From: Eric Dumazet edumazet@google.com

[ Upstream commit 8fb44d60d4142cd2a440620cd291d346e23c131e ]

If llc_mac_hdr_init() returns an error, we must drop the skb since no llc_build_and_send_ui_pkt() caller will take care of this.

BUG: memory leak unreferenced object 0xffff8881202b6800 (size 2048): comm "syz-executor907", pid 7074, jiffies 4294943781 (age 8.590s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 1a 00 07 40 00 00 00 00 00 00 00 00 00 00 00 00 ...@............ backtrace: [<00000000e25b5abe>] kmemleak_alloc_recursive include/linux/kmemleak.h:55 [inline] [<00000000e25b5abe>] slab_post_alloc_hook mm/slab.h:439 [inline] [<00000000e25b5abe>] slab_alloc mm/slab.c:3326 [inline] [<00000000e25b5abe>] __do_kmalloc mm/slab.c:3658 [inline] [<00000000e25b5abe>] __kmalloc+0x161/0x2c0 mm/slab.c:3669 [<00000000a1ae188a>] kmalloc include/linux/slab.h:552 [inline] [<00000000a1ae188a>] sk_prot_alloc+0xd6/0x170 net/core/sock.c:1608 [<00000000ded25bbe>] sk_alloc+0x35/0x2f0 net/core/sock.c:1662 [<000000002ecae075>] llc_sk_alloc+0x35/0x170 net/llc/llc_conn.c:950 [<00000000551f7c47>] llc_ui_create+0x7b/0x140 net/llc/af_llc.c:173 [<0000000029027f0e>] __sock_create+0x164/0x250 net/socket.c:1430 [<000000008bdec225>] sock_create net/socket.c:1481 [inline] [<000000008bdec225>] __sys_socket+0x69/0x110 net/socket.c:1523 [<00000000b6439228>] __do_sys_socket net/socket.c:1532 [inline] [<00000000b6439228>] __se_sys_socket net/socket.c:1530 [inline] [<00000000b6439228>] __x64_sys_socket+0x1e/0x30 net/socket.c:1530 [<00000000cec820c1>] do_syscall_64+0x76/0x1a0 arch/x86/entry/common.c:301 [<000000000c32554f>] entry_SYSCALL_64_after_hwframe+0x44/0xa9

BUG: memory leak unreferenced object 0xffff88811d750d00 (size 224): comm "syz-executor907", pid 7074, jiffies 4294943781 (age 8.600s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 f0 0c 24 81 88 ff ff 00 68 2b 20 81 88 ff ff ...$.....h+ .... backtrace: [<0000000053026172>] kmemleak_alloc_recursive include/linux/kmemleak.h:55 [inline] [<0000000053026172>] slab_post_alloc_hook mm/slab.h:439 [inline] [<0000000053026172>] slab_alloc_node mm/slab.c:3269 [inline] [<0000000053026172>] kmem_cache_alloc_node+0x153/0x2a0 mm/slab.c:3579 [<00000000fa8f3c30>] __alloc_skb+0x6e/0x210 net/core/skbuff.c:198 [<00000000d96fdafb>] alloc_skb include/linux/skbuff.h:1058 [inline] [<00000000d96fdafb>] alloc_skb_with_frags+0x5f/0x250 net/core/skbuff.c:5327 [<000000000a34a2e7>] sock_alloc_send_pskb+0x269/0x2a0 net/core/sock.c:2225 [<00000000ee39999b>] sock_alloc_send_skb+0x32/0x40 net/core/sock.c:2242 [<00000000e034d810>] llc_ui_sendmsg+0x10a/0x540 net/llc/af_llc.c:933 [<00000000c0bc8445>] sock_sendmsg_nosec net/socket.c:652 [inline] [<00000000c0bc8445>] sock_sendmsg+0x54/0x70 net/socket.c:671 [<000000003b687167>] __sys_sendto+0x148/0x1f0 net/socket.c:1964 [<00000000922d78d9>] __do_sys_sendto net/socket.c:1976 [inline] [<00000000922d78d9>] __se_sys_sendto net/socket.c:1972 [inline] [<00000000922d78d9>] __x64_sys_sendto+0x2a/0x30 net/socket.c:1972 [<00000000cec820c1>] do_syscall_64+0x76/0x1a0 arch/x86/entry/common.c:301 [<000000000c32554f>] entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/llc/llc_output.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/net/llc/llc_output.c +++ b/net/llc/llc_output.c @@ -72,6 +72,8 @@ int llc_build_and_send_ui_pkt(struct llc rc = llc_mac_hdr_init(skb, skb->dev->dev_addr, dmac); if (likely(!rc)) rc = dev_queue_xmit(skb); + else + kfree_skb(skb); return rc; }

From: Eric Dumazet edumazet@google.com

[ Upstream commit a4270d6795b0580287453ea55974d948393e66ef ]

If a network driver provides to napi_gro_frags() an skb with a page fragment of exactly 14 bytes, the call to gro_pull_from_frag0() will 'consume' the fragment by calling skb_frag_unref(skb, 0), and the page might be freed and reused.

Reading eth->h_proto at the end of napi_frags_skb() might read mangled data, or crash under specific debugging features.

BUG: KASAN: use-after-free in napi_frags_skb net/core/dev.c:5833 [inline] BUG: KASAN: use-after-free in napi_gro_frags+0xc6f/0xd10 net/core/dev.c:5841 Read of size 2 at addr ffff88809366840c by task syz-executor599/8957

CPU: 1 PID: 8957 Comm: syz-executor599 Not tainted 5.2.0-rc1+ #32 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:188 __kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317 kasan_report+0x12/0x20 mm/kasan/common.c:614 __asan_report_load_n_noabort+0xf/0x20 mm/kasan/generic_report.c:142 napi_frags_skb net/core/dev.c:5833 [inline] napi_gro_frags+0xc6f/0xd10 net/core/dev.c:5841 tun_get_user+0x2f3c/0x3ff0 drivers/net/tun.c:1991 tun_chr_write_iter+0xbd/0x156 drivers/net/tun.c:2037 call_write_iter include/linux/fs.h:1872 [inline] do_iter_readv_writev+0x5f8/0x8f0 fs/read_write.c:693 do_iter_write fs/read_write.c:970 [inline] do_iter_write+0x184/0x610 fs/read_write.c:951 vfs_writev+0x1b3/0x2f0 fs/read_write.c:1015 do_writev+0x15b/0x330 fs/read_write.c:1058

Fixes: a50e233c50db ("net-gro: restore frag0 optimization") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/core/dev.c +++ b/net/core/dev.c @@ -4828,7 +4828,6 @@ static struct sk_buff *napi_frags_skb(st skb_reset_mac_header(skb); skb_gro_reset_offset(skb);

- eth = skb_gro_header_fast(skb, 0); if (unlikely(skb_gro_header_hard(skb, hlen))) { eth = skb_gro_header_slow(skb, hlen, 0); if (unlikely(!eth)) { @@ -4838,6 +4837,7 @@ static struct sk_buff *napi_frags_skb(st return NULL; } } else { + eth = (const struct ethhdr *)skb->data; gro_pull_from_frag0(skb, hlen); NAPI_GRO_CB(skb)->frag0 += hlen; NAPI_GRO_CB(skb)->frag0_len -= hlen;

From: Kloetzke Jan Jan.Kloetzke@preh.de

[ Upstream commit ad70411a978d1e6e97b1e341a7bde9a79af0c93d ]

When disconnecting cdc_ncm the kernel sporadically crashes shortly after the disconnect:

[ 57.868812] Unable to handle kernel NULL pointer dereference at virtual address 00000000 ... [ 58.006653] PC is at 0x0 [ 58.009202] LR is at call_timer_fn+0xec/0x1b4 [ 58.013567] pc : [<0000000000000000>] lr : [<ffffff80080f5130>] pstate: 00000145 [ 58.020976] sp : ffffff8008003da0 [ 58.024295] x29: ffffff8008003da0 x28: 0000000000000001 [ 58.029618] x27: 000000000000000a x26: 0000000000000100 [ 58.034941] x25: 0000000000000000 x24: ffffff8008003e68 [ 58.040263] x23: 0000000000000000 x22: 0000000000000000 [ 58.045587] x21: 0000000000000000 x20: ffffffc68fac1808 [ 58.050910] x19: 0000000000000100 x18: 0000000000000000 [ 58.056232] x17: 0000007f885aff8c x16: 0000007f883a9f10 [ 58.061556] x15: 0000000000000001 x14: 000000000000006e [ 58.066878] x13: 0000000000000000 x12: 00000000000000ba [ 58.072201] x11: ffffffc69ff1db30 x10: 0000000000000020 [ 58.077524] x9 : 8000100008001000 x8 : 0000000000000001 [ 58.082847] x7 : 0000000000000800 x6 : ffffff8008003e70 [ 58.088169] x5 : ffffffc69ff17a28 x4 : 00000000ffff138b [ 58.093492] x3 : 0000000000000000 x2 : 0000000000000000 [ 58.098814] x1 : 0000000000000000 x0 : 0000000000000000 ... [ 58.205800] [< (null)>] (null) [ 58.210521] [<ffffff80080f5298>] expire_timers+0xa0/0x14c [ 58.215937] [<ffffff80080f542c>] run_timer_softirq+0xe8/0x128 [ 58.221702] [<ffffff8008081120>] __do_softirq+0x298/0x348 [ 58.227118] [<ffffff80080a6304>] irq_exit+0x74/0xbc [ 58.232009] [<ffffff80080e17dc>] __handle_domain_irq+0x78/0xac [ 58.237857] [<ffffff8008080cf4>] gic_handle_irq+0x80/0xac ...

The crash happens roughly 125..130ms after the disconnect. This correlates with the 'delay' timer that is started on certain USB tx/rx errors in the URB completion handler.

The problem is a race of usbnet_stop() with usbnet_start_xmit(). In usbnet_stop() we call usbnet_terminate_urbs() to cancel all URBs in flight. This only makes sense if no new URBs are submitted concurrently, though. But the usbnet_start_xmit() can run at the same time on another CPU which almost unconditionally submits an URB. The error callback of the new URB will then schedule the timer after it was already stopped.

The fix adds a check if the tx queue is stopped after the tx list lock has been taken. This should reliably prevent the submission of new URBs while usbnet_terminate_urbs() does its job. The same thing is done on the rx side even though it might be safe due to other flags that are checked there.

Signed-off-by: Jan Klötzke Jan.Kloetzke@preh.de Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/usb/usbnet.c | 6 ++++++ 1 file changed, 6 insertions(+)

--- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -508,6 +508,7 @@ static int rx_submit (struct usbnet *dev

if (netif_running (dev->net) && netif_device_present (dev->net) && + test_bit(EVENT_DEV_OPEN, &dev->flags) && !test_bit (EVENT_RX_HALT, &dev->flags) && !test_bit (EVENT_DEV_ASLEEP, &dev->flags)) { switch (retval = usb_submit_urb (urb, GFP_ATOMIC)) { @@ -1394,6 +1395,11 @@ netdev_tx_t usbnet_start_xmit (struct sk spin_unlock_irqrestore(&dev->txq.lock, flags); goto drop; } + if (netif_queue_stopped(net)) { + usb_autopm_put_interface_async(dev->intf); + spin_unlock_irqrestore(&dev->txq.lock, flags); + goto drop; + }

#ifdef CONFIG_PM /* if this triggers the device is still a sleep */

From: Michael Chan michael.chan@broadcom.com

[ Upstream commit 296d5b54163964b7ae536b8b57dfbd21d4e868e1 ]

For every RX packet, the driver replenishes all buffers used for that packet and puts them back into the RX ring and RX aggregation ring. In one code path where the RX packet has one RX buffer and one or more aggregation buffers, we missed recycling the aggregation buffer(s) if we are unable to allocate a new SKB buffer. This leads to the aggregation ring slowly running out of buffers over time. Fix it by properly recycling the aggregation buffers.

Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.") Reported-by: Rakesh Hemnani rhemnani@fb.com Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1425,6 +1425,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, skb = bnxt_copy_skb(bnapi, data, len, dma_addr); bnxt_reuse_rx_data(rxr, cons, data); if (!skb) { + if (agg_bufs) + bnxt_reuse_rx_agg_bufs(bnapi, cp_cons, agg_bufs); rc = -ENOMEM; goto next_rx; }

From: Eric Dumazet edumazet@google.com

[ Upstream commit 903869bd10e6719b9df6718e785be7ec725df59f ]

ip_sf_list_clear_all() needs to be defined even if !CONFIG_IP_MULTICAST

Fixes: 3580d04aa674 ("ipv4/igmp: fix another memory leak in igmpv3_del_delrec()") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: kbuild test robot lkp@intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/igmp.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-)

--- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -190,6 +190,17 @@ static void ip_ma_put(struct ip_mc_list pmc != NULL; \ pmc = rtnl_dereference(pmc->next_rcu))

+static void ip_sf_list_clear_all(struct ip_sf_list *psf) +{ + struct ip_sf_list *next; + + while (psf) { + next = psf->sf_next; + kfree(psf); + psf = next; + } +} + #ifdef CONFIG_IP_MULTICAST

/* @@ -635,17 +646,6 @@ static void igmpv3_clear_zeros(struct ip } }

-static void ip_sf_list_clear_all(struct ip_sf_list *psf) -{ - struct ip_sf_list *next; - - while (psf) { - next = psf->sf_next; - kfree(psf); - psf = next; - } -} - static void kfree_pmc(struct ip_mc_list *pmc) { ip_sf_list_clear_all(pmc->sources);

From: Jisheng Zhang Jisheng.Zhang@synaptics.com

[ Upstream commit d484e06e25ebb937d841dac02ac1fe76ec7d4ddd ]

Fix below issues in err code path of probe: 1. we don't need to unregister_netdev() because the netdev isn't registered. 2. when register_netdev() fails, we also need to destroy bm pool for HWBM case.

Fixes: dc35a10f68d3 ("net: mvneta: bm: add support for hardware buffer management") Signed-off-by: Jisheng Zhang Jisheng.Zhang@synaptics.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/marvell/mvneta.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

--- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -4162,7 +4162,7 @@ static int mvneta_probe(struct platform_ err = register_netdev(dev); if (err < 0) { dev_err(&pdev->dev, "failed to register\n"); - goto err_free_stats; + goto err_netdev; }

netdev_info(dev, "Using %s mac address %pM\n", mac_from, @@ -4181,13 +4181,11 @@ static int mvneta_probe(struct platform_ return 0;

err_netdev: - unregister_netdev(dev); if (pp->bm_priv) { mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_long, 1 << pp->id); mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_short, 1 << pp->id); } -err_free_stats: free_percpu(pp->stats); err_free_ports: free_percpu(pp->ports);

From: Daniel Axtens dja@axtens.net

commit 357d065a44cdd77ed5ff35155a989f2a763e96ef upstream.

VMX ghash was using a fallback that did not support interleaving simd and nosimd operations, leading to failures in the extended test suite.

If I understood correctly, Eric's suggestion was to use the same data format that the generic code uses, allowing us to call into it with the same contexts. I wasn't able to get that to work - I think there's a very different key structure and data layout being used.

So instead steal the arm64 approach and perform the fallback operations directly if required.

