel.org Cc: stable@vger.kernel.org Cc: linux-kernel@vger.kernel.org

Fixes: 9e1b74a63f77 ("tpm: add support for nonblocking operation") Tested-by: Jarkko Sakkinenjarkko@kernel.org Signed-off-by: Tadeusz Struk tstruk@gmail.com Reviewed-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Cc: Tadeusz Struk tadeusz.struk@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/char/tpm/tpm-dev-common.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

--- a/drivers/char/tpm/tpm-dev-common.c +++ b/drivers/char/tpm/tpm-dev-common.c @@ -70,7 +70,13 @@ static void tpm_dev_async_work(struct wo ret = tpm_dev_transmit(priv->chip, priv->space, priv->data_buffer, sizeof(priv->data_buffer)); tpm_put_ops(priv->chip); - if (ret > 0) { + + /* + * If ret is > 0 then tpm_dev_transmit returned the size of the + * response. If ret is < 0 then tpm_dev_transmit failed and + * returned an error code. + */ + if (ret != 0) { priv->response_length = ret; mod_timer(&priv->user_read_timer, jiffies + (120 * HZ)); }

From: Chuansheng Liu chuansheng.liu@intel.com

commit 3abea10e6a8f0e7804ed4c124bea2d15aca977c8 upstream.

It is easy to hit the below memory leaks in my TigerLake platform:

unreferenced object 0xffff927c8b91dbc0 (size 32): comm "kworker/0:2", pid 112, jiffies 4294893323 (age 83.604s) hex dump (first 32 bytes): 4e 41 4d 45 3d 49 4e 54 33 34 30 30 20 54 68 65 NAME=INT3400 The 72 6d 61 6c 00 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b a5 rmal.kkkkkkkkkk. backtrace: [<ffffffff9c502c3e>] __kmalloc_track_caller+0x2fe/0x4a0 [<ffffffff9c7b7c15>] kvasprintf+0x65/0xd0 [<ffffffff9c7b7d6e>] kasprintf+0x4e/0x70 [<ffffffffc04cb662>] int3400_notify+0x82/0x120 [int3400_thermal] [<ffffffff9c8b7358>] acpi_ev_notify_dispatch+0x54/0x71 [<ffffffff9c88f1a7>] acpi_os_execute_deferred+0x17/0x30 [<ffffffff9c2c2c0a>] process_one_work+0x21a/0x3f0 [<ffffffff9c2c2e2a>] worker_thread+0x4a/0x3b0 [<ffffffff9c2cb4dd>] kthread+0xfd/0x130 [<ffffffff9c201c1f>] ret_from_fork+0x1f/0x30

Fix it by calling kfree() accordingly.

Fixes: 38e44da59130 ("thermal: int3400_thermal: process "thermal table changed" event") Signed-off-by: Chuansheng Liu chuansheng.liu@intel.com Cc: 4.14+ stable@vger.kernel.org # 4.14+ Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com [sudip: adjust context] Signed-off-by: Sudip Mukherjee sudipm.mukherjee@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/thermal/intel/int340x_thermal/int3400_thermal.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c +++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c @@ -216,6 +216,10 @@ static void int3400_notify(acpi_handle h thermal_prop[4] = NULL; kobject_uevent_env(&priv->thermal->device.kobj, KOBJ_CHANGE, thermal_prop); + kfree(thermal_prop[0]); + kfree(thermal_prop[1]); + kfree(thermal_prop[2]); + kfree(thermal_prop[3]); break; default: /* Ignore unknown notification codes sent to INT3400 device */

From: Halil Pasic pasic@linux.ibm.com

commit ddbd89deb7d32b1fbb879f48d68fda1a8ac58e8e upstream.

The problem I'm addressing was discovered by the LTP test covering cve-2018-1000204.

