From c10910c323bb9e7fc53ba25c83d1adeb9fb20878 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 21 Jan 2016 15:51:17 -0800 Subject: [PATCH 001/417] sparc: Hook up copy_file_range syscall. Signed-off-by: David S. Miller --- arch/sparc/include/uapi/asm/unistd.h | 3 ++- arch/sparc/kernel/systbls_32.S | 2 +- arch/sparc/kernel/systbls_64.S | 4 ++-- 3 files changed, 5 insertions(+), 4 deletions(-) diff --git a/arch/sparc/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h index 1c26d440d288..b6de8b10a55b 100644 --- a/arch/sparc/include/uapi/asm/unistd.h +++ b/arch/sparc/include/uapi/asm/unistd.h @@ -422,8 +422,9 @@ #define __NR_listen 354 #define __NR_setsockopt 355 #define __NR_mlock2 356 +#define __NR_copy_file_range 357 -#define NR_syscalls 357 +#define NR_syscalls 358 /* Bitmask values returned from kern_features system call. */ #define KERN_FEATURE_MIXED_MODE_STACK 0x00000001 diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S index e663b6c78de2..6c3dd6c52f8b 100644 --- a/arch/sparc/kernel/systbls_32.S +++ b/arch/sparc/kernel/systbls_32.S @@ -88,4 +88,4 @@ sys_call_table: /*340*/ .long sys_ni_syscall, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr /*345*/ .long sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .long sys_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen -/*355*/ .long sys_setsockopt, sys_mlock2 +/*355*/ .long sys_setsockopt, sys_mlock2, sys_copy_file_range diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index 1557121f4cdc..12b524cfcfa0 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -89,7 +89,7 @@ sys_call_table32: /*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr .word sys32_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .word sys32_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen - .word compat_sys_setsockopt, sys_mlock2 + .word compat_sys_setsockopt, sys_mlock2, sys_copy_file_range #endif /* CONFIG_COMPAT */ @@ -170,4 +170,4 @@ sys_call_table: /*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr .word sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .word sys64_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen - .word sys_setsockopt, sys_mlock2 + .word sys_setsockopt, sys_mlock2, sys_copy_file_range From 1a40b95374f680625318ab61d81958e949e0afe3 Mon Sep 17 00:00:00 2001 From: Mike Frysinger Date: Mon, 18 Jan 2016 06:32:30 -0500 Subject: [PATCH 002/417] sparc: Fix system call tracing register handling. A system call trace trigger on entry allows the tracing process to inspect and potentially change the traced process's registers. Account for that by reloading the %g1 (syscall number) and %i0-%i5 (syscall argument) values. We need to be careful to revalidate the range of %g1, and reload the system call table entry it corresponds to into %l7. Reported-by: Mike Frysinger Signed-off-by: David S. Miller Tested-by: Mike Frysinger --- arch/sparc/kernel/entry.S | 17 +++++++++++++++++ arch/sparc/kernel/syscalls.S | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 53 insertions(+) diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S index 33c02b15f478..a83707c83be8 100644 --- a/arch/sparc/kernel/entry.S +++ b/arch/sparc/kernel/entry.S @@ -948,7 +948,24 @@ linux_syscall_trace: cmp %o0, 0 bne 3f mov -ENOSYS, %o0 + + /* Syscall tracing can modify the registers. */ + ld [%sp + STACKFRAME_SZ + PT_G1], %g1 + sethi %hi(sys_call_table), %l7 + ld [%sp + STACKFRAME_SZ + PT_I0], %i0 + or %l7, %lo(sys_call_table), %l7 + ld [%sp + STACKFRAME_SZ + PT_I1], %i1 + ld [%sp + STACKFRAME_SZ + PT_I2], %i2 + ld [%sp + STACKFRAME_SZ + PT_I3], %i3 + ld [%sp + STACKFRAME_SZ + PT_I4], %i4 + ld [%sp + STACKFRAME_SZ + PT_I5], %i5 + cmp %g1, NR_syscalls + bgeu 3f + mov -ENOSYS, %o0 + + sll %g1, 2, %l4 mov %i0, %o0 + ld [%l7 + %l4], %l7 mov %i1, %o1 mov %i2, %o2 mov %i3, %o3 diff --git a/arch/sparc/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S index bb0008927598..c4a1b5c40e4e 100644 --- a/arch/sparc/kernel/syscalls.S +++ b/arch/sparc/kernel/syscalls.S @@ -158,7 +158,25 @@ linux_syscall_trace32: add %sp, PTREGS_OFF, %o0 brnz,pn %o0, 3f mov -ENOSYS, %o0 + + /* Syscall tracing can modify the registers. */ + ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1 + sethi %hi(sys_call_table32), %l7 + ldx [%sp + PTREGS_OFF + PT_V9_I0], %i0 + or %l7, %lo(sys_call_table32), %l7 + ldx [%sp + PTREGS_OFF + PT_V9_I1], %i1 + ldx [%sp + PTREGS_OFF + PT_V9_I2], %i2 + ldx [%sp + PTREGS_OFF + PT_V9_I3], %i3 + ldx [%sp + PTREGS_OFF + PT_V9_I4], %i4 + ldx [%sp + PTREGS_OFF + PT_V9_I5], %i5 + + cmp %g1, NR_syscalls + bgeu,pn %xcc, 3f + mov -ENOSYS, %o0 + + sll %g1, 2, %l4 srl %i0, 0, %o0 + lduw [%l7 + %l4], %l7 srl %i4, 0, %o4 srl %i1, 0, %o1 srl %i2, 0, %o2 @@ -170,7 +188,25 @@ linux_syscall_trace: add %sp, PTREGS_OFF, %o0 brnz,pn %o0, 3f mov -ENOSYS, %o0 + + /* Syscall tracing can modify the registers. */ + ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1 + sethi %hi(sys_call_table64), %l7 + ldx [%sp + PTREGS_OFF + PT_V9_I0], %i0 + or %l7, %lo(sys_call_table64), %l7 + ldx [%sp + PTREGS_OFF + PT_V9_I1], %i1 + ldx [%sp + PTREGS_OFF + PT_V9_I2], %i2 + ldx [%sp + PTREGS_OFF + PT_V9_I3], %i3 + ldx [%sp + PTREGS_OFF + PT_V9_I4], %i4 + ldx [%sp + PTREGS_OFF + PT_V9_I5], %i5 + + cmp %g1, NR_syscalls + bgeu,pn %xcc, 3f + mov -ENOSYS, %o0 + + sll %g1, 2, %l4 mov %i0, %o0 + lduw [%l7 + %l4], %l7 mov %i1, %o1 mov %i2, %o2 mov %i3, %o3 From f5d0ca224a071d7077bbdae347cb514949d64fd9 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Tue, 12 Jan 2016 15:04:30 +0100 Subject: [PATCH 003/417] ARM: dts: imx6: remove bogus interrupt-parent from CAAM node The interrupt-parent property is not needed as it is inherited from the parent bus and in the case of the CAAM node actively points to the wrong interrupt controller (GIC instead of GPC). This leads to the CAAM IRQs not getting unmasked at the GPC level, leaving them unable to wake the CPU from wait mode, potentially impacting performance of the CAAM unit when CPUidle is enabled. Signed-off-by: Lucas Stach Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx6qdl.dtsi | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi index 4f6ae921656f..f74d3db4846d 100644 --- a/arch/arm/boot/dts/imx6qdl.dtsi +++ b/arch/arm/boot/dts/imx6qdl.dtsi @@ -896,7 +896,6 @@ crypto: caam@2100000 { #size-cells = <1>; reg = <0x2100000 0x10000>; ranges = <0 0x2100000 0x10000>; - interrupt-parent = <&intc>; clocks = <&clks IMX6QDL_CLK_CAAM_MEM>, <&clks IMX6QDL_CLK_CAAM_ACLK>, <&clks IMX6QDL_CLK_CAAM_IPG>, From 8bf862739a7786ae72409220914df960a0aa80d8 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 27 Jan 2016 12:37:52 +0100 Subject: [PATCH 004/417] wext: fix message delay/ordering Beniamino reported that he was getting an RTM_NEWLINK message for a given interface, after the RTM_DELLINK for it. It turns out that the message is a wireless extensions message, which was sent because the interface had been connected and disconnection while it was deleted caused a wext message. For its netlink messages, wext uses RTM_NEWLINK, but the message is without all the regular rtnetlink attributes, so "ip monitor link" prints just rudimentary information: 5: wlan1: mtu 1500 qdisc mq state DOWN group default link/ether 02:00:00:00:01:00 brd ff:ff:ff:ff:ff:ff Deleted 5: wlan1: mtu 1500 qdisc noop state DOWN group default link/ether 02:00:00:00:01:00 brd ff:ff:ff:ff:ff:ff 5: wlan1: link/ether (from my hwsim reproduction) This can cause userspace to get confused since it doesn't expect an RTM_NEWLINK message after RTM_DELLINK. The reason for this is that wext schedules a worker to send out the messages, and the scheduling delay can cause the messages to get out to userspace in different order. To fix this, have wext register a netdevice notifier and flush out any pending messages when netdevice state changes. This fixes any ordering whenever the original message wasn't sent by a notifier itself. Cc: stable@vger.kernel.org Reported-by: Beniamino Galvani Signed-off-by: Johannes Berg --- net/wireless/wext-core.c | 51 +++++++++++++++++++++++++++++++--------- 1 file changed, 40 insertions(+), 11 deletions(-) diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index c8717c1d082e..87dd619fb2e9 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -342,6 +342,39 @@ static const int compat_event_type_size[] = { /* IW event code */ +static void wireless_nlevent_flush(void) +{ + struct sk_buff *skb; + struct net *net; + + ASSERT_RTNL(); + + for_each_net(net) { + while ((skb = skb_dequeue(&net->wext_nlevents))) + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, + GFP_KERNEL); + } +} + +static int wext_netdev_notifier_call(struct notifier_block *nb, + unsigned long state, void *ptr) +{ + /* + * When a netdev changes state in any way, flush all pending messages + * to avoid them going out in a strange order, e.g. RTM_NEWLINK after + * RTM_DELLINK, or with IFF_UP after without IFF_UP during dev_close() + * or similar - all of which could otherwise happen due to delays from + * schedule_work(). + */ + wireless_nlevent_flush(); + + return NOTIFY_OK; +} + +static struct notifier_block wext_netdev_notifier = { + .notifier_call = wext_netdev_notifier_call, +}; + static int __net_init wext_pernet_init(struct net *net) { skb_queue_head_init(&net->wext_nlevents); @@ -360,7 +393,12 @@ static struct pernet_operations wext_pernet_ops = { static int __init wireless_nlevent_init(void) { - return register_pernet_subsys(&wext_pernet_ops); + int err = register_pernet_subsys(&wext_pernet_ops); + + if (err) + return err; + + return register_netdevice_notifier(&wext_netdev_notifier); } subsys_initcall(wireless_nlevent_init); @@ -368,17 +406,8 @@ subsys_initcall(wireless_nlevent_init); /* Process events generated by the wireless layer or the driver. */ static void wireless_nlevent_process(struct work_struct *work) { - struct sk_buff *skb; - struct net *net; - rtnl_lock(); - - for_each_net(net) { - while ((skb = skb_dequeue(&net->wext_nlevents))) - rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, - GFP_KERNEL); - } - + wireless_nlevent_flush(); rtnl_unlock(); } From cb150b9d23be6ee7f3a0fff29784f1c5b5ac514d Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 27 Jan 2016 13:29:34 +0100 Subject: [PATCH 005/417] cfg80211/wext: fix message ordering Since cfg80211 frequently takes actions from its netdev notifier call, wireless extensions messages could still be ordered badly since the wext netdev notifier, since wext is built into the kernel, runs before the cfg80211 netdev notifier. For example, the following can happen: 5: wlan1: mtu 1500 qdisc mq state DOWN group default link/ether 02:00:00:00:01:00 brd ff:ff:ff:ff:ff:ff 5: wlan1: link/ether when setting the interface down causes the wext message. To also fix this, export the wireless_nlevent_flush() function and also call it from the cfg80211 notifier. Cc: stable@vger.kernel.org Signed-off-by: Johannes Berg --- include/net/iw_handler.h | 6 ++++++ net/wireless/core.c | 2 ++ net/wireless/wext-core.c | 3 ++- 3 files changed, 10 insertions(+), 1 deletion(-) diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h index 8f81bbbc38fc..e0f4109e64c6 100644 --- a/include/net/iw_handler.h +++ b/include/net/iw_handler.h @@ -439,6 +439,12 @@ int dev_get_wireless_info(char *buffer, char **start, off_t offset, int length); /* Send a single event to user space */ void wireless_send_event(struct net_device *dev, unsigned int cmd, union iwreq_data *wrqu, const char *extra); +#ifdef CONFIG_WEXT_CORE +/* flush all previous wext events - if work is done from netdev notifiers */ +void wireless_nlevent_flush(void); +#else +static inline void wireless_nlevent_flush(void) {} +#endif /* We may need a function to send a stream of events to user space. * More on that later... */ diff --git a/net/wireless/core.c b/net/wireless/core.c index b0915515640e..8f0bac7e03c4 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1147,6 +1147,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, return NOTIFY_DONE; } + wireless_nlevent_flush(); + return NOTIFY_OK; } diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index 87dd619fb2e9..b50ee5d622e1 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -342,7 +342,7 @@ static const int compat_event_type_size[] = { /* IW event code */ -static void wireless_nlevent_flush(void) +void wireless_nlevent_flush(void) { struct sk_buff *skb; struct net *net; @@ -355,6 +355,7 @@ static void wireless_nlevent_flush(void) GFP_KERNEL); } } +EXPORT_SYMBOL_GPL(wireless_nlevent_flush); static int wext_netdev_notifier_call(struct notifier_block *nb, unsigned long state, void *ptr) From f39ea2690bd61efec97622c48323f40ed6e16317 Mon Sep 17 00:00:00 2001 From: Chris Bainbridge Date: Wed, 27 Jan 2016 15:46:18 +0000 Subject: [PATCH 006/417] mac80211: fix use of uninitialised values in RX aggregation Use kzalloc instead of kmalloc for struct tid_ampdu_rx to initialize the "removed" field (all others are initialized manually). That fixes: UBSAN: Undefined behaviour in net/mac80211/rx.c:932:29 load of value 2 is not a valid value for type '_Bool' CPU: 3 PID: 1134 Comm: kworker/u16:7 Not tainted 4.5.0-rc1+ #265 Workqueue: phy0 rt2x00usb_work_rxdone 0000000000000004 ffff880254a7ba50 ffffffff8181d866 0000000000000007 ffff880254a7ba78 ffff880254a7ba68 ffffffff8188422d ffffffff8379b500 ffff880254a7bab8 ffffffff81884747 0000000000000202 0000000348620032 Call Trace: [] dump_stack+0x45/0x5f [] ubsan_epilogue+0xd/0x40 [] __ubsan_handle_load_invalid_value+0x67/0x70 [] ieee80211_sta_reorder_release.isra.16+0x5ed/0x730 [] ieee80211_prepare_and_rx_handle+0xd04/0x1c00 [] __ieee80211_rx_handle_packet+0x1f3/0x750 [] ieee80211_rx_napi+0x447/0x990 While at it, convert to use sizeof(*tid_agg_rx) instead. Fixes: 788211d81bfdf ("mac80211: fix RX A-MPDU session reorder timer deletion") Cc: stable@vger.kernel.org Signed-off-by: Chris Bainbridge [reword commit message, use sizeof(*tid_agg_rx)] Signed-off-by: Johannes Berg --- net/mac80211/agg-rx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 10ad4ac1fa0b..367784be5df2 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -291,7 +291,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, } /* prepare A-MPDU MLME for Rx aggregation */ - tid_agg_rx = kmalloc(sizeof(struct tid_ampdu_rx), GFP_KERNEL); + tid_agg_rx = kzalloc(sizeof(*tid_agg_rx), GFP_KERNEL); if (!tid_agg_rx) goto end; From ca0bb0798022732773752fee97bb633c6f3623d2 Mon Sep 17 00:00:00 2001 From: "wim.coekaerts@oracle.com" Date: Fri, 29 Jan 2016 09:39:38 -0800 Subject: [PATCH 007/417] Add sun4v_wdt watchdog driver This driver adds sparc hypervisor watchdog support. The default timeout is 60 seconds and the range is between 1 and 31536000 seconds. Both watchdog-resolution and watchdog-max-timeout MD properties settings are supported. Signed-off-by: Wim Coekaerts Reviewed-by: Julian Calaby Reviewed-by: Guenter Roeck Signed-off-by: David S. Miller --- .../watchdog/watchdog-parameters.txt | 4 + arch/sparc/kernel/hvcalls.S | 3 +- arch/sparc/kernel/sparc_ksyms_64.c | 1 + drivers/watchdog/Kconfig | 11 + drivers/watchdog/Makefile | 1 + drivers/watchdog/sun4v_wdt.c | 191 ++++++++++++++++++ 6 files changed, 210 insertions(+), 1 deletion(-) create mode 100644 drivers/watchdog/sun4v_wdt.c diff --git a/Documentation/watchdog/watchdog-parameters.txt b/Documentation/watchdog/watchdog-parameters.txt index 9f9ec9f76039..4e4b6f10d841 100644 --- a/Documentation/watchdog/watchdog-parameters.txt +++ b/Documentation/watchdog/watchdog-parameters.txt @@ -400,3 +400,7 @@ wm8350_wdt: nowayout: Watchdog cannot be stopped once started (default=kernel config parameter) ------------------------------------------------- +sun4v_wdt: +timeout_ms: Watchdog timeout in milliseconds 1..180000, default=60000) +nowayout: Watchdog cannot be stopped once started +------------------------------------------------- diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S index afbaba52d2f1..d127130bf424 100644 --- a/arch/sparc/kernel/hvcalls.S +++ b/arch/sparc/kernel/hvcalls.S @@ -338,8 +338,9 @@ ENTRY(sun4v_mach_set_watchdog) mov %o1, %o4 mov HV_FAST_MACH_SET_WATCHDOG, %o5 ta HV_FAST_TRAP + brnz,a,pn %o4, 0f stx %o1, [%o4] - retl +0: retl nop ENDPROC(sun4v_mach_set_watchdog) diff --git a/arch/sparc/kernel/sparc_ksyms_64.c b/arch/sparc/kernel/sparc_ksyms_64.c index a92d5d2c46a3..9e034f29dcc5 100644 --- a/arch/sparc/kernel/sparc_ksyms_64.c +++ b/arch/sparc/kernel/sparc_ksyms_64.c @@ -37,6 +37,7 @@ EXPORT_SYMBOL(sun4v_niagara_getperf); EXPORT_SYMBOL(sun4v_niagara_setperf); EXPORT_SYMBOL(sun4v_niagara2_getperf); EXPORT_SYMBOL(sun4v_niagara2_setperf); +EXPORT_SYMBOL(sun4v_mach_set_watchdog); /* from hweight.S */ EXPORT_SYMBOL(__arch_hweight8); diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index 4f0e7be0da34..30d38ae685f6 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -1565,6 +1565,17 @@ config WATCHDOG_RIO machines. The watchdog timeout period is normally one minute but can be changed with a boot-time parameter. +config WATCHDOG_SUN4V + tristate "Sun4v Watchdog support" + select WATCHDOG_CORE + depends on SPARC64 + help + Say Y here to support the hypervisor watchdog capability embedded + in the SPARC sun4v architecture. + + To compile this driver as a module, choose M here. The module will + be called sun4v_wdt. + # XTENSA Architecture # Xen Architecture diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile index f566753256ab..f6a6a387c6c7 100644 --- a/drivers/watchdog/Makefile +++ b/drivers/watchdog/Makefile @@ -179,6 +179,7 @@ obj-$(CONFIG_SH_WDT) += shwdt.o obj-$(CONFIG_WATCHDOG_RIO) += riowd.o obj-$(CONFIG_WATCHDOG_CP1XXX) += cpwd.o +obj-$(CONFIG_WATCHDOG_SUN4V) += sun4v_wdt.o # XTENSA Architecture diff --git a/drivers/watchdog/sun4v_wdt.c b/drivers/watchdog/sun4v_wdt.c new file mode 100644 index 000000000000..1467fe50a76f --- /dev/null +++ b/drivers/watchdog/sun4v_wdt.c @@ -0,0 +1,191 @@ +/* + * sun4v watchdog timer + * (c) Copyright 2016 Oracle Corporation + * + * Implement a simple watchdog driver using the built-in sun4v hypervisor + * watchdog support. If time expires, the hypervisor stops or bounces + * the guest domain. + * + * 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; either version + * 2 of the License, or (at your option) any later version. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include + +#define WDT_TIMEOUT 60 +#define WDT_MAX_TIMEOUT 31536000 +#define WDT_MIN_TIMEOUT 1 +#define WDT_DEFAULT_RESOLUTION_MS 1000 /* 1 second */ + +static unsigned int timeout; +module_param(timeout, uint, 0); +MODULE_PARM_DESC(timeout, "Watchdog timeout in seconds (default=" + __MODULE_STRING(WDT_TIMEOUT) ")"); + +static bool nowayout = WATCHDOG_NOWAYOUT; +module_param(nowayout, bool, S_IRUGO); +MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" + __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); + +static int sun4v_wdt_stop(struct watchdog_device *wdd) +{ + sun4v_mach_set_watchdog(0, NULL); + + return 0; +} + +static int sun4v_wdt_ping(struct watchdog_device *wdd) +{ + int hverr; + + /* + * HV watchdog timer will round up the timeout + * passed in to the nearest multiple of the + * watchdog resolution in milliseconds. + */ + hverr = sun4v_mach_set_watchdog(wdd->timeout * 1000, NULL); + if (hverr == HV_EINVAL) + return -EINVAL; + + return 0; +} + +static int sun4v_wdt_set_timeout(struct watchdog_device *wdd, + unsigned int timeout) +{ + wdd->timeout = timeout; + + return 0; +} + +static const struct watchdog_info sun4v_wdt_ident = { + .options = WDIOF_SETTIMEOUT | + WDIOF_MAGICCLOSE | + WDIOF_KEEPALIVEPING, + .identity = "sun4v hypervisor watchdog", + .firmware_version = 0, +}; + +static struct watchdog_ops sun4v_wdt_ops = { + .owner = THIS_MODULE, + .start = sun4v_wdt_ping, + .stop = sun4v_wdt_stop, + .ping = sun4v_wdt_ping, + .set_timeout = sun4v_wdt_set_timeout, +}; + +static struct watchdog_device wdd = { + .info = &sun4v_wdt_ident, + .ops = &sun4v_wdt_ops, + .min_timeout = WDT_MIN_TIMEOUT, + .max_timeout = WDT_MAX_TIMEOUT, + .timeout = WDT_TIMEOUT, +}; + +static int __init sun4v_wdt_init(void) +{ + struct mdesc_handle *handle; + u64 node; + const u64 *value; + int err = 0; + unsigned long major = 1, minor = 1; + + /* + * There are 2 properties that can be set from the control + * domain for the watchdog. + * watchdog-resolution + * watchdog-max-timeout + * + * We can expect a handle to be returned otherwise something + * serious is wrong. Correct to return -ENODEV here. + */ + + handle = mdesc_grab(); + if (!handle) + return -ENODEV; + + node = mdesc_node_by_name(handle, MDESC_NODE_NULL, "platform"); + err = -ENODEV; + if (node == MDESC_NODE_NULL) + goto out_release; + + /* + * This is a safe way to validate if we are on the right + * platform. + */ + if (sun4v_hvapi_register(HV_GRP_CORE, major, &minor)) + goto out_hv_unreg; + + /* Allow value of watchdog-resolution up to 1s (default) */ + value = mdesc_get_property(handle, node, "watchdog-resolution", NULL); + err = -EINVAL; + if (value) { + if (*value == 0 || + *value > WDT_DEFAULT_RESOLUTION_MS) + goto out_hv_unreg; + } + + value = mdesc_get_property(handle, node, "watchdog-max-timeout", NULL); + if (value) { + /* + * If the property value (in ms) is smaller than + * min_timeout, return -EINVAL. + */ + if (*value < wdd.min_timeout * 1000) + goto out_hv_unreg; + + /* + * If the property value is smaller than + * default max_timeout then set watchdog max_timeout to + * the value of the property in seconds. + */ + if (*value < wdd.max_timeout * 1000) + wdd.max_timeout = *value / 1000; + } + + watchdog_init_timeout(&wdd, timeout, NULL); + + watchdog_set_nowayout(&wdd, nowayout); + + err = watchdog_register_device(&wdd); + if (err) + goto out_hv_unreg; + + pr_info("initialized (timeout=%ds, nowayout=%d)\n", + wdd.timeout, nowayout); + + mdesc_release(handle); + + return 0; + +out_hv_unreg: + sun4v_hvapi_unregister(HV_GRP_CORE); + +out_release: + mdesc_release(handle); + return err; +} + +static void __exit sun4v_wdt_exit(void) +{ + sun4v_hvapi_unregister(HV_GRP_CORE); + watchdog_unregister_device(&wdd); +} + +module_init(sun4v_wdt_init); +module_exit(sun4v_wdt_exit); + +MODULE_AUTHOR("Wim Coekaerts "); +MODULE_DESCRIPTION("sun4v watchdog driver"); +MODULE_LICENSE("GPL"); From f84a93726e0c0c53b5b6dbee96623e7e53e06dd8 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Fri, 29 Jan 2016 11:35:12 +0300 Subject: [PATCH 008/417] mac80211: minstrel_ht: fix out-of-bound in minstrel_ht_set_best_prob_rate Patch fixes this splat BUG: KASAN: slab-out-of-bounds in minstrel_ht_update_stats.isra.7+0x6e1/0x9e0 [mac80211] at addr ffff8800cee640f4 Read of size 4 by task swapper/3/0 Signed-off-by: Konstantin Khlebnikov Link: http://lkml.kernel.org/r/CALYGNiNyJhSaVnE35qS6UCGaSb2Dx1_i5HcRavuOX14oTz2P+w@mail.gmail.com Acked-by: Felix Fietkau Signed-off-by: Johannes Berg --- net/mac80211/rc80211_minstrel_ht.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 3928dbd24e25..93bf2b743e20 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -414,15 +414,16 @@ minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 index) (max_tp_group != MINSTREL_CCK_GROUP)) return; + max_gpr_group = mg->max_group_prob_rate / MCS_GROUP_RATES; + max_gpr_idx = mg->max_group_prob_rate % MCS_GROUP_RATES; + max_gpr_prob = mi->groups[max_gpr_group].rates[max_gpr_idx].prob_ewma; + if (mrs->prob_ewma > MINSTREL_FRAC(75, 100)) { cur_tp_avg = minstrel_ht_get_tp_avg(mi, cur_group, cur_idx, mrs->prob_ewma); if (cur_tp_avg > tmp_tp_avg) mi->max_prob_rate = index; - max_gpr_group = mg->max_group_prob_rate / MCS_GROUP_RATES; - max_gpr_idx = mg->max_group_prob_rate % MCS_GROUP_RATES; - max_gpr_prob = mi->groups[max_gpr_group].rates[max_gpr_idx].prob_ewma; max_gpr_tp_avg = minstrel_ht_get_tp_avg(mi, max_gpr_group, max_gpr_idx, max_gpr_prob); @@ -431,7 +432,7 @@ minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 index) } else { if (mrs->prob_ewma > tmp_prob) mi->max_prob_rate = index; - if (mrs->prob_ewma > mg->rates[mg->max_group_prob_rate].prob_ewma) + if (mrs->prob_ewma > max_gpr_prob) mg->max_group_prob_rate = index; } } From 212c5a5e6ba61678be6b5fee576e38bccb50b613 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Tue, 2 Feb 2016 08:12:26 +0100 Subject: [PATCH 009/417] mac80211: minstrel: Change expected throughput unit back to Kbps The change from cur_tp to the function minstrel_get_tp_avg/minstrel_ht_get_tp_avg changed the unit used for the current throughput. For example in minstrel_ht the correct conversion between them would be: mrs->cur_tp / 10 == minstrel_ht_get_tp_avg(..). This factor 10 must also be included in the calculation of minstrel_get_expected_throughput and minstrel_ht_get_expected_throughput to return values with the unit [Kbps] instead of [10Kbps]. Otherwise routing algorithms like B.A.T.M.A.N. V will make incorrect decision based on these values. Its kernel based implementation expects expected_throughput always to have the unit [Kbps] and not sometimes [10Kbps] and sometimes [Kbps]. The same requirement has iw or olsrdv2's nl80211 based statistics module which retrieve the same data via NL80211_STA_INFO_TX_BITRATE. Cc: stable@vger.kernel.org Fixes: 6a27b2c40b48 ("mac80211: restructure per-rate throughput calculation into function") Signed-off-by: Sven Eckelmann Signed-off-by: Johannes Berg --- net/mac80211/rc80211_minstrel.c | 2 +- net/mac80211/rc80211_minstrel_ht.c | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index 3ece7d1034c8..b54f398cda5d 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -711,7 +711,7 @@ static u32 minstrel_get_expected_throughput(void *priv_sta) * computing cur_tp */ tmp_mrs = &mi->r[idx].stats; - tmp_cur_tp = minstrel_get_tp_avg(&mi->r[idx], tmp_mrs->prob_ewma); + tmp_cur_tp = minstrel_get_tp_avg(&mi->r[idx], tmp_mrs->prob_ewma) * 10; tmp_cur_tp = tmp_cur_tp * 1200 * 8 / 1024; return tmp_cur_tp; diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 93bf2b743e20..702328bcabdc 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -1335,7 +1335,8 @@ static u32 minstrel_ht_get_expected_throughput(void *priv_sta) prob = mi->groups[i].rates[j].prob_ewma; /* convert tp_avg from pkt per second in kbps */ - tp_avg = minstrel_ht_get_tp_avg(mi, i, j, prob) * AVG_PKT_SIZE * 8 / 1024; + tp_avg = minstrel_ht_get_tp_avg(mi, i, j, prob) * 10; + tp_avg = tp_avg * AVG_PKT_SIZE * 8 / 1024; return tp_avg; } From f285aa8db7cc4432c1a03f8b55ff34fe96317c11 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 8 Feb 2016 15:30:18 +0100 Subject: [PATCH 010/417] xen/scsiback: correct frontend counting When adding a new frontend to xen-scsiback don't decrement the number of active frontends in case of no error. Doing so results in a failure when trying to remove the xen-pvscsi nexus even if no domain is using it. Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Cc: stable@vger.kernel.org Signed-off-by: David Vrabel --- drivers/xen/xen-scsiback.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index ad4eb1024d1f..51387d75c7bf 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -939,12 +939,12 @@ static int scsiback_add_translation_entry(struct vscsibk_info *info, spin_unlock_irqrestore(&info->v2p_lock, flags); out_free: - mutex_lock(&tpg->tv_tpg_mutex); - tpg->tv_tpg_fe_count--; - mutex_unlock(&tpg->tv_tpg_mutex); - - if (err) + if (err) { + mutex_lock(&tpg->tv_tpg_mutex); + tpg->tv_tpg_fe_count--; + mutex_unlock(&tpg->tv_tpg_mutex); kfree(new); + } return err; } From c9e2f531be000af652927ee0af3a0f24f8e9e046 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 8 Feb 2016 15:30:19 +0100 Subject: [PATCH 011/417] xen/scsiback: avoid warnings when adding multiple LUNs to a domain When adding more than one LUN to a frontend a warning for a failed assignment is issued in dom0 for each already existing LUN. Avoid this warning by checking for a LUN already existing when existence is allowed (scsiback_do_add_lun() called with try == 1). As the LUN existence check is needed now for a third time, factor it out into a function. This in turn leads to a more or less complete rewrite of scsiback_del_translation_entry() which will now return a proper error code in case of failure. Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Signed-off-by: David Vrabel --- drivers/xen/xen-scsiback.c | 70 ++++++++++++++++++++++---------------- 1 file changed, 41 insertions(+), 29 deletions(-) diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 51387d75c7bf..c46ee189466f 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -848,6 +848,24 @@ static int scsiback_map(struct vscsibk_info *info) return scsiback_init_sring(info, ring_ref, evtchn); } +/* + Check for a translation entry being present +*/ +static struct v2p_entry *scsiback_chk_translation_entry( + struct vscsibk_info *info, struct ids_tuple *v) +{ + struct list_head *head = &(info->v2p_entry_lists); + struct v2p_entry *entry; + + list_for_each_entry(entry, head, l) + if ((entry->v.chn == v->chn) && + (entry->v.tgt == v->tgt) && + (entry->v.lun == v->lun)) + return entry; + + return NULL; +} + /* Add a new translation entry */ @@ -855,9 +873,7 @@ static int scsiback_add_translation_entry(struct vscsibk_info *info, char *phy, struct ids_tuple *v) { int err = 0; - struct v2p_entry *entry; struct v2p_entry *new; - struct list_head *head = &(info->v2p_entry_lists); unsigned long flags; char *lunp; unsigned long long unpacked_lun; @@ -917,15 +933,10 @@ static int scsiback_add_translation_entry(struct vscsibk_info *info, spin_lock_irqsave(&info->v2p_lock, flags); /* Check double assignment to identical virtual ID */ - list_for_each_entry(entry, head, l) { - if ((entry->v.chn == v->chn) && - (entry->v.tgt == v->tgt) && - (entry->v.lun == v->lun)) { - pr_warn("Virtual ID is already used. Assignment was not performed.\n"); - err = -EEXIST; - goto out; - } - + if (scsiback_chk_translation_entry(info, v)) { + pr_warn("Virtual ID is already used. Assignment was not performed.\n"); + err = -EEXIST; + goto out; } /* Create a new translation entry and add to the list */ @@ -933,7 +944,7 @@ static int scsiback_add_translation_entry(struct vscsibk_info *info, new->v = *v; new->tpg = tpg; new->lun = unpacked_lun; - list_add_tail(&new->l, head); + list_add_tail(&new->l, &info->v2p_entry_lists); out: spin_unlock_irqrestore(&info->v2p_lock, flags); @@ -956,39 +967,40 @@ static void __scsiback_del_translation_entry(struct v2p_entry *entry) } /* - Delete the translation entry specfied + Delete the translation entry specified */ static int scsiback_del_translation_entry(struct vscsibk_info *info, struct ids_tuple *v) { struct v2p_entry *entry; - struct list_head *head = &(info->v2p_entry_lists); unsigned long flags; + int ret = 0; spin_lock_irqsave(&info->v2p_lock, flags); /* Find out the translation entry specified */ - list_for_each_entry(entry, head, l) { - if ((entry->v.chn == v->chn) && - (entry->v.tgt == v->tgt) && - (entry->v.lun == v->lun)) { - goto found; - } - } + entry = scsiback_chk_translation_entry(info, v); + if (entry) + __scsiback_del_translation_entry(entry); + else + ret = -ENOENT; spin_unlock_irqrestore(&info->v2p_lock, flags); - return 1; - -found: - /* Delete the translation entry specfied */ - __scsiback_del_translation_entry(entry); - - spin_unlock_irqrestore(&info->v2p_lock, flags); - return 0; + return ret; } static void scsiback_do_add_lun(struct vscsibk_info *info, const char *state, char *phy, struct ids_tuple *vir, int try) { + struct v2p_entry *entry; + unsigned long flags; + + if (try) { + spin_lock_irqsave(&info->v2p_lock, flags); + entry = scsiback_chk_translation_entry(info, vir); + spin_unlock_irqrestore(&info->v2p_lock, flags); + if (entry) + return; + } if (!scsiback_add_translation_entry(info, phy, vir)) { if (xenbus_printf(XBT_NIL, info->dev->nodename, state, "%d", XenbusStateInitialised)) { From 52ba0746b3b44c86aee121babf3b2fd9b8f84090 Mon Sep 17 00:00:00 2001 From: Ian Campbell Date: Mon, 8 Feb 2016 16:02:06 +0000 Subject: [PATCH 012/417] xen/arm: correctly handle DMA mapping of compound pages Currently xen_dma_map_page concludes that DMA to anything other than the head page of a compound page must be foreign, since the PFN of the page is that of the head. Fix the check to instead consider the whole of a compound page to be local if the PFN of the head passes the 1:1 check. We can never see a compound page which is a mixture of foreign and local sub-pages. The comment already correctly described the intention, but fixup the spelling and some grammar. This fixes the various SSH protocol errors which we have been seeing on the cubietrucks in our automated test infrastructure. This has been broken since commit 3567258d281b ("xen/arm: use hypercall to flush caches in map_page"), which was in v3.19-rc1. NB arch/arm64/.../xen/page-coherent.h also includes this file. Signed-off-by: Ian Campbell Reviewed-by: Stefano Stabellini Cc: xen-devel@lists.xenproject.org Cc: linux-arm-kernel@lists.infradead.org Cc: stable@vger.kernel.org # v3.19+ --- arch/arm/include/asm/xen/page-coherent.h | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h index 0375c8caa061..9408a994cc91 100644 --- a/arch/arm/include/asm/xen/page-coherent.h +++ b/arch/arm/include/asm/xen/page-coherent.h @@ -35,14 +35,21 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page, dma_addr_t dev_addr, unsigned long offset, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { - bool local = XEN_PFN_DOWN(dev_addr) == page_to_xen_pfn(page); + unsigned long page_pfn = page_to_xen_pfn(page); + unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr); + unsigned long compound_pages = + (1<map_page(hwdev, page, offset, size, dir, attrs); From 50ab8ec74a153eb30db26529088bc57dd700b24c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Feb 2016 21:11:50 +0100 Subject: [PATCH 013/417] nfs: fix nfs_size_to_loff_t See http: //www.infradead.org/rpr.html X-Evolution-Source: 1451162204.2173.11@leira.trondhjem.org Content-Transfer-Encoding: 8bit Mime-Version: 1.0 We support OFFSET_MAX just fine, so don't round down below it. Also switch to using min_t to make the helper more readable. Signed-off-by: Christoph Hellwig Fixes: 433c92379d9c ("NFS: Clean up nfs_size_to_loff_t()") Cc: stable@vger.kernel.org # 2.6.23+ Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 48e0320cd643..67300f8e5f2f 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -550,9 +550,7 @@ extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, static inline loff_t nfs_size_to_loff_t(__u64 size) { - if (size > (__u64) OFFSET_MAX - 1) - return OFFSET_MAX - 1; - return (loff_t) size; + return min_t(u64, size, OFFSET_MAX); } static inline ino_t From 9d021c9d1b4b774a35d8a03d58dbf029544debda Mon Sep 17 00:00:00 2001 From: Heinrich Schuchardt Date: Sun, 7 Feb 2016 19:34:26 +0100 Subject: [PATCH 014/417] ARM: dts: kirkwood: use unique machine name for ds112 Downstream packages like Debian flash-kernel use /proc/device-tree/model to determine which dtb file to install. Hence each dts in the Linux kernel should provide a unique model identifier. Commit 2d0a7addbd10 ("ARM: Kirkwood: Add support for many Synology NAS devices") created the new files kirkwood-ds111.dts and kirkwood-ds112.dts using the same model identifier. This patch provides a unique model identifier for the Synology DiskStation DS112. Fixes: 2d0a7addbd10 ("ARM: Kirkwood: Add support for many Synology NAS devices") Signed-off-by: Heinrich Schuchardt Reviewed-by: Andrew Lunn Signed-off-by: Gregory CLEMENT --- arch/arm/boot/dts/kirkwood-ds112.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/kirkwood-ds112.dts b/arch/arm/boot/dts/kirkwood-ds112.dts index bf4143c6cb8f..b84af3da8c84 100644 --- a/arch/arm/boot/dts/kirkwood-ds112.dts +++ b/arch/arm/boot/dts/kirkwood-ds112.dts @@ -14,7 +14,7 @@ #include "kirkwood-synology.dtsi" / { - model = "Synology DS111"; + model = "Synology DS112"; compatible = "synology,ds111", "marvell,kirkwood"; memory { From 44361a2cc13493fc41216d33bb9a562ec3a9cc4e Mon Sep 17 00:00:00 2001 From: Roger Shimizu Date: Sat, 6 Feb 2016 14:59:51 +0900 Subject: [PATCH 015/417] ARM: dts: orion5x: fix the missing mtd flash on linkstation lswtgl MTD flash stores u-boot and u-boot environment on linkstation lswtgl. The latter one can be easily read/write by u-boot-tools package in Debian. Fixes: dc57844a736f ("ARM: dts: orion5x: add buffalo linkstation ls-wtgl") Signed-off-by: Roger Shimizu Reviewed-by: Andrew Lunn Signed-off-by: Gregory CLEMENT --- .../boot/dts/orion5x-linkstation-lswtgl.dts | 31 +++++++++++++++++++ 1 file changed, 31 insertions(+) diff --git a/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts b/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts index 420788229e6f..aae8a7aceab7 100644 --- a/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts +++ b/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts @@ -228,6 +228,37 @@ hdd_power: regulator@2 { }; }; +&devbus_bootcs { + status = "okay"; + devbus,keep-config; + + flash@0 { + compatible = "jedec-flash"; + reg = <0 0x40000>; + bank-width = <1>; + + partitions { + compatible = "fixed-partitions"; + #address-cells = <1>; + #size-cells = <1>; + + header@0 { + reg = <0 0x30000>; + read-only; + }; + + uboot@30000 { + reg = <0x30000 0xF000>; + read-only; + }; + + uboot_env@3F000 { + reg = <0x3F000 0x1000>; + }; + }; + }; +}; + &mdio { status = "okay"; From 4f388a9210e2a2c1cd83a5580b74aa13876dbf14 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Fri, 5 Feb 2016 11:52:00 -0200 Subject: [PATCH 016/417] [media] media: davinci_vpfe: fix missing unlock on error in vpfe_prepare_pipeline() Add the missing unlock before return from function vpfe_prepare_pipeline() in the error handling case. video->lock is lock/unlock in function vpfe_open(), and no need to unlock it here, so remove unlock video->lock. Signed-off-by: Wei Yongjun Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- drivers/staging/media/davinci_vpfe/vpfe_video.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/media/davinci_vpfe/vpfe_video.c b/drivers/staging/media/davinci_vpfe/vpfe_video.c index 3ec7e65a3ffa..db49af90217e 100644 --- a/drivers/staging/media/davinci_vpfe/vpfe_video.c +++ b/drivers/staging/media/davinci_vpfe/vpfe_video.c @@ -147,7 +147,7 @@ static int vpfe_prepare_pipeline(struct vpfe_video_device *video) mutex_lock(&mdev->graph_mutex); ret = media_entity_graph_walk_init(&graph, entity->graph_obj.mdev); if (ret) { - mutex_unlock(&video->lock); + mutex_unlock(&mdev->graph_mutex); return -ENOMEM; } media_entity_graph_walk_start(&graph, entity); From b888d232142c0ac111c7e82d1731c6fbd56fc1fe Mon Sep 17 00:00:00 2001 From: Anton Protopopov Date: Sun, 7 Feb 2016 02:27:32 -0200 Subject: [PATCH 017/417] [media] media: i2c/adp1653: probe: fix erroneous return value The adp1653_probe() function may return positive value EINVAL which is obviously wrong. Signed-off-by: Anton Protopopov Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- drivers/media/i2c/adp1653.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/i2c/adp1653.c b/drivers/media/i2c/adp1653.c index 7e9cbf757e95..fb7ed730d932 100644 --- a/drivers/media/i2c/adp1653.c +++ b/drivers/media/i2c/adp1653.c @@ -497,7 +497,7 @@ static int adp1653_probe(struct i2c_client *client, if (!client->dev.platform_data) { dev_err(&client->dev, "Neither DT not platform data provided\n"); - return EINVAL; + return -EINVAL; } flash->platform_data = client->dev.platform_data; } From 5f35dc47c1744110d4119c4aa2a00872e8a1217b Mon Sep 17 00:00:00 2001 From: Ivaylo Dimitrov Date: Wed, 10 Feb 2016 20:23:02 +0200 Subject: [PATCH 018/417] ARM: OMAP2+: Set system_rev from ATAGS for n900 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This fixed a regression with DT boot compared to legacy boot. Reviewed-by: Pali Rohár Tested-by: Pali Rohár Signed-off-by: Ivaylo Dimitrov [tony@atomide.com: edited patch subject to follow standard] Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/board-generic.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c index 809827265fb3..bab814d2f37d 100644 --- a/arch/arm/mach-omap2/board-generic.c +++ b/arch/arm/mach-omap2/board-generic.c @@ -18,6 +18,7 @@ #include #include +#include #include "common.h" @@ -77,12 +78,31 @@ static const char *const n900_boards_compat[] __initconst = { NULL, }; +/* Set system_rev from atags */ +static void __init rx51_set_system_rev(const struct tag *tags) +{ + const struct tag *tag; + + if (tags->hdr.tag != ATAG_CORE) + return; + + for_each_tag(tag, tags) { + if (tag->hdr.tag == ATAG_REVISION) { + system_rev = tag->u.revision.rev; + break; + } + } +} + /* Legacy userspace on Nokia N900 needs ATAGS exported in /proc/atags, * save them while the data is still not overwritten */ static void __init rx51_reserve(void) { - save_atags((const struct tag *)(PAGE_OFFSET + 0x100)); + const struct tag *tags = (const struct tag *)(PAGE_OFFSET + 0x100); + + save_atags(tags); + rx51_set_system_rev(tags); omap_reserve(); } From a5b87513119248c87b9df938025d066af8ec8856 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 8 Feb 2016 21:55:53 +0000 Subject: [PATCH 019/417] ARM: dts: am335x/am57xx: replace gpio-key,wakeup with wakeup-source property MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 3efda00129bd ("ARM: dts: am335x: replace gpio-key,wakeup with wakeup-source property") replaces all the legacy "gpio-key,wakeup" with the unified "wakeup-source" property to prevent any further copy-paste duplication. However couple of use of these legacy property sneaked in during the merge window. This patch replaces them too. Cc: "Benoît Cousson" Cc: linux-omap@vger.kernel.org Signed-off-by: Sudeep Holla Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/am335x-shc.dts | 4 ++-- arch/arm/boot/dts/am57xx-cl-som-am57x.dts | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm/boot/dts/am335x-shc.dts b/arch/arm/boot/dts/am335x-shc.dts index 1b5b044fcd91..865de8500f1c 100644 --- a/arch/arm/boot/dts/am335x-shc.dts +++ b/arch/arm/boot/dts/am335x-shc.dts @@ -46,7 +46,7 @@ back_button { gpios = <&gpio1 29 GPIO_ACTIVE_HIGH>; linux,code = ; debounce-interval = <1000>; - gpio-key,wakeup; + wakeup-source; }; front_button { @@ -54,7 +54,7 @@ front_button { gpios = <&gpio1 25 GPIO_ACTIVE_HIGH>; linux,code = ; debounce-interval = <1000>; - gpio-key,wakeup; + wakeup-source; }; }; diff --git a/arch/arm/boot/dts/am57xx-cl-som-am57x.dts b/arch/arm/boot/dts/am57xx-cl-som-am57x.dts index 8d93882dc8d5..1c06cb76da07 100644 --- a/arch/arm/boot/dts/am57xx-cl-som-am57x.dts +++ b/arch/arm/boot/dts/am57xx-cl-som-am57x.dts @@ -545,7 +545,7 @@ ads7846@0 { ti,debounce-tol = /bits/ 16 <10>; ti,debounce-rep = /bits/ 16 <1>; - linux,wakeup; + wakeup-source; }; }; From bf26927b2c0780609e6e5361d177cf10107065f3 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Tue, 9 Feb 2016 13:46:57 +0200 Subject: [PATCH 020/417] ARM: DTS: am57xx-beagle-x15: Select SYS_CLK2 for audio clocks The tlv320aic3104 codec's master clock is coming from the SoC's CLKOUT2. Select the SYS_CLK2 (via divider) as parent clock for CLKOUT2 and select the same clock (SYS_CLK2) for McASP3 AHCLKX clock as well. SYS_CLK2 is sourced from an external oscillator running 22.5792MHz and it is coming in to the SoC via the X1_OSC1. Signed-off-by: Peter Ujfalusi Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/am57xx-beagle-x15.dts | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts index 36c0fa6c362a..a0986c65be0c 100644 --- a/arch/arm/boot/dts/am57xx-beagle-x15.dts +++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts @@ -173,6 +173,8 @@ simple-audio-card,cpu { sound0_master: simple-audio-card,codec { sound-dai = <&tlv320aic3104>; + assigned-clocks = <&clkoutmux2_clk_mux>; + assigned-clock-parents = <&sys_clk2_dclk_div>; clocks = <&clkout2_clk>; }; }; @@ -796,6 +798,8 @@ &mcasp3 { pinctrl-names = "default", "sleep"; pinctrl-0 = <&mcasp3_pins_default>; pinctrl-1 = <&mcasp3_pins_sleep>; + assigned-clocks = <&mcasp3_ahclkx_mux>; + assigned-clock-parents = <&sys_clkin2>; status = "okay"; op-mode = <0>; /* MCASP_IIS_MODE */ From f070d6715509dafc0af223577c896fe3d204ca88 Mon Sep 17 00:00:00 2001 From: Suman Tripathi Date: Sat, 6 Feb 2016 11:25:22 +0530 Subject: [PATCH 021/417] libahci: Implement the capability to override the generic ahci interrupt handler. This patch implements the capability to override the generic AHCI interrupt handler so that specific ahci drivers can implement their own custom interrupt handler routines. It also exports ahci_handle_port_intr so that custom irq_handler implementations can use it. tj: s/ahci_irq_handler/irq_handler/ and updated description. Signed-off-by: Suman Tripathi Signed-off-by: Tejun Heo --- drivers/ata/ahci.h | 2 ++ drivers/ata/libahci.c | 27 ++++++++++++++++++++------- 2 files changed, 22 insertions(+), 7 deletions(-) diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index a44c75d4c284..cf48e3ed234a 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -361,6 +361,7 @@ struct ahci_host_priv { * be overridden anytime before the host is activated. */ void (*start_engine)(struct ata_port *ap); + irqreturn_t (*irq_handler)(int irq, void *dev_instance); }; #ifdef CONFIG_PCI_MSI @@ -424,6 +425,7 @@ int ahci_reset_em(struct ata_host *host); void ahci_print_info(struct ata_host *host, const char *scc_s); int ahci_host_activate(struct ata_host *host, struct scsi_host_template *sht); void ahci_error_handler(struct ata_port *ap); +u32 ahci_handle_port_intr(struct ata_host *host, u32 irq_masked); static inline void __iomem *__ahci_port_base(struct ata_host *host, unsigned int port_no) diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 402967902cbe..cbfe8a2de4c5 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -113,6 +113,9 @@ static ssize_t ahci_store_em_buffer(struct device *dev, const char *buf, size_t size); static ssize_t ahci_show_em_supported(struct device *dev, struct device_attribute *attr, char *buf); +static irqreturn_t ahci_single_edge_irq_intr(int irq, void *dev_instance); + +static irqreturn_t ahci_single_level_irq_intr(int irq, void *dev_instance); static DEVICE_ATTR(ahci_host_caps, S_IRUGO, ahci_show_host_caps, NULL); static DEVICE_ATTR(ahci_host_cap2, S_IRUGO, ahci_show_host_cap2, NULL); @@ -512,6 +515,11 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv) if (!hpriv->start_engine) hpriv->start_engine = ahci_start_engine; + + if (!hpriv->irq_handler) + hpriv->irq_handler = (hpriv->flags & AHCI_HFLAG_EDGE_IRQ) ? + ahci_single_edge_irq_intr : + ahci_single_level_irq_intr; } EXPORT_SYMBOL_GPL(ahci_save_initial_config); @@ -1846,7 +1854,7 @@ static irqreturn_t ahci_multi_irqs_intr_hard(int irq, void *dev_instance) return IRQ_HANDLED; } -static u32 ahci_handle_port_intr(struct ata_host *host, u32 irq_masked) +u32 ahci_handle_port_intr(struct ata_host *host, u32 irq_masked) { unsigned int i, handled = 0; @@ -1872,6 +1880,7 @@ static u32 ahci_handle_port_intr(struct ata_host *host, u32 irq_masked) return handled; } +EXPORT_SYMBOL_GPL(ahci_handle_port_intr); static irqreturn_t ahci_single_edge_irq_intr(int irq, void *dev_instance) { @@ -2535,14 +2544,18 @@ int ahci_host_activate(struct ata_host *host, struct scsi_host_template *sht) int irq = hpriv->irq; int rc; - if (hpriv->flags & (AHCI_HFLAG_MULTI_MSI | AHCI_HFLAG_MULTI_MSIX)) + if (hpriv->flags & (AHCI_HFLAG_MULTI_MSI | AHCI_HFLAG_MULTI_MSIX)) { + if (hpriv->irq_handler) + dev_warn(host->dev, "both AHCI_HFLAG_MULTI_MSI flag set \ + and custom irq handler implemented\n"); + rc = ahci_host_activate_multi_irqs(host, sht); - else if (hpriv->flags & AHCI_HFLAG_EDGE_IRQ) - rc = ata_host_activate(host, irq, ahci_single_edge_irq_intr, - IRQF_SHARED, sht); - else - rc = ata_host_activate(host, irq, ahci_single_level_irq_intr, + } else { + rc = ata_host_activate(host, irq, hpriv->irq_handler, IRQF_SHARED, sht); + } + + return rc; } EXPORT_SYMBOL_GPL(ahci_host_activate); From d867b95f965457b9e85fb061ef8e3fdc029116ed Mon Sep 17 00:00:00 2001 From: Suman Tripathi Date: Sat, 6 Feb 2016 11:25:23 +0530 Subject: [PATCH 022/417] ata: Remove the AHCI_HFLAG_EDGE_IRQ support from libahci. The flexibility to override the irq handles in the LLD's are already present, so controllers implementing a edge trigger latch can implement their own interrupt handler inside the driver. This patch removes the AHCI_HFLAG_EDGE_IRQ support from libahci and moves edge irq handling to ahci_xgene. tj: Minor update to description. Signed-off-by: Suman Tripathi Signed-off-by: Tejun Heo --- drivers/ata/ahci.h | 3 +-- drivers/ata/ahci_xgene.c | 40 ++++++++++++++++++++++++++++++++++++- drivers/ata/libahci.c | 43 +--------------------------------------- 3 files changed, 41 insertions(+), 45 deletions(-) diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index cf48e3ed234a..167ba7e3b92e 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -240,8 +240,7 @@ enum { error-handling stage) */ AHCI_HFLAG_NO_DEVSLP = (1 << 17), /* no device sleep */ AHCI_HFLAG_NO_FBS = (1 << 18), /* no FBS */ - AHCI_HFLAG_EDGE_IRQ = (1 << 19), /* HOST_IRQ_STAT behaves as - Edge Triggered */ + #ifdef CONFIG_PCI_MSI AHCI_HFLAG_MULTI_MSI = (1 << 20), /* multiple PCI MSIs */ AHCI_HFLAG_MULTI_MSIX = (1 << 21), /* per-port MSI-X */ diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c index e2c6d9e0c5ac..8b8ccb6434e2 100644 --- a/drivers/ata/ahci_xgene.c +++ b/drivers/ata/ahci_xgene.c @@ -548,6 +548,43 @@ static int xgene_ahci_softreset(struct ata_link *link, unsigned int *class, return rc; } +static irqreturn_t xgene_ahci_irq_intr(int irq, void *dev_instance) +{ + struct ata_host *host = dev_instance; + struct ahci_host_priv *hpriv; + unsigned int rc = 0; + void __iomem *mmio; + u32 irq_stat, irq_masked; + + VPRINTK("ENTER\n"); + + hpriv = host->private_data; + mmio = hpriv->mmio; + + /* sigh. 0xffffffff is a valid return from h/w */ + irq_stat = readl(mmio + HOST_IRQ_STAT); + if (!irq_stat) + return IRQ_NONE; + + irq_masked = irq_stat & hpriv->port_map; + + spin_lock(&host->lock); + + /* + * HOST_IRQ_STAT behaves as edge triggered latch meaning that + * it should be cleared before all the port events are cleared. + */ + writel(irq_stat, mmio + HOST_IRQ_STAT); + + rc = ahci_handle_port_intr(host, irq_masked); + + spin_unlock(&host->lock); + + VPRINTK("EXIT\n"); + + return IRQ_RETVAL(rc); +} + static struct ata_port_operations xgene_ahci_v1_ops = { .inherits = &ahci_ops, .host_stop = xgene_ahci_host_stop, @@ -779,7 +816,8 @@ static int xgene_ahci_probe(struct platform_device *pdev) hpriv->flags = AHCI_HFLAG_NO_NCQ; break; case XGENE_AHCI_V2: - hpriv->flags |= AHCI_HFLAG_YES_FBS | AHCI_HFLAG_EDGE_IRQ; + hpriv->flags |= AHCI_HFLAG_YES_FBS; + hpriv->irq_handler = xgene_ahci_irq_intr; break; default: break; diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index cbfe8a2de4c5..513b3fa74d78 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -113,8 +113,6 @@ static ssize_t ahci_store_em_buffer(struct device *dev, const char *buf, size_t size); static ssize_t ahci_show_em_supported(struct device *dev, struct device_attribute *attr, char *buf); -static irqreturn_t ahci_single_edge_irq_intr(int irq, void *dev_instance); - static irqreturn_t ahci_single_level_irq_intr(int irq, void *dev_instance); static DEVICE_ATTR(ahci_host_caps, S_IRUGO, ahci_show_host_caps, NULL); @@ -517,9 +515,7 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv) hpriv->start_engine = ahci_start_engine; if (!hpriv->irq_handler) - hpriv->irq_handler = (hpriv->flags & AHCI_HFLAG_EDGE_IRQ) ? - ahci_single_edge_irq_intr : - ahci_single_level_irq_intr; + hpriv->irq_handler = ahci_single_level_irq_intr; } EXPORT_SYMBOL_GPL(ahci_save_initial_config); @@ -1882,43 +1878,6 @@ u32 ahci_handle_port_intr(struct ata_host *host, u32 irq_masked) } EXPORT_SYMBOL_GPL(ahci_handle_port_intr); -static irqreturn_t ahci_single_edge_irq_intr(int irq, void *dev_instance) -{ - struct ata_host *host = dev_instance; - struct ahci_host_priv *hpriv; - unsigned int rc = 0; - void __iomem *mmio; - u32 irq_stat, irq_masked; - - VPRINTK("ENTER\n"); - - hpriv = host->private_data; - mmio = hpriv->mmio; - - /* sigh. 0xffffffff is a valid return from h/w */ - irq_stat = readl(mmio + HOST_IRQ_STAT); - if (!irq_stat) - return IRQ_NONE; - - irq_masked = irq_stat & hpriv->port_map; - - spin_lock(&host->lock); - - /* - * HOST_IRQ_STAT behaves as edge triggered latch meaning that - * it should be cleared before all the port events are cleared. - */ - writel(irq_stat, mmio + HOST_IRQ_STAT); - - rc = ahci_handle_port_intr(host, irq_masked); - - spin_unlock(&host->lock); - - VPRINTK("EXIT\n"); - - return IRQ_RETVAL(rc); -} - static irqreturn_t ahci_single_level_irq_intr(int irq, void *dev_instance) { struct ata_host *host = dev_instance; From 32aea2680de01f539d928112150279fdeeabca00 Mon Sep 17 00:00:00 2001 From: Suman Tripathi Date: Sat, 6 Feb 2016 11:25:24 +0530 Subject: [PATCH 023/417] ahci_xgene: Implement the workaround to fix the missing of the edge interrupt for the HOST_IRQ_STAT. Due to H/W errata, the HOST_IRQ_STAT register misses the edge interrupt when clearing the HOST_IRQ_STAT register and hardware reporting the PORT_IRQ_STAT register happens to be at the same clock cycle. Signed-off-by: Suman Tripathi Signed-off-by: Tejun Heo --- drivers/ata/ahci_xgene.c | 47 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 46 insertions(+), 1 deletion(-) diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c index 8b8ccb6434e2..8e3f7faf00d3 100644 --- a/drivers/ata/ahci_xgene.c +++ b/drivers/ata/ahci_xgene.c @@ -548,6 +548,51 @@ static int xgene_ahci_softreset(struct ata_link *link, unsigned int *class, return rc; } +/** + * xgene_ahci_handle_broken_edge_irq - Handle the broken irq. + * @ata_host: Host that recieved the irq + * @irq_masked: HOST_IRQ_STAT value + * + * For hardware with broken edge trigger latch + * the HOST_IRQ_STAT register misses the edge interrupt + * when clearing of HOST_IRQ_STAT register and hardware + * reporting the PORT_IRQ_STAT register at the + * same clock cycle. + * As such, the algorithm below outlines the workaround. + * + * 1. Read HOST_IRQ_STAT register and save the state. + * 2. Clear the HOST_IRQ_STAT register. + * 3. Read back the HOST_IRQ_STAT register. + * 4. If HOST_IRQ_STAT register equals to zero, then + * traverse the rest of port's PORT_IRQ_STAT register + * to check if an interrupt is triggered at that point else + * go to step 6. + * 5. If PORT_IRQ_STAT register of rest ports is not equal to zero + * then update the state of HOST_IRQ_STAT saved in step 1. + * 6. Handle port interrupts. + * 7. Exit + */ +static int xgene_ahci_handle_broken_edge_irq(struct ata_host *host, + u32 irq_masked) +{ + struct ahci_host_priv *hpriv = host->private_data; + void __iomem *port_mmio; + int i; + + if (!readl(hpriv->mmio + HOST_IRQ_STAT)) { + for (i = 0; i < host->n_ports; i++) { + if (irq_masked & (1 << i)) + continue; + + port_mmio = ahci_port_base(host->ports[i]); + if (readl(port_mmio + PORT_IRQ_STAT)) + irq_masked |= (1 << i); + } + } + + return ahci_handle_port_intr(host, irq_masked); +} + static irqreturn_t xgene_ahci_irq_intr(int irq, void *dev_instance) { struct ata_host *host = dev_instance; @@ -576,7 +621,7 @@ static irqreturn_t xgene_ahci_irq_intr(int irq, void *dev_instance) */ writel(irq_stat, mmio + HOST_IRQ_STAT); - rc = ahci_handle_port_intr(host, irq_masked); + rc = xgene_ahci_handle_broken_edge_irq(host, irq_masked); spin_unlock(&host->lock); From 287e6611ab1eac76c2c5ebf6e345e04c80ca9c61 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 11 Feb 2016 14:16:27 +0100 Subject: [PATCH 024/417] libata: fix HDIO_GET_32BIT ioctl As reported by Soohoon Lee, the HDIO_GET_32BIT ioctl does not work correctly in compat mode with libata. I have investigated the issue further and found multiple problems that all appeared with the same commit that originally introduced HDIO_GET_32BIT handling in libata back in linux-2.6.8 and presumably also linux-2.4, as the code uses "copy_to_user(arg, &val, 1)" to copy a 'long' variable containing either 0 or 1 to user space. The problems with this are: * On big-endian machines, this will always write a zero because it stores the wrong byte into user space. * In compat mode, the upper three bytes of the variable are updated by the compat_hdio_ioctl() function, but they now contain uninitialized stack data. * The hdparm tool calling this ioctl uses a 'static long' variable to store the result. This means at least the upper bytes are initialized to zero, but calling another ioctl like HDIO_GET_MULTCOUNT would fill them with data that remains stale when the low byte is overwritten. Fortunately libata doesn't implement any of the affected ioctl commands, so this would only happen when we query both an IDE and an ATA device in the same command such as "hdparm -N -c /dev/hda /dev/sda" * The libata code for unknown reasons started using ATA_IOC_GET_IO32 and ATA_IOC_SET_IO32 as aliases for HDIO_GET_32BIT and HDIO_SET_32BIT, while the ioctl commands that were added later use the normal HDIO_* names. This is harmless but rather confusing. This addresses all four issues by changing the code to use put_user() on an 'unsigned long' variable in HDIO_GET_32BIT, like the IDE subsystem does, and by clarifying the names of the ioctl commands. Signed-off-by: Arnd Bergmann Reported-by: Soohoon Lee Tested-by: Soohoon Lee Cc: stable@vger.kernel.org Signed-off-by: Tejun Heo --- drivers/ata/libata-scsi.c | 11 +++++------ include/linux/ata.h | 4 ++-- 2 files changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 7e959f90c020..e417e1a1d02c 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -675,19 +675,18 @@ static int ata_ioc32(struct ata_port *ap) int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *scsidev, int cmd, void __user *arg) { - int val = -EINVAL, rc = -EINVAL; + unsigned long val; + int rc = -EINVAL; unsigned long flags; switch (cmd) { - case ATA_IOC_GET_IO32: + case HDIO_GET_32BIT: spin_lock_irqsave(ap->lock, flags); val = ata_ioc32(ap); spin_unlock_irqrestore(ap->lock, flags); - if (copy_to_user(arg, &val, 1)) - return -EFAULT; - return 0; + return put_user(val, (unsigned long __user *)arg); - case ATA_IOC_SET_IO32: + case HDIO_SET_32BIT: val = (unsigned long) arg; rc = 0; spin_lock_irqsave(ap->lock, flags); diff --git a/include/linux/ata.h b/include/linux/ata.h index d2992bfa1706..c1a2f345cbe6 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -487,8 +487,8 @@ enum ata_tf_protocols { }; enum ata_ioctls { - ATA_IOC_GET_IO32 = 0x309, - ATA_IOC_SET_IO32 = 0x324, + ATA_IOC_GET_IO32 = 0x309, /* HDIO_GET_32BIT */ + ATA_IOC_SET_IO32 = 0x324, /* HDIO_SET_32BIT */ }; /* core structures */ From 004fa08d7aba2a13974446bf212a48c0b3b0d9fd Mon Sep 17 00:00:00 2001 From: Ashok Kumar Date: Thu, 11 Feb 2016 05:38:53 -0800 Subject: [PATCH 025/417] irqchip/gic-v3-its: Fix double ICC_EOIR write for LPI in EOImode==1 When the GIC is using EOImode==1, the EOI is done immediately, leaving the deactivation to be performed when the EOI was previously done. Unfortunately, the ITS is not aware of the EOImode at all, and blindly EOIs the interrupt again. On most systems, this is ignored (despite being a programming error), but some others do raise a SError exception as there is no priority drop to perform for this interrupt. The fix is to stop trying to be clever, and always call into the underlying GIC to perform the right access, irrespective of the more we're in. [Marc: Reworked commit message] Fixes: 0b996fd35957a ("irqchip/GICv3: Convert to EOImode == 1") Cc: stable@vger.kernel.org Acked-by: Marc Zyngier Signed-off-by: Ashok Kumar Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3-its.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 0a73632b28d5..ff2be77a51f6 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -600,11 +600,6 @@ static void its_unmask_irq(struct irq_data *d) lpi_set_config(d, true); } -static void its_eoi_irq(struct irq_data *d) -{ - gic_write_eoir(d->hwirq); -} - static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val, bool force) { @@ -641,7 +636,7 @@ static struct irq_chip its_irq_chip = { .name = "ITS", .irq_mask = its_mask_irq, .irq_unmask = its_unmask_irq, - .irq_eoi = its_eoi_irq, + .irq_eoi = irq_chip_eoi_parent, .irq_set_affinity = its_set_affinity, .irq_compose_msi_msg = its_irq_compose_msi_msg, }; From 08c78e9d61a857c9077240e7ddb67550c6f96d06 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Fri, 12 Feb 2016 08:56:52 -0800 Subject: [PATCH 026/417] ARM: OMAP2+: Improve omap_device error for driver writers Drivers using pm_runtime_use_autosuspend() may not get disabled after -EPROBE_DEFER. On the following device driver probe, hardware state is different from the PM runtime state causing omap_device to produce the following error: omap_device_enable() called from invalid state 1 And with omap_device and omap hardware being picky for PM, this will block any deeper idle states in hardware. Let's add a proper error message so driver writers can easily fix their drivers for PM. In general, the solution is to fix the drivers to follow the PM runtime documentation: 1. For sections of code that needs the device disabled, use pm_runtime_put_sync_suspend() if pm_runtime_set_autosuspend() has been set. 2. For driver exit code, use pm_runtime_dont_use_autosuspend() before pm_runtime_put_sync() if pm_runtime_use_autosuspend() has been set. Let's not return with 0 from _od_runtime_resume() as that will eventually lead into new drivers with broken PM runtime that will block deeper idle states on omaps. Cc: Alan Stern Cc: Nishanth Menon Cc: Rafael J. Wysocki Cc: Tero Kristo Acked-by: Kevin Hilman Acked-by: Ulf Hansson Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/omap_device.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c index 0437537751bc..ebd83690ba48 100644 --- a/arch/arm/mach-omap2/omap_device.c +++ b/arch/arm/mach-omap2/omap_device.c @@ -602,8 +602,10 @@ static int _od_runtime_resume(struct device *dev) int ret; ret = omap_device_enable(pdev); - if (ret) + if (ret) { + dev_err(dev, "use pm_runtime_put_sync_suspend() in driver?\n"); return ret; + } return pm_generic_runtime_resume(dev); } From cf26f1137333251f3515dea31f95775b99df0fd5 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Fri, 12 Feb 2016 08:56:52 -0800 Subject: [PATCH 027/417] ARM: OMAP2+: Fix omap_device for module reload on PM runtime forbid If a driver PM runtime is disabled via sysfs, and the module is unloaded, PM runtime can't do anything to disable the device. Let's let the interconnect disable the device on BUS_NOTIFY_UNBOUND_DRIVER. Otherwise omap_device will produce and error on the following module reload. This can be easily tested with something like: # modprobe omap_hsmmc # echo on > /sys/devices/platform/68000000.ocp/4809c000.mmc/power/control # rmmod omap_hsmmc # modprobe omap_hsmmc Cc: Alan Stern Cc: Nishanth Menon Cc: Rafael J. Wysocki Cc: Tero Kristo Reported-by: Ulf Hansson Acked-by: Kevin Hilman Acked-by: Ulf Hansson Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/omap_device.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c index ebd83690ba48..f7ff3b9dad87 100644 --- a/arch/arm/mach-omap2/omap_device.c +++ b/arch/arm/mach-omap2/omap_device.c @@ -191,12 +191,22 @@ static int _omap_device_notifier_call(struct notifier_block *nb, { struct platform_device *pdev = to_platform_device(dev); struct omap_device *od; + int err; switch (event) { case BUS_NOTIFY_DEL_DEVICE: if (pdev->archdata.od) omap_device_delete(pdev->archdata.od); break; + case BUS_NOTIFY_UNBOUND_DRIVER: + od = to_omap_device(pdev); + if (od && (od->_state == OMAP_DEVICE_STATE_ENABLED)) { + dev_info(dev, "enabled after unload, idling\n"); + err = omap_device_idle(pdev); + if (err) + dev_err(dev, "failed to idle\n"); + } + break; case BUS_NOTIFY_ADD_DEVICE: if (pdev->dev.of_node) omap_device_build_from_dt(pdev); From 38714fbd299f992080a11b977f609136ec8530c2 Mon Sep 17 00:00:00 2001 From: Han Xu Date: Fri, 12 Feb 2016 05:13:25 +0000 Subject: [PATCH 028/417] MAINTAINERS: update Han's email Update my email address from freescale to nxp. Signed-off-by: Han Xu Signed-off-by: Brian Norris --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 30aca4aa5467..ce4a0d6e3d64 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4538,7 +4538,7 @@ F: include/linux/platform_data/video-imxfb.h F: drivers/video/fbdev/imxfb.c FREESCALE QUAD SPI DRIVER -M: Han Xu +M: Han Xu L: linux-mtd@lists.infradead.org S: Maintained F: drivers/mtd/spi-nor/fsl-quadspi.c From 814a3c0c2a8dfad97089f6bdc71b374f6076490e Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Wed, 10 Feb 2016 15:02:44 -0800 Subject: [PATCH 029/417] mmc: omap_hsmmc: Fix PM regression with deferred probe for pm_runtime_reinit Commit 5de85b9d57ab ("PM / runtime: Re-init runtime PM states at probe error and driver unbind") introduced pm_runtime_reinit() that is used to reinitialize PM runtime after -EPROBE_DEFER. This allows shutting down the device after a failed probe. However, for drivers using pm_runtime_use_autosuspend() this can cause a state where suspend callback is never called after -EPROBE_DEFER. On the following device driver probe, hardware state is different from the PM runtime state causing omap_device to produce the following error: omap_device_enable() called from invalid state 1 And with omap_device and omap hardware being picky for PM, this will block any deeper idle states in hardware. The solution is to fix the drivers to follow the PM runtime documentation: 1. For sections of code that needs the device disabled, use pm_runtime_put_sync_suspend() if pm_runtime_set_autosuspend() has been set. 2. For driver exit code, use pm_runtime_dont_use_autosuspend() before pm_runtime_put_sync() if pm_runtime_use_autosuspend() has been set. Fixes: 5de85b9d57ab ("PM / runtime: Re-init runtime PM states at probe error and driver unbind") Cc: linux-mmc@vger.kernel.org Cc: Alan Stern Cc: Kevin Hilman Cc: Nishanth Menon Cc: Rafael J. Wysocki Cc: Ulf Hansson Cc: Tero Kristo Signed-off-by: Tony Lindgren Signed-off-by: Ulf Hansson --- drivers/mmc/host/omap_hsmmc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index b6639ea0bf18..f6e4d9718035 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -2232,6 +2232,7 @@ static int omap_hsmmc_probe(struct platform_device *pdev) dma_release_channel(host->tx_chan); if (host->rx_chan) dma_release_channel(host->rx_chan); + pm_runtime_dont_use_autosuspend(host->dev); pm_runtime_put_sync(host->dev); pm_runtime_disable(host->dev); if (host->dbclk) @@ -2253,6 +2254,7 @@ static int omap_hsmmc_remove(struct platform_device *pdev) dma_release_channel(host->tx_chan); dma_release_channel(host->rx_chan); + pm_runtime_dont_use_autosuspend(host->dev); pm_runtime_put_sync(host->dev); pm_runtime_disable(host->dev); device_init_wakeup(&pdev->dev, false); From 85c0a87cd117e83361932b2b160c9af178fdb21a Mon Sep 17 00:00:00 2001 From: Insu Yun Date: Mon, 18 Jan 2016 11:54:43 -0500 Subject: [PATCH 030/417] xen: fix potential integer overflow in queue_reply When len is greater than UINT_MAX - sizeof(*rb), in next allocation, it can overflow integer range and allocates small size of heap. After that, memcpy will overflow the allocated heap. Therefore, it needs to check the size of given length. Signed-off-by: Insu Yun Signed-off-by: David Vrabel --- drivers/xen/xenbus/xenbus_dev_frontend.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 9433e46518c8..912b64edb42b 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -188,6 +188,8 @@ static int queue_reply(struct list_head *queue, const void *data, size_t len) if (len == 0) return 0; + if (len > XENSTORE_PAYLOAD_MAX) + return -EINVAL; rb = kmalloc(sizeof(*rb) + len, GFP_KERNEL); if (rb == NULL) From 8d47065f7d1980dde52abb874b301054f3013602 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Thu, 11 Feb 2016 16:10:23 -0500 Subject: [PATCH 031/417] xen/pciback: Check PF instead of VF for PCI_COMMAND_MEMORY Commit 408fb0e5aa7fda0059db282ff58c3b2a4278baa0 (xen/pciback: Don't allow MSI-X ops if PCI_COMMAND_MEMORY is not set) prevented enabling MSI-X on passed-through virtual functions, because it checked the VF for PCI_COMMAND_MEMORY but this is not a valid bit for VFs. Instead, check the physical function for PCI_COMMAND_MEMORY. Signed-off-by: Konrad Rzeszutek Wilk Cc: Reviewed-by: Jan Beulich Signed-off-by: David Vrabel --- drivers/xen/xen-pciback/pciback_ops.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/xen/xen-pciback/pciback_ops.c b/drivers/xen/xen-pciback/pciback_ops.c index 73dafdc494aa..1078e8d631c9 100644 --- a/drivers/xen/xen-pciback/pciback_ops.c +++ b/drivers/xen/xen-pciback/pciback_ops.c @@ -227,8 +227,9 @@ int xen_pcibk_enable_msix(struct xen_pcibk_device *pdev, /* * PCI_COMMAND_MEMORY must be enabled, otherwise we may not be able * to access the BARs where the MSI-X entries reside. + * But VF devices are unique in which the PF needs to be checked. */ - pci_read_config_word(dev, PCI_COMMAND, &cmd); + pci_read_config_word(pci_physfn(dev), PCI_COMMAND, &cmd); if (dev->msi_enabled || !(cmd & PCI_COMMAND_MEMORY)) return -ENXIO; From d159457b84395927b5a52adb72f748dd089ad5e5 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Thu, 11 Feb 2016 16:10:24 -0500 Subject: [PATCH 032/417] xen/pciback: Save the number of MSI-X entries to be copied later. Commit 8135cf8b092723dbfcc611fe6fdcb3a36c9951c5 (xen/pciback: Save xen_pci_op commands before processing it) broke enabling MSI-X because it would never copy the resulting vectors into the response. The number of vectors requested was being overwritten by the return value (typically zero for success). Save the number of vectors before processing the op, so the correct number of vectors are copied afterwards. Signed-off-by: Konrad Rzeszutek Wilk Cc: Reviewed-by: Jan Beulich Signed-off-by: David Vrabel --- drivers/xen/xen-pciback/pciback_ops.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/xen/xen-pciback/pciback_ops.c b/drivers/xen/xen-pciback/pciback_ops.c index 1078e8d631c9..fb0221434f81 100644 --- a/drivers/xen/xen-pciback/pciback_ops.c +++ b/drivers/xen/xen-pciback/pciback_ops.c @@ -333,6 +333,9 @@ void xen_pcibk_do_op(struct work_struct *data) struct xen_pcibk_dev_data *dev_data = NULL; struct xen_pci_op *op = &pdev->op; int test_intx = 0; +#ifdef CONFIG_PCI_MSI + unsigned int nr = 0; +#endif *op = pdev->sh_info->op; barrier(); @@ -361,6 +364,7 @@ void xen_pcibk_do_op(struct work_struct *data) op->err = xen_pcibk_disable_msi(pdev, dev, op); break; case XEN_PCI_OP_enable_msix: + nr = op->value; op->err = xen_pcibk_enable_msix(pdev, dev, op); break; case XEN_PCI_OP_disable_msix: @@ -383,7 +387,7 @@ void xen_pcibk_do_op(struct work_struct *data) if (op->cmd == XEN_PCI_OP_enable_msix && op->err == 0) { unsigned int i; - for (i = 0; i < op->value; i++) + for (i = 0; i < nr; i++) pdev->sh_info->op.msix_entries[i].vector = op->msix_entries[i].vector; } From 2cfec6a2f989d5c921ba11a329ff8ea986702b9b Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Thu, 11 Feb 2016 16:10:25 -0500 Subject: [PATCH 033/417] xen/pcifront: Report the errors better. The messages should be different depending on the type of error. Signed-off-by: Konrad Rzeszutek Wilk Signed-off-by: David Vrabel --- arch/x86/include/asm/xen/pci.h | 4 ++-- arch/x86/pci/xen.c | 5 ++++- 2 files changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h index 968d57dd54c9..f320ee32d5a1 100644 --- a/arch/x86/include/asm/xen/pci.h +++ b/arch/x86/include/asm/xen/pci.h @@ -57,7 +57,7 @@ static inline int xen_pci_frontend_enable_msi(struct pci_dev *dev, { if (xen_pci_frontend && xen_pci_frontend->enable_msi) return xen_pci_frontend->enable_msi(dev, vectors); - return -ENODEV; + return -ENOSYS; } static inline void xen_pci_frontend_disable_msi(struct pci_dev *dev) { @@ -69,7 +69,7 @@ static inline int xen_pci_frontend_enable_msix(struct pci_dev *dev, { if (xen_pci_frontend && xen_pci_frontend->enable_msix) return xen_pci_frontend->enable_msix(dev, vectors, nvec); - return -ENODEV; + return -ENOSYS; } static inline void xen_pci_frontend_disable_msix(struct pci_dev *dev) { diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index ff31ab464213..beac4dfdade6 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -196,7 +196,10 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) return 0; error: - dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n"); + if (ret == -ENOSYS) + dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n"); + else if (ret) + dev_err(&dev->dev, "Xen PCI frontend error: %d!\n", ret); free: kfree(v); return ret; From 4d8c8bd6f2062c9988817183a91fe2e623c8aa5e Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Thu, 11 Feb 2016 16:10:26 -0500 Subject: [PATCH 034/417] xen/pcifront: Fix mysterious crashes when NUMA locality information was extracted. Occasionaly PV guests would crash with: pciback 0000:00:00.1: Xen PCI mapped GSI0 to IRQ16 BUG: unable to handle kernel paging request at 0000000d1a8c0be0 .. snip.. ] find_next_bit+0xb/0x10 [] cpumask_next_and+0x22/0x40 [] pci_device_probe+0xb8/0x120 [] ? driver_sysfs_add+0x77/0xa0 [] driver_probe_device+0x1a4/0x2d0 [] ? pci_match_device+0xdd/0x110 [] __device_attach_driver+0xa7/0xb0 [] ? __driver_attach+0xa0/0xa0 [] bus_for_each_drv+0x62/0x90 [] __device_attach+0xbd/0x110 [] device_attach+0xb/0x10 [] pci_bus_add_device+0x3c/0x70 [] pci_bus_add_devices+0x38/0x80 [] pcifront_scan_root+0x13e/0x1a0 [] pcifront_backend_changed+0x262/0x60b [] ? xenbus_gather+0xd6/0x160 [] ? put_object+0x2f/0x50 [] xenbus_otherend_changed+0x9d/0xa0 [] backend_changed+0xe/0x10 [] xenwatch_thread+0xc8/0x190 [] ? woken_wake_function+0x10/0x10 which was the result of two things: When we call pci_scan_root_bus we would pass in 'sd' (sysdata) pointer which was an 'pcifront_sd' structure. However in the pci_device_add it expects that the 'sd' is 'struct sysdata' and sets the dev->node to what is in sd->node (offset 4): set_dev_node(&dev->dev, pcibus_to_node(bus)); __pcibus_to_node(const struct pci_bus *bus) { const struct pci_sysdata *sd = bus->sysdata; return sd->node; } However our structure was pcifront_sd which had nothing at that offset: struct pcifront_sd { int domain; /* 0 4 */ /* XXX 4 bytes hole, try to pack */ struct pcifront_device * pdev; /* 8 8 */ } That is an hole - filled with garbage as we used kmalloc instead of kzalloc (the second problem). This patch fixes the issue by: 1) Use kzalloc to initialize to a well known state. 2) Put 'struct pci_sysdata' at the start of 'pcifront_sd'. That way access to the 'node' will access the right offset. Signed-off-by: Konrad Rzeszutek Wilk Cc: Reviewed-by: Boris Ostrovsky Signed-off-by: David Vrabel --- drivers/pci/xen-pcifront.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index c777b97207d5..5f70fee59a94 100644 --- a/drivers/pci/xen-pcifront.c +++ b/drivers/pci/xen-pcifront.c @@ -53,7 +53,7 @@ struct pcifront_device { }; struct pcifront_sd { - int domain; + struct pci_sysdata sd; struct pcifront_device *pdev; }; @@ -67,7 +67,9 @@ static inline void pcifront_init_sd(struct pcifront_sd *sd, unsigned int domain, unsigned int bus, struct pcifront_device *pdev) { - sd->domain = domain; + /* Because we do not expose that information via XenBus. */ + sd->sd.node = first_online_node; + sd->sd.domain = domain; sd->pdev = pdev; } @@ -468,8 +470,8 @@ static int pcifront_scan_root(struct pcifront_device *pdev, dev_info(&pdev->xdev->dev, "Creating PCI Frontend Bus %04x:%02x\n", domain, bus); - bus_entry = kmalloc(sizeof(*bus_entry), GFP_KERNEL); - sd = kmalloc(sizeof(*sd), GFP_KERNEL); + bus_entry = kzalloc(sizeof(*bus_entry), GFP_KERNEL); + sd = kzalloc(sizeof(*sd), GFP_KERNEL); if (!bus_entry || !sd) { err = -ENOMEM; goto err_out; From 2f21596882f4a0edc387051910d56f8732970080 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 15 Feb 2016 12:36:04 -0500 Subject: [PATCH 035/417] pNFS: Fix pnfs_mark_matching_lsegs_return() We don't need to schedule a layoutreturn if the layout segment can be freed immediately. Signed-off-by: Trond Myklebust --- fs/nfs/pnfs.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 482b6e94bb37..8d9fa4e40e89 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1740,6 +1740,16 @@ pnfs_set_plh_return_iomode(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode) lo->plh_return_iomode = iomode; } +/** + * pnfs_mark_matching_lsegs_return - Free or return matching layout segments + * @lo: pointer to layout header + * @tmp_list: list header to be used with pnfs_free_lseg_list() + * @return_range: describe layout segment ranges to be returned + * + * This function is mainly intended for use by layoutrecall. It attempts + * to free the layout segment immediately, or else to mark it for return + * as soon as its reference count drops to zero. + */ int pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, struct list_head *tmp_list, @@ -1762,10 +1772,11 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, lseg, lseg->pls_range.iomode, lseg->pls_range.offset, lseg->pls_range.length); + if (mark_lseg_invalid(lseg, tmp_list)) + continue; + remaining++; set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags); pnfs_set_plh_return_iomode(lo, return_range->iomode); - if (!mark_lseg_invalid(lseg, tmp_list)) - remaining++; set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags); } From e0fa0d0189f6be61343dbff1f71bef20125576e7 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 15 Feb 2016 12:56:17 -0500 Subject: [PATCH 036/417] pNFS: Always set NFS_LAYOUT_RETURN_REQUESTED with lo->plh_return_iomode When setting the layout return mode, we must always also set the NFS_LAYOUT_RETURN_REQUESTED flag to ensure that we send a layoutreturn. Otherwise pnfs_error_mark_layout_for_return() could set the mode, but fail to send the layoutreturn because another is already in flight. Signed-off-by: Trond Myklebust --- fs/nfs/pnfs.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 8d9fa4e40e89..5064f23ca8cc 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1738,6 +1738,7 @@ pnfs_set_plh_return_iomode(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode) if (lo->plh_return_iomode != 0) iomode = IOMODE_ANY; lo->plh_return_iomode = iomode; + set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags); } /** @@ -1777,8 +1778,6 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, remaining++; set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags); pnfs_set_plh_return_iomode(lo, return_range->iomode); - set_bit(NFS_LAYOUT_RETURN_REQUESTED, - &lo->plh_flags); } return remaining; } From fb896c44f88a75843a072cd6961b1615732f7811 Mon Sep 17 00:00:00 2001 From: Liad Kaufman Date: Sun, 14 Feb 2016 15:32:58 +0200 Subject: [PATCH 037/417] iwlwifi: mvm: inc pending frames counter also when txing non-sta Until this patch, when TXing non-sta the pending_frames counter wasn't increased, but it WAS decreased in iwl_mvm_rx_tx_cmd_single(), what makes it negative in certain conditions. This in turn caused much trouble when we need to remove the station since we won't be waiting forever until pending_frames gets 0. In certain cases, we were exhausting the station table even in BSS mode, because we had a lot of stale stations. Increase the counter also in iwl_mvm_tx_skb_non_sta() after a successful TX to avoid this outcome. CC: [3.18+] Signed-off-by: Liad Kaufman Signed-off-by: Emmanuel Grumbach --- drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 0914ec2fd574..a040edc55057 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -423,6 +423,15 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb) return -1; } + /* + * Increase the pending frames counter, so that later when a reply comes + * in and the counter is decreased - we don't start getting negative + * values. + * Note that we don't need to make sure it isn't agg'd, since we're + * TXing non-sta + */ + atomic_inc(&mvm->pending_frames[sta_id]); + return 0; } From 1f4522400e7e49464da5e584a463bd315283790f Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 11 Feb 2016 12:28:55 -0200 Subject: [PATCH 038/417] [media] [for,v4.5] media.h: increase the spacing between function ranges Each function range is quite narrow and especially for connectors this will pose a problem. Increase the function ranges while we still can and move the connector range to the end so that range is practically limitless. [mchehab@osg.samsung.com: Rebased to apply at Linus tree] Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/media.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index 1e3c8cb43bd7..8b87bddecf1c 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -71,22 +71,22 @@ struct media_device_info { #define MEDIA_ENT_F_DTV_CA (MEDIA_ENT_F_BASE + 3) #define MEDIA_ENT_F_DTV_NET_DECAP (MEDIA_ENT_F_BASE + 4) +/* + * I/O entities + */ +#define MEDIA_ENT_F_IO_DTV (MEDIA_ENT_F_BASE + 1001) +#define MEDIA_ENT_F_IO_VBI (MEDIA_ENT_F_BASE + 1002) +#define MEDIA_ENT_F_IO_SWRADIO (MEDIA_ENT_F_BASE + 1003) + /* * Connectors */ /* It is a responsibility of the entity drivers to add connectors and links */ -#define MEDIA_ENT_F_CONN_RF (MEDIA_ENT_F_BASE + 21) -#define MEDIA_ENT_F_CONN_SVIDEO (MEDIA_ENT_F_BASE + 22) -#define MEDIA_ENT_F_CONN_COMPOSITE (MEDIA_ENT_F_BASE + 23) +#define MEDIA_ENT_F_CONN_RF (MEDIA_ENT_F_BASE + 10001) +#define MEDIA_ENT_F_CONN_SVIDEO (MEDIA_ENT_F_BASE + 10002) +#define MEDIA_ENT_F_CONN_COMPOSITE (MEDIA_ENT_F_BASE + 10003) /* For internal test signal generators and other debug connectors */ -#define MEDIA_ENT_F_CONN_TEST (MEDIA_ENT_F_BASE + 24) - -/* - * I/O entities - */ -#define MEDIA_ENT_F_IO_DTV (MEDIA_ENT_F_BASE + 31) -#define MEDIA_ENT_F_IO_VBI (MEDIA_ENT_F_BASE + 32) -#define MEDIA_ENT_F_IO_SWRADIO (MEDIA_ENT_F_BASE + 33) +#define MEDIA_ENT_F_CONN_TEST (MEDIA_ENT_F_BASE + 10004) /* * Don't touch on those. The ranges MEDIA_ENT_F_OLD_BASE and From 9727a9545adec59f4bccb83d1a709711f4acf242 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 12 Feb 2016 15:44:31 -0200 Subject: [PATCH 039/417] [media] media.h: get rid of MEDIA_ENT_F_CONN_TEST Defining it as a connector was a bad idea. Remove it while it is not too late. Signed-off-by: Mauro Carvalho Chehab --- Documentation/DocBook/media/v4l/media-types.xml | 4 ---- drivers/media/usb/au0828/au0828-video.c | 3 +-- include/uapi/linux/media.h | 2 -- 3 files changed, 1 insertion(+), 8 deletions(-) diff --git a/Documentation/DocBook/media/v4l/media-types.xml b/Documentation/DocBook/media/v4l/media-types.xml index 1af384250910..0ee0f3386cdf 100644 --- a/Documentation/DocBook/media/v4l/media-types.xml +++ b/Documentation/DocBook/media/v4l/media-types.xml @@ -56,10 +56,6 @@ MEDIA_ENT_F_CONN_COMPOSITE Connector for a RGB composite signal. - - MEDIA_ENT_F_CONN_TEST - Connector for a test generator. - MEDIA_ENT_F_CAM_SENSOR Camera video sensor entity. diff --git a/drivers/media/usb/au0828/au0828-video.c b/drivers/media/usb/au0828/au0828-video.c index 8c54fd21022e..a13625722848 100644 --- a/drivers/media/usb/au0828/au0828-video.c +++ b/drivers/media/usb/au0828/au0828-video.c @@ -1843,8 +1843,7 @@ static void au0828_analog_create_entities(struct au0828_dev *dev) ent->function = MEDIA_ENT_F_CONN_RF; break; default: /* AU0828_VMUX_DEBUG */ - ent->function = MEDIA_ENT_F_CONN_TEST; - break; + continue; } ret = media_entity_pads_init(ent, 1, &dev->input_pad[i]); diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index 8b87bddecf1c..f0328524be6e 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -85,8 +85,6 @@ struct media_device_info { #define MEDIA_ENT_F_CONN_RF (MEDIA_ENT_F_BASE + 10001) #define MEDIA_ENT_F_CONN_SVIDEO (MEDIA_ENT_F_BASE + 10002) #define MEDIA_ENT_F_CONN_COMPOSITE (MEDIA_ENT_F_BASE + 10003) -/* For internal test signal generators and other debug connectors */ -#define MEDIA_ENT_F_CONN_TEST (MEDIA_ENT_F_BASE + 10004) /* * Don't touch on those. The ranges MEDIA_ENT_F_OLD_BASE and From 0ba4581c84cfb39fd527f6b3457f1c97f6356c04 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 10 Feb 2016 08:09:10 -0200 Subject: [PATCH 040/417] [media] adv7604: fix tx 5v detect regression The 5 volt detect functionality broke in 3.14: the code reads IO register 0x70 again after it has already been cleared. Instead it should use the cached irq_reg_0x70 value and the io_write to 0x71 to clear 0x70 can be dropped since this has already been done. Signed-off-by: Hans Verkuil Cc: # for v3.14 and up Signed-off-by: Mauro Carvalho Chehab --- drivers/media/i2c/adv7604.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c index f8dd7505b529..e1719ffdfb3d 100644 --- a/drivers/media/i2c/adv7604.c +++ b/drivers/media/i2c/adv7604.c @@ -1960,10 +1960,9 @@ static int adv76xx_isr(struct v4l2_subdev *sd, u32 status, bool *handled) } /* tx 5v detect */ - tx_5v = io_read(sd, 0x70) & info->cable_det_mask; + tx_5v = irq_reg_0x70 & info->cable_det_mask; if (tx_5v) { v4l2_dbg(1, debug, sd, "%s: tx_5v: 0x%x\n", __func__, tx_5v); - io_write(sd, 0x71, tx_5v); adv76xx_s_detect_tx_5v_ctrl(sd); if (handled) *handled = true; From bd84f4ae9986ac9acd278566ccb39c60bc961abb Mon Sep 17 00:00:00 2001 From: John Youn Date: Mon, 15 Feb 2016 15:30:20 -0800 Subject: [PATCH 041/417] usb: dwc2: Add extra delay when forcing dr_mode Fixes an issue found on rockchip rk3036 and rk3188 SOC platforms. For some reason, the existing msleep(25) is not enough after the force mode. The following patch was reported to fix the issue. This does increase the probe delay again slightly, but not up to the level it was before the original series of patches that this fixes. It does not cause any other issues when tested on Synopsys HAPS and Altera socfpga platforms. Need to revisit this series next release to see if we can address these issues without having an unconditional delay. Fixes: 09c96980dc72 ("usb: dwc2: Add functions to set and clear force mode") Reported-by: Caesar Wang Reported-by: Michael Niewoehner Tested-by: Heiko Stuebner Tested-by: Caesar Wang Signed-off-by: John Youn Signed-off-by: Felipe Balbi --- drivers/usb/dwc2/core.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/usb/dwc2/core.c b/drivers/usb/dwc2/core.c index e991d55914db..46c4ba75dc2a 100644 --- a/drivers/usb/dwc2/core.c +++ b/drivers/usb/dwc2/core.c @@ -619,6 +619,12 @@ void dwc2_force_dr_mode(struct dwc2_hsotg *hsotg) __func__, hsotg->dr_mode); break; } + + /* + * NOTE: This is required for some rockchip soc based + * platforms. + */ + msleep(50); } /* From c450960187f45d4260db87c7dd4fc0bceb5565d8 Mon Sep 17 00:00:00 2001 From: John Youn Date: Tue, 16 Feb 2016 20:10:53 -0800 Subject: [PATCH 042/417] usb: dwc3: Fix assignment of EP transfer resources The assignement of EP transfer resources was not handled properly in the dwc3 driver. Commit aebda6187181 ("usb: dwc3: Reset the transfer resource index on SET_INTERFACE") previously fixed one aspect of this where resources may be exhausted with multiple calls to SET_INTERFACE. However, it introduced an issue where composite devices with multiple interfaces can be assigned the same transfer resources for different endpoints. This patch solves both issues. The assignment of transfer resources cannot perfectly follow the data book due to the fact that the controller driver does not have all knowledge of the configuration in advance. It is given this information piecemeal by the composite gadget framework after every SET_CONFIGURATION and SET_INTERFACE. Trying to follow the databook programming model in this scenario can cause errors. For two reasons: 1) The databook says to do DEPSTARTCFG for every SET_CONFIGURATION and SET_INTERFACE (8.1.5). This is incorrect in the scenario of multiple interfaces. 2) The databook does not mention doing more DEPXFERCFG for new endpoint on alt setting (8.1.6). The following simplified method is used instead: All hardware endpoints can be assigned a transfer resource and this setting will stay persistent until either a core reset or hibernation. So whenever we do a DEPSTARTCFG(0) we can go ahead and do DEPXFERCFG for every hardware endpoint as well. We are guaranteed that there are as many transfer resources as endpoints. This patch triggers off of the calling dwc3_gadget_start_config() for EP0-out, which always happens first, and which should only happen in one of the above conditions. Fixes: aebda6187181 ("usb: dwc3: Reset the transfer resource index on SET_INTERFACE") Cc: # v3.2+ Reported-by: Ravi Babu Signed-off-by: John Youn Signed-off-by: Felipe Balbi --- drivers/usb/dwc3/core.h | 1 - drivers/usb/dwc3/ep0.c | 5 --- drivers/usb/dwc3/gadget.c | 70 +++++++++++++++++++++++++++++---------- 3 files changed, 52 insertions(+), 24 deletions(-) diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 29130682e547..e4f8b90d9627 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -856,7 +856,6 @@ struct dwc3 { unsigned pullups_connected:1; unsigned resize_fifos:1; unsigned setup_packet_pending:1; - unsigned start_config_issued:1; unsigned three_stage_setup:1; unsigned usb3_lpm_capable:1; diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index 3a9354abcb68..8d6b75c2f53b 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -555,7 +555,6 @@ static int dwc3_ep0_set_config(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl) int ret; u32 reg; - dwc->start_config_issued = false; cfg = le16_to_cpu(ctrl->wValue); switch (state) { @@ -737,10 +736,6 @@ static int dwc3_ep0_std_request(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl) dwc3_trace(trace_dwc3_ep0, "USB_REQ_SET_ISOCH_DELAY"); ret = dwc3_ep0_set_isoch_delay(dwc, ctrl); break; - case USB_REQ_SET_INTERFACE: - dwc3_trace(trace_dwc3_ep0, "USB_REQ_SET_INTERFACE"); - dwc->start_config_issued = false; - /* Fall through */ default: dwc3_trace(trace_dwc3_ep0, "Forwarding to gadget driver"); ret = dwc3_ep0_delegate_req(dwc, ctrl); diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 7d1dd82a95ac..2363bad45af8 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -385,24 +385,66 @@ static void dwc3_free_trb_pool(struct dwc3_ep *dep) dep->trb_pool_dma = 0; } +static int dwc3_gadget_set_xfer_resource(struct dwc3 *dwc, struct dwc3_ep *dep); + +/** + * dwc3_gadget_start_config - Configure EP resources + * @dwc: pointer to our controller context structure + * @dep: endpoint that is being enabled + * + * The assignment of transfer resources cannot perfectly follow the + * data book due to the fact that the controller driver does not have + * all knowledge of the configuration in advance. It is given this + * information piecemeal by the composite gadget framework after every + * SET_CONFIGURATION and SET_INTERFACE. Trying to follow the databook + * programming model in this scenario can cause errors. For two + * reasons: + * + * 1) The databook says to do DEPSTARTCFG for every SET_CONFIGURATION + * and SET_INTERFACE (8.1.5). This is incorrect in the scenario of + * multiple interfaces. + * + * 2) The databook does not mention doing more DEPXFERCFG for new + * endpoint on alt setting (8.1.6). + * + * The following simplified method is used instead: + * + * All hardware endpoints can be assigned a transfer resource and this + * setting will stay persistent until either a core reset or + * hibernation. So whenever we do a DEPSTARTCFG(0) we can go ahead and + * do DEPXFERCFG for every hardware endpoint as well. We are + * guaranteed that there are as many transfer resources as endpoints. + * + * This function is called for each endpoint when it is being enabled + * but is triggered only when called for EP0-out, which always happens + * first, and which should only happen in one of the above conditions. + */ static int dwc3_gadget_start_config(struct dwc3 *dwc, struct dwc3_ep *dep) { struct dwc3_gadget_ep_cmd_params params; u32 cmd; + int i; + int ret; + + if (dep->number) + return 0; memset(¶ms, 0x00, sizeof(params)); + cmd = DWC3_DEPCMD_DEPSTARTCFG; - if (dep->number != 1) { - cmd = DWC3_DEPCMD_DEPSTARTCFG; - /* XferRscIdx == 0 for ep0 and 2 for the remaining */ - if (dep->number > 1) { - if (dwc->start_config_issued) - return 0; - dwc->start_config_issued = true; - cmd |= DWC3_DEPCMD_PARAM(2); - } + ret = dwc3_send_gadget_ep_cmd(dwc, 0, cmd, ¶ms); + if (ret) + return ret; - return dwc3_send_gadget_ep_cmd(dwc, 0, cmd, ¶ms); + for (i = 0; i < DWC3_ENDPOINTS_NUM; i++) { + struct dwc3_ep *dep = dwc->eps[i]; + + if (!dep) + continue; + + ret = dwc3_gadget_set_xfer_resource(dwc, dep); + if (ret) + return ret; } return 0; @@ -516,10 +558,6 @@ static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep, struct dwc3_trb *trb_st_hw; struct dwc3_trb *trb_link; - ret = dwc3_gadget_set_xfer_resource(dwc, dep); - if (ret) - return ret; - dep->endpoint.desc = desc; dep->comp_desc = comp_desc; dep->type = usb_endpoint_type(desc); @@ -1636,8 +1674,6 @@ static int dwc3_gadget_start(struct usb_gadget *g, } dwc3_writel(dwc->regs, DWC3_DCFG, reg); - dwc->start_config_issued = false; - /* Start with SuperSpeed Default */ dwc3_gadget_ep0_desc.wMaxPacketSize = cpu_to_le16(512); @@ -2237,7 +2273,6 @@ static void dwc3_gadget_disconnect_interrupt(struct dwc3 *dwc) dwc3_writel(dwc->regs, DWC3_DCTL, reg); dwc3_disconnect_gadget(dwc); - dwc->start_config_issued = false; dwc->gadget.speed = USB_SPEED_UNKNOWN; dwc->setup_packet_pending = false; @@ -2288,7 +2323,6 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc) dwc3_stop_active_transfers(dwc); dwc3_clear_stall_all_ep(dwc); - dwc->start_config_issued = false; /* Reset device address to zero */ reg = dwc3_readl(dwc->regs, DWC3_DCFG); From 3142a16b9816c24501103a92010a283eb6e2766c Mon Sep 17 00:00:00 2001 From: Vardan Mikayelyan Date: Tue, 16 Feb 2016 15:01:53 -0800 Subject: [PATCH 043/417] usb: dwc2: host: fix logical omissions in dwc2_process_non_isoc_desc Fixes memory manipulation issues and makes Host DDMA bulk transfers work. dwc2_process_non_isoc_desc() must return non zero value ONLY when failure happens in one of the queued descriptors. After receiving non zero value the caller must stop processing of remaining QTDs and their descriptors from chain. Commit 26a19ea699060fde ("usb: dwc2: host: fix use of qtd after free in desc dma mode") breaks non_isoc transaction completion logic in Host DDMA mode. There were bugs before that, but after this patch dwc2_process_non_isoc_desc() returns fail status even if descriptor was processed normally. This causes break from loop which is processing remaining descriptors assigned to QTD, which is not correct for QTDs containing more than one descriptor. Current dwc2 driver gathers queued BULK URBs until receiving URB without URB_NO_INTERRUPT flag. Once getting it, SW creates descriptor chain, stores it in qh structure and passes start address to HW. Multiple URB data is contained in that chain. Hence on getting error on descriptor after its processing by HW, SW should go out of both loops(qh->qtd, qtd->descs) and report the failure. Fixes: 26a19ea699060fde ("usb: dwc2: host: fix use of qtd after free in desc dma mode") Cc: Gregory Herrero Signed-off-by: Vardan Mikayelyan Signed-off-by: John Youn Signed-off-by: Felipe Balbi --- drivers/usb/dwc2/hcd_ddma.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) diff --git a/drivers/usb/dwc2/hcd_ddma.c b/drivers/usb/dwc2/hcd_ddma.c index 36606fc33c0d..89db47a1ffed 100644 --- a/drivers/usb/dwc2/hcd_ddma.c +++ b/drivers/usb/dwc2/hcd_ddma.c @@ -1174,14 +1174,11 @@ static int dwc2_process_non_isoc_desc(struct dwc2_hsotg *hsotg, failed = dwc2_update_non_isoc_urb_state_ddma(hsotg, chan, qtd, dma_desc, halt_status, n_bytes, xfer_done); - if (*xfer_done && urb->status != -EINPROGRESS) - failed = 1; - - if (failed) { + if (failed || (*xfer_done && urb->status != -EINPROGRESS)) { dwc2_host_complete(hsotg, qtd, urb->status); dwc2_hcd_qtd_unlink_and_free(hsotg, qtd, qh); - dev_vdbg(hsotg->dev, "failed=%1x xfer_done=%1x status=%08x\n", - failed, *xfer_done, urb->status); + dev_vdbg(hsotg->dev, "failed=%1x xfer_done=%1x\n", + failed, *xfer_done); return failed; } @@ -1236,21 +1233,23 @@ static void dwc2_complete_non_isoc_xfer_ddma(struct dwc2_hsotg *hsotg, list_for_each_safe(qtd_item, qtd_tmp, &qh->qtd_list) { int i; + int qtd_desc_count; qtd = list_entry(qtd_item, struct dwc2_qtd, qtd_list_entry); xfer_done = 0; + qtd_desc_count = qtd->n_desc; - for (i = 0; i < qtd->n_desc; i++) { + for (i = 0; i < qtd_desc_count; i++) { if (dwc2_process_non_isoc_desc(hsotg, chan, chnum, qtd, desc_num, halt_status, - &xfer_done)) { - qtd = NULL; - break; - } + &xfer_done)) + goto stop_scan; + desc_num++; } } +stop_scan: if (qh->ep_type != USB_ENDPOINT_XFER_CONTROL) { /* * Resetting the data toggle for bulk and interrupt endpoints From 62943b7dfa35887a40f71f698deec4488bf73036 Mon Sep 17 00:00:00 2001 From: "Tang, Jianqiang" Date: Tue, 16 Feb 2016 15:02:07 -0800 Subject: [PATCH 044/417] usb: dwc2: host: fix the data toggle error in full speed descriptor dma There will be data toggle error happen for full speed buld-out transfer. The data toggle bit is saved in qh for non-control transfers, it is wrong to check the qtd for that case. Also fix one static analysis tool issue after fix the data toggle error. John Youn: * Added WARN() to warn on improper usage of the dwc2_hcd_save_data_toggle() function. Signed-off-by: Dyson Lee Signed-off-by: Tang, Jianqiang Signed-off-by: John Youn Signed-off-by: Felipe Balbi --- drivers/usb/dwc2/hcd_ddma.c | 2 +- drivers/usb/dwc2/hcd_intr.c | 8 ++++++++ 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/usb/dwc2/hcd_ddma.c b/drivers/usb/dwc2/hcd_ddma.c index 89db47a1ffed..a41274aa52ad 100644 --- a/drivers/usb/dwc2/hcd_ddma.c +++ b/drivers/usb/dwc2/hcd_ddma.c @@ -1257,7 +1257,7 @@ static void dwc2_complete_non_isoc_xfer_ddma(struct dwc2_hsotg *hsotg, */ if (halt_status == DWC2_HC_XFER_STALL) qh->data_toggle = DWC2_HC_PID_DATA0; - else if (qtd) + else dwc2_hcd_save_data_toggle(hsotg, chan, chnum, qtd); } diff --git a/drivers/usb/dwc2/hcd_intr.c b/drivers/usb/dwc2/hcd_intr.c index f8253803a050..cadba8b13c48 100644 --- a/drivers/usb/dwc2/hcd_intr.c +++ b/drivers/usb/dwc2/hcd_intr.c @@ -525,11 +525,19 @@ void dwc2_hcd_save_data_toggle(struct dwc2_hsotg *hsotg, u32 pid = (hctsiz & TSIZ_SC_MC_PID_MASK) >> TSIZ_SC_MC_PID_SHIFT; if (chan->ep_type != USB_ENDPOINT_XFER_CONTROL) { + if (WARN(!chan || !chan->qh, + "chan->qh must be specified for non-control eps\n")) + return; + if (pid == TSIZ_SC_MC_PID_DATA0) chan->qh->data_toggle = DWC2_HC_PID_DATA0; else chan->qh->data_toggle = DWC2_HC_PID_DATA1; } else { + if (WARN(!qtd, + "qtd must be specified for control eps\n")) + return; + if (pid == TSIZ_SC_MC_PID_DATA0) qtd->data_toggle = DWC2_HC_PID_DATA0; else From ee89b641a9ddca5f2d1e38d205473c4b0d26c670 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 16 Feb 2016 16:10:59 +0100 Subject: [PATCH 045/417] usb: dwc2: USB_DWC2 should depend on HAS_DMA If NO_DMA=y: ERROR: "usb_gadget_map_request" [drivers/usb/dwc2/dwc2.ko] undefined! ERROR: "usb_gadget_unmap_request" [drivers/usb/dwc2/dwc2.ko] undefined! ERROR: "bad_dma_ops" [drivers/usb/dwc2/dwc2.ko] undefined! Add a dependency on HAS_DMA to fix this. Signed-off-by: Geert Uytterhoeven Acked-by: John Youn Signed-off-by: Felipe Balbi --- drivers/usb/dwc2/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/dwc2/Kconfig b/drivers/usb/dwc2/Kconfig index fd95ba6ec317..f0decc0d69b5 100644 --- a/drivers/usb/dwc2/Kconfig +++ b/drivers/usb/dwc2/Kconfig @@ -1,5 +1,6 @@ config USB_DWC2 tristate "DesignWare USB2 DRD Core Support" + depends on HAS_DMA depends on USB || USB_GADGET help Say Y here if your system has a Dual Role Hi-Speed USB From c219b7ddb6a3524a61a89438d86e4a8639706308 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 10 Feb 2016 12:04:22 -0500 Subject: [PATCH 046/417] sched/deadline: Fix trivial typo in printk() message It's "too much" not "to much". Signed-off-by: Steven Rostedt Acked-by: Juri Lelli Cc: Jiri Kosina Cc: Juri Lelli Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20160210120422.4ca77e68@gandalf.local.home Signed-off-by: Ingo Molnar --- kernel/sched/deadline.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index cd64c979d0e1..57b939c81bce 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -420,7 +420,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * entity. */ if (dl_time_before(dl_se->deadline, rq_clock(rq))) { - printk_deferred_once("sched: DL replenish lagged to much\n"); + printk_deferred_once("sched: DL replenish lagged too much\n"); dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; dl_se->runtime = pi_se->dl_runtime; } From d2613f56ce0287211d70a86443a143cae1887911 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 28 Jan 2016 16:04:21 +0100 Subject: [PATCH 047/417] ARM: shmobile: Move shmobile_scu_base from .text to .bss shmobile_scu_base is being written to, so it doesn't belong in the .text section. Fix this by moving it from asm .text to C .bss, as it's no longer used from asm code since commit 4f6da36f7edd5790 ("ARM: shmobile: Remove old SCU boot code"). Signed-off-by: Geert Uytterhoeven Signed-off-by: Simon Horman --- arch/arm/mach-shmobile/headsmp-scu.S | 6 ------ arch/arm/mach-shmobile/platsmp-scu.c | 3 +++ 2 files changed, 3 insertions(+), 6 deletions(-) diff --git a/arch/arm/mach-shmobile/headsmp-scu.S b/arch/arm/mach-shmobile/headsmp-scu.S index fa5248c52399..5e503d91ad70 100644 --- a/arch/arm/mach-shmobile/headsmp-scu.S +++ b/arch/arm/mach-shmobile/headsmp-scu.S @@ -38,9 +38,3 @@ ENTRY(shmobile_boot_scu) b secondary_startup ENDPROC(shmobile_boot_scu) - - .text - .align 2 - .globl shmobile_scu_base -shmobile_scu_base: - .space 4 diff --git a/arch/arm/mach-shmobile/platsmp-scu.c b/arch/arm/mach-shmobile/platsmp-scu.c index 64663110ab6c..f2198c9c7435 100644 --- a/arch/arm/mach-shmobile/platsmp-scu.c +++ b/arch/arm/mach-shmobile/platsmp-scu.c @@ -17,6 +17,9 @@ #include #include "common.h" + +void __iomem *shmobile_scu_base; + static int shmobile_smp_scu_notifier_call(struct notifier_block *nfb, unsigned long action, void *hcpu) { From b1568d80123a7e7ab528f587ef6896b2d5413b61 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 28 Jan 2016 16:13:31 +0100 Subject: [PATCH 048/417] ARM: shmobile: r8a7779: Remove remainings of removed SCU boot setup code Commit 0ca2894b5a900709 ("ARM: shmobile: Use shared SCU SMP boot code on r8a7779") obsoleted the r8a7779-specific SCU boot code, but forgot to remove the setup of shmobile_boot_fn and shmobile_boot_arg, which is overwritten by shmobile_smp_scu_prepare_cpus(). Note that shmobile_scu_base wasn't initialized at that point yet anyway. Signed-off-by: Geert Uytterhoeven Signed-off-by: Simon Horman --- arch/arm/mach-shmobile/smp-r8a7779.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/arm/mach-shmobile/smp-r8a7779.c b/arch/arm/mach-shmobile/smp-r8a7779.c index b854fe2095ad..0b024a9dbd43 100644 --- a/arch/arm/mach-shmobile/smp-r8a7779.c +++ b/arch/arm/mach-shmobile/smp-r8a7779.c @@ -92,8 +92,6 @@ static void __init r8a7779_smp_prepare_cpus(unsigned int max_cpus) { /* Map the reset vector (in headsmp-scu.S, headsmp.S) */ __raw_writel(__pa(shmobile_boot_vector), AVECR); - shmobile_boot_fn = virt_to_phys(shmobile_boot_scu); - shmobile_boot_arg = (unsigned long)shmobile_scu_base; /* setup r8a7779 specific SCU bits */ shmobile_scu_base = IOMEM(R8A7779_SCU_BASE); From 4e960f52fce16a3bf3261fa92c34cf2306059ba2 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 15 Feb 2016 13:20:07 +0100 Subject: [PATCH 049/417] ARM: shmobile: Move shmobile_smp_{mpidr, fn, arg}[] from .text to .bss If CONFIG_DEBUG_RODATA=y, the kernel crashes during system suspend: Freezing user space processes ... (elapsed 0.004 seconds) done. Freezing remaining freezable tasks ... (elapsed 0.002 seconds) done. PM: suspend of devices complete after 111.948 msecs PM: late suspend of devices complete after 1.086 msecs PM: noirq suspend of devices complete after 11.576 msecs Disabling non-boot CPUs ... Kernel panic - not syncing: Attempted to kill the idle task! 1014ec ---[ end Kernel panic - not syncing: Attempted to kill the idle task! CPU0: stopping This happens because the .text section is marked read-only, while the arrays shmobile_smp_mpidr[], shmobile_smp_fn[], and shmobile_smp_arg[] are being written to. Fix this by moving these arrays from the .text to the .bss section. This requires accessing them through PC-relative offsets. Signed-off-by: Geert Uytterhoeven Reviewed-by: Kees Cook Reviewed-by: Nicolas Pitre Signed-off-by: Simon Horman --- arch/arm/mach-shmobile/headsmp.S | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/arch/arm/mach-shmobile/headsmp.S b/arch/arm/mach-shmobile/headsmp.S index 330c1fc63197..94d86ed16414 100644 --- a/arch/arm/mach-shmobile/headsmp.S +++ b/arch/arm/mach-shmobile/headsmp.S @@ -50,9 +50,11 @@ ENTRY(shmobile_smp_boot) mrc p15, 0, r1, c0, c0, 5 @ r1 = MPIDR and r0, r1, r0 @ r0 = cpu_logical_map() value mov r1, #0 @ r1 = CPU index - adr r5, 1f @ array of per-cpu mpidr values - adr r6, 2f @ array of per-cpu functions - adr r7, 3f @ array of per-cpu arguments + adr r2, 1f + ldmia r2, {r5, r6, r7} + add r5, r5, r2 @ array of per-cpu mpidr values + add r6, r6, r2 @ array of per-cpu functions + add r7, r7, r2 @ array of per-cpu arguments shmobile_smp_boot_find_mpidr: ldr r8, [r5, r1, lsl #2] @@ -80,12 +82,18 @@ ENTRY(shmobile_smp_sleep) b shmobile_smp_boot ENDPROC(shmobile_smp_sleep) + .align 2 +1: .long shmobile_smp_mpidr - . + .long shmobile_smp_fn - 1b + .long shmobile_smp_arg - 1b + + .bss .globl shmobile_smp_mpidr shmobile_smp_mpidr: -1: .space NR_CPUS * 4 + .space NR_CPUS * 4 .globl shmobile_smp_fn shmobile_smp_fn: -2: .space NR_CPUS * 4 + .space NR_CPUS * 4 .globl shmobile_smp_arg shmobile_smp_arg: -3: .space NR_CPUS * 4 + .space NR_CPUS * 4 From 901c5ffaaed117a38be9d0c29247c4888d6c8636 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 15 Feb 2016 13:20:08 +0100 Subject: [PATCH 050/417] ARM: shmobile: Remove shmobile_boot_arg CPU boot configuration writes to shmobile_boot_arg, which is located in the .text section, and thus should not be written to. As of commit 1d33a354bbb618ba ("ARM: shmobile: Per-CPU SMP boot / sleep code for SCU SoCs"), and ignoring accidental remainings, shmobile_boot_arg is always set to MPIDR_HWID_BITMASK by C code. Hence we can just hardcode this in the assembler code, and remove the variable, and thus also remove the need to write to this variable. Signed-off-by: Geert Uytterhoeven Acked-by: Nicolas Pitre Signed-off-by: Simon Horman --- arch/arm/mach-shmobile/common.h | 1 - arch/arm/mach-shmobile/headsmp.S | 8 ++------ arch/arm/mach-shmobile/platsmp-apmu.c | 1 - arch/arm/mach-shmobile/platsmp-scu.c | 1 - 4 files changed, 2 insertions(+), 9 deletions(-) diff --git a/arch/arm/mach-shmobile/common.h b/arch/arm/mach-shmobile/common.h index 9cb11215ceba..b3a4ed5289ec 100644 --- a/arch/arm/mach-shmobile/common.h +++ b/arch/arm/mach-shmobile/common.h @@ -4,7 +4,6 @@ extern void shmobile_init_delay(void); extern void shmobile_boot_vector(void); extern unsigned long shmobile_boot_fn; -extern unsigned long shmobile_boot_arg; extern unsigned long shmobile_boot_size; extern void shmobile_smp_boot(void); extern void shmobile_smp_sleep(void); diff --git a/arch/arm/mach-shmobile/headsmp.S b/arch/arm/mach-shmobile/headsmp.S index 94d86ed16414..32e0bf6e3ccb 100644 --- a/arch/arm/mach-shmobile/headsmp.S +++ b/arch/arm/mach-shmobile/headsmp.S @@ -24,7 +24,6 @@ .arm .align 12 ENTRY(shmobile_boot_vector) - ldr r0, 2f ldr r1, 1f bx r1 @@ -34,9 +33,6 @@ ENDPROC(shmobile_boot_vector) .globl shmobile_boot_fn shmobile_boot_fn: 1: .space 4 - .globl shmobile_boot_arg -shmobile_boot_arg: -2: .space 4 .globl shmobile_boot_size shmobile_boot_size: .long . - shmobile_boot_vector @@ -46,9 +42,9 @@ shmobile_boot_size: */ ENTRY(shmobile_smp_boot) - @ r0 = MPIDR_HWID_BITMASK mrc p15, 0, r1, c0, c0, 5 @ r1 = MPIDR - and r0, r1, r0 @ r0 = cpu_logical_map() value + and r0, r1, #0xffffff @ MPIDR_HWID_BITMASK + @ r0 = cpu_logical_map() value mov r1, #0 @ r1 = CPU index adr r2, 1f ldmia r2, {r5, r6, r7} diff --git a/arch/arm/mach-shmobile/platsmp-apmu.c b/arch/arm/mach-shmobile/platsmp-apmu.c index 911884f7e28b..aba75c89f9c1 100644 --- a/arch/arm/mach-shmobile/platsmp-apmu.c +++ b/arch/arm/mach-shmobile/platsmp-apmu.c @@ -123,7 +123,6 @@ void __init shmobile_smp_apmu_prepare_cpus(unsigned int max_cpus, { /* install boot code shared by all CPUs */ shmobile_boot_fn = virt_to_phys(shmobile_smp_boot); - shmobile_boot_arg = MPIDR_HWID_BITMASK; /* perform per-cpu setup */ apmu_parse_cfg(apmu_init_cpu, apmu_config, num); diff --git a/arch/arm/mach-shmobile/platsmp-scu.c b/arch/arm/mach-shmobile/platsmp-scu.c index f2198c9c7435..081a097c9219 100644 --- a/arch/arm/mach-shmobile/platsmp-scu.c +++ b/arch/arm/mach-shmobile/platsmp-scu.c @@ -44,7 +44,6 @@ void __init shmobile_smp_scu_prepare_cpus(unsigned int max_cpus) { /* install boot code shared by all CPUs */ shmobile_boot_fn = virt_to_phys(shmobile_smp_boot); - shmobile_boot_arg = MPIDR_HWID_BITMASK; /* enable SCU and cache coherency on booting CPU */ scu_enable(shmobile_scu_base); From 96c7de4ff41c2ed6da43141a4deb922de09617d0 Mon Sep 17 00:00:00 2001 From: Andrzej Hajda Date: Mon, 15 Feb 2016 15:35:25 +0100 Subject: [PATCH 051/417] usb: gadget: fsl_qe_udc: fix IS_ERR_VALUE usage IS_ERR_VALUE macro should be used only with unsigned long type. Otherwise it can work incorrectly. The patch follows conclusion from discussion on LKML [1][2]. [1]: http://permalink.gmane.org/gmane.linux.kernel/2120927 [2]: http://permalink.gmane.org/gmane.linux.kernel/2150581 Signed-off-by: Andrzej Hajda Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/fsl_qe_udc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/udc/fsl_qe_udc.c b/drivers/usb/gadget/udc/fsl_qe_udc.c index 53c0692f1b09..93d28cb00b76 100644 --- a/drivers/usb/gadget/udc/fsl_qe_udc.c +++ b/drivers/usb/gadget/udc/fsl_qe_udc.c @@ -2340,7 +2340,7 @@ static struct qe_udc *qe_udc_config(struct platform_device *ofdev) { struct qe_udc *udc; struct device_node *np = ofdev->dev.of_node; - unsigned int tmp_addr = 0; + unsigned long tmp_addr = 0; struct usb_device_para __iomem *usbpram; unsigned int i; u64 size; From bba40e6948b94cba71965285fbac31bd078c024a Mon Sep 17 00:00:00 2001 From: Cristian Birsan Date: Thu, 11 Feb 2016 08:58:17 -0700 Subject: [PATCH 052/417] usb: musb: Fix DMA desired mode for Mentor DMA engine Commit 754fe4a92c07 ("usb: musb: Remove ifdefs for TX DMA for musb_host.c") introduces a problem setting the desired channel mode for the Mentor DMA engine. There is a case where an address is incorrectly assigned to the DMA channel desired mode when it should instead be assigned the actual mode value. This results in the value of channel->desired_mode not being correct. Acked-by: Sergei Shtylyov Signed-off-by: Cristian Birsan Signed-off-by: Joshua Henderson Signed-off-by: Felipe Balbi --- drivers/usb/musb/musb_host.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index 795a45b1b25b..79d081883628 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -662,7 +662,7 @@ static int musb_tx_dma_set_mode_mentor(struct dma_controller *dma, csr &= ~(MUSB_TXCSR_AUTOSET | MUSB_TXCSR_DMAMODE); csr |= MUSB_TXCSR_DMAENAB; /* against programmer's guide */ } - channel->desired_mode = mode; + channel->desired_mode = *mode; musb_writew(epio, MUSB_TXCSR, csr); return 0; From 9f74660bcf1e4cca577be99e54bc77b5df62b508 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 15 Feb 2016 10:23:59 -0500 Subject: [PATCH 053/417] xprtrdma: rpcrdma_bc_receive_call() should init rq_private_buf.len Some NFSv4.1 OPEN requests were hanging waiting for the NFS server to finish recalling delegations. Turns out that each NFSv4.1 CB request on RDMA gets a GARBAGE_ARGS reply from the Linux client. Commit 756b9b37cfb2e3dc added a line in bc_svc_process that overwrites the incoming rq_rcv_buf's length with the value in rq_private_buf.len. But rpcrdma_bc_receive_call() does not invoke xprt_complete_bc_request(), thus rq_private_buf.len is not initialized. svc_process_common() is invoked with a zero-length RPC message, and fails. Fixes: 756b9b37cfb2e3dc ('SUNRPC: Fix callback channel') Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/backchannel.