ARM: dts: imx51: Fix memory node duplication
Subsystems (36)
Sasha Levin
maintainerPATCH 173/219 PCI/MSI: Return -ENOSPC from pci_alloc_irq_vectors_affinity()
In reply to Sasha LevinFrom: Ming Lei <[email protected]>
[ Upstream commit 77f88abd4a6f73a1a68dbdc0e3f21575fd508fc3 ]
The API of pci_alloc_irq_vectors_affinity() says it returns -ENOSPC if fewer than @min_vecs interrupt vectors are available for @dev.
However, if a device supports MSI-X but not MSI and a caller requests @min_vecs that can't be satisfied by MSI-X, we previously returned -EINVAL (from the failed attempt to enable MSI), not -ENOSPC.
When -ENOSPC is returned, callers may reduce the number IRQs they request and try again. Most callers can use the @min_vecs and @max_vecs parameters to avoid this retry loop, but that doesn't work when using IRQ affinity "nr_sets" because rebalancing the sets is driver-specific.
This return value bug has been present since pci_alloc_irq_vectors() was added in v4.10 by aff171641d18 ("PCI: Provide sensible IRQ vector alloc/free routines"), but it wasn't an issue because @min_vecs/@max_vecs removed the need for callers to iteratively reduce the number of IRQs requested and retry the allocation, so they didn't need to distinguish -ENOSPC from -EINVAL.
In v5.0, 6da4b3ab9a6e ("genirq/affinity: Add support for allocating interrupt sets") added IRQ sets to the interface, which reintroduced the need to check for -ENOSPC and possibly reduce the number of IRQs requested and retry the allocation.
--- drivers/pci/msi.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-)
drivers/pci/msi.c +13 -9
@@ -1155,7 +1155,8 @@ int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, const struct irq_affinity *affd) {static const struct irq_affinity msi_default_affd; -int vecs = -ENOSPC ; +int msix_vecs = -ENOSPC ; +int msi_vecs = -ENOSPC ;if (flags &PCI_IRQ_AFFINITY ) {if (!affd)
@@ -1166,16 +1167,17 @@ int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, }if (flags &PCI_IRQ_MSIX ) { - vecs =__pci_enable_msix_range (dev,NULL , min_vecs, max_vecs, - affd); -if (vecs >0 ) -return vecs; + msix_vecs =__pci_enable_msix_range (dev,NULL , min_vecs, + max_vecs, affd); +if (msix_vecs >0 ) +return msix_vecs; }if (flags &PCI_IRQ_MSI ) { - vecs =__pci_enable_msi_range (dev, min_vecs, max_vecs, affd); -if (vecs >0 ) -return vecs; + msi_vecs =__pci_enable_msi_range (dev, min_vecs, max_vecs, + affd); +if (msi_vecs >0 ) +return msi_vecs; }/* use legacy irq if allowed */
@@ -1186,7 +1188,9 @@ int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, } } -return vecs; +if (msix_vecs == -ENOSPC ) +return -ENOSPC ; +return msi_vecs; }EXPORT_SYMBOL (pci_alloc_irq_vectors_affinity);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 174/219 net/core/neighbour: fix kmemleak minimal reference count for hash tables
In reply to Sasha LevinFrom: Konstantin Khlebnikov <[email protected]>
[ Upstream commit 01b833ab44c9e484060aad72267fc7e71beb559b ]
This should be 1 for normal allocations, 0 disables leak reporting.
--- net/core/neighbour.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/core/neighbour.c +1 -1
@@ -370,7 +370,7 @@ static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift) buckets = (struct neighbour __rcu **)__get_free_pages (GFP_ATOMIC | __GFP_ZERO,get_order (size)); -kmemleak_alloc (buckets, size,0 ,GFP_ATOMIC ); +kmemleak_alloc (buckets, size,1 ,GFP_ATOMIC ); }if (!buckets) {kfree (ret);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 175/219 serial: 8250: Fix serial8250 initialization crash
In reply to Sasha LevinFrom: He Zhe <[email protected]>
[ Upstream commit 352c4cf40c4a7d439fa5d30aa2160f54b394da82 ]
The initialization code of interrupt backoff work might reference NULL pointer and cause the following crash, if no port was found.
[ 10.017727] CPU 0 Unable to handle kernel paging request at virtual address 000001b0, epc == 807088e0, ra == 8070863c ---- snip ---- [ 11.704470] [<807088e0>] serial8250_register_8250_port+0x318/0x4ac [ 11.747251] [<80708d74>] serial8250_probe+0x148/0x1c0 [ 11.789301] [<80728450>] platform_drv_probe+0x40/0x94 [ 11.830515] [<807264f8>] really_probe+0xf8/0x318 [ 11.870876] [<80726b7c>] __driver_attach+0x110/0x12c [ 11.910960] [<80724374>] bus_for_each_dev+0x78/0xcc [ 11.951134] [<80725958>] bus_add_driver+0x200/0x234 [ 11.989756] [<807273d8>] driver_register+0x84/0x148 [ 12.029832] [<80d72f84>] serial8250_init+0x138/0x198 [ 12.070447] [<80100e6c>] do_one_initcall+0x5c/0x2a0 [ 12.110104] [<80d3a208>] kernel_init_freeable+0x370/0x484 [ 12.150722] [<80a49420>] kernel_init+0x10/0xf8 [ 12.191517] [<8010756c>] ret_from_kernel_thread+0x14/0x1c
This patch makes sure the initialization code can be reached only if a port is found.
--- drivers/tty/serial/8250/8250_core.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-)
drivers/tty/serial/8250/8250_core.c +9 -8
@@ -1074,15 +1074,16 @@ int serial8250_register_8250_port(struct uart_8250_port *up) ret =0 ; } - } -/* Initialise interrupt backoff work if required */ -if (up->overrun_backoff_time_ms >0 ) { - uart->overrun_backoff_time_ms = up->overrun_backoff_time_ms; -INIT_DELAYED_WORK (&uart->overrun_backoff, - serial_8250_overrun_backoff_work); - }else { - uart->overrun_backoff_time_ms =0 ; +/* Initialise interrupt backoff work if required */ +if (up->overrun_backoff_time_ms >0 ) { + uart->overrun_backoff_time_ms = + up->overrun_backoff_time_ms; +INIT_DELAYED_WORK (&uart->overrun_backoff, + serial_8250_overrun_backoff_work); + }else { + uart->overrun_backoff_time_ms =0 ; + } }mutex_unlock (&serial_mutex);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 176/219 gpu: ipu-v3: pre: don't trigger update if buffer address doesn't change
In reply to Sasha LevinFrom: Lucas Stach <[email protected]>
[ Upstream commit eb0200a4357da100064971689d3a0e9e3cf57f33 ]
On a NOP double buffer update where current buffer address is the same as the next buffer address, the SDW_UPDATE bit clears too late. As we are now using this bit to determine when it is safe to signal flip completion to userspace this will delay completion of atomic commits where one plane doesn't change the buffer by a whole frame period.
Fix this by remembering the last buffer address and just skip the double buffer update if it would not change the buffer address.
--- drivers/gpu/ipu-v3/ipu-pre.c | 6 ++++++ 1 file changed, 6 insertions(+)
drivers/gpu/ipu-v3/ipu-pre.c +6 -0
@@ -106,6 +106,7 @@ struct ipu_pre {void *buffer_virt;bool in_use;unsigned int safe_window_end; +unsigned int last_bufaddr; };static DEFINE_MUTEX (ipu_pre_list_mutex);
@@ -185,6 +186,7 @@ void ipu_pre_configure(struct ipu_pre *pre, unsigned int width,writel (bufaddr, pre->regs +IPU_PRE_CUR_BUF );writel (bufaddr, pre->regs +IPU_PRE_NEXT_BUF ); + pre->last_bufaddr = bufaddr; val =IPU_PRE_PREF_ENG_CTRL_INPUT_PIXEL_FORMAT (0 ) | IPU_PRE_PREF_ENG_CTRL_INPUT_ACTIVE_BPP(active_bpp) |
@@ -242,7 +244,11 @@ void ipu_pre_update(struct ipu_pre *pre, unsigned int bufaddr)unsigned short current_yblock;u32 val; +if (bufaddr == pre->last_bufaddr) +return ; +writel (bufaddr, pre->regs +IPU_PRE_NEXT_BUF ); + pre->last_bufaddr = bufaddr; do { if (time_after(jiffies, timeout)) {
Signature · 6 lines
2.20.1 _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel
Sasha Levin
maintainerPATCH 177/219 sfc: suppress duplicate nvmem partition types in efx_ef10_mtd_probe
In reply to Sasha LevinFrom: Edward Cree <[email protected]>
[ Upstream commit 3366463513f544c12c6b88c13da4462ee9e7a1a1 ]
Use a bitmap to keep track of which partition types we've already seen;
for duplicates, return -EEXIST from efx_ef10_mtd_probe_partition() and thus skip adding that partition.
Duplicate partitions occur because of the A/B backup scheme used by newer
sfc NICs. Prior to this patch they cause sysfs_warn_dup errors because they have the same name, causing us not to expose any MTDs at all.
