From 35d35aae817706800a4913711d563a99e1dc380a Mon Sep 17 00:00:00 2001 From: Tushar Behera Date: Thu, 6 Mar 2014 11:34:43 +0530 Subject: dt-bindings: clock: Move at91.h to dt-bindigs/clock Most of the clock related dt-binding header files are located in dt-bindings/clock folder. It would be good to keep all the similar header files at a single location. Signed-off-by: Tushar Behera CC: Rob Landley CC: Andrew Victor CC: Jean-Christophe Plagniol-Villard Acked-by: Boris BREZILLON [nicolas.ferre@atmel.com: add new at91sam9261 & at91sam9rl] Signed-off-by: Nicolas Ferre --- include/dt-bindings/clk/at91.h | 22 ---------------------- include/dt-bindings/clock/at91.h | 22 ++++++++++++++++++++++ 2 files changed, 22 insertions(+), 22 deletions(-) delete mode 100644 include/dt-bindings/clk/at91.h create mode 100644 include/dt-bindings/clock/at91.h (limited to 'include') diff --git a/include/dt-bindings/clk/at91.h b/include/dt-bindings/clk/at91.h deleted file mode 100644 index 0b4cb999a3f..00000000000 --- a/include/dt-bindings/clk/at91.h +++ /dev/null @@ -1,22 +0,0 @@ -/* - * This header provides constants for AT91 pmc status. - * - * The constants defined in this header are being used in dts. - * - * Licensed under GPLv2 or later. - */ - -#ifndef _DT_BINDINGS_CLK_AT91_H -#define _DT_BINDINGS_CLK_AT91_H - -#define AT91_PMC_MOSCS 0 /* MOSCS Flag */ -#define AT91_PMC_LOCKA 1 /* PLLA Lock */ -#define AT91_PMC_LOCKB 2 /* PLLB Lock */ -#define AT91_PMC_MCKRDY 3 /* Master Clock */ -#define AT91_PMC_LOCKU 6 /* UPLL Lock */ -#define AT91_PMC_PCKRDY(id) (8 + (id)) /* Programmable Clock */ -#define AT91_PMC_MOSCSELS 16 /* Main Oscillator Selection */ -#define AT91_PMC_MOSCRCS 17 /* Main On-Chip RC */ -#define AT91_PMC_CFDEV 18 /* Clock Failure Detector Event */ - -#endif diff --git a/include/dt-bindings/clock/at91.h b/include/dt-bindings/clock/at91.h new file mode 100644 index 00000000000..0b4cb999a3f --- /dev/null +++ b/include/dt-bindings/clock/at91.h @@ -0,0 +1,22 @@ +/* + * This header provides constants for AT91 pmc status. + * + * The constants defined in this header are being used in dts. + * + * Licensed under GPLv2 or later. + */ + +#ifndef _DT_BINDINGS_CLK_AT91_H +#define _DT_BINDINGS_CLK_AT91_H + +#define AT91_PMC_MOSCS 0 /* MOSCS Flag */ +#define AT91_PMC_LOCKA 1 /* PLLA Lock */ +#define AT91_PMC_LOCKB 2 /* PLLB Lock */ +#define AT91_PMC_MCKRDY 3 /* Master Clock */ +#define AT91_PMC_LOCKU 6 /* UPLL Lock */ +#define AT91_PMC_PCKRDY(id) (8 + (id)) /* Programmable Clock */ +#define AT91_PMC_MOSCSELS 16 /* Main Oscillator Selection */ +#define AT91_PMC_MOSCRCS 17 /* Main On-Chip RC */ +#define AT91_PMC_CFDEV 18 /* Clock Failure Detector Event */ + +#endif -- cgit v1.2.3-70-g09d2 From 9bbfd20abe5025adbb0ac75160bd2e41158a9e83 Mon Sep 17 00:00:00 2001 From: Paulo Zanoni Date: Tue, 29 Apr 2014 11:00:22 -0300 Subject: drm/i915: don't try DP_LINK_BW_5_4 on HSW ULX Because the docs say ULX doesn't support it on HSW. Reviewed-by: Dave Airlie Signed-off-by: Paulo Zanoni Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_drv.h | 3 +++ drivers/gpu/drm/i915/intel_dp.c | 3 ++- include/drm/i915_pciids.h | 4 ++-- 3 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index ec82f6bff12..108e1ec2fa4 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1954,6 +1954,9 @@ struct drm_i915_cmd_table { #define IS_ULT(dev) (IS_HSW_ULT(dev) || IS_BDW_ULT(dev)) #define IS_HSW_GT3(dev) (IS_HASWELL(dev) && \ ((dev)->pdev->device & 0x00F0) == 0x0020) +/* ULX machines are also considered ULT. */ +#define IS_HSW_ULX(dev) ((dev)->pdev->device == 0x0A0E || \ + (dev)->pdev->device == 0x0A1E) #define IS_PRELIMINARY_HW(intel_info) ((intel_info)->is_preliminary) /* diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index dfa85289f28..5ca68aa9f23 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -105,7 +105,8 @@ intel_dp_max_link_bw(struct intel_dp *intel_dp) case DP_LINK_BW_2_7: break; case DP_LINK_BW_5_4: /* 1.2 capable displays may advertise higher bw */ - if ((IS_HASWELL(dev) || INTEL_INFO(dev)->gen >= 8) && + if (((IS_HASWELL(dev) && !IS_HSW_ULX(dev)) || + INTEL_INFO(dev)->gen >= 8) && intel_dp->dpcd[DP_DPCD_REV] >= 0x12) max_link_bw = DP_LINK_BW_5_4; else diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h index 940ece4934b..012d58fa8ff 100644 --- a/include/drm/i915_pciids.h +++ b/include/drm/i915_pciids.h @@ -191,8 +191,8 @@ INTEL_VGA_DEVICE(0x0A06, info), /* ULT GT1 mobile */ \ INTEL_VGA_DEVICE(0x0A16, info), /* ULT GT2 mobile */ \ INTEL_VGA_DEVICE(0x0A26, info), /* ULT GT3 mobile */ \ - INTEL_VGA_DEVICE(0x0A0E, info), /* ULT GT1 reserved */ \ - INTEL_VGA_DEVICE(0x0A1E, info), /* ULT GT2 reserved */ \ + INTEL_VGA_DEVICE(0x0A0E, info), /* ULX GT1 mobile */ \ + INTEL_VGA_DEVICE(0x0A1E, info), /* ULX GT2 mobile */ \ INTEL_VGA_DEVICE(0x0A2E, info), /* ULT GT3 reserved */ \ INTEL_VGA_DEVICE(0x0D06, info), /* CRW GT1 mobile */ \ INTEL_VGA_DEVICE(0x0D16, info), /* CRW GT2 mobile */ \ -- cgit v1.2.3-70-g09d2 From 792e6aa7a15ea0fb16f8687e93caede1ea9118c7 Mon Sep 17 00:00:00 2001 From: Eliad Peller Date: Wed, 30 Apr 2014 16:14:23 +0300 Subject: cfg80211: add cfg80211_sched_scan_stopped_rtnl Add locked-version for cfg80211_sched_scan_stopped. This is used for some users that might want to call it when rtnl is already locked. Fixes: d43c6b6 ("mac80211: reschedule sched scan after HW restart") Cc: stable@vger.kernel.org (3.14+) Signed-off-by: Eliad Peller Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 12 ++++++++++++ net/wireless/scan.c | 12 ++++++++++-- 2 files changed, 22 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f3539a15c41..f856e5a746f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -3668,6 +3668,18 @@ void cfg80211_sched_scan_results(struct wiphy *wiphy); */ void cfg80211_sched_scan_stopped(struct wiphy *wiphy); +/** + * cfg80211_sched_scan_stopped_rtnl - notify that the scheduled scan has stopped + * + * @wiphy: the wiphy on which the scheduled scan stopped + * + * The driver can call this function to inform cfg80211 that the + * scheduled scan had to be stopped, for whatever reason. The driver + * is then called back via the sched_scan_stop operation when done. + * This function should be called with rtnl locked. + */ +void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy); + /** * cfg80211_inform_bss_width_frame - inform cfg80211 of a received BSS frame * diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 7d09a712cb1..88f108edfb5 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -284,14 +284,22 @@ void cfg80211_sched_scan_results(struct wiphy *wiphy) } EXPORT_SYMBOL(cfg80211_sched_scan_results); -void cfg80211_sched_scan_stopped(struct wiphy *wiphy) +void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy) { struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + ASSERT_RTNL(); + trace_cfg80211_sched_scan_stopped(wiphy); - rtnl_lock(); __cfg80211_stop_sched_scan(rdev, true); +} +EXPORT_SYMBOL(cfg80211_sched_scan_stopped_rtnl); + +void cfg80211_sched_scan_stopped(struct wiphy *wiphy) +{ + rtnl_lock(); + cfg80211_sched_scan_stopped_rtnl(wiphy); rtnl_unlock(); } EXPORT_SYMBOL(cfg80211_sched_scan_stopped); -- cgit v1.2.3-70-g09d2 From 3adc1beacdbc1d6c4be99ecc2f87eac1c1e6f857 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Fri, 2 May 2014 00:44:36 +0200 Subject: asmlinkage: Revert "lto: Make asmlinkage __visible" As requested by Linus, revert adding __visible to asmlinkage. Instead we add __visible explicitely to all the symbols that need it. This reverts commit 128ea04a9885af9629059e631ddf0cab4815b589. Link: http://lkml.kernel.org/r/1398984278-29319-2-git-send-email-andi@firstfloor.org Signed-off-by: H. Peter Anvin --- include/linux/linkage.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/linkage.h b/include/linux/linkage.h index 34a513a2727..a6a42dd0246 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -12,9 +12,9 @@ #endif #ifdef __cplusplus -#define CPP_ASMLINKAGE extern "C" __visible +#define CPP_ASMLINKAGE extern "C" #else -#define CPP_ASMLINKAGE __visible +#define CPP_ASMLINKAGE #endif #ifndef asmlinkage -- cgit v1.2.3-70-g09d2 From 573471c1374e6a54a78efc1d1c047733981c99e2 Mon Sep 17 00:00:00 2001 From: Samuel Li Date: Wed, 30 Apr 2014 18:40:55 -0400 Subject: drm/radeon: add pci ids for Mullins MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Samuel Li Signed-off-by: Alex Deucher Signed-off-by: Christian König --- include/drm/drm_pciids.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h index 49376aec2fb..6dfd64b3a60 100644 --- a/include/drm/drm_pciids.h +++ b/include/drm/drm_pciids.h @@ -637,6 +637,22 @@ {0x1002, 0x983d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KABINI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x983e, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KABINI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x983f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KABINI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9850, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9851, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9852, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9853, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9854, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9855, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9856, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9857, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9858, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9859, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x985A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x985B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x985C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x985D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x985E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x985F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x9900, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x9901, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x9903, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ -- cgit v1.2.3-70-g09d2 From 4c88d7f9b0d5fb0588c3386be62115cc2eaa8f9f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 23 Apr 2014 14:49:17 +0200 Subject: genirq: Provide irq_force_affinity fallback for non-SMP Patch 01f8fa4f01d "genirq: Allow forcing cpu affinity of interrupts" added an irq_force_affinity() function, and 30ccf03b4a6 "clocksource: Exynos_mct: Use irq_force_affinity() in cpu bringup" subsequently uses it. However, the driver can be used with CONFIG_SMP disabled, but the function declaration is only available for CONFIG_SMP, leading to this build error: drivers/clocksource/exynos_mct.c:431:3: error: implicit declaration of function 'irq_force_affinity' [-Werror=implicit-function-declaration] irq_force_affinity(mct_irqs[MCT_L0_IRQ + cpu], cpumask_of(cpu)); This patch introduces a dummy helper function for the non-SMP case that always returns success, to get rid of the build error. Since the patches causing the problem are marked for stable backports, this one should be as well. Signed-off-by: Arnd Bergmann Cc: Krzysztof Kozlowski Acked-by: Kukjin Kim Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/5619084.0zmrrIUZLV@wuerfel Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 97ac926c78a..051c85032f4 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -272,6 +272,11 @@ static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m) return -EINVAL; } +static inline int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask) +{ + return 0; +} + static inline int irq_can_set_affinity(unsigned int irq) { return 0; -- cgit v1.2.3-70-g09d2 From 5bfd126e80dca70431aef8fdbc1cf14535f3c338 Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Tue, 15 Apr 2014 13:49:04 +0200 Subject: sched/deadline: Fix sched_yield() behavior yield_task_dl() is broken: o it forces current to be throttled setting its runtime to zero; o it sets current's dl_se->dl_new to one, expecting that dl_task_timer() will queue it back with proper parameters at replenish time. Unfortunately, dl_task_timer() has this check at the very beginning: if (!dl_task(p) || dl_se->dl_new) goto unlock; So, it just bails out and the task is never replenished. It actually yielded forever. To fix this, introduce a new flag indicating that the task properly yielded the CPU before its current runtime expired. While this is a little overdoing at the moment, the flag would be useful in the future to discriminate between "good" jobs (of which remaining runtime could be reclaimed, i.e. recycled) and "bad" jobs (for which dl_throttled task has been set) that needed to be stopped. Reported-by: yjay.kim Signed-off-by: Juri Lelli Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20140429103953.e68eba1b2ac3309214e3dc5a@gmail.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 7 +++++-- kernel/sched/core.c | 1 + kernel/sched/deadline.c | 5 +++-- 3 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 25f54c79f75..2a4298fb0d8 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1153,9 +1153,12 @@ struct sched_dl_entity { * * @dl_boosted tells if we are boosted due to DI. If so we are * outside bandwidth enforcement mechanism (but only until we - * exit the critical section). + * exit the critical section); + * + * @dl_yielded tells if task gave up the cpu before consuming + * all its available runtime during the last job. */ - int dl_throttled, dl_new, dl_boosted; + int dl_throttled, dl_new, dl_boosted, dl_yielded; /* * Bandwidth enforcement timer. Each -deadline task has its diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9fe2190005c..e62c65a12d5 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3124,6 +3124,7 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr) dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime); dl_se->dl_throttled = 0; dl_se->dl_new = 1; + dl_se->dl_yielded = 0; } static void __setscheduler_params(struct task_struct *p, diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index b08095786cb..800e99b9907 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -528,6 +528,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) sched_clock_tick(); update_rq_clock(rq); dl_se->dl_throttled = 0; + dl_se->dl_yielded = 0; if (p->on_rq) { enqueue_task_dl(rq, p, ENQUEUE_REPLENISH); if (task_has_dl_policy(rq->curr)) @@ -893,10 +894,10 @@ static void yield_task_dl(struct rq *rq) * We make the task go to sleep until its current deadline by * forcing its runtime to zero. This way, update_curr_dl() stops * it and the bandwidth timer will wake it up and will give it - * new scheduling parameters (thanks to dl_new=1). + * new scheduling parameters (thanks to dl_yielded=1). */ if (p->dl.runtime > 0) { - rq->curr->dl.dl_new = 1; + rq->curr->dl.dl_yielded = 1; p->dl.runtime = 0; } update_curr_dl(rq); -- cgit v1.2.3-70-g09d2 From c1e756bfcbcac838a86a23f3e4501b556a961e3c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 5 May 2014 15:00:44 +0200 Subject: Revert "net: core: introduce netif_skb_dev_features" This reverts commit d206940319c41df4299db75ed56142177bb2e5f6, there are no more callers. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +------ net/core/dev.c | 22 ++++++++++------------ 2 files changed, 11 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7ed3a3aa660..20e99efb1ca 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3180,12 +3180,7 @@ void netdev_change_features(struct net_device *dev); void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev); -netdev_features_t netif_skb_dev_features(struct sk_buff *skb, - const struct net_device *dev); -static inline netdev_features_t netif_skb_features(struct sk_buff *skb) -{ - return netif_skb_dev_features(skb, skb->dev); -} +netdev_features_t netif_skb_features(struct sk_buff *skb); static inline bool net_gso_ok(netdev_features_t features, int gso_type) { diff --git a/net/core/dev.c b/net/core/dev.c index d2c8a06b3a9..c619b864133 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2418,7 +2418,7 @@ EXPORT_SYMBOL(netdev_rx_csum_fault); * 2. No high memory really exists on this machine. */ -static int illegal_highdma(const struct net_device *dev, struct sk_buff *skb) +static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_HIGHMEM int i; @@ -2493,38 +2493,36 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features) } static netdev_features_t harmonize_features(struct sk_buff *skb, - const struct net_device *dev, - netdev_features_t features) + netdev_features_t features) { int tmp; if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, skb_network_protocol(skb, &tmp))) { features &= ~NETIF_F_ALL_CSUM; - } else if (illegal_highdma(dev, skb)) { + } else if (illegal_highdma(skb->dev, skb)) { features &= ~NETIF_F_SG; } return features; } -netdev_features_t netif_skb_dev_features(struct sk_buff *skb, - const struct net_device *dev) +netdev_features_t netif_skb_features(struct sk_buff *skb) { __be16 protocol = skb->protocol; - netdev_features_t features = dev->features; + netdev_features_t features = skb->dev->features; - if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs) + if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs) features &= ~NETIF_F_GSO_MASK; if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; protocol = veh->h_vlan_encapsulated_proto; } else if (!vlan_tx_tag_present(skb)) { - return harmonize_features(skb, dev, features); + return harmonize_features(skb, features); } - features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | + features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) @@ -2532,9 +2530,9 @@ netdev_features_t netif_skb_dev_features(struct sk_buff *skb, NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; - return harmonize_features(skb, dev, features); + return harmonize_features(skb, features); } -EXPORT_SYMBOL(netif_skb_dev_features); +EXPORT_SYMBOL(netif_skb_features); int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) -- cgit v1.2.3-70-g09d2 From 23a456f05353035d1a2b3f1b9a92707acdc036e0 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Tue, 6 May 2014 18:52:16 +0200 Subject: net: mdio: of_mdiobus_register(): fall back to mdiobus_register() for !CONFIG_OF If CONFIG_OF is not set, make of_mdiobus_register() call mdiobus_register() instead of returning -ENOSYS. This way, we can just call of_mdiobus_register() from all DT-enabled drivers to handle the compat cases. Signed-off-by: Daniel Mack Suggested-by: Florian Fainelli Acked-by: Florian Fainelli Acked-by: Mugunthan V N Signed-off-by: David S. Miller --- include/linux/of_mdio.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 6fe8464ed76..881a7c3571f 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -31,7 +31,12 @@ extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np); #else /* CONFIG_OF */ static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) { - return -ENOSYS; + /* + * Fall back to the non-DT function to register a bus. + * This way, we don't have to keep compat bits around in drivers. + */ + + return mdiobus_register(mdio); } static inline struct phy_device *of_phy_find_device(struct device_node *phy_np) -- cgit v1.2.3-70-g09d2 From 98fcc5762dcecbb264fa4af5a9ae51136858e299 Mon Sep 17 00:00:00 2001 From: Micky Ching Date: Tue, 29 Apr 2014 09:54:54 +0800 Subject: mmc: rtsx: Revert "mmc: rtsx: add support for pre_req and post_req" This reverts commit c42deffd5b53c9e583d83c7964854ede2f12410d. commit did use mutex_unlock() in tasklet, but mutex_unlock() can't be used in tasklet(atomic context). The driver needs to use mutex to avoid concurrency, so we can't use tasklet here, the patch need to be removed. The spinlock host->lock and pcr->lock may deadlock, one way to solve the deadlock is remove host->lock in sd_isr_done_transfer(), but if using workqueue the we can avoid using the spinlock and also avoid the problem. Signed-off-by: Micky Ching Acked-by: Ulf Hansson Signed-off-by: Lee Jones --- drivers/mfd/rtsx_pcr.c | 132 ++++-------- drivers/mmc/host/rtsx_pci_sdmmc.c | 418 +++++++------------------------------- include/linux/mfd/rtsx_common.h | 1 - include/linux/mfd/rtsx_pci.h | 6 - 4 files changed, 109 insertions(+), 448 deletions(-) (limited to 'include') diff --git a/drivers/mfd/rtsx_pcr.c b/drivers/mfd/rtsx_pcr.c index c9de3d598ea..1d15735f9ef 100644 --- a/drivers/mfd/rtsx_pcr.c +++ b/drivers/mfd/rtsx_pcr.c @@ -338,28 +338,58 @@ int rtsx_pci_transfer_data(struct rtsx_pcr *pcr, struct scatterlist *sglist, int num_sg, bool read, int timeout) { struct completion trans_done; - int err = 0, count; + u8 dir; + int err = 0, i, count; long timeleft; unsigned long flags; + struct scatterlist *sg; + enum dma_data_direction dma_dir; + u32 val; + dma_addr_t addr; + unsigned int len; + + dev_dbg(&(pcr->pci->dev), "--> %s: num_sg = %d\n", __func__, num_sg); + + /* don't transfer data during abort processing */ + if (pcr->remove_pci) + return -EINVAL; + + if ((sglist == NULL) || (num_sg <= 0)) + return -EINVAL; - count = rtsx_pci_dma_map_sg(pcr, sglist, num_sg, read); + if (read) { + dir = DEVICE_TO_HOST; + dma_dir = DMA_FROM_DEVICE; + } else { + dir = HOST_TO_DEVICE; + dma_dir = DMA_TO_DEVICE; + } + + count = dma_map_sg(&(pcr->pci->dev), sglist, num_sg, dma_dir); if (count < 1) { dev_err(&(pcr->pci->dev), "scatterlist map failed\n"); return -EINVAL; } dev_dbg(&(pcr->pci->dev), "DMA mapping count: %d\n", count); + val = ((u32)(dir & 0x01) << 29) | TRIG_DMA | ADMA_MODE; + pcr->sgi = 0; + for_each_sg(sglist, sg, count, i) { + addr = sg_dma_address(sg); + len = sg_dma_len(sg); + rtsx_pci_add_sg_tbl(pcr, addr, len, i == count - 1); + } spin_lock_irqsave(&pcr->lock, flags); pcr->done = &trans_done; pcr->trans_result = TRANS_NOT_READY; init_completion(&trans_done); + rtsx_pci_writel(pcr, RTSX_HDBAR, pcr->host_sg_tbl_addr); + rtsx_pci_writel(pcr, RTSX_HDBCTLR, val); spin_unlock_irqrestore(&pcr->lock, flags); - rtsx_pci_dma_transfer(pcr, sglist, count, read); - timeleft = wait_for_completion_interruptible_timeout( &trans_done, msecs_to_jiffies(timeout)); if (timeleft <= 0) { @@ -383,7 +413,7 @@ out: pcr->done = NULL; spin_unlock_irqrestore(&pcr->lock, flags); - rtsx_pci_dma_unmap_sg(pcr, sglist, num_sg, read); + dma_unmap_sg(&(pcr->pci->dev), sglist, num_sg, dma_dir); if ((err < 0) && (err != -ENODEV)) rtsx_pci_stop_cmd(pcr); @@ -395,73 +425,6 @@ out: } EXPORT_SYMBOL_GPL(rtsx_pci_transfer_data); -int rtsx_pci_dma_map_sg(struct rtsx_pcr *pcr, struct scatterlist *sglist, - int num_sg, bool read) -{ - enum dma_data_direction dir = read ? DMA_FROM_DEVICE : DMA_TO_DEVICE; - - if (pcr->remove_pci) - return -EINVAL; - - if ((sglist == NULL) || num_sg < 1) - return -EINVAL; - - return dma_map_sg(&(pcr->pci->dev), sglist, num_sg, dir); -} -EXPORT_SYMBOL_GPL(rtsx_pci_dma_map_sg); - -int rtsx_pci_dma_unmap_sg(struct rtsx_pcr *pcr, struct scatterlist *sglist, - int num_sg, bool read) -{ - enum dma_data_direction dir = read ? DMA_FROM_DEVICE : DMA_TO_DEVICE; - - if (pcr->remove_pci) - return -EINVAL; - - if (sglist == NULL || num_sg < 1) - return -EINVAL; - - dma_unmap_sg(&(pcr->pci->dev), sglist, num_sg, dir); - return num_sg; -} -EXPORT_SYMBOL_GPL(rtsx_pci_dma_unmap_sg); - -int rtsx_pci_dma_transfer(struct rtsx_pcr *pcr, struct scatterlist *sglist, - int sg_count, bool read) -{ - struct scatterlist *sg; - dma_addr_t addr; - unsigned int len; - int i; - u32 val; - u8 dir = read ? DEVICE_TO_HOST : HOST_TO_DEVICE; - unsigned long flags; - - if (pcr->remove_pci) - return -EINVAL; - - if ((sglist == NULL) || (sg_count < 1)) - return -EINVAL; - - val = ((u32)(dir & 0x01) << 29) | TRIG_DMA | ADMA_MODE; - pcr->sgi = 0; - for_each_sg(sglist, sg, sg_count, i) { - addr = sg_dma_address(sg); - len = sg_dma_len(sg); - rtsx_pci_add_sg_tbl(pcr, addr, len, i == sg_count - 1); - } - - spin_lock_irqsave(&pcr->lock, flags); - - rtsx_pci_writel(pcr, RTSX_HDBAR, pcr->host_sg_tbl_addr); - rtsx_pci_writel(pcr, RTSX_HDBCTLR, val); - - spin_unlock_irqrestore(&pcr->lock, flags); - - return 0; -} -EXPORT_SYMBOL_GPL(rtsx_pci_dma_transfer); - int rtsx_pci_read_ppbuf(struct rtsx_pcr *pcr, u8 *buf, int buf_len) { int err; @@ -873,8 +836,6 @@ static irqreturn_t rtsx_pci_isr(int irq, void *dev_id) int_reg = rtsx_pci_readl(pcr, RTSX_BIPR); /* Clear interrupt flag */ rtsx_pci_writel(pcr, RTSX_BIPR, int_reg); - dev_dbg(&pcr->pci->dev, "=========== BIPR 0x%8x ==========\n", int_reg); - if ((int_reg & pcr->bier) == 0) { spin_unlock(&pcr->lock); return IRQ_NONE; @@ -905,28 +866,17 @@ static irqreturn_t rtsx_pci_isr(int irq, void *dev_id) } if (int_reg & (NEED_COMPLETE_INT | DELINK_INT)) { - if (int_reg & (TRANS_FAIL_INT | DELINK_INT)) + if (int_reg & (TRANS_FAIL_INT | DELINK_INT)) { pcr->trans_result = TRANS_RESULT_FAIL; - else if (int_reg & TRANS_OK_INT) + if (pcr->done) + complete(pcr->done); + } else if (int_reg & TRANS_OK_INT) { pcr->trans_result = TRANS_RESULT_OK; - - if (pcr->done) - complete(pcr->done); - - if (int_reg & SD_EXIST) { - struct rtsx_slot *slot = &pcr->slots[RTSX_SD_CARD]; - if (slot && slot->done_transfer) - slot->done_transfer(slot->p_dev); - } - - if (int_reg & MS_EXIST) { - struct rtsx_slot *slot = &pcr->slots[RTSX_SD_CARD]; - if (slot && slot->done_transfer) - slot->done_transfer(slot->p_dev); + if (pcr->done) + complete(pcr->done); } } - if (pcr->card_inserted || pcr->card_removed) schedule_delayed_work(&pcr->carddet_work, msecs_to_jiffies(200)); diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c index 5fb994f9a65..0b9ded13a3a 100644 --- a/drivers/mmc/host/rtsx_pci_sdmmc.c +++ b/drivers/mmc/host/rtsx_pci_sdmmc.c @@ -31,28 +31,14 @@ #include #include -struct realtek_next { - unsigned int sg_count; - s32 cookie; -}; - struct realtek_pci_sdmmc { struct platform_device *pdev; struct rtsx_pcr *pcr; struct mmc_host *mmc; struct mmc_request *mrq; - struct mmc_command *cmd; - struct mmc_data *data; - - spinlock_t lock; - struct timer_list timer; - struct tasklet_struct cmd_tasklet; - struct tasklet_struct data_tasklet; - struct tasklet_struct finish_tasklet; - - u8 rsp_type; - u8 rsp_len; - int sg_count; + + struct mutex host_mutex; + u8 ssc_depth; unsigned int clock; bool vpclk; @@ -62,13 +48,8 @@ struct realtek_pci_sdmmc { int power_state; #define SDMMC_POWER_ON 1 #define SDMMC_POWER_OFF 0 - - struct realtek_next next_data; }; -static int sd_start_multi_rw(struct realtek_pci_sdmmc *host, - struct mmc_request *mrq); - static inline struct device *sdmmc_dev(struct realtek_pci_sdmmc *host) { return &(host->pdev->dev); @@ -105,95 +86,6 @@ static void sd_print_debug_regs(struct realtek_pci_sdmmc *host) #define sd_print_debug_regs(host) #endif /* DEBUG */ -static void sd_isr_done_transfer(struct platform_device *pdev) -{ - struct realtek_pci_sdmmc *host = platform_get_drvdata(pdev); - - spin_lock(&host->lock); - if (host->cmd) - tasklet_schedule(&host->cmd_tasklet); - if (host->data) - tasklet_schedule(&host->data_tasklet); - spin_unlock(&host->lock); -} - -static void sd_request_timeout(unsigned long host_addr) -{ - struct realtek_pci_sdmmc *host = (struct realtek_pci_sdmmc *)host_addr; - unsigned long flags; - - spin_lock_irqsave(&host->lock, flags); - - if (!host->mrq) { - dev_err(sdmmc_dev(host), "error: no request exist\n"); - goto out; - } - - if (host->cmd) - host->cmd->error = -ETIMEDOUT; - if (host->data) - host->data->error = -ETIMEDOUT; - - dev_dbg(sdmmc_dev(host), "timeout for request\n"); - -out: - tasklet_schedule(&host->finish_tasklet); - spin_unlock_irqrestore(&host->lock, flags); -} - -static void sd_finish_request(unsigned long host_addr) -{ - struct realtek_pci_sdmmc *host = (struct realtek_pci_sdmmc *)host_addr; - struct rtsx_pcr *pcr = host->pcr; - struct mmc_request *mrq; - struct mmc_command *cmd; - struct mmc_data *data; - unsigned long flags; - bool any_error; - - spin_lock_irqsave(&host->lock, flags); - - del_timer(&host->timer); - mrq = host->mrq; - if (!mrq) { - dev_err(sdmmc_dev(host), "error: no request need finish\n"); - goto out; - } - - cmd = mrq->cmd; - data = mrq->data; - - any_error = (mrq->sbc && mrq->sbc->error) || - (mrq->stop && mrq->stop->error) || - (cmd && cmd->error) || (data && data->error); - - if (any_error) { - rtsx_pci_stop_cmd(pcr); - sd_clear_error(host); - } - - if (data) { - if (any_error) - data->bytes_xfered = 0; - else - data->bytes_xfered = data->blocks * data->blksz; - - if (!data->host_cookie) - rtsx_pci_dma_unmap_sg(pcr, data->sg, data->sg_len, - data->flags & MMC_DATA_READ); - - } - - host->mrq = NULL; - host->cmd = NULL; - host->data = NULL; - -out: - spin_unlock_irqrestore(&host->lock, flags); - mutex_unlock(&pcr->pcr_mutex); - mmc_request_done(host->mmc, mrq); -} - static int sd_read_data(struct realtek_pci_sdmmc *host, u8 *cmd, u16 byte_cnt, u8 *buf, int buf_len, int timeout) { @@ -311,7 +203,8 @@ static int sd_write_data(struct realtek_pci_sdmmc *host, u8 *cmd, u16 byte_cnt, return 0; } -static void sd_send_cmd(struct realtek_pci_sdmmc *host, struct mmc_command *cmd) +static void sd_send_cmd_get_rsp(struct realtek_pci_sdmmc *host, + struct mmc_command *cmd) { struct rtsx_pcr *pcr = host->pcr; u8 cmd_idx = (u8)cmd->opcode; @@ -319,14 +212,11 @@ static void sd_send_cmd(struct realtek_pci_sdmmc *host, struct mmc_command *cmd) int err = 0; int timeout = 100; int i; + u8 *ptr; + int stat_idx = 0; u8 rsp_type; int rsp_len = 5; - unsigned long flags; - - if (host->cmd) - dev_err(sdmmc_dev(host), "error: cmd already exist\n"); - - host->cmd = cmd; + bool clock_toggled = false; dev_dbg(sdmmc_dev(host), "%s: SD/MMC CMD %d, arg = 0x%08x\n", __func__, cmd_idx, arg); @@ -361,8 +251,6 @@ static void sd_send_cmd(struct realtek_pci_sdmmc *host, struct mmc_command *cmd) err = -EINVAL; goto out; } - host->rsp_type = rsp_type; - host->rsp_len = rsp_len; if (rsp_type == SD_RSP_TYPE_R1b) timeout = 3000; @@ -372,6 +260,8 @@ static void sd_send_cmd(struct realtek_pci_sdmmc *host, struct mmc_command *cmd) 0xFF, SD_CLK_TOGGLE_EN); if (err < 0) goto out; + + clock_toggled = true; } rtsx_pci_init_cmd(pcr); @@ -395,60 +285,25 @@ static void sd_send_cmd(struct realtek_pci_sdmmc *host, struct mmc_command *cmd) /* Read data from ping-pong buffer */ for (i = PPBUF_BASE2; i < PPBUF_BASE2 + 16; i++) rtsx_pci_add_cmd(pcr, READ_REG_CMD, (u16)i, 0, 0); + stat_idx = 16; } else if (rsp_type != SD_RSP_TYPE_R0) { /* Read data from SD_CMDx registers */ for (i = SD_CMD0; i <= SD_CMD4; i++) rtsx_pci_add_cmd(pcr, READ_REG_CMD, (u16)i, 0, 0); + stat_idx = 5; } rtsx_pci_add_cmd(pcr, READ_REG_CMD, SD_STAT1, 0, 0); - mod_timer(&host->timer, jiffies + msecs_to_jiffies(timeout)); - - spin_lock_irqsave(&pcr->lock, flags); - pcr->trans_result = TRANS_NOT_READY; - rtsx_pci_send_cmd_no_wait(pcr); - spin_unlock_irqrestore(&pcr->lock, flags); - - return; - -out: - cmd->error = err; - tasklet_schedule(&host->finish_tasklet); -} - -static void sd_get_rsp(unsigned long host_addr) -{ - struct realtek_pci_sdmmc *host = (struct realtek_pci_sdmmc *)host_addr; - struct rtsx_pcr *pcr = host->pcr; - struct mmc_command *cmd; - int i, err = 0, stat_idx; - u8 *ptr, rsp_type; - unsigned long flags; - - spin_lock_irqsave(&host->lock, flags); - - cmd = host->cmd; - host->cmd = NULL; - - if (!cmd) { - dev_err(sdmmc_dev(host), "error: cmd not exist\n"); + err = rtsx_pci_send_cmd(pcr, timeout); + if (err < 0) { + sd_print_debug_regs(host); + sd_clear_error(host); + dev_dbg(sdmmc_dev(host), + "rtsx_pci_send_cmd error (err = %d)\n", err); goto out; } - spin_lock(&pcr->lock); - if (pcr->trans_result == TRANS_NO_DEVICE) - err = -ENODEV; - else if (pcr->trans_result != TRANS_RESULT_OK) - err = -EINVAL; - spin_unlock(&pcr->lock); - - if (err < 0) - goto out; - - rsp_type = host->rsp_type; - stat_idx = host->rsp_len; - if (rsp_type == SD_RSP_TYPE_R0) { err = 0; goto out; @@ -485,106 +340,26 @@ static void sd_get_rsp(unsigned long host_addr) cmd->resp[0]); } - if (cmd == host->mrq->sbc) { - sd_send_cmd(host, host->mrq->cmd); - spin_unlock_irqrestore(&host->lock, flags); - return; - } - - if (cmd == host->mrq->stop) - goto out; - - if (cmd->data) { - sd_start_multi_rw(host, host->mrq); - spin_unlock_irqrestore(&host->lock, flags); - return; - } - out: cmd->error = err; - tasklet_schedule(&host->finish_tasklet); - spin_unlock_irqrestore(&host->lock, flags); -} - -static int sd_pre_dma_transfer(struct realtek_pci_sdmmc *host, - struct mmc_data *data, struct realtek_next *next) -{ - struct rtsx_pcr *pcr = host->pcr; - int read = data->flags & MMC_DATA_READ; - int sg_count = 0; - - if (!next && data->host_cookie && - data->host_cookie != host->next_data.cookie) { - dev_err(sdmmc_dev(host), - "error: invalid cookie data[%d] host[%d]\n", - data->host_cookie, host->next_data.cookie); - data->host_cookie = 0; - } - - if (next || (!next && data->host_cookie != host->next_data.cookie)) - sg_count = rtsx_pci_dma_map_sg(pcr, - data->sg, data->sg_len, read); - else - sg_count = host->next_data.sg_count; - - if (next) { - next->sg_count = sg_count; - if (++next->cookie < 0) - next->cookie = 1; - data->host_cookie = next->cookie; - } - - return sg_count; -} - -static void sdmmc_pre_req(struct mmc_host *mmc, struct mmc_request *mrq, - bool is_first_req) -{ - struct realtek_pci_sdmmc *host = mmc_priv(mmc); - struct mmc_data *data = mrq->data; - - if (data->host_cookie) { - dev_err(sdmmc_dev(host), - "error: descard already cookie data[%d]\n", - data->host_cookie); - data->host_cookie = 0; - } - - dev_dbg(sdmmc_dev(host), "dma sg prepared: %d\n", - sd_pre_dma_transfer(host, data, &host->next_data)); -} - -static void sdmmc_post_req(struct mmc_host *mmc, struct mmc_request *mrq, - int err) -{ - struct realtek_pci_sdmmc *host = mmc_priv(mmc); - struct rtsx_pcr *pcr = host->pcr; - struct mmc_data *data = mrq->data; - int read = data->flags & MMC_DATA_READ; - - rtsx_pci_dma_unmap_sg(pcr, data->sg, data->sg_len, read); - data->host_cookie = 0; + if (err && clock_toggled) + rtsx_pci_write_register(pcr, SD_BUS_STAT, + SD_CLK_TOGGLE_EN | SD_CLK_FORCE_STOP, 0); } -static int sd_start_multi_rw(struct realtek_pci_sdmmc *host, - struct mmc_request *mrq) +static int sd_rw_multi(struct realtek_pci_sdmmc *host, struct mmc_request *mrq) { struct rtsx_pcr *pcr = host->pcr; struct mmc_host *mmc = host->mmc; struct mmc_card *card = mmc->card; struct mmc_data *data = mrq->data; int uhs = mmc_card_uhs(card); - int read = data->flags & MMC_DATA_READ; + int read = (data->flags & MMC_DATA_READ) ? 