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index cc1251d07297..2dcd7640eeb5 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -341,6 +341,8 @@ void rpcrdma_bc_receive_call(struct rpcrdma_xprt *r_xprt, rqst->rq_reply_bytes_recvd = 0; rqst->rq_bytes_sent = 0; rqst->rq_xid = headerp->rm_xid; + + rqst->rq_private_buf.len = size; set_bit(RPC_BC_PA_IN_USE, &rqst->rq_bc_pa_state); buf = &rqst->rq_rcv_buf; From d9dfd8d741683347ee159d25f5b50c346a0df557 Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Wed, 17 Feb 2016 10:41:41 -0500 Subject: [PATCH 054/417] NFSv4: Fix a dentry leak on alias use In the case where d_add_unique() finds an appropriate alias to use it will have already incremented the reference count. An additional dget() to swap the open context's dentry is unnecessary and will leak a reference. Signed-off-by: Benjamin Coddington Fixes: 275bb307865a3 ("NFSv4: Move dentry instantiation into the NFSv4-...") Cc: stable@vger.kernel.org # 3.10+ Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 4bfc33ad0563..14881594dd07 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2466,9 +2466,9 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, dentry = d_add_unique(dentry, igrab(state->inode)); if (dentry == NULL) { dentry = opendata->dentry; - } else if (dentry != ctx->dentry) { + } else { dput(ctx->dentry); - ctx->dentry = dget(dentry); + ctx->dentry = dentry; } nfs_set_verifier(dentry, nfs_save_change_attribute(d_inode(opendata->dir))); From 4bdf87ebda016b864b388f96ae349e76983ebac4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 17 Feb 2016 15:48:28 +0100 Subject: [PATCH 055/417] nfs4: fix stateid handling for the NFS v4.2 operations The newly added NFS v4.2 operations (ALLOCATE, DEALLOCATE, SEEK and CLONE) use a helper called nfs42_set_rw_stateid to select a stateid that is sent to the server. But they don't set the inode and state fields in the nfs4_exception structure, and this don't partake in the stateid recovery protocol. Because of this they will simply return errors insted of trying to recover a stateid when the server return a BAD_STATEID error. Additionally CLONE has the problem that it operates on two files and thus two stateids, and thus needs to call the exception handler twice to recover stateids. While we're at it stop grabbing an addititional reference to the open context in all these operations - having the file open guarantees that the open context won't go away. All this can be produces with the generic/168 and generic/170 tests in xfstests which stress the CLONE stateid handling. Signed-off-by: Christoph Hellwig Signed-off-by: Trond Myklebust --- fs/nfs/nfs42proc.c | 119 +++++++++++++++++++++++++++++---------------- 1 file changed, 76 insertions(+), 43 deletions(-) diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index bd25dc7077f7..dff83460e5a6 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -16,29 +16,8 @@ #define NFSDBG_FACILITY NFSDBG_PROC -static int nfs42_set_rw_stateid(nfs4_stateid *dst, struct file *file, - fmode_t fmode) -{ - struct nfs_open_context *open; - struct nfs_lock_context *lock; - int ret; - - open = get_nfs_open_context(nfs_file_open_context(file)); - lock = nfs_get_lock_context(open); - if (IS_ERR(lock)) { - put_nfs_open_context(open); - return PTR_ERR(lock); - } - - ret = nfs4_set_rw_stateid(dst, open, lock, fmode); - - nfs_put_lock_context(lock); - put_nfs_open_context(open); - return ret; -} - static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, - loff_t offset, loff_t len) + struct nfs_lock_context *lock, loff_t offset, loff_t len) { struct inode *inode = file_inode(filep); struct nfs_server *server = NFS_SERVER(inode); @@ -56,7 +35,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, msg->rpc_argp = &args; msg->rpc_resp = &res; - status = nfs42_set_rw_stateid(&args.falloc_stateid, filep, FMODE_WRITE); + status = nfs4_set_rw_stateid(&args.falloc_stateid, lock->open_context, + lock, FMODE_WRITE); if (status) return status; @@ -78,15 +58,26 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, { struct nfs_server *server = NFS_SERVER(file_inode(filep)); struct nfs4_exception exception = { }; + struct nfs_lock_context *lock; int err; + lock = nfs_get_lock_context(nfs_file_open_context(filep)); + if (IS_ERR(lock)) + return PTR_ERR(lock); + + exception.inode = file_inode(filep); + exception.state = lock->open_context->state; + do { - err = _nfs42_proc_fallocate(msg, filep, offset, len); - if (err == -ENOTSUPP) - return -EOPNOTSUPP; + err = _nfs42_proc_fallocate(msg, filep, lock, offset, len); + if (err == -ENOTSUPP) { + err = -EOPNOTSUPP; + break; + } err = nfs4_handle_exception(server, err, &exception); } while (exception.retry); + nfs_put_lock_context(lock); return err; } @@ -135,7 +126,8 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len) return err; } -static loff_t _nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) +static loff_t _nfs42_proc_llseek(struct file *filep, + struct nfs_lock_context *lock, loff_t offset, int whence) { struct inode *inode = file_inode(filep); struct nfs42_seek_args args = { @@ -156,7 +148,8 @@ static loff_t _nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) if (!nfs_server_capable(inode, NFS_CAP_SEEK)) return -ENOTSUPP; - status = nfs42_set_rw_stateid(&args.sa_stateid, filep, FMODE_READ); + status = nfs4_set_rw_stateid(&args.sa_stateid, lock->open_context, + lock, FMODE_READ); if (status) return status; @@ -175,17 +168,28 @@ loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) { struct nfs_server *server = NFS_SERVER(file_inode(filep)); struct nfs4_exception exception = { }; + struct nfs_lock_context *lock; loff_t err; + lock = nfs_get_lock_context(nfs_file_open_context(filep)); + if (IS_ERR(lock)) + return PTR_ERR(lock); + + exception.inode = file_inode(filep); + exception.state = lock->open_context->state; + do { - err = _nfs42_proc_llseek(filep, offset, whence); + err = _nfs42_proc_llseek(filep, lock, offset, whence); if (err >= 0) break; - if (err == -ENOTSUPP) - return -EOPNOTSUPP; + if (err == -ENOTSUPP) { + err = -EOPNOTSUPP; + break; + } err = nfs4_handle_exception(server, err, &exception); } while (exception.retry); + nfs_put_lock_context(lock); return err; } @@ -298,8 +302,9 @@ int nfs42_proc_layoutstats_generic(struct nfs_server *server, } static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, - struct file *dst_f, loff_t src_offset, - loff_t dst_offset, loff_t count) + struct file *dst_f, struct nfs_lock_context *src_lock, + struct nfs_lock_context *dst_lock, loff_t src_offset, + loff_t dst_offset, loff_t count) { struct inode *src_inode = file_inode(src_f); struct inode *dst_inode = file_inode(dst_f); @@ -320,11 +325,13 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, msg->rpc_argp = &args; msg->rpc_resp = &res; - status = nfs42_set_rw_stateid(&args.src_stateid, src_f, FMODE_READ); + status = nfs4_set_rw_stateid(&args.src_stateid, src_lock->open_context, + src_lock, FMODE_READ); if (status) return status; - status = nfs42_set_rw_stateid(&args.dst_stateid, dst_f, FMODE_WRITE); + status = nfs4_set_rw_stateid(&args.dst_stateid, dst_lock->open_context, + dst_lock, FMODE_WRITE); if (status) return status; @@ -349,22 +356,48 @@ int nfs42_proc_clone(struct file *src_f, struct file *dst_f, }; struct inode *inode = file_inode(src_f); struct nfs_server *server = NFS_SERVER(file_inode(src_f)); - struct nfs4_exception exception = { }; - int err; + struct nfs_lock_context *src_lock; + struct nfs_lock_context *dst_lock; + struct nfs4_exception src_exception = { }; + struct nfs4_exception dst_exception = { }; + int err, err2; if (!nfs_server_capable(inode, NFS_CAP_CLONE)) return -EOPNOTSUPP; + src_lock = nfs_get_lock_context(nfs_file_open_context(src_f)); + if (IS_ERR(src_lock)) + return PTR_ERR(src_lock); + + src_exception.inode = file_inode(src_f); + src_exception.state = src_lock->open_context->state; + + dst_lock = nfs_get_lock_context(nfs_file_open_context(dst_f)); + if (IS_ERR(dst_lock)) { + err = PTR_ERR(dst_lock); + goto out_put_src_lock; + } + + dst_exception.inode = file_inode(dst_f); + dst_exception.state = dst_lock->open_context->state; + do { - err = _nfs42_proc_clone(&msg, src_f, dst_f, src_offset, - dst_offset, count); + err = _nfs42_proc_clone(&msg, src_f, dst_f, src_lock, dst_lock, + src_offset, dst_offset, count); if (err == -ENOTSUPP || err == -EOPNOTSUPP) { NFS_SERVER(inode)->caps &= ~NFS_CAP_CLONE; - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + break; } - err = nfs4_handle_exception(server, err, &exception); - } while (exception.retry); + err2 = nfs4_handle_exception(server, err, &src_exception); + err = nfs4_handle_exception(server, err, &dst_exception); + if (!err) + err = err2; + } while (src_exception.retry || dst_exception.retry); + + nfs_put_lock_context(dst_lock); +out_put_src_lock: + nfs_put_lock_context(src_lock); return err; - } From c89757061a4e4017a21ef632dc100449a7bab7dd Mon Sep 17 00:00:00 2001 From: Kinglong Mee Date: Mon, 1 Feb 2016 09:39:29 +0800 Subject: [PATCH 056/417] pnfs/blocklayout: fix a memeory leak when using,vmalloc_to_page unreferenced object 0xffffc90000abf000 (size 16900): comm "fsync02", pid 15765, jiffies 4297431627 (age 423.772s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 a0 c2 19 00 88 ff ff ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] kmemleak_alloc+0x4e/0xb0 [] __vmalloc_node_range+0x231/0x280 [] __vmalloc+0x4a/0x50 [] ext_tree_prepare_commit+0x231/0x2e0 [blocklayoutdriver] [] bl_prepare_layoutcommit+0xe/0x10 [blocklayoutdriver] [] pnfs_layoutcommit_inode+0x29c/0x330 [nfsv4] [] pnfs_generic_sync+0x13/0x20 [nfsv4] [] nfs4_file_fsync+0x58/0x150 [nfsv4] [] vfs_fsync_range+0x4b/0xb0 [] do_fsync+0x3d/0x70 [] SyS_fsync+0x10/0x20 [] entry_SYSCALL_64_fastpath+0x12/0x76 [] 0xffffffffffffffff v2, add missing include header Signed-off-by: Kinglong Mee Signed-off-by: Trond Myklebust --- fs/nfs/blocklayout/extent_tree.c | 10 ++++++++-- include/linux/nfs_xdr.h | 1 + 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/fs/nfs/blocklayout/extent_tree.c b/fs/nfs/blocklayout/extent_tree.c index c59a59c37f3d..35ab51c04814 100644 --- a/fs/nfs/blocklayout/extent_tree.c +++ b/fs/nfs/blocklayout/extent_tree.c @@ -476,6 +476,7 @@ static void ext_tree_free_commitdata(struct nfs4_layoutcommit_args *arg, for (i = 0; i < nr_pages; i++) put_page(arg->layoutupdate_pages[i]); + vfree(arg->start_p); kfree(arg->layoutupdate_pages); } else { put_page(arg->layoutupdate_page); @@ -559,10 +560,15 @@ ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg) if (unlikely(arg->layoutupdate_pages != &arg->layoutupdate_page)) { void *p = start_p, *end = p + arg->layoutupdate_len; + struct page *page = NULL; int i = 0; - for ( ; p < end; p += PAGE_SIZE) - arg->layoutupdate_pages[i++] = vmalloc_to_page(p); + arg->start_p = start_p; + for ( ; p < end; p += PAGE_SIZE) { + page = vmalloc_to_page(p); + arg->layoutupdate_pages[i++] = page; + get_page(page); + } } dprintk("%s found %zu ranges\n", __func__, count); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 791098a08a87..d320906cf13e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -275,6 +275,7 @@ struct nfs4_layoutcommit_args { size_t layoutupdate_len; struct page *layoutupdate_page; struct page **layoutupdate_pages; + __be32 *start_p; }; struct nfs4_layoutcommit_res { From 437b300c6b28040ad87e4caf042e05f2c5f13c6d Mon Sep 17 00:00:00 2001 From: Scott Mayhew Date: Tue, 16 Feb 2016 16:20:25 -0500 Subject: [PATCH 057/417] auth_gss: fix panic in gss_pipe_downcall() in fips mode On Mon, 15 Feb 2016, Trond Myklebust wrote: > Hi Scott, > > On Mon, Feb 15, 2016 at 2:28 PM, Scott Mayhew wrote: > > md5 is disabled in fips mode, and attempting to import a gss context > > using md5 while in fips mode will result in crypto_alg_mod_lookup() > > returning -ENOENT, which will make its way back up to > > gss_pipe_downcall(), where the BUG() is triggered. Handling the -ENOENT > > allows for a more graceful failure. > > > > Signed-off-by: Scott Mayhew > > --- > > net/sunrpc/auth_gss/auth_gss.c | 3 +++ > > 1 file changed, 3 insertions(+) > > > > diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c > > index 799e65b..c30fc3b 100644 > > --- a/net/sunrpc/auth_gss/auth_gss.c > > +++ b/net/sunrpc/auth_gss/auth_gss.c > > @@ -737,6 +737,9 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) > > case -ENOSYS: > > gss_msg->msg.errno = -EAGAIN; > > break; > > + case -ENOENT: > > + gss_msg->msg.errno = -EPROTONOSUPPORT; > > + break; > > default: > > printk(KERN_CRIT "%s: bad return from " > > "gss_fill_context: %zd\n", __func__, err); > > -- > > 2.4.3 > > > > Well debugged, but I unfortunately do have to ask if this patch is > sufficient? In addition to -ENOENT, and -ENOMEM, it looks to me as if > crypto_alg_mod_lookup() can also fail with -EINTR, -ETIMEDOUT, and > -EAGAIN. Don't we also want to handle those? You're right, I was focusing on the panic that I could easily reproduce. I'm still not sure how I could trigger those other conditions. > > In fact, peering into the rats nest that is > gss_import_sec_context_kerberos(), it looks as if that is just a tiny > subset of all the errors that we might run into. Perhaps the right > thing to do here is to get rid of the BUG() (but keep the above > printk) and just return a generic error? That sounds fine to me -- updated patch attached. -Scott >From d54c6b64a107a90a38cab97577de05f9a4625052 Mon Sep 17 00:00:00 2001 From: Scott Mayhew Date: Mon, 15 Feb 2016 15:12:19 -0500 Subject: [PATCH] auth_gss: remove the BUG() from gss_pipe_downcall() Instead return a generic error via gss_msg->msg.errno. None of the errors returned by gss_fill_context() should necessarily trigger a kernel panic. Signed-off-by: Scott Mayhew Signed-off-by: Trond Myklebust --- net/sunrpc/auth_gss/auth_gss.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 799e65b944b9..cabf586f47d7 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -740,7 +740,7 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) default: printk(KERN_CRIT "%s: bad return from " "gss_fill_context: %zd\n", __func__, err); - BUG(); + gss_msg->msg.errno = -EIO; } goto err_release_msg; } From 2eca0d6ceea1f108b2d3ac81fb34698c4fd41006 Mon Sep 17 00:00:00 2001 From: Shanker Donthineni Date: Tue, 16 Feb 2016 18:00:36 -0600 Subject: [PATCH 058/417] irqchip/gicv3-its: Avoid cache flush beyond ITS_BASERn memory size Function its_alloc_tables() maintains two local variables, "order" and and "alloc_size", to hold memory size that has been allocated to ITS_BASEn. We don't always refresh the variable alloc_size whenever value of the variable order changes, causing the following two problems. - Cache flush operation with size more than required. - Information reported by pr_info is not correct. Use a helper macro that converts page order to size in bytes instead of variable "alloc_size" to fix both the problems. Signed-off-by: Shanker Donthineni Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3-its.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index ff2be77a51f6..43dfd15c1dd2 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -78,6 +78,9 @@ struct its_node { #define ITS_ITT_ALIGN SZ_256 +/* Convert page order to size in bytes */ +#define PAGE_ORDER_TO_SIZE(o) (PAGE_SIZE << (o)) + struct event_lpi_map { unsigned long *lpi_map; u16 *col_map; @@ -841,7 +844,6 @@ static int its_alloc_tables(const char *node_name, struct its_node *its) u64 type = GITS_BASER_TYPE(val); u64 entry_size = GITS_BASER_ENTRY_SIZE(val); int order = get_order(psz); - int alloc_size; int alloc_pages; u64 tmp; void *base; @@ -873,9 +875,8 @@ static int its_alloc_tables(const char *node_name, struct its_node *its) } } - alloc_size = (1 << order) * PAGE_SIZE; retry_alloc_baser: - alloc_pages = (alloc_size / psz); + alloc_pages = (PAGE_ORDER_TO_SIZE(order) / psz); if (alloc_pages > GITS_BASER_PAGES_MAX) { alloc_pages = GITS_BASER_PAGES_MAX; order = get_order(GITS_BASER_PAGES_MAX * psz); @@ -928,7 +929,7 @@ static int its_alloc_tables(const char *node_name, struct its_node *its) shr = tmp & GITS_BASER_SHAREABILITY_MASK; if (!shr) { cache = GITS_BASER_nC; - __flush_dcache_area(base, alloc_size); + __flush_dcache_area(base, PAGE_ORDER_TO_SIZE(order)); } goto retry_baser; } @@ -961,7 +962,7 @@ static int its_alloc_tables(const char *node_name, struct its_node *its) } pr_info("ITS: allocated %d %s @%lx (psz %dK, shr %d)\n", - (int)(alloc_size / entry_size), + (int)(PAGE_ORDER_TO_SIZE(order) / entry_size), its_base_type_string[type], (unsigned long)virt_to_phys(base), psz / SZ_1K, (int)shr >> GITS_BASER_SHAREABILITY_SHIFT); From fe25d078874f2c29c38f4160467d74f5756537c9 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 17 Feb 2016 12:26:33 -0600 Subject: [PATCH 059/417] Revert "x86/PCI: Don't alloc pcibios-irq when MSI is enabled" Revert 8affb487d4a4 ("x86/PCI: Don't alloc pcibios-irq when MSI is enabled"). This is part of reverting 991de2e59090 ("PCI, x86: Implement pcibios_alloc_irq() and pcibios_free_irq()") to fix regressions it introduced. Link: https://bugzilla.kernel.org/show_bug.cgi?id=111211 Fixes: 991de2e59090 ("PCI, x86: Implement pcibios_alloc_irq() and pcibios_free_irq()") Signed-off-by: Bjorn Helgaas Acked-by: Rafael J. Wysocki CC: Jiang Liu CC: Joerg Roedel --- arch/x86/pci/common.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 2879efc73a96..cb499c5b6ae5 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -713,14 +713,6 @@ int pcibios_add_device(struct pci_dev *dev) int pcibios_alloc_irq(struct pci_dev *dev) { - /* - * If the PCI device was already claimed by core code and has - * MSI enabled, probing of the pcibios IRQ will overwrite - * dev->irq. So bail out if MSI is already enabled. - */ - if (pci_dev_msi_enabled(dev)) - return -EBUSY; - return pcibios_enable_irq(dev); } From aeb67ae7d1a318c8456345b8012474be6a3ff74a Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Fri, 29 Jan 2016 10:57:53 +0100 Subject: [PATCH 060/417] irqchip/mxs: Add missing set_handle_irq() The rework of the driver missed to move the call to set_handle_irq() into asm9260_of_init(). As a consequence no interrupt entry point is installed and no interrupts are delivered Solution is: Install the interrupt entry handler. Fixes: 7e4ac676ee ("irqchip/mxs: Add Alphascale ASM9260 support") Signed-off-by: Oleksij Rempel Link: https://lkml.kernel.org/r/1454061473-24957-1-git-send-email-linux@rempel-privat.de Signed-off-by: Jason Cooper --- drivers/irqchip/irq-mxs.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/irqchip/irq-mxs.c b/drivers/irqchip/irq-mxs.c index c22e2d40cb30..efe50845939d 100644 --- a/drivers/irqchip/irq-mxs.c +++ b/drivers/irqchip/irq-mxs.c @@ -241,6 +241,7 @@ static int __init asm9260_of_init(struct device_node *np, writel(0, icoll_priv.intr + i); icoll_add_domain(np, ASM9260_NUM_IRQS); + set_handle_irq(icoll_handle_irq); return 0; } From 67b4eab91caf2ad574cab1b17ae09180ea2e116e Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 17 Feb 2016 12:26:38 -0600 Subject: [PATCH 061/417] Revert "PCI: Add helpers to manage pci_dev->irq and pci_dev->irq_managed" Revert 811a4e6fce09 ("PCI: Add helpers to manage pci_dev->irq and pci_dev->irq_managed"). This is part of reverting 991de2e59090 ("PCI, x86: Implement pcibios_alloc_irq() and pcibios_free_irq()") to fix regressions it introduced. Link: https://bugzilla.kernel.org/show_bug.cgi?id=111211 Fixes: 991de2e59090 ("PCI, x86: Implement pcibios_alloc_irq() and pcibios_free_irq()") Signed-off-by: Bjorn Helgaas Acked-by: Rafael J. Wysocki CC: Jiang Liu --- arch/x86/pci/intel_mid_pci.c | 4 ++-- arch/x86/pci/irq.c | 10 ++++++---- drivers/acpi/pci_irq.c | 10 ++++++---- include/linux/pci.h | 17 ----------------- 4 files changed, 14 insertions(+), 27 deletions(-) diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 0d24e7c10145..8826ff593ebc 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -215,7 +215,7 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) int polarity; int ret; - if (pci_has_managed_irq(dev)) + if (dev->irq_managed && dev->irq > 0) return 0; switch (intel_mid_identify_cpu()) { @@ -256,7 +256,7 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) static void intel_mid_pci_irq_disable(struct pci_dev *dev) { - if (pci_has_managed_irq(dev)) { + if (dev->irq_managed && dev->irq > 0) { mp_unmap_irq(dev->irq); dev->irq_managed = 0; /* diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 32e70343e6fd..72108f0b66b1 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -1202,7 +1202,7 @@ static int pirq_enable_irq(struct pci_dev *dev) struct pci_dev *temp_dev; int irq; - if (pci_has_managed_irq(dev)) + if (dev->irq_managed && dev->irq > 0) return 0; irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, @@ -1230,7 +1230,8 @@ static int pirq_enable_irq(struct pci_dev *dev) } dev = temp_dev; if (irq >= 0) { - pci_set_managed_irq(dev, irq); + dev->irq_managed = 1; + dev->irq = irq; dev_info(&dev->dev, "PCI->APIC IRQ transform: " "INT %c -> IRQ %d\n", 'A' + pin - 1, irq); return 0; @@ -1258,8 +1259,9 @@ static int pirq_enable_irq(struct pci_dev *dev) static void pirq_disable_irq(struct pci_dev *dev) { - if (io_apic_assign_pci_irqs && pci_has_managed_irq(dev)) { + if (io_apic_assign_pci_irqs && dev->irq_managed && dev->irq) { mp_unmap_irq(dev->irq); - pci_reset_managed_irq(dev); + dev->irq = 0; + dev->irq_managed = 0; } } diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index d30184c7f3bc..9032db7e4b3a 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -406,7 +406,7 @@ int acpi_pci_irq_enable(struct pci_dev *dev) return 0; } - if (pci_has_managed_irq(dev)) + if (dev->irq_managed && dev->irq > 0) return 0; entry = acpi_pci_irq_lookup(dev, pin); @@ -451,7 +451,8 @@ int acpi_pci_irq_enable(struct pci_dev *dev) kfree(entry); return rc; } - pci_set_managed_irq(dev, rc); + dev->irq = rc; + dev->irq_managed = 1; if (link) snprintf(link_desc, sizeof(link_desc), " -> Link[%s]", link); @@ -474,7 +475,7 @@ void acpi_pci_irq_disable(struct pci_dev *dev) u8 pin; pin = dev->pin; - if (!pin || !pci_has_managed_irq(dev)) + if (!pin || !dev->irq_managed || dev->irq <= 0) return; entry = acpi_pci_irq_lookup(dev, pin); @@ -496,6 +497,7 @@ void acpi_pci_irq_disable(struct pci_dev *dev) dev_dbg(&dev->dev, "PCI INT %c disabled\n", pin_name(pin)); if (gsi >= 0) { acpi_unregister_gsi(gsi); - pci_reset_managed_irq(dev); + dev->irq_managed = 0; + dev->irq = 0; } } diff --git a/include/linux/pci.h b/include/linux/pci.h index 27df4a6585da..27716254dcc5 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -988,23 +988,6 @@ static inline int pci_is_managed(struct pci_dev *pdev) return pdev->is_managed; } -static inline void pci_set_managed_irq(struct pci_dev *pdev, unsigned int irq) -{ - pdev->irq = irq; - pdev->irq_managed = 1; -} - -static inline void pci_reset_managed_irq(struct pci_dev *pdev) -{ - pdev->irq = 0; - pdev->irq_managed = 0; -} - -static inline bool pci_has_managed_irq(struct pci_dev *pdev) -{ - return pdev->irq_managed && pdev->irq > 0; -} - void pci_disable_device(struct pci_dev *dev); extern unsigned int pcibios_max_latency; From 3158a8d416f4e1b79dcc867d67cb50013140772c Mon Sep 17 00:00:00 2001 From: Andrey Skvortsov Date: Fri, 29 Jan 2016 00:07:30 +0300 Subject: [PATCH 062/417] USB: option: add support for SIM7100E $ lsusb: Bus 001 Device 101: ID 1e0e:9001 Qualcomm / Option $ usb-devices: T: Bus=01 Lev=02 Prnt=02 Port=00 Cnt=01 Dev#=101 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 2 P: Vendor=1e0e ProdID=9001 Rev= 2.32 S: Manufacturer=SimTech, Incorporated S: Product=SimTech, Incorporated S: SerialNumber=0123456789ABCDEF C:* #Ifs= 7 Cfg#= 1 Atr=80 MxPwr=500mA I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I:* If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan I:* If#= 6 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none) The last interface (6) is used for Android Composite ADB interface. Serial port layout: 0: QCDM/DIAG 1: NMEA 2: AT 3: AT/PPP 4: audio Signed-off-by: Andrey Skvortsov Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index db86e512e0fc..e7eb08d56bae 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -315,6 +315,7 @@ static void option_instat_callback(struct urb *urb); #define TOSHIBA_PRODUCT_G450 0x0d45 #define ALINK_VENDOR_ID 0x1e0e +#define SIMCOM_PRODUCT_SIM7100E 0x9001 /* Yes, ALINK_VENDOR_ID */ #define ALINK_PRODUCT_PH300 0x9100 #define ALINK_PRODUCT_3GU 0x9200 @@ -607,6 +608,10 @@ static const struct option_blacklist_info zte_1255_blacklist = { .reserved = BIT(3) | BIT(4), }; +static const struct option_blacklist_info simcom_sim7100e_blacklist = { + .reserved = BIT(5) | BIT(6), +}; + static const struct option_blacklist_info telit_le910_blacklist = { .sendsetup = BIT(0), .reserved = BIT(1) | BIT(2), @@ -1645,6 +1650,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(ALINK_VENDOR_ID, 0x9000) }, { USB_DEVICE(ALINK_VENDOR_ID, ALINK_PRODUCT_PH300) }, { USB_DEVICE_AND_INTERFACE_INFO(ALINK_VENDOR_ID, ALINK_PRODUCT_3GU, 0xff, 0xff, 0xff) }, + { USB_DEVICE(ALINK_VENDOR_ID, SIMCOM_PRODUCT_SIM7100E), + .driver_info = (kernel_ulong_t)&simcom_sim7100e_blacklist }, { USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X060S_X200), .driver_info = (kernel_ulong_t)&alcatel_x200_blacklist }, From 6627ae19385283b89356a199d7f03c75ba35fb29 Mon Sep 17 00:00:00 2001 From: Ken Lin Date: Mon, 1 Feb 2016 14:57:25 -0500 Subject: [PATCH 063/417] USB: cp210x: add IDs for GE B650V3 and B850V3 boards Add USB ID for cp2104/5 devices on GE B650v3 and B850v3 boards. Signed-off-by: Ken Lin Signed-off-by: Akshay Bhat Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/cp210x.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 987813b8a7f9..7c319e7edda2 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -163,6 +163,8 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x1843, 0x0200) }, /* Vaisala USB Instrument Cable */ { USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */ { USB_DEVICE(0x18EF, 0xE025) }, /* ELV Marble Sound Board 1 */ + { USB_DEVICE(0x1901, 0x0190) }, /* GE B850 CP2105 Recorder interface */ + { USB_DEVICE(0x1901, 0x0193) }, /* GE B650 CP2104 PMC interface */ { USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */ { USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */ { USB_DEVICE(0x1BA4, 0x0002) }, /* Silicon Labs 358x factory default */ From 0eca6fdb3193410fbe66b6f064431cc394513e82 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Tue, 16 Feb 2016 09:42:57 +0530 Subject: [PATCH 064/417] ARC: Assume multiplier is always present It is unlikely that designs running Linux will not have multiplier. Further the current support is not complete as tool don't generate a multilib w/o multiplier. Signed-off-by: Vineet Gupta --- arch/arc/Kconfig | 8 -------- arch/arc/Makefile | 4 ---- arch/arc/kernel/setup.c | 2 -- 3 files changed, 14 deletions(-) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 0655495470ad..0f8df0aa2eb8 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -275,14 +275,6 @@ config ARC_DCCM_BASE default "0xA0000000" depends on ARC_HAS_DCCM -config ARC_HAS_HW_MPY - bool "Use Hardware Multiplier (Normal or Faster XMAC)" - default y - help - Influences how gcc generates code for MPY operations. - If enabled, MPYxx insns are generated, provided by Standard/XMAC - Multipler. Otherwise software multipy lib is used - choice prompt "MMU Version" default ARC_MMU_V3 if ARC_CPU_770 diff --git a/arch/arc/Makefile b/arch/arc/Makefile index aeb19021099e..c8230f3395f2 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -74,10 +74,6 @@ ldflags-$(CONFIG_CPU_BIG_ENDIAN) += -EB # --build-id w/o "-marclinux". Default arc-elf32-ld is OK ldflags-$(upto_gcc44) += -marclinux -ifndef CONFIG_ARC_HAS_HW_MPY - cflags-y += -mno-mpy -endif - LIBGCC := $(shell $(CC) $(cflags-y) --print-libgcc-file-name) # Modules with short calls might break for calls into builtin-kernel diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index a7edceba5f84..28dba569edd4 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -237,8 +237,6 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len) n += scnprintf(buf + n, len - n, "mpy[opt %d] ", opt); } - n += scnprintf(buf + n, len - n, "%s", - IS_USED_CFG(CONFIG_ARC_HAS_HW_MPY)); } n += scnprintf(buf + n, len - n, "%s%s%s%s%s%s%s%s\n", From 98341f7dc9d9080d7999654ab589657272559b04 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Mon, 15 Feb 2016 15:58:42 +0530 Subject: [PATCH 065/417] ARCv2: boot print Low Latency Memory Signed-off-by: Vineet Gupta --- arch/arc/kernel/mcip.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index bc771f58fefb..002c5fcf8947 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -111,10 +111,11 @@ static void mcip_probe_n_setup(void) READ_BCR(ARC_REG_MCIP_BCR, mp); sprintf(smp_cpuinfo_buf, - "Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s\n", + "Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s%s\n", mp.ver, mp.num_cores, IS_AVAIL1(mp.ipi, "IPI "), IS_AVAIL1(mp.idu, "IDU "), + IS_AVAIL1(mp.llm, "LLM "), IS_AVAIL1(mp.dbg, "DEBUG "), IS_AVAIL1(mp.gfrc, "GFRC")); From a150b085b66c87bd4d362a523cb85ce2b0a2d77b Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Tue, 16 Feb 2016 12:36:18 +0530 Subject: [PATCH 066/417] ARCv2: boot report CCMs (Closely Coupled Memories) - ARCv2 uses a seperate BCR for {I,D}CCM base address: ARCompact encoded both base/size in same BCR - Size encoding in common BCR is different for ARCompact/ARCv2 Signed-off-by: Vineet Gupta --- arch/arc/include/asm/arcregs.h | 32 ++++++++------ arch/arc/kernel/setup.c | 78 ++++++++++++++++++++++------------ 2 files changed, 70 insertions(+), 40 deletions(-) diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h index fdc5be5b1029..f9f4c6f59fdb 100644 --- a/arch/arc/include/asm/arcregs.h +++ b/arch/arc/include/asm/arcregs.h @@ -10,7 +10,8 @@ #define _ASM_ARC_ARCREGS_H /* Build Configuration Registers */ -#define ARC_REG_DCCMBASE_BCR 0x61 /* DCCM Base Addr */ +#define ARC_REG_AUX_DCCM 0x18 /* DCCM Base Addr ARCv2 */ +#define ARC_REG_DCCM_BASE_BUILD 0x61 /* DCCM Base Addr ARCompact */ #define ARC_REG_CRC_BCR 0x62 #define ARC_REG_VECBASE_BCR 0x68 #define ARC_REG_PERIBASE_BCR 0x69 @@ -18,10 +19,10 @@ #define ARC_REG_DPFP_BCR 0x6C /* ARCompact: Dbl Precision FPU */ #define ARC_REG_FP_V2_BCR 0xc8 /* ARCv2 FPU */ #define ARC_REG_SLC_BCR 0xce -#define ARC_REG_DCCM_BCR 0x74 /* DCCM Present + SZ */ +#define ARC_REG_DCCM_BUILD 0x74 /* DCCM size (common) */ #define ARC_REG_TIMERS_BCR 0x75 #define ARC_REG_AP_BCR 0x76 -#define ARC_REG_ICCM_BCR 0x78 +#define ARC_REG_ICCM_BUILD 0x78 /* ICCM size (common) */ #define ARC_REG_XY_MEM_BCR 0x79 #define ARC_REG_MAC_BCR 0x7a #define ARC_REG_MUL_BCR 0x7b @@ -36,6 +37,7 @@ #define ARC_REG_IRQ_BCR 0xF3 #define ARC_REG_SMART_BCR 0xFF #define ARC_REG_CLUSTER_BCR 0xcf +#define ARC_REG_AUX_ICCM 0x208 /* ICCM Base Addr (ARCv2) */ /* status32 Bits Positions */ #define STATUS_AE_BIT 5 /* Exception active */ @@ -246,7 +248,7 @@ struct bcr_perip { #endif }; -struct bcr_iccm { +struct bcr_iccm_arcompact { #ifdef CONFIG_CPU_BIG_ENDIAN unsigned int base:16, pad:5, sz:3, ver:8; #else @@ -254,17 +256,15 @@ struct bcr_iccm { #endif }; -/* DCCM Base Address Register: ARC_REG_DCCMBASE_BCR */ -struct bcr_dccm_base { +struct bcr_iccm_arcv2 { #ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int addr:24, ver:8; + unsigned int pad:8, sz11:4, sz01:4, sz10:4, sz00:4, ver:8; #else - unsigned int ver:8, addr:24; + unsigned int ver:8, sz00:4, sz10:4, sz01:4, sz11:4, pad:8; #endif }; -/* DCCM RAM Configuration Register: ARC_REG_DCCM_BCR */ -struct bcr_dccm { +struct bcr_dccm_arcompact { #ifdef CONFIG_CPU_BIG_ENDIAN unsigned int res:21, sz:3, ver:8; #else @@ -272,6 +272,14 @@ struct bcr_dccm { #endif }; +struct bcr_dccm_arcv2 { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int pad2:12, cyc:3, pad1:1, sz1:4, sz0:4, ver:8; +#else + unsigned int ver:8, sz0:4, sz1:4, pad1:1, cyc:3, pad2:12; +#endif +}; + /* ARCompact: Both SP and DP FPU BCRs have same format */ struct bcr_fp_arcompact { #ifdef CONFIG_CPU_BIG_ENDIAN @@ -315,9 +323,9 @@ struct bcr_bpu_arcv2 { struct bcr_generic { #ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int pad:24, ver:8; + unsigned int info:24, ver:8; #else - unsigned int ver:8, pad:24; + unsigned int ver:8, info:24; #endif }; diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index 28dba569edd4..cdc821df1809 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -42,6 +42,53 @@ struct task_struct *_current_task[NR_CPUS]; /* For stack switching */ struct cpuinfo_arc cpuinfo_arc700[NR_CPUS]; +static void read_decode_ccm_bcr(struct cpuinfo_arc *cpu) +{ + if (is_isa_arcompact()) { + struct bcr_iccm_arcompact iccm; + struct bcr_dccm_arcompact dccm; + + READ_BCR(ARC_REG_ICCM_BUILD, iccm); + if (iccm.ver) { + cpu->iccm.sz = 4096 << iccm.sz; /* 8K to 512K */ + cpu->iccm.base_addr = iccm.base << 16; + } + + READ_BCR(ARC_REG_DCCM_BUILD, dccm); + if (dccm.ver) { + unsigned long base; + cpu->dccm.sz = 2048 << dccm.sz; /* 2K to 256K */ + + base = read_aux_reg(ARC_REG_DCCM_BASE_BUILD); + cpu->dccm.base_addr = base & ~0xF; + } + } else { + struct bcr_iccm_arcv2 iccm; + struct bcr_dccm_arcv2 dccm; + unsigned long region; + + READ_BCR(ARC_REG_ICCM_BUILD, iccm); + if (iccm.ver) { + cpu->iccm.sz = 256 << iccm.sz00; /* 512B to 16M */ + if (iccm.sz00 == 0xF && iccm.sz01 > 0) + cpu->iccm.sz <<= iccm.sz01; + + region = read_aux_reg(ARC_REG_AUX_ICCM); + cpu->iccm.base_addr = region & 0xF0000000; + } + + READ_BCR(ARC_REG_DCCM_BUILD, dccm); + if (dccm.ver) { + cpu->dccm.sz = 256 << dccm.sz0; + if (dccm.sz0 == 0xF && dccm.sz1 > 0) + cpu->dccm.sz <<= dccm.sz1; + + region = read_aux_reg(ARC_REG_AUX_DCCM); + cpu->dccm.base_addr = region & 0xF0000000; + } + } +} + static void read_arc_build_cfg_regs(void) { struct bcr_perip uncached_space; @@ -76,36 +123,11 @@ static void read_arc_build_cfg_regs(void) cpu->extn.swap = read_aux_reg(ARC_REG_SWAP_BCR) ? 1 : 0; /* 1,3 */ cpu->extn.crc = read_aux_reg(ARC_REG_CRC_BCR) ? 1 : 0; cpu->extn.minmax = read_aux_reg(ARC_REG_MIXMAX_BCR) > 1 ? 1 : 0; /* 2 */ - - /* Note that we read the CCM BCRs independent of kernel config - * This is to catch the cases where user doesn't know that - * CCMs are present in hardware build - */ - { - struct bcr_iccm iccm; - struct bcr_dccm dccm; - struct bcr_dccm_base dccm_base; - unsigned int bcr_32bit_val; - - bcr_32bit_val = read_aux_reg(ARC_REG_ICCM_BCR); - if (bcr_32bit_val) { - iccm = *((struct bcr_iccm *)&bcr_32bit_val); - cpu->iccm.base_addr = iccm.base << 16; - cpu->iccm.sz = 0x2000 << (iccm.sz - 1); - } - - bcr_32bit_val = read_aux_reg(ARC_REG_DCCM_BCR); - if (bcr_32bit_val) { - dccm = *((struct bcr_dccm *)&bcr_32bit_val); - cpu->dccm.sz = 0x800 << (dccm.sz); - - READ_BCR(ARC_REG_DCCMBASE_BCR, dccm_base); - cpu->dccm.base_addr = dccm_base.addr << 8; - } - } - READ_BCR(ARC_REG_XY_MEM_BCR, cpu->extn_xymem); + /* Read CCM BCRs for boot reporting even if not enabled in Kconfig */ + read_decode_ccm_bcr(cpu); + read_decode_mmu_bcr(); read_decode_cache_bcr(); From d061c1caa31d4d9792cfe48a2c6b309a0e01ef46 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Fri, 12 Feb 2016 16:40:00 +0100 Subject: [PATCH 067/417] USB: option: add "4G LTE usb-modem U901" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Thomas reports: T: Bus=01 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#= 4 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=05c6 ProdID=6001 Rev=00.00 S: Manufacturer=USB Modem S: Product=USB Modem S: SerialNumber=1234567890ABCDEF C: #Ifs= 5 Cfg#= 1 Atr=e0 MxPwr=500mA I: If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan I: If#= 4 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage Cc: Reported-by: Thomas Schäfer Signed-off-by: Bjørn Mork Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index e7eb08d56bae..8849439a8f18 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1127,6 +1127,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC650) }, { USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC680) }, { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6000)}, /* ZTE AC8700 */ + { USB_DEVICE_AND_INTERFACE_INFO(QUALCOMM_VENDOR_ID, 0x6001, 0xff, 0xff, 0xff), /* 4G LTE usb-modem U901 */ + .driver_info = (kernel_ulong_t)&net_intf3_blacklist }, { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */ From 018361767a21fb2d5ebd3ac182c04baf8a8b4e08 Mon Sep 17 00:00:00 2001 From: Gabor Juhos Date: Wed, 17 Feb 2016 12:58:20 +0100 Subject: [PATCH 068/417] pata-rb532-cf: get rid of the irq_to_gpio() call The RB532 platform specific irq_to_gpio() implementation has been removed with commit 832f5dacfa0b ("MIPS: Remove all the uses of custom gpio.h"). Now the platform uses the generic stub which causes the following error: pata-rb532-cf pata-rb532-cf: no GPIO found for irq149 pata-rb532-cf: probe of pata-rb532-cf failed with error -2 Drop the irq_to_gpio() call and get the GPIO number from platform data instead. After this change, the driver works again: scsi host0: pata-rb532-cf ata1: PATA max PIO4 irq 149 ata1.00: CFA: CF 1GB, 20080820, max MWDMA4 ata1.00: 1989792 sectors, multi 0: LBA ata1.00: configured for PIO4 scsi 0:0:0:0: Direct-Access ATA CF 1GB 0820 PQ: 0\ ANSI: 5 sd 0:0:0:0: [sda] 1989792 512-byte logical blocks: (1.01 GB/971 MiB) sd 0:0:0:0: [sda] Write Protect is off sd 0:0:0:0: [sda] Write cache: disabled, read cache: enabled, doesn't\ support DPO or FUA sda: sda1 sda2 sd 0:0:0:0: [sda] Attached SCSI disk Fixes: 832f5dacfa0b ("MIPS: Remove all the uses of custom gpio.h") Cc: Alban Bedel Cc: Ralf Baechle Cc: Arnd Bergmann Cc: #v4.3+ Signed-off-by: Gabor Juhos Signed-off-by: Tejun Heo --- drivers/ata/pata_rb532_cf.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/ata/pata_rb532_cf.c b/drivers/ata/pata_rb532_cf.c index 12fe0f3bb7e9..c8b6a780a290 100644 --- a/drivers/ata/pata_rb532_cf.c +++ b/drivers/ata/pata_rb532_cf.c @@ -32,6 +32,8 @@ #include #include +#include + #define DRV_NAME "pata-rb532-cf" #define DRV_VERSION "0.1.0" #define DRV_DESC "PATA driver for RouterBOARD 532 Compact Flash" @@ -107,6 +109,7 @@ static int rb532_pata_driver_probe(struct platform_device *pdev) int gpio; struct resource *res; struct ata_host *ah; + struct cf_device *pdata; struct rb532_cf_info *info; int ret; @@ -122,7 +125,13 @@ static int rb532_pata_driver_probe(struct platform_device *pdev) return -ENOENT; } - gpio = irq_to_gpio(irq); + pdata = dev_get_platdata(&pdev->dev); + if (!pdata) { + dev_err(&pdev->dev, "no platform data specified\n"); + return -EINVAL; + } + + gpio = pdata->gpio_pin; if (gpio < 0) { dev_err(&pdev->dev, "no GPIO found for irq%d\n", irq); return -ENOENT; From f5bdd66c705484b4bc77eb914be15c1b7881fae7 Mon Sep 17 00:00:00 2001 From: Alexandra Yates Date: Wed, 17 Feb 2016 19:36:20 -0800 Subject: [PATCH 069/417] Adding Intel Lewisburg device IDs for SATA This patch complements the list of device IDs previously added for lewisburg sata. Signed-off-by: Alexandra Yates Signed-off-by: Tejun Heo Cc: stable@vger.kernel.org --- drivers/ata/ahci.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 546a3692774f..b6263b3996ab 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -367,15 +367,21 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H RAID */ { PCI_VDEVICE(INTEL, 0xa10f), board_ahci }, /* Sunrise Point-H RAID */ { PCI_VDEVICE(INTEL, 0x2822), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0x2823), board_ahci }, /* Lewisburg AHCI*/ { PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0x2827), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa182), board_ahci }, /* Lewisburg AHCI*/ { PCI_VDEVICE(INTEL, 0xa184), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa186), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa18e), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa1d2), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa1d6), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa202), board_ahci }, /* Lewisburg AHCI*/ { PCI_VDEVICE(INTEL, 0xa204), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa206), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa20e), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa252), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa256), board_ahci }, /* Lewisburg RAID*/ /* JMicron 360/1/3/5/6, match class to avoid IDE function */ { PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, From 8f318526a292c5e7cebb82f3f766b83c22343293 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 18 Feb 2016 19:15:45 +0000 Subject: [PATCH 070/417] irqchip/gic-v3: Add missing barrier to 32bit version of gic_read_iar() Commit 1a1ebd5 ("irqchip/gic-v3: Make sure read from ICC_IAR1_EL1 is visible on redestributor") fixed the missing barrier on arm64, but forgot to update the 32bit counterpart, which has the same requirements. Let's fix it. Fixes: 1a1ebd5 ("irqchip/gic-v3: Make sure read from ICC_IAR1_EL1 is visible on redestributor") Signed-off-by: Marc Zyngier --- arch/arm/include/asm/arch_gicv3.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h index 7da5503c0591..e08d15184056 100644 --- a/arch/arm/include/asm/arch_gicv3.h +++ b/arch/arm/include/asm/arch_gicv3.h @@ -117,6 +117,7 @@ static inline u32 gic_read_iar(void) u32 irqstat; asm volatile("mrc " __stringify(ICC_IAR1) : "=r" (irqstat)); + dsb(sy); return irqstat; } From a4de018d2b0364e40a626fa521ec21e31a10ac84 Mon Sep 17 00:00:00 2001 From: Alan Date: Mon, 15 Feb 2016 19:09:46 +0000 Subject: [PATCH 071/417] usb: chipidea: error on overflow for port_test_write The write value is 8bit, but currently writing a larger number (eg a doubled digit) is not errored but instead gets cast and sets off an action probably undesired. Signed-off-by: Alan Cox Signed-off-by: Peter Chen (Change the style of commit log to fix checkpatch.pl warning) --- drivers/usb/chipidea/debug.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/chipidea/debug.c b/drivers/usb/chipidea/debug.c index a4f7db2e18dd..df47110bad2d 100644 --- a/drivers/usb/chipidea/debug.c +++ b/drivers/usb/chipidea/debug.c @@ -100,6 +100,9 @@ static ssize_t ci_port_test_write(struct file *file, const char __user *ubuf, if (sscanf(buf, "%u", &mode) != 1) return -EINVAL; + if (mode > 255) + return -EBADRQC; + pm_runtime_get_sync(ci->dev); spin_lock_irqsave(&ci->lock, flags); ret = hw_port_test_set(ci, mode); From 8c0614ca312c847ca5409ea11c39434dec69631d Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Sat, 6 Feb 2016 22:57:06 +0800 Subject: [PATCH 072/417] usb: chipidea: fix return value check in ci_hdrc_pci_probe() In case of error, the function usb_phy_generic_register() returns ERR_PTR() and never returns NULL. The NULL test in the return value check should be replaced with IS_ERR(). Signed-off-by: Wei Yongjun Signed-off-by: Peter Chen --- drivers/usb/chipidea/ci_hdrc_pci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/usb/chipidea/ci_hdrc_pci.c b/drivers/usb/chipidea/ci_hdrc_pci.c index b59195edf636..b635ab67490d 100644 --- a/drivers/usb/chipidea/ci_hdrc_pci.c +++ b/drivers/usb/chipidea/ci_hdrc_pci.c @@ -85,8 +85,8 @@ static int ci_hdrc_pci_probe(struct pci_dev *pdev, /* register a nop PHY */ ci->phy = usb_phy_generic_register(); - if (!ci->phy) - return -ENOMEM; + if (IS_ERR(ci->phy)) + return PTR_ERR(ci->phy); memset(res, 0, sizeof(res)); res[0].start = pci_resource_start(pdev, 0); From e327b3f564031a8d0090a6b3e3562a8b59bafe0e Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Fri, 19 Feb 2016 16:12:19 +0200 Subject: [PATCH 073/417] Revert "regulator: tps65217: remove tps65217.dtsi file" This reverts commit 8e6ebfaa9b384088002baa10f7534efa73a0794e. Without the patch reverted regulators will not work. This prevents MMC to be working for example so the boards can not boot to MMC rootfs. Tested it on beaglebone white and bisect also points to the reverted commit. The issue can be also fixed by adding "regulator-compatible =" to all board dts file for the regulators. Signed-off-by: Peter Ujfalusi Signed-off-by: Tony Lindgren --- .../bindings/regulator/tps65217.txt | 10 ---- arch/arm/boot/dts/am335x-bone-common.dtsi | 14 +---- arch/arm/boot/dts/am335x-chilisom.dtsi | 14 +---- arch/arm/boot/dts/am335x-nano.dts | 14 +---- arch/arm/boot/dts/am335x-pepper.dts | 14 +---- arch/arm/boot/dts/am335x-sl50.dts | 13 +---- arch/arm/boot/dts/tps65217.dtsi | 56 +++++++++++++++++++ 7 files changed, 67 insertions(+), 68 deletions(-) create mode 100644 arch/arm/boot/dts/tps65217.dtsi diff --git a/Documentation/devicetree/bindings/regulator/tps65217.txt b/Documentation/devicetree/bindings/regulator/tps65217.txt index d18109657da6..4f05d208c95c 100644 --- a/Documentation/devicetree/bindings/regulator/tps65217.txt +++ b/Documentation/devicetree/bindings/regulator/tps65217.txt @@ -26,11 +26,7 @@ Example: ti,pmic-shutdown-controller; regulators { - #address-cells = <1>; - #size-cells = <0>; - dcdc1_reg: dcdc1 { - reg = <0>; regulator-min-microvolt = <900000>; regulator-max-microvolt = <1800000>; regulator-boot-on; @@ -38,7 +34,6 @@ Example: }; dcdc2_reg: dcdc2 { - reg = <1>; regulator-min-microvolt = <900000>; regulator-max-microvolt = <3300000>; regulator-boot-on; @@ -46,7 +41,6 @@ Example: }; dcdc3_reg: dcc3 { - reg = <2>; regulator-min-microvolt = <900000>; regulator-max-microvolt = <1500000>; regulator-boot-on; @@ -54,7 +48,6 @@ Example: }; ldo1_reg: ldo1 { - reg = <3>; regulator-min-microvolt = <1000000>; regulator-max-microvolt = <3300000>; regulator-boot-on; @@ -62,7 +55,6 @@ Example: }; ldo2_reg: ldo2 { - reg = <4>; regulator-min-microvolt = <900000>; regulator-max-microvolt = <3300000>; regulator-boot-on; @@ -70,7 +62,6 @@ Example: }; ldo3_reg: ldo3 { - reg = <5>; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; regulator-boot-on; @@ -78,7 +69,6 @@ Example: }; ldo4_reg: ldo4 { - reg = <6>; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; regulator-boot-on; diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi index f3db13d2d90e..0cc150b87b86 100644 --- a/arch/arm/boot/dts/am335x-bone-common.dtsi +++ b/arch/arm/boot/dts/am335x-bone-common.dtsi @@ -285,8 +285,10 @@ cape3_data: cape_data@0 { }; }; + +/include/ "tps65217.dtsi" + &tps { - compatible = "ti,tps65217"; /* * Configure pmic to enter OFF-state instead of SLEEP-state ("RTC-only * mode") at poweroff. Most BeagleBone versions do not support RTC-only @@ -307,17 +309,12 @@ &tps { ti,pmic-shutdown-controller; regulators { - #address-cells = <1>; - #size-cells = <0>; - dcdc1_reg: regulator@0 { - reg = <0>; regulator-name = "vdds_dpr"; regulator-always-on; }; dcdc2_reg: regulator@1 { - reg = <1>; /* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */ regulator-name = "vdd_mpu"; regulator-min-microvolt = <925000>; @@ -327,7 +324,6 @@ dcdc2_reg: regulator@1 { }; dcdc3_reg: regulator@2 { - reg = <2>; /* VDD_CORE voltage limits 0.95V - 1.1V with +/-4% tolerance */ regulator-name = "vdd_core"; regulator-min-microvolt = <925000>; @@ -337,25 +333,21 @@ dcdc3_reg: regulator@2 { }; ldo1_reg: regulator@3 { - reg = <3>; regulator-name = "vio,vrtc,vdds"; regulator-always-on; }; ldo2_reg: regulator@4 { - reg = <4>; regulator-name = "vdd_3v3aux"; regulator-always-on; }; ldo3_reg: regulator@5 { - reg = <5>; regulator-name = "vdd_1v8"; regulator-always-on; }; ldo4_reg: regulator@6 { - reg = <6>; regulator-name = "vdd_3v3a"; regulator-always-on; }; diff --git a/arch/arm/boot/dts/am335x-chilisom.dtsi b/arch/arm/boot/dts/am335x-chilisom.dtsi index fda457b07e15..857d9894103a 100644 --- a/arch/arm/boot/dts/am335x-chilisom.dtsi +++ b/arch/arm/boot/dts/am335x-chilisom.dtsi @@ -128,21 +128,16 @@ tps: tps@24 { }; +/include/ "tps65217.dtsi" + &tps { - compatible = "ti,tps65217"; - regulators { - #address-cells = <1>; - #size-cells = <0>; - dcdc1_reg: regulator@0 { - reg = <0>; regulator-name = "vdds_dpr"; regulator-always-on; }; dcdc2_reg: regulator@1 { - reg = <1>; /* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */ regulator-name = "vdd_mpu"; regulator-min-microvolt = <925000>; @@ -152,7 +147,6 @@ dcdc2_reg: regulator@1 { }; dcdc3_reg: regulator@2 { - reg = <2>; /* VDD_CORE voltage limits 0.95V - 1.1V with +/-4% tolerance */ regulator-name = "vdd_core"; regulator-min-microvolt = <925000>; @@ -162,28 +156,24 @@ dcdc3_reg: regulator@2 { }; ldo1_reg: regulator@3 { - reg = <3>; regulator-name = "vio,vrtc,vdds"; regulator-boot-on; regulator-always-on; }; ldo2_reg: regulator@4 { - reg = <4>; regulator-name = "vdd_3v3aux"; regulator-boot-on; regulator-always-on; }; ldo3_reg: regulator@5 { - reg = <5>; regulator-name = "vdd_1v8"; regulator-boot-on; regulator-always-on; }; ldo4_reg: regulator@6 { - reg = <6>; regulator-name = "vdd_3v3d"; regulator-boot-on; regulator-always-on; diff --git a/arch/arm/boot/dts/am335x-nano.dts b/arch/arm/boot/dts/am335x-nano.dts index 77559a1ded60..f313999c503e 100644 --- a/arch/arm/boot/dts/am335x-nano.dts +++ b/arch/arm/boot/dts/am335x-nano.dts @@ -375,15 +375,11 @@ &mmc1 { wp-gpios = <&gpio3 18 0>; }; +#include "tps65217.dtsi" + &tps { - compatible = "ti,tps65217"; - regulators { - #address-cells = <1>; - #size-cells = <0>; - dcdc1_reg: regulator@0 { - reg = <0>; /* +1.5V voltage with ±4% tolerance */ regulator-min-microvolt = <1450000>; regulator-max-microvolt = <1550000>; @@ -392,7 +388,6 @@ dcdc1_reg: regulator@0 { }; dcdc2_reg: regulator@1 { - reg = <1>; /* VDD_MPU voltage limits 0.95V - 1.1V with ±4% tolerance */ regulator-name = "vdd_mpu"; regulator-min-microvolt = <915000>; @@ -402,7 +397,6 @@ dcdc2_reg: regulator@1 { }; dcdc3_reg: regulator@2 { - reg = <2>; /* VDD_CORE voltage limits 0.95V - 1.1V with ±4% tolerance */ regulator-name = "vdd_core"; regulator-min-microvolt = <915000>; @@ -412,7 +406,6 @@ dcdc3_reg: regulator@2 { }; ldo1_reg: regulator@3 { - reg = <3>; /* +1.8V voltage with ±4% tolerance */ regulator-min-microvolt = <1750000>; regulator-max-microvolt = <1870000>; @@ -421,7 +414,6 @@ ldo1_reg: regulator@3 { }; ldo2_reg: regulator@4 { - reg = <4>; /* +3.3V voltage with ±4% tolerance */ regulator-min-microvolt = <3175000>; regulator-max-microvolt = <3430000>; @@ -430,7 +422,6 @@ ldo2_reg: regulator@4 { }; ldo3_reg: regulator@5 { - reg = <5>; /* +1.8V voltage with ±4% tolerance */ regulator-min-microvolt = <1750000>; regulator-max-microvolt = <1870000>; @@ -439,7 +430,6 @@ ldo3_reg: regulator@5 { }; ldo4_reg: regulator@6 { - reg = <6>; /* +3.3V voltage with ±4% tolerance */ regulator-min-microvolt = <3175000>; regulator-max-microvolt = <3430000>; diff --git a/arch/arm/boot/dts/am335x-pepper.dts b/arch/arm/boot/dts/am335x-pepper.dts index 471a3a70ea1f..8867aaaec54d 100644 --- a/arch/arm/boot/dts/am335x-pepper.dts +++ b/arch/arm/boot/dts/am335x-pepper.dts @@ -420,9 +420,9 @@ &vdd5_reg { vin-supply = <&vbat>; }; -&tps { - compatible = "ti,tps65217"; +/include/ "tps65217.dtsi" +&tps { backlight { isel = <1>; /* ISET1 */ fdim = <200>; /* TPS65217_BL_FDIM_200HZ */ @@ -430,17 +430,12 @@ backlight { }; regulators { - #address-cells = <1>; - #size-cells = <0>; - dcdc1_reg: regulator@0 { - reg = <0>; /* VDD_1V8 system supply */ regulator-always-on; }; dcdc2_reg: regulator@1 { - reg = <1>; /* VDD_CORE voltage limits 0.95V - 1.26V with +/-4% tolerance */ regulator-name = "vdd_core"; regulator-min-microvolt = <925000>; @@ -450,7 +445,6 @@ dcdc2_reg: regulator@1 { }; dcdc3_reg: regulator@2 { - reg = <2>; /* VDD_MPU voltage limits 0.95V - 1.1V with +/-4% tolerance */ regulator-name = "vdd_mpu"; regulator-min-microvolt = <925000>; @@ -460,21 +454,18 @@ dcdc3_reg: regulator@2 { }; ldo1_reg: regulator@3 { - reg = <3>; /* VRTC 1.8V always-on supply */ regulator-name = "vrtc,vdds"; regulator-always-on; }; ldo2_reg: regulator@4 { - reg = <4>; /* 3.3V rail */ regulator-name = "vdd_3v3aux"; regulator-always-on; }; ldo3_reg: regulator@5 { - reg = <5>; /* VDD_3V3A 3.3V rail */ regulator-name = "vdd_3v3a"; regulator-min-microvolt = <3300000>; @@ -482,7 +473,6 @@ ldo3_reg: regulator@5 { }; ldo4_reg: regulator@6 { - reg = <6>; /* VDD_3V3B 3.3V rail */ regulator-name = "vdd_3v3b"; regulator-always-on; diff --git a/arch/arm/boot/dts/am335x-sl50.dts b/arch/arm/boot/dts/am335x-sl50.dts index d38edfa53bb9..3303c281697b 100644 --- a/arch/arm/boot/dts/am335x-sl50.dts +++ b/arch/arm/boot/dts/am335x-sl50.dts @@ -375,19 +375,16 @@ &uart4 { pinctrl-0 = <&uart4_pins>; }; +#include "tps65217.dtsi" + &tps { - compatible = "ti,tps65217"; ti,pmic-shutdown-controller; interrupt-parent = <&intc>; interrupts = <7>; /* NNMI */ regulators { - #address-cells = <1>; - #size-cells = <0>; - dcdc1_reg: regulator@0 { - reg = <0>; /* VDDS_DDR */ regulator-min-microvolt = <1500000>; regulator-max-microvolt = <1500000>; @@ -395,7 +392,6 @@ dcdc1_reg: regulator@0 { }; dcdc2_reg: regulator@1 { - reg = <1>; /* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */ regulator-name = "vdd_mpu"; regulator-min-microvolt = <925000>; @@ -405,7 +401,6 @@ dcdc2_reg: regulator@1 { }; dcdc3_reg: regulator@2 { - reg = <2>; /* VDD_CORE voltage limits 0.95V - 1.1V with +/-4% tolerance */ regulator-name = "vdd_core"; regulator-min-microvolt = <925000>; @@ -415,7 +410,6 @@ dcdc3_reg: regulator@2 { }; ldo1_reg: regulator@3 { - reg = <3>; /* VRTC / VIO / VDDS*/ regulator-always-on; regulator-min-microvolt = <1800000>; @@ -423,7 +417,6 @@ ldo1_reg: regulator@3 { }; ldo2_reg: regulator@4 { - reg = <4>; /* VDD_3V3AUX */ regulator-always-on; regulator-min-microvolt = <3300000>; @@ -431,7 +424,6 @@ ldo2_reg: regulator@4 { }; ldo3_reg: regulator@5 { - reg = <5>; /* VDD_1V8 */ regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; @@ -439,7 +431,6 @@ ldo3_reg: regulator@5 { }; ldo4_reg: regulator@6 { - reg = <6>; /* VDD_3V3A */ regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; diff --git a/arch/arm/boot/dts/tps65217.dtsi b/arch/arm/boot/dts/tps65217.dtsi new file mode 100644 index 000000000000..a63272422d76 --- /dev/null +++ b/arch/arm/boot/dts/tps65217.dtsi @@ -0,0 +1,56 @@ +/* + * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* + * Integrated Power Management Chip + * http://www.ti.com/lit/ds/symlink/tps65217.pdf + */ + +&tps { + compatible = "ti,tps65217"; + + regulators { + #address-cells = <1>; + #size-cells = <0>; + + dcdc1_reg: regulator@0 { + reg = <0>; + regulator-compatible = "dcdc1"; + }; + + dcdc2_reg: regulator@1 { + reg = <1>; + regulator-compatible = "dcdc2"; + }; + + dcdc3_reg: regulator@2 { + reg = <2>; + regulator-compatible = "dcdc3"; + }; + + ldo1_reg: regulator@3 { + reg = <3>; + regulator-compatible = "ldo1"; + }; + + ldo2_reg: regulator@4 { + reg = <4>; + regulator-compatible = "ldo2"; + }; + + ldo3_reg: regulator@5 { + reg = <5>; + regulator-compatible = "ldo3"; + }; + + ldo4_reg: regulator@6 { + reg = <6>; + regulator-compatible = "ldo4"; + }; + }; +}; From 9a154c8911e39e32bdbc2cd6c9b08a64e17612aa Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 11 Dec 2015 14:36:17 -0500 Subject: [PATCH 074/417] ftracetest: Fix instance test to use proper shell command for pids The ftracetest instance test used parsing of the "jobs" output to find the pid of the subshell that is executed previously. But this is not portable to all major shells that may run these tests. The proper way to get the pid of the subshell is the shell command "$!". This will return the pid of the previously executed command. Use that instead, otherwise the test does not work in all environments. Link: http://lkml.kernel.org/r/20151211143617.65f4d7a1@gandalf.local.home Reported-by: Michael Ellerman Signed-off-by: Steven Rostedt --- .../selftests/ftrace/test.d/instances/instance.tc | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/ftrace/test.d/instances/instance.tc b/tools/testing/selftests/ftrace/test.d/instances/instance.tc index 773e276ff90b..1e1abe0ad354 100644 --- a/tools/testing/selftests/ftrace/test.d/instances/instance.tc +++ b/tools/testing/selftests/ftrace/test.d/instances/instance.tc @@ -39,28 +39,23 @@ instance_slam() { } instance_slam & -x=`jobs -l` -p1=`echo $x | cut -d' ' -f2` +p1=$! echo $p1 instance_slam & -x=`jobs -l | tail -1` -p2=`echo $x | cut -d' ' -f2` +p2=$! echo $p2 instance_slam & -x=`jobs -l | tail -1` -p3=`echo $x | cut -d' ' -f2` +p3=$! echo $p3 instance_slam & -x=`jobs -l | tail -1` -p4=`echo $x | cut -d' ' -f2` +p4=$! echo $p4 instance_slam & -x=`jobs -l | tail -1` -p5=`echo $x | cut -d' ' -f2` +p5=$! echo $p5 ls -lR >/dev/null From 6e22c8366416251a3d88ba6c92d13d595089f0ed Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 12 Feb 2016 12:46:00 -0800 Subject: [PATCH 075/417] tracing, kasan: Silence Kasan warning in check_stack of stack_tracer When enabling stack trace via "echo 1 > /proc/sys/kernel/stack_tracer_enabled", the below KASAN warning is triggered: BUG: KASAN: stack-out-of-bounds in check_stack+0x344/0x848 at addr ffffffc0689ebab8 Read of size 8 by task ksoftirqd/4/29 page:ffffffbdc3a27ac0 count:0 mapcount:0 mapping: (null) index:0x0 flags: 0x0() page dumped because: kasan: bad access detected CPU: 4 PID: 29 Comm: ksoftirqd/4 Not tainted 4.5.0-rc1 #129 Hardware name: Freescale Layerscape 2085a RDB Board (DT) Call trace: [] dump_backtrace+0x0/0x3a0 [] show_stack+0x24/0x30 [] dump_stack+0xd8/0x168 [] kasan_report_error+0x6a0/0x920 [] kasan_report+0x70/0xb8 [] __asan_load8+0x60/0x78 [] check_stack+0x344/0x848 [] stack_trace_call+0x1c4/0x370 [] ftrace_ops_no_ops+0x2c0/0x590 [] ftrace_graph_call+0x0/0x14 [] fpsimd_thread_switch+0x24/0x1e8 [] __switch_to+0x34/0x218 [] __schedule+0x3ac/0x15b8 [] schedule+0x5c/0x178 [] smpboot_thread_fn+0x350/0x960 [] kthread+0x1d8/0x2b0 [] ret_from_fork+0x10/0x40 Memory state around the buggy address: ffffffc0689eb980: 00 00 00 00 00 00 00 00 f1 f1 f1 f1 00 f4 f4 f4 ffffffc0689eba00: f3 f3 f3 f3 00 00 00 00 00 00 00 00 00 00 00 00 >ffffffc0689eba80: 00 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 ^ ffffffc0689ebb00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffffffc0689ebb80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 The stacker tracer traverses the whole kernel stack when saving the max stack trace. It may touch the stack red zones to cause the warning. So, just disable the instrumentation to silence the warning. Link: http://lkml.kernel.org/r/1455309960-18930-1-git-send-email-yang.shi@linaro.org Signed-off-by: Yang Shi Signed-off-by: Steven Rostedt --- kernel/trace/trace_stack.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 202df6cffcca..2a1abbaca10e 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -156,7 +156,11 @@ check_stack(unsigned long ip, unsigned long *stack) for (; p < top && i < stack_trace_max.nr_entries; p++) { if (stack_dump_trace[i] == ULONG_MAX) break; - if (*p == stack_dump_trace[i]) { + /* + * The READ_ONCE_NOCHECK is used to let KASAN know that + * this is not a stack-out-of-bounds error. + */ + if ((READ_ONCE_NOCHECK(*p)) == stack_dump_trace[i]) { stack_dump_trace[x] = stack_dump_trace[i++]; this_size = stack_trace_index[x++] = (top - p) * sizeof(unsigned long); From 6697b2cf69d4363266ca47eaebc49ef13dabc1c9 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 4 Feb 2016 16:51:00 -0800 Subject: [PATCH 076/417] nfit: fix multi-interface dimm handling, acpi6.1 compatibility ACPI 6.1 clarified that multi-interface dimms require multiple control region entries (DCRs) per dimm. Previously we were assuming that a control region is only present when block-data-windows are present. This implementation was done with an eye to be compatibility with the looser ACPI 6.0 interpretation of this table. 1/ When coalescing the memory device (MEMDEV) tables for a single dimm, coalesce on device_handle rather than control region index. 2/ Whenever we disocver a control region with non-zero block windows re-scan for block-data-window (BDW) entries. We may need to revisit this if a DIMM ever implements a format interface outside of blk or pmem, but that is not on the foreseeable horizon. Cc: Signed-off-by: Dan Williams --- drivers/acpi/nfit.c | 71 ++++++++++++++++++++++----------------------- 1 file changed, 35 insertions(+), 36 deletions(-) diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index ad6d8c6b777e..424b362e8fdc 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -469,37 +469,16 @@ static void nfit_mem_find_spa_bdw(struct acpi_nfit_desc *acpi_desc, nfit_mem->bdw = NULL; } -static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc, +static void nfit_mem_init_bdw(struct acpi_nfit_desc *acpi_desc, struct nfit_mem *nfit_mem, struct acpi_nfit_system_address *spa) { u16 dcr = __to_nfit_memdev(nfit_mem)->region_index; struct nfit_memdev *nfit_memdev; struct nfit_flush *nfit_flush; - struct nfit_dcr *nfit_dcr; struct nfit_bdw *nfit_bdw; struct nfit_idt *nfit_idt; u16 idt_idx, range_index; - list_for_each_entry(nfit_dcr, &acpi_desc->dcrs, list) { - if (nfit_dcr->dcr->region_index != dcr) - continue; - nfit_mem->dcr = nfit_dcr->dcr; - break; - } - - if (!nfit_mem->dcr) { - dev_dbg(acpi_desc->dev, "SPA %d missing:%s%s\n", - spa->range_index, __to_nfit_memdev(nfit_mem) - ? "" : " MEMDEV", nfit_mem->dcr ? "" : " DCR"); - return -ENODEV; - } - - /* - * We've found enough to create an nvdimm, optionally - * find an associated BDW - */ - list_add(&nfit_mem->list, &acpi_desc->dimms); - list_for_each_entry(nfit_bdw, &acpi_desc->bdws, list) { if (nfit_bdw->bdw->region_index != dcr) continue; @@ -508,12 +487,12 @@ static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc, } if (!nfit_mem->bdw) - return 0; + return; nfit_mem_find_spa_bdw(acpi_desc, nfit_mem); if (!nfit_mem->spa_bdw) - return 0; + return; range_index = nfit_mem->spa_bdw->range_index; list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { @@ -538,8 +517,6 @@ static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc, } break; } - - return 0; } static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, @@ -548,7 +525,6 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, struct nfit_mem *nfit_mem, *found; struct nfit_memdev *nfit_memdev; int type = nfit_spa_type(spa); - u16 dcr; switch (type) { case NFIT_SPA_DCR: @@ -559,14 +535,18 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, } list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { - int rc; + struct nfit_dcr *nfit_dcr; + u32 device_handle; + u16 dcr; if (nfit_memdev->memdev->range_index != spa->range_index) continue; found = NULL; dcr = nfit_memdev->memdev->region_index; + device_handle = nfit_memdev->memdev->device_handle; list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) - if (__to_nfit_memdev(nfit_mem)->region_index == dcr) { + if (__to_nfit_memdev(nfit_mem)->device_handle + == device_handle) { found = nfit_mem; break; } @@ -579,6 +559,31 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, if (!nfit_mem) return -ENOMEM; INIT_LIST_HEAD(&nfit_mem->list); + list_add(&nfit_mem->list, &acpi_desc->dimms); + } + + list_for_each_entry(nfit_dcr, &acpi_desc->dcrs, list) { + if (nfit_dcr->dcr->region_index != dcr) + continue; + /* + * Record the control region for the dimm. For + * the ACPI 6.1 case, where there are separate + * control regions for the pmem vs blk + * interfaces, be sure to record the extended + * blk details. + */ + if (!nfit_mem->dcr) + nfit_mem->dcr = nfit_dcr->dcr; + else if (nfit_mem->dcr->windows == 0 + && nfit_dcr->dcr->windows) + nfit_mem->dcr = nfit_dcr->dcr; + break; + } + + if (dcr && !nfit_mem->dcr) { + dev_err(acpi_desc->dev, "SPA %d missing DCR %d\n", + spa->range_index, dcr); + return -ENODEV; } if (type == NFIT_SPA_DCR) { @@ -595,6 +600,7 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, nfit_mem->idt_dcr = nfit_idt->idt; break; } + nfit_mem_init_bdw(acpi_desc, nfit_mem, spa); } else { /* * A single dimm may belong to multiple SPA-PM @@ -603,13 +609,6 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, */ nfit_mem->memdev_pmem = nfit_memdev->memdev; } - - if (found) - continue; - - rc = nfit_mem_add(acpi_desc, nfit_mem, spa); - if (rc) - return rc; } return 0; From e817c2f33efb4aa7f02c98dfab9a5f8ff383ea7e Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 18 Feb 2016 12:04:08 +0100 Subject: [PATCH 077/417] selinux: Don't sleep inside inode_getsecid hook The inode_getsecid hook is called from contexts in which sleeping is not allowed, so we cannot revalidate inode security labels from there. Use the non-validating version of inode_security() instead. Reported-by: Benjamin Coddington Signed-off-by: Andreas Gruenbacher Acked-by: Stephen Smalley Signed-off-by: Paul Moore --- security/selinux/hooks.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index f8110cfd80ff..f1ab71504e1d 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3249,7 +3249,7 @@ static int selinux_inode_listsecurity(struct inode *inode, char *buffer, size_t static void selinux_inode_getsecid(struct inode *inode, u32 *secid) { - struct inode_security_struct *isec = inode_security(inode); + struct inode_security_struct *isec = inode_security_novalidate(inode); *secid = isec->sid; } From 2b8341b3f917c108b47f6a8a771a40d226c57883 Mon Sep 17 00:00:00 2001 From: Mario Kleiner Date: Fri, 19 Feb 2016 02:06:38 +0100 Subject: [PATCH 078/417] drm/radeon: Don't hang in radeon_flip_work_func on disabled crtc. (v2) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This fixes a regression introduced in Linux 4.4. Limit the amount of time radeon_flip_work_func can delay programming a page flip, by both limiting the maximum amount of time per wait cycle and the maximum number of wait cycles. Continue the flip if the limit is exceeded, even if that may result in a visual or timing glitch. This is to prevent a hang of page flips, as reported in fdo bug #93746: Disconnecting a DisplayPort display in parallel to a kms pageflip getting queued can cause the following hang of page flips and thereby an unusable desktop: 1. kms pageflip ioctl() queues pageflip -> queues execution of radeon_flip_work_func. 2. Hotunplug of display causes the driver to DPMS OFF the unplugged display. Display engine shuts down, scanout no longer moves, but stays at its resting position at start line of vblank. 3. radeon_flip_work_func executes while crtc is off, and due to the non-moving scanout position, the new flip delay code introduced into Linux 4.4 by commit 5b5561b3660d ("drm/radeon: Fixup hw vblank counter/ts..") enters an infinite wait loop. 4. After reconnecting the display, the pageflip continues to hang in 3. and the display doesn't update its view of the desktop. This patch fixes the Linux 4.4 regression from fdo bug #93746 v2: Skip wait immediately if !radeon_crtc->enabled, as suggested by Michel. Reported-by: Bernd Steinhauser Signed-off-by: Mario Kleiner Tested-by: Bernd Steinhauser Cc: # 4.4+ Cc: Michel Dänzer Cc: Alex Deucher Reviewed-by: Michel Dänzer Signed-off-by: Alex Deucher --- drivers/gpu/drm/radeon/radeon_display.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index 298ea1c453c3..2b9ba03a7c1a 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -403,7 +403,8 @@ static void radeon_flip_work_func(struct work_struct *__work) struct drm_crtc *crtc = &radeon_crtc->base; unsigned long flags; int r; - int vpos, hpos, stat, min_udelay; + int vpos, hpos, stat, min_udelay = 0; + unsigned repcnt = 4; struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id]; down_read(&rdev->exclusive_lock); @@ -454,7 +455,7 @@ static void radeon_flip_work_func(struct work_struct *__work) * In practice this won't execute very often unless on very fast * machines because the time window for this to happen is very small. */ - for (;;) { + while (radeon_crtc->enabled && repcnt--) { /* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank * start in hpos, and to the "fudged earlier" vblank start in * vpos. @@ -472,10 +473,22 @@ static void radeon_flip_work_func(struct work_struct *__work) /* Sleep at least until estimated real start of hw vblank */ spin_unlock_irqrestore(&crtc->dev->event_lock, flags); min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5); + if (min_udelay > vblank->framedur_ns / 2000) { + /* Don't wait ridiculously long - something is wrong */ + repcnt = 0; + break; + } usleep_range(min_udelay, 2 * min_udelay); spin_lock_irqsave(&crtc->dev->event_lock, flags); }; + if (!repcnt) + DRM_DEBUG_DRIVER("Delay problem on crtc %d: min_udelay %d, " + "framedur %d, linedur %d, stat %d, vpos %d, " + "hpos %d\n", work->crtc_id, min_udelay, + vblank->framedur_ns / 1000, + vblank->linedur_ns / 1000, stat, vpos, hpos); + /* do the flip (mmio) */ radeon_page_flip(rdev, radeon_crtc->crtc_id, work->base); From e1d09dc0ccc6c91e3916476f636edb76da1f65bb Mon Sep 17 00:00:00 2001 From: Mario Kleiner Date: Fri, 19 Feb 2016 02:06:39 +0100 Subject: [PATCH 079/417] drm/amdgpu: Don't hang in amdgpu_flip_work_func on disabled crtc. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This fixes a regression introduced in Linux 4.4. This is a port of the same fix for radeon-kms in the patch "drm/radeon: Don't hang in radeon_flip_work_func on disabled crtc. (v2)" Limit the amount of time amdgpu_flip_work_func can delay programming a page flip, by both limiting the maximum amount of time per wait cycle and the maximum number of wait cycles. Continue the flip if the limit is exceeded, even if that may result in a visual or timing glitch. This is to prevent a hang of page flips, as reported in fdo bug #93746: Disconnecting a DisplayPort display in parallel to a kms pageflip getting queued can cause the following hang of page flips and thereby an unusable desktop: 1. kms pageflip ioctl() queues pageflip -> queues execution of amdgpu_flip_work_func. 2. Hotunplug of display causes the driver to DPMS OFF the unplugged display. Display engine shuts down, scanout no longer moves, but stays at its resting position at start line of vblank. 3. amdgpu_flip_work_func executes while crtc is off, and due to the non-moving scanout position, the new flip delay code introduced into Linux 4.4 by commit 8e36f9d33c13 ("drm/amdgpu: Fixup hw vblank counter/ts..") enters an infinite wait loop. 4. After reconnecting the display, the pageflip continues to hang in 3. and the display doesn't update its view of the desktop. This patch fixes the Linux 4.4 regression from fdo bug #93746 Reported-by: Bernd Steinhauser Signed-off-by: Mario Kleiner Cc: # 4.4+ Cc: Michel Dänzer Cc: Alex Deucher Reviewed-by: Michel Dänzer Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_display.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index acd066d0a805..8297bc319369 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -72,8 +72,8 @@ static void amdgpu_flip_work_func(struct work_struct *__work) struct drm_crtc *crtc = &amdgpuCrtc->base; unsigned long flags; - unsigned i; - int vpos, hpos, stat, min_udelay; + unsigned i, repcnt = 4; + int vpos, hpos, stat, min_udelay = 0; struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id]; amdgpu_flip_wait_fence(adev, &work->excl); @@ -96,7 +96,7 @@ static void amdgpu_flip_work_func(struct work_struct *__work) * In practice this won't execute very often unless on very fast * machines because the time window for this to happen is very small. */ - for (;;) { + while (amdgpuCrtc->enabled && repcnt--) { /* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank * start in hpos, and to the "fudged earlier" vblank start in * vpos. @@ -114,10 +114,22 @@ static void amdgpu_flip_work_func(struct work_struct *__work) /* Sleep at least until estimated real start of hw vblank */ spin_unlock_irqrestore(&crtc->dev->event_lock, flags); min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5); + if (min_udelay > vblank->framedur_ns / 2000) { + /* Don't wait ridiculously long - something is wrong */ + repcnt = 0; + break; + } usleep_range(min_udelay, 2 * min_udelay); spin_lock_irqsave(&crtc->dev->event_lock, flags); }; + if (!repcnt) + DRM_DEBUG_DRIVER("Delay problem on crtc %d: min_udelay %d, " + "framedur %d, linedur %d, stat %d, vpos %d, " + "hpos %d\n", work->crtc_id, min_udelay, + vblank->framedur_ns / 1000, + vblank->linedur_ns / 1000, stat, vpos, hpos); + /* do the flip (mmio) */ adev->mode_info.funcs->page_flip(adev, work->crtc_id, work->base); /* set the flip status */ From 747ffe11b440ef9ea752888806d3aac677ca52a4 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 19 Feb 2016 15:21:14 -0800 Subject: [PATCH 080/417] libnvdimm, tools/testing/nvdimm: fix 'ars_status' output buffer sizing Use the output length specified in the command to size the receive buffer rather than the arbitrary 4K limit. This bug was hiding the fact that the ndctl implementation of ndctl_bus_cmd_new_ars_status() was not specifying an output buffer size. Cc: Cc: Vishal Verma Signed-off-by: Dan Williams --- drivers/acpi/nfit.c | 13 +++++++------ drivers/nvdimm/bus.c | 8 ++++---- include/linux/libnvdimm.h | 1 - tools/testing/nvdimm/test/nfit.c | 8 ++++++-- 4 files changed, 17 insertions(+), 13 deletions(-) diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index 424b362e8fdc..1d4b9c6bdf45 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -1516,13 +1516,13 @@ static int ars_do_start(struct nvdimm_bus_descriptor *nd_desc, } static int ars_get_status(struct nvdimm_bus_descriptor *nd_desc, - struct nd_cmd_ars_status *cmd) + struct nd_cmd_ars_status *cmd, u32 size) { int rc; while (1) { rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_STATUS, cmd, - sizeof(*cmd)); + size); if (rc || cmd->status & 0xffff) return -ENXIO; @@ -1580,6 +1580,7 @@ static int acpi_nfit_find_poison(struct acpi_nfit_desc *acpi_desc, struct nd_cmd_ars_start *ars_start = NULL; struct nd_cmd_ars_cap *ars_cap = NULL; u64 start, len, cur, remaining; + u32 ars_status_size; int rc; ars_cap = kzalloc(sizeof(*ars_cap), GFP_KERNEL); @@ -1609,14 +1610,14 @@ static int acpi_nfit_find_poison(struct acpi_nfit_desc *acpi_desc, * Check if a full-range ARS has been run. If so, use those results * without having to start a new ARS. */ - ars_status = kzalloc(ars_cap->max_ars_out + sizeof(*ars_status), - GFP_KERNEL); + ars_status_size = ars_cap->max_ars_out; + ars_status = kzalloc(ars_status_size, GFP_KERNEL); if (!ars_status) { rc = -ENOMEM; goto out; } - rc = ars_get_status(nd_desc, ars_status); + rc = ars_get_status(nd_desc, ars_status, ars_status_size); if (rc) goto out; @@ -1646,7 +1647,7 @@ static int acpi_nfit_find_poison(struct acpi_nfit_desc *acpi_desc, if (rc) goto out; - rc = ars_get_status(nd_desc, ars_status); + rc = ars_get_status(nd_desc, ars_status, ars_status_size); if (rc) goto out; diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 7e2c43f701bc..99953b34fa1d 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -392,8 +392,8 @@ static const struct nd_cmd_desc __nd_cmd_bus_descs[] = { .out_sizes = { 4, }, }, [ND_CMD_ARS_STATUS] = { - .out_num = 2, - .out_sizes = { 4, UINT_MAX, }, + .out_num = 3, + .out_sizes = { 4, 4, UINT_MAX, }, }, }; @@ -442,8 +442,8 @@ u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd, return in_field[1]; else if (nvdimm && cmd == ND_CMD_VENDOR && idx == 2) return out_field[1]; - else if (!nvdimm && cmd == ND_CMD_ARS_STATUS && idx == 1) - return ND_CMD_ARS_STATUS_MAX; + else if (!nvdimm && cmd == ND_CMD_ARS_STATUS && idx == 2) + return out_field[1] - 8; return UINT_MAX; } diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index bed40dff0e86..c736382fd260 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -28,7 +28,6 @@ enum { ND_IOCTL_MAX_BUFLEN = SZ_4M, ND_CMD_MAX_ELEM = 4, ND_CMD_MAX_ENVELOPE = 16, - ND_CMD_ARS_STATUS_MAX = SZ_4K, ND_MAX_MAPPINGS = 32, /* region flag indicating to direct-map persistent memory by default */ diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 90bd2ea41032..b3281dcd4a5d 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -217,13 +217,16 @@ static int nfit_test_cmd_set_config_data(struct nd_cmd_set_config_hdr *nd_cmd, return rc; } +#define NFIT_TEST_ARS_RECORDS 4 + static int nfit_test_cmd_ars_cap(struct nd_cmd_ars_cap *nd_cmd, unsigned int buf_len) { if (buf_len < sizeof(*nd_cmd)) return -EINVAL; - nd_cmd->max_ars_out = 256; + nd_cmd->max_ars_out = sizeof(struct nd_cmd_ars_status) + + NFIT_TEST_ARS_RECORDS * sizeof(struct nd_ars_record); nd_cmd->status = (ND_ARS_PERSISTENT | ND_ARS_VOLATILE) << 16; return 0; @@ -246,7 +249,8 @@ static int nfit_test_cmd_ars_status(struct nd_cmd_ars_status *nd_cmd, if (buf_len < sizeof(*nd_cmd)) return -EINVAL; - nd_cmd->out_length = 256; + nd_cmd->out_length = sizeof(struct nd_cmd_ars_status); + /* TODO: emit error records */ nd_cmd->num_records = 0; nd_cmd->address = 0; nd_cmd->length = -1ULL; From 2feb55f89096b22e2de066e411a3263647211987 Mon Sep 17 00:00:00 2001 From: Wouter van Kesteren Date: Tue, 16 Feb 2016 22:20:59 +0100 Subject: [PATCH 081/417] fs: allow no_seek_end_llseek to actually seek The user-visible impact of the issue is for example that without this patch sensors-detect breaks when trying to seek in /dev/cpu/0/cpuid. '~0ULL' is a 'unsigned long long' that when converted to a loff_t, which is signed, gets turned into -1. later in vfs_setpos we have 'if (offset > maxsize)', which makes it always return EINVAL. Fixes: b25472f9b961 ("new helpers: no_seek_end_llseek{,_size}()") Signed-off-by: Wouter van Kesteren Reviewed-by: Andreas Dilger Signed-off-by: Al Viro --- fs/read_write.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/read_write.c b/fs/read_write.c index 324ec271cc4e..0c8782aa3d71 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "internal.h" #include @@ -183,7 +184,7 @@ loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence) switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, - ~0ULL, 0); + OFFSET_MAX, 0); default: return -EINVAL; } From 0e9a7da51b028aee7a72c95096c99fe5ea2a01f0 Mon Sep 17 00:00:00 2001 From: Mateusz Guzik Date: Thu, 4 Feb 2016 02:56:30 +0100 Subject: [PATCH 082/417] xattr handlers: plug a lock leak in simple_xattr_list The code could leak xattrs->lock on error. Problem introduced with 786534b92f3ce68f4 "tmpfs: listxattr should include POSIX ACL xattrs". Signed-off-by: Mateusz Guzik Signed-off-by: Al Viro --- fs/xattr.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/xattr.c b/fs/xattr.c index 07d0e47f6a7f..4861322e28e8 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -940,7 +940,7 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, bool trusted = capable(CAP_SYS_ADMIN); struct simple_xattr *xattr; ssize_t remaining_size = size; - int err; + int err = 0; #ifdef CONFIG_FS_POSIX_ACL if (inode->i_acl) { @@ -965,11 +965,11 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, err = xattr_list_one(&buffer, &remaining_size, xattr->name); if (err) - return err; + break; } spin_unlock(&xattrs->lock); - return size - remaining_size; + return err ? err : size - remaining_size; } /* From 0bacbe528e26422e424d110ebda4ec68ea0fd5eb Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 2 Feb 2016 02:28:05 +0000 Subject: [PATCH 083/417] affs_do_readpage_ofs(): just use kmap_atomic() around memcpy() It forgets kunmap() on a failure exit, but there's really no point keeping the page kmapped at all - after all, what we are doing is a bunch of memcpy() into the parts of page, so kmap_atomic()/kunmap_atomic() just around those memcpy() is enough. Spotted-by: Insu Yun Signed-off-by: Al Viro --- fs/affs/file.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/affs/file.c b/fs/affs/file.c index 0548c53f41d5..22fc7c802d69 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -511,8 +511,6 @@ affs_do_readpage_ofs(struct page *page, unsigned to) pr_debug("%s(%lu, %ld, 0, %d)\n", __func__, inode->i_ino, page->index, to); BUG_ON(to > PAGE_CACHE_SIZE); - kmap(page); - data = page_address(page); bsize = AFFS_SB(sb)->s_data_blksize; tmp = page->index << PAGE_CACHE_SHIFT; bidx = tmp / bsize; @@ -524,14 +522,15 @@ affs_do_readpage_ofs(struct page *page, unsigned to) return PTR_ERR(bh); tmp = min(bsize - boff, to - pos); BUG_ON(pos + tmp > to || tmp > bsize); + data = kmap_atomic(page); memcpy(data + pos, AFFS_DATA(bh) + boff, tmp); + kunmap_atomic(data); affs_brelse(bh); bidx++; pos += tmp; boff = 0; } flush_dcache_page(page); - kunmap(page); return 0; } From 7ae8fd0351f912b075149a1e03a017be8b903b9a Mon Sep 17 00:00:00 2001 From: Maxim Patlasov Date: Tue, 16 Feb 2016 11:45:33 -0800 Subject: [PATCH 084/417] fs/pnode.c: treat zero mnt_group_id-s as unequal propagate_one(m) calculates "type" argument for copy_tree() like this: > if (m->mnt_group_id == last_dest->mnt_group_id) { > type = CL_MAKE_SHARED; > } else { > type = CL_SLAVE; > if (IS_MNT_SHARED(m)) > type |= CL_MAKE_SHARED; > } The "type" argument then governs clone_mnt() behavior with respect to flags and mnt_master of new mount. When we iterate through a slave group, it is possible that both current "m" and "last_dest" are not shared (although, both are slaves, i.e. have non-NULL mnt_master-s). Then the comparison above erroneously makes new mount shared and sets its mnt_master to last_source->mnt_master. The patch fixes the problem by handling zero mnt_group_id-s as though they are unequal. The similar problem exists in the implementation of "else" clause above when we have to ascend upward in the master/slave tree by calling: > last_source = last_source->mnt_master; > last_dest = last_source->mnt_parent; proper number of times. The last step is governed by "n->mnt_group_id != last_dest->mnt_group_id" condition that may lie if both are zero. The patch fixes this case in the same way as the former one. [AV: don't open-code an obvious helper...] Signed-off-by: Maxim Patlasov Signed-off-by: Al Viro --- fs/pnode.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/fs/pnode.c b/fs/pnode.c index 6367e1e435c6..c524fdddc7fb 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -202,6 +202,11 @@ static struct mount *last_dest, *last_source, *dest_master; static struct mountpoint *mp; static struct hlist_head *list; +static inline bool peers(struct mount *m1, struct mount *m2) +{ + return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id; +} + static int propagate_one(struct mount *m) { struct mount *child; @@ -212,7 +217,7 @@ static int propagate_one(struct mount *m) /* skip if mountpoint isn't covered by it */ if (!is_subdir(mp->m_dentry, m->mnt.mnt_root)) return 0; - if (m->mnt_group_id == last_dest->mnt_group_id) { + if (peers(m, last_dest)) { type = CL_MAKE_SHARED; } else { struct mount *n, *p; @@ -223,7 +228,7 @@ static int propagate_one(struct mount *m) last_source = last_source->mnt_master; last_dest = last_source->mnt_parent; } - if (n->mnt_group_id != last_dest->mnt_group_id) { + if (!peers(n, last_dest)) { last_source = last_source->mnt_master; last_dest = last_source->mnt_parent; } From e5bdfd50d6f76077bf8441d130c606229e100d40 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 20 Feb 2016 14:19:34 -0800 Subject: [PATCH 085/417] Revert "usb: hub: do not clear BOS field during reset device" This reverts commit d8f00cd685f5c8e0def8593e520a7fef12c22407. Tony writes: This upstream commit is causing an oops: d8f00cd685f5 ("usb: hub: do not clear BOS field during reset device") This patch has already been included in several -stable kernels. Here are the affected kernels: 4.5.0-rc4 (current git) 4.4.2 4.3.6 (currently in review) 4.1.18 3.18.27 3.14.61 How to reproduce the problem: Boot kernel with slub debugging enabled (otherwise memory corruption will cause random oopses later instead of immediately) Plug in USB 3.0 disk to xhci USB 3.0 port dd if=/dev/sdc of=/dev/null bs=65536 (where /dev/sdc is the USB 3.0 disk) Unplug USB cable while dd is still going Oops is immediate: Reported-by: Tony Battersby Cc: Du, Changbin Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hub.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 350dcd9af5d8..51b436918f78 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -5401,6 +5401,7 @@ static int usb_reset_and_verify_device(struct usb_device *udev) } bos = udev->bos; + udev->bos = NULL; for (i = 0; i < SET_CONFIG_TRIES; ++i) { @@ -5493,11 +5494,8 @@ static int usb_reset_and_verify_device(struct usb_device *udev) usb_set_usb2_hardware_lpm(udev, 1); usb_unlocked_enable_lpm(udev); usb_enable_ltm(udev); - /* release the new BOS descriptor allocated by hub_port_init() */ - if (udev->bos != bos) { - usb_release_bos_descriptor(udev); - udev->bos = bos; - } + usb_release_bos_descriptor(udev); + udev->bos = bos; return 0; re_enumerate: From 7a64cd887fdb97f074c3fda03bee0bfb9faceac3 Mon Sep 17 00:00:00 2001 From: Lisa Du Date: Wed, 17 Feb 2016 09:32:52 +0800 Subject: [PATCH 086/417] drivers: android: correct the size of struct binder_uintptr_t for BC_DEAD_BINDER_DONE There's one point was missed in the patch commit da49889deb34 ("staging: binder: Support concurrent 32 bit and 64 bit processes."). When configure BINDER_IPC_32BIT, the size of binder_uintptr_t was 32bits, but size of void * is 64bit on 64bit system. Correct it here. Signed-off-by: Lisa Du Signed-off-by: Nicolas Boichat Fixes: da49889deb34 ("staging: binder: Support concurrent 32 bit and 64 bit processes.") Cc: Acked-by: Olof Johansson Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index a39e85f9efa9..7d00b7a015ea 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2074,7 +2074,7 @@ static int binder_thread_write(struct binder_proc *proc, if (get_user(cookie, (binder_uintptr_t __user *)ptr)) return -EFAULT; - ptr += sizeof(void *); + ptr += sizeof(cookie); list_for_each_entry(w, &proc->delivered_death, entry) { struct binder_ref_death *tmp_death = container_of(w, struct binder_ref_death, work); From e35a49b163fa2108cf82c6f07a3fbe371e468878 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Sun, 17 Jan 2016 21:36:03 +0100 Subject: [PATCH 087/417] MAINTAINERS: update bq27xxx driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Update reviewers for bq27xxx, so that Pali and Andrew are reviewers with status and maintainer inherited from the power supply subsystem entry. Signed-off-by: Sebastian Reichel Acked-by: Pali Rohár Acked-by: Andrew F. Davis --- MAINTAINERS | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 4978dc19a4d2..116a448ae77e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7686,13 +7686,13 @@ S: Maintained F: arch/nios2/ NOKIA N900 POWER SUPPLY DRIVERS -M: Pali Rohár -S: Maintained +R: Pali Rohár F: include/linux/power/bq2415x_charger.h F: include/linux/power/bq27xxx_battery.h F: include/linux/power/isp1704_charger.h F: drivers/power/bq2415x_charger.c F: drivers/power/bq27xxx_battery.c +F: drivers/power/bq27xxx_battery_i2c.c F: drivers/power/isp1704_charger.c F: drivers/power/rx51_battery.c @@ -9558,6 +9558,12 @@ M: Andreas Noever S: Maintained F: drivers/thunderbolt/ +TI BQ27XXX POWER SUPPLY DRIVER +R: Andrew F. Davis +F: include/linux/power/bq27xxx_battery.h +F: drivers/power/bq27xxx_battery.c +F: drivers/power/bq27xxx_battery_i2c.c + TIMEKEEPING, CLOCKSOURCE CORE, NTP, ALARMTIMER M: John Stultz M: Thomas Gleixner From 9aafabc7fece13c8e2a1f680908c73ee19f0f79b Mon Sep 17 00:00:00 2001 From: Ivaylo Dimitrov Date: Tue, 2 Feb 2016 14:47:37 +0200 Subject: [PATCH 088/417] power: bq27xxx_battery: Restore device name MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch <703df6c09795> ("power: bq27xxx_battery: Reorganize I2C into a module") has removed the device name numbering from bq27xxx_battery_i2c_probe. Fix that by restoring the code. Fixes: 703df6c097956d17a818e63961c82e8e9eef9fef Signed-off-by: Ivaylo Dimitrov Reviewed-by: Pali Rohár Tested-by: Pali Rohár Signed-off-by: Sebastian Reichel --- drivers/power/bq27xxx_battery_i2c.c | 37 ++++++++++++++++++++++++--- include/linux/power/bq27xxx_battery.h | 1 + 2 files changed, 35 insertions(+), 3 deletions(-) diff --git a/drivers/power/bq27xxx_battery_i2c.c b/drivers/power/bq27xxx_battery_i2c.c index 9429e66be096..8eafc6f0df88 100644 --- a/drivers/power/bq27xxx_battery_i2c.c +++ b/drivers/power/bq27xxx_battery_i2c.c @@ -21,6 +21,9 @@ #include +static DEFINE_IDR(battery_id); +static DEFINE_MUTEX(battery_mutex); + static irqreturn_t bq27xxx_battery_irq_handler_thread(int irq, void *data) { struct bq27xxx_device_info *di = data; @@ -70,19 +73,33 @@ static int bq27xxx_battery_i2c_probe(struct i2c_client *client, { struct bq27xxx_device_info *di; int ret; + char *name; + int num; + + /* Get new ID for the new battery device */ + mutex_lock(&battery_mutex); + num = idr_alloc(&battery_id, client, 0, 0, GFP_KERNEL); + mutex_unlock(&battery_mutex); + if (num < 0) + return num; + + name = devm_kasprintf(&client->dev, GFP_KERNEL, "%s-%d", id->name, num); + if (!name) + goto err_mem; di = devm_kzalloc(&client->dev, sizeof(*di), GFP_KERNEL); if (!di) - return -ENOMEM; + goto err_mem; + di->id = num; di->dev = &client->dev; di->chip = id->driver_data; - di->name = id->name; + di->name = name; di->bus.read = bq27xxx_battery_i2c_read; ret = bq27xxx_battery_setup(di); if (ret) - return ret; + goto err_failed; /* Schedule a polling after about 1 min */ schedule_delayed_work(&di->work, 60 * HZ); @@ -103,6 +120,16 @@ static int bq27xxx_battery_i2c_probe(struct i2c_client *client, } return 0; + +err_mem: + ret = -ENOMEM; + +err_failed: + mutex_lock(&battery_mutex); + idr_remove(&battery_id, num); + mutex_unlock(&battery_mutex); + + return ret; } static int bq27xxx_battery_i2c_remove(struct i2c_client *client) @@ -111,6 +138,10 @@ static int bq27xxx_battery_i2c_remove(struct i2c_client *client) bq27xxx_battery_teardown(di); + mutex_lock(&battery_mutex); + idr_remove(&battery_id, di->id); + mutex_unlock(&battery_mutex); + return 0; } diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index 998d8f1c3c91..b50c0492629d 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -49,6 +49,7 @@ struct bq27xxx_reg_cache { struct bq27xxx_device_info { struct device *dev; + int id; enum bq27xxx_chip chip; const char *name; struct bq27xxx_access_methods bus; From 4328daa2e79ed904a42ce00a9f38b9c36b44b21a Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Sun, 21 Feb 2016 19:09:22 -0500 Subject: [PATCH 089/417] dm: fix dm_rq_target_io leak on faults with .request_fn DM w/ blk-mq paths Using request-based DM mpath configured with the following stacking (.request_fn DM mpath ontop of scsi-mq paths): echo Y > /sys/module/scsi_mod/parameters/use_blk_mq echo N > /sys/module/dm_mod/parameters/use_blk_mq 'struct dm_rq_target_io' would leak if a request is requeued before a blk-mq clone is allocated (or fails to allocate). free_rq_tio() wasn't being called. kmemleak reported: unreferenced object 0xffff8800b90b98c0 (size 112): comm "kworker/7:1H", pid 5692, jiffies 4295056109 (age 78.589s) hex dump (first 32 bytes): 00 d0 5c 2c 03 88 ff ff 40 00 bf 01 00 c9 ff ff ..\,....@....... e0 d9 b1 34 00 88 ff ff 00 00 00 00 00 00 00 00 ...4............ backtrace: [] kmemleak_alloc+0x4e/0xb0 [] kmem_cache_alloc+0xc3/0x1e0 [] mempool_alloc_slab+0x15/0x20 [] mempool_alloc+0x6e/0x170 [] dm_old_prep_fn+0x3c/0x180 [dm_mod] [] blk_peek_request+0x168/0x290 [] dm_request_fn+0xb2/0x1b0 [dm_mod] [] __blk_run_queue+0x33/0x40 [] blk_delay_work+0x25/0x40 [] process_one_work+0x14f/0x3d0 [] worker_thread+0x125/0x4b0 [] kthread+0xd8/0xf0 [] ret_from_fork+0x3f/0x70 [] 0xffffffffffffffff crash> struct -o dm_rq_target_io struct dm_rq_target_io { ... } SIZE: 112 Fixes: e5863d9ad7 ("dm: allocate requests in target when stacking on blk-mq devices") Cc: stable@vger.kernel.org # 4.0+ Signed-off-by: Mike Snitzer --- drivers/md/dm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 5df40480228b..dd834927bc66 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1191,6 +1191,8 @@ static void dm_unprep_request(struct request *rq) if (clone) free_rq_clone(clone); + else if (!tio->md->queue->mq_ops) + free_rq_tio(tio); } /* From f6bf0fa14cf848ae770e0b7842c9b11ce2f01645 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Fri, 12 Feb 2016 16:03:05 +1100 Subject: [PATCH 090/417] powerpc/eeh: Fix partial hotplug criterion During error recovery, the device could be removed as part of the partial hotplug. The criterion used to come with partial hotplug is: if the device driver provides error_detected(), slot_reset() and resume() callbacks, it's immune from hotplug. Otherwise, it's going to experience partial hotplug during EEH recovery. But the criterion isn't correct enough: mlx4_core driver for Mellanox adapters provides error_detected(), slot_reset() callbacks, but resume() isn't there. Those Mellanox adapters won't be to involved in the partial hotplug. This fixes the criterion to a practical one: adpater with driver that provides error_detected(), slot_reset() will be immune from partial hotplug. resume() isn't mandatory. Fixes: f2da4ccf ("powerpc/eeh: More relaxed hotplug criterion") Cc: stable@vger.kernel.org #v4.4+ Signed-off-by: Gavin Shan Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/eeh_driver.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index f69ecaa7ce33..52c1e273f8cd 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -418,8 +418,7 @@ static void *eeh_rmv_device(void *data, void *userdata) eeh_pcid_put(dev); if (driver->err_handler && driver->err_handler->error_detected && - driver->err_handler->slot_reset && - driver->err_handler->resume) + driver->err_handler->slot_reset) return NULL; } From 9ab3ac233a8b4ffcc27c8475b83dee49fc46bc76 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Sat, 20 Feb 2016 20:41:54 +0530 Subject: [PATCH 091/417] powerpc/mm/hash: Clear the invalid slot information correctly We can get a hash pte fault with 4k base page size and find the pte already inserted with 64K base page size. In that case we need to clear the existing slot information from the old pte. Fix this correctly With THP, we also clear the slot information with respect to all the 64K hash pte mapping that 16MB page. They are all invalid now. This make sure we don't find the slot valid when we fault with 4k base page size. Finding the slot valid should not result in any wrong behavior because we do check again in hash page table for the validity. But we can avoid that check completely. Fixes: a43c0eb8364c022 ("powerpc/mm: Convert 4k hash insert to C") Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/mm/hash64_64k.c | 8 +++++++- arch/powerpc/mm/hugepage-hash64.c | 12 +++++++++++- 2 files changed, 18 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c index 0762c1e08c88..edb09912f0c9 100644 --- a/arch/powerpc/mm/hash64_64k.c +++ b/arch/powerpc/mm/hash64_64k.c @@ -111,7 +111,13 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, */ if (!(old_pte & _PAGE_COMBO)) { flush_hash_page(vpn, rpte, MMU_PAGE_64K, ssize, flags); - old_pte &= ~_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND; + /* + * clear the old slot details from the old and new pte. + * On hash insert failure we use old pte value and we don't + * want slot information there if we have a insert failure. + */ + old_pte &= ~(_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND); + new_pte &= ~(_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND); goto htab_insert_hpte; } /* diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c index 49b152b0f926..eb2accdd76fd 100644 --- a/arch/powerpc/mm/hugepage-hash64.c +++ b/arch/powerpc/mm/hugepage-hash64.c @@ -78,9 +78,19 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, * base page size. This is because demote_segment won't flush * hash page table entries. */ - if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO)) + if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO)) { flush_hash_hugepage(vsid, ea, pmdp, MMU_PAGE_64K, ssize, flags); + /* + * With THP, we also clear the slot information with + * respect to all the 64K hash pte mapping the 16MB + * page. They are all invalid now. This make sure we + * don't find the slot valid when we fault with 4k + * base page size. + * + */ + memset(hpte_slot_array, 0, PTE_FRAG_SIZE); + } } valid = hpte_valid(hpte_slot_array, index); From 342300cc9cd3428bc6bfe5809bfcc1b9a0f06702 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Fri, 19 Feb 2016 14:44:14 +0100 Subject: [PATCH 092/417] s390/compat: correct restore of high gprs on signal return git commit 8070361799ae1e3f4ef347bd10f0a508ac10acfb "s390: add support for vector extension" broke 31-bit compat processes in regard to signal handling. The restore_sigregs_ext32() function is used to restore the additional elements from the user space signal frame. Among the additional elements are the upper registers halves for 64-bit register support for 31-bit processes. The copy_from_user that is used to retrieve the high-gprs array from the user stack uses an incorrect length, 8 bytes instead of 64 bytes. This causes incorrect upper register halves to get loaded. Cc: stable@vger.kernel.org # 3.8+ Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/compat_signal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index 66c94417c0ba..4af60374eba0 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -271,7 +271,7 @@ static int restore_sigregs_ext32(struct pt_regs *regs, /* Restore high gprs from signal stack */ if (__copy_from_user(&gprs_high, &sregs_ext->gprs_high, - sizeof(&sregs_ext->gprs_high))) + sizeof(sregs_ext->gprs_high))) return -EFAULT; for (i = 0; i < NUM_GPRS; i++) *(__u32 *)®s->gprs[i] = gprs_high[i]; From 1b17cb796f5d40ffa239c6926385abd83a77a49b Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Fri, 19 Feb 2016 15:29:05 +0100 Subject: [PATCH 093/417] s390/fpu: signals vs. floating point control register git commit 904818e2f229f3d94ec95f6932a6358c81e73d78 "s390/kernel: introduce fpu-internal.h with fpu helper functions" introduced the fpregs_store / fp_regs_load helper. These function fail to save and restore the floating pointer control registers. The effect is that the FPC is not correctly handled on signal delivery and signal return. Cc: stable@vger.kernel.org # 4.4 Signed-off-by: Martin Schwidefsky --- arch/s390/include/asm/fpu/internal.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/s390/include/asm/fpu/internal.h b/arch/s390/include/asm/fpu/internal.h index ea91ddfe54eb..629c90865a07 100644 --- a/arch/s390/include/asm/fpu/internal.h +++ b/arch/s390/include/asm/fpu/internal.h @@ -40,6 +40,7 @@ static inline void convert_fp_to_vx(__vector128 *vxrs, freg_t *fprs) static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu) { fpregs->pad = 0; + fpregs->fpc = fpu->fpc; if (MACHINE_HAS_VX) convert_vx_to_fp((freg_t *)&fpregs->fprs, fpu->vxrs); else @@ -49,6 +50,7 @@ static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu) static inline void fpregs_load(_s390_fp_regs *fpregs, struct fpu *fpu) { + fpu->fpc = fpregs->fpc; if (MACHINE_HAS_VX) convert_fp_to_vx(fpu->vxrs, (freg_t *)&fpregs->fprs); else From c7edd7f99cdaec65e9303b4c9edc19bb595564ed Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Fri, 19 Feb 2016 11:04:45 +0100 Subject: [PATCH 094/417] ARM: 8534/1: virt: fix hyp-stub build for pre-ARMv7 CPUs ARMv6 CPUs do not have virtualisation extensions, but hyp-stub.S is still included into the image to keep it generic. In order to use ARMv7 instructions during HYP initialisation, add -march=armv7-a flag to hyp-stub's build. On an ARMv6 CPU, __hyp_stub_install returns as soon as it detects that the mode isn't HYP, so we will never reach those instructions. Signed-off-by: Jean-Philippe Brucker Signed-off-by: Russell King --- arch/arm/boot/compressed/Makefile | 2 ++ arch/arm/kernel/Makefile | 1 + 2 files changed, 3 insertions(+) diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 7a6a58ef8aaf..43788b1a1ac5 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -195,5 +195,7 @@ CFLAGS_font.o := -Dstatic= $(obj)/font.c: $(FONTC) $(call cmd,shipped) +AFLAGS_hyp-stub.o := -Wa,-march=armv7-a + $(obj)/hyp-stub.S: $(srctree)/arch/$(SRCARCH)/kernel/hyp-stub.S $(call cmd,shipped) diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 2c5f160be65e..ad325a8c7e1e 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -88,6 +88,7 @@ obj-$(CONFIG_DEBUG_LL) += debug.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-$(CONFIG_ARM_VIRT_EXT) += hyp-stub.o +AFLAGS_hyp-stub.o :=-Wa,-march=armv7-a ifeq ($(CONFIG_ARM_PSCI),y) obj-$(CONFIG_SMP) += psci_smp.o endif From 5af9a454769bb5528ba1e5268e5649414ae832bd Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Wed, 17 Feb 2016 14:17:42 +0200 Subject: [PATCH 095/417] drm/i915: Add helper to get a display power ref if it was already enabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We have many places in the code where we check if a given display power domain is enabled and if so access registers backed by this power domain. We assumed that some modeset lock will prevent the power reference from vanishing in the middle of the HW access, but this assumption doesn't always hold. In such cases we get either the wakeref not held, or an unclaimed register access error message. To fix this in a future-proof way that's independent of other locks wrap any such access with a get_ref_if_enabled()/put_ref() pair. Kudos to Ville and Joonas for the ideas of this new interface. v2: - init the power_domains ptr when declaring it everywhere (Joonas) v3: - don't report the device to be powered if runtime PM is disabled CC: Mika Kuoppala CC: Chris Wilson CC: Joonas Lahtinen CC: Ville Syrjälä Signed-off-by: Imre Deak Reviewed-by: Joonas Lahtinen Link: http://patchwork.freedesktop.org/patch/msgid/1455711462-7442-1-git-send-email-imre.deak@intel.com (cherry picked from commit 09731280028ce03e6a27e1998137f1775a2839f3) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_drv.h | 3 + drivers/gpu/drm/i915/intel_runtime_pm.c | 100 +++++++++++++++++++++--- 2 files changed, 94 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index ea5415851c6e..df7f3cb66056 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -1428,6 +1428,8 @@ bool __intel_display_power_is_enabled(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain); void intel_display_power_get(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain); +bool intel_display_power_get_if_enabled(struct drm_i915_private *dev_priv, + enum intel_display_power_domain domain); void intel_display_power_put(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain); @@ -1514,6 +1516,7 @@ enable_rpm_wakeref_asserts(struct drm_i915_private *dev_priv) enable_rpm_wakeref_asserts(dev_priv) void intel_runtime_pm_get(struct drm_i915_private *dev_priv); +bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv); void intel_runtime_pm_get_noresume(struct drm_i915_private *dev_priv); void intel_runtime_pm_put(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index ddbdbffe829a..89dcc99ac3ca 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -1442,6 +1442,22 @@ static void chv_pipe_power_well_disable(struct drm_i915_private *dev_priv, chv_set_pipe_power_well(dev_priv, power_well, false); } +static void +__intel_display_power_get_domain(struct drm_i915_private *dev_priv, + enum intel_display_power_domain domain) +{ + struct i915_power_domains *power_domains = &dev_priv->power_domains; + struct i915_power_well *power_well; + int i; + + for_each_power_well(i, power_well, BIT(domain), power_domains) { + if (!power_well->count++) + intel_power_well_enable(dev_priv, power_well); + } + + power_domains->domain_use_count[domain]++; +} + /** * intel_display_power_get - grab a power domain reference * @dev_priv: i915 device instance @@ -1457,24 +1473,53 @@ static void chv_pipe_power_well_disable(struct drm_i915_private *dev_priv, void intel_display_power_get(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain) { - struct i915_power_domains *power_domains; - struct i915_power_well *power_well; - int i; + struct i915_power_domains *power_domains = &dev_priv->power_domains; intel_runtime_pm_get(dev_priv); - power_domains = &dev_priv->power_domains; + mutex_lock(&power_domains->lock); + + __intel_display_power_get_domain(dev_priv, domain); + + mutex_unlock(&power_domains->lock); +} + +/** + * intel_display_power_get_if_enabled - grab a reference for an enabled display power domain + * @dev_priv: i915 device instance + * @domain: power domain to reference + * + * This function grabs a power domain reference for @domain and ensures that the + * power domain and all its parents are powered up. Therefore users should only + * grab a reference to the innermost power domain they need. + * + * Any power domain reference obtained by this function must have a symmetric + * call to intel_display_power_put() to release the reference again. + */ +bool intel_display_power_get_if_enabled(struct drm_i915_private *dev_priv, + enum intel_display_power_domain domain) +{ + struct i915_power_domains *power_domains = &dev_priv->power_domains; + bool is_enabled; + + if (!intel_runtime_pm_get_if_in_use(dev_priv)) + return false; mutex_lock(&power_domains->lock); - for_each_power_well(i, power_well, BIT(domain), power_domains) { - if (!power_well->count++) - intel_power_well_enable(dev_priv, power_well); + if (__intel_display_power_is_enabled(dev_priv, domain)) { + __intel_display_power_get_domain(dev_priv, domain); + is_enabled = true; + } else { + is_enabled = false; } - power_domains->domain_use_count[domain]++; - mutex_unlock(&power_domains->lock); + + if (!is_enabled) + intel_runtime_pm_put(dev_priv); + + return is_enabled; } /** @@ -2245,6 +2290,43 @@ void intel_runtime_pm_get(struct drm_i915_private *dev_priv) assert_rpm_wakelock_held(dev_priv); } +/** + * intel_runtime_pm_get_if_in_use - grab a runtime pm reference if device in use + * @dev_priv: i915 device instance + * + * This function grabs a device-level runtime pm reference if the device is + * already in use and ensures that it is powered up. + * + * Any runtime pm reference obtained by this function must have a symmetric + * call to intel_runtime_pm_put() to release the reference again. + */ +bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv) +{ + struct drm_device *dev = dev_priv->dev; + struct device *device = &dev->pdev->dev; + int ret; + + if (!IS_ENABLED(CONFIG_PM)) + return true; + + ret = pm_runtime_get_if_in_use(device); + + /* + * In cases runtime PM is disabled by the RPM core and we get an + * -EINVAL return value we are not supposed to call this function, + * since the power state is undefined. This applies atm to the + * late/early system suspend/resume handlers. + */ + WARN_ON_ONCE(ret < 0); + if (ret <= 0) + return false; + + atomic_inc(&dev_priv->pm.wakeref_count); + assert_rpm_wakelock_held(dev_priv); + + return true; +} + /** * intel_runtime_pm_get_noresume - grab a runtime pm reference * @dev_priv: i915 device instance From 9fb84d5a9299ac678dedc56487f394e5f68b91cb Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:11 +0200 Subject: [PATCH 096/417] drm/i915: Ensure the HW is powered during display pipe HW readout The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. Signed-off-by: Imre Deak Revieved-by: Mika Kuoppala Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-3-git-send-email-imre.deak@intel.com (cherry picked from commit 1729050eb4bbc192e54069e82069f2811313c1dd) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_display.c | 67 ++++++++++++++++++++-------- 1 file changed, 48 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 5feb65725c04..892c53e3418a 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -8171,18 +8171,22 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc, { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; + enum intel_display_power_domain power_domain; uint32_t tmp; + bool ret; - if (!intel_display_power_is_enabled(dev_priv, - POWER_DOMAIN_PIPE(crtc->pipe))) + power_domain = POWER_DOMAIN_PIPE(crtc->pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe; pipe_config->shared_dpll = DPLL_ID_PRIVATE; + ret = false; + tmp = I915_READ(PIPECONF(crtc->pipe)); if (!(tmp & PIPECONF_ENABLE)) - return false; + goto out; if (IS_G4X(dev) || IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) { switch (tmp & PIPECONF_BPC_MASK) { @@ -8262,7 +8266,12 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc, pipe_config->base.adjusted_mode.crtc_clock = pipe_config->port_clock / pipe_config->pixel_multiplier; - return true; + ret = true; + +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } static void ironlake_init_pch_refclk(struct drm_device *dev) @@ -9366,18 +9375,21 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc, { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; + enum intel_display_power_domain power_domain; uint32_t tmp; + bool ret; - if (!intel_display_power_is_enabled(dev_priv, - POWER_DOMAIN_PIPE(crtc->pipe))) + power_domain = POWER_DOMAIN_PIPE(crtc->pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe; pipe_config->shared_dpll = DPLL_ID_PRIVATE; + ret = false; tmp = I915_READ(PIPECONF(crtc->pipe)); if (!(tmp & PIPECONF_ENABLE)) - return false; + goto out; switch (tmp & PIPECONF_BPC_MASK) { case PIPECONF_6BPC: @@ -9440,7 +9452,12 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc, ironlake_get_pfit_config(crtc, pipe_config); - return true; + ret = true; + +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } static void assert_can_disable_lcpll(struct drm_i915_private *dev_priv) @@ -9950,12 +9967,17 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc, { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - enum intel_display_power_domain pfit_domain; + enum intel_display_power_domain power_domain; + unsigned long power_domain_mask; uint32_t tmp; + bool ret; - if (!intel_display_power_is_enabled(dev_priv, - POWER_DOMAIN_PIPE(crtc->pipe))) + power_domain = POWER_DOMAIN_PIPE(crtc->pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; + power_domain_mask = BIT(power_domain); + + ret = false; pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe; pipe_config->shared_dpll = DPLL_ID_PRIVATE; @@ -9982,13 +10004,14 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc, pipe_config->cpu_transcoder = TRANSCODER_EDP; } - if (!intel_display_power_is_enabled(dev_priv, - POWER_DOMAIN_TRANSCODER(pipe_config->cpu_transcoder))) - return false; + power_domain = POWER_DOMAIN_TRANSCODER(pipe_config->cpu_transcoder); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) + goto out; + power_domain_mask |= BIT(power_domain); tmp = I915_READ(PIPECONF(pipe_config->cpu_transcoder)); if (!(tmp & PIPECONF_ENABLE)) - return false; + goto out; haswell_get_ddi_port_state(crtc, pipe_config); @@ -9998,14 +10021,14 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc, skl_init_scalers(dev, crtc, pipe_config); } - pfit_domain = POWER_DOMAIN_PIPE_PANEL_FITTER(crtc->pipe); - if (INTEL_INFO(dev)->gen >= 9) { pipe_config->scaler_state.scaler_id = -1; pipe_config->scaler_state.scaler_users &= ~(1 << SKL_CRTC_INDEX); } - if (intel_display_power_is_enabled(dev_priv, pfit_domain)) { + power_domain = POWER_DOMAIN_PIPE_PANEL_FITTER(crtc->pipe); + if (intel_display_power_get_if_enabled(dev_priv, power_domain)) { + power_domain_mask |= BIT(power_domain); if (INTEL_INFO(dev)->gen >= 9) skylake_get_pfit_config(crtc, pipe_config); else @@ -10023,7 +10046,13 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc, pipe_config->pixel_multiplier = 1; } - return true; + ret = true; + +out: + for_each_power_domain(power_domain, power_domain_mask) + intel_display_power_put(dev_priv, power_domain); + + return ret; } static void i845_update_cursor(struct drm_crtc *crtc, u32 base, bool on) From 013ef6cfc411bfe4a6009eaa7dabb6531bbb41bb Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:12 +0200 Subject: [PATCH 097/417] drm/i915/ibx: Ensure the HW is powered during PLL HW readout The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. Signed-off-by: Imre Deak Reviewed-by: Mika Kuoppala Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-4-git-send-email-imre.deak@intel.com (cherry picked from commit 12fda3876d08519bdf6f0acc70dd35754b422ed5) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_display.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 892c53e3418a..46a84bb9ca1f 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -13659,7 +13659,7 @@ static bool ibx_pch_dpll_get_hw_state(struct drm_i915_private *dev_priv, { uint32_t val; - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS)) + if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS)) return false; val = I915_READ(PCH_DPLL(pll->id)); @@ -13667,6 +13667,8 @@ static bool ibx_pch_dpll_get_hw_state(struct drm_i915_private *dev_priv, hw_state->fp0 = I915_READ(PCH_FP0(pll->id)); hw_state->fp1 = I915_READ(PCH_FP1(pll->id)); + intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS); + return val & DPLL_VCO_ENABLE; } From bacd67d6a36c8905258d08ed6ef41346fa01607c Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:13 +0200 Subject: [PATCH 098/417] drm/i915: Ensure the HW is powered when disabling VGA The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. Signed-off-by: Imre Deak Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-5-git-send-email-imre.deak@intel.com (cherry picked from commit 6392f8478e6f119467b1ad06e30e1f078e62efc1) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_display.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 46a84bb9ca1f..7934c45366ff 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -15599,10 +15599,12 @@ void i915_redisable_vga(struct drm_device *dev) * level, just check if the power well is enabled instead of trying to * follow the "don't touch the power well if we don't need it" policy * the rest of the driver uses. */ - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_VGA)) + if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_VGA)) return; i915_redisable_vga_power_on(dev); + + intel_display_power_put(dev_priv, POWER_DOMAIN_VGA); } static bool primary_get_hw_state(struct intel_plane *plane) From 5a24fab098d6f1aeae3e184a704cf2cd1f677ecd Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:14 +0200 Subject: [PATCH 099/417] drm/i915: Ensure the HW is powered during HW access in assert_pipe The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. Signed-off-by: Imre Deak Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-6-git-send-email-imre.deak@intel.com (cherry picked from commit 4feed0ebfa45879bc422c9a0bfa3cffec82ea60a) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_display.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 7934c45366ff..46947fffd599 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -1351,18 +1351,21 @@ void assert_pipe(struct drm_i915_private *dev_priv, bool cur_state; enum transcoder cpu_transcoder = intel_pipe_to_cpu_transcoder(dev_priv, pipe); + enum intel_display_power_domain power_domain; /* if we need the pipe quirk it must be always on */ if ((pipe == PIPE_A && dev_priv->quirks & QUIRK_PIPEA_FORCE) || (pipe == PIPE_B && dev_priv->quirks & QUIRK_PIPEB_FORCE)) state = true; - if (!intel_display_power_is_enabled(dev_priv, - POWER_DOMAIN_TRANSCODER(cpu_transcoder))) { - cur_state = false; - } else { + power_domain = POWER_DOMAIN_TRANSCODER(cpu_transcoder); + if (intel_display_power_get_if_enabled(dev_priv, power_domain)) { u32 val = I915_READ(PIPECONF(cpu_transcoder)); cur_state = !!(val & PIPECONF_ENABLE); + + intel_display_power_put(dev_priv, power_domain); + } else { + cur_state = false; } I915_STATE_WARN(cur_state != state, From 7a6252c6bce1124eebf620948280f8255a83f04a Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:15 +0200 Subject: [PATCH 100/417] drm/i915/crt: Ensure the HW is powered during HW state readout The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=93439 CC: Chris Wilson Signed-off-by: Imre Deak Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-7-git-send-email-imre.deak@intel.com (cherry picked from commit 1c8fdda1ea947ae8cf994969a1c285acc7089cb9) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_crt.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index 9c89df1af036..a7b4a524fadd 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -71,22 +71,29 @@ static bool intel_crt_get_hw_state(struct intel_encoder *encoder, struct intel_crt *crt = intel_encoder_to_crt(encoder); enum intel_display_power_domain power_domain; u32 tmp; + bool ret; power_domain = intel_display_port_power_domain(encoder); - if (!intel_display_power_is_enabled(dev_priv, power_domain)) + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; + ret = false; + tmp = I915_READ(crt->adpa_reg); if (!(tmp & ADPA_DAC_ENABLE)) - return false; + goto out; if (HAS_PCH_CPT(dev)) *pipe = PORT_TO_PIPE_CPT(tmp); else *pipe = PORT_TO_PIPE(tmp); - return true; + ret = true; +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } static unsigned int intel_crt_get_flags(struct intel_encoder *encoder) From d59410219ae396a5649eecff1a041e4588aff999 Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:16 +0200 Subject: [PATCH 101/417] drm/i915/ddi: Ensure the HW is powered during HW state readout The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. CC: Chris Wilson Signed-off-by: Imre Deak Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-8-git-send-email-imre.deak@intel.com (cherry picked from commit e27daab49718e3232318d8b539cb302521b4b724) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_ddi.c | 112 ++++++++++++++++++++++--------- 1 file changed, 79 insertions(+), 33 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 54a165b9c92d..0f3df2c39f7c 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -1969,13 +1969,16 @@ bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector) enum transcoder cpu_transcoder; enum intel_display_power_domain power_domain; uint32_t tmp; + bool ret; power_domain = intel_display_port_power_domain(intel_encoder); - if (!intel_display_power_is_enabled(dev_priv, power_domain)) + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; - if (!intel_encoder->get_hw_state(intel_encoder, &pipe)) - return false; + if (!intel_encoder->get_hw_state(intel_encoder, &pipe)) { + ret = false; + goto out; + } if (port == PORT_A) cpu_transcoder = TRANSCODER_EDP; @@ -1987,23 +1990,33 @@ bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector) switch (tmp & TRANS_DDI_MODE_SELECT_MASK) { case TRANS_DDI_MODE_SELECT_HDMI: case TRANS_DDI_MODE_SELECT_DVI: - return (type == DRM_MODE_CONNECTOR_HDMIA); + ret = type == DRM_MODE_CONNECTOR_HDMIA; + break; case TRANS_DDI_MODE_SELECT_DP_SST: - if (type == DRM_MODE_CONNECTOR_eDP) - return true; - return (type == DRM_MODE_CONNECTOR_DisplayPort); + ret = type == DRM_MODE_CONNECTOR_eDP || + type == DRM_MODE_CONNECTOR_DisplayPort; + break; + case TRANS_DDI_MODE_SELECT_DP_MST: /* if the transcoder is in MST state then * connector isn't connected */ - return false; + ret = false; + break; case TRANS_DDI_MODE_SELECT_FDI: - return (type == DRM_MODE_CONNECTOR_VGA); + ret = type == DRM_MODE_CONNECTOR_VGA; + break; default: - return false; + ret = false; + break; } + +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } bool intel_ddi_get_hw_state(struct intel_encoder *encoder, @@ -2015,15 +2028,18 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder, enum intel_display_power_domain power_domain; u32 tmp; int i; + bool ret; power_domain = intel_display_port_power_domain(encoder); - if (!intel_display_power_is_enabled(dev_priv, power_domain)) + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; + ret = false; + tmp = I915_READ(DDI_BUF_CTL(port)); if (!