--- drivers/net/ethernet/sfc/ef10.c | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-)
drivers/net/ethernet/sfc/ef10.c +21 -8
@@ -6042,22 +6042,25 @@ static const struct efx_ef10_nvram_type_info efx_ef10_nvram_types[] = { { NVRAM_PARTITION_TYPE_LICENSE, 0, 0, "sfc_license" }, { NVRAM_PARTITION_TYPE_PHY_MIN, 0xff, 0, "sfc_phy_fw" }, }; +#define EF10_NVRAM_PARTITION_COUNT ARRAY_SIZE(efx_ef10_nvram_types)static int efx_ef10_mtd_probe_partition (struct efx_nic *efx,struct efx_mcdi_mtd_partition *part, -unsigned int type) +unsigned int type, +unsigned long *found) {MCDI_DECLARE_BUF (inbuf,MC_CMD_NVRAM_METADATA_IN_LEN );MCDI_DECLARE_BUF (outbuf,MC_CMD_NVRAM_METADATA_OUT_LENMAX );const struct efx_ef10_nvram_type_info *info;size_t size, erase_size, outlen; +int type_idx =0 ;bool protected;int rc; -for (info = efx_ef10_nvram_types; ; info++) { -if (info == - efx_ef10_nvram_types +ARRAY_SIZE (efx_ef10_nvram_types)) +for (type_idx =0 ; ; type_idx++) { +if (type_idx ==EF10_NVRAM_PARTITION_COUNT )return -ENODEV ; + info = efx_ef10_nvram_types + type_idx;if ((type & ~info->type_mask) == info->type)break ; }
@@ -6070,6 +6073,13 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,if (protected)return -ENODEV ;/* hide it */ +/* If we've already exposed a partition of this type, hide this +* duplicate. All operations on MTDs are keyed by the type anyway, +* so we can't act on the duplicate. +*/ +if (__test_and_set_bit (type_idx, found)) +return -EEXIST ; + part->nvram_type = type;MCDI_SET_DWORD (inbuf,NVRAM_METADATA_IN_TYPE , type);
@@ -6098,6 +6108,7 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,static int efx_ef10_mtd_probe (struct efx_nic *efx) {MCDI_DECLARE_BUF (outbuf,MC_CMD_NVRAM_PARTITIONS_OUT_LENMAX ); +DECLARE_BITMAP (found,EF10_NVRAM_PARTITION_COUNT );struct efx_mcdi_mtd_partition *parts;size_t outlen, n_parts_total, i, n_parts;unsigned int type;
@@ -6126,11 +6137,13 @@ static int efx_ef10_mtd_probe(struct efx_nic *efx)for (i =0 ; i < n_parts_total; i++) { type =MCDI_ARRAY_DWORD (outbuf,NVRAM_PARTITIONS_OUT_TYPE_ID , i); - rc =efx_ef10_mtd_probe_partition (efx, &parts[n_parts], type); -if (rc ==0 ) - n_parts++; -else if (rc != -ENODEV ) + rc =efx_ef10_mtd_probe_partition (efx, &parts[n_parts], type, + found); +if (rc == -EEXIST || rc == -ENODEV ) +continue ; +if (rc) goto fail; + n_parts++; } rc =efx_mtd_add (efx, &parts[0 ].common, n_parts,sizeof (*parts));
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 178/219 ip_tunnel: Make none-tunnel-dst tunnel port work with lwtunnel
In reply to Sasha LevinFrom: wenxu <[email protected]>
[ Upstream commit d71b57532d70c03f4671dd04e84157ac6bf021b0 ]
ip l add dev tun type gretap key 1000
ip a a dev tun 10.0.0.1/24
Packets with tun-id 1000 can be recived by tun dev. But packet can't be sent through dev tun for non-tunnel-dst
With this patch: tunnel-dst can be get through lwtunnel like beflow:
ip r a 10.0.0.7 encap ip dst 172.168.0.11 dev tun
--- net/ipv4/ip_tunnel.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)
net/ipv4/ip_tunnel.c +7 -1
@@ -644,13 +644,19 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, dst = tnl_params->daddr;if (dst ==0 ) {/* NBMA tunnel */ +struct ip_tunnel_info *tun_info;if (!skb_dst (skb)) { dev->stats.tx_fifo_errors++; goto tx_error; } -if (skb->protocol ==htons (ETH_P_IP )) { + tun_info =skb_tunnel_info (skb); +if (tun_info && (tun_info->mode &IP_TUNNEL_INFO_TX ) && +ip_tunnel_info_af (tun_info) ==AF_INET && + tun_info->key.u.ipv4.dst) + dst = tun_info->key.u.ipv4.dst; +else if (skb->protocol ==htons (ETH_P_IP )) { rt =skb_rtable (skb); dst =rt_nexthop (rt, inner_iph->daddr); }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 179/219 decnet: fix DN_IFREQ_SIZE
In reply to Sasha LevinFrom: Johannes Berg <[email protected]>
[ Upstream commit 50c2936634bcb1db78a8ca63249236810c11a80f ]
Digging through the ioctls with Al because of the previous patches, we found that on 64-bit decnet's dn_dev_ioctl() is wrong, because struct ifreq::ifr_ifru is actually 24 bytes (not 16 as expected from struct sockaddr) due to the ifru_map and ifru_settings members.
Clearly, decnet expects the ioctl to be called with a struct like
struct ifreq_dn {
char ifr_name[IFNAMSIZ];
struct sockaddr_dn ifr_addr;};
since it does
struct ifreq *ifr = ...;
struct sockaddr_dn *sdn = (struct sockaddr_dn *)&ifr->ifr_addr;
This means that DN_IFREQ_SIZE is too big for what it wants on 64-bit, as it is
sizeof(struct ifreq) - sizeof(struct sockaddr) + sizeof(struct sockaddr_dn)
This assumes that sizeof(struct sockaddr) is the size of ifr_ifru but that isn't true.
Fix this to use offsetof(struct ifreq, ifr_ifru).
This indeed doesn't really matter much - the result is that we copy in/out 8 bytes more than we should on 64-bit platforms. In case the "struct ifreq_dn" lands just on the end of a page though it might lead to faults.
As far as I can tell, it has been like this forever, so it seems very likely that nobody cares.
--- net/decnet/dn_dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/decnet/dn_dev.c +1 -1
@@ -56,7 +56,7 @@#include <net/dn_neigh.h> #include <net/dn_fib.h> -#define DN_IFREQ_SIZE (sizeof(struct ifreq) - sizeof(struct sockaddr) + sizeof(struct sockaddr_dn)) +#define DN_IFREQ_SIZE (offsetof(struct ifreq, ifr_ifru) + sizeof(struct sockaddr_dn))static char dn_rt_all_end_mcast[ETH_ALEN ] = {0xAB ,0x00 ,0x00 ,0x04 ,0x00 ,0x00 };static char dn_rt_all_rt_mcast[ETH_ALEN ] = {0xAB ,0x00 ,0x00 ,0x03 ,0x00 ,0x00 };
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 180/219 net/smc: prevent races between smc_lgr_terminate() and smc_conn_free()
In reply to Sasha LevinFrom: Karsten Graul <[email protected]>
[ Upstream commit 77f838ace755d2f466536c44dac6c856f62cd901 ]
To prevent races between smc_lgr_terminate() and smc_conn_free() add an extra check of the lgr field before accessing it, and cancel a delayed free_work when a new smc connection is created.
This fixes the problem that free_work cleared the lgr variable but smc_lgr_terminate() or smc_conn_free() still access it in parallel.
--- net/smc/smc_core.c | 4 ++++ 1 file changed, 4 insertions(+)
net/smc/smc_core.c +4 -0
@@ -128,6 +128,8 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn) {struct smc_link_group *lgr = conn->lgr; +if (!lgr) +return ;write_lock_bh (&lgr->conns_lock);if (conn->alert_token_local) {__smc_lgr_unregister_conn (conn);
@@ -612,6 +614,8 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact, local_contact =SMC_REUSE_CONTACT ; conn->lgr = lgr;smc_lgr_register_conn (conn);/* add smc conn to lgr */ +if (delayed_work_pending (&lgr->free_work)) +cancel_delayed_work (&lgr->free_work);write_unlock_bh (&lgr->conns_lock);break ; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 181/219 net/smc: don't wait for send buffer space when data was already sent
In reply to Sasha LevinFrom: Karsten Graul <[email protected]>
[ Upstream commit 6889b36da78a21a312d8b462c1fa25a03c2ff192 ]
When there is no more send buffer space and at least 1 byte was already sent then return to user space. The wait is only done when no data was sent by the sendmsg() call.
This fixes smc_tx_sendmsg() which tried to always send all user data and started to wait for free send buffer space when needed. During this wait the user space program was blocked in the sendmsg() call and hence not able to receive incoming data. When both sides were in such a situation then the connection stalled forever.
--- net/smc/smc_tx.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)
net/smc/smc_tx.c +3 -4
@@ -163,12 +163,11 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) conn->local_tx_ctrl.prod_flags.urg_data_pending =1 ;if (!atomic_read (&conn->sndbuf_space) || conn->urg_tx_pend) { +if (send_done) +return send_done; rc =smc_tx_wait (smc, msg->msg_flags); -if (rc) { -if (send_done) -return send_done; +if (rc) goto out_err; - }continue ; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 182/219 mm/hotplug: invalid PFNs from pfn_to_online_page()
In reply to Sasha LevinFrom: Qian Cai <[email protected]>
[ Upstream commit b13bc35193d9e7a8c050a24928ca5c9e7c9a009b ]
On an arm64 ThunderX2 server, the first kmemleak scan would crash [1] with CONFIG_DEBUG_VM_PGFLAGS=y due to page_to_nid() found a pfn that is not directly mapped (MEMBLOCK_NOMAP). Hence, the page->flags is uninitialized.
This is due to the commit 9f1eb38e0e11 ("mm, kmemleak: little optimization while scanning") starts to use pfn_to_online_page() instead of pfn_valid(). However, in the CONFIG_MEMORY_HOTPLUG=y case, pfn_to_online_page() does not call memblock_is_map_memory() while pfn_valid() does.
Historically, the commit 68709f45385a ("arm64: only consider memblocks with NOMAP cleared for linear mapping") causes pages marked as nomap being no long reassigned to the new zone in memmap_init_zone() by calling __init_single_page().
Since the commit 2d070eab2e82 ("mm: consider zone which is not fully populated to have holes") introduced pfn_to_online_page() and was designed to return a valid pfn only, but it is clearly broken on arm64.
Therefore, let pfn_to_online_page() call pfn_valid_within(), so it can handle nomap thanks to the commit f52bb98f5ade ("arm64: mm: always enable CONFIG_HOLES_IN_ZONE"), while it will be optimized away on architectures where have no HOLES_IN_ZONE.