1 : 0; u8 cfg2, trans_mode; int err; size_t data_len = data->blksz * data->blocks; - if (host->data) - dev_err(sdmmc_dev(host), "error: data already exist\n"); - - host->data = data; - if (read) { cfg2 = SD_CALCULATE_CRC7 | SD_CHECK_CRC16 | SD_NO_WAIT_BUSY_END | SD_CHECK_CRC7 | SD_RSP_LEN_0; @@ -635,54 +410,15 @@ static int sd_start_multi_rw(struct realtek_pci_sdmmc *host, rtsx_pci_add_cmd(pcr, CHECK_REG_CMD, SD_TRANSFER, SD_TRANSFER_END, SD_TRANSFER_END); - mod_timer(&host->timer, jiffies + 10 * HZ); rtsx_pci_send_cmd_no_wait(pcr); - err = rtsx_pci_dma_transfer(pcr, data->sg, host->sg_count, read); - if (err < 0) { - data->error = err; - tasklet_schedule(&host->finish_tasklet); - } - return 0; -} - -static void sd_finish_multi_rw(unsigned long host_addr) -{ - struct realtek_pci_sdmmc *host = (struct realtek_pci_sdmmc *)host_addr; - struct rtsx_pcr *pcr = host->pcr; - struct mmc_data *data; - int err = 0; - unsigned long flags; - - spin_lock_irqsave(&host->lock, flags); - - if (!host->data) { - dev_err(sdmmc_dev(host), "error: no data exist\n"); - goto out; - } - - data = host->data; - host->data = NULL; - - if (pcr->trans_result == TRANS_NO_DEVICE) - err = -ENODEV; - else if (pcr->trans_result != TRANS_RESULT_OK) - err = -EINVAL; - + err = rtsx_pci_transfer_data(pcr, data->sg, data->sg_len, read, 10000); if (err < 0) { - data->error = err; - goto out; - } - - if (!host->mrq->sbc && data->stop) { - sd_send_cmd(host, data->stop); - spin_unlock_irqrestore(&host->lock, flags); - return; + sd_clear_error(host); + return err; } -out: - tasklet_schedule(&host->finish_tasklet); - spin_unlock_irqrestore(&host->lock, flags); + return 0; } static inline void sd_enable_initial_mode(struct realtek_pci_sdmmc *host) @@ -901,13 +637,6 @@ static int sd_tuning_rx(struct realtek_pci_sdmmc *host, u8 opcode) return 0; } -static inline bool sd_use_muti_rw(struct mmc_command *cmd) -{ - return mmc_op_multi(cmd->opcode) || - (cmd->opcode == MMC_READ_SINGLE_BLOCK) || - (cmd->opcode == MMC_WRITE_BLOCK); -} - static void sdmmc_request(struct mmc_host *mmc, struct mmc_request *mrq) { struct realtek_pci_sdmmc *host = mmc_priv(mmc); @@ -916,14 +645,6 @@ static void sdmmc_request(struct mmc_host *mmc, struct mmc_request *mrq) struct mmc_data *data = mrq->data; unsigned int data_size = 0; int err; - unsigned long flags; - - mutex_lock(&pcr->pcr_mutex); - spin_lock_irqsave(&host->lock, flags); - - if (host->mrq) - dev_err(sdmmc_dev(host), "error: request already exist\n"); - host->mrq = mrq; if (host->eject) { cmd->error = -ENOMEDIUM; @@ -936,6 +657,8 @@ static void sdmmc_request(struct mmc_host *mmc, struct mmc_request *mrq) goto finish; } + mutex_lock(&pcr->pcr_mutex); + rtsx_pci_start_run(pcr); rtsx_pci_switch_clock(pcr, host->clock, host->ssc_depth, @@ -944,28 +667,46 @@ static void sdmmc_request(struct mmc_host *mmc, struct mmc_request *mrq) rtsx_pci_write_register(pcr, CARD_SHARE_MODE, CARD_SHARE_MASK, CARD_SHARE_48_SD); + mutex_lock(&host->host_mutex); + host->mrq = mrq; + mutex_unlock(&host->host_mutex); + if (mrq->data) data_size = data->blocks * data->blksz; - if (sd_use_muti_rw(cmd)) - host->sg_count = sd_pre_dma_transfer(host, data, NULL); + if (!data_size || mmc_op_multi(cmd->opcode) || + (cmd->opcode == MMC_READ_SINGLE_BLOCK) || + (cmd->opcode == MMC_WRITE_BLOCK)) { + sd_send_cmd_get_rsp(host, cmd); - if (!data_size || sd_use_muti_rw(cmd)) { - if (mrq->sbc) - sd_send_cmd(host, mrq->sbc); - else - sd_send_cmd(host, cmd); - spin_unlock_irqrestore(&host->lock, flags); + if (!cmd->error && data_size) { + sd_rw_multi(host, mrq); + + if (mmc_op_multi(cmd->opcode) && mrq->stop) + sd_send_cmd_get_rsp(host, mrq->stop); + } } else { - spin_unlock_irqrestore(&host->lock, flags); sd_normal_rw(host, mrq); - tasklet_schedule(&host->finish_tasklet); } - return; + + if (mrq->data) { + if (cmd->error || data->error) + data->bytes_xfered = 0; + else + data->bytes_xfered = data->blocks * data->blksz; + } + + mutex_unlock(&pcr->pcr_mutex); finish: - tasklet_schedule(&host->finish_tasklet); - spin_unlock_irqrestore(&host->lock, flags); + if (cmd->error) + dev_dbg(sdmmc_dev(host), "cmd->error = %d\n", cmd->error); + + mutex_lock(&host->host_mutex); + host->mrq = NULL; + mutex_unlock(&host->host_mutex); + + mmc_request_done(mmc, mrq); } static int sd_set_bus_width(struct realtek_pci_sdmmc *host, @@ -1400,8 +1141,6 @@ out: } static const struct mmc_host_ops realtek_pci_sdmmc_ops = { - .pre_req = sdmmc_pre_req, - .post_req = sdmmc_post_req, .request = sdmmc_request, .set_ios = sdmmc_set_ios, .get_ro = sdmmc_get_ro, @@ -1465,7 +1204,6 @@ static int rtsx_pci_sdmmc_drv_probe(struct platform_device *pdev) struct realtek_pci_sdmmc *host; struct rtsx_pcr *pcr; struct pcr_handle *handle = pdev->dev.platform_data; - unsigned long host_addr; if (!handle) return -ENXIO; @@ -1489,15 +1227,8 @@ static int rtsx_pci_sdmmc_drv_probe(struct platform_device *pdev) pcr->slots[RTSX_SD_CARD].p_dev = pdev; pcr->slots[RTSX_SD_CARD].card_event = rtsx_pci_sdmmc_card_event; - host_addr = (unsigned long)host; - host->next_data.cookie = 1; - setup_timer(&host->timer, sd_request_timeout, host_addr); - tasklet_init(&host->cmd_tasklet, sd_get_rsp, host_addr); - tasklet_init(&host->data_tasklet, sd_finish_multi_rw, host_addr); - tasklet_init(&host->finish_tasklet, sd_finish_request, host_addr); - spin_lock_init(&host->lock); + mutex_init(&host->host_mutex); - pcr->slots[RTSX_SD_CARD].done_transfer = sd_isr_done_transfer; realtek_init_host(host); mmc_add_host(mmc); @@ -1510,8 +1241,6 @@ static int rtsx_pci_sdmmc_drv_remove(struct platform_device *pdev) struct realtek_pci_sdmmc *host = platform_get_drvdata(pdev); struct rtsx_pcr *pcr; struct mmc_host *mmc; - struct mmc_request *mrq; - unsigned long flags; if (!host) return 0; @@ -1519,33 +1248,22 @@ static int rtsx_pci_sdmmc_drv_remove(struct platform_device *pdev) pcr = host->pcr; pcr->slots[RTSX_SD_CARD].p_dev = NULL; pcr->slots[RTSX_SD_CARD].card_event = NULL; - pcr->slots[RTSX_SD_CARD].done_transfer = NULL; mmc = host->mmc; - mrq = host->mrq; - spin_lock_irqsave(&host->lock, flags); + mutex_lock(&host->host_mutex); if (host->mrq) { dev_dbg(&(pdev->dev), "%s: Controller removed during transfer\n", mmc_hostname(mmc)); - if (mrq->sbc) - mrq->sbc->error = -ENOMEDIUM; - if (mrq->cmd) - mrq->cmd->error = -ENOMEDIUM; - if (mrq->stop) - mrq->stop->error = -ENOMEDIUM; - if (mrq->data) - mrq->data->error = -ENOMEDIUM; + rtsx_pci_complete_unfinished_transfer(pcr); - tasklet_schedule(&host->finish_tasklet); + host->mrq->cmd->error = -ENOMEDIUM; + if (host->mrq->stop) + host->mrq->stop->error = -ENOMEDIUM; + mmc_request_done(mmc, host->mrq); } - spin_unlock_irqrestore(&host->lock, flags); - - del_timer_sync(&host->timer); - tasklet_kill(&host->cmd_tasklet); - tasklet_kill(&host->data_tasklet); - tasklet_kill(&host->finish_tasklet); + mutex_unlock(&host->host_mutex); mmc_remove_host(mmc); host->eject = true; diff --git a/include/linux/mfd/rtsx_common.h b/include/linux/mfd/rtsx_common.h index 7c36cc55d2c..443176ee1ab 100644 --- a/include/linux/mfd/rtsx_common.h +++ b/include/linux/mfd/rtsx_common.h @@ -45,7 +45,6 @@ struct platform_device; struct rtsx_slot { struct platform_device *p_dev; void (*card_event)(struct platform_device *p_dev); - void (*done_transfer)(struct platform_device *p_dev); }; #endif diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h index 8d6bbd609ad..a3835976f7c 100644 --- a/include/linux/mfd/rtsx_pci.h +++ b/include/linux/mfd/rtsx_pci.h @@ -943,12 +943,6 @@ void rtsx_pci_send_cmd_no_wait(struct rtsx_pcr *pcr); int rtsx_pci_send_cmd(struct rtsx_pcr *pcr, int timeout); int rtsx_pci_transfer_data(struct rtsx_pcr *pcr, struct scatterlist *sglist, int num_sg, bool read, int timeout); -int rtsx_pci_dma_map_sg(struct rtsx_pcr *pcr, struct scatterlist *sglist, - int num_sg, bool read); -int rtsx_pci_dma_unmap_sg(struct rtsx_pcr *pcr, struct scatterlist *sglist, - int num_sg, bool read); -int rtsx_pci_dma_transfer(struct rtsx_pcr *pcr, struct scatterlist *sglist, - int sg_count, bool read); int rtsx_pci_read_ppbuf(struct rtsx_pcr *pcr, u8 *buf, int buf_len); int rtsx_pci_write_ppbuf(struct rtsx_pcr *pcr, u8 *buf, int buf_len); int rtsx_pci_card_pull_ctl_enable(struct rtsx_pcr *pcr, int card); -- cgit v1.2.3-70-g09d2 From 098507ae3ec2331476fb52e85d4040c1cc6d0ef4 Mon Sep 17 00:00:00 2001 From: Romain Izard Date: Tue, 4 Mar 2014 10:09:39 +0100 Subject: trace: module: Maintain a valid user count The replacement of the 'count' variable by two variables 'incs' and 'decs' to resolve some race conditions during module unloading was done in parallel with some cleanup in the trace subsystem, and was integrated as a merge. Unfortunately, the formula for this replacement was wrong in the tracing code, and the refcount in the traces was not usable as a result. Use 'count = incs - decs' to compute the user count. Link: http://lkml.kernel.org/p/1393924179-9147-1-git-send-email-romain.izard.pro@gmail.com Acked-by: Ingo Molnar Cc: Rusty Russell Cc: Frederic Weisbecker Cc: stable@vger.kernel.org # 2.6.35 Fixes: c1ab9cab7509 "merge conflict resolution" Signed-off-by: Romain Izard Signed-off-by: Steven Rostedt --- include/trace/events/module.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/module.h b/include/trace/events/module.h index 11fd51b413d..daa60c73945 100644 --- a/include/trace/events/module.h +++ b/include/trace/events/module.h @@ -80,7 +80,7 @@ DECLARE_EVENT_CLASS(module_refcnt, TP_fast_assign( __entry->ip = ip; - __entry->refcnt = __this_cpu_read(mod->refptr->incs) + __this_cpu_read(mod->refptr->decs); + __entry->refcnt = __this_cpu_read(mod->refptr->incs) - __this_cpu_read(mod->refptr->decs); __assign_str(name, mod->name); ), -- cgit v1.2.3-70-g09d2 From c9d8f1a64225dfcc2f721d73a5984a2444920744 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 6 May 2014 11:02:49 -0700 Subject: ipv4: move local_port_range out of CONFIG_SYSCTL When CONFIG_SYSCTL is not set, ip_local_port_range should still work, just that no one can change it. Therefore we should move it out of sysctl_inet.c. Also, rename it to ->ip_local_ports instead. Cc: David S. Miller Cc: Francois Romieu Reported-by: Stefan de Konink Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 2 +- net/ipv4/af_inet.c | 28 ++++++++++++++++++++++++++++ net/ipv4/inet_connection_sock.c | 8 ++++---- net/ipv4/ping.c | 4 ++-- net/ipv4/sysctl_net_ipv4.c | 29 +++++++++++------------------ 5 files changed, 46 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 80f500a2949..3d95cd47531 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -66,7 +66,7 @@ struct netns_ipv4 { int sysctl_icmp_ratemask; int sysctl_icmp_errors_use_inbound_ifaddr; - struct local_ports sysctl_local_ports; + struct local_ports ip_local_ports; int sysctl_tcp_ecn; int sysctl_ip_no_pmtu_disc; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 8c54870db79..cccc8e487c7 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1650,6 +1650,31 @@ static int __init init_ipv4_mibs(void) return register_pernet_subsys(&ipv4_mib_ops); } +static __net_init int inet_init_net(struct net *net) +{ + /* + * Set defaults for local port range + */ + seqlock_init(&net->ipv4.ip_local_ports.lock); + net->ipv4.ip_local_ports.range[0] = 32768; + net->ipv4.ip_local_ports.range[1] = 61000; + return 0; +} + +static __net_exit void inet_exit_net(struct net *net) +{ +} + +static __net_initdata struct pernet_operations af_inet_ops = { + .init = inet_init_net, + .exit = inet_exit_net, +}; + +static int __init init_inet_pernet_ops(void) +{ + return register_pernet_subsys(&af_inet_ops); +} + static int ipv4_proc_init(void); /* @@ -1794,6 +1819,9 @@ static int __init inet_init(void) if (ip_mr_init()) pr_crit("%s: Cannot init ipv4 mroute\n", __func__); #endif + + if (init_inet_pernet_ops()) + pr_crit("%s: Cannot init ipv4 inet pernet ops\n", __func__); /* * Initialise per-cpu ipv4 mibs */ diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 0d1e2cb877e..a56b8e6e866 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -37,11 +37,11 @@ void inet_get_local_port_range(struct net *net, int *low, int *high) unsigned int seq; do { - seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock); + seq = read_seqbegin(&net->ipv4.ip_local_ports.lock); - *low = net->ipv4.sysctl_local_ports.range[0]; - *high = net->ipv4.sysctl_local_ports.range[1]; - } while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq)); + *low = net->ipv4.ip_local_ports.range[0]; + *high = net->ipv4.ip_local_ports.range[1]; + } while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq)); } EXPORT_SYMBOL(inet_get_local_port_range); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 8210964a9f1..347bdde9a58 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -240,11 +240,11 @@ static void inet_get_ping_group_range_net(struct net *net, kgid_t *low, unsigned int seq; do { - seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock); + seq = read_seqbegin(&net->ipv4.ip_local_ports.lock); *low = data[0]; *high = data[1]; - } while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq)); + } while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq)); } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 44eba052b43..a116c41b05d 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -45,10 +45,10 @@ static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; /* Update system visible IP port range */ static void set_local_port_range(struct net *net, int range[2]) { - write_seqlock(&net->ipv4.sysctl_local_ports.lock); - net->ipv4.sysctl_local_ports.range[0] = range[0]; - net->ipv4.sysctl_local_ports.range[1] = range[1]; - write_sequnlock(&net->ipv4.sysctl_local_ports.lock); + write_seqlock(&net->ipv4.ip_local_ports.lock); + net->ipv4.ip_local_ports.range[0] = range[0]; + net->ipv4.ip_local_ports.range[1] = range[1]; + write_sequnlock(&net->ipv4.ip_local_ports.lock); } /* Validate changes from /proc interface. */ @@ -57,7 +57,7 @@ static int ipv4_local_port_range(struct ctl_table *table, int write, size_t *lenp, loff_t *ppos) { struct net *net = - container_of(table->data, struct net, ipv4.sysctl_local_ports.range); + container_of(table->data, struct net, ipv4.ip_local_ports.range); int ret; int range[2]; struct ctl_table tmp = { @@ -90,11 +90,11 @@ static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low container_of(table->data, struct net, ipv4.sysctl_ping_group_range); unsigned int seq; do { - seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock); + seq = read_seqbegin(&net->ipv4.ip_local_ports.lock); *low = data[0]; *high = data[1]; - } while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq)); + } while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq)); } /* Update system visible IP port range */ @@ -103,10 +103,10 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig kgid_t *data = table->data; struct net *net = container_of(table->data, struct net, ipv4.sysctl_ping_group_range); - write_seqlock(&net->ipv4.sysctl_local_ports.lock); + write_seqlock(&net->ipv4.ip_local_ports.lock); data[0] = low; data[1] = high; - write_sequnlock(&net->ipv4.sysctl_local_ports.lock); + write_sequnlock(&net->ipv4.ip_local_ports.lock); } /* Validate changes from /proc interface. */ @@ -819,8 +819,8 @@ static struct ctl_table ipv4_net_table[] = { }, { .procname = "ip_local_port_range", - .maxlen = sizeof(init_net.ipv4.sysctl_local_ports.range), - .data = &init_net.ipv4.sysctl_local_ports.range, + .maxlen = sizeof(init_net.ipv4.ip_local_ports.range), + .data = &init_net.ipv4.ip_local_ports.range, .mode = 0644, .proc_handler = ipv4_local_port_range, }, @@ -865,13 +865,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) net->ipv4.sysctl_ping_group_range[0] = make_kgid(&init_user_ns, 1); net->ipv4.sysctl_ping_group_range[1] = make_kgid(&init_user_ns, 0); - /* - * Set defaults for local port range - */ - seqlock_init(&net->ipv4.sysctl_local_ports.lock); - net->ipv4.sysctl_local_ports.range[0] = 32768; - net->ipv4.sysctl_local_ports.range[1] = 61000; - net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table); if (net->ipv4.ipv4_hdr == NULL) goto err_reg; -- cgit v1.2.3-70-g09d2 From ba6b918ab234186d3aa1663e296586a1b526b77a Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 6 May 2014 11:02:50 -0700 Subject: ping: move ping_group_range out of CONFIG_SYSCTL Similarly, when CONFIG_SYSCTL is not set, ping_group_range should still work, just that no one can change it. Therefore we should move it out of sysctl_net_ipv4.c. And, it should not share the same seqlock with ip_local_port_range. BTW, rename it to ->ping_group_range instead. Cc: David S. Miller Cc: Francois Romieu Reported-by: Stefan de Konink Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 7 ++++++- net/ipv4/af_inet.c | 8 ++++++++ net/ipv4/ping.c | 6 +++--- net/ipv4/sysctl_net_ipv4.c | 13 +++---------- 4 files changed, 20 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 3d95cd47531..b2704fd0ec8 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -20,6 +20,11 @@ struct local_ports { int range[2]; }; +struct ping_group_range { + seqlock_t lock; + kgid_t range[2]; +}; + struct netns_ipv4 { #ifdef CONFIG_SYSCTL struct ctl_table_header *forw_hdr; @@ -72,7 +77,7 @@ struct netns_ipv4 { int sysctl_ip_no_pmtu_disc; int sysctl_ip_fwd_use_pmtu; - kgid_t sysctl_ping_group_range[2]; + struct ping_group_range ping_group_range; atomic_t dev_addr_genid; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index cccc8e487c7..6d6dd345bc4 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1658,6 +1658,14 @@ static __net_init int inet_init_net(struct net *net) seqlock_init(&net->ipv4.ip_local_ports.lock); net->ipv4.ip_local_ports.range[0] = 32768; net->ipv4.ip_local_ports.range[1] = 61000; + + seqlock_init(&net->ipv4.ping_group_range.lock); + /* + * Sane defaults - nobody may create ping sockets. + * Boot scripts should set this to distro-specific group. + */ + net->ipv4.ping_group_range.range[0] = make_kgid(&init_user_ns, 1); + net->ipv4.ping_group_range.range[1] = make_kgid(&init_user_ns, 0); return 0; } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 347bdde9a58..044a0ddf6a7 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -236,15 +236,15 @@ exit: static void inet_get_ping_group_range_net(struct net *net, kgid_t *low, kgid_t *high) { - kgid_t *data = net->ipv4.sysctl_ping_group_range; + kgid_t *data = net->ipv4.ping_group_range.range; unsigned int seq; do { - seq = read_seqbegin(&net->ipv4.ip_local_ports.lock); + seq = read_seqbegin(&net->ipv4.ping_group_range.lock); *low = data[0]; *high = data[1]; - } while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq)); + } while (read_seqretry(&net->ipv4.ping_group_range.lock, seq)); } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index a116c41b05d..5cde8f263d4 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -87,7 +87,7 @@ static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low { kgid_t *data = table->data; struct net *net = - container_of(table->data, struct net, ipv4.sysctl_ping_group_range); + container_of(table->data, struct net, ipv4.ping_group_range.range); unsigned int seq; do { seq = read_seqbegin(&net->ipv4.ip_local_ports.lock); @@ -102,7 +102,7 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig { kgid_t *data = table->data; struct net *net = - container_of(table->data, struct net, ipv4.sysctl_ping_group_range); + container_of(table->data, struct net, ipv4.ping_group_range.range); write_seqlock(&net->ipv4.ip_local_ports.lock); data[0] = low; data[1] = high; @@ -805,7 +805,7 @@ static struct ctl_table ipv4_net_table[] = { }, { .procname = "ping_group_range", - .data = &init_net.ipv4.sysctl_ping_group_range, + .data = &init_net.ipv4.ping_group_range.range, .maxlen = sizeof(gid_t)*2, .mode = 0644, .proc_handler = ipv4_ping_group_range, @@ -858,13 +858,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) table[i].data += (void *)net - (void *)&init_net; } - /* - * Sane defaults - nobody may create ping sockets. - * Boot scripts should set this to distro-specific group. - */ - net->ipv4.sysctl_ping_group_range[0] = make_kgid(&init_user_ns, 1); - net->ipv4.sysctl_ping_group_range[1] = make_kgid(&init_user_ns, 0); - net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table); if (net->ipv4.ipv4_hdr == NULL) goto err_reg; -- cgit v1.2.3-70-g09d2 From 555724a831b4a146e7bdf16ecc989cda032b076d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 12 May 2014 13:56:27 -0400 Subject: kernfs, sysfs, cgroup: restrict extra perm check on open to sysfs The kernfs open method - kernfs_fop_open() - inherited extra permission checks from sysfs. While the vfs layer allows ignoring the read/write permissions checks if the issuer has CAP_DAC_OVERRIDE, sysfs explicitly denied open regardless of the cap if the file doesn't have any of the UGO perms of the requested access or doesn't implement the requested operation. It can be debated whether this was a good idea or not but the behavior is too subtle and dangerous to change at this point. After cgroup got converted to kernfs, this extra perm check also got applied to cgroup breaking libcgroup which opens write-only files with O_RDWR as root. This patch gates the extra open permission check with a new flag KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK and enables it for sysfs. For sysfs, nothing changes. For cgroup, root now can perform any operation regardless of the permissions as it was before kernfs conversion. Note that kernfs still fails unimplemented operations with -EINVAL. While at it, add comments explaining KERNFS_ROOT flags. Signed-off-by: Tejun Heo Reported-by: Andrey Wagin Tested-by: Andrey Wagin Cc: Li Zefan References: http://lkml.kernel.org/g/CANaxB-xUm3rJ-Cbp72q-rQJO5mZe1qK6qXsQM=vh0U8upJ44+A@mail.gmail.com Fixes: 2bd59d48ebfb ("cgroup: convert to kernfs") Signed-off-by: Greg Kroah-Hartman --- fs/kernfs/file.c | 17 ++++++++++------- fs/sysfs/mount.c | 3 ++- include/linux/kernfs.h | 19 ++++++++++++++++++- 3 files changed, 30 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index e01ea4a14a0..5e9a80cfc3d 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -610,6 +610,7 @@ static void kernfs_put_open_node(struct kernfs_node *kn, static int kernfs_fop_open(struct inode *inode, struct file *file) { struct kernfs_node *kn = file->f_path.dentry->d_fsdata; + struct kernfs_root *root = kernfs_root(kn); const struct kernfs_ops *ops; struct kernfs_open_file *of; bool has_read, has_write, has_mmap; @@ -624,14 +625,16 @@ static int kernfs_fop_open(struct inode *inode, struct file *file) has_write = ops->write || ops->mmap; has_mmap = ops->mmap; - /* check perms and supported operations */ - if ((file->f_mode & FMODE_WRITE) && - (!(inode->i_mode & S_IWUGO) || !has_write)) - goto err_out; + /* see the flag definition for details */ + if (root->flags & KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK) { + if ((file->f_mode & FMODE_WRITE) && + (!(inode->i_mode & S_IWUGO) || !has_write)) + goto err_out; - if ((file->f_mode & FMODE_READ) && - (!(inode->i_mode & S_IRUGO) || !has_read)) - goto err_out; + if ((file->f_mode & FMODE_READ) && + (!(inode->i_mode & S_IRUGO) || !has_read)) + goto err_out; + } /* allocate a kernfs_open_file for the file */ error = -ENOMEM; diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index a66ad6196f5..8794423f7ef 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -63,7 +63,8 @@ int __init sysfs_init(void) { int err; - sysfs_root = kernfs_create_root(NULL, 0, NULL); + sysfs_root = kernfs_create_root(NULL, KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK, + NULL); if (IS_ERR(sysfs_root)) return PTR_ERR(sysfs_root); diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index b0122dc6f96..ca1be5c9136 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -50,7 +50,24 @@ enum kernfs_node_flag { /* @flags for kernfs_create_root() */ enum kernfs_root_flag { - KERNFS_ROOT_CREATE_DEACTIVATED = 0x0001, + /* + * kernfs_nodes are created in the deactivated state and invisible. + * They require explicit kernfs_activate() to become visible. This + * can be used to make related nodes become visible atomically + * after all nodes are created successfully. + */ + KERNFS_ROOT_CREATE_DEACTIVATED = 0x0001, + + /* + * For regular flies, if the opener has CAP_DAC_OVERRIDE, open(2) + * succeeds regardless of the RW permissions. sysfs had an extra + * layer of enforcement where open(2) fails with -EACCES regardless + * of CAP_DAC_OVERRIDE if the permission doesn't have the + * respective read or write access at all (none of S_IRUGO or + * S_IWUGO) or the respective operation isn't implemented. The + * following flag enables that behavior. + */ + KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK = 0x0002, }; /* type-specific structures for kernfs_node union members */ -- cgit v1.2.3-70-g09d2 From f5651986fe438c1ba05fdafa383d38bd86713d13 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 13 May 2014 15:45:55 +0200 Subject: nl80211: fix NL80211_FEATURE_P2P_DEVICE_NEEDS_CHANNEL API My commit removing that also removed it from the header file which can break compilation of userspace that needed it, add it back for API/ABI compatibility purposes (but no code to implement anything for it.) Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 1ba9d626aa8..194c1eab04d 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3856,6 +3856,8 @@ enum nl80211_ap_sme_features { * @NL80211_FEATURE_CELL_BASE_REG_HINTS: This driver has been tested * to work properly to suppport receiving regulatory hints from * cellular base stations. + * @NL80211_FEATURE_P2P_DEVICE_NEEDS_CHANNEL: (no longer available, only + * here to reserve the value for API/ABI compatibility) * @NL80211_FEATURE_SAE: This driver supports simultaneous authentication of * equals (SAE) with user space SME (NL80211_CMD_AUTHENTICATE) in station * mode @@ -3897,7 +3899,7 @@ enum nl80211_feature_flags { NL80211_FEATURE_HT_IBSS = 1 << 1, NL80211_FEATURE_INACTIVITY_TIMER = 1 << 2, NL80211_FEATURE_CELL_BASE_REG_HINTS = 1 << 3, - /* bit 4 is reserved - don't use */ + NL80211_FEATURE_P2P_DEVICE_NEEDS_CHANNEL = 1 << 4, NL80211_FEATURE_SAE = 1 << 5, NL80211_FEATURE_LOW_PRIORITY_SCAN = 1 << 6, NL80211_FEATURE_SCAN_FLUSH = 1 << 7, -- cgit v1.2.3-70-g09d2 From 5024ae29cd285ce9e736776414da645d3a91828c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 7 May 2014 21:31:17 -0400 Subject: cgroup: introduce task_css_is_root() Determining the css of a task usually requires RCU read lock as that's the only thing which keeps the returned css accessible till its reference is acquired; however, testing whether a task belongs to the root can be performed without dereferencing the returned css by comparing the returned pointer against the root one in init_css_set[] which never changes. Implement task_css_is_root() which can be invoked in any context. This will be used by the scheduled cgroup_freezer change. v2: cgroup no longer supports modular controllers. No need to export init_css_set. Pointed out by Li. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 15 +++++++++++++++ kernel/cgroup.c | 2 +- 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index c2515851c1a..d60904b9e50 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -473,6 +473,7 @@ struct cftype { }; extern struct cgroup_root cgrp_dfl_root; +extern struct css_set init_css_set; static inline bool cgroup_on_dfl(const struct cgroup *cgrp) { @@ -700,6 +701,20 @@ static inline struct cgroup_subsys_state *task_css(struct task_struct *task, return task_css_check(task, subsys_id, false); } +/** + * task_css_is_root - test whether a task belongs to the root css + * @task: the target task + * @subsys_id: the target subsystem ID + * + * Test whether @task belongs to the root css on the specified subsystem. + * May be invoked in any context. + */ +static inline bool task_css_is_root(struct task_struct *task, int subsys_id) +{ + return task_css_check(task, subsys_id, true) == + init_css_set.subsys[subsys_id]; +} + static inline struct cgroup *task_cgroup(struct task_struct *task, int subsys_id) { diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 11a03d67635..3f1ca934a23 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -348,7 +348,7 @@ struct cgrp_cset_link { * reference-counted, to improve performance when child cgroups * haven't been created. */ -static struct css_set init_css_set = { +struct css_set init_css_set = { .refcount = ATOMIC_INIT(1), .