(tmp & DDI_BUF_CTL_ENABLE)) - return false; + goto out; if (port == PORT_A) { tmp = I915_READ(TRANS_DDI_FUNC_CTL(TRANSCODER_EDP)); @@ -2041,25 +2057,32 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder, break; } - return true; - } else { - for (i = TRANSCODER_A; i <= TRANSCODER_C; i++) { - tmp = I915_READ(TRANS_DDI_FUNC_CTL(i)); + ret = true; - if ((tmp & TRANS_DDI_PORT_MASK) - == TRANS_DDI_SELECT_PORT(port)) { - if ((tmp & TRANS_DDI_MODE_SELECT_MASK) == TRANS_DDI_MODE_SELECT_DP_MST) - return false; + goto out; + } - *pipe = i; - return true; - } + for (i = TRANSCODER_A; i <= TRANSCODER_C; i++) { + tmp = I915_READ(TRANS_DDI_FUNC_CTL(i)); + + if ((tmp & TRANS_DDI_PORT_MASK) == TRANS_DDI_SELECT_PORT(port)) { + if ((tmp & TRANS_DDI_MODE_SELECT_MASK) == + TRANS_DDI_MODE_SELECT_DP_MST) + goto out; + + *pipe = i; + ret = true; + + goto out; } } DRM_DEBUG_KMS("No pipe for ddi port %c found\n", port_name(port)); - return false; +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } void intel_ddi_enable_pipe_clock(struct intel_crtc *intel_crtc) @@ -2508,12 +2531,14 @@ static bool hsw_ddi_wrpll_get_hw_state(struct drm_i915_private *dev_priv, { uint32_t val; - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS)) + if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS)) return false; val = I915_READ(WRPLL_CTL(pll->id)); hw_state->wrpll = val; + intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS); + return val & WRPLL_PLL_ENABLE; } @@ -2523,12 +2548,14 @@ static bool hsw_ddi_spll_get_hw_state(struct drm_i915_private *dev_priv, { uint32_t val; - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS)) + if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS)) return false; val = I915_READ(SPLL_CTL); hw_state->spll = val; + intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS); + return val & SPLL_PLL_ENABLE; } @@ -2645,16 +2672,19 @@ static bool skl_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv, uint32_t val; unsigned int dpll; const struct skl_dpll_regs *regs = skl_dpll_regs; + bool ret; - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS)) + if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS)) return false; + ret = false; + /* DPLL0 is not part of the shared DPLLs, so pll->id is 0 for DPLL1 */ dpll = pll->id + 1; val = I915_READ(regs[pll->id].ctl); if (!(val & LCPLL_PLL_ENABLE)) - return false; + goto out; val = I915_READ(DPLL_CTRL1); hw_state->ctrl1 = (val >> (dpll * 6)) & 0x3f; @@ -2664,8 +2694,12 @@ static bool skl_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv, hw_state->cfgcr1 = I915_READ(regs[pll->id].cfgcr1); hw_state->cfgcr2 = I915_READ(regs[pll->id].cfgcr2); } + ret = true; - return true; +out: + intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS); + + return ret; } static void skl_shared_dplls_init(struct drm_i915_private *dev_priv) @@ -2932,13 +2966,16 @@ static bool bxt_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv, { enum port port = (enum port)pll->id; /* 1:1 port->PLL mapping */ uint32_t val; + bool ret; - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS)) + if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS)) return false; + ret = false; + val = I915_READ(BXT_PORT_PLL_ENABLE(port)); if (!(val & PORT_PLL_ENABLE)) - return false; + goto out; hw_state->ebb0 = I915_READ(BXT_PORT_PLL_EBB_0(port)); hw_state->ebb0 &= PORT_PLL_P1_MASK | PORT_PLL_P2_MASK; @@ -2985,7 +3022,12 @@ static bool bxt_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv, I915_READ(BXT_PORT_PCS_DW12_LN23(port))); hw_state->pcsdw12 &= LANE_STAGGER_MASK | LANESTAGGER_STRAP_OVRD; - return true; + ret = true; + +out: + intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS); + + return ret; } static void bxt_shared_dplls_init(struct drm_i915_private *dev_priv) @@ -3120,11 +3162,15 @@ bool intel_ddi_is_audio_enabled(struct drm_i915_private *dev_priv, { u32 temp; - if (intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_AUDIO)) { + if (intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_AUDIO)) { temp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD); + + intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO); + if (temp & AUDIO_OUTPUT_ENABLE(intel_crtc->pipe)) return true; } + return false; } From 02f9f5e62a9b0a1af2edd4fbd8194c9c5475459b Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:17 +0200 Subject: [PATCH 102/417] drm/i915: Ensure the HW is powered when accessing the CRC HW block The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. While at it also add the missing reference around the HW access in i915_interrupt_info(). v2: - update the commit message mentioning that this also fixes the HW access in the interrupt info debugfs entry (Daniel) Signed-off-by: Imre Deak Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-9-git-send-email-imre.deak@intel.com (cherry picked from commit e129649b7a3e1d50d196e159492496777769437e) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_debugfs.c | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 0fc38bb7276c..cf39ed3133d6 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -825,8 +825,11 @@ static int i915_interrupt_info(struct seq_file *m, void *data) } for_each_pipe(dev_priv, pipe) { - if (!intel_display_power_is_enabled(dev_priv, - POWER_DOMAIN_PIPE(pipe))) { + enum intel_display_power_domain power_domain; + + power_domain = POWER_DOMAIN_PIPE(pipe); + if (!intel_display_power_get_if_enabled(dev_priv, + power_domain)) { seq_printf(m, "Pipe %c power disabled\n", pipe_name(pipe)); continue; @@ -840,6 +843,8 @@ static int i915_interrupt_info(struct seq_file *m, void *data) seq_printf(m, "Pipe %c IER:\t%08x\n", pipe_name(pipe), I915_READ(GEN8_DE_PIPE_IER(pipe))); + + intel_display_power_put(dev_priv, power_domain); } seq_printf(m, "Display Engine port interrupt mask:\t%08x\n", @@ -3985,6 +3990,7 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe, struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[pipe]; struct intel_crtc *crtc = to_intel_crtc(intel_get_crtc_for_pipe(dev, pipe)); + enum intel_display_power_domain power_domain; u32 val = 0; /* shut up gcc */ int ret; @@ -3995,7 +4001,8 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe, if (pipe_crc->source && source) return -EINVAL; - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PIPE(pipe))) { + power_domain = POWER_DOMAIN_PIPE(pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) { DRM_DEBUG_KMS("Trying to capture CRC while pipe is off\n"); return -EIO; } @@ -4012,7 +4019,7 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe, ret = ivb_pipe_crc_ctl_reg(dev, pipe, &source, &val); if (ret != 0) - return ret; + goto out; /* none -> real source transition */ if (source) { @@ -4024,8 +4031,10 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe, entries = kcalloc(INTEL_PIPE_CRC_ENTRIES_NR, sizeof(pipe_crc->entries[0]), GFP_KERNEL); - if (!entries) - return -ENOMEM; + if (!entries) { + ret = -ENOMEM; + goto out; + } /* * When IPS gets enabled, the pipe CRC changes. Since IPS gets @@ -4081,7 +4090,12 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe, hsw_enable_ips(crtc); } - return 0; + ret = 0; + +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } /* From b81b801f8675838d69d1062a47ca46530ca7217b Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:18 +0200 Subject: [PATCH 103/417] drm/i915/dp: Ensure the HW is powered during HW state readout The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. Signed-off-by: Imre Deak Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-10-git-send-email-imre.deak@intel.com (cherry picked from commit 6fa9a5ecf7a54450b255229ac1fc6df276cf0653) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_dp.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 1bbd67b046da..1d8de43bed56 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -2362,15 +2362,18 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder, struct drm_i915_private *dev_priv = dev->dev_private; enum intel_display_power_domain power_domain; u32 tmp; + bool ret; power_domain = intel_display_port_power_domain(encoder); - if (!intel_display_power_is_enabled(dev_priv, power_domain)) + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; + ret = false; + tmp = I915_READ(intel_dp->output_reg); if (!(tmp & DP_PORT_EN)) - return false; + goto out; if (IS_GEN7(dev) && port == PORT_A) { *pipe = PORT_TO_PIPE_CPT(tmp); @@ -2381,7 +2384,9 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder, u32 trans_dp = I915_READ(TRANS_DP_CTL(p)); if (TRANS_DP_PIPE_TO_PORT(trans_dp) == port) { *pipe = p; - return true; + ret = true; + + goto out; } } @@ -2393,7 +2398,12 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder, *pipe = PORT_TO_PIPE(tmp); } - return true; + ret = true; + +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } static void intel_dp_get_config(struct intel_encoder *encoder, From fe97fd7eb87255883ae1da2d726baaae2b50e80d Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:19 +0200 Subject: [PATCH 104/417] drm/i915/dsi: Ensure the HW is powered during HW state readout The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. Signed-off-by: Imre Deak Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-11-git-send-email-imre.deak@intel.com (cherry picked from commit 3f3f42b887fbffc3353e44ef9f32456c19ae4280) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_dsi.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c index 44742fa2f616..0193c62a53ef 100644 --- a/drivers/gpu/drm/i915/intel_dsi.c +++ b/drivers/gpu/drm/i915/intel_dsi.c @@ -664,13 +664,16 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder, struct drm_device *dev = encoder->base.dev; enum intel_display_power_domain power_domain; enum port port; + bool ret; DRM_DEBUG_KMS("\n"); power_domain = intel_display_port_power_domain(encoder); - if (!intel_display_power_is_enabled(dev_priv, power_domain)) + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; + ret = false; + /* XXX: this only works for one DSI output */ for_each_dsi_port(port, intel_dsi->ports) { i915_reg_t ctrl_reg = IS_BROXTON(dev) ? @@ -691,12 +694,16 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder, if (dpi_enabled || (func & CMD_MODE_DATA_WIDTH_MASK)) { if (I915_READ(MIPI_DEVICE_READY(port)) & DEVICE_READY) { *pipe = port == PORT_A ? PIPE_A : PIPE_B; - return true; + ret = true; + + goto out; } } } +out: + intel_display_power_put(dev_priv, power_domain); - return false; + return ret; } static void intel_dsi_get_config(struct intel_encoder *encoder, From 31feb61a688bd4b1c1cb66cc24d931ee77826d93 Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:20 +0200 Subject: [PATCH 105/417] drm/i915/hdmi: Ensure the HW is powered during HW state readout The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. Signed-off-by: Imre Deak Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-12-git-send-email-imre.deak@intel.com (cherry picked from commit 5b0921748c0b1d0362bbfa802dc25a5c23de7e76) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_hdmi.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 4a77639a489d..cb5d1b15755c 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -880,15 +880,18 @@ static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder, struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base); enum intel_display_power_domain power_domain; u32 tmp; + bool ret; power_domain = intel_display_port_power_domain(encoder); - if (!intel_display_power_is_enabled(dev_priv, power_domain)) + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; + ret = false; + tmp = I915_READ(intel_hdmi->hdmi_reg); if (!(tmp & SDVO_ENABLE)) - return false; + goto out; if (HAS_PCH_CPT(dev)) *pipe = PORT_TO_PIPE_CPT(tmp); @@ -897,7 +900,12 @@ static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder, else *pipe = PORT_TO_PIPE(tmp); - return true; + ret = true; + +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } static void intel_hdmi_get_config(struct intel_encoder *encoder, From 380bdff2d05b498227c80caedd125e8cfcdba00d Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:21 +0200 Subject: [PATCH 106/417] drm/i915/lvds: Ensure the HW is powered during HW state readout The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. Signed-off-by: Imre Deak Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-13-git-send-email-imre.deak@intel.com (cherry picked from commit ecb2448218acf23c401434c26be256147833b221) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_lvds.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index 0da0240caf81..bc04d8d29acb 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -75,22 +75,30 @@ static bool intel_lvds_get_hw_state(struct intel_encoder *encoder, struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base); enum intel_display_power_domain power_domain; u32 tmp; + bool ret; power_domain = intel_display_port_power_domain(encoder); - if (!intel_display_power_is_enabled(dev_priv, power_domain)) + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; + ret = false; + tmp = I915_READ(lvds_encoder->reg); if (!(tmp & LVDS_PORT_EN)) - return false; + goto out; if (HAS_PCH_CPT(dev)) *pipe = PORT_TO_PIPE_CPT(tmp); else *pipe = PORT_TO_PIPE(tmp); - return true; + ret = true; + +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } static void intel_lvds_get_config(struct intel_encoder *encoder, From 53188eb40121a135892881c5f61e41efce60b00a Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Tue, 16 Feb 2016 18:56:46 +0200 Subject: [PATCH 107/417] drm/i915/skl: Ensure HW is powered during DDB HW state readout The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. Spotted-by: Mika Kuoppala Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=93441 CC: Chris Wilson Signed-off-by: Imre Deak Reviewed-by: Mika Kuoppala Link: http://patchwork.freedesktop.org/patch/msgid/1455719489-3008-1-git-send-email-imre.deak@intel.com (cherry picked from commit 4d800030238878c1a98d1d3a37a3d673eea661ce) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_pm.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index a234687792f0..b28c29f20e75 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -2829,7 +2829,10 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, memset(ddb, 0, sizeof(*ddb)); for_each_pipe(dev_priv, pipe) { - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PIPE(pipe))) + enum intel_display_power_domain power_domain; + + power_domain = POWER_DOMAIN_PIPE(pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) continue; for_each_plane(dev_priv, pipe, plane) { @@ -2841,6 +2844,8 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, val = I915_READ(CUR_BUF_CFG(pipe)); skl_ddb_entry_init_from_hw(&ddb->plane[pipe][PLANE_CURSOR], val); + + intel_display_power_put(dev_priv, power_domain); } } From 7e31a0159461818a1bda49662921b98a29c1187b Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 22 Feb 2016 15:18:13 +0100 Subject: [PATCH 108/417] ALSA: hda - Apply clock gate workaround to Skylake, too Some Skylake machines show the codec probe errors in certain situations, e.g. HP Z240 desktop fails to probe the onboard Realtek codec at reloading the snd-hda-intel module like: snd_hda_intel 0000:00:1f.3: spurious response 0x200:0x2, last cmd=0x000000 snd_hda_intel 0000:00:1f.3: azx_get_response timeout, switching to polling mode: lastcmd=0x000f0000 snd_hda_intel 0000:00:1f.3: No response from codec, disabling MSI: last cmd=0x000f0000 snd_hda_intel 0000:00:1f.3: Codec #0 probe error; disabling it... hdaudio hdaudioC0D2: no AFG or MFG node found snd_hda_intel 0000:00:1f.3: no codecs initialized Also, HP G470 G3 suffers from the similar problem, as reported in bugzilla below. On this machine, the codec probe error appears even at a fresh boot. As Libin suggested, the same workaround used for Broxton in the commit [6639484ddaf6: ALSA: hda - disable dynamic clock gating on Broxton before reset] can be applied for Skylake in order to fix this problem. The Intel HW team also confirmed that this is needed for SKL. This patch makes the workaround applied to both SKL and BXT platforms. The referred macros are moved and one superfluous macro (IS_BROXTON()) is another one (IS_BXT()) as well. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=112731 Suggested-by: Libin Yang Cc: # v4.4+ Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_intel.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index ce6b97f31390..e5240cb3749f 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -363,7 +363,10 @@ enum { ((pci)->device == 0x0d0c) || \ ((pci)->device == 0x160c)) -#define IS_BROXTON(pci) ((pci)->device == 0x5a98) +#define IS_SKL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa170) +#define IS_SKL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d70) +#define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98) +#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci)) static char *driver_short_names[] = { [AZX_DRIVER_ICH] = "HDA Intel", @@ -540,13 +543,13 @@ static void hda_intel_init_chip(struct azx *chip, bool full_reset) if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) snd_hdac_set_codec_wakeup(bus, true); - if (IS_BROXTON(pci)) { + if (IS_SKL_PLUS(pci)) { pci_read_config_dword(pci, INTEL_HDA_CGCTL, &val); val = val & ~INTEL_HDA_CGCTL_MISCBDCGE; pci_write_config_dword(pci, INTEL_HDA_CGCTL, val); } azx_init_chip(chip, full_reset); - if (IS_BROXTON(pci)) { + if (IS_SKL_PLUS(pci)) { pci_read_config_dword(pci, INTEL_HDA_CGCTL, &val); val = val | INTEL_HDA_CGCTL_MISCBDCGE; pci_write_config_dword(pci, INTEL_HDA_CGCTL, val); @@ -555,7 +558,7 @@ static void hda_intel_init_chip(struct azx *chip, bool full_reset) snd_hdac_set_codec_wakeup(bus, false); /* reduce dma latency to avoid noise */ - if (IS_BROXTON(pci)) + if (IS_BXT(pci)) bxt_reduce_dma_latency(chip); } @@ -977,11 +980,6 @@ static int azx_resume(struct device *dev) /* put codec down to D3 at hibernation for Intel SKL+; * otherwise BIOS may still access the codec and screw up the driver */ -#define IS_SKL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa170) -#define IS_SKL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d70) -#define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98) -#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci)) - static int azx_freeze_noirq(struct device *dev) { struct pci_dev *pci = to_pci_dev(dev); From 04ab3b7622a618ea081d17427c15a292710b40cb Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 18 Feb 2016 11:10:09 -0500 Subject: [PATCH 109/417] drm/amdgpu/gfx8: fix priv reg interrupt enable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Looks like a copy/paste typo. Reviewed-by: Christian König Noticed-by: David Panariti Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 8f8ec37ecd88..1c40bd90afbb 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -4995,7 +4995,7 @@ static int gfx_v8_0_set_priv_reg_fault_state(struct amdgpu_device *adev, case AMDGPU_IRQ_STATE_ENABLE: cp_int_cntl = RREG32(mmCP_INT_CNTL_RING0); cp_int_cntl = REG_SET_FIELD(cp_int_cntl, CP_INT_CNTL_RING0, - PRIV_REG_INT_ENABLE, 0); + PRIV_REG_INT_ENABLE, 1); WREG32(mmCP_INT_CNTL_RING0, cp_int_cntl); break; default: From 10f950f640e689336af0a0d587a4b3c26a73cd44 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 19 Feb 2016 15:18:45 -0500 Subject: [PATCH 110/417] drm/amdgpu: fix locking in force performance level MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Looks like a copy paste typo when we added powerplay support. Reviewed-by: Christian König Acked-by: Harry Wentland Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 7d8d84eaea4a..5ed5598997e9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -157,6 +157,7 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev, mutex_lock(&adev->pm.mutex); if (adev->pm.dpm.thermal_active) { count = -EINVAL; + mutex_unlock(&adev->pm.mutex); goto fail; } ret = amdgpu_dpm_force_performance_level(adev, level); @@ -167,8 +168,6 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev, mutex_unlock(&adev->pm.mutex); } fail: - mutex_unlock(&adev->pm.mutex); - return count; } From 0c67df48597f0e60eaf7f187ee38f6ccce56561e Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 19 Feb 2016 15:30:15 -0500 Subject: [PATCH 111/417] drm/amdgpu/pm: add some checks for PX MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit I.e., doesn't make sense to change power states or check the temperature when the asic is powered off. Reviewed-by: Christian König Acked-by: Harry Wentland Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 5ed5598997e9..8de765dee3e7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -113,6 +113,10 @@ static ssize_t amdgpu_get_dpm_forced_performance_level(struct device *dev, struct drm_device *ddev = dev_get_drvdata(dev); struct amdgpu_device *adev = ddev->dev_private; + if ((adev->flags & AMD_IS_PX) && + (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) + return snprintf(buf, PAGE_SIZE, "off\n"); + if (adev->pp_enabled) { enum amd_dpm_forced_level level; @@ -140,6 +144,11 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev, enum amdgpu_dpm_forced_level level; int ret = 0; + /* Can't force performance level when the card is off */ + if ((adev->flags & AMD_IS_PX) && + (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) + return -EINVAL; + if (strncmp("low", buf, strlen("low")) == 0) { level = AMDGPU_DPM_FORCED_LEVEL_LOW; } else if (strncmp("high", buf, strlen("high")) == 0) { @@ -181,8 +190,14 @@ static ssize_t amdgpu_hwmon_show_temp(struct device *dev, char *buf) { struct amdgpu_device *adev = dev_get_drvdata(dev); + struct drm_device *ddev = adev->ddev; int temp; + /* Can't get temperature when the card is off */ + if ((adev->flags & AMD_IS_PX) && + (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) + return -EINVAL; + if (!adev->pp_enabled && !adev->pm.funcs->get_temperature) temp = 0; else @@ -846,12 +861,16 @@ static int amdgpu_debugfs_pm_info(struct seq_file *m, void *data) struct drm_info_node *node = (struct drm_info_node *) m->private; struct drm_device *dev = node->minor->dev; struct amdgpu_device *adev = dev->dev_private; + struct drm_device *ddev = adev->ddev; if (!adev->pm.dpm_enabled) { seq_printf(m, "dpm not enabled\n"); return 0; } - if (adev->pp_enabled) { + if ((adev->flags & AMD_IS_PX) && + (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) { + seq_printf(m, "PX asic powered off\n"); + } else if (adev->pp_enabled) { amdgpu_dpm_debugfs_print_current_performance_level(adev, m); } else { mutex_lock(&adev->pm.mutex); From 8e7cedc6f7fe762ffe6e348502be34b11fa79298 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 19 Feb 2016 17:55:31 -0500 Subject: [PATCH 112/417] drm/amdgpu/pm: adjust display configuration after powerstate MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit set_power_state defaults to no displays, so we need to update the display configuration after setting up the powerstate on the first call. In most cases this is not an issue since ends up getting called multiple times at any given modeset and the proper order is achieved in the display changed handling at the top of the function. Reviewed-by: Christian König Acked-by: Jordan Lazare Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 8de765dee3e7..66855b62a603 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -648,8 +648,6 @@ static void amdgpu_dpm_change_power_state_locked(struct amdgpu_device *adev) /* update display watermarks based on new power state */ amdgpu_display_bandwidth_update(adev); - /* update displays */ - amdgpu_dpm_display_configuration_changed(adev); adev->pm.dpm.current_active_crtcs = adev->pm.dpm.new_active_crtcs; adev->pm.dpm.current_active_crtc_count = adev->pm.dpm.new_active_crtc_count; @@ -669,6 +667,9 @@ static void amdgpu_dpm_change_power_state_locked(struct amdgpu_device *adev) amdgpu_dpm_post_set_power_state(adev); + /* update displays */ + amdgpu_dpm_display_configuration_changed(adev); + if (adev->pm.funcs->force_performance_level) { if (adev->pm.dpm.thermal_active) { enum amdgpu_dpm_forced_level level = adev->pm.dpm.forced_level; From 39d4275058baf53e89203407bf3841ff2c74fa32 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 19 Feb 2016 18:05:10 -0500 Subject: [PATCH 113/417] drm/radeon/pm: adjust display configuration after powerstate MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit set_power_state defaults to no displays, so we need to update the display configuration after setting up the powerstate on the first call. In most cases this is not an issue since ends up getting called multiple times at any given modeset and the proper order is achieved in the display changed handling at the top of the function. Reviewed-by: Christian König Acked-by: Jordan Lazare Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/radeon/radeon_pm.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 248c5a9fb0b6..ca3be90a3bb4 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -1079,8 +1079,6 @@ static void radeon_dpm_change_power_state_locked(struct radeon_device *rdev) /* update display watermarks based on new power state */ radeon_bandwidth_update(rdev); - /* update displays */ - radeon_dpm_display_configuration_changed(rdev); rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs; rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count; @@ -1101,6 +1099,9 @@ static void radeon_dpm_change_power_state_locked(struct radeon_device *rdev) radeon_dpm_post_set_power_state(rdev); + /* update displays */ + radeon_dpm_display_configuration_changed(rdev); + if (rdev->asic->dpm.force_performance_level) { if (rdev->pm.dpm.thermal_active) { enum radeon_dpm_forced_level level = rdev->pm.dpm.forced_level; From 9b6f20984c5402af06e13cde64b5fe7c31853d1a Mon Sep 17 00:00:00 2001 From: Patrik Jakobsson Date: Thu, 18 Feb 2016 17:21:11 +0200 Subject: [PATCH 114/417] drm/i915/gen9: Check for DC state mismatch The DMC can incorrectly run off and allow DC states on it's own. We don't know the root-cause for this yet but this patch makes it more visible. Reviewed-by: Mika Kuoppala Signed-off-by: Patrik Jakobsson Signed-off-by: Imre Deak Link: http://patchwork.freedesktop.org/patch/msgid/1455808874-22089-2-git-send-email-mika.kuoppala@intel.com (cherry picked from commit 832dba889e27487c3087149f1039acc3feb89003) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_drv.h | 1 + drivers/gpu/drm/i915/intel_csr.c | 2 ++ drivers/gpu/drm/i915/intel_runtime_pm.c | 8 ++++++++ 3 files changed, 11 insertions(+) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index e7cd311e9fbb..b0847b915545 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -751,6 +751,7 @@ struct intel_csr { uint32_t mmio_count; i915_reg_t mmioaddr[8]; uint32_t mmiodata[8]; + uint32_t dc_state; }; #define DEV_INFO_FOR_EACH_FLAG(func, sep) \ diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c index 9bb63a85997a..647d85e77c2f 100644 --- a/drivers/gpu/drm/i915/intel_csr.c +++ b/drivers/gpu/drm/i915/intel_csr.c @@ -240,6 +240,8 @@ void intel_csr_load_program(struct drm_i915_private *dev_priv) I915_WRITE(dev_priv->csr.mmioaddr[i], dev_priv->csr.mmiodata[i]); } + + dev_priv->csr.dc_state = 0; } static uint32_t *parse_csr_fw(struct drm_i915_private *dev_priv, diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index 89dcc99ac3ca..19e6ff64ce9d 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -494,10 +494,18 @@ static void gen9_set_dc_state(struct drm_i915_private *dev_priv, uint32_t state) val = I915_READ(DC_STATE_EN); DRM_DEBUG_KMS("Setting DC state from %02x to %02x\n", val & mask, state); + + /* Check if DMC is ignoring our DC state requests */ + if ((val & mask) != dev_priv->csr.dc_state) + DRM_ERROR("DC state mismatch (0x%x -> 0x%x)\n", + dev_priv->csr.dc_state, val & mask); + val &= ~mask; val |= state; I915_WRITE(DC_STATE_EN, val); POSTING_READ(DC_STATE_EN); + + dev_priv->csr.dc_state = val & mask; } void bxt_enable_dc9(struct drm_i915_private *dev_priv) From 9b18572e83bfd5378b3fcff3acf123f7bddf558a Mon Sep 17 00:00:00 2001 From: Mika Kuoppala Date: Thu, 18 Feb 2016 17:58:09 +0200 Subject: [PATCH 115/417] drm/i915/gen9: Verify and enforce dc6 state writes It has been observed that sometimes disabling the dc6 fails and dc6 state pops back up, brief moment after disabling. This has to be dmc save/restore timing issue or other bug in the way dc states are handled. Try to work around this issue as we don't have firmware fix yet available. Verify that the value we wrote for the dmc sticks, and also enforce it by rewriting it, if it didn't. v2: Zero rereads on rewrite for extra paranoia (Imre) Testcase: kms_flip/basic-flip-vs-dpms References: https://bugs.freedesktop.org/show_bug.cgi?id=93768 Cc: Patrik Jakobsson Cc: Rodrigo Vivi Cc: Imre Deak Signed-off-by: Mika Kuoppala Reviewed-by: Imre Deak Signed-off-by: Imre Deak Link: http://patchwork.freedesktop.org/patch/msgid/1455811089-27884-1-git-send-email-mika.kuoppala@intel.com (cherry picked from commit 779cb5d3ddd72950ec726f86e38f7575c7fbdd4c) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_runtime_pm.c | 41 +++++++++++++++++++++++-- 1 file changed, 39 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index 19e6ff64ce9d..678ed3475d7e 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -470,6 +470,43 @@ static void gen9_set_dc_state_debugmask_memory_up( } } +static void gen9_write_dc_state(struct drm_i915_private *dev_priv, + u32 state) +{ + int rewrites = 0; + int rereads = 0; + u32 v; + + I915_WRITE(DC_STATE_EN, state); + + /* It has been observed that disabling the dc6 state sometimes + * doesn't stick and dmc keeps returning old value. Make sure + * the write really sticks enough times and also force rewrite until + * we are confident that state is exactly what we want. + */ + do { + v = I915_READ(DC_STATE_EN); + + if (v != state) { + I915_WRITE(DC_STATE_EN, state); + rewrites++; + rereads = 0; + } else if (rereads++ > 5) { + break; + } + + } while (rewrites < 100); + + if (v != state) + DRM_ERROR("Writing dc state to 0x%x failed, now 0x%x\n", + state, v); + + /* Most of the times we need one retry, avoid spam */ + if (rewrites > 1) + DRM_DEBUG_KMS("Rewrote dc state to 0x%x %d times\n", + state, rewrites); +} + static void gen9_set_dc_state(struct drm_i915_private *dev_priv, uint32_t state) { uint32_t val; @@ -502,8 +539,8 @@ static void gen9_set_dc_state(struct drm_i915_private *dev_priv, uint32_t state) val &= ~mask; val |= state; - I915_WRITE(DC_STATE_EN, val); - POSTING_READ(DC_STATE_EN); + + gen9_write_dc_state(dev_priv, val); dev_priv->csr.dc_state = val & mask; } From 3f315c5b850fa7aff73f50de8e316b98f611a32b Mon Sep 17 00:00:00 2001 From: Ivaylo Dimitrov Date: Fri, 5 Feb 2016 16:37:08 +0200 Subject: [PATCH 116/417] ARM: OMAP2+: Fix onenand initialization to avoid filesystem corruption Commit e7b11dc7b77b ("ARM: OMAP2+: Fix onenand rate detection to avoid filesystem corruption") partially fixed onenand configuration when GPMC module is reset. Finish the job by also providing the correct values in ONENAND_REG_SYS_CFG1 register. Fixes: e7b11dc7b77b ("ARM: OMAP2+: Fix onenand rate detection to avoid filesystem corruption") Cc: stable@vger.kernel.org # v4.2+ Signed-off-by: Ivaylo Dimitrov Tested-by: Aaro Koskinen Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/gpmc-onenand.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c index 7b76ce01c21d..8633c703546a 100644 --- a/arch/arm/mach-omap2/gpmc-onenand.c +++ b/arch/arm/mach-omap2/gpmc-onenand.c @@ -101,10 +101,8 @@ static void omap2_onenand_set_async_mode(void __iomem *onenand_base) static void set_onenand_cfg(void __iomem *onenand_base) { - u32 reg; + u32 reg = ONENAND_SYS_CFG1_RDY | ONENAND_SYS_CFG1_INT; - reg = readw(onenand_base + ONENAND_REG_SYS_CFG1); - reg &= ~((0x7 << ONENAND_SYS_CFG1_BRL_SHIFT) | (0x7 << 9)); reg |= (latency << ONENAND_SYS_CFG1_BRL_SHIFT) | ONENAND_SYS_CFG1_BL_16; if (onenand_flags & ONENAND_FLAG_SYNCREAD) @@ -123,6 +121,7 @@ static void set_onenand_cfg(void __iomem *onenand_base) reg |= ONENAND_SYS_CFG1_VHF; else reg &= ~ONENAND_SYS_CFG1_VHF; + writew(reg, onenand_base + ONENAND_REG_SYS_CFG1); } @@ -289,6 +288,7 @@ static int omap2_onenand_setup_async(void __iomem *onenand_base) } } + onenand_async.sync_write = true; omap2_onenand_calc_async_timings(&t); ret = gpmc_cs_program_settings(gpmc_onenand_data->cs, &onenand_async); From a0d54c3899aaeb047969d9479263c6bcf385c331 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Sat, 20 Feb 2016 13:12:57 +0200 Subject: [PATCH 117/417] clk: ti: omap3+: dpll: use non-locking version of clk_get_rate As the code in this file is being executed within irq context in some cases, we must avoid the clk_get_rate which uses mutex internally. Switch the code to use clk_hw_get_rate instead which is non-locking. This fixes an issue where PM runtime will hang the system if enabled with a serial console before a suspend-resume cycle. Signed-off-by: Tero Kristo Tested-by: Tony Lindgren Fixes: a53ad8ef3dcc ("clk: ti: Convert to clk_hw based provider APIs") Signed-off-by: Stephen Boyd --- drivers/clk/ti/dpll3xxx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/clk/ti/dpll3xxx.c b/drivers/clk/ti/dpll3xxx.c index 1c300388782b..cc739291a3ce 100644 --- a/drivers/clk/ti/dpll3xxx.c +++ b/drivers/clk/ti/dpll3xxx.c @@ -460,7 +460,8 @@ int omap3_noncore_dpll_enable(struct clk_hw *hw) parent = clk_hw_get_parent(hw); - if (clk_hw_get_rate(hw) == clk_get_rate(dd->clk_bypass)) { + if (clk_hw_get_rate(hw) == + clk_hw_get_rate(__clk_get_hw(dd->clk_bypass))) { WARN_ON(parent != __clk_get_hw(dd->clk_bypass)); r = _omap3_noncore_dpll_bypass(clk); } else { From 2454dfea0aef8a883d4302c38124edb373d47a25 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 22 Feb 2016 17:34:59 -0500 Subject: [PATCH 118/417] NFSv4.x/pnfs: Fix a race between layoutget and pnfs_destroy_layout If the server reboots while there is a layoutget outstanding, then the call to pnfs_choose_layoutget_stateid() will fail with an EAGAIN error, which causes an infinite loop in send_layoutget(). The reason why we never break out of the loop is that the layout 'plh_block_lgets' field is never cleared. Fix is to replace plh_block_lgets with NFS_LAYOUT_INVALID_STID, which can be reset after a new layoutget. Fixes: ab7d763e477c5 ("pNFS: Ensure nfs4_layoutget_prepare returns...") Signed-off-by: Trond Myklebust --- fs/nfs/pnfs.c | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 5064f23ca8cc..8a41538f1155 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -252,6 +252,27 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo) } } +/* + * Mark a pnfs_layout_hdr and all associated layout segments as invalid + * + * In order to continue using the pnfs_layout_hdr, a full recovery + * is required. + * Note that caller must hold inode->i_lock. + */ +static void +pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo, + struct list_head *lseg_list) +{ + struct pnfs_layout_range range = { + .iomode = IOMODE_ANY, + .offset = 0, + .length = NFS4_MAX_UINT64, + }; + + set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags); + pnfs_mark_matching_lsegs_invalid(lo, lseg_list, &range); +} + static int pnfs_iomode_to_fail_bit(u32 iomode) { @@ -554,9 +575,8 @@ pnfs_destroy_layout(struct nfs_inode *nfsi) spin_lock(&nfsi->vfs_inode.i_lock); lo = nfsi->layout; if (lo) { - lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */ - pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL); pnfs_get_layout_hdr(lo); + pnfs_mark_layout_stateid_invalid(lo, &tmp_list); pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RO_FAILED); pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RW_FAILED); spin_unlock(&nfsi->vfs_inode.i_lock); From 9fd4b9fc7695a4da1363a0b439853f88fb6a034f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 22 Feb 2016 17:46:34 -0500 Subject: [PATCH 119/417] NFSv4.x/pnfs: Fix a race between layoutget and bulk recalls Replace another case where the layout 'plh_block_lgets' can trigger infinite loops in send_layoutget(). Signed-off-by: Trond Myklebust --- fs/nfs/pnfs.c | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 8a41538f1155..2fa483e6dbe2 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -259,7 +259,7 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo) * is required. * Note that caller must hold inode->i_lock. */ -static void +static int pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo, struct list_head *lseg_list) { @@ -270,7 +270,7 @@ pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo, }; set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags); - pnfs_mark_matching_lsegs_invalid(lo, lseg_list, &range); + return pnfs_mark_matching_lsegs_invalid(lo, lseg_list, &range); } static int @@ -637,11 +637,6 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list, { struct pnfs_layout_hdr *lo; struct inode *inode; - struct pnfs_layout_range range = { - .iomode = IOMODE_ANY, - .offset = 0, - .length = NFS4_MAX_UINT64, - }; LIST_HEAD(lseg_list); int ret = 0; @@ -656,11 +651,11 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list, spin_lock(&inode->i_lock); list_del_init(&lo->plh_bulk_destroy); - lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */ - if (is_bulk_recall) - set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags); - if (pnfs_mark_matching_lsegs_invalid(lo, &lseg_list, &range)) + if (pnfs_mark_layout_stateid_invalid(lo, &lseg_list)) { + if (is_bulk_recall) + set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags); ret = -EAGAIN; + } spin_unlock(&inode->i_lock); pnfs_free_lseg_list(&lseg_list); /* Free all lsegs that are attached to commit buckets */ From dbb0c7c430ddbe4299f3580baec0e2503f6f5a93 Mon Sep 17 00:00:00 2001 From: Tomeu Vizoso Date: Thu, 21 Jan 2016 08:52:26 +0100 Subject: [PATCH 120/417] PM / devfreq: tegra: Set freq in rate callback As per the documentation of the devfreq_dev_profile.target callback, set the freq argument to the new frequency before returning. This caused endless messages like this after recent changes in the core: devfreq 6000c800.actmon: Couldn't update frequency transition information. Signed-off-by: Tomeu Vizoso Reported-by: Tyler Baker Tested-by: Thierry Reding Acked-by: Thierry Reding Signed-off-by: MyungJoo Ham --- drivers/devfreq/tegra-devfreq.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/devfreq/tegra-devfreq.c b/drivers/devfreq/tegra-devfreq.c index 848b93ee930f..fe9dce0245bf 100644 --- a/drivers/devfreq/tegra-devfreq.c +++ b/drivers/devfreq/tegra-devfreq.c @@ -500,6 +500,8 @@ static int tegra_devfreq_target(struct device *dev, unsigned long *freq, clk_set_min_rate(tegra->emc_clock, rate); clk_set_rate(tegra->emc_clock, 0); + *freq = rate; + return 0; } From dd71a17b1193dd4a4c35ecd0ba227aac3d110836 Mon Sep 17 00:00:00 2001 From: Bryan O'Donoghue Date: Tue, 23 Feb 2016 01:29:58 +0000 Subject: [PATCH 121/417] x86/platform/intel/quark: Change the kernel's IMR lock bit to false Currently when setting up an IMR around the kernel's .text section we lock that IMR, preventing further modification. While superficially this appears to be the right thing to do, in fact this doesn't account for a legitimate change in the memory map such as when executing a new kernel via kexec. In such a scenario a second kernel can have a different size and location to it's predecessor and can view some of the memory occupied by it's predecessor as legitimately usable DMA RAM. If this RAM were then subsequently allocated to DMA agents within the system it could conceivably trigger an IMR violation. This patch fixes the this potential situation by keeping the kernel's .text section IMR lock bit false by default. Suggested-by: Ingo Molnar Reported-by: Andy Shevchenko Signed-off-by: Bryan O'Donoghue Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: boon.leong.ong@intel.com Cc: paul.gortmaker@windriver.com Link: http://lkml.kernel.org/r/1456190999-12685-2-git-send-email-pure.logic@nexus-software.ie Signed-off-by: Ingo Molnar --- arch/x86/platform/intel-quark/imr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c index c61b6c332e97..bfadcd0f4944 100644 --- a/arch/x86/platform/intel-quark/imr.c +++ b/arch/x86/platform/intel-quark/imr.c @@ -592,14 +592,14 @@ static void __init imr_fixup_memmap(struct imr_device *idev) end = (unsigned long)__end_rodata - 1; /* - * Setup a locked IMR around the physical extent of the kernel + * Setup an unlocked IMR around the physical extent of the kernel * from the beginning of the .text secton to the end of the * .rodata section as one physically contiguous block. * * We don't round up @size since it is already PAGE_SIZE aligned. * See vmlinux.lds.S for details. */ - ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, true); + ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, false); if (ret < 0) { pr_err("unable to setup IMR for kernel: %zu KiB (%lx - %lx)\n", size / 1024, start, end); From 31b994a4986dcdd664c597afcef2c0918763019a Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Mon, 8 Feb 2016 13:42:14 +0100 Subject: [PATCH 122/417] usb: gadget: remove driver from pending list on probe error Retry gadget probe only if the probe result is -EPROBE_DEFER, not on every probe error. Signed-off-by: Marek Szyprowski Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/udc-core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c index fd73a3ea07c2..b86a6f03592e 100644 --- a/drivers/usb/gadget/udc/udc-core.c +++ b/drivers/usb/gadget/udc/udc-core.c @@ -413,9 +413,10 @@ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget, if (!driver->udc_name || strcmp(driver->udc_name, dev_name(&udc->dev)) == 0) { ret = udc_bind_to_driver(udc, driver); + if (ret != -EPROBE_DEFER) + list_del(&driver->pending); if (ret) goto err4; - list_del(&driver->pending); break; } } From 7b0a271d5cadf5fbb5a9c7cb868776af2a2c248c Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Thu, 18 Feb 2016 08:59:26 +0100 Subject: [PATCH 123/417] usb: gadget: gadgetfs: unregister gadget only if it got successfully registered Gadgetfs driver called usb_gadget_unregister_driver unconditionally, even if it didn't register it earlier due to other failures. This patch fixes this. Reported-by: Vegard Nossum Signed-off-by: Marek Szyprowski Tested-by: Vegard Nossum Signed-off-by: Felipe Balbi --- drivers/usb/gadget/legacy/inode.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 7e179f81d05c..87fb0fd6aaab 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -130,7 +130,8 @@ struct dev_data { setup_can_stall : 1, setup_out_ready : 1, setup_out_error : 1, - setup_abort : 1; + setup_abort : 1, + gadget_registered : 1; unsigned setup_wLength; /* the rest is basically write-once */ @@ -1179,7 +1180,8 @@ dev_release (struct inode *inode, struct file *fd) /* closing ep0 === shutdown all */ - usb_gadget_unregister_driver (&gadgetfs_driver); + if (dev->gadget_registered) + usb_gadget_unregister_driver (&gadgetfs_driver); /* at this point "good" hardware has disconnected the * device from USB; the host won't see it any more. @@ -1847,6 +1849,7 @@ dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) * kick in after the ep0 descriptor is closed. */ value = len; + dev->gadget_registered = true; } return value; From ca1c11894274c1687417945c034d6b8aee49f625 Mon Sep 17 00:00:00 2001 From: Simon Appleby Date: Tue, 9 Feb 2016 09:19:46 +0000 Subject: [PATCH 124/417] usb: gadget: net2280: fix endpoint max packet for super speed connections This patch fixes the register offset used for super-speed connection's max packet size. Without it using the 338x series of devices in enhanced mode will only allow full or high speed operation to function correctly. Signed-off-by: Simon Appleby Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/net2280.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/usb/gadget/udc/net2280.h b/drivers/usb/gadget/udc/net2280.h index 4dff60d34f73..0d32052bf16f 100644 --- a/drivers/usb/gadget/udc/net2280.h +++ b/drivers/usb/gadget/udc/net2280.h @@ -369,9 +369,20 @@ static inline void set_max_speed(struct net2280_ep *ep, u32 max) static const u32 ep_enhanced[9] = { 0x10, 0x60, 0x30, 0x80, 0x50, 0x20, 0x70, 0x40, 0x90 }; - if (ep->dev->enhanced_mode) + if (ep->dev->enhanced_mode) { reg = ep_enhanced[ep->num]; - else{ + switch (ep->dev->gadget.speed) { + case USB_SPEED_SUPER: + reg += 2; + break; + case USB_SPEED_FULL: + reg += 1; + break; + case USB_SPEED_HIGH: + default: + break; + } + } else { reg = (ep->num + 1) * 0x10; if (ep->dev->gadget.speed != USB_SPEED_HIGH) reg += 1; From 8de4b3a3fcbc18e0aa62e9defe5c08821351be12 Mon Sep 17 00:00:00 2001 From: "Ivan T. Ivanov" Date: Fri, 5 Feb 2016 19:17:09 +0000 Subject: [PATCH 125/417] usb: phy: msm: Trigger USB state detection work in DRD mode When working in Dual Role Device mode, USB state machine is not kicked, when host or gadget drivers are loaded. Fix this be explicitly triggering state detection on client driver load. Issue is that if the board is booted without micro usb cable and usb device attached, kernel fails to populate the usb host and device. The reason for this is that the state machine worker logic only checks for USB_DR_MODE_PERIPHERAL and USB_DR_MODE_HOST modes to run worker thread. However if the phy is configured in OTG mode it would fail to run the state machine, resulting in failure to detect for very first time. This patch fixes the issue by removing the explicit checks. Issue is noticed on Qualcomm Dragon board DB410C. [srinivas.kandagatla@linaro.org: Added more details to log] Signed-off-by: Ivan T. Ivanov Signed-off-by: Srinivas Kandagatla Signed-off-by: Felipe Balbi --- drivers/usb/phy/phy-msm-usb.c | 20 ++++---------------- 1 file changed, 4 insertions(+), 16 deletions(-) diff --git a/drivers/usb/phy/phy-msm-usb.c b/drivers/usb/phy/phy-msm-usb.c index 970a30e155cb..72b387d592c2 100644 --- a/drivers/usb/phy/phy-msm-usb.c +++ b/drivers/usb/phy/phy-msm-usb.c @@ -757,14 +757,8 @@ static int msm_otg_set_host(struct usb_otg *otg, struct usb_bus *host) otg->host = host; dev_dbg(otg->usb_phy->dev, "host driver registered w/ tranceiver\n"); - /* - * Kick the state machine work, if peripheral is not supported - * or peripheral is already registered with us. - */ - if (motg->pdata->mode == USB_DR_MODE_HOST || otg->gadget) { - pm_runtime_get_sync(otg->usb_phy->dev); - schedule_work(&motg->sm_work); - } + pm_runtime_get_sync(otg->usb_phy->dev); + schedule_work(&motg->sm_work); return 0; } @@ -827,14 +821,8 @@ static int msm_otg_set_peripheral(struct usb_otg *otg, dev_dbg(otg->usb_phy->dev, "peripheral driver registered w/ tranceiver\n"); - /* - * Kick the state machine work, if host is not supported - * or host is already registered with us. - */ - if (motg->pdata->mode == USB_DR_MODE_PERIPHERAL || otg->host) { - pm_runtime_get_sync(otg->usb_phy->dev); - schedule_work(&motg->sm_work); - } + pm_runtime_get_sync(otg->usb_phy->dev); + schedule_work(&motg->sm_work); return 0; } From 4c2ba0c67394514f3f75c660c9f5d02e66a7efd4 Mon Sep 17 00:00:00 2001 From: Cristian Birsan Date: Fri, 19 Feb 2016 10:11:56 +0200 Subject: [PATCH 126/417] usb: musb: fix DMA for host mode Commit ac33cdb16681 ("usb: musb: Remove ifdefs for musb_host_rx in musb_host.c part5") introduces a problem setting DMA host mode. The musb_advance_schedule() is called immediately after receiving an endpoint RX interrupt without waiting for the DMA transfer to complete. As a consequence when the dma complete interrupt arrives the in_qh member of hw_ep is already null an the musb_host_rx() exits on !urb error case. Fix the done condition that advances the musb schedule. Signed-off-by: Cristian Birsan Signed-off-by: Joshua Henderson Tested-by: Ladislav Michl Signed-off-by: Felipe Balbi --- drivers/usb/musb/musb_host.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index 79d081883628..58487a473521 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -2003,10 +2003,8 @@ void musb_host_rx(struct musb *musb, u8 epnum) qh->offset, urb->transfer_buffer_length); - done = musb_rx_dma_in_inventra_cppi41(c, hw_ep, qh, - urb, xfer_len, - iso_err); - if (done) + if (musb_rx_dma_in_inventra_cppi41(c, hw_ep, qh, urb, + xfer_len, iso_err)) goto finish; else dev_err(musb->controller, "error: rx_dma failed\n"); From 3b2435192fe917a826c91c8b34032428d6efdfc7 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Fri, 19 Feb 2016 11:04:55 +0200 Subject: [PATCH 127/417] MAINTAINERS: drop OMAP USB and MUSB maintainership Now that I have switched to another company, I won't be able to help by maintaining OMAP USB Support and/or the MUSB driver. OMAP USB Support is left Orphaned. MUSB's new maintainer will be Bin Liu from Texas Instruments who has accepted to take over starting with v4.6. Cc: Bin Liu Acked-by: Greg Kroah-Hartman Signed-off-by: Felipe Balbi --- MAINTAINERS | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index cc2f753cb357..65f34bb04d7a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3444,7 +3444,6 @@ F: drivers/usb/dwc2/ DESIGNWARE USB3 DRD IP DRIVER M: Felipe Balbi L: linux-usb@vger.kernel.org -L: linux-omap@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git S: Maintained F: drivers/usb/dwc3/ @@ -7354,7 +7353,7 @@ F: drivers/tty/isicom.c F: include/linux/isicom.h MUSB MULTIPOINT HIGH SPEED DUAL-ROLE CONTROLLER -M: Felipe Balbi +M: Bin Liu L: linux-usb@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git S: Maintained @@ -7923,11 +7922,9 @@ F: drivers/media/platform/omap3isp/ F: drivers/staging/media/omap4iss/ OMAP USB SUPPORT -M: Felipe Balbi L: linux-usb@vger.kernel.org L: linux-omap@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git -S: Maintained +S: Orphan F: drivers/usb/*/*omap* F: arch/arm/*omap*/usb* From 3e5177c1919bdc7651b5056f35409d0b4d728841 Mon Sep 17 00:00:00 2001 From: Alexey Brodkin Date: Sat, 20 Feb 2016 16:04:26 +0300 Subject: [PATCH 128/417] arc: get rid of DEVTMPFS dependency on INITRAMFS_SOURCE Even though DEVTMPFS is required when our pre-built initramfs is used it is not the case in general. It is perfectly possible to use initramfs with device nodes already populated or there could be other usages, see discussion below for more detials: http://thread.gmane.org/gmane.comp.embedded.openwrt.devel/37819/focus=37821 This change removes mentioned dependency from arch/arc/Kconfig updating instead those defconfigs that are usually used with this kind of pre-build initramfs. And while at it all touched defconfigs were regenerated via savedefconfig and some options were removed: * USB is selected by other options implicitly * VGA_CONSOLE is disableb for ARC since 031e29b5877f31676739dc2f847d04c2c0732034 * EXT3_FS automatically selects EXT4_FS * MTDxxx and JFFS2_FS make no sense for AXS because AXS NAND controller is not upstreamed * NET_OSCI_LAN is not in upstream as well * ARCPGU_xxx options make no sense because ARC PGU is not yet in upstream and when it gets there all config options would be taken from devicetree Signed-off-by: Alexey Brodkin Signed-off-by: Vineet Gupta --- arch/arc/Kconfig | 2 -- arch/arc/configs/axs101_defconfig | 4 +--- arch/arc/configs/axs103_defconfig | 10 +--------- arch/arc/configs/axs103_smp_defconfig | 10 +--------- arch/arc/configs/nsim_700_defconfig | 5 ++--- arch/arc/configs/nsim_hs_defconfig | 3 +-- arch/arc/configs/nsim_hs_smp_defconfig | 6 ++---- arch/arc/configs/nsimosci_defconfig | 2 +- arch/arc/configs/nsimosci_hs_defconfig | 3 +-- arch/arc/configs/nsimosci_hs_smp_defconfig | 12 ++---------- arch/arc/configs/tb10x_defconfig | 18 ++++++------------ 11 files changed, 18 insertions(+), 57 deletions(-) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 0f8df0aa2eb8..4abc81907071 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -12,8 +12,6 @@ config ARC select BUILDTIME_EXTABLE_SORT select COMMON_CLK select CLONE_BACKWARDS - # ARC Busybox based initramfs absolutely relies on DEVTMPFS for /dev - select DEVTMPFS if !INITRAMFS_SOURCE="" select GENERIC_ATOMIC64 select GENERIC_CLOCKEVENTS select GENERIC_FIND_FIRST_BIT diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig index f1ac9818b751..5d4e2a07ad3e 100644 --- a/arch/arc/configs/axs101_defconfig +++ b/arch/arc/configs/axs101_defconfig @@ -39,6 +39,7 @@ CONFIG_IP_PNP_RARP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set @@ -73,7 +74,6 @@ CONFIG_I2C_CHARDEV=y CONFIG_I2C_DESIGNWARE_PLATFORM=y # CONFIG_HWMON is not set CONFIG_FB=y -# CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y CONFIG_LOGO=y @@ -91,12 +91,10 @@ CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_DW=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_EXT3_FS=y -CONFIG_EXT4_FS=y CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y CONFIG_NTFS_FS=y CONFIG_TMPFS=y -CONFIG_JFFS2_FS=y CONFIG_NFS_FS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig index 323486d6ee83..87ee46b237ef 100644 --- a/arch/arc/configs/axs103_defconfig +++ b/arch/arc/configs/axs103_defconfig @@ -39,14 +39,10 @@ CONFIG_IP_PNP_RARP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set -CONFIG_MTD=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_NAND=y -CONFIG_MTD_NAND_AXS=y CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_NETDEVICES=y @@ -78,14 +74,12 @@ CONFIG_I2C_CHARDEV=y CONFIG_I2C_DESIGNWARE_PLATFORM=y # CONFIG_HWMON is not set CONFIG_FB=y -# CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y CONFIG_LOGO=y # CONFIG_LOGO_LINUX_MONO is not set # CONFIG_LOGO_LINUX_VGA16 is not set # CONFIG_LOGO_LINUX_CLUT224 is not set -CONFIG_USB=y CONFIG_USB_EHCI_HCD=y CONFIG_USB_EHCI_HCD_PLATFORM=y CONFIG_USB_OHCI_HCD=y @@ -97,12 +91,10 @@ CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_DW=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_EXT3_FS=y -CONFIG_EXT4_FS=y CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y CONFIG_NTFS_FS=y CONFIG_TMPFS=y -CONFIG_JFFS2_FS=y CONFIG_NFS_FS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig index 66191cd0447e..d80daf4f7e73 100644 --- a/arch/arc/configs/axs103_smp_defconfig +++ b/arch/arc/configs/axs103_smp_defconfig @@ -40,14 +40,10 @@ CONFIG_IP_PNP_RARP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set -CONFIG_MTD=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_NAND=y -CONFIG_MTD_NAND_AXS=y CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_NETDEVICES=y @@ -79,14 +75,12 @@ CONFIG_I2C_CHARDEV=y CONFIG_I2C_DESIGNWARE_PLATFORM=y # CONFIG_HWMON is not set CONFIG_FB=y -# CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y CONFIG_LOGO=y # CONFIG_LOGO_LINUX_MONO is not set # CONFIG_LOGO_LINUX_VGA16 is not set # CONFIG_LOGO_LINUX_CLUT224 is not set -CONFIG_USB=y CONFIG_USB_EHCI_HCD=y CONFIG_USB_EHCI_HCD_PLATFORM=y CONFIG_USB_OHCI_HCD=y @@ -98,12 +92,10 @@ CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_DW=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_EXT3_FS=y -CONFIG_EXT4_FS=y CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y CONFIG_NTFS_FS=y CONFIG_TMPFS=y -CONFIG_JFFS2_FS=y CONFIG_NFS_FS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig index 138f9d887957..f41095340b6a 100644 --- a/arch/arc/configs/nsim_700_defconfig +++ b/arch/arc/configs/nsim_700_defconfig @@ -4,6 +4,7 @@ CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y +# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y @@ -26,7 +27,6 @@ CONFIG_ARC_PLAT_SIM=y CONFIG_ARC_BUILTIN_DTB_NAME="nsim_700" CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set -# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -34,6 +34,7 @@ CONFIG_UNIX_DIAG=y CONFIG_NET_KEY=y CONFIG_INET=y # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set @@ -51,7 +52,6 @@ CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set -# CONFIG_VGA_CONSOLE is not set # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set # CONFIG_IOMMU_SUPPORT is not set @@ -63,4 +63,3 @@ CONFIG_NFS_FS=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set # CONFIG_DEBUG_PREEMPT is not set -CONFIG_XZ_DEC=y diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig index f68838e8068a..cfaa33cb5921 100644 --- a/arch/arc/configs/nsim_hs_defconfig +++ b/arch/arc/configs/nsim_hs_defconfig @@ -35,6 +35,7 @@ CONFIG_UNIX_DIAG=y CONFIG_NET_KEY=y CONFIG_INET=y # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set @@ -49,7 +50,6 @@ CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set -# CONFIG_VGA_CONSOLE is not set # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set # CONFIG_IOMMU_SUPPORT is not set @@ -61,4 +61,3 @@ CONFIG_NFS_FS=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set # CONFIG_DEBUG_PREEMPT is not set -CONFIG_XZ_DEC=y diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig index 96bd1c20fb0b..bb2a8dc778b5 100644 --- a/arch/arc/configs/nsim_hs_smp_defconfig +++ b/arch/arc/configs/nsim_hs_smp_defconfig @@ -2,6 +2,7 @@ CONFIG_CROSS_COMPILE="arc-linux-" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set +# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y @@ -21,13 +22,11 @@ CONFIG_MODULES=y # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set CONFIG_ARC_PLAT_SIM=y -CONFIG_ARC_BOARD_ML509=y CONFIG_ISA_ARCV2=y CONFIG_SMP=y CONFIG_ARC_BUILTIN_DTB_NAME="nsim_hs_idu" CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set -# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -35,6 +34,7 @@ CONFIG_UNIX_DIAG=y CONFIG_NET_KEY=y CONFIG_INET=y # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set @@ -49,7 +49,6 @@ CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set -# CONFIG_VGA_CONSOLE is not set # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set # CONFIG_IOMMU_SUPPORT is not set @@ -60,4 +59,3 @@ CONFIG_TMPFS=y CONFIG_NFS_FS=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set -CONFIG_XZ_DEC=y diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig index 31e1d95764ff..646182e93753 100644 --- a/arch/arc/configs/nsimosci_defconfig +++ b/arch/arc/configs/nsimosci_defconfig @@ -33,6 +33,7 @@ CONFIG_UNIX_DIAG=y CONFIG_NET_KEY=y CONFIG_INET=y # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set @@ -58,7 +59,6 @@ CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set CONFIG_FB=y -# CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y # CONFIG_HID is not set diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig index fcae66683ca0..ceca2541950d 100644 --- a/arch/arc/configs/nsimosci_hs_defconfig +++ b/arch/arc/configs/nsimosci_hs_defconfig @@ -34,12 +34,12 @@ CONFIG_UNIX_DIAG=y CONFIG_NET_KEY=y CONFIG_INET=y # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set # CONFIG_BLK_DEV is not set CONFIG_NETDEVICES=y -CONFIG_NET_OSCI_LAN=y CONFIG_INPUT_EVDEV=y # CONFIG_MOUSE_PS2_ALPS is not set # CONFIG_MOUSE_PS2_LOGIPS2PP is not set @@ -58,7 +58,6 @@ CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set CONFIG_FB=y -# CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y # CONFIG_HID is not set diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig index b01b659168ea..4b6da90f6f26 100644 --- a/arch/arc/configs/nsimosci_hs_smp_defconfig +++ b/arch/arc/configs/nsimosci_hs_smp_defconfig @@ -2,6 +2,7 @@ CONFIG_CROSS_COMPILE="arc-linux-" CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y +# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y @@ -18,15 +19,11 @@ CONFIG_MODULES=y # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set CONFIG_ARC_PLAT_SIM=y -CONFIG_ARC_BOARD_ML509=y CONFIG_ISA_ARCV2=y CONFIG_SMP=y -CONFIG_ARC_HAS_LL64=y -# CONFIG_ARC_HAS_RTSC is not set CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci_hs_idu" CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set -# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=y @@ -40,6 +37,7 @@ CONFIG_INET=y # CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set @@ -56,14 +54,11 @@ CONFIG_NETDEVICES=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -CONFIG_NET_OSCI_LAN=y # CONFIG_WLAN is not set CONFIG_INPUT_EVDEV=y CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set -CONFIG_SERIO_LIBPS2=y CONFIG_SERIO_ARC_PS2=y -CONFIG_VT_HW_CONSOLE_BINDING=y # CONFIG_LEGACY_PTYS is not set # CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y @@ -75,9 +70,6 @@ CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set CONFIG_FB=y -CONFIG_ARCPGU_RGB888=y -CONFIG_ARCPGU_DISPTYPE=0 -# CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y # CONFIG_HID is not set diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig index 3b4dc9cebcf1..9b342eaf95ae 100644 --- a/arch/arc/configs/tb10x_defconfig +++ b/arch/arc/configs/tb10x_defconfig @@ -3,6 +3,7 @@ CONFIG_CROSS_COMPILE="arc-linux-" CONFIG_DEFAULT_HOSTNAME="tb10x" CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y +# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y @@ -26,12 +27,10 @@ CONFIG_MODULE_UNLOAD=y # CONFIG_BLOCK is not set CONFIG_ARC_PLAT_TB10X=y CONFIG_ARC_CACHE_LINE_SHIFT=5 -CONFIG_ARC_STACK_NONEXEC=y CONFIG_HZ=250 CONFIG_ARC_BUILTIN_DTB_NAME="abilis_tb100_dvk" CONFIG_PREEMPT_VOLUNTARY=y # CONFIG_COMPACTION is not set -# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -44,8 +43,8 @@ CONFIG_IP_MULTICAST=y # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set +CONFIG_DEVTMPFS=y # CONFIG_FIRMWARE_IN_KERNEL is not set -CONFIG_PROC_DEVICETREE=y CONFIG_NETDEVICES=y # CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set @@ -55,9 +54,6 @@ CONFIG_NETDEVICES=y # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_SEEQ is not set CONFIG_STMMAC_ETH=y -CONFIG_STMMAC_DEBUG_FS=y -CONFIG_STMMAC_DA=y -CONFIG_STMMAC_CHAINED=y # CONFIG_NET_VENDOR_WIZNET is not set # CONFIG_WLAN is not set # CONFIG_INPUT is not set @@ -91,7 +87,6 @@ CONFIG_LEDS_TRIGGER_DEFAULT_ON=y CONFIG_LEDS_TRIGGER_TRANSIENT=y CONFIG_DMADEVICES=y CONFIG_DW_DMAC=y -CONFIG_NET_DMA=y CONFIG_ASYNC_TX_DMA=y # CONFIG_IOMMU_SUPPORT is not set # CONFIG_DNOTIFY is not set @@ -100,17 +95,16 @@ CONFIG_TMPFS=y CONFIG_CONFIGFS_FS=y # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set +CONFIG_DEBUG_INFO=y # CONFIG_ENABLE_WARN_DEPRECATED is not set -CONFIG_MAGIC_SYSRQ=y CONFIG_STRIP_ASM_SYMS=y CONFIG_DEBUG_FS=y CONFIG_HEADERS_CHECK=y CONFIG_DEBUG_SECTION_MISMATCH=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_MEMORY_INIT=y +CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_DETECT_HUNG_TASK=y CONFIG_SCHEDSTATS=y CONFIG_TIMER_STATS=y -CONFIG_DEBUG_INFO=y -CONFIG_DEBUG_MEMORY_INIT=y -CONFIG_DEBUG_STACKOVERFLOW=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set # CONFIG_CRYPTO_HW is not set From 7a36b930e6ed4702c866dc74a5ad07318a57c688 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Thu, 18 Feb 2016 19:49:18 +0100 Subject: [PATCH 129/417] mac80211: minstrel_ht: set default tx aggregation timeout to 0 The value 5000 was put here with the addition of the timeout field to ieee80211_start_tx_ba_session. It was originally added in mac80211 to save resources for drivers like iwlwifi, which only supports a limited number of concurrent aggregation sessions. Since iwlwifi does not use minstrel_ht and other drivers don't need this, 0 is a better default - especially since there have been recent reports of aggregation setup related issues reproduced with ath9k. This should improve stability without causing any adverse effects. Cc: stable@vger.kernel.org Acked-by: Avery Pennarun Signed-off-by: Felix Fietkau Signed-off-by: Johannes Berg --- net/mac80211/rc80211_minstrel_ht.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 702328bcabdc..409b3640da6c 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -692,7 +692,7 @@ minstrel_aggr_check(struct ieee80211_sta *pubsta, struct sk_buff *skb) if (likely(sta->ampdu_mlme.tid_tx[tid])) return; - ieee80211_start_tx_ba_session(pubsta, tid, 5000); + ieee80211_start_tx_ba_session(pubsta, tid, 0); } static void From 5e950a78bf5b18ded277a27aed0bcdbe7c1b868a Mon Sep 17 00:00:00 2001 From: Ola Olsson Date: Thu, 11 Feb 2016 01:00:22 +0100 Subject: [PATCH 130/417] nl80211: Zero out the connection keys memory when freeing them. The connection keys are zeroed out in all other cases except this one. Let's fix the last one as well. Signed-off-by: Ola Olsson Reviewed-by: Julian Calaby Signed-off-by: Johannes Berg --- net/wireless/nl80211.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index d4786f2802aa..711cb7ad6ae0 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -7547,7 +7547,7 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info) if ((ibss.chandef.width != NL80211_CHAN_WIDTH_20_NOHT) && no_ht) { - kfree(connkeys); + kzfree(connkeys); return -EINVAL; } } From b86071528f3261ab592fad5b9b1a02aea3dcabf3 Mon Sep 17 00:00:00 2001 From: Arend van Spriel Date: Mon, 15 Feb 2016 14:35:53 +0100 Subject: [PATCH 131/417] cfg80211: stop critical protocol session upon disconnect event When user-space has started a critical protocol session and a disconnect event occurs, the rdev::crit_prot_nlportid remains set. This caused a subsequent NL80211_CMD_CRIT_PROTO_START to fail (-EBUSY). Fix this by clearing the rdev attribute and call .crit_proto_stop() callback upon disconnect event. Reviewed-by: Hante Meuleman Reviewed-by: Pieter-Paul Giesberts Signed-off-by: Arend van Spriel Signed-off-by: Johannes Berg --- net/wireless/sme.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 8020b5b094d4..d49ed7666d4c 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -917,6 +917,12 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, nl80211_send_disconnected(rdev, dev, reason, ie, ie_len, from_ap); + /* stop critical protocol if supported */ + if (rdev->ops->crit_proto_stop && rdev->crit_proto_nlportid) { + rdev->crit_proto_nlportid = 0; + rdev_crit_proto_stop(rdev, wdev); + } + /* * Delete all the keys ... pairwise keys can't really * exist any more anyway, but default keys might. From b7052cd7bcf3c1478796e93e3dff2b44c9e82943 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Thu, 18 Feb 2016 18:55:54 +0000 Subject: [PATCH 132/417] sunrpc/cache: fix off-by-one in qword_get() The qword_get() function NUL-terminates its output buffer. If the input string is in hex format \xXXXX... and the same length as the output buffer, there is an off-by-one: int qword_get(char **bpp, char *dest, int bufsize) { ... while (len < bufsize) { ... *dest++ = (h << 4) | l; len++; } ... *dest = '\0'; return len; } This patch ensures the NUL terminator doesn't fall outside the output buffer. Signed-off-by: Stefan Hajnoczi Cc: stable@vger.kernel.org Signed-off-by: J. Bruce Fields --- net/sunrpc/cache.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 2b32fd602669..273bc3a35425 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1225,7 +1225,7 @@ int qword_get(char **bpp, char *dest, int bufsize) if (bp[0] == '\\' && bp[1] == 'x') { /* HEX STRING */ bp += 2; - while (len < bufsize) { + while (len < bufsize - 1) { int h, l; h = hex_to_bin(bp[0]); From 236cf17c2502007a9d2dda3c39fb0d9a6bd03cc2 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 16 Feb 2016 14:47:31 +0000 Subject: [PATCH 133/417] KVM: arm/arm64: vgic: Ensure bitmaps are long enough When we allocate bitmaps in vgic_vcpu_init_maps, we divide the number of bits we need by 8 to figure out how many bytes to allocate. However, bitmap elements are always accessed as unsigned longs, and if we didn't happen to allocate a size such that size % sizeof(unsigned long) == 0, bitmap accesses may go past the end of the allocation. When using KASAN (which does byte-granular access checks), this results in a continuous stream of BUGs whenever these bitmaps are accessed: ============================================================================= BUG kmalloc-128 (Tainted: G B ): kasan: bad access detected ----------------------------------------------------------------------------- INFO: Allocated in vgic_init.part.25+0x55c/0x990 age=7493 cpu=3 pid=1730 INFO: Slab 0xffffffbde6d5da40 objects=16 used=15 fp=0xffffffc935769700 flags=0x4000000000000080 INFO: Object 0xffffffc935769500 @offset=1280 fp=0x (null) Bytes b4 ffffffc9357694f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Object ffffffc935769500: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Object ffffffc935769510: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Object ffffffc935769520: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Object ffffffc935769530: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Object ffffffc935769540: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Object ffffffc935769550: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Object ffffffc935769560: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Object ffffffc935769570: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Padding ffffffc9357695b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Padding ffffffc9357695c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Padding ffffffc9357695d0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Padding ffffffc9357695e0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Padding ffffffc9357695f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ CPU: 3 PID: 1740 Comm: kvm-vcpu-0 Tainted: G B 4.4.0+ #17 Hardware name: ARM Juno development board (r1) (DT) Call trace: [] dump_backtrace+0x0/0x280 [] show_stack+0x14/0x20 [] dump_stack+0x100/0x188 [] print_trailer+0xfc/0x168 [] object_err+0x3c/0x50 [] kasan_report_error+0x244/0x558 [] __asan_report_load8_noabort+0x48/0x50 [] __bitmap_or+0xc0/0xc8 [] kvm_vgic_flush_hwstate+0x1bc/0x650 [] kvm_arch_vcpu_ioctl_run+0x2ec/0xa60 [] kvm_vcpu_ioctl+0x474/0xa68 [] do_vfs_ioctl+0x5b8/0xcb0 [] SyS_ioctl+0x8c/0xa0 [] el0_svc_naked+0x24/0x28 Memory state around the buggy address: ffffffc935769400: 00 00 fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffffffc935769480: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffffffc935769500: 04 fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ^ ffffffc935769580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffffffc935769600: 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc fc ================================================================== Fix the issue by always allocating a multiple of sizeof(unsigned long), as we do elsewhere in the vgic code. Fixes: c1bfb577a ("arm/arm64: KVM: vgic: switch to dynamic allocation") Cc: stable@vger.kernel.org Acked-by: Marc Zyngier Acked-by: Christoffer Dall Signed-off-by: Mark Rutland Signed-off-by: Marc Zyngier --- virt/kvm/arm/vgic.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index 043032c6a5a4..00429b392c61 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -1875,8 +1875,8 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - - int sz = (nr_irqs - VGIC_NR_PRIVATE_IRQS) / 8; + int nr_longs = BITS_TO_LONGS(nr_irqs - VGIC_NR_PRIVATE_IRQS); + int sz = nr_longs * sizeof(unsigned long); vgic_cpu->pending_shared = kzalloc(sz, GFP_KERNEL); vgic_cpu->active_shared = kzalloc(sz, GFP_KERNEL); vgic_cpu->pend_act_shared = kzalloc(sz, GFP_KERNEL); From 905e36ae172c83a30894a3adefab7d4f850fcf54 Mon Sep 17 00:00:00 2001 From: Matti Gottlieb Date: Sun, 14 Feb 2016 17:05:39 +0200 Subject: [PATCH 134/417] iwlwifi: mvm: Fix paging memory leak If the opmode is stopped and started again we did not free the paging buffers. Fix that. In addition when freeing the firmware's paging download buffer, set the pointer to NULL. Signed-off-by: Matti Gottlieb Signed-off-by: Emmanuel Grumbach --- drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 4 +++- drivers/net/wireless/intel/iwlwifi/mvm/mvm.h | 3 +++ drivers/net/wireless/intel/iwlwifi/mvm/ops.c | 2 ++ 3 files changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 4ed5180c547b..0ccc697fef76 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -107,7 +107,7 @@ static int iwl_send_tx_ant_cfg(struct iwl_mvm *mvm, u8 valid_tx_ant) sizeof(tx_ant_cmd), &tx_ant_cmd); } -static void iwl_free_fw_paging(struct iwl_mvm *mvm) +void iwl_free_fw_paging(struct iwl_mvm *mvm) { int i; @@ -127,6 +127,8 @@ static void iwl_free_fw_paging(struct iwl_mvm *mvm) get_order(mvm->fw_paging_db[i].fw_paging_size)); } kfree(mvm->trans->paging_download_buf); + mvm->trans->paging_download_buf = NULL; + memset(mvm->fw_paging_db, 0, sizeof(mvm->fw_paging_db)); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 5f3ac8cccf49..ff7c6df9f941 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -1225,6 +1225,9 @@ void iwl_mvm_rx_umac_scan_complete_notif(struct iwl_mvm *mvm, void iwl_mvm_rx_umac_scan_iter_complete_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb); +/* Paging */ +void iwl_free_fw_paging(struct iwl_mvm *mvm); + /* MVM debugfs */ #ifdef CONFIG_IWLWIFI_DEBUGFS int iwl_mvm_dbgfs_register(struct iwl_mvm *mvm, struct dentry *dbgfs_dir); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index 89ea70deeb84..e80be9a59520 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -684,6 +684,8 @@ static void iwl_op_mode_mvm_stop(struct iwl_op_mode *op_mode) for (i = 0; i < NVM_MAX_NUM_SECTIONS; i++) kfree(mvm->nvm_sections[i].data); + iwl_free_fw_paging(mvm); + iwl_mvm_tof_clean(mvm); ieee80211_free_hw(mvm->hw); From fb5eb24cdd5cdb83be77d3e4b2f16e92e06bd9e9 Mon Sep 17 00:00:00 2001 From: Patrik Halfar Date: Sat, 20 Feb 2016 18:49:40 +0100 Subject: [PATCH 135/417] Add Dell Wireless 5809e Gobi 4G HSPA+ Mobile Broadband Card (rev3) to qmi_wwan MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit New revison of Dell Wireless 5809e Gobi 4G HSPA+ Mobile Broadband Card has new idProduct Bus 002 Device 006: ID 413c:81b3 Dell Computer Corp. Device Descriptor: bLength 18 bDescriptorType 1 bcdUSB 2.00 bDeviceClass 0 bDeviceSubClass 0 bDeviceProtocol 0 bMaxPacketSize0 64 idVendor 0x413c Dell Computer Corp. idProduct 0x81b3 bcdDevice 0.06 iManufacturer 1 Sierra Wireless, Incorporated iProduct 2 Dell Wireless 5809e Gobi™ 4G HSPA+ Mobile Broadband Card iSerial 3 bNumConfigurations 2 Signed-off-by: Patrik Halfar Signed-off-by: David S. Miller --- drivers/net/usb/qmi_wwan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 570deef53f74..4ce4ec16e968 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -885,6 +885,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81a8, 8)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */ {QMI_FIXED_INTF(0x413c, 0x81a9, 8)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */ {QMI_FIXED_INTF(0x413c, 0x81b1, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */ + {QMI_FIXED_INTF(0x413c, 0x81b3, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */ {QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */ {QMI_FIXED_INTF(0x1e0e, 0x9001, 5)}, /* SIMCom 7230E */ From 9bdfb3b79e61c60e1a3e2dc05ad164528afa6b8a Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Sun, 21 Feb 2016 10:12:39 +0300 Subject: [PATCH 136/417] tcp: convert cached rtt from usec to jiffies when feeding initial rto Currently it's converted into msecs, thus HZ=1000 intact. Signed-off-by: Konstantin Khlebnikov Fixes: 740b0f1841f6 ("tcp: switch rtt estimations to usec resolution") Signed-off-by: David S. Miller --- net/ipv4/tcp_metrics.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index c8cbc2b4b792..a726d7853ce5 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -550,7 +550,7 @@ void tcp_init_metrics(struct sock *sk) */ if (crtt > tp->srtt_us) { /* Set RTO like tcp_rtt_estimator(), but from cached RTT. */ - crtt /= 8 * USEC_PER_MSEC; + crtt /= 8 * USEC_PER_SEC / HZ; inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk)); } else if (tp->srtt_us == 0) { /* RFC6298: 5.7 We've failed to get a valid RTT sample from From 5146d1f151122e868e594c7b45115d64825aee5f Mon Sep 17 00:00:00 2001 From: Bernie Harris Date: Mon, 22 Feb 2016 12:58:05 +1300 Subject: [PATCH 137/417] tunnel: Clear IPCB(skb)->opt before dst_link_failure called IPCB may contain data from previous layers (in the observed case the qdisc layer). In the observed scenario, the data was misinterpreted as ip header options, which later caused the ihl to be set to an invalid value (<5). This resulted in an infinite loop in the mips implementation of ip_fast_csum. This patch clears IPCB(skb)->opt before dst_link_failure can be called for various types of tunnels. This change only applies to encapsulated ipv4 packets. The code introduced in 11c21a30 which clears all of IPCB has been removed to be consistent with these changes, and instead the opt field is cleared unconditionally in ip_tunnel_xmit. The change in ip_tunnel_xmit applies to SIT, GRE, and IPIP tunnels. The relevant vti, l2tp, and pptp functions already contain similar code for clearing the IPCB. Signed-off-by: Bernie Harris Signed-off-by: David S. Miller --- net/ipv4/ip_tunnel.c | 3 ++- net/ipv4/udp_tunnel.c | 2 ++ net/ipv6/ip6_gre.c | 2 ++ net/ipv6/ip6_tunnel.c | 2 ++ 4 files changed, 8 insertions(+), 1 deletion(-) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 89e8861e05fc..336e6892a93c 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -661,6 +661,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, inner_iph = (const struct iphdr *)skb_inner_network_header(skb); connected = (tunnel->parms.iph.daddr != 0); + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + dst = tnl_params->daddr; if (dst == 0) { /* NBMA tunnel */ @@ -758,7 +760,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { tunnel->err_count--; - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); dst_link_failure(skb); } else tunnel->err_count = 0; diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c index 0ec08814f37d..96599d1a1318 100644 --- a/net/ipv4/udp_tunnel.c +++ b/net/ipv4/udp_tunnel.c @@ -89,6 +89,8 @@ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb uh->source = src_port; uh->len = htons(skb->len); + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + udp_set_csum(nocheck, skb, src, dst, skb->len); iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, tos, ttl, df, xnet); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index a69aad1e29d1..c0d4dc1c5ea4 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -777,6 +777,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev) __u32 mtu; int err; + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) encap_limit = t->parms.encap_limit; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 137fca42aaa6..6c5dfec7a377 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1180,6 +1180,8 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) u8 tproto; int err; + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + tproto = ACCESS_ONCE(t->parms.proto); if (tproto != IPPROTO_IPIP && tproto != 0) return -1; From fbb0fa8b48892a3db8f5b89fb591c741fbd2fe7a Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Mon, 22 Feb 2016 02:10:26 -0500 Subject: [PATCH 138/417] bnxt_en: Fix zero padding of tx push data. The arithmetic to zero pad the last 64-bit word in the push buffer is not correct. 1. It should be pdata + length to get to the end. 2. 'pdata' is void pointer and passing it to PTR_ALIGN() will cast the aligned pointer to void. Pass 'end' which is u64 pointer to PTR_ALIGN() instead so that the aligned pointer - 1 is the last 64-bit pointer to data. Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 8ab000dd52d9..82f191382989 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -248,7 +248,8 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) tx_push1->tx_bd_cfa_meta = cpu_to_le32(vlan_tag_flags); tx_push1->tx_bd_cfa_action = cpu_to_le32(cfa_action); - end = PTR_ALIGN(pdata + length + 1, 8) - 1; + end = pdata + length; + end = PTR_ALIGN(end, 8) - 1; *end = 0; skb_copy_from_linear_data(skb, pdata, len); From de9e478b9d49f3a0214310d921450cf5bb4a21e6 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 23 Feb 2016 14:58:52 -0800 Subject: [PATCH 139/417] x86: fix SMAP in 32-bit environments In commit 11f1a4b9755f ("x86: reorganize SMAP handling in user space accesses") I changed how the stac/clac instructions were generated around the user space accesses, which then made it possible to do batched accesses efficiently for user string copies etc. However, in doing so, I completely spaced out, and didn't even think about the 32-bit case. And nobody really even seemed to notice, because SMAP doesn't even exist until modern Skylake processors, and you'd have to be crazy to run 32-bit kernels on a modern CPU. Which brings us to Andy Lutomirski. He actually tested the 32-bit kernel on new hardware, and noticed that it doesn't work. My bad. The trivial fix is to add the required uaccess begin/end markers around the raw accesses in . I feel a bit bad about this patch, just because that header file really should be cleaned up to avoid all the duplicated code in it, and this commit just expands on the problem. But this just fixes the bug without any bigger cleanup surgery. Reported-and-tested-by: Andy Lutomirski Signed-off-by: Linus Torvalds --- arch/x86/include/asm/uaccess_32.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index f5dcb5204dcd..3fe0eac59462 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -48,20 +48,28 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) switch (n) { case 1: + __uaccess_begin(); __put_user_size(*(u8 *)from, (u8 __user *)to, 1, ret, 1); + __uaccess_end(); return ret; case 2: + __uaccess_begin(); __put_user_size(*(u16 *)from, (u16 __user *)to, 2, ret, 2); + __uaccess_end(); return ret; case 4: + __uaccess_begin(); __put_user_size(*(u32 *)from, (u32 __user *)to, 4, ret, 4); + __uaccess_end(); return ret; case 8: + __uaccess_begin(); __put_user_size(*(u64 *)from, (u64 __user *)to, 8, ret, 8); + __uaccess_end(); return ret; } } @@ -103,13 +111,19 @@ __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) switch (n) { case 1: + __uaccess_begin(); __get_user_size(*(u8 *)to, from, 1, ret, 1); + __uaccess_end(); return ret; case 2: + __uaccess_begin(); __get_user_size(*(u16 *)to, from, 2, ret, 2); + __uaccess_end(); return ret; case 4: + __uaccess_begin(); __get_user_size(*(u32 *)to, from, 4, ret, 4); + __uaccess_end(); return ret; } } @@ -148,13 +162,19 @@ __copy_from_user(void *to, const void __user *from, unsigned long n) switch (n) { case 1: + __uaccess_begin(); __get_user_size(*(u8 *)to, from, 1, ret, 1); + __uaccess_end(); return ret; case 2: + __uaccess_begin(); __get_user_size(*(u16 *)to, from, 2, ret, 2); + __uaccess_end(); return ret; case 4: + __uaccess_begin(); __get_user_size(*(u32 *)to, from, 4, ret, 4); + __uaccess_end(); return ret; } } @@ -170,13 +190,19 @@ static __always_inline unsigned long __copy_from_user_nocache(void *to, switch (n) { case 1: + __uaccess_begin(); __get_user_size(*(u8 *)to, from, 1, ret, 1); + __uaccess_end(); return ret; case 2: + __uaccess_begin(); __get_user_size(*(u16 *)to, from, 2, ret, 2); + __uaccess_end(); return ret; case 4: + __uaccess_begin(); __get_user_size(*(u32 *)to, from, 4, ret, 4); + __uaccess_end(); return ret; } } From 4577b0665515e0abc7bc72562d6328d179598815 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 17 Feb 2016 13:08:58 -0800 Subject: [PATCH 140/417] nfit: update address range scrub commands to the acpi 6.1 format The original format of these commands from the "NVDIMM DSM Interface Example" [1] are superseded by the ACPI 6.1 definition of the "NVDIMM Root Device _DSMs" [2]. [1]: http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf [2]: http://www.uefi.org/sites/default/files/resources/ACPI_6_1.pdf "9.20.7 NVDIMM Root Device _DSMs" Changes include: 1/ New 'restart' fields in ars_status, unfortunately these are implemented in the middle of the existing definition so this change is not backwards compatible. The expectation is that shipping platforms will only ever support the ACPI 6.1 definition. 2/ New status values for ars_start ('busy') and ars_status ('overflow'). Cc: Vishal Verma Cc: Linda Knippers Cc: Signed-off-by: Dan Williams --- drivers/acpi/nfit.c | 6 +++--- drivers/nvdimm/bus.c | 12 ++++++------ include/linux/libnvdimm.h | 2 +- include/uapi/linux/ndctl.h | 11 +++++++++-- 4 files changed, 19 insertions(+), 12 deletions(-) diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index 1d4b9c6bdf45..fb53db187854 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -1503,9 +1503,7 @@ static int ars_do_start(struct nvdimm_bus_descriptor *nd_desc, case 1: /* ARS unsupported, but we should never get here */ return 0; - case 2: - return -EINVAL; - case 3: + case 6: /* ARS is in progress */ msleep(1000); break; @@ -1537,6 +1535,8 @@ static int ars_get_status(struct nvdimm_bus_descriptor *nd_desc, case 2: /* No ARS performed for the current boot */ return 0; + case 3: + /* TODO: error list overflow support */ default: return -ENXIO; } diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 99953b34fa1d..5d28e9405f32 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -382,14 +382,14 @@ static const struct nd_cmd_desc __nd_cmd_bus_descs[] = { [ND_CMD_ARS_CAP] = { .in_num = 2, .in_sizes = { 8, 8, }, - .out_num = 2, - .out_sizes = { 4, 4, }, + .out_num = 4, + .out_sizes = { 4, 4, 4, 4, }, }, [ND_CMD_ARS_START] = { - .in_num = 4, - .in_sizes = { 8, 8, 2, 6, }, - .out_num = 1, - .out_sizes = { 4, }, + .in_num = 5, + .in_sizes = { 8, 8, 2, 1, 5, }, + .out_num = 2, + .out_sizes = { 4, 4, }, }, [ND_CMD_ARS_STATUS] = { .out_num = 3, diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index c736382fd260..141ffdd59960 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -26,7 +26,7 @@ enum { /* need to set a limit somewhere, but yes, this is likely overkill */ ND_IOCTL_MAX_BUFLEN = SZ_4M, - ND_CMD_MAX_ELEM = 4, + ND_CMD_MAX_ELEM = 5, ND_CMD_MAX_ENVELOPE = 16, ND_MAX_MAPPINGS = 32, diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index 5b4a4be06e2b..cc68b92124d4 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -66,14 +66,18 @@ struct nd_cmd_ars_cap { __u64 length; __u32 status; __u32 max_ars_out; + __u32 clear_err_unit; + __u32 reserved; } __packed; struct nd_cmd_ars_start { __u64 address; __u64 length; __u16 type; - __u8 reserved[6]; + __u8 flags; + __u8 reserved[5]; __u32 status; + __u32 scrub_time; } __packed; struct nd_cmd_ars_status { @@ -81,11 +85,14 @@ struct nd_cmd_ars_status { __u32 out_length; __u64 address; __u64 length; + __u64 restart_address; + __u64 restart_length; __u16 type; + __u16 flags; __u32 num_records; struct nd_ars_record { __u32 handle; - __u32 flags; + __u32 reserved; __u64 err_address; __u64 length; } __packed records[0]; From 93f834df9c2d4e362dfdc4b05daa0a4e18814836 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Sat, 20 Feb 2016 14:32:24 -0800 Subject: [PATCH 141/417] devm_memremap: Fix error value when memremap failed devm_memremap() returns an ERR_PTR() value in case of error. However, it returns NULL when memremap() failed. This causes the caller, such as the pmem driver, to proceed and oops later. Change devm_memremap() to return ERR_PTR(-ENXIO) when memremap() failed. Signed-off-by: Toshi Kani Cc: Andrew Morton Cc: Reviewed-by: Ross Zwisler Signed-off-by: Dan Williams --- kernel/memremap.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/memremap.c b/kernel/memremap.c index 2c468dea60bc..b04ea2f5fbfe 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -136,8 +136,10 @@ void *devm_memremap(struct device *dev, resource_size_t offset, if (addr) { *ptr = addr; devres_add(dev, ptr); - } else + } else { devres_free(ptr); + return ERR_PTR(-ENXIO); + } return addr; } From c45442055dfdeb265cc20c9eeaa9fd11a75fbf51 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 22 Feb 2016 22:58:34 +0100 Subject: [PATCH 142/417] nvdimm: use 'u64' for pfn flags A recent bugfix changed pfn_t to always be 64-bit wide, but did not change the code in pmem.c, which is now broken on 32-bit architectures as reported by gcc: In file included from ../drivers/nvdimm/pmem.c:28:0: drivers/nvdimm/pmem.c: In function 'pmem_alloc': include/linux/pfn_t.h:15:17: error: large integer implicitly truncated to unsigned type [-Werror=overflow] #define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3)) This changes the intermediate pfn_flags in struct pmem_device to be 64 bit wide as well, so they can store the flags correctly. Signed-off-by: Arnd Bergmann Fixes: db78c22230d0 ("mm: fix pfn_t vs highmem") Signed-off-by: Dan Williams --- drivers/nvdimm/pmem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 7edf31671dab..8d0b54670184 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -41,7 +41,7 @@ struct pmem_device { phys_addr_t phys_addr; /* when non-zero this device is hosting a 'pfn' instance */ phys_addr_t data_offset; - unsigned long pfn_flags; + u64 pfn_flags; void __pmem *virt_addr; size_t size; struct badblocks bb; From bb143f814ea488769ca2e79e0b376139cb5f134b Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Tue, 23 Feb 2016 11:55:16 +0530 Subject: [PATCH 143/417] ARCv2: SMP: Emulate IPI to self using software triggered interrupt ARConnect/MCIP Inter-Core-Interrupt module can't send interrupt to local core. So use core intc capability to trigger software interrupt to self, using an unsued IRQ #21. This showed up as csd deadlock with LTP trace_sched on a dual core system. This test acts as scheduler fuzzer, triggering all sorts of schedulting activity. Trouble starts with IPI to self, which doesn't get delivered (effectively lost due to H/w capability), but the msg intended to be sent remain enqueued in per-cpu @ipi_data. All subsequent IPIs to this core from other cores get elided due to the IPI coalescing optimization in ipi_send_msg_one() where a pending msg implies an IPI already sent and assumes other core is yet to ack it. After the elided IPI, other core simply goes into csd_lock_wait() but never comes out as this core never sees the interrupt. Fixes STAR 9001008624 Cc: Peter Zijlstra Cc: [4.2] Signed-off-by: Vineet Gupta --- arch/arc/include/asm/irqflags-arcv2.h | 11 +++++++++++ arch/arc/kernel/entry-arcv2.S | 11 ++++++----- arch/arc/kernel/mcip.c | 15 +++++++++++++++ 3 files changed, 32 insertions(+), 5 deletions(-) diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h index 1fc18ee06cf2..37c2f751eebf 100644 --- a/arch/arc/include/asm/irqflags-arcv2.h +++ b/arch/arc/include/asm/irqflags-arcv2.h @@ -22,6 +22,7 @@ #define AUX_IRQ_CTRL 0x00E #define AUX_IRQ_ACT 0x043 /* Active Intr across all levels */ #define AUX_IRQ_LVL_PEND 0x200 /* Pending Intr across all levels */ +#define AUX_IRQ_HINT 0x201 /* For generating Soft Interrupts */ #define AUX_IRQ_PRIORITY 0x206 #define ICAUSE 0x40a #define AUX_IRQ_SELECT 0x40b @@ -115,6 +116,16 @@ static inline int arch_irqs_disabled(void) return arch_irqs_disabled_flags(arch_local_save_flags()); } +static inline void arc_softirq_trigger(int irq) +{ + write_aux_reg(AUX_IRQ_HINT, irq); +} + +static inline void arc_softirq_clear(int irq) +{ + write_aux_reg(AUX_IRQ_HINT, 0); +} + #else .macro IRQ_DISABLE scratch diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S index b17830294706..c1264607bbff 100644 --- a/arch/arc/kernel/entry-arcv2.S +++ b/arch/arc/kernel/entry-arcv2.S @@ -45,11 +45,12 @@ VECTOR reserved ; Reserved slots VECTOR handle_interrupt ; (16) Timer0 VECTOR handle_interrupt ; unused (Timer1) VECTOR handle_interrupt ; unused (WDT) -VECTOR handle_interrupt ; (19) ICI (inter core interrupt) -VECTOR handle_interrupt -VECTOR handle_interrupt -VECTOR handle_interrupt -VECTOR handle_interrupt ; (23) End of fixed IRQs +VECTOR handle_interrupt ; (19) Inter core Interrupt (IPI) +VECTOR handle_interrupt ; (20) perf Interrupt +VECTOR handle_interrupt ; (21) Software Triggered Intr (Self IPI) +VECTOR handle_interrupt ; unused +VECTOR handle_interrupt ; (23) unused +# End of fixed IRQs .rept CONFIG_ARC_NUMBER_OF_INTERRUPTS - 8 VECTOR handle_interrupt diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index 002c5fcf8947..9e1bd03b87a6 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -11,9 +11,12 @@ #include #include #include +#include #include #include +#define SOFTIRQ_IRQ 21 + static char smp_cpuinfo_buf[128]; static int idu_detected; @@ -22,6 +25,7 @@ static DEFINE_RAW_SPINLOCK(mcip_lock); static void mcip_setup_per_cpu(int cpu) { smp_ipi_irq_setup(cpu, IPI_IRQ); + smp_ipi_irq_setup(cpu, SOFTIRQ_IRQ); } static void mcip_ipi_send(int cpu) @@ -29,6 +33,12 @@ static void mcip_ipi_send(int cpu) unsigned long flags; int ipi_was_pending; + /* ARConnect can only send IPI to others */ + if (unlikely(cpu == raw_smp_processor_id())) { + arc_softirq_trigger(SOFTIRQ_IRQ); + return; + } + /* * NOTE: We must spin here if the other cpu hasn't yet * serviced a previous message. This can burn lots @@ -63,6 +73,11 @@ static void mcip_ipi_clear(int irq) unsigned long flags; unsigned int __maybe_unused copy; + if (unlikely(irq == SOFTIRQ_IRQ)) { + arc_softirq_clear(irq); + return; + } + raw_spin_lock_irqsave(&mcip_lock, flags); /* Who sent the IPI */ From dbcbc7e7cee15058fdb9696b2b38c692680fc413 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Thu, 28 Jan 2016 12:48:05 +0530 Subject: [PATCH 144/417] ARC: [intc-compact] Remove IPI setup from ARCompact port There is no real ARC700 based SMP SoC so remove IPI definition. EZChip's SMP ARC700 is going to use a different intc and IPI provider anyways. Signed-off-by: Vineet Gupta --- arch/arc/include/asm/irq.h | 1 - arch/arc/kernel/intc-compact.c | 3 --- 2 files changed, 4 deletions(-) diff --git a/arch/arc/include/asm/irq.h b/arch/arc/include/asm/irq.h index 4fd7d62a6e30..bc5103637326 100644 --- a/arch/arc/include/asm/irq.h +++ b/arch/arc/include/asm/irq.h @@ -16,7 +16,6 @@ #ifdef CONFIG_ISA_ARCOMPACT #define TIMER0_IRQ 3 #define TIMER1_IRQ 4 -#define IPI_IRQ (NR_CPU_IRQS-1) /* dummy to enable SMP build for up hardware */ #else #define TIMER0_IRQ 16 #define TIMER1_IRQ 17 diff --git a/arch/arc/kernel/intc-compact.c b/arch/arc/kernel/intc-compact.c index 06bcedf19b62..224d1c3aa9c4 100644 --- a/arch/arc/kernel/intc-compact.c +++ b/arch/arc/kernel/intc-compact.c @@ -81,9 +81,6 @@ static int arc_intc_domain_map(struct irq_domain *d, unsigned int irq, { switch (irq) { case TIMER0_IRQ: -#ifdef CONFIG_SMP - case IPI_IRQ: -#endif irq_set_chip_and_handler(irq, &onchip_intc, handle_percpu_irq); break; default: From 9681787930cec7cee77db0a93c747153ef962b8a Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Tue, 23 Feb 2016 13:35:12 +0530 Subject: [PATCH 145/417] ARCv2: SMP: Push IPI_IRQ into IPI provider Signed-off-by: Vineet Gupta --- arch/arc/include/asm/irq.h | 1 - arch/arc/kernel/mcip.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arc/include/asm/irq.h b/arch/arc/include/asm/irq.h index bc5103637326..49014f0ef36d 100644 --- a/arch/arc/include/asm/irq.h +++ b/arch/arc/include/asm/irq.h @@ -19,7 +19,6 @@ #else #define TIMER0_IRQ 16 #define TIMER1_IRQ 17 -#define IPI_IRQ 19 #endif #include diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index 9e1bd03b87a6..e30d5d428330 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -15,6 +15,7 @@ #include #include +#define IPI_IRQ 19 #define SOFTIRQ_IRQ 21 static char smp_cpuinfo_buf[128]; From 3dea30ca5bef0e013abe857057a952a9d6757fe5 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Fri, 19 Feb 2016 07:57:41 +0530 Subject: [PATCH 146/417] ARCv2: Elide sending new cross core intr if receiver didn't ack prev ARConnect/MCIP IPI sending has a retry-wait loop in case caller had not seen a previous such interrupt. Turns out that it is not needed at all. Linux cross core calling allows coalescing multiple IPIs to same receiver - it is fine as long as there is one. This logic is built into upper layer already, at a higher level of abstraction. ipi_send_msg_one() sets the actual msg payload, but it only calls MCIP IPI sending if msg holder was empty (using atomic-set-new-and-get-old construct). Thus it is unlikely that the retry-wait looping was ever getting exercised at all. Cc: Chuck Jordan Cc: Peter Zijlstra Signed-off-by: Vineet Gupta --- arch/arc/kernel/mcip.c | 27 ++++++++++----------------- 1 file changed, 10 insertions(+), 17 deletions(-) diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index e30d5d428330..7afc3c703ed1 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -40,26 +40,19 @@ static void mcip_ipi_send(int cpu) return; } + raw_spin_lock_irqsave(&mcip_lock, flags); + /* - * NOTE: We must spin here if the other cpu hasn't yet - * serviced a previous message. This can burn lots - * of time, but we MUST follows this protocol or - * ipi messages can be lost!!! - * Also, we must release the lock in this loop because - * the other side may get to this same loop and not - * be able to ack -- thus causing deadlock. + * If receiver already has a pending interrupt, elide sending this one. + * Linux cross core calling works well with concurrent IPIs + * coalesced into one + * see arch/arc/kernel/smp.c: ipi_send_msg_one() */ + __mcip_cmd(CMD_INTRPT_READ_STATUS, cpu); + ipi_was_pending = read_aux_reg(ARC_REG_MCIP_READBACK); + if (!ipi_was_pending) + __mcip_cmd(CMD_INTRPT_GENERATE_IRQ, cpu); - do { - raw_spin_lock_irqsave(&mcip_lock, flags); - __mcip_cmd(CMD_INTRPT_READ_STATUS, cpu); - ipi_was_pending = read_aux_reg(ARC_REG_MCIP_READBACK); - if (ipi_was_pending == 0) - break; /* break out but keep lock */ - raw_spin_unlock_irqrestore(&mcip_lock, flags); - } while (1); - - __mcip_cmd(CMD_INTRPT_GENERATE_IRQ, cpu); raw_spin_unlock_irqrestore(&mcip_lock, flags); #ifdef CONFIG_ARC_IPI_DBG From d73b73f5626ac0b131b31b7b9457e19201bc570b Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Fri, 19 Feb 2016 08:18:11 +0530 Subject: [PATCH 147/417] ARC: SMP: No need for CONFIG_ARC_IPI_DBG This was more relevant during SMP bringup. The warning for bogus msg better be visible always. Signed-off-by: Vineet Gupta --- arch/arc/Kconfig | 8 -------- arch/arc/kernel/mcip.c | 9 +-------- arch/arc/kernel/smp.c | 3 --- 3 files changed, 1 insertion(+), 19 deletions(-) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 4abc81907071..8a188bc1786a 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -532,14 +532,6 @@ config ARC_DBG_TLB_MISS_COUNT Counts number of I and D TLB Misses and exports them via Debugfs The counters can be cleared via Debugfs as well -if SMP - -config ARC_IPI_DBG - bool "Debug Inter Core interrupts" - default n - -endif - endif config ARC_UBOOT_SUPPORT diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index 7afc3c703ed1..7b4af70ffd18 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -65,7 +65,6 @@ static void mcip_ipi_clear(int irq) { unsigned int cpu, c; unsigned long flags; - unsigned int __maybe_unused copy; if (unlikely(irq == SOFTIRQ_IRQ)) { arc_softirq_clear(irq); @@ -77,7 +76,7 @@ static void mcip_ipi_clear(int irq) /* Who sent the IPI */ __mcip_cmd(CMD_INTRPT_CHECK_SOURCE, 0); - copy = cpu = read_aux_reg(ARC_REG_MCIP_READBACK); /* 1,2,4,8... */ + cpu = read_aux_reg(ARC_REG_MCIP_READBACK); /* 1,2,4,8... */ /* * In rare case, multiple concurrent IPIs sent to same target can @@ -91,12 +90,6 @@ static void mcip_ipi_clear(int irq) } while (cpu); raw_spin_unlock_irqrestore(&mcip_lock, flags); - -#ifdef CONFIG_ARC_IPI_DBG - if (c != __ffs(copy)) - pr_info("IPIs from %x coalesced to %x\n", - copy, raw_smp_processor_id()); -#endif } static void mcip_probe_n_setup(void) diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index ef6e9e15b82a..424e937da5c8 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -336,11 +336,8 @@ irqreturn_t do_IPI(int irq, void *dev_id) int rc; rc = __do_IPI(msg); -#ifdef CONFIG_ARC_IPI_DBG - /* IPI received but no valid @msg */ if (rc) pr_info("IPI with bogus msg %ld in %ld\n", msg, copy); -#endif pending &= ~(1U << msg); } while (pending); From 04d1d281dcfe683a53cddfab8371fc8bb302b069 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 23 Feb 2016 13:19:29 -0800 Subject: [PATCH 148/417] x86/entry/32: Add an ASM_CLAC to entry_SYSENTER_32 Both before and after 5f310f739b4c ("x86/entry/32: Re-implement SYSENTER using the new C path"), we relied on a uaccess very early in the SYSENTER path to clear AC. After that change, though, we can potentially make it all the way into C code with AC set, which enlarges the attack surface for SMAP bypass by doing SYSENTER with AC set. Strengthen the SMAP protection by addding the missing ASM_CLAC right at the beginning. Signed-off-by: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/3e36be110724896e32a4a1fe73bacb349d3cba94.1456262295.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_32.S | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 77d8c5112900..bb3e376d0f33 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -294,6 +294,7 @@ sysenter_past_esp: pushl $__USER_DS /* pt_regs->ss */ pushl %ebp /* pt_regs->sp (stashed in bp) */ pushfl /* pt_regs->flags (except IF = 0) */ + ASM_CLAC /* Clear AC after saving FLAGS */ orl $X86_EFLAGS_IF, (%esp) /* Fix IF */ pushl $__USER_CS /* pt_regs->cs */ pushl $0 /* pt_regs->ip = 0 (placeholder) */ From 5e45a2589d24573c564630990c88ac93659f8fe4 Mon Sep 17 00:00:00 2001 From: Ludovic Desroches Date: Fri, 19 Feb 2016 20:21:17 +0100 Subject: [PATCH 149/417] ARM: at91/dt: fix typo in sama5d2 pinmux descriptions PIN_PA15 macro has the same value as PIN_PA14 so we were overriding PA14 mux/configuration. Signed-off-by: Ludovic Desroches Reported-by: Cyrille Pitchen Fixes: 7f16cb676c00 ("ARM: at91/dt: add sama5d2 pinmux") Cc: # v4.4+ Signed-off-by: Alexandre Belloni Signed-off-by: Olof Johansson --- arch/arm/boot/dts/sama5d2-pinfunc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/sama5d2-pinfunc.h b/arch/arm/boot/dts/sama5d2-pinfunc.h index 1afe24629d1f..b0c912feaa2f 100644 --- a/arch/arm/boot/dts/sama5d2-pinfunc.h +++ b/arch/arm/boot/dts/sama5d2-pinfunc.h @@ -90,7 +90,7 @@ #define PIN_PA14__I2SC1_MCK PINMUX_PIN(PIN_PA14, 4, 2) #define PIN_PA14__FLEXCOM3_IO2 PINMUX_PIN(PIN_PA14, 5, 1) #define PIN_PA14__D9 PINMUX_PIN(PIN_PA14, 6, 2) -#define PIN_PA15 14 +#define PIN_PA15 15 #define PIN_PA15__GPIO PINMUX_PIN(PIN_PA15, 0, 0) #define PIN_PA15__SPI0_MOSI PINMUX_PIN(PIN_PA15, 1, 1) #define PIN_PA15__TF1 PINMUX_PIN(PIN_PA15, 2, 1) From a9e5547b1908ee282b875470a08c96acf17656d6 Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Mon, 22 Feb 2016 14:22:30 +0100 Subject: [PATCH 150/417] MAINTAINERS: alpine: add a new maintainer and update the entry Add myself as a co-maintainer for the Alpine support. Also update the entry to take in account Alpine ARM64 boards, Alpine ARM device trees and Alpine-specific drivers. Signed-off-by: Antoine Tenart Acked-by: Tsahee Zidenberg Signed-off-by: Olof Johansson --- MAINTAINERS | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 4978dc19a4d2..42cc0d76296d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -929,8 +929,12 @@ N: meson[x68] ARM/Annapurna Labs ALPINE ARCHITECTURE M: Tsahee Zidenberg +M: Antoine Tenart S: Maintained F: arch/arm/mach-alpine/ +F: arch/arm/boot/dts/alpine* +F: arch/arm64/boot/dts/al/ +F: drivers/*/*alpine* ARM/ATMEL AT91RM9200, AT91SAM9 AND SAMA5 SOC SUPPORT M: Nicolas Ferre From 79318452cb36678bde20d384dc3eab537d930d3e Mon Sep 17 00:00:00 2001 From: Carlo Caione Date: Tue, 23 Feb 2016 10:43:11 +0100 Subject: [PATCH 151/417] MAINTAINERS: Extend info, add wiki and ml for meson arch Update the maintainers info with wiki and mailing list for the meson platform. Fix a wrong file attribution and add maintainership for the generic meson platforms. Signed-off-by: Carlo Caione Signed-off-by: Olof Johansson --- MAINTAINERS | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 42cc0d76296d..536adfcf1319 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -920,12 +920,15 @@ M: Emilio López S: Maintained F: drivers/clk/sunxi/ -ARM/Amlogic MesonX SoC support +ARM/Amlogic Meson SoC support M: Carlo Caione L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +L: linux-meson@googlegroups.com +W: http://linux-meson.com/ S: Maintained -F: drivers/media/rc/meson-ir.c -N: meson[x68] +F: arch/arm/mach-meson/ +F: arch/arm/boot/dts/meson* +N: meson ARM/Annapurna Labs ALPINE ARCHITECTURE M: Tsahee Zidenberg From 9ef2d8be55652804205a34dcbfec78b933c0ea30 Mon Sep 17 00:00:00 2001 From: Valentin Rothberg Date: Wed, 24 Feb 2016 09:40:22 +0100 Subject: [PATCH 152/417] arc: SMP: CONFIG_ARC_IPI_DBG cleanup Previous Commit ("ARC: SMP: No need for CONFIG_ARC_IPI_DBG") removed the Kconfig option ARC_IPI_DBG. Remove the last reference on this option. Signed-off-by: Valentin Rothberg Signed-off-by: Vineet Gupta --- arch/arc/kernel/mcip.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index 7b4af70ffd18..c41c364b926c 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -54,11 +54,6 @@ static void mcip_ipi_send(int cpu) __mcip_cmd(CMD_INTRPT_GENERATE_IRQ, cpu); raw_spin_unlock_irqrestore(&mcip_lock, flags); - -#ifdef CONFIG_ARC_IPI_DBG - if (ipi_was_pending) - pr_info("IPI ACK delayed from cpu %d\n", cpu); -#endif } static void mcip_ipi_clear(int irq) From 1d6a821277aaa0cdd666278aaff93298df313d41 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 15 Feb 2016 17:04:04 +0000 Subject: [PATCH 153/417] arm/arm64: KVM: Feed initialized memory to MMIO accesses On an MMIO access, we always copy the on-stack buffer info the shared "run" structure, even if this is a read access. This ends up leaking up to 8 bytes of uninitialized memory into userspace, depending on the size of the access. An obvious fix for this one is to only perform the copy if this is an actual write. Reviewed-by: Christoffer Dall Signed-off-by: Marc Zyngier --- arch/arm/kvm/mmio.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c index 7f33b2056ae6..0f6600f05137 100644 --- a/arch/arm/kvm/mmio.c +++ b/arch/arm/kvm/mmio.c @@ -206,7 +206,8 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, run->mmio.is_write = is_write; run->mmio.phys_addr = fault_ipa; run->mmio.len = len; - memcpy(run->mmio.data, data_buf, len); + if (is_write) + memcpy(run->mmio.data, data_buf, len); if (!ret) { /* We handled the access successfully in the kernel. */ From 5ec5d10682745d3280a37e8ffee1ddcd37ecfa94 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 24 Feb 2016 13:53:46 +0100 Subject: [PATCH 154/417] Revert "ACPI / PCI: Simplify acpi_penalize_isa_irq()" Revert commit 0971686954f9 "ACPI / PCI: Simplify acpi_penalize_isa_irq()" that depends on commit b5bd02695471 (ACPI, PCI, irq: remove interrupt count restriction) which introduced a regression and needs to be reverted for this reason. Signed-off-by: Rafael J. Wysocki --- drivers/acpi/pci_link.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c index fa2863567eed..5114d8007aa0 100644 --- a/drivers/acpi/pci_link.c +++ b/drivers/acpi/pci_link.c @@ -877,9 +877,17 @@ static int __init acpi_irq_penalty_update(char *str, int used) */ void acpi_penalize_isa_irq(int irq, int active) { - if (irq >= 0) - acpi_irq_add_penalty(irq, active ? - PIRQ_PENALTY_ISA_USED : PIRQ_PENALTY_PCI_USING); + int penalty; + + if (irq < 0) + return; + + if (active) + penalty = PIRQ_PENALTY_ISA_USED; + else + penalty = PIRQ_PENALTY_PCI_USING; + + acpi_irq_add_penalty(irq, penalty); } bool acpi_isa_irq_available(int irq) From e249714571db26cdb1ae8df7ed39971bafa041a7 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 24 Feb 2016 13:55:38 +0100 Subject: [PATCH 155/417] Revert "ACPI, PCI, irq: remove interrupt count restriction" Revert commit b5bd02695471 (ACPI, PCI, irq: remove interrupt count restriction) that introduced a boot regression on some systems where it caused kmalloc() to be used too early. Link: http://marc.info/?l=linux-acpi&m=145580159209240&w=2 Reported-by: Nalla, Ravikanth Signed-off-by: Rafael J. Wysocki --- drivers/acpi/pci_link.c | 136 ++++++++++------------------------------ 1 file changed, 34 insertions(+), 102 deletions(-) diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c index 5114d8007aa0..ededa909df2f 100644 --- a/drivers/acpi/pci_link.c +++ b/drivers/acpi/pci_link.c @@ -4,7 +4,6 @@ * Copyright (C) 2001, 2002 Andy Grover * Copyright (C) 2001, 2002 Paul Diefenbaugh * Copyright (C) 2002 Dominik Brodowski - * Copyright (c) 2015, The Linux Foundation. All rights reserved. * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * @@ -438,6 +437,7 @@ static int acpi_pci_link_set(struct acpi_pci_link *link, int irq) * enabled system. */ +#define ACPI_MAX_IRQS 256 #define ACPI_MAX_ISA_IRQ 16 #define PIRQ_PENALTY_PCI_AVAILABLE (0) @@ -447,7 +447,7 @@ static int acpi_pci_link_set(struct acpi_pci_link *link, int irq) #define PIRQ_PENALTY_ISA_USED (16*16*16*16*16) #define PIRQ_PENALTY_ISA_ALWAYS (16*16*16*16*16*16) -static int acpi_irq_isa_penalty[ACPI_MAX_ISA_IRQ] = { +static int acpi_irq_penalty[ACPI_MAX_IRQS] = { PIRQ_PENALTY_ISA_ALWAYS, /* IRQ0 timer */ PIRQ_PENALTY_ISA_ALWAYS, /* IRQ1 keyboard */ PIRQ_PENALTY_ISA_ALWAYS, /* IRQ2 cascade */ @@ -464,68 +464,9 @@ static int acpi_irq_isa_penalty[ACPI_MAX_ISA_IRQ] = { PIRQ_PENALTY_ISA_USED, /* IRQ13 fpe, sometimes */ PIRQ_PENALTY_ISA_USED, /* IRQ14 ide0 */ PIRQ_PENALTY_ISA_USED, /* IRQ15 ide1 */ + /* >IRQ15 */ }; -struct irq_penalty_info { - int irq; - int penalty; - struct list_head node; -}; - -static LIST_HEAD(acpi_irq_penalty_list); - -static int acpi_irq_get_penalty(int irq) -{ - struct irq_penalty_info *irq_info; - - if (irq < ACPI_MAX_ISA_IRQ) - return acpi_irq_isa_penalty[irq]; - - list_for_each_entry(irq_info, &acpi_irq_penalty_list, node) { - if (irq_info->irq == irq) - return irq_info->penalty; - } - - return 0; -} - -static int acpi_irq_set_penalty(int irq, int new_penalty) -{ - struct irq_penalty_info *irq_info; - - /* see if this is a ISA IRQ */ - if (irq < ACPI_MAX_ISA_IRQ) { - acpi_irq_isa_penalty[irq] = new_penalty; - return 0; - } - - /* next, try to locate from the dynamic list */ - list_for_each_entry(irq_info, &acpi_irq_penalty_list, node) { - if (irq_info->irq == irq) { - irq_info->penalty = new_penalty; - return 0; - } - } - - /* nope, let's allocate a slot for this IRQ */ - irq_info = kzalloc(sizeof(*irq_info), GFP_KERNEL); - if (!irq_info) - return -ENOMEM; - - irq_info->irq = irq; - irq_info->penalty = new_penalty; - list_add_tail(&irq_info->node, &acpi_irq_penalty_list); - - return 0; -} - -static void acpi_irq_add_penalty(int irq, int penalty) -{ - int curpen = acpi_irq_get_penalty(irq); - - acpi_irq_set_penalty(irq, curpen + penalty); -} - int __init acpi_irq_penalty_init(void) { struct acpi_pci_link *link; @@ -546,16 +487,15 @@ int __init acpi_irq_penalty_init(void) link->irq.possible_count; for (i = 0; i < link->irq.possible_count; i++) { - if (link->irq.possible[i] < ACPI_MAX_ISA_IRQ) { - int irqpos = link->irq.possible[i]; - - acpi_irq_add_penalty(irqpos, penalty); - } + if (link->irq.possible[i] < ACPI_MAX_ISA_IRQ) + acpi_irq_penalty[link->irq. + possible[i]] += + penalty; } } else if (link->irq.active) { - acpi_irq_add_penalty(link->irq.active, - PIRQ_PENALTY_PCI_POSSIBLE); + acpi_irq_penalty[link->irq.active] += + PIRQ_PENALTY_PCI_POSSIBLE; } } @@ -607,12 +547,12 @@ static int acpi_pci_link_allocate(struct acpi_pci_link *link) * the use of IRQs 9, 10, 11, and >15. */ for (i = (link->irq.possible_count - 1); i >= 0; i--) { - if (acpi_irq_get_penalty(irq) > - acpi_irq_get_penalty(link->irq.possible[i])) + if (acpi_irq_penalty[irq] > + acpi_irq_penalty[link->irq.possible[i]]) irq = link->irq.possible[i]; } } - if (acpi_irq_get_penalty(irq) >= PIRQ_PENALTY_ISA_ALWAYS) { + if (acpi_irq_penalty[irq] >= PIRQ_PENALTY_ISA_ALWAYS) { printk(KERN_ERR PREFIX "No IRQ available for %s [%s]. " "Try pci=noacpi or acpi=off\n", acpi_device_name(link->device), @@ -628,8 +568,7 @@ static int acpi_pci_link_allocate(struct acpi_pci_link *link) acpi_device_bid(link->device)); return -ENODEV; } else { - acpi_irq_add_penalty(link->irq.active, PIRQ_PENALTY_PCI_USING); - + acpi_irq_penalty[link->irq.active] += PIRQ_PENALTY_PCI_USING; printk(KERN_WARNING PREFIX "%s [%s] enabled at IRQ %d\n", acpi_device_name(link->device), acpi_device_bid(link->device), link->irq.active); @@ -839,7 +778,7 @@ static void acpi_pci_link_remove(struct acpi_device *device) } /* - * modify penalty from cmdline + * modify acpi_irq_penalty[] from cmdline */ static int __init acpi_irq_penalty_update(char *str, int used) { @@ -857,10 +796,13 @@ static int __init acpi_irq_penalty_update(char *str, int used) if (irq < 0) continue; + if (irq >= ARRAY_SIZE(acpi_irq_penalty)) + continue; + if (used) - acpi_irq_add_penalty(irq, PIRQ_PENALTY_ISA_USED); + acpi_irq_penalty[irq] += PIRQ_PENALTY_ISA_USED; else - acpi_irq_set_penalty(irq, PIRQ_PENALTY_PCI_AVAILABLE); + acpi_irq_penalty[irq] = PIRQ_PENALTY_PCI_AVAILABLE; if (retval != 2) /* no next number */ break; @@ -877,23 +819,18 @@ static int __init acpi_irq_penalty_update(char *str, int used) */ void acpi_penalize_isa_irq(int irq, int active) { - int penalty; - - if (irq < 0) - return; - - if (active) - penalty = PIRQ_PENALTY_ISA_USED; - else - penalty = PIRQ_PENALTY_PCI_USING; - - acpi_irq_add_penalty(irq, penalty); + if (irq >= 0 && irq < ARRAY_SIZE(acpi_irq_penalty)) { + if (active) + acpi_irq_penalty[irq] += PIRQ_PENALTY_ISA_USED; + else + acpi_irq_penalty[irq] += PIRQ_PENALTY_PCI_USING; + } } bool acpi_isa_irq_available(int irq) { - return irq >= 0 && - (acpi_irq_get_penalty(irq) < PIRQ_PENALTY_ISA_ALWAYS); + return irq >= 0 && (irq >= ARRAY_SIZE(acpi_irq_penalty) || + acpi_irq_penalty[irq] < PIRQ_PENALTY_ISA_ALWAYS); } /* @@ -903,18 +840,13 @@ bool acpi_isa_irq_available(int irq) */ void acpi_penalize_sci_irq(int irq, int trigger, int polarity) { - int penalty; - - if (irq < 0) - return; - - if (trigger != ACPI_MADT_TRIGGER_LEVEL || - polarity != ACPI_MADT_POLARITY_ACTIVE_LOW) - penalty = PIRQ_PENALTY_ISA_ALWAYS; - else - penalty = PIRQ_PENALTY_PCI_USING; - - acpi_irq_add_penalty(irq, penalty); + if (irq >= 0 && irq < ARRAY_SIZE(acpi_irq_penalty)) { + if (trigger != ACPI_MADT_TRIGGER_LEVEL || + polarity != ACPI_MADT_POLARITY_ACTIVE_LOW) + acpi_irq_penalty[irq] += PIRQ_PENALTY_ISA_ALWAYS; + else + acpi_irq_penalty[irq] += PIRQ_PENALTY_PCI_USING; + } } /* From 172b2386ed16a9143d9a456aae5ec87275c61489 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 10 Feb 2016 17:50:23 +0100 Subject: [PATCH 156/417] KVM: x86: fix missed hardware breakpoints Sometimes when setting a breakpoint a process doesn't stop on it. This is because the debug registers are not loaded correctly on VCPU load. The following simple reproducer from Oleg Nesterov tries using debug registers in two threads. To see the bug, run a 2-VCPU guest with "taskset -c 0" and run "./bp 0 1" inside the guest. #include #include #include #include #include #include #include #include #include #define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER) unsigned long encode_dr7(int drnum, int enable, unsigned int type, unsigned int len) { unsigned long dr7; dr7 = ((len | type) & 0xf) << (DR_CONTROL_SHIFT + drnum * DR_CONTROL_SIZE); if (enable) dr7 |= (DR_GLOBAL_ENABLE << (drnum * DR_ENABLE_SIZE)); return dr7; } int write_dr(int pid, int dr, unsigned long val) { return ptrace(PTRACE_POKEUSER, pid, offsetof (struct user, u_debugreg[dr]), val); } void set_bp(pid_t pid, void *addr) { unsigned long dr7; assert(write_dr(pid, 0, (long)addr) == 0); dr7 = encode_dr7(0, 1, DR_RW_EXECUTE, DR_LEN_1); assert(write_dr(pid, 7, dr7) == 0); } void *get_rip(int pid) { return (void*)ptrace(PTRACE_PEEKUSER, pid, offsetof(struct user, regs.rip), 0); } void test(int nr) { void *bp_addr = &&label + nr, *bp_hit; int pid; printf("test bp %d\n", nr); assert(nr < 16); // see 16 asm nops below pid = fork(); if (!pid) { assert(ptrace(PTRACE_TRACEME, 0,0,0) == 0); kill(getpid(), SIGSTOP); for (;;) { label: asm ( "nop; nop; nop; nop;" "nop; nop; nop; nop;" "nop; nop; nop; nop;" "nop; nop; nop; nop;" ); } } assert(pid == wait(NULL)); set_bp(pid, bp_addr); for (;;) { assert(ptrace(PTRACE_CONT, pid, 0, 0) == 0); assert(pid == wait(NULL)); bp_hit = get_rip(pid); if (bp_hit != bp_addr) fprintf(stderr, "ERR!! hit wrong bp %ld != %d\n", bp_hit - &&label, nr); } } int main(int argc, const char *argv[]) { while (--argc) { int nr = atoi(*++argv); if (!fork()) test(nr); } while (wait(NULL) > 0) ; return 0; } Cc: stable@vger.kernel.org Suggested-by: Nadav Amit Reported-by: Andrey Wagin Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4244c2baf57d..f4891f2ece23 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2752,6 +2752,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) } kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); + vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD; } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) From 0c1d77f4ba5cc9c05a29adca3d6466cdf4969b70 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Fri, 19 Feb 2016 18:07:21 +0100 Subject: [PATCH 157/417] KVM: x86: fix conversion of addresses to linear in 32-bit protected mode Commit e8dd2d2d641c ("Silence compiler warning in arch/x86/kvm/emulate.c", 2015-09-06) broke boot of the Hurd. The bug is that the "default:" case actually could modify "la", but after the patch this change is not reflected in *linear. The bug is visible whenever a non-zero segment base causes the linear address to wrap around the 4GB mark. Fixes: e8dd2d2d641cb2724ee10e76c0ad02e04289c017 Cc: stable@vger.kernel.org Reported-by: Aurelien Jarno Tested-by: Aurelien Jarno Signed-off-by: Paolo Bonzini --- arch/x86/kvm/emulate.