A short description of what happens follows: 1) The test case issues a command code 00 (TEST UNIT READY) via the SG_IO interface with: dxfer_len == 524288, dxdfer_dir == SG_DXFER_FROM_DEV and a corresponding dxferp. The peculiar thing about this is that TUR is not reading from the device. 2) In sg_start_req() the invocation of blk_rq_map_user() effectively bounces the user-space buffer. As if the device was to transfer into it. Since commit a45b599ad808 ("scsi: sg: allocate with __GFP_ZERO in sg_build_indirect()") we make sure this first bounce buffer is allocated with GFP_ZERO. 3) For the rest of the story we keep ignoring that we have a TUR, so the device won't touch the buffer we prepare as if the we had a DMA_FROM_DEVICE type of situation. My setup uses a virtio-scsi device and the buffer allocated by SG is mapped by the function virtqueue_add_split() which uses DMA_FROM_DEVICE for the "in" sgs (here scatter-gather and not scsi generics). This mapping involves bouncing via the swiotlb (we need swiotlb to do virtio in protected guest like s390 Secure Execution, or AMD SEV). 4) When the SCSI TUR is done, we first copy back the content of the second (that is swiotlb) bounce buffer (which most likely contains some previous IO data), to the first bounce buffer, which contains all zeros. Then we copy back the content of the first bounce buffer to the user-space buffer. 5) The test case detects that the buffer, which it zero-initialized, ain't all zeros and fails.

One can argue that this is an swiotlb problem, because without swiotlb we leak all zeros, and the swiotlb should be transparent in a sense that it does not affect the outcome (if all other participants are well behaved).

Copying the content of the original buffer into the swiotlb buffer is the only way I can think of to make swiotlb transparent in such scenarios. So let's do just that if in doubt, but allow the driver to tell us that the whole mapped buffer is going to be overwritten, in which case we can preserve the old behavior and avoid the performance impact of the extra bounce.

Signed-off-by: Halil Pasic pasic@linux.ibm.com Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/DMA-attributes.txt | 10 ++++++++++ include/linux/dma-mapping.h | 8 ++++++++ kernel/dma/swiotlb.c | 3 ++- 3 files changed, 20 insertions(+), 1 deletion(-)

--- a/Documentation/DMA-attributes.txt +++ b/Documentation/DMA-attributes.txt @@ -156,3 +156,13 @@ accesses to DMA buffers in both privileg subsystem that the buffer is fully accessible at the elevated privilege level (and ideally inaccessible or at least read-only at the lesser-privileged levels). + +DMA_ATTR_PRIVILEGED +------------------- + +Some advanced peripherals such as remote processors and GPUs perform +accesses to DMA buffers in both privileged "supervisor" and unprivileged +"user" modes. This attribute is used to indicate to the DMA-mapping +subsystem that the buffer is fully accessible at the elevated privilege +level (and ideally inaccessible or at least read-only at the +lesser-privileged levels). --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -71,6 +71,14 @@ #define DMA_ATTR_PRIVILEGED (1UL << 9)

/* + * This is a hint to the DMA-mapping subsystem that the device is expected + * to overwrite the entire mapped size, thus the caller does not require any + * of the previous buffer contents to be preserved. This allows + * bounce-buffering implementations to optimise DMA_FROM_DEVICE transfers. + */ +#define DMA_ATTR_OVERWRITE (1UL << 10) + +/* * A dma_addr_t can hold any valid DMA or bus address for the platform. * It can be given to a device to use as a DMA source or target. A CPU cannot * reference a dma_addr_t directly because there may be translation between --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -572,7 +572,8 @@ found: for (i = 0; i < nslots; i++) io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT); if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && - (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) + (!(attrs & DMA_ATTR_OVERWRITE) || dir == DMA_TO_DEVICE || + dir == DMA_BIDIRECTIONAL)) swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_TO_DEVICE);

return tlb_addr;

From: Takashi Iwai tiwai@suse.de

commit 1f68915b2efd0d6bfd6e124aa63c94b3c69f127c upstream.

snd_pcm_reset() is a non-atomic operation, and it's allowed to run during the PCM stream running. It implies that the manipulation of hw_ptr and other parameters might be racy.

This patch adds the PCM stream lock at appropriate places in snd_pcm_*_reset() actions for covering that.