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links), .tasks = LIST_HEAD_INIT(init_css_set.tasks), -- cgit v1.2.3-70-g09d2 From f2d0801f00b7aff0ac6b3666cbcdab499267418a Mon Sep 17 00:00:00 2001 From: Markos Chandras Date: Tue, 22 Apr 2014 15:40:36 +0100 Subject: MIPS: Add new AUDIT_ARCH token for the N32 ABI on MIPS64 A MIPS64 kernel may support ELF files for all 3 MIPS ABIs (O32, N32, N64). Furthermore, the AUDIT_ARCH_MIPS{,EL}64 token does not provide enough information about the ABI for the 64-bit process. As a result of which, userland needs to use complex seccomp filters to decide whether a syscall belongs to the o32 or n32 or n64 ABI. Therefore, a new arch token for MIPS64/n32 is added so it can be used by seccomp to explicitely set syscall filters for this ABI. Signed-off-by: Markos Chandras Acked-by: Eric Paris Acked-by: Paul Moore Cc: Andy Lutomirski Cc: Ralf Baechle Cc: Andy Lutomirski Cc: linux-mips@linux-mips.org Link: http://sourceforge.net/p/libseccomp/mailman/message/32239040/ Patchwork: https://patchwork.linux-mips.org/patch/6818/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/syscall.h | 2 ++ include/uapi/linux/audit.h | 12 ++++++++++++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h index c6e9cd2bca8..17960fe7a8c 100644 --- a/arch/mips/include/asm/syscall.h +++ b/arch/mips/include/asm/syscall.h @@ -133,6 +133,8 @@ static inline int syscall_get_arch(void) #ifdef CONFIG_64BIT if (!test_thread_flag(TIF_32BIT_REGS)) arch |= __AUDIT_ARCH_64BIT; + if (test_thread_flag(TIF_32BIT_ADDR)) + arch |= __AUDIT_ARCH_CONVENTION_MIPS64_N32; #endif #if defined(__LITTLE_ENDIAN) arch |= __AUDIT_ARCH_LE; diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index 11917f747cb..1b1efddb91c 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -331,9 +331,17 @@ enum { #define AUDIT_FAIL_PRINTK 1 #define AUDIT_FAIL_PANIC 2 +/* + * These bits disambiguate different calling conventions that share an + * ELF machine type, bitness, and endianness + */ +#define __AUDIT_ARCH_CONVENTION_MASK 0x30000000 +#define __AUDIT_ARCH_CONVENTION_MIPS64_N32 0x20000000 + /* distinguish syscall tables */ #define __AUDIT_ARCH_64BIT 0x80000000 #define __AUDIT_ARCH_LE 0x40000000 + #define AUDIT_ARCH_ALPHA (EM_ALPHA|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE) #define AUDIT_ARCH_ARM (EM_ARM|__AUDIT_ARCH_LE) #define AUDIT_ARCH_ARMEB (EM_ARM) @@ -346,7 +354,11 @@ enum { #define AUDIT_ARCH_MIPS (EM_MIPS) #define AUDIT_ARCH_MIPSEL (EM_MIPS|__AUDIT_ARCH_LE) #define AUDIT_ARCH_MIPS64 (EM_MIPS|__AUDIT_ARCH_64BIT) +#define AUDIT_ARCH_MIPS64N32 (EM_MIPS|__AUDIT_ARCH_64BIT|\ + __AUDIT_ARCH_CONVENTION_MIPS64_N32) #define AUDIT_ARCH_MIPSEL64 (EM_MIPS|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE) +#define AUDIT_ARCH_MIPSEL64N32 (EM_MIPS|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE\ + __AUDIT_ARCH_CONVENTION_MIPS64_N32) #define AUDIT_ARCH_OPENRISC (EM_OPENRISC) #define AUDIT_ARCH_PARISC (EM_PARISC) #define AUDIT_ARCH_PARISC64 (EM_PARISC|__AUDIT_ARCH_64BIT) -- cgit v1.2.3-70-g09d2 From 3d4405226d27b3a215e4d03cfa51f536244e5de7 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Sun, 11 May 2014 22:59:30 +0200 Subject: net: avoid dependency of net_get_random_once on nop patching MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit net_get_random_once depends on the static keys infrastructure to patch up the branch to the slow path during boot. This was realized by abusing the static keys api and defining a new initializer to not enable the call site while still indicating that the branch point should get patched up. This was needed to have the fast path considered likely by gcc. The static key initialization during boot up normally walks through all the registered keys and either patches in ideal nops or enables the jump site but omitted that step on x86 if ideal nops where already placed at static_key branch points. Thus net_get_random_once branches not always became active. This patch switches net_get_random_once to the ordinary static_key api and thus places the kernel fast path in the - by gcc considered - unlikely path. Microbenchmarks on Intel and AMD x86-64 showed that the unlikely path actually beats the likely path in terms of cycle cost and that different nop patterns did not make much difference, thus this switch should not be noticeable. Fixes: a48e42920ff38b ("net: introduce new macro net_get_random_once") Reported-by: Tuomas Räsänen Cc: Linus Torvalds Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/net.h | 15 ++++----------- net/core/utils.c | 8 ++++---- 2 files changed, 8 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/net.h b/include/linux/net.h index 94734a6259a..17d83393afc 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -248,24 +248,17 @@ do { \ bool __net_get_random_once(void *buf, int nbytes, bool *done, struct static_key *done_key); -#ifdef HAVE_JUMP_LABEL -#define ___NET_RANDOM_STATIC_KEY_INIT ((struct static_key) \ - { .enabled = ATOMIC_INIT(0), .entries = (void *)1 }) -#else /* !HAVE_JUMP_LABEL */ -#define ___NET_RANDOM_STATIC_KEY_INIT STATIC_KEY_INIT_FALSE -#endif /* HAVE_JUMP_LABEL */ - #define net_get_random_once(buf, nbytes) \ ({ \ bool ___ret = false; \ static bool ___done = false; \ - static struct static_key ___done_key = \ - ___NET_RANDOM_STATIC_KEY_INIT; \ - if (!static_key_true(&___done_key)) \ + static struct static_key ___once_key = \ + STATIC_KEY_INIT_TRUE; \ + if (static_key_true(&___once_key)) \ ___ret = __net_get_random_once(buf, \ nbytes, \ &___done, \ - &___done_key); \ + &___once_key); \ ___ret; \ }) diff --git a/net/core/utils.c b/net/core/utils.c index 2f737bf90b3..eed34338736 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -348,8 +348,8 @@ static void __net_random_once_deferred(struct work_struct *w) { struct __net_random_once_work *work = container_of(w, struct __net_random_once_work, work); - if (!static_key_enabled(work->key)) - static_key_slow_inc(work->key); + BUG_ON(!static_key_enabled(work->key)); + static_key_slow_dec(work->key); kfree(work); } @@ -367,7 +367,7 @@ static void __net_random_once_disable_jump(struct static_key *key) } bool __net_get_random_once(void *buf, int nbytes, bool *done, - struct static_key *done_key) + struct static_key *once_key) { static DEFINE_SPINLOCK(lock); unsigned long flags; @@ -382,7 +382,7 @@ bool __net_get_random_once(void *buf, int nbytes, bool *done, *done = true; spin_unlock_irqrestore(&lock, flags); - __net_random_once_disable_jump(done_key); + __net_random_once_disable_jump(once_key); return true; } -- cgit v1.2.3-70-g09d2 From ffe6902b66aaa4ca6694bc19639259c16d84ddb1 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Thu, 1 May 2014 15:05:07 +0100 Subject: asm-generic: remove _STK_LIM_MAX _STK_LIM_MAX could be used to override the RLIMIT_STACK hard limit from an arch's include/uapi/asm-generic/resource.h file, but is no longer used since both parisc and metag removed the override. Therefore remove it entirely, setting the hard RLIMIT_STACK limit to RLIM_INFINITY directly in include/asm-generic/resource.h. Signed-off-by: James Hogan Cc: Arnd Bergmann Cc: linux-arch@vger.kernel.org Cc: Helge Deller Cc: John David Anglin --- include/asm-generic/resource.h | 2 +- include/uapi/asm-generic/resource.h | 7 ------- 2 files changed, 1 insertion(+), 8 deletions(-) (limited to 'include') diff --git a/include/asm-generic/resource.h b/include/asm-generic/resource.h index b4ea8f50fc6..5e752b95905 100644 --- a/include/asm-generic/resource.h +++ b/include/asm-generic/resource.h @@ -12,7 +12,7 @@ [RLIMIT_CPU] = { RLIM_INFINITY, RLIM_INFINITY }, \ [RLIMIT_FSIZE] = { RLIM_INFINITY, RLIM_INFINITY }, \ [RLIMIT_DATA] = { RLIM_INFINITY, RLIM_INFINITY }, \ - [RLIMIT_STACK] = { _STK_LIM, _STK_LIM_MAX }, \ + [RLIMIT_STACK] = { _STK_LIM, RLIM_INFINITY }, \ [RLIMIT_CORE] = { 0, RLIM_INFINITY }, \ [RLIMIT_RSS] = { RLIM_INFINITY, RLIM_INFINITY }, \ [RLIMIT_NPROC] = { 0, 0 }, \ diff --git a/include/uapi/asm-generic/resource.h b/include/uapi/asm-generic/resource.h index f863428796d..c6d10af5012 100644 --- a/include/uapi/asm-generic/resource.h +++ b/include/uapi/asm-generic/resource.h @@ -57,12 +57,5 @@ # define RLIM_INFINITY (~0UL) #endif -/* - * RLIMIT_STACK default maximum - some architectures override it: - */ -#ifndef _STK_LIM_MAX -# define _STK_LIM_MAX RLIM_INFINITY -#endif - #endif /* _UAPI_ASM_GENERIC_RESOURCE_H */ -- cgit v1.2.3-70-g09d2 From 4c358e15553ed88bf2ddae422624624e1dd663d1 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Thu, 15 May 2014 14:44:30 +1000 Subject: of: fix CONFIG_OF=n prototype of of_node_full_name() Make the CONFIG_OF=n prototpe of of_node_full_name() mateh the CONFIG_OF=y version. Fixes compile warnings like this: sound/soc/soc-core.c: In function 'soc_check_aux_dev': sound/soc/soc-core.c:1667:3: warning: passing argument 1 of 'of_node_full_name' discards 'const' qualifier from pointer target type [enabled by default] codecname = of_node_full_name(aux_dev->codec_of_node); when CONFIG_OF is not defined. Signed-off-by: Stephen Rothwell Signed-off-by: Grant Likely --- include/linux/of.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/of.h b/include/linux/of.h index 3bad8d106e0..e6f0988c1c6 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -349,7 +349,7 @@ int of_device_is_stdout_path(struct device_node *dn); #else /* CONFIG_OF */ -static inline const char* of_node_full_name(struct device_node *np) +static inline const char* of_node_full_name(const struct device_node *np) { return ""; } -- cgit v1.2.3-70-g09d2 From 200b916f3575bdf11609cb447661b8d5957b0bbf Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 12 May 2014 15:11:20 -0700 Subject: rtnetlink: wait for unregistering devices in rtnl_link_unregister() From: Cong Wang commit 50624c934db18ab90 (net: Delay default_device_exit_batch until no devices are unregistering) introduced rtnl_lock_unregistering() for default_device_exit_batch(). Same race could happen we when rmmod a driver which calls rtnl_link_unregister() as we call dev->destructor without rtnl lock. For long term, I think we should clean up the mess of netdev_run_todo() and net namespce exit code. Cc: Eric W. Biederman Cc: David S. Miller Signed-off-by: Cong Wang Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 5 +++++ net/core/dev.c | 2 +- net/core/net_namespace.c | 2 +- net/core/rtnetlink.c | 33 ++++++++++++++++++++++++++++++++- 4 files changed, 39 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 8e3e66ac0a5..953937ea523 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -4,6 +4,7 @@ #include #include +#include #include extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo); @@ -22,6 +23,10 @@ extern void rtnl_lock(void); extern void rtnl_unlock(void); extern int rtnl_trylock(void); extern int rtnl_is_locked(void); + +extern wait_queue_head_t netdev_unregistering_wq; +extern struct mutex net_mutex; + #ifdef CONFIG_PROVE_LOCKING extern int lockdep_rtnl_is_held(void); #else diff --git a/net/core/dev.c b/net/core/dev.c index c619b864133..6da649bde4f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5541,7 +5541,7 @@ static int dev_new_index(struct net *net) /* Delayed registration/unregisteration */ static LIST_HEAD(net_todo_list); -static DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); +DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); static void net_set_todo(struct net_device *dev) { diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 81d3a9a0845..7c8ffd97496 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -24,7 +24,7 @@ static LIST_HEAD(pernet_list); static struct list_head *first_device = &pernet_list; -static DEFINE_MUTEX(net_mutex); +DEFINE_MUTEX(net_mutex); LIST_HEAD(net_namespace_list); EXPORT_SYMBOL_GPL(net_namespace_list); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 9837bebf93c..2d8d8fcfa06 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -353,15 +353,46 @@ void __rtnl_link_unregister(struct rtnl_link_ops *ops) } EXPORT_SYMBOL_GPL(__rtnl_link_unregister); +/* Return with the rtnl_lock held when there are no network + * devices unregistering in any network namespace. + */ +static void rtnl_lock_unregistering_all(void) +{ + struct net *net; + bool unregistering; + DEFINE_WAIT(wait); + + for (;;) { + prepare_to_wait(&netdev_unregistering_wq, &wait, + TASK_UNINTERRUPTIBLE); + unregistering = false; + rtnl_lock(); + for_each_net(net) { + if (net->dev_unreg_count > 0) { + unregistering = true; + break; + } + } + if (!unregistering) + break; + __rtnl_unlock(); + schedule(); + } + finish_wait(&netdev_unregistering_wq, &wait); +} + /** * rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink. * @ops: struct rtnl_link_ops * to unregister */ void rtnl_link_unregister(struct rtnl_link_ops *ops) { - rtnl_lock(); + /* Close the race with cleanup_net() */ + mutex_lock(&net_mutex); + rtnl_lock_unregistering_all(); __rtnl_link_unregister(ops); rtnl_unlock(); + mutex_unlock(&net_mutex); } EXPORT_SYMBOL_GPL(rtnl_link_unregister); -- cgit v1.2.3-70-g09d2 From be7a010d6fa33dca9327ad8e91844278dfd1e712 Mon Sep 17 00:00:00 2001 From: Duan Jiong Date: Thu, 15 May 2014 15:56:14 +0800 Subject: ipv6: update Destination Cache entries when gateway turn into host RFC 4861 states in 7.2.5: The IsRouter flag in the cache entry MUST be set based on the Router flag in the received advertisement. In those cases where the IsRouter flag changes from TRUE to FALSE as a result of this update, the node MUST remove that router from the Default Router List and update the Destination Cache entries for all destinations using that neighbor as a router as specified in Section 7.3.3. This is needed to detect when a node that is used as a router stops forwarding packets due to being configured as a host. Currently, when dealing with NA Message which IsRouter flag changes from TRUE to FALSE, the kernel only removes router from the Default Router List, and don't update the Destination Cache entries. Now in order to update those Destination Cache entries, i introduce function rt6_clean_tohost(). Signed-off-by: Duan Jiong Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/ip6_route.h | 1 + net/ipv6/ndisc.c | 7 ++----- net/ipv6/route.c | 21 +++++++++++++++++++++ 3 files changed, 24 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 6c4f5eac98e..216cecce65e 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -127,6 +127,7 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg); void rt6_ifdown(struct net *net, struct net_device *dev); void rt6_mtu_change(struct net_device *dev, unsigned int mtu); void rt6_remove_prefsrc(struct inet6_ifaddr *ifp); +void rt6_clean_tohost(struct net *net, struct in6_addr *gateway); /* diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 09a22f4f36c..ca8d4ea48a5 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -851,7 +851,7 @@ out: static void ndisc_recv_na(struct sk_buff *skb) { struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb); - const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; + struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + @@ -944,10 +944,7 @@ static void ndisc_recv_na(struct sk_buff *skb) /* * Change: router to host */ - struct rt6_info *rt; - rt = rt6_get_dflt_router(saddr, dev); - if (rt) - ip6_del_rt(rt); + rt6_clean_tohost(dev_net(dev), saddr); } out: diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 004fffb6c22..58c449ad7f6 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2234,6 +2234,27 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp) fib6_clean_all(net, fib6_remove_prefsrc, &adni); } +#define RTF_RA_ROUTER (RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY) +#define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE) + +/* Remove routers and update dst entries when gateway turn into host. */ +static int fib6_clean_tohost(struct rt6_info *rt, void *arg) +{ + struct in6_addr *gateway = (struct in6_addr *)arg; + + if ((((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) || + ((rt->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY)) && + ipv6_addr_equal(gateway, &rt->rt6i_gateway)) { + return -1; + } + return 0; +} + +void rt6_clean_tohost(struct net *net, struct in6_addr *gateway) +{ + fib6_clean_all(net, fib6_clean_tohost, gateway); +} + struct arg_dev_net { struct net_device *dev; struct net *net; -- cgit v1.2.3-70-g09d2 From ce8d9e0d6746ff67c1870386b7121a4448f21130 Mon Sep 17 00:00:00 2001 From: Matan Barak Date: Thu, 15 May 2014 15:29:27 +0300 Subject: net/mlx4_core: Add UPDATE_QP SRIOV wrapper support This patch adds UPDATE_QP SRIOV wrapper support. The mechanism is a general one, but currently only source MAC index changes are allowed for VFs. Signed-off-by: Matan Barak Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/cmd.c | 4 +- drivers/net/ethernet/mellanox/mlx4/mlx4.h | 6 +++ drivers/net/ethernet/mellanox/mlx4/qp.c | 35 ++++++++++++++ .../net/ethernet/mellanox/mlx4/resource_tracker.c | 54 ++++++++++++++++++++++ include/linux/mlx4/qp.h | 11 +++++ 5 files changed, 108 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 78099eab767..92d3249f63f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -1253,12 +1253,12 @@ static struct mlx4_cmd_info cmd_info[] = { }, { .opcode = MLX4_CMD_UPDATE_QP, - .has_inbox = false, + .has_inbox = true, .has_outbox = false, .out_is_imm = false, .encode_slave_id = false, .verify = NULL, - .wrapper = mlx4_CMD_EPERM_wrapper + .wrapper = mlx4_UPDATE_QP_wrapper }, { .opcode = MLX4_CMD_GET_OP_REQ, diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index f9c46510196..212cea440f9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -1195,6 +1195,12 @@ int