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 1505587d06e9..b9b09fec173b 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -650,10 +650,10 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, u16 sel; la = seg_base(ctxt, addr.seg) + addr.ea; - *linear = la; *max_size = 0; switch (mode) { case X86EMUL_MODE_PROT64: + *linear = la; if (is_noncanonical_address(la)) goto bad; @@ -662,6 +662,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, goto bad; break; default: + *linear = la = (u32)la; usable = ctxt->ops->get_segment(ctxt, &sel, &desc, NULL, addr.seg); if (!usable) @@ -689,7 +690,6 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, if (size > *max_size) goto bad; } - la &= (u32)-1; break; } if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0)) From d7444794a02ff655eda87e3cc54e86b940e7736f Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Fri, 19 Feb 2016 13:11:46 +0100 Subject: [PATCH 158/417] KVM: async_pf: do not warn on page allocation failures In async_pf we try to allocate with NOWAIT to get an element quickly or fail. This code also handle failures gracefully. Lets silence potential page allocation failures under load. qemu-system-s39: page allocation failure: order:0,mode:0x2200000 [...] Call Trace: ([<00000000001146b8>] show_trace+0xf8/0x148) [<000000000011476a>] show_stack+0x62/0xe8 [<00000000004a36b8>] dump_stack+0x70/0x98 [<0000000000272c3a>] warn_alloc_failed+0xd2/0x148 [<000000000027709e>] __alloc_pages_nodemask+0x94e/0xb38 [<00000000002cd36a>] new_slab+0x382/0x400 [<00000000002cf7ac>] ___slab_alloc.constprop.30+0x2dc/0x378 [<00000000002d03d0>] kmem_cache_alloc+0x160/0x1d0 [<0000000000133db4>] kvm_setup_async_pf+0x6c/0x198 [<000000000013dee8>] kvm_arch_vcpu_ioctl_run+0xd48/0xd58 [<000000000012fcaa>] kvm_vcpu_ioctl+0x372/0x690 [<00000000002f66f6>] do_vfs_ioctl+0x3be/0x510 [<00000000002f68ec>] SyS_ioctl+0xa4/0xb8 [<0000000000781c5e>] system_call+0xd6/0x264 [<000003ffa24fa06a>] 0x3ffa24fa06a Cc: stable@vger.kernel.org Signed-off-by: Christian Borntraeger Reviewed-by: Dominik Dingel Signed-off-by: Paolo Bonzini --- virt/kvm/async_pf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 353159922456..db2dd3335c6a 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -172,7 +172,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva, * do alloc nowait since if we are going to sleep anyway we * may as well sleep faulting in page */ - work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT); + work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT | __GFP_NOWARN); if (!work) return 0; From d045437a169f899dfb0f6f7ede24cc042543ced9 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Wed, 24 Feb 2016 09:04:24 -0500 Subject: [PATCH 159/417] tracing: Fix showing function event in available_events The ftrace:function event is only displayed for parsing the function tracer data. It is not used to enable function tracing, and does not include an "enable" file in its event directory. Originally, this event was kept separate from other events because it did not have a ->reg parameter. But perf added a "reg" parameter for its use which caused issues, because it made the event available to functions where it was not compatible for. Commit 9b63776fa3ca9 "tracing: Do not enable function event with enable" added a TRACE_EVENT_FL_IGNORE_ENABLE flag that prevented the function event from being enabled by normal trace events. But this commit missed keeping the function event from being displayed by the "available_events" directory, which is used to show what events can be enabled by set_event. One documented way to enable all events is to: cat available_events > set_event But because the function event is displayed in the available_events, this now causes an INVALID error: cat: write error: Invalid argument Reported-by: Chunyu Hu Fixes: 9b63776fa3ca9 "tracing: Do not enable function event with enable" Cc: stable@vger.kernel.org # 3.4+ Signed-off-by: Steven Rostedt --- kernel/trace/trace_events.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index f333e57c4614..ab09829d3b97 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -869,7 +869,8 @@ t_next(struct seq_file *m, void *v, loff_t *pos) * The ftrace subsystem is for showing formats only. * They can not be enabled or disabled via the event files. */ - if (call->class && call->class->reg) + if (call->class && call->class->reg && + !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) return file; } From c7dfe3abf40ec9a298884a4c0775062eac27afc9 Mon Sep 17 00:00:00 2001 From: Sebastian Frias Date: Mon, 22 Feb 2016 13:33:14 +0100 Subject: [PATCH 160/417] net: ethernet: nb8800: support fixed-link DT node Under some circumstances, e.g. when connecting to a switch, the ethernet port will not be connected to a PHY. In that case a "fixed-link" DT node can be used to replace it. https://stackoverflow.com/questions/31046172/device-tree-for-phy-less-connection-to-a-dsa-switch This patch adds support for the "fixed-link" node to the nb8800 driver. Signed-off-by: Sebastian Frias Acked-by: Mans Rullgard Cc: Mason Signed-off-by: David S. Miller --- drivers/net/ethernet/aurora/nb8800.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c index f71ab2647a3b..08a23e6b60e9 100644 --- a/drivers/net/ethernet/aurora/nb8800.c +++ b/drivers/net/ethernet/aurora/nb8800.c @@ -1460,7 +1460,19 @@ static int nb8800_probe(struct platform_device *pdev) goto err_disable_clk; } - priv->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); + if (of_phy_is_fixed_link(pdev->dev.of_node)) { + ret = of_phy_register_fixed_link(pdev->dev.of_node); + if (ret < 0) { + dev_err(&pdev->dev, "bad fixed-link spec\n"); + goto err_free_bus; + } + priv->phy_node = of_node_get(pdev->dev.of_node); + } + + if (!priv->phy_node) + priv->phy_node = of_parse_phandle(pdev->dev.of_node, + "phy-handle", 0); + if (!priv->phy_node) { dev_err(&pdev->dev, "no PHY specified\n"); ret = -ENODEV; From fd451b90e78c4178bcfc5072f2b2b637500c109a Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 17 Feb 2016 10:25:05 +0000 Subject: [PATCH 161/417] arm64: KVM: vgic-v3: Restore ICH_APR0Rn_EL2 before ICH_APR1Rn_EL2 The GICv3 architecture spec says: Writing to the active priority registers in any order other than the following order will result in UNPREDICTABLE behavior: - ICH_AP0R_EL2. - ICH_AP1R_EL2. So let's not pointlessly go against the rule... Acked-by: Christoffer Dall Signed-off-by: Marc Zyngier --- arch/arm64/kvm/hyp/vgic-v3-sr.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c index 9142e082f5f3..5dd2a26444ec 100644 --- a/arch/arm64/kvm/hyp/vgic-v3-sr.c +++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c @@ -147,16 +147,6 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu) max_lr_idx = vtr_to_max_lr_idx(val); nr_pri_bits = vtr_to_nr_pri_bits(val); - switch (nr_pri_bits) { - case 7: - write_gicreg(cpu_if->vgic_ap1r[3], ICH_AP1R3_EL2); - write_gicreg(cpu_if->vgic_ap1r[2], ICH_AP1R2_EL2); - case 6: - write_gicreg(cpu_if->vgic_ap1r[1], ICH_AP1R1_EL2); - default: - write_gicreg(cpu_if->vgic_ap1r[0], ICH_AP1R0_EL2); - } - switch (nr_pri_bits) { case 7: write_gicreg(cpu_if->vgic_ap0r[3], ICH_AP0R3_EL2); @@ -167,6 +157,16 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu) write_gicreg(cpu_if->vgic_ap0r[0], ICH_AP0R0_EL2); } + switch (nr_pri_bits) { + case 7: + write_gicreg(cpu_if->vgic_ap1r[3], ICH_AP1R3_EL2); + write_gicreg(cpu_if->vgic_ap1r[2], ICH_AP1R2_EL2); + case 6: + write_gicreg(cpu_if->vgic_ap1r[1], ICH_AP1R1_EL2); + default: + write_gicreg(cpu_if->vgic_ap1r[0], ICH_AP1R0_EL2); + } + switch (max_lr_idx) { case 15: write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(15)], ICH_LR15_EL2); From 827108d08070c7515c14eb47e5fa03f59cfe38cf Mon Sep 17 00:00:00 2001 From: Bradley Pankow Date: Mon, 22 Feb 2016 20:11:47 -0500 Subject: [PATCH 162/417] amdgpu: fix NULL pointer dereference at tonga_check_states_equal The event_data passed from pem_fini was not cleared upon initialization. This caused NULL checks to pass and cast_const_phw_tonga_power_state to attempt to dereference an invalid pointer. Clear the event_data in pem_init and pem_fini before calling pem_handle_event. Reviewed-by: Rex Zhu Signed-off-by: Bradley Pankow Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c b/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c index 52a3efc97f05..46410e3c7349 100644 --- a/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c +++ b/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c @@ -31,7 +31,7 @@ static int pem_init(struct pp_eventmgr *eventmgr) { int result = 0; - struct pem_event_data event_data; + struct pem_event_data event_data = { {0} }; /* Initialize PowerPlay feature info */ pem_init_feature_info(eventmgr); @@ -52,7 +52,7 @@ static int pem_init(struct pp_eventmgr *eventmgr) static void pem_fini(struct pp_eventmgr *eventmgr) { - struct pem_event_data event_data; + struct pem_event_data event_data = { {0} }; pem_uninit_featureInfo(eventmgr); pem_unregister_interrupts(eventmgr); From 6378076bcfdcd1d4f8d726d08d3fa044736873eb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Fri, 19 Feb 2016 10:03:03 +0100 Subject: [PATCH 163/417] drm/amdgpu: disable direct VM updates when vm_debug is set MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit That should make user space bugs more obvious. Signed-off-by: Christian König Reviewed-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 7380f782cd14..d20c2a8929cb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -596,7 +596,8 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, break; } ttm_eu_backoff_reservation(&ticket, &list); - if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE)) + if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE) && + !amdgpu_vm_debug) amdgpu_gem_va_update_vm(adev, bo_va, args->operation); drm_gem_object_unreference_unlocked(gobj); From 2ac015e293bbe3858533009612eac58842daf325 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 24 Feb 2016 18:58:03 +0300 Subject: [PATCH 164/417] thp: call pmdp_invalidate() with correct virtual address Sebastian Ott and Gerald Schaefer reported random crashes on s390. It was bisected to my THP refcounting patchset. The problem is that pmdp_invalidated() called with wrong virtual address. It got offset up by HPAGE_PMD_SIZE by loop over ptes. The solution is to introduce new variable to be used in loop and don't touch 'haddr'. Signed-off-by: Kirill A. Shutemov Reported-and-tested-by: Gerald Schaefer Reported-and-tested-by Sebastian Ott Reviewed-by: Will Deacon Cc: Christian Borntraeger Cc: Martin Schwidefsky Cc: Aneesh Kumar K.V Cc: Andrea Arcangeli Cc: Sasha Levin Cc: Jerome Marchand Cc: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1c317b85ea7d..e10a4fee88d2 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2836,6 +2836,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, pgtable_t pgtable; pmd_t _pmd; bool young, write, dirty; + unsigned long addr; int i; VM_BUG_ON(haddr & ~HPAGE_PMD_MASK); @@ -2865,7 +2866,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); - for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { + for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) { pte_t entry, *pte; /* * Note that NUMA hinting access restrictions are not @@ -2886,9 +2887,9 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, } if (dirty) SetPageDirty(page + i); - pte = pte_offset_map(&_pmd, haddr); + pte = pte_offset_map(&_pmd, addr); BUG_ON(!pte_none(*pte)); - set_pte_at(mm, haddr, pte, entry); + set_pte_at(mm, addr, pte, entry); atomic_inc(&page[i]._mapcount); pte_unmap(pte); } @@ -2938,7 +2939,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, pmd_populate(mm, pmd, pgtable); if (freeze) { - for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { + for (i = 0; i < HPAGE_PMD_NR; i++) { page_remove_rmap(page + i, false); put_page(page + i); } From a8c4a2522a0808c5c2143612909717d1115c40cf Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Mon, 22 Feb 2016 18:43:25 +0100 Subject: [PATCH 165/417] ipv4: only create late gso-skb if skb is already set up with CHECKSUM_PARTIAL Otherwise we break the contract with GSO to only pass CHECKSUM_PARTIAL skbs down. This can easily happen with UDP+IPv4 sockets with the first MSG_MORE write smaller than the MTU, second write is a sendfile. Returning -EOPNOTSUPP lets the callers fall back into normal sendmsg path, were we calculate the checksum manually during copying. Commit d749c9cbffd6 ("ipv4: no CHECKSUM_PARTIAL on MSG_MORE corked sockets") started to exposes this bug. Fixes: d749c9cbffd6 ("ipv4: no CHECKSUM_PARTIAL on MSG_MORE corked sockets") Reported-by: Jiri Benc Cc: Jiri Benc Reported-by: Wakko Warner Cc: Wakko Warner Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv4/ip_output.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 64878efa045c..565bf64b2b7d 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1236,13 +1236,16 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, if (!skb) return -EINVAL; - cork->length += size; if ((size + skb->len > mtu) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO)) { + if (skb->ip_summed != CHECKSUM_PARTIAL) + return -EOPNOTSUPP; + skb_shinfo(skb)->gso_size = mtu - fragheaderlen; skb_shinfo(skb)->gso_type = SKB_GSO_UDP; } + cork->length += size; while (size > 0) { if (skb_is_gso(skb)) { From e7a88e82fe380459b864e05b372638aeacb0f52d Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 17 Feb 2016 20:04:08 +0100 Subject: [PATCH 166/417] libceph: don't bail early from try_read() when skipping a message The contract between try_read() and try_write() is that when called each processes as much data as possible. When instructed by osd_client to skip a message, try_read() is violating this contract by returning after receiving and discarding a single message instead of checking for more. try_write() then gets a chance to write out more requests, generating more replies/skips for try_read() to handle, forcing the messenger into a starvation loop. Cc: stable@vger.kernel.org # 3.10+ Reported-by: Varada Kari Signed-off-by: Ilya Dryomov Tested-by: Varada Kari Reviewed-by: Alex Elder --- net/ceph/messenger.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 9cfedf565f5b..fec20819a5ea 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -2337,7 +2337,7 @@ static int read_partial_message(struct ceph_connection *con) con->in_base_pos = -front_len - middle_len - data_len - sizeof(m->footer); con->in_tag = CEPH_MSGR_TAG_READY; - return 0; + return 1; } else if ((s64)seq - (s64)con->in_seq > 1) { pr_err("read_partial_message bad seq %lld expected %lld\n", seq, con->in_seq + 1); @@ -2363,7 +2363,7 @@ static int read_partial_message(struct ceph_connection *con) sizeof(m->footer); con->in_tag = CEPH_MSGR_TAG_READY; con->in_seq++; - return 0; + return 1; } BUG_ON(!con->in_msg); From dbc0d3caff5b7591e0cf8e34ca686ca6f4479ee1 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 19 Feb 2016 11:38:57 +0100 Subject: [PATCH 167/417] libceph: use the right footer size when skipping a message ceph_msg_footer is 21 bytes long, while ceph_msg_footer_old is only 13. Don't skip too much when CEPH_FEATURE_MSG_AUTH isn't negotiated. Cc: stable@vger.kernel.org # 3.19+ Signed-off-by: Ilya Dryomov Reviewed-by: Alex Elder --- net/ceph/messenger.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index fec20819a5ea..9382619a405b 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1197,6 +1197,13 @@ static bool ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, return new_piece; } +static size_t sizeof_footer(struct ceph_connection *con) +{ + return (con->peer_features & CEPH_FEATURE_MSG_AUTH) ? + sizeof(struct ceph_msg_footer) : + sizeof(struct ceph_msg_footer_old); +} + static void prepare_message_data(struct ceph_msg *msg, u32 data_len) { BUG_ON(!msg); @@ -2335,7 +2342,7 @@ static int read_partial_message(struct ceph_connection *con) ceph_pr_addr(&con->peer_addr.in_addr), seq, con->in_seq + 1); con->in_base_pos = -front_len - middle_len - data_len - - sizeof(m->footer); + sizeof_footer(con); con->in_tag = CEPH_MSGR_TAG_READY; return 1; } else if ((s64)seq - (s64)con->in_seq > 1) { @@ -2360,7 +2367,7 @@ static int read_partial_message(struct ceph_connection *con) /* skip this message */ dout("alloc_msg said skip message\n"); con->in_base_pos = -front_len - middle_len - data_len - - sizeof(m->footer); + sizeof_footer(con); con->in_tag = CEPH_MSGR_TAG_READY; con->in_seq++; return 1; From cd8140c673d9ba9be3591220e1b2226d9e1e40d3 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 19 Feb 2016 11:38:57 +0100 Subject: [PATCH 168/417] libceph: don't spam dmesg with stray reply warnings Commit d15f9d694b77 ("libceph: check data_len in ->alloc_msg()") mistakenly bumped the log level on the "tid %llu unknown, skipping" message. Turn it back into a dout() - stray replies are perfectly normal when OSDs flap, crash, get killed for testing purposes, etc. Cc: stable@vger.kernel.org # 4.3+ Signed-off-by: Ilya Dryomov Reviewed-by: Alex Elder --- net/ceph/osd_client.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 3534e12683d3..5bc053778fed 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -2853,8 +2853,8 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, mutex_lock(&osdc->request_mutex); req = __lookup_request(osdc, tid); if (!req) { - pr_warn("%s osd%d tid %llu unknown, skipping\n", - __func__, osd->o_osd, tid); + dout("%s osd%d tid %llu unknown, skipping\n", __func__, + osd->o_osd, tid); m = NULL; *skip = 1; goto out; From 2da897e51d7f23f872224218b9a4314503b0d360 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 23 Feb 2016 02:05:26 +0100 Subject: [PATCH 169/417] bpf: fix csum setting for bpf_set_tunnel_key The fix in 35e2d1152b22 ("tunnels: Allow IPv6 UDP checksums to be correctly controlled.") changed behavior for bpf_set_tunnel_key() when in use with IPv6 and thus uncovered a bug that TUNNEL_CSUM needed to be set but wasn't. As a result, the stack dropped ingress vxlan IPv6 packets, that have been sent via eBPF through collect meta data mode due to checksum now being zero. Since after LCO, we enable IPv4 checksum by default, so make that analogous and only provide a flag BPF_F_ZERO_CSUM_TX for the user to turn it off in IPv4 case. Fixes: 35e2d1152b22 ("tunnels: Allow IPv6 UDP checksums to be correctly controlled.") Fixes: c6c33454072f ("bpf: support ipv6 for bpf_skb_{set,get}_tunnel_key") Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 3 +++ net/core/filter.c | 6 ++++-- 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index aa6f8571de13..5df4881dea7b 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -292,6 +292,9 @@ enum bpf_func_id { /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ #define BPF_F_TUNINFO_IPV6 (1ULL << 0) +/* BPF_FUNC_skb_set_tunnel_key flags. */ +#define BPF_F_ZERO_CSUM_TX (1ULL << 1) + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ diff --git a/net/core/filter.c b/net/core/filter.c index 94d26201080d..bba502f7cd57 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1752,7 +1752,7 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) u8 compat[sizeof(struct bpf_tunnel_key)]; struct ip_tunnel_info *info; - if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6))) + if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX))) return -EINVAL; if (unlikely(size != sizeof(struct bpf_tunnel_key))) { switch (size) { @@ -1776,7 +1776,7 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) info = &md->u.tun_info; info->mode = IP_TUNNEL_INFO_TX; - info->key.tun_flags = TUNNEL_KEY; + info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM; info->key.tun_id = cpu_to_be64(from->tunnel_id); info->key.tos = from->tunnel_tos; info->key.ttl = from->tunnel_ttl; @@ -1787,6 +1787,8 @@ static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) sizeof(from->remote_ipv6)); } else { info->key.u.ipv4.dst = cpu_to_be32(from->remote_ipv4); + if (flags & BPF_F_ZERO_CSUM_TX) + info->key.tun_flags &= ~TUNNEL_CSUM; } return 0; From 0378ba4899d5fbd8494ed6580cbc81d7b44dbac6 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 24 Feb 2016 09:43:23 +0100 Subject: [PATCH 170/417] drivers: sh: Restore legacy clock domain on SuperH platforms CONFIG_ARCH_SHMOBILE is not only enabled for Renesas ARM platforms (which are DT based and multi-platform), but also on a select set of Renesas SuperH platforms (SH7722/SH7723/SH7724/SH7343/SH7366). Hence since commit 0ba58de231066e47 ("drivers: sh: Get rid of CONFIG_ARCH_SHMOBILE_MULTI"), the legacy clock domain is no longer installed on these SuperH platforms, and module clocks may not be enabled when needed, leading to driver failures. To fix this, add an additional check for CONFIG_OF. Fixes: 0ba58de231066e47 ("drivers: sh: Get rid of CONFIG_ARCH_SHMOBILE_MULTI"). Signed-off-by: Geert Uytterhoeven Signed-off-by: Simon Horman --- drivers/sh/pm_runtime.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/sh/pm_runtime.c b/drivers/sh/pm_runtime.c index 91a003011acf..a9bac3bf20de 100644 --- a/drivers/sh/pm_runtime.c +++ b/drivers/sh/pm_runtime.c @@ -34,7 +34,7 @@ static struct pm_clk_notifier_block platform_bus_notifier = { static int __init sh_pm_runtime_init(void) { - if (IS_ENABLED(CONFIG_ARCH_SHMOBILE)) { + if (IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_ARCH_SHMOBILE)) { if (!of_find_compatible_node(NULL, NULL, "renesas,cpg-mstp-clocks")) return 0; From d144dfea8af7108f613139623e63952ed7e69c0c Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Wed, 24 Feb 2016 11:05:25 +0800 Subject: [PATCH 171/417] usb: chipidea: otg: change workqueue ci_otg as freezable If we use USB ID pin as wakeup source, and there is a USB block device on this USB OTG (ID) cable, the system will be deadlock after system resume. The root cause for this problem is: the workqueue ci_otg may try to remove hcd before the driver resume has finished, and hcd will disconnect the device on it, then, it will call device_release_driver, and holds the device lock "dev->mutex", but it is never unlocked since it waits workqueue writeback to run to flush the block information, but the workqueue writeback is freezable, it is not thawed before driver resume has finished. When the driver (device: sd 0:0:0:0:) resume goes to dpm_complete, it tries to get its device lock "dev->mutex", but it can't get it forever, then the deadlock occurs. Below call stacks show the situation. So, in order to fix this problem, we need to change workqueue ci_otg as freezable, then the work item in this workqueue will be run after driver's resume, this workqueue will not be blocked forever like above case since the workqueue writeback has been thawed too. Tested at: i.mx6qdl-sabresd and i.mx6sx-sdb. [ 555.178869] kworker/u2:13 D c07de74c 0 826 2 0x00000000 [ 555.185310] Workqueue: ci_otg ci_otg_work [ 555.189353] Backtrace: [ 555.191849] [] (__schedule) from [] (schedule+0x48/0xa0) [ 555.198912] r10:ee471ba0 r9:00000000 r8:00000000 r7:00000002 r6:ee470000 r5:ee471ba4 [ 555.206867] r4:ee470000 [ 555.209453] [] (schedule) from [] (schedule_timeout+0x15c/0x1e0) [ 555.217212] r4:7fffffff r3:edc2b000 [ 555.220862] [] (schedule_timeout) from [] (wait_for_common+0x94/0x144) [ 555.229140] r8:00000000 r7:00000002 r6:ee470000 r5:ee471ba4 r4:7fffffff [ 555.235980] [] (wait_for_common) from [] (wait_for_completion+0x18/0x1c) [ 555.244430] r10:00000001 r9:c0b5563c r8:c0042e48 r7:ef086000 r6:eea4372c r5:ef131b00 [ 555.252383] r4:00000000 [ 555.254970] [] (wait_for_completion) from [] (flush_work+0x19c/0x234) [ 555.263177] [] (flush_work) from [] (flush_delayed_work+0x48/0x4c) [ 555.271106] r8:ed5b5000 r7:c0b38a3c r6:eea439cc r5:eea4372c r4:eea4372c [ 555.277958] [] (flush_delayed_work) from [] (bdi_unregister+0x84/0xec) [ 555.286236] r4:eea43520 r3:20000153 [ 555.289885] [] (bdi_unregister) from [] (blk_cleanup_queue+0x180/0x29c) [ 555.298250] r5:eea43808 r4:eea43400 [ 555.301909] [] (blk_cleanup_queue) from [] (__scsi_remove_device+0x48/0xb8) [ 555.310623] r7:00000000 r6:20000153 r5:ededa950 r4:ededa800 [ 555.316403] [] (__scsi_remove_device) from [] (scsi_forget_host+0x64/0x68) [ 555.325028] r5:ededa800 r4:ed5b5000 [ 555.328689] [] (scsi_forget_host) from [] (scsi_remove_host+0x78/0x104) [ 555.337054] r5:ed5b5068 r4:ed5b5000 [ 555.340709] [] (scsi_remove_host) from [] (usb_stor_disconnect+0x50/0xb4) [ 555.349247] r6:ed5b56e4 r5:ed5b5818 r4:ed5b5690 r3:00000008 [ 555.355025] [] (usb_stor_disconnect) from [] (usb_unbind_interface+0x78/0x25c) [ 555.363997] r8:c13919b4 r7:edd3c000 r6:edd3c020 r5:ee551c68 r4:ee551c00 r3:c04cdf7c [ 555.371892] [] (usb_unbind_interface) from [] (__device_release_driver+0x8c/0x118) [ 555.381213] r10:00000001 r9:edd90c00 r8:c13919b4 r7:ee551c68 r6:c0b546e0 r5:c0b5563c [ 555.389167] r4:edd3c020 [ 555.391752] [] (__device_release_driver) from [] (device_release_driver+0x28/0x34) [ 555.401071] r5:edd3c020 r4:edd3c054 [ 555.404721] [] (device_release_driver) from [] (bus_remove_device+0xe0/0x110) [ 555.413607] r5:edd3c020 r4:ef17f04c [ 555.417253] [] (bus_remove_device) from [] (device_del+0x114/0x21c) [ 555.425270] r6:edd3c028 r5:edd3c020 r4:ee551c00 r3:00000000 [ 555.431045] [] (device_del) from [] (usb_disable_device+0xa4/0x1e8) [ 555.439061] r8:edd3c000 r7:eded8000 r6:00000000 r5:00000001 r4:ee551c00 [ 555.445906] [] (usb_disable_device) from [] (usb_disconnect+0x74/0x224) [ 555.454271] r9:edd90c00 r8:ee551000 r7:ee551c68 r6:ee551c9c r5:ee551c00 r4:00000001 [ 555.462156] [] (usb_disconnect) from [] (usb_disconnect+0x1d8/0x224) [ 555.470259] r10:00000001 r9:edd90000 r8:ee471e2c r7:ee551468 r6:ee55149c r5:ee551400 [ 555.478213] r4:00000001 [ 555.480797] [] (usb_disconnect) from [] (usb_remove_hcd+0xa0/0x1ac) [ 555.488813] r10:00000001 r9:ee471eb0 r8:00000000 r7:ef3d9500 r6:eded810c r5:eded80b0 [ 555.496765] r4:eded8000 [ 555.499351] [] (usb_remove_hcd) from [] (host_stop+0x28/0x64) [ 555.506847] r6:eeb50010 r5:eded8000 r4:eeb51010 [ 555.511563] [] (host_stop) from [] (ci_otg_work+0xc4/0x124) [ 555.518885] r6:00000001 r5:eeb50010 r4:eeb502a0 r3:c04d4130 [ 555.524665] [] (ci_otg_work) from [] (process_one_work+0x194/0x420) [ 555.532682] r6:ef086000 r5:eeb502a0 r4:edc44480 [ 555.537393] [] (process_one_work) from [] (worker_thread+0x34/0x514) [ 555.545496] r10:edc44480 r9:ef086000 r8:c0b1a100 r7:ef086034 r6:00000088 r5:edc44498 [ 555.553450] r4:ef086000 [ 555.556032] [] (worker_thread) from [] (kthread+0xdc/0xf8) [ 555.563268] r10:00000000 r9:00000000 r8:00000000 r7:c004577c r6:edc44480 r5:eddc15c0 [ 555.571221] r4:00000000 [ 555.573804] [] (kthread) from [] (ret_from_fork+0x14/0x24) [ 555.581040] r7:00000000 r6:00000000 r5:c004b9d8 r4:eddc15c0 [ 553.429383] sh D c07de74c 0 694 691 0x00000000 [ 553.435801] Backtrace: [ 553.438295] [] (__schedule) from [] (schedule+0x48/0xa0) [ 553.445358] r10:edd3c054 r9:edd3c078 r8:edddbd50 r7:edcbbc00 r6:c1377c34 r5:60000153 [ 553.453313] r4:eddda000 [ 553.455896] [] (schedule) from [] (schedule_preempt_disabled+0x10/0x14) [ 553.464261] r4:edd3c058 r3:0000000a [ 553.467910] [] (schedule_preempt_disabled) from [] (mutex_lock_nested+0x1a0/0x3e8) [ 553.477254] [] (mutex_lock_nested) from [] (dpm_complete+0xc0/0x1b0) [ 553.485358] r10:00561408 r9:edd3c054 r8:c0b4863c r7:edddbd90 r6:c0b485d8 r5:edd3c020 [ 553.493313] r4:edd3c0d0 [ 553.495896] [] (dpm_complete) from [] (dpm_resume_end+0x1c/0x20) [ 553.503652] r9:00000000 r8:c0b1a9d0 r7:c1334ec0 r6:c1334edc r5:00000003 r4:00000010 [ 553.511544] [] (dpm_resume_end) from [] (suspend_devices_and_enter+0x158/0x504) [ 553.520604] r4:00000000 r3:c1334efc [ 553.524250] [] (suspend_devices_and_enter) from [] (pm_suspend+0x234/0x2cc) [ 553.532961] r10:00561408 r9:ed6b7300 r8:00000004 r7:c1334eec r6:00000000 r5:c1334ee8 [ 553.540914] r4:00000003 [ 553.543493] [] (pm_suspend) from [] (state_store+0x6c/0xc0) [ 555.703684] 7 locks held by kworker/u2:13/826: [ 555.708140] #0: ("%s""ci_otg"){++++.+}, at: [] process_one_work+0x128/0x420 [ 555.716277] #1: ((&ci->work)){+.+.+.}, at: [] process_one_work+0x128/0x420 [ 555.724317] #2: (usb_bus_list_lock){+.+.+.}, at: [] usb_remove_hcd+0x98/0x1ac [ 555.732626] #3: (&dev->mutex){......}, at: [] usb_disconnect+0x48/0x224 [ 555.740403] #4: (&dev->mutex){......}, at: [] usb_disconnect+0x48/0x224 [ 555.748179] #5: (&dev->mutex){......}, at: [] device_release_driver+0x20/0x34 [ 555.756487] #6: (&shost->scan_mutex){+.+.+.}, at: [] scsi_remove_host+0x20/0x104 Cc: #v3.14+ Cc: Jun Li Signed-off-by: Peter Chen --- drivers/usb/chipidea/otg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/chipidea/otg.c b/drivers/usb/chipidea/otg.c index 45f86da1d6d3..03b6743461d1 100644 --- a/drivers/usb/chipidea/otg.c +++ b/drivers/usb/chipidea/otg.c @@ -158,7 +158,7 @@ static void ci_otg_work(struct work_struct *work) int ci_hdrc_otg_init(struct ci_hdrc *ci) { INIT_WORK(&ci->work, ci_otg_work); - ci->wq = create_singlethread_workqueue("ci_otg"); + ci->wq = create_freezable_workqueue("ci_otg"); if (!ci->wq) { dev_err(ci->dev, "can't create workqueue\n"); return -ENODEV; From 870571a5698b2e9d0f4d2e5c6245967b582aab45 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Wed, 24 Feb 2016 18:34:43 +0100 Subject: [PATCH 172/417] drm/nouveau: platform: Fix deferred probe The error cleanup paths aren't quite correct and will crash upon deferred probe. Cc: stable@vger.kernel.org # v4.3+ Reviewed-by: Ben Skeggs Reviewed-by: Alexandre Courbot Signed-off-by: Thierry Reding Signed-off-by: Dave Airlie --- drivers/gpu/drm/nouveau/nouveau_platform.c | 2 +- .../drm/nouveau/nvkm/engine/device/tegra.c | 40 ++++++++++++++----- 2 files changed, 30 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_platform.c b/drivers/gpu/drm/nouveau/nouveau_platform.c index 8a70cec59bcd..2dfe58af12e4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_platform.c +++ b/drivers/gpu/drm/nouveau/nouveau_platform.c @@ -24,7 +24,7 @@ static int nouveau_platform_probe(struct platform_device *pdev) { const struct nvkm_device_tegra_func *func; - struct nvkm_device *device; + struct nvkm_device *device = NULL; struct drm_device *drm; int ret; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c index 7f8a42721eb2..e7e581d6a8ff 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c @@ -252,32 +252,40 @@ nvkm_device_tegra_new(const struct nvkm_device_tegra_func *func, if (!(tdev = kzalloc(sizeof(*tdev), GFP_KERNEL))) return -ENOMEM; - *pdevice = &tdev->device; + tdev->func = func; tdev->pdev = pdev; tdev->irq = -1; tdev->vdd = devm_regulator_get(&pdev->dev, "vdd"); - if (IS_ERR(tdev->vdd)) - return PTR_ERR(tdev->vdd); + if (IS_ERR(tdev->vdd)) { + ret = PTR_ERR(tdev->vdd); + goto free; + } tdev->rst = devm_reset_control_get(&pdev->dev, "gpu"); - if (IS_ERR(tdev->rst)) - return PTR_ERR(tdev->rst); + if (IS_ERR(tdev->rst)) { + ret = PTR_ERR(tdev->rst); + goto free; + } tdev->clk = devm_clk_get(&pdev->dev, "gpu"); - if (IS_ERR(tdev->clk)) - return PTR_ERR(tdev->clk); + if (IS_ERR(tdev->clk)) { + ret = PTR_ERR(tdev->clk); + goto free; + } tdev->clk_pwr = devm_clk_get(&pdev->dev, "pwr"); - if (IS_ERR(tdev->clk_pwr)) - return PTR_ERR(tdev->clk_pwr); + if (IS_ERR(tdev->clk_pwr)) { + ret = PTR_ERR(tdev->clk_pwr); + goto free; + } nvkm_device_tegra_probe_iommu(tdev); ret = nvkm_device_tegra_power_up(tdev); if (ret) - return ret; + goto remove; tdev->gpu_speedo = tegra_sku_info.gpu_speedo_value; ret = nvkm_device_ctor(&nvkm_device_tegra_func, NULL, &pdev->dev, @@ -285,9 +293,19 @@ nvkm_device_tegra_new(const struct nvkm_device_tegra_func *func, cfg, dbg, detect, mmio, subdev_mask, &tdev->device); if (ret) - return ret; + goto powerdown; + + *pdevice = &tdev->device; return 0; + +powerdown: + nvkm_device_tegra_power_down(tdev); +remove: + nvkm_device_tegra_remove_iommu(tdev); +free: + kfree(tdev); + return ret; } #else int From 95664e66fad964c3dd7945d6edfb1d0931844664 Mon Sep 17 00:00:00 2001 From: Ben Skeggs Date: Thu, 18 Feb 2016 08:14:19 +1000 Subject: [PATCH 173/417] drm/nouveau/disp/dp: ensure sink is powered up before attempting link training This can happen under some annoying circumstances, and is a quick fix until more substantial changes can be made. Fixed eDP mode changes on (at least) the Lenovo P50. Signed-off-by: Ben Skeggs Cc: stable@vger.kernel.org --- drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c | 10 ++++++++++ drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h | 6 ++++++ 2 files changed, 16 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c index 74e2f7c6c07e..9688970eca47 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c @@ -328,6 +328,7 @@ nvkm_dp_train(struct work_struct *w) .outp = outp, }, *dp = &_dp; u32 datarate = 0; + u8 pwr; int ret; if (!outp->base.info.location && disp->func->sor.magic) @@ -355,6 +356,15 @@ nvkm_dp_train(struct work_struct *w) /* disable link interrupt handling during link training */ nvkm_notify_put(&outp->irq); + /* ensure sink is not in a low-power state */ + if (!nvkm_rdaux(outp->aux, DPCD_SC00, &pwr, 1)) { + if ((pwr & DPCD_SC00_SET_POWER) != DPCD_SC00_SET_POWER_D0) { + pwr &= ~DPCD_SC00_SET_POWER; + pwr |= DPCD_SC00_SET_POWER_D0; + nvkm_wraux(outp->aux, DPCD_SC00, &pwr, 1); + } + } + /* enable down-spreading and execute pre-train script from vbios */ dp_link_train_init(dp, outp->dpcd[3] & 0x01); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h index 9596290329c7..6e10c5e0ef11 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h @@ -71,5 +71,11 @@ #define DPCD_LS0C_LANE1_POST_CURSOR2 0x0c #define DPCD_LS0C_LANE0_POST_CURSOR2 0x03 +/* DPCD Sink Control */ +#define DPCD_SC00 0x00600 +#define DPCD_SC00_SET_POWER 0x03 +#define DPCD_SC00_SET_POWER_D0 0x01 +#define DPCD_SC00_SET_POWER_D3 0x03 + void nvkm_dp_train(struct work_struct *); #endif From ee50c130c82175eaa0820c96b6d3763928af2241 Mon Sep 17 00:00:00 2001 From: Diego Viola Date: Tue, 23 Feb 2016 12:04:04 -0300 Subject: [PATCH 174/417] net: jme: fix suspend/resume on JMC260 The JMC260 network card fails to suspend/resume because the call to jme_start_irq() was too early, moving the call to jme_start_irq() after the call to jme_reset_link() makes it work. Prior this change suspend/resume would fail unless /sys/power/pm_async=0 was explicitly specified. Relevant bug report: https://bugzilla.kernel.org/show_bug.cgi?id=112351 Signed-off-by: Diego Viola Signed-off-by: David S. Miller --- drivers/net/ethernet/jme.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index b1de7afd4116..8adbe8ff0eb8 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -3312,13 +3312,14 @@ jme_resume(struct device *dev) jme_reset_phy_processor(jme); jme_phy_calibration(jme); jme_phy_setEA(jme); - jme_start_irq(jme); netif_device_attach(netdev); atomic_inc(&jme->link_changing); jme_reset_link(jme); + jme_start_irq(jme); + return 0; } From 3d44d51bd339766f0178f0cf2e8d048b4a4872aa Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Wed, 24 Feb 2016 12:18:49 -0800 Subject: [PATCH 175/417] x86/entry/compat: Add missing CLAC to entry_INT80_32 This doesn't seem to fix a regression -- I don't think the CLAC was ever there. I double-checked in a debugger: entries through the int80 gate do not automatically clear AC. Stable maintainers: I can provide a backport to 4.3 and earlier if needed. This needs to be backported all the way to 3.10. Reported-by: Brian Gerst Signed-off-by: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: # v3.10 and later Fixes: 63bcff2a307b ("x86, smap: Add STAC and CLAC instructions to control user space access") Link: http://lkml.kernel.org/r/b02b7e71ae54074be01fc171cbd4b72517055c0e.1456345086.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_64_compat.S | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index ff1c6d61f332..3c990eeee40b 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -261,6 +261,7 @@ ENTRY(entry_INT80_compat) * Interrupts are off on entry. */ PARAVIRT_ADJUST_EXCEPTION_FRAME + ASM_CLAC /* Do this early to minimize exposure */ SWAPGS /* From 84c4e620d35f49f486a900af214ad12276afb386 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:40 +0100 Subject: [PATCH 176/417] perf: Close install vs. exit race Consider the following scenario: CPU0 CPU1 ctx = find_get_ctx(); perf_event_exit_task_context() mutex_lock(&ctx->mutex); perf_install_in_context(ctx, ...); /* NO-OP */ mutex_unlock(&ctx->mutex); ... perf_release() WARN_ON_ONCE(event->state != STATE_EXIT); Since the event doesn't pass through perf_remove_from_context() because perf_install_in_context() NO-OPs because the ctx is dead, and perf_event_exit_task_context() will not observe the event because its not attached yet, the event->state will not be set. Solve this by revalidating ctx->task after we acquire ctx->mutex and failing the event creation as a whole. Tested-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Link: http://lkml.kernel.org/r/20160224174947.626853419@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 35 ++++++++++++++++++++++++++--------- 1 file changed, 26 insertions(+), 9 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 0d58522103cd..d7b0316e3465 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2158,13 +2158,15 @@ perf_install_in_context(struct perf_event_context *ctx, */ raw_spin_lock_irq(&ctx->lock); task = ctx->task; + /* - * Worse, we cannot even rely on the ctx actually existing anymore. If - * between find_get_context() and perf_install_in_context() the task - * went through perf_event_exit_task() its dead and we should not be - * adding new events. + * If between ctx = find_get_context() and mutex_lock(&ctx->mutex) the + * ctx gets destroyed, we must not install an event into it. + * + * This is normally tested for after we acquire the mutex, so this is + * a sanity check. */ - if (task == TASK_TOMBSTONE) { + if (WARN_ON_ONCE(task == TASK_TOMBSTONE)) { raw_spin_unlock_irq(&ctx->lock); return; } @@ -8389,10 +8391,19 @@ SYSCALL_DEFINE5(perf_event_open, if (move_group) { gctx = group_leader->ctx; mutex_lock_double(&gctx->mutex, &ctx->mutex); + if (gctx->task == TASK_TOMBSTONE) { + err = -ESRCH; + goto err_locked; + } } else { mutex_lock(&ctx->mutex); } + if (ctx->task == TASK_TOMBSTONE) { + err = -ESRCH; + goto err_locked; + } + if (!perf_event_validate_size(event)) { err = -E2BIG; goto err_locked; @@ -8563,12 +8574,14 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, WARN_ON_ONCE(ctx->parent_ctx); mutex_lock(&ctx->mutex); + if (ctx->task == TASK_TOMBSTONE) { + err = -ESRCH; + goto err_unlock; + } + if (!exclusive_event_installable(event, ctx)) { - mutex_unlock(&ctx->mutex); - perf_unpin_context(ctx); - put_ctx(ctx); err = -EBUSY; - goto err_free; + goto err_unlock; } perf_install_in_context(ctx, event, cpu); @@ -8577,6 +8590,10 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, return event; +err_unlock: + mutex_unlock(&ctx->mutex); + perf_unpin_context(ctx); + put_ctx(ctx); err_free: free_event(event); err: From 130056275ade730e7a79c110212c8815202773ee Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:41 +0100 Subject: [PATCH 177/417] perf: Do not double free In case of: err_file: fput(event_file), we'll end up calling perf_release() which in turn will free the event. Do not then free the event _again_. Tested-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Link: http://lkml.kernel.org/r/20160224174947.697350349@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index d7b0316e3465..211a5ce64e3f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8520,7 +8520,12 @@ SYSCALL_DEFINE5(perf_event_open, perf_unpin_context(ctx); put_ctx(ctx); err_alloc: - free_event(event); + /* + * If event_file is set, the fput() above will have called ->release() + * and that will take care of freeing the event. + */ + if (!event_file) + free_event(event); err_cpus: put_online_cpus(); err_task: From a4f4bb6d0c69d0bb573f1d9e6f1b806f9b038b19 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:42 +0100 Subject: [PATCH 178/417] perf: Allow perf_release() with !event->ctx In the err_file: fput(event_file) case, the event will not yet have been attached to a context. However perf_release() does assume it has been. Cure this. Tested-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Link: http://lkml.kernel.org/r/20160224174947.793996260@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 211a5ce64e3f..d5299e2e435d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3754,9 +3754,19 @@ static void put_event(struct perf_event *event) */ int perf_event_release_kernel(struct perf_event *event) { - struct perf_event_context *ctx; + struct perf_event_context *ctx = event->ctx; struct perf_event *child, *tmp; + /* + * If we got here through err_file: fput(event_file); we will not have + * attached to a context yet. + */ + if (!ctx) { + WARN_ON_ONCE(event->attach_state & + (PERF_ATTACH_CONTEXT|PERF_ATTACH_GROUP)); + goto no_ctx; + } + if (!is_kernel_event(event)) perf_remove_from_owner(event); @@ -3832,8 +3842,8 @@ int perf_event_release_kernel(struct perf_event *event) } mutex_unlock(&event->child_mutex); - /* Must be the last reference */ - put_event(event); +no_ctx: + put_event(event); /* Must be the 'last' reference */ return 0; } EXPORT_SYMBOL_GPL(perf_event_release_kernel); From 6f932e5be1503ab0783699e843db325d44c2fabb Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:43 +0100 Subject: [PATCH 179/417] perf: Only update context time when active Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Link: http://lkml.kernel.org/r/20160224174947.860690919@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index d5299e2e435d..64698fbfad9f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2170,12 +2170,12 @@ perf_install_in_context(struct perf_event_context *ctx, raw_spin_unlock_irq(&ctx->lock); return; } - update_context_time(ctx); - /* - * Update cgrp time only if current cgrp matches event->cgrp. - * Must be done before calling add_event_to_ctx(). - */ - update_cgrp_time_from_event(event); + + if (ctx->is_active) { + update_context_time(ctx); + update_cgrp_time_from_event(event); + } + add_event_to_ctx(event, ctx); raw_spin_unlock_irq(&ctx->lock); From a69b0ca4ac3bf5427b571f11cbf33f0a32b728d5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:44 +0100 Subject: [PATCH 180/417] perf: Fix cloning Alexander reported that when the 'original' context gets destroyed, no new clones happen. This can happen irrespective of the ctx switch optimization, any task can die, even the parent, and we want to continue monitoring the task hierarchy until we either close the event or no tasks are left in the hierarchy. perf_event_init_context() will attempt to pin the 'parent' context during clone(). At that point current is the parent, and since current cannot have exited while executing clone(), its context cannot have passed through perf_event_exit_task_context(). Therefore perf_pin_task_context() cannot observe ctx->task == TASK_TOMBSTONE. However, since inherit_event() does: if (parent_event->parent) parent_event = parent_event->parent; it looks at the 'original' event when it does: is_orphaned_event(). This can return true if the context that contains the this event has passed through perf_event_exit_task_context(). And thus we'll fail to clone the perf context. Fix this by adding a new state: STATE_DEAD, which is set by perf_release() to indicate that the filedesc (or kernel reference) is dead and there are no observers for our data left. Only for STATE_DEAD will is_orphaned_event() be true and inhibit cloning. STATE_EXIT is otherwise preserved such that is_event_hup() remains functional and will report when the observed task hierarchy becomes empty. Reported-by: Alexander Shishkin Tested-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Fixes: c6e5b73242d2 ("perf: Synchronously clean up child events") Link: http://lkml.kernel.org/r/20160224174947.919845295@infradead.org Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 1 + kernel/events/core.c | 29 ++++++++++++++--------------- 2 files changed, 15 insertions(+), 15 deletions(-) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index b35a61a481fa..39156619e108 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -397,6 +397,7 @@ struct pmu { * enum perf_event_active_state - the states of a event */ enum perf_event_active_state { + PERF_EVENT_STATE_DEAD = -4, PERF_EVENT_STATE_EXIT = -3, PERF_EVENT_STATE_ERROR = -2, PERF_EVENT_STATE_OFF = -1, diff --git a/kernel/events/core.c b/kernel/events/core.c index 64698fbfad9f..92d6999a4f2f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1645,7 +1645,7 @@ static void perf_group_detach(struct perf_event *event) static bool is_orphaned_event(struct perf_event *event) { - return event->state == PERF_EVENT_STATE_EXIT; + return event->state == PERF_EVENT_STATE_DEAD; } static inline int pmu_filter_match(struct perf_event *event) @@ -1732,7 +1732,6 @@ group_sched_out(struct perf_event *group_event, } #define DETACH_GROUP 0x01UL -#define DETACH_STATE 0x02UL /* * Cross CPU call to remove a performance event @@ -1752,8 +1751,6 @@ __perf_remove_from_context(struct perf_event *event, if (flags & DETACH_GROUP) perf_group_detach(event); list_del_event(event, ctx); - if (flags & DETACH_STATE) - event->state = PERF_EVENT_STATE_EXIT; if (!ctx->nr_events && ctx->is_active) { ctx->is_active = 0; @@ -3772,22 +3769,24 @@ int perf_event_release_kernel(struct perf_event *event) ctx = perf_event_ctx_lock(event); WARN_ON_ONCE(ctx->parent_ctx); - perf_remove_from_context(event, DETACH_GROUP | DETACH_STATE); - perf_event_ctx_unlock(event, ctx); + perf_remove_from_context(event, DETACH_GROUP); + raw_spin_lock_irq(&ctx->lock); /* - * At this point we must have event->state == PERF_EVENT_STATE_EXIT, - * either from the above perf_remove_from_context() or through - * perf_event_exit_event(). + * Mark this even as STATE_DEAD, there is no external reference to it + * anymore. * - * Therefore, anybody acquiring event->child_mutex after the below - * loop _must_ also see this, most importantly inherit_event() which - * will avoid placing more children on the list. + * Anybody acquiring event->child_mutex after the below loop _must_ + * also see this, most importantly inherit_event() which will avoid + * placing more children on the list. * * Thus this guarantees that we will in fact observe and kill _ALL_ * child events. */ - WARN_ON_ONCE(event->state != PERF_EVENT_STATE_EXIT); + event->state = PERF_EVENT_STATE_DEAD; + raw_spin_unlock_irq(&ctx->lock); + + perf_event_ctx_unlock(event, ctx); again: mutex_lock(&event->child_mutex); @@ -4000,7 +3999,7 @@ static bool is_event_hup(struct perf_event *event) { bool no_children; - if (event->state != PERF_EVENT_STATE_EXIT) + if (event->state > PERF_EVENT_STATE_EXIT) return false; mutex_lock(&event->child_mutex); @@ -8727,7 +8726,7 @@ perf_event_exit_event(struct perf_event *child_event, if (parent_event) perf_group_detach(child_event); list_del_event(child_event, child_ctx); - child_event->state = PERF_EVENT_STATE_EXIT; /* see perf_event_release_kernel() */ + child_event->state = PERF_EVENT_STATE_EXIT; /* is_event_hup() */ raw_spin_unlock_irq(&child_ctx->lock); /* From 9107c89e269d2738019861bb518e3d59bef01781 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:45 +0100 Subject: [PATCH 181/417] perf: Fix race between event install and jump_labels perf_install_in_context() relies upon the context switch hooks to have scheduled in events when the IPI misses its target -- after all, if the task has moved from the CPU (or wasn't running at all), it will have to context switch to run elsewhere. This however doesn't appear to be happening. It is possible for the IPI to not happen (task wasn't running) only to later observe the task running with an inactive context. The only possible explanation is that the context switch hooks are not called. Therefore put in a sync_sched() after toggling the jump_label to guarantee all CPUs will have them enabled before we install an event. A simple if (0->1) sync_sched() will not in fact work, because any further increment can race and complete before the sync_sched(). Therefore we must jump through some hoops. Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Link: http://lkml.kernel.org/r/20160224174947.980211985@infradead.org Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 6 ++--- kernel/events/core.c | 49 +++++++++++++++++++++++++++++++------- 2 files changed, 44 insertions(+), 11 deletions(-) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 39156619e108..f5c5a3fa2c81 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -906,7 +906,7 @@ perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) } } -extern struct static_key_deferred perf_sched_events; +extern struct static_key_false perf_sched_events; static __always_inline bool perf_sw_migrate_enabled(void) @@ -925,7 +925,7 @@ static inline void perf_event_task_migrate(struct task_struct *task) static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { - if (static_key_false(&perf_sched_events.key)) + if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_in(prev, task); if (perf_sw_migrate_enabled() && task->sched_migrated) { @@ -942,7 +942,7 @@ static inline void perf_event_task_sched_out(struct task_struct *prev, { perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0); - if (static_key_false(&perf_sched_events.key)) + if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_out(prev, next); } diff --git a/kernel/events/core.c b/kernel/events/core.c index 92d6999a4f2f..ea064ca8dd3c 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -321,7 +321,13 @@ enum event_type_t { * perf_sched_events : >0 events exist * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu */ -struct static_key_deferred perf_sched_events __read_mostly; + +static void perf_sched_delayed(struct work_struct *work); +DEFINE_STATIC_KEY_FALSE(perf_sched_events); +static DECLARE_DELAYED_WORK(perf_sched_work, perf_sched_delayed); +static DEFINE_MUTEX(perf_sched_mutex); +static atomic_t perf_sched_count; + static DEFINE_PER_CPU(atomic_t, perf_cgroup_events); static DEFINE_PER_CPU(int, perf_sched_cb_usages); @@ -3536,12 +3542,22 @@ static void unaccount_event(struct perf_event *event) if (has_branch_stack(event)) dec = true; - if (dec) - static_key_slow_dec_deferred(&perf_sched_events); + if (dec) { + if (!atomic_add_unless(&perf_sched_count, -1, 1)) + schedule_delayed_work(&perf_sched_work, HZ); + } unaccount_event_cpu(event, event->cpu); } +static void perf_sched_delayed(struct work_struct *work) +{ + mutex_lock(&perf_sched_mutex); + if (atomic_dec_and_test(&perf_sched_count)) + static_branch_disable(&perf_sched_events); + mutex_unlock(&perf_sched_mutex); +} + /* * The following implement mutual exclusion of events on "exclusive" pmus * (PERF_PMU_CAP_EXCLUSIVE). Such pmus can only have one event scheduled @@ -7780,8 +7796,28 @@ static void account_event(struct perf_event *event) if (is_cgroup_event(event)) inc = true; - if (inc) - static_key_slow_inc(&perf_sched_events.key); + if (inc) { + if (atomic_inc_not_zero(&perf_sched_count)) + goto enabled; + + mutex_lock(&perf_sched_mutex); + if (!atomic_read(&perf_sched_count)) { + static_branch_enable(&perf_sched_events); + /* + * Guarantee that all CPUs observe they key change and + * call the perf scheduling hooks before proceeding to + * install events that need them. + */ + synchronize_sched(); + } + /* + * Now that we have waited for the sync_sched(), allow further + * increments to by-pass the mutex. + */ + atomic_inc(&perf_sched_count); + mutex_unlock(&perf_sched_mutex); + } +enabled: account_event_cpu(event, event->cpu); } @@ -9344,9 +9380,6 @@ void __init perf_event_init(void) ret = init_hw_breakpoint(); WARN(ret, "hw_breakpoint initialization failed with: %d", ret); - /* do not patch jump label more than once per second */ - jump_label_rate_limit(&perf_sched_events, HZ); - /* * Build time assertion that we keep the data_head at the intended * location. IOW, validation we got the __reserved[] size right. From 28a967c3a2f99fa3b5f762f25cb2a319d933571b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:46 +0100 Subject: [PATCH 182/417] perf: Cure event->pending_disable race Because event_sched_out() checks event->pending_disable _before_ actually disabling the event, it can happen that the event fires after it checks but before it gets disabled. This would leave event->pending_disable set and the queued irq_work will try and process it. However, if the event trigger was during schedule(), the event might have been de-scheduled by the time the irq_work runs, and perf_event_disable_local() will fail. Fix this by checking event->pending_disable _after_ we call event->pmu->del(). This depends on the latter being a compiler barrier, such that the compiler does not lift the load and re-creates the problem. Tested-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Link: http://lkml.kernel.org/r/20160224174948.040469884@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index ea064ca8dd3c..de14b67a3b0b 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1696,14 +1696,14 @@ event_sched_out(struct perf_event *event, perf_pmu_disable(event->pmu); + event->tstamp_stopped = tstamp; + event->pmu->del(event, 0); + event->oncpu = -1; event->state = PERF_EVENT_STATE_INACTIVE; if (event->pending_disable) { event->pending_disable = 0; event->state = PERF_EVENT_STATE_OFF; } - event->tstamp_stopped = tstamp; - event->pmu->del(event, 0); - event->oncpu = -1; if (!is_software_event(event)) cpuctx->active_oncpu--; From 3cbaa59069677920186dcf502632ca1df4329f80 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:47 +0100 Subject: [PATCH 183/417] perf: Fix ctx time tracking by introducing EVENT_TIME Currently any ctx_sched_in() call will re-start the ctx time tracking, this means that calls like: ctx_sched_in(.event_type = EVENT_PINNED); ctx_sched_in(.event_type = EVENT_FLEXIBLE); will have a hole in their ctx time tracking. This is likely harmless but can confuse things a little. By adding EVENT_TIME, we can have the first ctx_sched_in() (is_active: 0 -> !0) start the time and any further ctx_sched_in() will leave the timestamps alone. Secondly, this allows for an early disable like: ctx_sched_out(.event_type = EVENT_TIME); which would update the ctx time (if the ctx is active) and any further calls to ctx_sched_out() would not further modify the ctx time. For ctx_sched_in() any 0 -> !0 transition will automatically include EVENT_TIME. For ctx_sched_out(), any transition that clears EVENT_ALL will automatically clear EVENT_TIME. These two rules ensure that under normal circumstances we need not bother with EVENT_TIME and get natural ctx time behaviour. Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Link: http://lkml.kernel.org/r/20160224174948.100446561@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 42 ++++++++++++++++++++++++++++++------------ 1 file changed, 30 insertions(+), 12 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index de14b67a3b0b..75bde93eb76f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -314,6 +314,7 @@ static void event_function_call(struct perf_event *event, event_f func, void *da enum event_type_t { EVENT_FLEXIBLE = 0x1, EVENT_PINNED = 0x2, + EVENT_TIME = 0x4, EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED, }; @@ -1294,16 +1295,18 @@ static u64 perf_event_time(struct perf_event *event) /* * Update the total_time_enabled and total_time_running fields for a event. - * The caller of this function needs to hold the ctx->lock. */ static void update_event_times(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; u64 run_end; + lockdep_assert_held(&ctx->lock); + if (event->state < PERF_EVENT_STATE_INACTIVE || event->group_leader->state < PERF_EVENT_STATE_INACTIVE) return; + /* * in cgroup mode, time_enabled represents * the time the event was enabled AND active @@ -2349,24 +2352,33 @@ static void ctx_sched_out(struct perf_event_context *ctx, } ctx->is_active &= ~event_type; + if (!(ctx->is_active & EVENT_ALL)) + ctx->is_active = 0; + if (ctx->task) { WARN_ON_ONCE(cpuctx->task_ctx != ctx); if (!ctx->is_active) cpuctx->task_ctx = NULL; } - update_context_time(ctx); - update_cgrp_time_from_cpuctx(cpuctx); - if (!ctx->nr_active) + is_active ^= ctx->is_active; /* changed bits */ + + if (is_active & EVENT_TIME) { + /* update (and stop) ctx time */ + update_context_time(ctx); + update_cgrp_time_from_cpuctx(cpuctx); + } + + if (!ctx->nr_active || !(is_active & EVENT_ALL)) return; perf_pmu_disable(ctx->pmu); - if ((is_active & EVENT_PINNED) && (event_type & EVENT_PINNED)) { + if (is_active & EVENT_PINNED) { list_for_each_entry(event, &ctx->pinned_groups, group_entry) group_sched_out(event, cpuctx, ctx); } - if ((is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE)) { + if (is_active & EVENT_FLEXIBLE) { list_for_each_entry(event, &ctx->flexible_groups, group_entry) group_sched_out(event, cpuctx, ctx); } @@ -2740,7 +2752,7 @@ ctx_sched_in(struct perf_event_context *ctx, if (likely(!ctx->nr_events)) return; - ctx->is_active |= event_type; + ctx->is_active |= (event_type | EVENT_TIME); if (ctx->task) { if (!is_active) cpuctx->task_ctx = ctx; @@ -2748,18 +2760,24 @@ ctx_sched_in(struct perf_event_context *ctx, WARN_ON_ONCE(cpuctx->task_ctx != ctx); } - now = perf_clock(); - ctx->timestamp = now; - perf_cgroup_set_timestamp(task, ctx); + is_active ^= ctx->is_active; /* changed bits */ + + if (is_active & EVENT_TIME) { + /* start ctx time */ + now = perf_clock(); + ctx->timestamp = now; + perf_cgroup_set_timestamp(task, ctx); + } + /* * First go through the list and put on any pinned groups * in order to give them the best chance of going on. */ - if (!(is_active & EVENT_PINNED) && (event_type & EVENT_PINNED)) + if (is_active & EVENT_PINNED) ctx_pinned_sched_in(ctx, cpuctx); /* Then walk through the lower prio flexible groups */ - if (!(is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE)) + if (is_active & EVENT_FLEXIBLE) ctx_flexible_sched_in(ctx, cpuctx); } From 7fce250915efca0f8f51dddee3ae89bf30d86ca5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:48 +0100 Subject: [PATCH 184/417] perf: Fix scaling vs. perf_event_enable_on_exec() The recent commit 3e349507d12d ("perf: Fix perf_enable_on_exec() event scheduling") caused this by moving task_ctx_sched_out() from before __perf_event_mask_enable() to after it. The overlooked consequence of that change is that task_ctx_sched_out() would update the ctx time fields, and now __perf_event_mask_enable() uses stale time. In order to fix this, explicitly stop our context's time before enabling the event(s). Reported-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Fixes: 3e349507d12d ("perf: Fix perf_enable_on_exec() event scheduling") Link: http://lkml.kernel.org/r/20160224174948.159242158@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/events/core.c b/kernel/events/core.c index 75bde93eb76f..d0030886c402 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3143,6 +3143,7 @@ static void perf_event_enable_on_exec(int ctxn) cpuctx = __get_cpu_context(ctx); perf_ctx_lock(cpuctx, ctx); + ctx_sched_out(ctx, cpuctx, EVENT_TIME); list_for_each_entry(event, &ctx->event_list, event_entry) enabled |= event_enable_on_exec(event, ctx); From bd2afa49d194c6412c333e9fdd48bc5d06bb465d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:49 +0100 Subject: [PATCH 185/417] perf: Fix scaling vs. perf_event_enable() Similar to the perf_enable_on_exec(), ensure that event timings are consistent across perf_event_enable(). Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Link: http://lkml.kernel.org/r/20160224174948.218288698@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 42 +++++++++++++++++++++++------------------- 1 file changed, 23 insertions(+), 19 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index d0030886c402..57c25faecfa5 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2069,14 +2069,27 @@ static void add_event_to_ctx(struct perf_event *event, event->tstamp_stopped = tstamp; } -static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx); +static void ctx_sched_out(struct perf_event_context *ctx, + struct perf_cpu_context *cpuctx, + enum event_type_t event_type); static void ctx_sched_in(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, enum event_type_t event_type, struct task_struct *task); +static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx) +{ + if (!cpuctx->task_ctx) + return; + + if (WARN_ON_ONCE(ctx != cpuctx->task_ctx)) + return; + + ctx_sched_out(ctx, cpuctx, EVENT_ALL); +} + static void perf_event_sched_in(struct perf_cpu_context *cpuctx, struct perf_event_context *ctx, struct task_struct *task) @@ -2227,17 +2240,18 @@ static void __perf_event_enable(struct perf_event *event, event->state <= PERF_EVENT_STATE_ERROR) return; - update_context_time(ctx); + if (ctx->is_active) + ctx_sched_out(ctx, cpuctx, EVENT_TIME); + __perf_event_mark_enabled(event); if (!ctx->is_active) return; if (!event_filter_match(event)) { - if (is_cgroup_event(event)) { - perf_cgroup_set_timestamp(current, ctx); // XXX ? + if (is_cgroup_event(event)) perf_cgroup_defer_enabled(event); - } + ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); return; } @@ -2245,8 +2259,10 @@ static void __perf_event_enable(struct perf_event *event, * If the event is in a group and isn't the group leader, * then don't put it on unless the group is on. */ - if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) + if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) { + ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); return; + } task_ctx = cpuctx->task_ctx; if (ctx->task) @@ -2658,18 +2674,6 @@ void __perf_event_task_sched_out(struct task_struct *task, perf_cgroup_sched_out(task, next); } -static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx) -{ - if (!cpuctx->task_ctx) - return; - - if (WARN_ON_ONCE(ctx != cpuctx->task_ctx)) - return; - - ctx_sched_out(ctx, cpuctx, EVENT_ALL); -} - /* * Called with IRQs disabled */ From a096309bc4677f60caa8e93fcc613a55073c51d4 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:50 +0100 Subject: [PATCH 186/417] perf: Fix scaling vs. perf_install_in_context() Completely reworks perf_install_in_context() (again!) in order to ensure that there will be no ctx time hole between add_event_to_ctx() and any potential ctx_sched_in(). Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Link: http://lkml.kernel.org/r/20160224174948.279399438@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 127 ++++++++++++++++++++++++++----------------- 1 file changed, 76 insertions(+), 51 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 57c25faecfa5..25edabd207de 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -276,10 +276,10 @@ static void event_function_call(struct perf_event *event, event_f func, void *da return; } -again: if (task == TASK_TOMBSTONE) return; +again: if (!task_function_call(task, event_function, &efs)) return; @@ -289,13 +289,15 @@ static void event_function_call(struct perf_event *event, event_f func, void *da * a concurrent perf_event_context_sched_out(). */ task = ctx->task; - if (task != TASK_TOMBSTONE) { - if (ctx->is_active) { - raw_spin_unlock_irq(&ctx->lock); - goto again; - } - func(event, NULL, ctx, data); + if (task == TASK_TOMBSTONE) { + raw_spin_unlock_irq(&ctx->lock); + return; } + if (ctx->is_active) { + raw_spin_unlock_irq(&ctx->lock); + goto again; + } + func(event, NULL, ctx, data); raw_spin_unlock_irq(&ctx->lock); } @@ -2116,49 +2118,68 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, /* * Cross CPU call to install and enable a performance event * - * Must be called with ctx->mutex held + * Very similar to remote_function() + event_function() but cannot assume that + * things like ctx->is_active and cpuctx->task_ctx are set. */ static int __perf_install_in_context(void *info) { - struct perf_event_context *ctx = info; + struct perf_event *event = info; + struct perf_event_context *ctx = event->ctx; struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); struct perf_event_context *task_ctx = cpuctx->task_ctx; + bool activate = true; + int ret = 0; raw_spin_lock(&cpuctx->ctx.lock); if (ctx->task) { raw_spin_lock(&ctx->lock); - /* - * If we hit the 'wrong' task, we've since scheduled and - * everything should be sorted, nothing to do! - */ task_ctx = ctx; - if (ctx->task != current) + + /* If we're on the wrong CPU, try again */ + if (task_cpu(ctx->task) != smp_processor_id()) { + ret = -ESRCH; goto unlock; + } /* - * If task_ctx is set, it had better be to us. + * If we're on the right CPU, see if the task we target is + * current, if not we don't have to activate the ctx, a future + * context switch will do that for us. */ - WARN_ON_ONCE(cpuctx->task_ctx != ctx && cpuctx->task_ctx); + if (ctx->task != current) + activate = false; + else + WARN_ON_ONCE(cpuctx->task_ctx && cpuctx->task_ctx != ctx); + } else if (task_ctx) { raw_spin_lock(&task_ctx->lock); } - ctx_resched(cpuctx, task_ctx); + if (activate) { + ctx_sched_out(ctx, cpuctx, EVENT_TIME); + add_event_to_ctx(event, ctx); + ctx_resched(cpuctx, task_ctx); + } else { + add_event_to_ctx(event, ctx); + } + unlock: perf_ctx_unlock(cpuctx, task_ctx); - return 0; + return ret; } /* - * Attach a performance event to a context + * Attach a performance event to a context. + * + * Very similar to event_function_call, see comment there. */ static void perf_install_in_context(struct perf_event_context *ctx, struct perf_event *event, int cpu) { - struct task_struct *task = NULL; + struct task_struct *task = READ_ONCE(ctx->task); lockdep_assert_held(&ctx->mutex); @@ -2166,42 +2187,46 @@ perf_install_in_context(struct perf_event_context *ctx, if (event->cpu != -1) event->cpu = cpu; - /* - * Installing events is tricky because we cannot rely on ctx->is_active - * to be set in case this is the nr_events 0 -> 1 transition. - * - * So what we do is we add the event to the list here, which will allow - * a future context switch to DTRT and then send a racy IPI. If the IPI - * fails to hit the right task, this means a context switch must have - * happened and that will have taken care of business. - */ - raw_spin_lock_irq(&ctx->lock); - task = ctx->task; - - /* - * If between ctx = find_get_context() and mutex_lock(&ctx->mutex) the - * ctx gets destroyed, we must not install an event into it. - * - * This is normally tested for after we acquire the mutex, so this is - * a sanity check. - */ - if (WARN_ON_ONCE(task == TASK_TOMBSTONE)) { - raw_spin_unlock_irq(&ctx->lock); + if (!task) { + cpu_function_call(cpu, __perf_install_in_context, event); return; } - if (ctx->is_active) { - update_context_time(ctx); - update_cgrp_time_from_event(event); + /* + * Should not happen, we validate the ctx is still alive before calling. + */ + if (WARN_ON_ONCE(task == TASK_TOMBSTONE)) + return; + + /* + * Installing events is tricky because we cannot rely on ctx->is_active + * to be set in case this is the nr_events 0 -> 1 transition. + */ +again: + /* + * Cannot use task_function_call() because we need to run on the task's + * CPU regardless of whether its current or not. + */ + if (!cpu_function_call(task_cpu(task), __perf_install_in_context, event)) + return; + + raw_spin_lock_irq(&ctx->lock); + task = ctx->task; + if (WARN_ON_ONCE(task == TASK_TOMBSTONE)) { + /* + * Cannot happen because we already checked above (which also + * cannot happen), and we hold ctx->mutex, which serializes us + * against perf_event_exit_task_context(). + */ + raw_spin_unlock_irq(&ctx->lock); + return; } - - add_event_to_ctx(event, ctx); raw_spin_unlock_irq(&ctx->lock); - - if (task) - task_function_call(task, __perf_install_in_context, ctx); - else - cpu_function_call(cpu, __perf_install_in_context, ctx); + /* + * Since !ctx->is_active doesn't mean anything, we must IPI + * unconditionally. + */ + goto again; } /* From 0da4cf3e0a68c97ef811569804616a811f786729 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:51 +0100 Subject: [PATCH 187/417] perf: Robustify task_function_call() Since there is no serialization between task_function_call() doing task_curr() and the other CPU doing context switches, we could end up not sending an IPI even if we had to. And I'm not sure I still buy my own argument we're OK. Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Link: http://lkml.kernel.org/r/20160224174948.340031200@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 40 ++++++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 20 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 25edabd207de..614614821f00 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -64,8 +64,17 @@ static void remote_function(void *data) struct task_struct *p = tfc->p; if (p) { - tfc->ret = -EAGAIN; - if (task_cpu(p) != smp_processor_id() || !task_curr(p)) + /* -EAGAIN */ + if (task_cpu(p) != smp_processor_id()) + return; + + /* + * Now that we're on right CPU with IRQs disabled, we can test + * if we hit the right task without races. + */ + + tfc->ret = -ESRCH; /* No such (running) process */ + if (p != current) return; } @@ -92,13 +101,17 @@ task_function_call(struct task_struct *p, remote_function_f func, void *info) .p = p, .func = func, .info = info, - .ret = -ESRCH, /* No such (running) process */ + .ret = -EAGAIN, }; + int ret; - if (task_curr(p)) - smp_call_function_single(task_cpu(p), remote_function, &data, 1); + do { + ret = smp_call_function_single(task_cpu(p), remote_function, &data, 1); + if (!ret) + ret = data.ret; + } while (ret == -EAGAIN); - return data.ret; + return ret; } /** @@ -169,19 +182,6 @@ static bool is_kernel_event(struct perf_event *event) * rely on ctx->is_active and therefore cannot use event_function_call(). * See perf_install_in_context(). * - * This is because we need a ctx->lock serialized variable (ctx->is_active) - * to reliably determine if a particular task/context is scheduled in. The - * task_curr() use in task_function_call() is racy in that a remote context - * switch is not a single atomic operation. - * - * As is, the situation is 'safe' because we set rq->curr before we do the - * actual context switch. This means that task_curr() will fail early, but - * we'll continue spinning on ctx->is_active until we've passed - * perf_event_task_sched_out(). - * - * Without this ctx->lock serialized variable we could have race where we find - * the task (and hence the context) would not be active while in fact they are. - * * If ctx->nr_events, then ctx->is_active and cpuctx->task_ctx are set. */ @@ -212,7 +212,7 @@ static int event_function(void *info) */ if (ctx->task) { if (ctx->task != current) { - ret = -EAGAIN; + ret = -ESRCH; goto unlock; } From 3b43b71f05d3ecd01c4116254666d9492301697d Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Thu, 25 Feb 2016 15:19:38 +0800 Subject: [PATCH 188/417] ALSA: hda - Fixing background noise on Dell Inspiron 3162 After login to the desktop on Dell Inspiron 3162, there's a very loud background noise comes from the builtin speaker. The noise does not go away even if the speaker is muted. The noise disappears after using the aamix fixup. Codec: Realtek ALC3234 Address: 0 AFG Function Id: 0x1 (unsol 1) Vendor Id: 0x10ec0255 Subsystem Id: 0x10280725 Revision Id: 0x100002 No Modem Function Group found BugLink: http://bugs.launchpad.net/bugs/1549620 Signed-off-by: Kai-Heng Feng Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index efd4980cffb8..72fa58dd7723 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4749,6 +4749,7 @@ enum { ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE, ALC293_FIXUP_LENOVO_SPK_NOISE, ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY, + ALC255_FIXUP_DELL_SPK_NOISE, }; static const struct hda_fixup alc269_fixups[] = { @@ -5368,6 +5369,12 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc233_fixup_lenovo_line2_mic_hotkey, }, + [ALC255_FIXUP_DELL_SPK_NOISE] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_disable_aamix, + .chained = true, + .chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -5410,6 +5417,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x06df, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK), SND_PCI_QUIRK(0x1028, 0x06e0, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK), SND_PCI_QUIRK(0x1028, 0x0704, "Dell XPS 13", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), + SND_PCI_QUIRK(0x1028, 0x0725, "Dell Inspiron 3162", ALC255_FIXUP_DELL_SPK_NOISE), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), From 17e4bce0ae63c7e03f3c7fa8d80890e7af3d4971 Mon Sep 17 00:00:00 2001 From: Mike Krinkin Date: Wed, 24 Feb 2016 21:02:31 +0300 Subject: [PATCH 189/417] KVM: x86: MMU: fix ubsan index-out-of-range warning Ubsan reports the following warning due to a typo in update_accessed_dirty_bits template, the patch fixes the typo: [ 168.791851] ================================================================================ [ 168.791862] UBSAN: Undefined behaviour in arch/x86/kvm/paging_tmpl.h:252:15 [ 168.791866] index 4 is out of range for type 'u64 [4]' [ 168.791871] CPU: 0 PID: 2950 Comm: qemu-system-x86 Tainted: G O L 4.5.0-rc5-next-20160222 #7 [ 168.791873] Hardware name: LENOVO 23205NG/23205NG, BIOS G2ET95WW (2.55 ) 07/09/2013 [ 168.791876] 0000000000000000 ffff8801cfcaf208 ffffffff81c9f780 0000000041b58ab3 [ 168.791882] ffffffff82eb2cc1 ffffffff81c9f6b4 ffff8801cfcaf230 ffff8801cfcaf1e0 [ 168.791886] 0000000000000004 0000000000000001 0000000000000000 ffffffffa1981600 [ 168.791891] Call Trace: [ 168.791899] [] dump_stack+0xcc/0x12c [ 168.791904] [] ? _atomic_dec_and_lock+0xc4/0xc4 [ 168.791910] [] ubsan_epilogue+0xd/0x8a [ 168.791914] [] __ubsan_handle_out_of_bounds+0x15c/0x1a3 [ 168.791918] [] ? __ubsan_handle_shift_out_of_bounds+0x2bd/0x2bd [ 168.791922] [] ? get_user_pages_fast+0x2bf/0x360 [ 168.791954] [] ? kvm_largepages_enabled+0x30/0x30 [kvm] [ 168.791958] [] ? __get_user_pages_fast+0x360/0x360 [ 168.791987] [] paging64_walk_addr_generic+0x1b28/0x2600 [kvm] [ 168.792014] [] ? init_kvm_mmu+0x1100/0x1100 [kvm] [ 168.792019] [] ? debug_check_no_locks_freed+0x350/0x350 [ 168.792044] [] ? init_kvm_mmu+0x1100/0x1100 [kvm] [ 168.792076] [] paging64_gva_to_gpa+0x7d/0x110 [kvm] [ 168.792121] [] ? paging64_walk_addr_generic+0x2600/0x2600 [kvm] [ 168.792130] [] ? debug_lockdep_rcu_enabled+0x7b/0x90 [ 168.792178] [] emulator_read_write_onepage+0x27a/0x1150 [kvm] [ 168.792208] [] ? __kvm_read_guest_page+0x54/0x70 [kvm] [ 168.792234] [] ? kvm_task_switch+0x160/0x160 [kvm] [ 168.792238] [] ? debug_lockdep_rcu_enabled+0x7b/0x90 [ 168.792263] [] emulator_read_write+0xe7/0x6d0 [kvm] [ 168.792290] [] ? em_cr_write+0x230/0x230 [kvm] [ 168.792314] [] emulator_write_emulated+0x15/0x20 [kvm] [ 168.792340] [] segmented_write+0xf8/0x130 [kvm] [ 168.792367] [] ? em_lgdt+0x20/0x20 [kvm] [ 168.792374] [] ? vmx_read_guest_seg_ar+0x42/0x1e0 [kvm_intel] [ 168.792400] [] writeback+0x3f2/0x700 [kvm] [ 168.792424] [] ? em_sidt+0xa0/0xa0 [kvm] [ 168.792449] [] ? x86_decode_insn+0x1b3d/0x4f70 [kvm] [ 168.792474] [] x86_emulate_insn+0x572/0x3010 [kvm] [ 168.792499] [] x86_emulate_instruction+0x3bd/0x2110 [kvm] [ 168.792524] [] ? reexecute_instruction.part.110+0x2e0/0x2e0 [kvm] [ 168.792532] [] handle_ept_misconfig+0x61/0x460 [kvm_intel] [ 168.792539] [] ? handle_pause+0x450/0x450 [kvm_intel] [ 168.792546] [] vmx_handle_exit+0xd6a/0x1ad0 [kvm_intel] [ 168.792572] [] ? kvm_arch_vcpu_ioctl_run+0xbdc/0x6090 [kvm] [ 168.792597] [] kvm_arch_vcpu_ioctl_run+0xd3d/0x6090 [kvm] [ 168.792621] [] ? kvm_arch_vcpu_ioctl_run+0xbdc/0x6090 [kvm] [ 168.792627] [] ? __ww_mutex_lock_interruptible+0x1630/0x1630 [ 168.792651] [] ? kvm_arch_vcpu_runnable+0x4f0/0x4f0 [kvm] [ 168.792656] [] ? preempt_notifier_unregister+0x190/0x190 [ 168.792681] [] ? kvm_arch_vcpu_load+0x127/0x650 [kvm] [ 168.792704] [] kvm_vcpu_ioctl+0x553/0xda0 [kvm] [ 168.792727] [] ? vcpu_put+0x40/0x40 [kvm] [ 168.792732] [] ? debug_check_no_locks_freed+0x350/0x350 [ 168.792735] [] ? _raw_spin_unlock+0x27/0x40 [ 168.792740] [] ? handle_mm_fault+0x1673/0x2e40 [ 168.792744] [] ? trace_hardirqs_on_caller+0x478/0x6c0 [ 168.792747] [] ? trace_hardirqs_on+0xd/0x10 [ 168.792751] [] ? debug_lockdep_rcu_enabled+0x7b/0x90 [ 168.792756] [] do_vfs_ioctl+0x1b0/0x12b0 [ 168.792759] [] ? ioctl_preallocate+0x210/0x210 [ 168.792763] [] ? __fget+0x273/0x4a0 [ 168.792766] [] ? __fget+0x50/0x4a0 [ 168.792770] [] ? __fget_light+0x96/0x2b0 [ 168.792773] [] SyS_ioctl+0x79/0x90 [ 168.792777] [] entry_SYSCALL_64_fastpath+0x23/0xc1 [ 168.792780] ================================================================================ Signed-off-by: Mike Krinkin Reviewed-by: Xiao Guangrong Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/kvm/paging_tmpl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 6c9fed957cce..2ce4f05e81d3 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -249,7 +249,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, return ret; kvm_vcpu_mark_page_dirty(vcpu, table_gfn); - walker->ptes[level] = pte; + walker->ptes[level - 1] = pte; } return 0; } From 2ae955774f29bbd7d16149cb0ae8d0319bf2ecc4 Mon Sep 17 00:00:00 2001 From: David Henningsson Date: Thu, 25 Feb 2016 09:37:05 +0100 Subject: [PATCH 190/417] ALSA: hda - Fixup speaker pass-through control for nid 0x14 on ALC225 On one of the machines we enable, we found that the actual speaker volume did not always correspond to the volume set in alsamixer. This patch fixes that problem. This patch was orginally written by Kailang @ Realtek, I've rebased it to fit sound git master. Cc: stable@vger.kernel.org BugLink: https://bugs.launchpad.net/bugs/1549660 Co-Authored-By: Kailang Signed-off-by: David Henningsson Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 72fa58dd7723..7fded69fb58e 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3801,6 +3801,10 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin, static void alc_headset_mode_default(struct hda_codec *codec) { + static struct coef_fw coef0225[] = { + UPDATE_COEF(0x45, 0x3f<<10, 0x34<<10), + {} + }; static struct coef_fw coef0255[] = { WRITE_COEF(0x45, 0xc089), WRITE_COEF(0x45, 0xc489), @@ -3842,6 +3846,9 @@ static void alc_headset_mode_default(struct hda_codec *codec) }; switch (codec->core.vendor_id) { + case 0x10ec0225: + alc_process_coef_fw(codec, coef0225); + break; case 0x10ec0255: case 0x10ec0256: alc_process_coef_fw(codec, coef0255); @@ -4750,6 +4757,7 @@ enum { ALC293_FIXUP_LENOVO_SPK_NOISE, ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY, ALC255_FIXUP_DELL_SPK_NOISE, + ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, }; static const struct hda_fixup alc269_fixups[] = { @@ -5375,6 +5383,17 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE }, + [ALC225_FIXUP_DELL1_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + /* Disable pass-through path for FRONT 14h */ + { 0x20, AC_VERB_SET_COEF_INDEX, 0x36 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x57d7 }, + {} + }, + .chained = true, + .chain_id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -5646,10 +5665,10 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {0x21, 0x03211020} static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { - SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, + SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, ALC225_STANDARD_PINS, {0x14, 0x901701a0}), - SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, + SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, ALC225_STANDARD_PINS, {0x14, 0x901701b0}), SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE, From 157078f64b8a9cd7011b6b900b2f2498df850748 Mon Sep 17 00:00:00 2001 From: Thomas Betker Date: Tue, 10 Nov 2015 22:18:15 +0100 Subject: [PATCH 191/417] Revert "jffs2: Fix lock acquisition order bug in jffs2_write_begin" This reverts commit 5ffd3412ae55 ("jffs2: Fix lock acquisition order bug in jffs2_write_begin"). The commit modified jffs2_write_begin() to remove a deadlock with jffs2_garbage_collect_live(), but this introduced new deadlocks found by multiple users. page_lock() actually has to be called before mutex_lock(&c->alloc_sem) or mutex_lock(&f->sem) because jffs2_write_end() and jffs2_readpage() are called with the page locked, and they acquire c->alloc_sem and f->sem, resp. In other words, the lock order in jffs2_write_begin() was correct, and it is the jffs2_garbage_collect_live() path that has to be changed. Revert the commit to get rid of the new deadlocks, and to clear the way for a better fix of the original deadlock. Reported-by: Deng Chao Reported-by: Ming Liu Reported-by: wangzaiwei Signed-off-by: Thomas Betker Signed-off-by: David Woodhouse Cc: stable@vger.kernel.org --- fs/jffs2/file.c | 41 +++++++++++++++++++---------------------- 1 file changed, 19 insertions(+), 22 deletions(-) diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index c5ac5944bc1b..cad86bac3453 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -137,39 +137,33 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, struct page *pg; struct inode *inode = mapping->host; struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); - struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); - struct jffs2_raw_inode ri; - uint32_t alloc_len = 0; pgoff_t index = pos >> PAGE_CACHE_SHIFT; uint32_t pageofs = index << PAGE_CACHE_SHIFT; int ret = 0; + pg = grab_cache_page_write_begin(mapping, index, flags); + if (!pg) + return -ENOMEM; + *pagep = pg; + jffs2_dbg(1, "%s()\n", __func__); if (pageofs > inode->i_size) { - ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len, - ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE); - if (ret) - return ret; - } - - mutex_lock(&f->sem); - pg = grab_cache_page_write_begin(mapping, index, flags); - if (!pg) { - if (alloc_len) - jffs2_complete_reservation(c); - mutex_unlock(&f->sem); - return -ENOMEM; - } - *pagep = pg; - - if (alloc_len) { /* Make new hole frag from old EOF to new page */ + struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); + struct jffs2_raw_inode ri; struct jffs2_full_dnode *fn; + uint32_t alloc_len; jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new page\n", (unsigned int)inode->i_size, pageofs); + ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len, + ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE); + if (ret) + goto out_page; + + mutex_lock(&f->sem); memset(&ri, 0, sizeof(ri)); ri.magic = cpu_to_je16(JFFS2_MAGIC_BITMASK); @@ -196,6 +190,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, if (IS_ERR(fn)) { ret = PTR_ERR(fn); jffs2_complete_reservation(c); + mutex_unlock(&f->sem); goto out_page; } ret = jffs2_add_full_dnode_to_inode(c, f, fn); @@ -210,10 +205,12 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, jffs2_mark_node_obsolete(c, fn->raw); jffs2_free_full_dnode(fn); jffs2_complete_reservation(c); + mutex_unlock(&f->sem); goto out_page; } jffs2_complete_reservation(c); inode->i_size = pageofs; + mutex_unlock(&f->sem); } /* @@ -222,18 +219,18 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, * case of a short-copy. */ if (!PageUptodate(pg)) { + mutex_lock(&f->sem); ret = jffs2_do_readpage_nolock(inode, pg); + mutex_unlock(&f->sem); if (ret) goto out_page; } - mutex_unlock(&f->sem); jffs2_dbg(1, "end write_begin(). pg->flags %lx\n", pg->flags); return ret; out_page: unlock_page(pg); page_cache_release(pg); - mutex_unlock(&f->sem); return ret; } From 49e91e7079febe59a20ca885a87dd1c54240d0f1 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 1 Feb 2016 12:37:20 +0000 Subject: [PATCH 192/417] jffs2: Fix page lock / f->sem deadlock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With this fix, all code paths should now be obtaining the page lock before f->sem. Reported-by: Szabó Tamás Tested-by: Thomas Betker Signed-off-by: David Woodhouse Cc: stable@vger.kernel.org --- fs/jffs2/README.Locking | 5 +---- fs/jffs2/gc.c | 17 ++++++++++------- 2 files changed, 11 insertions(+), 11 deletions(-) diff --git a/fs/jffs2/README.Locking b/fs/jffs2/README.Locking index 3ea36554107f..8918ac905a3b 100644 --- a/fs/jffs2/README.Locking +++ b/fs/jffs2/README.Locking @@ -2,10 +2,6 @@ JFFS2 LOCKING DOCUMENTATION --------------------------- -At least theoretically, JFFS2 does not require the Big Kernel Lock -(BKL), which was always helpfully obtained for it by Linux 2.4 VFS -code. It has its own locking, as described below. - This document attempts to describe the existing locking rules for JFFS2. It is not expected to remain perfectly up to date, but ought to be fairly close. @@ -69,6 +65,7 @@ Ordering constraints: any f->sem held. 2. Never attempt to lock two file mutexes in one thread. No ordering rules have been made for doing so. + 3. Never lock a page cache page with f->sem held. erase_completion_lock spinlock diff --git a/fs/jffs2/gc.c b/fs/jffs2/gc.c index 5a2dec2b064c..95d5880a63ee 100644 --- a/fs/jffs2/gc.c +++ b/fs/jffs2/gc.c @@ -1296,14 +1296,17 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era BUG_ON(start > orig_start); } - /* First, use readpage() to read the appropriate page into the page cache */ - /* Q: What happens if we actually try to GC the _same_ page for which commit_write() - * triggered garbage collection in the first place? - * A: I _think_ it's OK. read_cache_page shouldn't deadlock, we'll write out the - * page OK. We'll actually write it out again in commit_write, which is a little - * suboptimal, but at least we're correct. - */ + /* The rules state that we must obtain the page lock *before* f->sem, so + * drop f->sem temporarily. Since we also hold c->alloc_sem, nothing's + * actually going to *change* so we're safe; we only allow reading. + * + * It is important to note that jffs2_write_begin() will ensure that its + * page is marked Uptodate before allocating space. That means that if we + * end up here trying to GC the *same* page that jffs2_write_begin() is + * trying to write out, read_cache_page() will not deadlock. */ + mutex_unlock(&f->sem); pg_ptr = jffs2_gc_fetch_page(c, f, start, &pg); + mutex_lock(&f->sem); if (IS_ERR(pg_ptr)) { pr_warn("read_cache_page() returned error: %ld\n", From be629c62a603e5935f8177fd8a19e014100a259e Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 1 Feb 2016 14:04:46 +0000 Subject: [PATCH 193/417] Fix directory hardlinks from deleted directories MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When a directory is deleted, we don't take too much care about killing off all the dirents that belong to it — on the basis that on remount, the scan will conclude that the directory is dead anyway. This doesn't work though, when the deleted directory contained a child directory which was moved *out*. In the early stages of the fs build we can then end up with an apparent hard link, with the child directory appearing both in its true location, and as a child of the original directory which are this stage of the mount process we don't *yet* know is defunct. To resolve this, take out the early special-casing of the "directories shall not have hard links" rule in jffs2_build_inode_pass1(), and let the normal nlink processing happen for directories as well as other inodes. Then later in the build process we can set ic->pino_nlink to the parent inode#, as is required for directories during normal operaton, instead of the nlink. And complain only *then* about hard links which are still in evidence even after killing off all the unreachable paths. Reported-by: Liu Song Signed-off-by: David Woodhouse Cc: stable@vger.kernel.org --- fs/jffs2/build.c | 75 ++++++++++++++++++++++++++++++++++----------- fs/jffs2/nodelist.h | 6 +++- 2 files changed, 62 insertions(+), 19 deletions(-) diff --git a/fs/jffs2/build.c b/fs/jffs2/build.c index 0ae91ad6df2d..b288c8ae1236 100644 --- a/fs/jffs2/build.c +++ b/fs/jffs2/build.c @@ -50,7 +50,8 @@ next_inode(int *i, struct jffs2_inode_cache *ic, struct jffs2_sb_info *c) static void jffs2_build_inode_pass1(struct jffs2_sb_info *c, - struct jffs2_inode_cache *ic) + struct jffs2_inode_cache *ic, + int *dir_hardlinks) { struct jffs2_full_dirent *fd; @@ -69,19 +70,21 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c, dbg_fsbuild("child \"%s\" (ino #%u) of dir ino #%u doesn't exist!\n", fd->name, fd->ino, ic->ino); jffs2_mark_node_obsolete(c, fd->raw); + /* Clear the ic/raw union so it doesn't cause problems later. */ + fd->ic = NULL; continue; } + /* From this point, fd->raw is no longer used so we can set fd->ic */ + fd->ic = child_ic; + child_ic->pino_nlink++; + /* If we appear (at this stage) to have hard-linked directories, + * set a flag to trigger a scan later */ if (fd->type == DT_DIR) { - if (child_ic->pino_nlink) { - JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u appears to be a hard link\n", - fd->name, fd->ino, ic->ino); - /* TODO: What do we do about it? */ - } else { - child_ic->pino_nlink = ic->ino; - } - } else - child_ic->pino_nlink++; + child_ic->flags |= INO_FLAGS_IS_DIR; + if (child_ic->pino_nlink > 1) + *dir_hardlinks = 1; + } dbg_fsbuild("increased nlink for child \"%s\" (ino #%u)\n", fd->name, fd->ino); /* Can't free scan_dents so far. We might need them in pass 2 */ @@ -95,8 +98,7 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c, */ static int jffs2_build_filesystem(struct jffs2_sb_info *c) { - int ret; - int i; + int ret, i, dir_hardlinks = 0; struct jffs2_inode_cache *ic; struct jffs2_full_dirent *fd; struct jffs2_full_dirent *dead_fds = NULL; @@ -120,7 +122,7 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c) /* Now scan the directory tree, increasing nlink according to every dirent found. */ for_each_inode(i, c, ic) { if (ic->scan_dents) { - jffs2_build_inode_pass1(c, ic); + jffs2_build_inode_pass1(c, ic, &dir_hardlinks); cond_resched(); } } @@ -156,6 +158,20 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c) } dbg_fsbuild("pass 2a complete\n"); + + if (dir_hardlinks) { + /* If we detected directory hardlinks earlier, *hopefully* + * they are gone now because some of the links were from + * dead directories which still had some old dirents lying + * around and not yet garbage-collected, but which have + * been discarded above. So clear the pino_nlink field + * in each directory, so that the final scan below can + * print appropriate warnings. */ + for_each_inode(i, c, ic) { + if (ic->flags & INO_FLAGS_IS_DIR) + ic->pino_nlink = 0; + } + } dbg_fsbuild("freeing temporary data structures\n"); /* Finally, we can scan again and free the dirent structs */ @@ -163,6 +179,33 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c) while(ic->scan_dents) { fd = ic->scan_dents; ic->scan_dents = fd->next; + /* We do use the pino_nlink field to count nlink of + * directories during fs build, so set it to the + * parent ino# now. Now that there's hopefully only + * one. */ + if (fd->type == DT_DIR) { + if (!fd->ic) { + /* We'll have complained about it and marked the coresponding + raw node obsolete already. Just skip it. */ + continue; + } + + /* We *have* to have set this in jffs2_build_inode_pass1() */ + BUG_ON(!(fd->ic->flags & INO_FLAGS_IS_DIR)); + + /* We clear ic->pino_nlink ∀ directories' ic *only* if dir_hardlinks + * is set. Otherwise, we know this should never trigger anyway, so + * we don't do the check. And ic->pino_nlink still contains the nlink + * value (which is 1). */ + if (dir_hardlinks && fd->ic->pino_nlink) { + JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u is also hard linked from dir ino #%u\n", + fd->name, fd->ino, ic->ino, fd->ic->pino_nlink); + /* Should we unlink it from its previous parent? */ + } + + /* For directories, ic->pino_nlink holds that parent inode # */ + fd->ic->pino_nlink = ic->ino; + } jffs2_free_full_dirent(fd); } ic->scan_dents = NULL; @@ -241,11 +284,7 @@ static void jffs2_build_remove_unlinked_inode(struct jffs2_sb_info *c, /* Reduce nlink of the child. If it's now zero, stick it on the dead_fds list to be cleaned up later. Else just free the fd */ - - if (fd->type == DT_DIR) - child_ic->pino_nlink = 0; - else - child_ic->pino_nlink--; + child_ic->pino_nlink--; if (!child_ic->pino_nlink) { dbg_fsbuild("inode #%u (\"%s\") now has no links; adding to dead_fds list.\n", diff --git a/fs/jffs2/nodelist.h b/fs/jffs2/nodelist.h index fa35ff79ab35..0637271f3770 100644 --- a/fs/jffs2/nodelist.h +++ b/fs/jffs2/nodelist.h @@ -194,6 +194,7 @@ struct jffs2_inode_cache { #define INO_STATE_CLEARING 6 /* In clear_inode() */ #define INO_FLAGS_XATTR_CHECKED 0x01 /* has no duplicate xattr_ref */ +#define INO_FLAGS_IS_DIR 0x02 /* is a directory */ #define RAWNODE_CLASS_INODE_CACHE 0 #define RAWNODE_CLASS_XATTR_DATUM 1 @@ -249,7 +250,10 @@ struct jffs2_readinode_info struct jffs2_full_dirent { - struct jffs2_raw_node_ref *raw; + union { + struct jffs2_raw_node_ref *raw; + struct jffs2_inode_cache *ic; /* Just during part of build */ + }; struct jffs2_full_dirent *next; uint32_t version; uint32_t ino; /* == zero for unlink */ From f883982dc1b117f04579f0896821cd9f2e397f94 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 25 Feb 2016 14:31:59 +0100 Subject: [PATCH 194/417] ALSA: hda - Fix headset support and noise on HP EliteBook 755 G2 HP EliteBook 755 G2 with ALC3228 (ALC280) codec [103c:221c] requires the known fixup (ALC269_FIXUP_HEADSET_MIC) for making the headset mic working. Also, it suffers from the loopback noise problem, so we should disable aamix path as well. Reported-by: Derick Eddington Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 7fded69fb58e..1f357cd72d9c 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4758,6 +4758,7 @@ enum { ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY, ALC255_FIXUP_DELL_SPK_NOISE, ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, + ALC280_FIXUP_HP_HEADSET_MIC, }; static const struct hda_fixup alc269_fixups[] = { @@ -5394,6 +5395,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE }, + [ALC280_FIXUP_HP_HEADSET_MIC] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_disable_aamix, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MIC, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -5497,6 +5504,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x2335, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x2336, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x2337, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x221c, "HP EliteBook 755 G2", ALC280_FIXUP_HP_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1043, 0x115d, "Asus 1015E", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), From b26a719bdba9aa926ceaadecc66e07623d2b8a53 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 18 Feb 2016 17:06:30 +0100 Subject: [PATCH 195/417] gpio: rcar: Add Runtime PM handling for interrupts The R-Car GPIO driver handles Runtime PM for requested GPIOs only. When using a GPIO purely as an interrupt source, no Runtime PM handling is done, and the GPIO module's clock may not be enabled. To fix this: - Add .irq_request_resources() and .irq_release_resources() callbacks to handle Runtime PM when an interrupt is requested, - Add irq_bus_lock() and sync_unlock() callbacks to handle Runtime PM when e.g. disabling/enabling an interrupt, or configuring the interrupt type. Fixes: d5c3d84657db57bd "net: phy: Avoid polling PHY with PHY_IGNORE_INTERRUPTS" Signed-off-by: Geert Uytterhoeven Signed-off-by: Linus Walleij --- drivers/gpio/gpio-rcar.c | 42 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c index cf41440aff91..d9ab0cd1d205 100644 --- a/drivers/gpio/gpio-rcar.c +++ b/drivers/gpio/gpio-rcar.c @@ -196,6 +196,44 @@ static int gpio_rcar_irq_set_wake(struct irq_data *d, unsigned int on) return 0; } +static void gpio_rcar_irq_bus_lock(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct gpio_rcar_priv *p = gpiochip_get_data(gc); + + pm_runtime_get_sync(&p->pdev->dev); +} + +static void gpio_rcar_irq_bus_sync_unlock(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct gpio_rcar_priv *p = gpiochip_get_data(gc); + + pm_runtime_put(&p->pdev->dev); +} + + +static int gpio_rcar_irq_request_resources(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct gpio_rcar_priv *p = gpiochip_get_data(gc); + int error; + + error = pm_runtime_get_sync(&p->pdev->dev); + if (error < 0) + return error; + + return 0; +} + +static void gpio_rcar_irq_release_resources(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct gpio_rcar_priv *p = gpiochip_get_data(gc); + + pm_runtime_put(&p->pdev->dev); +} + static irqreturn_t gpio_rcar_irq_handler(int irq, void *dev_id) { struct gpio_rcar_priv *p = dev_id; @@ -450,6 +488,10 @@ static int gpio_rcar_probe(struct platform_device *pdev) irq_chip->irq_unmask = gpio_rcar_irq_enable; irq_chip->irq_set_type = gpio_rcar_irq_set_type; irq_chip->irq_set_wake = gpio_rcar_irq_set_wake; + irq_chip->irq_bus_lock = gpio_rcar_irq_bus_lock; + irq_chip->irq_bus_sync_unlock = gpio_rcar_irq_bus_sync_unlock; + irq_chip->irq_request_resources = gpio_rcar_irq_request_resources; + irq_chip->irq_release_resources = gpio_rcar_irq_release_resources; irq_chip->flags = IRQCHIP_SET_TYPE_MASKED | IRQCHIP_MASK_ON_SUSPEND; ret = gpiochip_add_data(gpio_chip, p); From 38e45d02ea9f194b89d6bf41e52ccafc8e2c2b47 Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Tue, 23 Feb 2016 13:03:30 +0100 Subject: [PATCH 196/417] iommu/amd: Fix boot warning when device 00:00.0 is not iommu covered The setup code for the performance counters in the AMD IOMMU driver tests whether the counters can be written. It tests to setup a counter for device 00:00.0, which fails on systems where this particular device is not covered by the IOMMU. Fix this by not relying on device 00:00.0 but only on the IOMMU being present. Cc: stable@vger.kernel.org Signed-off-by: Suravee Suthikulpanit Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu_init.c | 34 ++++++++++++++++++++++------------ 1 file changed, 22 insertions(+), 12 deletions(-) diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 013bdfff2d4d..d06a6d9edbca 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -228,6 +228,10 @@ static int amd_iommu_enable_interrupts(void); static int __init iommu_go_to_state(enum iommu_init_state state); static void init_device_table_dma(void); +static int iommu_pc_get_set_reg_val(struct amd_iommu *iommu, + u8 bank, u8 cntr, u8 fxn, + u64 *value, bool is_write); + static inline void update_last_devid(u16 devid) { if (devid > amd_iommu_last_bdf) @@ -1142,8 +1146,8 @@ static void init_iommu_perf_ctr(struct amd_iommu *iommu) amd_iommu_pc_present = true; /* Check if the performance counters can be written to */ - if ((0 != amd_iommu_pc_get_set_reg_val(0, 0, 0, 0, &val, true)) || - (0 != amd_iommu_pc_get_set_reg_val(0, 0, 0, 0, &val2, false)) || + if ((0 != iommu_pc_get_set_reg_val(iommu, 0, 0, 0, &val, true)) || + (0 != iommu_pc_get_set_reg_val(iommu, 0, 0, 0, &val2, false)) || (val != val2)) { pr_err("AMD-Vi: Unable to write to IOMMU perf counter.\n"); amd_iommu_pc_present = false; @@ -2283,22 +2287,15 @@ u8 amd_iommu_pc_get_max_counters(u16 devid) } EXPORT_SYMBOL(amd_iommu_pc_get_max_counters); -int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn, +static int iommu_pc_get_set_reg_val(struct amd_iommu *iommu, + u8 bank, u8 cntr, u8 fxn, u64 *value, bool is_write) { - struct amd_iommu *iommu; u32 offset; u32 max_offset_lim; - /* Make sure the IOMMU PC resource is available */ - if (!amd_iommu_pc_present) - return -ENODEV; - - /* Locate the iommu associated with the device ID */ - iommu = amd_iommu_rlookup_table[devid]; - /* Check for valid iommu and pc register indexing */ - if (WARN_ON((iommu == NULL) || (fxn > 0x28) || (fxn & 7))) + if (WARN_ON((fxn > 0x28) || (fxn & 7))) return -ENODEV; offset = (u32)(((0x40|bank) << 12) | (cntr << 8) | fxn); @@ -2322,3 +2319,16 @@ int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn, return 0; } EXPORT_SYMBOL(amd_iommu_pc_get_set_reg_val); + +int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn, + u64 *value, bool is_write) +{ + struct amd_iommu *iommu = amd_iommu_rlookup_table[devid]; + + /* Make sure the IOMMU PC resource is available */ + if (!amd_iommu_pc_present || iommu == NULL) + return -ENODEV; + + return iommu_pc_get_set_reg_val(iommu, bank, cntr, fxn, + value, is_write); +} From 358875fd52ab8f00f66328cbf1a1d2486f265829 Mon Sep 17 00:00:00 2001 From: Jay Cornwall Date: Wed, 10 Feb 2016 15:48:01 -0600 Subject: [PATCH 197/417] iommu/amd: Apply workaround for ATS write permission check The AMD Family 15h Models 30h-3Fh (Kaveri) BIOS and Kernel Developer's Guide omitted part of the BIOS IOMMU L2 register setup specification. Without this setup the IOMMU L2 does not fully respect write permissions when handling an ATS translation request. The IOMMU L2 will set PTE dirty bit when handling an ATS translation with write permission request, even when PTE RW bit is clear. This may occur by direct translation (which would cause a PPR) or by prefetch request from the ATC. This is observed in practice when the IOMMU L2 modifies a PTE which maps a pagecache page. The ext4 filesystem driver BUGs when asked to writeback these (non-modified) pages. Enable ATS write permission check in the Kaveri IOMMU L2 if BIOS has not. Signed-off-by: Jay Cornwall Cc: # v3.19+ Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu_init.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index d06a6d9edbca..bf4959f4225b 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -1019,6 +1019,34 @@ static void amd_iommu_erratum_746_workaround(struct amd_iommu *iommu) pci_write_config_dword(iommu->dev, 0xf0, 0x90); } +/* + * Family15h Model 30h-3fh (IOMMU Mishandles ATS Write Permission) + * Workaround: + * BIOS should enable ATS write permission check by setting + * L2_DEBUG_3[AtsIgnoreIWDis](D0F2xF4_x47[0]) = 1b + */ +static void amd_iommu_ats_write_check_workaround(struct amd_iommu *iommu) +{ + u32 value; + + if ((boot_cpu_data.x86 != 0x15) || + (boot_cpu_data.x86_model < 0x30) || + (boot_cpu_data.x86_model > 0x3f)) + return; + + /* Test L2_DEBUG_3[AtsIgnoreIWDis] == 1 */ + value = iommu_read_l2(iommu, 0x47); + + if (value & BIT(0)) + return; + + /* Set L2_DEBUG_3[AtsIgnoreIWDis] = 1 */ + iommu_write_l2(iommu, 0x47, value | BIT(0)); + + pr_info("AMD-Vi: Applying ATS write check workaround for IOMMU at %s\n", + dev_name(&iommu->dev->dev)); +} + /* * This function clues the initialization function for one IOMMU * together and also allocates the command buffer and programs the @@ -1288,6 +1316,7 @@ static int iommu_init_pci(struct amd_iommu *iommu) } amd_iommu_erratum_746_workaround(iommu); + amd_iommu_ats_write_check_workaround(iommu); iommu->iommu_dev = iommu_device_create(&iommu->dev->dev, iommu, amd_iommu_groups, "ivhd%d", From bf70e5513dfea29c3682e7eb3dbb45f0723bac09 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Thu, 25 Feb 2016 01:58:12 -0800 Subject: [PATCH 198/417] x86/mm: Fix slow_virt_to_phys() for X86_PAE again "d1cd12108346: x86, pageattr: Prevent overflow in slow_virt_to_phys() for X86_PAE" was unintentionally removed by the recent "34437e67a672: x86/mm: Fix slow_virt_to_phys() to handle large PAT bit". And, the variable 'phys_addr' was defined as "unsigned long" by mistake -- it should be "phys_addr_t". As a result, Hyper-V network driver in 32-PAE Linux guest can't work again. Fixes: commit 34437e67a672: "x86/mm: Fix slow_virt_to_phys() to handle large PAT bit" Signed-off-by: Dexuan Cui Reviewed-by: Toshi Kani Cc: olaf@aepfle.de Cc: gregkh@linuxfoundation.org Cc: jasowang@redhat.com Cc: driverdev-devel@linuxdriverproject.org Cc: linux-mm@kvack.org Cc: apw@canonical.com Cc: Andrew Morton Cc: K. Y. Srinivasan Cc: Haiyang Zhang Link: http://lkml.kernel.org/r/1456394292-9030-1-git-send-email-decui@microsoft.com Signed-off-by: Thomas Gleixner --- arch/x86/mm/pageattr.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 2440814b0069..9cf96d82147a 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -419,24 +419,30 @@ pmd_t *lookup_pmd_address(unsigned long address) phys_addr_t slow_virt_to_phys(void *__virt_addr) { unsigned long virt_addr = (unsigned long)__virt_addr; - unsigned long phys_addr, offset; + phys_addr_t phys_addr; + unsigned long offset; enum pg_level level; pte_t *pte; pte = lookup_address(virt_addr, &level); BUG_ON(!pte); + /* + * pXX_pfn() returns unsigned long, which must be cast to phys_addr_t + * before being left-shifted PAGE_SHIFT bits -- this trick is to + * make 32-PAE kernel work correctly. + */ switch (level) { case PG_LEVEL_1G: - phys_addr = pud_pfn(*(pud_t *)pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pud_pfn(*(pud_t *)pte) << PAGE_SHIFT; offset = virt_addr & ~PUD_PAGE_MASK; break; case PG_LEVEL_2M: - phys_addr = pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT; offset = virt_addr & ~PMD_PAGE_MASK; break; default: - phys_addr = pte_pfn(*pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; offset = virt_addr & ~PAGE_MASK; } From 44248affb5d82d32cdb58a92a94ce191d4ddee60 Mon Sep 17 00:00:00 2001 From: Han Xu Date: Thu, 18 Feb 2016 03:55:15 +0000 Subject: [PATCH 199/417] MAINTAINERS: add maintainer entry for FREESCALE GPMI NAND driver Add a maintainer entry for FREESCALE GPMI NAND driver and add myself as a maintainer. Signed-off-by: Han Xu Acked-by: Huang Shijie Signed-off-by: Brian Norris --- MAINTAINERS | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index ce4a0d6e3d64..0db5eb97f70d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4522,6 +4522,12 @@ L: linuxppc-dev@lists.ozlabs.org S: Maintained F: drivers/dma/fsldma.* +FREESCALE GPMI NAND DRIVER +M: Han Xu +L: linux-mtd@lists.infradead.org +S: Maintained +F: drivers/mtd/nand/gpmi-nand/* + FREESCALE I2C CPM DRIVER M: Jochen Friedrich L: linuxppc-dev@lists.ozlabs.org From 65c38aa653c14df49e19faad74bd375f36e61c57 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 23 Feb 2016 10:10:26 -0800 Subject: [PATCH 200/417] net: vrf: Remove direct access to skb->data Nik pointed that the VRF driver should be using skb_header_pointer instead of accessing skb->data and bits beyond directly which can be garbage. Fixes: 35402e313663 ("net: Add IPv6 support to VRF device") Cc: Nikolay Aleksandrov Signed-off-by: David Ahern Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- drivers/net/vrf.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 66addb7a7911..bdcf617a9d52 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -104,20 +104,23 @@ static struct dst_ops vrf_dst_ops = { #if IS_ENABLED(CONFIG_IPV6) static bool check_ipv6_frame(const struct sk_buff *skb) { - const struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb->data; - size_t hlen = sizeof(*ipv6h); + const struct ipv6hdr *ipv6h; + struct ipv6hdr _ipv6h; bool rc = true; - if (skb->len < hlen) + ipv6h = skb_header_pointer(skb, 0, sizeof(_ipv6h), &_ipv6h); + if (!ipv6h) goto out; if (ipv6h->nexthdr == NEXTHDR_ICMP) { const struct icmp6hdr *icmph; + struct icmp6hdr _icmph; - if (skb->len < hlen + sizeof(*icmph)) + icmph = skb_header_pointer(skb, sizeof(_ipv6h), + sizeof(_icmph), &_icmph); + if (!icmph) goto out; - icmph = (struct icmp6hdr *)(skb->data + sizeof(*ipv6h)); switch (icmph->icmp6_type) { case NDISC_ROUTER_SOLICITATION: case NDISC_ROUTER_ADVERTISEMENT: From 2b70bad23c89b121a3e4a00f8968d14ebb78887d Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Tue, 23 Feb 2016 19:23:23 +0000 Subject: [PATCH 201/417] net: qca_spi: Don't clear IFF_BROADCAST Currently qcaspi_netdev_setup accidentally clears IFF_BROADCAST. So fix this by keeping the flags from ether_setup. Reported-by: Michael Heimpold Signed-off-by: Stefan Wahren Fixes: 291ab06ecf67 (net: qualcomm: new Ethernet over SPI driver for QCA7000) Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/qca_spi.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index 689a4a5c8dcf..f2ee3e5fb167 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -811,7 +811,6 @@ qcaspi_netdev_setup(struct net_device *dev) dev->netdev_ops = &qcaspi_netdev_ops; qcaspi_set_ethtool_ops(dev); dev->watchdog_timeo = QCASPI_TX_TIMEOUT; - dev->flags = IFF_MULTICAST; dev->tx_queue_len = 100; qca = netdev_priv(dev); From a4690afeb0d2d7ba4d60dfa98a89f3bb1ce60ecd Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Tue, 23 Feb 2016 19:23:24 +0000 Subject: [PATCH 202/417] net: qca_spi: clear IFF_TX_SKB_SHARING ether_setup sets IFF_TX_SKB_SHARING but this is not supported by qca_spi as it modifies the skb on xmit. Signed-off-by: Stefan Wahren Fixes: 291ab06ecf67 (net: qualcomm: new Ethernet over SPI driver for QCA7000) Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/qca_spi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index f2ee3e5fb167..1ef03939d25f 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -811,6 +811,7 @@ qcaspi_netdev_setup(struct net_device *dev) dev->netdev_ops = &qcaspi_netdev_ops; qcaspi_set_ethtool_ops(dev); dev->watchdog_timeo = QCASPI_TX_TIMEOUT; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->tx_queue_len = 100; qca = netdev_priv(dev); From 9b368814b336b0a1a479135eb2815edbc00efd3c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Linus=20L=C3=BCssing?= Date: Wed, 24 Feb 2016 04:21:42 +0100 Subject: [PATCH 203/417] net: fix bridge multicast packet checksum validation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We need to update the skb->csum after pulling the skb, otherwise an unnecessary checksum (re)computation can ocure for IGMP/MLD packets in the bridge code. Additionally this fixes the following splats for network devices / bridge ports with support for and enabled RX checksum offloading: [...] [ 43.986968] eth0: hw csum failure [ 43.990344] CPU: 3 PID: 0 Comm: swapper/3 Not tainted 4.4.0 #2 [ 43.996193] Hardware name: BCM2709 [ 43.999647] [<800204e0>] (unwind_backtrace) from [<8001cf14>] (show_stack+0x10/0x14) [ 44.007432] [<8001cf14>] (show_stack) from [<801ab614>] (dump_stack+0x80/0x90) [ 44.014695] [<801ab614>] (dump_stack) from [<802e4548>] (__skb_checksum_complete+0x6c/0xac) [ 44.023090] [<802e4548>] (__skb_checksum_complete) from [<803a055c>] (ipv6_mc_validate_checksum+0x104/0x178) [ 44.032959] [<803a055c>] (ipv6_mc_validate_checksum) from [<802e111c>] (skb_checksum_trimmed+0x130/0x188) [ 44.042565] [<802e111c>] (skb_checksum_trimmed) from [<803a06e8>] (ipv6_mc_check_mld+0x118/0x338) [ 44.051501] [<803a06e8>] (ipv6_mc_check_mld) from [<803b2c98>] (br_multicast_rcv+0x5dc/0xd00) [ 44.060077] [<803b2c98>] (br_multicast_rcv) from [<803aa510>] (br_handle_frame_finish+0xac/0x51c) [...] Fixes: 9afd85c9e455 ("net: Export IGMP/MLD message validation code") Reported-by: Álvaro Fernández Rojas Signed-off-by: Linus Lüssing Signed-off-by: David S. Miller --- net/core/skbuff.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 5bf88f58bee7..8616d1147c93 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2947,6 +2947,24 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page, } EXPORT_SYMBOL_GPL(skb_append_pagefrags); +/** + * skb_push_rcsum - push skb and update receive checksum + * @skb: buffer to update + * @len: length of data pulled + * + * This function performs an skb_push on the packet and updates + * the CHECKSUM_COMPLETE checksum. It should be used on + * receive path processing instead of skb_push unless you know + * that the checksum difference is zero (e.g., a valid IP header) + * or you are setting ip_summed to CHECKSUM_NONE. + */ +static unsigned char *skb_push_rcsum(struct sk_buff *skb, unsigned len) +{ + skb_push(skb, len); + skb_postpush_rcsum(skb, skb->data, len); + return skb->data; +} + /** * skb_pull_rcsum - pull skb and update receive checksum * @skb: buffer to update @@ -4084,9 +4102,9 @@ struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, if (!pskb_may_pull(skb_chk, offset)) goto err; - __skb_pull(skb_chk, offset); + skb_pull_rcsum(skb_chk, offset); ret = skb_chkf(skb_chk); - __skb_push(skb_chk, offset); + skb_push_rcsum(skb_chk, offset); if (ret) goto err; From f09cf4b7832d029fb22d8f476eac12fc27dde61f Mon Sep 17 00:00:00 2001 From: Chun-Hao Lin Date: Wed, 24 Feb 2016 14:18:42 +0800 Subject: [PATCH 204/417] r8169:fix "rtl_counters_cond == 1 (loop: 1000, delay: 10)" log spam. There will be a log spam when there is no cable plugged. Please refer to following links. https://bugzilla.kernel.org/show_bug.cgi?id=104351 https://bugzilla.kernel.org/show_bug.cgi?id=107421 This issue is caused by runtime power management. When there is no cable plugged, the driver will be suspend (runtime suspend) by OS and NIC will be put into the D3 state. During this time, if OS call rtl8169_get_stats64() to dump tally counter, because NIC is in D3 state, the register value read by driver will return all 0xff. This will let driver think tally counter flag is not toggled and then sends the warning message "rtl_counters_cond == 1 (loop: 1000, delay: 10)" to kernel log. For fixing this issue, 1.add checking driver's pm runtime status in rtl8169_get_stats64(). 