Fixes: cc333cd68dfa ("crypto: vmx - Adding GHASH routines for VMX module") Cc: stable@vger.kernel.org # v4.1+ Reported-by: Eric Biggers ebiggers@google.com Signed-off-by: Daniel Axtens dja@axtens.net Acked-by: Ard Biesheuvel ard.biesheuvel@linaro.org Tested-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Daniel Axtens dja@axtens.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/crypto/vmx/ghash.c | 213 ++++++++++++++++++--------------------------- 1 file changed, 87 insertions(+), 126 deletions(-)

--- a/drivers/crypto/vmx/ghash.c +++ b/drivers/crypto/vmx/ghash.c @@ -1,22 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 /** * GHASH routines supporting VMX instructions on the Power 8 * - * Copyright (C) 2015 International Business Machines Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 only. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + * Copyright (C) 2015, 2019 International Business Machines Inc. * * Author: Marcelo Henrique Cerri mhcerri@br.ibm.com + * + * Extended by Daniel Axtens dja@axtens.net to replace the fallback + * mechanism. The new approach is based on arm64 code, which is: + * Copyright (C) 2014 - 2018 Linaro Ltd. ard.biesheuvel@linaro.org */

#include <linux/types.h> @@ -39,71 +31,25 @@ void gcm_ghash_p8(u64 Xi[2], const u128 const u8 *in, size_t len);

struct p8_ghash_ctx { + /* key used by vector asm */ u128 htable[16]; - struct crypto_shash *fallback; + /* key used by software fallback */ + be128 key; };

struct p8_ghash_desc_ctx { u64 shash[2]; u8 buffer[GHASH_DIGEST_SIZE]; int bytes; - struct shash_desc fallback_desc; };

-static int p8_ghash_init_tfm(struct crypto_tfm *tfm) -{ - const char *alg = "ghash-generic"; - struct crypto_shash *fallback; - struct crypto_shash *shash_tfm = __crypto_shash_cast(tfm); - struct p8_ghash_ctx *ctx = crypto_tfm_ctx(tfm); - - fallback = crypto_alloc_shash(alg, 0, CRYPTO_ALG_NEED_FALLBACK); - if (IS_ERR(fallback)) { - printk(KERN_ERR - "Failed to allocate transformation for '%s': %ld\n", - alg, PTR_ERR(fallback)); - return PTR_ERR(fallback); - } - - crypto_shash_set_flags(fallback, - crypto_shash_get_flags((struct crypto_shash - *) tfm)); - - /* Check if the descsize defined in the algorithm is still enough. */ - if (shash_tfm->descsize < sizeof(struct p8_ghash_desc_ctx) - + crypto_shash_descsize(fallback)) { - printk(KERN_ERR - "Desc size of the fallback implementation (%s) does not match the expected value: %lu vs %u\n", - alg, - shash_tfm->descsize - sizeof(struct p8_ghash_desc_ctx), - crypto_shash_descsize(fallback)); - return -EINVAL; - } - ctx->fallback = fallback; - - return 0; -} - -static void p8_ghash_exit_tfm(struct crypto_tfm *tfm) -{ - struct p8_ghash_ctx *ctx = crypto_tfm_ctx(tfm); - - if (ctx->fallback) { - crypto_free_shash(ctx->fallback); - ctx->fallback = NULL; - } -} - static int p8_ghash_init(struct shash_desc *desc) { - struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm)); struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);

dctx->bytes = 0; memset(dctx->shash, 0, GHASH_DIGEST_SIZE); - dctx->fallback_desc.tfm = ctx->fallback; - dctx->fallback_desc.flags = desc->flags; - return crypto_shash_init(&dctx->fallback_desc); + return 0; }

static int p8_ghash_setkey(struct crypto_shash *tfm, const u8 *key, @@ -121,7 +67,51 @@ static int p8_ghash_setkey(struct crypto disable_kernel_vsx(); pagefault_enable(); preempt_enable(); - return crypto_shash_setkey(ctx->fallback, key, keylen); + + memcpy(&ctx->key, key, GHASH_BLOCK_SIZE); + + return 0; +} + +static inline void __ghash_block(struct p8_ghash_ctx *ctx, + struct p8_ghash_desc_ctx *dctx) +{ + if (!IN_INTERRUPT) { + preempt_disable(); + pagefault_disable(); + enable_kernel_vsx(); + gcm_ghash_p8(dctx->shash, ctx->htable, + dctx->buffer, GHASH_DIGEST_SIZE); + disable_kernel_vsx(); + pagefault_enable(); + preempt_enable(); + } else { + crypto_xor((u8 *)dctx->shash, dctx->buffer, GHASH_BLOCK_SIZE); + gf128mul_lle((be128 *)dctx->shash, &ctx->key); + } +} + +static inline void __ghash_blocks(struct p8_ghash_ctx *ctx, + struct p8_ghash_desc_ctx *dctx, + const u8 *src, unsigned int srclen) +{ + if (!IN_INTERRUPT) { + preempt_disable(); + pagefault_disable(); + enable_kernel_vsx(); + gcm_ghash_p8(dctx->shash, ctx->htable, + src, srclen); + disable_kernel_vsx(); + pagefault_enable(); + preempt_enable(); + } else { + while (srclen >= GHASH_BLOCK_SIZE) { + crypto_xor((u8 *)dctx->shash, src, GHASH_BLOCK_SIZE); + gf128mul_lle((be128 *)dctx->shash, &ctx->key); + srclen -= GHASH_BLOCK_SIZE; + src += GHASH_BLOCK_SIZE; + } + } }

static int p8_ghash_update(struct shash_desc *desc, @@ -131,49 +121,33 @@ static int p8_ghash_update(struct shash_ struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm)); struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);

- if (IN_INTERRUPT) { - return crypto_shash_update(&dctx->fallback_desc, src, - srclen); - } else { - if (dctx->bytes) { - if (dctx->bytes + srclen < GHASH_DIGEST_SIZE) { - memcpy(dctx->buffer + dctx->bytes, src, - srclen); - dctx->bytes += srclen; - return 0; - } + if (dctx->bytes) { + if (dctx->bytes + srclen < GHASH_DIGEST_SIZE) { memcpy(dctx->buffer + dctx->bytes, src, - GHASH_DIGEST_SIZE - dctx->bytes); - preempt_disable(); - pagefault_disable(); - enable_kernel_vsx(); - gcm_ghash_p8(dctx->shash, ctx->htable, - dctx->buffer, GHASH_DIGEST_SIZE); - disable_kernel_vsx(); - pagefault_enable(); - preempt_enable(); - src += GHASH_DIGEST_SIZE - dctx->bytes; - srclen -= GHASH_DIGEST_SIZE - dctx->bytes; - dctx->bytes = 0; + srclen); + dctx->bytes += srclen; + return 0; } - len = srclen & ~(GHASH_DIGEST_SIZE - 1); - if (len) { - preempt_disable(); - pagefault_disable(); - enable_kernel_vsx(); - gcm_ghash_p8(dctx->shash, ctx->htable, src, len); - disable_kernel_vsx(); - pagefault_enable(); - preempt_enable(); - src += len; - srclen -= len; - } - if (srclen) { - memcpy(dctx->buffer, src, srclen); - dctx->bytes = srclen; - } - return 0; + memcpy(dctx->buffer + dctx->bytes, src, + GHASH_DIGEST_SIZE - dctx->bytes); + + __ghash_block(ctx, dctx); + + src += GHASH_DIGEST_SIZE - dctx->bytes; + srclen -= GHASH_DIGEST_SIZE - dctx->bytes; + dctx->bytes = 0; + } + len = srclen & ~(GHASH_DIGEST_SIZE - 1); + if (len) { + __ghash_blocks(ctx, dctx, src, len); + src += len; + srclen -= len; } + if (srclen) { + memcpy(dctx->buffer, src, srclen); + dctx->bytes = srclen; + } + return 0; }

static int p8_ghash_final(struct shash_desc *desc, u8 *out) @@ -182,25 +156,14 @@ static int p8_ghash_final(struct shash_d struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm)); struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);

- if (IN_INTERRUPT) { - return crypto_shash_final(&dctx->fallback_desc, out); - } else { - if (dctx->bytes) { - for (i = dctx->bytes; i < GHASH_DIGEST_SIZE; i++) - dctx->buffer[i] = 0; - preempt_disable(); - pagefault_disable(); - enable_kernel_vsx(); - gcm_ghash_p8(dctx->shash, ctx->htable, - dctx->buffer, GHASH_DIGEST_SIZE); - disable_kernel_vsx(); - pagefault_enable(); - preempt_enable(); - dctx->bytes = 0; - } - memcpy(out, dctx->shash, GHASH_DIGEST_SIZE); - return 0; + if (dctx->bytes) { + for (i = dctx->bytes; i < GHASH_DIGEST_SIZE; i++) + dctx->buffer[i] = 0; + __ghash_block(ctx, dctx); + dctx->bytes = 0; } + memcpy(out, dctx->shash, GHASH_DIGEST_SIZE); + return 0; }

struct shash_alg p8_ghash_alg = { @@ -215,11 +178,9 @@ struct shash_alg p8_ghash_alg = { .cra_name = "ghash", .cra_driver_name = "p8_ghash", .cra_priority = 1000, - .cra_flags = CRYPTO_ALG_TYPE_SHASH | CRYPTO_ALG_NEED_FALLBACK, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = GHASH_BLOCK_SIZE, .cra_ctxsize = sizeof(struct p8_ghash_ctx), .cra_module = THIS_MODULE, - .cra_init = p8_ghash_init_tfm, - .cra_exit = p8_ghash_exit_tfm, }, };

From: David S. Miller davem@davemloft.net

commit 5593530e56943182ebb6d81eca8a3be6db6dbba4 upstream.

This reverts commit 532b0f7ece4cb2ffd24dc723ddf55242d1188e5e.

More revisions coming up.

Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/tipc/core.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-)

--- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -62,10 +62,6 @@ static int __net_init tipc_init_net(stru INIT_LIST_HEAD(&tn->node_list); spin_lock_init(&tn->node_list_lock);

- err = tipc_socket_init(); - if (err) - goto out_socket; - err = tipc_sk_rht_init(net); if (err) goto out_sk_rht; @@ -92,8 +88,6 @@ out_subscr: out_nametbl: tipc_sk_rht_destroy(net); out_sk_rht: - tipc_socket_stop(); -out_socket: return err; }

@@ -104,7 +98,6 @@ static void __net_exit tipc_exit_net(str tipc_bcast_stop(net); tipc_nametbl_stop(net); tipc_sk_rht_destroy(net); - tipc_socket_stop(); }

static struct pernet_operations tipc_net_ops = { @@ -140,6 +133,10 @@ static int __init tipc_init(void) if (err) goto out_pernet;

+ err = tipc_socket_init(); + if (err) + goto out_socket; + err = tipc_bearer_setup(); if (err) goto out_bearer; @@ -147,6 +144,8 @@ static int __init tipc_init(void) pr_info("Started in single node mode\n"); return 0; out_bearer: + tipc_socket_stop(); +out_socket: unregister_pernet_subsys(&tipc_net_ops); out_pernet: tipc_unregister_sysctl(); @@ -162,6 +161,7 @@ out_netlink: static void __exit tipc_exit(void) { tipc_bearer_cleanup(); + tipc_socket_stop(); unregister_pernet_subsys(&tipc_net_ops); tipc_netlink_stop(); tipc_netlink_compat_stop();

From: James Clarke jrtc27@jrtc27.com

commit d3c976c14ad8af421134c428b0a89ff8dd3bd8f8 upstream.

Previously, %g2 would end up with the value PAGE_SIZE, but after the commit mentioned below it ends up with the value 1 due to being reused for a different purpose. We need it to be PAGE_SIZE as we use it to step through pages in our demap loop, otherwise we set different flags in the low 12 bits of the address written to, thereby doing things other than a nucleus page flush.

Fixes: a74ad5e660a9 ("sparc64: Handle extremely large kernel TLB range flushes more gracefully.") Reported-by: Meelis Roos mroos@linux.ee Tested-by: Meelis Roos mroos@linux.ee Signed-off-by: James Clarke jrtc27@jrtc27.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/sparc/mm/ultra.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/arch/sparc/mm/ultra.S +++ b/arch/sparc/mm/ultra.S @@ -586,7 +586,7 @@ xcall_flush_tlb_kernel_range: /* 44 insn sub %g7, %g1, %g3 srlx %g3, 18, %g2 brnz,pn %g2, 2f - add %g2, 1, %g2 + sethi %hi(PAGE_SIZE), %g2 sub %g3, %g2, %g3 or %g1, 0x20, %g1 ! Nucleus 1: stxa %g0, [%g1 + %g3] ASI_DMMU_DEMAP @@ -750,7 +750,7 @@ __cheetah_xcall_flush_tlb_kernel_range: sub %g7, %g1, %g3 srlx %g3, 18, %g2 brnz,pn %g2, 2f - add %g2, 1, %g2 + sethi %hi(PAGE_SIZE), %g2 sub %g3, %g2, %g3 or %g1, 0x20, %g1 ! Nucleus 1: stxa %g0, [%g1 + %g3] ASI_DMMU_DEMAP

From: Henry Lin henryl@nvidia.com

commit 597c56e372dab2c7f79b8d700aad3a5deebf9d1b upstream.

This change fixes a data corruption issue occurred on USB hard disk for the case that bounce buffer is used during transferring data.

While updating data between sg list and bounce buffer, current implementation passes mapped sg number (urb->num_mapped_sgs) to sg_pcopy_from_buffer() and sg_pcopy_to_buffer(). This causes data not get copied if target buffer is located in the elements after mapped sg elements. This change passes sg number for full list to fix issue.

Besides, for copying data from bounce buffer, calling dma_unmap_single() on the bounce buffer before copying data to sg list can avoid cache issue.

Fixes: f9c589e142d0 ("xhci: TD-fragment, align the unsplittable case with a bounce buffer") Cc: stable@vger.kernel.org # v4.8+ Signed-off-by: Henry Lin henryl@nvidia.com Signed-off-by: Mathias Nyman mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/host/xhci-ring.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-)

--- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -678,6 +678,7 @@ void xhci_unmap_td_bounce_buffer(struct struct device *dev = xhci_to_hcd(xhci)->self.controller; struct xhci_segment *seg = td->bounce_seg; struct urb *urb = td->urb; + size_t len;

if (!seg || !urb) return; @@ -688,11 +689,14 @@ void xhci_unmap_td_bounce_buffer(struct return; }

- /* for in tranfers we need to copy the data from bounce to sg */ - sg_pcopy_from_buffer(urb->sg, urb->num_mapped_sgs, seg->bounce_buf, - seg->bounce_len, seg->bounce_offs); dma_unmap_single(dev, seg->bounce_dma, ring->bounce_buf_len, DMA_FROM_DEVICE); + /* for in tranfers we need to copy the data from bounce to sg */ + len = sg_pcopy_from_buffer(urb->sg, urb->num_sgs, seg->bounce_buf, + seg->bounce_len, seg->bounce_offs); + if (len != seg->bounce_len) + xhci_warn(xhci, "WARN Wrong bounce buffer read length: %ld != %d\n", + len, seg->bounce_len); seg->bounce_len = 0; seg->bounce_offs = 0; } @@ -3163,6 +3167,7 @@ static int xhci_align_td(struct xhci_hcd unsigned int unalign; unsigned int max_pkt; u32 new_buff_len; + size_t len;

max_pkt = GET_MAX_PACKET(usb_endpoint_maxp(&urb->ep->desc)); unalign = (enqd_len + *trb_buff_len) % max_pkt; @@ -3193,8 +3198,12 @@ static int xhci_align_td(struct xhci_hcd

/* create a max max_pkt sized bounce buffer pointed to by last trb */ if (usb_urb_dir_out(urb)) { - sg_pcopy_to_buffer(urb->sg, urb->num_mapped_sgs, + len = sg_pcopy_to_buffer(urb->sg, urb->num_sgs, seg->bounce_buf, new_buff_len, enqd_len); + if (len != seg->bounce_len) + xhci_warn(xhci, + "WARN Wrong bounce buffer write length: %ld != %d\n", + len, seg->bounce_len); seg->bounce_dma = dma_map_single(dev, seg->bounce_buf, max_pkt, DMA_TO_DEVICE); } else {

From: Andrey Smirnov andrew.smirnov@gmail.com

commit f7fac17ca925faa03fc5eb854c081a24075f8bad upstream.

Xhci_handshake() implements the algorithm already captured by readl_poll_timeout_atomic(). Convert the former to use the latter to avoid repetition.

Turned out this patch also fixes a bug on the AMD Stoneyridge platform where usleep(1) sometimes takes over 10ms. This means a 5 second timeout can easily take over 15 seconds which will trigger the watchdog and reboot the system.

[Add info about patch fixing a bug to commit message -Mathias] Signed-off-by: Andrey Smirnov andrew.smirnov@gmail.com Tested-by: Raul E Rangel rrangel@chromium.org Reviewed-by: Raul E Rangel rrangel@chromium.org Cc: stable@vger.kernel.org Signed-off-by: Mathias Nyman mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/host/xhci.c | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-)

--- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -21,6 +21,7 @@ */

#include <linux/pci.h> +#include <linux/iopoll.h> #include <linux/irq.h> #include <linux/log2.h> #include <linux/module.h> @@ -47,7 +48,6 @@ static unsigned int quirks; module_param(quirks, uint, S_IRUGO); MODULE_PARM_DESC(quirks, "Bit flags for quirks to be enabled as default");

-/* TODO: copied from ehci-hcd.c - can this be refactored? */ /* * xhci_handshake - spin reading hc until handshake completes or fails * @ptr: address of hc register to be read @@ -64,18 +64,16 @@ MODULE_PARM_DESC(quirks, "Bit flags for int xhci_handshake(void __iomem *ptr, u32 mask, u32 done, int usec) { u32 result; + int ret;

- do { - result = readl(ptr); - if (result == ~(u32)0) /* card removed */ - return -ENODEV; - result &= mask; - if (result == done) - return 0; - udelay(1); - usec--; - } while (usec > 0); - return -ETIMEDOUT; + ret = readl_poll_timeout_atomic(ptr, result, + (result & mask) == done || + result == U32_MAX, + 1, usec); + if (result == U32_MAX) /* card removed */ + return -ENODEV; + + return ret; }

/*

From: Shuah Khan skhan@linuxfoundation.org

commit 0c9e8b3cad654bfc499c10b652fbf8f0b890af8f upstream.

stub_probe() and stub_disconnect() call functions which could call sleeping function in invalid context whil holding busid_lock.

Fix the problem by refining the lock holds to short critical sections to change the busid_priv fields. This fix restructures the code to limit the lock holds in stub_probe() and stub_disconnect().

stub_probe():

[15217.927028] BUG: sleeping function called from invalid context at mm/slab.h:418 [15217.927038] in_atomic(): 1, irqs_disabled(): 0, pid: 29087, name: usbip [15217.927044] 5 locks held by usbip/29087: [15217.927047] #0: 0000000091647f28 (sb_writers#6){....}, at: vfs_write+0x191/0x1c0 [15217.927062] #1: 000000008f9ba75b (&of->mutex){....}, at: kernfs_fop_write+0xf7/0x1b0 [15217.927072] #2: 00000000872e5b4b (&dev->mutex){....}, at: __device_driver_lock+0x3b/0x50 [15217.927082] #3: 00000000e74ececc (&dev->mutex){....}, at: __device_driver_lock+0x46/0x50 [15217.927090] #4: 00000000b20abbe0 (&(&busid_table[i].busid_lock)->rlock){....}, at: get_busid_priv+0x48/0x60 [usbip_host] [15217.927103] CPU: 3 PID: 29087 Comm: usbip Tainted: G W 5.1.0-rc6+ #40 [15217.927106] Hardware name: Dell Inc. OptiPlex 790/0HY9JP, BIOS A18 09/24/2013 [15217.927109] Call Trace: [15217.927118] dump_stack+0x63/0x85 [15217.927127] ___might_sleep+0xff/0x120 [15217.927133] __might_sleep+0x4a/0x80 [15217.927143] kmem_cache_alloc_trace+0x1aa/0x210 [15217.927156] stub_probe+0xe8/0x440 [usbip_host] [15217.927171] usb_probe_device+0x34/0x70

stub_disconnect():

[15279.182478] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:908 [15279.182487] in_atomic(): 1, irqs_disabled(): 0, pid: 29114, name: usbip [15279.182492] 5 locks held by usbip/29114: [15279.182494] #0: 0000000091647f28 (sb_writers#6){....}, at: vfs_write+0x191/0x1c0 [15279.182506] #1: 00000000702cf0f3 (&of->mutex){....}, at: kernfs_fop_write+0xf7/0x1b0 [15279.182514] #2: 00000000872e5b4b (&dev->mutex){....}, at: __device_driver_lock+0x3b/0x50 [15279.182522] #3: 00000000e74ececc (&dev->mutex){....}, at: __device_driver_lock+0x46/0x50 [15279.182529] #4: 00000000b20abbe0 (&(&busid_table[i].busid_lock)->rlock){....}, at: get_busid_priv+0x48/0x60 [usbip_host] [15279.182541] CPU: 0 PID: 29114 Comm: usbip Tainted: G W 5.1.0-rc6+ #40 [15279.182543] Hardware name: Dell Inc. OptiPlex 790/0HY9JP, BIOS A18 09/24/2013 [15279.182546] Call Trace: [15279.182554] dump_stack+0x63/0x85 [15279.182561] ___might_sleep+0xff/0x120 [15279.182566] __might_sleep+0x4a/0x80 [15279.182574] __mutex_lock+0x55/0x950 [15279.182582] ? get_busid_priv+0x48/0x60 [usbip_host] [15279.182587] ? reacquire_held_locks+0xec/0x1a0 [15279.182591] ? get_busid_priv+0x48/0x60 [usbip_host] [15279.182597] ? find_held_lock+0x94/0xa0 [15279.182609] mutex_lock_nested+0x1b/0x20 [15279.182614] ? mutex_lock_nested+0x1b/0x20 [15279.182618] kernfs_remove_by_name_ns+0x2a/0x90 [15279.182625] sysfs_remove_file_ns+0x15/0x20 [15279.182629] device_remove_file+0x19/0x20 [15279.182634] stub_disconnect+0x6d/0x180 [usbip_host] [15279.182643] usb_unbind_device+0x27/0x60

Signed-off-by: Shuah Khan skhan@linuxfoundation.org Cc: stable stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/usbip/stub_dev.c | 65 ++++++++++++++++++++++++++++--------------- 1 file changed, 43 insertions(+), 22 deletions(-)

--- a/drivers/usb/usbip/stub_dev.c +++ b/drivers/usb/usbip/stub_dev.c @@ -315,9 +315,17 @@ static int stub_probe(struct usb_device const char *udev_busid = dev_name(&udev->dev); struct bus_id_priv *busid_priv; int rc = 0; + char save_status;

dev_dbg(&udev->dev, "Enter probe\n");

+ /* Not sure if this is our device. Allocate here to avoid + * calling alloc while holding busid_table lock. + */ + sdev = stub_device_alloc(udev); + if (!sdev) + return -ENOMEM; + /* check we should claim or not by busid_table */ busid_priv = get_busid_priv(udev_busid); if (!busid_priv || (busid_priv->status == STUB_BUSID_REMOV) || @@ -332,14 +340,14 @@ static int stub_probe(struct usb_device * See driver_probe_device() in driver/base/dd.c */ rc = -ENODEV; - goto call_put_busid_priv; + goto sdev_free; }

if (udev->descriptor.bDeviceClass == USB_CLASS_HUB) { dev_dbg(&udev->dev, "%s is a usb hub device... skip!\n", udev_busid); rc = -ENODEV; - goto call_put_busid_priv; + goto sdev_free; }

if (!strcmp(udev->bus->bus_name, "vhci_hcd")) { @@ -348,15 +356,9 @@ static int stub_probe(struct usb_device udev_busid);

rc = -ENODEV; - goto call_put_busid_priv; + goto sdev_free; }

- /* ok, this is my device */ - sdev = stub_device_alloc(udev); - if (!sdev) { - rc = -ENOMEM; - goto call_put_busid_priv; - }

dev_info(&udev->dev, "usbip-host: register new device (bus %u dev %u)\n", @@ -366,9 +368,13 @@ static int stub_probe(struct usb_device

/* set private data to usb_device */ dev_set_drvdata(&udev->dev, sdev); + busid_priv->sdev = sdev; busid_priv->udev = udev;

+ save_status = busid_priv->status; + busid_priv->status = STUB_BUSID_ALLOC; + /* * Claim this hub port. * It doesn't matter what value we pass as owner @@ -381,15 +387,16 @@ static int stub_probe(struct usb_device goto err_port; }

+ /* release the busid_lock */ + put_busid_priv(busid_priv); + rc = stub_add_files(&udev->dev); if (rc) { dev_err(&udev->dev, "stub_add_files for %s\n", udev_busid); goto err_files; } - busid_priv->status = STUB_BUSID_ALLOC;

- rc = 0; - goto call_put_busid_priv; + return 0;

err_files: usb_hub_release_port(udev->parent, udev->portnum, @@ -398,23 +405,24 @@ err_port: dev_set_drvdata(&udev->dev, NULL); usb_put_dev(udev);

+ /* we already have busid_priv, just lock busid_lock */ + spin_lock(&busid_priv->busid_lock); busid_priv->sdev = NULL; + busid_priv->status = save_status; +sdev_free: stub_device_free(sdev); - -call_put_busid_priv: + /* release the busid_lock */ put_busid_priv(busid_priv); + return rc; }

static void shutdown_busid(struct bus_id_priv *busid_priv) { - if (busid_priv->sdev && !busid_priv->shutdown_busid) { - busid_priv->shutdown_busid = 1; - usbip_event_add(&busid_priv->sdev->ud, SDEV_EVENT_REMOVED); + usbip_event_add(&busid_priv->sdev->ud, SDEV_EVENT_REMOVED);

- /* wait for the stop of the event handler */ - usbip_stop_eh(&busid_priv->sdev->ud); - } + /* wait for the stop of the event handler */ + usbip_stop_eh(&busid_priv->sdev->ud); }

/* @@ -446,6 +454,9 @@ static void stub_disconnect(struct usb_d

dev_set_drvdata(&udev->dev, NULL);

+ /* release busid_lock before call to remove device files */ + put_busid_priv(busid_priv); + /* * NOTE: rx/tx threads are invoked for each usb_device. */ @@ -456,18 +467,27 @@ static void stub_disconnect(struct usb_d (struct usb_dev_state *) udev); if (rc) { dev_dbg(&udev->dev, "unable to release port\n"); - goto call_put_busid_priv; + return; }

/* If usb reset is called from event handler */ if (usbip_in_eh(current)) - goto call_put_busid_priv; + return; + + /* we already have busid_priv, just lock busid_lock */ + spin_lock(&busid_priv->busid_lock); + if (!busid_priv->shutdown_busid) + busid_priv->shutdown_busid = 1; + /* release busid_lock */ + put_busid_priv(busid_priv);

/* shutdown the current connection */ shutdown_busid(busid_priv);

usb_put_dev(sdev->udev);

+ /* we already have busid_priv, just lock busid_lock */ + spin_lock(&busid_priv->busid_lock); /* free sdev */ busid_priv->sdev = NULL; stub_device_free(sdev); @@ -476,6 +496,7 @@ static void stub_disconnect(struct usb_d busid_priv->status = STUB_BUSID_ADDED;

call_put_busid_priv: + /* release busid_lock */ put_busid_priv(busid_priv); }

From: Alan Stern stern@rowland.harvard.edu

commit a03ff54460817c76105f81f3aa8ef655759ccc9a upstream.

The syzkaller USB fuzzer found a slab-out-of-bounds write bug in the USB core, caused by a failure to check the actual size of a BOS descriptor. This patch adds a check to make sure the descriptor is at least as large as it is supposed to be, so that the code doesn't inadvertently access memory beyond the end of the allocated region when assigning to dev->bos->desc->bNumDeviceCaps later on.

Signed-off-by: Alan Stern stern@rowland.harvard.edu Reported-and-tested-by: syzbot+71f1e64501a309fcc012@syzkaller.appspotmail.com CC: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/core/config.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -931,8 +931,8 @@ int usb_get_bos_descriptor(struct usb_de

/* Get BOS descriptor */ ret = usb_get_descriptor(dev, USB_DT_BOS, 0, bos, USB_DT_BOS_SIZE); - if (ret < USB_DT_BOS_SIZE) { - dev_err(ddev, "unable to get BOS descriptor\n"); + if (ret < USB_DT_BOS_SIZE || bos->bLength < USB_DT_BOS_SIZE) { + dev_err(ddev, "unable to get BOS descriptor or descriptor too short\n"); if (ret >= 0) ret = -ENOMSG; kfree(bos);

From: Maximilian Luz luzmaximilian@gmail.com

commit ea261113385ac0a71c2838185f39e8452d54b152 upstream.

Without USB_QUIRK_NO_LPM ethernet will not work and rtl8152 will complain with

r8152 <device...>: Stop submitting intr, status -71

Adding the quirk resolves this. As the dock is externally powered, this should not have any drawbacks.

Signed-off-by: Maximilian Luz luzmaximilian@gmail.com Cc: stable stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/core/quirks.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -64,6 +64,9 @@ static const struct usb_device_id usb_qu /* Microsoft LifeCam-VX700 v2.0 */ { USB_DEVICE(0x045e, 0x0770), .driver_info = USB_QUIRK_RESET_RESUME },

+ /* Microsoft Surface Dock Ethernet (RTL8153 GigE) */ + { USB_DEVICE(0x045e, 0x07c6), .driver_info = USB_QUIRK_NO_LPM }, + /* Cherry Stream G230 2.0 (G85-231) and 3.0 (G85-232) */ { USB_DEVICE(0x046a, 0x0023), .driver_info = USB_QUIRK_RESET_RESUME },

From: Oliver Neukum oneukum@suse.com

commit e0feb73428b69322dd5caae90b0207de369b5575 upstream.

If a disconnected device is closed, rio_close() must free the buffers.

Signed-off-by: Oliver Neukum oneukum@suse.com Cc: stable stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/usb/misc/rio500.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-)

--- a/drivers/usb/misc/rio500.c +++ b/drivers/usb/misc/rio500.c @@ -103,9 +103,22 @@ static int close_rio(struct inode *inode { struct rio_usb_data *rio = &rio_instance;

- rio->isopen = 0; + /* against disconnect() */ + mutex_lock(&rio500_mutex); + mutex_lock(&(rio->lock));

- dev_info(&rio->rio_dev->dev, "Rio closed.\n"); + rio->isopen = 0; + if (!rio->present) { + /* cleanup has been delayed */ + kfree(rio->ibuf); + kfree(rio->obuf); + rio->ibuf = NULL; + rio->obuf = NULL; + } else { + dev_info(&rio->rio_dev->dev, "Rio closed.\n"); + } + mutex_unlock(&(rio->lock)); + mutex_unlock(&rio500_mutex); return 0; }

From: Alan Stern stern@rowland.harvard.edu

commit 45457c01171fd1488a7000d1751c06ed8560ee38 upstream.

GCC complains about an apparently uninitialized variable recently added to smsusb_init_device(). It's a false positive, but to silence the warning this patch adds a trivial initialization.

Signed-off-by: Alan Stern stern@rowland.harvard.edu Reported-by: kbuild test robot lkp@intel.com CC: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/media/usb/siano/smsusb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/media/usb/siano/smsusb.c +++ b/drivers/media/usb/siano/smsusb.c @@ -402,7 +402,7 @@ static int smsusb_init_device(struct usb struct smsusb_device_t *dev; void *mdev; int i, rc; - int in_maxp; + int in_maxp = 0;

/* create device object */ dev = kzalloc(sizeof(struct smsusb_device_t), GFP_KERNEL);

From: Steffen Maier maier@linux.ibm.com

commit d27e5e07f9c49bf2a6a4ef254ce531c1b4fb5a38 upstream.

With this early return due to zfcp_unit child(ren), we don't use the zfcp_port reference from the earlier zfcp_get_port_by_wwpn() anymore and need to put it.

Signed-off-by: Steffen Maier maier@linux.ibm.com Fixes: d99b601b6338 ("[SCSI] zfcp: restore refcount check on port_remove") Cc: stable@vger.kernel.org #3.7+ Reviewed-by: Jens Remus jremus@linux.ibm.com Reviewed-by: Benjamin Block bblock@linux.ibm.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/s390/scsi/zfcp_sysfs.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/s390/scsi/zfcp_sysfs.c +++ b/drivers/s390/scsi/zfcp_sysfs.c @@ -263,6 +263,7 @@ static ssize_t zfcp_sysfs_port_remove_st if (atomic_read(&port->units) > 0) { retval = -EBUSY; mutex_unlock(&zfcp_sysfs_port_units_mutex); + put_device(&port->dev); /* undo zfcp_get_port_by_wwpn() */ goto out; } /* port is about to be removed, so no more unit_add */

From: Filipe Manana fdmanana@suse.com

commit 06989c799f04810f6876900d4760c0edda369cf7 upstream.

When syncing the log, the final phase of a fsync operation, we need to either create a log root's item or update the existing item in the log tree of log roots, and that depends on the current value of the log root's log_transid - if it's 1 we need to create the log root item, otherwise it must exist already and we update it. Since there is no synchronization between updating the log_transid and checking it for deciding whether the log root's item needs to be created or updated, we end up with a tiny race window that results in attempts to update the item to fail because the item was not yet created:

CPU 1 CPU 2

btrfs_sync_log()

lock root->log_mutex

set log root's log_transid to 1

unlock root->log_mutex

btrfs_sync_log()

lock root->log_mutex

sets log root's log_transid to 2

unlock root->log_mutex

update_log_root()

sees log root's log_transid with a value of 2

calls btrfs_update_root(), which fails with -EUCLEAN and causes transaction abort

Until recently the race lead to a BUG_ON at btrfs_update_root(), but after the recent commit 7ac1e464c4d47 ("btrfs: Don't panic when we can't find a root key") we just abort the current transaction.

A sample trace of the BUG_ON() on a SLE12 kernel:

------------[ cut here ]------------ kernel BUG at ../fs/btrfs/root-tree.c:157! Oops: Exception in kernel mode, sig: 5 [#1] SMP NR_CPUS=2048 NUMA pSeries (...) Supported: Yes, External CPU: 78 PID: 76303 Comm: rtas_errd Tainted: G X 4.4.156-94.57-default #1 task: c00000ffa906d010 ti: c00000ff42b08000 task.ti: c00000ff42b08000 NIP: d000000036ae5cdc LR: d000000036ae5cd8 CTR: 0000000000000000 REGS: c00000ff42b0b860 TRAP: 0700 Tainted: G X (4.4.156-94.57-default) MSR: 8000000002029033 <SF,VEC,EE,ME,IR,DR,RI,LE> CR: 22444484 XER: 20000000 CFAR: d000000036aba66c SOFTE: 1 GPR00: d000000036ae5cd8 c00000ff42b0bae0 d000000036bda220 0000000000000054 GPR04: 0000000000000001 0000000000000000 c00007ffff8d37c8 0000000000000000 GPR08: c000000000e19c00 0000000000000000 0000000000000000 3736343438312079 GPR12: 3930373337303434 c000000007a3a800 00000000007fffff 0000000000000023 GPR16: c00000ffa9d26028 c00000ffa9d261f8 0000000000000010 c00000ffa9d2ab28 GPR20: c00000ff42b0bc48 0000000000000001 c00000ff9f0d9888 0000000000000001 GPR24: c00000ffa9d26000 c00000ffa9d261e8 c00000ffa9d2a800 c00000ff9f0d9888 GPR28: c00000ffa9d26028 c00000ffa9d2aa98 0000000000000001 c00000ffa98f5b20 NIP [d000000036ae5cdc] btrfs_update_root+0x25c/0x4e0 [btrfs] LR [d000000036ae5cd8] btrfs_update_root+0x258/0x4e0 [btrfs] Call Trace: [c00000ff42b0bae0] [d000000036ae5cd8] btrfs_update_root+0x258/0x4e0 [btrfs] (unreliable) [c00000ff42b0bba0] [d000000036b53610] btrfs_sync_log+0x2d0/0xc60 [btrfs] [c00000ff42b0bce0] [d000000036b1785c] btrfs_sync_file+0x44c/0x4e0 [btrfs] [c00000ff42b0bd80] [c00000000032e300] vfs_fsync_range+0x70/0x120 [c00000ff42b0bdd0] [c00000000032e44c] do_fsync+0x5c/0xb0 [c00000ff42b0be10] [c00000000032e8dc] SyS_fdatasync+0x2c/0x40 [c00000ff42b0be30] [c000000000009488] system_call+0x3c/0x100 Instruction dump: 7f43d378 4bffebb9 60000000 88d90008 3d220000 e8b90000 3b390009 e87a01f0 e8898e08 e8f90000 4bfd48e5 60000000 <0fe00000> e95b0060 39200004 394a0ea0 ---[ end trace 8f2dc8f919cabab8 ]---

So fix this by doing the check of log_transid and updating or creating the log root's item while holding the root's log_mutex.

Fixes: 7237f1833601d ("Btrfs: fix tree logs parallel sync") CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana fdmanana@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/btrfs/tree-log.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

--- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2827,6 +2827,12 @@ int btrfs_sync_log(struct btrfs_trans_ha log->log_transid = root->log_transid; root->log_start_pid = 0; /* + * Update or create log root item under the root's log_mutex to prevent + * races with concurrent log syncs that can lead to failure to update + * log root item because it was not created yet. + */ + ret = update_log_root(trans, log); + /* * IO has been started, blocks of the log tree have WRITTEN flag set * in their headers. new modifications of the log will be written to * new positions. so it's safe to allow log writers to go in. @@ -2845,8 +2851,6 @@ int btrfs_sync_log(struct btrfs_trans_ha

mutex_unlock(&log_root_tree->log_mutex);

- ret = update_log_root(trans, log); - mutex_lock(&log_root_tree->log_mutex); if (atomic_dec_and_test(&log_root_tree->log_writers)) { /*

From: Kailang Yang kailang@realtek.com

commit 317d9313925cd8388304286c0d3c8dda7f060a2d upstream.

I measured power consumption between power_save_node=1 and power_save_node=0. It's almost the same. Codec will enter to runtime suspend and suspend. That pin also will enter to D3. Don't need to enter to D3 by single pin. So, Disable power_save_node as default. It will avoid more issues. Windows Driver also has not this option at runtime PM.

Signed-off-by: Kailang Yang kailang@realtek.com Cc: stable@vger.kernel.org Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/pci/hda/patch_realtek.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6317,7 +6317,7 @@ static int patch_alc269(struct hda_codec

spec = codec->spec; spec->gen.shared_mic_vref_pin = 0x18; - codec->power_save_node = 1; + codec->power_save_node = 0;

#ifdef CONFIG_PM codec->patch_ops.suspend = alc269_suspend;

From: Jorge Ramirez-Ortiz jorge.ramirez-ortiz@linaro.org

commit 61c0e37950b88bad590056286c1d766b1f167f4e upstream.

When the tty layer requests the uart to throttle, the current code executing in msm_serial will trigger "Bad mode in Error Handler" and generate an invalid stack frame in pstore before rebooting (that is if pstore is indeed configured: otherwise the user shall just notice a reboot with no further information dumped to the console).

This patch replaces the PIO byte accessor with the word accessor already used in PIO mode.

Fixes: 68252424a7c7 ("tty: serial: msm: Support big-endian CPUs") Cc: stable@vger.kernel.org Signed-off-by: Jorge Ramirez-Ortiz jorge.ramirez-ortiz@linaro.org Reviewed-by: Bjorn Andersson bjorn.andersson@linaro.org Reviewed-by: Stephen Boyd swboyd@chromium.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/tty/serial/msm_serial.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/drivers/tty/serial/msm_serial.c +++ b/drivers/tty/serial/msm_serial.c @@ -868,6 +868,7 @@ static void msm_handle_tx(struct uart_po struct circ_buf *xmit = &msm_port->uart.state->xmit; struct msm_dma *dma = &msm_port->tx_dma; unsigned int pio_count, dma_count, dma_min; + char buf[4] = { 0 }; void __iomem *tf; int err = 0;

@@ -877,10 +878,12 @@ static void msm_handle_tx(struct uart_po else tf = port->membase + UART_TF;

+ buf[0] = port->x_char; + if (msm_port->is_uartdm) msm_reset_dm_count(port, 1);

- iowrite8_rep(tf, &port->x_char, 1); + iowrite32_rep(tf, buf, 1); port->icount.tx++; port->x_char = 0; return;

From: Jiri Slaby jslaby@suse.cz

commit 3e8589963773a5c23e2f1fe4bcad0e9a90b7f471 upstream.

We have a single node system with node 0 disabled: Scanning NUMA topology in Northbridge 24 Number of physical nodes 2 Skipping disabled node 0 Node 1 MemBase 0000000000000000 Limit 00000000fbff0000 NODE_DATA(1) allocated [mem 0xfbfda000-0xfbfeffff]

This causes crashes in memcg when system boots: BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 #PF error: [normal kernel read fault] ... RIP: 0010:list_lru_add+0x94/0x170 ... Call Trace: d_lru_add+0x44/0x50 dput.part.34+0xfc/0x110 __fput+0x108/0x230 task_work_run+0x9f/0xc0 exit_to_usermode_loop+0xf5/0x100

It is reproducible as far as 4.12. I did not try older kernels. You have to have a new enough systemd, e.g. 241 (the reason is unknown -- was not investigated). Cannot be reproduced with systemd 234.

The system crashes because the size of lru array is never updated in memcg_update_all_list_lrus and the reads are past the zero-sized array, causing dereferences of random memory.

The root cause are list_lru_memcg_aware checks in the list_lru code. The test in list_lru_memcg_aware is broken: it assumes node 0 is always present, but it is not true on some systems as can be seen above.

So fix this by avoiding checks on node 0. Remember the memcg-awareness by a bool flag in struct list_lru.

Link: http://lkml.kernel.org/r/20190522091940.3615-1-jslaby@suse.cz Fixes: 60d3fd32a7a9 ("list_lru: introduce per-memcg lists") Signed-off-by: Jiri Slaby jslaby@suse.cz Acked-by: Michal Hocko mhocko@suse.com Suggested-by: Vladimir Davydov vdavydov.dev@gmail.com Acked-by: Vladimir Davydov vdavydov.dev@gmail.com Reviewed-by: Shakeel Butt shakeelb@google.com Cc: Johannes Weiner hannes@cmpxchg.org Cc: Raghavendra K T raghavendra.kt@linux.vnet.ibm.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- include/linux/list_lru.h | 1 + mm/list_lru.c | 8 +++----- 2 files changed, 4 insertions(+), 5 deletions(-)

--- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -51,6 +51,7 @@ struct list_lru { struct list_lru_node *node; #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) struct list_head list; + bool memcg_aware; #endif };

--- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -42,11 +42,7 @@ static void list_lru_unregister(struct l #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) static inline bool list_lru_memcg_aware(struct list_lru *lru) { - /* - * This needs node 0 to be always present, even - * in the systems supporting sparse numa ids. - */ - return !!lru->node[0].memcg_lrus; + return lru->memcg_aware; }

static inline struct list_lru_one * @@ -389,6 +385,8 @@ static int memcg_init_list_lru(struct li { int i;

+ lru->memcg_aware = memcg_aware; + if (!memcg_aware) return 0;

From: Jonathan Corbet corbet@lwn.net

commit 3bc8088464712fdcb078eefb68837ccfcc413c88 upstream.

Our version check in Documentation/conf.py never envisioned a world where Sphinx moved beyond 1.x. Now that the unthinkable has happened, fix our version check to handle higher version numbers correctly.

Cc: stable@vger.kernel.org Signed-off-by: Jonathan Corbet corbet@lwn.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- Documentation/conf.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/Documentation/conf.py +++ b/Documentation/conf.py @@ -37,7 +37,7 @@ from load_config import loadConfig extensions = ['kernel-doc', 'rstFlatTable', 'kernel_include', 'cdomain']

# The name of the math extension changed on Sphinx 1.4 -if major == 1 and minor > 3: +if (major == 1 and minor > 3) or (major > 1): extensions.append("sphinx.ext.imgmath") else: extensions.append("sphinx.ext.pngmath")

From: Roberto Bergantinos Corpas rbergant@redhat.com

commit 31fad7d41e73731f05b8053d17078638cf850fa6 upstream.

In cifs_read_allocate_pages, in case of ENOMEM, we go through whole rdata->pages array but we have failed the allocation before nr_pages, therefore we may end up calling put_page with NULL pointer, causing oops

Signed-off-by: Roberto Bergantinos Corpas rbergant@redhat.com Acked-by: Pavel Shilovsky pshilov@microsoft.com Signed-off-by: Steve French stfrench@microsoft.com CC: Stable stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/cifs/file.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2892,7 +2892,9 @@ cifs_read_allocate_pages(struct cifs_rea }

if (rc) { - for (i = 0; i < nr_pages; i++) { + unsigned int nr_page_failed = i; + + for (i = 0; i < nr_page_failed; i++) { put_page(rdata->pages[i]); rdata->pages[i] = NULL; }

From: Thomas Hellstrom thellstrom@vmware.com

commit 63cb44441826e842b7285575b96db631cc9f2505 upstream.

This may confuse user-space clients like plymouth that opens a drm file descriptor as a result of a hotplug event and then generates a new event...

Cc: stable@vger.kernel.org Fixes: 5ea1734827bb ("drm/vmwgfx: Send a hotplug event at master_set") Signed-off-by: Thomas Hellstrom thellstrom@vmware.com Reviewed-by: Deepak Rawat drawat@vmware.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -1245,7 +1245,13 @@ static int vmw_master_set(struct drm_dev }

dev_priv->active_master = vmaster; - drm_sysfs_hotplug_event(dev); + + /* + * Inform a new master that the layout may have changed while + * it was gone. + */ + if (!from_open) + drm_sysfs_hotplug_event(dev);

return 0; }

From: Arend van Spriel arend.vanspriel@broadcom.com

commit 1b5e2423164b3670e8bc9174e4762d297990deff upstream.

The SSID length as received from firmware should not exceed IEEE80211_MAX_SSID_LEN as that would result in heap overflow.

Reviewed-by: Hante Meuleman hante.meuleman@broadcom.com Reviewed-by: Pieter-Paul Giesberts pieter-paul.giesberts@broadcom.com Reviewed-by: Franky Lin franky.lin@broadcom.com Signed-off-by: Arend van Spriel arend.vanspriel@broadcom.com Signed-off-by: Kalle Valo kvalo@codeaurora.org [bwh: Backported to 4.9: adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -3579,6 +3579,8 @@ brcmf_wowl_nd_results(struct brcmf_if *i

data += sizeof(struct brcmf_pno_scanresults_le); netinfo = (struct brcmf_pno_net_info_le *)data; + if (netinfo->SSID_len > IEEE80211_MAX_SSID_LEN) + netinfo->SSID_len = IEEE80211_MAX_SSID_LEN; memcpy(cfg->wowl.nd->ssid.ssid, netinfo->SSID, netinfo->SSID_len); cfg->wowl.nd->ssid.ssid_len = netinfo->SSID_len; cfg->wowl.nd->n_channels = 1;

From: Ben Hutchings ben.hutchings@codethink.co.uk

This was done as part of upstream commits fdfb4a99b6ab "8inder: separate binder allocator structure from binder proc", 19c987241ca1 "binder: separate out binder_alloc functions", and 7a4408c6bd3e "binder: make sure accesses to proc/thread are safe". However, those commits made lots of other changes that are not suitable for stable.

Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/android/binder.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-)

--- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -488,7 +488,7 @@ static void binder_insert_free_buffer(st new_buffer_size = binder_buffer_size(proc, new_buffer);

binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: add free buffer, size %zd, at %p\n", + "%d: add free buffer, size %zd, at %pK\n", proc->pid, new_buffer_size, new_buffer);

while (*p) { @@ -566,7 +566,7 @@ static int binder_update_page_range(stru struct mm_struct *mm;

binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: %s pages %p-%p\n", proc->pid, + "%d: %s pages %pK-%pK\n", proc->pid, allocate ? "allocate" : "free", start, end);

if (end <= start) @@ -606,7 +606,7 @@ static int binder_update_page_range(stru BUG_ON(*page); *page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO); if (*page == NULL) { - pr_err("%d: binder_alloc_buf failed for page at %p\n", + pr_err("%d: binder_alloc_buf failed for page at %pK\n", proc->pid, page_addr); goto err_alloc_page_failed; } @@ -615,7 +615,7 @@ static int binder_update_page_range(stru flush_cache_vmap((unsigned long)page_addr, (unsigned long)page_addr + PAGE_SIZE); if (ret != 1) { - pr_err("%d: binder_alloc_buf failed to map page at %p in kernel\n", + pr_err("%d: binder_alloc_buf failed to map page at %pK in kernel\n", proc->pid, page_addr); goto err_map_kernel_failed; } @@ -719,7 +719,7 @@ static struct binder_buffer *binder_allo }

binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: binder_alloc_buf size %zd got buffer %p size %zd\n", + "%d: binder_alloc_buf size %zd got buffer %pK size %zd\n", proc->pid, size, buffer, buffer_size);

has_page_addr = @@ -749,7 +749,7 @@ static struct binder_buffer *binder_allo binder_insert_free_buffer(proc, new_buffer); } binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: binder_alloc_buf size %zd got %p\n", + "%d: binder_alloc_buf size %zd got %pK\n", proc->pid, size, buffer); buffer->data_size = data_size; buffer->offsets_size = offsets_size; @@ -789,7 +789,7 @@ static void binder_delete_free_buffer(st if (buffer_end_page(prev) == buffer_end_page(buffer)) free_page_end = 0; binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: merge free, buffer %p share page with %p\n", + "%d: merge free, buffer %pK share page with %pK\n", proc->pid, buffer, prev); }

@@ -802,14 +802,14 @@ static void binder_delete_free_buffer(st buffer_start_page(buffer)) free_page_start = 0; binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: merge free, buffer %p share page with %p\n", + "%d: merge free, buffer %pK share page with %pK\n", proc->pid, buffer, prev); } } list_del(&buffer->entry); if (free_page_start || free_page_end) { binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: merge free, buffer %p do not share page%s%s with %p or %p\n", + "%d: merge free, buffer %pK do not share page%s%s with %pK or %pK\n", proc->pid, buffer, free_page_start ? "" : " end", free_page_end ? "" : " start", prev, next); binder_update_page_range(proc, 0, free_page_start ? @@ -830,7 +830,7 @@ static void binder_free_buf(struct binde ALIGN(buffer->offsets_size, sizeof(void *));

binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: binder_free_buf %p size %zd buffer_size %zd\n", + "%d: binder_free_buf %pK size %zd buffer_size %zd\n", proc->pid, buffer, size, buffer_size);

BUG_ON(buffer->free); @@ -2930,7 +2930,7 @@ static int binder_mmap(struct file *filp #ifdef CONFIG_CPU_CACHE_VIPT if (cache_is_vipt_aliasing()) { while (CACHE_COLOUR((vma->vm_start ^ (uint32_t)proc->buffer))) { - pr_info("binder_mmap: %d %lx-%lx maps %p bad alignment\n", proc->pid, vma->vm_start, vma->vm_end, proc->buffer); + pr_info("binder_mmap: %d %lx-%lx maps %pK bad alignment\n", proc->pid, vma->vm_start, vma->vm_end, proc->buffer); vma->vm_start += PAGE_SIZE; } } @@ -3191,7 +3191,7 @@ static void binder_deferred_release(stru

page_addr = proc->buffer + i * PAGE_SIZE; binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%s: %d: page %d at %p not freed\n", + "%s: %d: page %d at %pK not freed\n", __func__, proc->pid, i, page_addr); unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE); __free_page(proc->pages[i]); @@ -3294,7 +3294,7 @@ static void print_binder_transaction(str static void print_binder_buffer(struct seq_file *m, const char *prefix, struct binder_buffer *buffer) { - seq_printf(m, "%s %d: %p size %zd:%zd %s\n", + seq_printf(m, "%s %d: %pK size %zd:%zd %s\n", prefix, buffer->debug_id, buffer->data, buffer->data_size, buffer->offsets_size, buffer->transaction ? "active" : "delivered"); @@ -3397,7 +3397,7 @@ static void print_binder_node(struct seq

static void print_binder_ref(struct seq_file *m, struct binder_ref *ref) { - seq_printf(m, " ref %d: desc %d %snode %d s %d w %d d %p\n", + seq_printf(m, " ref %d: desc %d %snode %d s %d w %d d %pK\n", ref->debug_id, ref->desc, ref->node->proc ? "" : "dead ", ref->node->debug_id, ref->strong, ref->weak, ref->death); }

From: Matthew Wilcox willy@infradead.org

commit 15fab63e1e57be9fdb5eec1bbc5916e9825e9acb upstream.

Change pipe_buf_get() to return a bool indicating whether it succeeded in raising the refcount of the page (if the thing in the pipe is a page). This removes another mechanism for overflowing the page refcount. All callers converted to handle a failure.

Reported-by: Jann Horn jannh@google.com Signed-off-by: Matthew Wilcox willy@infradead.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org [bwh: Backported to 4.9: adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/fuse/dev.c | 12 ++++++------ fs/pipe.c | 4 ++-- fs/splice.c | 12 ++++++++++-- include/linux/pipe_fs_i.h | 10 ++++++---- kernel/trace/trace.c | 6 +++++- 5 files changed, 29 insertions(+), 15 deletions(-)

--- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1975,10 +1975,8 @@ static ssize_t fuse_dev_splice_write(str rem += pipe->bufs[(pipe->curbuf + idx) & (pipe->buffers - 1)].len;

ret = -EINVAL; - if (rem < len) { - pipe_unlock(pipe); - goto out; - } + if (rem < len) + goto out_free;

rem = len; while (rem) { @@ -1996,7 +1994,9 @@ static ssize_t fuse_dev_splice_write(str pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1); pipe->nrbufs--; } else { - pipe_buf_get(pipe, ibuf); + if (!pipe_buf_get(pipe, ibuf)) + goto out_free; + *obuf = *ibuf; obuf->flags &= ~PIPE_BUF_FLAG_GIFT; obuf->len = rem; @@ -2019,11 +2019,11 @@ static ssize_t fuse_dev_splice_write(str ret = fuse_dev_do_write(fud, &cs, len);

pipe_lock(pipe); +out_free: for (idx = 0; idx < nbuf; idx++) pipe_buf_release(pipe, &bufs[idx]); pipe_unlock(pipe);

-out: kfree(bufs); return ret; } --- a/fs/pipe.c +++ b/fs/pipe.c @@ -193,9 +193,9 @@ EXPORT_SYMBOL(generic_pipe_buf_steal); * in the tee() system call, when we duplicate the buffers in one * pipe into another. */ -void generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) +bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - get_page(buf->page); + return try_get_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_get);

--- a/fs/splice.c +++ b/fs/splice.c @@ -1585,7 +1585,11 @@ retry: * Get a reference to this pipe buffer, * so we can copy the contents over. */ - pipe_buf_get(ipipe, ibuf); + if (!pipe_buf_get(ipipe, ibuf)) { + if (ret == 0) + ret = -EFAULT; + break; + } *obuf = *ibuf;

/* @@ -1659,7 +1663,11 @@ static int link_pipe(struct pipe_inode_i * Get a reference to this pipe buffer, * so we can copy the contents over. */ - pipe_buf_get(ipipe, ibuf); + if (!pipe_buf_get(ipipe, ibuf)) { + if (ret == 0) + ret = -EFAULT; + break; + }

obuf = opipe->bufs + nbuf; *obuf = *ibuf; --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -107,18 +107,20 @@ struct pipe_buf_operations { /* * Get a reference to the pipe buffer. */ - void (*get)(struct pipe_inode_info *, struct pipe_buffer *); + bool (*get)(struct pipe_inode_info *, struct pipe_buffer *); };

/** * pipe_buf_get - get a reference to a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to get a reference to + * + * Return: %true if the reference was successfully obtained. */ -static inline void pipe_buf_get(struct pipe_inode_info *pipe, +static inline __must_check bool pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - buf->ops->get(pipe, buf); + return buf->ops->get(pipe, buf); }

/** @@ -178,7 +180,7 @@ struct pipe_inode_info *alloc_pipe_info( void free_pipe_info(struct pipe_inode_info *);

/* Generic pipe buffer ops functions */ -void generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); +bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6145,12 +6145,16 @@ static void buffer_pipe_buf_release(stru buf->private = 0; }

-static void buffer_pipe_buf_get(struct pipe_inode_info *pipe, +static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct buffer_ref *ref = (struct buffer_ref *)buf->private;

+ if (ref->ref > INT_MAX/2) + return false; + ref->ref++; + return true; }

/* Pipe buffer operations for a buffer. */

From: Punit Agrawal punit.agrawal@arm.com

commit d63206ee32b6e64b0e12d46e5d6004afd9913713 upstream.

When speculatively taking references to a hugepage using page_cache_add_speculative() in gup_huge_pmd(), it is assumed that the page returned by pmd_page() is the head page. Although normally true, this assumption doesn't hold when the hugepage comprises of successive page table entries such as when using contiguous bit on arm64 at PTE or PMD levels.

This can be addressed by ensuring that the page passed to page_cache_add_speculative() is the real head or by de-referencing the head page within the function.

We take the first approach to keep the usage pattern aligned with page_cache_get_speculative() where users already pass the appropriate page, i.e., the de-referenced head.

Apply the same logic to fix gup_huge_[pud|pgd]() as well.

[punit.agrawal@arm.com: fix arm64 ltp failure] Link: http://lkml.kernel.org/r/20170619170145.25577-5-punit.agrawal@arm.com Link: http://lkml.kernel.org/r/20170522133604.11392-3-punit.agrawal@arm.com Signed-off-by: Punit Agrawal punit.agrawal@arm.com Acked-by: Steve Capper steve.capper@arm.com Cc: Michal Hocko mhocko@suse.com Cc: "Kirill A. Shutemov" kirill.shutemov@linux.intel.com Cc: Aneesh Kumar K.V aneesh.kumar@linux.vnet.ibm.com Cc: Catalin Marinas catalin.marinas@arm.com Cc: Will Deacon will.deacon@arm.com Cc: Naoya Horiguchi n-horiguchi@ah.jp.nec.com Cc: Mark Rutland mark.rutland@arm.com Cc: Hillf Danton hillf.zj@alibaba-inc.com Cc: Mike Kravetz mike.kravetz@oracle.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/gup.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)

--- a/mm/gup.c +++ b/mm/gup.c @@ -1313,8 +1313,7 @@ static int gup_huge_pmd(pmd_t orig, pmd_ return 0;

refs = 0; - head = pmd_page(orig); - page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); do { pages[*nr] = page; (*nr)++; @@ -1322,6 +1321,7 @@ static int gup_huge_pmd(pmd_t orig, pmd_ refs++; } while (addr += PAGE_SIZE, addr != end);

+ head = compound_head(pmd_page(orig)); if (!page_cache_add_speculative(head, refs)) { *nr -= refs; return 0; @@ -1347,8 +1347,7 @@ static int gup_huge_pud(pud_t orig, pud_ return 0;

refs = 0; - head = pud_page(orig); - page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT); + page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); do { pages[*nr] = page; (*nr)++; @@ -1356,6 +1355,7 @@ static int gup_huge_pud(pud_t orig, pud_ refs++; } while (addr += PAGE_SIZE, addr != end);

+ head = compound_head(pud_page(orig)); if (!page_cache_add_speculative(head, refs)) { *nr -= refs; return 0; @@ -1382,8 +1382,7 @@ static int gup_huge_pgd(pgd_t orig, pgd_ return 0;

refs = 0; - head = pgd_page(orig); - page = head + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT); + page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT); do { pages[*nr] = page; (*nr)++; @@ -1391,6 +1390,7 @@ static int gup_huge_pgd(pgd_t orig, pgd_ refs++; } while (addr += PAGE_SIZE, addr != end);

+ head = compound_head(pgd_page(orig)); if (!page_cache_add_speculative(head, refs)) { *nr -= refs; return 0;

From: Greg Kroah-Hartman gregkh@linuxfoundation.org

This reverts commit 392bef709659abea614abfe53cf228e7a59876a4.

It seems to cause lots of problems when using the gold linker, and no one really needs this at the moment, so just revert it from the stable trees.

Cc: Sami Tolvanen samitolvanen@google.com Reported-by: Kees Cook keescook@chromium.org Cc: Borislav Petkov bp@suse.de Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Reported-by: Alec Ari neotheuser@gmail.com Cc: Ingo Molnar mingo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/vmlinux.lds.S | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -111,10 +111,10 @@ SECTIONS *(.text.__x86.indirect_thunk) __indirect_thunk_end = .; #endif - } :text = 0x9090

- /* End of text section */ - _etext = .; + /* End of text section */ + _etext = .; + } :text = 0x9090

NOTES :text :note

From: Ard Biesheuvel ard.biesheuvel@linaro.org

commit 60f38de7a8d4e816100ceafd1b382df52527bd50 upstream.

Merge the parsing of the command line carried out in arm-stub.c with the handling in efi_parse_options(). Note that this also fixes the missing handling of CONFIG_CMDLINE_FORCE=y, in which case the builtin command line should supersede the one passed by the firmware.

Signed-off-by: Ard Biesheuvel ard.biesheuvel@linaro.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Matt Fleming matt@codeblueprint.co.uk Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Cc: bhe@redhat.com Cc: bhsharma@redhat.com Cc: bp@alien8.de Cc: eugene@hp.com Cc: evgeny.kalugin@intel.com Cc: jhugo@codeaurora.org Cc: leif.lindholm@linaro.org Cc: linux-efi@vger.kernel.org Cc: mark.rutland@arm.com Cc: roy.franz@cavium.com Cc: rruigrok@codeaurora.org Link: http://lkml.kernel.org/r/20170404160910.28115-1-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar mingo@kernel.org [ardb: fix up merge conflicts with 4.9.180] Signed-off-by: Ard Biesheuvel ard.biesheuvel@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/firmware/efi/libstub/arm-stub.c | 23 +++++++---------------- drivers/firmware/efi/libstub/arm64-stub.c | 4 +--- drivers/firmware/efi/libstub/efi-stub-helper.c | 19 +++++++++++-------- drivers/firmware/efi/libstub/efistub.h | 2 ++ include/linux/efi.h | 2 +- 5 files changed, 22 insertions(+), 28 deletions(-)

--- a/drivers/firmware/efi/libstub/arm-stub.c +++ b/drivers/firmware/efi/libstub/arm-stub.c @@ -18,7 +18,6 @@

#include "efistub.h"

-bool __nokaslr;

static int efi_get_secureboot(efi_system_table_t *sys_table_arg) { @@ -268,18 +267,6 @@ unsigned long efi_entry(void *handle, ef goto fail; }

- /* check whether 'nokaslr' was passed on the command line */ - if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { - static const u8 default_cmdline[] = CONFIG_CMDLINE; - const u8 *str, *cmdline = cmdline_ptr; - - if (IS_ENABLED(CONFIG_CMDLINE_FORCE)) - cmdline = default_cmdline; - str = strstr(cmdline, "nokaslr"); - if (str == cmdline || (str > cmdline && *(str - 1) == ' ')) - __nokaslr = true; - } - si = setup_graphics(sys_table);

status = handle_kernel_image(sys_table, image_addr, &image_size, @@ -291,9 +278,13 @@ unsigned long efi_entry(void *handle, ef goto fail_free_cmdline; }

- status = efi_parse_options(cmdline_ptr); - if (status != EFI_SUCCESS) - pr_efi_err(sys_table, "Failed to parse EFI cmdline options\n"); + if (IS_ENABLED(CONFIG_CMDLINE_EXTEND) || + IS_ENABLED(CONFIG_CMDLINE_FORCE) || + cmdline_size == 0) + efi_parse_options(CONFIG_CMDLINE); + + if (!IS_ENABLED(CONFIG_CMDLINE_FORCE) && cmdline_size > 0) + efi_parse_options(cmdline_ptr);

secure_boot = efi_get_secureboot(sys_table); if (secure_boot > 0) --- a/drivers/firmware/efi/libstub/arm64-stub.c +++ b/drivers/firmware/efi/libstub/arm64-stub.c @@ -24,8 +24,6 @@

#include "efistub.h"

-extern bool __nokaslr; - efi_status_t check_platform_features(efi_system_table_t *sys_table_arg) { u64 tg; @@ -60,7 +58,7 @@ efi_status_t handle_kernel_image(efi_sys u64 phys_seed = 0;

if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { - if (!__nokaslr) { + if (!nokaslr()) { status = efi_get_random_bytes(sys_table_arg, sizeof(phys_seed), (u8 *)&phys_seed); --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -32,6 +32,13 @@

static unsigned long __chunk_size = EFI_READ_CHUNK_SIZE;

+static int __section(.data) __nokaslr; + +int __pure nokaslr(void) +{ + return __nokaslr; +} + /* * Allow the platform to override the allocation granularity: this allows * systems that have the capability to run with a larger page size to deal @@ -351,17 +358,13 @@ void efi_free(efi_system_table_t *sys_ta * environments, first in the early boot environment of the EFI boot * stub, and subsequently during the kernel boot. */ -efi_status_t efi_parse_options(char *cmdline) +efi_status_t efi_parse_options(char const *cmdline) { char *str;

- /* - * Currently, the only efi= option we look for is 'nochunk', which - * is intended to work around known issues on certain x86 UEFI - * versions. So ignore for now on other architectures. - */ - if (!IS_ENABLED(CONFIG_X86)) - return EFI_SUCCESS; + str = strstr(cmdline, "nokaslr"); + if (str == cmdline || (str && str > cmdline && *(str - 1) == ' ')) + __nokaslr = 1;

/* * If no EFI parameters were specified on the cmdline we've got --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -15,6 +15,8 @@ */ #undef __init

+extern int __pure nokaslr(void); + void efi_char16_printk(efi_system_table_t *, efi_char16_t *);

efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, void *__image, --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1427,7 +1427,7 @@ efi_status_t handle_cmdline_files(efi_sy unsigned long *load_addr, unsigned long *load_size);

-efi_status_t efi_parse_options(char *cmdline); +efi_status_t efi_parse_options(char const *cmdline);

efi_status_t efi_setup_gop(efi_system_table_t *sys_table_arg, struct screen_info *si, efi_guid_t *proto,

From: Vivien Didelot vivien.didelot@gmail.com

[ Upstream commit 0ee4e76937d69128a6a66861ba393ebdc2ffc8a2 ]

ethtool_get_regs() allocates a buffer of size ops->get_regs_len(), and pass it to the kernel driver via ops->get_regs() for filling.

There is no restriction about what the kernel drivers can or cannot do with the open ethtool_regs structure. They usually set regs->version and ignore regs->len or set it to the same size as ops->get_regs_len().

But if userspace allocates a smaller buffer for the registers dump, we would cause a userspace buffer overflow in the final copy_to_user() call, which uses the regs.len value potentially reset by the driver.

To fix this, make this case obvious and store regs.len before calling ops->get_regs(), to only copy as much data as requested by userspace, up to the value returned by ops->get_regs_len().

While at it, remove the redundant check for non-null regbuf.

Signed-off-by: Vivien Didelot vivien.didelot@gmail.com Reviewed-by: Michal Kubecek mkubecek@suse.cz Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/ethtool.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1390,13 +1390,16 @@ static int ethtool_get_regs(struct net_d return -ENOMEM; }

+ if (regs.len < reglen) + reglen = regs.len; + ops->get_regs(dev, &regs, regbuf);

ret = -EFAULT; if (copy_to_user(useraddr, &regs, sizeof(regs))) goto out; useraddr += offsetof(struct ethtool_regs, data); - if (regbuf && copy_to_user(useraddr, regbuf, regs.len)) + if (copy_to_user(useraddr, regbuf, reglen)) goto out; ret = 0;

From: Erez Alfasi ereza@mellanox.com

[ Upstream commit 135dd9594f127c8a82d141c3c8430e9e2143216a ]

Querying EEPROM high pages data for SFP module is currently not supported by our driver but is still tried, resulting in invalid FW queries.

Set the EEPROM ethtool data length to 256 for SFP module to limit the reading for page 0 only and prevent invalid FW queries.

Fixes: 7202da8b7f71 ("ethtool, net/mlx4_en: Cable info, get_module_info/eeprom ethtool support") Signed-off-by: Erez Alfasi ereza@mellanox.com Signed-off-by: Tariq Toukan tariqt@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 4 +++- drivers/net/ethernet/mellanox/mlx4/port.c | 5 ----- 2 files changed, 3 insertions(+), 6 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1930,6 +1930,8 @@ static int mlx4_en_set_tunable(struct ne return ret; }

+#define MLX4_EEPROM_PAGE_LEN 256 + static int mlx4_en_get_module_info(struct net_device *dev, struct ethtool_modinfo *modinfo) { @@ -1964,7 +1966,7 @@ static int mlx4_en_get_module_info(struc break; case MLX4_MODULE_ID_SFP: modinfo->type = ETH_MODULE_SFF_8472; - modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; + modinfo->eeprom_len = MLX4_EEPROM_PAGE_LEN; break; default: return -ENOSYS; --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -1960,11 +1960,6 @@ int mlx4_get_module_info(struct mlx4_dev size -= offset + size - I2C_PAGE_SIZE;

i2c_addr = I2C_ADDR_LOW; - if (offset >= I2C_PAGE_SIZE) { - /* Reset offset to high page */ - i2c_addr = I2C_ADDR_HIGH; - offset -= I2C_PAGE_SIZE; - }

cable_info = (struct mlx4_cable_info *)inmad->data; cable_info->dev_mem_address = cpu_to_be16(offset);

From: Paolo Abeni pabeni@redhat.com

[ Upstream commit 720f1de4021f09898b8c8443f3b3e995991b6e3a ]

Currently, the process issuing a "start" command on the pktgen procfs interface, acquires the pktgen thread lock and never release it, until all pktgen threads are completed. The above can blocks indefinitely any other pktgen command and any (even unrelated) netdevice removal - as the pktgen netdev notifier acquires the same lock.

The issue is demonstrated by the following script, reported by Matteo:

ip -b - <<'EOF' link add type dummy link add type veth link set dummy0 up EOF modprobe pktgen echo reset >/proc/net/pktgen/pgctrl { echo rem_device_all echo add_device dummy0 } >/proc/net/pktgen/kpktgend_0 echo count 0 >/proc/net/pktgen/dummy0 echo start >/proc/net/pktgen/pgctrl & sleep 1 rmmod veth

Fix the above releasing the thread lock around the sleep call.

Additionally we must prevent racing with forcefull rmmod - as the thread lock no more protects from them. Instead, acquire a self-reference before waiting for any thread. As a side effect, running

rmmod pktgen

while some thread is running now fails with "module in use" error, before this patch such command hanged indefinitely.

Note: the issue predates the commit reported in the fixes tag, but this fix can't be applied before the mentioned commit.

v1 -> v2: - no need to check for thread existence after flipping the lock, pktgen threads are freed only at net exit time -

Fixes: 6146e6a43b35 ("[PKTGEN]: Removes thread_{un,}lock() macros.") Reported-and-tested-by: Matteo Croce mcroce@redhat.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/pktgen.c | 11 +++++++++++ 1 file changed, 11 insertions(+)

--- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3147,7 +3147,13 @@ static int pktgen_wait_thread_run(struct { while (thread_is_running(t)) {

+ /* note: 't' will still be around even after the unlock/lock + * cycle because pktgen_thread threads are only cleared at + * net exit + */ + mutex_unlock(&pktgen_thread_lock); msleep_interruptible(100); + mutex_lock(&pktgen_thread_lock);

if (signal_pending(current)) goto signal; @@ -3162,6 +3168,10 @@ static int pktgen_wait_all_threads_run(s struct pktgen_thread *t; int sig = 1;

+ /* prevent from racing with rmmod */ + if (!try_module_get(THIS_MODULE)) + return sig; + mutex_lock(&pktgen_thread_lock);

list_for_each_entry(t, &pn->pktgen_threads, th_list) { @@ -3175,6 +3185,7 @@ static int pktgen_wait_all_threads_run(s t->control |= (T_STOP);

mutex_unlock(&pktgen_thread_lock); + module_put(THIS_MODULE); return sig; }

From: Olivier Matz olivier.matz@6wind.com

[ Upstream commit 59e3e4b52663a9d97efbce7307f62e4bc5c9ce91 ]

As it was done in commit 8f659a03a0ba ("net: ipv4: fix for a race condition in raw_sendmsg") and commit 20b50d79974e ("net: ipv4: emulate READ_ONCE() on ->hdrincl bit-field in raw_sendmsg()") for ipv4, copy the value of inet->hdrincl in a local variable, to avoid introducing a race condition in the next commit.

Signed-off-by: Olivier Matz olivier.matz@6wind.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/raw.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-)

--- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -774,6 +774,7 @@ static int rawv6_sendmsg(struct sock *sk struct sockcm_cookie sockc; struct ipcm6_cookie ipc6; int addr_len = msg->msg_namelen; + int hdrincl; u16 proto; int err;

@@ -787,6 +788,13 @@ static int rawv6_sendmsg(struct sock *sk if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP;

+ /* hdrincl should be READ_ONCE(inet->hdrincl) + * but READ_ONCE() doesn't work with bit fields. + * Doing this indirectly yields the same result. + */ + hdrincl = inet->hdrincl; + hdrincl = READ_ONCE(hdrincl); + /* * Get and verify the address. */ @@ -904,7 +912,7 @@ static int rawv6_sendmsg(struct sock *sk fl6.flowi6_oif = np->ucast_oif; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));

- if (inet->hdrincl) + if (hdrincl) fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH;

if (ipc6.tclass < 0) @@ -927,7 +935,7 @@ static int rawv6_sendmsg(struct sock *sk goto do_confirm;

back_from_confirm: - if (inet->hdrincl) + if (hdrincl) err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst, msg->msg_flags); else { ipc6.opt = opt;

From: Hangbin Liu liuhangbin@gmail.com

[ Upstream commit 4970b42d5c362bf873982db7d93245c5281e58f4 ]

This reverts commit e9919a24d3022f72bcadc407e73a6ef17093a849.

Nathan reported the new behaviour breaks Android, as Android just add new rules and delete old ones.

If we return 0 without adding dup rules, Android will remove the new added rules and causing system to soft-reboot.

Fixes: e9919a24d302 ("fib_rules: return 0 directly if an exactly same rule exists when NLM_F_EXCL not supplied") Reported-by: Nathan Chancellor natechancellor@gmail.com Reported-by: Yaro Slav yaro330@gmail.com Reported-by: Maciej Żenczykowski zenczykowski@gmail.com Signed-off-by: Hangbin Liu liuhangbin@gmail.com Reviewed-by: Nathan Chancellor natechancellor@gmail.com Tested-by: Nathan Chancellor natechancellor@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/fib_rules.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -429,9 +429,9 @@ int fib_nl_newrule(struct sk_buff *skb, if (rule->l3mdev && rule->table) goto errout_free;

- if (rule_exists(ops, frh, tb, rule)) { - if (nlh->nlmsg_flags & NLM_F_EXCL) - err = -EEXIST; + if ((nlh->nlmsg_flags & NLM_F_EXCL) && + rule_exists(ops, frh, tb, rule)) { + err = -EEXIST; goto errout_free; }

From: John David Anglin dave.anglin@bell.net

commit 63923d2c3800919774f5c651d503d1dd2adaddd5 upstream.

We only support I/O to kernel space. Using %sr1 to load the coherence index may be racy unless interrupts are disabled. This patch changes the code used to load the coherence index to use implicit space register selection. This saves one instruction and eliminates the race.

Tested on rp3440, c8000 and c3750.

Signed-off-by: John David Anglin dave.anglin@bell.net Cc: stable@vger.kernel.org Signed-off-by: Helge Deller deller@gmx.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/parisc/ccio-dma.c | 4 +--- drivers/parisc/sba_iommu.c | 3 +-- 2 files changed, 2 insertions(+), 5 deletions(-)

--- a/drivers/parisc/ccio-dma.c +++ b/drivers/parisc/ccio-dma.c @@ -563,8 +563,6 @@ ccio_io_pdir_entry(u64 *pdir_ptr, space_ /* We currently only support kernel addresses */ BUG_ON(sid != KERNEL_SPACE);

- mtsp(sid,1); - /* ** WORD 1 - low order word ** "hints" parm includes the VALID bit! @@ -595,7 +593,7 @@ ccio_io_pdir_entry(u64 *pdir_ptr, space_ ** Grab virtual index [0:11] ** Deposit virt_idx bits into I/O PDIR word */ - asm volatile ("lci %%r0(%%sr1, %1), %0" : "=r" (ci) : "r" (vba)); + asm volatile ("lci %%r0(%1), %0" : "=r" (ci) : "r" (vba)); asm volatile ("extru %1,19,12,%0" : "+r" (ci) : "r" (ci)); asm volatile ("depw %1,15,12,%0" : "+r" (pa) : "r" (ci));

--- a/drivers/parisc/sba_iommu.c +++ b/drivers/parisc/sba_iommu.c @@ -573,8 +573,7 @@ sba_io_pdir_entry(u64 *pdir_ptr, space_t pa = virt_to_phys(vba); pa &= IOVP_MASK;

- mtsp(sid,1); - asm("lci 0(%%sr1, %1), %0" : "=r" (ci) : "r" (vba)); + asm("lci 0(%1), %0" : "=r" (ci) : "r" (vba)); pa |= (ci >> PAGE_SHIFT) & 0xff; /* move CI (8 bits) into lowest byte */

pa |= SBA_PDIR_VALID_BIT; /* set "valid" bit */

From: Jiri Kosina jkosina@suse.cz

commit ec527c318036a65a083ef68d8ba95789d2212246 upstream.

As explained in

0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once")

we always, no matter what, have to bring up x86 HT siblings during boot at least once in order to avoid first MCE bringing the system to its knees.

That means that whenever 'nosmt' is supplied on the kernel command-line, all the HT siblings are as a result sitting in mwait or cpudile after going through the online-offline cycle at least once.

This causes a serious issue though when a kernel, which saw 'nosmt' on its commandline, is going to perform resume from hibernation: if the resume from the hibernated image is successful, cr3 is flipped in order to point to the address space of the kernel that is being resumed, which in turn means that all the HT siblings are all of a sudden mwaiting on address which is no longer valid.

That results in triple fault shortly after cr3 is switched, and machine reboots.

Fix this by always waking up all the SMT siblings before initiating the 'restore from hibernation' process; this guarantees that all the HT siblings will be properly carried over to the resumed kernel waiting in resume_play_dead(), and acted upon accordingly afterwards, based on the target kernel configuration.

Symmetricaly, the resumed kernel has to push the SMT siblings to mwait again in case it has SMT disabled; this means it has to online all the siblings when resuming (so that they come out of hlt) and offline them again to let them reach mwait.

Cc: 4.19+ stable@vger.kernel.org # v4.19+ Debugged-by: Thomas Gleixner tglx@linutronix.de Fixes: 0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once") Signed-off-by: Jiri Kosina jkosina@suse.cz Acked-by: Pavel Machek pavel@ucw.cz Reviewed-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Josh Poimboeuf jpoimboe@redhat.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/power/cpu.c | 10 ++++++++++ arch/x86/power/hibernate_64.c | 33 +++++++++++++++++++++++++++++++++ include/linux/cpu.h | 4 ++++ kernel/cpu.c | 4 ++-- kernel/power/hibernate.c | 9 +++++++++ 5 files changed, 58 insertions(+), 2 deletions(-)

--- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -292,7 +292,17 @@ int hibernate_resume_nonboot_cpu_disable * address in its instruction pointer may not be possible to resolve * any more at that point (the page tables used by it previously may * have been overwritten by hibernate image data). + * + * First, make sure that we wake up all the potentially disabled SMT + * threads which have been initially brought up and then put into + * mwait/cpuidle sleep. + * Those will be put to proper (not interfering with hibernation + * resume) sleep afterwards, and the resumed kernel will decide itself + * what to do with them. */ + ret = cpuhp_smt_enable(); + if (ret) + return ret; smp_ops.play_dead = resume_play_dead; ret = disable_nonboot_cpus(); smp_ops.play_dead = play_dead; --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -11,6 +11,7 @@ #include <linux/gfp.h> #include <linux/smp.h> #include <linux/suspend.h> +#include <linux/cpu.h>

#include <asm/init.h> #include <asm/proto.h> @@ -218,3 +219,35 @@ int arch_hibernation_header_restore(void restore_cr3 = rdr->cr3; return (rdr->magic == RESTORE_MAGIC) ? 0 : -EINVAL; } + +int arch_resume_nosmt(void) +{ + int ret = 0; + /* + * We reached this while coming out of hibernation. This means + * that SMT siblings are sleeping in hlt, as mwait is not safe + * against control transition during resume (see comment in + * hibernate_resume_nonboot_cpu_disable()). + * + * If the resumed kernel has SMT disabled, we have to take all the + * SMT siblings out of hlt, and offline them again so that they + * end up in mwait proper. + * + * Called with hotplug disabled. + */ + cpu_hotplug_enable(); + if (cpu_smt_control == CPU_SMT_DISABLED || + cpu_smt_control == CPU_SMT_FORCE_DISABLED) { + enum cpuhp_smt_control old = cpu_smt_control; + + ret = cpuhp_smt_enable(); + if (ret) + goto out; + ret = cpuhp_smt_disable(old); + if (ret) + goto out; + } +out: + cpu_hotplug_disable(); + return ret; +} --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -271,11 +271,15 @@ extern enum cpuhp_smt_control cpu_smt_co extern void cpu_smt_disable(bool force); extern void cpu_smt_check_topology_early(void); extern void cpu_smt_check_topology(void); +extern int cpuhp_smt_enable(void); +extern int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval); #else # define cpu_smt_control (CPU_SMT_ENABLED) static inline void cpu_smt_disable(bool force) { } static inline void cpu_smt_check_topology_early(void) { } static inline void cpu_smt_check_topology(void) { } +static inline int cpuhp_smt_enable(void) { return 0; } +static inline int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { return 0; } #endif

/* --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1995,7 +1995,7 @@ static void cpuhp_online_cpu_device(unsi kobject_uevent(&dev->kobj, KOBJ_ONLINE); }

-static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) +int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { int cpu, ret = 0;

@@ -2029,7 +2029,7 @@ static int cpuhp_smt_disable(enum cpuhp_ return ret; }

-static int cpuhp_smt_enable(void) +int cpuhp_smt_enable(void) { int cpu, ret = 0;

--- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -256,6 +256,11 @@ void swsusp_show_speed(ktime_t start, kt kps / 1000, (kps % 1000) / 10); }

+__weak int arch_resume_nosmt(void) +{ + return 0; +} + /** * create_image - Create a hibernation image. * @platform_mode: Whether or not to use the platform driver. @@ -322,6 +327,10 @@ static int create_image(int platform_mod Enable_cpus: enable_nonboot_cpus();

+ /* Allow architectures to do nosmt-specific post-resume dances */ + if (!in_suspend) + error = arch_resume_nosmt(); + Platform_finish: platform_finish(platform_mode);

From: Greg Kroah-Hartman gregkh@linuxfoundation.org

This reverts commit f9b1baac265600a61d36ebaf9ba657119303b5b5 which is commit a1e8783db8e0d58891681bc1e6d9ada66eae8e20 upstream.

Petr writes: Karl has reported to me today, that he's experiencing weird reboot hang on his devices with 4.9.180 kernel and that he has bisected it down to my backported patch.

I would like to kindly ask you for removal of this patch. This patch should be reverted from all stable kernels up to 5.1, because perf counters were not broken on those kernels, and this patch won't work on the ath79 legacy IRQ code anyway, it needs new irqchip driver which was enabled on ath79 with commit 51fa4f8912c0 ("MIPS: ath79: drop legacy IRQ code").

Reported-by: Petr Štetiar ynezz@true.cz Cc: Kevin 'ldir' Darbyshire-Bryant ldir@darbyshire-bryant.me.uk Cc: John Crispin john@phrozen.org Cc: Marc Zyngier marc.zyngier@arm.com Cc: Paul Burton paul.burton@mips.com Cc: linux-mips@vger.kernel.org Cc: Ralf Baechle ralf@linux-mips.org Cc: James Hogan jhogan@kernel.org Cc: Thomas Gleixner tglx@linutronix.de Cc: Jason Cooper jason@lakedaemon.net Cc: Sasha Levin sashal@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/mips/ath79/setup.c | 6 ++++++ drivers/irqchip/irq-ath79-misc.c | 11 ----------- 2 files changed, 6 insertions(+), 11 deletions(-)

--- a/arch/mips/ath79/setup.c +++ b/arch/mips/ath79/setup.c @@ -183,6 +183,12 @@ const char *get_system_type(void) return ath79_sys_type; }

+int get_c0_perfcount_int(void) +{ + return ATH79_MISC_IRQ(5); +} +EXPORT_SYMBOL_GPL(get_c0_perfcount_int); + unsigned int get_c0_compare_int(void) { return CP0_LEGACY_COMPARE_IRQ; --- a/drivers/irqchip/irq-ath79-misc.c +++ b/drivers/irqchip/irq-ath79-misc.c @@ -22,15 +22,6 @@ #define AR71XX_RESET_REG_MISC_INT_ENABLE 4

#define ATH79_MISC_IRQ_COUNT 32 -#define ATH79_MISC_PERF_IRQ 5 - -static int ath79_perfcount_irq; - -int get_c0_perfcount_int(void) -{ - return ath79_perfcount_irq; -} -EXPORT_SYMBOL_GPL(get_c0_perfcount_int);

static void ath79_misc_irq_handler(struct irq_desc *desc) { @@ -122,8 +113,6 @@ static void __init ath79_misc_intc_domai { void __iomem *base = domain->host_data;

- ath79_perfcount_irq = irq_create_mapping(domain, ATH79_MISC_PERF_IRQ); - /* Disable and clear all interrupts */ __raw_writel(0, base + AR71XX_RESET_REG_MISC_INT_ENABLE); __raw_writel(0, base + AR71XX_RESET_REG_MISC_INT_STATUS);

From: Patrik Jakobsson patrik.r.jakobsson@gmail.com

commit 7c420636860a719049fae9403e2c87804f53bdde upstream.

Some machines have an lvds child device in vbt even though a panel is not attached. To make detection more reliable we now also check the lvds config bits available in the vbt.

Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1665766 Cc: stable@vger.kernel.org Reviewed-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Patrik Jakobsson patrik.r.jakobsson@gmail.com Link: https://patchwork.freedesktop.org/patch/msgid/20190416114607.1072-1-patrik.r... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/gpu/drm/gma500/cdv_intel_lvds.c | 3 +++ drivers/gpu/drm/gma500/intel_bios.c | 3 +++ drivers/gpu/drm/gma500/psb_drv.h | 1 + 3 files changed, 7 insertions(+)

--- a/drivers/gpu/drm/gma500/cdv_intel_lvds.c +++ b/drivers/gpu/drm/gma500/cdv_intel_lvds.c @@ -609,6 +609,9 @@ void cdv_intel_lvds_init(struct drm_devi int pipe; u8 pin;

+ if (!dev_priv->lvds_enabled_in_vbt) + return; + pin = GMBUS_PORT_PANEL; if (!lvds_is_present_in_vbt(dev, &pin)) { DRM_DEBUG_KMS("LVDS is not present in VBT\n"); --- a/drivers/gpu/drm/gma500/intel_bios.c +++ b/drivers/gpu/drm/gma500/intel_bios.c @@ -436,6 +436,9 @@ parse_driver_features(struct drm_psb_pri if (driver->lvds_config == BDB_DRIVER_FEATURE_EDP) dev_priv->edp.support = 1;

+ dev_priv->lvds_enabled_in_vbt = driver->lvds_config != 0; + DRM_DEBUG_KMS("LVDS VBT config bits: 0x%x\n", driver->lvds_config); + /* This bit means to use 96Mhz for DPLL_A or not */ if (driver->primary_lfp_id) dev_priv->dplla_96mhz = true; --- a/drivers/gpu/drm/gma500/psb_drv.h +++ b/drivers/gpu/drm/gma500/psb_drv.h @@ -538,6 +538,7 @@ struct drm_psb_private { int lvds_ssc_freq; bool is_lvds_on; bool is_mipi_on; + bool lvds_enabled_in_vbt; u32 mipi_ctrl_display;

unsigned int core_freq;

From: Chris Wilson chris@chris-wilson.co.uk

commit d90c06d57027203f73021bb7ddb30b800d65c636 upstream.

This was supposed to be a mask of all known rings, but it is being used by execbuffer to filter out invalid rings, and so is instead mapping high unused values onto valid rings. Instead of a mask of all known rings, we need it to be the mask of all possible rings.

Fixes: 549f7365820a ("drm/i915: Enable SandyBridge blitter ring") Fixes: de1add360522 ("drm/i915: Decouple execbuf uAPI from internal implementation") Signed-off-by: Chris Wilson chris@chris-wilson.co.uk Cc: Tvrtko Ursulin tvrtko.ursulin@intel.com Cc: stable@vger.kernel.org # v4.6+ Reviewed-by: Tvrtko Ursulin tvrtko.ursulin@intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20190301140404.26690-21-chris@... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- include/uapi/drm/i915_drm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -756,7 +756,7 @@ struct drm_i915_gem_execbuffer2 { __u32 num_cliprects; /** This is a struct drm_clip_rect *cliprects */ __u64 cliprects_ptr; -#define I915_EXEC_RING_MASK (7<<0) +#define I915_EXEC_RING_MASK (0x3f) #define I915_EXEC_DEFAULT (0<<0) #define I915_EXEC_RENDER (1<<0) #define I915_EXEC_BSD (2<<0)

From: Kirill Smelkov kirr@nexedi.com

commit 10dce8af34226d90fa56746a934f8da5dcdba3df upstream.

Commit 9c225f2655e3 ("vfs: atomic f_pos accesses as per POSIX") added locking for file.f_pos access and in particular made concurrent read and write not possible - now both those functions take f_pos lock for the whole run, and so if e.g. a read is blocked waiting for data, write will deadlock waiting for that read to complete.

This caused regression for stream-like files where previously read and write could run simultaneously, but after that patch could not do so anymore. See e.g. commit 581d21a2d02a ("xenbus: fix deadlock on writes to /proc/xen/xenbus") which fixes such regression for particular case of /proc/xen/xenbus.

The patch that added f_pos lock in 2014 did so to guarantee POSIX thread safety for read/write/lseek and added the locking to file descriptors of all regular files. In 2014 that thread-safety problem was not new as it was already discussed earlier in 2006.

However even though 2006'th version of Linus's patch was adding f_pos locking "only for files that are marked seekable with FMODE_LSEEK (thus avoiding the stream-like objects like pipes and sockets)", the 2014 version - the one that actually made it into the tree as 9c225f2655e3 - is doing so irregardless of whether a file is seekable or not.

See

https://lore.kernel.org/lkml/53022DB1.4070805@gmail.com/ https://lwn.net/Articles/180387 https://lwn.net/Articles/180396

for historic context.

The reason that it did so is, probably, that there are many files that are marked non-seekable, but e.g. their read implementation actually depends on knowing current position to correctly handle the read. Some examples:

kernel/power/user.c snapshot_read fs/debugfs/file.c u32_array_read fs/fuse/control.c fuse_conn_waiting_read + ... drivers/hwmon/asus_atk0110.c atk_debugfs_ggrp_read arch/s390/hypfs/inode.c hypfs_read_iter ...

Despite that, many nonseekable_open users implement read and write with pure stream semantics - they don't depend on passed ppos at all. And for those cases where read could wait for something inside, it creates a situation similar to xenbus - the write could be never made to go until read is done, and read is waiting for some, potentially external, event, for potentially unbounded time -> deadlock.

Besides xenbus, there are 14 such places in the kernel that I've found with semantic patch (see below):

drivers/xen/evtchn.c:667:8-24: ERROR: evtchn_fops: .read() can deadlock .write() drivers/isdn/capi/capi.c:963:8-24: ERROR: capi_fops: .read() can deadlock .write() drivers/input/evdev.c:527:1-17: ERROR: evdev_fops: .read() can deadlock .write() drivers/char/pcmcia/cm4000_cs.c:1685:7-23: ERROR: cm4000_fops: .read() can deadlock .write() net/rfkill/core.c:1146:8-24: ERROR: rfkill_fops: .read() can deadlock .write() drivers/s390/char/fs3270.c:488:1-17: ERROR: fs3270_fops: .read() can deadlock .write() drivers/usb/misc/ldusb.c:310:1-17: ERROR: ld_usb_fops: .read() can deadlock .write() drivers/hid/uhid.c:635:1-17: ERROR: uhid_fops: .read() can deadlock .write() net/batman-adv/icmp_socket.c:80:1-17: ERROR: batadv_fops: .read() can deadlock .write() drivers/media/rc/lirc_dev.c:198:1-17: ERROR: lirc_fops: .read() can deadlock .write() drivers/leds/uleds.c:77:1-17: ERROR: uleds_fops: .read() can deadlock .write() drivers/input/misc/uinput.c:400:1-17: ERROR: uinput_fops: .read() can deadlock .write() drivers/infiniband/core/user_mad.c:985:7-23: ERROR: umad_fops: .read() can deadlock .write() drivers/gnss/core.c:45:1-17: ERROR: gnss_fops: .read() can deadlock .write()

In addition to the cases above another regression caused by f_pos locking is that now FUSE filesystems that implement open with FOPEN_NONSEEKABLE flag, can no longer implement bidirectional stream-like files - for the same reason as above e.g. read can deadlock write locking on file.f_pos in the kernel.

FUSE's FOPEN_NONSEEKABLE was added in 2008 in a7c1b990f715 ("fuse: implement nonseekable open") to support OSSPD. OSSPD implements /dev/dsp in userspace with FOPEN_NONSEEKABLE flag, with corresponding read and write routines not depending on current position at all, and with both read and write being potentially blocking operations:

See

https://github.com/libfuse/osspd https://lwn.net/Articles/308445

https://github.com/libfuse/osspd/blob/14a9cff0/osspd.c#L1406 https://github.com/libfuse/osspd/blob/14a9cff0/osspd.c#L1438-L1477 https://github.com/libfuse/osspd/blob/14a9cff0/osspd.c#L1479-L1510

Corresponding libfuse example/test also describes FOPEN_NONSEEKABLE as "somewhat pipe-like files ..." with read handler not using offset. However that test implements only read without write and cannot exercise the deadlock scenario:

https://github.com/libfuse/libfuse/blob/fuse-3.4.2-3-ga1bff7d/example/poll.c... https://github.com/libfuse/libfuse/blob/fuse-3.4.2-3-ga1bff7d/example/poll.c... https://github.com/libfuse/libfuse/blob/fuse-3.4.2-3-ga1bff7d/example/poll.c...

I've actually hit the read vs write deadlock for real while implementing my FUSE filesystem where there is /head/watch file, for which open creates separate bidirectional socket-like stream in between filesystem and its user with both read and write being later performed simultaneously. And there it is semantically not easy to split the stream into two separate read-only and write-only channels:

https://lab.nexedi.com/kirr/wendelin.core/blob/f13aa600/wcfs/wcfs.go#L88-169

Let's fix this regression. The plan is:

1. We can't change nonseekable_open to include &~FMODE_ATOMIC_POS - doing so would break many in-kernel nonseekable_open users which actually use ppos in read/write handlers.

2. Add stream_open() to kernel to open stream-like non-seekable file descriptors. Read and write on such file descriptors would never use nor change ppos. And with that property on stream-like files read and write will be running without taking f_pos lock - i.e. read and write could be running simultaneously.

3. With semantic patch search and convert to stream_open all in-kernel nonseekable_open users for which read and write actually do not depend on ppos and where there is no other methods in file_operations which assume @offset access.

4. Add FOPEN_STREAM to fs/fuse/ and open in-kernel file-descriptors via steam_open if that bit is present in filesystem open reply.

It was tempting to change fs/fuse/ open handler to use stream_open instead of nonseekable_open on just FOPEN_NONSEEKABLE flags, but grepping through Debian codesearch shows users of FOPEN_NONSEEKABLE, and in particular GVFS which actually uses offset in its read and write handlers

https://codesearch.debian.net/search?q=-%3Enonseekable+%3D https://gitlab.gnome.org/GNOME/gvfs/blob/1.40.0-6-gcbc54396/client/gvfsfused... https://gitlab.gnome.org/GNOME/gvfs/blob/1.40.0-6-gcbc54396/client/gvfsfused... https://gitlab.gnome.org/GNOME/gvfs/blob/1.40.0-6-gcbc54396/client/gvfsfused...

so if we would do such a change it will break a real user.

5. Add stream_open and FOPEN_STREAM handling to stable kernels starting from v3.14+ (the kernel where 9c225f2655 first appeared).

This will allow to patch OSSPD and other FUSE filesystems that provide stream-like files to return FOPEN_STREAM | FOPEN_NONSEEKABLE in their open handler and this way avoid the deadlock on all kernel versions. This should work because fs/fuse/ ignores unknown open flags returned from a filesystem and so passing FOPEN_STREAM to a kernel that is not aware of this flag cannot hurt. In turn the kernel that is not aware of FOPEN_STREAM will be < v3.14 where just FOPEN_NONSEEKABLE is sufficient to implement streams without read vs write deadlock.

This patch adds stream_open, converts /proc/xen/xenbus to it and adds semantic patch to automatically locate in-kernel places that are either required to be converted due to read vs write deadlock, or that are just safe to be converted because read and write do not use ppos and there are no other funky methods in file_operations.

Regarding semantic patch I've verified each generated change manually - that it is correct to convert - and each other nonseekable_open instance left - that it is either not correct to convert there, or that it is not converted due to current stream_open.cocci limitations.

The script also does not convert files that should be valid to convert, but that currently have .llseek = noop_llseek or generic_file_llseek for unknown reason despite file being opened with nonseekable_open (e.g. drivers/input/mousedev.c)

Cc: Michael Kerrisk mtk.manpages@gmail.com Cc: Yongzhi Pan panyongzhi@gmail.com Cc: Jonathan Corbet corbet@lwn.net Cc: David Vrabel david.vrabel@citrix.com Cc: Juergen Gross jgross@suse.com Cc: Miklos Szeredi miklos@szeredi.hu Cc: Tejun Heo tj@kernel.org Cc: Kirill Tkhai ktkhai@virtuozzo.com Cc: Arnd Bergmann arnd@arndb.de Cc: Christoph Hellwig hch@lst.de Cc: Greg Kroah-Hartman gregkh@linuxfoundation.org Cc: Julia Lawall Julia.Lawall@lip6.fr Cc: Nikolaus Rath Nikolaus@rath.org Cc: Han-Wen Nienhuys hanwen@google.com Signed-off-by: Kirill Smelkov kirr@nexedi.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/xen/xenbus/xenbus_dev_frontend.c | 2 fs/open.c | 18 + fs/read_write.c | 5 include/linux/fs.h | 4 scripts/coccinelle/api/stream_open.cocci | 363 +++++++++++++++++++++++++++++++ 5 files changed, 389 insertions(+), 3 deletions(-)

--- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -536,7 +536,7 @@ static int xenbus_file_open(struct inode if (xen_store_evtchn == 0) return -ENOENT;

- nonseekable_open(inode, filp); + stream_open(inode, filp);

u = kzalloc(sizeof(*u), GFP_KERNEL); if (u == NULL) --- a/fs/open.c +++ b/fs/open.c @@ -1192,3 +1192,21 @@ int nonseekable_open(struct inode *inode }

EXPORT_SYMBOL(nonseekable_open); + +/* + * stream_open is used by subsystems that want stream-like file descriptors. + * Such file descriptors are not seekable and don't have notion of position + * (file.f_pos is always 0). Contrary to file descriptors of other regular + * files, .read() and .write() can run simultaneously. + * + * stream_open never fails and is marked to return int so that it could be + * directly used as file_operations.open . + */ +int stream_open(struct inode *inode, struct file *filp) +{ + filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS); + filp->f_mode |= FMODE_STREAM; + return 0; +} + +EXPORT_SYMBOL(stream_open); --- a/fs/read_write.c +++ b/fs/read_write.c @@ -575,12 +575,13 @@ EXPORT_SYMBOL(vfs_write);

static inline loff_t file_pos_read(struct file *file) { - return file->f_pos; + return file->f_mode & FMODE_STREAM ? 0 : file->f_pos; }

static inline void file_pos_write(struct file *file, loff_t pos) { - file->f_pos = pos; + if ((file->f_mode & FMODE_STREAM) == 0) + file->f_pos = pos; }

SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -143,6 +143,9 @@ typedef int (dio_iodone_t)(struct kiocb /* Has write method(s) */ #define FMODE_CAN_WRITE ((__force fmode_t)0x40000)

+/* File is stream-like */ +#define FMODE_STREAM ((__force fmode_t)0x200000) + /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000)

@@ -2843,6 +2846,7 @@ extern loff_t no_seek_end_llseek_size(st extern loff_t no_seek_end_llseek(struct file *, loff_t, int); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); +extern int stream_open(struct inode * inode, struct file * filp);

#ifdef CONFIG_BLOCK typedef void (dio_submit_t)(struct bio *bio, struct inode *inode, --- /dev/null +++ b/scripts/coccinelle/api/stream_open.cocci @@ -0,0 +1,363 @@ +// SPDX-License-Identifier: GPL-2.0 +// Author: Kirill Smelkov (kirr@nexedi.com) +// +// Search for stream-like files that are using nonseekable_open and convert +// them to stream_open. A stream-like file is a file that does not use ppos in +// its read and write. Rationale for the conversion is to avoid deadlock in +// between read and write. + +virtual report +virtual patch +virtual explain // explain decisions in the patch (SPFLAGS="-D explain") + +// stream-like reader & writer - ones that do not depend on f_pos. +@ stream_reader @ +identifier readstream, ppos; +identifier f, buf, len; +type loff_t; +@@ + ssize_t readstream(struct file *f, char *buf, size_t len, loff_t *ppos) + { + ... when != ppos + } + +@ stream_writer @ +identifier writestream, ppos; +identifier f, buf, len; +type loff_t; +@@ + ssize_t writestream(struct file *f, const char *buf, size_t len, loff_t *ppos) + { + ... when != ppos + } + + +// a function that blocks +@ blocks @ +identifier block_f; +identifier wait_event =~ "^wait_event_.*"; +@@ + block_f(...) { + ... when exists + wait_event(...) + ... when exists + } + +// stream_reader that can block inside. +// +// XXX wait_* can be called not directly from current function (e.g. func -> f -> g -> wait()) +// XXX currently reader_blocks supports only direct and 1-level indirect cases. +@ reader_blocks_direct @ +identifier stream_reader.readstream; +identifier wait_event =~ "^wait_event_.*"; +@@ + readstream(...) + { + ... when exists + wait_event(...) + ... when exists + } + +@ reader_blocks_1 @ +identifier stream_reader.readstream; +identifier blocks.block_f; +@@ + readstream(...) + { + ... when exists + block_f(...) + ... when exists + } + +@ reader_blocks depends on reader_blocks_direct || reader_blocks_1 @ +identifier stream_reader.readstream; +@@ + readstream(...) { + ... + } + + +// file_operations + whether they have _any_ .read, .write, .llseek ... at all. +// +// XXX add support for file_operations xxx[N] = ... (sound/core/pcm_native.c) +@ fops0 @ +identifier fops; +@@ + struct file_operations fops = { + ... + }; + +@ has_read @ +identifier fops0.fops; +identifier read_f; +@@ + struct file_operations fops = { + .read = read_f, + }; + +@ has_read_iter @ +identifier fops0.fops; +identifier read_iter_f; +@@ + struct file_operations fops = { + .read_iter = read_iter_f, + }; + +@ has_write @ +identifier fops0.fops; +identifier write_f; +@@ + struct file_operations fops = { + .write = write_f, + }; + +@ has_write_iter @ +identifier fops0.fops; +identifier write_iter_f; +@@ + struct file_operations fops = { + .write_iter = write_iter_f, + }; + +@ has_llseek @ +identifier fops0.fops; +identifier llseek_f; +@@ + struct file_operations fops = { + .llseek = llseek_f, + }; + +@ has_no_llseek @ +identifier fops0.fops; +@@ + struct file_operations fops = { + .llseek = no_llseek, + }; + +@ has_mmap @ +identifier fops0.fops; +identifier mmap_f; +@@ + struct file_operations fops = { + .mmap = mmap_f, + }; + +@ has_copy_file_range @ +identifier fops0.fops; +identifier copy_file_range_f; +@@ + struct file_operations fops = { + .copy_file_range = copy_file_range_f, + }; + +@ has_remap_file_range @ +identifier fops0.fops; +identifier remap_file_range_f; +@@ + struct file_operations fops = { + .remap_file_range = remap_file_range_f, + }; + +@ has_splice_read @ +identifier fops0.fops; +identifier splice_read_f; +@@ + struct file_operations fops = { + .splice_read = splice_read_f, + }; + +@ has_splice_write @ +identifier fops0.fops; +identifier splice_write_f; +@@ + struct file_operations fops = { + .splice_write = splice_write_f, + }; + + +// file_operations that is candidate for stream_open conversion - it does not +// use mmap and other methods that assume @offset access to file. +// +// XXX for simplicity require no .{read/write}_iter and no .splice_{read/write} for now. +// XXX maybe_steam.fops cannot be used in other rules - it gives "bad rule maybe_stream or bad variable fops". +@ maybe_stream depends on (!has_llseek || has_no_llseek) && !has_mmap && !has_copy_file_range && !has_remap_file_range && !has_read_iter && !has_write_iter && !has_splice_read && !has_splice_write @ +identifier fops0.fops; +@@ + struct file_operations fops = { + }; + + +// ---- conversions ---- + +// XXX .open = nonseekable_open -> .open = stream_open +// XXX .open = func -> openfunc -> nonseekable_open + +// read & write +// +// if both are used in the same file_operations together with an opener - +// under that conditions we can use stream_open instead of nonseekable_open. +@ fops_rw depends on maybe_stream @ +identifier fops0.fops, openfunc; +identifier stream_reader.readstream; +identifier stream_writer.writestream; +@@ + struct file_operations fops = { + .open = openfunc, + .read = readstream, + .write = writestream, + }; + +@ report_rw depends on report @ +identifier fops_rw.openfunc; +position p1; +@@ + openfunc(...) { + <... + nonseekable_open@p1 + ...> + } + +@ script:python depends on report && reader_blocks @ +fops << fops0.fops; +p << report_rw.p1; +@@ +coccilib.report.print_report(p[0], + "ERROR: %s: .read() can deadlock .write(); change nonseekable_open -> stream_open to fix." % (fops,)) + +@ script:python depends on report && !reader_blocks @ +fops << fops0.fops; +p << report_rw.p1; +@@ +coccilib.report.print_report(p[0], + "WARNING: %s: .read() and .write() have stream semantic; safe to change nonseekable_open -> stream_open." % (fops,)) + + +@ explain_rw_deadlocked depends on explain && reader_blocks @ +identifier fops_rw.openfunc; +@@ + openfunc(...) { + <... +- nonseekable_open ++ nonseekable_open /* read & write (was deadlock) */ + ...> + } + + +@ explain_rw_nodeadlock depends on explain && !reader_blocks @ +identifier fops_rw.openfunc; +@@ + openfunc(...) { + <... +- nonseekable_open ++ nonseekable_open /* read & write (no direct deadlock) */ + ...> + } + +@ patch_rw depends on patch @ +identifier fops_rw.openfunc; +@@ + openfunc(...) { + <... +- nonseekable_open ++ stream_open + ...> + } + + +// read, but not write +@ fops_r depends on maybe_stream && !has_write @ +identifier fops0.fops, openfunc; +identifier stream_reader.readstream; +@@ + struct file_operations fops = { + .open = openfunc, + .read = readstream, + }; + +@ report_r depends on report @ +identifier fops_r.openfunc; +position p1; +@@ + openfunc(...) { + <... + nonseekable_open@p1 + ...> + } + +@ script:python depends on report @ +fops << fops0.fops; +p << report_r.p1; +@@ +coccilib.report.print_report(p[0], + "WARNING: %s: .read() has stream semantic; safe to change nonseekable_open -> stream_open." % (fops,)) + +@ explain_r depends on explain @ +identifier fops_r.openfunc; +@@ + openfunc(...) { + <... +- nonseekable_open ++ nonseekable_open /* read only */ + ...> + } + +@ patch_r depends on patch @ +identifier fops_r.openfunc; +@@ + openfunc(...) { + <... +- nonseekable_open ++ stream_open + ...> + } + + +// write, but not read +@ fops_w depends on maybe_stream && !has_read @ +identifier fops0.fops, openfunc; +identifier stream_writer.writestream; +@@ + struct file_operations fops = { + .open = openfunc, + .write = writestream, + }; + +@ report_w depends on report @ +identifier fops_w.openfunc; +position p1; +@@ + openfunc(...) { + <... + nonseekable_open@p1 + ...> + } + +@ script:python depends on report @ +fops << fops0.fops; +p << report_w.p1; +@@ +coccilib.report.print_report(p[0], + "WARNING: %s: .write() has stream semantic; safe to change nonseekable_open -> stream_open." % (fops,)) + +@ explain_w depends on explain @ +identifier fops_w.openfunc; +@@ + openfunc(...) { + <... +- nonseekable_open ++ nonseekable_open /* write only */ + ...> + } + +@ patch_w depends on patch @ +identifier fops_w.openfunc; +@@ + openfunc(...) { + <... +- nonseekable_open ++ stream_open + ...> + } + + +// no read, no write - don't change anything