mlx4_QP_ATTACH_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_cmd_mailbox *outbox, struct mlx4_cmd_info *cmd); +int mlx4_UPDATE_QP_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd); + int mlx4_PROMISC_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox, diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c index 61d64ebffd5..fbd32af89c7 100644 --- a/drivers/net/ethernet/mellanox/mlx4/qp.c +++ b/drivers/net/ethernet/mellanox/mlx4/qp.c @@ -389,6 +389,41 @@ err_icm: EXPORT_SYMBOL_GPL(mlx4_qp_alloc); +#define MLX4_UPDATE_QP_SUPPORTED_ATTRS MLX4_UPDATE_QP_SMAC +int mlx4_update_qp(struct mlx4_dev *dev, struct mlx4_qp *qp, + enum mlx4_update_qp_attr attr, + struct mlx4_update_qp_params *params) +{ + struct mlx4_cmd_mailbox *mailbox; + struct mlx4_update_qp_context *cmd; + u64 pri_addr_path_mask = 0; + int err = 0; + + mailbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(mailbox)) + return PTR_ERR(mailbox); + + cmd = (struct mlx4_update_qp_context *)mailbox->buf; + + if (!attr || (attr & ~MLX4_UPDATE_QP_SUPPORTED_ATTRS)) + return -EINVAL; + + if (attr & MLX4_UPDATE_QP_SMAC) { + pri_addr_path_mask |= 1ULL << MLX4_UPD_QP_PATH_MASK_MAC_INDEX; + cmd->qp_context.pri_path.grh_mylmc = params->smac_index; + } + + cmd->primary_addr_path_mask = cpu_to_be64(pri_addr_path_mask); + + err = mlx4_cmd(dev, mailbox->dma, qp->qpn & 0xffffff, 0, + MLX4_CMD_UPDATE_QP, MLX4_CMD_TIME_CLASS_A, + MLX4_CMD_NATIVE); + + mlx4_free_cmd_mailbox(dev, mailbox); + return err; +} +EXPORT_SYMBOL_GPL(mlx4_update_qp); + void mlx4_qp_remove(struct mlx4_dev *dev, struct mlx4_qp *qp) { struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table; diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 1c3fdd4a1f7..8f1254a7983 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -3895,6 +3895,60 @@ static int add_eth_header(struct mlx4_dev *dev, int slave, } +#define MLX4_UPD_QP_PATH_MASK_SUPPORTED (1ULL << MLX4_UPD_QP_PATH_MASK_MAC_INDEX) +int mlx4_UPDATE_QP_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd_info) +{ + int err; + u32 qpn = vhcr->in_modifier & 0xffffff; + struct res_qp *rqp; + u64 mac; + unsigned port; + u64 pri_addr_path_mask; + struct mlx4_update_qp_context *cmd; + int smac_index; + + cmd = (struct mlx4_update_qp_context *)inbox->buf; + + pri_addr_path_mask = be64_to_cpu(cmd->primary_addr_path_mask); + if (cmd->qp_mask || cmd->secondary_addr_path_mask || + (pri_addr_path_mask & ~MLX4_UPD_QP_PATH_MASK_SUPPORTED)) + return -EPERM; + + /* Just change the smac for the QP */ + err = get_res(dev, slave, qpn, RES_QP, &rqp); + if (err) { + mlx4_err(dev, "Updating qpn 0x%x for slave %d rejected\n", qpn, slave); + return err; + } + + port = (rqp->sched_queue >> 6 & 1) + 1; + smac_index = cmd->qp_context.pri_path.grh_mylmc; + err = mac_find_smac_ix_in_slave(dev, slave, port, + smac_index, &mac); + if (err) { + mlx4_err(dev, "Failed to update qpn 0x%x, MAC is invalid. smac_ix: %d\n", + qpn, smac_index); + goto err_mac; + } + + err = mlx4_cmd(dev, inbox->dma, + vhcr->in_modifier, 0, + MLX4_CMD_UPDATE_QP, MLX4_CMD_TIME_CLASS_A, + MLX4_CMD_NATIVE); + if (err) { + mlx4_err(dev, "Failed to update qpn on qpn 0x%x, command failed\n", qpn); + goto err_mac; + } + +err_mac: + put_res(dev, slave, qpn, RES_QP); + return err; +} + int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox, diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index b66e7610d4e..7040dc98ff8 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -421,6 +421,17 @@ struct mlx4_wqe_inline_seg { __be32 byte_count; }; +enum mlx4_update_qp_attr { + MLX4_UPDATE_QP_SMAC = 1 << 0, +}; + +struct mlx4_update_qp_params { + u8 smac_index; +}; + +int mlx4_update_qp(struct mlx4_dev *dev, struct mlx4_qp *qp, + enum mlx4_update_qp_attr attr, + struct mlx4_update_qp_params *params); int mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt, enum mlx4_qp_state cur_state, enum mlx4_qp_state new_state, struct mlx4_qp_context *context, enum mlx4_qp_optpar optpar, -- cgit v1.2.3-70-g09d2 From 4085ebe8c31face855fd01ee40372cb4aab1df3a Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Fri, 16 May 2014 17:04:53 -0400 Subject: net: Find the nesting level of a given device by type. Multiple devices in the kernel can be stacked/nested and they need to know their nesting level for the purposes of lockdep. This patch provides a generic function that determines a nesting level of a particular device by its type (ex: vlan, macvlan, etc). We only care about nesting of the same type of devices. For example: eth0 <- vlan0.10 <- macvlan0 <- vlan1.20 The nesting level of vlan1.20 would be 1, since there is another vlan in the stack under it. Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 ++++++++++ net/core/dev.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 60 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 20e99efb1ca..fb912e8e5c7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3077,6 +3077,14 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev, priv; \ priv = netdev_lower_get_next_private_rcu(dev, &(iter))) +void *netdev_lower_get_next(struct net_device *dev, + struct list_head **iter); +#define netdev_for_each_lower_dev(dev, ldev, iter) \ + for (iter = &(dev)->adj_list.lower, \ + ldev = netdev_lower_get_next(dev, &(iter)); \ + ldev; \ + ldev = netdev_lower_get_next(dev, &(iter))) + void *netdev_adjacent_get_private(struct list_head *adj_list); void *netdev_lower_get_first_private_rcu(struct net_device *dev); struct net_device *netdev_master_upper_dev_get(struct net_device *dev); @@ -3092,6 +3100,8 @@ void netdev_upper_dev_unlink(struct net_device *dev, void netdev_adjacent_rename_links(struct net_device *dev, char *oldname); void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev); +int dev_get_nest_level(struct net_device *dev, + bool (*type_check)(struct net_device *dev)); int skb_checksum_help(struct sk_buff *skb); struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path); diff --git a/net/core/dev.c b/net/core/dev.c index ed928e84655..6ee3ac25ed7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4622,6 +4622,32 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev, } EXPORT_SYMBOL(netdev_lower_get_next_private_rcu); +/** + * netdev_lower_get_next - Get the next device from the lower neighbour + * list + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next netdev_adjacent from the dev's lower neighbour + * list, starting from iter position. The caller must hold RTNL lock or + * its own locking that guarantees that the neighbour lower + * list will remain unchainged. + */ +void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter) +{ + struct netdev_adjacent *lower; + + lower = list_entry((*iter)->next, struct netdev_adjacent, list); + + if (&lower->list == &dev->adj_list.lower) + return NULL; + + *iter = &lower->list; + + return lower->dev; +} +EXPORT_SYMBOL(netdev_lower_get_next); + /** * netdev_lower_get_first_private_rcu - Get the first ->private from the * lower neighbour list, RCU @@ -5072,6 +5098,30 @@ void *netdev_lower_dev_get_private(struct net_device *dev, } EXPORT_SYMBOL(netdev_lower_dev_get_private); + +int dev_get_nest_level(struct net_device *dev, + bool (*type_check)(struct net_device *dev)) +{ + struct net_device *lower = NULL; + struct list_head *iter; + int max_nest = -1; + int nest; + + ASSERT_RTNL(); + + netdev_for_each_lower_dev(dev, lower, iter) { + nest = dev_get_nest_level(lower, type_check); + if (max_nest < nest) + max_nest = nest; + } + + if (type_check(dev)) + max_nest++; + + return max_nest; +} +EXPORT_SYMBOL(dev_get_nest_level); + static void dev_change_rx_flags(struct net_device *dev, int flags) { const struct net_device_ops *ops = dev->netdev_ops; -- cgit v1.2.3-70-g09d2 From 25175ba5c9bff9aaf0229df34bb5d54c81633ec3 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Fri, 16 May 2014 17:04:54 -0400 Subject: net: Allow for more then a single subclass for netif_addr_lock Currently netif_addr_lock_nested assumes that there can be only a single nesting level between 2 devices. However, if we have multiple devices of the same type stacked, this fails. For example: eth0 <-- vlan0.10 <-- vlan0.10.20 A more complicated configuration may stack more then one type of device in different order. Ex: eth0 <-- vlan0.10 <-- macvlan0 <-- vlan1.10.20 <-- macvlan1 This patch adds an ndo_* function that allows each stackable device to report its nesting level. If the device doesn't provide this function default subclass of 1 is used. Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fb912e8e5c7..9d4b1f1b6b7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1144,6 +1144,7 @@ struct net_device_ops { netdev_tx_t (*ndo_dfwd_start_xmit) (struct sk_buff *skb, struct net_device *dev, void *priv); + int (*ndo_get_lock_subclass)(struct net_device *dev); }; /** @@ -2950,7 +2951,12 @@ static inline void netif_addr_lock(struct net_device *dev) static inline void netif_addr_lock_nested(struct net_device *dev) { - spin_lock_nested(&dev->addr_list_lock, SINGLE_DEPTH_NESTING); + int subclass = SINGLE_DEPTH_NESTING; + + if (dev->netdev_ops->ndo_get_lock_subclass) + subclass = dev->netdev_ops->ndo_get_lock_subclass(dev); + + spin_lock_nested(&dev->addr_list_lock, subclass); } static inline void netif_addr_lock_bh(struct net_device *dev) -- cgit v1.2.3-70-g09d2 From d38569ab2bba6e6b3233acfc3a84cdbcfbd1f79f Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Fri, 16 May 2014 17:04:55 -0400 Subject: vlan: Fix lockdep warning with stacked vlan devices. This reverts commit dc8eaaa006350d24030502a4521542e74b5cb39f. vlan: Fix lockdep warning when vlan dev handle notification Instead we use the new new API to find the lock subclass of our vlan device. This way we can support configurations where vlans are interspersed with other devices: bond -> vlan -> macvlan -> vlan Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 3 ++- net/8021q/vlan.c | 1 + net/8021q/vlan_dev.c | 52 +++++++++---------------------------------------- net/core/dev.c | 1 - 4 files changed, 12 insertions(+), 45 deletions(-) (limited to 'include') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 13bbbde00e6..724bde8477b 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -73,7 +73,7 @@ static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb) /* found in socket.c */ extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *)); -static inline int is_vlan_dev(struct net_device *dev) +static inline bool is_vlan_dev(struct net_device *dev) { return dev->priv_flags & IFF_802_1Q_VLAN; } @@ -159,6 +159,7 @@ struct vlan_dev_priv { #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; #endif + unsigned int nest_level; }; static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev) diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 175273f38cb..44ebd5c2cd4 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -169,6 +169,7 @@ int register_vlan_dev(struct net_device *dev) if (err < 0) goto out_uninit_mvrp; + vlan->nest_level = dev_get_nest_level(real_dev, is_vlan_dev) + 1; err = register_netdevice(dev); if (err < 0) goto out_uninit_mvrp; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 733ec283ed1..019efb79708 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -493,48 +493,10 @@ static void vlan_dev_change_rx_flags(struct net_device *dev, int change) } } -static int vlan_calculate_locking_subclass(struct net_device *real_dev) -{ - int subclass = 0; - - while (is_vlan_dev(real_dev)) { - subclass++; - real_dev = vlan_dev_priv(real_dev)->real_dev; - } - - return subclass; -} - -static void vlan_dev_mc_sync(struct net_device *to, struct net_device *from) -{ - int err = 0, subclass; - - subclass = vlan_calculate_locking_subclass(to); - - spin_lock_nested(&to->addr_list_lock, subclass); - err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len); - if (!err) - __dev_set_rx_mode(to); - spin_unlock(&to->addr_list_lock); -} - -static void vlan_dev_uc_sync(struct net_device *to, struct net_device *from) -{ - int err = 0, subclass; - - subclass = vlan_calculate_locking_subclass(to); - - spin_lock_nested(&to->addr_list_lock, subclass); - err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); - if (!err) - __dev_set_rx_mode(to); - spin_unlock(&to->addr_list_lock); -} - static void vlan_dev_set_rx_mode(struct net_device *vlan_dev) { - vlan_dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); - vlan_dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); + dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); + dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); } /* @@ -562,6 +524,11 @@ static void vlan_dev_set_lockdep_class(struct net_device *dev, int subclass) netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, &subclass); } +static int vlan_dev_get_lock_subclass(struct net_device *dev) +{ + return vlan_dev_priv(dev)->nest_level; +} + static const struct header_ops vlan_header_ops = { .create = vlan_dev_hard_header, .rebuild = vlan_dev_rebuild_header, @@ -597,7 +564,6 @@ static const struct net_device_ops vlan_netdev_ops; static int vlan_dev_init(struct net_device *dev) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; - int subclass = 0; netif_carrier_off(dev); @@ -646,8 +612,7 @@ static int vlan_dev_init(struct net_device *dev) SET_NETDEV_DEVTYPE(dev, &vlan_type); - subclass = vlan_calculate_locking_subclass(dev); - vlan_dev_set_lockdep_class(dev, subclass); + vlan_dev_set_lockdep_class(dev, vlan_dev_get_lock_subclass(dev)); vlan_dev_priv(dev)->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); if (!vlan_dev_priv(dev)->vlan_pcpu_stats) @@ -819,6 +784,7 @@ static const struct net_device_ops vlan_netdev_ops = { .ndo_netpoll_cleanup = vlan_dev_netpoll_cleanup, #endif .ndo_fix_features = vlan_dev_fix_features, + .ndo_get_lock_subclass = vlan_dev_get_lock_subclass, }; void vlan_setup(struct net_device *dev) diff --git a/net/core/dev.c b/net/core/dev.c index 6ee3ac25ed7..2b872bfbd17 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5287,7 +5287,6 @@ void __dev_set_rx_mode(struct net_device *dev) if (ops->ndo_set_rx_mode) ops->ndo_set_rx_mode(dev); } -EXPORT_SYMBOL(__dev_set_rx_mode); void dev_set_rx_mode(struct net_device *dev) { -- cgit v1.2.3-70-g09d2 From c674ac30c549596295eb0a5af7f4714c0b905b6f Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Fri, 16 May 2014 17:04:56 -0400 Subject: macvlan: Fix lockdep warnings with stacked macvlan devices Macvlan devices try to avoid stacking, but that's not always successfull or even desired. As an example, the following configuration is perefectly legal and valid: eth0 <--- macvlan0 <---- vlan0.10 <--- macvlan1 However, this configuration produces the following lockdep trace: [ 115.620418] ====================================================== [ 115.620477] [ INFO: possible circular locking dependency detected ] [ 115.620516] 3.15.0-rc1+ #24 Not tainted [ 115.620540] ------------------------------------------------------- [ 115.620577] ip/1704 is trying to acquire lock: [ 115.620604] (&vlan_netdev_addr_lock_key/1){+.....}, at: [] dev_uc_sync+0x3c/0x80 [ 115.620686] but task is already holding lock: [ 115.620723] (&macvlan_netdev_addr_lock_key){+.....}, at: [] dev_set_rx_mode+0x1e/0x40 [ 115.620795] which lock already depends on the new lock. [ 115.620853] the existing dependency chain (in reverse order) is: [ 115.620894] -> #1 (&macvlan_netdev_addr_lock_key){+.....}: [ 115.620935] [] lock_acquire+0xa2/0x130 [ 115.620974] [] _raw_spin_lock_nested+0x37/0x50 [ 115.621019] [] vlan_dev_set_rx_mode+0x53/0x110 [8021q] [ 115.621066] [] __dev_set_rx_mode+0x57/0xa0 [ 115.621105] [] dev_set_rx_mode+0x26/0x40 [ 115.621143] [] __dev_open+0xde/0x140 [ 115.621174] [] __dev_change_flags+0x9d/0x170 [ 115.621174] [] dev_change_flags+0x29/0x60 [ 115.621174] [] do_setlink+0x321/0x9a0 [ 115.621174] [] rtnl_newlink+0x51f/0x730 [ 115.621174] [] rtnetlink_rcv_msg+0x95/0x250 [ 115.621174] [] netlink_rcv_skb+0xa9/0xc0 [ 115.621174] [] rtnetlink_rcv+0x2a/0x40 [ 115.621174] [] netlink_unicast+0xf0/0x1c0 [ 115.621174] [] netlink_sendmsg+0x2ff/0x740 [ 115.621174] [] sock_sendmsg+0x8b/0xc0 [ 115.621174] [] ___sys_sendmsg+0x369/0x380 [ 115.621174] [] __sys_sendmsg+0x42/0x80 [ 115.621174] [] SyS_sendmsg+0x12/0x20 [ 115.621174] [] system_call_fastpath+0x16/0x1b [ 115.621174] -> #0 (&vlan_netdev_addr_lock_key/1){+.....