2.dump tally counter before going runtime suspend for counter accuracy in runtime suspend. Signed-off-by: Chunhao Lin Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/r8169.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 537974cfd427..4caeacb45136 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -7730,10 +7730,13 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct rtl8169_private *tp = netdev_priv(dev); void __iomem *ioaddr = tp->mmio_addr; + struct pci_dev *pdev = tp->pci_dev; struct rtl8169_counters *counters = tp->counters; unsigned int start; - if (netif_running(dev)) + pm_runtime_get_noresume(&pdev->dev); + + if (netif_running(dev) && pm_runtime_active(&pdev->dev)) rtl8169_rx_missed(dev, ioaddr); do { @@ -7761,7 +7764,8 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) * Fetch additonal counter values missing in stats collected by driver * from tally counters. */ - rtl8169_update_counters(dev); + if (pm_runtime_active(&pdev->dev)) + rtl8169_update_counters(dev); /* * Subtract values fetched during initalization. @@ -7774,6 +7778,8 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->tx_aborted_errors = le16_to_cpu(counters->tx_aborted) - le16_to_cpu(tp->tc_offset.tx_aborted); + pm_runtime_put_noidle(&pdev->dev); + return stats; } @@ -7853,6 +7859,10 @@ static int rtl8169_runtime_suspend(struct device *device) rtl8169_net_suspend(dev); + /* Update counters before going runtime suspend */ + rtl8169_rx_missed(dev, tp->mmio_addr); + rtl8169_update_counters(dev); + return 0; } From 4c0b6eaf373a5323f03a3a20c42fc435715b073d Mon Sep 17 00:00:00 2001 From: Sunil Goutham Date: Wed, 24 Feb 2016 16:40:50 +0530 Subject: [PATCH 205/417] net: thunderx: Fix for Qset error due to CQ full On Thunderx pass 1.x and pass2 due to a HW errata default CQ DROP_LEVEL of 0x80 is not sufficient to avoid CQ_WR_FULL Qset error when packets are being received at >20Mpps resulting in complete stall of packet reception. This patch will configure it to 0x100 which is what is expected by HW on Thunderx. On future passes of thunderx and other chips HW default/reset value will be 0x100 or higher hence not overwritten. Signed-off-by: Jerin Jacob Signed-off-by: Sunil Goutham Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/thunder/nic.h | 9 +++++++++ drivers/net/ethernet/cavium/thunder/nic_main.c | 6 ++++++ drivers/net/ethernet/cavium/thunder/nic_reg.h | 2 +- 3 files changed, 16 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h index 688828865c48..34e9acea8747 100644 --- a/drivers/net/ethernet/cavium/thunder/nic.h +++ b/drivers/net/ethernet/cavium/thunder/nic.h @@ -116,6 +116,15 @@ #define NIC_PF_INTR_ID_MBOX0 8 #define NIC_PF_INTR_ID_MBOX1 9 +/* Minimum FIFO level before all packets for the CQ are dropped + * + * This value ensures that once a packet has been "accepted" + * for reception it will not get dropped due to non-availability + * of CQ descriptor. An errata in HW mandates this value to be + * atleast 0x100. + */ +#define NICPF_CQM_MIN_DROP_LEVEL 0x100 + /* Global timer for CQ timer thresh interrupts * Calculated for SCLK of 700Mhz * value written should be a 1/16th of what is expected diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index 4dded90076c8..95f17f8cadac 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -304,6 +304,7 @@ static void nic_set_lmac_vf_mapping(struct nicpf *nic) static void nic_init_hw(struct nicpf *nic) { int i; + u64 cqm_cfg; /* Enable NIC HW block */ nic_reg_write(nic, NIC_PF_CFG, 0x3); @@ -340,6 +341,11 @@ static void nic_init_hw(struct nicpf *nic) /* Enable VLAN ethertype matching and stripping */ nic_reg_write(nic, NIC_PF_RX_ETYPE_0_7, (2 << 19) | (ETYPE_ALG_VLAN_STRIP << 16) | ETH_P_8021Q); + + /* Check if HW expected value is higher (could be in future chips) */ + cqm_cfg = nic_reg_read(nic, NIC_PF_CQM_CFG); + if (cqm_cfg < NICPF_CQM_MIN_DROP_LEVEL) + nic_reg_write(nic, NIC_PF_CQM_CFG, NICPF_CQM_MIN_DROP_LEVEL); } /* Channel parse index configuration */ diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h index dd536be20193..afb10e326b4f 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_reg.h +++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h @@ -21,7 +21,7 @@ #define NIC_PF_TCP_TIMER (0x0060) #define NIC_PF_BP_CFG (0x0080) #define NIC_PF_RRM_CFG (0x0088) -#define NIC_PF_CQM_CF (0x00A0) +#define NIC_PF_CQM_CFG (0x00A0) #define NIC_PF_CNM_CF (0x00A8) #define NIC_PF_CNM_STATUS (0x00B0) #define NIC_PF_CQ_AVG_CFG (0x00C0) From 4ee34ea3a12396f35b26d90a094c75db95080baa Mon Sep 17 00:00:00 2001 From: Harvey Hunt Date: Wed, 24 Feb 2016 15:16:43 +0000 Subject: [PATCH 206/417] libata: Align ata_device's id on a cacheline The id buffer in ata_device is a DMA target, but it isn't explicitly cacheline aligned. Due to this, adjacent fields can be overwritten with stale data from memory on non coherent architectures. As a result, the kernel is sometimes unable to communicate with an ATA device. Fix this by ensuring that the id buffer is cacheline aligned. This issue is similar to that fixed by Commit 84bda12af31f ("libata: align ap->sector_buf"). Signed-off-by: Harvey Hunt Cc: linux-kernel@vger.kernel.org Cc: # 2.6.18 Signed-off-by: Tejun Heo --- include/linux/libata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/libata.h b/include/linux/libata.h index bec2abbd7ab2..2c4ebef79d0c 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -720,7 +720,7 @@ struct ata_device { union { u16 id[ATA_ID_WORDS]; /* IDENTIFY xxx DEVICE data */ u32 gscr[SATA_PMP_GSCR_DWORDS]; /* PMP GSCR block */ - }; + } ____cacheline_aligned; /* DEVSLP Timing Variables from Identify Device Data Log */ u8 devslp_timing[ATA_LOG_DEVSLP_SIZE]; From e9a2d81b1761093386a0bb8a4f51642ac785ef63 Mon Sep 17 00:00:00 2001 From: Maximilain Schneider Date: Tue, 23 Feb 2016 01:17:28 +0000 Subject: [PATCH 207/417] can: gs_usb: fixed disconnect bug by removing erroneous use of kfree() gs_destroy_candev() erroneously calls kfree() on a struct gs_can *, which is allocated through alloc_candev() and should instead be freed using free_candev() alone. The inappropriate use of kfree() causes the kernel to hang when gs_destroy_candev() is called. Only the struct gs_usb * which is allocated through kzalloc() should be freed using kfree() when the device is disconnected. Signed-off-by: Maximilian Schneider Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/gs_usb.c | 24 +++++++++++------------- 1 file changed, 11 insertions(+), 13 deletions(-) diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 5eee62badf45..cbc99d5649af 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -826,9 +826,8 @@ static struct gs_can *gs_make_candev(unsigned int channel, struct usb_interface static void gs_destroy_candev(struct gs_can *dev) { unregister_candev(dev->netdev); - free_candev(dev->netdev); usb_kill_anchored_urbs(&dev->tx_submitted); - kfree(dev); + free_candev(dev->netdev); } static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) @@ -913,12 +912,15 @@ static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id * for (i = 0; i < icount; i++) { dev->canch[i] = gs_make_candev(i, intf); if (IS_ERR_OR_NULL(dev->canch[i])) { + /* save error code to return later */ + rc = PTR_ERR(dev->canch[i]); + /* on failure destroy previously created candevs */ icount = i; - for (i = 0; i < icount; i++) { + for (i = 0; i < icount; i++) gs_destroy_candev(dev->canch[i]); - dev->canch[i] = NULL; - } + + usb_kill_anchored_urbs(&dev->rx_submitted); kfree(dev); return rc; } @@ -939,16 +941,12 @@ static void gs_usb_disconnect(struct usb_interface *intf) return; } - for (i = 0; i < GS_MAX_INTF; i++) { - struct gs_can *can = dev->canch[i]; - - if (!can) - continue; - - gs_destroy_candev(can); - } + for (i = 0; i < GS_MAX_INTF; i++) + if (dev->canch[i]) + gs_destroy_candev(dev->canch[i]); usb_kill_anchored_urbs(&dev->rx_submitted); + kfree(dev); } static const struct usb_device_id gs_usb_table[] = { From 473f414564528a819f0c2bb6b4bf26366b64c9ab Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 23 Feb 2016 15:54:47 +0100 Subject: [PATCH 208/417] ALSA: hda - Loop interrupt handling until really cleared Currently the interrupt handler of HD-audio driver assumes that no irq update is needed while processing the irq. But in reality, it has been confirmed that the HW irq is issued even during the irq handling. Since we clear the irq status at the beginning, process the interrupt, then exits from the handler, the lately issued interrupt is left untouched without being properly processed. This patch changes the interrupt handler code to loop over the check-and-process. The handler tries repeatedly as long as the IRQ status are turned on, and either stream or CORB/RIRB is handled. For checking the stream handling, snd_hdac_bus_handle_stream_irq() returns a value indicating the stream indices bits. Other than that, the change is only in the irq handler itself. Reported-by: Libin Yang Cc: Signed-off-by: Takashi Iwai --- include/sound/hdaudio.h | 2 +- sound/hda/hdac_controller.c | 7 +++++- sound/pci/hda/hda_controller.c | 45 +++++++++++++++++++--------------- 3 files changed, 32 insertions(+), 22 deletions(-) diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index e2b712c90d3f..c21c38ce7450 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -343,7 +343,7 @@ void snd_hdac_bus_enter_link_reset(struct hdac_bus *bus); void snd_hdac_bus_exit_link_reset(struct hdac_bus *bus); void snd_hdac_bus_update_rirb(struct hdac_bus *bus); -void snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status, +int snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status, void (*ack)(struct hdac_bus *, struct hdac_stream *)); diff --git a/sound/hda/hdac_controller.c b/sound/hda/hdac_controller.c index b5a17cb510a0..8c486235c905 100644 --- a/sound/hda/hdac_controller.c +++ b/sound/hda/hdac_controller.c @@ -426,18 +426,22 @@ EXPORT_SYMBOL_GPL(snd_hdac_bus_stop_chip); * @bus: HD-audio core bus * @status: INTSTS register value * @ask: callback to be called for woken streams + * + * Returns the bits of handled streams, or zero if no stream is handled. */ -void snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status, +int snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status, void (*ack)(struct hdac_bus *, struct hdac_stream *)) { struct hdac_stream *azx_dev; u8 sd_status; + int handled = 0; list_for_each_entry(azx_dev, &bus->stream_list, list) { if (status & azx_dev->sd_int_sta_mask) { sd_status = snd_hdac_stream_readb(azx_dev, SD_STS); snd_hdac_stream_writeb(azx_dev, SD_STS, SD_INT_MASK); + handled |= 1 << azx_dev->index; if (!azx_dev->substream || !azx_dev->running || !(sd_status & SD_INT_COMPLETE)) continue; @@ -445,6 +449,7 @@ void snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status, ack(bus, azx_dev); } } + return handled; } EXPORT_SYMBOL_GPL(snd_hdac_bus_handle_stream_irq); diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c index 37cf9cee9835..27de8015717d 100644 --- a/sound/pci/hda/hda_controller.c +++ b/sound/pci/hda/hda_controller.c @@ -930,6 +930,8 @@ irqreturn_t azx_interrupt(int irq, void *dev_id) struct azx *chip = dev_id; struct hdac_bus *bus = azx_bus(chip); u32 status; + bool active, handled = false; + int repeat = 0; /* count for avoiding endless loop */ #ifdef CONFIG_PM if (azx_has_pm_runtime(chip)) @@ -939,33 +941,36 @@ irqreturn_t azx_interrupt(int irq, void *dev_id) spin_lock(&bus->reg_lock); - if (chip->disabled) { - spin_unlock(&bus->reg_lock); - return IRQ_NONE; - } + if (chip->disabled) + goto unlock; - status = azx_readl(chip, INTSTS); - if (status == 0 || status == 0xffffffff) { - spin_unlock(&bus->reg_lock); - return IRQ_NONE; - } + do { + status = azx_readl(chip, INTSTS); + if (status == 0 || status == 0xffffffff) + break; - snd_hdac_bus_handle_stream_irq(bus, status, stream_update); + handled = true; + active = false; + if (snd_hdac_bus_handle_stream_irq(bus, status, stream_update)) + active = true; - /* clear rirb int */ - status = azx_readb(chip, RIRBSTS); - if (status & RIRB_INT_MASK) { - if (status & RIRB_INT_RESPONSE) { - if (chip->driver_caps & AZX_DCAPS_CTX_WORKAROUND) - udelay(80); - snd_hdac_bus_update_rirb(bus); + /* clear rirb int */ + status = azx_readb(chip, RIRBSTS); + if (status & RIRB_INT_MASK) { + active = true; + if (status & RIRB_INT_RESPONSE) { + if (chip->driver_caps & AZX_DCAPS_CTX_WORKAROUND) + udelay(80); + snd_hdac_bus_update_rirb(bus); + } + azx_writeb(chip, RIRBSTS, RIRB_INT_MASK); } - azx_writeb(chip, RIRBSTS, RIRB_INT_MASK); - } + } while (active && ++repeat < 10); + unlock: spin_unlock(&bus->reg_lock); - return IRQ_HANDLED; + return IRQ_RETVAL(handled); } EXPORT_SYMBOL_GPL(azx_interrupt); From 10da848f67a7e7152bf7cbe332e4c92d71a990d2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 25 Feb 2016 21:57:43 +0100 Subject: [PATCH 209/417] ssb: host_soc depends on sprom Drivers that use the SSB sprom functionality typically 'select SSB_SPROM' from Kconfig, but CONFIG_SSB_HOST_SOC misses this, which results in a build failure unless at least one of the other drivers that selects it is enabled: drivers/built-in.o: In function `ssb_host_soc_get_invariants': (.text+0x459494): undefined reference to `ssb_fill_sprom_with_fallback' This adds the same select statement that is used elsewhere. Signed-off-by: Arnd Bergmann Fixes: 541c9a84cd85 ("ssb: pick SoC invariants code from MIPS BCM47xx arch") Signed-off-by: Kalle Valo --- drivers/ssb/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/ssb/Kconfig b/drivers/ssb/Kconfig index 0c675861623f..d8e4219c2324 100644 --- a/drivers/ssb/Kconfig +++ b/drivers/ssb/Kconfig @@ -83,6 +83,7 @@ config SSB_SDIOHOST config SSB_HOST_SOC bool "Support for SSB bus on SoC" depends on SSB && BCM47XX_NVRAM + select SSB_SPROM help Host interface for a SSB directly mapped into memory. This is for some Broadcom SoCs from the BCM47xx and BCM53xx lines. From a1e533ec07d583d01349ef13c0c965b8633e1b91 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Mon, 15 Feb 2016 18:41:33 +0000 Subject: [PATCH 210/417] fbcon: set a default value to blink interval Since commit 27a4c827c34ac4256a190cc9d24607f953c1c459 fbcon: use the cursor blink interval provided by vt two attempts have been made at fixing a possible hang caused by cursor_timer_handler. That function registers a timer to be triggered at "jiffies + fbcon_ops.cur_blink_jiffies". A new case had been encountered during initialisation of clcd-pl11x: fbcon_fb_registered do_fbcon_takeover -> do_register_con_driver fbcon_startup (A) add_cursor_timer (with cur_blink_jiffies = 0) -> do_bind_con_driver visual_init fbcon_init (B) cur_blink_jiffies = msecs_to_jiffies(vc->vc_cur_blink_ms); If we take an softirq anywhere between A and B (and we do), cursor_timer_handler executes indefinitely. Instead of patching all possible paths that lead to this case one at a time, fix the issue at the source and initialise cur_blink_jiffies to 200ms when allocating fbcon_ops. This was its default value before aforesaid commit. fbcon_cursor or fbcon_init will refine this value downstream. Signed-off-by: Jean-Philippe Brucker Cc: # v4.2 Tested-by: Scot Doyle Signed-off-by: Tomi Valkeinen --- drivers/video/console/fbcon.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c index 92f394927f24..6e92917ba77a 100644 --- a/drivers/video/console/fbcon.c +++ b/drivers/video/console/fbcon.c @@ -709,6 +709,7 @@ static int con2fb_acquire_newinfo(struct vc_data *vc, struct fb_info *info, } if (!err) { + ops->cur_blink_jiffies = HZ / 5; info->fbcon_par = ops; if (vc) @@ -956,6 +957,7 @@ static const char *fbcon_startup(void) ops->currcon = -1; ops->graphics = 1; ops->cur_rotate = -1; + ops->cur_blink_jiffies = HZ / 5; info->fbcon_par = ops; p->con_rotate = initial_rotation; set_blitting_type(vc, info); From 70e4da7a8ff62f2775337b705f45c804bb450454 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Fri, 26 Feb 2016 12:28:40 +0100 Subject: [PATCH 211/417] KVM: x86: fix root cause for missed hardware breakpoints Commit 172b2386ed16 ("KVM: x86: fix missed hardware breakpoints", 2016-02-10) worked around a case where the debug registers are not loaded correctly on preemption and on the first entry to KVM_RUN. However, Xiao Guangrong pointed out that the root cause must be that KVM_DEBUGREG_BP_ENABLED is not being set correctly. This can indeed happen due to the lazy debug exit mechanism, which does not call kvm_update_dr7. Fix it by replacing the existing loop (more or less equivalent to kvm_update_dr0123) with calls to all the kvm_update_dr* functions. Cc: stable@vger.kernel.org # 4.1+ Fixes: 172b2386ed16a9143d9a456aae5ec87275c61489 Reviewed-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f4891f2ece23..eaf6ee8c28b8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2752,7 +2752,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) } kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); - vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD; } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) @@ -6619,12 +6618,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * KVM_DEBUGREG_WONT_EXIT again. */ if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) { - int i; - WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP); kvm_x86_ops->sync_dirty_debug_regs(vcpu); - for (i = 0; i < KVM_NR_DB_REGS; i++) - vcpu->arch.eff_db[i] = vcpu->arch.db[i]; + kvm_update_dr0123(vcpu); + kvm_update_dr6(vcpu); + kvm_update_dr7(vcpu); + vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } /* From dfd55ad85e4a7fbaa82df12467515ac3c81e8a3e Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 26 Feb 2016 17:57:13 +0100 Subject: [PATCH 212/417] arm64: vmemmap: use virtual projection of linear region Commit dd006da21646 ("arm64: mm: increase VA range of identity map") made some changes to the memory mapping code to allow physical memory to reside at an offset that exceeds the size of the virtual mapping. However, since the size of the vmemmap area is proportional to the size of the VA area, but it is populated relative to the physical space, we may end up with the struct page array being mapped outside of the vmemmap region. For instance, on my Seattle A0 box, I can see the following output in the dmesg log. vmemmap : 0xffffffbdc0000000 - 0xffffffbfc0000000 ( 8 GB maximum) 0xffffffbfc0000000 - 0xffffffbfd0000000 ( 256 MB actual) We can fix this by deciding that the vmemmap region is not a projection of the physical space, but of the virtual space above PAGE_OFFSET, i.e., the linear region. This way, we are guaranteed that the vmemmap region is of sufficient size, and we can even reduce the size by half. Cc: Signed-off-by: Ard Biesheuvel Signed-off-by: Will Deacon --- arch/arm64/include/asm/pgtable.h | 7 ++++--- arch/arm64/mm/init.c | 4 ++-- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index bf464de33f52..f50608674580 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -34,13 +34,13 @@ /* * VMALLOC and SPARSEMEM_VMEMMAP ranges. * - * VMEMAP_SIZE: allows the whole VA space to be covered by a struct page array + * VMEMAP_SIZE: allows the whole linear region to be covered by a struct page array * (rounded up to PUD_SIZE). * VMALLOC_START: beginning of the kernel VA space * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space, * fixed mappings and modules */ -#define VMEMMAP_SIZE ALIGN((1UL << (VA_BITS - PAGE_SHIFT)) * sizeof(struct page), PUD_SIZE) +#define VMEMMAP_SIZE ALIGN((1UL << (VA_BITS - PAGE_SHIFT - 1)) * sizeof(struct page), PUD_SIZE) #ifndef CONFIG_KASAN #define VMALLOC_START (VA_START) @@ -51,7 +51,8 @@ #define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K) -#define vmemmap ((struct page *)(VMALLOC_END + SZ_64K)) +#define VMEMMAP_START (VMALLOC_END + SZ_64K) +#define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)) #define FIRST_USER_ADDRESS 0UL diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index f3b061e67bfe..7802f216a67a 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -319,8 +319,8 @@ void __init mem_init(void) #endif MLG(VMALLOC_START, VMALLOC_END), #ifdef CONFIG_SPARSEMEM_VMEMMAP - MLG((unsigned long)vmemmap, - (unsigned long)vmemmap + VMEMMAP_SIZE), + MLG(VMEMMAP_START, + VMEMMAP_START + VMEMMAP_SIZE), MLM((unsigned long)virt_to_page(PAGE_OFFSET), (unsigned long)virt_to_page(high_memory)), #endif From 472681d57a5dde7c6d16b05469be57f1c4ed9d99 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?MINOURA=20Makoto=20/=20=E7=AE=95=E6=B5=A6=20=E7=9C=9F?= Date: Thu, 25 Feb 2016 14:20:48 +0900 Subject: [PATCH 213/417] net: ndo_fdb_dump should report -EMSGSIZE to rtnl_fdb_dump. When the send skbuff reaches the end, nlmsg_put and friends returns -EMSGSIZE but it is silently thrown away in ndo_fdb_dump. It is called within a for_each_netdev loop and the first fdb entry of a following netdev could fit in the remaining skbuff. This breaks the mechanism of cb->args[0] and idx to keep track of the entries that are already dumped, which results missing entries in bridge fdb show command. Signed-off-by: Minoura Makoto Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 4 +++- net/bridge/br_fdb.c | 15 ++++++++++----- net/core/rtnetlink.c | 6 ++++++ net/switchdev/switchdev.c | 5 ++++- 4 files changed, 23 insertions(+), 7 deletions(-) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index e6944b29588e..b601139a145a 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -931,8 +931,10 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, rd); - if (err < 0) + if (err < 0) { + cb->args[1] = err; goto out; + } skip: ++idx; } diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 82e3e9705017..dcea4f4c62b3 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -723,6 +723,8 @@ int br_fdb_dump(struct sk_buff *skb, struct net_bridge_fdb_entry *f; hlist_for_each_entry_rcu(f, &br->hash[i], hlist) { + int err; + if (idx < cb->args[0]) goto skip; @@ -741,12 +743,15 @@ int br_fdb_dump(struct sk_buff *skb, if (!filter_dev && f->dst) goto skip; - if (fdb_fill_info(skb, br, f, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWNEIGH, - NLM_F_MULTI) < 0) + err = fdb_fill_info(skb, br, f, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNEIGH, + NLM_F_MULTI); + if (err < 0) { + cb->args[1] = err; break; + } skip: ++idx; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d735e854f916..8261d95dd846 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2911,6 +2911,7 @@ int ndo_dflt_fdb_dump(struct sk_buff *skb, nlmsg_populate_fdb(skb, cb, dev, &idx, &dev->mc); out: netif_addr_unlock_bh(dev); + cb->args[1] = err; return idx; } EXPORT_SYMBOL(ndo_dflt_fdb_dump); @@ -2944,6 +2945,7 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) ops = br_dev->netdev_ops; } + cb->args[1] = 0; for_each_netdev(net, dev) { if (brport_idx && (dev->ifindex != brport_idx)) continue; @@ -2971,12 +2973,16 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) idx = cops->ndo_fdb_dump(skb, cb, br_dev, dev, idx); } + if (cb->args[1] == -EMSGSIZE) + break; if (dev->netdev_ops->ndo_fdb_dump) idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, NULL, idx); else idx = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx); + if (cb->args[1] == -EMSGSIZE) + break; cops = NULL; } diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 47f7da58a7f0..8b5833c1ff2e 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -1093,8 +1093,11 @@ int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, .cb = cb, .idx = idx, }; + int err; - switchdev_port_obj_dump(dev, &dump.fdb.obj, switchdev_port_fdb_dump_cb); + err = switchdev_port_obj_dump(dev, &dump.fdb.obj, + switchdev_port_fdb_dump_cb); + cb->args[1] = err; return dump.idx; } EXPORT_SYMBOL_GPL(switchdev_port_fdb_dump); From 9bf148cb0812595bfdf5100bd2c07e9bec9c6ef5 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 26 Feb 2016 18:55:31 +0000 Subject: [PATCH 214/417] x86/mpx: Fix off-by-one comparison with nr_registers In the unlikely event that regno == nr_registers then we get an array overrun on regoff because the invalid register check is currently off-by-one. Fix this with a check that regno is >= nr_registers instead. Detected with static analysis using CoverityScan. Fixes: fcc7ffd67991 "x86, mpx: Decode MPX instruction to get bound violation information" Signed-off-by: Colin Ian King Acked-by: Dave Hansen Cc: Borislav Petkov Cc: "Kirill A . Shutemov" Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1456512931-3388-1-git-send-email-colin.king@canonical.com Signed-off-by: Thomas Gleixner --- arch/x86/mm/mpx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index b2fd67da1701..ef05755a1900 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -123,7 +123,7 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs, break; } - if (regno > nr_registers) { + if (regno >= nr_registers) { WARN_ONCE(1, "decoded an instruction with an invalid register"); return -EINVAL; } From e1cd3911170eda37fd9501e81ee1c2eb63803fd0 Mon Sep 17 00:00:00 2001 From: jiangyiwen Date: Tue, 16 Feb 2016 20:14:13 +0800 Subject: [PATCH 215/417] SCSI: Free resources when we return BLKPREP_INVALID When called scsi_prep_fn return BLKPREP_INVALID, we should use the same code with BLKPREP_KILL in scsi_prep_return. Signed-off-by: Yiwen Jiang Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_lib.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index fa6b2c4eb7a2..8c6e31874171 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1344,6 +1344,7 @@ scsi_prep_return(struct request_queue *q, struct request *req, int ret) switch (ret) { case BLKPREP_KILL: + case BLKPREP_INVALID: req->errors = DID_NO_CONNECT << 16; /* release the command and kill it */ if (req->special) { From 21b81716c6bff24cda52dc75588455f879ddbfe9 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Thu, 25 Feb 2016 13:54:20 -0300 Subject: [PATCH 216/417] ipr: Fix regression when loading firmware Commit d63c7dd5bcb9 ("ipr: Fix out-of-bounds null overwrite") removed the end of line handling when storing the update_fw sysfs attribute. This changed the userpace API because it started refusing writes terminated by a line feed, which broke the update tools we already have. This patch re-adds that handling, so both a write terminated by a line feed or not can make it through with the update. Fixes: d63c7dd5bcb9 ("ipr: Fix out-of-bounds null overwrite") Signed-off-by: Gabriel Krisman Bertazi Cc: Insu Yun Acked-by: Brian King Signed-off-by: Martin K. Petersen --- drivers/scsi/ipr.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 3b3e0998fa6e..d6a691e27d33 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -4002,6 +4002,7 @@ static ssize_t ipr_store_update_fw(struct device *dev, struct ipr_sglist *sglist; char fname[100]; char *src; + char *endline; int result, dnld_size; if (!capable(CAP_SYS_ADMIN)) @@ -4009,6 +4010,10 @@ static ssize_t ipr_store_update_fw(struct device *dev, snprintf(fname, sizeof(fname), "%s", buf); + endline = strchr(fname, '\n'); + if (endline) + *endline = '\0'; + if (request_firmware(&fw_entry, fname, &ioa_cfg->pdev->dev)) { dev_err(&ioa_cfg->pdev->dev, "Firmware file %s not found\n", fname); return -EIO; From 6c777e8799a93e3bdb67bec622429e1b48dc90fb Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 17 Feb 2016 12:26:42 -0600 Subject: [PATCH 217/417] Revert "PCI, x86: Implement pcibios_alloc_irq() and pcibios_free_irq()" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 991de2e59090 ("PCI, x86: Implement pcibios_alloc_irq() and pcibios_free_irq()") appeared in v4.3 and helps support IOAPIC hotplug. Олег reported that the Elcus-1553 TA1-PCI driver worked in v4.2 but not v4.3 and bisected it to 991de2e59090. Sunjin reported that the RocketRAID 272x driver worked in v4.2 but not v4.3. In both cases booting with "pci=routirq" is a workaround. I think the problem is that after 991de2e59090, we no longer call pcibios_enable_irq() for upstream bridges. Prior to 991de2e59090, when a driver called pci_enable_device(), we recursively called pcibios_enable_irq() for upstream bridges via pci_enable_bridge(). After 991de2e59090, we call pcibios_enable_irq() from pci_device_probe() instead of the pci_enable_device() path, which does *not* call pcibios_enable_irq() for upstream bridges. Revert 991de2e59090 to fix these driver regressions. Link: https://bugzilla.kernel.org/show_bug.cgi?id=111211 Fixes: 991de2e59090 ("PCI, x86: Implement pcibios_alloc_irq() and pcibios_free_irq()") Reported-and-tested-by: Олег Мороз Reported-by: Sunjin Yang Signed-off-by: Bjorn Helgaas Acked-by: Rafael J. Wysocki CC: Jiang Liu --- arch/x86/include/asm/pci_x86.h | 2 ++ arch/x86/pci/common.c | 26 ++++++++++++++------------ arch/x86/pci/intel_mid_pci.c | 7 ++----- arch/x86/pci/irq.c | 15 ++++++++++++++- drivers/acpi/pci_irq.c | 9 ++++++++- 5 files changed, 40 insertions(+), 19 deletions(-) diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index 46873fbd44e1..d08eacd298c2 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -93,6 +93,8 @@ extern raw_spinlock_t pci_config_lock; extern int (*pcibios_enable_irq)(struct pci_dev *dev); extern void (*pcibios_disable_irq)(struct pci_dev *dev); +extern bool mp_should_keep_irq(struct device *dev); + struct pci_raw_ops { int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn, int reg, int len, u32 *val); diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index cb499c5b6ae5..d34b5118b4e8 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -711,20 +711,22 @@ int pcibios_add_device(struct pci_dev *dev) return 0; } -int pcibios_alloc_irq(struct pci_dev *dev) -{ - return pcibios_enable_irq(dev); -} - -void pcibios_free_irq(struct pci_dev *dev) -{ - if (pcibios_disable_irq) - pcibios_disable_irq(dev); -} - int pcibios_enable_device(struct pci_dev *dev, int mask) { - return pci_enable_resources(dev, mask); + int err; + + if ((err = pci_enable_resources(dev, mask)) < 0) + return err; + + if (!pci_dev_msi_enabled(dev)) + return pcibios_enable_irq(dev); + return 0; +} + +void pcibios_disable_device (struct pci_dev *dev) +{ + if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq) + pcibios_disable_irq(dev); } int pci_ext_cfg_avail(void) diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 8826ff593ebc..8b93e634af84 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -256,13 +256,10 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) static void intel_mid_pci_irq_disable(struct pci_dev *dev) { - if (dev->irq_managed && dev->irq > 0) { + if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed && + dev->irq > 0) { mp_unmap_irq(dev->irq); dev->irq_managed = 0; - /* - * Don't reset dev->irq here, otherwise - * intel_mid_pci_irq_enable() will fail on next call. - */ } } diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 72108f0b66b1..9bd115484745 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -1257,9 +1257,22 @@ static int pirq_enable_irq(struct pci_dev *dev) return 0; } +bool mp_should_keep_irq(struct device *dev) +{ + if (dev->power.is_prepared) + return true; +#ifdef CONFIG_PM + if (dev->power.runtime_status == RPM_SUSPENDING) + return true; +#endif + + return false; +} + static void pirq_disable_irq(struct pci_dev *dev) { - if (io_apic_assign_pci_irqs && dev->irq_managed && dev->irq) { + if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) && + dev->irq_managed && dev->irq) { mp_unmap_irq(dev->irq); dev->irq = 0; dev->irq_managed = 0; diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index 9032db7e4b3a..c8e169e46673 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -478,6 +478,14 @@ void acpi_pci_irq_disable(struct pci_dev *dev) if (!pin || !dev->irq_managed || dev->irq <= 0) return; + /* Keep IOAPIC pin configuration when suspending */ + if (dev->dev.power.is_prepared) + return; +#ifdef CONFIG_PM + if (dev->dev.power.runtime_status == RPM_SUSPENDING) + return; +#endif + entry = acpi_pci_irq_lookup(dev, pin); if (!entry) return; @@ -498,6 +506,5 @@ void acpi_pci_irq_disable(struct pci_dev *dev) if (gsi >= 0) { acpi_unregister_gsi(gsi); dev->irq_managed = 0; - dev->irq = 0; } } From 61d9e854dfb91b46b99ffd3d31fc7d45d2b95f31 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 18 Feb 2016 14:32:10 +0100 Subject: [PATCH 218/417] PCI: mvebu: Restrict build to 32-bit ARM This driver uses PCI glue that is only available on 32-bit ARM. This used to work fine as long as ARCH_MVEBU and ARCH_DOVE were exclusively 32-bit, but there's a patch in the pipe to make ARCH_MVEBU also available on 64-bit ARM. [bhelgaas: changelog; patch is coming but not merged yet] Signed-off-by: Thierry Reding Signed-off-by: Bjorn Helgaas Acked-by: Thomas Petazzoni --- drivers/pci/host/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pci/host/Kconfig b/drivers/pci/host/Kconfig index 75a605426538..d1cdd9c992ac 100644 --- a/drivers/pci/host/Kconfig +++ b/drivers/pci/host/Kconfig @@ -14,6 +14,7 @@ config PCI_DRA7XX config PCI_MVEBU bool "Marvell EBU PCIe controller" depends on ARCH_MVEBU || ARCH_DOVE + depends on ARM depends on OF config PCIE_DW From ad33bb04b2a6cee6c1f99fabb15cddbf93ff0433 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Fri, 26 Feb 2016 15:19:28 -0800 Subject: [PATCH 219/417] mm: thp: fix SMP race condition between THP page fault and MADV_DONTNEED pmd_trans_unstable()/pmd_none_or_trans_huge_or_clear_bad() were introduced to locklessy (but atomically) detect when a pmd is a regular (stable) pmd or when the pmd is unstable and can infinitely transition from pmd_none() and pmd_trans_huge() from under us, while only holding the mmap_sem for reading (for writing not). While holding the mmap_sem only for reading, MADV_DONTNEED can run from under us and so before we can assume the pmd to be a regular stable pmd we need to compare it against pmd_none() and pmd_trans_huge() in an atomic way, with pmd_trans_unstable(). The old pmd_trans_huge() left a tiny window for a race. Useful applications are unlikely to notice the difference as doing MADV_DONTNEED concurrently with a page fault would lead to undefined behavior. [akpm@linux-foundation.org: tidy up comment grammar/layout] Signed-off-by: Andrea Arcangeli Reported-by: Kirill A. Shutemov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index 635451abc8f7..8132787ae4d5 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3404,8 +3404,18 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(pmd_none(*pmd)) && unlikely(__pte_alloc(mm, vma, pmd, address))) return VM_FAULT_OOM; - /* if an huge pmd materialized from under us just retry later */ - if (unlikely(pmd_trans_huge(*pmd) || pmd_devmap(*pmd))) + /* + * If a huge pmd materialized under us just retry later. Use + * pmd_trans_unstable() instead of pmd_trans_huge() to ensure the pmd + * didn't become pmd_trans_huge under us and then back to pmd_none, as + * a result of MADV_DONTNEED running immediately after a huge pmd fault + * in a different thread of this mm, in turn leading to a misleading + * pmd_trans_huge() retval. All we have to ensure is that it is a + * regular pmd that we can walk with pte_offset_map() and we can do that + * through an atomic read in C, which is what pmd_trans_unstable() + * provides. + */ + if (unlikely(pmd_trans_unstable(pmd) || pmd_devmap(*pmd))) return 0; /* * A regular pmd is established and it can't morph into a huge pmd From 8479eba7781fa9ffb28268840de6facfc12c35a7 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 26 Feb 2016 15:19:31 -0800 Subject: [PATCH 220/417] mm: numa: quickly fail allocations for NUMA balancing on full nodes Commit 4167e9b2cf10 ("mm: remove GFP_THISNODE") removed the GFP_THISNODE flag combination due to confusing semantics. It noted that alloc_misplaced_dst_page() was one such user after changes made by commit e97ca8e5b864 ("mm: fix GFP_THISNODE callers and clarify"). Unfortunately when GFP_THISNODE was removed, users of alloc_misplaced_dst_page() started waking kswapd and entering direct reclaim because the wrong GFP flags are cleared. The consequence is that workloads that used to fit into memory now get reclaimed which is addressed by this patch. The problem can be demonstrated with "mutilate" that exercises memcached which is software dedicated to memory object caching. The configuration uses 80% of memory and is run 3 times for varying numbers of clients. The results on a 4-socket NUMA box are mutilate 4.4.0 4.4.0 vanilla numaswap-v1 Hmean 1 8394.71 ( 0.00%) 8395.32 ( 0.01%) Hmean 4 30024.62 ( 0.00%) 34513.54 ( 14.95%) Hmean 7 32821.08 ( 0.00%) 70542.96 (114.93%) Hmean 12 55229.67 ( 0.00%) 93866.34 ( 69.96%) Hmean 21 39438.96 ( 0.00%) 85749.21 (117.42%) Hmean 30 37796.10 ( 0.00%) 50231.49 ( 32.90%) Hmean 47 18070.91 ( 0.00%) 38530.13 (113.22%) The metric is queries/second with the more the better. The results are way outside of the noise and the reason for the improvement is obvious from some of the vmstats 4.4.0 4.4.0 vanillanumaswap-v1r1 Minor Faults 1929399272 2146148218 Major Faults 19746529 3567 Swap Ins 57307366 9913 Swap Outs 50623229 17094 Allocation stalls 35909 443 DMA allocs 0 0 DMA32 allocs 72976349 170567396 Normal allocs 5306640898 5310651252 Movable allocs 0 0 Direct pages scanned 404130893 799577 Kswapd pages scanned 160230174 0 Kswapd pages reclaimed 55928786 0 Direct pages reclaimed 1843936 41921 Page writes file 2391 0 Page writes anon 50623229 17094 The vanilla kernel is swapping like crazy with large amounts of direct reclaim and kswapd activity. The figures are aggregate but it's known that the bad activity is throughout the entire test. Note that simple streaming anon/file memory consumers also see this problem but it's not as obvious. In those cases, kswapd is awake when it should not be. As there are at least two reclaim-related bugs out there, it's worth spelling out the user-visible impact. This patch only addresses bugs related to excessive reclaim on NUMA hardware when the working set is larger than a NUMA node. There is a bug related to high kswapd CPU usage but the reports are against laptops and other UMA hardware and is not addressed by this patch. Signed-off-by: Mel Gorman Cc: Vlastimil Babka Cc: Johannes Weiner Cc: David Rientjes Cc: [4.1+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/migrate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/migrate.c b/mm/migrate.c index b1034f9c77e7..3ad0fea5c438 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1582,7 +1582,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page, (GFP_HIGHUSER_MOVABLE | __GFP_THISNODE | __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) & - ~(__GFP_IO | __GFP_FS), 0); + ~__GFP_RECLAIM, 0); return newpage; } From ec9ee4acd97c0039a61c0ae4f12705767ae62153 Mon Sep 17 00:00:00 2001 From: Daniel Cashman Date: Fri, 26 Feb 2016 15:19:34 -0800 Subject: [PATCH 221/417] drivers: char: random: add get_random_long() Commit d07e22597d1d ("mm: mmap: add new /proc tunable for mmap_base ASLR") added the ability to choose from a range of values to use for entropy count in generating the random offset to the mmap_base address. The maximum value on this range was set to 32 bits for 64-bit x86 systems, but this value could be increased further, requiring more than the 32 bits of randomness provided by get_random_int(), as is already possible for arm64. Add a new function: get_random_long() which more naturally fits with the mmap usage of get_random_int() but operates exactly the same as get_random_int(). Also, fix the shifting constant in mmap_rnd() to be an unsigned long so that values greater than 31 bits generate an appropriate mask without overflow. This is especially important on x86, as its shift instruction uses a 5-bit mask for the shift operand, which meant that any value for mmap_rnd_bits over 31 acts as a no-op and effectively disables mmap_base randomization. Finally, replace calls to get_random_int() with get_random_long() where appropriate. This patch (of 2): Add get_random_long(). Signed-off-by: Daniel Cashman Acked-by: Kees Cook Cc: "Theodore Ts'o" Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Cc: Catalin Marinas Cc: Will Deacon Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: David S. Miller Cc: Thomas Gleixner Cc: Ingo Molnar Cc: H. Peter Anvin Cc: Al Viro Cc: Nick Kralevich Cc: Jeff Vander Stoep Cc: Mark Salyzyn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/char/random.c | 22 ++++++++++++++++++++++ include/linux/random.h | 1 + 2 files changed, 23 insertions(+) diff --git a/drivers/char/random.c b/drivers/char/random.c index d0da5d852d41..b583e5336630 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1818,6 +1818,28 @@ unsigned int get_random_int(void) } EXPORT_SYMBOL(get_random_int); +/* + * Same as get_random_int(), but returns unsigned long. + */ +unsigned long get_random_long(void) +{ + __u32 *hash; + unsigned long ret; + + if (arch_get_random_long(&ret)) + return ret; + + hash = get_cpu_var(get_random_int_hash); + + hash[0] += current->pid + jiffies + random_get_entropy(); + md5_transform(hash, random_int_secret); + ret = *(unsigned long *)hash; + put_cpu_var(get_random_int_hash); + + return ret; +} +EXPORT_SYMBOL(get_random_long); + /* * randomize_range() returns a start address such that * diff --git a/include/linux/random.h b/include/linux/random.h index a75840c1aa71..9c29122037f9 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -34,6 +34,7 @@ extern const struct file_operations random_fops, urandom_fops; #endif unsigned int get_random_int(void); +unsigned long get_random_long(void); unsigned long randomize_range(unsigned long start, unsigned long end, unsigned long len); u32 prandom_u32(void); From 5ef11c35ce86b94bfb878b684de4cdaf96f54b2f Mon Sep 17 00:00:00 2001 From: Daniel Cashman Date: Fri, 26 Feb 2016 15:19:37 -0800 Subject: [PATCH 222/417] mm: ASLR: use get_random_long() Replace calls to get_random_int() followed by a cast to (unsigned long) with calls to get_random_long(). Also address shifting bug which, in case of x86 removed entropy mask for mmap_rnd_bits values > 31 bits. Signed-off-by: Daniel Cashman Acked-by: Kees Cook Cc: "Theodore Ts'o" Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Cc: Catalin Marinas Cc: Will Deacon Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: David S. Miller Cc: Thomas Gleixner Cc: Ingo Molnar Cc: H. Peter Anvin Cc: Al Viro Cc: Nick Kralevich Cc: Jeff Vander Stoep Cc: Mark Salyzyn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/mm/mmap.c | 2 +- arch/arm64/mm/mmap.c | 4 ++-- arch/mips/mm/mmap.c | 4 ++-- arch/powerpc/kernel/process.c | 4 ++-- arch/powerpc/mm/mmap.c | 4 ++-- arch/sparc/kernel/sys_sparc_64.c | 2 +- arch/x86/mm/mmap.c | 6 +++--- fs/binfmt_elf.c | 2 +- 8 files changed, 14 insertions(+), 14 deletions(-) diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index 4b4058db0781..66353caa35b9 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -173,7 +173,7 @@ unsigned long arch_mmap_rnd(void) { unsigned long rnd; - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 4c893b5189dd..232f787a088a 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -53,10 +53,10 @@ unsigned long arch_mmap_rnd(void) #ifdef CONFIG_COMPAT if (test_thread_flag(TIF_32BIT)) - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_compat_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1); else #endif - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c index 5c81fdd032c3..353037699512 100644 --- a/arch/mips/mm/mmap.c +++ b/arch/mips/mm/mmap.c @@ -146,7 +146,7 @@ unsigned long arch_mmap_rnd(void) { unsigned long rnd; - rnd = (unsigned long)get_random_int(); + rnd = get_random_long(); rnd <<= PAGE_SHIFT; if (TASK_IS_32BIT_ADDR) rnd &= 0xfffffful; @@ -174,7 +174,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm) static inline unsigned long brk_rnd(void) { - unsigned long rnd = get_random_int(); + unsigned long rnd = get_random_long(); rnd = rnd << PAGE_SHIFT; /* 8MB for 32bit, 256MB for 64bit */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index dccc87e8fee5..3c5736e52a14 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1768,9 +1768,9 @@ static inline unsigned long brk_rnd(void) /* 8MB for 32bit, 1GB for 64bit */ if (is_32bit_task()) - rnd = (long)(get_random_int() % (1<<(23-PAGE_SHIFT))); + rnd = (get_random_long() % (1UL<<(23-PAGE_SHIFT))); else - rnd = (long)(get_random_int() % (1<<(30-PAGE_SHIFT))); + rnd = (get_random_long() % (1UL<<(30-PAGE_SHIFT))); return rnd << PAGE_SHIFT; } diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c index 0f0502e12f6c..4087705ba90f 100644 --- a/arch/powerpc/mm/mmap.c +++ b/arch/powerpc/mm/mmap.c @@ -59,9 +59,9 @@ unsigned long arch_mmap_rnd(void) /* 8MB for 32bit, 1GB for 64bit */ if (is_32bit_task()) - rnd = (unsigned long)get_random_int() % (1<<(23-PAGE_SHIFT)); + rnd = get_random_long() % (1<<(23-PAGE_SHIFT)); else - rnd = (unsigned long)get_random_int() % (1<<(30-PAGE_SHIFT)); + rnd = get_random_long() % (1UL<<(30-PAGE_SHIFT)); return rnd << PAGE_SHIFT; } diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index c690c8e16a96..b489e9759518 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -264,7 +264,7 @@ static unsigned long mmap_rnd(void) unsigned long rnd = 0UL; if (current->flags & PF_RANDOMIZE) { - unsigned long val = get_random_int(); + unsigned long val = get_random_long(); if (test_thread_flag(TIF_32BIT)) rnd = (val % (1UL << (23UL-PAGE_SHIFT))); else diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 96bd1e2bffaf..72bb52f93c3d 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -71,12 +71,12 @@ unsigned long arch_mmap_rnd(void) if (mmap_is_ia32()) #ifdef CONFIG_COMPAT - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_compat_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1); #else - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); #endif else - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 051ea4809c14..7d914c67a9d0 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -653,7 +653,7 @@ static unsigned long randomize_stack_top(unsigned long stack_top) if ((current->flags & PF_RANDOMIZE) && !(current->personality & ADDR_NO_RANDOMIZE)) { - random_variable = (unsigned long) get_random_int(); + random_variable = get_random_long(); random_variable &= STACK_RND_MASK; random_variable <<= PAGE_SHIFT; } From a4a8481ff68a8a324a878e281bc37f18665224f7 Mon Sep 17 00:00:00 2001 From: Guozhonghua Date: Fri, 26 Feb 2016 15:19:40 -0800 Subject: [PATCH 223/417] ocfs2: unlock inode if deleting inode from orphan fails When doing append direct io cleanup, if deleting inode fails, it goes out without unlocking inode, which will cause the inode deadlock. This issue was introduced by commit cf1776a9e834 ("ocfs2: fix a tiny race when truncate dio orohaned entry"). Signed-off-by: Guozhonghua Signed-off-by: Joseph Qi Reviewed-by: Gang He Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: [4.2+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/aops.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 794fd1587f34..cda0361e95a4 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -956,6 +956,7 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb, tmp_ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh, update_isize, end); if (tmp_ret < 0) { + ocfs2_inode_unlock(inode, 1); ret = tmp_ret; mlog_errno(ret); brelse(di_bh); From 03cdadb04077b9311bbc67d98cc5401aff76482d Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 26 Feb 2016 15:19:43 -0800 Subject: [PATCH 224/417] block: disable block device DAX by default The recent *sync enabling discovered that we are inserting into the block_device pagecache counter to the expectations of the dirty data tracking for dax mappings. This can lead to data corruption. We want to support DAX for block devices eventually, but it requires wider changes to properly manage the pagecache. dump_stack+0x85/0xc2 dax_writeback_mapping_range+0x60/0xe0 blkdev_writepages+0x3f/0x50 do_writepages+0x21/0x30 __filemap_fdatawrite_range+0xc6/0x100 filemap_write_and_wait+0x4a/0xa0 set_blocksize+0x70/0xd0 sb_set_blocksize+0x1d/0x50 ext4_fill_super+0x75b/0x3360 mount_bdev+0x180/0x1b0 ext4_mount+0x15/0x20 mount_fs+0x38/0x170 Mark the support broken so its disabled by default, but otherwise still available for testing. Signed-off-by: Dan Williams Signed-off-by: Ross Zwisler Reported-by: Ross Zwisler Suggested-by: Dave Chinner Reviewed-by: Jan Kara Cc: Jens Axboe Cc: Matthew Wilcox Cc: Al Viro Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- block/Kconfig | 13 +++++++++++++ fs/block_dev.c | 6 +++++- 2 files changed, 18 insertions(+), 1 deletion(-) diff --git a/block/Kconfig b/block/Kconfig index 161491d0a879..0363cd731320 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -88,6 +88,19 @@ config BLK_DEV_INTEGRITY T10/SCSI Data Integrity Field or the T13/ATA External Path Protection. If in doubt, say N. +config BLK_DEV_DAX + bool "Block device DAX support" + depends on FS_DAX + depends on BROKEN + help + When DAX support is available (CONFIG_FS_DAX) raw block + devices can also support direct userspace access to the + storage capacity via MMAP(2) similar to a file on a + DAX-enabled filesystem. However, the DAX I/O-path disables + some standard I/O-statistics, and the MMAP(2) path has some + operational differences due to bypassing the page + cache. If in doubt, say N. + config BLK_DEV_THROTTLING bool "Block layer bio throttling support" depends on BLK_CGROUP=y diff --git a/fs/block_dev.c b/fs/block_dev.c index 39b3a174a425..31c6d1090f11 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1201,7 +1201,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) bdev->bd_disk = disk; bdev->bd_queue = disk->queue; bdev->bd_contains = bdev; - bdev->bd_inode->i_flags = disk->fops->direct_access ? S_DAX : 0; + if (IS_ENABLED(CONFIG_BLK_DEV_DAX) && disk->fops->direct_access) + bdev->bd_inode->i_flags = S_DAX; + else + bdev->bd_inode->i_flags = 0; + if (!partno) { ret = -ENXIO; bdev->bd_part = disk_get_part(disk, partno); From 0a6cf9137ded4856b41910a4336677ee0ffa6736 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Fri, 26 Feb 2016 15:19:46 -0800 Subject: [PATCH 225/417] ext2, ext4: only set S_DAX for regular inodes When S_DAX is set on an inode we assume that if there are pages attached to the mapping (mapping->nrpages != 0), those pages are clean zero pages that were used to service reads from holes. Any dirty data associated with the inode should be in the form of DAX exceptional entries (mapping->nrexceptional) that is written back via dax_writeback_mapping_range(). With the current code, though, this isn't always true. For example, ext2 and ext4 directory inodes can have S_DAX set, but have their dirty data stored as dirty page cache entries. For these types of inodes, having S_DAX set doesn't really make sense since their I/O doesn't actually happen through the DAX code path. Instead, only allow S_DAX to be set for regular inodes for ext2 and ext4. This allows us to have strict DAX vs non-DAX paths in the writeback code. Signed-off-by: Ross Zwisler Reviewed-by: Jan Kara Cc: Theodore Ts'o Cc: Al Viro Cc: Dan Williams Cc: Dave Chinner Cc: Jens Axboe Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext2/inode.c | 2 +- fs/ext4/inode.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 338eefda70c6..27e2cdd4999b 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1296,7 +1296,7 @@ void ext2_set_inode_flags(struct inode *inode) inode->i_flags |= S_NOATIME; if (flags & EXT2_DIRSYNC_FL) inode->i_flags |= S_DIRSYNC; - if (test_opt(inode->i_sb, DAX)) + if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode)) inode->i_flags |= S_DAX; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 9cc57c3b4661..5708e689e63d 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4155,7 +4155,7 @@ void ext4_set_inode_flags(struct inode *inode) new_fl |= S_NOATIME; if (flags & EXT4_DIRSYNC_FL) new_fl |= S_DIRSYNC; - if (test_opt(inode->i_sb, DAX)) + if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode)) new_fl |= S_DAX; inode_set_flags(inode, new_fl, S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX); From 73f34a5e2ceddfca27c999c170620e6354aaf6d7 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Fri, 26 Feb 2016 15:19:49 -0800 Subject: [PATCH 226/417] ext4: online defrag not supported with DAX Online defrag operations for ext4 are hard coded to use the page cache. See ext4_ioctl() -> ext4_move_extents() -> move_extent_per_page() When combined with DAX I/O, which circumvents the page cache, this can result in data corruption. This was observed with xfstests ext4/307 and ext4/308. Fix this by only allowing online defrag for non-DAX files. Signed-off-by: Ross Zwisler Reviewed-by: Jan Kara Cc: Theodore Ts'o Cc: Al Viro Cc: Dan Williams Cc: Dave Chinner Cc: Jens Axboe Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext4/ioctl.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index a99b010e2194..eae5917c534e 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -583,6 +583,11 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) "Online defrag not supported with bigalloc"); err = -EOPNOTSUPP; goto mext_out; + } else if (IS_DAX(inode)) { + ext4_msg(sb, KERN_ERR, + "Online defrag not supported with DAX"); + err = -EOPNOTSUPP; + goto mext_out; } err = mnt_want_write_file(filp); From 20a90f58997245749c2bdfaea9e51f785ec90d0b Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Fri, 26 Feb 2016 15:19:52 -0800 Subject: [PATCH 227/417] dax: give DAX clearing code correct bdev dax_clear_blocks() needs a valid struct block_device and previously it was using inode->i_sb->s_bdev in all cases. This is correct for normal inodes on mounted ext2, ext4 and XFS filesystems, but is incorrect for DAX raw block devices and for XFS real-time devices. Instead, rename dax_clear_blocks() to dax_clear_sectors(), and change its arguments to take a bdev and a sector instead of an inode and a block. This better reflects what the function does, and it allows the filesystem and raw block device code to pass in an appropriate struct block_device. Signed-off-by: Ross Zwisler Suggested-by: Dan Williams Reviewed-by: Jan Kara Cc: Theodore Ts'o Cc: Al Viro Cc: Dave Chinner Cc: Jens Axboe Cc: Matthew Wilcox Cc: Ross Zwisler Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/dax.c | 9 ++++----- fs/ext2/inode.c | 6 ++++-- fs/xfs/xfs_aops.c | 2 +- fs/xfs/xfs_aops.h | 1 + fs/xfs/xfs_bmap_util.c | 3 ++- include/linux/dax.h | 2 +- 6 files changed, 13 insertions(+), 10 deletions(-) diff --git a/fs/dax.c b/fs/dax.c index fc2e3141138b..9a173dd8c4a3 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -79,15 +79,14 @@ struct page *read_dax_sector(struct block_device *bdev, sector_t n) } /* - * dax_clear_blocks() is called from within transaction context from XFS, + * dax_clear_sectors() is called from within transaction context from XFS, * and hence this means the stack from this point must follow GFP_NOFS * semantics for all operations. */ -int dax_clear_blocks(struct inode *inode, sector_t block, long _size) +int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size) { - struct block_device *bdev = inode->i_sb->s_bdev; struct blk_dax_ctl dax = { - .sector = block << (inode->i_blkbits - 9), + .sector = _sector, .size = _size, }; @@ -109,7 +108,7 @@ int dax_clear_blocks(struct inode *inode, sector_t block, long _size) wmb_pmem(); return 0; } -EXPORT_SYMBOL_GPL(dax_clear_blocks); +EXPORT_SYMBOL_GPL(dax_clear_sectors); /* the clear_pmem() calls are ordered by a wmb_pmem() in the caller */ static void dax_new_buf(void __pmem *addr, unsigned size, unsigned first, diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 27e2cdd4999b..4467cbd75f24 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -737,8 +737,10 @@ static int ext2_get_blocks(struct inode *inode, * so that it's not found by another thread before it's * initialised */ - err = dax_clear_blocks(inode, le32_to_cpu(chain[depth-1].key), - 1 << inode->i_blkbits); + err = dax_clear_sectors(inode->i_sb->s_bdev, + le32_to_cpu(chain[depth-1].key) << + (inode->i_blkbits - 9), + 1 << inode->i_blkbits); if (err) { mutex_unlock(&ei->truncate_mutex); goto cleanup; diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 379c089fb051..fc20518e2398 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -55,7 +55,7 @@ xfs_count_page_state( } while ((bh = bh->b_this_page) != head); } -STATIC struct block_device * +struct block_device * xfs_find_bdev_for_inode( struct inode *inode) { diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h index f6ffc9ae5ceb..a4343c63fb38 100644 --- a/fs/xfs/xfs_aops.h +++ b/fs/xfs/xfs_aops.h @@ -62,5 +62,6 @@ int xfs_get_blocks_dax_fault(struct inode *inode, sector_t offset, struct buffer_head *map_bh, int create); extern void xfs_count_page_state(struct page *, int *, int *); +extern struct block_device *xfs_find_bdev_for_inode(struct inode *); #endif /* __XFS_AOPS_H__ */ diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 45ec9e40150c..6c876012b2e5 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -75,7 +75,8 @@ xfs_zero_extent( ssize_t size = XFS_FSB_TO_B(mp, count_fsb); if (IS_DAX(VFS_I(ip))) - return dax_clear_blocks(VFS_I(ip), block, size); + return dax_clear_sectors(xfs_find_bdev_for_inode(VFS_I(ip)), + sector, size); /* * let the block layer decide on the fastest method of diff --git a/include/linux/dax.h b/include/linux/dax.h index 818e45078929..7b6bcedb980f 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -7,7 +7,7 @@ ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t, get_block_t, dio_iodone_t, int flags); -int dax_clear_blocks(struct inode *, sector_t block, long size); +int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size); int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t); int dax_truncate_page(struct inode *, loff_t from, get_block_t); int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t, From 7f6d5b529b7dfe2fca30cbf4bc81e16575090025 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Fri, 26 Feb 2016 15:19:55 -0800 Subject: [PATCH 228/417] dax: move writeback calls into the filesystems Previously calls to dax_writeback_mapping_range() for all DAX filesystems (ext2, ext4 & xfs) were centralized in filemap_write_and_wait_range(). dax_writeback_mapping_range() needs a struct block_device, and it used to get that from inode->i_sb->s_bdev. This is correct for normal inodes mounted on ext2, ext4 and XFS filesystems, but is incorrect for DAX raw block devices and for XFS real-time files. Instead, call dax_writeback_mapping_range() directly from the filesystem ->writepages function so that it can supply us with a valid block device. This also fixes DAX code to properly flush caches in response to sync(2). Signed-off-by: Ross Zwisler Signed-off-by: Jan Kara Cc: Al Viro Cc: Dan Williams Cc: Dave Chinner Cc: Jens Axboe Cc: Matthew Wilcox Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/block_dev.c | 13 ++++++++++++- fs/dax.c | 12 +++++++----- fs/ext2/inode.c | 8 ++++++++ fs/ext4/inode.c | 4 ++++ fs/xfs/xfs_aops.c | 4 ++++ include/linux/dax.h | 6 ++++-- mm/filemap.c | 12 ++++-------- 7 files changed, 43 insertions(+), 16 deletions(-) diff --git a/fs/block_dev.c b/fs/block_dev.c index 31c6d1090f11..826b164a4b5b 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1697,13 +1697,24 @@ static int blkdev_releasepage(struct page *page, gfp_t wait) return try_to_free_buffers(page); } +static int blkdev_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + if (dax_mapping(mapping)) { + struct block_device *bdev = I_BDEV(mapping->host); + + return dax_writeback_mapping_range(mapping, bdev, wbc); + } + return generic_writepages(mapping, wbc); +} + static const struct address_space_operations def_blk_aops = { .readpage = blkdev_readpage, .readpages = blkdev_readpages, .writepage = blkdev_writepage, .write_begin = blkdev_write_begin, .write_end = blkdev_write_end, - .writepages = generic_writepages, + .writepages = blkdev_writepages, .releasepage = blkdev_releasepage, .direct_IO = blkdev_direct_IO, .is_dirty_writeback = buffer_check_dirty_writeback, diff --git a/fs/dax.c b/fs/dax.c index 9a173dd8c4a3..711172450da6 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -484,11 +484,10 @@ static int dax_writeback_one(struct block_device *bdev, * end]. This is required by data integrity operations to ensure file data is * on persistent storage prior to completion of the operation. */ -int dax_writeback_mapping_range(struct address_space *mapping, loff_t start, - loff_t end) +int dax_writeback_mapping_range(struct address_space *mapping, + struct block_device *bdev, struct writeback_control *wbc) { struct inode *inode = mapping->host; - struct block_device *bdev = inode->i_sb->s_bdev; pgoff_t start_index, end_index, pmd_index; pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; @@ -499,8 +498,11 @@ int dax_writeback_mapping_range(struct address_space *mapping, loff_t start, if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT)) return -EIO; - start_index = start >> PAGE_CACHE_SHIFT; - end_index = end >> PAGE_CACHE_SHIFT; + if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL) + return 0; + + start_index = wbc->range_start >> PAGE_CACHE_SHIFT; + end_index = wbc->range_end >> PAGE_CACHE_SHIFT; pmd_index = DAX_PMD_INDEX(start_index); rcu_read_lock(); diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 4467cbd75f24..6bd58e6ff038 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -876,6 +876,14 @@ ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) static int ext2_writepages(struct address_space *mapping, struct writeback_control *wbc) { +#ifdef CONFIG_FS_DAX + if (dax_mapping(mapping)) { + return dax_writeback_mapping_range(mapping, + mapping->host->i_sb->s_bdev, + wbc); + } +#endif + return mpage_writepages(mapping, wbc, ext2_get_block); } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 5708e689e63d..aee960b1af34 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2478,6 +2478,10 @@ static int ext4_writepages(struct address_space *mapping, trace_ext4_writepages(inode, wbc); + if (dax_mapping(mapping)) + return dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, + wbc); + /* * No pages to write? This is mainly a kludge to avoid starting * a transaction for special inodes like journal inode on last iput() diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index fc20518e2398..a9ebabfe7587 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -1208,6 +1208,10 @@ xfs_vm_writepages( struct writeback_control *wbc) { xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED); + if (dax_mapping(mapping)) + return dax_writeback_mapping_range(mapping, + xfs_find_bdev_for_inode(mapping->host), wbc); + return generic_writepages(mapping, wbc); } diff --git a/include/linux/dax.h b/include/linux/dax.h index 7b6bcedb980f..636dd59ab505 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -52,6 +52,8 @@ static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); } -int dax_writeback_mapping_range(struct address_space *mapping, loff_t start, - loff_t end); + +struct writeback_control; +int dax_writeback_mapping_range(struct address_space *mapping, + struct block_device *bdev, struct writeback_control *wbc); #endif diff --git a/mm/filemap.c b/mm/filemap.c index 23edccecadb0..3461d97ecb30 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -446,7 +446,8 @@ int filemap_write_and_wait(struct address_space *mapping) { int err = 0; - if (mapping->nrpages) { + if ((!dax_mapping(mapping) && mapping->nrpages) || + (dax_mapping(mapping) && mapping->nrexceptional)) { err = filemap_fdatawrite(mapping); /* * Even if the above returned error, the pages may be @@ -482,13 +483,8 @@ int filemap_write_and_wait_range(struct address_space *mapping, { int err = 0; - if (dax_mapping(mapping) && mapping->nrexceptional) { - err = dax_writeback_mapping_range(mapping, lstart, lend); - if (err) - return err; - } - - if (mapping->nrpages) { + if ((!dax_mapping(mapping) && mapping->nrpages) || + (dax_mapping(mapping) && mapping->nrexceptional)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* See comment of filemap_write_and_wait() */ From 1e9d180ba39f42e8ca4a808baef3a3ef034b1c2c Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Sat, 27 Feb 2016 14:01:13 -0500 Subject: [PATCH 229/417] ext2, ext4: fix issue with missing journal entry in ext4_dax_mkwrite() As it is currently written ext4_dax_mkwrite() assumes that the call into __dax_mkwrite() will not have to do a block allocation so it doesn't create a journal entry. For a read that creates a zero page to cover a hole followed by a write that actually allocates storage this is incorrect. The ext4_dax_mkwrite() -> __dax_mkwrite() -> __dax_fault() path calls get_blocks() to allocate storage. Fix this by having the ->page_mkwrite fault handler call ext4_dax_fault() as this function already has all the logic needed to allocate a journal entry and call __dax_fault(). Also update the ext2 fault handlers in this same way to remove duplicate code and keep the logic between ext2 and ext4 the same. Reviewed-by: Jan Kara Signed-off-by: Ross Zwisler Signed-off-by: Theodore Ts'o --- fs/ext2/file.c | 19 +------------------ fs/ext4/file.c | 19 ++----------------- 2 files changed, 3 insertions(+), 35 deletions(-) diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 2c88d683cd91..c1400b109805 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -80,23 +80,6 @@ static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, return ret; } -static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) -{ - struct inode *inode = file_inode(vma->vm_file); - struct ext2_inode_info *ei = EXT2_I(inode); - int ret; - - sb_start_pagefault(inode->i_sb); - file_update_time(vma->vm_file); - down_read(&ei->dax_sem); - - ret = __dax_mkwrite(vma, vmf, ext2_get_block, NULL); - - up_read(&ei->dax_sem); - sb_end_pagefault(inode->i_sb); - return ret; -} - static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { @@ -124,7 +107,7 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma, static const struct vm_operations_struct ext2_dax_vm_ops = { .fault = ext2_dax_fault, .pmd_fault = ext2_dax_pmd_fault, - .page_mkwrite = ext2_dax_mkwrite, + .page_mkwrite = ext2_dax_fault, .pfn_mkwrite = ext2_dax_pfn_mkwrite, }; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 474f1a4d2ca8..4cd318f31cbe 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -262,23 +262,8 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, return result; } -static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) -{ - int err; - struct inode *inode = file_inode(vma->vm_file); - - sb_start_pagefault(inode->i_sb); - file_update_time(vma->vm_file); - down_read(&EXT4_I(inode)->i_mmap_sem); - err = __dax_mkwrite(vma, vmf, ext4_dax_mmap_get_block, NULL); - up_read(&EXT4_I(inode)->i_mmap_sem); - sb_end_pagefault(inode->i_sb); - - return err; -} - /* - * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_mkwrite() + * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_fault() * handler we check for races agaist truncate. Note that since we cycle through * i_mmap_sem, we are sure that also any hole punching that began before we * were called is finished by now and so if it included part of the file we @@ -311,7 +296,7 @@ static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma, static const struct vm_operations_struct ext4_dax_vm_ops = { .fault = ext4_dax_fault, .pmd_fault = ext4_dax_pmd_fault, - .page_mkwrite = ext4_dax_mkwrite, + .page_mkwrite = ext4_dax_fault, .pfn_mkwrite = ext4_dax_pfn_mkwrite, }; #else From b6853f78e763d42c7a158d8de3549c9827c604ab Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Thu, 25 Feb 2016 18:17:38 +0100 Subject: [PATCH 230/417] hpfs: don't truncate the file when delete fails The delete opration can allocate additional space on the HPFS filesystem due to btree split. The HPFS driver checks in advance if there is available space, so that it won't corrupt the btree if we run out of space during splitting. If there is not enough available space, the HPFS driver attempted to truncate the file, but this results in a deadlock since the commit 7dd29d8d865efdb00c0542a5d2c87af8c52ea6c7 ("HPFS: Introduce a global mutex and lock it on every callback from VFS"). This patch removes the code that tries to truncate the file and -ENOSPC is returned instead. If the user hits -ENOSPC on delete, he should try to delete other files (that are stored in a leaf btree node), so that the delete operation will make some space for deleting the file stored in non-leaf btree node. Reported-by: Al Viro Signed-off-by: Mikulas Patocka Cc: stable@vger.kernel.org # 2.6.39+ Signed-off-by: Al Viro --- fs/hpfs/namei.c | 31 +++---------------------------- 1 file changed, 3 insertions(+), 28 deletions(-) diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index 506765afa1a3..bb8d67e2740a 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -376,12 +376,11 @@ static int hpfs_unlink(struct inode *dir, struct dentry *dentry) struct inode *inode = d_inode(dentry); dnode_secno dno; int r; - int rep = 0; int err; hpfs_lock(dir->i_sb); hpfs_adjust_length(name, &len); -again: + err = -ENOENT; de = map_dirent(dir, hpfs_i(dir)->i_dno, name, len, &dno, &qbh); if (!de) @@ -401,33 +400,9 @@ static int hpfs_unlink(struct inode *dir, struct dentry *dentry) hpfs_error(dir->i_sb, "there was error when removing dirent"); err = -EFSERROR; break; - case 2: /* no space for deleting, try to truncate file */ - + case 2: /* no space for deleting */ err = -ENOSPC; - if (rep++) - break; - - dentry_unhash(dentry); - if (!d_unhashed(dentry)) { - hpfs_unlock(dir->i_sb); - return -ENOSPC; - } - if (generic_permission(inode, MAY_WRITE) || - !S_ISREG(inode->i_mode) || - get_write_access(inode)) { - d_rehash(dentry); - } else { - struct iattr newattrs; - /*pr_info("truncating file before delete.\n");*/ - newattrs.ia_size = 0; - newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME; - err = notify_change(dentry, &newattrs, NULL); - put_write_access(inode); - if (!err) - goto again; - } - hpfs_unlock(dir->i_sb); - return -ENOSPC; + break; default: drop_nlink(inode); err = 0; From 0fcbf996d848d03573113d83f4e3fb3bcfa5ab5e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 26 Feb 2016 18:53:12 +0100 Subject: [PATCH 231/417] fs: return -EOPNOTSUPP if clone is not supported -EBADF is a rather confusing error if an operations is not supported, and nfsd gets rather upset about it. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/read_write.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/read_write.c b/fs/read_write.c index 0c8782aa3d71..dadf24e5c95b 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1533,10 +1533,12 @@ int vfs_clone_file_range(struct file *file_in, loff_t pos_in, if (!(file_in->f_mode & FMODE_READ) || !(file_out->f_mode & FMODE_WRITE) || - (file_out->f_flags & O_APPEND) || - !file_in->f_op->clone_file_range) + (file_out->f_flags & O_APPEND)) return -EBADF; + if (!file_in->f_op->clone_file_range) + return -EOPNOTSUPP; + ret = clone_verify_area(file_in, pos_in, len, false); if (ret) return ret; From c80567c82ae4814a41287618e315a60ecf513be6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 27 Feb 2016 19:17:33 -0500 Subject: [PATCH 232/417] do_last(): don't let a bogus return value from ->open() et.al. to confuse us ... into returning a positive to path_openat(), which would interpret that as "symlink had been encountered" and proceed to corrupt memory, etc. It can only happen due to a bug in some ->open() instance or in some LSM hook, etc., so we report any such event *and* make sure it doesn't trick us into further unpleasantness. Cc: stable@vger.kernel.org # v3.6+, at least Signed-off-by: Al Viro --- fs/namei.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/namei.c b/fs/namei.c index f624d132e01e..e30deefad8f8 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3273,6 +3273,10 @@ static int do_last(struct nameidata *nd, goto exit_fput; } out: + if (unlikely(error > 0)) { + WARN_ON(1); + error = -EINVAL; + } if (got_write) mnt_drop_write(nd->path.mnt); path_put(&save_parent); From d4565649b6d6923369112758212b851adc407f0c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 27 Feb 2016 19:23:16 -0500 Subject: [PATCH 233/417] namei: ->d_inode of a pinned dentry is stable only for positives both do_last() and walk_component() risk picking a NULL inode out of dentry about to become positive, *then* checking its flags and seeing that it's not negative anymore and using (already stale by then) value they'd fetched earlier. Usually ends up oopsing soon after that... Cc: stable@vger.kernel.org # v3.13+ Signed-off-by: Al Viro --- fs/namei.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index e30deefad8f8..e0881c0bd228 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1743,11 +1743,11 @@ static int walk_component(struct nameidata *nd, int flags) if (err < 0) return err; - inode = d_backing_inode(path.dentry); seq = 0; /* we are already out of RCU mode */ err = -ENOENT; if (d_is_negative(path.dentry)) goto out_path_put; + inode = d_backing_inode(path.dentry); } if (flags & WALK_PUT) @@ -3192,12 +3192,12 @@ static int do_last(struct nameidata *nd, return error; BUG_ON(nd->flags & LOOKUP_RCU); - inode = d_backing_inode(path.dentry); seq = 0; /* out of RCU mode, so the value doesn't matter */ if (unlikely(d_is_negative(path.dentry))) { path_to_nameidata(&path, nd); return -ENOENT; } + inode = d_backing_inode(path.dentry); finish_lookup: if (nd->depth) put_link(nd); From a7f775428b8f5808815c0e3004020cedb94cbe3b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 27 Feb 2016 19:31:01 -0500 Subject: [PATCH 234/417] should_follow_link(): validate ->d_seq after having decided to follow ... otherwise d_is_symlink() above might have nothing to do with the inode value we've got. Cc: stable@vger.kernel.org # v4.2+ Signed-off-by: Al Viro --- fs/namei.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/namei.c b/fs/namei.c index e0881c0bd228..65a0e9d1ea48 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1712,6 +1712,11 @@ static inline int should_follow_link(struct nameidata *nd, struct path *link, return 0; if (!follow) return 0; + /* make sure that d_is_symlink above matches inode */ + if (nd->flags & LOOKUP_RCU) { + if (read_seqcount_retry(&link->dentry->d_seq, seq)) + return -ECHILD; + } return pick_link(nd, link, inode, seq); } From 5129fa482b16615fd4464d2f5d23acb1b7056c66 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 27 Feb 2016 19:37:37 -0500 Subject: [PATCH 235/417] do_last(): ELOOP failure exit should be done after leaving RCU mode ... or we risk seeing a bogus value of d_is_symlink() there. Cc: stable@vger.kernel.org # v4.2+ Signed-off-by: Al Viro --- fs/namei.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index 65a0e9d1ea48..9c590e0f66e9 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3211,11 +3211,6 @@ static int do_last(struct nameidata *nd, if (unlikely(error)) return error; - if (unlikely(d_is_symlink(path.dentry)) && !(open_flag & O_PATH)) { - path_to_nameidata(&path, nd); - return -ELOOP; - } - if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path.mnt) { path_to_nameidata(&path, nd); } else { @@ -3234,6 +3229,10 @@ static int do_last(struct nameidata *nd, return error; } audit_inode(nd->name, nd->path.dentry, 0); + if (unlikely(d_is_symlink(nd->path.dentry)) && !(open_flag & O_PATH)) { + error = -ELOOP; + goto out; + } error = -EISDIR; if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry)) goto out; From 8160c4e455820d5008a1116d2dca35f0363bb062 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Sun, 28 Feb 2016 16:31:39 +0200 Subject: [PATCH 236/417] vfio: fix ioctl error handling Calling return copy_to_user(...) in an ioctl will not do the right thing if there's a pagefault: copy_to_user returns the number of bytes not copied in this case. Fix up vfio to do return copy_to_user(...)) ? -EFAULT : 0; everywhere. Cc: stable@vger.kernel.org Signed-off-by: Michael S. Tsirkin Signed-off-by: Alex Williamson --- drivers/vfio/pci/vfio_pci.c | 9 ++++++--- drivers/vfio/platform/vfio_platform_common.c | 9 ++++++--- drivers/vfio/vfio_iommu_type1.c | 6 ++++-- 3 files changed, 16 insertions(+), 8 deletions(-) diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 2760a7ba3f30..8c80a48e3233 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -446,7 +446,8 @@ static long vfio_pci_ioctl(void *device_data, info.num_regions = VFIO_PCI_NUM_REGIONS; info.num_irqs = VFIO_PCI_NUM_IRQS; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_GET_REGION_INFO) { struct pci_dev *pdev = vdev->pdev; @@ -520,7 +521,8 @@ static long vfio_pci_ioctl(void *device_data, return -EINVAL; } - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_GET_IRQ_INFO) { struct vfio_irq_info info; @@ -555,7 +557,8 @@ static long vfio_pci_ioctl(void *device_data, else info.flags |= VFIO_IRQ_INFO_NORESIZE; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_SET_IRQS) { struct vfio_irq_set hdr; diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c index 418cdd9ba3f4..e65b142d3422 100644 --- a/drivers/vfio/platform/vfio_platform_common.c +++ b/drivers/vfio/platform/vfio_platform_common.c @@ -219,7 +219,8 @@ static long vfio_platform_ioctl(void *device_data, info.num_regions = vdev->num_regions; info.num_irqs = vdev->num_irqs; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_GET_REGION_INFO) { struct vfio_region_info info; @@ -240,7 +241,8 @@ static long vfio_platform_ioctl(void *device_data, info.size = vdev->regions[info.index].size; info.flags = vdev->regions[info.index].flags; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_GET_IRQ_INFO) { struct vfio_irq_info info; @@ -259,7 +261,8 @@ static long vfio_platform_ioctl(void *device_data, info.flags = vdev->irqs[info.index].flags; info.count = vdev->irqs[info.index].count; - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_DEVICE_SET_IRQS) { struct vfio_irq_set hdr; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 6f1ea3dddbad..75b24e93cedb 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -999,7 +999,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data, info.iova_pgsizes = vfio_pgsize_bitmap(iommu); - return copy_to_user((void __user *)arg, &info, minsz); + return copy_to_user((void __user *)arg, &info, minsz) ? + -EFAULT : 0; } else if (cmd == VFIO_IOMMU_MAP_DMA) { struct vfio_iommu_type1_dma_map map; @@ -1032,7 +1033,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data, if (ret) return ret; - return copy_to_user((void __user *)arg, &unmap, minsz); + return copy_to_user((void __user *)arg, &unmap, minsz) ? + -EFAULT : 0; } return -ENOTTY; From fc77dbd34c5c99bce46d40a2491937c3bcbd10af Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 28 Feb 2016 08:41:20 -0800 Subject: [PATCH 237/417] Linux 4.5-rc6 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index fbe1b921798f..af6e5f893d56 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 5 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Blurry Fish Butt # *DOCUMENTATION* From 6236d8bb2afcfe71b88ecea554e0dc638090a45f Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sat, 27 Feb 2016 17:52:42 +0100 Subject: [PATCH 238/417] ALSA: ctl: Fix ioctls for X32 ABI The X32 ABI takes the same alignment like x86-64, and this may result in the incompatible struct size from ia32. Unfortunately, we hit this in some control ABI: struct snd_ctl_elem_value differs between them due to the position of 64bit variable array. This ends up with the unknown ioctl (ENOTTY) error. The fix is to add the compat entries for the new aligned struct. Reported-and-tested-by: Steven Newbury Cc: # v3.4+ Signed-off-by: Takashi Iwai --- sound/core/control_compat.c | 90 ++++++++++++++++++++++++++++++------- 1 file changed, 74 insertions(+), 16 deletions(-) diff --git a/sound/core/control_compat.c b/sound/core/control_compat.c index b9c0910fb8c4..0608f216f359 100644 --- a/sound/core/control_compat.c +++ b/sound/core/control_compat.c @@ -170,6 +170,19 @@ struct snd_ctl_elem_value32 { unsigned char reserved[128]; }; +#ifdef CONFIG_X86_X32 +/* x32 has a different alignment for 64bit values from ia32 */ +struct snd_ctl_elem_value_x32 { + struct snd_ctl_elem_id id; + unsigned int indirect; /* bit-field causes misalignment */ + union { + s32 integer[128]; + unsigned char data[512]; + s64 integer64[64]; + } value; + unsigned char reserved[128]; +}; +#endif /* CONFIG_X86_X32 */ /* get the value type and count of the control */ static int get_ctl_type(struct snd_card *card, struct snd_ctl_elem_id *id, @@ -219,9 +232,11 @@ static int get_elem_size(int type, int count) static int copy_ctl_value_from_user(struct snd_card *card, struct snd_ctl_elem_value *data, - struct snd_ctl_elem_value32 __user *data32, + void __user *userdata, + void __user *valuep, int *typep, int *countp) { + struct snd_ctl_elem_value32 __user *data32 = userdata; int i, type, size; int uninitialized_var(count); unsigned int indirect; @@ -239,8 +254,9 @@ static int copy_ctl_value_from_user(struct snd_card *card, if (type == SNDRV_CTL_ELEM_TYPE_BOOLEAN || type == SNDRV_CTL_ELEM_TYPE_INTEGER) { for (i = 0; i < count; i++) { + s32 __user *intp = valuep; int val; - if (get_user(val, &data32->value.integer[i])) + if (get_user(val, &intp[i])) return -EFAULT; data->value.integer.value[i] = val; } @@ -250,8 +266,7 @@ static int copy_ctl_value_from_user(struct snd_card *card, dev_err(card->dev, "snd_ioctl32_ctl_elem_value: unknown type %d\n", type); return -EINVAL; } - if (copy_from_user(data->value.bytes.data, - data32->value.data, size)) + if (copy_from_user(data->value.bytes.data, valuep, size)) return -EFAULT; } @@ -261,7 +276,8 @@ static int copy_ctl_value_from_user(struct snd_card *card, } /* restore the value to 32bit */ -static int copy_ctl_value_to_user(struct snd_ctl_elem_value32 __user *data32, +static int copy_ctl_value_to_user(void __user *userdata, + void __user *valuep, struct snd_ctl_elem_value *data, int type, int count) { @@ -270,22 +286,22 @@ static int copy_ctl_value_to_user(struct snd_ctl_elem_value32 __user *data32, if (type == SNDRV_CTL_ELEM_TYPE_BOOLEAN || type == SNDRV_CTL_ELEM_TYPE_INTEGER) { for (i = 0; i < count; i++) { + s32 __user *intp = valuep; int val; val = data->value.integer.value[i]; - if (put_user(val, &data32->value.integer[i])) + if (put_user(val, &intp[i])) return -EFAULT; } } else { size = get_elem_size(type, count); - if (copy_to_user(data32->value.data, - data->value.bytes.data, size)) + if (copy_to_user(valuep, data->value.bytes.data, size)) return -EFAULT; } return 0; } -static int snd_ctl_elem_read_user_compat(struct snd_card *card, - struct snd_ctl_elem_value32 __user *data32) +static int ctl_elem_read_user(struct snd_card *card, + void __user *userdata, void __user *valuep) { struct snd_ctl_elem_value *data; int err, type, count; @@ -294,7 +310,9 @@ static int snd_ctl_elem_read_user_compat(struct snd_card *card, if (data == NULL) return -ENOMEM; - if ((err = copy_ctl_value_from_user(card, data, data32, &type, &count)) < 0) + err = copy_ctl_value_from_user(card, data, userdata, valuep, + &type, &count); + if (err < 0) goto error; snd_power_lock(card); @@ -303,14 +321,15 @@ static int snd_ctl_elem_read_user_compat(struct snd_card *card, err = snd_ctl_elem_read(card, data); snd_power_unlock(card); if (err >= 0) - err = copy_ctl_value_to_user(data32, data, type, count); + err = copy_ctl_value_to_user(userdata, valuep, data, + type, count); error: kfree(data); return err; } -static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file, - struct snd_ctl_elem_value32 __user *data32) +static int ctl_elem_write_user(struct snd_ctl_file *file, + void __user *userdata, void __user *valuep) { struct snd_ctl_elem_value *data; struct snd_card *card = file->card; @@ -320,7 +339,9 @@ static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file, if (data == NULL) return -ENOMEM; - if ((err = copy_ctl_value_from_user(card, data, data32, &type, &count)) < 0) + err = copy_ctl_value_from_user(card, data, userdata, valuep, + &type, &count); + if (err < 0) goto error; snd_power_lock(card); @@ -329,12 +350,39 @@ static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file, err = snd_ctl_elem_write(card, file, data); snd_power_unlock(card); if (err >= 0) - err = copy_ctl_value_to_user(data32, data, type, count); + err = copy_ctl_value_to_user(userdata, valuep, data, + type, count); error: kfree(data); return err; } +static int snd_ctl_elem_read_user_compat(struct snd_card *card, + struct snd_ctl_elem_value32 __user *data32) +{ + return ctl_elem_read_user(card, data32, &data32->value); +} + +static int snd_ctl_elem_write_user_compat(struct snd_ctl_file *file, + struct snd_ctl_elem_value32 __user *data32) +{ + return ctl_elem_write_user(file, data32, &data32->value); +} + +#ifdef CONFIG_X86_X32 +static int snd_ctl_elem_read_user_x32(struct snd_card *card, + struct snd_ctl_elem_value_x32 __user *data32) +{ + return ctl_elem_read_user(card, data32, &data32->value); +} + +static int snd_ctl_elem_write_user_x32(struct snd_ctl_file *file, + struct snd_ctl_elem_value_x32 __user *data32) +{ + return ctl_elem_write_user(file, data32, &data32->value); +} +#endif /* CONFIG_X86_X32 */ + /* add or replace a user control */ static int snd_ctl_elem_add_compat(struct snd_ctl_file *file, struct snd_ctl_elem_info32 __user *data32, @@ -393,6 +441,10 @@ enum { SNDRV_CTL_IOCTL_ELEM_WRITE32 = _IOWR('U', 0x13, struct snd_ctl_elem_value32), SNDRV_CTL_IOCTL_ELEM_ADD32 = _IOWR('U', 0x17, struct snd_ctl_elem_info32), SNDRV_CTL_IOCTL_ELEM_REPLACE32 = _IOWR('U', 0x18, struct snd_ctl_elem_info32), +#ifdef CONFIG_X86_X32 + SNDRV_CTL_IOCTL_ELEM_READ_X32 = _IOWR('U', 0x12, struct snd_ctl_elem_value_x32), + SNDRV_CTL_IOCTL_ELEM_WRITE_X32 = _IOWR('U', 0x13, struct snd_ctl_elem_value_x32), +#endif /* CONFIG_X86_X32 */ }; static inline long snd_ctl_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) @@ -431,6 +483,12 @@ static inline long snd_ctl_ioctl_compat(struct file *file, unsigned int cmd, uns return snd_ctl_elem_add_compat(ctl, argp, 0); case SNDRV_CTL_IOCTL_ELEM_REPLACE32: return snd_ctl_elem_add_compat(ctl, argp, 1); +#ifdef CONFIG_X86_X32 + case SNDRV_CTL_IOCTL_ELEM_READ_X32: + return snd_ctl_elem_read_user_x32(ctl->card, argp); + case SNDRV_CTL_IOCTL_ELEM_WRITE_X32: + return snd_ctl_elem_write_user_x32(ctl, argp); +#endif /* CONFIG_X86_X32 */ } down_read(&snd_ioctl_rwsem); From 513ace79b657e2022a592e77f24074e088681ecc Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sun, 28 Feb 2016 11:23:09 +0100 Subject: [PATCH 239/417] ALSA: pcm: Fix ioctls for X32 ABI X32 ABI uses the 64bit timespec in addition to 64bit alignment of 64bit values. This leads to incompatibilities in some PCM ioctls involved with snd_pcm_channel_info, snd_pcm_status and snd_pcm_sync_ptr structs. Fix the PCM compat ABI for these ioctls like the previous commit for ctl API. Reported-by: Steven Newbury Cc: # v3.4+ Signed-off-by: Takashi Iwai --- sound/core/pcm_compat.c | 177 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 176 insertions(+), 1 deletion(-) diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c index 9630e9f72b7b..1f64ab0c2a95 100644 --- a/sound/core/pcm_compat.c +++ b/sound/core/pcm_compat.c @@ -183,6 +183,14 @@ static int snd_pcm_ioctl_channel_info_compat(struct snd_pcm_substream *substream return err; } +#ifdef CONFIG_X86_X32 +/* X32 ABI has the same struct as x86-64 for snd_pcm_channel_info */ +static int snd_pcm_channel_info_user(struct snd_pcm_substream *substream, + struct snd_pcm_channel_info __user *src); +#define snd_pcm_ioctl_channel_info_x32(s, p) \ + snd_pcm_channel_info_user(s, p) +#endif /* CONFIG_X86_X32 */ + struct snd_pcm_status32 { s32 state; struct compat_timespec trigger_tstamp; @@ -243,6 +251,71 @@ static int snd_pcm_status_user_compat(struct snd_pcm_substream *substream, return err; } +#ifdef CONFIG_X86_X32 +/* X32 ABI has 64bit timespec and 64bit alignment */ +struct snd_pcm_status_x32 { + s32 state; + u32 rsvd; /* alignment */ + struct timespec trigger_tstamp; + struct timespec tstamp; + u32 appl_ptr; + u32 hw_ptr; + s32 delay; + u32 avail; + u32 avail_max; + u32 overrange; + s32 suspended_state; + u32 audio_tstamp_data; + struct timespec audio_tstamp; + struct timespec driver_tstamp; + u32 audio_tstamp_accuracy; + unsigned char reserved[52-2*sizeof(struct timespec)]; +} __packed; + +#define put_timespec(src, dst) copy_to_user(dst, src, sizeof(*dst)) + +static int snd_pcm_status_user_x32(struct snd_pcm_substream *substream, + struct snd_pcm_status_x32 __user *src, + bool ext) +{ + struct snd_pcm_status status; + int err; + + memset(&status, 0, sizeof(status)); + /* + * with extension, parameters are read/write, + * get audio_tstamp_data from user, + * ignore rest of status structure + */ + if (ext && get_user(status.audio_tstamp_data, + (u32 __user *)(&src->audio_tstamp_data))) + return -EFAULT; + err = snd_pcm_status(substream, &status); + if (err < 0) + return err; + + if (clear_user(src, sizeof(*src))) + return -EFAULT; + if (put_user(status.state, &src->state) || + put_timespec(&status.trigger_tstamp, &src->trigger_tstamp) || + put_timespec(&status.tstamp, &src->tstamp) || + put_user(status.appl_ptr, &src->appl_ptr) || + put_user(status.hw_ptr, &src->hw_ptr) || + put_user(status.delay, &src->delay) || + put_user(status.avail, &src->avail) || + put_user(status.avail_max, &src->avail_max) || + put_user(status.overrange, &src->overrange) || + put_user(status.suspended_state, &src->suspended_state) || + put_user(status.audio_tstamp_data, &src->audio_tstamp_data) || + put_timespec(&status.audio_tstamp, &src->audio_tstamp) || + put_timespec(&status.driver_tstamp, &src->driver_tstamp) || + put_user(status.audio_tstamp_accuracy, &src->audio_tstamp_accuracy)) + return -EFAULT; + + return err; +} +#endif /* CONFIG_X86_X32 */ + /* both for HW_PARAMS and HW_REFINE */ static int snd_pcm_ioctl_hw_params_compat(struct snd_pcm_substream *substream, int refine, @@ -469,6 +542,93 @@ static int snd_pcm_ioctl_sync_ptr_compat(struct snd_pcm_substream *substream, return 0; } +#ifdef CONFIG_X86_X32 +/* X32 ABI has 64bit timespec and 64bit alignment */ +struct snd_pcm_mmap_status_x32 { + s32 state; + s32 pad1; + u32 hw_ptr; + u32 pad2; /* alignment */ + struct timespec tstamp; + s32 suspended_state; + struct timespec audio_tstamp; +} __packed; + +struct snd_pcm_mmap_control_x32 { + u32 appl_ptr; + u32 avail_min; +}; + +struct snd_pcm_sync_ptr_x32 { + u32 flags; + u32 rsvd; /* alignment */ + union { + struct snd_pcm_mmap_status_x32 status; + unsigned char reserved[64]; + } s; + union { + struct snd_pcm_mmap_control_x32 control; + unsigned char reserved[64]; + } c; +} __packed; + +static int snd_pcm_ioctl_sync_ptr_x32(struct snd_pcm_substream *substream, + struct snd_pcm_sync_ptr_x32 __user *src) +{ + struct snd_pcm_runtime *runtime = substream->runtime; + volatile struct snd_pcm_mmap_status *status; + volatile struct snd_pcm_mmap_control *control; + u32 sflags; + struct snd_pcm_mmap_control scontrol; + struct snd_pcm_mmap_status sstatus; + snd_pcm_uframes_t boundary; + int err; + + if (snd_BUG_ON(!runtime)) + return -EINVAL; + + if (get_user(sflags, &src->flags) || + get_user(scontrol.appl_ptr, &src->c.control.appl_ptr) || + get_user(scontrol.avail_min, &src->c.control.avail_min)) + return -EFAULT; + if (sflags & SNDRV_PCM_SYNC_PTR_HWSYNC) { + err = snd_pcm_hwsync(substream); + if (err < 0) + return err; + } + status = runtime->status; + control = runtime->control; + boundary = recalculate_boundary(runtime); + if (!boundary) + boundary = 0x7fffffff; + snd_pcm_stream_lock_irq(substream); + /* FIXME: we should consider the boundary for the sync from app */ + if (!(sflags & SNDRV_PCM_SYNC_PTR_APPL)) + control->appl_ptr = scontrol.appl_ptr; + else + scontrol.appl_ptr = control->appl_ptr % boundary; + if (!(sflags & SNDRV_PCM_SYNC_PTR_AVAIL_MIN)) + control->avail_min = scontrol.avail_min; + else + scontrol.avail_min = control->avail_min; + sstatus.state = status->state; + sstatus.hw_ptr = status->hw_ptr % boundary; + sstatus.tstamp = status->tstamp; + sstatus.suspended_state = status->suspended_state; + sstatus.audio_tstamp = status->audio_tstamp; + snd_pcm_stream_unlock_irq(substream); + if (put_user(sstatus.state, &src->s.status.state) || + put_user(sstatus.hw_ptr, &src->s.status.hw_ptr) || + put_timespec(&sstatus.tstamp, &src->s.status.tstamp) || + put_user(sstatus.suspended_state, &src->s.status.suspended_state) || + put_timespec(&sstatus.audio_tstamp, &src->s.status.audio_tstamp) || + put_user(scontrol.appl_ptr, &src->c.control.appl_ptr) || + put_user(scontrol.avail_min, &src->c.control.avail_min)) + return -EFAULT; + + return 0; +} +#endif /* CONFIG_X86_X32 */ /* */ @@ -487,7 +647,12 @@ enum { SNDRV_PCM_IOCTL_WRITEN_FRAMES32 = _IOW('A', 0x52, struct snd_xfern32), SNDRV_PCM_IOCTL_READN_FRAMES32 = _IOR('A', 0x53, struct snd_xfern32), SNDRV_PCM_IOCTL_SYNC_PTR32 = _IOWR('A', 0x23, struct snd_pcm_sync_ptr32), - +#ifdef CONFIG_X86_X32 + SNDRV_PCM_IOCTL_CHANNEL_INFO_X32 = _IOR('A', 0x32, struct snd_pcm_channel_info), + SNDRV_PCM_IOCTL_STATUS_X32 = _IOR('A', 0x20, struct snd_pcm_status_x32), + SNDRV_PCM_IOCTL_STATUS_EXT_X32 = _IOWR('A', 0x24, struct snd_pcm_status_x32), + SNDRV_PCM_IOCTL_SYNC_PTR_X32 = _IOWR('A', 0x23, struct snd_pcm_sync_ptr_x32), +#endif /* CONFIG_X86_X32 */ }; static long snd_pcm_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) @@ -559,6 +724,16 @@ static long snd_pcm_ioctl_compat(struct file *file, unsigned int cmd, unsigned l return snd_pcm_ioctl_rewind_compat(substream, argp); case SNDRV_PCM_IOCTL_FORWARD32: return snd_pcm_ioctl_forward_compat(substream, argp); +#ifdef CONFIG_X86_X32 + case SNDRV_PCM_IOCTL_STATUS_X32: + return snd_pcm_status_user_x32(substream, argp, false); + case SNDRV_PCM_IOCTL_STATUS_EXT_X32: + return snd_pcm_status_user_x32(substream, argp, true); + case SNDRV_PCM_IOCTL_SYNC_PTR_X32: + return snd_pcm_ioctl_sync_ptr_x32(substream, argp); + case SNDRV_PCM_IOCTL_CHANNEL_INFO_X32: + return snd_pcm_ioctl_channel_info_x32(substream, argp); +#endif /* CONFIG_X86_X32 */ } return -ENOIOCTLCMD; From dd7e3f805231cf83317c39bd346d5e4839f5cbb0 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sun, 28 Feb 2016 11:30:53 +0100 Subject: [PATCH 240/417] ALSA: rawmidi: Use comapt_put_timespec() Instead of open-coding, use the existing helper to copy a 32bit timespec from/to 64bit. Signed-off-by: Takashi Iwai --- sound/core/rawmidi_compat.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/sound/core/rawmidi_compat.c b/sound/core/rawmidi_compat.c index 5268c1f58c25..836d1c9fc2cc 100644 --- a/sound/core/rawmidi_compat.c +++ b/sound/core/rawmidi_compat.c @@ -85,8 +85,7 @@ static int snd_rawmidi_ioctl_status_compat(struct snd_rawmidi_file *rfile, if (err < 0) return err; - if (put_user(status.tstamp.tv_sec, &src->tstamp.tv_sec) || - put_user(status.tstamp.tv_nsec, &src->tstamp.tv_nsec) || + if (compat_put_timespec(&status.tstamp, &src->tstamp) || put_user(status.avail, &src->avail) || put_user(status.xruns, &src->xruns)) return -EFAULT; From 2251fbbc1539f05b0b206b37a602d5776be37252 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sun, 28 Feb 2016 11:28:08 +0100 Subject: [PATCH 241/417] ALSA: rawmidi: Fix ioctls X32 ABI Like the previous fixes for ctl and PCM, we need a fix for incompatible X32 ABI regarding the rawmidi: namely, struct snd_rawmidi_status has the timespec, and the size and the alignment on X32 differ from IA32. This patch fixes the incompatible ioctl for X32. Cc: # v3.4+ Signed-off-by: Takashi Iwai --- sound/core/rawmidi_compat.c | 53 +++++++++++++++++++++++++++++++++++++ 1 file changed, 53 insertions(+) diff --git a/sound/core/rawmidi_compat.c b/sound/core/rawmidi_compat.c index 836d1c9fc2cc..f69764d7cdd7 100644 --- a/sound/core/rawmidi_compat.c +++ b/sound/core/rawmidi_compat.c @@ -93,9 +93,58 @@ static int snd_rawmidi_ioctl_status_compat(struct snd_rawmidi_file *rfile, return 0; } +#ifdef CONFIG_X86_X32 +/* X32 ABI has 64bit timespec and 64bit alignment */ +struct snd_rawmidi_status_x32 { + s32 stream; + u32 rsvd; /* alignment */ + struct timespec tstamp; + u32 avail; + u32 xruns; + unsigned char reserved[16]; +} __attribute__((packed)); + +#define put_timespec(src, dst) copy_to_user(dst, src, sizeof(*dst)) + +static int snd_rawmidi_ioctl_status_x32(struct snd_rawmidi_file *rfile, + struct snd_rawmidi_status_x32 __user *src) +{ + int err; + struct snd_rawmidi_status status; + + if (rfile->output == NULL) + return -EINVAL; + if (get_user(status.stream, &src->stream)) + return -EFAULT; + + switch (status.stream) { + case SNDRV_RAWMIDI_STREAM_OUTPUT: + err = snd_rawmidi_output_status(rfile->output, &status); + break; + case SNDRV_RAWMIDI_STREAM_INPUT: + err = snd_rawmidi_input_status(rfile->input, &status); + break; + default: + return -EINVAL; + } + if (err < 0) + return err; + + if (put_timespec(&status.tstamp, &src->tstamp) || + put_user(status.avail, &src->avail) || + put_user(status.xruns, &src->xruns)) + return -EFAULT; + + return 0; +} +#endif /* CONFIG_X86_X32 */ + enum { SNDRV_RAWMIDI_IOCTL_PARAMS32 = _IOWR('W', 0x10, struct snd_rawmidi_params32), SNDRV_RAWMIDI_IOCTL_STATUS32 = _IOWR('W', 0x20, struct snd_rawmidi_status32), +#ifdef CONFIG_X86_X32 + SNDRV_RAWMIDI_IOCTL_STATUS_X32 = _IOWR('W', 0x20, struct snd_rawmidi_status_x32), +#endif /* CONFIG_X86_X32 */ }; static long snd_rawmidi_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) @@ -114,6 +163,10 @@ static long snd_rawmidi_ioctl_compat(struct file *file, unsigned int cmd, unsign return snd_rawmidi_ioctl_params_compat(rfile, argp); case SNDRV_RAWMIDI_IOCTL_STATUS32: return snd_rawmidi_ioctl_status_compat(rfile, argp); +#ifdef CONFIG_X86_X32 + case SNDRV_RAWMIDI_IOCTL_STATUS_X32: + return snd_rawmidi_ioctl_status_x32(rfile, argp); +#endif /* CONFIG_X86_X32 */ } return -ENOIOCTLCMD; } From 3a72494ac2a3bd229db941d51e7efe2f6ccd947b Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sun, 28 Feb 2016 11:36:14 +0100 Subject: [PATCH 242/417] ALSA: timer: Fix broken compat timer user status ioctl The timer user status compat ioctl returned the bogus struct used for 64bit architectures instead of the 32bit one. This patch addresses it to return the proper struct. Cc: Signed-off-by: Takashi Iwai --- sound/core/timer_compat.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/sound/core/timer_compat.c b/sound/core/timer_compat.c index e05802ae6e1b..8e7eddf35c6a 100644 --- a/sound/core/timer_compat.c +++ b/sound/core/timer_compat.c @@ -70,13 +70,14 @@ static int snd_timer_user_status_compat(struct file *file, struct snd_timer_status32 __user *_status) { struct snd_timer_user *tu; - struct snd_timer_status status; + struct snd_timer_status32 status; tu = file->private_data; if (snd_BUG_ON(!tu->timeri)) return -ENXIO; memset(&status, 0, sizeof(status)); - status.tstamp = tu->tstamp; + status.tstamp.tv_sec = tu->tstamp.tv_sec; + status.tstamp.tv_nsec = tu->tstamp.tv_nsec; status.resolution = snd_timer_resolution(tu->timeri); status.lost = tu->timeri->lost; status.overrun = tu->overrun; From b24e7ad1fdc22177eb3e51584e1cfcb45d818488 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sun, 28 Feb 2016 11:41:47 +0100 Subject: [PATCH 243/417] ALSA: timer: Fix ioctls for X32 ABI X32 ABI takes the 64bit timespec, thus the timer user status ioctl becomes incompatible with IA32. This results in NOTTY error when the ioctl is issued. Meanwhile, this struct in X32 is essentially identical with the one in X86-64, so we can just bypassing to the existing code for this specific compat ioctl. Cc: # v3.4+ Signed-off-by: Takashi Iwai --- sound/core/timer_compat.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/sound/core/timer_compat.c b/sound/core/timer_compat.c index 8e7eddf35c6a..2e908225d754 100644 --- a/sound/core/timer_compat.c +++ b/sound/core/timer_compat.c @@ -89,12 +89,21 @@ static int snd_timer_user_status_compat(struct file *file, return 0; } +#ifdef CONFIG_X86_X32 +/* X32 ABI has the same struct as x86-64 */ +#define snd_timer_user_status_x32(file, s) \ + snd_timer_user_status(file, s) +#endif /* CONFIG_X86_X32 */ + /* */ enum { SNDRV_TIMER_IOCTL_INFO32 = _IOR('T', 0x11, struct snd_timer_info32), SNDRV_TIMER_IOCTL_STATUS32 = _IOW('T', 0x14, struct snd_timer_status32), +#ifdef CONFIG_X86_X32 + SNDRV_TIMER_IOCTL_STATUS_X32 = _IOW('T', 0x14, struct snd_timer_status), +#endif /* CONFIG_X86_X32 */ }; static long snd_timer_user_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) @@ -123,6 +132,10 @@ static long snd_timer_user_ioctl_compat(struct file *file, unsigned int cmd, uns return snd_timer_user_info_compat(file, argp); case SNDRV_TIMER_IOCTL_STATUS32: return snd_timer_user_status_compat(file, argp); +#ifdef CONFIG_X86_X32 + case SNDRV_TIMER_IOCTL_STATUS_X32: + return snd_timer_user_status_x32(file, argp); +#endif /* CONFIG_X86_X32 */ } return -ENOIOCTLCMD; } From deb7deff2f00bdbbcb3d560dad2a89ef37df837d Mon Sep 17 00:00:00 2001 From: Justin Maggard Date: Tue, 9 Feb 2016 15:52:08 -0800 Subject: [PATCH 244/417] cifs: fix out-of-bounds access in lease parsing When opening a file, SMB2_open() attempts to parse the lease state from the SMB2 CREATE Response. However, the parsing code was not careful to ensure that the create contexts are not empty or invalid, which can lead to out- of-bounds memory access. This can be seen easily by trying to read a file from a OSX 10.11 SMB3 server. Here is sample crash output: BUG: unable to handle kernel paging request at ffff8800a1a77cc6 IP: [] SMB2_open+0x804/0x960 PGD 8f77067 PUD 0 Oops: 0000 [#1] SMP Modules linked in: CPU: 3 PID: 2876 Comm: cp Not tainted 4.5.0-rc3.x86_64.1+ #14 Hardware name: NETGEAR ReadyNAS 314 /ReadyNAS 314 , BIOS 4.6.5 10/11/2012 task: ffff880073cdc080 ti: ffff88005b31c000 task.ti: ffff88005b31c000 RIP: 0010:[] [] SMB2_open+0x804/0x960 RSP: 0018:ffff88005b31fa08 EFLAGS: 00010282 RAX: 0000000000000015 RBX: 0000000000000000 RCX: 0000000000000006 RDX: 0000000000000000 RSI: 0000000000000246 RDI: ffff88007eb8c8b0 RBP: ffff88005b31fad8 R08: 666666203d206363 R09: 6131613030383866 R10: 3030383866666666 R11: 00000000000002b0 R12: ffff8800660fd800 R13: ffff8800a1a77cc2 R14: 00000000424d53fe R15: ffff88005f5a28c0 FS: 00007f7c8a2897c0(0000) GS:ffff88007eb80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: ffff8800a1a77cc6 CR3: 000000005b281000 CR4: 00000000000006e0 Stack: ffff88005b31fa70 ffffffff88278789 00000000000001d3 ffff88005f5a2a80 ffffffff00000003 ffff88005d029d00 ffff88006fde05a0 0000000000000000 ffff88005b31fc78 ffff88006fde0780 ffff88005b31fb2f 0000000100000fe0 Call Trace: [] ? cifsConvertToUTF16+0x159/0x2d0 [] smb2_open_file+0x98/0x210 [] ? __kmalloc+0x1c/0xe0 [] cifs_open+0x2a4/0x720 [] do_dentry_open+0x1ff/0x310 [] ? cifsFileInfo_get+0x30/0x30 [] vfs_open+0x52/0x60 [] path_openat+0x170/0xf70 [] ? remove_wait_queue+0x48/0x50 [] do_filp_open+0x79/0xd0 [] ? __alloc_fd+0x3a/0x170 [] do_sys_open+0x114/0x1e0 [] SyS_open+0x19/0x20 [] entry_SYSCALL_64_fastpath+0x12/0x6a Code: 4d 8d 6c 07 04 31 c0 4c 89 ee e8 47 6f e5 ff 31 c9 41 89 ce 44 89 f1 48 c7 c7 28 b1 bd 88 31 c0 49 01 cd 4c 89 ee e8 2b 6f e5 ff <45> 0f b7 75 04 48 c7 c7 31 b1 bd 88 31 c0 4d 01 ee 4c 89 f6 e8 RIP [] SMB2_open+0x804/0x960 RSP CR2: ffff8800a1a77cc6 ---[ end trace d9f69ba64feee469 ]--- Signed-off-by: Justin Maggard Signed-off-by: Steve French CC: Stable --- fs/cifs/smb2pdu.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 10f8d5cf5681..42e1f440eb1e 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1106,21 +1106,25 @@ parse_lease_state(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp, { char *data_offset; struct create_context *cc; - unsigned int next = 0; + unsigned int next; + unsigned int remaining; char *name; data_offset = (char *)rsp + 4 + le32_to_cpu(rsp->CreateContextsOffset); + remaining = le32_to_cpu(rsp->CreateContextsLength); cc = (struct create_context *)data_offset; - do { - cc = (struct create_context *)((char *)cc + next); + while (remaining >= sizeof(struct create_context)) { name = le16_to_cpu(cc->NameOffset) + (char *)cc; - if (le16_to_cpu(cc->NameLength) != 4 || - strncmp(name, "RqLs", 4)) { - next = le32_to_cpu(cc->Next); - continue; - } - return server->ops->parse_lease_buf(cc, epoch); - } while (next != 0); + if (le16_to_cpu(cc->NameLength) == 4 && + strncmp(name, "RqLs", 4) == 0) + return server->ops->parse_lease_buf(cc, epoch); + + next = le32_to_cpu(cc->Next); + if (!next) + break; + remaining -= next; + cc = (struct create_context *)((char *)cc + next); + } return 0; } From 6cc3b24235929b54acd5ecc987ef11a425bd209e Mon Sep 17 00:00:00 2001 From: Pavel Shilovsky Date: Sat, 27 Feb 2016 11:58:18 +0300 Subject: [PATCH 245/417] CIFS: Fix SMB2+ interim response processing for read requests For interim responses we only need to parse a header and update a number credits. Now it is done for all SMB2+ command except SMB2_READ which is wrong. Fix this by adding such processing. Signed-off-by: Pavel Shilovsky Tested-by: Shirish Pargaonkar CC: Stable Signed-off-by: Steve French --- fs/cifs/cifssmb.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 90b4f9f7de66..76fcb50295a3 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -1396,11 +1396,10 @@ CIFS_open(const unsigned int xid, struct cifs_open_parms *oparms, int *oplock, * current bigbuf. */ static int -cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) +discard_remaining_data(struct TCP_Server_Info *server) { unsigned int rfclen = get_rfc1002_length(server->smallbuf); int remaining = rfclen + 4 - server->total_read; - struct cifs_readdata *rdata = mid->callback_data; while (remaining > 0) { int length; @@ -1414,10 +1413,20 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) remaining -= length; } - dequeue_mid(mid, rdata->result); return 0; } +static int +cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) +{ + int length; + struct cifs_readdata *rdata = mid->callback_data; + + length = discard_remaining_data(server); + dequeue_mid(mid, rdata->result); + return length; +} + int cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) { @@ -1446,6 +1455,12 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) return length; server->total_read += length; + if (server->ops->is_status_pending && + server->ops->is_status_pending(buf, server, 0)) { + discard_remaining_data(server); + return -1; + } + /* Was the SMB read successful? */ rdata->result = server->ops->map_error(buf, false); if (rdata->result != 0) { From 1ee9f4bd1a97026a7b2d7ae9f1f74b45680d0003 Mon Sep 17 00:00:00 2001 From: Yadan Fan Date: Mon, 29 Feb 2016 14:44:57 +0800 Subject: [PATCH 246/417] Fix cifs_uniqueid_to_ino_t() function for s390x This issue is caused by commit 02323db17e3a7 ("cifs: fix cifs_uniqueid_to_ino_t not to ever return 0"), when BITS_PER_LONG is 64 on s390x, the corresponding cifs_uniqueid_to_ino_t() function will cast 64-bit fileid to 32-bit by using (ino_t)fileid, because ino_t (typdefed __kernel_ino_t) is int type. It's defined in arch/s390/include/uapi/asm/posix_types.h #ifndef __s390x__ typedef unsigned long __kernel_ino_t; ... #else /* __s390x__ */ typedef unsigned int __kernel_ino_t; So the #ifdef condition is wrong for s390x, we can just still use one cifs_uniqueid_to_ino_t() function with comparing sizeof(ino_t) and sizeof(u64) to choose the correct execution accordingly. Signed-off-by: Yadan Fan CC: stable Signed-off-by: Steve French --- fs/cifs/cifsfs.h | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 68c4547528c4..83aac8ba50b0 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -31,19 +31,15 @@ * so that it will fit. We use hash_64 to convert the value to 31 bits, and * then add 1, to ensure that we don't end up with a 0 as the value. */ -#if BITS_PER_LONG == 64 static inline ino_t cifs_uniqueid_to_ino_t(u64 fileid) { + if ((sizeof(ino_t)) < (sizeof(u64))) + return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1; + return (ino_t)fileid; + } -#else -static inline ino_t -cifs_uniqueid_to_ino_t(u64 fileid) -{ - return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1; -} -#endif extern struct file_system_type cifs_fs_type; extern const struct address_space_operations cifs_addr_ops; From 4cad67fca3fc952d6f2ed9e799621f07666a560f Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Sun, 28 Feb 2016 17:32:07 +0200 Subject: [PATCH 247/417] arm/arm64: KVM: Fix ioctl error handling Calling return copy_to_user(...) in an ioctl will not do the right thing if there's a pagefault: copy_to_user returns the number of bytes not copied in this case. Fix up kvm to do return copy_to_user(...)) ? -EFAULT : 0; everywhere. Cc: stable@vger.kernel.org Acked-by: Christoffer Dall Signed-off-by: Michael S. Tsirkin Signed-off-by: Marc Zyngier --- arch/arm/kvm/guest.c | 2 +- arch/arm64/kvm/guest.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index 5fa69d7bae58..99361f11354a 100644 --- a/arch/arm/kvm/guest.c +++ b/arch/arm/kvm/guest.c @@ -161,7 +161,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) u64 val; val = kvm_arm_timer_get_reg(vcpu, reg->id); - return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)); + return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0; } static unsigned long num_core_regs(void) diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index fcb778899a38..9e54ad7c240a 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -194,7 +194,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) u64 val; val = kvm_arm_timer_get_reg(vcpu, reg->id); - return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)); + return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0; } /** From 71e60073ca7b5f931b16f29add16c68b2e06949a Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Tue, 16 Feb 2016 12:29:46 +0100 Subject: [PATCH 248/417] MIPS: jz4740: Fix surviving instance of irq_to_gpio() This is fallout from commit 832f5dacfa0b ("MIPS: Remove all the uses of custom gpio.h"). Signed-off-by: Ralf Baechle Suggested-by: Lars-Peter Clausen --- arch/mips/jz4740/gpio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/jz4740/gpio.c b/arch/mips/jz4740/gpio.c index 8c6d76c9b2d6..d9907e57e9b9 100644 --- a/arch/mips/jz4740/gpio.c +++ b/arch/mips/jz4740/gpio.c @@ -270,7 +270,7 @@ uint32_t jz_gpio_port_get_value(int port, uint32_t mask) } EXPORT_SYMBOL(jz_gpio_port_get_value); -#define IRQ_TO_BIT(irq) BIT(irq_to_gpio(irq) & 0x1f) +#define IRQ_TO_BIT(irq) BIT((irq - JZ4740_IRQ_GPIO(0)) & 0x1f) static void jz_gpio_check_trigger_both(struct jz_gpio_chip *chip, unsigned int irq) { From 51ff5d7767eae285969da75c209e9425d84b012d Mon Sep 17 00:00:00 2001 From: Daniel Sanders Date: Tue, 23 Feb 2016 10:29:20 +0000 Subject: [PATCH 249/417] MIPS: Avoid variant of .type unsupported by LLVM Assembler The target independent parts of the LLVM Lexer considers 'fault@function' to be a single token representing the 'fault' symbol with a 'function' modifier. However, this is not the case in the .type directive where 'function' refers to STT_FUNC from the ELF standard. Although GAS accepts it, '.type symbol@function' is an undocumented form of this directive. The documentation specifies a comma between the symbol and '@function'. Signed-off-by: Scott Egerton Signed-off-by: Daniel Sanders Reviewed-by: Maciej W. Rozycki Cc: Paul Burton Cc: Leonid Yegoshin Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/12587/ Signed-off-by: Ralf Baechle --- arch/mips/kernel/r2300_fpu.S | 2 +- arch/mips/kernel/r4k_fpu.S | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/mips/kernel/r2300_fpu.S b/arch/mips/kernel/r2300_fpu.S index 5ce3b746cedc..b4ac6374a38f 100644 --- a/arch/mips/kernel/r2300_fpu.S +++ b/arch/mips/kernel/r2300_fpu.S @@ -125,7 +125,7 @@ LEAF(_restore_fp_context) END(_restore_fp_context) .set reorder - .type fault@function + .type fault, @function .ent fault fault: li v0, -EFAULT jr ra diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S index f09546ee2cdc..17732f876eff 100644 --- a/arch/mips/kernel/r4k_fpu.S +++ b/arch/mips/kernel/r4k_fpu.S @@ -358,7 +358,7 @@ LEAF(_restore_msa_all_upper) .set reorder - .type fault@function + .type fault, @function .ent fault fault: li v0, -EFAULT # failure jr ra From 923adb1646d5ba739d2a1e63ee20d60574d9da8e Mon Sep 17 00:00:00 2001 From: Frederic Barrat Date: Wed, 24 Feb 2016 18:27:51 +0100 Subject: [PATCH 250/417] cxl: Fix PSL timebase synchronization detection The PSL timebase synchronization is seemingly failing for configuration not including VIRT_CPU_ACCOUNTING_NATIVE. The driver shows the following trace in dmesg: PSL: Timebase sync: giving up! The PSL timebase register is actually syncing correctly, but the cxl driver is not detecting it. Fix is to use the proper timebase-to-time conversion. Signed-off-by: Frederic Barrat Cc: # 4.3+ Acked-by: Michael Neuling Reviewed-by: Matthew R. Ochs Acked-by: Ian Munsie Reviewed-by: Andrew Donnellan Reviewed-by: Vaibhav Jain Signed-off-by: Michael Ellerman --- drivers/misc/cxl/pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index 4c1903f781fc..0c6c17a1c59e 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -415,7 +415,7 @@ static int cxl_setup_psl_timebase(struct cxl *adapter, struct pci_dev *dev) delta = mftb() - psl_tb; if (delta < 0) delta = -delta; - } while (cputime_to_usecs(delta) > 16); + } while (tb_to_ns(delta) > 16000); return 0; } From 56fa81fc9a5445938f3aa2e63d15ab63dc938ad6 Mon Sep 17 00:00:00 2001 From: Govindraj Raja Date: Mon, 29 Feb 2016 11:41:20 +0000 Subject: [PATCH 251/417] MIPS: scache: Fix scache init with invalid line size. In current scache init cache line_size is determined from cpu config register, however if there there no scache then mips_sc_probe_cm3 function populates a invalid line_size of 2. The invalid line_size can cause a NULL pointer deference during r4k_dma_cache_inv as r4k_blast_scache is populated based on line_size. Scache line_size of 2 is invalid option in r4k_blast_scache_setup. This issue was faced during a MIPS I6400 based virtual platform bring up where scache was not available in virtual platform model. Signed-off-by: Govindraj Raja Fixes: 7d53e9c4cd21("MIPS: CM3: Add support for CM3 L2 cache.") Cc: Paul Burton Cc: James Hogan Cc: Ralf Baechle Cc: James Hartley Cc: linux-mips@linux-mips.org Cc: stable@vger.kernel.org # v4.2+ Patchwork: https://patchwork.linux-mips.org/patch/12710/ Signed-off-by: Ralf Baechle --- arch/mips/mm/sc-mips.