Cc: stable@vger.kernel.org Reviewed-by: Jaroslav Kysela perex@perex.cz Link: https://lore.kernel.org/r/20220322171325.4355-1-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/core/pcm_native.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -1656,21 +1656,25 @@ static int snd_pcm_do_reset(struct snd_p int err = substream->ops->ioctl(substream, SNDRV_PCM_IOCTL1_RESET, NULL); if (err < 0) return err; + snd_pcm_stream_lock_irq(substream); runtime->hw_ptr_base = 0; runtime->hw_ptr_interrupt = runtime->status->hw_ptr - runtime->status->hw_ptr % runtime->period_size; runtime->silence_start = runtime->status->hw_ptr; runtime->silence_filled = 0; + snd_pcm_stream_unlock_irq(substream); return 0; }

static void snd_pcm_post_reset(struct snd_pcm_substream *substream, int state) { struct snd_pcm_runtime *runtime = substream->runtime; + snd_pcm_stream_lock_irq(substream); runtime->control->appl_ptr = runtime->status->hw_ptr; if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK && runtime->silence_size > 0) snd_pcm_playback_silence(substream, ULONG_MAX); + snd_pcm_stream_unlock_irq(substream); }

static const struct action_ops snd_pcm_action_reset = {

From: Jonathan Teh jonathan.teh@outlook.com

commit c14231cc04337c2c2a937db084af342ce704dbde upstream.

Save and restore CM_REG_AUX_VOL instead of register 0x24 twice on suspend/resume.

Tested on CMI8738LX.

Fixes: cb60e5f5b2b1 ("[ALSA] cmipci - Add PM support") Signed-off-by: Jonathan Teh jonathan.teh@outlook.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/DBAPR04MB7366CB3EA9C8521C35C56E8B920E9@DBAPR04MB73... Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/cmipci.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/sound/pci/cmipci.c +++ b/sound/pci/cmipci.c @@ -302,7 +302,6 @@ MODULE_PARM_DESC(joystick_port, "Joystic #define CM_MICGAINZ 0x01 /* mic boost */ #define CM_MICGAINZ_SHIFT 0

-#define CM_REG_MIXER3 0x24 #define CM_REG_AUX_VOL 0x26 #define CM_VAUXL_MASK 0xf0 #define CM_VAUXR_MASK 0x0f @@ -3310,7 +3309,7 @@ static void snd_cmipci_remove(struct pci */ static unsigned char saved_regs[] = { CM_REG_FUNCTRL1, CM_REG_CHFORMAT, CM_REG_LEGACY_CTRL, CM_REG_MISC_CTRL, - CM_REG_MIXER0, CM_REG_MIXER1, CM_REG_MIXER2, CM_REG_MIXER3, CM_REG_PLL, + CM_REG_MIXER0, CM_REG_MIXER1, CM_REG_MIXER2, CM_REG_AUX_VOL, CM_REG_PLL, CM_REG_CH0_FRAME1, CM_REG_CH0_FRAME2, CM_REG_CH1_FRAME1, CM_REG_CH1_FRAME2, CM_REG_EXT_MISC, CM_REG_INT_STATUS, CM_REG_INT_HLDCLR, CM_REG_FUNCTRL0,

From: Stephane Graber stgraber@ubuntu.com

commit e9e6faeafaa00da1851bcf47912b0f1acae666b4 upstream.

All packets on ingress (except for jumbo) are terminated with a 4-bytes CRC checksum. It's the responsability of the driver to strip those 4 bytes. Unfortunately a change dating back to March 2017 re-shuffled some code and made the CRC stripping code effectively dead.

This change re-orders that part a bit such that the datalen is immediately altered if needed.

Fixes: 4902a92270fb ("drivers: net: xgene: Add workaround for errata 10GE_8/ENET_11") Cc: stable@vger.kernel.org Signed-off-by: Stephane Graber stgraber@ubuntu.com Tested-by: Stephane Graber stgraber@ubuntu.com Link: https://lore.kernel.org/r/20220322224205.752795-1-stgraber@ubuntu.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/apm/xgene/xgene_enet_main.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-)

--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -696,6 +696,12 @@ static int xgene_enet_rx_frame(struct xg buf_pool->rx_skb[skb_index] = NULL;

datalen = xgene_enet_get_data_len(le64_to_cpu(raw_desc->m1)); + + /* strip off CRC as HW isn't doing this */ + nv = GET_VAL(NV, le64_to_cpu(raw_desc->m0)); + if (!nv) + datalen -= 4; + skb_put(skb, datalen); prefetch(skb->data - NET_IP_ALIGN); skb->protocol = eth_type_trans(skb, ndev); @@ -717,12 +723,8 @@ static int xgene_enet_rx_frame(struct xg } }