[1]
Unable to handle kernel NULL pointer dereference at virtual address 0000000000000006
Mem abort info:
ESR = 0x96000005
Exception class = DABT (current EL), IL = 32 bits
SET = 0, FnV = 0
EA = 0, S1PTW = 0
Data abort info:
ISV = 0, ISS = 0x00000005
CM = 0, WnR = 0
Internal error: Oops: 96000005 [#1] SMP
CPU: 60 PID: 1408 Comm: kmemleak Not tainted 5.0.0-rc2+ #8
pstate: 60400009 (nZCv daif +PAN -UAO)
pc : page_mapping+0x24/0x144
lr : __dump_page+0x34/0x3dc
sp : ffff00003a5cfd10
x29: ffff00003a5cfd10 x28: 000000000000802f
x27: 0000000000000000 x26: 0000000000277d00
x25: ffff000010791f56 x24: ffff7fe000000000
x23: ffff000010772f8b x22: ffff00001125f670
x21: ffff000011311000 x20: ffff000010772f8b
x19: fffffffffffffffe x18: 0000000000000000
x17: 0000000000000000 x16: 0000000000000000
x15: 0000000000000000 x14: ffff802698b19600
x13: ffff802698b1a200 x12: ffff802698b16f00
x11: ffff802698b1a400 x10: 0000000000001400
x9 : 0000000000000001 x8 : ffff00001121a000
x7 : 0000000000000000 x6 : ffff0000102c53b8
x5 : 0000000000000000 x4 : 0000000000000003
x3 : 0000000000000100 x2 : 0000000000000000
x1 : ffff000010772f8b x0 : ffffffffffffffff
Process kmemleak (pid: 1408, stack limit = 0x(____ptrval____))
Call trace:
page_mapping+0x24/0x144
__dump_page+0x34/0x3dc
dump_page+0x28/0x4c
kmemleak_scan+0x4ac/0x680
kmemleak_scan_thread+0xb4/0xdc
kthread+0x12c/0x13c
ret_from_fork+0x10/0x18
Code: d503201f f9400660 36000040 d1000413 (f9400661)
---[ end trace 4d4bd7f573490c8e ]---
Kernel panic - not syncing: Fatal exception
SMP: stopping secondary CPUs
Kernel Offset: disabled
CPU features: 0x002,20000c38
Memory Limit: none
---[ end Kernel panic - not syncing: Fatal exception ]------ include/linux/memory_hotplug.h | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-)
include/linux/memory_hotplug.h +10 -8
@@ -21,14 +21,16 @@ struct vmem_altmap;* walkers which rely on the fully initialized page->flags and others * should use this rather than pfn_valid && pfn_to_page */ -#define pfn_to_online_page (pfn) \ -({ \ - struct page *___page = NULL; \ - unsigned long ___nr = pfn_to_section_nr(pfn); \ - \ - if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr))\ - ___page = pfn_to_page(pfn); \ - ___page; \ +#define pfn_to_online_page (pfn) \ +({ \ + struct page *___page = NULL; \ + unsigned long ___pfn = pfn; \ + unsigned long ___nr = pfn_to_section_nr(___pfn); \ + \ + if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr) && \ + pfn_valid_within(___pfn)) \ + ___page = pfn_to_page(___pfn); \ + ___page; \ })/*
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 183/219 xfs: end sync buffer I/O properly on shutdown error
In reply to Sasha LevinFrom: Brian Foster <[email protected]>
[ Upstream commit 465fa17f4a303d9fdff9eac4d45f91ece92e96ca ]
As of commit e339dd8d8b ("xfs: use sync buffer I/O for sync delwri queue submission"), the delwri submission code uses sync buffer I/O for sync delwri I/O. Instead of waiting on async I/O to unlock the buffer, it uses the underlying sync I/O completion mechanism.
If delwri buffer submission fails due to a shutdown scenario, an error is set on the buffer and buffer completion never occurs. This can cause xfs_buf_delwri_submit() to deadlock waiting on a completion event.
We could check the error state before waiting on such buffers, but that doesn't serialize against the case of an error set via a racing I/O completion. Instead, invoke I/O completion in the shutdown case regardless of buffer I/O type.
--- fs/xfs/xfs_buf.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
fs/xfs/xfs_buf.c +1 -2
@@ -1470,8 +1470,7 @@ __xfs_buf_submit(xfs_buf_ioerror (bp, -EIO ); bp->b_flags &= ~XBF_DONE ;xfs_buf_stale (bp); -if (bp->b_flags &XBF_ASYNC ) -xfs_buf_ioend (bp); +xfs_buf_ioend (bp);return -EIO ; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 184/219 net/smc: fix sender_free computation
In reply to Sasha LevinFrom: Ursula Braun <[email protected]>
[ Upstream commit b8649efad879c69c7ab1f19ce8814fcabef1f72b ]
In some scenarios a separate consumer cursor update is necessary. The decision is made in smc_tx_consumer_cursor_update(). The sender_free computation could be wrong:
The rx confirmed cursor is always smaller than or equal to the rx producer cursor. The parameters in the smc_curs_diff() call have to be exchanged, otherwise sender_free might even be negative.
And if more data arrives local_rx_ctrl.prod might be updated, enabling a cursor difference between local_rx_ctrl.prod and rx confirmed cursor larger than the RMB size. This case is not covered by smc_curs_diff(). Thus function smc_curs_diff_large() is introduced here.
If a recvmsg() is processed in parallel, local_tx_ctrl.cons might change during smc_cdc_msg_send. Make sure rx_curs_confirmed is updated with the actually sent local_tx_ctrl.cons value.
--- net/smc/smc_cdc.c | 5 +++-- net/smc/smc_cdc.h | 26 +++++++++++++++++++++++++- net/smc/smc_tx.c | 3 ++- 3 files changed, 30 insertions(+), 4 deletions(-)
net/smc/smc_cdc.c +3 -2
@@ -96,6 +96,7 @@ int smc_cdc_msg_send(struct smc_connection *conn,struct smc_wr_buf *wr_buf, struct smc_cdc_tx_pend *pend) { + union smc_host_cursor cfed;struct smc_link *link;int rc;
@@ -107,10 +108,10 @@ int smc_cdc_msg_send(struct smc_connection *conn, conn->local_tx_ctrl.seqno = conn->tx_cdc_seq;smc_host_msg_to_cdc ((struct smc_cdc_msg *)wr_buf, &conn->local_tx_ctrl, conn); +smc_curs_copy (&cfed, &((struct smc_host_cdc_msg *)wr_buf)->cons, conn); rc =smc_wr_tx_send (link, (struct smc_wr_tx_pend_priv *)pend);if (!rc) -smc_curs_copy (&conn->rx_curs_confirmed, - &conn->local_tx_ctrl.cons, conn); +smc_curs_copy (&conn->rx_curs_confirmed, &cfed, conn);return rc; }
net/smc/smc_cdc.h +25 -1
@@ -135,7 +135,9 @@ static inline void smc_curs_copy_net(union smc_cdc_cursor *tgt,#endif } -/* calculate cursor difference between old and new, where old <= new */ +/* calculate cursor difference between old and new, where old <= new and +* difference cannot exceed size +*/ static inline int smc_curs_diff (unsigned int size,union smc_host_cursor *old,union smc_host_cursor *new)
@@ -160,6 +162,28 @@ static inline int smc_curs_comp(unsigned int size,return smc_curs_diff (size, old, new); } +/* calculate cursor difference between old and new, where old <= new and +* difference may exceed size +*/ +static inline int smc_curs_diff_large (unsigned int size, +union smc_host_cursor *old, +union smc_host_cursor *new) +{ +if (old->wrap < new->wrap) +return min_t (int, + (size - old->count) + new->count + + (new->wrap - old->wrap -1 ) * size, + size); + +if (old->wrap > new->wrap)/* wrap has switched from 0xffff to 0x0000 */ +return min_t (int, + (size - old->count) + new->count + + (new->wrap +0xffff - old->wrap) * size, + size); + +return max_t (int,0 , (new->count - old->count)); +} +static inline void smc_host_cursor_to_cdc (union smc_cdc_cursor *peer,union smc_host_cursor *local,struct smc_connection *conn)
net/smc/smc_tx.c +2 -1
@@ -595,7 +595,8 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force)if (to_confirm > conn->rmbe_update_limit) {smc_curs_copy (&prod, &conn->local_rx_ctrl.prod, conn); sender_free = conn->rmb_desc->len - -smc_curs_diff (conn->rmb_desc->len, &prod, &cfed); +smc_curs_diff_large (conn->rmb_desc->len, + &cfed, &prod); } if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req ||
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 185/219 blktrace: Show requests without sector
In reply to Sasha LevinFrom: Jan Kara <[email protected]>
[ Upstream commit 0803de78049fe1b0baf44bcddc727b036fb9139b ]
Currently, blktrace will not show requests that don't have any data as rq->__sector is initialized to -1 which is out of device range and thus discarded by act_log_check(). This is most notably the case for cache flush requests sent to the device. Fix the problem by making blk_rq_trace_sector() return 0 for requests without initialized sector.
--- include/linux/blktrace_api.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)
include/linux/blktrace_api.h +7 -1
@@ -116,7 +116,13 @@ extern void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes);static inline sector_t blk_rq_trace_sector (struct request *rq) { -return blk_rq_is_passthrough (rq) ?0 :blk_rq_pos (rq); +/* +* Tracing should ignore starting sector for passthrough requests and +* requests where starting sector didn't get set. +*/ +if (blk_rq_is_passthrough (rq) ||blk_rq_pos (rq) == (sector_t)-1 ) +return 0 ; +return blk_rq_pos (rq); }static inline unsigned int blk_rq_trace_nr_sectors (struct request *rq)
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 186/219 net/smc: fix byte_order for rx_curs_confirmed
In reply to Sasha LevinFrom: Ursula Braun <[email protected]>
[ Upstream commit ccc8ca9b90acb45a3309f922b2591b07b4e070ec ]
The recent change in the rx_curs_confirmed assignment disregards byte order, which causes problems on little endian architectures. This patch fixes it.
--- net/smc/smc_cdc.c | 4 +--- net/smc/smc_cdc.h | 19 ++++++++++--------- 2 files changed, 11 insertions(+), 12 deletions(-)
net/smc/smc_cdc.c +1 -3
@@ -106,9 +106,7 @@ int smc_cdc_msg_send(struct smc_connection *conn, conn->tx_cdc_seq++; conn->local_tx_ctrl.seqno = conn->tx_cdc_seq; -smc_host_msg_to_cdc ((struct smc_cdc_msg *)wr_buf, - &conn->local_tx_ctrl, conn); -smc_curs_copy (&cfed, &((struct smc_host_cdc_msg *)wr_buf)->cons, conn); +smc_host_msg_to_cdc ((struct smc_cdc_msg *)wr_buf, conn, &cfed); rc =smc_wr_tx_send (link, (struct smc_wr_tx_pend_priv *)pend);if (!rc)smc_curs_copy (&conn->rx_curs_confirmed, &cfed, conn);
net/smc/smc_cdc.h +10 -9
@@ -186,26 +186,27 @@ static inline int smc_curs_diff_large(unsigned int size,static inline void smc_host_cursor_to_cdc (union smc_cdc_cursor *peer,union smc_host_cursor *local, +union smc_host_cursor *save,struct smc_connection *conn) { -union smc_host_cursor temp; - -smc_curs_copy (&temp, local, conn); - peer->count =htonl (temp.count); - peer->wrap =htons (temp.wrap); +smc_curs_copy (save, local, conn); + peer->count =htonl (save->count); + peer->wrap =htons (save->wrap);/* peer->reserved = htons(0); must be ensured by caller */ }static inline void smc_host_msg_to_cdc (struct smc_cdc_msg *peer, -struct smc_host_cdc_msg *local, -struct smc_connection *conn) +struct smc_connection *conn, +union smc_host_cursor *save) { +struct smc_host_cdc_msg *local = &conn->local_tx_ctrl; + peer->common.type = local->common.type; peer->len = local->len; peer->seqno =htons (local->seqno); peer->token =htonl (local->token); -smc_host_cursor_to_cdc (&peer->prod, &local->prod, conn); -smc_host_cursor_to_cdc (&peer->cons, &local->cons, conn); +smc_host_cursor_to_cdc (&peer->prod, &local->prod, save, conn); +smc_host_cursor_to_cdc (&peer->cons, &local->cons, save, conn); peer->prod_flags = local->prod_flags; peer->conn_state_flags = local->conn_state_flags; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 187/219 tipc: fix skb may be leaky in tipc_link_input
In reply to Sasha LevinFrom: Hoang Le <[email protected]>
[ Upstream commit 7384b538d3aed2ed49d3575483d17aeee790fb06 ]
When we free skb at tipc_data_input, we return a 'false' boolean. Then, skb passed to subcalling tipc_link_input in tipc_link_rcv,
<snip>
1303 int tipc_link_rcv:
...