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c index 249647578e58..91dec32c77b7 100644 --- a/arch/mips/mm/sc-mips.c +++ b/arch/mips/mm/sc-mips.c @@ -164,11 +164,13 @@ static int __init mips_sc_probe_cm3(void) sets = cfg & CM_GCR_L2_CONFIG_SET_SIZE_MSK; sets >>= CM_GCR_L2_CONFIG_SET_SIZE_SHF; - c->scache.sets = 64 << sets; + if (sets) + c->scache.sets = 64 << sets; line_sz = cfg & CM_GCR_L2_CONFIG_LINE_SIZE_MSK; line_sz >>= CM_GCR_L2_CONFIG_LINE_SIZE_SHF; - c->scache.linesz = 2 << line_sz; + if (line_sz) + c->scache.linesz = 2 << line_sz; assoc = cfg & CM_GCR_L2_CONFIG_ASSOC_MSK; assoc >>= CM_GCR_L2_CONFIG_ASSOC_SHF; @@ -176,9 +178,12 @@ static int __init mips_sc_probe_cm3(void) c->scache.waysize = c->scache.sets * c->scache.linesz; c->scache.waybit = __ffs(c->scache.waysize); - c->scache.flags &= ~MIPS_CACHE_NOT_PRESENT; + if (c->scache.linesz) { + c->scache.flags &= ~MIPS_CACHE_NOT_PRESENT; + return 1; + } - return 1; + return 0; } static inline int __init mips_sc_probe(void) From 887349f69f37e71e2a8bfbd743831625a0b2ff51 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Sun, 28 Feb 2016 17:35:59 +0200 Subject: [PATCH 252/417] MIPS: kvm: Fix ioctl error handling. Calling return copy_to_user(...) or return copy_from_user in an ioctl will not do the right thing if there's a pagefault: copy_to_user/copy_from_user return the number of bytes not copied in this case. Fix up kvm on mips to do return copy_to_user(...)) ? -EFAULT : 0; and return copy_from_user(...)) ? -EFAULT : 0; everywhere. Signed-off-by: Michael S. Tsirkin Cc: Paolo Bonzini Cc: James Hogan Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Cc: stable@vger.kernel.org Cc: kvm@vger.kernel.org Patchwork: https://patchwork.linux-mips.org/patch/12709/ Signed-off-by: Ralf Baechle --- arch/mips/kvm/mips.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 8bc3977576e6..3110447ab1e9 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -702,7 +702,7 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, } else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) { void __user *uaddr = (void __user *)(long)reg->addr; - return copy_to_user(uaddr, vs, 16); + return copy_to_user(uaddr, vs, 16) ? -EFAULT : 0; } else { return -EINVAL; } @@ -732,7 +732,7 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, } else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) { void __user *uaddr = (void __user *)(long)reg->addr; - return copy_from_user(vs, uaddr, 16); + return copy_from_user(vs, uaddr, 16) ? -EFAULT : 0; } else { return -EINVAL; } From b6809ee573cc2f8de97f7c8f45eacc5db1129060 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 26 Feb 2016 16:48:59 +0100 Subject: [PATCH 253/417] iommu/amd: Detach device from domain before removal Detach the device that is about to be removed from its domain (if it has one) to clear any related state like DTE entry and device's ATS state. Reported-by: Kelly Zytaruk Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index e5e223938eec..374c129219ef 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -114,6 +114,7 @@ struct kmem_cache *amd_iommu_irq_cache; static void update_domain(struct protection_domain *domain); static int protection_domain_init(struct protection_domain *domain); +static void detach_device(struct device *dev); /* * For dynamic growth the aperture size is split into ranges of 128MB of @@ -384,6 +385,9 @@ static void iommu_uninit_device(struct device *dev) if (!dev_data) return; + if (dev_data->domain) + detach_device(dev); + iommu_device_unlink(amd_iommu_rlookup_table[dev_data->devid]->iommu_dev, dev); From 537e48136295c5860a92138c5ea3959b9542868b Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 29 Feb 2016 14:25:16 +0100 Subject: [PATCH 254/417] ALSA: hdspm: Fix wrong boolean ctl value accesses snd-hdspm driver accesses enum item values (int) instead of boolean values (long) wrongly for some ctl elements. This patch fixes them. Cc: Signed-off-by: Takashi Iwai --- sound/pci/rme9652/hdspm.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c index 8bc8016c173d..b047b1ba48fd 100644 --- a/sound/pci/rme9652/hdspm.c +++ b/sound/pci/rme9652/hdspm.c @@ -2261,7 +2261,7 @@ static int snd_hdspm_put_system_sample_rate(struct snd_kcontrol *kcontrol, { struct hdspm *hdspm = snd_kcontrol_chip(kcontrol); - hdspm_set_dds_value(hdspm, ucontrol->value.enumerated.item[0]); + hdspm_set_dds_value(hdspm, ucontrol->value.integer.value[0]); return 0; } @@ -4449,7 +4449,7 @@ static int snd_hdspm_get_tco_word_term(struct snd_kcontrol *kcontrol, { struct hdspm *hdspm = snd_kcontrol_chip(kcontrol); - ucontrol->value.enumerated.item[0] = hdspm->tco->term; + ucontrol->value.integer.value[0] = hdspm->tco->term; return 0; } @@ -4460,8 +4460,8 @@ static int snd_hdspm_put_tco_word_term(struct snd_kcontrol *kcontrol, { struct hdspm *hdspm = snd_kcontrol_chip(kcontrol); - if (hdspm->tco->term != ucontrol->value.enumerated.item[0]) { - hdspm->tco->term = ucontrol->value.enumerated.item[0]; + if (hdspm->tco->term != ucontrol->value.integer.value[0]) { + hdspm->tco->term = ucontrol->value.integer.value[0]; hdspm_tco_write(hdspm); From c1099c3294c2344110085a38c50e478a5992b368 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 29 Feb 2016 14:32:42 +0100 Subject: [PATCH 255/417] ALSA: hdspm: Fix zero-division HDSPM driver contains a code issuing zero-division potentially in system sample rate ctl code. This patch fixes it by not processing a zero or invalid rate value as a divisor, as well as excluding the invalid value to be passed via the given ctl element. Cc: Signed-off-by: Takashi Iwai --- sound/pci/rme9652/hdspm.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c index b047b1ba48fd..a4a999a0317e 100644 --- a/sound/pci/rme9652/hdspm.c +++ b/sound/pci/rme9652/hdspm.c @@ -1601,6 +1601,9 @@ static void hdspm_set_dds_value(struct hdspm *hdspm, int rate) { u64 n; + if (snd_BUG_ON(rate <= 0)) + return; + if (rate >= 112000) rate /= 4; else if (rate >= 56000) @@ -2215,6 +2218,8 @@ static int hdspm_get_system_sample_rate(struct hdspm *hdspm) } else { /* slave mode, return external sample rate */ rate = hdspm_external_sample_rate(hdspm); + if (!rate) + rate = hdspm->system_sample_rate; } } @@ -2260,7 +2265,10 @@ static int snd_hdspm_put_system_sample_rate(struct snd_kcontrol *kcontrol, ucontrol) { struct hdspm *hdspm = snd_kcontrol_chip(kcontrol); + int rate = ucontrol->value.integer.value[0]; + if (rate < 27000 || rate > 207000) + return -EINVAL; hdspm_set_dds_value(hdspm, ucontrol->value.integer.value[0]); return 0; } From eab3c4db193f5fcccf70e884de9a922ca2c63d80 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 29 Feb 2016 14:26:43 +0100 Subject: [PATCH 256/417] ALSA: hdsp: Fix wrong boolean ctl value accesses snd-hdsp driver accesses enum item values (int) instead of boolean values (long) wrongly for some ctl elements. This patch fixes them. Cc: Signed-off-by: Takashi Iwai --- sound/pci/rme9652/hdsp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/pci/rme9652/hdsp.c b/sound/pci/rme9652/hdsp.c index 2875b4f6d8c9..7c8941b8b2de 100644 --- a/sound/pci/rme9652/hdsp.c +++ b/sound/pci/rme9652/hdsp.c @@ -2879,7 +2879,7 @@ static int snd_hdsp_get_dds_offset(struct snd_kcontrol *kcontrol, struct snd_ctl { struct hdsp *hdsp = snd_kcontrol_chip(kcontrol); - ucontrol->value.enumerated.item[0] = hdsp_dds_offset(hdsp); + ucontrol->value.integer.value[0] = hdsp_dds_offset(hdsp); return 0; } @@ -2891,7 +2891,7 @@ static int snd_hdsp_put_dds_offset(struct snd_kcontrol *kcontrol, struct snd_ctl if (!snd_hdsp_use_is_exclusive(hdsp)) return -EBUSY; - val = ucontrol->value.enumerated.item[0]; + val = ucontrol->value.integer.value[0]; spin_lock_irq(&hdsp->lock); if (val != hdsp_dds_offset(hdsp)) change = (hdsp_set_dds_offset(hdsp, val) == 0) ? 1 : 0; From a528aca7f359f4b0b1d72ae406097e491a5ba9ea Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 29 Feb 2016 12:12:46 -0500 Subject: [PATCH 257/417] use ->d_seq to get coherency between ->d_inode and ->d_flags Games with ordering and barriers are way too brittle. Just bump ->d_seq before and after updating ->d_inode and ->d_flags type bits, so that verifying ->d_seq would guarantee they are coherent. Cc: stable@vger.kernel.org # v3.13+ Signed-off-by: Al Viro --- fs/dcache.c | 20 +++++--------------- include/linux/dcache.h | 4 +--- 2 files changed, 6 insertions(+), 18 deletions(-) diff --git a/fs/dcache.c b/fs/dcache.c index 92d5140de851..2398f9f94337 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -269,9 +269,6 @@ static inline int dname_external(const struct dentry *dentry) return dentry->d_name.name != dentry->d_iname; } -/* - * Make sure other CPUs see the inode attached before the type is set. - */ static inline void __d_set_inode_and_type(struct dentry *dentry, struct inode *inode, unsigned type_flags) @@ -279,28 +276,18 @@ static inline void __d_set_inode_and_type(struct dentry *dentry, unsigned flags; dentry->d_inode = inode; - smp_wmb(); flags = READ_ONCE(dentry->d_flags); flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); flags |= type_flags; WRITE_ONCE(dentry->d_flags, flags); } -/* - * Ideally, we want to make sure that other CPUs see the flags cleared before - * the inode is detached, but this is really a violation of RCU principles - * since the ordering suggests we should always set inode before flags. - * - * We should instead replace or discard the entire dentry - but that sucks - * performancewise on mass deletion/rename. - */ static inline void __d_clear_type_and_inode(struct dentry *dentry) { unsigned flags = READ_ONCE(dentry->d_flags); flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); WRITE_ONCE(dentry->d_flags, flags); - smp_wmb(); dentry->d_inode = NULL; } @@ -370,9 +357,11 @@ static void dentry_unlink_inode(struct dentry * dentry) __releases(dentry->d_inode->i_lock) { struct inode *inode = dentry->d_inode; + + raw_write_seqcount_begin(&dentry->d_seq); __d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_u.d_alias); - dentry_rcuwalk_invalidate(dentry); + raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) @@ -1758,8 +1747,9 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) spin_lock(&dentry->d_lock); if (inode) hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); + raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); - dentry_rcuwalk_invalidate(dentry); + raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); fsnotify_d_instantiate(dentry, inode); } diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 7781ce110503..c4b5f4b3f8f8 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -409,9 +409,7 @@ static inline bool d_mountpoint(const struct dentry *dentry) */ static inline unsigned __d_entry_type(const struct dentry *dentry) { - unsigned type = READ_ONCE(dentry->d_flags); - smp_rmb(); - return type & DCACHE_ENTRY_TYPE; + return dentry->d_flags & DCACHE_ENTRY_TYPE; } static inline bool d_is_miss(const struct dentry *dentry) From 013dd239d6220a4e0dfdf0d45a82c34f1fd73deb Mon Sep 17 00:00:00 2001 From: Patrik Halfar Date: Sat, 20 Feb 2016 18:49:56 +0100 Subject: [PATCH 258/417] USB: qcserial: add Dell Wireless 5809e Gobi 4G HSPA+ (rev3) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit New revision of Dell Wireless 5809e Gobi 4G HSPA+ Mobile Broadband Card has new idProduct. Bus 002 Device 006: ID 413c:81b3 Dell Computer Corp. Device Descriptor: bLength 18 bDescriptorType 1 bcdUSB 2.00 bDeviceClass 0 bDeviceSubClass 0 bDeviceProtocol 0 bMaxPacketSize0 64 idVendor 0x413c Dell Computer Corp. idProduct 0x81b3 bcdDevice 0.06 iManufacturer 1 Sierra Wireless, Incorporated iProduct 2 Dell Wireless 5809e Gobi™ 4G HSPA+ Mobile Broadband Card iSerial 3 bNumConfigurations 2 Signed-off-by: Patrik Halfar Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/qcserial.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index 9919d2a9faf2..9c09d5feb50d 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -165,6 +165,7 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x413c, 0x81a8)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a9)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81b1)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */ + {DEVICE_SWI(0x413c, 0x81b3)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ /* Huawei devices */ {DEVICE_HWI(0x03f0, 0x581d)}, /* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */ From 3c4c615d70c8cbdc8ba8c79ed702640930652a79 Mon Sep 17 00:00:00 2001 From: Vittorio Alfieri Date: Sun, 28 Feb 2016 14:40:24 +0100 Subject: [PATCH 259/417] USB: cp210x: Add ID for Parrot NMEA GPS Flight Recorder The Parrot NMEA GPS Flight Recorder is a USB composite device consisting of hub, flash storage, and cp210x usb to serial chip. It is an accessory to the mass-produced Parrot AR Drone 2. The device emits standard NMEA messages which make the it compatible with NMEA compatible software. It was tested using gpsd version 3.11-3 as an NMEA interpreter and using the official Parrot Flight Recorder. Signed-off-by: Vittorio Alfieri Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/cp210x.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 7c319e7edda2..73a366de5102 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -165,6 +165,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x18EF, 0xE025) }, /* ELV Marble Sound Board 1 */ { USB_DEVICE(0x1901, 0x0190) }, /* GE B850 CP2105 Recorder interface */ { USB_DEVICE(0x1901, 0x0193) }, /* GE B650 CP2104 PMC interface */ + { USB_DEVICE(0x19CF, 0x3000) }, /* Parrot NMEA GPS Flight Recorder */ { USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */ { USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */ { USB_DEVICE(0x1BA4, 0x0002) }, /* Silicon Labs 358x factory default */ From d243bed32f5042582896237f88fa1798aee55ff9 Mon Sep 17 00:00:00 2001 From: Tirumalesh Chalamarla Date: Tue, 16 Feb 2016 12:08:49 -0800 Subject: [PATCH 260/417] ahci: Workaround for ThunderX Errata#22536 Due to Errata in ThunderX, HOST_IRQ_STAT should be cleared before leaving the interrupt handler. The patch attempts to satisfy the need. Changes from V2: - removed newfile - code is now under CONFIG_ARM64 Changes from V1: - Rebased on top of libata/for-4.6 - Moved ThunderX intr handler to new file tj: Minor adjustments to comments. Signed-off-by: Tirumalesh Chalamarla Signed-off-by: Tejun Heo --- drivers/ata/ahci.c | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index b6263b3996ab..146dc0b8ec61 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1331,6 +1331,44 @@ static inline void ahci_gtf_filter_workaround(struct ata_host *host) {} #endif +#ifdef CONFIG_ARM64 +/* + * Due to ERRATA#22536, ThunderX needs to handle HOST_IRQ_STAT differently. + * Workaround is to make sure all pending IRQs are served before leaving + * handler. + */ +static irqreturn_t ahci_thunderx_irq_handler(int irq, void *dev_instance) +{ + struct ata_host *host = dev_instance; + struct ahci_host_priv *hpriv; + unsigned int rc = 0; + void __iomem *mmio; + u32 irq_stat, irq_masked; + unsigned int handled = 1; + + VPRINTK("ENTER\n"); + hpriv = host->private_data; + mmio = hpriv->mmio; + irq_stat = readl(mmio + HOST_IRQ_STAT); + if (!irq_stat) + return IRQ_NONE; + + do { + irq_masked = irq_stat & hpriv->port_map; + spin_lock(&host->lock); + rc = ahci_handle_port_intr(host, irq_masked); + if (!rc) + handled = 0; + writel(irq_stat, mmio + HOST_IRQ_STAT); + irq_stat = readl(mmio + HOST_IRQ_STAT); + spin_unlock(&host->lock); + } while (irq_stat); + VPRINTK("EXIT\n"); + + return IRQ_RETVAL(handled); +} +#endif + /* * ahci_init_msix() - optionally enable per-port MSI-X otherwise defer * to single msi. @@ -1566,6 +1604,11 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (ahci_broken_devslp(pdev)) hpriv->flags |= AHCI_HFLAG_NO_DEVSLP; +#ifdef CONFIG_ARM64 + if (pdev->vendor == 0x177d && pdev->device == 0xa01c) + hpriv->irq_handler = ahci_thunderx_irq_handler; +#endif + /* save initial config */ ahci_pci_save_initial_config(pdev, hpriv); From dc8b4afc4a04fac8ee55a19b59f2356a25e7e778 Mon Sep 17 00:00:00 2001 From: Manuel Lauss Date: Sat, 27 Feb 2016 16:10:05 +0100 Subject: [PATCH 261/417] ata: ahci: don't mark HotPlugCapable Ports as external/removable The HPCP bit is set by bioses for on-board sata ports either because they think sata is hotplug capable in general or to allow Windows to display a "device eject" icon on ports which are routed to an external connector bracket. However in Redhat Bugzilla #1310682, users report that with kernel 4.4, where this bit test first appeared, a lot of partitions on sata drives are now mounted automatically. This patch should fix redhat and a lot of other distros which unconditionally automount all devices which have the "removable" bit set. Signed-off-by: Manuel Lauss Signed-off-by: Tejun Heo Fixes: 8a3e33cf92c7 ("ata: ahci: find eSATA ports and flag them as removable" changes userspace behavior) Link: http://lkml.kernel.org/g/56CF35FA.1070500@redhat.com Cc: stable@vger.kernel.org #v4.4+ --- drivers/ata/libahci.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 513b3fa74d78..85ea5142a095 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -1168,8 +1168,7 @@ static void ahci_port_init(struct device *dev, struct ata_port *ap, /* mark esata ports */ tmp = readl(port_mmio + PORT_CMD); - if ((tmp & PORT_CMD_HPCP) || - ((tmp & PORT_CMD_ESP) && (hpriv->cap & HOST_CAP_SXS))) + if ((tmp & PORT_CMD_ESP) && (hpriv->cap & HOST_CAP_SXS)) ap->pflags |= ATA_PFLAG_EXTERNAL; } From a6522c08987daa6f9ac25a9c08870041a43db6b0 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Thu, 25 Feb 2016 13:02:50 -0500 Subject: [PATCH 262/417] 3c59x: mask LAST_FRAG bit from length field in ring Recently, I fixed a bug in 3c59x: commit 6e144419e4da11a9a4977c8d899d7247d94ca338 Author: Neil Horman Date: Wed Jan 13 12:43:54 2016 -0500 3c59x: fix another page map/single unmap imbalance Which correctly rebalanced dma mapping and unmapping types. Unfortunately it introduced a new bug which causes oopses on older systems. When mapping dma regions, the last entry for a packet in the 3c59x tx ring encodes a LAST_FRAG bit, which is encoded as the high order bit of the buffers length field. When it is unmapped the LAST_FRAG bit is cleared prior to being passed to the unmap function. Unfortunately the commit above fails to do that masking. It was missed in testing because the system on which I tested it had an intel iommu, the driver for which ignores the size field, using only the DMA address as the token to identify the mapping to be released. However, on older systems that rely on swiotlb (or other dma drivers that key off that length field), not masking off that LAST_FRAG high order bit results in parsing a huge size to be release, leading to all sorts of odd corruptions and the like. Fix is easy, just mask the length with 0xFFF. It should really be &(LAST_FRAG-1), but 0xFFF is the style of the file, and I'd like to make this fix minimal and correct before making it prettier. Appies to the net tree cleanly. All testing on both iommu and swiommu based systems produce good results Signed-off-by: Neil Horman CC: Steffen Klassert CC: "David S. Miller" Signed-off-by: David S. Miller --- drivers/net/ethernet/3com/3c59x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 79e1a0282163..17b2126075e0 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -2461,7 +2461,7 @@ boomerang_interrupt(int irq, void *dev_id) int i; pci_unmap_single(VORTEX_PCI(vp), le32_to_cpu(vp->tx_ring[entry].frag[0].addr), - le32_to_cpu(vp->tx_ring[entry].frag[0].length), + le32_to_cpu(vp->tx_ring[entry].frag[0].length)&0xFFF, PCI_DMA_TODEVICE); for (i=1; i<=skb_shinfo(skb)->nr_frags; i++) From e6a8c9b337eed56eb481e1b4dd2180c25a1e5310 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 29 Feb 2016 23:49:47 +0100 Subject: [PATCH 263/417] iommu/vt-d: Use BUS_NOTIFY_REMOVED_DEVICE in hotplug path In the PCI hotplug path of the Intel IOMMU driver, replace the usage of the BUS_NOTIFY_DEL_DEVICE notifier, which is executed before the driver is unbound from the device, with BUS_NOTIFY_REMOVED_DEVICE, which runs after that. This fixes a kernel BUG being triggered in the VT-d code when the device driver tries to unmap DMA buffers and the VT-d driver already destroyed all mappings. Reported-by: Stefani Seibold Cc: stable@vger.kernel.org # v4.3+ Signed-off-by: Joerg Roedel --- drivers/iommu/dmar.c | 5 +++-- drivers/iommu/intel-iommu.c | 4 ++-- 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index fb092f3f11cb..8ffd7568fc91 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -329,7 +329,8 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb, /* Only care about add/remove events for physical functions */ if (pdev->is_virtfn) return NOTIFY_DONE; - if (action != BUS_NOTIFY_ADD_DEVICE && action != BUS_NOTIFY_DEL_DEVICE) + if (action != BUS_NOTIFY_ADD_DEVICE && + action != BUS_NOTIFY_REMOVED_DEVICE) return NOTIFY_DONE; info = dmar_alloc_pci_notify_info(pdev, action); @@ -339,7 +340,7 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb, down_write(&dmar_global_lock); if (action == BUS_NOTIFY_ADD_DEVICE) dmar_pci_bus_add_dev(info); - else if (action == BUS_NOTIFY_DEL_DEVICE) + else if (action == BUS_NOTIFY_REMOVED_DEVICE) dmar_pci_bus_del_dev(info); up_write(&dmar_global_lock); diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 986a53e3eb96..a2e1b7f14df2 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -4367,7 +4367,7 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) rmrru->devices_cnt); if(ret < 0) return ret; - } else if (info->event == BUS_NOTIFY_DEL_DEVICE) { + } else if (info->event == BUS_NOTIFY_REMOVED_DEVICE) { dmar_remove_dev_scope(info, rmrr->segment, rmrru->devices, rmrru->devices_cnt); } @@ -4387,7 +4387,7 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) break; else if(ret < 0) return ret; - } else if (info->event == BUS_NOTIFY_DEL_DEVICE) { + } else if (info->event == BUS_NOTIFY_REMOVED_DEVICE) { if (dmar_remove_dev_scope(info, atsr->segment, atsru->devices, atsru->devices_cnt)) break; From 79e3f4a853ed161cd4c06d84b50beebf961a47c6 Mon Sep 17 00:00:00 2001 From: Murali Karicheri Date: Mon, 29 Feb 2016 17:18:22 -0600 Subject: [PATCH 264/417] PCI: keystone: Fix MSI code that retrieves struct pcie_port pointer Commit cbce7900598c ("PCI: designware: Make driver arch-agnostic") changed the host bridge sysdata pointer from the ARM pci_sys_data to the DesignWare pcie_port structure, and changed pcie-designware.c to reflect that. But it did not change the corresponding code in pci-keystone-dw.c, so it caused crashes on Keystone: Unable to handle kernel NULL pointer dereference at virtual address 00000030 pgd = c0003000 [00000030] *pgd=80000800004003, *pmd=00000000 Internal error: Oops: 206 [#1] PREEMPT SMP ARM CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.4.2-00139-gb74f926 #2 Hardware name: Keystone PC is at ks_dw_pcie_msi_irq_unmask+0x24/0x58 Change pci-keystone-dw.c to expect sysdata to be the struct pcie_port pointer. [bhelgaas: changelog] Fixes: cbce7900598c ("PCI: designware: Make driver arch-agnostic") Signed-off-by: Murali Karicheri Signed-off-by: Bjorn Helgaas CC: stable@vger.kernel.org # v4.4+ CC: Zhou Wang --- drivers/pci/host/pci-keystone-dw.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/drivers/pci/host/pci-keystone-dw.c b/drivers/pci/host/pci-keystone-dw.c index ed34c9520a02..6153853ca9c3 100644 --- a/drivers/pci/host/pci-keystone-dw.c +++ b/drivers/pci/host/pci-keystone-dw.c @@ -58,11 +58,6 @@ #define to_keystone_pcie(x) container_of(x, struct keystone_pcie, pp) -static inline struct pcie_port *sys_to_pcie(struct pci_sys_data *sys) -{ - return sys->private_data; -} - static inline void update_reg_offset_bit_pos(u32 offset, u32 *reg_offset, u32 *bit_pos) { @@ -108,7 +103,7 @@ static void ks_dw_pcie_msi_irq_ack(struct irq_data *d) struct pcie_port *pp; msi = irq_data_get_msi_desc(d); - pp = sys_to_pcie(msi_desc_to_pci_sysdata(msi)); + pp = (struct pcie_port *) msi_desc_to_pci_sysdata(msi); ks_pcie = to_keystone_pcie(pp); offset = d->irq - irq_linear_revmap(pp->irq_domain, 0); update_reg_offset_bit_pos(offset, ®_offset, &bit_pos); @@ -146,7 +141,7 @@ static void ks_dw_pcie_msi_irq_mask(struct irq_data *d) u32 offset; msi = irq_data_get_msi_desc(d); - pp = sys_to_pcie(msi_desc_to_pci_sysdata(msi)); + pp = (struct pcie_port *) msi_desc_to_pci_sysdata(msi); ks_pcie = to_keystone_pcie(pp); offset = d->irq - irq_linear_revmap(pp->irq_domain, 0); @@ -167,7 +162,7 @@ static void ks_dw_pcie_msi_irq_unmask(struct irq_data *d) u32 offset; msi = irq_data_get_msi_desc(d); - pp = sys_to_pcie(msi_desc_to_pci_sysdata(msi)); + pp = (struct pcie_port *) msi_desc_to_pci_sysdata(msi); ks_pcie = to_keystone_pcie(pp); offset = d->irq - irq_linear_revmap(pp->irq_domain, 0); From 1195c103f6c98d9ff381cac3a8760d4f8a133627 Mon Sep 17 00:00:00 2001 From: Minghuan Lian Date: Mon, 29 Feb 2016 17:24:15 -0600 Subject: [PATCH 265/417] PCI: layerscape: Fix MSG TLP drop setting Some kinds of Layerscape PCIe controllers will forward the received message TLPs to system application address space, which could corrupt system memory or lead to a system hang. Enable MSG_DROP to fix this issue. Signed-off-by: Minghuan Lian Signed-off-by: Bjorn Helgaas --- drivers/pci/host/pci-layerscape.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/drivers/pci/host/pci-layerscape.c b/drivers/pci/host/pci-layerscape.c index 3923bed93c7e..f39961bcf7aa 100644 --- a/drivers/pci/host/pci-layerscape.c +++ b/drivers/pci/host/pci-layerscape.c @@ -77,6 +77,16 @@ static void ls_pcie_fix_class(struct ls_pcie *pcie) iowrite16(PCI_CLASS_BRIDGE_PCI, pcie->dbi + PCI_CLASS_DEVICE); } +/* Drop MSG TLP except for Vendor MSG */ +static void ls_pcie_drop_msg_tlp(struct ls_pcie *pcie) +{ + u32 val; + + val = ioread32(pcie->dbi + PCIE_STRFMR1); + val &= 0xDFFFFFFF; + iowrite32(val, pcie->dbi + PCIE_STRFMR1); +} + static int ls1021_pcie_link_up(struct pcie_port *pp) { u32 state; @@ -97,7 +107,7 @@ static int ls1021_pcie_link_up(struct pcie_port *pp) static void ls1021_pcie_host_init(struct pcie_port *pp) { struct ls_pcie *pcie = to_ls_pcie(pp); - u32 val, index[2]; + u32 index[2]; pcie->scfg = syscon_regmap_lookup_by_phandle(pp->dev->of_node, "fsl,pcie-scfg"); @@ -116,13 +126,7 @@ static void ls1021_pcie_host_init(struct pcie_port *pp) dw_pcie_setup_rc(pp); - /* - * LS1021A Workaround for internal TKT228622 - * to fix the INTx hang issue - */ - val = ioread32(pcie->dbi + PCIE_STRFMR1); - val &= 0xffff; - iowrite32(val, pcie->dbi + PCIE_STRFMR1); + ls_pcie_drop_msg_tlp(pcie); } static int ls_pcie_link_up(struct pcie_port *pp) @@ -147,6 +151,7 @@ static void ls_pcie_host_init(struct pcie_port *pp) iowrite32(1, pcie->dbi + PCIE_DBI_RO_WR_EN); ls_pcie_fix_class(pcie); ls_pcie_clear_multifunction(pcie); + ls_pcie_drop_msg_tlp(pcie); iowrite32(0, pcie->dbi + PCIE_DBI_RO_WR_EN); } From 5adebafb75bdfbbe4ec69f14c3613e70f6ed7f6f Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sun, 21 Feb 2016 18:12:26 +0200 Subject: [PATCH 266/417] IB/core: Fix missed clean call in registration path In case of failure returned from query function in IB device registration, we need to clean IB cache which was missed. This change fixes it. Fixes: 3e153a93a1c1 ('IB/core: Save the device attributes on the device structure') Signed-off-by: Leon Romanovsky Reviewed-by: Ira Weiny Reviewed-by: Sagi Grimberg Signed-off-by: Doug Ledford --- drivers/infiniband/core/device.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 00da80e02154..94b80a51ab68 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -358,6 +358,7 @@ int ib_register_device(struct ib_device *device, ret = device->query_device(device, &device->attrs, &uhw); if (ret) { printk(KERN_WARNING "Couldn't query the device attributes\n"); + ib_cache_cleanup_one(device); goto out; } From ddd30ef4741c30945e43a2956bfbc3afe74a73b5 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 29 Feb 2016 17:04:20 +0100 Subject: [PATCH 267/417] cpufreq: qoriq: allow building as module with THERMAL=m My previous patch to avoid link errors with the qoriq cpufreq driver disallowed all of the broken cases, but also prevented the driver from being built when CONFIG_THERMAL is a module. This changes the dependency to allow the cpufreq driver to also be a module in this case, just not built-in. Signed-off-by: Arnd Bergmann Fixes: 8ae1702a0df5 (cpufreq: qoriq: Register cooling device based on device tree) Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index 659879a56dba..f93511031177 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -296,6 +296,7 @@ endif config QORIQ_CPUFREQ tristate "CPU frequency scaling driver for Freescale QorIQ SoCs" depends on OF && COMMON_CLK && (PPC_E500MC || ARM) + depends on !CPU_THERMAL || THERMAL select CLK_QORIQ help This adds the CPUFreq driver support for Freescale QorIQ SoCs From 3c2002aec3ee3a9fc86ff8f8618f1253c94ec919 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 29 Feb 2016 17:04:21 +0100 Subject: [PATCH 268/417] cpufreq: mediatek: allow building as a module The MT8173 cpufreq driver can currently only be built-in, but it has a Kconfig dependency on the thermal core. THERMAL can be a loadable module, which in turn makes this driver impossible to build. It is nicer to make the cpufreq driver a module as well, so this patch turns the option in to a 'tristate' and adapts the dependency accordingly. The driver has no module_exit() function, so it will continue to not support unloading, but it can be built as a module and loaded at runtime now. Signed-off-by: Arnd Bergmann Fixes: 5269e7067cd6 (cpufreq: Add ARM_MT8173_CPUFREQ dependency on THERMAL) Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/Kconfig.arm | 4 ++-- drivers/cpufreq/mt8173-cpufreq.c | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index 0031069b64c9..14b1f9393b05 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -84,10 +84,10 @@ config ARM_KIRKWOOD_CPUFREQ SoCs. config ARM_MT8173_CPUFREQ - bool "Mediatek MT8173 CPUFreq support" + tristate "Mediatek MT8173 CPUFreq support" depends on ARCH_MEDIATEK && REGULATOR depends on ARM64 || (ARM_CPU_TOPOLOGY && COMPILE_TEST) - depends on !CPU_THERMAL || THERMAL=y + depends on !CPU_THERMAL || THERMAL select PM_OPP help This adds the CPUFreq driver support for Mediatek MT8173 SoC. diff --git a/drivers/cpufreq/mt8173-cpufreq.c b/drivers/cpufreq/mt8173-cpufreq.c index 1efba340456d..2058e6d292ce 100644 --- a/drivers/cpufreq/mt8173-cpufreq.c +++ b/drivers/cpufreq/mt8173-cpufreq.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include From ead8f34c701ec7bf3234118b8c746227f30dfd1a Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 25 Feb 2016 21:10:28 +0000 Subject: [PATCH 269/417] drm/i915: Balance assert_rpm_wakelock_held() for !IS_ENABLED(CONFIG_PM) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 09731280028ce03e6a27e1998137f1775a2839f3 Author: Imre Deak Date: Wed Feb 17 14:17:42 2016 +0200 drm/i915: Add helper to get a display power ref if it was already enabled left the rpm wakelock assertions unbalanced if CONFIG_PM was disabled as intel_runtime_pm_get_if_in_use() would return true without incrementing the local bookkeeping required for the assertions. Signed-off-by: Chris Wilson CC: Mika Kuoppala CC: Joonas Lahtinen CC: Ville Syrjälä Reviewed-by: Imre Deak Signed-off-by: Dave Airlie --- drivers/gpu/drm/i915/intel_runtime_pm.c | 26 ++++++++++++------------- 1 file changed, 12 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index 678ed3475d7e..92f8d96ef9c5 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -2349,22 +2349,20 @@ bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv) { struct drm_device *dev = dev_priv->dev; struct device *device = &dev->pdev->dev; - int ret; - if (!IS_ENABLED(CONFIG_PM)) - return true; + if (IS_ENABLED(CONFIG_PM)) { + int ret = pm_runtime_get_if_in_use(device); - ret = pm_runtime_get_if_in_use(device); - - /* - * In cases runtime PM is disabled by the RPM core and we get an - * -EINVAL return value we are not supposed to call this function, - * since the power state is undefined. This applies atm to the - * late/early system suspend/resume handlers. - */ - WARN_ON_ONCE(ret < 0); - if (ret <= 0) - return false; + /* + * In cases runtime PM is disabled by the RPM core and we get + * an -EINVAL return value we are not supposed to call this + * function, since the power state is undefined. This applies + * atm to the late/early system suspend/resume handlers. + */ + WARN_ON_ONCE(ret < 0); + if (ret <= 0) + return false; + } atomic_inc(&dev_priv->pm.wakeref_count); assert_rpm_wakelock_held(dev_priv); From 22be3b105597002ad3499bdb9c0aba49c9ab05f7 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sun, 17 Jan 2016 11:47:29 -0500 Subject: [PATCH 270/417] sparc32: Add -Wa,-Av8 to KBUILD_CFLAGS. Binutils used to be (erroneously) extremely permissive about instruction usage. But that got fixed and if you don't properly tell it to accept classes of instructions it will fail. This uncovered a specs bug on sparc in gcc where it wouldn't pass the proper options to binutils options. Deal with this in the kernel build by adding -Wa,-Av8 to KBUILD_CFLAGS. Reported-by: Al Viro Signed-off-by: David S. Miller --- arch/sparc/Makefile | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/sparc/Makefile b/arch/sparc/Makefile index eaee14637d93..8496a074bd0e 100644 --- a/arch/sparc/Makefile +++ b/arch/sparc/Makefile @@ -24,7 +24,13 @@ LDFLAGS := -m elf32_sparc export BITS := 32 UTS_MACHINE := sparc +# We are adding -Wa,-Av8 to KBUILD_CFLAGS to deal with a specs bug in some +# versions of gcc. Some gcc versions won't pass -Av8 to binutils when you +# give -mcpu=v8. This silently worked with older bintutils versions but +# does not any more. KBUILD_CFLAGS += -m32 -mcpu=v8 -pipe -mno-fpu -fcall-used-g5 -fcall-used-g7 +KBUILD_CFLAGS += -Wa,-Av8 + KBUILD_AFLAGS += -m32 -Wa,-Av8 else From 397d1533b6cce0ccb5379542e2e6d079f6936c46 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 1 Mar 2016 00:25:32 -0500 Subject: [PATCH 271/417] sparc64: Fix sparc64_set_context stack handling. Like a signal return, we should use synchronize_user_stack() rather than flush_user_windows(). Reported-by: Ilya Malakhov Signed-off-by: David S. Miller --- arch/sparc/kernel/signal_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index d88beff47bab..39aaec173f66 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -52,7 +52,7 @@ asmlinkage void sparc64_set_context(struct pt_regs *regs) unsigned char fenab; int err; - flush_user_windows(); + synchronize_user_stack(); if (get_thread_wsaved() || (((unsigned long)ucp) & (sizeof(unsigned long)-1)) || (!__access_ok(ucp, sizeof(*ucp)))) From 5deef5551c77e488922cc4bf4bc76df63be650d0 Mon Sep 17 00:00:00 2001 From: Daniele Palmas Date: Mon, 29 Feb 2016 15:36:11 +0100 Subject: [PATCH 272/417] USB: serial: option: add support for Telit LE922 PID 0x1045 This patch adds support for 0x1045 PID of Telit LE922. Signed-off-by: Daniele Palmas Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 8849439a8f18..8cea03fbdbf0 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -270,6 +270,7 @@ static void option_instat_callback(struct urb *urb); #define TELIT_PRODUCT_UE910_V2 0x1012 #define TELIT_PRODUCT_LE922_USBCFG0 0x1042 #define TELIT_PRODUCT_LE922_USBCFG3 0x1043 +#define TELIT_PRODUCT_LE922_USBCFG5 0x1045 #define TELIT_PRODUCT_LE920 0x1200 #define TELIT_PRODUCT_LE910 0x1201 @@ -1183,6 +1184,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG3), .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG5, 0xff), + .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910), .driver_info = (kernel_ulong_t)&telit_le910_blacklist }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920), From c0992d0f54847d0d1d85c60fcaa054f175ab1ccd Mon Sep 17 00:00:00 2001 From: Yegor Yefremov Date: Mon, 29 Feb 2016 16:39:57 +0100 Subject: [PATCH 273/417] USB: serial: option: add support for Quectel UC20 Add support for Quectel UC20 and blacklist the QMI interface. Signed-off-by: Yegor Yefremov Cc: stable [johan: amend commit message ] Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 8cea03fbdbf0..348e19834b83 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1133,6 +1133,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */ + { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9003), /* Quectel UC20 */ + .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6003), From 537b8a8695ea0fbc857fe68f99cd5294f8fca5e3 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 29 Feb 2016 18:56:02 +0100 Subject: [PATCH 274/417] Revert "USB: serial: add Moxa UPORT 11x0 driver" This reverts commit 0b2b093ad405b56a9e6f4f20a25da77ebfa9549c. Turns out the MOXA vendor driver was basically just a copy of the ti_usb_3410_5052 driver. We don't want two drivers for the same chip even if mxu11x0 had gotten some much needed clean up before merge. So let's remove the mxu11x0 driver, add support for these Moxa devices to the TI driver, and then clean that driver up instead. Signed-off-by: Johan Hovold Acked-by: Greg Kroah-Hartman --- drivers/usb/serial/Kconfig | 16 - drivers/usb/serial/Makefile | 1 - drivers/usb/serial/mxu11x0.c | 1006 ---------------------------------- 3 files changed, 1023 deletions(-) delete mode 100644 drivers/usb/serial/mxu11x0.c diff --git a/drivers/usb/serial/Kconfig b/drivers/usb/serial/Kconfig index f612dda9c977..56ecb8b5115d 100644 --- a/drivers/usb/serial/Kconfig +++ b/drivers/usb/serial/Kconfig @@ -475,22 +475,6 @@ config USB_SERIAL_MOS7840 To compile this driver as a module, choose M here: the module will be called mos7840. If unsure, choose N. -config USB_SERIAL_MXUPORT11 - tristate "USB Moxa UPORT 11x0 Serial Driver" - ---help--- - Say Y here if you want to use a MOXA UPort 11x0 Serial hub. - - This driver supports: - - - UPort 1110 : 1 port RS-232 USB to Serial Hub. - - UPort 1130 : 1 port RS-422/485 USB to Serial Hub. - - UPort 1130I : 1 port RS-422/485 USB to Serial Hub with Isolation. - - UPort 1150 : 1 port RS-232/422/485 USB to Serial Hub. - - UPort 1150I : 1 port RS-232/422/485 USB to Serial Hub with Isolation. - - To compile this driver as a module, choose M here: the - module will be called mxu11x0. - config USB_SERIAL_MXUPORT tristate "USB Moxa UPORT Serial Driver" ---help--- diff --git a/drivers/usb/serial/Makefile b/drivers/usb/serial/Makefile index f3fa5e53702d..349d9df0895f 100644 --- a/drivers/usb/serial/Makefile +++ b/drivers/usb/serial/Makefile @@ -38,7 +38,6 @@ obj-$(CONFIG_USB_SERIAL_METRO) += metro-usb.o obj-$(CONFIG_USB_SERIAL_MOS7720) += mos7720.o obj-$(CONFIG_USB_SERIAL_MOS7840) += mos7840.o obj-$(CONFIG_USB_SERIAL_MXUPORT) += mxuport.o -obj-$(CONFIG_USB_SERIAL_MXUPORT11) += mxu11x0.o obj-$(CONFIG_USB_SERIAL_NAVMAN) += navman.o obj-$(CONFIG_USB_SERIAL_OMNINET) += omninet.o obj-$(CONFIG_USB_SERIAL_OPTICON) += opticon.o diff --git a/drivers/usb/serial/mxu11x0.c b/drivers/usb/serial/mxu11x0.c deleted file mode 100644 index 619607323bfd..000000000000 --- a/drivers/usb/serial/mxu11x0.c +++ /dev/null @@ -1,1006 +0,0 @@ -/* - * USB Moxa UPORT 11x0 Serial Driver - * - * Copyright (C) 2007 MOXA Technologies Co., Ltd. - * Copyright (C) 2015 Mathieu Othacehe - * - * 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; either version 2 of the License, or - * (at your option) any later version. - * - * - * Supports the following Moxa USB to serial converters: - * UPort 1110, 1 port RS-232 USB to Serial Hub. - * UPort 1130, 1 port RS-422/485 USB to Serial Hub. - * UPort 1130I, 1 port RS-422/485 USB to Serial Hub with isolation - * protection. - * UPort 1150, 1 port RS-232/422/485 USB to Serial Hub. - * UPort 1150I, 1 port RS-232/422/485 USB to Serial Hub with isolation - * protection. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -/* Vendor and product ids */ -#define MXU1_VENDOR_ID 0x110a -#define MXU1_1110_PRODUCT_ID 0x1110 -#define MXU1_1130_PRODUCT_ID 0x1130 -#define MXU1_1150_PRODUCT_ID 0x1150 -#define MXU1_1151_PRODUCT_ID 0x1151 -#define MXU1_1131_PRODUCT_ID 0x1131 - -/* Commands */ -#define MXU1_GET_VERSION 0x01 -#define MXU1_GET_PORT_STATUS 0x02 -#define MXU1_GET_PORT_DEV_INFO 0x03 -#define MXU1_GET_CONFIG 0x04 -#define MXU1_SET_CONFIG 0x05 -#define MXU1_OPEN_PORT 0x06 -#define MXU1_CLOSE_PORT 0x07 -#define MXU1_START_PORT 0x08 -#define MXU1_STOP_PORT 0x09 -#define MXU1_TEST_PORT 0x0A -#define MXU1_PURGE_PORT 0x0B -#define MXU1_RESET_EXT_DEVICE 0x0C -#define MXU1_GET_OUTQUEUE 0x0D -#define MXU1_WRITE_DATA 0x80 -#define MXU1_READ_DATA 0x81 -#define MXU1_REQ_TYPE_CLASS 0x82 - -/* Module identifiers */ -#define MXU1_I2C_PORT 0x01 -#define MXU1_IEEE1284_PORT 0x02 -#define MXU1_UART1_PORT 0x03 -#define MXU1_UART2_PORT 0x04 -#define MXU1_RAM_PORT 0x05 - -/* Modem status */ -#define MXU1_MSR_DELTA_CTS 0x01 -#define MXU1_MSR_DELTA_DSR 0x02 -#define MXU1_MSR_DELTA_RI 0x04 -#define MXU1_MSR_DELTA_CD 0x08 -#define MXU1_MSR_CTS 0x10 -#define MXU1_MSR_DSR 0x20 -#define MXU1_MSR_RI 0x40 -#define MXU1_MSR_CD 0x80 -#define MXU1_MSR_DELTA_MASK 0x0F -#define MXU1_MSR_MASK 0xF0 - -/* Line status */ -#define MXU1_LSR_OVERRUN_ERROR 0x01 -#define MXU1_LSR_PARITY_ERROR 0x02 -#define MXU1_LSR_FRAMING_ERROR 0x04 -#define MXU1_LSR_BREAK 0x08 -#define MXU1_LSR_ERROR 0x0F -#define MXU1_LSR_RX_FULL 0x10 -#define MXU1_LSR_TX_EMPTY 0x20 - -/* Modem control */ -#define MXU1_MCR_LOOP 0x04 -#define MXU1_MCR_DTR 0x10 -#define MXU1_MCR_RTS 0x20 - -/* Mask settings */ -#define MXU1_UART_ENABLE_RTS_IN 0x0001 -#define MXU1_UART_DISABLE_RTS 0x0002 -#define MXU1_UART_ENABLE_PARITY_CHECKING 0x0008 -#define MXU1_UART_ENABLE_DSR_OUT 0x0010 -#define MXU1_UART_ENABLE_CTS_OUT 0x0020 -#define MXU1_UART_ENABLE_X_OUT 0x0040 -#define MXU1_UART_ENABLE_XA_OUT 0x0080 -#define MXU1_UART_ENABLE_X_IN 0x0100 -#define MXU1_UART_ENABLE_DTR_IN 0x0800 -#define MXU1_UART_DISABLE_DTR 0x1000 -#define MXU1_UART_ENABLE_MS_INTS 0x2000 -#define MXU1_UART_ENABLE_AUTO_START_DMA 0x4000 -#define MXU1_UART_SEND_BREAK_SIGNAL 0x8000 - -/* Parity */ -#define MXU1_UART_NO_PARITY 0x00 -#define MXU1_UART_ODD_PARITY 0x01 -#define MXU1_UART_EVEN_PARITY 0x02 -#define MXU1_UART_MARK_PARITY 0x03 -#define MXU1_UART_SPACE_PARITY 0x04 - -/* Stop bits */ -#define MXU1_UART_1_STOP_BITS 0x00 -#define MXU1_UART_1_5_STOP_BITS 0x01 -#define MXU1_UART_2_STOP_BITS 0x02 - -/* Bits per character */ -#define MXU1_UART_5_DATA_BITS 0x00 -#define MXU1_UART_6_DATA_BITS 0x01 -#define MXU1_UART_7_DATA_BITS 0x02 -#define MXU1_UART_8_DATA_BITS 0x03 - -/* Operation modes */ -#define MXU1_UART_232 0x00 -#define MXU1_UART_485_RECEIVER_DISABLED 0x01 -#define MXU1_UART_485_RECEIVER_ENABLED 0x02 - -/* Pipe transfer mode and timeout */ -#define MXU1_PIPE_MODE_CONTINUOUS 0x01 -#define MXU1_PIPE_MODE_MASK 0x03 -#define MXU1_PIPE_TIMEOUT_MASK 0x7C -#define MXU1_PIPE_TIMEOUT_ENABLE 0x80 - -/* Config struct */ -struct mxu1_uart_config { - __be16 wBaudRate; - __be16 wFlags; - u8 bDataBits; - u8 bParity; - u8 bStopBits; - char cXon; - char cXoff; - u8 bUartMode; -} __packed; - -/* Purge modes */ -#define MXU1_PURGE_OUTPUT 0x00 -#define MXU1_PURGE_INPUT 0x80 - -/* Read/Write data */ -#define MXU1_RW_DATA_ADDR_SFR 0x10 -#define MXU1_RW_DATA_ADDR_IDATA 0x20 -#define MXU1_RW_DATA_ADDR_XDATA 0x30 -#define MXU1_RW_DATA_ADDR_CODE 0x40 -#define MXU1_RW_DATA_ADDR_GPIO 0x50 -#define MXU1_RW_DATA_ADDR_I2C 0x60 -#define MXU1_RW_DATA_ADDR_FLASH 0x70 -#define MXU1_RW_DATA_ADDR_DSP 0x80 - -#define MXU1_RW_DATA_UNSPECIFIED 0x00 -#define MXU1_RW_DATA_BYTE 0x01 -#define MXU1_RW_DATA_WORD 0x02 -#define MXU1_RW_DATA_DOUBLE_WORD 0x04 - -struct mxu1_write_data_bytes { - u8 bAddrType; - u8 bDataType; - u8 bDataCounter; - __be16 wBaseAddrHi; - __be16 wBaseAddrLo; - u8 bData[0]; -} __packed; - -/* Interrupt codes */ -#define MXU1_CODE_HARDWARE_ERROR 0xFF -#define MXU1_CODE_DATA_ERROR 0x03 -#define MXU1_CODE_MODEM_STATUS 0x04 - -static inline int mxu1_get_func_from_code(unsigned char code) -{ - return code & 0x0f; -} - -/* Download firmware max packet size */ -#define MXU1_DOWNLOAD_MAX_PACKET_SIZE 64 - -/* Firmware image header */ -struct mxu1_firmware_header { - __le16 wLength; - u8 bCheckSum; -} __packed; - -#define MXU1_UART_BASE_ADDR 0xFFA0 -#define MXU1_UART_OFFSET_MCR 0x0004 - -#define MXU1_BAUD_BASE 923077 - -#define MXU1_TRANSFER_TIMEOUT 2 -#define MXU1_DOWNLOAD_TIMEOUT 1000 -#define MXU1_DEFAULT_CLOSING_WAIT 4000 /* in .01 secs */ - -struct mxu1_port { - u8 msr; - u8 mcr; - u8 uart_mode; - spinlock_t spinlock; /* Protects msr */ - struct mutex mutex; /* Protects mcr */ - bool send_break; -}; - -struct mxu1_device { - u16 mxd_model; -}; - -static const struct usb_device_id mxu1_idtable[] = { - { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1110_PRODUCT_ID) }, - { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1130_PRODUCT_ID) }, - { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1150_PRODUCT_ID) }, - { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1151_PRODUCT_ID) }, - { USB_DEVICE(MXU1_VENDOR_ID, MXU1_1131_PRODUCT_ID) }, - { } -}; - -MODULE_DEVICE_TABLE(usb, mxu1_idtable); - -/* Write the given buffer out to the control pipe. */ -static int mxu1_send_ctrl_data_urb(struct usb_serial *serial, - u8 request, - u16 value, u16 index, - void *data, size_t size) -{ - int status; - - status = usb_control_msg(serial->dev, - usb_sndctrlpipe(serial->dev, 0), - request, - (USB_DIR_OUT | USB_TYPE_VENDOR | - USB_RECIP_DEVICE), value, index, - data, size, - USB_CTRL_SET_TIMEOUT); - if (status < 0) { - dev_err(&serial->interface->dev, - "%s - usb_control_msg failed: %d\n", - __func__, status); - return status; - } - - if (status != size) { - dev_err(&serial->interface->dev, - "%s - short write (%d / %zd)\n", - __func__, status, size); - return -EIO; - } - - return 0; -} - -/* Send a vendor request without any data */ -static int mxu1_send_ctrl_urb(struct usb_serial *serial, - u8 request, u16 value, u16 index) -{ - return mxu1_send_ctrl_data_urb(serial, request, value, index, - NULL, 0); -} - -static int mxu1_download_firmware(struct usb_serial *serial, - const struct firmware *fw_p) -{ - int status = 0; - int buffer_size; - int pos; - int len; - int done; - u8 cs = 0; - u8 *buffer; - struct usb_device *dev = serial->dev; - struct mxu1_firmware_header *header; - unsigned int pipe; - - pipe = usb_sndbulkpipe(dev, serial->port[0]->bulk_out_endpointAddress); - - buffer_size = fw_p->size + sizeof(*header); - buffer = kmalloc(buffer_size, GFP_KERNEL); - if (!buffer) - return -ENOMEM; - - memcpy(buffer, fw_p->data, fw_p->size); - memset(buffer + fw_p->size, 0xff, buffer_size - fw_p->size); - - for (pos = sizeof(*header); pos < buffer_size; pos++) - cs = (u8)(cs + buffer[pos]); - - header = (struct mxu1_firmware_header *)buffer; - header->wLength = cpu_to_le16(buffer_size - sizeof(*header)); - header->bCheckSum = cs; - - dev_dbg(&dev->dev, "%s - downloading firmware\n", __func__); - - for (pos = 0; pos < buffer_size; pos += done) { - len = min(buffer_size - pos, MXU1_DOWNLOAD_MAX_PACKET_SIZE); - - status = usb_bulk_msg(dev, pipe, buffer + pos, len, &done, - MXU1_DOWNLOAD_TIMEOUT); - if (status) - break; - } - - kfree(buffer); - - if (status) { - dev_err(&dev->dev, "failed to download firmware: %d\n", status); - return status; - } - - msleep_interruptible(100); - usb_reset_device(dev); - - dev_dbg(&dev->dev, "%s - download successful\n", __func__); - - return 0; -} - -static int mxu1_port_probe(struct usb_serial_port *port) -{ - struct mxu1_port *mxport; - struct mxu1_device *mxdev; - - if (!port->interrupt_in_urb) { - dev_err(&port->dev, "no interrupt urb\n"); - return -ENODEV; - } - - mxport = kzalloc(sizeof(struct mxu1_port), GFP_KERNEL); - if (!mxport) - return -ENOMEM; - - spin_lock_init(&mxport->spinlock); - mutex_init(&mxport->mutex); - - mxdev = usb_get_serial_data(port->serial); - - switch (mxdev->mxd_model) { - case MXU1_1110_PRODUCT_ID: - case MXU1_1150_PRODUCT_ID: - case MXU1_1151_PRODUCT_ID: - mxport->uart_mode = MXU1_UART_232; - break; - case MXU1_1130_PRODUCT_ID: - case MXU1_1131_PRODUCT_ID: - mxport->uart_mode = MXU1_UART_485_RECEIVER_DISABLED; - break; - } - - usb_set_serial_port_data(port, mxport); - - port->port.closing_wait = - msecs_to_jiffies(MXU1_DEFAULT_CLOSING_WAIT * 10); - port->port.drain_delay = 1; - - return 0; -} - -static int mxu1_port_remove(struct usb_serial_port *port) -{ - struct mxu1_port *mxport; - - mxport = usb_get_serial_port_data(port); - kfree(mxport); - - return 0; -} - -static int mxu1_startup(struct usb_serial *serial) -{ - struct mxu1_device *mxdev; - struct usb_device *dev = serial->dev; - struct usb_host_interface *cur_altsetting; - char fw_name[32]; - const struct firmware *fw_p = NULL; - int err; - - dev_dbg(&serial->interface->dev, "%s - product 0x%04X, num configurations %d, configuration value %d\n", - __func__, le16_to_cpu(dev->descriptor.idProduct), - dev->descriptor.bNumConfigurations, - dev->actconfig->desc.bConfigurationValue); - - /* create device structure */ - mxdev = kzalloc(sizeof(struct mxu1_device), GFP_KERNEL); - if (!mxdev) - return -ENOMEM; - - usb_set_serial_data(serial, mxdev); - - mxdev->mxd_model = le16_to_cpu(dev->descriptor.idProduct); - - cur_altsetting = serial->interface->cur_altsetting; - - /* if we have only 1 configuration, download firmware */ - if (cur_altsetting->desc.bNumEndpoints == 1) { - - snprintf(fw_name, - sizeof(fw_name), - "moxa/moxa-%04x.fw", - mxdev->mxd_model); - - err = request_firmware(&fw_p, fw_name, &serial->interface->dev); - if (err) { - dev_err(&serial->interface->dev, "failed to request firmware: %d\n", - err); - goto err_free_mxdev; - } - - err = mxu1_download_firmware(serial, fw_p); - if (err) - goto err_release_firmware; - - /* device is being reset */ - err = -ENODEV; - goto err_release_firmware; - } - - return 0; - -err_release_firmware: - release_firmware(fw_p); -err_free_mxdev: - kfree(mxdev); - - return err; -} - -static void mxu1_release(struct usb_serial *serial) -{ - struct mxu1_device *mxdev; - - mxdev = usb_get_serial_data(serial); - kfree(mxdev); -} - -static int mxu1_write_byte(struct usb_serial_port *port, u32 addr, - u8 mask, u8 byte) -{ - int status; - size_t size; - struct mxu1_write_data_bytes *data; - - dev_dbg(&port->dev, "%s - addr 0x%08X, mask 0x%02X, byte 0x%02X\n", - __func__, addr, mask, byte); - - size = sizeof(struct mxu1_write_data_bytes) + 2; - data = kzalloc(size, GFP_KERNEL); - if (!data) - return -ENOMEM; - - data->bAddrType = MXU1_RW_DATA_ADDR_XDATA; - data->bDataType = MXU1_RW_DATA_BYTE; - data->bDataCounter = 1; - data->wBaseAddrHi = cpu_to_be16(addr >> 16); - data->wBaseAddrLo = cpu_to_be16(addr); - data->bData[0] = mask; - data->bData[1] = byte; - - status = mxu1_send_ctrl_data_urb(port->serial, MXU1_WRITE_DATA, 0, - MXU1_RAM_PORT, data, size); - if (status < 0) - dev_err(&port->dev, "%s - failed: %d\n", __func__, status); - - kfree(data); - - return status; -} - -static int mxu1_set_mcr(struct usb_serial_port *port, unsigned int mcr) -{ - int status; - - status = mxu1_write_byte(port, - MXU1_UART_BASE_ADDR + MXU1_UART_OFFSET_MCR, - MXU1_MCR_RTS | MXU1_MCR_DTR | MXU1_MCR_LOOP, - mcr); - return status; -} - -static void mxu1_set_termios(struct tty_struct *tty, - struct usb_serial_port *port, - struct ktermios *old_termios) -{ - struct mxu1_port *mxport = usb_get_serial_port_data(port); - struct mxu1_uart_config *config; - tcflag_t cflag, iflag; - speed_t baud; - int status; - unsigned int mcr; - - cflag = tty->termios.c_cflag; - iflag = tty->termios.c_iflag; - - if (old_termios && - !tty_termios_hw_change(&tty->termios, old_termios) && - tty->termios.c_iflag == old_termios->c_iflag) { - dev_dbg(&port->dev, "%s - nothing to change\n", __func__); - return; - } - - dev_dbg(&port->dev, - "%s - cflag 0x%08x, iflag 0x%08x\n", __func__, cflag, iflag); - - if (old_termios) { - dev_dbg(&port->dev, "%s - old cflag 0x%08x, old iflag 0x%08x\n", - __func__, - old_termios->c_cflag, - old_termios->c_iflag); - } - - config = kzalloc(sizeof(*config), GFP_KERNEL); - if (!config) - return; - - /* these flags must be set */ - config->wFlags |= MXU1_UART_ENABLE_MS_INTS; - config->wFlags |= MXU1_UART_ENABLE_AUTO_START_DMA; - if (mxport->send_break) - config->wFlags |= MXU1_UART_SEND_BREAK_SIGNAL; - config->bUartMode = mxport->uart_mode; - - switch (C_CSIZE(tty)) { - case CS5: - config->bDataBits = MXU1_UART_5_DATA_BITS; - break; - case CS6: - config->bDataBits = MXU1_UART_6_DATA_BITS; - break; - case CS7: - config->bDataBits = MXU1_UART_7_DATA_BITS; - break; - default: - case CS8: - config->bDataBits = MXU1_UART_8_DATA_BITS; - break; - } - - if (C_PARENB(tty)) { - config->wFlags |= MXU1_UART_ENABLE_PARITY_CHECKING; - if (C_CMSPAR(tty)) { - if (C_PARODD(tty)) - config->bParity = MXU1_UART_MARK_PARITY; - else - config->bParity = MXU1_UART_SPACE_PARITY; - } else { - if (C_PARODD(tty)) - config->bParity = MXU1_UART_ODD_PARITY; - else - config->bParity = MXU1_UART_EVEN_PARITY; - } - } else { - config->bParity = MXU1_UART_NO_PARITY; - } - - if (C_CSTOPB(tty)) - config->bStopBits = MXU1_UART_2_STOP_BITS; - else - config->bStopBits = MXU1_UART_1_STOP_BITS; - - if (C_CRTSCTS(tty)) { - /* RTS flow control must be off to drop RTS for baud rate B0 */ - if (C_BAUD(tty) != B0) - config->wFlags |= MXU1_UART_ENABLE_RTS_IN; - config->wFlags |= MXU1_UART_ENABLE_CTS_OUT; - } - - if (I_IXOFF(tty) || I_IXON(tty)) { - config->cXon = START_CHAR(tty); - config->cXoff = STOP_CHAR(tty); - - if (I_IXOFF(tty)) - config->wFlags |= MXU1_UART_ENABLE_X_IN; - - if (I_IXON(tty)) - config->wFlags |= MXU1_UART_ENABLE_X_OUT; - } - - baud = tty_get_baud_rate(tty); - if (!baud) - baud = 9600; - config->wBaudRate = MXU1_BAUD_BASE / baud; - - dev_dbg(&port->dev, "%s - BaudRate=%d, wBaudRate=%d, wFlags=0x%04X, bDataBits=%d, bParity=%d, bStopBits=%d, cXon=%d, cXoff=%d, bUartMode=%d\n", - __func__, baud, config->wBaudRate, config->wFlags, - config->bDataBits, config->bParity, config->bStopBits, - config->cXon, config->cXoff, config->bUartMode); - - cpu_to_be16s(&config->wBaudRate); - cpu_to_be16s(&config->wFlags); - - status = mxu1_send_ctrl_data_urb(port->serial, MXU1_SET_CONFIG, 0, - MXU1_UART1_PORT, config, - sizeof(*config)); - if (status) - dev_err(&port->dev, "cannot set config: %d\n", status); - - mutex_lock(&mxport->mutex); - mcr = mxport->mcr; - - if (C_BAUD(tty) == B0) - mcr &= ~(MXU1_MCR_DTR | MXU1_MCR_RTS); - else if (old_termios && (old_termios->c_cflag & CBAUD) == B0) - mcr |= MXU1_MCR_DTR | MXU1_MCR_RTS; - - status = mxu1_set_mcr(port, mcr); - if (status) - dev_err(&port->dev, "cannot set modem control: %d\n", status); - else - mxport->mcr = mcr; - - mutex_unlock(&mxport->mutex); - - kfree(config); -} - -static int mxu1_get_serial_info(struct usb_serial_port *port, - struct serial_struct __user *ret_arg) -{ - struct serial_struct ret_serial; - unsigned cwait; - - if (!ret_arg) - return -EFAULT; - - cwait = port->port.closing_wait; - if (cwait != ASYNC_CLOSING_WAIT_NONE) - cwait = jiffies_to_msecs(cwait) / 10; - - memset(&ret_serial, 0, sizeof(ret_serial)); - - ret_serial.type = PORT_16550A; - ret_serial.line = port->minor; - ret_serial.port = 0; - ret_serial.xmit_fifo_size = port->bulk_out_size; - ret_serial.baud_base = MXU1_BAUD_BASE; - ret_serial.close_delay = 5*HZ; - ret_serial.closing_wait = cwait; - - if (copy_to_user(ret_arg, &ret_serial, sizeof(*ret_arg))) - return -EFAULT; - - return 0; -} - - -static int mxu1_set_serial_info(struct usb_serial_port *port, - struct serial_struct __user *new_arg) -{ - struct serial_struct new_serial; - unsigned cwait; - - if (copy_from_user(&new_serial, new_arg, sizeof(new_serial))) - return -EFAULT; - - cwait = new_serial.closing_wait; - if (cwait != ASYNC_CLOSING_WAIT_NONE) - cwait = msecs_to_jiffies(10 * new_serial.closing_wait); - - port->port.closing_wait = cwait; - - return 0; -} - -static int mxu1_ioctl(struct tty_struct *tty, - unsigned int cmd, unsigned long arg) -{ - struct usb_serial_port *port = tty->driver_data; - - switch (cmd) { - case TIOCGSERIAL: - return mxu1_get_serial_info(port, - (struct serial_struct __user *)arg); - case TIOCSSERIAL: - return mxu1_set_serial_info(port, - (struct serial_struct __user *)arg); - } - - return -ENOIOCTLCMD; -} - -static int mxu1_tiocmget(struct tty_struct *tty) -{ - struct usb_serial_port *port = tty->driver_data; - struct mxu1_port *mxport = usb_get_serial_port_data(port); - unsigned int result; - unsigned int msr; - unsigned int mcr; - unsigned long flags; - - mutex_lock(&mxport->mutex); - spin_lock_irqsave(&mxport->spinlock, flags); - - msr = mxport->msr; - mcr = mxport->mcr; - - spin_unlock_irqrestore(&mxport->spinlock, flags); - mutex_unlock(&mxport->mutex); - - result = ((mcr & MXU1_MCR_DTR) ? TIOCM_DTR : 0) | - ((mcr & MXU1_MCR_RTS) ? TIOCM_RTS : 0) | - ((mcr & MXU1_MCR_LOOP) ? TIOCM_LOOP : 0) | - ((msr & MXU1_MSR_CTS) ? TIOCM_CTS : 0) | - ((msr & MXU1_MSR_CD) ? TIOCM_CAR : 0) | - ((msr & MXU1_MSR_RI) ? TIOCM_RI : 0) | - ((msr & MXU1_MSR_DSR) ? TIOCM_DSR : 0); - - dev_dbg(&port->dev, "%s - 0x%04X\n", __func__, result); - - return result; -} - -static int mxu1_tiocmset(struct tty_struct *tty, - unsigned int set, unsigned int clear) -{ - struct usb_serial_port *port = tty->driver_data; - struct mxu1_port *mxport = usb_get_serial_port_data(port); - int err; - unsigned int mcr; - - mutex_lock(&mxport->mutex); - mcr = mxport->mcr; - - if (set & TIOCM_RTS) - mcr |= MXU1_MCR_RTS; - if (set & TIOCM_DTR) - mcr |= MXU1_MCR_DTR; - if (set & TIOCM_LOOP) - mcr |= MXU1_MCR_LOOP; - - if (clear & TIOCM_RTS) - mcr &= ~MXU1_MCR_RTS; - if (clear & TIOCM_DTR) - mcr &= ~MXU1_MCR_DTR; - if (clear & TIOCM_LOOP) - mcr &= ~MXU1_MCR_LOOP; - - err = mxu1_set_mcr(port, mcr); - if (!err) - mxport->mcr = mcr; - - mutex_unlock(&mxport->mutex); - - return err; -} - -static void mxu1_break(struct tty_struct *tty, int break_state) -{ - struct usb_serial_port *port = tty->driver_data; - struct mxu1_port *mxport = usb_get_serial_port_data(port); - - if (break_state == -1) - mxport->send_break = true; - else - mxport->send_break = false; - - mxu1_set_termios(tty, port, NULL); -} - -static int mxu1_open(struct tty_struct *tty, struct usb_serial_port *port) -{ - struct mxu1_port *mxport = usb_get_serial_port_data(port); - struct usb_serial *serial = port->serial; - int status; - u16 open_settings; - - open_settings = (MXU1_PIPE_MODE_CONTINUOUS | - MXU1_PIPE_TIMEOUT_ENABLE | - (MXU1_TRANSFER_TIMEOUT << 2)); - - mxport->msr = 0; - - status = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL); - if (status) { - dev_err(&port->dev, "failed to submit interrupt urb: %d\n", - status); - return status; - } - - if (tty) - mxu1_set_termios(tty, port, NULL); - - status = mxu1_send_ctrl_urb(serial, MXU1_OPEN_PORT, - open_settings, MXU1_UART1_PORT); - if (status) { - dev_err(&port->dev, "cannot send open command: %d\n", status); - goto unlink_int_urb; - } - - status = mxu1_send_ctrl_urb(serial, MXU1_START_PORT, - 0, MXU1_UART1_PORT); - if (status) { - dev_err(&port->dev, "cannot send start command: %d\n", status); - goto unlink_int_urb; - } - - status = mxu1_send_ctrl_urb(serial, MXU1_PURGE_PORT, - MXU1_PURGE_INPUT, MXU1_UART1_PORT); - if (status) { - dev_err(&port->dev, "cannot clear input buffers: %d\n", - status); - - goto unlink_int_urb; - } - - status = mxu1_send_ctrl_urb(serial, MXU1_PURGE_PORT, - MXU1_PURGE_OUTPUT, MXU1_UART1_PORT); - if (status) { - dev_err(&port->dev, "cannot clear output buffers: %d\n", - status); - - goto unlink_int_urb; - } - - /* - * reset the data toggle on the bulk endpoints to work around bug in - * host controllers where things get out of sync some times - */ - usb_clear_halt(serial->dev, port->write_urb->pipe); - usb_clear_halt(serial->dev, port->read_urb->pipe); - - if (tty) - mxu1_set_termios(tty, port, NULL); - - status = mxu1_send_ctrl_urb(serial, MXU1_OPEN_PORT, - open_settings, MXU1_UART1_PORT); - if (status) { - dev_err(&port->dev, "cannot send open command: %d\n", status); - goto unlink_int_urb; - } - - status = mxu1_send_ctrl_urb(serial, MXU1_START_PORT, - 0, MXU1_UART1_PORT); - if (status) { - dev_err(&port->dev, "cannot send start command: %d\n", status); - goto unlink_int_urb; - } - - status = usb_serial_generic_open(tty, port); - if (status) - goto unlink_int_urb; - - return 0; - -unlink_int_urb: - usb_kill_urb(port->interrupt_in_urb); - - return status; -} - -static void mxu1_close(struct usb_serial_port *port) -{ - int status; - - usb_serial_generic_close(port); - usb_kill_urb(port->interrupt_in_urb); - - status = mxu1_send_ctrl_urb(port->serial, MXU1_CLOSE_PORT, - 0, MXU1_UART1_PORT); - if (status) { - dev_err(&port->dev, "failed to send close port command: %d\n", - status); - } -} - -static void mxu1_handle_new_msr(struct usb_serial_port *port, u8 msr) -{ - struct mxu1_port *mxport = usb_get_serial_port_data(port); - struct async_icount *icount; - unsigned long flags; - - dev_dbg(&port->dev, "%s - msr 0x%02X\n", __func__, msr); - - spin_lock_irqsave(&mxport->spinlock, flags); - mxport->msr = msr & MXU1_MSR_MASK; - spin_unlock_irqrestore(&mxport->spinlock, flags); - - if (msr & MXU1_MSR_DELTA_MASK) { - icount = &port->icount; - if (msr & MXU1_MSR_DELTA_CTS) - icount->cts++; - if (msr & MXU1_MSR_DELTA_DSR) - icount->dsr++; - if (msr & MXU1_MSR_DELTA_CD) - icount->dcd++; - if (msr & MXU1_MSR_DELTA_RI) - icount->rng++; - - wake_up_interruptible(&port->port.delta_msr_wait); - } -} - -static void mxu1_interrupt_callback(struct urb *urb) -{ - struct usb_serial_port *port = urb->context; - unsigned char *data = urb->transfer_buffer; - int length = urb->actual_length; - int function; - int status; - u8 msr; - - switch (urb->status) { - case 0: - break; - case -ECONNRESET: - case -ENOENT: - case -ESHUTDOWN: - dev_dbg(&port->dev, "%s - urb shutting down: %d\n", - __func__, urb->status); - return; - default: - dev_dbg(&port->dev, "%s - nonzero urb status: %d\n", - __func__, urb->status); - goto exit; - } - - if (length != 2) { - dev_dbg(&port->dev, "%s - bad packet size: %d\n", - __func__, length); - goto exit; - } - - if (data[0] == MXU1_CODE_HARDWARE_ERROR) { - dev_err(&port->dev, "hardware error: %d\n", data[1]); - goto exit; - } - - function = mxu1_get_func_from_code(data[0]); - - dev_dbg(&port->dev, "%s - function %d, data 0x%02X\n", - __func__, function, data[1]); - - switch (function) { - case MXU1_CODE_DATA_ERROR: - dev_dbg(&port->dev, "%s - DATA ERROR, data 0x%02X\n", - __func__, data[1]); - break; - - case MXU1_CODE_MODEM_STATUS: - msr = data[1]; - mxu1_handle_new_msr(port, msr); - break; - - default: - dev_err(&port->dev, "unknown interrupt code: 0x%02X\n", - data[1]); - break; - } - -exit: - status = usb_submit_urb(urb, GFP_ATOMIC); - if (status) { - dev_err(&port->dev, "resubmit interrupt urb failed: %d\n", - status); - } -} - -static struct usb_serial_driver mxu11x0_device = { - .driver = { - .owner = THIS_MODULE, - .name = "mxu11x0", - }, - .description = "MOXA UPort 11x0", - .id_table = mxu1_idtable, - .num_ports = 1, - .port_probe = mxu1_port_probe, - .port_remove = mxu1_port_remove, - .attach = mxu1_startup, - .release = mxu1_release, - .open = mxu1_open, - .close = mxu1_close, - .ioctl = mxu1_ioctl, - .set_termios = mxu1_set_termios, - .tiocmget = mxu1_tiocmget, - .tiocmset = mxu1_tiocmset, - .tiocmiwait = usb_serial_generic_tiocmiwait, - .get_icount = usb_serial_generic_get_icount, - .break_ctl = mxu1_break, - .read_int_callback = mxu1_interrupt_callback, -}; - -static struct usb_serial_driver *const serial_drivers[] = { - &mxu11x0_device, NULL -}; - -module_usb_serial_driver(serial_drivers, mxu1_idtable); - -MODULE_AUTHOR("Mathieu Othacehe "); -MODULE_DESCRIPTION("MOXA UPort 11x0 USB to Serial Hub Driver"); -MODULE_LICENSE("GPL"); -MODULE_FIRMWARE("moxa/moxa-1110.fw"); -MODULE_FIRMWARE("moxa/moxa-1130.fw"); -MODULE_FIRMWARE("moxa/moxa-1131.fw"); -MODULE_FIRMWARE("moxa/moxa-1150.fw"); -MODULE_FIRMWARE("moxa/moxa-1151.fw"); From 17e2df4613be57d0fab68df749f6b8114e453152 Mon Sep 17 00:00:00 2001 From: Dennis Kadioglu Date: Tue, 1 Mar 2016 14:23:29 +0100 Subject: [PATCH 275/417] ALSA: usb-audio: Add a quirk for Plantronics DA45 Plantronics DA45 does not support reading the sample rate which leads to many lines of "cannot get freq at ep 0x4" and "cannot get freq at ep 0x84". This patch adds the USB ID of the DA45 to quirks.c and avoids those error messages. Signed-off-by: Dennis Kadioglu Cc: Signed-off-by: Takashi Iwai --- sound/usb/quirks.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 4f6ce1cac8e2..c458d60d5030 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1124,6 +1124,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) case USB_ID(0x045E, 0x076F): /* MS Lifecam HD-6000 */ case USB_ID(0x045E, 0x0772): /* MS Lifecam Studio */ case USB_ID(0x045E, 0x0779): /* MS Lifecam HD-3000 */ + case USB_ID(0x047F, 0xAA05): /* Plantronics DA45 */ case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */ case USB_ID(0x074D, 0x3553): /* Outlaw RR2150 (Micronas UAC3553B) */ case USB_ID(0x21B4, 0x0081): /* AudioQuest DragonFly */ From 9acc54beb474c81148e2946603d141cf8716b19f Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 26 Feb 2016 22:13:40 +0100 Subject: [PATCH 276/417] mac80211: check PN correctly for GCMP-encrypted fragmented MPDUs Just like for CCMP we need to check that for GCMP the fragments have PNs that increment by one; the spec was updated to fix this security issue and now has the following text: The receiver shall discard MSDUs and MMPDUs whose constituent MPDU PN values are not incrementing in steps of 1. Adapt the code for CCMP to work for GCMP as well, luckily the relevant fields already alias each other so no code duplication is needed (just check the aliasing with BUILD_BUG_ON.) Cc: stable@vger.kernel.org Signed-off-by: Johannes Berg --- net/mac80211/ieee80211_i.h | 2 +- net/mac80211/rx.c | 36 +++++++++++++++++++++++++++--------- 2 files changed, 28 insertions(+), 10 deletions(-) diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index b84f6aa32c08..f006f4a44c0e 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -92,7 +92,7 @@ struct ieee80211_fragment_entry { u16 extra_len; u16 last_frag; u8 rx_queue; - bool ccmp; /* Whether fragments were encrypted with CCMP */ + bool check_sequential_pn; /* needed for CCMP/GCMP */ u8 last_pn[6]; /* PN of the last fragment if CCMP was used */ }; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index bc081850ac0e..bf2c3f281dcd 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1753,7 +1753,7 @@ ieee80211_reassemble_add(struct ieee80211_sub_if_data *sdata, entry->seq = seq; entry->rx_queue = rx_queue; entry->last_frag = frag; - entry->ccmp = 0; + entry->check_sequential_pn = false; entry->extra_len = 0; return entry; @@ -1849,15 +1849,27 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) rx->seqno_idx, &(rx->skb)); if (rx->key && (rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP || - rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256) && + rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256 || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP_256) && ieee80211_has_protected(fc)) { int queue = rx->security_idx; - /* Store CCMP PN so that we can verify that the next - * fragment has a sequential PN value. */ - entry->ccmp = 1; + + /* Store CCMP/GCMP PN so that we can verify that the + * next fragment has a sequential PN value. + */ + entry->check_sequential_pn = true; memcpy(entry->last_pn, rx->key->u.ccmp.rx_pn[queue], IEEE80211_CCMP_PN_LEN); + BUILD_BUG_ON(offsetof(struct ieee80211_key, + u.ccmp.rx_pn) != + offsetof(struct ieee80211_key, + u.gcmp.rx_pn)); + BUILD_BUG_ON(sizeof(rx->key->u.ccmp.rx_pn[queue]) != + sizeof(rx->key->u.gcmp.rx_pn[queue])); + BUILD_BUG_ON(IEEE80211_CCMP_PN_LEN != + IEEE80211_GCMP_PN_LEN); } return RX_QUEUED; } @@ -1872,15 +1884,21 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) return RX_DROP_MONITOR; } - /* Verify that MPDUs within one MSDU have sequential PN values. - * (IEEE 802.11i, 8.3.3.4.5) */ - if (entry->ccmp) { + /* "The receiver shall discard MSDUs and MMPDUs whose constituent + * MPDU PN values are not incrementing in steps of 1." + * see IEEE P802.11-REVmc/D5.0, 12.5.3.4.4, item d (for CCMP) + * and IEEE P802.11-REVmc/D5.0, 12.5.5.4.4, item d (for GCMP) + */ + if (entry->check_sequential_pn) { int i; u8 pn[IEEE80211_CCMP_PN_LEN], *rpn; int queue; + if (!rx->key || (rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP && - rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256)) + rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256 && + rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP && + rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP_256)) return RX_DROP_UNUSABLE; memcpy(pn, entry->last_pn, IEEE80211_CCMP_PN_LEN); for (i = IEEE80211_CCMP_PN_LEN - 1; i >= 0; i--) { From 1ec7bae8bec9b72e347e01330c745ab5cdd66f0e Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Tue, 1 Mar 2016 00:29:00 +0200 Subject: [PATCH 277/417] mac80211: Fix Public Action frame RX in AP mode Public Action frames use special rules for how the BSSID field (Address 3) is set. A wildcard BSSID is used in cases where the transmitter and recipient are not members of the same BSS. As such, we need to accept Public Action frames with wildcard BSSID. Commit db8e17324553 ("mac80211: ignore frames between TDLS peers when operating as AP") added a rule that drops Action frames to TDLS-peers based on an Action frame having different DA (Address 1) and BSSID (Address 3) values. This is not correct since it misses the possibility of BSSID being a wildcard BSSID in which case the Address 1 would not necessarily match. Fix this by allowing mac80211 to accept wildcard BSSID in an Action frame when in AP mode. Fixes: db8e17324553 ("mac80211: ignore frames between TDLS peers when operating as AP") Cc: stable@vger.kernel.org Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- net/mac80211/rx.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index bf2c3f281dcd..60d093f40f1d 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3384,6 +3384,7 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) return false; /* ignore action frames to TDLS-peers */ if (ieee80211_is_action(hdr->frame_control) && + !is_broadcast_ether_addr(bssid) && !ether_addr_equal(bssid, hdr->addr1)) return false; } From c36dd3eaf1a674a45b58b922258d6eaa8932e292 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Wed, 24 Feb 2016 12:07:17 +0100 Subject: [PATCH 278/417] mac80211: minstrel_ht: fix a logic error in RTS/CTS handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit RTS/CTS needs to be enabled if the rate is a fallback rate *or* if it's a dual-stream rate and the sta is in dynamic SMPS mode. Cc: stable@vger.kernel.org Fixes: a3ebb4e1b763 ("mac80211: minstrel_ht: handle peers in dynamic SMPS") Reported-by: Matías Richart Signed-off-by: Felix Fietkau Signed-off-by: Johannes Berg --- net/mac80211/rc80211_minstrel_ht.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 409b3640da6c..370d677b547b 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -872,7 +872,7 @@ minstrel_ht_set_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, * - if station is in dynamic SMPS (and streams > 1) * - for fallback rates, to increase chances of getting through */ - if (offset > 0 && + if (offset > 0 || (mi->sta->smps_mode == IEEE80211_SMPS_DYNAMIC && group->streams > 1)) { ratetbl->rate[offset].count = ratetbl->rate[offset].count_rts; From 9589995e46d89c70c6fa4723c5f3e5ec04c3c3e3 Mon Sep 17 00:00:00 2001 From: Steve French Date: Mon, 29 Feb 2016 01:02:11 -0600 Subject: [PATCH 279/417] CIFS: Fix duplicate line introduced by clone_file_range patch Commit 04b38d601239b4 ("vfs: pull btrfs clone API to vfs layer") added a duplicated line (in cifsfs.c) which causes a sparse compile warning. Signed-off-by: Steve French Reviewed-by: Christoph Hellwig --- fs/cifs/cifsfs.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index c48ca13673e3..2eea40353e60 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1013,7 +1013,6 @@ const struct file_operations cifs_file_strict_ops = { .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, .clone_file_range = cifs_clone_file_range, - .clone_file_range = cifs_clone_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; From 7314d22a2f5bd40468d57768be368c3d9b4bd726 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sun, 21 Feb 2016 15:16:48 +0100 Subject: [PATCH 280/417] i2c: brcmstb: allocate correct amount of memory for regmap We want the size of the struct, not of a pointer to it. To be future proof, just dereference the pointer to get the desired type. Fixes: dd1aa2524bc5 ("i2c: brcmstb: Add Broadcom settop SoC i2c controller driver") Acked-by: Gregory Fong Acked-by: Florian Fainelli Reviewed-by: Kamal Dasu Signed-off-by: Wolfram Sang Cc: stable@kernel.org --- drivers/i2c/busses/i2c-brcmstb.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/i2c/busses/i2c-brcmstb.c b/drivers/i2c/busses/i2c-brcmstb.c index 3711df1d4526..4a45408dd820 100644 --- a/drivers/i2c/busses/i2c-brcmstb.c +++ b/drivers/i2c/busses/i2c-brcmstb.c @@ -586,8 +586,7 @@ static int brcmstb_i2c_probe(struct platform_device *pdev) if (!dev) return -ENOMEM; - dev->bsc_regmap = devm_kzalloc(&pdev->dev, sizeof(struct bsc_regs *), - GFP_KERNEL); + dev->bsc_regmap = devm_kzalloc(&pdev->dev, sizeof(*dev->bsc_regmap), GFP_KERNEL); if (!dev->bsc_regmap) return -ENOMEM; From 197b958c1e76a575d77038cc98b4bebc2134279f Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 1 Mar 2016 18:30:18 +0100 Subject: [PATCH 281/417] ALSA: seq: oss: Don't drain at closing a client The OSS sequencer client tries to drain the pending events at releasing. Unfortunately, as spotted by syzkaller fuzzer, this may lead to an unkillable process state when the event has been queued at the far future. Since the process being released can't be signaled any longer, it remains and waits for the echo-back event in that far future. Back to history, the draining feature was implemented at the time we misinterpreted POSIX definition for blocking file operation. Actually, such a behavior is superfluous at release, and we should just release the device as is instead of keeping it up forever. This patch just removes the draining call that may block the release for too long time unexpectedly. BugLink: http://lkml.kernel.org/r/CACT4Y+Y4kD-aBGj37rf-xBw9bH3GMU6P+MYg4W1e-s-paVD2pg@mail.gmail.com Reported-by: Dmitry Vyukov Cc: Signed-off-by: Takashi Iwai --- sound/core/seq/oss/seq_oss.c | 2 -- sound/core/seq/oss/seq_oss_device.h | 1 - sound/core/seq/oss/seq_oss_init.c | 16 ---------------- 3 files changed, 19 deletions(-) diff --git a/sound/core/seq/oss/seq_oss.c b/sound/core/seq/oss/seq_oss.c index 8db156b207f1..8cdf489df80e 100644 --- a/sound/core/seq/oss/seq_oss.c +++ b/sound/core/seq/oss/seq_oss.c @@ -149,8 +149,6 @@ odev_release(struct inode *inode, struct file *file) if ((dp = file->private_data) == NULL) return 0; - snd_seq_oss_drain_write(dp); - mutex_lock(®ister_mutex); snd_seq_oss_release(dp); mutex_unlock(®ister_mutex); diff --git a/sound/core/seq/oss/seq_oss_device.h b/sound/core/seq/oss/seq_oss_device.h index b43924325249..d7b4d016b547 100644 --- a/sound/core/seq/oss/seq_oss_device.h +++ b/sound/core/seq/oss/seq_oss_device.h @@ -127,7 +127,6 @@ int snd_seq_oss_write(struct seq_oss_devinfo *dp, const char __user *buf, int co unsigned int snd_seq_oss_poll(struct seq_oss_devinfo *dp, struct file *file, poll_table * wait); void snd_seq_oss_reset(struct seq_oss_devinfo *dp); -void snd_seq_oss_drain_write(struct seq_oss_devinfo *dp); /* */ void snd_seq_oss_process_queue(struct seq_oss_devinfo *dp, abstime_t time); diff --git a/sound/core/seq/oss/seq_oss_init.c b/sound/core/seq/oss/seq_oss_init.c index 6779e82b46dd..92c96a95a903 100644 --- a/sound/core/seq/oss/seq_oss_init.c +++ b/sound/core/seq/oss/seq_oss_init.c @@ -435,22 +435,6 @@ snd_seq_oss_release(struct seq_oss_devinfo *dp) } -/* - * Wait until the queue is empty (if we don't have nonblock) - */ -void -snd_seq_oss_drain_write(struct seq_oss_devinfo *dp) -{ - if (! dp->timer->running) - return; - if (is_write_mode(dp->file_mode) && !is_nonblock_mode(dp->file_mode) && - dp->writeq) { - while (snd_seq_oss_writeq_sync(dp->writeq)) - ; - } -} - - /* * reset sequencer devices */ From a7f4b98896f6aede26431a3017d32d722fcec5cb Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Fri, 26 Feb 2016 09:15:50 +0100 Subject: [PATCH 282/417] bna: fix list corruption Use list_move_tail() to move MAC address entry from list of pending to list of active entries. Simple list_add_tail() leaves the entry also in the first list, this leads to list corruption. Cc: Rasesh Mody Signed-off-by: Ivan Vecera Acked-by: Rasesh Mody Signed-off-by: David S. Miller --- drivers/net/ethernet/brocade/bna/bna_tx_rx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c index 04b0d16b210e..95bc470ae441 100644 --- a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c +++ b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c @@ -987,7 +987,7 @@ bna_rxf_ucast_cfg_apply(struct bna_rxf *rxf) if (!list_empty(&rxf->ucast_pending_add_q)) { mac = list_first_entry(&rxf->ucast_pending_add_q, struct bna_mac, qe); - list_add_tail(&mac->qe, &rxf->ucast_active_q); + list_move_tail(&mac->qe, &rxf->ucast_active_q); bna_bfi_ucast_req(rxf, mac, BFI_ENET_H2I_MAC_UCAST_ADD_REQ); return 1; } From edffc2178d4ba10a61e150b42ef5e7d797714eb3 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 26 Feb 2016 18:45:34 +0100 Subject: [PATCH 283/417] ppp: lock ppp->flags in ppp_read() and ppp_poll() ppp_read() and ppp_poll() can be called concurrently with ppp_ioctl(). In this case, ppp_ioctl() might call ppp_ccp_closed(), which may update ppp->flags while ppp_read() or ppp_poll() is reading it. The update done by ppp_ccp_closed() isn't atomic due to the bit mask operation ('ppp->flags &= ~(SC_CCP_OPEN | SC_CCP_UP)'), so concurrent readers might get transient values. Reading incorrect ppp->flags may disturb the 'ppp->flags & SC_LOOP_TRAFFIC' test in ppp_read() and ppp_poll(), which in turn can lead to improper decision on whether the PPP unit file is ready for reading or not. Since ppp_ccp_closed() is protected by the Rx and Tx locks (with ppp_lock()), taking the Rx lock is enough for ppp_read() and ppp_poll() to guarantee that ppp_ccp_closed() won't update ppp->flags concurrently. The same reasoning applies to ppp->n_channels. The 'n_channels' field can also be written to concurrently by ppp_ioctl() (through ppp_connect_channel() or ppp_disconnect_channel()). These writes aren't atomic (simple increment/decrement), but are protected by both the Rx and Tx locks (like in the ppp->flags case). So holding the Rx lock before reading ppp->n_channels also prevents concurrent writes. Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- drivers/net/ppp/ppp_generic.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index fc8ad001bc94..e8a5936289c5 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -443,9 +443,14 @@ static ssize_t ppp_read(struct file *file, char __user *buf, * network traffic (demand mode). */ struct ppp *ppp = PF_TO_PPP(pf); + + ppp_recv_lock(ppp); if (ppp->n_channels == 0 && - (ppp->flags & SC_LOOP_TRAFFIC) == 0) + (ppp->flags & SC_LOOP_TRAFFIC) == 0) { + ppp_recv_unlock(ppp); break; + } + ppp_recv_unlock(ppp); } ret = -EAGAIN; if (file->f_flags & O_NONBLOCK) @@ -532,9 +537,12 @@ static unsigned int ppp_poll(struct file *file, poll_table *wait) else if (pf->kind == INTERFACE) { /* see comment in ppp_read */ struct ppp *ppp = PF_TO_PPP(pf); + + ppp_recv_lock(ppp); if (ppp->n_channels == 0 && (ppp->flags & SC_LOOP_TRAFFIC) == 0) mask |= POLLIN | POLLRDNORM; + ppp_recv_unlock(ppp); } return mask; From 9a334d39daad92e2c46539b0bb3bd32b68df2af2 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Wed, 3 Feb 2016 20:54:56 +0100 Subject: [PATCH 284/417] parisc: Use parentheses around expression in floppy.h David Binderman reported a style issue in the floppy.h header file: arch/parisc/include/asm/floppy.h:221: (style) Boolean result is used in bitwise operation. Clarify expression with parentheses. Reported-by: David Binderman Cc: David Binderman Signed-off-by: Helge Deller --- arch/parisc/include/asm/floppy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/parisc/include/asm/floppy.h b/arch/parisc/include/asm/floppy.h index f84ff12574b7..6d8276cd25ca 100644 --- a/arch/parisc/include/asm/floppy.h +++ b/arch/parisc/include/asm/floppy.h @@ -33,7 +33,7 @@ * floppy accesses go through the track buffer. */ #define _CROSS_64KB(a,s,vdma) \ -(!vdma && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64)) +(!(vdma) && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64)) #define CROSS_64KB(a,s) _CROSS_64KB(a,s,use_virtual_dma & 1) From f5aba91d7f186cba84af966a741a0346de603cd4 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Fri, 26 Feb 2016 19:18:22 +0100 Subject: [PATCH 285/417] phy: micrel: Ensure interrupts are reenabled on resume At least on ksz8081, when getting back from power down, interrupts are disabled. ensure they are reenabled if they were previously enabled. This fixes resuming which is failing on the xplained boards from atmel since 321beec5047a (net: phy: Use interrupts when available in NOLINK state) Fixes: 321beec5047a (net: phy: Use interrupts when available in NOLINK state) Signed-off-by: Alexandre Belloni Signed-off-by: David S. Miller --- drivers/net/phy/micrel.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 03833dbfca67..a5e265b2bbfb 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -635,6 +635,21 @@ static void kszphy_get_stats(struct phy_device *phydev, data[i] = kszphy_get_stat(phydev, i); } +static int kszphy_resume(struct phy_device *phydev) +{ + int value; + + mutex_lock(&phydev->lock); + + value = phy_read(phydev, MII_BMCR); + phy_write(phydev, MII_BMCR, value & ~BMCR_PDOWN); + + kszphy_config_intr(phydev); + mutex_unlock(&phydev->lock); + + return 0; +} + static int kszphy_probe(struct phy_device *phydev) { const struct kszphy_type *type = phydev->drv->driver_data; @@ -844,7 +859,7 @@ static struct phy_driver ksphy_driver[] = { .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, .suspend = genphy_suspend, - .resume = genphy_resume, + .resume = kszphy_resume, }, { .phy_id = PHY_ID_KSZ8061, .name = "Micrel KSZ8061", From 99f81afc139c6edd14d77a91ee91685a414a1c66 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Fri, 26 Feb 2016 19:18:23 +0100 Subject: [PATCH 286/417] phy: micrel: Disable auto negotiation on startup Disable auto negotiation on init to properly detect an already plugged cable at boot. At boot, when the phy is started, it is in the PHY_UP state. However, if a cable is plugged at boot, because auto negociation is already enabled at the time we get the first interrupt, the phy is already running. But the state machine then switches from PHY_UP to PHY_AN and calls phy_start_aneg(). phy_start_aneg() will not do anything because aneg is already enabled on the phy. It will then wait for a interrupt before going further. This interrupt will never happen unless the cable is unplugged and then replugged. It was working properly before 321beec5047a (net: phy: Use interrupts when available in NOLINK state) because switching to NOLINK meant starting polling the phy, even if IRQ were enabled. Fixes: 321beec5047a (net: phy: Use interrupts when available in NOLINK state) Signed-off-by: Alexandre Belloni Signed-off-by: David S. Miller --- drivers/net/phy/micrel.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index a5e265b2bbfb..dc85f7095e51 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -297,6 +297,17 @@ static int kszphy_config_init(struct phy_device *phydev) if (priv->led_mode >= 0) kszphy_setup_led(phydev, type->led_mode_reg, priv->led_mode); + if (phy_interrupt_is_valid(phydev)) { + int ctl = phy_read(phydev, MII_BMCR); + + if (ctl < 0) + return ctl; + + ret = phy_write(phydev, MII_BMCR, ctl & ~BMCR_ANENABLE); + if (ret < 0) + return ret; + } + return 0; } From 98e8b6c9ac9d1b1e9d1122dfa6783d5d566bb8f7 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Tue, 19 Jan 2016 16:08:49 +0100 Subject: [PATCH 287/417] parisc: Fix ptrace syscall number and return value modification Mike Frysinger reported that his ptrace testcase showed strange behaviour on parisc: It was not possible to avoid a syscall and the return value of a syscall couldn't be changed. To modify a syscall number, we were missing to save the new syscall number to gr20 which is then picked up later in assembly again. The effect that the return value couldn't be changed is a side-effect of another bug in the assembly code. When a process is ptraced, userspace expects each syscall to report entrance and exit of a syscall. If a syscall number was given which doesn't exist, we jumped to the normal syscall exit code instead of informing userspace that the (non-existant) syscall exits. This unexpected behaviour confuses userspace and thus the bug was misinterpreted as if we can't change the return value. This patch fixes both problems and was tested on 64bit kernel with 32bit userspace. Signed-off-by: Helge Deller Cc: Mike Frysinger Cc: stable@vger.kernel.org # v4.0+ Tested-by: Mike Frysinger --- arch/parisc/kernel/ptrace.c | 16 +++++++++++----- arch/parisc/kernel/syscall.S | 5 ++++- 2 files changed, 15 insertions(+), 6 deletions(-) diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index 9585c81f755f..ce0b2b4075c7 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -269,14 +269,19 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, long do_syscall_trace_enter(struct pt_regs *regs) { - long ret = 0; - /* Do the secure computing check first. */ secure_computing_strict(regs->gr[20]); if (test_thread_flag(TIF_SYSCALL_TRACE) && - tracehook_report_syscall_entry(regs)) - ret = -1L; + tracehook_report_syscall_entry(regs)) { + /* + * Tracing decided this syscall should not happen or the + * debugger stored an invalid system call number. Skip + * the system call and the system call restart handling. + */ + regs->gr[20] = -1UL; + goto out; + } #ifdef CONFIG_64BIT if (!is_compat_task()) @@ -290,7 +295,8 @@ long do_syscall_trace_enter(struct pt_regs *regs) regs->gr[24] & 0xffffffff, regs->gr[23] & 0xffffffff); - return ret ? : regs->gr[20]; +out: + return regs->gr[20]; } void do_syscall_trace_exit(struct pt_regs *regs) diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 3fbd7252a4b2..fbafa0d0e2bf 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -343,7 +343,7 @@ tracesys_next: #endif comiclr,>>= __NR_Linux_syscalls, %r20, %r0 - b,n .Lsyscall_nosys + b,n .Ltracesys_nosys LDREGX %r20(%r19), %r19 @@ -359,6 +359,9 @@ tracesys_next: be 0(%sr7,%r19) ldo R%tracesys_exit(%r2),%r2 +.Ltracesys_nosys: + ldo -ENOSYS(%r0),%r28 /* set errno */ + /* Do *not* call this function on the gateway page, because it makes a direct call to syscall_trace. */ From b4f09ae6db2a98ff7817c3371aaab39ca22daf80 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Tue, 1 Mar 2016 23:18:43 +0100 Subject: [PATCH 288/417] parisc: Wire up copy_file_range syscall Signed-off-by: Helge Deller --- arch/parisc/include/uapi/asm/unistd.h | 3 ++- arch/parisc/kernel/syscall_table.S | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h index 35bdccbb2036..b75039f92116 100644 --- a/arch/parisc/include/uapi/asm/unistd.h +++ b/arch/parisc/include/uapi/asm/unistd.h @@ -361,8 +361,9 @@ #define __NR_membarrier (__NR_Linux + 343) #define __NR_userfaultfd (__NR_Linux + 344) #define __NR_mlock2 (__NR_Linux + 345) +#define __NR_copy_file_range (__NR_Linux + 346) -#define __NR_Linux_syscalls (__NR_mlock2 + 1) +#define __NR_Linux_syscalls (__NR_copy_file_range + 1) #define __IGNORE_select /* newselect */ diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index d4ffcfbc9885..585d50fc75c0 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -441,6 +441,7 @@ ENTRY_SAME(membarrier) ENTRY_SAME(userfaultfd) ENTRY_SAME(mlock2) /* 345 */ + ENTRY_SAME(copy_file_range) .ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b)) From 40b4f0fd74e46c017814618d67ec9127ff20f157 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 28 Feb 2016 10:03:51 +0800 Subject: [PATCH 289/417] sctp: lack the check for ports in sctp_v6_cmp_addr As the member .cmp_addr of sctp_af_inet6, sctp_v6_cmp_addr should also check the port of addresses, just like sctp_v4_cmp_addr, cause it's invoked by sctp_cmp_addr_exact(). Now sctp_v6_cmp_addr just check the port when two addresses have different family, and lack the port check for two ipv6 addresses. that will make sctp_hash_cmp() cannot work well. so fix it by adding ports comparison in sctp_v6_cmp_addr(). Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/sctp/ipv6.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index ec529121f38a..ce46f1c7f133 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -526,6 +526,8 @@ static int sctp_v6_cmp_addr(const union sctp_addr *addr1, } return 0; } + if (addr1->v6.sin6_port != addr2->v6.sin6_port) + return 0; if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr)) return 0; /* If this is a linklocal address, compare the scope_id. */ From 3d73e8fac8f84942f15307d6d9cb1dba843d3fb2 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 28 Feb 2016 10:33:11 +0800 Subject: [PATCH 290/417] sctp: sctp_remaddr_seq_show use the wrong variable to dump transport info Now in sctp_remaddr_seq_show(), we use variable *tsp to get the param *v. but *tsp is also used to traversal transport_addr_list, which will cover the previous value, and make sctp_transport_put work on the wrong transport. So fix it by adding a new variable to get the param *v. Fixes: fba4c330c5b9 ("sctp: hold transport before we access t->asoc in sctp proc") Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/sctp/proc.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/net/sctp/proc.c b/net/sctp/proc.c index ded7d931a6a5..963dffcc2618 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -482,7 +482,7 @@ static void sctp_remaddr_seq_stop(struct seq_file *seq, void *v) static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) { struct sctp_association *assoc; - struct sctp_transport *tsp; + struct sctp_transport *transport, *tsp; if (v == SEQ_START_TOKEN) { seq_printf(seq, "ADDR ASSOC_ID HB_ACT RTO MAX_PATH_RTX " @@ -490,10 +490,10 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) return 0; } - tsp = (struct sctp_transport *)v; - if (!sctp_transport_hold(tsp)) + transport = (struct sctp_transport *)v; + if (!sctp_transport_hold(transport)) return 0; - assoc = tsp->asoc; + assoc = transport->asoc; list_for_each_entry_rcu(tsp, &assoc->peer.transport_addr_list, transports) { @@ -546,7 +546,7 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "\n"); } - sctp_transport_put(tsp); + sctp_transport_put(transport); return 0; } From 735c1e2511a5c4e6c451c8b3d29916c4b0fa39ae Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Sun, 28 Feb 2016 22:50:59 +0300 Subject: [PATCH 291/417] of_mdio: fix kernel-doc for of_phy_connect() The 'flags' parameter of the of_phy_connect() function wasn't described in the kernel-doc comment... Signed-off-by: Sergei Shtylyov Signed-off-by: David S. Miller --- drivers/of/of_mdio.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 39c4be41ef83..365dc7e83ab4 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -305,6 +305,7 @@ EXPORT_SYMBOL(of_phy_find_device); * @dev: pointer to net_device claiming the phy * @phy_np: Pointer to device tree node for the PHY * @hndlr: Link state callback for the network device + * @flags: flags to pass to the PHY * @iface: PHY data interface type * * If successful, returns a pointer to the phy_device with the embedded From 949024d6702d1da8a266f42226d8402f0df078dc Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Sun, 14 Feb 2016 01:26:34 +0300 Subject: [PATCH 292/417] ARM: dts: porter: remove enable prop from HS-USB device node In the final versions of the Porter board (called "PORTER_C") Renesas decided to get rid of the Maxim Integrated MAX3355 OTG chip and didn't add any other provision to differ the host/gadget mode, so we'll have to remove no longer valid "renesas,enable-gpio" property from the HS-USB device node. Hopefully, the earlier revisions of the board were never seen in the wild... Fixes: c794f6a09a25 ("ARM: shmobile: porter: add HS-USB DT support") Reported-by: Yoshihiro Shimoda Signed-off-by: Sergei Shtylyov Signed-off-by: Simon Horman --- arch/arm/boot/dts/r8a7791-porter.dts | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm/boot/dts/r8a7791-porter.dts b/arch/arm/boot/dts/r8a7791-porter.dts index 6713b1ea732b..01d239c3eaaa 100644 --- a/arch/arm/boot/dts/r8a7791-porter.dts +++ b/arch/arm/boot/dts/r8a7791-porter.dts @@ -283,7 +283,6 @@ &hsusb { pinctrl-names = "default"; status = "okay"; - renesas,enable-gpio = <&gpio5 31 GPIO_ACTIVE_HIGH>; }; &usbphy { From 2d02b8bdba322b527c5f5168ce1ca10c2d982a78 Mon Sep 17 00:00:00 2001 From: Timothy Pearson Date: Fri, 26 Feb 2016 15:29:32 -0600 Subject: [PATCH 293/417] drm/ast: Fix incorrect register check for DRAM width During DRAM initialization on certain ASpeed devices, an incorrect bit (bit 10) was checked in the "SDRAM Bus Width Status" register to determine DRAM width. Query bit 6 instead in accordance with the Aspeed AST2050 datasheet v1.05. Signed-off-by: Timothy Pearson Cc: stable@vger.kernel.org Signed-off-by: Dave Airlie --- drivers/gpu/drm/ast/ast_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index 9759009d1da3..b1480acbb3c3 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -227,7 +227,7 @@ static int ast_get_dram_info(struct drm_device *dev) } while (ast_read32(ast, 0x10000) != 0x01); data = ast_read32(ast, 0x10004); - if (data & 0x400) + if (data & 0x40) ast->dram_bus_width = 16; else ast->dram_bus_width = 32; From 04fdbc825ffc02fb098964b92de802fff44e73fd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Tue, 1 Mar 2016 14:36:32 +0100 Subject: [PATCH 294/417] USB: qcserial: add Sierra Wireless EM74xx device ID MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The MC74xx and EM74xx modules use different IDs by default, according to the Lenovo EM7455 driver for Windows. Cc: Signed-off-by: Bjørn Mork Signed-off-by: Johan Hovold --- drivers/usb/serial/qcserial.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index 9c09d5feb50d..1bc6089b9008 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -157,8 +157,10 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x1199, 0x9056)}, /* Sierra Wireless Modem */ {DEVICE_SWI(0x1199, 0x9060)}, /* Sierra Wireless Modem */ {DEVICE_SWI(0x1199, 0x9061)}, /* Sierra Wireless Modem */ - {DEVICE_SWI(0x1199, 0x9070)}, /* Sierra Wireless MC74xx/EM74xx */ - {DEVICE_SWI(0x1199, 0x9071)}, /* Sierra Wireless MC74xx/EM74xx */ + {DEVICE_SWI(0x1199, 0x9070)}, /* Sierra Wireless MC74xx */ + {DEVICE_SWI(0x1199, 0x9071)}, /* Sierra Wireless MC74xx */ + {DEVICE_SWI(0x1199, 0x9078)}, /* Sierra Wireless EM74xx */ + {DEVICE_SWI(0x1199, 0x9079)}, /* Sierra Wireless EM74xx */ {DEVICE_SWI(0x413c, 0x81a2)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a3)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a4)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */ From 0178fd7dcc4451fcb90bec5e91226586962478d2 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Sun, 28 Feb 2016 17:35:59 +0200 Subject: [PATCH 295/417] mips/kvm: fix ioctl error handling Returning directly whatever copy_to_user(...) or copy_from_user(...) returns may not do the right thing if there's a pagefault: copy_to_user/copy_from_user return the number of bytes not copied in this case, but ioctls need to return -EFAULT instead. Fix up kvm on mips to do return copy_to_user(...)) ? -EFAULT : 0; and return copy_from_user(...)) ? -EFAULT : 0; everywhere. Cc: stable@vger.kernel.org Signed-off-by: Michael S. Tsirkin Signed-off-by: Paolo Bonzini --- arch/mips/kvm/mips.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 8bc3977576e6..3110447ab1e9 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -702,7 +702,7 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, } else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) { void __user *uaddr = (void __user *)(long)reg->addr; - return copy_to_user(uaddr, vs, 16); + return copy_to_user(uaddr, vs, 16) ? -EFAULT : 0; } else { return -EINVAL; } @@ -732,7 +732,7 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, } else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) { void __user *uaddr = (void __user *)(long)reg->addr; - return copy_from_user(vs, uaddr, 16); + return copy_from_user(vs, uaddr, 16) ? -EFAULT : 0; } else { return -EINVAL; } From 2680d6da455b636dd006636780c0f235c6561d70 Mon Sep 17 00:00:00 2001 From: Owen Hofmann Date: Tue, 1 Mar 2016 13:36:13 -0800 Subject: [PATCH 296/417] kvm: x86: Update tsc multiplier on change. vmx.c writes the TSC_MULTIPLIER field in vmx_vcpu_load, but only when a vcpu has migrated physical cpus. Record the last value written and update in vmx_vcpu_load on any change, otherwise a cpu migration must occur for TSC frequency scaling to take effect. Cc: stable@vger.kernel.org Fixes: ff2c3a1803775cc72dc6f624b59554956396b0ee Signed-off-by: Owen Hofmann Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index e2951b6edbbc..0ff453749a90 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -596,6 +596,8 @@ struct vcpu_vmx { /* Support for PML */ #define PML_ENTITY_NUM 512 struct page *pml_pg; + + u64 current_tsc_ratio; }; enum segment_cache_field { @@ -2127,14 +2129,16 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ - /* Setup TSC multiplier */ - if (cpu_has_vmx_tsc_scaling()) - vmcs_write64(TSC_MULTIPLIER, - vcpu->arch.tsc_scaling_ratio); - vmx->loaded_vmcs->cpu = cpu; } + /* Setup TSC multiplier */ + if (kvm_has_tsc_control && + vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) { + vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio; + vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); + } + vmx_vcpu_pi_load(vcpu, cpu); } From bd90123c4973821775d7ffae9891ad36017702a9 Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Mon, 29 Feb 2016 22:49:02 +0200 Subject: [PATCH 297/417] drm/i915/skl: Fix power domain suspend sequence During system suspend we need to first disable power wells then unitialize the display core. In case power well support is disabled we did this in the wrong order, so fix this up. Fixes: d314cd43 ("drm/i915: fix handling of the disable_power_well module option") CC: stable@vger.kernel.org CC: Patrik Jakobsson Signed-off-by: Imre Deak Reviewed-by: Patrik Jakobsson Link: http://patchwork.freedesktop.org/patch/msgid/1456778945-5411-1-git-send-email-imre.deak@intel.com (cherry picked from commit 2622d79bd9d18fd04b650234e6a218c5f95cf308) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_runtime_pm.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index 678ed3475d7e..ef8d24d9a50f 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -2303,15 +2303,15 @@ void intel_power_domains_init_hw(struct drm_i915_private *dev_priv, bool resume) */ void intel_power_domains_suspend(struct drm_i915_private *dev_priv) { - if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) - skl_display_core_uninit(dev_priv); - /* * Even if power well support was disabled we still want to disable * power wells while we are system suspended. */ if (!i915.disable_power_well) intel_display_power_put(dev_priv, POWER_DOMAIN_INIT); + + if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) + skl_display_core_uninit(dev_priv); } /** From eda908967feecf7575a8ab74f1695b0445cf324e Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 25 Feb 2016 21:10:28 +0000 Subject: [PATCH 298/417] drm/i915: Balance assert_rpm_wakelock_held() for !IS_ENABLED(CONFIG_PM) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 09731280028ce03e6a27e1998137f1775a2839f3 Author: Imre Deak Date: Wed Feb 17 14:17:42 2016 +0200 drm/i915: Add helper to get a display power ref if it was already enabled left the rpm wakelock assertions unbalanced if CONFIG_PM was disabled as intel_runtime_pm_get_if_in_use() would return true without incrementing the local bookkeeping required for the assertions. Fixes: 09731280028c ("drm/i915: Add helper to get a display power ref if it was already enabled") Signed-off-by: Chris Wilson CC: Mika Kuoppala CC: Joonas Lahtinen CC: Ville Syrjälä Cc: Imre Deak Link: http://patchwork.freedesktop.org/patch/msgid/1456434628-22574-1-git-send-email-chris@chris-wilson.co.uk Reviewed-by: Imre Deak (cherry picked from commit 135dc79efbc119ea5fb34475996983159e6ca31c) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_runtime_pm.c | 26 ++++++++++++------------- 1 file changed, 12 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index ef8d24d9a50f..4f43d9b32e66 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -2349,22 +2349,20 @@ bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv) { struct drm_device *dev = dev_priv->dev; struct device *device = &dev->pdev->dev; - int ret; - if (!IS_ENABLED(CONFIG_PM)) - return true; + if (IS_ENABLED(CONFIG_PM)) { + int ret = pm_runtime_get_if_in_use(device); - ret = pm_runtime_get_if_in_use(device); - - /* - * In cases runtime PM is disabled by the RPM core and we get an - * -EINVAL return value we are not supposed to call this function, - * since the power state is undefined. This applies atm to the - * late/early system suspend/resume handlers. - */ - WARN_ON_ONCE(ret < 0); - if (ret <= 0) - return false; + /* + * In cases runtime PM is disabled by the RPM core and we get + * an -EINVAL return value we are not supposed to call this + * function, since the power state is undefined. This applies + * atm to the late/early system suspend/resume handlers. + */ + WARN_ON_ONCE(ret < 0); + if (ret <= 0) + return false; + } atomic_inc(&dev_priv->pm.wakeref_count); assert_rpm_wakelock_held(dev_priv); From 2af8c4dc2e9c7038aefe9a822aa1df62e2b106b7 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 26 Feb 2016 10:50:34 +0100 Subject: [PATCH 299/417] mac80211_hwsim: treat as part of mac80211 for MAINTAINERS Since I maintain this driver as part of mac80211, add it to the file list for mac80211; this helps submitters send it to me instead of Kalle and also makes the build robot apply the patches for it on the right tree for build attempts. Acked-by: Kalle Valo Signed-off-by: Johannes Berg --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index ded96408efe6..25bdfe6a3c0e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6664,6 +6664,7 @@ S: Maintained F: Documentation/networking/mac80211-injection.txt F: include/net/mac80211.h F: net/mac80211/ +F: drivers/net/wireless/mac80211_hwsim.[ch] MACVLAN DRIVER M: Patrick McHardy From 4e94ebdd06d5dc72b7a40fc12fc496d601fb7bbc Mon Sep 17 00:00:00 2001 From: Ladi Prosek Date: Mon, 1 Feb 2016 19:36:31 +0100 Subject: [PATCH 300/417] virtio-pci: read the right virtio_pci_notify_cap field Looks like a copy-paste bug. The value is used as an optimization and a wrong value probably isn't causing any serious damage. Found when porting this code to Windows. Signed-off-by: Ladi Prosek Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_pci_modern.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index c0c11fad4611..7760fc1a2218 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -679,7 +679,7 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev) pci_read_config_dword(pci_dev, notify + offsetof(struct virtio_pci_notify_cap, - cap.length), + cap.offset), ¬ify_offset); /* We don't know how many VQs we'll map, ahead of the time. From e1f33be9186363da7955bcb5f0b03e6685544c50 Mon Sep 17 00:00:00 2001 From: Greg Kurz Date: Tue, 16 Feb 2016 15:54:28 +0100 Subject: [PATCH 301/417] vhost: fix error path in vhost_init_used() We don't want side effects. If something fails, we rollback vq->is_le to its previous value. Signed-off-by: Greg Kurz Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vhost.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index ad2146a9ab2d..236553e81027 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1156,6 +1156,8 @@ int vhost_init_used(struct vhost_virtqueue *vq) { __virtio16 last_used_idx; int r; + bool is_le = vq->is_le; + if (!vq->private_data) { vq->is_le = virtio_legacy_is_little_endian(); return 0; @@ -1165,15 +1167,20 @@ int vhost_init_used(struct vhost_virtqueue *vq) r = vhost_update_used_flags(vq); if (r) - return r; + goto err; vq->signalled_used_valid = false; - if (!access_ok(VERIFY_READ, &vq->used->idx, sizeof vq->used->idx)) - return -EFAULT; + if (!access_ok(VERIFY_READ, &vq->used->idx, sizeof vq->used->idx)) { + r = -EFAULT; + goto err; + } r = __get_user(last_used_idx, &vq->used->idx); if (r) - return r; + goto err; vq->last_used_idx = vhost16_to_cpu(vq, last_used_idx); return 0; +err: + vq->is_le = is_le; + return r; } EXPORT_SYMBOL_GPL(vhost_init_used); From eda1d1cf8d18383f19cd2b752f786120efa4768f Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 24 Feb 2016 17:18:25 -0500 Subject: [PATCH 302/417] drm/amdgpu/pm: update current crtc info after setting the powerstate MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On CI, we need to see if the number of crtcs changes to determine whether or not we need to upload the mclk table again. In practice we don't currently upload the mclk table again after the initial load. The only reason you would would be to add new states, e.g., for arbitrary mclk setting which is not currently supported. Acked-by: Jordan Lazare Acked-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 66855b62a603..95a4a25d8df9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -649,9 +649,6 @@ static void amdgpu_dpm_change_power_state_locked(struct amdgpu_device *adev) /* update display watermarks based on new power state */ amdgpu_display_bandwidth_update(adev); - adev->pm.dpm.current_active_crtcs = adev->pm.dpm.new_active_crtcs; - adev->pm.dpm.current_active_crtc_count = adev->pm.dpm.new_active_crtc_count; - /* wait for the rings to drain */ for (i = 0; i < AMDGPU_MAX_RINGS; i++) { struct amdgpu_ring *ring = adev->rings[i]; @@ -670,6 +667,9 @@ static void amdgpu_dpm_change_power_state_locked(struct amdgpu_device *adev) /* update displays */ amdgpu_dpm_display_configuration_changed(adev); + adev->pm.dpm.current_active_crtcs = adev->pm.dpm.new_active_crtcs; + adev->pm.dpm.current_active_crtc_count = adev->pm.dpm.new_active_crtc_count; + if (adev->pm.funcs->force_performance_level) { if (adev->pm.dpm.thermal_active) { enum amdgpu_dpm_forced_level level = adev->pm.dpm.forced_level; From 5e031d9fe8b0741f11d49667dfc3ebf5454121fd Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 24 Feb 2016 17:38:38 -0500 Subject: [PATCH 303/417] drm/radeon/pm: update current crtc info after setting the powerstate MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On CI, we need to see if the number of crtcs changes to determine whether or not we need to upload the mclk table again. In practice we don't currently upload the mclk table again after the initial load. The only reason you would would be to add new states, e.g., for arbitrary mclk setting which is not currently supported. Acked-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/radeon/radeon_pm.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index ca3be90a3bb4..0f14d897baf9 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -1080,10 +1080,6 @@ static void radeon_dpm_change_power_state_locked(struct radeon_device *rdev) /* update display watermarks based on new power state */ radeon_bandwidth_update(rdev); - rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs; - rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count; - rdev->pm.dpm.single_display = single_display; - /* wait for the rings to drain */ for (i = 0; i < RADEON_NUM_RINGS; i++) { struct radeon_ring *ring = &rdev->ring[i]; @@ -1102,6 +1098,10 @@ static void radeon_dpm_change_power_state_locked(struct radeon_device *rdev) /* update displays */ radeon_dpm_display_configuration_changed(rdev); + rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs; + rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count; + rdev->pm.dpm.single_display = single_display; + if (rdev->asic->dpm.force_performance_level) { if (rdev->pm.dpm.thermal_active) { enum radeon_dpm_forced_level level = rdev->pm.dpm.forced_level; From dc26a2a2b3f037c2727f514b64e8a865721ec74b Mon Sep 17 00:00:00 2001 From: Rex Zhu Date: Thu, 25 Feb 2016 17:16:52 +0800 Subject: [PATCH 304/417] drm/amd/powerplay: export AMD_PP_EVENT_COMPLETE_INIT task to amdgpu. This is needed to init the dynamic states without a display. To be used in the next commit. Signed-off-by: Rex Zhu Reviewed-by: Alex Deucher --- drivers/gpu/drm/amd/powerplay/amd_powerplay.c | 5 ++++- drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c | 1 + 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c index aa67244a77ae..589599f66fcc 100644 --- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c @@ -402,8 +402,11 @@ int pp_dpm_dispatch_tasks(void *handle, enum amd_pp_event event_id, void *input, data.requested_ui_label = power_state_convert(ps); ret = pem_handle_event(pp_handle->eventmgr, event_id, &data); + break; } - break; + case AMD_PP_EVENT_COMPLETE_INIT: + ret = pem_handle_event(pp_handle->eventmgr, event_id, &data); + break; default: break; } diff --git a/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c b/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c index 83be3cf210e0..6b52c78cb404 100644 --- a/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c +++ b/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c @@ -165,6 +165,7 @@ const struct action_chain resume_action_chain = { }; static const pem_event_action *complete_init_event[] = { + unblock_adjust_power_state_tasks, adjust_power_state_tasks, enable_gfx_clock_gating_tasks, enable_gfx_voltage_island_power_gating_tasks, From 4ea2efae0d117c5b5f44081bab941542d892e758 Mon Sep 17 00:00:00 2001 From: Rex Zhu Date: Thu, 25 Feb 2016 17:32:45 +0800 Subject: [PATCH 305/417] drm/amd/powerplay: send event to notify powerplay all modules are initialized. with this event, powerplay can adjust current power state if needed. Signed-off-by: Rex Zhu Reviewed-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c index b9d0d55f6b47..3cb6d6c413c7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c @@ -143,8 +143,10 @@ static int amdgpu_pp_late_init(void *handle) adev->powerplay.pp_handle); #ifdef CONFIG_DRM_AMD_POWERPLAY - if (adev->pp_enabled) + if (adev->pp_enabled) { amdgpu_pm_sysfs_init(adev); + amdgpu_dpm_dispatch_task(adev, AMD_PP_EVENT_COMPLETE_INIT, NULL, NULL); + } #endif return ret; } From feebe91aa9a9d99d9ec157612a614fadb79beb99 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Fri, 26 Feb 2016 16:18:15 +0100 Subject: [PATCH 306/417] drm/amdgpu: apply gfx_v8 fixes to gfx_v7 as well MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We never ported that back to CIK, so we could run into VM faults here. Signed-off-by: Christian König Reviewed-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index 7732059ae30f..06602df707f8 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -3628,6 +3628,19 @@ static void gfx_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring, unsigned vm_id, uint64_t pd_addr) { int usepfp = (ring->type == AMDGPU_RING_TYPE_GFX); + uint32_t seq = ring->fence_drv.sync_seq; + uint64_t addr = ring->fence_drv.gpu_addr; + + amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5)); + amdgpu_ring_write(ring, (WAIT_REG_MEM_MEM_SPACE(1) | /* memory */ + WAIT_REG_MEM_FUNCTION(3) | /* equal */ + WAIT_REG_MEM_ENGINE(usepfp))); /* pfp or me */ + amdgpu_ring_write(ring, addr & 0xfffffffc); + amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff); + amdgpu_ring_write(ring, seq); + amdgpu_ring_write(ring, 0xffffffff); + amdgpu_ring_write(ring, 4); /* poll interval */ + if (usepfp) { /* synce CE with ME to prevent CE fetch CEIB before context switch done */ amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0)); From 9cac537332f5502c103415b25609548c276a09f8 Mon Sep 17 00:00:00 2001 From: Chunming Zhou Date: Mon, 29 Feb 2016 14:12:38 +0800 Subject: [PATCH 307/417] drm/amdgpu/gfx8: specify which engine to wait before vm flush MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Select between me and pfp properly. Signed-off-by: Chunming Zhou Reviewed-by: Christian König Cc: stable@vger.kernel.org Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 1c40bd90afbb..7086ac17abee 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -4809,7 +4809,8 @@ static void gfx_v8_0_ring_emit_vm_flush(struct amdgpu_ring *ring, amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5)); amdgpu_ring_write(ring, (WAIT_REG_MEM_MEM_SPACE(1) | /* memory */ - WAIT_REG_MEM_FUNCTION(3))); /* equal */ + WAIT_REG_MEM_FUNCTION(3) | /* equal */ + WAIT_REG_MEM_ENGINE(usepfp))); /* pfp or me */ amdgpu_ring_write(ring, addr & 0xfffffffc); amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff); amdgpu_ring_write(ring, seq); From b3dae7828399ef316e3fabf7e82c6415cb03a02e Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 25 Feb 2016 11:24:52 -0500 Subject: [PATCH 308/417] drm/amdgpu/cz: enable/disable vce dpm even if vce pg is disabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit I missed this when cleaning up the vce pg handling. Reviewed-by: Christian König Reviewed-by: Rex Zhu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/cz_dpm.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c index 9056355309d1..208990ab83d3 100644 --- a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c @@ -2226,10 +2226,8 @@ static void cz_dpm_powergate_vce(struct amdgpu_device *adev, bool gate) } } else { /*pi->caps_vce_pg*/ cz_update_vce_dpm(adev); - cz_enable_vce_dpm(adev, true); + cz_enable_vce_dpm(adev, !gate); } - - return; } const struct amd_ip_funcs cz_dpm_ip_funcs = { From 370afa7ac5dc6c65cebeaee841ae700eb2387a55 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 29 Feb 2016 15:29:48 -0500 Subject: [PATCH 309/417] drm/amdgpu/powerplay/cz: enable/disable vce dpm independent of vce pg MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If we don't disable it when vce is not in use, we use extra power if vce pg is disabled. Reviewed-by: Christian König Reviewed-by: Rex Zhu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c index ad7700822a1c..ff08ce41bde9 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c @@ -226,7 +226,7 @@ int cz_dpm_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate) } } else { cz_dpm_update_vce_dpm(hwmgr); - cz_enable_disable_vce_dpm(hwmgr, true); + cz_enable_disable_vce_dpm(hwmgr, !bgate); return 0; } From 89913ea615754163ae9a066c9c1b95aa2a2f51b4 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 29 Feb 2016 16:11:07 -0500 Subject: [PATCH 310/417] drm/amdgpu/cz: remove commented out call to enable vce pg MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This code path is not currently enabled now that we properly respect the vce pg flags, so uncomment the actual pg calls so the code is as it should be we are eventually able to enable vce pg. Reviewed-by: Christian König Reviewed-by: Rex Zhu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/cz_dpm.