}: [ 115.621174] [] __lock_acquire+0x1773/0x1a60 [ 115.621174] [] lock_acquire+0xa2/0x130 [ 115.621174] [] _raw_spin_lock_nested+0x37/0x50 [ 115.621174] [] dev_uc_sync+0x3c/0x80 [ 115.621174] [] macvlan_set_mac_lists+0xca/0x110 [macvlan] [ 115.621174] [] __dev_set_rx_mode+0x57/0xa0 [ 115.621174] [] dev_set_rx_mode+0x26/0x40 [ 115.621174] [] __dev_open+0xde/0x140 [ 115.621174] [] __dev_change_flags+0x9d/0x170 [ 115.621174] [] dev_change_flags+0x29/0x60 [ 115.621174] [] do_setlink+0x321/0x9a0 [ 115.621174] [] rtnl_newlink+0x51f/0x730 [ 115.621174] [] rtnetlink_rcv_msg+0x95/0x250 [ 115.621174] [] netlink_rcv_skb+0xa9/0xc0 [ 115.621174] [] rtnetlink_rcv+0x2a/0x40 [ 115.621174] [] netlink_unicast+0xf0/0x1c0 [ 115.621174] [] netlink_sendmsg+0x2ff/0x740 [ 115.621174] [] sock_sendmsg+0x8b/0xc0 [ 115.621174] [] ___sys_sendmsg+0x369/0x380 [ 115.621174] [] __sys_sendmsg+0x42/0x80 [ 115.621174] [] SyS_sendmsg+0x12/0x20 [ 115.621174] [] system_call_fastpath+0x16/0x1b [ 115.621174] other info that might help us debug this: [ 115.621174] Possible unsafe locking scenario: [ 115.621174] CPU0 CPU1 [ 115.621174] ---- ---- [ 115.621174] lock(&macvlan_netdev_addr_lock_key); [ 115.621174] lock(&vlan_netdev_addr_lock_key/1); [ 115.621174] lock(&macvlan_netdev_addr_lock_key); [ 115.621174] lock(&vlan_netdev_addr_lock_key/1); [ 115.621174] *** DEADLOCK *** [ 115.621174] 2 locks held by ip/1704: [ 115.621174] #0: (rtnl_mutex){+.+.+.}, at: [] rtnetlink_rcv+0x1b/0x40 [ 115.621174] #1: (&macvlan_netdev_addr_lock_key){+.....}, at: [] dev_set_rx_mode+0x1e/0x40 [ 115.621174] stack backtrace: [ 115.621174] CPU: 3 PID: 1704 Comm: ip Not tainted 3.15.0-rc1+ #24 [ 115.621174] Hardware name: Hewlett-Packard HP xw8400 Workstation/0A08h, BIOS 786D5 v02.38 10/25/2010 [ 115.621174] ffffffff82339ae0 ffff880465f79568 ffffffff816ee20c ffffffff82339ae0 [ 115.621174] ffff880465f795a8 ffffffff816e9e1b ffff880465f79600 ffff880465b019c8 [ 115.621174] 0000000000000001 0000000000000002 ffff880465b019c8 ffff880465b01230 [ 115.621174] Call Trace: [ 115.621174] [] dump_stack+0x4d/0x66 [ 115.621174] [] print_circular_bug+0x200/0x20e [ 115.621174] [] __lock_acquire+0x1773/0x1a60 [ 115.621174] [] ? trace_hardirqs_on_caller+0xb2/0x1d0 [ 115.621174] [] lock_acquire+0xa2/0x130 [ 115.621174] [] ? dev_uc_sync+0x3c/0x80 [ 115.621174] [] _raw_spin_lock_nested+0x37/0x50 [ 115.621174] [] ? dev_uc_sync+0x3c/0x80 [ 115.621174] [] dev_uc_sync+0x3c/0x80 [ 115.621174] [] macvlan_set_mac_lists+0xca/0x110 [macvlan] [ 115.621174] [] __dev_set_rx_mode+0x57/0xa0 [ 115.621174] [] dev_set_rx_mode+0x26/0x40 [ 115.621174] [] __dev_open+0xde/0x140 [ 115.621174] [] __dev_change_flags+0x9d/0x170 [ 115.621174] [] dev_change_flags+0x29/0x60 [ 115.621174] [] ? mem_cgroup_bad_page_check+0x21/0x30 [ 115.621174] [] do_setlink+0x321/0x9a0 [ 115.621174] [] ? __lock_acquire+0x37c/0x1a60 [ 115.621174] [] rtnl_newlink+0x51f/0x730 [ 115.621174] [] ? rtnl_newlink+0xe9/0x730 [ 115.621174] [] rtnetlink_rcv_msg+0x95/0x250 [ 115.621174] [] ? trace_hardirqs_on+0xd/0x10 [ 115.621174] [] ? rtnetlink_rcv+0x1b/0x40 [ 115.621174] [] ? rtnetlink_rcv+0x40/0x40 [ 115.621174] [] netlink_rcv_skb+0xa9/0xc0 [ 115.621174] [] rtnetlink_rcv+0x2a/0x40 [ 115.621174] [] netlink_unicast+0xf0/0x1c0 [ 115.621174] [] netlink_sendmsg+0x2ff/0x740 [ 115.621174] [] sock_sendmsg+0x8b/0xc0 [ 115.621174] [] ? might_fault+0x5f/0xb0 [ 115.621174] [] ? might_fault+0xa8/0xb0 [ 115.621174] [] ? might_fault+0x5f/0xb0 [ 115.621174] [] ? verify_iovec+0x5e/0xe0 [ 115.621174] [] ___sys_sendmsg+0x369/0x380 [ 115.621174] [] ? __do_page_fault+0x11d/0x570 [ 115.621174] [] ? up_read+0x1f/0x40 [ 115.621174] [] ? __do_page_fault+0x214/0x570 [ 115.621174] [] ? mntput_no_expire+0x6b/0x1c0 [ 115.621174] [] ? mntput_no_expire+0x17/0x1c0 [ 115.621174] [] ? mntput+0x24/0x40 [ 115.621174] [] __sys_sendmsg+0x42/0x80 [ 115.621174] [] SyS_sendmsg+0x12/0x20 [ 115.621174] [] system_call_fastpath+0x16/0x1b Fix this by correctly providing macvlan lockdep class. Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- drivers/net/macvlan.c | 12 ++++++++++-- include/linux/if_macvlan.h | 1 + 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index c5fb9cf95c1..d53e299ae1d 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -517,6 +517,11 @@ static struct lock_class_key macvlan_netdev_addr_lock_key; #define MACVLAN_STATE_MASK \ ((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT)) +static int macvlan_get_nest_level(struct net_device *dev) +{ + return ((struct macvlan_dev *)netdev_priv(dev))->nest_level; +} + static void macvlan_set_lockdep_class_one(struct net_device *dev, struct netdev_queue *txq, void *_unused) @@ -527,8 +532,9 @@ static void macvlan_set_lockdep_class_one(struct net_device *dev, static void macvlan_set_lockdep_class(struct net_device *dev) { - lockdep_set_class(&dev->addr_list_lock, - &macvlan_netdev_addr_lock_key); + lockdep_set_class_and_subclass(&dev->addr_list_lock, + &macvlan_netdev_addr_lock_key, + macvlan_get_nest_level(dev)); netdev_for_each_tx_queue(dev, macvlan_set_lockdep_class_one, NULL); } @@ -723,6 +729,7 @@ static const struct net_device_ops macvlan_netdev_ops = { .ndo_fdb_add = macvlan_fdb_add, .ndo_fdb_del = macvlan_fdb_del, .ndo_fdb_dump = ndo_dflt_fdb_dump, + .ndo_get_lock_subclass = macvlan_get_nest_level, }; void macvlan_common_setup(struct net_device *dev) @@ -851,6 +858,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, vlan->dev = dev; vlan->port = port; vlan->set_features = MACVLAN_FEATURES; + vlan->nest_level = dev_get_nest_level(lowerdev, netif_is_macvlan) + 1; vlan->mode = MACVLAN_MODE_VEPA; if (data && data[IFLA_MACVLAN_MODE]) diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 7c8b20b120e..a9a53b12397 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -56,6 +56,7 @@ struct macvlan_dev { int numqueues; netdev_features_t tap_features; int minor; + int nest_level; }; static inline void macvlan_count_rx(const struct macvlan_dev *vlan, -- cgit v1.2.3-70-g09d2 From 44a4085538c844e79d6ee6bcf46fabf7c57a9a38 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Fri, 16 May 2014 17:20:38 -0400 Subject: bonding: Fix stacked device detection in arp monitoring Prior to commit fbd929f2dce460456807a51e18d623db3db9f077 bonding: support QinQ for bond arp interval the arp monitoring code allowed for proper detection of devices stacked on top of vlans. Since the above commit, the code can still detect a device stacked on top of single vlan, but not a device stacked on top of Q-in-Q configuration. The search will only set the inner vlan tag if the route device is the vlan device. However, this is not always the case, as it is possible to extend the stacked configuration. With this patch it is possible to provision devices on top Q-in-Q vlan configuration that should be used as a source of ARP monitoring information. For example: ip link add link bond0 vlan10 type vlan proto 802.1q id 10 ip link add link vlan10 vlan100 type vlan proto 802.1q id 100 ip link add link vlan100 type macvlan Note: This patch limites the number of stacked VLANs to 2, just like before. The original, however had another issue in that if we had more then 2 levels of VLANs, we would end up generating incorrectly tagged traffic. This is no longer possible. Fixes: fbd929f2dce460456807a51e18d623db3db9f077 (bonding: support QinQ for bond arp interval) CC: Jay Vosburgh CC: Veaceslav Falico CC: Andy Gospodarek CC: Ding Tianhong CC: Patric McHardy Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 134 +++++++++++++++++++--------------------- drivers/net/bonding/bonding.h | 1 + include/linux/if_vlan.h | 6 ++ include/linux/netdevice.h | 9 +++ net/core/dev.c | 26 ++++++++ 5 files changed, 107 insertions(+), 69 deletions(-) (limited to 'include') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 69aff72c895..d3a67896d43 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2126,10 +2126,10 @@ static bool bond_has_this_ip(struct bonding *bond, __be32 ip) */ static void bond_arp_send(struct net_device *slave_dev, int arp_op, __be32 dest_ip, __be32 src_ip, - struct bond_vlan_tag *inner, - struct bond_vlan_tag *outer) + struct bond_vlan_tag *tags) { struct sk_buff *skb; + int i; pr_debug("arp %d on slave %s: dst %pI4 src %pI4\n", arp_op, slave_dev->name, &dest_ip, &src_ip); @@ -2141,21 +2141,26 @@ static void bond_arp_send(struct net_device *slave_dev, int arp_op, net_err_ratelimited("ARP packet allocation failed\n"); return; } - if (outer->vlan_id) { - if (inner->vlan_id) { - pr_debug("inner tag: proto %X vid %X\n", - ntohs(inner->vlan_proto), inner->vlan_id); - skb = __vlan_put_tag(skb, inner->vlan_proto, - inner->vlan_id); - if (!skb) { - net_err_ratelimited("failed to insert inner VLAN tag\n"); - return; - } - } - pr_debug("outer reg: proto %X vid %X\n", - ntohs(outer->vlan_proto), outer->vlan_id); - skb = vlan_put_tag(skb, outer->vlan_proto, outer->vlan_id); + /* Go through all the tags backwards and add them to the packet */ + for (i = BOND_MAX_VLAN_ENCAP - 1; i > 0; i--) { + if (!tags[i].vlan_id) + continue; + + pr_debug("inner tag: proto %X vid %X\n", + ntohs(tags[i].vlan_proto), tags[i].vlan_id); + skb = __vlan_put_tag(skb, tags[i].vlan_proto, + tags[i].vlan_id); + if (!skb) { + net_err_ratelimited("failed to insert inner VLAN tag\n"); + return; + } + } + /* Set the outer tag */ + if (tags[0].vlan_id) { + pr_debug("outer tag: proto %X vid %X\n", + ntohs(tags[0].vlan_proto), tags[0].vlan_id); + skb = vlan_put_tag(skb, tags[0].vlan_proto, tags[0].vlan_id); if (!skb) { net_err_ratelimited("failed to insert outer VLAN tag\n"); return; @@ -2164,22 +2169,52 @@ static void bond_arp_send(struct net_device *slave_dev, int arp_op, arp_xmit(skb); } +/* Validate the device path between the @start_dev and the @end_dev. + * The path is valid if the @end_dev is reachable through device + * stacking. + * When the path is validated, collect any vlan information in the + * path. + */ +static bool bond_verify_device_path(struct net_device *start_dev, + struct net_device *end_dev, + struct bond_vlan_tag *tags) +{ + struct net_device *upper; + struct list_head *iter; + int idx; + + if (start_dev == end_dev) + return true; + + netdev_for_each_upper_dev_rcu(start_dev, upper, iter) { + if (bond_verify_device_path(upper, end_dev, tags)) { + if (is_vlan_dev(upper)) { + idx = vlan_get_encap_level(upper); + if (idx >= BOND_MAX_VLAN_ENCAP) + return false; + + tags[idx].vlan_proto = + vlan_dev_vlan_proto(upper); + tags[idx].vlan_id = vlan_dev_vlan_id(upper); + } + return true; + } + } + + return false; +} static void bond_arp_send_all(struct bonding *bond, struct slave *slave) { - struct net_device *upper, *vlan_upper; - struct list_head *iter, *vlan_iter; struct rtable *rt; - struct bond_vlan_tag inner, outer; + struct bond_vlan_tag tags[BOND_MAX_VLAN_ENCAP]; __be32 *targets = bond->params.arp_targets, addr; int i; + bool ret; for (i = 0; i < BOND_MAX_ARP_TARGETS && targets[i]; i++) { pr_debug("basa: target %pI4\n", &targets[i]); - inner.vlan_proto = 0; - inner.vlan_id = 0; - outer.vlan_proto = 0; - outer.vlan_id = 0; + memset(tags, 0, sizeof(tags)); /* Find out through which dev should the packet go */ rt = ip_route_output(dev_net(bond->dev), targets[i], 0, @@ -2192,7 +2227,8 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) net_warn_ratelimited("%s: no route to arp_ip_target %pI4 and arp_validate is set\n", bond->dev->name, &targets[i]); - bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], 0, &inner, &outer); + bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], + 0, tags); continue; } @@ -2201,52 +2237,12 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) goto found; rcu_read_lock(); - /* first we search only for vlan devices. for every vlan - * found we verify its upper dev list, searching for the - * rt->dst.dev. If found we save the tag of the vlan and - * proceed to send the packet. - */ - netdev_for_each_all_upper_dev_rcu(bond->dev, vlan_upper, - vlan_iter) { - if (!is_vlan_dev(vlan_upper)) - continue; - - if (vlan_upper == rt->dst.dev) { - outer.vlan_proto = vlan_dev_vlan_proto(vlan_upper); - outer.vlan_id = vlan_dev_vlan_id(vlan_upper); - rcu_read_unlock(); - goto found; - } - netdev_for_each_all_upper_dev_rcu(vlan_upper, upper, - iter) { - if (upper == rt->dst.dev) { - /* If the upper dev is a vlan dev too, - * set the vlan tag to inner tag. - */ - if (is_vlan_dev(upper)) { - inner.vlan_proto = vlan_dev_vlan_proto(upper); - inner.vlan_id = vlan_dev_vlan_id(upper); - } - outer.vlan_proto = vlan_dev_vlan_proto(vlan_upper); - outer.vlan_id = vlan_dev_vlan_id(vlan_upper); - rcu_read_unlock(); - goto found; - } - } - } - - /* if the device we're looking for is not on top of any of - * our upper vlans, then just search for any dev that - * matches, and in case it's a vlan - save the id - */ - netdev_for_each_all_upper_dev_rcu(bond->dev, upper, iter) { - if (upper == rt->dst.dev) { - rcu_read_unlock(); - goto found; - } - } + ret = bond_verify_device_path(bond->dev, rt->dst.dev, tags); rcu_read_unlock(); + if (ret) + goto found; + /* Not our device - skip */ pr_debug("%s: no path to arp_ip_target %pI4 via rt.dev %s\n", bond->dev->name, &targets[i], @@ -2259,7 +2255,7 @@ found: addr = bond_confirm_addr(rt->dst.dev, targets[i], 0); ip_rt_put(rt); bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], - addr, &inner, &outer); + addr, tags); } } diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index b8bdd0acc8f..00bea320e3b 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -36,6 +36,7 @@ #define bond_version DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n" +#define BOND_MAX_VLAN_ENCAP 2 #define BOND_MAX_ARP_TARGETS 16 #define BOND_DEFAULT_MIIMON 100 diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 724bde8477b..c901b13b6f0 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -484,4 +484,10 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb, */ skb->protocol = htons(ETH_P_802_2); } + +static inline int vlan_get_encap_level(struct net_device *dev) +{ + BUG_ON(!is_vlan_dev(dev)); + return vlan_dev_priv(dev)->nest_level; +} #endif /* !(_LINUX_IF_VLAN_H_) */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9d4b1f1b6b7..b42d07b0390 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3056,9 +3056,18 @@ extern int weight_p; extern int bpf_jit_enable; bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); +struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, + struct list_head **iter); struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter); +/* iterate through upper list, must be called under RCU read lock */ +#define netdev_for_each_upper_dev_rcu(dev, updev, iter) \ + for (iter = &(dev)->adj_list.upper, \ + updev = netdev_upper_get_next_dev_rcu(dev, &(iter)); \ + updev; \ + updev = netdev_upper_get_next_dev_rcu(dev, &(iter))) + /* iterate through upper list, must be called under RCU read lock */ #define netdev_for_each_all_upper_dev_rcu(dev, updev, iter) \ for (iter = &(dev)->all_adj_list.upper, \ diff --git a/net/core/dev.c b/net/core/dev.c index 2b872bfbd17..9abc503b19b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4541,6 +4541,32 @@ void *netdev_adjacent_get_private(struct list_head *adj_list) } EXPORT_SYMBOL(netdev_adjacent_get_private); +/** + * netdev_upper_get_next_dev_rcu - Get the next dev from upper list + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next device from the dev's upper list, starting from iter + * position. The caller must hold RCU read lock. + */ +struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, + struct list_head **iter) +{ + struct netdev_adjacent *upper; + + WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); + + upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); + + if (&upper->list == &dev->adj_list.upper) + return NULL; + + *iter = &upper->list; + + return upper->dev; +} +EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu); + /** * netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list * @dev: device -- cgit v1.2.3-70-g09d2 From b69cf53640da2b86439596118cfa95233154ee76 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 14 Mar 2014 10:50:33 +0100 Subject: perf: Fix a race between ring_buffer_detach() and ring_buffer_attach() Alexander noticed that we use RCU iteration on rb->event_list but do not use list_{add,del}_rcu() to add,remove entries to that list, nor do we observe proper grace periods when re-using the entries. Merge ring_buffer_detach() into ring_buffer_attach() such that attaching to the NULL buffer is detaching. Furthermore, ensure that between any 'detach' and 'attach' of the same event we observe the required grace period, but only when strictly required. In effect this means that only ioctl(.request = PERF_EVENT_IOC_SET_OUTPUT) will wait for a grace period, while the normal initial attach and final detach will not be delayed. This patch should, I think, do the right thing under all circumstances, the 'normal' cases all should never see the extra grace period, but the two cases: 1) PERF_EVENT_IOC_SET_OUTPUT on an event which already has a ring_buffer set, will now observe the required grace period between removing itself from the old and attaching itself to the new buffer. This case is 'simple' in that both buffers are present in perf_event_set_output() one could think an unconditional synchronize_rcu() would be sufficient; however... 2) an event that has a buffer attached, the buffer is destroyed (munmap) and then the event is attached to a new/different buffer using PERF_EVENT_IOC_SET_OUTPUT. This case is more complex because the buffer destruction does: ring_buffer_attach(.rb = NULL) followed by the ioctl() doing: ring_buffer_attach(.rb = foo); and we still need to observe the grace period between these two calls due to us reusing the event->rb_entry list_head. In order to make 2 happen we use Paul's latest cond_synchronize_rcu() call. Cc: Paul Mackerras Cc: Stephane Eranian Cc: Andi Kleen Cc: "Paul E. McKenney" Cc: Ingo Molnar Cc: Frederic Weisbecker Cc: Mike Galbraith Reported-by: Alexander Shishkin Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20140507123526.GD13658@twins.programming.kicks-ass.net Signed-off-by: Thomas Gleixner --- include/linux/perf_event.h | 2 + kernel/events/core.c | 109 ++++++++++++++++++++------------------------- 2 files changed, 51 insertions(+), 60 deletions(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 3356abcfff1..3ef6ea12806 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -402,6 +402,8 @@ struct perf_event { struct ring_buffer *rb; struct list_head rb_entry; + unsigned long rcu_batches; + int rcu_pending; /* poll related */ wait_queue_head_t waitq; diff --git a/kernel/events/core.c b/kernel/events/core.c index feb1329ca33..440eefc6739 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3192,7 +3192,8 @@ static void free_event_rcu(struct rcu_head *head) } static void ring_buffer_put(struct ring_buffer *rb); -static void ring_buffer_detach(struct perf_event *event, struct ring_buffer *rb); +static void ring_buffer_attach(struct perf_event *event, + struct ring_buffer *rb); static void unaccount_event_cpu(struct perf_event *event, int cpu) { @@ -3252,8 +3253,6 @@ static void free_event(struct perf_event *event) unaccount_event(event); if (event->rb) { - struct ring_buffer *rb; - /* * Can happen when we close an event with re-directed output. * @@ -3261,12 +3260,7 @@ static void free_event(struct perf_event *event) * over us; possibly making our ring_buffer_put() the last. */ mutex_lock(&event->mmap_mutex); - rb = event->rb; - if (rb) { - rcu_assign_pointer(event->rb, NULL); - ring_buffer_detach(event, rb); - ring_buffer_put(rb); /* could be last */ - } + ring_buffer_attach(event, NULL); mutex_unlock(&event->mmap_mutex); } @@ -3850,28 +3844,47 @@ unlock: static void ring_buffer_attach(struct perf_event *event, struct ring_buffer *rb) { + struct ring_buffer *old_rb = NULL; unsigned long flags; - if (!list_empty(&event->rb_entry)) - return; + if (event->rb) { + /* + * Should be impossible, we set this when removing + * event->rb_entry and wait/clear when adding event->rb_entry. + */ + WARN_ON_ONCE(event->rcu_pending); - spin_lock_irqsave(&rb->event_lock, flags); - if (list_empty(&event->rb_entry)) - list_add(&event->rb_entry, &rb->event_list); - spin_unlock_irqrestore(&rb->event_lock, flags); -} + old_rb = event->rb; + event->rcu_batches = get_state_synchronize_rcu(); + event->rcu_pending = 1; -static void ring_buffer_detach(struct perf_event *event, struct ring_buffer *rb) -{ - unsigned long flags; + spin_lock_irqsave(&old_rb->event_lock, flags); + list_del_rcu(&event->rb_entry); + spin_unlock_irqrestore(&old_rb->event_lock, flags); + } - if (list_empty(&event->rb_entry)) - return; + if (event->rcu_pending && rb) { + cond_synchronize_rcu(event->rcu_batches); + event->rcu_pending = 0; + } - spin_lock_irqsave(&rb->event_lock, flags); - list_del_init(&event->rb_entry); - wake_up_all(&event->waitq); - spin_unlock_irqrestore(&rb->event_lock, flags); + if (rb) { + spin_lock_irqsave(&rb->event_lock, flags); + list_add_rcu(&event->rb_entry, &rb->event_list); + spin_unlock_irqrestore(&rb->event_lock, flags); + } + + rcu_assign_pointer(event->rb, rb); + + if (old_rb) { + ring_buffer_put(old_rb); + /* + * Since we detached before setting the new rb, so that we + * could attach the new rb, we could have missed a wakeup. + * Provide it now. + */ + wake_up_all(&event->waitq); + } } static void ring_buffer_wakeup(struct perf_event *event) @@ -3940,7 +3953,7 @@ static void perf_mmap_close(struct vm_area_struct *vma) { struct perf_event *event = vma->vm_file->private_data; - struct ring_buffer *rb = event->rb; + struct ring_buffer *rb = ring_buffer_get(event); struct user_struct *mmap_user = rb->mmap_user; int mmap_locked = rb->mmap_locked; unsigned long size = perf_data_size(rb); @@ -3948,18 +3961,14 @@ static void perf_mmap_close(struct vm_area_struct *vma) atomic_dec(&rb->mmap_count); if (!atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) - return; + goto out_put; - /* Detach current event from the buffer. */ - rcu_assign_pointer(event->rb, NULL); - ring_buffer_detach(event, rb); + ring_buffer_attach(event, NULL); mutex_unlock(&event->mmap_mutex); /* If there's still other mmap()s of this buffer, we're done. */ - if (atomic_read(&rb->mmap_count)) { - ring_buffer_put(rb); /* can't be last */ - return; - } + if (atomic_read(&rb->mmap_count)) + goto out_put; /* * No other mmap()s, detach from all other events that might redirect @@ -3989,11 +3998,9 @@ again: * still restart the iteration to make sure we're not now * iterating the wrong list. */ - if (event->rb == rb) { - rcu_assign_pointer(event->rb, NULL); - ring_buffer_detach(event, rb); - ring_buffer_put(rb); /* can't be last, we still have one */ - } + if (event->rb == rb) + ring_buffer_attach(event, NULL); + mutex_unlock(&event->mmap_mutex); put_event(event); @@ -4018,6 +4025,7 @@ again: vma->vm_mm->pinned_vm -= mmap_locked; free_uid(mmap_user); +out_put: ring_buffer_put(rb); /* could be last */ } @@ -4135,7 +4143,6 @@ again: vma->vm_mm->pinned_vm += extra; ring_buffer_attach(event, rb); - rcu_assign_pointer(event->rb, rb); perf_event_init_userpage(event); perf_event_update_userpage(event); @@ -6934,7 +6941,7 @@ err_size: static int perf_event_set_output(struct perf_event *event, struct perf_event *output_event) { - struct ring_buffer *rb = NULL, *old_rb = NULL; + struct ring_buffer *rb = NULL; int ret = -EINVAL; if (!output_event) @@ -6962,8 +6969,6 @@ set: if (atomic_read(&event->mmap_count)) goto unlock; - old_rb = event->rb; - if (output_event) { /* get the rb we want to redirect to */ rb = ring_buffer_get(output_event); @@ -6971,23 +6976,7 @@ set: goto unlock; } - if (old_rb) - ring_buffer_detach(event, old_rb); - - if (rb) - ring_buffer_attach(event, rb); - - rcu_assign_pointer(event->rb, rb); - - if (old_rb) { - ring_buffer_put(old_rb); - /* - * Since we detached before setting the new rb, so that we - * could attach the new rb, we could have missed a wakeup. - * Provide it now. - */ - wake_up_all(&event->waitq); - } + ring_buffer_attach(event, rb); ret = 0; unlock: -- cgit v1.2.3-70-g09d2 From 63ba600028a001fa19f427486527387f54926d61 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Wed, 23 Apr 2014 11:08:05 +0100 Subject: asm-generic: Add renameat2 syscall Add the renameat2 syscall to the generic syscall list, which is used by the following architectures: arc, arm64, c6x, hexagon, metag, openrisc, score, tile, unicore32. Signed-off-by: James Hogan Acked-by: Arnd Bergmann Signed-off-by: Miklos Szeredi Cc: linux-arch@vger.kernel.org Cc: Vineet Gupta Cc: Catalin Marinas Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: Mark Salter Cc: Aurelien Jacquiot Cc: Richard Kuo Cc: linux-hexagon@vger.kernel.org Cc: linux-metag@vger.kernel.org Cc: Jonas Bonn Cc: Chen Liqin Cc: Lennox Wu Cc: Chris Metcalf Cc: Guan Xuetao --- include/uapi/asm-generic/unistd.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 6db66783d26..33364060808 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -697,9 +697,11 @@ __SYSCALL(__NR_finit_module, sys_finit_module) __SYSCALL(__NR_sched_setattr, sys_sched_setattr) #define __NR_sched_getattr 275 __SYSCALL(__NR_sched_getattr, sys_sched_getattr) +#define __NR_renameat2 276 +__SYSCALL(__NR_renameat2, sys_renameat2) #undef __NR_syscalls -#define __NR_syscalls 276 +#define __NR_syscalls 277 /* * All syscalls below here should go away really, -- cgit v1.2.3-70-g09d2 From e1618d461ca18d40f9c3ef70598abb72e75d27ae Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Tue, 20 May 2014 10:59:26 -0400 Subject: vlan: Fix build error wth vlan_get_encap_level() The new function vlan_get_encap_level() uses vlan_dev_priv() which is only conditionally avaialble when VLAN support is enabled. Make vlan_get_encap_level() conditionally available as well. Fixes: 44a4085538c8 ("bonding: Fix stacked device detection in arp monitoring") Reported-by: Stephen Rothwell CC: Stephen Rothwell Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index c901b13b6f0..b2acc4a1b13 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -198,6 +198,12 @@ extern void vlan_vids_del_by_dev(struct net_device *dev, const struct net_device *by_dev); extern bool vlan_uses_dev(const struct net_device *dev); + +static inline int vlan_get_encap_level(struct net_device *dev) +{ + BUG_ON(!is_vlan_dev(dev)); + return vlan_dev_priv(dev)->nest_level; +} #else static inline struct net_device * __vlan_find_dev_deep(struct net_device *real_dev, @@ -264,6 +270,11 @@ static inline bool vlan_uses_dev(const struct net_device *dev) { return false; } +static inline int vlan_get_encap_level(struct net_device *dev) +{ + BUG(); + return 0; +} #endif static inline bool vlan_hw_offload_capable(netdev_features_t features, @@ -485,9 +496,4 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb, skb->protocol = htons(ETH_P_802_2); } -static inline int vlan_get_encap_level(struct net_device *dev) -{ - BUG_ON(!is_vlan_dev(dev)); - return vlan_dev_priv(dev)->nest_level; -} #endif /* !(_LINUX_IF_VLAN_H_) */ -- cgit v1.2.3-70-g09d2 From a8246fedacadaab18b23b280ea3cf916ef5fc30e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 8 May 2014 16:56:12 +0200 Subject: dmaengine: omap: hide filter_fn for built-in drivers It is not possible to reference the omap_dma_filter_fn filter function from a built-in driver if the dmaengine driver itself is a loadable module, which is a valid configuration otherwise. This provides only the dummy alternative if the function is referenced by a built-in driver to allow a successful build. The filter function is only required by ATAGS based platforms, which will continue to be broken after this change for the bogus configuration. When booting from DT, with the dma channels correctly listed there, it will work fine. Signed-off-by: Arnd Bergmann Acked-by: Tony Lindgren Cc: Russell King Cc: Vinod Koul Cc: dmaengine@vger.kernel.org Signed-off-by: Vinod Koul --- include/linux/omap-dma.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h index 41a13e70f41..7944cdc27be 100644 --- a/include/linux/omap-dma.h +++ b/include/linux/omap-dma.h @@ -10,7 +10,7 @@ struct dma_chan; -#if defined(CONFIG_DMA_OMAP) || defined(CONFIG_DMA_OMAP_MODULE) +#if defined(CONFIG_DMA_OMAP) || (defined(CONFIG_DMA_OMAP_MODULE) && defined(MODULE)) bool omap_dma_filter_fn(struct dma_chan *, void *); #else static inline bool omap_dma_filter_fn(struct dma_chan *c, void *d) -- cgit v1.2.3-70-g09d2 From c1f43dd9c20d85e66c4d77e284f64ac114abe3f8 Mon Sep 17 00:00:00 2001 From: Xuelin Shi Date: Wed, 21 May 2014 14:02:37 -0700 Subject: dmaengine: fix dmaengine_unmap failure The count which is used to get_unmap_data maybe not the same as the count computed in dmaengine_unmap which causes to free data in a wrong pool. This patch fixes this issue by keeping the map count with unmap_data structure and use this count to get the pool. Cc: Signed-off-by: Xuelin Shi Signed-off-by: Dan Williams --- drivers/dma/dmaengine.c | 2 ++ include/linux/dmaengine.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index a886713937f..d5d30ed863c 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -1009,6 +1009,7 @@ static void dmaengine_unmap(struct kref *kref) dma_unmap_page(dev, unmap->addr[i], unmap->len, DMA_BIDIRECTIONAL); } + cnt = unmap->map_cnt; mempool_free(unmap, __get_unmap_pool(cnt)->pool); } @@ -1074,6 +1075,7 @@ dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags) memset(unmap, 0, sizeof(*unmap)); kref_init(&unmap->kref); unmap->dev = dev; + unmap->map_cnt = nr; return unmap; } diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 8300fb87b84..72cb0ddb967 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -429,6 +429,7 @@ typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param); typedef void (*dma_async_tx_callback)(void *dma_async_param); struct dmaengine_unmap_data { + u8 map_cnt; u8 to_cnt; u8 from_cnt; u8 bidi_cnt; -- cgit v1.2.3-70-g09d2 From ad0f614e4723db8cead439cf414108cbf975b224 Mon Sep 17 00:00:00 2001 From: Masatake YAMATO Date: Thu, 22 May 2014 11:54:20 -0700 Subject: wait: swap EXIT_ZOMBIE(Z) and EXIT_DEAD(X) chars in TASK_STATE_TO_CHAR_STR In commit ad86622b478e ("wait: swap EXIT_ZOMBIE and EXIT_DEAD to hide EXIT_TRACE from user-space") the order of task state definitions were changed: EXIT_DEAD and EXIT_ZOMBIE were swapped. Though the charterers for the states in TASK_STATE_TO_CHAR_STR string were not updated. This patch synchronizes the string to the order of definitions. Signed-off-by: Masatake YAMATO Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 25f54c79f75..21fbdae61b9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -220,7 +220,7 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq); #define TASK_PARKED 512 #define TASK_STATE_MAX 1024 -#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP" +#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWP" extern char ___assert_task_state[1 - 2*!!( sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)]; -- cgit v1.2.3-70-g09d2 From fbebf59778600488147744cdf7d7c20d22531025 Mon Sep 17 00:00:00 2001 From: srinik Date: Thu, 15 May 2014 11:28:44 +0100 Subject: ARM: 8057/1: amba: Add Qualcomm vendor ID. This patch adds Qualcomm amba vendor Id to the list. This ID is used in mmci driver. The ID selected in same lines like 0x41 is "A" for ARM, 0x51 is "Q" for Qualcomm. As there are no physical register on Qcom SOC for amba vendor id, this is a fake ID assigned based on "Q" prefix from Qualcomm. Signed-off-by: Srinivas Kandagatla Acked-by: Linus Walleij Signed-off-by: Russell King --- include/linux/amba/bus.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 63b5eff0a80..fdd7e1b61f6 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -47,6 +47,7 @@ struct amba_driver { enum amba_vendor { AMBA_VENDOR_ARM = 0x41, AMBA_VENDOR_ST = 0x80, + AMBA_VENDOR_QCOM = 0x51, }; extern struct bus_type amba_bustype; -- cgit v1.2.3-70-g09d2