1354 if (!tipc_data_input(l, skb, l->inputq))
1355 rc |= tipc_link_input(l, skb, l->inputq);
</snip>
Fix it by simple changing to a 'true' boolean when skb is being free-ed. Then, tipc_link_rcv will bypassed to subcalling tipc_link_input as above condition.
--- net/tipc/link.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/tipc/link.c +1 -1
@@ -1114,7 +1114,7 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb,default :pr_warn ("Dropping received illegal msg type\n" );kfree_skb (skb); -return false; +return true; }; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 188/219 ASoC: samsung: i2s: Fix prescaler setting for the secondary DAI
In reply to Sasha LevinFrom: Sylwester Nawrocki <[email protected]>
[ Upstream commit 323fb7b947b265753de34703dbbf8acc8ea3a4de ]
Make sure i2s->rclk_srcrate is properly initialized also during playback through the secondary DAI.
--- sound/soc/samsung/i2s.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)
sound/soc/samsung/i2s.c +7 -1
@@ -604,6 +604,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) {struct i2s_dai *i2s =to_info (dai); +struct i2s_dai *other =get_other_dai (i2s);int lrp_shift, sdf_shift, sdf_mask, lrp_rlow, mod_slave;u32 mod, tmp =0 ;unsigned long flags;
@@ -661,7 +662,8 @@ static int i2s_set_fmt(struct snd_soc_dai *dai,* CLK_I2S_RCLK_SRC clock is not exposed so we ensure any * clock configuration assigned in DT is not overwritten. */ -if (i2s->rclk_srcrate ==0 && i2s->clk_data.clks ==NULL ) +if (i2s->rclk_srcrate ==0 && i2s->clk_data.clks ==NULL && + other->clk_data.clks ==NULL )i2s_set_sysclk (dai,SAMSUNG_I2S_RCLKSRC_0 ,0 ,SND_SOC_CLOCK_IN );break ;
@@ -699,6 +701,7 @@ static int i2s_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, struct snd_soc_dai *dai) { struct i2s_dai *i2s = to_info(dai); +struct i2s_dai *other =get_other_dai (i2s);u32 mod, mask =0 , val =0 ;struct clk *rclksrc;unsigned long flags;
@@ -784,6 +787,9 @@ static int i2s_hw_params(struct snd_pcm_substream *substream, i2s->frmclk =params_rate (params); rclksrc = i2s->clk_table[CLK_I2S_RCLK_SRC ]; +if (!rclksrc ||IS_ERR (rclksrc)) + rclksrc = other->clk_table[CLK_I2S_RCLK_SRC ]; +if (rclksrc && !IS_ERR (rclksrc)) i2s->rclk_srcrate =clk_get_rate (rclksrc);
Signature · 6 lines
2.20.1 _______________________________________________ Alsa-devel mailing list [email protected] https://mailman.alsa-project.org/mailman/listinfo/alsa-devel
Sasha Levin
maintainerPATCH 189/219 sfc: initialise found bitmap in efx_ef10_mtd_probe
In reply to Sasha LevinFrom: Bert Kenward <[email protected]>
[ Upstream commit c65285428b6e7797f1bb063f33b0ae7e93397b7b ]
The bitmap of found partitions in efx_ef10_mtd_probe was not initialised, causing partitions to be suppressed based off whatever value was in the bitmap at the start.
--- drivers/net/ethernet/sfc/ef10.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/sfc/ef10.c +1 -1
@@ -6108,7 +6108,7 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,static int efx_ef10_mtd_probe (struct efx_nic *efx) {MCDI_DECLARE_BUF (outbuf,MC_CMD_NVRAM_PARTITIONS_OUT_LENMAX ); -DECLARE_BITMAP (found,EF10_NVRAM_PARTITION_COUNT ); + DECLARE_BITMAP(found, EF10_NVRAM_PARTITION_COUNT) = { 0 };struct efx_mcdi_mtd_partition *parts;size_t outlen, n_parts_total, i, n_parts;unsigned int type;
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 190/219 geneve: change NET_UDP_TUNNEL dependency to select
In reply to Sasha LevinFrom: Matteo Croce <[email protected]>
[ Upstream commit a7603ac1fc8ce1409f8ff70e6ce505f308b2c002 ]
Due to the depends on NET_UDP_TUNNEL, at the moment it is impossible to compile GENEVE if no other protocol depending on NET_UDP_TUNNEL is selected.
Fix this changing the depends to a select, and drop NET_IP_TUNNEL from the select list, as it already depends on NET_UDP_TUNNEL.
--- drivers/net/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/Kconfig +2 -2
@@ -197,9 +197,9 @@ config VXLAN config GENEVE tristate "Generic Network Virtualization Encapsulation" - depends on INET && NET_UDP_TUNNEL + depends on INET depends on IPV6 || !IPV6 - select NET_IP_TUNNEL + select NET_UDP_TUNNEL select GRO_CELLS ---help--- This allows one to create geneve virtual interfaces that provide
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 191/219 net: fix possible overflow in __sk_mem_raise_allocated()
In reply to Sasha LevinFrom: Eric Dumazet <[email protected]>
[ Upstream commit 5bf325a53202b8728cf7013b72688c46071e212e ]
With many active TCP sockets, fat TCP sockets could fool __sk_mem_raise_allocated() thanks to an overflow.
They would increase their share of the memory, instead of decreasing it.
--- include/net/sock.h | 2 +- net/core/sock.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)
include/net/sock.h +1 -1
@@ -1272,7 +1272,7 @@ static inline void sk_sockets_allocated_inc(struct sock *sk)percpu_counter_inc (sk->sk_prot->sockets_allocated); } -static inline int +static inline u64 sk_sockets_allocated_read_positive (struct sock *sk) {return percpu_counter_read_positive (sk->sk_prot->sockets_allocated);
net/core/sock.c +1 -1
@@ -2435,7 +2435,7 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) }if (sk_has_memory_pressure (sk)) { -int alloc; +u64 alloc;if (!sk_under_memory_pressure (sk))return 1 ;
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 192/219 net: ip_gre: do not report erspan_ver for gre or gretap
In reply to Sasha LevinFrom: Lorenzo Bianconi <[email protected]>
[ Upstream commit 2bdf700e538828d6456150b9319e5f689b062d54 ]
Report erspan version field to userspace in ipgre_fill_info just for erspan tunnels. The issue can be triggered with the following reproducer:
$ip link add name gre1 type gre local 192.168.0.1 remote 192.168.1.1
$ip link set dev gre1 up
$ip -d link sh gre1
13: gre1@NONE: <POINTOPOINT,NOARP,UP,LOWER_UP> mtu 1476 qdisc noqueue state UNKNOWN mode DEFAULT group default qlen 1000
link/gre 192.168.0.1 peer 192.168.1.1 promiscuity 0 minmtu 0 maxmtu 0
gre remote 192.168.1.1 local 192.168.0.1 ttl inherit erspan_ver 0 addrgenmode eui64 numtxqueues 1 numrxqueues 1--- net/ipv4/ip_gre.c | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-)
net/ipv4/ip_gre.c +17 -16
@@ -1469,9 +1469,23 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)struct ip_tunnel_parm *p = &t->parms;__be16 o_flags = p->o_flags; -if ((t->erspan_ver ==1 || t->erspan_ver ==2 ) && - !t->collect_md) - o_flags |=TUNNEL_KEY ; +if (t->erspan_ver ==1 || t->erspan_ver ==2 ) { +if (!t->collect_md) + o_flags |=TUNNEL_KEY ; + +if (nla_put_u8 (skb,IFLA_GRE_ERSPAN_VER , t->erspan_ver)) + goto nla_put_failure; + +if (t->erspan_ver ==1 ) { +if (nla_put_u32 (skb,IFLA_GRE_ERSPAN_INDEX , t->index)) + goto nla_put_failure; + }else { +if (nla_put_u8 (skb,IFLA_GRE_ERSPAN_DIR , t->dir)) + goto nla_put_failure; +if (nla_put_u16 (skb,IFLA_GRE_ERSPAN_HWID , t->hwid)) + goto nla_put_failure; + } + }if (nla_put_u32 (skb,IFLA_GRE_LINK , p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS,
@@ -1507,19 +1521,6 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) goto nla_put_failure; } -if (nla_put_u8 (skb,IFLA_GRE_ERSPAN_VER , t->erspan_ver)) - goto nla_put_failure; - -if (t->erspan_ver ==1 ) { -if (nla_put_u32 (skb,IFLA_GRE_ERSPAN_INDEX , t->index)) - goto nla_put_failure; - }else if (t->erspan_ver ==2 ) { -if (nla_put_u8 (skb,IFLA_GRE_ERSPAN_DIR , t->dir)) - goto nla_put_failure; -if (nla_put_u16 (skb,IFLA_GRE_ERSPAN_HWID , t->hwid)) - goto nla_put_failure; - } -return 0 ; nla_put_failure:
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 193/219 net: ip6_gre: do not report erspan_ver for ip6gre or ip6gretap
In reply to Sasha LevinFrom: Lorenzo Bianconi <[email protected]>
[ Upstream commit 103d0244d29fcaf38f1339d4538919bbbc051490 ]
Report erspan version field to userspace in ip6gre_fill_info just for erspan_v6 tunnels. Moreover report IFLA_GRE_ERSPAN_INDEX only for erspan version 1.