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c index 208990ab83d3..e7ef2261ff4a 100644 --- a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c @@ -2202,8 +2202,7 @@ static void cz_dpm_powergate_vce(struct amdgpu_device *adev, bool gate) AMD_PG_STATE_GATE); cz_enable_vce_dpm(adev, false); - /* TODO: to figure out why vce can't be poweroff. */ - /* cz_send_msg_to_smc(adev, PPSMC_MSG_VCEPowerOFF); */ + cz_send_msg_to_smc(adev, PPSMC_MSG_VCEPowerOFF); pi->vce_power_gated = true; } else { cz_send_msg_to_smc(adev, PPSMC_MSG_VCEPowerON); From 0b39c531cfa12dad54eac238c2e303b994df1ef7 Mon Sep 17 00:00:00 2001 From: Arindam Nath Date: Wed, 2 Mar 2016 17:19:01 +0530 Subject: [PATCH 311/417] drm/amdgpu: return from atombios_dp_get_dpcd only when error In amdgpu_connector_hotplug(), we need to start DP link training only after we have received DPCD. The function amdgpu_atombios_dp_get_dpcd() returns non-zero value only when an error condition is met, otherwise returns zero. So in case the function encounters an error, we need to skip rest of the code and return from amdgpu_connector_hotplug() immediately. Only when we are successfull in reading DPCD pin, we should carry on with turning-on the monitor. Signed-off-by: Arindam Nath Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c index 89c3dd62ba21..119cdc2c43e7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c @@ -77,7 +77,7 @@ void amdgpu_connector_hotplug(struct drm_connector *connector) } else if (amdgpu_atombios_dp_needs_link_train(amdgpu_connector)) { /* Don't try to start link training before we * have the dpcd */ - if (!amdgpu_atombios_dp_get_dpcd(amdgpu_connector)) + if (amdgpu_atombios_dp_get_dpcd(amdgpu_connector)) return; /* set it to OFF so that drm_helper_connector_dpms() From 39680f50ae54cbbb6e72ac38b8329dd3eb9105f4 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 1 Mar 2016 11:56:22 -0800 Subject: [PATCH 312/417] userfaultfd: don't block on the last VM updates at exit time The exit path will do some final updates to the VM of an exiting process to inform others of the fact that the process is going away. That happens, for example, for robust futex state cleanup, but also if the parent has asked for a TID update when the process exits (we clear the child tid field in user space). However, at the time we do those final VM accesses, we've already stopped accepting signals, so the usual "stop waiting for userfaults on signal" code in fs/userfaultfd.c no longer works, and the process can become an unkillable zombie waiting for something that will never happen. To solve this, just make handle_userfault() abort any user fault handling if we're already in the exit path past the signal handling state being dead (marked by PF_EXITING). This VM special case is pretty ugly, and it is possible that we should look at finalizing signals later (or move the VM final accesses earlier). But in the meantime this is a fairly minimally intrusive fix. Reported-and-tested-by: Dmitry Vyukov Acked-by: Andrea Arcangeli Signed-off-by: Linus Torvalds --- fs/userfaultfd.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 50311703135b..66cdb44616d5 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -286,6 +286,12 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address, if (unlikely(ACCESS_ONCE(ctx->released))) goto out; + /* + * We don't do userfault handling for the final child pid update. + */ + if (current->flags & PF_EXITING) + goto out; + /* * Check that we can return VM_FAULT_RETRY. * From 9cd753a1f449b9af49a4c994ffab8c4f99d91f14 Mon Sep 17 00:00:00 2001 From: Michal Schmidt Date: Wed, 2 Mar 2016 13:47:05 +0100 Subject: [PATCH 313/417] bnx2x: fix crash on big-endian when adding VLAN bnx2x crashes during the initialization of the 8021q module on ppc64. The bug is a missing conversion from le32 in bnx2x_handle_classification_eqe() when obtaining the cid value from struct eth_event_data. The fields in struct eth_event_data should all be declared as little-endian and conversions added where missing. Signed-off-by: Michal Schmidt Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h | 6 +++--- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 13 +++++-------- drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c | 9 ++++----- 3 files changed, 12 insertions(+), 16 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h index 27aa0802d87d..90a4dba3eccf 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h @@ -5207,9 +5207,9 @@ struct e2_integ_data { * set mac event data */ struct eth_event_data { - u32 echo; - u32 reserved0; - u32 reserved1; + __le32 echo; + __le32 reserved0; + __le32 reserved1; }; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 6c4e3a69976f..b707ba8a7535 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -5280,14 +5280,14 @@ static void bnx2x_handle_classification_eqe(struct bnx2x *bp, { unsigned long ramrod_flags = 0; int rc = 0; - u32 cid = elem->message.data.eth_event.echo & BNX2X_SWCID_MASK; + u32 echo = le32_to_cpu(elem->message.data.eth_event.echo); + u32 cid = echo & BNX2X_SWCID_MASK; struct bnx2x_vlan_mac_obj *vlan_mac_obj; /* Always push next commands out, don't wait here */ __set_bit(RAMROD_CONT, &ramrod_flags); - switch (le32_to_cpu((__force __le32)elem->message.data.eth_event.echo) - >> BNX2X_SWCID_SHIFT) { + switch (echo >> BNX2X_SWCID_SHIFT) { case BNX2X_FILTER_MAC_PENDING: DP(BNX2X_MSG_SP, "Got SETUP_MAC completions\n"); if (CNIC_LOADED(bp) && (cid == BNX2X_ISCSI_ETH_CID(bp))) @@ -5308,8 +5308,7 @@ static void bnx2x_handle_classification_eqe(struct bnx2x *bp, bnx2x_handle_mcast_eqe(bp); return; default: - BNX2X_ERR("Unsupported classification command: %d\n", - elem->message.data.eth_event.echo); + BNX2X_ERR("Unsupported classification command: 0x%x\n", echo); return; } @@ -5596,10 +5595,8 @@ static void bnx2x_eq_int(struct bnx2x *bp) BNX2X_STATE_OPENING_WAIT4_PORT): case (EVENT_RING_OPCODE_RSS_UPDATE_RULES | BNX2X_STATE_CLOSING_WAIT4_HALT): - cid = elem->message.data.eth_event.echo & - BNX2X_SWCID_MASK; DP(BNX2X_MSG_SP, "got RSS_UPDATE ramrod. CID %d\n", - cid); + SW_CID(elem->message.data.eth_event.echo)); rss_raw->clear_pending(rss_raw); break; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 9d027348cd09..55fcc216bd35 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -1672,11 +1672,12 @@ void bnx2x_vf_handle_classification_eqe(struct bnx2x *bp, { unsigned long ramrod_flags = 0; int rc = 0; + u32 echo = le32_to_cpu(elem->message.data.eth_event.echo); /* Always push next commands out, don't wait here */ set_bit(RAMROD_CONT, &ramrod_flags); - switch (elem->message.data.eth_event.echo >> BNX2X_SWCID_SHIFT) { + switch (echo >> BNX2X_SWCID_SHIFT) { case BNX2X_FILTER_MAC_PENDING: rc = vfq->mac_obj.complete(bp, &vfq->mac_obj, elem, &ramrod_flags); @@ -1686,8 +1687,7 @@ void bnx2x_vf_handle_classification_eqe(struct bnx2x *bp, &ramrod_flags); break; default: - BNX2X_ERR("Unsupported classification command: %d\n", - elem->message.data.eth_event.echo); + BNX2X_ERR("Unsupported classification command: 0x%x\n", echo); return; } if (rc < 0) @@ -1755,8 +1755,7 @@ int bnx2x_iov_eq_sp_event(struct bnx2x *bp, union event_ring_elem *elem) case EVENT_RING_OPCODE_MULTICAST_RULES: case EVENT_RING_OPCODE_FILTERS_RULES: case EVENT_RING_OPCODE_RSS_UPDATE_RULES: - cid = (elem->message.data.eth_event.echo & - BNX2X_SWCID_MASK); + cid = SW_CID(elem->message.data.eth_event.echo); DP(BNX2X_MSG_IOV, "checking filtering comp cid=%d\n", cid); break; case EVENT_RING_OPCODE_VF_FLR: From 5cc5c2d2e5a46c7395a0453f9ea1a446ac4c1b97 Mon Sep 17 00:00:00 2001 From: Michal Schmidt Date: Wed, 2 Mar 2016 13:47:06 +0100 Subject: [PATCH 314/417] bnx2x: fix sending VF->PF messages on big-endian When a VF is sending a message to the PF, it needs to trigger the PF to tell it the message is ready. The trigger did not work on ppc64. No interrupt appeared in the PF. The bug is due to confusion about the layout of struct trigger_vf_zone. In bnx2x_send_msg2pf() the trigger is written using writeb(), not writel(), so the attempt to define the struct with a reversed layout on big-endian is counter-productive. Signed-off-by: Michal Schmidt Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h index 90a4dba3eccf..47b13ed6a01a 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h @@ -5114,15 +5114,9 @@ struct vf_pf_channel_zone_trigger { * zone that triggers the in-bound interrupt */ struct trigger_vf_zone { -#if defined(__BIG_ENDIAN) - u16 reserved1; - u8 reserved0; - struct vf_pf_channel_zone_trigger vf_pf_channel; -#elif defined(__LITTLE_ENDIAN) struct vf_pf_channel_zone_trigger vf_pf_channel; u8 reserved0; u16 reserved1; -#endif u32 reserved2; }; From a524ef77d54d7e12045841f4fcc430c1850f71f2 Mon Sep 17 00:00:00 2001 From: Michal Schmidt Date: Wed, 2 Mar 2016 13:47:07 +0100 Subject: [PATCH 315/417] bnx2x: fix receive of VF->PF mailbox messages by the PF on big-endian On ppc64 the PF did not receive messages from VFs correctly. Fields of struct vf_pf_event_data are little-endian. Signed-off-by: Michal Schmidt Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h | 6 +++--- drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c | 6 ++++-- 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h index 47b13ed6a01a..10585916a4bb 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h @@ -5213,9 +5213,9 @@ struct eth_event_data { struct vf_pf_event_data { u8 vf_id; u8 reserved0; - u16 reserved1; - u32 msg_addr_lo; - u32 msg_addr_hi; + __le16 reserved1; + __le32 msg_addr_lo; + __le32 msg_addr_hi; }; /* diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c index 1374e5394a79..bfae300cf25f 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c @@ -2187,8 +2187,10 @@ void bnx2x_vf_mbx_schedule(struct bnx2x *bp, /* Update VFDB with current message and schedule its handling */ mutex_lock(&BP_VFDB(bp)->event_mutex); - BP_VF_MBX(bp, vf_idx)->vf_addr_hi = vfpf_event->msg_addr_hi; - BP_VF_MBX(bp, vf_idx)->vf_addr_lo = vfpf_event->msg_addr_lo; + BP_VF_MBX(bp, vf_idx)->vf_addr_hi = + le32_to_cpu(vfpf_event->msg_addr_hi); + BP_VF_MBX(bp, vf_idx)->vf_addr_lo = + le32_to_cpu(vfpf_event->msg_addr_lo); BP_VFDB(bp)->event_occur |= (1ULL << vf_idx); mutex_unlock(&BP_VFDB(bp)->event_mutex); From ca4f2d5036be809b0f82ce38a7663d237efa3986 Mon Sep 17 00:00:00 2001 From: Michal Schmidt Date: Wed, 2 Mar 2016 13:47:08 +0100 Subject: [PATCH 316/417] bnx2x: access cfc_del_event only if the opcode is CFC_DEL It's not really a bug, but it was odd that bnx2x_eq_int() read the message data as if it were a cfc_del_event regardless of the event type. It's cleaner to access only the appropriate member of union event_data after checking the event opcode. Signed-off-by: Michal Schmidt Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index b707ba8a7535..0e0bcbdb84d1 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -5477,9 +5477,6 @@ static void bnx2x_eq_int(struct bnx2x *bp) goto next_spqe; } - /* elem CID originates from FW; actually LE */ - cid = SW_CID((__force __le32) - elem->message.data.cfc_del_event.cid); opcode = elem->message.opcode; /* handle eq element */ @@ -5502,6 +5499,11 @@ static void bnx2x_eq_int(struct bnx2x *bp) * we may want to verify here that the bp state is * HALTING */ + + /* elem CID originates from FW; actually LE */ + cid = SW_CID((__force __le32) + elem->message.data.cfc_del_event.cid); + DP(BNX2X_MSG_SP, "got delete ramrod for MULTI[%d]\n", cid); From da472731d8d0a50c451f5116477ffd9b3165f309 Mon Sep 17 00:00:00 2001 From: Michal Schmidt Date: Wed, 2 Mar 2016 13:47:09 +0100 Subject: [PATCH 317/417] bnx2x: define fields of struct cfc_del_event_data as little-endian There were no missing endianness conversions in this case, but the fields of struct cfc_del_event_data should be defined as little-endian to get rid of the ugly (__force __le32) casts. Signed-off-by: Michal Schmidt Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h | 6 +++--- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 3 +-- drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c | 3 +-- 3 files changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h index 10585916a4bb..a24909a3ed72 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h @@ -4896,9 +4896,9 @@ struct c2s_pri_trans_table_entry { * cfc delete event data */ struct cfc_del_event_data { - u32 cid; - u32 reserved0; - u32 reserved1; + __le32 cid; + __le32 reserved0; + __le32 reserved1; }; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 0e0bcbdb84d1..9f5716aea180 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -5501,8 +5501,7 @@ static void bnx2x_eq_int(struct bnx2x *bp) */ /* elem CID originates from FW; actually LE */ - cid = SW_CID((__force __le32) - elem->message.data.cfc_del_event.cid); + cid = SW_CID(elem->message.data.cfc_del_event.cid); DP(BNX2X_MSG_SP, "got delete ramrod for MULTI[%d]\n", cid); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 55fcc216bd35..632daff117d3 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -1747,8 +1747,7 @@ int bnx2x_iov_eq_sp_event(struct bnx2x *bp, union event_ring_elem *elem) switch (opcode) { case EVENT_RING_OPCODE_CFC_DEL: - cid = SW_CID((__force __le32) - elem->message.data.cfc_del_event.cid); + cid = SW_CID(elem->message.data.cfc_del_event.cid); DP(BNX2X_MSG_IOV, "checking cfc-del comp cid=%d\n", cid); break; case EVENT_RING_OPCODE_CLASSIFICATION_RULES: From 8d1c6bcb0f7f6e9f1481bcd3a1c52e75cc1f7fa4 Mon Sep 17 00:00:00 2001 From: Michal Schmidt Date: Wed, 2 Mar 2016 13:47:10 +0100 Subject: [PATCH 318/417] bnx2x: define event data reserved fields as little-endian For consistency with other event data structs and to lessen the chance of a mistake should one of the reserved fields become used in the future, define the reserved fields as little-endian. Signed-off-by: Michal Schmidt Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h index a24909a3ed72..91874d24fd56 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h @@ -5224,9 +5224,9 @@ struct vf_pf_event_data { struct vf_flr_event_data { u8 vf_id; u8 reserved0; - u16 reserved1; - u32 reserved2; - u32 reserved3; + __le16 reserved1; + __le32 reserved2; + __le32 reserved3; }; /* @@ -5235,9 +5235,9 @@ struct vf_flr_event_data { struct malicious_vf_event_data { u8 vf_id; u8 err_id; - u16 reserved1; - u32 reserved2; - u32 reserved3; + __le16 reserved1; + __le32 reserved2; + __le32 reserved3; }; /* From 7e88009b9b2a22a20064abdb2a6536eeb3bcf432 Mon Sep 17 00:00:00 2001 From: Michal Schmidt Date: Wed, 2 Mar 2016 13:47:11 +0100 Subject: [PATCH 319/417] bnx2x: fix indentation in bnx2x_sp_task() Fix a case of misleading code indentation. Signed-off-by: Michal Schmidt Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 9f5716aea180..2bf9c871144f 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -5682,7 +5682,7 @@ static void bnx2x_sp_task(struct work_struct *work) if (status & BNX2X_DEF_SB_IDX) { struct bnx2x_fastpath *fp = bnx2x_fcoe_fp(bp); - if (FCOE_INIT(bp) && + if (FCOE_INIT(bp) && (bnx2x_has_rx_work(fp) || bnx2x_has_tx_work(fp))) { /* Prevent local bottom-halves from running as * we are going to change the local NAPI list. From 607e681111800f9bbfcd823a385a45dd0295dfb8 Mon Sep 17 00:00:00 2001 From: Chunhao Lin Date: Thu, 3 Mar 2016 00:59:15 +0800 Subject: [PATCH 320/417] r8169: Enable RX_MULTI_EN for RTL_GIGA_MAC_VER_41~48 For RTL8168G/RTL8168H/RTL8411B/RTL8107E, enable this flag to eliminate message "AMD-Vi: Event logged [IO_PAGE_FAULT device=01:00.0 domain=0x0002 address=0x0000000000003000 flags=0x0050] in dmesg. Signed-off-by: Chunhao Lin Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/r8169.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 4caeacb45136..dd2cf3738b73 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -4933,8 +4933,6 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST); break; case RTL_GIGA_MAC_VER_40: - RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF); - break; case RTL_GIGA_MAC_VER_41: case RTL_GIGA_MAC_VER_42: case RTL_GIGA_MAC_VER_43: @@ -4943,8 +4941,6 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_46: case RTL_GIGA_MAC_VER_47: case RTL_GIGA_MAC_VER_48: - RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST | RX_EARLY_OFF); - break; case RTL_GIGA_MAC_VER_49: case RTL_GIGA_MAC_VER_50: case RTL_GIGA_MAC_VER_51: From 59a7c2fd336eaafb030aac9c91ac21d136a99f33 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 29 Feb 2016 21:17:09 +0200 Subject: [PATCH 321/417] net/mlx5e: Remove wrong poll CQ optimization With the MLX5E_CQ_HAS_CQES optimization flag, the following buggy flow might occur: - Suppose RX is always busy, TX has a single packet every second. - We poll a single TX cqe and clear its flag. - We never arm it again as RX is always busy. - TX CQ flag is never changed, and new TX cqes are not polled. We revert this optimization. Fixes: e586b3b0baee ('net/mlx5: Ethernet Datapath files') Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 5 ----- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 7 ------- drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 10 +--------- drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c | 1 - 4 files changed, 1 insertion(+), 22 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index aac071a7e830..614a6022db25 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -304,14 +304,9 @@ enum { MLX5E_RQ_STATE_POST_WQES_ENABLE, }; -enum cq_flags { - MLX5E_CQ_HAS_CQES = 1, -}; - struct mlx5e_cq { /* data path - accessed per cqe */ struct mlx5_cqwq wq; - unsigned long flags; /* data path - accessed per napi poll */ struct napi_struct *napi; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index dd959d929aad..3fd6a583e88a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -230,10 +230,6 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq); int work_done; - /* avoid accessing cq (dma coherent memory) if not needed */ - if (!test_and_clear_bit(MLX5E_CQ_HAS_CQES, &cq->flags)) - return 0; - for (work_done = 0; work_done < budget; work_done++) { struct mlx5e_rx_wqe *wqe; struct mlx5_cqe64 *cqe; @@ -279,8 +275,5 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) /* ensure cq space is freed before enabling more cqes */ wmb(); - if (work_done == budget) - set_bit(MLX5E_CQ_HAS_CQES, &cq->flags); - return work_done; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 2c3fba0fff54..2beea8cdb604 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -335,10 +335,6 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq) u16 sqcc; int i; - /* avoid accessing cq (dma coherent memory) if not needed */ - if (!test_and_clear_bit(MLX5E_CQ_HAS_CQES, &cq->flags)) - return false; - sq = container_of(cq, struct mlx5e_sq, cq); npkts = 0; @@ -422,10 +418,6 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq) netif_tx_wake_queue(sq->txq); sq->stats.wake++; } - if (i == MLX5E_TX_CQ_POLL_BUDGET) { - set_bit(MLX5E_CQ_HAS_CQES, &cq->flags); - return true; - } - return false; + return (i == MLX5E_TX_CQ_POLL_BUDGET); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index 4ac8d716dbdd..66d51a77609e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -88,7 +88,6 @@ void mlx5e_completion_event(struct mlx5_core_cq *mcq) { struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq); - set_bit(MLX5E_CQ_HAS_CQES, &cq->flags); set_bit(MLX5E_CHANNEL_NAPI_SCHED, &cq->channel->flags); barrier(); napi_schedule(cq->napi); From ab0394fe2c258fdb5086c51a251b28f8ee7ab35c Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 29 Feb 2016 21:17:10 +0200 Subject: [PATCH 322/417] net/mlx5e: Fix LRO modify Ethtool LRO enable/disable is broken, as of today we only modify TCP TIRs in order to apply the requested configuration. Hardware requires that all TIRs pointing to the same RQ should share the same LRO configuration. For that all other TIRs' LRO fields must be modified as well. Fixes: 5c50368f3831 ('net/mlx5e: Light-weight netdev open/stop') Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index d4e1c3045200..137b05e1c68a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1317,7 +1317,7 @@ static void mlx5e_build_tir_ctx_lro(void *tirc, struct mlx5e_priv *priv) lro_timer_supported_periods[2])); } -static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt) +static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; @@ -1325,6 +1325,7 @@ static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt) void *tirc; int inlen; int err; + int tt; inlen = MLX5_ST_SZ_BYTES(modify_tir_in); in = mlx5_vzalloc(inlen); @@ -1336,7 +1337,11 @@ static int mlx5e_modify_tir_lro(struct mlx5e_priv *priv, int tt) mlx5e_build_tir_ctx_lro(tirc, priv); - err = mlx5_core_modify_tir(mdev, priv->tirn[tt], in, inlen); + for (tt = 0; tt < MLX5E_NUM_TT; tt++) { + err = mlx5_core_modify_tir(mdev, priv->tirn[tt], in, inlen); + if (err) + break; + } kvfree(in); @@ -1885,8 +1890,10 @@ static int mlx5e_set_features(struct net_device *netdev, mlx5e_close_locked(priv->netdev); priv->params.lro_en = !!(features & NETIF_F_LRO); - mlx5e_modify_tir_lro(priv, MLX5E_TT_IPV4_TCP); - mlx5e_modify_tir_lro(priv, MLX5E_TT_IPV6_TCP); + err = mlx5e_modify_tirs_lro(priv); + if (err) + mlx5_core_warn(priv->mdev, "lro modify failed, %d\n", + err); if (was_opened) err = mlx5e_open_locked(priv->netdev); From 0ad9b20415a461332611666301e7812900a15ad4 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Mon, 29 Feb 2016 21:17:11 +0200 Subject: [PATCH 323/417] net/mlx5e: Fix soft lockup when HW Timestamping is enabled Readers/Writers lock for SW timecounter was acquired without disabling interrupts on local CPU. The problematic scenario: * HW timestamping is enabled * Timestamp overflow periodic service task is running on local CPU and holding write_lock for SW timecounter * Completion arrives, triggers interrupt for local CPU. Interrupt routine calls napi_schedule(), which triggers rx/tx skb process. An attempt to read SW timecounter using read_lock is done, which is already locked by a writer on the same CPU and cause soft lockup. Add irqsave/irqrestore for when using the readers/writers lock for writing. Fixes: ef9814deafd0 ('net/mlx5e: Add HW timestamping (TS) support') Signed-off-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- .../ethernet/mellanox/mlx5/core/en_clock.c | 25 +++++++++++-------- 1 file changed, 15 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c index be6543570b2b..2018eebe1531 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c @@ -62,10 +62,11 @@ static void mlx5e_timestamp_overflow(struct work_struct *work) struct delayed_work *dwork = to_delayed_work(work); struct mlx5e_tstamp *tstamp = container_of(dwork, struct mlx5e_tstamp, overflow_work); + unsigned long flags; - write_lock(&tstamp->lock); + write_lock_irqsave(&tstamp->lock, flags); timecounter_read(&tstamp->clock); - write_unlock(&tstamp->lock); + write_unlock_irqrestore(&tstamp->lock, flags); schedule_delayed_work(&tstamp->overflow_work, tstamp->overflow_period); } @@ -136,10 +137,11 @@ static int mlx5e_ptp_settime(struct ptp_clock_info *ptp, struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, ptp_info); u64 ns = timespec64_to_ns(ts); + unsigned long flags; - write_lock(&tstamp->lock); + write_lock_irqsave(&tstamp->lock, flags); timecounter_init(&tstamp->clock, &tstamp->cycles, ns); - write_unlock(&tstamp->lock); + write_unlock_irqrestore(&tstamp->lock, flags); return 0; } @@ -150,10 +152,11 @@ static int mlx5e_ptp_gettime(struct ptp_clock_info *ptp, struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, ptp_info); u64 ns; + unsigned long flags; - write_lock(&tstamp->lock); + write_lock_irqsave(&tstamp->lock, flags); ns = timecounter_read(&tstamp->clock); - write_unlock(&tstamp->lock); + write_unlock_irqrestore(&tstamp->lock, flags); *ts = ns_to_timespec64(ns); @@ -164,10 +167,11 @@ static int mlx5e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) { struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, ptp_info); + unsigned long flags; - write_lock(&tstamp->lock); + write_lock_irqsave(&tstamp->lock, flags); timecounter_adjtime(&tstamp->clock, delta); - write_unlock(&tstamp->lock); + write_unlock_irqrestore(&tstamp->lock, flags); return 0; } @@ -176,6 +180,7 @@ static int mlx5e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta) { u64 adj; u32 diff; + unsigned long flags; int neg_adj = 0; struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, ptp_info); @@ -189,11 +194,11 @@ static int mlx5e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta) adj *= delta; diff = div_u64(adj, 1000000000ULL); - write_lock(&tstamp->lock); + write_lock_irqsave(&tstamp->lock, flags); timecounter_read(&tstamp->clock); tstamp->cycles.mult = neg_adj ? tstamp->nominal_c_mult - diff : tstamp->nominal_c_mult + diff; - write_unlock(&tstamp->lock); + write_unlock_irqrestore(&tstamp->lock, flags); return 0; } From bdfc028de1b3cd59490d5413a5c87b0fa50040c2 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 29 Feb 2016 21:17:12 +0200 Subject: [PATCH 324/417] net/mlx5e: Fix ethtool RX hash func configuration change We should modify TIRs explicitly to apply the new RSS configuration. The light ndo close/open calls do not "refresh" them. Fixes: 2d75b2bc8a8c ('net/mlx5e: Add ethtool RSS configuration options') Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 3 ++ .../ethernet/mellanox/mlx5/core/en_ethtool.c | 34 +++++++++++++------ .../net/ethernet/mellanox/mlx5/core/en_main.c | 27 +++++++++------ include/linux/mlx5/mlx5_ifc.h | 4 ++- 4 files changed, 46 insertions(+), 22 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 614a6022db25..976bddbddb5d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -447,6 +447,8 @@ enum mlx5e_traffic_types { MLX5E_NUM_TT, }; +#define IS_HASHING_TT(tt) (tt != MLX5E_TT_ANY) + enum mlx5e_rqt_ix { MLX5E_INDIRECTION_RQT, MLX5E_SINGLE_RQ_RQT, @@ -613,6 +615,7 @@ void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv); void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv); int mlx5e_redirect_rqt(struct mlx5e_priv *priv, enum mlx5e_rqt_ix rqt_ix); +void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv); int mlx5e_open_locked(struct net_device *netdev); int mlx5e_close_locked(struct net_device *netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 65624ac65b4c..64af1b0dd3e7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -703,18 +703,36 @@ static int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, return 0; } +static void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen) +{ + struct mlx5_core_dev *mdev = priv->mdev; + void *tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx); + int i; + + MLX5_SET(modify_tir_in, in, bitmask.hash, 1); + mlx5e_build_tir_ctx_hash(tirc, priv); + + for (i = 0; i < MLX5E_NUM_TT; i++) + if (IS_HASHING_TT(i)) + mlx5_core_modify_tir(mdev, priv->tirn[i], in, inlen); +} + static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key, const u8 hfunc) { struct mlx5e_priv *priv = netdev_priv(dev); - bool close_open; - int err = 0; + int inlen = MLX5_ST_SZ_BYTES(modify_tir_in); + void *in; if ((hfunc != ETH_RSS_HASH_NO_CHANGE) && (hfunc != ETH_RSS_HASH_XOR) && (hfunc != ETH_RSS_HASH_TOP)) return -EINVAL; + in = mlx5_vzalloc(inlen); + if (!in) + return -ENOMEM; + mutex_lock(&priv->state_lock); if (indir) { @@ -723,11 +741,6 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, mlx5e_redirect_rqt(priv, MLX5E_INDIRECTION_RQT); } - close_open = (key || (hfunc != ETH_RSS_HASH_NO_CHANGE)) && - test_bit(MLX5E_STATE_OPENED, &priv->state); - if (close_open) - mlx5e_close_locked(dev); - if (key) memcpy(priv->params.toeplitz_hash_key, key, sizeof(priv->params.toeplitz_hash_key)); @@ -735,12 +748,13 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, if (hfunc != ETH_RSS_HASH_NO_CHANGE) priv->params.rss_hfunc = hfunc; - if (close_open) - err = mlx5e_open_locked(priv->netdev); + mlx5e_modify_tirs_hash(priv, in, inlen); mutex_unlock(&priv->state_lock); - return err; + kvfree(in); + + return 0; } static int mlx5e_get_rxnfc(struct net_device *netdev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 137b05e1c68a..34b10492569a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1317,6 +1317,21 @@ static void mlx5e_build_tir_ctx_lro(void *tirc, struct mlx5e_priv *priv) lro_timer_supported_periods[2])); } +void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv) +{ + MLX5_SET(tirc, tirc, rx_hash_fn, + mlx5e_rx_hash_fn(priv->params.rss_hfunc)); + if (priv->params.rss_hfunc == ETH_RSS_HASH_TOP) { + void *rss_key = MLX5_ADDR_OF(tirc, tirc, + rx_hash_toeplitz_key); + size_t len = MLX5_FLD_SZ_BYTES(tirc, + rx_hash_toeplitz_key); + + MLX5_SET(tirc, tirc, rx_hash_symmetric, 1); + memcpy(rss_key, priv->params.toeplitz_hash_key, len); + } +} + static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; @@ -1677,17 +1692,7 @@ static void mlx5e_build_tir_ctx(struct mlx5e_priv *priv, u32 *tirc, int tt) default: MLX5_SET(tirc, tirc, indirect_table, priv->rqtn[MLX5E_INDIRECTION_RQT]); - MLX5_SET(tirc, tirc, rx_hash_fn, - mlx5e_rx_hash_fn(priv->params.rss_hfunc)); - if (priv->params.rss_hfunc == ETH_RSS_HASH_TOP) { - void *rss_key = MLX5_ADDR_OF(tirc, tirc, - rx_hash_toeplitz_key); - size_t len = MLX5_FLD_SZ_BYTES(tirc, - rx_hash_toeplitz_key); - - MLX5_SET(tirc, tirc, rx_hash_symmetric, 1); - memcpy(rss_key, priv->params.toeplitz_hash_key, len); - } + mlx5e_build_tir_ctx_hash(tirc, priv); break; } diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 51f1e540fc2b..58eef02edc7e 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -4245,7 +4245,9 @@ struct mlx5_ifc_modify_tir_bitmask_bits { u8 reserved_at_20[0x1b]; u8 self_lb_en[0x1]; - u8 reserved_at_3c[0x3]; + u8 reserved_at_3c[0x1]; + u8 hash[0x1]; + u8 reserved_at_3e[0x1]; u8 lro[0x1]; }; From 85082dba0a5059c538cfa786d07f5ec5370d22fe Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 29 Feb 2016 21:17:13 +0200 Subject: [PATCH 325/417] net/mlx5e: Correctly handle RSS indirection table when changing number of channels Upon changing num_channels, reset the RSS indirection table to match the new value. Fixes: 2d75b2bc8a8c ('net/mlx5e: Add ethtool RSS configuration options') Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 ++ .../net/ethernet/mellanox/mlx5/core/en_ethtool.c | 2 ++ drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 15 +++++++++++---- 3 files changed, 15 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 976bddbddb5d..d0a57d53e125 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -619,6 +619,8 @@ void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv); int mlx5e_open_locked(struct net_device *netdev); int mlx5e_close_locked(struct net_device *netdev); +void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len, + int num_channels); static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq, struct mlx5e_tx_wqe *wqe, int bf_sz) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 64af1b0dd3e7..5abeb00fceb8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -385,6 +385,8 @@ static int mlx5e_set_channels(struct net_device *dev, mlx5e_close_locked(dev); priv->params.num_channels = count; + mlx5e_build_default_indir_rqt(priv->params.indirection_rqt, + MLX5E_INDIR_RQT_SIZE, count); if (was_opened) err = mlx5e_open_locked(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 34b10492569a..02689ca38ab6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1199,7 +1199,6 @@ static void mlx5e_fill_indir_rqt_rqns(struct mlx5e_priv *priv, void *rqtc) ix = mlx5e_bits_invert(i, MLX5E_LOG_INDIR_RQT_SIZE); ix = priv->params.indirection_rqt[ix]; - ix = ix % priv->params.num_channels; MLX5_SET(rqtc, rqtc, rq_num[i], test_bit(MLX5E_STATE_OPENED, &priv->state) ? priv->channel[ix]->rq.rqn : @@ -2101,12 +2100,20 @@ u16 mlx5e_get_max_inline_cap(struct mlx5_core_dev *mdev) 2 /*sizeof(mlx5e_tx_wqe.inline_hdr_start)*/; } +void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len, + int num_channels) +{ + int i; + + for (i = 0; i < len; i++) + indirection_rqt[i] = i % num_channels; +} + static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev, struct net_device *netdev, int num_channels) { struct mlx5e_priv *priv = netdev_priv(netdev); - int i; priv->params.log_sq_size = MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE; @@ -2130,8 +2137,8 @@ static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev, netdev_rss_key_fill(priv->params.toeplitz_hash_key, sizeof(priv->params.toeplitz_hash_key)); - for (i = 0; i < MLX5E_INDIR_RQT_SIZE; i++) - priv->params.indirection_rqt[i] = i % num_channels; + mlx5e_build_default_indir_rqt(priv->params.indirection_rqt, + MLX5E_INDIR_RQT_SIZE, num_channels); priv->params.lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ; From b081da5ee1860d1874381a413a1b71d8f9f67e83 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Mon, 29 Feb 2016 21:17:14 +0200 Subject: [PATCH 326/417] net/mlx5e: Add rx/tx bytes software counters Sum up rx/tx bytes in software as we do for rx/tx packets, to be reported in upcoming statistics fix. Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 8 ++++++-- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 9 ++++++--- 3 files changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index d0a57d53e125..5b1753233c5d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -223,6 +223,7 @@ struct mlx5e_pport_stats { static const char rq_stats_strings[][ETH_GSTRING_LEN] = { "packets", + "bytes", "csum_none", "csum_sw", "lro_packets", @@ -232,16 +233,18 @@ static const char rq_stats_strings[][ETH_GSTRING_LEN] = { struct mlx5e_rq_stats { u64 packets; + u64 bytes; u64 csum_none; u64 csum_sw; u64 lro_packets; u64 lro_bytes; u64 wqe_err; -#define NUM_RQ_STATS 6 +#define NUM_RQ_STATS 7 }; static const char sq_stats_strings[][ETH_GSTRING_LEN] = { "packets", + "bytes", "tso_packets", "tso_bytes", "csum_offload_none", @@ -253,6 +256,7 @@ static const char sq_stats_strings[][ETH_GSTRING_LEN] = { struct mlx5e_sq_stats { u64 packets; + u64 bytes; u64 tso_packets; u64 tso_bytes; u64 csum_offload_none; @@ -260,7 +264,7 @@ struct mlx5e_sq_stats { u64 wake; u64 dropped; u64 nop; -#define NUM_SQ_STATS 8 +#define NUM_SQ_STATS 9 }; struct mlx5e_stats { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 3fd6a583e88a..59658b9d05d1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -263,6 +263,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) mlx5e_build_rx_skb(cqe, rq, skb); rq->stats.packets++; + rq->stats.bytes += be32_to_cpu(cqe->byte_cnt); napi_gro_receive(cq->napi, skb); wq_ll_pop: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 2beea8cdb604..bb4eeeb007de 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -179,6 +179,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) unsigned int skb_len = skb->len; u8 opcode = MLX5_OPCODE_SEND; dma_addr_t dma_addr = 0; + unsigned int num_bytes; bool bf = false; u16 headlen; u16 ds_cnt; @@ -204,8 +205,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) opcode = MLX5_OPCODE_LSO; ihs = skb_transport_offset(skb) + tcp_hdrlen(skb); payload_len = skb->len - ihs; - wi->num_bytes = skb->len + - (skb_shinfo(skb)->gso_segs - 1) * ihs; + num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs; sq->stats.tso_packets++; sq->stats.tso_bytes += payload_len; } else { @@ -213,9 +213,11 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) !skb->xmit_more && !skb_shinfo(skb)->nr_frags; ihs = mlx5e_get_inline_hdr_size(sq, skb, bf); - wi->num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN); + num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN); } + wi->num_bytes = num_bytes; + if (skb_vlan_tag_present(skb)) { mlx5e_insert_vlan(eseg->inline_hdr_start, skb, ihs, &skb_data, &skb_len); @@ -307,6 +309,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) sq->bf_budget = bf ? sq->bf_budget - 1 : 0; sq->stats.packets++; + sq->stats.bytes += num_bytes; return NETDEV_TX_OK; dma_unmap_wqe_err: From faf4478bf8b7b5e6c94cb07a52a00e4d1cd647c6 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Mon, 29 Feb 2016 21:17:15 +0200 Subject: [PATCH 327/417] net/mlx5e: Provide correct packet/bytes statistics Using the HW VPort counters for traffic (rx/tx packets/bytes) statistics is wrong. This is because frames dropped due to steering or out of buffer will be counted as received. To fix that, we move to use the packet/bytes accounting done by the driver for what the netdev reports out. Fixes: f62b8bb8f2d3 ('net/mlx5: Extend mlx5_core to support [...]') Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlx5/core/en_main.c | 25 ++++++------------- 1 file changed, 8 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 02689ca38ab6..402994bf7e16 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -141,6 +141,10 @@ void mlx5e_update_stats(struct mlx5e_priv *priv) return; /* Collect firts the SW counters and then HW for consistency */ + s->rx_packets = 0; + s->rx_bytes = 0; + s->tx_packets = 0; + s->tx_bytes = 0; s->tso_packets = 0; s->tso_bytes = 0; s->tx_queue_stopped = 0; @@ -155,6 +159,8 @@ void mlx5e_update_stats(struct mlx5e_priv *priv) for (i = 0; i < priv->params.num_channels; i++) { rq_stats = &priv->channel[i]->rq.stats; + s->rx_packets += rq_stats->packets; + s->rx_bytes += rq_stats->bytes; s->lro_packets += rq_stats->lro_packets; s->lro_bytes += rq_stats->lro_bytes; s->rx_csum_none += rq_stats->csum_none; @@ -164,6 +170,8 @@ void mlx5e_update_stats(struct mlx5e_priv *priv) for (j = 0; j < priv->params.num_tc; j++) { sq_stats = &priv->channel[i]->sq[j].stats; + s->tx_packets += sq_stats->packets; + s->tx_bytes += sq_stats->bytes; s->tso_packets += sq_stats->tso_packets; s->tso_bytes += sq_stats->tso_bytes; s->tx_queue_stopped += sq_stats->stopped; @@ -225,23 +233,6 @@ void mlx5e_update_stats(struct mlx5e_priv *priv) s->tx_broadcast_bytes = MLX5_GET_CTR(out, transmitted_eth_broadcast.octets); - s->rx_packets = - s->rx_unicast_packets + - s->rx_multicast_packets + - s->rx_broadcast_packets; - s->rx_bytes = - s->rx_unicast_bytes + - s->rx_multicast_bytes + - s->rx_broadcast_bytes; - s->tx_packets = - s->tx_unicast_packets + - s->tx_multicast_packets + - s->tx_broadcast_packets; - s->tx_bytes = - s->tx_unicast_bytes + - s->tx_multicast_bytes + - s->tx_broadcast_bytes; - /* Update calculated offload counters */ s->tx_csum_offload = s->tx_packets - tx_offload_none; s->rx_csum_good = s->rx_packets - s->rx_csum_none - From 03a79f31ef5fb7a2298258432f3dc0f558f24d48 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Wed, 2 Mar 2016 17:47:44 +0200 Subject: [PATCH 328/417] net/mlx4_core: Fix lockdep warning in handling of mac/vlan tables In the mac and vlan register/unregister/replace functions, the driver locks the mac table mutex (or vlan table mutex) on both ports. We move to use mutex_lock_nested() to prevent warnings, such as the one below. [ 101.828445] ============================================= [ 101.834820] [ INFO: possible recursive locking detected ] [ 101.841199] 4.5.0-rc2+ #49 Not tainted [ 101.850251] --------------------------------------------- [ 101.856621] modprobe/3054 is trying to acquire lock: [ 101.862514] (&table->mutex#2){+.+.+.}, at: [] __mlx4_register_mac+0x87e/0xa90 [mlx4_core] [ 101.874598] [ 101.874598] but task is already holding lock: [ 101.881703] (&table->mutex#2){+.+.+.}, at: [] __mlx4_register_mac+0x860/0xa90 [mlx4_core] [ 101.893776] [ 101.893776] other info that might help us debug this: [ 101.901658] Possible unsafe locking scenario: [ 101.901658] [ 101.908859] CPU0 [ 101.911923] ---- [ 101.914985] lock(&table->mutex#2); [ 101.919595] lock(&table->mutex#2); [ 101.924199] [ 101.924199] * DEADLOCK * [ 101.924199] [ 101.931643] May be due to missing lock nesting notation Fixes: 5f61385d2ebc ('net/mlx4_core: Keep VLAN/MAC tables mirrored in multifunc HA mode') Signed-off-by: Jack Morgenstein Suggested-by: Doron Tsur Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/port.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index 787b7bb54d52..211c65087997 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -193,10 +193,10 @@ int __mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac) if (need_mf_bond) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); @@ -389,10 +389,10 @@ void __mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac) if (dup) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); @@ -479,10 +479,10 @@ int __mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac) if (dup) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); @@ -588,10 +588,10 @@ int __mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, if (need_mf_bond) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); @@ -764,10 +764,10 @@ void __mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan) if (dup) { if (port == 1) { mutex_lock(&table->mutex); - mutex_lock(&dup_table->mutex); + mutex_lock_nested(&dup_table->mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&dup_table->mutex); - mutex_lock(&table->mutex); + mutex_lock_nested(&table->mutex, SINGLE_DEPTH_NESTING); } } else { mutex_lock(&table->mutex); From 00ada91039fc03100cb4fab41d04f9b30f27340f Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Wed, 2 Mar 2016 17:47:45 +0200 Subject: [PATCH 329/417] net/mlx4_core: Check the correct limitation on VFs for HA mode The limit of 63 is only for virtual functions while the actual enforcement was for VFs plus physical functions, fix that. Fixes: e57968a10bc1 ('net/mlx4_core: Support the HA mode for SRIOV VFs too') Signed-off-by: Moni Shoua Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/main.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 2cc3c626c3fe..f8674ae62752 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -1256,6 +1256,7 @@ static ssize_t set_port_ib_mtu(struct device *dev, static int mlx4_mf_bond(struct mlx4_dev *dev) { int err = 0; + int nvfs; struct mlx4_slaves_pport slaves_port1; struct mlx4_slaves_pport slaves_port2; DECLARE_BITMAP(slaves_port_1_2, MLX4_MFUNC_MAX); @@ -1272,11 +1273,18 @@ static int mlx4_mf_bond(struct mlx4_dev *dev) return -EINVAL; } + /* number of virtual functions is number of total functions minus one + * physical function for each port. + */ + nvfs = bitmap_weight(slaves_port1.slaves, dev->persist->num_vfs + 1) + + bitmap_weight(slaves_port2.slaves, dev->persist->num_vfs + 1) - 2; + /* limit on maximum allowed VFs */ - if ((bitmap_weight(slaves_port1.slaves, dev->persist->num_vfs + 1) + - bitmap_weight(slaves_port2.slaves, dev->persist->num_vfs + 1)) > - MAX_MF_BOND_ALLOWED_SLAVES) + if (nvfs > MAX_MF_BOND_ALLOWED_SLAVES) { + mlx4_warn(dev, "HA mode is not supported for %d VFs (max %d are allowed)\n", + nvfs, MAX_MF_BOND_ALLOWED_SLAVES); return -EINVAL; + } if (dev->caps.steering_mode != MLX4_STEERING_MODE_DEVICE_MANAGED) { mlx4_warn(dev, "HA mode unsupported for NON DMFS steering\n"); From 6e5224224faa50ec4c8949dcefadf895e565f0d1 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Wed, 2 Mar 2016 17:47:46 +0200 Subject: [PATCH 330/417] net/mlx4_core: Allow resetting VF admin mac to zero The VF administrative mac addresses (stored in the PF driver) are initialized to zero when the PF driver starts up. These addresses may be modified in the PF driver through ndo calls initiated by iproute2 or libvirt. While we allow the PF/host to change the VF admin mac address from zero to a valid unicast mac, we do not allow restoring the VF admin mac to zero. We currently only allow changing this mac to a different unicast mac. This leads to problems when libvirt scripts are used to deal with VF mac addresses, and libvirt attempts to revoke the mac so this host will not use it anymore. Fix this by allowing resetting a VF administrative MAC back to zero. Fixes: 8f7ba3ca12f6 ('net/mlx4: Add set VF mac address support') Signed-off-by: Jack Morgenstein Reported-by: Moshe Levi Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index f191a1612589..21e2c0960271 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2245,7 +2245,7 @@ static int mlx4_en_set_vf_mac(struct net_device *dev, int queue, u8 *mac) struct mlx4_en_dev *mdev = en_priv->mdev; u64 mac_u64 = mlx4_mac_to_u64(mac); - if (!is_valid_ether_addr(mac)) + if (is_multicast_ether_addr(mac)) return -EINVAL; return mlx4_set_vf_mac(mdev->dev, en_priv->port, queue, mac_u64); From 8afb6c474b0dd8f9cf7e122a19c71924566fdb97 Mon Sep 17 00:00:00 2001 From: Rabin Vincent Date: Mon, 29 Feb 2016 16:22:30 +0100 Subject: [PATCH 331/417] dwc_eth_qos: fix race condition in dwceqos_start_xmit The xmit handler and the tx_reclaim tasklet had a race on the tx_free variable which could lead to a tx timeout if tx_free was updated after the tx complete interrupt. Signed-off-by: Rabin Vincent Signed-off-by: Lars Persson Signed-off-by: David S. Miller --- drivers/net/ethernet/synopsys/dwc_eth_qos.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c index fc8bbff2d7e3..926db2d58fb5 100644 --- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c +++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c @@ -2178,12 +2178,10 @@ static int dwceqos_start_xmit(struct sk_buff *skb, struct net_device *ndev) ((trans.initial_descriptor + trans.nr_descriptors) % DWCEQOS_TX_DCNT)); - dwceqos_tx_finalize(skb, lp, &trans); - - netdev_sent_queue(ndev, skb->len); - spin_lock_bh(&lp->tx_lock); lp->tx_free -= trans.nr_descriptors; + dwceqos_tx_finalize(skb, lp, &trans); + netdev_sent_queue(ndev, skb->len); spin_unlock_bh(&lp->tx_lock); ndev->trans_start = jiffies; From d4dc35f26e1017e2a632339ecae43706cbc06986 Mon Sep 17 00:00:00 2001 From: Lars Persson Date: Mon, 29 Feb 2016 16:22:31 +0100 Subject: [PATCH 332/417] dwc_eth_qos: release descriptors outside netif_tx_lock To prepare for using the CMA, we can not be in atomic context when de-allocating DMA buffers. The tx lock was needed only to protect the hw reset against the xmit handler. Now we briefly grab the tx lock while stopping the queue to make sure no thread is inside or will enter the xmit handler. Signed-off-by: Lars Persson Signed-off-by: David S. Miller --- drivers/net/ethernet/synopsys/dwc_eth_qos.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c index 926db2d58fb5..53d48c0f41bc 100644 --- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c +++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c @@ -1918,15 +1918,17 @@ static int dwceqos_stop(struct net_device *ndev) phy_stop(lp->phy_dev); tasklet_disable(&lp->tx_bdreclaim_tasklet); - netif_stop_queue(ndev); napi_disable(&lp->napi); - dwceqos_drain_dma(lp); + /* Stop all tx before we drain the tx dma. */ + netif_tx_lock_bh(lp->ndev); + netif_stop_queue(ndev); + netif_tx_unlock_bh(lp->ndev); - netif_tx_lock(lp->ndev); + dwceqos_drain_dma(lp); dwceqos_reset_hw(lp); + dwceqos_descriptor_free(lp); - netif_tx_unlock(lp->ndev); return 0; } From e8b0c32eae319e287d0329b4148c9a1a51525053 Mon Sep 17 00:00:00 2001 From: Rabin Vincent Date: Mon, 29 Feb 2016 16:22:32 +0100 Subject: [PATCH 333/417] dwc_eth_qos: use GFP_KERNEL in dma_alloc_coherent() Since we are in non-atomic context here we can pass GFP_KERNEL to dma_alloc_coherent(). This enables use of the CMA. Signed-off-by: Rabin Vincent Signed-off-by: Lars Persson Signed-off-by: David S. Miller --- drivers/net/ethernet/synopsys/dwc_eth_qos.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c index 53d48c0f41bc..3ca2d5c9707a 100644 --- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c +++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c @@ -1113,7 +1113,7 @@ static int dwceqos_descriptor_init(struct net_local *lp) /* Allocate DMA descriptors */ size = DWCEQOS_RX_DCNT * sizeof(struct dwceqos_dma_desc); lp->rx_descs = dma_alloc_coherent(lp->ndev->dev.parent, size, - &lp->rx_descs_addr, 0); + &lp->rx_descs_addr, GFP_KERNEL); if (!lp->rx_descs) goto err_out; lp->rx_descs_tail_addr = lp->rx_descs_addr + @@ -1121,7 +1121,7 @@ static int dwceqos_descriptor_init(struct net_local *lp) size = DWCEQOS_TX_DCNT * sizeof(struct dwceqos_dma_desc); lp->tx_descs = dma_alloc_coherent(lp->ndev->dev.parent, size, - &lp->tx_descs_addr, 0); + &lp->tx_descs_addr, GFP_KERNEL); if (!lp->tx_descs) goto err_out; lp->tx_descs_tail_addr = lp->tx_descs_addr + From 016a91c64de6621e5917b2ddfe2afc0abb0a884c Mon Sep 17 00:00:00 2001 From: Rabin Vincent Date: Mon, 29 Feb 2016 16:22:33 +0100 Subject: [PATCH 334/417] dwc_eth_qos: use DWCEQOS_MSG_DEFAULT Since debug is hardcoded to 3, the defaults in the DWCEQOS_MSG_DEFAULT macro are never used, which does not seem to be the intended behaviour here. Set debug to -1 like other drivers so that DWCEQOS_MSG_DEFAULT is actually used by default. Signed-off-by: Rabin Vincent Signed-off-by: Lars Persson Signed-off-by: David S. Miller --- drivers/net/ethernet/synopsys/dwc_eth_qos.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c index 3ca2d5c9707a..6897c1d0f86e 100644 --- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c +++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c @@ -426,7 +426,7 @@ #define DWC_MMC_RXOCTETCOUNT_GB 0x0784 #define DWC_MMC_RXPACKETCOUNT_GB 0x0780 -static int debug = 3; +static int debug = -1; module_param(debug, int, 0); MODULE_PARM_DESC(debug, "DWC_eth_qos debug level (0=none,...,16=all)"); From cd5e41234729966153595fd3c2a7912cc4f95bc2 Mon Sep 17 00:00:00 2001 From: Lars Persson Date: Mon, 29 Feb 2016 16:22:34 +0100 Subject: [PATCH 335/417] dwc_eth_qos: do phy_start before resetting hardware This reverts the changed init order from commit 3647bc35bd42 ("dwc_eth_qos: Reset hardware before PHY start") and makes another fix for the race. It turned out that the reset state machine of the dwceqos hardware requires PHY clocks to be present in order to complete the reset cycle. To plug the race with the phy state machine we defer link speed setting until the hardware init has finished. Signed-off-by: Lars Persson Signed-off-by: David S. Miller --- drivers/net/ethernet/synopsys/dwc_eth_qos.c | 23 ++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c index 6897c1d0f86e..af11ed1e0bcc 100644 --- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c +++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c @@ -650,6 +650,11 @@ struct net_local { u32 mmc_tx_counters_mask; struct dwceqos_flowcontrol flowcontrol; + + /* Tracks the intermediate state of phy started but hardware + * init not finished yet. + */ + bool phy_defer; }; static void dwceqos_read_mmc_counters(struct net_local *lp, u32 rx_mask, @@ -901,6 +906,9 @@ static void dwceqos_adjust_link(struct net_device *ndev) struct phy_device *phydev = lp->phy_dev; int status_change = 0; + if (lp->phy_defer) + return; + if (phydev->link) { if ((lp->speed != phydev->speed) || (lp->duplex != phydev->duplex)) { @@ -1635,6 +1643,12 @@ static void dwceqos_init_hw(struct net_local *lp) regval = dwceqos_read(lp, REG_DWCEQOS_MAC_CFG); dwceqos_write(lp, REG_DWCEQOS_MAC_CFG, regval | DWCEQOS_MAC_CFG_TE | DWCEQOS_MAC_CFG_RE); + + lp->phy_defer = false; + mutex_lock(&lp->phy_dev->lock); + phy_read_status(lp->phy_dev); + dwceqos_adjust_link(lp->ndev); + mutex_unlock(&lp->phy_dev->lock); } static void dwceqos_tx_reclaim(unsigned long data) @@ -1880,9 +1894,13 @@ static int dwceqos_open(struct net_device *ndev) } netdev_reset_queue(ndev); + /* The dwceqos reset state machine requires all phy clocks to complete, + * hence the unusual init order with phy_start first. + */ + lp->phy_defer = true; + phy_start(lp->phy_dev); dwceqos_init_hw(lp); napi_enable(&lp->napi); - phy_start(lp->phy_dev); netif_start_queue(ndev); tasklet_enable(&lp->tx_bdreclaim_tasklet); @@ -1915,8 +1933,6 @@ static int dwceqos_stop(struct net_device *ndev) { struct net_local *lp = netdev_priv(ndev); - phy_stop(lp->phy_dev); - tasklet_disable(&lp->tx_bdreclaim_tasklet); napi_disable(&lp->napi); @@ -1927,6 +1943,7 @@ static int dwceqos_stop(struct net_device *ndev) dwceqos_drain_dma(lp); dwceqos_reset_hw(lp); + phy_stop(lp->phy_dev); dwceqos_descriptor_free(lp); From 92f9e179a702a6adbc11e2fedc76ecd6ffc9e3f7 Mon Sep 17 00:00:00 2001 From: Todd E Brandt Date: Wed, 2 Mar 2016 16:05:29 -0800 Subject: [PATCH 336/417] PM / sleep / x86: Fix crash on graph trace through x86 suspend Pause/unpause graph tracing around do_suspend_lowlevel as it has inconsistent call/return info after it jumps to the wakeup vector. The graph trace buffer will otherwise become misaligned and may eventually crash and hang on suspend. To reproduce the issue and test the fix: Run a function_graph trace over suspend/resume and set the graph function to suspend_devices_and_enter. This consistently hangs the system without this fix. Signed-off-by: Todd Brandt Cc: All applicable Signed-off-by: Rafael J. Wysocki --- arch/x86/kernel/acpi/sleep.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index d1daead5fcdd..adb3eaf8fe2a 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -16,6 +16,7 @@ #include #include +#include #include "../../realmode/rm/wakeup.h" #include "sleep.h" @@ -107,7 +108,13 @@ int x86_acpi_suspend_lowlevel(void) saved_magic = 0x123456789abcdef0L; #endif /* CONFIG_64BIT */ + /* + * Pause/unpause graph tracing around do_suspend_lowlevel as it has + * inconsistent call/return info after it jumps to the wakeup vector. + */ + pause_graph_tracing(); do_suspend_lowlevel(); + unpause_graph_tracing(); return 0; } From 58402b6e98f9059420e64b296db6c4cb6f6c1117 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Mon, 29 Feb 2016 09:02:47 +0100 Subject: [PATCH 337/417] [media] media.h: use hex values for range offsets, move connectors base up. Make the base offset hexadecimal to simplify debugging since the base addresses are hex too. The offsets for connectors is also changed to start after the 'reserved' range 0x10000-0x2ffff. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/media.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index f0328524be6e..13e19a18f97f 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -66,25 +66,25 @@ struct media_device_info { /* * DVB entities */ -#define MEDIA_ENT_F_DTV_DEMOD (MEDIA_ENT_F_BASE + 1) -#define MEDIA_ENT_F_TS_DEMUX (MEDIA_ENT_F_BASE + 2) -#define MEDIA_ENT_F_DTV_CA (MEDIA_ENT_F_BASE + 3) -#define MEDIA_ENT_F_DTV_NET_DECAP (MEDIA_ENT_F_BASE + 4) +#define MEDIA_ENT_F_DTV_DEMOD (MEDIA_ENT_F_BASE + 0x00001) +#define MEDIA_ENT_F_TS_DEMUX (MEDIA_ENT_F_BASE + 0x00002) +#define MEDIA_ENT_F_DTV_CA (MEDIA_ENT_F_BASE + 0x00003) +#define MEDIA_ENT_F_DTV_NET_DECAP (MEDIA_ENT_F_BASE + 0x00004) /* * I/O entities */ -#define MEDIA_ENT_F_IO_DTV (MEDIA_ENT_F_BASE + 1001) -#define MEDIA_ENT_F_IO_VBI (MEDIA_ENT_F_BASE + 1002) -#define MEDIA_ENT_F_IO_SWRADIO (MEDIA_ENT_F_BASE + 1003) +#define MEDIA_ENT_F_IO_DTV (MEDIA_ENT_F_BASE + 0x01001) +#define MEDIA_ENT_F_IO_VBI (MEDIA_ENT_F_BASE + 0x01002) +#define MEDIA_ENT_F_IO_SWRADIO (MEDIA_ENT_F_BASE + 0x01003) /* * Connectors */ /* It is a responsibility of the entity drivers to add connectors and links */ -#define MEDIA_ENT_F_CONN_RF (MEDIA_ENT_F_BASE + 10001) -#define MEDIA_ENT_F_CONN_SVIDEO (MEDIA_ENT_F_BASE + 10002) -#define MEDIA_ENT_F_CONN_COMPOSITE (MEDIA_ENT_F_BASE + 10003) +#define MEDIA_ENT_F_CONN_RF (MEDIA_ENT_F_BASE + 0x30001) +#define MEDIA_ENT_F_CONN_SVIDEO (MEDIA_ENT_F_BASE + 0x30002) +#define MEDIA_ENT_F_CONN_COMPOSITE (MEDIA_ENT_F_BASE + 0x30003) /* * Don't touch on those. The ranges MEDIA_ENT_F_OLD_BASE and From 02322ac9dee9aff8d8862e8d6660ebe102f492ea Mon Sep 17 00:00:00 2001 From: Simon South Date: Wed, 2 Mar 2016 23:10:44 -0500 Subject: [PATCH 338/417] ALSA: hda - Fix mic issues on Acer Aspire E1-472 This patch applies the microphone-related fix created for the Acer Aspire E1-572 to the E1-472 as well, as it uses the same Realtek ALC282 CODEC and demonstrates the same issues. This patch allows an external, headset microphone to be used and limits the gain on the (quite noisy) internal microphone. Signed-off-by: Simon South Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 1f357cd72d9c..93d2156b6241 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5412,6 +5412,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x080d, "Acer Aspire V5-122P", ALC269_FIXUP_ASPIRE_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x0740, "Acer AO725", ALC271_FIXUP_HP_GATE_MIC_JACK), SND_PCI_QUIRK(0x1025, 0x0742, "Acer AO756", ALC271_FIXUP_HP_GATE_MIC_JACK), + SND_PCI_QUIRK(0x1025, 0x0762, "Acer Aspire E1-472", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572), SND_PCI_QUIRK(0x1025, 0x0775, "Acer Aspire E1-572", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572), SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS), SND_PCI_QUIRK(0x1025, 0x106d, "Acer Cloudbook 14", ALC283_FIXUP_CHROME_BOOK), From fb822e6076d972691c5dd33431c10f82dda94ae9 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Wed, 2 Mar 2016 15:25:17 +0530 Subject: [PATCH 339/417] powerpc/hw_breakpoint: Fix oops when destroying hw_breakpoint event When destroying a hw_breakpoint event, the kernel oopses as follows: Unable to handle kernel paging request for data at address 0x00000c07 NIP [c0000000000291d0] arch_unregister_hw_breakpoint+0x40/0x60 LR [c00000000020b6b4] release_bp_slot+0x44/0x80 Call chain: hw_breakpoint_event_init() bp->destroy = bp_perf_event_destroy; do_exit() perf_event_exit_task() perf_event_exit_task_context() WRITE_ONCE(child_ctx->task, TASK_TOMBSTONE); perf_event_exit_event() free_event() _free_event() bp_perf_event_destroy() // event->destroy(event); release_bp_slot() arch_unregister_hw_breakpoint() perf_event_exit_task_context() sets child_ctx->task as TASK_TOMBSTONE which is (void *)-1. arch_unregister_hw_breakpoint() tries to fetch 'thread' attribute of 'task' resulting in oops. Peterz points out that the code shouldn't be using bp->ctx anyway, but fixing that will require a decent amount of rework. So for now to fix the oops, check if bp->ctx->task has been set to (void *)-1, before dereferencing it. We don't use TASK_TOMBSTONE, because that would require exporting it and it's supposed to be an internal detail. Fixes: 63b6da39bb38 ("perf: Fix perf_event_exit_task() race") Signed-off-by: Ravi Bangoria Acked-by: Peter Zijlstra (Intel) Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/hw_breakpoint.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 05e804cdecaa..aec9a1b1d25b 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -109,8 +109,9 @@ void arch_unregister_hw_breakpoint(struct perf_event *bp) * If the breakpoint is unregistered between a hw_breakpoint_handler() * and the single_step_dabr_instruction(), then cleanup the breakpoint * restoration variables to prevent dangling pointers. + * FIXME, this should not be using bp->ctx at all! Sayeth peterz. */ - if (bp->ctx && bp->ctx->task) + if (bp->ctx && bp->ctx->task && bp->ctx->task != ((void *)-1L)) bp->ctx->task->thread.last_hit_ubp = NULL; } From 85d9691ccc96d95629939a877fd6c1f8c4724f56 Mon Sep 17 00:00:00 2001 From: Majd Dibbiny Date: Sun, 14 Feb 2016 18:35:51 +0200 Subject: [PATCH 340/417] IB/mlx5: Avoid using user-index for SRQs Normal SRQs, unlike XRC SRQs, don't have user-index, therefore avoid verifying it and using it. Fixes: cfb5e088e26a ('IB/mlx5: Add CQE version 1 support to user QPs and SRQs') Signed-off-by: Majd Dibbiny Reviewed-by: Matan Barak Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/srq.c | 30 +++++++++++++++++++----------- 1 file changed, 19 insertions(+), 11 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c index 4659256cd95e..a1b7122c2ad6 100644 --- a/drivers/infiniband/hw/mlx5/srq.c +++ b/drivers/infiniband/hw/mlx5/srq.c @@ -75,7 +75,8 @@ static void mlx5_ib_srq_event(struct mlx5_core_srq *srq, enum mlx5_event type) static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq, struct mlx5_create_srq_mbox_in **in, - struct ib_udata *udata, int buf_size, int *inlen) + struct ib_udata *udata, int buf_size, int *inlen, + int is_xrc) { struct mlx5_ib_dev *dev = to_mdev(pd->device); struct mlx5_ib_create_srq ucmd = {}; @@ -108,10 +109,12 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq, drv_data - sizeof(ucmd))) return -EINVAL; - err = get_srq_user_index(to_mucontext(pd->uobject->context), - &ucmd, udata->inlen, &uidx); - if (err) - return err; + if (is_xrc) { + err = get_srq_user_index(to_mucontext(pd->uobject->context), + &ucmd, udata->inlen, &uidx); + if (err) + return err; + } srq->wq_sig = !!(ucmd.flags & MLX5_SRQ_FLAG_SIGNATURE); @@ -151,7 +154,8 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq, (*in)->ctx.log_pg_sz = page_shift - MLX5_ADAPTER_PAGE_SHIFT; (*in)->ctx.pgoff_cqn = cpu_to_be32(offset << 26); - if (MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1) { + if ((MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1) && + is_xrc){ xsrqc = MLX5_ADDR_OF(create_xrc_srq_in, *in, xrc_srq_context_entry); MLX5_SET(xrc_srqc, xsrqc, user_index, uidx); @@ -170,7 +174,7 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq, static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq, struct mlx5_create_srq_mbox_in **in, int buf_size, - int *inlen) + int *inlen, int is_xrc) { int err; int i; @@ -224,7 +228,8 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq, (*in)->ctx.log_pg_sz = page_shift - MLX5_ADAPTER_PAGE_SHIFT; - if (MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1) { + if ((MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1) && + is_xrc){ xsrqc = MLX5_ADDR_OF(create_xrc_srq_in, *in, xrc_srq_context_entry); /* 0xffffff means we ask to work with cqe version 0 */ @@ -302,10 +307,14 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd, desc_size, init_attr->attr.max_wr, srq->msrq.max, srq->msrq.max_gs, srq->msrq.max_avail_gather); + is_xrc = (init_attr->srq_type == IB_SRQT_XRC); + if (pd->uobject) - err = create_srq_user(pd, srq, &in, udata, buf_size, &inlen); + err = create_srq_user(pd, srq, &in, udata, buf_size, &inlen, + is_xrc); else - err = create_srq_kernel(dev, srq, &in, buf_size, &inlen); + err = create_srq_kernel(dev, srq, &in, buf_size, &inlen, + is_xrc); if (err) { mlx5_ib_warn(dev, "create srq %s failed, err %d\n", @@ -313,7 +322,6 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd, goto err_srq; } - is_xrc = (init_attr->srq_type == IB_SRQT_XRC); in->ctx.state_log_sz = ilog2(srq->msrq.max); flgs = ((srq->msrq.wqe_shift - 4) | (is_xrc << 5) | (srq->wq_sig << 7)) << 24; xrcdn = 0; From 3d943c9d1cc5ad1825e46291ef5ce627e1b6b660 Mon Sep 17 00:00:00 2001 From: Majd Dibbiny Date: Sun, 14 Feb 2016 18:35:52 +0200 Subject: [PATCH 341/417] IB/{core, mlx5}: Fix input len in vendor part of create_qp/srq Currently, the inlen field of the vendor's part of the command doesn't match the command buffer. This happens because the inlen accommodates ib_uverbs_cmd_hdr which is deducted from the in buffer. This is problematic since the vendor function could be called either from the legacy verb (where the input length mismatches the actual length) or by the extended verb (where the length matches). The vendor has no idea which function calls it and therefore has no way to know how the length variable should be treated. Fixing this by aligning the inlen to the correct length. All vendor drivers either assumed that inlen >= sizeof(vendor_uhw_cmd) or just failed wrongly (mlx5) and fixed in this patch. Fixes: cfb5e088e26a ('IB/mlx5: Add CQE version 1 support to user QPs and SRQs') Signed-off-by: Majd Dibbiny Reviewed-by: Matan Barak Reviewed-by: Haggai Eran Signed-off-by: Doug Ledford --- drivers/infiniband/core/uverbs_cmd.c | 9 ++++++--- drivers/infiniband/hw/mlx5/srq.c | 11 +++-------- 2 files changed, 9 insertions(+), 11 deletions(-) diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 6ffc9c4e93af..6c6fbff19752 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -1970,7 +1970,8 @@ ssize_t ib_uverbs_create_qp(struct ib_uverbs_file *file, resp_size); INIT_UDATA(&uhw, buf + sizeof(cmd), (unsigned long)cmd.response + resp_size, - in_len - sizeof(cmd), out_len - resp_size); + in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr), + out_len - resp_size); memset(&cmd_ex, 0, sizeof(cmd_ex)); cmd_ex.user_handle = cmd.user_handle; @@ -3413,7 +3414,8 @@ ssize_t ib_uverbs_create_srq(struct ib_uverbs_file *file, INIT_UDATA(&udata, buf + sizeof cmd, (unsigned long) cmd.response + sizeof resp, - in_len - sizeof cmd, out_len - sizeof resp); + in_len - sizeof cmd - sizeof(struct ib_uverbs_cmd_hdr), + out_len - sizeof resp); ret = __uverbs_create_xsrq(file, ib_dev, &xcmd, &udata); if (ret) @@ -3439,7 +3441,8 @@ ssize_t ib_uverbs_create_xsrq(struct ib_uverbs_file *file, INIT_UDATA(&udata, buf + sizeof cmd, (unsigned long) cmd.response + sizeof resp, - in_len - sizeof cmd, out_len - sizeof resp); + in_len - sizeof cmd - sizeof(struct ib_uverbs_cmd_hdr), + out_len - sizeof resp); ret = __uverbs_create_xsrq(file, ib_dev, &cmd, &udata); if (ret) diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c index a1b7122c2ad6..3b2ddd64a371 100644 --- a/drivers/infiniband/hw/mlx5/srq.c +++ b/drivers/infiniband/hw/mlx5/srq.c @@ -88,13 +88,8 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq, int ncont; u32 offset; u32 uidx = MLX5_IB_DEFAULT_UIDX; - int drv_data = udata->inlen - sizeof(struct ib_uverbs_cmd_hdr); - if (drv_data < 0) - return -EINVAL; - - ucmdlen = (drv_data < sizeof(ucmd)) ? - drv_data : sizeof(ucmd); + ucmdlen = min(udata->inlen, sizeof(ucmd)); if (ib_copy_from_udata(&ucmd, udata, ucmdlen)) { mlx5_ib_dbg(dev, "failed copy udata\n"); @@ -104,9 +99,9 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq, if (ucmd.reserved0 || ucmd.reserved1) return -EINVAL; - if (drv_data > sizeof(ucmd) && + if (udata->inlen > sizeof(ucmd) && !ib_is_udata_cleared(udata, sizeof(ucmd), - drv_data - sizeof(ucmd))) + udata->inlen - sizeof(ucmd))) return -EINVAL; if (is_xrc) { From f16921275cc3c2442d0b95225785a601603b990f Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Tue, 16 Feb 2016 22:54:02 +0100 Subject: [PATCH 342/417] dmaengine: pxa_dma: fix cyclic transfers While testing audio with pxa2xx-ac97, underrun were happening while the user application was correctly feeding the music. Debug proved that the cyclic transfer is not cyclic, ie. the last descriptor did not loop on the first. Another issue is that the descriptor length was always set to 8192, because of an trivial operator issue. This was tested on a pxa27x platform. Fixes: a57e16cf0333 ("dmaengine: pxa: add pxa dmaengine driver") Reported-by: Vasily Khoruzhick Tested-by: Vasily Khoruzhick Signed-off-by: Robert Jarzmik Signed-off-by: Vinod Koul --- drivers/dma/pxa_dma.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c index f2a0310ae771..debca824bed6 100644 --- a/drivers/dma/pxa_dma.c +++ b/drivers/dma/pxa_dma.c @@ -583,6 +583,8 @@ static void set_updater_desc(struct pxad_desc_sw *sw_desc, (PXA_DCMD_LENGTH & sizeof(u32)); if (flags & DMA_PREP_INTERRUPT) updater->dcmd |= PXA_DCMD_ENDIRQEN; + if (sw_desc->cyclic) + sw_desc->hw_desc[sw_desc->nb_desc - 2]->ddadr = sw_desc->first; } static bool is_desc_completed(struct virt_dma_desc *vd) @@ -673,6 +675,10 @@ static irqreturn_t pxad_chan_handler(int irq, void *dev_id) dev_dbg(&chan->vc.chan.dev->device, "%s(): checking txd %p[%x]: completed=%d\n", __func__, vd, vd->tx.cookie, is_desc_completed(vd)); + if (to_pxad_sw_desc(vd)->cyclic) { + vchan_cyclic_callback(vd); + break; + } if (is_desc_completed(vd)) { list_del(&vd->node); vchan_cookie_complete(vd); @@ -1080,7 +1086,7 @@ pxad_prep_dma_cyclic(struct dma_chan *dchan, return NULL; pxad_get_config(chan, dir, &dcmd, &dsadr, &dtadr); - dcmd |= PXA_DCMD_ENDIRQEN | (PXA_DCMD_LENGTH | period_len); + dcmd |= PXA_DCMD_ENDIRQEN | (PXA_DCMD_LENGTH & period_len); dev_dbg(&chan->vc.chan.dev->device, "%s(): buf_addr=0x%lx len=%zu period=%zu dir=%d flags=%lx\n", __func__, (unsigned long)buf_addr, len, period_len, dir, flags); From 11d8d645343efba0c975aefe7c2cf3b33c836c75 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Tue, 1 Mar 2016 18:52:23 +0200 Subject: [PATCH 343/417] IB/core: Use GRH when the path hop-limit > 0 According to IBTA spec v1.3 section 12.7.19, QPs should use GRH when the path returned by the SA has hop-limit > 0. Currently, we do that only for the > 1 case, fix that. Fixes: 6d969a471ba1 ('IB/sa: Add ib_init_ah_from_path()') Signed-off-by: Or Gerlitz Reviewed-by: Jason Gunthorpe Signed-off-by: Doug Ledford --- drivers/infiniband/core/sa_query.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c index f334090bb612..1e37f3515d98 100644 --- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -1071,7 +1071,7 @@ int ib_init_ah_from_path(struct ib_device *device, u8 port_num, } } - if (rec->hop_limit > 1 || use_roce) { + if (rec->hop_limit > 0 || use_roce) { ah_attr->ah_flags = IB_AH_GRH; ah_attr->grh.dgid = rec->dgid; From b5891cfab08fe3144a616e8e734df7749fb3b7d0 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Sun, 31 Jan 2016 16:22:16 +0300 Subject: [PATCH 344/417] ovl: fix working on distributed fs as lower layer This adds missing .d_select_inode into alternative dentry_operations. Signed-off-by: Konstantin Khlebnikov Fixes: 7c03b5d45b8e ("ovl: allow distributed fs as lower layer") Fixes: 4bacc9c9234c ("overlayfs: Make f_path always point to the overlay and f_inode to the underlay") Reviewed-by: Nikolay Borisov Tested-by: Nikolay Borisov Signed-off-by: Miklos Szeredi Cc: # 4.2+ --- fs/overlayfs/super.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 8d826bd56b26..588a4b51ab0c 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -341,6 +341,7 @@ static const struct dentry_operations ovl_dentry_operations = { static const struct dentry_operations ovl_reval_dentry_operations = { .d_release = ovl_dentry_release, + .d_select_inode = ovl_d_select_inode, .d_revalidate = ovl_dentry_revalidate, .d_weak_revalidate = ovl_dentry_weak_revalidate, }; From ce9113bbcbf45a57c082d6603b9a9f342be3ef74 Mon Sep 17 00:00:00 2001 From: Rui Wang Date: Fri, 8 Jan 2016 23:09:59 +0800 Subject: [PATCH 345/417] ovl: fix getcwd() failure after unsuccessful rmdir ovl_remove_upper() should do d_drop() only after it successfully removes the dir, otherwise a subsequent getcwd() system call will fail, breaking userspace programs. This is to fix: https://bugzilla.kernel.org/show_bug.cgi?id=110491 Signed-off-by: Rui Wang Reviewed-by: Konstantin Khlebnikov Signed-off-by: Miklos Szeredi Cc: --- fs/overlayfs/dir.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index ed95272d57a6..795ab65ccdf5 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -618,7 +618,8 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir) * sole user of this dentry. Too tricky... Just unhash for * now. */ - d_drop(dentry); + if (!err) + d_drop(dentry); inode_unlock(dir); return err; From 45d11738969633ec07ca35d75d486bf2d8918df6 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Sun, 31 Jan 2016 16:17:53 +0300 Subject: [PATCH 346/417] ovl: ignore lower entries when checking purity of non-directory entries After rename file dentry still holds reference to lower dentry from previous location. This doesn't matter for data access because data comes from upper dentry. But this stale lower dentry taints dentry at new location and turns it into non-pure upper. Such file leaves visible whiteout entry after remove in directory which shouldn't have whiteouts at all. Overlayfs already tracks pureness of file location in oe->opaque. This patch just uses that for detecting actual path type. Comment from Vivek Goyal's patch: Here are the details of the problem. Do following. $ mkdir upper lower work merged upper/dir/ $ touch lower/test $ sudo mount -t overlay overlay -olowerdir=lower,upperdir=upper,workdir= work merged $ mv merged/test merged/dir/ $ rm merged/dir/test $ ls -l merged/dir/ /usr/bin/ls: cannot access merged/dir/test: No such file or directory total 0 c????????? ? ? ? ? ? test Basic problem seems to be that once a file has been unlinked, a whiteout has been left behind which was not needed and hence it becomes visible. Whiteout is visible because parent dir is of not type MERGE, hence od->is_real is set during ovl_dir_open(). And that means ovl_iterate() passes on iterate handling directly to underlying fs. Underlying fs does not know/filter whiteouts so it becomes visible to user. Why did we leave a whiteout to begin with when we should not have. ovl_do_remove() checks for OVL_TYPE_PURE_UPPER() and does not leave whiteout if file is pure upper. In this case file is not found to be pure upper hence whiteout is left. So why file was not PURE_UPPER in this case? I think because dentry is still carrying some leftover state which was valid before rename. For example, od->numlower was set to 1 as it was a lower file. After rename, this state is not valid anymore as there is no such file in lower. Signed-off-by: Konstantin Khlebnikov Reported-by: Viktor Stanchev Suggested-by: Vivek Goyal Link: https://bugzilla.kernel.org/show_bug.cgi?id=109611 Acked-by: Vivek Goyal Signed-off-by: Miklos Szeredi Cc: --- fs/overlayfs/dir.c | 7 +++++++ fs/overlayfs/super.c | 12 +++++++----- 2 files changed, 14 insertions(+), 5 deletions(-) diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 795ab65ccdf5..52f6de5d40a9 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -904,6 +904,13 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old, if (!overwrite && new_is_dir && !old_opaque && new_opaque) ovl_remove_opaque(newdentry); + /* + * Old dentry now lives in different location. Dentries in + * lowerstack are stale. We cannot drop them here because + * access to them is lockless. This could be only pure upper + * or opaque directory - numlower is zero. Or upper non-dir + * entry - its pureness is tracked by flag opaque. + */ if (old_opaque != new_opaque) { ovl_dentry_set_opaque(old, new_opaque); if (!overwrite) diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 588a4b51ab0c..619ad4b016d2 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -76,12 +76,14 @@ enum ovl_path_type ovl_path_type(struct dentry *dentry) if (oe->__upperdentry) { type = __OVL_PATH_UPPER; - if (oe->numlower) { - if (S_ISDIR(dentry->d_inode->i_mode)) - type |= __OVL_PATH_MERGE; - } else if (!oe->opaque) { + /* + * Non-dir dentry can hold lower dentry from previous + * location. Its purity depends only on opaque flag. + */ + if (oe->numlower && S_ISDIR(dentry->d_inode->i_mode)) + type |= __OVL_PATH_MERGE; + else if (!oe->opaque) type |= __OVL_PATH_PURE; - } } else { if (oe->numlower > 1) type |= __OVL_PATH_MERGE; From b81de061fa59f17d2730aabb1b84419ef3913810 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Sun, 31 Jan 2016 16:21:29 +0300 Subject: [PATCH 347/417] ovl: copy new uid/gid into overlayfs runtime inode Overlayfs must update uid/gid after chown, otherwise functions like inode_owner_or_capable() will check user against stale uid. Catched by xfstests generic/087, it chowns file and calls utimes. Signed-off-by: Konstantin Khlebnikov Signed-off-by: Miklos Szeredi Cc: --- fs/overlayfs/inode.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 49e204560655..a4ff5d0d7db9 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -65,6 +65,8 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr) inode_lock(upperdentry->d_inode); err = notify_change(upperdentry, attr, NULL); + if (!err) + ovl_copyattr(upperdentry->d_inode, dentry->d_inode); inode_unlock(upperdentry->d_inode); } ovl_drop_write(dentry); From 93125094c07d8c9ec25dff5869f191b33eb9dd6e Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 3 Mar 2016 14:52:51 -0300 Subject: [PATCH 348/417] [media] media.h: postpone connectors entities The representation of external connections got some heated discussions recently. As we're too close to the merge window, let's not set those entities into a stone. Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/media.h | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index 13e19a18f97f..323f1af35062 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -82,10 +82,18 @@ struct media_device_info { * Connectors */ /* It is a responsibility of the entity drivers to add connectors and links */ +#ifdef __KERNEL__ + /* + * For now, it should not be used in userspace, as some + * definitions may change + */ + #define MEDIA_ENT_F_CONN_RF (MEDIA_ENT_F_BASE + 0x30001) #define MEDIA_ENT_F_CONN_SVIDEO (MEDIA_ENT_F_BASE + 0x30002) #define MEDIA_ENT_F_CONN_COMPOSITE (MEDIA_ENT_F_BASE + 0x30003) +#endif + /* * Don't touch on those. The ranges MEDIA_ENT_F_OLD_BASE and * MEDIA_ENT_F_OLD_SUBDEV_BASE are kept to keep backward compatibility From 88f8b1bb41c6208f81b6a480244533ded7b59493 Mon Sep 17 00:00:00 2001 From: Gabriel Fernandez Date: Mon, 29 Feb 2016 17:18:22 +0100 Subject: [PATCH 349/417] stmmac: Fix 'eth0: No PHY found' regression This patch manages the case when you have an Ethernet MAC with a "fixed link", and not connected to a normal MDIO-managed PHY device. The test of phy_bus_name was not helpful because it was never affected and replaced by the mdio test node. Signed-off-by: Gabriel Fernandez Acked-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 11 +---------- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 9 ++++++++- include/linux/stmmac.h | 1 + 3 files changed, 10 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index 0faf16336035..efb54f356a67 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -199,21 +199,12 @@ int stmmac_mdio_register(struct net_device *ndev) struct stmmac_priv *priv = netdev_priv(ndev); struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data; int addr, found; - struct device_node *mdio_node = NULL; - struct device_node *child_node = NULL; + struct device_node *mdio_node = priv->plat->mdio_node; if (!mdio_bus_data) return 0; if (IS_ENABLED(CONFIG_OF)) { - for_each_child_of_node(priv->device->of_node, child_node) { - if (of_device_is_compatible(child_node, - "snps,dwmac-mdio")) { - mdio_node = child_node; - break; - } - } - if (mdio_node) { netdev_dbg(ndev, "FOUND MDIO subnode\n"); } else { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 6a52fa18cbf2..4514ba73d961 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -110,6 +110,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) struct device_node *np = pdev->dev.of_node; struct plat_stmmacenet_data *plat; struct stmmac_dma_cfg *dma_cfg; + struct device_node *child_node = NULL; plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); if (!plat) @@ -140,13 +141,19 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) plat->phy_node = of_node_get(np); } + for_each_child_of_node(np, child_node) + if (of_device_is_compatible(child_node, "snps,dwmac-mdio")) { + plat->mdio_node = child_node; + break; + } + /* "snps,phy-addr" is not a standard property. Mark it as deprecated * and warn of its use. Remove this when phy node support is added. */ if (of_property_read_u32(np, "snps,phy-addr", &plat->phy_addr) == 0) dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n"); - if ((plat->phy_node && !of_phy_is_fixed_link(np)) || plat->phy_bus_name) + if ((plat->phy_node && !of_phy_is_fixed_link(np)) || !plat->mdio_node) plat->mdio_bus_data = NULL; else plat->mdio_bus_data = diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index eead8ab93c0a..881a79d52467 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -100,6 +100,7 @@ struct plat_stmmacenet_data { int interface; struct stmmac_mdio_bus_data *mdio_bus_data; struct device_node *phy_node; + struct device_node *mdio_node; struct stmmac_dma_cfg *dma_cfg; int clk_csr; int has_gmac; From 878e3c1be2dc8a759c18bb280a7390f9ed0bd544 Mon Sep 17 00:00:00 2001 From: Igal Liberman Date: Sun, 28 Feb 2016 23:59:53 +0200 Subject: [PATCH 350/417] fsl/fman: Initialize fman->dev earlier Currently, in a case of error, dev_err is using fman->dev before its initialization and "(NULL device *)" is printed. This patch fixes this issue. Signed-off-by: Igal Liberman Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fman/fman.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c index 623aa1c8ebc6..79a210aaf0bb 100644 --- a/drivers/net/ethernet/freescale/fman/fman.c +++ b/drivers/net/ethernet/freescale/fman/fman.c @@ -2791,6 +2791,8 @@ static struct fman *read_dts_node(struct platform_device *of_dev) goto fman_free; } + fman->dev = &of_dev->dev; + return fman; fman_node_put: @@ -2845,8 +2847,6 @@ static int fman_probe(struct platform_device *of_dev) dev_set_drvdata(dev, fman); - fman->dev = dev; - dev_dbg(dev, "FMan%d probed\n", fman->dts_params.id); return 0; From 1837b2e2bcd23137766555a63867e649c0b637f0 Mon Sep 17 00:00:00 2001 From: Benjamin Poirier Date: Mon, 29 Feb 2016 15:03:33 -0800 Subject: [PATCH 351/417] mld, igmp: Fix reserved tailroom calculation The current reserved_tailroom calculation fails to take hlen and tlen into account. skb: [__hlen__|__data____________|__tlen___|__extra__] ^ ^ head skb_end_offset In this representation, hlen + data + tlen is the size passed to alloc_skb. "extra" is the extra space made available in __alloc_skb because of rounding up by kmalloc. We can reorder the representation like so: [__hlen__|__data____________|__extra__|__tlen___] ^ ^ head skb_end_offset The maximum space available for ip headers and payload without fragmentation is min(mtu, data + extra). Therefore, reserved_tailroom = data + extra + tlen - min(mtu, data + extra) = skb_end_offset - hlen - min(mtu, skb_end_offset - hlen - tlen) = skb_tailroom - min(mtu, skb_tailroom - tlen) ; after skb_reserve(hlen) Compare the second line to the current expression: reserved_tailroom = skb_end_offset - min(mtu, skb_end_offset) and we can see that hlen and tlen are not taken into account. The min() in the third line can be expanded into: if mtu < skb_tailroom - tlen: reserved_tailroom = skb_tailroom - mtu else: reserved_tailroom = tlen Depending on hlen, tlen, mtu and the number of multicast address records, the current code may output skbs that have less tailroom than dev->needed_tailroom or it may output more skbs than needed because not all space available is used. Fixes: 4c672e4b ("ipv6: mld: fix add_grhead skb_over_panic for devs with large MTUs") Signed-off-by: Benjamin Poirier Acked-by: Hannes Frederic Sowa Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/skbuff.h | 24 ++++++++++++++++++++++++ net/ipv4/igmp.c | 3 +-- net/ipv6/mcast.c | 3 +-- 3 files changed, 26 insertions(+), 4 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4ce9ff7086f4..d3fcd4591ce4 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1985,6 +1985,30 @@ static inline void skb_reserve(struct sk_buff *skb, int len) skb->tail += len; } +/** + * skb_tailroom_reserve - adjust reserved_tailroom + * @skb: buffer to alter + * @mtu: maximum amount of headlen permitted + * @needed_tailroom: minimum amount of reserved_tailroom + * + * Set reserved_tailroom so that headlen can be as large as possible but + * not larger than mtu and tailroom cannot be smaller than + * needed_tailroom. + * The required headroom should already have been reserved before using + * this function. + */ +static inline void skb_tailroom_reserve(struct sk_buff *skb, unsigned int mtu, + unsigned int needed_tailroom) +{ + SKB_LINEAR_ASSERT(skb); + if (mtu < skb_tailroom(skb) - needed_tailroom) + /* use at most mtu */ + skb->reserved_tailroom = skb_tailroom(skb) - mtu; + else + /* use up to all available space */ + skb->reserved_tailroom = needed_tailroom; +} + #define ENCAP_TYPE_ETHER 0 #define ENCAP_TYPE_IPPROTO 1 diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 05e4cba14162..b3086cf27027 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -356,9 +356,8 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) skb_dst_set(skb, &rt->dst); skb->dev = dev; - skb->reserved_tailroom = skb_end_offset(skb) - - min(mtu, skb_end_offset(skb)); skb_reserve(skb, hlen); + skb_tailroom_reserve(skb, mtu, tlen); skb_reset_network_header(skb); pip = ip_hdr(skb); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 5ee56d0a8699..d64ee7e83664 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1574,9 +1574,8 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) return NULL; skb->priority = TC_PRIO_CONTROL; - skb->reserved_tailroom = skb_end_offset(skb) - - min(mtu, skb_end_offset(skb)); skb_reserve(skb, hlen); + skb_tailroom_reserve(skb, mtu, tlen); if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) { /* : From fbe093ac9f0201939279cdfe8b0fce20ce5ef7a9 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 3 Mar 2016 14:20:14 -0300 Subject: [PATCH 352/417] [media] media: Sanitise the reserved fields of the G_TOPOLOGY IOCTL arguments The argument structs are used in arrays for G_TOPOLOGY IOCTL. The arguments themselves do not need to be aligned to a power of two, but aligning them up to the largest basic type alignment (u64) on common ABIs is a good thing to do. The patch changes the size of the reserved fields to 5 or 6 u32's and aligns the size of the struct to 8 bytes so we do no longer depend on the compiler to perform the alignment. While at it, add __attribute__ ((packed)) to these structs as well. Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/media.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index 323f1af35062..625b38f65764 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -297,14 +297,14 @@ struct media_v2_entity { __u32 id; char name[64]; /* FIXME: move to a property? (RFC says so) */ __u32 function; /* Main function of the entity */ - __u16 reserved[12]; -}; + __u32 reserved[6]; +} __attribute__ ((packed)); /* Should match the specific fields at media_intf_devnode */ struct media_v2_intf_devnode { __u32 major; __u32 minor; -}; +} __attribute__ ((packed)); struct media_v2_interface { __u32 id; @@ -316,22 +316,22 @@ struct media_v2_interface { struct media_v2_intf_devnode devnode; __u32 raw[16]; }; -}; +} __attribute__ ((packed)); struct media_v2_pad { __u32 id; __u32 entity_id; __u32 flags; - __u16 reserved[9]; -}; + __u32 reserved[5]; +} __attribute__ ((packed)); struct media_v2_link { __u32 id; __u32 source_id; __u32 sink_id; __u32 flags; - __u32 reserved[5]; -}; + __u32 reserved[6]; +} __attribute__ ((packed)); struct media_v2_topology { __u64 topology_version; @@ -351,7 +351,7 @@ struct media_v2_topology { __u32 num_links; __u32 reserved4; __u64 ptr_links; -}; +} __attribute__ ((packed)); static inline void __user *media_get_uptr(__u64 arg) { From f214fc402967e1bc94ad7f39faa03db5813d6849 Mon Sep 17 00:00:00 2001 From: Parthasarathy Bhuvaragan Date: Tue, 1 Mar 2016 11:07:09 +0100 Subject: [PATCH 353/417] tipc: Revert "tipc: use existing sk_write_queue for outgoing packet chain" reverts commit 94153e36e709e ("tipc: use existing sk_write_queue for outgoing packet chain") In Commit 94153e36e709e, we assume that we fill & empty the socket's sk_write_queue within the same lock_sock() session. This is not true if the link is congested. During congestion, the socket lock is released while we wait for the congestion to cease. This implementation causes a nullptr exception, if the user space program has several threads accessing the same socket descriptor. Consider two threads of the same program performing the following: Thread1 Thread2 -------------------- ---------------------- Enter tipc_sendmsg() Enter tipc_sendmsg() lock_sock() lock_sock() Enter tipc_link_xmit(), ret=ELINKCONG spin on socket lock.. sk_wait_event() : release_sock() grab socket lock : Enter tipc_link_xmit(), ret=0 : release_sock() Wakeup after congestion lock_sock() skb = skb_peek(pktchain); !! TIPC_SKB_CB(skb)->wakeup_pending = tsk->link_cong; In this case, the second thread transmits the buffers belonging to both thread1 and thread2 successfully. When the first thread wakeup after the congestion it assumes that the pktchain is intact and operates on the skb's in it, which leads to the following exception: [2102.439969] BUG: unable to handle kernel NULL pointer dereference at 00000000000000d0 [2102.440074] IP: [] __tipc_link_xmit+0x2b0/0x4d0 [tipc] [2102.440074] PGD 3fa3f067 PUD 3fa6b067 PMD 0 [2102.440074] Oops: 0000 [#1] SMP [2102.440074] CPU: 2 PID: 244 Comm: sender Not tainted 3.12.28 #1 [2102.440074] RIP: 0010:[] [] __tipc_link_xmit+0x2b0/0x4d0 [tipc] [...] [2102.440074] Call Trace: [2102.440074] [] ? schedule+0x29/0x70 [2102.440074] [] ? tipc_node_unlock+0x46/0x170 [tipc] [2102.440074] [] tipc_link_xmit+0x51/0xf0 [tipc] [2102.440074] [] tipc_send_stream+0x11e/0x4f0 [tipc] [2102.440074] [] ? __wake_up_sync+0x20/0x20 [2102.440074] [] tipc_send_packet+0x1c/0x20 [tipc] [2102.440074] [] sock_sendmsg+0xa8/0xd0 [2102.440074] [] ? release_sock+0x145/0x170 [2102.440074] [] ___sys_sendmsg+0x3d8/0x3e0 [2102.440074] [] ? _raw_spin_unlock+0xe/0x10 [2102.440074] [] ? handle_mm_fault+0x6ca/0x9d0 [2102.440074] [] ? set_next_entity+0x85/0xa0 [2102.440074] [] ? _raw_spin_unlock_irq+0xe/0x20 [2102.440074] [] ? finish_task_switch+0x5c/0xc0 [2102.440074] [] ? __schedule+0x34c/0x950 [2102.440074] [] __sys_sendmsg+0x42/0x80 [2102.440074] [] SyS_sendmsg+0x12/0x20 [2102.440074] [] system_call_fastpath+0x16/0x1b In this commit, we maintain the skb list always in the stack. Signed-off-by: Parthasarathy Bhuvaragan Acked-by: Ying Xue Acked-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/socket.c | 33 +++++++++++++++++++-------------- 1 file changed, 19 insertions(+), 14 deletions(-) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 69c29050f14a..4d420bb27396 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -673,7 +673,7 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, struct tipc_sock *tsk = tipc_sk(sk); struct net *net = sock_net(sk); struct tipc_msg *mhdr = &tsk->phdr; - struct sk_buff_head *pktchain = &sk->sk_write_queue; + struct sk_buff_head pktchain; struct iov_iter save = msg->msg_iter; uint mtu; int rc; @@ -687,14 +687,16 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, msg_set_nameupper(mhdr, seq->upper); msg_set_hdr_sz(mhdr, MCAST_H_SIZE); + skb_queue_head_init(&pktchain); + new_mtu: mtu = tipc_bcast_get_mtu(net); - rc = tipc_msg_build(mhdr, msg, 0, dsz, mtu, pktchain); + rc = tipc_msg_build(mhdr, msg, 0, dsz, mtu, &pktchain); if (unlikely(rc < 0)) return rc; do { - rc = tipc_bcast_xmit(net, pktchain); + rc = tipc_bcast_xmit(net, &pktchain); if (likely(!rc)) return dsz; @@ -704,7 +706,7 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, if (!rc) continue; } - __skb_queue_purge(pktchain); + __skb_queue_purge(&pktchain); if (rc == -EMSGSIZE) { msg->msg_iter = save; goto new_mtu; @@ -863,7 +865,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz) struct net *net = sock_net(sk); struct tipc_msg *mhdr = &tsk->phdr; u32 dnode, dport; - struct sk_buff_head *pktchain = &sk->sk_write_queue; + struct sk_buff_head pktchain; struct sk_buff *skb; struct tipc_name_seq *seq; struct iov_iter save; @@ -924,17 +926,18 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz) msg_set_hdr_sz(mhdr, BASIC_H_SIZE); } + skb_queue_head_init(&pktchain); save = m->msg_iter; new_mtu: mtu = tipc_node_get_mtu(net, dnode, tsk->portid); - rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, pktchain); + rc = tipc_msg_build(mhdr, m, 0, dsz, mtu, &pktchain); if (rc < 0) return rc; do { - skb = skb_peek(pktchain); + skb = skb_peek(&pktchain); TIPC_SKB_CB(skb)->wakeup_pending = tsk->link_cong; - rc = tipc_node_xmit(net, pktchain, dnode, tsk->portid); + rc = tipc_node_xmit(net, &pktchain, dnode, tsk->portid); if (likely(!rc)) { if (sock->state != SS_READY) sock->state = SS_CONNECTING; @@ -946,7 +949,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz) if (!rc) continue; } - __skb_queue_purge(pktchain); + __skb_queue_purge(&pktchain); if (rc == -EMSGSIZE) { m->msg_iter = save; goto new_mtu; @@ -1016,7 +1019,7 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz) struct net *net = sock_net(sk); struct tipc_sock *tsk = tipc_sk(sk); struct tipc_msg *mhdr = &tsk->phdr; - struct sk_buff_head *pktchain = &sk->sk_write_queue; + struct sk_buff_head pktchain; DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); u32 portid = tsk->portid; int rc = -EINVAL; @@ -1044,17 +1047,19 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz) timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); dnode = tsk_peer_node(tsk); + skb_queue_head_init(&pktchain); next: save = m->msg_iter; mtu = tsk->max_pkt; send = min_t(uint, dsz - sent, TIPC_MAX_USER_MSG_SIZE); - rc = tipc_msg_build(mhdr, m, sent, send, mtu, pktchain); + rc = tipc_msg_build(mhdr, m, sent, send, mtu, &pktchain); if (unlikely(rc < 0)) return rc; + do { if (likely(!tsk_conn_cong(tsk))) { - rc = tipc_node_xmit(net, pktchain, dnode, portid); + rc = tipc_node_xmit(net, &pktchain, dnode, portid); if (likely(!rc)) { tsk->sent_unacked++; sent += send; @@ -1063,7 +1068,7 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz) goto next; } if (rc == -EMSGSIZE) { - __skb_queue_purge(pktchain); + __skb_queue_purge(&pktchain); tsk->max_pkt = tipc_node_get_mtu(net, dnode, portid); m->msg_iter = save; @@ -1077,7 +1082,7 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz) rc = tipc_wait_for_sndpkt(sock, &timeo); } while (!rc); - __skb_queue_purge(pktchain); + __skb_queue_purge(&pktchain); return sent ? sent : rc; } From bf13c94ccb33c3182efc92ce4989506a0f541243 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Tue, 1 Mar 2016 14:31:02 +0100 Subject: [PATCH 354/417] qmi_wwan: add Sierra Wireless EM74xx device ID MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The MC74xx and EM74xx modules use different IDs by default, according to the Lenovo EM7455 driver for Windows. Signed-off-by: Bjørn Mork Signed-off-by: David S. Miller --- drivers/net/usb/qmi_wwan.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 4ce4ec16e968..a3a4ccf7cf52 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -861,8 +861,10 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1199, 0x9056, 8)}, /* Sierra Wireless Modem */ {QMI_FIXED_INTF(0x1199, 0x9057, 8)}, {QMI_FIXED_INTF(0x1199, 0x9061, 8)}, /* Sierra Wireless Modem */ - {QMI_FIXED_INTF(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx/EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx/EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx */ + {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx */ + {QMI_FIXED_INTF(0x1199, 0x9079, 8)}, /* Sierra Wireless EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x9079, 10)}, /* Sierra Wireless EM74xx */ {QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */ {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ From 5d150a985520bbe3cb2aa1ceef24a7e32f20c15f Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 1 Mar 2016 16:15:16 +0100 Subject: [PATCH 355/417] ipv6: re-enable fragment header matching in ipv6_find_hdr When ipv6_find_hdr is used to find a fragment header (caller specifies target NEXTHDR_FRAGMENT) we erronously return -ENOENT for all fragments with nonzero offset. Before commit 9195bb8e381d, when target was specified, we did not enter the exthdr walk loop as nexthdr == target so this used to work. Now we do (so we can skip empty route headers). When we then stumble upon a frag with nonzero frag_off we must return -ENOENT ("header not found") only if the caller did not specifically request NEXTHDR_FRAGMENT. This allows nfables exthdr expression to match ipv6 fragments, e.g. via nft add rule ip6 filter input frag frag-off gt 0 Fixes: 9195bb8e381d ("ipv6: improve ipv6_find_hdr() to skip empty routing headers") Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- net/ipv6/exthdrs_core.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 5c5d23e59da5..9508a20fbf61 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -257,7 +257,11 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, *fragoff = _frag_off; return hp->nexthdr; } - return -ENOENT; + if (!found) + return -ENOENT; + if (fragoff) + *fragoff = _frag_off; + break; } hdrlen = 8; } else if (nexthdr == NEXTHDR_AUTH) { From de89e854bcc71ebaf30d415a0c015d1cb6c68856 Mon Sep 17 00:00:00 2001 From: Thomas Falcon Date: Tue, 1 Mar 2016 10:20:09 -0600 Subject: [PATCH 356/417] ibmvnic: Fix ibmvnic_capability struct The ibmvnic_capability struct was defined incorrectly. The last two elements of the struct are in the wrong order. In addition, the number element should be 64-bit. Byteswapping functions are updated as well. Signed-off-by: Thomas Falcon Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmvnic.c | 62 +++++++++++++++--------------- drivers/net/ethernet/ibm/ibmvnic.h | 4 +- 2 files changed, 32 insertions(+), 34 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 7d6570843723..6e9e16eee5d0 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1348,44 +1348,44 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry) crq.request_capability.cmd = REQUEST_CAPABILITY; crq.request_capability.capability = cpu_to_be16(REQ_TX_QUEUES); - crq.request_capability.number = cpu_to_be32(adapter->req_tx_queues); + crq.request_capability.number = cpu_to_be64(adapter->req_tx_queues); ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_RX_QUEUES); - crq.request_capability.number = cpu_to_be32(adapter->req_rx_queues); + crq.request_capability.number = cpu_to_be64(adapter->req_rx_queues); ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_RX_ADD_QUEUES); - crq.request_capability.number = cpu_to_be32(adapter->req_rx_add_queues); + crq.request_capability.number = cpu_to_be64(adapter->req_rx_add_queues); ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_TX_ENTRIES_PER_SUBCRQ); crq.request_capability.number = - cpu_to_be32(adapter->req_tx_entries_per_subcrq); + cpu_to_be64(adapter->req_tx_entries_per_subcrq); ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_RX_ADD_ENTRIES_PER_SUBCRQ); crq.request_capability.number = - cpu_to_be32(adapter->req_rx_add_entries_per_subcrq); + cpu_to_be64(adapter->req_rx_add_entries_per_subcrq); ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_MTU); - crq.request_capability.number = cpu_to_be32(adapter->req_mtu); + crq.request_capability.number = cpu_to_be64(adapter->req_mtu); ibmvnic_send_crq(adapter, &crq); if (adapter->netdev->flags & IFF_PROMISC) { if (adapter->promisc_supported) { crq.request_capability.capability = cpu_to_be16(PROMISC_REQUESTED); - crq.request_capability.number = cpu_to_be32(1); + crq.request_capability.number = cpu_to_be64(1); ibmvnic_send_crq(adapter, &crq); } } else { crq.request_capability.capability = cpu_to_be16(PROMISC_REQUESTED); - crq.request_capability.number = cpu_to_be32(0); + crq.request_capability.number = cpu_to_be64(0); ibmvnic_send_crq(adapter, &crq); } @@ -2312,93 +2312,93 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq, switch (be16_to_cpu(crq->query_capability.capability)) { case MIN_TX_QUEUES: adapter->min_tx_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_tx_queues = %lld\n", adapter->min_tx_queues); break; case MIN_RX_QUEUES: adapter->min_rx_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_rx_queues = %lld\n", adapter->min_rx_queues); break; case MIN_RX_ADD_QUEUES: adapter->min_rx_add_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_rx_add_queues = %lld\n", adapter->min_rx_add_queues); break; case MAX_TX_QUEUES: adapter->max_tx_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_tx_queues = %lld\n", adapter->max_tx_queues); break; case MAX_RX_QUEUES: adapter->max_rx_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_rx_queues = %lld\n", adapter->max_rx_queues); break; case MAX_RX_ADD_QUEUES: adapter->max_rx_add_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_rx_add_queues = %lld\n", adapter->max_rx_add_queues); break; case MIN_TX_ENTRIES_PER_SUBCRQ: adapter->min_tx_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_tx_entries_per_subcrq = %lld\n", adapter->min_tx_entries_per_subcrq); break; case MIN_RX_ADD_ENTRIES_PER_SUBCRQ: adapter->min_rx_add_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_rx_add_entrs_per_subcrq = %lld\n", adapter->min_rx_add_entries_per_subcrq); break; case MAX_TX_ENTRIES_PER_SUBCRQ: adapter->max_tx_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_tx_entries_per_subcrq = %lld\n", adapter->max_tx_entries_per_subcrq); break; case MAX_RX_ADD_ENTRIES_PER_SUBCRQ: adapter->max_rx_add_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_rx_add_entrs_per_subcrq = %lld\n", adapter->max_rx_add_entries_per_subcrq); break; case TCP_IP_OFFLOAD: adapter->tcp_ip_offload = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "tcp_ip_offload = %lld\n", adapter->tcp_ip_offload); break; case PROMISC_SUPPORTED: adapter->promisc_supported = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "promisc_supported = %lld\n", adapter->promisc_supported); break; case MIN_MTU: - adapter->min_mtu = be32_to_cpu(crq->query_capability.number); + adapter->min_mtu = be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "min_mtu = %lld\n", adapter->min_mtu); break; case MAX_MTU: - adapter->max_mtu = be32_to_cpu(crq->query_capability.number); + adapter->max_mtu = be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_mtu = %lld\n", adapter->max_mtu); break; case MAX_MULTICAST_FILTERS: adapter->max_multicast_filters = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_multicast_filters = %lld\n", adapter->max_multicast_filters); break; case VLAN_HEADER_INSERTION: adapter->vlan_header_insertion = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); if (adapter->vlan_header_insertion) netdev->features |= NETIF_F_HW_VLAN_STAG_TX; netdev_dbg(netdev, "vlan_header_insertion = %lld\n", @@ -2406,43 +2406,43 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq, break; case MAX_TX_SG_ENTRIES: adapter->max_tx_sg_entries = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "max_tx_sg_entries = %lld\n", adapter->max_tx_sg_entries); break; case RX_SG_SUPPORTED: adapter->rx_sg_supported = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "rx_sg_supported = %lld\n", adapter->rx_sg_supported); break; case OPT_TX_COMP_SUB_QUEUES: adapter->opt_tx_comp_sub_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "opt_tx_comp_sub_queues = %lld\n", adapter->opt_tx_comp_sub_queues); break; case OPT_RX_COMP_QUEUES: adapter->opt_rx_comp_queues = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "opt_rx_comp_queues = %lld\n", adapter->opt_rx_comp_queues); break; case OPT_RX_BUFADD_Q_PER_RX_COMP_Q: adapter->opt_rx_bufadd_q_per_rx_comp_q = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "opt_rx_bufadd_q_per_rx_comp_q = %lld\n", adapter->opt_rx_bufadd_q_per_rx_comp_q); break; case OPT_TX_ENTRIES_PER_SUBCRQ: adapter->opt_tx_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "opt_tx_entries_per_subcrq = %lld\n", adapter->opt_tx_entries_per_subcrq); break; case OPT_RXBA_ENTRIES_PER_SUBCRQ: adapter->opt_rxba_entries_per_subcrq = - be32_to_cpu(crq->query_capability.number); + be64_to_cpu(crq->query_capability.number); netdev_dbg(netdev, "opt_rxba_entries_per_subcrq = %lld\n", adapter->opt_rxba_entries_per_subcrq); break; diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 1242925ad34c..1a9993cc79b5 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -319,10 +319,8 @@ struct ibmvnic_capability { u8 first; u8 cmd; __be16 capability; /* one of ibmvnic_capabilities */ + __be64 number; struct ibmvnic_rc rc; - __be32 number; /*FIX: should be __be64, but I'm getting the least - * significant word first - */ } __packed __aligned(8); struct ibmvnic_login { From e866863066a4e6c42117434dd5cd35c9842f5b82 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 1 Mar 2016 17:37:58 +0100 Subject: [PATCH 357/417] net: ethernet: renesas: ravb_main: don't open code of_device_get_match_data() This change will also make Coverity happy by avoiding a theoretical NULL pointer dereference; yet another reason is to use the above helper function to tighten the code and make it more readable. Signed-off-by: Wolfram Sang Reviewed-by: Simon Horman Acked-by: Geert Uytterhoeven Signed-off-by: David S. Miller --- drivers/net/ethernet/renesas/ravb_main.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 744d7806a9ee..86449c357168 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1722,7 +1722,6 @@ static int ravb_set_gti(struct net_device *ndev) static int ravb_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; - const struct of_device_id *match; struct ravb_private *priv; enum ravb_chip_id chip_id; struct net_device *ndev; @@ -1754,8 +1753,7 @@ static int ravb_probe(struct platform_device *pdev) ndev->base_addr = res->start; ndev->dma = -1; - match = of_match_device(of_match_ptr(ravb_match_table), &pdev->dev); - chip_id = (enum ravb_chip_id)match->data; + chip_id = (enum ravb_chip_id)of_device_get_match_data(&pdev->dev); if (chip_id == RCAR_GEN3) irq = platform_get_irq_byname(pdev, "ch22"); From 42a67c9b0c0853f6a1159bd54ed0ba50df9f9ad8 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 1 Mar 2016 17:37:59 +0100 Subject: [PATCH 358/417] net: ethernet: renesas: sh_eth: don't open code of_device_get_match_data() This change will also make Coverity happy by avoiding a theoretical NULL pointer dereference; yet another reason is to use the above helper function to tighten the code and make it more readable. Signed-off-by: Wolfram Sang Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/renesas/sh_eth.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index dfa9e59c9442..738449992876 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -3061,15 +3061,11 @@ static int sh_eth_drv_probe(struct platform_device *pdev) mdp->ether_link_active_low = pd->ether_link_active_low; /* set cpu data */ - if (id) { + if (id) mdp->cd = (struct sh_eth_cpu_data *)id->driver_data; - } else { - const struct of_device_id *match; + else + mdp->cd = (struct sh_eth_cpu_data *)of_device_get_match_data(&pdev->dev); - match = of_match_device(of_match_ptr(sh_eth_match_table), - &pdev->dev); - mdp->cd = (struct sh_eth_cpu_data *)match->data; - } mdp->reg_offset = sh_eth_get_register_offset(mdp->cd->register_type); if (!mdp->reg_offset) { dev_err(&pdev->dev, "Unknown register type (%d)\n", From 7bcd79ac50d9d83350a835bdb91c04ac9e098412 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 26 Feb 2016 23:40:50 +0800 Subject: [PATCH 359/417] block: bio: introduce helpers to get the 1st and last bvec The bio passed to bio_will_gap() may be fast cloned from upper layer(dm, md, bcache, fs, ...), or from bio splitting in block core. Unfortunately bio_will_gap() just figures out the last bvec via 'bi_io_vec[prev->bi_vcnt - 1]' directly, and this way is obviously wrong. This patch introduces two helpers for getting the first and last bvec of one bio for fixing the issue. Cc: stable@vger.kernel.org Reported-by: Sagi Grimberg Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bio.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) diff --git a/include/linux/bio.h b/include/linux/bio.h index 5349e6816cbb..cb6888824108 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -310,6 +310,43 @@ static inline void bio_clear_flag(struct bio *bio, unsigned int bit) bio->bi_flags &= ~(1U << bit); } +static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv) +{ + *bv = bio_iovec(bio); +} + +static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) +{ + struct bvec_iter iter = bio->bi_iter; + int idx; + + if (!bio_flagged(bio, BIO_CLONED)) { + *bv = bio->bi_io_vec[bio->bi_vcnt - 1]; + return; + } + + if (unlikely(!bio_multiple_segments(bio))) { + *bv = bio_iovec(bio); + return; + } + + bio_advance_iter(bio, &iter, iter.bi_size); + + if (!iter.bi_bvec_done) + idx = iter.bi_idx - 1; + else /* in the middle of bvec */ + idx = iter.bi_idx; + + *bv = bio->bi_io_vec[idx]; + + /* + * iter.bi_bvec_done records actual length of the last bvec + * if this bio ends in the middle of one io vector + */ + if (iter.bi_bvec_done) + bv->bv_len = iter.bi_bvec_done; +} + enum bip_flags { BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */ BIP_MAPPED_INTEGRITY = 1 << 1, /* ref tag has been remapped */ From e0af29171aa8912e1ca95023b75ef336cd70d661 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 26 Feb 2016 23:40:51 +0800 Subject: [PATCH 360/417] block: check virt boundary in bio_will_gap() In the following patch, the way for figuring out the last bvec will be changed with a bit cost introduced, so return immediately if the queue doesn't have virt boundary limit. Actually most of devices have not this limit. Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4571ef1a12a9..cd06a41581b3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1372,6 +1372,13 @@ static inline void put_dev_sector(Sector p) page_cache_release(p.v); } +static inline bool __bvec_gap_to_prev(struct request_queue *q, + struct bio_vec *bprv, unsigned int offset) +{ + return offset || + ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); +} + /* * Check if adding a bio_vec after bprv with offset would create a gap in * the SG list. Most drivers don't care about this, but some do. @@ -1381,18 +1388,17 @@ static inline bool bvec_gap_to_prev(struct request_queue *q, { if (!queue_virt_boundary(q)) return false; - return offset || - ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); + return __bvec_gap_to_prev(q, bprv, offset); } static inline bool bio_will_gap(struct request_queue *q, struct bio *prev, struct bio *next) { - if (!bio_has_data(prev)) + if (!bio_has_data(prev) || !queue_virt_boundary(q)) return false; - return bvec_gap_to_prev(q, &prev->bi_io_vec[prev->bi_vcnt - 1], - next->bi_io_vec[0].bv_offset); + return __bvec_gap_to_prev(q, &prev->bi_io_vec[prev->bi_vcnt - 1], + next->bi_io_vec[0].bv_offset); } static inline bool req_gap_back_merge(struct request *req, struct bio *bio) From 25e71a99f10e444cd00bb2ebccb11e1c9fb672b1 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 26 Feb 2016 23:40:52 +0800 Subject: [PATCH 361/417] block: get the 1st and last bvec via helpers This patch applies the two introduced helpers to figure out the 1st and last bvec, and fixes the original way after bio splitting. Cc: stable@vger.kernel.org Reported-by: Sagi Grimberg Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index cd06a41581b3..d7f6bca707ef 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1394,11 +1394,16 @@ static inline bool bvec_gap_to_prev(struct request_queue *q, static inline bool bio_will_gap(struct request_queue *q, struct bio *prev, struct bio *next) { - if (!bio_has_data(prev) || !queue_virt_boundary(q)) - return false; + if (bio_has_data(prev) && queue_virt_boundary(q)) { + struct bio_vec pb, nb; - return __bvec_gap_to_prev(q, &prev->bi_io_vec[prev->bi_vcnt - 1], - next->bi_io_vec[0].bv_offset); + bio_get_last_bvec(prev, &pb); + bio_get_first_bvec(next, &nb); + + return __bvec_gap_to_prev(q, &pb, nb.bv_offset); + } + + return false; } static inline bool req_gap_back_merge(struct request *req, struct bio *bio) From e827091cb1bcd8e718ac3657845fb809c0b93324 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 26 Feb 2016 23:40:53 +0800 Subject: [PATCH 362/417] block: merge: get the 1st and last bvec via helpers This patch applies the two introduced helpers to figure out the 1st and last bvec. Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-merge.