- nv = GET_VAL(NV, le64_to_cpu(raw_desc->m0)); - if (!nv) { - /* strip off CRC as HW isn't doing this */ - datalen -= 4; + if (!nv) goto skip_jumbo; - }

slots = page_pool->slots - 1; head = page_pool->head;

From: Takashi Iwai tiwai@suse.de

commit efb6402c3c4a7c26d97c92d70186424097b6e366 upstream.

We've got syzbot reports hitting INT_MAX overflow at vmalloc() allocation that is called from snd_pcm_plug_alloc(). Although we apply the restrictions to input parameters, it's based only on the hw_params of the underlying PCM device. Since the PCM OSS layer allocates a temporary buffer for the data conversion, the size may become unexpectedly large when more channels or higher rates is given; in the reported case, it went over INT_MAX, hence it hits WARN_ON().

This patch is an attempt to avoid such an overflow and an allocation for too large buffers. First off, it adds the limit of 1MB as the upper bound for period bytes. This must be large enough for all use cases, and we really don't want to handle a larger temporary buffer than this size. The size check is performed at two places, where the original period bytes is calculated and where the plugin buffer size is calculated.

In addition, the driver uses array_size() and array3_size() for multiplications to catch overflows for the converted period size and buffer bytes.

Reported-by: syzbot+72732c532ac1454eeee9@syzkaller.appspotmail.com Suggested-by: Linus Torvalds torvalds@linux-foundation.org Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/00000000000085b1b305da5a66f3@google.com Link: https://lore.kernel.org/r/20220318082036.29699-1-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/core/oss/pcm_oss.c | 12 ++++++++---- sound/core/oss/pcm_plugin.c | 5 ++++- 2 files changed, 12 insertions(+), 5 deletions(-)

--- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -774,6 +774,11 @@ static int snd_pcm_oss_period_size(struc

if (oss_period_size < 16) return -EINVAL; + + /* don't allocate too large period; 1MB period must be enough */ + if (oss_period_size > 1024 * 1024) + return -ENOMEM; + runtime->oss.period_bytes = oss_period_size; runtime->oss.period_frames = 1; runtime->oss.periods = oss_periods; @@ -1045,10 +1050,9 @@ static int snd_pcm_oss_change_params_loc goto failure; } #endif - oss_period_size *= oss_frame_size; - - oss_buffer_size = oss_period_size * runtime->oss.periods; - if (oss_buffer_size < 0) { + oss_period_size = array_size(oss_period_size, oss_frame_size); + oss_buffer_size = array_size(oss_period_size, runtime->oss.periods); + if (oss_buffer_size <= 0) { err = -EINVAL; goto failure; } --- a/sound/core/oss/pcm_plugin.c +++ b/sound/core/oss/pcm_plugin.c @@ -61,7 +61,10 @@ static int snd_pcm_plugin_alloc(struct s } if ((width = snd_pcm_format_physical_width(format->format)) < 0) return width; - size = frames * format->channels * width; + size = array3_size(frames, format->channels, width); + /* check for too large period size once again */ + if (size > 1024 * 1024) + return -ENOMEM; if (snd_BUG_ON(size % 8)) return -ENXIO; size /= 8;

From: Jason Zheng jasonzheng2004@gmail.com

commit b7557267c233b55d8e8d7ba4c68cf944fe2ec02c upstream.

ASUS GA402 requires a workaround to manage the routing of its 4 speakers like the other ASUS models. Add a corresponding quirk entry to fix it.

Signed-off-by: Jason Zheng jasonzheng2004@gmail.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220313092216.29858-1-jasonzheng2004@gmail.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+)

--- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -8183,6 +8183,7 @@ static const struct snd_pci_quirk alc269 SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS), SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401), + SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x16b2, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2), SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC),

From: Mark Cilissen mark@yotsuba.nl

commit e702196bf85778f2c5527ca47f33ef2e2fca8297 upstream.

On this board the ACPI RSDP structure points to both a RSDT and an XSDT, but the XSDT points to a truncated FADT. This causes all sorts of trouble and usually a complete failure to boot after the following error occurs:

ACPI Error: Unsupported address space: 0x20 (*/hwregs-*) ACPI Error: AE_SUPPORT, Unable to initialize fixed events (*/evevent-*) ACPI: Unable to start ACPI Interpreter

This leaves the ACPI implementation in such a broken state that subsequent kernel subsystem initialisations go wrong, resulting in among others mismapped PCI memory, SATA and USB enumeration failures, and freezes.

As this is an older embedded platform that will likely never see any BIOS updates to address this issue and its default shipping OS only complies to ACPI 1.0, work around this by forcing `acpi=rsdt`. This patch, applied on top of Linux 5.10.102, was confirmed on real hardware to fix the issue.

Signed-off-by: Mark Cilissen mark@yotsuba.nl Cc: All applicable stable@vger.kernel.org Reviewed-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/acpi/boot.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+)

--- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -1339,6 +1339,17 @@ static int __init disable_acpi_pci(const return 0; }

+static int __init disable_acpi_xsdt(const struct dmi_system_id *d) +{ + if (!acpi_force) { + pr_notice("%s detected: force use of acpi=rsdt\n", d->ident); + acpi_gbl_do_not_use_xsdt = TRUE; + } else { + pr_notice("Warning: DMI blacklist says broken, but acpi XSDT forced\n"); + } + return 0; +} + static int __init dmi_disable_acpi(const struct dmi_system_id *d) { if (!acpi_force) { @@ -1463,6 +1474,19 @@ static const struct dmi_system_id acpi_d DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 360"), }, }, + /* + * Boxes that need ACPI XSDT use disabled due to corrupted tables + */ + { + .callback = disable_acpi_xsdt, + .ident = "Advantech DAC-BJ01", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "NEC"), + DMI_MATCH(DMI_PRODUCT_NAME, "Bearlake CRB Board"), + DMI_MATCH(DMI_BIOS_VERSION, "V1.12"), + DMI_MATCH(DMI_BIOS_DATE, "02/01/2011"), + }, + }, {} };

From: Werner Sembach wse@tuxedocomputers.com

commit c844d22fe0c0b37dc809adbdde6ceb6462c43acf upstream.

Clevo NL5xRU and NL5xNU/TUXEDO Aura 15 Gen1 and Gen2 have both a working native and video interface. However the default detection mechanism first registers the video interface before unregistering it again and switching to the native interface during boot. This results in a dangling SBIOS request for backlight change for some reason, causing the backlight to switch to ~2% once per boot on the first power cord connect or disconnect event. Setting the native interface explicitly circumvents this buggy behaviour by avoiding the unregistering process.

Signed-off-by: Werner Sembach wse@tuxedocomputers.com Cc: All applicable stable@vger.kernel.org Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/acpi/video_detect.c | 75 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 75 insertions(+)

--- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -372,6 +372,81 @@ static const struct dmi_system_id video_ DMI_MATCH(DMI_BOARD_NAME, "BA51_MV"), }, }, + /* + * Clevo NL5xRU and NL5xNU/TUXEDO Aura 15 Gen1 and Gen2 have both a + * working native and video interface. However the default detection + * mechanism first registers the video interface before unregistering + * it again and switching to the native interface during boot. This + * results in a dangling SBIOS request for backlight change for some + * reason, causing the backlight to switch to ~2% once per boot on the + * first power cord connect or disconnect event. Setting the native + * interface explicitly circumvents this buggy behaviour, by avoiding + * the unregistering process. + */ + { + .callback = video_detect_force_native, + .ident = "Clevo NL5xRU", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_BOARD_NAME, "NL5xRU"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "Clevo NL5xRU", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "SchenkerTechnologiesGmbH"), + DMI_MATCH(DMI_BOARD_NAME, "NL5xRU"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "Clevo NL5xRU", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Notebook"), + DMI_MATCH(DMI_BOARD_NAME, "NL5xRU"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "Clevo NL5xRU", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_BOARD_NAME, "AURA1501"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "Clevo NL5xRU", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_BOARD_NAME, "EDUBOOK1502"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "Clevo NL5xNU", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_BOARD_NAME, "NL5xNU"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "Clevo NL5xNU", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "SchenkerTechnologiesGmbH"), + DMI_MATCH(DMI_BOARD_NAME, "NL5xNU"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "Clevo NL5xNU", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Notebook"), + DMI_MATCH(DMI_BOARD_NAME, "NL5xNU"), + }, + },

/* * Desktops which falsely report a backlight and which our heuristics

From: Paul E. McKenney paulmck@kernel.org

commit 10c535787436d62ea28156a4b91365fd89b5a432 upstream.

Currently rcu_preempt_deferred_qs_irqrestore() releases rnp->boost_mtx before reporting the expedited quiescent state. Under heavy real-time load, this can result in this function being preempted before the quiescent state is reported, which can in turn prevent the expedited grace period from completing. Tim Murray reports that the resulting expedited grace periods can take hundreds of milliseconds and even more than one second, when they should normally complete in less than a millisecond.

This was fine given that there were no particular response-time constraints for synchronize_rcu_expedited(), as it was designed for throughput rather than latency. However, some users now need sub-100-millisecond response-time constratints.

This patch therefore follows Neeraj's suggestion (seconded by Tim and by Uladzislau Rezki) of simply reversing the two operations.

Reported-by: Tim Murray timmurray@google.com Reported-by: Joel Fernandes joelaf@google.com Reported-by: Neeraj Upadhyay quic_neeraju@quicinc.com Reviewed-by: Neeraj Upadhyay quic_neeraju@quicinc.com Reviewed-by: Uladzislau Rezki (Sony) urezki@gmail.com Tested-by: Tim Murray timmurray@google.com Cc: Todd Kjos tkjos@google.com Cc: Sandeep Patil sspatil@google.com Cc: stable@vger.kernel.org # 5.4.x Signed-off-by: Paul E. McKenney paulmck@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/rcu/tree_plugin.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)

--- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -523,16 +523,17 @@ rcu_preempt_deferred_qs_irqrestore(struc raw_spin_unlock_irqrestore_rcu_node(rnp, flags); }

- /* Unboost if we were boosted. */ - if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex) - rt_mutex_futex_unlock(&rnp->boost_mtx); - /* * If this was the last task on the expedited lists, * then we need to report up the rcu_node hierarchy. */ if (!empty_exp && empty_exp_now) rcu_report_exp_rnp(rnp, true); + + /* Unboost if we were boosted. */ + if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex) + rt_mutex_futex_unlock(&rnp->boost_mtx); + } else { local_irq_restore(flags); }

From: James Bottomley James.Bottomley@HansenPartnership.com

commit fb5abce6b2bb5cb3d628aaa63fa821da8c4600f9 upstream.

As part of the series conversion to remove nested TPM operations:

https://lore.kernel.org/all/20190205224723.19671-1-jarkko.sakkinen@linux.int...

exposure of the chip->tpm_mutex was removed from much of the upper level code. In this conversion, tpm2_del_space() was missed. This didn't matter much because it's usually called closely after a converted operation, so there's only a very tiny race window where the chip can be removed before the space flushing is done which causes a NULL deref on the mutex. However, there are reports of this window being hit in practice, so fix this by converting tpm2_del_space() to use tpm_try_get_ops(), which performs all the teardown checks before acquring the mutex.

Cc: stable@vger.kernel.org # 5.4.x Signed-off-by: James Bottomley James.Bottomley@HansenPartnership.com Reviewed-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/char/tpm/tpm2-space.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/drivers/char/tpm/tpm2-space.c +++ b/drivers/char/tpm/tpm2-space.c @@ -58,12 +58,12 @@ int tpm2_init_space(struct tpm_space *sp

void tpm2_del_space(struct tpm_chip *chip, struct tpm_space *space) { - mutex_lock(&chip->tpm_mutex); - if (!tpm_chip_start(chip)) { + + if (tpm_try_get_ops(chip) == 0) { tpm2_flush_sessions(chip, space); - tpm_chip_stop(chip); + tpm_put_ops(chip); } - mutex_unlock(&chip->tpm_mutex); + kfree(space->context_buf); kfree(space->session_buf); }