The issue can be triggered with the following reproducer:
$ip link add name gre6 type ip6gre local 2001::1 remote 2002::2
$ip link set gre6 up
$ip -d link sh gre6
14: grep6@NONE: <POINTOPOINT,NOARP,UP,LOWER_UP> mtu 1448 qdisc noqueue state UNKNOWN mode DEFAULT group default qlen 1000
link/gre6 2001::1 peer 2002::2 promiscuity 0 minmtu 0 maxmtu 0
ip6gre remote 2002::2 local 2001::1 hoplimit 64 encaplimit 4 tclass 0x00 flowlabel 0x00000 erspan_index 0 erspan_ver 0 addrgenmode eui64--- net/ipv6/ip6_gre.c | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-)
net/ipv6/ip6_gre.c +18 -18
@@ -2135,9 +2135,23 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)struct __ip6_tnl_parm *p = &t->parms;__be16 o_flags = p->o_flags; -if ((p->erspan_ver ==1 || p->erspan_ver ==2 ) && - !p->collect_md) - o_flags |=TUNNEL_KEY ; +if (p->erspan_ver ==1 || p->erspan_ver ==2 ) { +if (!p->collect_md) + o_flags |=TUNNEL_KEY ; + +if (nla_put_u8 (skb,IFLA_GRE_ERSPAN_VER , p->erspan_ver)) + goto nla_put_failure; + +if (p->erspan_ver ==1 ) { +if (nla_put_u32 (skb,IFLA_GRE_ERSPAN_INDEX , p->index)) + goto nla_put_failure; + }else { +if (nla_put_u8 (skb,IFLA_GRE_ERSPAN_DIR , p->dir)) + goto nla_put_failure; +if (nla_put_u16 (skb,IFLA_GRE_ERSPAN_HWID , p->hwid)) + goto nla_put_failure; + } + }if (nla_put_u32 (skb,IFLA_GRE_LINK , p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS,
@@ -2152,8 +2166,7 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)nla_put_u8 (skb,IFLA_GRE_ENCAP_LIMIT , p->encap_limit) ||nla_put_be32 (skb,IFLA_GRE_FLOWINFO , p->flowinfo) ||nla_put_u32 (skb,IFLA_GRE_FLAGS , p->flags) || -nla_put_u32 (skb,IFLA_GRE_FWMARK , p->fwmark) || - nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index)) + nla_put_u32(skb, IFLA_GRE_FWMARK, p->fwmark)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE,
@@ -2171,19 +2184,6 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) goto nla_put_failure; } -if (nla_put_u8 (skb,IFLA_GRE_ERSPAN_VER , p->erspan_ver)) - goto nla_put_failure; - -if (p->erspan_ver ==1 ) { -if (nla_put_u32 (skb,IFLA_GRE_ERSPAN_INDEX , p->index)) - goto nla_put_failure; - }else if (p->erspan_ver ==2 ) { -if (nla_put_u8 (skb,IFLA_GRE_ERSPAN_DIR , p->dir)) - goto nla_put_failure; -if (nla_put_u16 (skb,IFLA_GRE_ERSPAN_HWID , p->hwid)) - goto nla_put_failure; - } -return 0 ; nla_put_failure:
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 194/219 sctp: don't compare hb_timer expire date before starting it
In reply to Sasha LevinFrom: Maciej Kwiecien <[email protected]>
[ Upstream commit d1f20c03f48102e52eb98b8651d129b83134cae4 ]
hb_timer might not start at all for a particular transport because its start is conditional. In a result a node is not sending heartbeats.
Function sctp_transport_reset_hb_timer has two roles:
- initial start of hb_timer for a given transport,
- update expire date of hb_timer for a given transport.
The function is optimized to update timer's expire only if it is before a new calculated one but this comparison is invalid for a timer which has not yet started. Such a timer has expire = 0 and if a new expire value is bigger than (MAX_JIFFIES / 2 + 2) then "time_before" macro will fail and timer will not start resulting in no heartbeat packets send by the node.
This was found when association was initialized within first 5 mins after system boot due to jiffies init value which is near to MAX_JIFFIES.
Test kernel version: 4.9.154 (ARCH=arm)
hb_timer.expire = 0; //initialized, not started timernew_expire = MAX_JIFFIES / 2 + 2; //or moretime_before(hb_timer.expire, new_expire) = false
--- net/sctp/transport.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
net/sctp/transport.c +2 -1
@@ -207,7 +207,8 @@ void sctp_transport_reset_hb_timer(struct sctp_transport *transport)/* When a data chunk is sent, reset the heartbeat interval. */ expires = jiffies +sctp_transport_timeout (transport); -if (time_before (transport->hb_timer.expires, expires) && +if ((time_before (transport->hb_timer.expires, expires) || + !timer_pending (&transport->hb_timer)) && !mod_timer (&transport->hb_timer, expires +prandom_u32_max (transport->rto)))sctp_transport_hold (transport);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 195/219 bpf: decrease usercnt if bpf_map_new_fd() fails in bpf_map_get_fd_by_id()
In reply to Sasha LevinFrom: Peng Sun <[email protected]>
[ Upstream commit 781e62823cb81b972dc8652c1827205cda2ac9ac ]
In bpf/syscall.c, bpf_map_get_fd_by_id() use bpf_map_inc_not_zero() to increase the refcount, both map->refcnt and map->usercnt. Then, if bpf_map_new_fd() fails, should handle map->usercnt too.
--- kernel/bpf/syscall.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/bpf/syscall.c +1 -1
@@ -1887,7 +1887,7 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr) fd =bpf_map_new_fd (map, f_flags);if (fd <0 ) -bpf_map_put (map); +bpf_map_put_with_uref (map);return fd; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 196/219 mmc: core: align max segment size with logical block size
In reply to Sasha LevinFrom: Ming Lei <[email protected]>
[ Upstream commit c53336c8f5f29043fded57912cc06c24e12613d7 ]
Logical block size is the lowest possible block size that the storage device can address. Max segment size is often related with controller's DMA capability. And it is reasonable to align max segment size with logical block size.
SDHCI sets un-aligned max segment size, and causes ADMA error, so fix it by aligning max segment size with logical block size.
--- drivers/mmc/core/block.c | 6 ------ drivers/mmc/core/queue.c | 9 ++++++++- 2 files changed, 8 insertions(+), 7 deletions(-)
drivers/mmc/core/block.c +0 -6
@@ -2384,12 +2384,6 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,snprintf (md->disk->disk_name,sizeof (md->disk->disk_name),"mmcblk%u%s" , card->host->index, subname ? subname :"" ); -if (mmc_card_mmc (card)) -blk_queue_logical_block_size (md->queue.queue, - card->ext_csd.data_sector_size); -else -blk_queue_logical_block_size (md->queue.queue,512 ); -set_capacity (md->disk, size);if (mmc_host_cmd23 (card->host)) {
drivers/mmc/core/queue.c +8 -1
@@ -355,6 +355,7 @@ static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card) {struct mmc_host *host = card->host;u64 limit =BLK_BOUNCE_HIGH ; +unsigned block_size =512 ;if (mmc_dev (host)->dma_mask && *mmc_dev (host)->dma_mask) limit = (u64 )dma_max_pfn (mmc_dev (host)) <<PAGE_SHIFT ;
@@ -368,7 +369,13 @@ static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card)blk_queue_max_hw_sectors (mq->queue,min (host->max_blk_count, host->max_req_size /512 ));blk_queue_max_segments (mq->queue, host->max_segs); -blk_queue_max_segment_size (mq->queue, host->max_seg_size); + +if (mmc_card_mmc (card)) + block_size = card->ext_csd.data_sector_size; + +blk_queue_logical_block_size (mq->queue, block_size); +blk_queue_max_segment_size (mq->queue, +round_down (host->max_seg_size, block_size));INIT_WORK (&mq->recovery_work, mmc_mq_recovery_handler);INIT_WORK (&mq->complete_work, mmc_blk_mq_complete_work);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 197/219 net: dev: Use unsigned integer as an argument to left-shift
In reply to Sasha LevinFrom: Andy Shevchenko <[email protected]>
[ Upstream commit f4d7b3e23d259c44f1f1c39645450680fcd935d6 ]
1 << 31 is Undefined Behaviour according to the C standard. Use U type modifier to avoid theoretical overflow.
--- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
include/linux/netdevice.h +1 -1
@@ -3790,7 +3790,7 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits)if (debug_value ==0 )/* no output */ return 0 ;/* set low N bits */ -return (1 << debug_value) -1 ; +return (1U << debug_value) -1 ; }static inline void __netif_tx_lock (struct netdev_queue *txq,int cpu)
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 199/219 bpf: drop refcount if bpf_map_new_fd() fails in map_create()
In reply to Sasha LevinFrom: Peng Sun <[email protected]>
[ Upstream commit 352d20d611414715353ee65fc206ee57ab1a6984 ]
In bpf/syscall.c, map_create() first set map->usercnt to 1, a file descriptor is supposed to return to userspace. When bpf_map_new_fd() fails, drop the refcount.
--- kernel/bpf/syscall.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
kernel/bpf/syscall.c +2 -2
@@ -559,12 +559,12 @@ static int map_create(union bpf_attr *attr) err =bpf_map_new_fd (map, f_flags);if (err <0 ) {/* failed to allocate fd. -* bpf_map_put() is needed because the above +* bpf_map_put_with_uref() is needed because the above * bpf_map_alloc_id() has published the map * to the userspace and the userspace may * have refcnt-ed it through BPF_MAP_GET_FD_BY_ID. */ -bpf_map_put (map); +bpf_map_put_with_uref (map);return err; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 200/219 net: hns3: Change fw error code NOT_EXEC to NOT_SUPPORTED
In reply to Sasha LevinFrom: Yunsheng Lin <[email protected]>
[ Upstream commit 4a402f47cfce904051cd8b31bef4fe2910d9dce9 ]
According to firmware error code definition, the error code of 2 means NOT_SUPPORTED, this patch changes it to NOT_SUPPORTED.
--- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c | 2 ++ drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-)
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c +2 -0
@@ -260,6 +260,8 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)if (desc_ret ==HCLGE_CMD_EXEC_SUCCESS ) retval =0 ; +else if (desc_ret ==HCLGE_CMD_NOT_SUPPORTED ) + retval = -EOPNOTSUPP ;else retval = -EIO ; hw->cmq.last_status = desc_ret;
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +1 -1
@@ -39,7 +39,7 @@ struct hclge_cmq_ring {enum hclge_cmd_return_status {HCLGE_CMD_EXEC_SUCCESS =0 ,HCLGE_CMD_NO_AUTH =1 , -HCLGE_CMD_NOT_EXEC =2 , +HCLGE_CMD_NOT_SUPPORTED =2 ,HCLGE_CMD_QUEUE_FULL =3 , };
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 201/219 net: hns3: fix PFC not setting problem for DCB module
In reply to Sasha LevinFrom: Yunsheng Lin <[email protected]>
[ Upstream commit d3ad430ac531e65f29c9737f86744c425c9173ef ]
The PFC enabling is based on user priority, currently it is based on TC, which may cause PFC not setting correctly when pri to TC mapping is not one to one relation.
This patch adds pfc_en in tm_info to fix it.
--- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c | 7 ++++--- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 1 + drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c | 2 +- 3 files changed, 6 insertions(+), 4 deletions(-)
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c +4 -3
@@ -245,6 +245,9 @@ static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc) hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE)return -EINVAL ; +if (pfc->pfc_en == hdev->tm_info.pfc_en) +return 0 ; + prio_tc = hdev->tm_info.prio_tc; pfc_map =0 ;
@@ -257,10 +260,8 @@ static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc) } } -if (pfc_map == hdev->tm_info.hw_pfc_map) -return 0 ; - hdev->tm_info.hw_pfc_map = pfc_map; + hdev->tm_info.pfc_en = pfc->pfc_en;return hclge_pause_setup_hw (hdev); }
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +1 -0
@@ -249,6 +249,7 @@ struct hclge_tm_info {struct hclge_tc_info tc_info[HNAE3_MAX_TC ];enum hclge_fc_mode fc_mode;u8 hw_pfc_map;/* Allow for packet drop or not on this TC */ +u8 pfc_en;/* PFC enabled or not for user priority */ };struct hclge_comm_stats_str {
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +1 -1
@@ -1162,7 +1162,7 @@ static int hclge_pfc_setup_hw(struct hclge_dev *hdev)HCLGE_RX_MAC_PAUSE_EN_MSK ;return hclge_pfc_pause_en_cfg (hdev, enable_bitmap, - hdev->tm_info.hw_pfc_map); + hdev->tm_info.pfc_en); }/* Each Tc has a 1024 queue sets to backpress, it divides to
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 202/219 net: hns3: fix an issue for hclgevf_ae_get_hdev
In reply to Sasha LevinFrom: Peng Li <[email protected]>
[ Upstream commit eed9535f9f716a532ec0c5d6cc7a48584acdf435 ]
HNS3 VF driver support NIC and Roce, hdev stores NIC handle and Roce handle, should use correct parameter for container_of.
--- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +6 -1
@@ -26,7 +26,12 @@ MODULE_DEVICE_TABLE(pci, ae_algovf_pci_tbl);static inline struct hclgevf_dev *hclgevf_ae_get_hdev (struct hnae3_handle *handle) { - return container_of(handle, struct hclgevf_dev, nic); +if (!handle->client) + return container_of(handle, struct hclgevf_dev, nic); +else if (handle->client->type ==HNAE3_CLIENT_ROCE ) + return container_of(handle, struct hclgevf_dev, roce); +else + return container_of(handle, struct hclgevf_dev, nic); }static int hclgevf_tqps_update_stats (struct hnae3_handle *handle)
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 203/219 net: hns3: fix an issue for hns3_update_new_int_gl
In reply to Sasha LevinFrom: Peng Li <[email protected]>
[ Upstream commit 6241e71e7207102ffc733991f7a00f74098d7da0 ]
HNS3 supports setting rx-usecs|tx-usecs as 0, but it will not update dynamically when adaptive-tx or adaptive-rx is enable. This patch removes the Redundant check.
--- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +1 -1
@@ -2377,7 +2377,7 @@ static bool hns3_get_new_int_gl(struct hns3_enet_ring_group *ring_group)u32 time_passed_ms;u16 new_int_gl; -if (!ring_group->coal.int_gl || !tqp_vector->last_jiffies) +if (!tqp_vector->last_jiffies)return false;if (ring_group->total_packets ==0 ) {
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 204/219 iommu/amd: Fix NULL dereference bug in match_hid_uid
In reply to Sasha LevinFrom: Aaron Ma <[email protected]>
[ Upstream commit bb6bccba390c7d743c1e4427de4ef284c8cc6869 ]
Add a non-NULL check to fix potential NULL pointer dereference Cleanup code to call function once.
--- drivers/iommu/amd_iommu.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
drivers/iommu/amd_iommu.c +6 -2
@@ -139,10 +139,14 @@ static struct lock_class_key reserved_rbtree_key;static inline int match_hid_uid (struct device *dev,struct acpihid_map_entry *entry) { +struct acpi_device *adev =ACPI_COMPANION (dev);const char *hid, *uid; - hid =acpi_device_hid (ACPI_COMPANION (dev)); - uid =acpi_device_uid (ACPI_COMPANION (dev)); +if (!adev) +return -ENODEV ; + + hid =acpi_device_hid (adev); + uid =acpi_device_uid (adev);if (!hid || !(*hid))return -ENODEV ;
Signature · 6 lines
2.20.1 _______________________________________________ iommu mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/iommu
Sasha Levin
maintainerPATCH 205/219 apparmor: delete the dentry in aafs_remove() to avoid a leak
In reply to Sasha LevinFrom: Chris Coulson <[email protected]>
[ Upstream commit 201218e4d3dfa1346e30997f48725acce3f26d01 ]
Although the apparmorfs dentries are always dropped from the dentry cache when the usage count drops to zero, there is no guarantee that this will happen in aafs_remove(), as another thread might still be using it. In this scenario, this means that the dentry will temporarily continue to appear in the results of lookups, even after the call to aafs_remove().
In the case of removal of a profile - it also causes simple_rmdir() on the profile directory to fail, as the directory won't be empty until the usage counts of all child dentries have decreased to zero. This results in the dentry for the profile directory leaking and appearing empty in the file system tree forever.
--- security/apparmor/apparmorfs.c | 1 + 1 file changed, 1 insertion(+)
security/apparmor/apparmorfs.c +1 -0
@@ -361,6 +361,7 @@ static void aafs_remove(struct dentry *dentry)simple_rmdir (dir, dentry); elsesimple_unlink (dir ,dentry ); +d_delete (dentry);dput (dentry); }inode_unlock (dir);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 206/219 scsi: libsas: Support SATA PHY connection rate unmatch fixing during discovery
In reply to Sasha LevinFrom: John Garry <[email protected]>
[ Upstream commit cec9771d2e954650095aa37a6a97722c8194e7d2 ]
+----------+ +----------+ | | | | | |--- 3.0 G ---| |--- 6.0 G --- SAS disk | | | | | |--- 3.0 G ---| |--- 6.0 G --- SAS disk |initiator | | | | device |--- 3.0 G ---| Expander |--- 6.0 G --- SAS disk | | | | | |--- 3.0 G ---| |--- 6.0 G --- SATA disk -->failed to connect | | | | | | | |--- 6.0 G --- SATA disk -->failed to connect | | | | +----------+ +----------+
According to Serial Attached SCSI - 1.1 (SAS-1.1):
If an expander PHY attached to a SATA PHY is using a physical link rate greater than the maximum connection rate supported by the pathway from an STP initiator port, a management application client should use the SMP PHY CONTROL function (see 10.4.3.10) to set the PROGRAMMED MAXIMUM PHYSICAL LINK RATE field of the expander PHY to the maximum connection rate supported by the pathway from that STP initiator port.
Currently libsas does not support checking if this condition occurs, nor rectifying when it does.
Such a condition is not at all common, however it has been seen on some pre-silicon environments where the initiator PHY only supports a 1.5 Gbit maximum linkrate, mated with 12G expander PHYs and 3/6G SATA phy.
This patch adds support for checking and rectifying this condition during initial device discovery only.
We do support checking min pathway connection rate during revalidation phase, when new devices can be detected in the topology. However we do not support in the case of the the user reprogramming PHY linkrates, such that min pathway condition is not met/maintained.
A note on root port PHY rates:
The libsas root port PHY rates calculation is broken. Libsas sets the rates (min, max, and current linkrate) of a root port to the same linkrate of the first PHY member of that same port. In doing so, it assumes that all other PHYs which subsequently join the port to have the same negotiated linkrate, when they could actually be different.
In practice this doesn't happen, as initiator and expander PHYs are normally initialised with consistent min/max linkrates.
This has not caused an issue so far, so leave alone for now.
--- drivers/scsi/libsas/sas_expander.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+)
drivers/scsi/libsas/sas_expander.c +20 -0
@@ -817,6 +817,26 @@ static struct domain_device *sas_ex_discover_end_dev(#ifdef CONFIG_SCSI_SAS_ATA if ((phy->attached_tproto &SAS_PROTOCOL_STP ) || phy->attached_sata_dev) { +if (child->linkrate > parent->min_linkrate) { +struct sas_phy_linkrates rates = { + .maximum_linkrate = parent->min_linkrate, + .minimum_linkrate = parent->min_linkrate, + }; +int ret; + +pr_notice ("ex %016llx phy%02d SATA device linkrate > min pathway connection rate, attempting to lower device linkrate\n" , +SAS_ADDR (child->sas_addr), phy_id); + ret =sas_smp_phy_control (parent, phy_id, +PHY_FUNC_LINK_RESET , &rates); +if (ret) { +pr_err ("ex %016llx phy%02d SATA device could not set linkrate (%d)\n" , +SAS_ADDR (child->sas_addr), phy_id, ret); + goto out_free; + } +pr_notice ("ex %016llx phy%02d SATA device set linkrate successfully\n" , +SAS_ADDR (child->sas_addr), phy_id); + child->linkrate = child->min_linkrate; + } res =sas_get_ata_info (child, phy);if (res) goto out_free;
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 207/219 ACPI / APEI: Don't wait to serialise with oops messages when panic()ing
In reply to Sasha LevinFrom: James Morse <[email protected]>
[ Upstream commit 78b0b690f6558ed788dccafa45965325dd11ba89 ]
oops_begin() exists to group printk() messages with the oops message printed by die(). To reach this caller we know that platform firmware took this error first, then notified the OS via NMI with a 'panic' severity.
Don't wait for another CPU to release the die-lock before panic()ing, our only goal is to print this fatal error and panic().
This code is always called in_nmi(), and since commit 42a0bb3f7138 ("printk/nmi: generic solution for safe printk in NMI"), it has been safe to call printk() from this context. Messages are batched in a per-cpu buffer and printed via irq-work, or a call back from panic().
--- drivers/acpi/apei/ghes.c | 2 -- 1 file changed, 2 deletions(-)
drivers/acpi/apei/ghes.c +0 -2
@@ -33,7 +33,6 @@#include <linux/interrupt.h> #include <linux/timer.h> #include <linux/cper.h> -#include <linux/kdebug.h> #include <linux/platform_device.h> #include <linux/mutex.h> #include <linux/ratelimit.h>
@@ -949,7 +948,6 @@ static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs) sev =ghes_severity (ghes->estatus->error_severity);if (sev >=GHES_SEV_PANIC ) { -oops_begin ();ghes_print_queued_estatus ();__ghes_panic (ghes); }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 208/219 ACPI / APEI: Switch estatus pool to use vmalloc memory
In reply to Sasha LevinFrom: James Morse <[email protected]>
[ Upstream commit 0ac234be1a9497498e57d958f4251f5257b116b4 ]
The ghes code is careful to parse and round firmware's advertised memory requirements for CPER records, up to a maximum of 64K. However when ghes_estatus_pool_expand() does its work, it splits the requested size into PAGE_SIZE granules.
This means if firmware generates 5K of CPER records, and correctly describes this in the table, __process_error() will silently fail as it is unable to allocate more than PAGE_SIZE.
Switch the estatus pool to vmalloc() memory. On x86 vmalloc() memory may fault and be fixed up by vmalloc_fault(). To prevent this call vmalloc_sync_all() before an NMI handler could discover the memory.
--- drivers/acpi/apei/ghes.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-)
drivers/acpi/apei/ghes.c +15 -15
@@ -170,40 +170,40 @@ static int ghes_estatus_pool_init(void)return 0 ; } -static void ghes_estatus_pool_free_chunk_page (struct gen_pool *pool, +static void ghes_estatus_pool_free_chunk (struct gen_pool *pool,struct gen_pool_chunk *chunk,void *data) { -free_page (chunk->start_addr); +vfree ((void *)chunk->start_addr); }static void ghes_estatus_pool_exit (void ) {gen_pool_for_each_chunk (ghes_estatus_pool, - ghes_estatus_pool_free_chunk_page,NULL ); + ghes_estatus_pool_free_chunk,NULL );gen_pool_destroy (ghes_estatus_pool); }static int ghes_estatus_pool_expand (unsigned long len) { -unsigned long i, pages, size, addr; -int ret; +unsigned long size, addr; ghes_estatus_pool_size_request +=PAGE_ALIGN (len); size =gen_pool_size (ghes_estatus_pool);if (size >= ghes_estatus_pool_size_request)return 0 ; - pages = (ghes_estatus_pool_size_request - size) /PAGE_SIZE ; -for (i =0 ; i < pages; i++) { - addr =__get_free_page (GFP_KERNEL ); -if (!addr) -return -ENOMEM ; - ret =gen_pool_add (ghes_estatus_pool, addr,PAGE_SIZE ,-1 ); -if (ret) -return ret; - } -return 0 ; + addr = (unsigned long )vmalloc (PAGE_ALIGN (len)); +if (!addr) +return -ENOMEM ; + +/* +* New allocation must be visible in all pgd before it can be found by +* an NMI allocating from the pool. +*/ +vmalloc_sync_all (); + +return gen_pool_add (ghes_estatus_pool, addr,PAGE_ALIGN (len),-1 ); }static int map_gen_v2 (struct ghes *ghes)
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 209/219 scsi: hisi_sas: shutdown axi bus to avoid exception CQ returned
In reply to Sasha LevinFrom: Xiang Chen <[email protected]>
[ Upstream commit 5c31b0c677531c2b8b4e29b3cfb923df663f39b7 ]
When injecting 2 bit ECC error, it will cause fatal AXI interrupts. Before the recovery of SAS controller reset, the internal of SAS controller is in error. If CQ interrupts return at the time, actually it is exception CQ interrupt, and it may cause resource release in disorder.
To avoid the exception situation, shutdown AXI bus after fatal AXI interrupt. In SAS controller reset, it will restart AXI bus. For later version of v3 hw, hardware will shutdown AXI bus for this situation, so just fix current ver of v3 hw.
--- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)
drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +12 -0
@@ -1520,6 +1520,7 @@ static irqreturn_t fatal_axi_int_v3_hw(int irq_no, void *p)u32 irq_value, irq_msk;struct hisi_hba *hisi_hba = p;struct device *dev = hisi_hba->dev; +struct pci_dev *pdev = hisi_hba->pci_dev;int i; irq_msk =hisi_sas_read32 (hisi_hba,ENT_INT_SRC_MSK3 );
@@ -1551,6 +1552,17 @@ static irqreturn_t fatal_axi_int_v3_hw(int irq_no, void *p) error->msg, irq_value);queue_work (hisi_hba->wq, &hisi_hba->rst_work); } + +if (pdev->revision <0x21 ) { +u32 reg_val; + + reg_val =hisi_sas_read32 (hisi_hba, +AXI_MASTER_CFG_BASE + +AM_CTRL_GLOBAL ); + reg_val |=AM_CTRL_SHUTDOWN_REQ_MSK ; +hisi_sas_write32 (hisi_hba,AXI_MASTER_CFG_BASE + +AM_CTRL_GLOBAL , reg_val); + } }if (irq_value &BIT (ENT_INT_SRC3_ITC_INT_OFF )) {
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 210/219 scsi: libsas: Check SMP PHY control function result
In reply to Sasha LevinFrom: John Garry <[email protected]>
[ Upstream commit 01929a65dfa13e18d89264ab1378854a91857e59 ]
Currently the SMP PHY control execution result is checked, however the function result for the command is not.
As such, we may be missing all potential errors, like SMP FUNCTION FAILED, INVALID REQUEST FRAME LENGTH, etc., meaning the PHY control request has failed.
In some scenarios we need to ensure the function result is accepted, so add a check for this.
--- drivers/scsi/libsas/sas_expander.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)
drivers/scsi/libsas/sas_expander.c +8 -1
@@ -614,7 +614,14 @@ int sas_smp_phy_control(struct domain_device *dev, int phy_id, } res =smp_execute_task (dev, pc_req,PC_REQ_SIZE , pc_resp,PC_RESP_SIZE ); - +if (res) { +pr_err ("ex %016llx phy%02d PHY control failed: %d\n" , +SAS_ADDR (dev->sas_addr), phy_id, res); + }else if (pc_resp[2 ] !=SMP_RESP_FUNC_ACC ) { +pr_err ("ex %016llx phy%02d PHY control failed: function result 0x%x\n" , +SAS_ADDR (dev->sas_addr), phy_id, pc_resp[2 ]); + res = pc_resp[2 ]; + }kfree (pc_resp);kfree (pc_req);return res;
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 211/219 RDMA/hns: Fix the bug with updating rq head pointer when flush cqe
In reply to Sasha LevinFrom: Lijun Ou <[email protected]>
[ Upstream commit 9c6ccc035c209dda07685e8dba829a203ba17499 ]
When flush cqe with srq, the driver disable to update the rq head pointer into the hardware.
--- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)
drivers/infiniband/hw/hns/hns_roce_hw_v2.c +7 -3
@@ -3499,13 +3499,16 @@ static int hns_roce_v2_modify_qp(struct ib_qp *ibqp,roce_set_field (qpc_mask->byte_160_sq_ci_pi,V2_QPC_BYTE_160_SQ_PRODUCER_IDX_M ,V2_QPC_BYTE_160_SQ_PRODUCER_IDX_S ,0 ); -roce_set_field (context->byte_84_rq_ci_pi, + +if (!ibqp->srq) { +roce_set_field (context->byte_84_rq_ci_pi,V2_QPC_BYTE_84_RQ_PRODUCER_IDX_M ,V2_QPC_BYTE_84_RQ_PRODUCER_IDX_S , hr_qp->rq.head); -roce_set_field (qpc_mask->byte_84_rq_ci_pi, +roce_set_field (qpc_mask->byte_84_rq_ci_pi,V2_QPC_BYTE_84_RQ_PRODUCER_IDX_M ,V2_QPC_BYTE_84_RQ_PRODUCER_IDX_S ,0 ); + } }if (attr_mask &IB_QP_AV ) {
@@ -3967,7 +3970,8 @@ static void hns_roce_set_qps_to_err(struct hns_roce_dev *hr_dev, u32 qpn)if (hr_qp->ibqp.uobject) {if (hr_qp->sdb_en ==1 ) { hr_qp->sq.head = *(int *)(hr_qp->sdb.virt_addr); - hr_qp->rq.head = *(int *)(hr_qp->rdb.virt_addr); +if (hr_qp->rdb_en ==1 ) + hr_qp->rq.head = *(int *)(hr_qp->rdb.virt_addr); }else {dev_warn (hr_dev->dev,"flush cqe is unsupported in userspace!\n" );return ;
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 212/219 RDMA/hns: Bugfix for the scene without receiver queue
In reply to Sasha LevinFrom: Lijun Ou <[email protected]>
[ Upstream commit 4d103905eb1e4f14cb62fcf962c9d35da7005dea ]
In some application scenario, the user could not have receive queue when run rdma write or read operation.
--- drivers/infiniband/hw/hns/hns_roce_qp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/infiniband/hw/hns/hns_roce_qp.c +2 -1
@@ -503,7 +503,8 @@ static int hns_roce_qp_has_sq(struct ib_qp_init_attr *attr)static int hns_roce_qp_has_rq (struct ib_qp_init_attr *attr) {if (attr->qp_type ==IB_QPT_XRC_INI || - attr->qp_type ==IB_QPT_XRC_TGT || attr->srq) + attr->qp_type ==IB_QPT_XRC_TGT || attr->srq || + !attr->cap.max_recv_wr)return 0 ;return 1 ;
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 213/219 RDMA/hns: Fix the state of rereg mr
In reply to Sasha LevinFrom: Yixian Liu <[email protected]>
[ Upstream commit ab22bf05216a6bb4812448f3a8609489047cf311 ]
The state of mr after reregister operation should be set to valid state. Otherwise, it will keep the same as the state before reregistered.
--- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/infiniband/hw/hns/hns_roce_hw_v2.c +3 -0
@@ -1773,6 +1773,9 @@ static int hns_roce_v2_rereg_write_mtpt(struct hns_roce_dev *hr_dev,struct hns_roce_v2_mpt_entry *mpt_entry = mb_buf;int ret =0 ; +roce_set_field (mpt_entry->byte_4_pd_hop_st,V2_MPT_BYTE_4_MPT_ST_M , +V2_MPT_BYTE_4_MPT_ST_S ,V2_MPT_ST_VALID ); +if (flags &IB_MR_REREG_PD ) {roce_set_field (mpt_entry->byte_4_pd_hop_st,V2_MPT_BYTE_4_PD_M ,V2_MPT_BYTE_4_PD_S , pdn);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 214/219 RDMA/hns: Use GFP_ATOMIC in hns_roce_v2_modify_qp
In reply to Sasha LevinFrom: YueHaibing <[email protected]>
[ Upstream commit 4e69cf1fe2c52d189acdd06c1fd99cc258aba61f ]
The the below commit, hns_roce_v2_modify_qp is called inside spinlock while using GFP_KERNEL. Change it to GFP_ATOMIC.
--- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/infiniband/hw/hns/hns_roce_hw_v2.c +1 -1
@@ -3442,7 +3442,7 @@ static int hns_roce_v2_modify_qp(struct ib_qp *ibqp,struct device *dev = hr_dev->dev;int ret = -EINVAL ; - context =kcalloc (2 ,sizeof (*context),GFP_KERNEL ); + context =kcalloc (2 ,sizeof (*context),GFP_ATOMIC );if (!context)return -ENOMEM ;
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 215/219 ASoC: rt5645: Headphone Jack sense inverts on the LattePanda board
In reply to Sasha LevinFrom: Hui Wang <[email protected]>
[ Upstream commit 406dcbc55a0a20fd155be889a4a0c4b812f7c18e ]
The LattePanda board has a sound card chtrt5645, when there is nothing plugged in the headphone jack, the system thinks the headphone is plugged in, while we plug a headphone in the jack, the system thinks the headphone is unplugged.
If adding quirk=0x21 in the module parameter, the headphone jack can work well. So let us fix it via platform_data.
https://bugs.launchpad.net/bugs/182459
--- sound/soc/codecs/rt5645.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+)
sound/soc/codecs/rt5645.c +14 -0
@@ -3662,6 +3662,11 @@ static const struct rt5645_platform_data jd_mode3_platform_data = { .jd_mode = 3, }; +static const struct rt5645_platform_data lattepanda_board_platform_data = { + .jd_mode =2 , + .inv_jd1_1 = true +}; +static const struct dmi_system_id dmi_platform_data[] = { { .ident ="Chrome Buddy" ,
@@ -3759,6 +3764,15 @@ static const struct dmi_system_id dmi_platform_data[] = { }, .driver_data = (void *)&intel_braswell_platform_data, }, + { + .ident = "LattePanda board", + .matches = { + DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"), + DMI_EXACT_MATCH(DMI_BOARD_NAME, "Cherry Trail CR"), + DMI_EXACT_MATCH(DMI_BOARD_VERSION, "Default string"), + }, + .driver_data = (void *)&lattepanda_board_platform_data, + }, { } };
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 216/219 f2fs: fix to data block override node segment by mistake
In reply to Sasha LevinFrom: zhengliang <[email protected]>
[ Upstream commit a0770e13c8da83bdb64738c0209ab02dd3cfff8b ]
v4: Rearrange the previous three versions.
The following scenario could lead to data block override by mistake.
TASK A | TASK kworker | TASK B | TASK C
| | |
open | | |
write | | |
close | | |
| f2fs_write_data_pages | |
| f2fs_write_cache_pages | |
| f2fs_outplace_write_data | |
| f2fs_allocate_data_block (get block in seg S, | |
| S is full, and only | |
| have this valid data | |
| block) | |
| allocate_segment | |
| locate_dirty_segment (mark S as PRE) | |
| f2fs_submit_page_write (submit but is not | |
| written on dev) | |
unlink | | |
iput_final | | |
f2fs_drop_inode | | |
f2fs_truncate | | |
(not evict) | | |
| | write_checkpoint |
| | flush merged bio but not wait file data writeback |
| | set_prefree_as_free (mark S as FREE) |
| | | update NODE/DATA
| | | allocate_segment (select S)
| writeback done | |So we need to guarantee io complete before truncate inode in f2fs_drop_inode.
--- fs/f2fs/super.c | 4 ++++ 1 file changed, 4 insertions(+)
fs/f2fs/super.c +4 -0
@@ -890,6 +890,10 @@ static int f2fs_drop_inode(struct inode *inode)sb_start_intwrite (inode->i_sb);f2fs_i_size_write (inode,0 ); +f2fs_submit_merged_write_cond (F2FS_I_SB (inode), + inode,NULL ,0 ,DATA ); +truncate_inode_pages_final (inode->i_mapping); +if (F2FS_HAS_BLOCKS (inode))f2fs_truncate (inode);
Signature · 8 lines
2.20.1 _______________________________________________ Linux-f2fs-devel mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel
Sasha Levin
maintainerPATCH 217/219 powerpc/pseries/dlpar: Fix a missing check in dlpar_parse_cc_property()
In reply to Sasha LevinFrom: Gen Zhang <[email protected]>
[ Upstream commit efa9ace68e487ddd29c2b4d6dd23242158f1f607 ]
In dlpar_parse_cc_property(), 'prop->name' is allocated by kstrdup(). kstrdup() may return NULL, so it should be checked and handle error. And prop should be freed if 'prop->name' is NULL.
--- arch/powerpc/platforms/pseries/dlpar.c | 4 ++++ 1 file changed, 4 insertions(+)
arch/powerpc/platforms/pseries/dlpar.c +4 -0
@@ -63,6 +63,10 @@ static struct property *dlpar_parse_cc_property(struct cc_workarea *ccwa) name = (char *)ccwa +be32_to_cpu (ccwa->name_offset); prop->name =kstrdup (name,GFP_KERNEL ); +if (!prop->name) { +dlpar_free_cc_property (prop); +return NULL ; + } prop->length =be32_to_cpu (ccwa->prop_length); value = (char *)ccwa +be32_to_cpu (ccwa->prop_offset);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 218/219 xdp: fix cpumap redirect SKB creation bug
In reply to Sasha LevinFrom: Jesper Dangaard Brouer <[email protected]>
[ Upstream commit 676e4a6fe703f2dae699ee9d56f14516f9ada4ea ]
We want to avoid leaking pointer info from xdp_frame (that is placed in top of frame) like commit 6dfb970d3dbd ("xdp: avoid leaking info stored in frame data on page reuse"), and followup commit 97e19cce05e5 ("bpf:
reserve xdp_frame size in xdp headroom") that reserve this headroom.
These changes also affected how cpumap constructed SKBs, as xdpf->headroom size changed, the skb data starting point were in-effect shifted with 32 bytes (sizeof xdp_frame). This was still okay, as the cpumap frame_size calculation also included xdpf->headroom which were reduced by same amount.
A bug was introduced in commit 77ea5f4cbe20 ("bpf/cpumap: make sure frame_size for build_skb is aligned if headroom isn't"), where the xdpf->headroom became part of the SKB_DATA_ALIGN rounding up. This round-up to find the frame_size is in principle still correct as it does not exceed the 2048 bytes frame_size (which is max for ixgbe and i40e), but the 32 bytes offset of pkt_data_start puts this over the 2048 bytes limit. This cause skb_shared_info to spill into next frame. It is a little hard to trigger, as the SKB need to use above 15 skb_shinfo->frags[] as far as I calculate. This does happen in practise for TCP streams when skb_try_coalesce() kicks in.
KASAN can be used to detect these wrong memory accesses, I've seen:
BUG: KASAN: use-after-free in skb_try_coalesce+0x3cb/0x760 BUG: KASAN: wild-memory-access in skb_release_data+0xe2/0x250
Driver veth also construct a SKB from xdp_frame in this way, but is not affected, as it doesn't reserve/deduct the room (used by xdp_frame) from the SKB headroom. Instead is clears the pointers via xdp_scrub_frame(), and allows SKB to use this area.
The fix in this patch is to do like veth and instead allow SKB to (re)use the area occupied by xdp_frame, by clearing via xdp_scrub_frame(). (This does kill the idea of the SKB being able to access (mem) info from this area, but I guess it was a bad idea anyhow, and it was already killed by the veth changes.)
--- kernel/bpf/cpumap.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)
kernel/bpf/cpumap.c +10 -3
@@ -162,10 +162,14 @@ static void cpu_map_kthread_stop(struct work_struct *work)static struct sk_buff *cpu_map_build_skb (struct bpf_cpu_map_entry *rcpu,struct xdp_frame *xdpf) { +unsigned int hard_start_headroom;unsigned int frame_size;void *pkt_data_start;struct sk_buff *skb; +/* Part of headroom was reserved to xdpf */ + hard_start_headroom =sizeof (struct xdp_frame ) + xdpf->headroom; +/* build_skb need to place skb_shared_info after SKB end, and * also want to know the memory "truesize". Thus, need to * know the memory frame size backing xdp_buff.
@@ -183,15 +187,15 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,* is not at a fixed memory location, with mixed length * packets, which is bad for cache-line hotness. */ - frame_size =SKB_DATA_ALIGN (xdpf->len + xdpf->headroom) + + frame_size =SKB_DATA_ALIGN (xdpf->len + hard_start_headroom) +SKB_DATA_ALIGN (sizeof (struct skb_shared_info )); - pkt_data_start = xdpf->data - xdpf->headroom; + pkt_data_start = xdpf->data - hard_start_headroom; skb =build_skb (pkt_data_start, frame_size);if (!skb)return NULL ; -skb_reserve (skb, xdpf->headroom); +skb_reserve (skb, hard_start_headroom);__skb_put (skb, xdpf->len);if (xdpf->metasize)skb_metadata_set (skb, xdpf->metasize);
@@ -205,6 +209,9 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,* - RX ring dev queue index (skb_record_rx_queue) */ +/* Allow SKB to reuse area used by xdp_frame */ +xdp_scrub_frame (xdpf); +return skb; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 219/219 mtd: Remove a debug trace in mtdpart.c
In reply to Sasha LevinFrom: Boris Brezillon <[email protected]>
[ Upstream commit bda2ab56356b9acdfab150f31c4bac9846253092 ]
Commit 2b6f0090a333 ("mtd: Check add_mtd_device() ret code") contained a leftover of the debug session that led to this bug fix. Remove this pr_info().
--- drivers/mtd/mtdpart.c | 1 - 1 file changed, 1 deletion(-)
drivers/mtd/mtdpart.c +0 -1
@@ -626,7 +626,6 @@ int mtd_add_partition(struct mtd_info *parent, const char *name,mutex_unlock (&mtd_partitions_mutex);free_partition (new); -pr_info ("%s:%i\n" , __func__, __LINE__);return ret; }
Signature · 1 line
2.20.1