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/block/blk-merge.c b/block/blk-merge.c index 888a7fec81f7..261353166dcf 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -304,7 +304,6 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio, struct bio *nxt) { struct bio_vec end_bv = { NULL }, nxt_bv; - struct bvec_iter iter; if (!blk_queue_cluster(q)) return 0; @@ -316,11 +315,8 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio, if (!bio_has_data(bio)) return 1; - bio_for_each_segment(end_bv, bio, iter) - if (end_bv.bv_len == iter.bi_size) - break; - - nxt_bv = bio_iovec(nxt); + bio_get_last_bvec(bio, &end_bv); + bio_get_first_bvec(nxt, &nxt_bv); if (!BIOVEC_PHYS_MERGEABLE(&end_bv, &nxt_bv)) return 0; From b00a726a9fd82ddd4c10344e46f0d371e1674303 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 24 Feb 2016 09:15:52 -0700 Subject: [PATCH 363/417] NVMe: Don't unmap controller registers on reset Unmapping the registers on reset or shutdown is not necessary. Keeping the mapping simplifies reset handling. Signed-off-by: Keith Busch Reviewed-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/pci.c | 71 ++++++++++++++++++++++++----------------- 1 file changed, 42 insertions(+), 29 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index a128672472ec..2ea3e398536c 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1694,10 +1694,10 @@ static int nvme_dev_add(struct nvme_dev *dev) return 0; } -static int nvme_dev_map(struct nvme_dev *dev) +static int nvme_pci_enable(struct nvme_dev *dev) { u64 cap; - int bars, result = -ENOMEM; + int result = -ENOMEM; struct pci_dev *pdev = to_pci_dev(dev->dev); if (pci_enable_device_mem(pdev)) @@ -1705,24 +1705,14 @@ static int nvme_dev_map(struct nvme_dev *dev) dev->entry[0].vector = pdev->irq; pci_set_master(pdev); - bars = pci_select_bars(pdev, IORESOURCE_MEM); - if (!bars) - goto disable_pci; - - if (pci_request_selected_regions(pdev, bars, "nvme")) - goto disable_pci; if (dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64)) && dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(32))) goto disable; - dev->bar = ioremap(pci_resource_start(pdev, 0), 8192); - if (!dev->bar) - goto disable; - if (readl(dev->bar + NVME_REG_CSTS) == -1) { result = -ENODEV; - goto unmap; + goto disable; } /* @@ -1732,7 +1722,7 @@ static int nvme_dev_map(struct nvme_dev *dev) if (!pdev->irq) { result = pci_enable_msix(pdev, dev->entry, 1); if (result < 0) - goto unmap; + goto disable; } cap = lo_hi_readq(dev->bar + NVME_REG_CAP); @@ -1759,17 +1749,19 @@ static int nvme_dev_map(struct nvme_dev *dev) pci_save_state(pdev); return 0; - unmap: - iounmap(dev->bar); - dev->bar = NULL; disable: - pci_release_regions(pdev); - disable_pci: pci_disable_device(pdev); return result; } static void nvme_dev_unmap(struct nvme_dev *dev) +{ + if (dev->bar) + iounmap(dev->bar); + pci_release_regions(to_pci_dev(dev->dev)); +} + +static void nvme_pci_disable(struct nvme_dev *dev) { struct pci_dev *pdev = to_pci_dev(dev->dev); @@ -1778,12 +1770,6 @@ static void nvme_dev_unmap(struct nvme_dev *dev) else if (pdev->msix_enabled) pci_disable_msix(pdev); - if (dev->bar) { - iounmap(dev->bar); - dev->bar = NULL; - pci_release_regions(pdev); - } - if (pci_is_enabled(pdev)) { pci_disable_pcie_error_reporting(pdev); pci_disable_device(pdev); @@ -1842,7 +1828,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) nvme_dev_list_remove(dev); mutex_lock(&dev->shutdown_lock); - if (dev->bar) { + if (pci_is_enabled(to_pci_dev(dev->dev))) { nvme_stop_queues(&dev->ctrl); csts = readl(dev->bar + NVME_REG_CSTS); } @@ -1855,7 +1841,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) nvme_disable_io_queues(dev); nvme_disable_admin_queue(dev, shutdown); } - nvme_dev_unmap(dev); + nvme_pci_disable(dev); for (i = dev->queue_count - 1; i >= 0; i--) nvme_clear_queue(dev->queues[i]); @@ -1911,12 +1897,12 @@ static void nvme_reset_work(struct work_struct *work) * If we're called to reset a live controller first shut it down before * moving on. */ - if (dev->bar) + if (dev->ctrl.ctrl_config & NVME_CC_ENABLE) nvme_dev_disable(dev, false); set_bit(NVME_CTRL_RESETTING, &dev->flags); - result = nvme_dev_map(dev); + result = nvme_pci_enable(dev); if (result) goto out; @@ -2042,6 +2028,27 @@ static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = { .free_ctrl = nvme_pci_free_ctrl, }; +static int nvme_dev_map(struct nvme_dev *dev) +{ + int bars; + struct pci_dev *pdev = to_pci_dev(dev->dev); + + bars = pci_select_bars(pdev, IORESOURCE_MEM); + if (!bars) + return -ENODEV; + if (pci_request_selected_regions(pdev, bars, "nvme")) + return -ENODEV; + + dev->bar = ioremap(pci_resource_start(pdev, 0), 8192); + if (!dev->bar) + goto release; + + return 0; + release: + pci_release_regions(pdev); + return -ENODEV; +} + static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) { int node, result = -ENOMEM; @@ -2066,6 +2073,10 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) dev->dev = get_device(&pdev->dev); pci_set_drvdata(pdev, dev); + result = nvme_dev_map(dev); + if (result) + goto free; + INIT_LIST_HEAD(&dev->node); INIT_WORK(&dev->scan_work, nvme_dev_scan); INIT_WORK(&dev->reset_work, nvme_reset_work); @@ -2089,6 +2100,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) nvme_release_prp_pools(dev); put_pci: put_device(dev->dev); + nvme_dev_unmap(dev); free: kfree(dev->queues); kfree(dev->entry); @@ -2126,6 +2138,7 @@ static void nvme_remove(struct pci_dev *pdev) nvme_free_queues(dev, 0); nvme_release_cmb(dev); nvme_release_prp_pools(dev); + nvme_dev_unmap(dev); nvme_put_ctrl(&dev->ctrl); } From 075790ebba4a1eb297f9875e581b55c0382b1f3d Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 24 Feb 2016 09:15:53 -0700 Subject: [PATCH 364/417] NVMe: Use IDA for namespace disk naming A namespace may be detached from a controller, but a user may be holding a reference to it. Attaching a new namespace with the same NSID will create duplicate names when using the NSID to name the disk. This patch uses an IDA that is released only when the last reference is released instead of using the namespace ID. Signed-off-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 15 ++++++++++++--- drivers/nvme/host/nvme.h | 2 ++ 2 files changed, 14 insertions(+), 3 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 3cd921e6121e..6c39dbf0290f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -55,8 +55,9 @@ static void nvme_free_ns(struct kref *kref) ns->disk->private_data = NULL; spin_unlock(&dev_list_lock); - nvme_put_ctrl(ns->ctrl); put_disk(ns->disk); + ida_simple_remove(&ns->ctrl->ns_ida, ns->instance); + nvme_put_ctrl(ns->ctrl); kfree(ns); } @@ -1118,9 +1119,13 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) if (!ns) return; + ns->instance = ida_simple_get(&ctrl->ns_ida, 1, 0, GFP_KERNEL); + if (ns->instance < 0) + goto out_free_ns; + ns->queue = blk_mq_init_queue(ctrl->tagset); if (IS_ERR(ns->queue)) - goto out_free_ns; + goto out_release_instance; queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue); ns->queue->queuedata = ns; ns->ctrl = ctrl; @@ -1153,7 +1158,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) disk->queue = ns->queue; disk->driverfs_dev = ctrl->device; disk->flags = GENHD_FL_EXT_DEVT; - sprintf(disk->disk_name, "nvme%dn%d", ctrl->instance, nsid); + sprintf(disk->disk_name, "nvme%dn%d", ctrl->instance, ns->instance); if (nvme_revalidate_disk(ns->disk)) goto out_free_disk; @@ -1173,6 +1178,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) kfree(disk); out_free_queue: blk_cleanup_queue(ns->queue); + out_release_instance: + ida_simple_remove(&ctrl->ns_ida, ns->instance); out_free_ns: kfree(ns); } @@ -1350,6 +1357,7 @@ static void nvme_free_ctrl(struct kref *kref) put_device(ctrl->device); nvme_release_instance(ctrl); + ida_destroy(&ctrl->ns_ida); ctrl->ops->free_ctrl(ctrl); } @@ -1390,6 +1398,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, } get_device(ctrl->device); dev_set_drvdata(ctrl->device, ctrl); + ida_init(&ctrl->ns_ida); spin_lock(&dev_list_lock); list_add_tail(&ctrl->node, &nvme_ctrl_list); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 9664d07d807d..9407f2fa4487 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -72,6 +72,7 @@ struct nvme_ctrl { struct mutex namespaces_mutex; struct device *device; /* char device */ struct list_head node; + struct ida ns_ida; char name[12]; char serial[20]; @@ -102,6 +103,7 @@ struct nvme_ns { struct request_queue *queue; struct gendisk *disk; struct kref kref; + int instance; u8 eui[8]; u8 uuid[16]; From 646017a612e72f19bd9f991fe25287a149c5f627 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 24 Feb 2016 09:15:54 -0700 Subject: [PATCH 365/417] NVMe: Fix namespace removal deadlock This patch makes nvme namespace removal lockless. It is up to the caller to ensure no active namespace scanning is occuring. To ensure no scan work occurs, the nvme pci driver adds a removing state to the controller device to avoid queueing scan work during removal. The work is flushed after setting the state, so no new scan work can be queued. The lockless removal allows the driver to cleanup a namespace request_queue if the controller fails during removal. Previously this could deadlock trying to acquire the namespace mutex in order to handle such events. Signed-off-by: Keith Busch Reviewed-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 14 ++++++++------ drivers/nvme/host/nvme.h | 4 ++++ drivers/nvme/host/pci.c | 17 +++++++++++++++-- 3 files changed, 27 insertions(+), 8 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 6c39dbf0290f..8c2ddd5025ab 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1186,11 +1186,13 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) static void nvme_ns_remove(struct nvme_ns *ns) { - bool kill = nvme_io_incapable(ns->ctrl) && + bool kill; + + if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags)) + return; + + kill = nvme_io_incapable(ns->ctrl) && !blk_queue_dying(ns->queue); - - lockdep_assert_held(&ns->ctrl->namespaces_mutex); - if (kill) { blk_set_queue_dying(ns->queue); @@ -1213,7 +1215,9 @@ static void nvme_ns_remove(struct nvme_ns *ns) blk_mq_abort_requeue_list(ns->queue); blk_cleanup_queue(ns->queue); } + mutex_lock(&ns->ctrl->namespaces_mutex); list_del_init(&ns->list); + mutex_unlock(&ns->ctrl->namespaces_mutex); nvme_put_ns(ns); } @@ -1307,10 +1311,8 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl) { struct nvme_ns *ns, *next; - mutex_lock(&ctrl->namespaces_mutex); list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) nvme_ns_remove(ns); - mutex_unlock(&ctrl->namespaces_mutex); } static DEFINE_IDA(nvme_instance_ida); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 9407f2fa4487..4075fa9e0c34 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -114,6 +114,10 @@ struct nvme_ns { bool ext; u8 pi_type; int type; + unsigned long flags; + +#define NVME_NS_REMOVING 0 + u64 mode_select_num_blocks; u32 mode_select_block_len; }; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 2ea3e398536c..122f803f0efb 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -120,6 +120,7 @@ struct nvme_dev { unsigned long flags; #define NVME_CTRL_RESETTING 0 +#define NVME_CTRL_REMOVING 1 struct nvme_ctrl ctrl; struct completion ioq_wait; @@ -286,6 +287,17 @@ static int nvme_init_request(void *data, struct request *req, return 0; } +static void nvme_queue_scan(struct nvme_dev *dev) +{ + /* + * Do not queue new scan work when a controller is reset during + * removal. + */ + if (test_bit(NVME_CTRL_REMOVING, &dev->flags)) + return; + queue_work(nvme_workq, &dev->scan_work); +} + static void nvme_complete_async_event(struct nvme_dev *dev, struct nvme_completion *cqe) { @@ -300,7 +312,7 @@ static void nvme_complete_async_event(struct nvme_dev *dev, switch (result & 0xff07) { case NVME_AER_NOTICE_NS_CHANGED: dev_info(dev->dev, "rescanning\n"); - queue_work(nvme_workq, &dev->scan_work); + nvme_queue_scan(dev); default: dev_warn(dev->dev, "async event result %08x\n", result); } @@ -1690,7 +1702,7 @@ static int nvme_dev_add(struct nvme_dev *dev) return 0; dev->ctrl.tagset = &dev->tagset; } - queue_work(nvme_workq, &dev->scan_work); + nvme_queue_scan(dev); return 0; } @@ -2128,6 +2140,7 @@ static void nvme_remove(struct pci_dev *pdev) { struct nvme_dev *dev = pci_get_drvdata(pdev); + set_bit(NVME_CTRL_REMOVING, &dev->flags); pci_set_drvdata(pdev, NULL); flush_work(&dev->scan_work); nvme_remove_namespaces(&dev->ctrl); From f58944e265d4ebe47216a5d7488aee3928823d30 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 24 Feb 2016 09:15:55 -0700 Subject: [PATCH 366/417] NVMe: Simplify device reset failure A reset failure schedules the device to unbind from the driver through the pci driver's remove. This cleans up all intialization, so there is no need to duplicate the potentially racy cleanup. To help understand why a reset failed, the status is logged with the existing warning message. Signed-off-by: Keith Busch Reviewed-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/pci.c | 48 ++++++++++++++++++----------------------- 1 file changed, 21 insertions(+), 27 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 122f803f0efb..6d2e4257308b 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -86,7 +86,6 @@ struct nvme_queue; static int nvme_reset(struct nvme_dev *dev); static void nvme_process_cq(struct nvme_queue *nvmeq); -static void nvme_remove_dead_ctrl(struct nvme_dev *dev); static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown); /* @@ -1897,10 +1896,19 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl) kfree(dev); } +static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status) +{ + dev_warn(dev->dev, "Removing after probe failure status: %d\n", status); + + kref_get(&dev->ctrl.kref); + if (!schedule_work(&dev->remove_work)) + nvme_put_ctrl(&dev->ctrl); +} + static void nvme_reset_work(struct work_struct *work) { struct nvme_dev *dev = container_of(work, struct nvme_dev, reset_work); - int result; + int result = -ENODEV; if (WARN_ON(test_bit(NVME_CTRL_RESETTING, &dev->flags))) goto out; @@ -1920,26 +1928,26 @@ static void nvme_reset_work(struct work_struct *work) result = nvme_configure_admin_queue(dev); if (result) - goto unmap; + goto out; nvme_init_queue(dev->queues[0], 0); result = nvme_alloc_admin_tags(dev); if (result) - goto disable; + goto out; result = nvme_init_identify(&dev->ctrl); if (result) - goto free_tags; + goto out; result = nvme_setup_io_queues(dev); if (result) - goto free_tags; + goto out; dev->ctrl.event_limit = NVME_NR_AEN_COMMANDS; result = nvme_dev_list_add(dev); if (result) - goto remove; + goto out; /* * Keep the controller around but remove all namespaces if we don't have @@ -1956,19 +1964,8 @@ static void nvme_reset_work(struct work_struct *work) clear_bit(NVME_CTRL_RESETTING, &dev->flags); return; - remove: - nvme_dev_list_remove(dev); - free_tags: - nvme_dev_remove_admin(dev); - blk_put_queue(dev->ctrl.admin_q); - dev->ctrl.admin_q = NULL; - dev->queues[0]->tags = NULL; - disable: - nvme_disable_admin_queue(dev, false); - unmap: - nvme_dev_unmap(dev); out: - nvme_remove_dead_ctrl(dev); + nvme_remove_dead_ctrl(dev, result); } static void nvme_remove_dead_ctrl_work(struct work_struct *work) @@ -1981,14 +1978,6 @@ static void nvme_remove_dead_ctrl_work(struct work_struct *work) nvme_put_ctrl(&dev->ctrl); } -static void nvme_remove_dead_ctrl(struct nvme_dev *dev) -{ - dev_warn(dev->dev, "Removing after probe failure\n"); - kref_get(&dev->ctrl.kref); - if (!schedule_work(&dev->remove_work)) - nvme_put_ctrl(&dev->ctrl); -} - static int nvme_reset(struct nvme_dev *dev) { if (!dev->ctrl.admin_q || blk_queue_dying(dev->ctrl.admin_q)) @@ -2136,6 +2125,11 @@ static void nvme_shutdown(struct pci_dev *pdev) nvme_dev_disable(dev, true); } +/* + * The driver's remove may be called on a device in a partially initialized + * state. This function must not have any dependencies on the device state in + * order to proceed. + */ static void nvme_remove(struct pci_dev *pdev) { struct nvme_dev *dev = pci_get_drvdata(pdev); From 69d9a99c258eb1d6478fd9608a2070890797eed7 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 24 Feb 2016 09:15:56 -0700 Subject: [PATCH 367/417] NVMe: Move error handling to failed reset handler This moves failed queue handling out of the namespace removal path and into the reset failure path, fixing a hanging condition if the controller fails or link down during del_gendisk. Previously the driver had to see the controller as degraded prior to calling del_gendisk to setup the queues to fail. But, if the controller happened to fail after this, there was no task to end outstanding requests. On failure, all namespace states are set to dead. This has capacity revalidate to 0, and ends all new requests with error status. Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 53 +++++++++++++++++++++++++++------------- drivers/nvme/host/nvme.h | 2 ++ drivers/nvme/host/pci.c | 13 +++++++++- 3 files changed, 50 insertions(+), 18 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 8c2ddd5025ab..7fd5a7ac8375 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -557,6 +557,10 @@ static int nvme_revalidate_disk(struct gendisk *disk) u16 old_ms; unsigned short bs; + if (test_bit(NVME_NS_DEAD, &ns->flags)) { + set_capacity(disk, 0); + return -ENODEV; + } if (nvme_identify_ns(ns->ctrl, ns->ns_id, &id)) { dev_warn(ns->ctrl->dev, "%s: Identify failure nvme%dn%d\n", __func__, ns->ctrl->instance, ns->ns_id); @@ -1186,32 +1190,15 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) static void nvme_ns_remove(struct nvme_ns *ns) { - bool kill; - if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags)) return; - kill = nvme_io_incapable(ns->ctrl) && - !blk_queue_dying(ns->queue); - if (kill) { - blk_set_queue_dying(ns->queue); - - /* - * The controller was shutdown first if we got here through - * device removal. The shutdown may requeue outstanding - * requests. These need to be aborted immediately so - * del_gendisk doesn't block indefinitely for their completion. - */ - blk_mq_abort_requeue_list(ns->queue); - } if (ns->disk->flags & GENHD_FL_UP) { if (blk_get_integrity(ns->disk)) blk_integrity_unregister(ns->disk); sysfs_remove_group(&disk_to_dev(ns->disk)->kobj, &nvme_ns_attr_group); del_gendisk(ns->disk); - } - if (kill || !blk_queue_dying(ns->queue)) { blk_mq_abort_requeue_list(ns->queue); blk_cleanup_queue(ns->queue); } @@ -1413,6 +1400,38 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, return ret; } +/** + * nvme_kill_queues(): Ends all namespace queues + * @ctrl: the dead controller that needs to end + * + * Call this function when the driver determines it is unable to get the + * controller in a state capable of servicing IO. + */ +void nvme_kill_queues(struct nvme_ctrl *ctrl) +{ + struct nvme_ns *ns; + + mutex_lock(&ctrl->namespaces_mutex); + list_for_each_entry(ns, &ctrl->namespaces, list) { + if (!kref_get_unless_zero(&ns->kref)) + continue; + + /* + * Revalidating a dead namespace sets capacity to 0. This will + * end buffered writers dirtying pages that can't be synced. + */ + if (!test_and_set_bit(NVME_NS_DEAD, &ns->flags)) + revalidate_disk(ns->disk); + + blk_set_queue_dying(ns->queue); + blk_mq_abort_requeue_list(ns->queue); + blk_mq_start_stopped_hw_queues(ns->queue, true); + + nvme_put_ns(ns); + } + mutex_unlock(&ctrl->namespaces_mutex); +} + void nvme_stop_queues(struct nvme_ctrl *ctrl) { struct nvme_ns *ns; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 4075fa9e0c34..fb15ba5f5d19 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -117,6 +117,7 @@ struct nvme_ns { unsigned long flags; #define NVME_NS_REMOVING 0 +#define NVME_NS_DEAD 1 u64 mode_select_num_blocks; u32 mode_select_block_len; @@ -246,6 +247,7 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl); void nvme_stop_queues(struct nvme_ctrl *ctrl); void nvme_start_queues(struct nvme_ctrl *ctrl); +void nvme_kill_queues(struct nvme_ctrl *ctrl); struct request *nvme_alloc_request(struct request_queue *q, struct nvme_command *cmd, unsigned int flags); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 6d2e4257308b..680f5780750c 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -690,7 +690,10 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx, spin_lock_irq(&nvmeq->q_lock); if (unlikely(nvmeq->cq_vector < 0)) { - ret = BLK_MQ_RQ_QUEUE_BUSY; + if (ns && !test_bit(NVME_NS_DEAD, &ns->flags)) + ret = BLK_MQ_RQ_QUEUE_BUSY; + else + ret = BLK_MQ_RQ_QUEUE_ERROR; spin_unlock_irq(&nvmeq->q_lock); goto out; } @@ -1261,6 +1264,12 @@ static struct blk_mq_ops nvme_mq_ops = { static void nvme_dev_remove_admin(struct nvme_dev *dev) { if (dev->ctrl.admin_q && !blk_queue_dying(dev->ctrl.admin_q)) { + /* + * If the controller was reset during removal, it's possible + * user requests may be waiting on a stopped queue. Start the + * queue to flush these to completion. + */ + blk_mq_start_stopped_hw_queues(dev->ctrl.admin_q, true); blk_cleanup_queue(dev->ctrl.admin_q); blk_mq_free_tag_set(&dev->admin_tagset); } @@ -1901,6 +1910,7 @@ static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status) dev_warn(dev->dev, "Removing after probe failure status: %d\n", status); kref_get(&dev->ctrl.kref); + nvme_dev_disable(dev, false); if (!schedule_work(&dev->remove_work)) nvme_put_ctrl(&dev->ctrl); } @@ -1973,6 +1983,7 @@ static void nvme_remove_dead_ctrl_work(struct work_struct *work) struct nvme_dev *dev = container_of(work, struct nvme_dev, remove_work); struct pci_dev *pdev = to_pci_dev(dev->dev); + nvme_kill_queues(&dev->ctrl); if (pci_get_drvdata(pdev)) pci_stop_and_remove_bus_device_locked(pdev); nvme_put_ctrl(&dev->ctrl); From 63088ec7c8eadfe08b96127a41b385ec9742dace Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 24 Feb 2016 09:15:57 -0700 Subject: [PATCH 368/417] NVMe: Don't allow unsupported flags The command flags can change the meaning of other fields in the command that the driver is not prepared to handle. Specifically, the user could passthrough an SGL flag, causing the controller to misinterpret the PRP list the driver created, potentially corrupting memory or data. Signed-off-by: Keith Busch Reviewed-by: Jon Derrick Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 7fd5a7ac8375..ba1501514128 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -374,6 +374,8 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) if (copy_from_user(&io, uio, sizeof(io))) return -EFAULT; + if (io.flags) + return -EINVAL; switch (io.opcode) { case nvme_cmd_write: @@ -425,6 +427,8 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, return -EACCES; if (copy_from_user(&cmd, ucmd, sizeof(cmd))) return -EFAULT; + if (cmd.flags) + return -EINVAL; memset(&c, 0, sizeof(c)); c.common.opcode = cmd.opcode; From e9fc63d682dbbef17921aeb00d03fd52d6735ffd Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 24 Feb 2016 09:15:58 -0700 Subject: [PATCH 369/417] NVMe: Fix 0-length integrity payload A user could send a passthrough IO command with a metadata pointer to a namespace without metadata. With metadata length of 0, kmalloc returns ZERO_SIZE_PTR. Since that is not NULL, the driver would have set this as the bio's integrity payload, which causes an access fault on completion. This patch ignores the users metadata buffer if the namespace format does not support separate metadata. Reported-by: Stephen Bates Signed-off-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index ba1501514128..470d4f373841 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -184,7 +184,7 @@ int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd, goto out_unmap; } - if (meta_buffer) { + if (meta_buffer && meta_len) { struct bio_integrity_payload *bip; meta = kmalloc(meta_len, GFP_KERNEL); From a1a0e23e49037c23ea84bc8cc146a03584d13577 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 29 Feb 2016 18:28:53 -0500 Subject: [PATCH 370/417] writeback: flush inode cgroup wb switches instead of pinning super_block If cgroup writeback is in use, inodes can be scheduled for asynchronous wb switching. Before 5ff8eaac1636 ("writeback: keep superblock pinned during cgroup writeback association switches"), this could race with umount leading to super_block being destroyed while inodes are pinned for wb switching. 5ff8eaac1636 fixed it by bumping s_active while wb switches are in flight; however, this allowed in-flight wb switches to make umounts asynchronous when the userland expected synchronosity - e.g. fsck immediately following umount may fail because the device is still busy. This patch removes the problematic super_block pinning and instead makes generic_shutdown_super() flush in-flight wb switches. wb switches are now executed on a dedicated isw_wq so that they can be flushed and isw_nr_in_flight keeps track of the number of in-flight wb switches so that flushing can be avoided in most cases. v2: Move cgroup_writeback_umount() further below and add MS_ACTIVE check in inode_switch_wbs() as Jan an Al suggested. Signed-off-by: Tejun Heo Reported-by: Tahsin Erdogan Cc: Jan Kara Cc: Al Viro Link: http://lkml.kernel.org/g/CAAeU0aNCq7LGODvVGRU-oU_o-6enii5ey0p1c26D1ZzYwkDc5A@mail.gmail.com Fixes: 5ff8eaac1636 ("writeback: keep superblock pinned during cgroup writeback association switches") Cc: stable@vger.kernel.org #v4.5 Reviewed-by: Jan Kara Tested-by: Tahsin Erdogan Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 54 +++++++++++++++++++++++++++++---------- fs/super.c | 1 + include/linux/writeback.h | 5 ++++ 3 files changed, 47 insertions(+), 13 deletions(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 1f76d8950a57..5c46ed9f3e14 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -223,6 +223,9 @@ static void wb_wait_for_completion(struct backing_dev_info *bdi, #define WB_FRN_HIST_MAX_SLOTS (WB_FRN_HIST_THR_SLOTS / 2 + 1) /* one round can affect upto 5 slots */ +static atomic_t isw_nr_in_flight = ATOMIC_INIT(0); +static struct workqueue_struct *isw_wq; + void __inode_attach_wb(struct inode *inode, struct page *page) { struct backing_dev_info *bdi = inode_to_bdi(inode); @@ -317,7 +320,6 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) struct inode_switch_wbs_context *isw = container_of(work, struct inode_switch_wbs_context, work); struct inode *inode = isw->inode; - struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; struct bdi_writeback *old_wb = inode->i_wb; struct bdi_writeback *new_wb = isw->new_wb; @@ -424,8 +426,9 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) wb_put(new_wb); iput(inode); - deactivate_super(sb); kfree(isw); + + atomic_dec(&isw_nr_in_flight); } static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head) @@ -435,7 +438,7 @@ static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head) /* needs to grab bh-unsafe locks, bounce to work item */ INIT_WORK(&isw->work, inode_switch_wbs_work_fn); - schedule_work(&isw->work); + queue_work(isw_wq, &isw->work); } /** @@ -471,20 +474,20 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); - - if (inode->i_state & (I_WB_SWITCH | I_FREEING) || - inode_to_wb(inode) == isw->new_wb) - goto out_unlock; - - if (!atomic_inc_not_zero(&inode->i_sb->s_active)) - goto out_unlock; - + if (!(inode->i_sb->s_flags & MS_ACTIVE) || + inode->i_state & (I_WB_SWITCH | I_FREEING) || + inode_to_wb(inode) == isw->new_wb) { + spin_unlock(&inode->i_lock); + goto out_free; + } inode->i_state |= I_WB_SWITCH; spin_unlock(&inode->i_lock); ihold(inode); isw->inode = inode; + atomic_inc(&isw_nr_in_flight); + /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the mapping's @@ -494,8 +497,6 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn); return; -out_unlock: - spin_unlock(&inode->i_lock); out_free: if (isw->new_wb) wb_put(isw->new_wb); @@ -847,6 +848,33 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, wb_put(last_wb); } +/** + * cgroup_writeback_umount - flush inode wb switches for umount + * + * This function is called when a super_block is about to be destroyed and + * flushes in-flight inode wb switches. An inode wb switch goes through + * RCU and then workqueue, so the two need to be flushed in order to ensure + * that all previously scheduled switches are finished. As wb switches are + * rare occurrences and synchronize_rcu() can take a while, perform + * flushing iff wb switches are in flight. + */ +void cgroup_writeback_umount(void) +{ + if (atomic_read(&isw_nr_in_flight)) { + synchronize_rcu(); + flush_workqueue(isw_wq); + } +} + +static int __init cgroup_writeback_init(void) +{ + isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0); + if (!isw_wq) + return -ENOMEM; + return 0; +} +fs_initcall(cgroup_writeback_init); + #else /* CONFIG_CGROUP_WRITEBACK */ static struct bdi_writeback * diff --git a/fs/super.c b/fs/super.c index 1182af8fd5ff..74914b1bae70 100644 --- a/fs/super.c +++ b/fs/super.c @@ -415,6 +415,7 @@ void generic_shutdown_super(struct super_block *sb) sb->s_flags &= ~MS_ACTIVE; fsnotify_unmount_inodes(sb); + cgroup_writeback_umount(); evict_inodes(sb); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index b333c945e571..d0b5ca5d4e08 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -198,6 +198,7 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc, void wbc_detach_inode(struct writeback_control *wbc); void wbc_account_io(struct writeback_control *wbc, struct page *page, size_t bytes); +void cgroup_writeback_umount(void); /** * inode_attach_wb - associate an inode with its wb @@ -301,6 +302,10 @@ static inline void wbc_account_io(struct writeback_control *wbc, { } +static inline void cgroup_writeback_umount(void) +{ +} + #endif /* CONFIG_CGROUP_WRITEBACK */ /* From da35825d9a091a7a1d5824c8468168e2658333ff Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 2 Mar 2016 18:07:11 +0100 Subject: [PATCH 371/417] nvme: set queue limits for the admin queue Factor out a helper to set all the device specific queue limits and apply them to the admin queue in addition to the I/O queues. Without this the command size on the admin queue is arbitrarily low, and the missing other limitations are just minefields waiting for victims. Signed-off-by: Christoph Hellwig Reported-by: Jeff Lien Tested-by: Jeff Lien Reviewed-by: Keith Busch Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 29 +++++++++++++++++++---------- 1 file changed, 19 insertions(+), 10 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 470d4f373841..cfee6ac399a3 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -840,6 +840,21 @@ int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl) return ret; } +static void nvme_set_queue_limits(struct nvme_ctrl *ctrl, + struct request_queue *q) +{ + if (ctrl->max_hw_sectors) { + blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors); + blk_queue_max_segments(q, + (ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1); + } + if (ctrl->stripe_size) + blk_queue_chunk_sectors(q, ctrl->stripe_size >> 9); + if (ctrl->vwc & NVME_CTRL_VWC_PRESENT) + blk_queue_flush(q, REQ_FLUSH | REQ_FUA); + blk_queue_virt_boundary(q, ctrl->page_size - 1); +} + /* * Initialize the cached copies of the Identify data and various controller * register in our nvme_ctrl structure. This should be called as soon as @@ -897,6 +912,8 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) } } + nvme_set_queue_limits(ctrl, ctrl->admin_q); + kfree(id); return 0; } @@ -1147,17 +1164,9 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) ns->disk = disk; ns->lba_shift = 9; /* set to a default value for 512 until disk is validated */ + blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift); - if (ctrl->max_hw_sectors) { - blk_queue_max_hw_sectors(ns->queue, ctrl->max_hw_sectors); - blk_queue_max_segments(ns->queue, - (ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1); - } - if (ctrl->stripe_size) - blk_queue_chunk_sectors(ns->queue, ctrl->stripe_size >> 9); - if (ctrl->vwc & NVME_CTRL_VWC_PRESENT) - blk_queue_flush(ns->queue, REQ_FLUSH | REQ_FUA); - blk_queue_virt_boundary(ns->queue, ctrl->page_size - 1); + nvme_set_queue_limits(ctrl, ns->queue); disk->major = nvme_major; disk->first_minor = 0; From 45686b6198bd824f083ff5293f191d78db9d708a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 2 Mar 2016 18:07:12 +0100 Subject: [PATCH 372/417] nvme: fix max_segments integer truncation The block layer uses an unsigned short for max_segments. The way we calculate the value for NVMe tends to generate very large 32-bit values, which after integer truncation may lead to a zero value instead of the desired outcome. Signed-off-by: Christoph Hellwig Reported-by: Jeff Lien Tested-by: Jeff Lien Reviewed-by: Keith Busch Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index cfee6ac399a3..03c46412fff4 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -844,9 +844,11 @@ static void nvme_set_queue_limits(struct nvme_ctrl *ctrl, struct request_queue *q) { if (ctrl->max_hw_sectors) { + u32 max_segments = + (ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1; + blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors); - blk_queue_max_segments(q, - (ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1); + blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX)); } if (ctrl->stripe_size) blk_queue_chunk_sectors(q, ctrl->stripe_size >> 9); From f21018427cb007a0894c36ad702990ab639cbbb4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 3 Mar 2016 14:43:45 -0700 Subject: [PATCH 373/417] block: fix blk_rq_get_max_sectors for driver private requests Driver private request types should not get the artifical cap for the FS requests. This is important to use the full device capabilities for internal command or NVMe pass through commands. Signed-off-by: Christoph Hellwig Reported-by: Jeff Lien Tested-by: Jeff Lien Reviewed-by: Keith Busch Updated by me to use an explicit check for the one command type that does support extended checking, instead of relying on the ordering of the enum command values - as suggested by Keith. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d7f6bca707ef..413c84fbc4ed 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -895,7 +895,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq) { struct request_queue *q = rq->q; - if (unlikely(rq->cmd_type == REQ_TYPE_BLOCK_PC)) + if (unlikely(rq->cmd_type != REQ_TYPE_FS)) return q->limits.max_hw_sectors; if (!q->limits.chunk_sectors || (rq->cmd_flags & REQ_DISCARD)) From 4d6af73d9e43f78651a43ee4c5ad221107ac8365 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 2 Mar 2016 18:07:14 +0100 Subject: [PATCH 374/417] block: support large requests in blk_rq_map_user_iov This patch adds support for larger requests in blk_rq_map_user_iov by allowing it to build multiple bios for a request. This functionality used to exist for the non-vectored blk_rq_map_user in the past, and this patch reuses the existing functionality for it on the unmap side, which stuck around. Thanks to the iov_iter API supporting multiple bios is fairly trivial, as we can just iterate the iov until we've consumed the whole iov_iter. Signed-off-by: Christoph Hellwig Reported-by: Jeff Lien Tested-by: Jeff Lien Reviewed-by: Keith Busch Signed-off-by: Jens Axboe --- block/blk-map.c | 91 +++++++++++++++++++++++++++++++++---------------- 1 file changed, 61 insertions(+), 30 deletions(-) diff --git a/block/blk-map.c b/block/blk-map.c index f565e11f465a..a54f0543b956 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -57,6 +57,49 @@ static int __blk_rq_unmap_user(struct bio *bio) return ret; } +static int __blk_rq_map_user_iov(struct request *rq, + struct rq_map_data *map_data, struct iov_iter *iter, + gfp_t gfp_mask, bool copy) +{ + struct request_queue *q = rq->q; + struct bio *bio, *orig_bio; + int ret; + + if (copy) + bio = bio_copy_user_iov(q, map_data, iter, gfp_mask); + else + bio = bio_map_user_iov(q, iter, gfp_mask); + + if (IS_ERR(bio)) + return PTR_ERR(bio); + + if (map_data && map_data->null_mapped) + bio_set_flag(bio, BIO_NULL_MAPPED); + + iov_iter_advance(iter, bio->bi_iter.bi_size); + if (map_data) + map_data->offset += bio->bi_iter.bi_size; + + orig_bio = bio; + blk_queue_bounce(q, &bio); + + /* + * We link the bounce buffer in and could have to traverse it + * later so we have to get a ref to prevent it from being freed + */ + bio_get(bio); + + ret = blk_rq_append_bio(q, rq, bio); + if (ret) { + bio_endio(bio); + __blk_rq_unmap_user(orig_bio); + bio_put(bio); + return ret; + } + + return 0; +} + /** * blk_rq_map_user_iov - map user data to a request, for REQ_TYPE_BLOCK_PC usage * @q: request queue where request should be inserted @@ -82,10 +125,11 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, struct rq_map_data *map_data, const struct iov_iter *iter, gfp_t gfp_mask) { - struct bio *bio; - int unaligned = 0; - struct iov_iter i; struct iovec iov, prv = {.iov_base = NULL, .iov_len = 0}; + bool copy = (q->dma_pad_mask & iter->count) || map_data; + struct bio *bio = NULL; + struct iov_iter i; + int ret; if (!iter || !iter->count) return -EINVAL; @@ -101,42 +145,29 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, */ if ((uaddr & queue_dma_alignment(q)) || iovec_gap_to_prv(q, &prv, &iov)) - unaligned = 1; + copy = true; prv.iov_base = iov.iov_base; prv.iov_len = iov.iov_len; } - if (unaligned || (q->dma_pad_mask & iter->count) || map_data) - bio = bio_copy_user_iov(q, map_data, iter, gfp_mask); - else - bio = bio_map_user_iov(q, iter, gfp_mask); - - if (IS_ERR(bio)) - return PTR_ERR(bio); - - if (map_data && map_data->null_mapped) - bio_set_flag(bio, BIO_NULL_MAPPED); - - if (bio->bi_iter.bi_size != iter->count) { - /* - * Grab an extra reference to this bio, as bio_unmap_user() - * expects to be able to drop it twice as it happens on the - * normal IO completion path - */ - bio_get(bio); - bio_endio(bio); - __blk_rq_unmap_user(bio); - return -EINVAL; - } + i = *iter; + do { + ret =__blk_rq_map_user_iov(rq, map_data, &i, gfp_mask, copy); + if (ret) + goto unmap_rq; + if (!bio) + bio = rq->bio; + } while (iov_iter_count(&i)); if (!bio_flagged(bio, BIO_USER_MAPPED)) rq->cmd_flags |= REQ_COPY_USER; - - blk_queue_bounce(q, &bio); - bio_get(bio); - blk_rq_bio_prep(q, rq, bio); return 0; + +unmap_rq: + __blk_rq_unmap_user(bio); + rq->bio = NULL; + return -EINVAL; } EXPORT_SYMBOL(blk_rq_map_user_iov); From 4024fcf70556311521e7b6cf79fa50e16f31013a Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 2 Mar 2016 02:32:08 +0100 Subject: [PATCH 375/417] vxlan: fix missing options_len update on RX with collect metadata When signalling to metadata consumers that the metadata_dst entry carries additional GBP extension data for vxlan (TUNNEL_VXLAN_OPT), the dst's vxlan_metadata information is populated, but options_len is left to zero. F.e. in ovs, ovs_flow_key_extract() checks for options_len before extracting the data through ip_tunnel_info_opts_get(). Geneve uses ip_tunnel_info_opts_set() helper in receive path, which sets options_len internally, vxlan however uses ip_tunnel_info_opts(), so when filling vxlan_metadata, we do need to update options_len. Fixes: 4c22279848c5 ("ip-tunnel: Use API to access tunnel metadata options.") Signed-off-by: Daniel Borkmann Acked-by: Thomas Graf Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index b601139a145a..1c32bd104797 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1308,8 +1308,10 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) gbp = (struct vxlanhdr_gbp *)vxh; md->gbp = ntohs(gbp->policy_id); - if (tun_dst) + if (tun_dst) { tun_dst->u.tun_info.key.tun_flags |= TUNNEL_VXLAN_OPT; + tun_dst->u.tun_info.options_len = sizeof(*md); + } if (gbp->dont_learn) md->gbp |= VXLAN_GBP_DONT_LEARN; From 63a0a00b90b5193173bcf76ef24afdda8eb05d3a Mon Sep 17 00:00:00 2001 From: Nimrod Andy Date: Wed, 2 Mar 2016 17:24:53 +0800 Subject: [PATCH 376/417] MAINTAINERS: add maintainer entry for FREESCALE FEC ethernet driver Add a maintainer entry for FREESCALE FEC ethernet driver and add myself as a maintainer. Signed-off-by: Fugang Duan Acked-by: Frank Li Signed-off-by: David S. Miller --- MAINTAINERS | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index e6b14f2ead18..bcda6232cc98 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4542,6 +4542,15 @@ S: Maintained F: drivers/net/ethernet/freescale/fs_enet/ F: include/linux/fs_enet_pd.h +FREESCALE IMX / MXC FEC DRIVER +M: Fugang Duan +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/ethernet/freescale/fec_main.c +F: drivers/net/ethernet/freescale/fec_ptp.c +F: drivers/net/ethernet/freescale/fec.h +F: Documentation/devicetree/bindings/net/fsl-fec.txt + FREESCALE QUICC ENGINE LIBRARY L: linuxppc-dev@lists.ozlabs.org S: Orphan From 1d3cd1773fddfdc9ffb0c2dec9a954c7a54bc207 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 2 Mar 2016 13:11:10 +0300 Subject: [PATCH 377/417] net: moxa: fix an error code We accidentally return IS_ERR(priv->base) which is 1 instead of PTR_ERR(priv->base) which is the error code. Fixes: 6c821bd9edc9 ('net: Add MOXA ART SoCs ethernet driver') Signed-off-by: Dan Carpenter Acked-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/moxa/moxart_ether.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index 00cfd95ca59d..3e67f451f2ab 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -474,9 +474,9 @@ static int moxart_mac_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); ndev->base_addr = res->start; priv->base = devm_ioremap_resource(p_dev, res); - ret = IS_ERR(priv->base); - if (ret) { + if (IS_ERR(priv->base)) { dev_err(p_dev, "devm_ioremap_resource failed\n"); + ret = PTR_ERR(priv->base); goto init_fail; } From c1bb0a5588816ec26abc08aa9adcf90e32656781 Mon Sep 17 00:00:00 2001 From: Venkat Duvvuru Date: Wed, 2 Mar 2016 06:00:28 -0500 Subject: [PATCH 378/417] be2net: don't enable multicast flag in be_enable_if_filters() routine When the interface is opened (in be_open()) the routine be_enable_if_filters() must be called to switch on the basic filtering capabilities of an interface that are not changed at run-time. These include the flags UNTAGGED, BROADCAST and PASS_L3L4_ERRORS. Other flags such as MULTICAST and PROMISC must be enabled later by be_set_rx_mode() based on the state in the netdev/adapter struct. be_enable_if_filters() routine is wrongly trying to enable MULTICAST flag without checking the current adapter state. This can cause the RX_FILTER cmds to the FW to fail. This patch fixes this problem by only enabling the basic filtering flags in be_enable_if_filters(). The VF must be able to issue RX_FILTER cmd with any filter flag, as long as the PF allowed those flags (if_cap_flags) in the iface it provisioned for the VF. This rule is applicable even when the VF doesn't have the FILTMGMT privilege. There is a bug in BE3 FW that wrongly fails RX_FILTER multicast programming cmds on VFs that don't have FILTMGMT privilege. This patch also helps in insulating the VF driver from be_open failures due to the FW bug. A fix for the BE3 FW issue will be available in versions >= 11.0.283.0 and 10.6.334.0 Reported-by: Ivan Vecera Signed-off-by: Venkat Duvvuru Signed-off-by: Sathya Perla Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be_cmds.h | 9 ++++++--- drivers/net/ethernet/emulex/benet/be_main.c | 16 +++++++++------- 2 files changed, 15 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index 241819b36ca7..6d9a8d78e8ad 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -622,10 +622,13 @@ enum be_if_flags { BE_IF_FLAGS_VLAN_PROMISCUOUS |\ BE_IF_FLAGS_MCAST_PROMISCUOUS) -#define BE_IF_EN_FLAGS (BE_IF_FLAGS_BROADCAST | BE_IF_FLAGS_PASS_L3L4_ERRORS |\ - BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_UNTAGGED) +#define BE_IF_FILT_FLAGS_BASIC (BE_IF_FLAGS_BROADCAST | \ + BE_IF_FLAGS_PASS_L3L4_ERRORS | \ + BE_IF_FLAGS_UNTAGGED) -#define BE_IF_ALL_FILT_FLAGS (BE_IF_EN_FLAGS | BE_IF_FLAGS_ALL_PROMISCUOUS) +#define BE_IF_ALL_FILT_FLAGS (BE_IF_FILT_FLAGS_BASIC | \ + BE_IF_FLAGS_MULTICAST | \ + BE_IF_FLAGS_ALL_PROMISCUOUS) /* An RX interface is an object with one or more MAC addresses and * filtering capabilities. */ diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index f99de3657ce3..db81e3d9623f 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -125,6 +125,11 @@ static const char * const ue_status_hi_desc[] = { "Unknown" }; +#define BE_VF_IF_EN_FLAGS (BE_IF_FLAGS_UNTAGGED | \ + BE_IF_FLAGS_BROADCAST | \ + BE_IF_FLAGS_MULTICAST | \ + BE_IF_FLAGS_PASS_L3L4_ERRORS) + static void be_queue_free(struct be_adapter *adapter, struct be_queue_info *q) { struct be_dma_mem *mem = &q->dma_mem; @@ -3537,7 +3542,7 @@ static int be_enable_if_filters(struct be_adapter *adapter) { int status; - status = be_cmd_rx_filter(adapter, BE_IF_EN_FLAGS, ON); + status = be_cmd_rx_filter(adapter, BE_IF_FILT_FLAGS_BASIC, ON); if (status) return status; @@ -3857,8 +3862,7 @@ static int be_vfs_if_create(struct be_adapter *adapter) int status; /* If a FW profile exists, then cap_flags are updated */ - cap_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST | - BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_PASS_L3L4_ERRORS; + cap_flags = BE_VF_IF_EN_FLAGS; for_all_vfs(adapter, vf_cfg, vf) { if (!BE3_chip(adapter)) { @@ -3874,10 +3878,8 @@ static int be_vfs_if_create(struct be_adapter *adapter) } } - en_flags = cap_flags & (BE_IF_FLAGS_UNTAGGED | - BE_IF_FLAGS_BROADCAST | - BE_IF_FLAGS_MULTICAST | - BE_IF_FLAGS_PASS_L3L4_ERRORS); + /* PF should enable IF flags during proxy if_create call */ + en_flags = cap_flags & BE_VF_IF_EN_FLAGS; status = be_cmd_if_create(adapter, cap_flags, en_flags, &vf_cfg->if_handle, vf + 1); if (status) From 909c3a22da3b8d2cfd3505ca5658f0176859d400 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 2 Mar 2016 15:49:38 +0000 Subject: [PATCH 379/417] Btrfs: fix loading of orphan roots leading to BUG_ON When looking for orphan roots during mount we can end up hitting a BUG_ON() (at root-item.c:btrfs_find_orphan_roots()) if a log tree is replayed and qgroups are enabled. This is because after a log tree is replayed, a transaction commit is made, which triggers qgroup extent accounting which in turn does backref walking which ends up reading and inserting all roots in the radix tree fs_info->fs_root_radix, including orphan roots (deleted snapshots). So after the log tree is replayed, when finding orphan roots we hit the BUG_ON with the following trace: [118209.182438] ------------[ cut here ]------------ [118209.183279] kernel BUG at fs/btrfs/root-tree.c:314! [118209.184074] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC [118209.185123] Modules linked in: btrfs dm_flakey dm_mod crc32c_generic ppdev xor raid6_pq evdev sg parport_pc parport acpi_cpufreq tpm_tis tpm psmouse processor i2c_piix4 serio_raw pcspkr i2c_core button loop autofs4 ext4 crc16 mbcache jbd2 sd_mod sr_mod cdrom ata_generic virtio_scsi ata_piix libata virtio_pci virtio_ring virtio scsi_mod e1000 floppy [last unloaded: btrfs] [118209.186318] CPU: 14 PID: 28428 Comm: mount Tainted: G W 4.5.0-rc5-btrfs-next-24+ #1 [118209.186318] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS by qemu-project.org 04/01/2014 [118209.186318] task: ffff8801ec131040 ti: ffff8800af34c000 task.ti: ffff8800af34c000 [118209.186318] RIP: 0010:[] [] btrfs_find_orphan_roots+0x1fc/0x244 [btrfs] [118209.186318] RSP: 0018:ffff8800af34faa8 EFLAGS: 00010246 [118209.186318] RAX: 00000000ffffffef RBX: 00000000ffffffef RCX: 0000000000000001 [118209.186318] RDX: 0000000080000000 RSI: 0000000000000001 RDI: 00000000ffffffff [118209.186318] RBP: ffff8800af34fb08 R08: 0000000000000001 R09: 0000000000000000 [118209.186318] R10: ffff8800af34f9f0 R11: 6db6db6db6db6db7 R12: ffff880171b97000 [118209.186318] R13: ffff8801ca9d65e0 R14: ffff8800afa2e000 R15: 0000160000000000 [118209.186318] FS: 00007f5bcb914840(0000) GS:ffff88023edc0000(0000) knlGS:0000000000000000 [118209.186318] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [118209.186318] CR2: 00007f5bcaceb5d9 CR3: 00000000b49b5000 CR4: 00000000000006e0 [118209.186318] Stack: [118209.186318] fffffbffffffffff 010230ffffffffff 0101000000000000 ff84000000000000 [118209.186318] fbffffffffffffff 30ffffffffffffff 0000000000000101 ffff880082348000 [118209.186318] 0000000000000000 ffff8800afa2e000 ffff8800afa2e000 0000000000000000 [118209.186318] Call Trace: [118209.186318] [] open_ctree+0x1e37/0x21b9 [btrfs] [118209.186318] [] btrfs_mount+0x97e/0xaed [btrfs] [118209.186318] [] ? trace_hardirqs_on+0xd/0xf [118209.186318] [] mount_fs+0x67/0x131 [118209.186318] [] vfs_kern_mount+0x6c/0xde [118209.186318] [] btrfs_mount+0x1ac/0xaed [btrfs] [118209.186318] [] ? trace_hardirqs_on+0xd/0xf [118209.186318] [] ? lockdep_init_map+0xb9/0x1b3 [118209.186318] [] mount_fs+0x67/0x131 [118209.186318] [] vfs_kern_mount+0x6c/0xde [118209.186318] [] do_mount+0x8a6/0x9e8 [118209.186318] [] SyS_mount+0x77/0x9f [118209.186318] [] entry_SYSCALL_64_fastpath+0x12/0x6b [118209.186318] Code: 64 00 00 85 c0 89 c3 75 24 f0 41 80 4c 24 20 20 49 8b bc 24 f0 01 00 00 4c 89 e6 e8 e8 65 00 00 85 c0 89 c3 74 11 83 f8 ef 75 02 <0f> 0b 4c 89 e7 e8 da 72 00 00 eb 1c 41 83 bc 24 00 01 00 00 00 [118209.186318] RIP [] btrfs_find_orphan_roots+0x1fc/0x244 [btrfs] [118209.186318] RSP [118209.230735] ---[ end trace 83938f987d85d477 ]--- So fix this by not treating the error -EEXIST, returned when attempting to insert a root already inserted by the backref walking code, as an error. The following test case for xfstests reproduces the bug: seq=`basename $0` seqres=$RESULT_DIR/$seq echo "QA output created by $seq" tmp=/tmp/$$ status=1 # failure is the default! trap "_cleanup; exit \$status" 0 1 2 3 15 _cleanup() { _cleanup_flakey cd / rm -f $tmp.* } # get standard environment, filters and checks . ./common/rc . ./common/filter . ./common/dmflakey # real QA test starts here _supported_fs btrfs _supported_os Linux _require_scratch _require_dm_target flakey _require_metadata_journaling $SCRATCH_DEV rm -f $seqres.full _scratch_mkfs >>$seqres.full 2>&1 _init_flakey _mount_flakey _run_btrfs_util_prog quota enable $SCRATCH_MNT # Create 2 directories with one file in one of them. # We use these just to trigger a transaction commit later, moving the file from # directory a to directory b and doing an fsync against directory a. mkdir $SCRATCH_MNT/a mkdir $SCRATCH_MNT/b touch $SCRATCH_MNT/a/f sync # Create our test file with 2 4K extents. $XFS_IO_PROG -f -s -c "pwrite -S 0xaa 0 8K" $SCRATCH_MNT/foobar | _filter_xfs_io # Create a snapshot and delete it. This doesn't really delete the snapshot # immediately, just makes it inaccessible and invisible to user space, the # snapshot is deleted later by a dedicated kernel thread (cleaner kthread) # which is woke up at the next transaction commit. # A root orphan item is inserted into the tree of tree roots, so that if a # power failure happens before the dedicated kernel thread does the snapshot # deletion, the next time the filesystem is mounted it resumes the snapshot # deletion. _run_btrfs_util_prog subvolume snapshot $SCRATCH_MNT $SCRATCH_MNT/snap _run_btrfs_util_prog subvolume delete $SCRATCH_MNT/snap # Now overwrite half of the extents we wrote before. Because we made a snapshpot # before, which isn't really deleted yet (since no transaction commit happened # after we did the snapshot delete request), the non overwritten extents get # referenced twice, once by the default subvolume and once by the snapshot. $XFS_IO_PROG -c "pwrite -S 0xbb 4K 8K" $SCRATCH_MNT/foobar | _filter_xfs_io # Now move file f from directory a to directory b and fsync directory a. # The fsync on the directory a triggers a transaction commit (because a file # was moved from it to another directory) and the file fsync leaves a log tree # with file extent items to replay. mv $SCRATCH_MNT/a/f $SCRATCH_MNT/a/b $XFS_IO_PROG -c "fsync" $SCRATCH_MNT/a $XFS_IO_PROG -c "fsync" $SCRATCH_MNT/foobar echo "File digest before power failure:" md5sum $SCRATCH_MNT/foobar | _filter_scratch # Now simulate a power failure and mount the filesystem to replay the log tree. # After the log tree was replayed, we used to hit a BUG_ON() when processing # the root orphan item for the deleted snapshot. This is because when processing # an orphan root the code expected to be the first code inserting the root into # the fs_info->fs_root_radix radix tree, while in reallity it was the second # caller attempting to do it - the first caller was the transaction commit that # took place after replaying the log tree, when updating the qgroup counters. _flakey_drop_and_remount echo "File digest before after failure:" # Must match what he got before the power failure. md5sum $SCRATCH_MNT/foobar | _filter_scratch _unmount_flakey status=0 exit Fixes: 2d9e97761087 ("Btrfs: use btrfs_get_fs_root in resolve_indirect_ref") Cc: stable@vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana Reviewed-by: Qu Wenruo Signed-off-by: Chris Mason --- fs/btrfs/root-tree.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 7cf8509deda7..2c849b08a91b 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -310,8 +310,16 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state); err = btrfs_insert_fs_root(root->fs_info, root); + /* + * The root might have been inserted already, as before we look + * for orphan roots, log replay might have happened, which + * triggers a transaction commit and qgroup accounting, which + * in turn reads and inserts fs roots while doing backref + * walking. + */ + if (err == -EEXIST) + err = 0; if (err) { - BUG_ON(err == -EEXIST); btrfs_free_fs_root(root); break; } From 37c5e942bb2eedd98c1cd1fa1f94d79f6b830c38 Mon Sep 17 00:00:00 2001 From: Scott Wood Date: Wed, 2 Mar 2016 22:51:04 -0600 Subject: [PATCH 380/417] powerpc/fsl-book3e: Avoid lbarx on e5500 lbarx/stbcx. are implemented on e6500, but not on e5500. Likewise, SMT is on e6500, but not on e5500. So, avoid executing an unimplemented instruction by only locking when needed (i.e. in the presence of SMT). Signed-off-by: Scott Wood --- arch/powerpc/mm/hugetlbpage-book3e.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/arch/powerpc/mm/hugetlbpage-book3e.c b/arch/powerpc/mm/hugetlbpage-book3e.c index 7e6d0880813f..83a8be791e06 100644 --- a/arch/powerpc/mm/hugetlbpage-book3e.c +++ b/arch/powerpc/mm/hugetlbpage-book3e.c @@ -8,6 +8,8 @@ #include #include +#include + #ifdef CONFIG_PPC_FSL_BOOK3E #ifdef CONFIG_PPC64 static inline int tlb1_next(void) @@ -60,6 +62,14 @@ static inline void book3e_tlb_lock(void) unsigned long tmp; int token = smp_processor_id() + 1; + /* + * Besides being unnecessary in the absence of SMT, this + * check prevents trying to do lbarx/stbcx. on e5500 which + * doesn't implement either feature. + */ + if (!cpu_has_feature(CPU_FTR_SMT)) + return; + asm volatile("1: lbarx %0, 0, %1;" "cmpwi %0, 0;" "bne 2f;" @@ -80,6 +90,9 @@ static inline void book3e_tlb_unlock(void) { struct paca_struct *paca = get_paca(); + if (!cpu_has_feature(CPU_FTR_SMT)) + return; + isync(); paca->tcd_ptr->lock = 0; } From ec75a940b1037e877efd9a5a9e94eab1e464f73b Mon Sep 17 00:00:00 2001 From: Libin Yang Date: Fri, 4 Mar 2016 14:33:06 +0800 Subject: [PATCH 381/417] ALSA: hda - hdmi add wmb barrier for audio component To make sure audio_ptr is set before intel_audio_codec_enable() or intel_audio_codec_disable() calling pin_eld_notify(), this patch adds wmb barrier to prevent optimizing. Signed-off-by: Libin Yang Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_hdmi.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 8ee78dbd4c60..6858e88c7326 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -2480,6 +2480,11 @@ static int patch_generic_hdmi(struct hda_codec *codec) if (codec_has_acomp(codec)) { codec->depop_delay = 0; spec->i915_audio_ops.audio_ptr = codec; + /* intel_audio_codec_enable() or intel_audio_codec_disable() + * will call pin_eld_notify with using audio_ptr pointer + * We need make sure audio_ptr is really setup + */ + wmb(); spec->i915_audio_ops.pin_eld_notify = intel_pin_eld_notify; snd_hdac_i915_register_notifier(&spec->i915_audio_ops); } From 790b415c98de62602810b0eedce26f0f9d6ddd78 Mon Sep 17 00:00:00 2001 From: Libin Yang Date: Fri, 4 Mar 2016 14:33:43 +0800 Subject: [PATCH 382/417] ALSA: hda - hdmi defer to register acomp eld notifier Defer to register acomp eld notifier until hdmi audio driver is fully ready. After registering eld notifier, gfx driver can use this callback function to notify audio driver the monitor connection event. However this action may happen when audio driver is adding the pins or doing other initialization. This is not always safe, however. For example, using per_pin->lock before the lock is initialized. Let's register the eld notifier after the initialization is done. Signed-off-by: Libin Yang Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_hdmi.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 6858e88c7326..bcbc4ee10130 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -2477,18 +2477,6 @@ static int patch_generic_hdmi(struct hda_codec *codec) is_broxton(codec)) codec->core.link_power_control = 1; - if (codec_has_acomp(codec)) { - codec->depop_delay = 0; - spec->i915_audio_ops.audio_ptr = codec; - /* intel_audio_codec_enable() or intel_audio_codec_disable() - * will call pin_eld_notify with using audio_ptr pointer - * We need make sure audio_ptr is really setup - */ - wmb(); - spec->i915_audio_ops.pin_eld_notify = intel_pin_eld_notify; - snd_hdac_i915_register_notifier(&spec->i915_audio_ops); - } - if (hdmi_parse_codec(codec) < 0) { if (spec->i915_bound) snd_hdac_i915_exit(&codec->bus->core); @@ -2510,6 +2498,18 @@ static int patch_generic_hdmi(struct hda_codec *codec) init_channel_allocations(); + if (codec_has_acomp(codec)) { + codec->depop_delay = 0; + spec->i915_audio_ops.audio_ptr = codec; + /* intel_audio_codec_enable() or intel_audio_codec_disable() + * will call pin_eld_notify with using audio_ptr pointer + * We need make sure audio_ptr is really setup + */ + wmb(); + spec->i915_audio_ops.pin_eld_notify = intel_pin_eld_notify; + snd_hdac_i915_register_notifier(&spec->i915_audio_ops); + } + return 0; } From d694b06c42a56c9610861ee0474b4d441af8ada6 Mon Sep 17 00:00:00 2001 From: Ed Spiridonov Date: Fri, 4 Mar 2016 09:07:27 +0300 Subject: [PATCH 383/417] can: mcp251x: avoid write to error flag register if it's unnecessary Only two bits (RX0OVR and RX1OVR) are writable in EFLG, write is useless if these bits aren't set. Signed-off-by: Ed Spiridonov Signed-off-by: Marc Kleine-Budde --- drivers/net/can/spi/mcp251x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index 575790e8a75a..74a7dfecee27 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -843,7 +843,7 @@ static irqreturn_t mcp251x_can_ist(int irq, void *dev_id) if (clear_intf) mcp251x_write_bits(spi, CANINTF, clear_intf, 0x00); - if (eflag) + if (eflag & (EFLG_RX0OVR | EFLG_RX1OVR)) mcp251x_write_bits(spi, EFLG, eflag, 0x00); /* Update can state */ From e57cbaf0eb006eaa207395f3bfd7ce52c1b5539c Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Thu, 3 Mar 2016 17:18:20 -0500 Subject: [PATCH 384/417] tracing: Do not have 'comm' filter override event 'comm' field Commit 9f61668073a8d "tracing: Allow triggers to filter for CPU ids and process names" added a 'comm' filter that will filter events based on the current tasks struct 'comm'. But this now hides the ability to filter events that have a 'comm' field too. For example, sched_migrate_task trace event. That has a 'comm' field of the task to be migrated. echo 'comm == "bash"' > events/sched_migrate_task/filter will now filter all sched_migrate_task events for tasks named "bash" that migrates other tasks (in interrupt context), instead of seeing when "bash" itself gets migrated. This fix requires a couple of changes. 1) Change the look up order for filter predicates to look at the events fields before looking at the generic filters. 2) Instead of basing the filter function off of the "comm" name, have the generic "comm" filter have its own filter_type (FILTER_COMM). Test against the type instead of the name to assign the filter function. 3) Add a new "COMM" filter that works just like "comm" but will filter based on the current task, even if the trace event contains a "comm" field. Do the same for "cpu" field, adding a FILTER_CPU and a filter "CPU". Cc: stable@vger.kernel.org # v4.3+ Fixes: 9f61668073a8d "tracing: Allow triggers to filter for CPU ids and process names" Reported-by: Matt Fleming Signed-off-by: Steven Rostedt --- include/linux/trace_events.h | 2 ++ kernel/trace/trace_events.c | 18 ++++++++++-------- kernel/trace/trace_events_filter.c | 13 +++++++------ 3 files changed, 19 insertions(+), 14 deletions(-) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 429fdfc3baf5..925730bc9fc1 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -568,6 +568,8 @@ enum { FILTER_DYN_STRING, FILTER_PTR_STRING, FILTER_TRACE_FN, + FILTER_COMM, + FILTER_CPU, }; extern int trace_event_raw_init(struct trace_event_call *call); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index ab09829d3b97..05ddc0820771 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -97,16 +97,16 @@ trace_find_event_field(struct trace_event_call *call, char *name) struct ftrace_event_field *field; struct list_head *head; + head = trace_get_fields(call); + field = __find_event_field(head, name); + if (field) + return field; + field = __find_event_field(&ftrace_generic_fields, name); if (field) return field; - field = __find_event_field(&ftrace_common_fields, name); - if (field) - return field; - - head = trace_get_fields(call); - return __find_event_field(head, name); + return __find_event_field(&ftrace_common_fields, name); } static int __trace_define_field(struct list_head *head, const char *type, @@ -171,8 +171,10 @@ static int trace_define_generic_fields(void) { int ret; - __generic_field(int, cpu, FILTER_OTHER); - __generic_field(char *, comm, FILTER_PTR_STRING); + __generic_field(int, CPU, FILTER_CPU); + __generic_field(int, cpu, FILTER_CPU); + __generic_field(char *, COMM, FILTER_COMM); + __generic_field(char *, comm, FILTER_COMM); return ret; } diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index f93a219b18da..6816302542b2 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1043,13 +1043,14 @@ static int init_pred(struct filter_parse_state *ps, return -EINVAL; } - if (is_string_field(field)) { + if (field->filter_type == FILTER_COMM) { + filter_build_regex(pred); + fn = filter_pred_comm; + pred->regex.field_len = TASK_COMM_LEN; + } else if (is_string_field(field)) { filter_build_regex(pred); - if (!strcmp(field->name, "comm")) { - fn = filter_pred_comm; - pred->regex.field_len = TASK_COMM_LEN; - } else if (field->filter_type == FILTER_STATIC_STRING) { + if (field->filter_type == FILTER_STATIC_STRING) { fn = filter_pred_string; pred->regex.field_len = field->size; } else if (field->filter_type == FILTER_DYN_STRING) @@ -1072,7 +1073,7 @@ static int init_pred(struct filter_parse_state *ps, } pred->val = val; - if (!strcmp(field->name, "cpu")) + if (field->filter_type == FILTER_CPU) fn = filter_pred_cpu; else fn = select_comparison_fn(pred->op, field->size, From 097452e61366a939a4772332181cea7cdcc74760 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Fri, 26 Feb 2016 18:06:52 +0900 Subject: [PATCH 385/417] gpu: host1x: Set DMA mask The default DMA mask covers a 32 bits address range, but host1x devices can address a larger range on TK1 and TX1. Set the DMA mask to the range addressable when we use the IOMMU to prevent the use of bounce buffers. Signed-off-by: Alexandre Courbot Signed-off-by: Thierry Reding --- drivers/gpu/host1x/dev.c | 7 +++++++ drivers/gpu/host1x/dev.h | 1 + 2 files changed, 8 insertions(+) diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index 314bf3718cc7..ff348690df94 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -23,6 +23,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -68,6 +69,7 @@ static const struct host1x_info host1x01_info = { .nb_bases = 8, .init = host1x01_init, .sync_offset = 0x3000, + .dma_mask = DMA_BIT_MASK(32), }; static const struct host1x_info host1x02_info = { @@ -77,6 +79,7 @@ static const struct host1x_info host1x02_info = { .nb_bases = 12, .init = host1x02_init, .sync_offset = 0x3000, + .dma_mask = DMA_BIT_MASK(32), }; static const struct host1x_info host1x04_info = { @@ -86,6 +89,7 @@ static const struct host1x_info host1x04_info = { .nb_bases = 64, .init = host1x04_init, .sync_offset = 0x2100, + .dma_mask = DMA_BIT_MASK(34), }; static const struct host1x_info host1x05_info = { @@ -95,6 +99,7 @@ static const struct host1x_info host1x05_info = { .nb_bases = 64, .init = host1x05_init, .sync_offset = 0x2100, + .dma_mask = DMA_BIT_MASK(34), }; static struct of_device_id host1x_of_match[] = { @@ -148,6 +153,8 @@ static int host1x_probe(struct platform_device *pdev) if (IS_ERR(host->regs)) return PTR_ERR(host->regs); + dma_set_mask_and_coherent(host->dev, host->info->dma_mask); + if (host->info->init) { err = host->info->init(host); if (err) diff --git a/drivers/gpu/host1x/dev.h b/drivers/gpu/host1x/dev.h index 0b6e8e9629c5..dace124994bb 100644 --- a/drivers/gpu/host1x/dev.h +++ b/drivers/gpu/host1x/dev.h @@ -96,6 +96,7 @@ struct host1x_info { int nb_mlocks; /* host1x: number of mlocks */ int (*init)(struct host1x *); /* initialize per SoC ops */ int sync_offset; + u64 dma_mask; /* mask of addressable memory */ }; struct host1x { From c95469aa5a188384ccf8ac520ece931c66caf8aa Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Fri, 26 Feb 2016 18:06:53 +0900 Subject: [PATCH 386/417] gpu: host1x: Set DMA ops on device creation Currently host1x-instanciated devices have their dma_ops left to NULL, which makes any DMA operation (like buffer import) on ARM64 fallback to the dummy_dma_ops and fail with an error. This patch calls of_dma_configure() with the host1x node when creating such a device, so the proper DMA operations are set. Suggested-by: Thierry Reding Signed-off-by: Alexandre Courbot Signed-off-by: Thierry Reding --- drivers/gpu/host1x/bus.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c index da462afcb225..dd2dbb9746ce 100644 --- a/drivers/gpu/host1x/bus.c +++ b/drivers/gpu/host1x/bus.c @@ -18,6 +18,7 @@ #include #include #include +#include #include "bus.h" #include "dev.h" @@ -394,6 +395,7 @@ static int host1x_device_add(struct host1x *host1x, device->dev.coherent_dma_mask = host1x->dev->coherent_dma_mask; device->dev.dma_mask = &device->dev.coherent_dma_mask; dev_set_name(&device->dev, "%s", driver->driver.name); + of_dma_configure(&device->dev, host1x->dev->of_node); device->dev.release = host1x_device_release; device->dev.bus = &host1x_bus_type; device->dev.parent = host1x->dev; From 5ea5c5e0a7f70b256417d3b6e36bd9851504babd Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Sun, 14 Feb 2016 18:06:41 +0800 Subject: [PATCH 387/417] ceph: initial CEPH_FEATURE_FS_FILE_LAYOUT_V2 support Add support for the format change of MClientReply/MclientCaps. Also add code that denies access to inodes with pool_ns layouts. Signed-off-by: Yan, Zheng Reviewed-by: Sage Weil --- fs/ceph/addr.c | 4 ++++ fs/ceph/caps.c | 27 ++++++++++++++++++++++++--- fs/ceph/inode.c | 2 ++ fs/ceph/mds_client.c | 16 ++++++++++++++++ fs/ceph/mds_client.h | 1 + fs/ceph/super.h | 1 + include/linux/ceph/ceph_features.h | 1 + 7 files changed, 49 insertions(+), 3 deletions(-) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index c22213789090..19adeb0ef82a 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1756,6 +1756,10 @@ int ceph_pool_perm_check(struct ceph_inode_info *ci, int need) u32 pool; int ret, flags; + /* does not support pool namespace yet */ + if (ci->i_pool_ns_len) + return -EIO; + if (ceph_test_mount_opt(ceph_inode_to_client(&ci->vfs_inode), NOPOOLPERM)) return 0; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index cdbf8cf3d52c..6fe0ad26a7df 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2753,7 +2753,8 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc, void *inline_data, int inline_len, struct ceph_buffer *xattr_buf, struct ceph_mds_session *session, - struct ceph_cap *cap, int issued) + struct ceph_cap *cap, int issued, + u32 pool_ns_len) __releases(ci->i_ceph_lock) __releases(mdsc->snap_rwsem) { @@ -2873,6 +2874,8 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc, if (newcaps & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR)) { /* file layout may have changed */ ci->i_layout = grant->layout; + ci->i_pool_ns_len = pool_ns_len; + /* size/truncate_seq? */ queue_trunc = ceph_fill_file_size(inode, issued, le32_to_cpu(grant->truncate_seq), @@ -3411,6 +3414,7 @@ void ceph_handle_caps(struct ceph_mds_session *session, u32 inline_len = 0; void *snaptrace; size_t snaptrace_len; + u32 pool_ns_len = 0; void *p, *end; dout("handle_caps from mds%d\n", mds); @@ -3463,6 +3467,21 @@ void ceph_handle_caps(struct ceph_mds_session *session, p += inline_len; } + if (le16_to_cpu(msg->hdr.version) >= 8) { + u64 flush_tid; + u32 caller_uid, caller_gid; + u32 osd_epoch_barrier; + /* version >= 5 */ + ceph_decode_32_safe(&p, end, osd_epoch_barrier, bad); + /* version >= 6 */ + ceph_decode_64_safe(&p, end, flush_tid, bad); + /* version >= 7 */ + ceph_decode_32_safe(&p, end, caller_uid, bad); + ceph_decode_32_safe(&p, end, caller_gid, bad); + /* version >= 8 */ + ceph_decode_32_safe(&p, end, pool_ns_len, bad); + } + /* lookup ino */ inode = ceph_find_inode(sb, vino); ci = ceph_inode(inode); @@ -3518,7 +3537,8 @@ void ceph_handle_caps(struct ceph_mds_session *session, &cap, &issued); handle_cap_grant(mdsc, inode, h, inline_version, inline_data, inline_len, - msg->middle, session, cap, issued); + msg->middle, session, cap, issued, + pool_ns_len); if (realm) ceph_put_snap_realm(mdsc, realm); goto done_unlocked; @@ -3542,7 +3562,8 @@ void ceph_handle_caps(struct ceph_mds_session *session, issued |= __ceph_caps_dirty(ci); handle_cap_grant(mdsc, inode, h, inline_version, inline_data, inline_len, - msg->middle, session, cap, issued); + msg->middle, session, cap, issued, + pool_ns_len); goto done_unlocked; case CEPH_CAP_OP_FLUSH_ACK: diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index fb4ba2e4e2a5..5849b88bbed3 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -396,6 +396,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb) ci->i_symlink = NULL; memset(&ci->i_dir_layout, 0, sizeof(ci->i_dir_layout)); + ci->i_pool_ns_len = 0; ci->i_fragtree = RB_ROOT; mutex_init(&ci->i_fragtree_mutex); @@ -756,6 +757,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page, if (ci->i_layout.fl_pg_pool != info->layout.fl_pg_pool) ci->i_ceph_flags &= ~CEPH_I_POOL_PERM; ci->i_layout = info->layout; + ci->i_pool_ns_len = iinfo->pool_ns_len; queue_trunc = ceph_fill_file_size(inode, issued, le32_to_cpu(info->truncate_seq), diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index e7b130a637f9..911d64d865f1 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -100,6 +100,14 @@ static int parse_reply_info_in(void **p, void *end, } else info->inline_version = CEPH_INLINE_NONE; + if (features & CEPH_FEATURE_FS_FILE_LAYOUT_V2) { + ceph_decode_32_safe(p, end, info->pool_ns_len, bad); + ceph_decode_need(p, end, info->pool_ns_len, bad); + *p += info->pool_ns_len; + } else { + info->pool_ns_len = 0; + } + return 0; bad: return err; @@ -2298,6 +2306,14 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc, ceph_get_cap_refs(ceph_inode(req->r_old_dentry_dir), CEPH_CAP_PIN); + /* deny access to directories with pool_ns layouts */ + if (req->r_inode && S_ISDIR(req->r_inode->i_mode) && + ceph_inode(req->r_inode)->i_pool_ns_len) + return -EIO; + if (req->r_locked_dir && + ceph_inode(req->r_locked_dir)->i_pool_ns_len) + return -EIO; + /* issue */ mutex_lock(&mdsc->mutex); __register_request(mdsc, req, dir); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index ccf11ef0ca87..37712ccffcc6 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -44,6 +44,7 @@ struct ceph_mds_reply_info_in { u64 inline_version; u32 inline_len; char *inline_data; + u32 pool_ns_len; }; /* diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 75b7d125ce66..9c458eb52245 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -287,6 +287,7 @@ struct ceph_inode_info { struct ceph_dir_layout i_dir_layout; struct ceph_file_layout i_layout; + size_t i_pool_ns_len; char *i_symlink; /* for dirs */ diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index c1ef6f14e7be..15151f3c4120 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -75,6 +75,7 @@ #define CEPH_FEATURE_CRUSH_TUNABLES5 (1ULL<<58) /* chooseleaf stable mode */ // duplicated since it was introduced at the same time as CEPH_FEATURE_CRUSH_TUNABLES5 #define CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING (1ULL<<58) /* New, v7 encoding */ +#define CEPH_FEATURE_FS_FILE_LAYOUT_V2 (1ULL<<58) /* file_layout_t */ /* * The introduction of CEPH_FEATURE_OSD_SNAPMAPPER caused the feature From e723e3f7f9591b79e8c56b3d7c5a204a9c571b55 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Fri, 4 Mar 2016 01:42:49 +0000 Subject: [PATCH 388/417] MIPS: traps: Fix SIGFPE information leak from `do_ov' and `do_trap_or_bp' Avoid sending a partially initialised `siginfo_t' structure along SIGFPE signals issued from `do_ov' and `do_trap_or_bp', leading to information leaking from the kernel stack. Signed-off-by: Maciej W. Rozycki Cc: stable@vger.kernel.org Signed-off-by: Ralf Baechle --- arch/mips/kernel/traps.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index ae790c575d4f..bf14da9f3e33 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -690,15 +690,15 @@ static int simulate_sync(struct pt_regs *regs, unsigned int opcode) asmlinkage void do_ov(struct pt_regs *regs) { enum ctx_state prev_state; - siginfo_t info; + siginfo_t info = { + .si_signo = SIGFPE, + .si_code = FPE_INTOVF, + .si_addr = (void __user *)regs->cp0_epc, + }; prev_state = exception_enter(); die_if_kernel("Integer overflow", regs); - info.si_code = FPE_INTOVF; - info.si_signo = SIGFPE; - info.si_errno = 0; - info.si_addr = (void __user *) regs->cp0_epc; force_sig_info(SIGFPE, &info, current); exception_exit(prev_state); } @@ -874,7 +874,7 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31) void do_trap_or_bp(struct pt_regs *regs, unsigned int code, const char *str) { - siginfo_t info; + siginfo_t info = { 0 }; char b[40]; #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP @@ -903,7 +903,6 @@ void do_trap_or_bp(struct pt_regs *regs, unsigned int code, else info.si_code = FPE_INTOVF; info.si_signo = SIGFPE; - info.si_errno = 0; info.si_addr = (void __user *) regs->cp0_epc; force_sig_info(SIGFPE, &info, current); break; From f474c8c857d996f34c39f66bbed23faaa739fad6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Mika=20Penttil=C3=A4?= Date: Mon, 22 Feb 2016 17:56:52 +0100 Subject: [PATCH 389/417] ARM: 8544/1: set_memory_xx fixes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Allow zero size updates. This makes set_memory_xx() consistent with x86, s390 and arm64 and makes apply_to_page_range() not to BUG() when loading modules. Signed-off-by: Mika Penttilä mika.penttila@nextfour.com Signed-off-by: Russell King --- arch/arm/mm/pageattr.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm/mm/pageattr.c b/arch/arm/mm/pageattr.c index cf30daff8932..d19b1ad29b07 100644 --- a/arch/arm/mm/pageattr.c +++ b/arch/arm/mm/pageattr.c @@ -49,6 +49,9 @@ static int change_memory_common(unsigned long addr, int numpages, WARN_ON_ONCE(1); } + if (!numpages) + return 0; + if (start < MODULES_VADDR || start >= MODULES_END) return -EINVAL; From 6e2452dff4441e3dc24d415c8b2cda8a3ba52116 Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Thu, 3 Mar 2016 15:39:41 -0700 Subject: [PATCH 390/417] nfit: Continue init even if ARS commands are unimplemented If firmware doesn't implement any of the ARS commands, take that to mean that ARS is unsupported, and continue to initialize regions without bad block lists. We cannot make the assumption that ARS commands will be unconditionally supported on all NVDIMMs. Reported-by: Haozhong Zhang Signed-off-by: Vishal Verma Acked-by: Xiao Guangrong Tested-by: Haozhong Zhang Signed-off-by: Dan Williams --- drivers/acpi/nfit.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index fb53db187854..35947ac87644 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -1590,14 +1590,21 @@ static int acpi_nfit_find_poison(struct acpi_nfit_desc *acpi_desc, start = ndr_desc->res->start; len = ndr_desc->res->end - ndr_desc->res->start + 1; + /* + * If ARS is unimplemented, unsupported, or if the 'Persistent Memory + * Scrub' flag in extended status is not set, skip this but continue + * initialization + */ rc = ars_get_cap(nd_desc, ars_cap, start, len); + if (rc == -ENOTTY) { + dev_dbg(acpi_desc->dev, + "Address Range Scrub is not implemented, won't create an error list\n"); + rc = 0; + goto out; + } if (rc) goto out; - /* - * If ARS is unsupported, or if the 'Persistent Memory Scrub' flag in - * extended status is not set, skip this but continue initialization - */ if ((ars_cap->status & 0xffff) || !(ars_cap->status >> 16 & ND_ARS_PERSISTENT)) { dev_warn(acpi_desc->dev, From e4f6daac20332448529b11f09388f1d55ef2084c Mon Sep 17 00:00:00 2001 From: Richard Weinberger Date: Sun, 21 Feb 2016 10:53:03 +0100 Subject: [PATCH 391/417] ubi: Fix out of bounds write in volume update code ubi_start_leb_change() allocates too few bytes. ubi_more_leb_change_data() will write up to req->upd_bytes + ubi->min_io_size bytes. Cc: stable@vger.kernel.org Signed-off-by: Richard Weinberger Reviewed-by: Boris Brezillon --- drivers/mtd/ubi/upd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/ubi/upd.c b/drivers/mtd/ubi/upd.c index 2a1b6e037e1a..0134ba32a057 100644 --- a/drivers/mtd/ubi/upd.c +++ b/drivers/mtd/ubi/upd.c @@ -193,7 +193,7 @@ int ubi_start_leb_change(struct ubi_device *ubi, struct ubi_volume *vol, vol->changing_leb = 1; vol->ch_lnum = req->lnum; - vol->upd_buf = vmalloc(req->bytes); + vol->upd_buf = vmalloc(ALIGN((int)req->bytes, ubi->min_io_size)); if (!vol->upd_buf) return -ENOMEM; From 322740efbb7ca26df845161e61cc41484b7e328e Mon Sep 17 00:00:00 2001 From: Richard Weinberger Date: Mon, 25 Jan 2016 23:33:30 +0100 Subject: [PATCH 392/417] Revert "um: Fix get_signal() usage" Commit db2f24dc240856fb1d78005307f1523b7b3c121b was plain wrong. I did not realize the we are allowed to loop here. In fact we have to loop and must not return to userspace before all SIGSEGVs have been delivered. Other archs do this directly in their entry code, UML does it here. Reported-by: Al Viro Signed-off-by: Richard Weinberger --- arch/um/kernel/signal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c index fc8be0e3a4ff..57acbd67d85d 100644 --- a/arch/um/kernel/signal.c +++ b/arch/um/kernel/signal.c @@ -69,7 +69,7 @@ void do_signal(struct pt_regs *regs) struct ksignal ksig; int handled_sig = 0; - if (get_signal(&ksig)) { + while (get_signal(&ksig)) { handled_sig = 1; /* Whee! Actually deliver the signal. */ handle_signal(&ksig, regs); From 0834f9cc9f1c5a104e87000378b9cda290c4f406 Mon Sep 17 00:00:00 2001 From: Richard Weinberger Date: Mon, 25 Jan 2016 23:24:21 +0100 Subject: [PATCH 393/417] um: Export pm_power_off ...modules are using this symbol. Export it like all other archs to. Signed-off-by: Richard Weinberger --- arch/um/kernel/reboot.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/um/kernel/reboot.c b/arch/um/kernel/reboot.c index 9bdf67a092a5..b60a9f8cda75 100644 --- a/arch/um/kernel/reboot.c +++ b/arch/um/kernel/reboot.c @@ -12,6 +12,7 @@ #include void (*pm_power_off)(void); +EXPORT_SYMBOL(pm_power_off); static void kill_off_processes(void) { From ad32a1f3c36b046b2e7b0361b88c18e3af61419e Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Sat, 23 Jan 2016 19:17:59 +0000 Subject: [PATCH 394/417] um: use %lx format specifiers for unsigned longs static analysis from cppcheck detected %x being used for unsigned longs: [arch/x86/um/os-Linux/task_size.c:112]: (warning) %x in format string (no. 1) requires 'unsigned int' but the argument type is 'unsigned long'. Use %lx instead of %x Signed-off-by: Colin Ian King Signed-off-by: Richard Weinberger --- arch/x86/um/os-Linux/task_size.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/um/os-Linux/task_size.c b/arch/x86/um/os-Linux/task_size.c index 8502ad30e61b..5adb6a2fd117 100644 --- a/arch/x86/um/os-Linux/task_size.c +++ b/arch/x86/um/os-Linux/task_size.c @@ -109,7 +109,7 @@ unsigned long os_get_top_address(void) exit(1); } - printf("0x%x\n", bottom << UM_KERN_PAGE_SHIFT); + printf("0x%lx\n", bottom << UM_KERN_PAGE_SHIFT); printf("Locating the top of the address space ... "); fflush(stdout); @@ -134,7 +134,7 @@ unsigned long os_get_top_address(void) exit(1); } top <<= UM_KERN_PAGE_SHIFT; - printf("0x%x\n", top); + printf("0x%lx\n", top); return top; } From f6cede5b49e822ebc41a099fe41ab4989f64e2cb Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 6 Mar 2016 14:48:03 -0800 Subject: [PATCH 395/417] Linux 4.5-rc7 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index af6e5f893d56..2d519d2fb3a9 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 5 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Blurry Fish Butt # *DOCUMENTATION* From 7bfc60822d1cd44069f4fdb16f81a66f716bf787 Mon Sep 17 00:00:00 2001 From: Atsushi Nemoto Date: Thu, 3 Mar 2016 09:07:51 +0900 Subject: [PATCH 396/417] gianfar: Enable eTSEC-106 erratum w/a for MPC8548E Rev2 Enable workaround for MPC8548E erratum eTSEC 106, "Excess delays when transmitting TOE=1 large frames". (see commit 53fad77375ce "gianfar: Enable eTSEC-20 erratum w/a for P2020 Rev1") This erratum was fixed in Rev 3.1.x. Signed-off-by: Atsushi Nemoto Acked-by: Claudiu Manoil Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/gianfar.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 2aa7b401cc3b..b9ecf197ad11 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -1111,8 +1111,10 @@ static void __gfar_detect_errata_85xx(struct gfar_private *priv) if ((SVR_SOC_VER(svr) == SVR_8548) && (SVR_REV(svr) == 0x20)) priv->errata |= GFAR_ERRATA_12; + /* P2020/P1010 Rev 1; MPC8548 Rev 2 */ if (((SVR_SOC_VER(svr) == SVR_P2020) && (SVR_REV(svr) < 0x20)) || - ((SVR_SOC_VER(svr) == SVR_P2010) && (SVR_REV(svr) < 0x20))) + ((SVR_SOC_VER(svr) == SVR_P2010) && (SVR_REV(svr) < 0x20)) || + ((SVR_SOC_VER(svr) == SVR_8548) && (SVR_REV(svr) < 0x31))) priv->errata |= GFAR_ERRATA_76; /* aka eTSEC 20 */ } #endif From eb1f420214adf81fd98d9e8df6b60318ef883102 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 3 Mar 2016 13:27:56 +0000 Subject: [PATCH 397/417] asix: do not free array priv->mdio->irq Used to be allocated and required freeing, but now priv->mdio->irq is now a fixed sized array and should no longer be free'd. Issue detected using static analysis with CoverityScan Fixes: e7f4dc3536a400 ("mdio: Move allocation of interrupts into core") Signed-off-by: Colin Ian King Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/usb/ax88172a.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c index 224e7d82de6d..cf77f2dffa69 100644 --- a/drivers/net/usb/ax88172a.c +++ b/drivers/net/usb/ax88172a.c @@ -134,7 +134,6 @@ static void ax88172a_remove_mdio(struct usbnet *dev) netdev_info(dev->net, "deregistering mdio bus %s\n", priv->mdio->id); mdiobus_unregister(priv->mdio); - kfree(priv->mdio->irq); mdiobus_free(priv->mdio); } From 44ef548f4f8bbc739070583f9844ff0cd8fcc6b4 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Thu, 3 Mar 2016 14:34:14 +0100 Subject: [PATCH 398/417] net: sched: fix act_ipt for LOG target Before calling the destroy() or target() callbacks, the family parameter field has to be initialized. Otherwise at least the LOG target will refuse to work and upon removal oops the kernel. Cc: Jamal Hadi Salim Signed-off-by: Phil Sutter Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- net/sched/act_ipt.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index d05869646515..6b70399ab781 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -62,6 +62,7 @@ static void ipt_destroy_target(struct xt_entry_target *t) struct xt_tgdtor_param par = { .target = t->u.kernel.target, .targinfo = t->data, + .family = NFPROTO_IPV4, }; if (par.target->destroy != NULL) par.target->destroy(&par); @@ -195,6 +196,7 @@ static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a, par.hooknum = ipt->tcfi_hook; par.target = ipt->tcfi_t->u.kernel.target; par.targinfo = ipt->tcfi_t->data; + par.family = NFPROTO_IPV4; ret = par.target->target(skb, &par); switch (ret) { From 57a0f3675489181c31636d204fa5c5daf5fa3c83 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 3 Mar 2016 13:43:34 +0000 Subject: [PATCH 399/417] net/ethoc: do not free array priv->mdio->irq priv->mdio->irq used to be allocated and required freeing, but it is now a fixed sized array and should no longer be free'd. Issue detected using static analysis with CoverityScan Fixes: e7f4dc3536a400 ("mdio: Move allocation of interrupts into core") Signed-off-by: Colin Ian King Reviewed-by: Tobias Klauser Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/ethernet/ethoc.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index 62fa136554ac..41b010645100 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -1265,7 +1265,6 @@ static int ethoc_remove(struct platform_device *pdev) if (priv->mdio) { mdiobus_unregister(priv->mdio); - kfree(priv->mdio->irq); mdiobus_free(priv->mdio); } if (priv->clk) From 11f7f79b40ebfbac6a1bcdbc61d5d13d365e744b Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 3 Mar 2016 13:47:18 +0000 Subject: [PATCH 400/417] net: eth: altera: do not free array priv->mdio->irq priv->mdio->irq used to be allocated and required freeing, but it is now a fixed sized array and should no longer be free'd. Issue detected using static analysis with CoverityScan Fixes: e7f4dc3536a400 ("mdio: Move allocation of interrupts into core") Signed-off-by: Colin Ian King Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/ethernet/altera/altera_tse_main.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index 17472851674f..f749e4d389eb 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -193,7 +193,6 @@ static void altera_tse_mdio_destroy(struct net_device *dev) priv->mdio->id); mdiobus_unregister(priv->mdio); - kfree(priv->mdio->irq); mdiobus_free(priv->mdio); priv->mdio = NULL; } From 4de13d7ed6ffdcbb34317acaa9236f121176f5f8 Mon Sep 17 00:00:00 2001 From: Parthasarathy Bhuvaragan Date: Thu, 3 Mar 2016 17:54:54 +0100 Subject: [PATCH 401/417] tipc: fix nullptr crash during subscription cancel commit 4d5cfcba2f6e ('tipc: fix connection abort during subscription cancel'), removes the check for a valid subscription before calling tipc_nametbl_subscribe(). This will lead to a nullptr exception when we process a subscription cancel request. For a cancel request, a null subscription is passed to tipc_nametbl_subscribe() resulting in exception. In this commit, we call tipc_nametbl_subscribe() only for a valid subscription. Fixes: 4d5cfcba2f6e ('tipc: fix connection abort during subscription cancel') Reported-by: Anders Widell Signed-off-by: Parthasarathy Bhuvaragan Acked-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/subscr.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 69ee2eeef968..f9ff73a8d815 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -296,7 +296,8 @@ static void tipc_subscrb_rcv_cb(struct net *net, int conid, if (tipc_subscrp_create(net, (struct tipc_subscr *)buf, subscrb, &sub)) return tipc_conn_terminate(tn->topsrv, subscrb->conid); - tipc_nametbl_subscribe(sub); + if (sub) + tipc_nametbl_subscribe(sub); } /* Handle one request to establish a new subscriber */ From 912b1c89c5043e163f8cfa568512a131976121b2 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Mon, 7 Mar 2016 15:15:29 +0100 Subject: [PATCH 402/417] mlxsw: spectrum: Always decrement bridge's ref count Since we only support one VLAN filtering bridge we need to associate a reference count with it, so that when the last port netdev leaves it, we would know that a different bridge can be offloaded to hardware. When a LAG device is memeber in a bridge and port netdevs are leaving the LAG, we should always decrement the bridge's reference count, as it's incremented for any port in the LAG. Fixes: 4dc236c31733 ("mlxsw: spectrum: Handle port leaving LAG while bridged") Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 09ce451c283b..a94daa8c346c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2358,9 +2358,7 @@ static int mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port, if (mlxsw_sp_port->bridged) { mlxsw_sp_port_active_vlans_del(mlxsw_sp_port); mlxsw_sp_port_bridge_leave(mlxsw_sp_port, false); - - if (lag->ref_count == 1) - mlxsw_sp_master_bridge_dec(mlxsw_sp, NULL); + mlxsw_sp_master_bridge_dec(mlxsw_sp, NULL); } if (lag->ref_count == 1) { From 5091730d7795ccb21eb880699b5194730641c70b Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Mon, 7 Mar 2016 15:15:30 +0100 Subject: [PATCH 403/417] mlxsw: pci: Correctly determine if descriptor queue is full The descriptor queues for sending (SDQs) and receiving (RDQs) packets are managed by two counters - producer and consumer - which are both 16-bit in size. A queue is considered full when the difference between the two equals the queue's maximum number of descriptors. However, if the producer counter overflows, then it's possible for the full queue check to fail, as it doesn't take the overflow into account. In such a case, descriptors already passed to the device - but for which a completion has yet to be posted - will be overwritten, thereby causing undefined behavior. The above can be achieved under heavy load (~30 netperf instances). Fix that by casting the subtraction result to u16, preventing it from being treated as a signed integer. Fixes: eda6500a987a ("mlxsw: Add PCI bus implementation") Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index c071077aafbd..7992c553c1f5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -215,7 +215,7 @@ mlxsw_pci_queue_elem_info_producer_get(struct mlxsw_pci_queue *q) { int index = q->producer_counter & (q->count - 1); - if ((q->producer_counter - q->consumer_counter) == q->count) + if ((u16) (q->producer_counter - q->consumer_counter) == q->count) return NULL; return mlxsw_pci_queue_elem_info_get(q, index); } From 1666984c8625b3db19a9abc298931d35ab7bc64b Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Mon, 7 Mar 2016 11:31:10 +0100 Subject: [PATCH 404/417] usbnet: cleanup after bind() in probe() In case bind() works, but a later error forces bailing in probe() in error cases work and a timer may be scheduled. They must be killed. This fixes an error case related to the double free reported in http://www.spinics.net/lists/netdev/msg367669.html and needs to go on top of Linus' fix to cdc-ncm. Signed-off-by: Oliver Neukum Signed-off-by: David S. Miller --- drivers/net/usb/usbnet.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 0b0ba7ef14e4..10798128c03f 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1769,6 +1769,13 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) if (info->unbind) info->unbind (dev, udev); out1: + /* subdrivers must undo all they did in bind() if they + * fail it, but we may fail later and a deferred kevent + * may trigger an error resubmitting itself and, worse, + * schedule a timer. So we kill it all just in case. + */ + cancel_work_sync(&dev->kevent); + del_timer_sync(&dev->delay); free_netdev(net); out: return status; From 48906f62c96cc2cd35753e59310cb70eb08cc6a5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Thu, 3 Mar 2016 22:20:53 +0100 Subject: [PATCH 405/417] cdc_ncm: toggle altsetting to force reset before setup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some devices will silently fail setup unless they are reset first. This is necessary even if the data interface is already in altsetting 0, which it will be when the device is probed for the first time. Briefly toggling the altsetting forces a function reset regardless of the initial state. This fixes a setup problem observed on a number of Huawei devices, appearing to operate in NTB-32 mode even if we explicitly set them to NTB-16 mode. Signed-off-by: Bjørn Mork Signed-off-by: David S. Miller --- drivers/net/usb/cdc_ncm.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index dc0212c3cc28..be927964375b 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -837,7 +837,11 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ iface_no = ctx->data->cur_altsetting->desc.bInterfaceNumber; - /* reset data interface */ + /* Reset data interface. Some devices will not reset properly + * unless they are configured first. Toggle the altsetting to + * force a reset + */ + usb_set_interface(dev->udev, iface_no, data_altsetting); temp = usb_set_interface(dev->udev, iface_no, 0); if (temp) { dev_dbg(&intf->dev, "set interface failed\n"); From 2c42bf4b43170ee83354bb68a12f8fc84c2e27a9 Mon Sep 17 00:00:00 2001 From: Thomas Falcon Date: Thu, 3 Mar 2016 15:22:36 -0600 Subject: [PATCH 406/417] ibmveth: check return of skb_linearize in ibmveth_start_xmit If skb_linearize fails, the driver should drop the packet instead of trying to copy it into the bounce buffer. Signed-off-by: Thomas Falcon Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmveth.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 335417b4756b..ebe60719e489 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1166,7 +1166,10 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb, if (!firmware_has_feature(FW_FEATURE_CMO)) netdev_err(netdev, "tx: unable to map xmit buffer\n"); adapter->tx_map_failed++; - skb_linearize(skb); + if (skb_linearize(skb)) { + netdev->stats.tx_dropped++; + goto out; + } force_bounce = 1; goto retry_bounce; } From 979d804e5bc926f8f3133715736f26456c910a97 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 4 Mar 2016 10:04:52 +0900 Subject: [PATCH 407/417] net: ethernet: Add missing MFD_SYSCON dependency on HAS_IOMEM The MFD_SYSCON depends on HAS_IOMEM so when selecting it avoid unmet direct dependencies. Signed-off-by: Krzysztof Kozlowski Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig index 74beb1867230..4ccc032633c4 100644 --- a/drivers/net/ethernet/hisilicon/Kconfig +++ b/drivers/net/ethernet/hisilicon/Kconfig @@ -25,6 +25,7 @@ config HIX5HD2_GMAC config HIP04_ETH tristate "HISILICON P04 Ethernet support" + depends on HAS_IOMEM # For MFD_SYSCON select MARVELL_PHY select MFD_SYSCON select HNS_MDIO From cec05562fb1dcdf09ef7b46e1e3eade98e488893 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Fri, 4 Mar 2016 13:40:48 -0500 Subject: [PATCH 408/417] vmxnet3: avoid calling pskb_may_pull with interrupts disabled vmxnet3 has a function vmxnet3_parse_and_copy_hdr which, among other operations, uses pskb_may_pull to linearize the header portion of an skb. That operation eventually uses local_bh_disable/enable to ensure that it doesn't race with the drivers bottom half handler. Unfortunately, vmxnet3 preforms this parse_and_copy operation with a spinlock held and interrupts disabled. This causes us to run afoul of the WARN_ON_ONCE(irqs_disabled()) warning in local_bh_enable, resulting in this: WARNING: at kernel/softirq.c:159 local_bh_enable+0x59/0x90() (Not tainted) Hardware name: VMware Virtual Platform Modules linked in: ipv6 ppdev parport_pc parport microcode e1000 vmware_balloon vmxnet3 i2c_piix4 sg ext4 jbd2 mbcache sd_mod crc_t10dif sr_mod cdrom mptspi mptscsih mptbase scsi_transport_spi pata_acpi ata_generic ata_piix vmwgfx ttm drm_kms_helper drm i2c_core dm_mirror dm_region_hash dm_log dm_mod [last unloaded: mperf] Pid: 6229, comm: sshd Not tainted 2.6.32-616.el6.i686 #1 Call Trace: [] ? warn_slowpath_common+0x89/0xe0 [] ? local_bh_enable+0x59/0x90 [] ? warn_slowpath_null+0x1b/0x20 [] ? local_bh_enable+0x59/0x90 [] ? skb_copy_bits+0x126/0x210 [] ? ext4_ext_find_extent+0x24e/0x2d0 [ext4] [] ? __pskb_pull_tail+0x6e/0x2b0 [] ? vmxnet3_xmit_frame+0xba4/0xef0 [vmxnet3] [] ? selinux_ip_postroute+0x56/0x320 [] ? cfq_add_rq_rb+0x98/0x110 [] ? packet_rcv+0x48/0x350 [] ? dev_queue_xmit_nit+0xc9/0x140 ... Fix it by splitting vmxnet3_parse_and_copy_hdr into two functions: vmxnet3_parse_hdr, which sets up the internal/on stack ctx datastructure, and pulls the skb (both of which can be done without holding the spinlock with irqs disabled and vmxnet3_copy_header, which just copies the skb to the tx ring under the lock safely. tested and shown to correct the described problem. Applies cleanly to the head of the net tree Signed-off-by: Neil Horman CC: Shrikrishna Khare CC: "VMware, Inc." CC: "David S. Miller" Acked-by: Shrikrishna Khare Signed-off-by: David S. Miller --- drivers/net/vmxnet3/vmxnet3_drv.c | 73 +++++++++++++++++++------------ 1 file changed, 46 insertions(+), 27 deletions(-) diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 0cbf520cea77..fc895d0e85d9 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -814,7 +814,7 @@ vmxnet3_tq_init_all(struct vmxnet3_adapter *adapter) /* - * parse and copy relevant protocol headers: + * parse relevant protocol headers: * For a tso pkt, relevant headers are L2/3/4 including options * For a pkt requesting csum offloading, they are L2/3 and may include L4 * if it's a TCP/UDP pkt @@ -827,15 +827,14 @@ vmxnet3_tq_init_all(struct vmxnet3_adapter *adapter) * Other effects: * 1. related *ctx fields are updated. * 2. ctx->copy_size is # of bytes copied - * 3. the portion copied is guaranteed to be in the linear part + * 3. the portion to be copied is guaranteed to be in the linear part * */ static int -vmxnet3_parse_and_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, - struct vmxnet3_tx_ctx *ctx, - struct vmxnet3_adapter *adapter) +vmxnet3_parse_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, + struct vmxnet3_tx_ctx *ctx, + struct vmxnet3_adapter *adapter) { - struct Vmxnet3_TxDataDesc *tdd; u8 protocol = 0; if (ctx->mss) { /* TSO */ @@ -892,16 +891,34 @@ vmxnet3_parse_and_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, return 0; } + return 1; +err: + return -1; +} + +/* + * copy relevant protocol headers to the transmit ring: + * For a tso pkt, relevant headers are L2/3/4 including options + * For a pkt requesting csum offloading, they are L2/3 and may include L4 + * if it's a TCP/UDP pkt + * + * + * Note that this requires that vmxnet3_parse_hdr be called first to set the + * appropriate bits in ctx first + */ +static void +vmxnet3_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, + struct vmxnet3_tx_ctx *ctx, + struct vmxnet3_adapter *adapter) +{ + struct Vmxnet3_TxDataDesc *tdd; + tdd = tq->data_ring.base + tq->tx_ring.next2fill; memcpy(tdd->data, skb->data, ctx->copy_size); netdev_dbg(adapter->netdev, "copy %u bytes to dataRing[%u]\n", ctx->copy_size, tq->tx_ring.next2fill); - return 1; - -err: - return -1; } @@ -998,22 +1015,7 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, } } - spin_lock_irqsave(&tq->tx_lock, flags); - - if (count > vmxnet3_cmd_ring_desc_avail(&tq->tx_ring)) { - tq->stats.tx_ring_full++; - netdev_dbg(adapter->netdev, - "tx queue stopped on %s, next2comp %u" - " next2fill %u\n", adapter->netdev->name, - tq->tx_ring.next2comp, tq->tx_ring.next2fill); - - vmxnet3_tq_stop(tq, adapter); - spin_unlock_irqrestore(&tq->tx_lock, flags); - return NETDEV_TX_BUSY; - } - - - ret = vmxnet3_parse_and_copy_hdr(skb, tq, &ctx, adapter); + ret = vmxnet3_parse_hdr(skb, tq, &ctx, adapter); if (ret >= 0) { BUG_ON(ret <= 0 && ctx.copy_size != 0); /* hdrs parsed, check against other limits */ @@ -1033,9 +1035,26 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, } } else { tq->stats.drop_hdr_inspect_err++; - goto unlock_drop_pkt; + goto drop_pkt; } + spin_lock_irqsave(&tq->tx_lock, flags); + + if (count > vmxnet3_cmd_ring_desc_avail(&tq->tx_ring)) { + tq->stats.tx_ring_full++; + netdev_dbg(adapter->netdev, + "tx queue stopped on %s, next2comp %u" + " next2fill %u\n", adapter->netdev->name, + tq->tx_ring.next2comp, tq->tx_ring.next2fill); + + vmxnet3_tq_stop(tq, adapter); + spin_unlock_irqrestore(&tq->tx_lock, flags); + return NETDEV_TX_BUSY; + } + + + vmxnet3_copy_hdr(skb, tq, &ctx, adapter); + /* fill tx descs related to addr & len */ if (vmxnet3_map_pkt(skb, &ctx, tq, adapter->pdev, adapter)) goto unlock_drop_pkt; From a69bf3c5b49ef488970c74e26ba0ec12f08491c2 Mon Sep 17 00:00:00 2001 From: Douglas Miller Date: Fri, 4 Mar 2016 15:36:56 -0600 Subject: [PATCH 409/417] be2net: Don't leak iomapped memory on removal. The adapter->pcicfg resource is either mapped via pci_iomap() or derived from adapter->db. During be_remove() this resource was ignored and so could remain mapped after remove. Add a flag to track whether adapter->pcicfg was mapped or not, then use that flag in be_unmap_pci_bars() to unmap if required. Fixes: 25848c901 ("use PCI MMIO read instead of config read for errors") Signed-off-by: Douglas Miller Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be.h | 1 + drivers/net/ethernet/emulex/benet/be_main.c | 4 ++++ 2 files changed, 5 insertions(+) diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index cf837831304b..f9751294ece7 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -531,6 +531,7 @@ struct be_adapter { struct delayed_work be_err_detection_work; u8 err_flags; + bool pcicfg_mapped; /* pcicfg obtained via pci_iomap() */ u32 flags; u32 cmd_privileges; /* Ethtool knobs and info */ diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index db81e3d9623f..d1cf1274fc2f 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -4970,6 +4970,8 @@ static void be_unmap_pci_bars(struct be_adapter *adapter) pci_iounmap(adapter->pdev, adapter->csr); if (adapter->db) pci_iounmap(adapter->pdev, adapter->db); + if (adapter->pcicfg && adapter->pcicfg_mapped) + pci_iounmap(adapter->pdev, adapter->pcicfg); } static int db_bar(struct be_adapter *adapter) @@ -5021,8 +5023,10 @@ static int be_map_pci_bars(struct be_adapter *adapter) if (!addr) goto pci_map_err; adapter->pcicfg = addr; + adapter->pcicfg_mapped = true; } else { adapter->pcicfg = adapter->db + SRIOV_VF_PCICFG_OFFSET; + adapter->pcicfg_mapped = false; } } From 59dca1d8a6725a121dae6c452de0b2611d5865dc Mon Sep 17 00:00:00 2001 From: Bill Sommerfeld Date: Fri, 4 Mar 2016 14:47:21 -0800 Subject: [PATCH 410/417] udp6: fix UDP/IPv6 encap resubmit path IPv4 interprets a negative return value from a protocol handler as a request to redispatch to a new protocol. In contrast, IPv6 interprets a negative value as an error, and interprets a positive value as a request for redispatch. UDP for IPv6 was unaware of this difference. Change __udp6_lib_rcv() to return a positive value for redispatch. Note that the socket's encap_rcv hook still needs to return a negative value to request dispatch, and in the case of IPv6 packets, adjust IP6CB(skb)->nhoff to identify the byte containing the next protocol. Signed-off-by: Bill Sommerfeld Signed-off-by: David S. Miller --- net/ipv6/udp.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 22e28a44e3c8..422dd014aa2c 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -962,11 +962,9 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, ret = udpv6_queue_rcv_skb(sk, skb); sock_put(sk); - /* a return value > 0 means to resubmit the input, but - * it wants the return to be -protocol, or 0 - */ + /* a return value > 0 means to resubmit the input */ if (ret > 0) - return -ret; + return ret; return 0; } From 0772a99b818079e628a1da122ac7ee023faed83e Mon Sep 17 00:00:00 2001 From: Guo-Fu Tseng Date: Sat, 5 Mar 2016 08:11:55 +0800 Subject: [PATCH 411/417] jme: Do not enable NIC WoL functions on S0 Otherwise it might be back on resume right after going to suspend in some hardware. Reported-by: Diego Viola Signed-off-by: Guo-Fu Tseng Signed-off-by: David S. Miller --- drivers/net/ethernet/jme.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index 8adbe8ff0eb8..74b9c9d93473 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -270,11 +270,17 @@ jme_reset_mac_processor(struct jme_adapter *jme) } static inline void -jme_clear_pm(struct jme_adapter *jme) +jme_clear_pm_enable_wol(struct jme_adapter *jme) { jwrite32(jme, JME_PMCS, PMCS_STMASK | jme->reg_pmcs); } +static inline void +jme_clear_pm_disable_wol(struct jme_adapter *jme) +{ + jwrite32(jme, JME_PMCS, PMCS_STMASK); +} + static int jme_reload_eeprom(struct jme_adapter *jme) { @@ -1853,7 +1859,7 @@ jme_open(struct net_device *netdev) struct jme_adapter *jme = netdev_priv(netdev); int rc; - jme_clear_pm(jme); + jme_clear_pm_disable_wol(jme); JME_NAPI_ENABLE(jme); tasklet_init(&jme->linkch_task, jme_link_change_tasklet, @@ -1929,7 +1935,7 @@ jme_powersave_phy(struct jme_adapter *jme) jme_set_100m_half(jme); if (jme->reg_pmcs & (PMCS_LFEN | PMCS_LREN)) jme_wait_link(jme); - jme_clear_pm(jme); + jme_clear_pm_enable_wol(jme); } else { jme_phy_off(jme); } @@ -2646,7 +2652,6 @@ jme_set_wol(struct net_device *netdev, if (wol->wolopts & WAKE_MAGIC) jme->reg_pmcs |= PMCS_MFEN; - jwrite32(jme, JME_PMCS, jme->reg_pmcs); device_set_wakeup_enable(&jme->pdev->dev, !!(jme->reg_pmcs)); return 0; @@ -3172,7 +3177,7 @@ jme_init_one(struct pci_dev *pdev, jme->mii_if.mdio_read = jme_mdio_read; jme->mii_if.mdio_write = jme_mdio_write; - jme_clear_pm(jme); + jme_clear_pm_disable_wol(jme); device_set_wakeup_enable(&pdev->dev, true); jme_set_phyfifo_5level(jme); @@ -3304,7 +3309,7 @@ jme_resume(struct device *dev) if (!netif_running(netdev)) return 0; - jme_clear_pm(jme); + jme_clear_pm_disable_wol(jme); jme_phy_on(jme); if (test_bit(JME_FLAG_SSET, &jme->flags)) jme_set_settings(netdev, &jme->old_ecmd); From 81422e672f8181d7ad1ee6c60c723aac649f538f Mon Sep 17 00:00:00 2001 From: Guo-Fu Tseng Date: Sat, 5 Mar 2016 08:11:56 +0800 Subject: [PATCH 412/417] jme: Fix device PM wakeup API usage According to Documentation/power/devices.txt The driver should not use device_set_wakeup_enable() which is the policy for user to decide. Using device_init_wakeup() to initialize dev->power.should_wakeup and dev->power.can_wakeup on driver initialization. And use device_may_wakeup() on suspend to decide if WoL function should be enabled on NIC. Reported-by: Diego Viola Signed-off-by: Guo-Fu Tseng Signed-off-by: David S. Miller --- drivers/net/ethernet/jme.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index 74b9c9d93473..3ddf657bc10b 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -1931,7 +1931,7 @@ jme_wait_link(struct jme_adapter *jme) static void jme_powersave_phy(struct jme_adapter *jme) { - if (jme->reg_pmcs) { + if (jme->reg_pmcs && device_may_wakeup(&jme->pdev->dev)) { jme_set_100m_half(jme); if (jme->reg_pmcs & (PMCS_LFEN | PMCS_LREN)) jme_wait_link(jme); @@ -2652,8 +2652,6 @@ jme_set_wol(struct net_device *netdev, if (wol->wolopts & WAKE_MAGIC) jme->reg_pmcs |= PMCS_MFEN; - device_set_wakeup_enable(&jme->pdev->dev, !!(jme->reg_pmcs)); - return 0; } @@ -3178,7 +3176,7 @@ jme_init_one(struct pci_dev *pdev, jme->mii_if.mdio_write = jme_mdio_write; jme_clear_pm_disable_wol(jme); - device_set_wakeup_enable(&pdev->dev, true); + device_init_wakeup(&pdev->dev, true); jme_set_phyfifo_5level(jme); jme->pcirev = pdev->revision; From 68c222a6bc90e4bf03df7ae36a9b196fa869928e Mon Sep 17 00:00:00 2001 From: yankejian Date: Sat, 5 Mar 2016 14:10:42 +0800 Subject: [PATCH 413/417] net: hns: fix the bug about loopback It will always be passed if the soc is tested the loopback cases. This patch will fix this bug. Signed-off-by: Kejian Yan Signed-off-by: David S. Miller --- .../net/ethernet/hisilicon/hns/hns_ae_adapt.c | 8 ++++ .../ethernet/hisilicon/hns/hns_dsaf_main.c | 37 +++++++++++++++++++ .../ethernet/hisilicon/hns/hns_dsaf_main.h | 1 + .../net/ethernet/hisilicon/hns/hns_dsaf_reg.h | 5 +++ .../net/ethernet/hisilicon/hns/hns_ethtool.c | 15 +++++++- 5 files changed, 65 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index a0070d0e740d..d4f92ed322d6 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -675,8 +675,12 @@ static int hns_ae_config_loopback(struct hnae_handle *handle, { int ret; struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(handle); + struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle); switch (loop) { + case MAC_INTERNALLOOP_PHY: + ret = 0; + break; case MAC_INTERNALLOOP_SERDES: ret = hns_mac_config_sds_loopback(vf_cb->mac_cb, en); break; @@ -686,6 +690,10 @@ static int hns_ae_config_loopback(struct hnae_handle *handle, default: ret = -EINVAL; } + + if (!ret) + hns_dsaf_set_inner_lb(mac_cb->dsaf_dev, mac_cb->mac_id, en); + return ret; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index 9439f04962e1..38fc5be3870c 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -230,6 +230,30 @@ static void hns_dsaf_mix_def_qid_cfg(struct dsaf_device *dsaf_dev) } } +static void hns_dsaf_inner_qid_cfg(struct dsaf_device *dsaf_dev) +{ + u16 max_q_per_vf, max_vfn; + u32 q_id, q_num_per_port; + u32 mac_id; + + if (AE_IS_VER1(dsaf_dev->dsaf_ver)) + return; + + hns_rcb_get_queue_mode(dsaf_dev->dsaf_mode, + HNS_DSAF_COMM_SERVICE_NW_IDX, + &max_vfn, &max_q_per_vf); + q_num_per_port = max_vfn * max_q_per_vf; + + for (mac_id = 0, q_id = 0; mac_id < DSAF_SERVICE_NW_NUM; mac_id++) { + dsaf_set_dev_field(dsaf_dev, + DSAFV2_SERDES_LBK_0_REG + 4 * mac_id, + DSAFV2_SERDES_LBK_QID_M, + DSAFV2_SERDES_LBK_QID_S, + q_id); + q_id += q_num_per_port; + } +} + /** * hns_dsaf_sw_port_type_cfg - cfg sw type * @dsaf_id: dsa fabric id @@ -691,6 +715,16 @@ void hns_dsaf_set_promisc_mode(struct dsaf_device *dsaf_dev, u32 en) dsaf_set_dev_bit(dsaf_dev, DSAF_CFG_0_REG, DSAF_CFG_MIX_MODE_S, !!en); } +void hns_dsaf_set_inner_lb(struct dsaf_device *dsaf_dev, u32 mac_id, u32 en) +{ + if (AE_IS_VER1(dsaf_dev->dsaf_ver) || + dsaf_dev->mac_cb[mac_id].mac_type == HNAE_PORT_DEBUG) + return; + + dsaf_set_dev_bit(dsaf_dev, DSAFV2_SERDES_LBK_0_REG + 4 * mac_id, + DSAFV2_SERDES_LBK_EN_B, !!en); +} + /** * hns_dsaf_tbl_stat_en - tbl * @dsaf_id: dsa fabric id @@ -1022,6 +1056,9 @@ static void hns_dsaf_comm_init(struct dsaf_device *dsaf_dev) /* set promisc def queue id */ hns_dsaf_mix_def_qid_cfg(dsaf_dev); + /* set inner loopback queue id */ + hns_dsaf_inner_qid_cfg(dsaf_dev); + /* in non switch mode, set all port to access mode */ hns_dsaf_sw_port_type_cfg(dsaf_dev, DSAF_SW_PORT_TYPE_NON_VLAN); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h index 40205b910f80..5fea226efaf3 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h @@ -417,5 +417,6 @@ void hns_dsaf_get_strings(int stringset, u8 *data, int port); void hns_dsaf_get_regs(struct dsaf_device *ddev, u32 port, void *data); int hns_dsaf_get_regs_count(void); void hns_dsaf_set_promisc_mode(struct dsaf_device *dsaf_dev, u32 en); +void hns_dsaf_set_inner_lb(struct dsaf_device *dsaf_dev, u32 mac_id, u32 en); #endif /* __HNS_DSAF_MAIN_H__ */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h index f0c4f9b09d5b..60d695daa471 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h @@ -134,6 +134,7 @@ #define DSAF_XGE_INT_STS_0_REG 0x1C0 #define DSAF_PPE_INT_STS_0_REG 0x1E0 #define DSAF_ROCEE_INT_STS_0_REG 0x200 +#define DSAFV2_SERDES_LBK_0_REG 0x220 #define DSAF_PPE_QID_CFG_0_REG 0x300 #define DSAF_SW_PORT_TYPE_0_REG 0x320 #define DSAF_STP_PORT_TYPE_0_REG 0x340 @@ -857,6 +858,10 @@ #define PPEV2_CFG_RSS_TBL_4N3_S 24 #define PPEV2_CFG_RSS_TBL_4N3_M (((1UL << 5) - 1) << PPEV2_CFG_RSS_TBL_4N3_S) +#define DSAFV2_SERDES_LBK_EN_B 8 +#define DSAFV2_SERDES_LBK_QID_S 0 +#define DSAFV2_SERDES_LBK_QID_M (((1UL << 8) - 1) << DSAFV2_SERDES_LBK_QID_S) + #define PPE_CNT_CLR_CE_B 0 #define PPE_CNT_CLR_SNAP_EN_B 1 diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 3df22840fcd1..3c4a3bc31a89 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -295,8 +295,10 @@ static int __lb_setup(struct net_device *ndev, switch (loop) { case MAC_INTERNALLOOP_PHY: - if ((phy_dev) && (!phy_dev->is_c45)) + if ((phy_dev) && (!phy_dev->is_c45)) { ret = hns_nic_config_phy_loopback(phy_dev, 0x1); + ret |= h->dev->ops->set_loopback(h, loop, 0x1); + } break; case MAC_INTERNALLOOP_MAC: if ((h->dev->ops->set_loopback) && @@ -376,6 +378,7 @@ static void __lb_other_process(struct hns_nic_ring_data *ring_data, struct sk_buff *skb) { struct net_device *ndev; + struct hns_nic_priv *priv; struct hnae_ring *ring; struct netdev_queue *dev_queue; struct sk_buff *new_skb; @@ -385,8 +388,17 @@ static void __lb_other_process(struct hns_nic_ring_data *ring_data, char buff[33]; /* 32B data and the last character '\0' */ if (!ring_data) { /* Just for doing create frame*/ + ndev = skb->dev; + priv = netdev_priv(ndev); + frame_size = skb->len; memset(skb->data, 0xFF, frame_size); + if ((!AE_IS_VER1(priv->enet_ver)) && + (priv->ae_handle->port_type == HNAE_PORT_SERVICE)) { + memcpy(skb->data, ndev->dev_addr, 6); + skb->data[5] += 0x1f; + } + frame_size &= ~1ul; memset(&skb->data[frame_size / 2], 0xAA, frame_size / 2 - 1); memset(&skb->data[frame_size / 2 + 10], 0xBE, @@ -486,6 +498,7 @@ static int __lb_run_test(struct net_device *ndev, /* place data into test skb */ (void)skb_put(skb, size); + skb->dev = ndev; __lb_other_process(NULL, skb); skb->queue_mapping = NIC_LB_TEST_RING_ID; From a9d99ce28ed359d68cf6f3c1a69038aefedf6d6a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 6 Mar 2016 09:29:21 -0800 Subject: [PATCH 414/417] tcp: fix tcpi_segs_in after connection establishment If final packet (ACK) of 3WHS is lost, it appears we do not properly account the following incoming segment into tcpi_segs_in While we are at it, starts segs_in with one, to count the SYN packet. We do not yet count number of SYN we received for a request sock, we might add this someday. packetdrill script showing proper behavior after fix : // Tests tcpi_segs_in when 3rd packet (ACK) of 3WHS is lost 0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 +0 bind(3, ..., ...) = 0 +0 listen(3, 1) = 0 +0 < S 0:0(0) win 32792 +0 > S. 0:0(0) ack 1 +.020 < P. 1:1001(1000) ack 1 win 32792 +0 accept(3, ..., ...) = 4 +.000 %{ assert tcpi_segs_in == 2, 'tcpi_segs_in=%d' % tcpi_segs_in }% Fixes: 2efd055c53c06 ("tcp: add tcpi_segs_in and tcpi_segs_out to tcp_info") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_minisocks.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 75632a925824..9b02af2139d3 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -455,7 +455,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->rcv_wup = newtp->copied_seq = newtp->rcv_nxt = treq->rcv_isn + 1; - newtp->segs_in = 0; + newtp->segs_in = 1; newtp->snd_sml = newtp->snd_una = newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1; @@ -815,6 +815,7 @@ int tcp_child_process(struct sock *parent, struct sock *child, int ret = 0; int state = child->sk_state; + tcp_sk(child)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs); if (!sock_owned_by_user(child)) { ret = tcp_rcv_state_process(child, skb); /* Wakeup parent, send SIGIO */ From 4d06dd537f95683aba3651098ae288b7cbff8274 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Mon, 7 Mar 2016 21:15:36 +0100 Subject: [PATCH 415/417] cdc_ncm: do not call usbnet_link_change from cdc_ncm_bind MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit usbnet_link_change will call schedule_work and should be avoided if bind is failing. Otherwise we will end up with scheduled work referring to a netdev which has gone away. Instead of making the call conditional, we can just defer it to usbnet_probe, using the driver_info flag made for this purpose. Fixes: 8a34b0ae8778 ("usbnet: cdc_ncm: apply usbnet_link_change") Reported-by: Andrey Konovalov Suggested-by: Linus Torvalds Signed-off-by: Bjørn Mork Signed-off-by: David S. Miller --- drivers/net/usb/cdc_ncm.c | 20 +++++--------------- 1 file changed, 5 insertions(+), 15 deletions(-) diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index be927964375b..86ba30ba35e8 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -988,8 +988,6 @@ EXPORT_SYMBOL_GPL(cdc_ncm_select_altsetting); static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf) { - int ret; - /* MBIM backwards compatible function? */ if (cdc_ncm_select_altsetting(intf) != CDC_NCM_COMM_ALTSETTING_NCM) return -ENODEV; @@ -998,16 +996,7 @@ static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf) * Additionally, generic NCM devices are assumed to accept arbitrarily * placed NDP. */ - ret = cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM, 0); - - /* - * We should get an event when network connection is "connected" or - * "disconnected". Set network connection in "disconnected" state - * (carrier is OFF) during attach, so the IP network stack does not - * start IPv6 negotiation and more. - */ - usbnet_link_change(dev, 0, 0); - return ret; + return cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM, 0); } static void cdc_ncm_align_tail(struct sk_buff *skb, size_t modulus, size_t remainder, size_t max) @@ -1590,7 +1579,8 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb) static const struct driver_info cdc_ncm_info = { .description = "CDC NCM", - .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET, + .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET + | FLAG_LINK_INTR, .bind = cdc_ncm_bind, .unbind = cdc_ncm_unbind, .manage_power = usbnet_manage_power, @@ -1603,7 +1593,7 @@ static const struct driver_info cdc_ncm_info = { static const struct driver_info wwan_info = { .description = "Mobile Broadband Network Device", .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET - | FLAG_WWAN, + | FLAG_LINK_INTR | FLAG_WWAN, .bind = cdc_ncm_bind, .unbind = cdc_ncm_unbind, .manage_power = usbnet_manage_power, @@ -1616,7 +1606,7 @@ static const struct driver_info wwan_info = { static const struct driver_info wwan_noarp_info = { .description = "Mobile Broadband Network Device (NO ARP)", .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET - | FLAG_WWAN | FLAG_NOARP, + | FLAG_LINK_INTR | FLAG_WWAN | FLAG_NOARP, .bind = cdc_ncm_bind, .unbind = cdc_ncm_unbind, .manage_power = usbnet_manage_power, From 6faac63a6986f29ef39827f460edd3a5ba64ad5c Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Mon, 7 Mar 2016 19:36:44 +0100 Subject: [PATCH 416/417] ppp: release rtnl mutex when interface creation fails Add missing rtnl_unlock() in the error path of ppp_create_interface(). Fixes: 58a89ecaca53 ("ppp: fix lockdep splat in ppp_dev_uninit()") Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- drivers/net/ppp/ppp_generic.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index e8a5936289c5..d61da9ece3ba 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -2816,6 +2816,7 @@ static struct ppp *ppp_create_interface(struct net *net, int unit, out2: mutex_unlock(&pn->all_ppp_mutex); + rtnl_unlock(); free_netdev(dev); out1: *retp = ret; From 256faedcfd646161477d47a1a78c32a562d2e845 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 7 Mar 2016 13:15:09 -0800 Subject: [PATCH 417/417] Revert "drm/radeon: call hpd_irq_event on resume" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit dbb17a21c131eca94eb31136eee9a7fe5aff00d9. It turns out that commit can cause problems for systems with multiple GPUs, and causes X to hang on at least a HP Pavilion dv7 with hybrid graphics. This got noticed originally in 4.4.4, where this patch had already gotten back-ported, but 4.5-rc7 was verified to have the same problem. Alexander Deucher says: "It looks like you have a muxed system so I suspect what's happening is that one of the display is being reported as connected for both the IGP and the dGPU and then the desktop environment gets confused or there some sort problem in the detect functions since the mux is not switched to the dGPU. I don't see an easy fix unless Dave has any ideas. I'd say just revert for now" Reported-by: Jörg-Volker Peetz Acked-by: Alexander Deucher Cc: Dave Airlie Cc: stable@kernel.org # wherever dbb17a21c131 got back-ported Signed-off-by: Linus Torvalds --- drivers/gpu/drm/radeon/radeon_device.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 902b59cebac5..4197ca1bb1e4 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1744,7 +1744,6 @@ int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon) } drm_kms_helper_poll_enable(dev); - drm_helper_hpd_irq_event(dev); /* set the power state here in case we are a PX system or headless */ if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled)