From 4902c2025b8ade9c230d4bca25ec5f691e91cb1f Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Wed, 26 Jul 2017 16:47:27 +0300 Subject: clk: ti: add support for register read-modify-write low-level operation Useful for changing few bits on a register, this makes sure for example that the operation is done atomically in case of syscon. Signed-off-by: Tero Kristo --- include/linux/clk/ti.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index d18da839b810..9e8611470187 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -211,6 +211,7 @@ enum { * struct ti_clk_ll_ops - low-level ops for clocks * @clk_readl: pointer to register read function * @clk_writel: pointer to register write function + * @clk_rmw: pointer to register read-modify-write function * @clkdm_clk_enable: pointer to clockdomain enable function * @clkdm_clk_disable: pointer to clockdomain disable function * @clkdm_lookup: pointer to clockdomain lookup function @@ -226,6 +227,7 @@ enum { struct ti_clk_ll_ops { u32 (*clk_readl)(const struct clk_omap_reg *reg); void (*clk_writel)(u32 val, const struct clk_omap_reg *reg); + void (*clk_rmw)(u32 val, u32 mask, const struct clk_omap_reg *reg); int (*clkdm_clk_enable)(struct clockdomain *clkdm, struct clk *clk); int (*clkdm_clk_disable)(struct clockdomain *clkdm, struct clk *clk); -- cgit v1.2.3 From e403d00573431e1e3de1710a91c6090c60ec16af Mon Sep 17 00:00:00 2001 From: Peter De Schrijver Date: Thu, 25 Jan 2018 16:00:12 +0200 Subject: clk: tegra: MBIST work around for Tegra210 Tegra210 has a hw bug which can cause IP blocks to lock up when ungating a domain. The reason is that the logic responsible for resetting the memory built-in self test mode can come up in an undefined state because its clock is gated by a second level clock gate (SLCG). Work around this by making sure the logic will get some clock edges by ensuring the relevant clock is enabled and temporarily override the relevant SLCGs. Unfortunately for some IP blocks, the control bits for overriding the SLCGs are not in CAR, but in the IP block itself. This means we need to map a few extra register banks in the clock code. Signed-off-by: Peter De Schrijver Reviewed-by: Jon Hunter Tested-by: Jon Hunter Tested-by: Hector Martin Tested-by: Andre Heider Tested-by: Mikko Perttunen Signed-off-by: Thierry Reding fixup mbist --- include/linux/clk/tegra.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clk/tegra.h b/include/linux/clk/tegra.h index d23c9cf26993..afb9edfa5d58 100644 --- a/include/linux/clk/tegra.h +++ b/include/linux/clk/tegra.h @@ -128,5 +128,6 @@ extern void tegra210_sata_pll_hw_sequence_start(void); extern void tegra210_set_sata_pll_seq_sw(bool state); extern void tegra210_put_utmipll_in_iddq(void); extern void tegra210_put_utmipll_out_iddq(void); +extern int tegra210_clk_handle_mbist_war(unsigned int id); #endif /* __LINUX_CLK_TEGRA_H_ */ -- cgit v1.2.3 From e6d3cc7b1fac3d7f1313faf8ac9b23830113e3ec Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Wed, 14 Feb 2018 14:43:33 +0100 Subject: clk: divider: export clk_div_mask() helper Export clk_div_mask() in clk-provider header so every clock providers derived from the generic clock divider may share the definition instead of redefining it. Signed-off-by: Jerome Brunet Signed-off-by: Michael Turquette Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index f711be6e8c44..d8ba26d03332 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -399,6 +399,7 @@ struct clk_divider { spinlock_t *lock; }; +#define clk_div_mask(width) ((1 << (width)) - 1) #define to_clk_divider(_hw) container_of(_hw, struct clk_divider, hw) #define CLK_DIVIDER_ONE_BASED BIT(0) -- cgit v1.2.3 From 77deb66d262f8512130ff75ec5ea8e31070b41ed Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Wed, 14 Feb 2018 14:43:34 +0100 Subject: clk: mux: add helper function for index/value translation Add helper functions for the translation between parent index and register value in the generic multiplexer function. The purpose of this change is avoid duplicating the code in other clock providers, using the same generic logic. Signed-off-by: Jerome Brunet Signed-off-by: Michael Turquette Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index d8ba26d03332..fe720d679c31 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -511,6 +511,10 @@ struct clk_hw *clk_hw_register_mux_table(struct device *dev, const char *name, void __iomem *reg, u8 shift, u32 mask, u8 clk_mux_flags, u32 *table, spinlock_t *lock); +int clk_mux_val_to_index(struct clk_hw *hw, u32 *table, unsigned int flags, + unsigned int val); +unsigned int clk_mux_index_to_val(u32 *table, unsigned int flags, u8 index); + void clk_unregister_mux(struct clk *clk); void clk_hw_unregister_mux(struct clk_hw *hw); -- cgit v1.2.3 From fe3f338f0cb2ed4d4f06da054c21ae2f8a36ef2d Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Wed, 14 Feb 2018 14:43:38 +0100 Subject: clk: fix mux clock documentation The mux documentation mentions the non-existing parameter width instead of mask, so just sed this. The table field is missing in the documentation of clk_mux. Add a small blurb explaining what it is Fixes: 9d9f78ed9af0 ("clk: basic clock hardware types") Signed-off-by: Jerome Brunet Signed-off-by: Michael Turquette Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index fe720d679c31..cb18526d69cb 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -450,8 +450,9 @@ void clk_hw_unregister_divider(struct clk_hw *hw); * * @hw: handle between common and hardware-specific interfaces * @reg: register controlling multiplexer + * @table: array of register values corresponding to the parent index * @shift: shift to multiplexer bit field - * @width: width of mutliplexer bit field + * @mask: mask of mutliplexer bit field * @flags: hardware-specific flags * @lock: register lock * -- cgit v1.2.3 From b15ee490e16324c35b51f04bad54ae45a2cefd29 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Wed, 14 Feb 2018 14:43:39 +0100 Subject: clk: divider: read-only divider can propagate rate change When a divider clock has CLK_DIVIDER_READ_ONLY set, it means that the register shall be left un-touched, but it does not mean the clock should stop rate propagation if CLK_SET_RATE_PARENT is set This is properly handled in qcom clk-regmap-divider but it was not in the generic divider To fix this situation, introduce a new helper function divider_ro_round_rate, on the same model as divider_round_rate. Fixes: e6d5e7d90be9 ("clk-divider: Fix READ_ONLY when divider > 1") Signed-off-by: Jerome Brunet Tested-By: David Lechner Signed-off-by: Michael Turquette Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index cb18526d69cb..210a890008f9 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -420,6 +420,10 @@ long divider_round_rate_parent(struct clk_hw *hw, struct clk_hw *parent, unsigned long rate, unsigned long *prate, const struct clk_div_table *table, u8 width, unsigned long flags); +long divider_ro_round_rate_parent(struct clk_hw *hw, struct clk_hw *parent, + unsigned long rate, unsigned long *prate, + const struct clk_div_table *table, u8 width, + unsigned long flags, unsigned int val); int divider_get_val(unsigned long rate, unsigned long parent_rate, const struct clk_div_table *table, u8 width, unsigned long flags); @@ -780,6 +784,17 @@ static inline long divider_round_rate(struct clk_hw *hw, unsigned long rate, rate, prate, table, width, flags); } +static inline long divider_ro_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *prate, + const struct clk_div_table *table, + u8 width, unsigned long flags, + unsigned int val) +{ + return divider_ro_round_rate_parent(hw, clk_hw_get_parent(hw), + rate, prate, table, width, flags, + val); +} + /* * FIXME clock api without lock protection */ -- cgit v1.2.3 From 6e0d4ff4580c1272f4e4860bf22841ef31fd31ba Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Tue, 23 Jan 2018 20:24:45 +0800 Subject: clk: add more __must_check for bulk APIs we need it even when !CONFIG_HAVE_CLK because it allows us to catch missing checking return values in the non-clk compile configurations too. More test coverage. Cc: Stephen Boyd Suggested-by: Stephen Boyd Signed-off-by: Dong Aisheng Signed-off-by: Stephen Boyd --- include/linux/clk.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk.h b/include/linux/clk.h index 4c4ef9f34db3..0dbd0885b2c2 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -209,7 +209,7 @@ static inline int clk_prepare(struct clk *clk) return 0; } -static inline int clk_bulk_prepare(int num_clks, struct clk_bulk_data *clks) +static inline int __must_check clk_bulk_prepare(int num_clks, struct clk_bulk_data *clks) { might_sleep(); return 0; @@ -603,8 +603,8 @@ static inline struct clk *clk_get(struct device *dev, const char *id) return NULL; } -static inline int clk_bulk_get(struct device *dev, int num_clks, - struct clk_bulk_data *clks) +static inline int __must_check clk_bulk_get(struct device *dev, int num_clks, + struct clk_bulk_data *clks) { return 0; } @@ -614,8 +614,8 @@ static inline struct clk *devm_clk_get(struct device *dev, const char *id) return NULL; } -static inline int devm_clk_bulk_get(struct device *dev, int num_clks, - struct clk_bulk_data *clks) +static inline int __must_check devm_clk_bulk_get(struct device *dev, int num_clks, + struct clk_bulk_data *clks) { return 0; } @@ -645,7 +645,7 @@ static inline int clk_enable(struct clk *clk) return 0; } -static inline int clk_bulk_enable(int num_clks, struct clk_bulk_data *clks) +static inline int __must_check clk_bulk_enable(int num_clks, struct clk_bulk_data *clks) { return 0; } @@ -719,8 +719,8 @@ static inline void clk_disable_unprepare(struct clk *clk) clk_unprepare(clk); } -static inline int clk_bulk_prepare_enable(int num_clks, - struct clk_bulk_data *clks) +static inline int __must_check clk_bulk_prepare_enable(int num_clks, + struct clk_bulk_data *clks) { int ret; -- cgit v1.2.3 From 08fdc8a0138afaf324296a342f32ad26ec465e43 Mon Sep 17 00:00:00 2001 From: Mateusz Guzik Date: Tue, 3 Oct 2017 18:17:41 +0200 Subject: buffer.c: call thaw_super during emergency thaw There are 2 distinct freezing mechanisms - one operates on block devices and another one directly on super blocks. Both end up with the same result, but thaw of only one of these does not thaw the other. In particular fsfreeze --freeze uses the ioctl variant going to the super block. Since prior to this patch emergency thaw was not doing a relevant thaw, filesystems frozen with this method remained unaffected. The patch is a hack which adds blind unfreezing. In order to keep the super block write-locked the whole time the code is shuffled around and the newly introduced __iterate_supers is employed. Signed-off-by: Mateusz Guzik Signed-off-by: Al Viro --- include/linux/fs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 339e73742e73..b864fcb3b5aa 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2428,6 +2428,7 @@ extern int sync_blockdev(struct block_device *bdev); extern void kill_bdev(struct block_device *); extern struct super_block *freeze_bdev(struct block_device *); extern void emergency_thaw_all(void); +extern void emergency_thaw_bdev(struct super_block *sb); extern int thaw_bdev(struct block_device *bdev, struct super_block *sb); extern int fsync_bdev(struct block_device *); @@ -2453,6 +2454,11 @@ static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb) return 0; } +static inline int emergency_thaw_bdev(struct super_block *sb) +{ + return 0; +} + static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg) { } -- cgit v1.2.3 From 2d172691515961cad2abb4bf1b15d187bf2106cf Mon Sep 17 00:00:00 2001 From: David Lechner Date: Thu, 15 Mar 2018 21:52:18 -0500 Subject: clk: davinci: New driver for davinci PLL clocks This adds a new driver for mach-davinci PLL clocks. This is porting the code from arch/arm/mach-davinci/clock.c to the common clock framework. Additionally, it adds device tree support for these clocks. The ifeq ($(CONFIG_COMMON_CLK), y) in the Makefile is needed to prevent compile errors until the clock code in arch/arm/mach-davinci is removed. Note: although there are similar clocks for TI Keystone we are not able to share the code for a few reasons. The keystone clocks are device tree only and use legacy one-node-per-clock bindings. Also the register layouts are a bit different, which would add even more if/else mess to the keystone clocks. And the keystone PLL driver doesn't support setting clock rates. Signed-off-by: David Lechner Signed-off-by: Stephen Boyd --- include/linux/platform_data/clk-davinci-pll.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 include/linux/platform_data/clk-davinci-pll.h (limited to 'include/linux') diff --git a/include/linux/platform_data/clk-davinci-pll.h b/include/linux/platform_data/clk-davinci-pll.h new file mode 100644 index 000000000000..e55dab1d578b --- /dev/null +++ b/include/linux/platform_data/clk-davinci-pll.h @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PLL clock driver for TI Davinci SoCs + * + * Copyright (C) 2018 David Lechner + */ + +#ifndef __LINUX_PLATFORM_DATA_CLK_DAVINCI_PLL_H__ +#define __LINUX_PLATFORM_DATA_CLK_DAVINCI_PLL_H__ + +#include + +/** + * davinci_pll_platform_data + * @cfgchip: CFGCHIP syscon regmap + */ +struct davinci_pll_platform_data { + struct regmap *cfgchip; +}; + +#endif /* __LINUX_PLATFORM_DATA_CLK_DAVINCI_PLL_H__ */ -- cgit v1.2.3 From 1e88a8d64f221208801bb279ee7452df0b6d609f Mon Sep 17 00:00:00 2001 From: David Lechner Date: Thu, 15 Mar 2018 21:52:34 -0500 Subject: clk: davinci: New driver for TI DA8XX CFGCHIP clocks This adds a new driver for the gate and multiplexer clocks in the CFGCHIPn syscon registers on TI DA8XX-type SoCs. Signed-off-by: David Lechner Signed-off-by: Stephen Boyd --- include/linux/platform_data/clk-da8xx-cfgchip.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 include/linux/platform_data/clk-da8xx-cfgchip.h (limited to 'include/linux') diff --git a/include/linux/platform_data/clk-da8xx-cfgchip.h b/include/linux/platform_data/clk-da8xx-cfgchip.h new file mode 100644 index 000000000000..de0f77d38669 --- /dev/null +++ b/include/linux/platform_data/clk-da8xx-cfgchip.h @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * clk-da8xx-cfgchip - TI DaVinci DA8xx CFGCHIP clock driver + * + * Copyright (C) 2018 David Lechner + */ + +#ifndef __LINUX_PLATFORM_DATA_CLK_DA8XX_CFGCHIP_H__ +#define __LINUX_PLATFORM_DATA_CLK_DA8XX_CFGCHIP_H__ + +#include + +/** + * da8xx_cfgchip_clk_platform_data + * @cfgchip: CFGCHIP syscon regmap + */ +struct da8xx_cfgchip_clk_platform_data { + struct regmap *cfgchip; +}; + +#endif /* __LINUX_PLATFORM_DATA_CLK_DA8XX_CFGCHIP_H__ */ -- cgit v1.2.3 From 8ea229511e06f9635ecc338dcbe0db41a73623f0 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Mon, 2 Apr 2018 16:26:25 +0530 Subject: thermal: Add cooling device's statistics in sysfs This extends the sysfs interface for thermal cooling devices and exposes some pretty useful statistics. These statistics have proven to be quite useful specially while doing benchmarks related to the task scheduler, where we want to make sure that nothing has disrupted the test, specially the cooling device which may have put constraints on the CPUs. The information exposed here tells us to what extent the CPUs were constrained by the thermal framework. The write-only "reset" file is used to reset the statistics. The read-only "time_in_state_ms" file shows the time (in msec) spent by the device in the respective cooling states, and it prints one line per cooling state. The read-only "total_trans" file shows single positive integer value showing the total number of cooling state transitions the device has gone through since the time the cooling device is registered or the time when statistics were reset last. The read-only "trans_table" file shows a two dimensional matrix, where an entry (row i, column j) represents the number of transitions from State_i to State_j. This is how the directory structure looks like for a single cooling device: $ ls -R /sys/class/thermal/cooling_device0/ /sys/class/thermal/cooling_device0/: cur_state max_state power stats subsystem type uevent /sys/class/thermal/cooling_device0/power: autosuspend_delay_ms runtime_active_time runtime_suspended_time control runtime_status /sys/class/thermal/cooling_device0/stats: reset time_in_state_ms total_trans trans_table This is tested on ARM 64-bit Hisilicon hikey620 board running Ubuntu and ARM 64-bit Hisilicon hikey960 board running Android. Signed-off-by: Viresh Kumar Signed-off-by: Zhang Rui --- include/linux/thermal.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 8c5302374eaa..7834be668d80 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -148,6 +148,7 @@ struct thermal_cooling_device { struct device device; struct device_node *np; void *devdata; + void *stats; const struct thermal_cooling_device_ops *ops; bool updated; /* true if the cooling device does not need update */ struct mutex lock; /* protect thermal_instances list */ -- cgit v1.2.3 From 317d359df95dd0cb7653d09b7fc513770590cf85 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 5 Apr 2018 10:05:21 +0200 Subject: sched/core: Force proper alignment of 'struct util_est' For some as yet not understood reason, Tony gets unaligned access traps on IA64 because of: struct util_est ue = READ_ONCE(p->se.avg.util_est); and: WRITE_ONCE(p->se.avg.util_est, ue); introduced by commit: d519329f72a6 ("sched/fair: Update util_est only on util_avg updates") Normally those two fields should end up on an 8-byte aligned location, but UP and RANDSTRUCT can mess that up so enforce the alignment explicitly. Also make the alignment on sched_avg unconditional, as it is really about data locality, not false-sharing. With or without this patch the layout for sched_avg on a ia64-defconfig build looks like: $ pahole -EC sched_avg ia64-defconfig/kernel/sched/core.o die__process_function: tag not supported (INVALID)! struct sched_avg { /* typedef u64 */ long long unsigned int last_update_time; /* 0 8 */ /* typedef u64 */ long long unsigned int load_sum; /* 8 8 */ /* typedef u64 */ long long unsigned int runnable_load_sum; /* 16 8 */ /* typedef u32 */ unsigned int util_sum; /* 24 4 */ /* typedef u32 */ unsigned int period_contrib; /* 28 4 */ long unsigned int load_avg; /* 32 8 */ long unsigned int runnable_load_avg; /* 40 8 */ long unsigned int util_avg; /* 48 8 */ struct util_est { unsigned int enqueued; /* 56 4 */ unsigned int ewma; /* 60 4 */ } util_est; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ /* size: 64, cachelines: 1, members: 9 */ }; Reported-and-Tested-by: Tony Luck Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Cc: Linus Torvalds Cc: Mel Gorman Cc: Norbert Manthey Cc: Patrick Bellasi Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Tony Cc: Vincent Guittot Fixes: d519329f72a6 ("sched/fair: Update util_est only on util_avg updates") Link: http://lkml.kernel.org/r/20180405080521.GG4129@hirez.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- include/linux/sched.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index f228c6033832..b3d697f3b573 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -300,7 +300,7 @@ struct util_est { unsigned int enqueued; unsigned int ewma; #define UTIL_EST_WEIGHT_SHIFT 2 -}; +} __attribute__((__aligned__(sizeof(u64)))); /* * The load_avg/util_avg accumulates an infinite geometric series @@ -364,7 +364,7 @@ struct sched_avg { unsigned long runnable_load_avg; unsigned long util_avg; struct util_est util_est; -}; +} ____cacheline_aligned; struct sched_statistics { #ifdef CONFIG_SCHEDSTATS @@ -435,7 +435,7 @@ struct sched_entity { * Put into separate cache line so it does not * collide with read-mostly values above. */ - struct sched_avg avg ____cacheline_aligned_in_smp; + struct sched_avg avg; #endif }; -- cgit v1.2.3 From 1bd21c6c21e848996339508d3ffb106d505256a8 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Thu, 5 Apr 2018 11:53:01 +0200 Subject: syscalls/core: Introduce CONFIG_ARCH_HAS_SYSCALL_WRAPPER=y It may be useful for an architecture to override the definitions of the SYSCALL_DEFINE0() and __SYSCALL_DEFINEx() macros in , in particular to use a different calling convention for syscalls. This patch provides a mechanism to do so: It introduces CONFIG_ARCH_HAS_SYSCALL_WRAPPER. If it is enabled, is included in and may be used to define the macros mentioned above. Moreover, as the syscall calling convention may be different if CONFIG_ARCH_HAS_SYSCALL_WRAPPER is set, the syscall function prototypes in are #ifndef'd out in that case. Signed-off-by: Dominik Brodowski Acked-by: Linus Torvalds Cc: Al Viro Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180405095307.3730-3-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- include/linux/syscalls.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index b961184f597a..503ab245d4ce 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -81,6 +81,17 @@ union bpf_attr; #include #include +#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER +/* + * It may be useful for an architecture to override the definitions of the + * SYSCALL_DEFINE0() and __SYSCALL_DEFINEx() macros, in particular to use a + * different calling convention for syscalls. To allow for that, the prototypes + * for the sys_*() functions below will *not* be included if + * CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled. + */ +#include +#endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ + /* * __MAP - apply a macro to syscall arguments * __MAP(n, m, t1, a1, t2, a2, ..., tn, an) will expand to @@ -189,11 +200,13 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) } #endif +#ifndef SYSCALL_DEFINE0 #define SYSCALL_DEFINE0(sname) \ SYSCALL_METADATA(_##sname, 0); \ asmlinkage long sys_##sname(void); \ ALLOW_ERROR_INJECTION(sys_##sname, ERRNO); \ asmlinkage long sys_##sname(void) +#endif /* SYSCALL_DEFINE0 */ #define SYSCALL_DEFINE1(name, ...) SYSCALL_DEFINEx(1, _##name, __VA_ARGS__) #define SYSCALL_DEFINE2(name, ...) SYSCALL_DEFINEx(2, _##name, __VA_ARGS__) @@ -209,6 +222,8 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) __SYSCALL_DEFINEx(x, sname, __VA_ARGS__) #define __PROTECT(...) asmlinkage_protect(__VA_ARGS__) + +#ifndef __SYSCALL_DEFINEx #define __SYSCALL_DEFINEx(x, name, ...) \ asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \ __attribute__((alias(__stringify(SyS##name)))); \ @@ -223,6 +238,7 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) return ret; \ } \ static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) +#endif /* __SYSCALL_DEFINEx */ /* * Called before coming back to user-mode. Returning to user-mode with an @@ -252,7 +268,12 @@ static inline void addr_limit_user_check(void) * Please note that these prototypes here are only provided for information * purposes, for static analysis, and for linking from the syscall table. * These functions should not be called elsewhere from kernel code. + * + * As the syscall calling convention may be different from the default + * for architectures overriding the syscall calling convention, do not + * include the prototypes if CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled. */ +#ifndef CONFIG_ARCH_HAS_SYSCALL_WRAPPER asmlinkage long sys_io_setup(unsigned nr_reqs, aio_context_t __user *ctx); asmlinkage long sys_io_destroy(aio_context_t ctx); asmlinkage long sys_io_submit(aio_context_t, long, @@ -1076,6 +1097,8 @@ asmlinkage long sys_old_mmap(struct mmap_arg_struct __user *arg); */ asmlinkage long sys_ni_syscall(void); +#endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ + /* * Kernel code should not call syscalls (i.e., sys_xyzyyz()) directly. -- cgit v1.2.3 From fa697140f9a20119a9ec8fd7460cc4314fbdaff3 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Thu, 5 Apr 2018 11:53:02 +0200 Subject: syscalls/x86: Use 'struct pt_regs' based syscall calling convention for 64-bit syscalls Let's make use of ARCH_HAS_SYSCALL_WRAPPER=y on pure 64-bit x86-64 systems: Each syscall defines a stub which takes struct pt_regs as its only argument. It decodes just those parameters it needs, e.g: asmlinkage long sys_xyzzy(const struct pt_regs *regs) { return SyS_xyzzy(regs->di, regs->si, regs->dx); } This approach avoids leaking random user-provided register content down the call chain. For example, for sys_recv() which is a 4-parameter syscall, the assembly now is (in slightly reordered fashion): : callq <__fentry__> /* decode regs->di, ->si, ->dx and ->r10 */ mov 0x70(%rdi),%rdi mov 0x68(%rdi),%rsi mov 0x60(%rdi),%rdx mov 0x38(%rdi),%rcx [ SyS_recv() is automatically inlined by the compiler, as it is not [yet] used anywhere else ] /* clear %r9 and %r8, the 5th and 6th args */ xor %r9d,%r9d xor %r8d,%r8d /* do the actual work */ callq __sys_recvfrom /* cleanup and return */ cltq retq The only valid place in an x86-64 kernel which rightfully calls a syscall function on its own -- vsyscall -- needs to be modified to pass struct pt_regs onwards as well. To keep the syscall table generation working independent of SYSCALL_PTREGS being enabled, the stubs are named the same as the "original" syscall stubs, i.e. sys_*(). This patch is based on an original proof-of-concept | From: Linus Torvalds | Signed-off-by: Linus Torvalds and was split up and heavily modified by me, in particular to base it on ARCH_HAS_SYSCALL_WRAPPER, to limit it to 64-bit-only for the time being, and to update the vsyscall to the new calling convention. Signed-off-by: Dominik Brodowski Acked-by: Linus Torvalds Cc: Al Viro Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180405095307.3730-4-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- include/linux/syscalls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 503ab245d4ce..d7168b3a4b4c 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -102,7 +102,7 @@ union bpf_attr; * for SYSCALL_DEFINE/COMPAT_SYSCALL_DEFINE */ #define __MAP0(m,...) -#define __MAP1(m,t,a) m(t,a) +#define __MAP1(m,t,a,...) m(t,a) #define __MAP2(m,t,a,...) m(t,a), __MAP1(m,__VA_ARGS__) #define __MAP3(m,t,a,...) m(t,a), __MAP2(m,__VA_ARGS__) #define __MAP4(m,t,a,...) m(t,a), __MAP3(m,__VA_ARGS__) -- cgit v1.2.3 From 7303e30ec1d8fb5ca1f07c92d069241c32b2ee1b Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Thu, 5 Apr 2018 11:53:03 +0200 Subject: syscalls/core: Prepare CONFIG_ARCH_HAS_SYSCALL_WRAPPER=y for compat syscalls It may be useful for an architecture to override the definitions of the COMPAT_SYSCALL_DEFINE0() and __COMPAT_SYSCALL_DEFINEx() macros in , in particular to use a different calling convention for syscalls. This patch provides a mechanism to do so, based on the previously introduced CONFIG_ARCH_HAS_SYSCALL_WRAPPER. If it is enabled, is included in and may be used to define the macros mentioned above. Moreover, as the syscall calling convention may be different if CONFIG_ARCH_HAS_SYSCALL_WRAPPER is set, the compat syscall function prototypes in are #ifndef'd out in that case. As some of the syscalls and/or compat syscalls may not be present, the COND_SYSCALL() and COND_SYSCALL_COMPAT() macros in kernel/sys_ni.c as well as the SYS_NI() and COMPAT_SYS_NI() macros in kernel/time/posix-stubs.c can be re-defined in iff CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled. Signed-off-by: Dominik Brodowski Acked-by: Linus Torvalds Cc: Al Viro Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180405095307.3730-5-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- include/linux/compat.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 9847c5a013c3..2d85ec5cfda2 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -24,6 +24,17 @@ #include #include +#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER +/* + * It may be useful for an architecture to override the definitions of the + * COMPAT_SYSCALL_DEFINE0 and COMPAT_SYSCALL_DEFINEx() macros, in particular + * to use a different calling convention for syscalls. To allow for that, + + the prototypes for the compat_sys_*() functions below will *not* be included + * if CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled. + */ +#include +#endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ + #ifndef COMPAT_USE_64BIT_TIME #define COMPAT_USE_64BIT_TIME 0 #endif @@ -32,10 +43,12 @@ #define __SC_DELOUSE(t,v) ((__force t)(unsigned long)(v)) #endif +#ifndef COMPAT_SYSCALL_DEFINE0 #define COMPAT_SYSCALL_DEFINE0(name) \ asmlinkage long compat_sys_##name(void); \ ALLOW_ERROR_INJECTION(compat_sys_##name, ERRNO); \ asmlinkage long compat_sys_##name(void) +#endif /* COMPAT_SYSCALL_DEFINE0 */ #define COMPAT_SYSCALL_DEFINE1(name, ...) \ COMPAT_SYSCALL_DEFINEx(1, _##name, __VA_ARGS__) @@ -50,6 +63,7 @@ #define COMPAT_SYSCALL_DEFINE6(name, ...) \ COMPAT_SYSCALL_DEFINEx(6, _##name, __VA_ARGS__) +#ifndef COMPAT_SYSCALL_DEFINEx #define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))\ @@ -62,6 +76,7 @@ return C_SYSC##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__)); \ } \ static inline long C_SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) +#endif /* COMPAT_SYSCALL_DEFINEx */ #ifndef compat_user_stack_pointer #define compat_user_stack_pointer() current_user_stack_pointer() @@ -517,7 +532,12 @@ int __compat_save_altstack(compat_stack_t __user *, unsigned long); * Please note that these prototypes here are only provided for information * purposes, for static analysis, and for linking from the syscall table. * These functions should not be called elsewhere from kernel code. + * + * As the syscall calling convention may be different from the default + * for architectures overriding the syscall calling convention, do not + * include the prototypes if CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled. */ +#ifndef CONFIG_ARCH_HAS_SYSCALL_WRAPPER asmlinkage long compat_sys_io_setup(unsigned nr_reqs, u32 __user *ctx32p); asmlinkage long compat_sys_io_submit(compat_aio_context_t ctx_id, int nr, u32 __user *iocb); @@ -955,6 +975,8 @@ asmlinkage long compat_sys_stime(compat_time_t __user *tptr); /* obsolete: net/socket.c */ asmlinkage long compat_sys_socketcall(int call, u32 __user *args); +#endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ + /* * For most but not all architectures, "am I in a compat syscall?" and -- cgit v1.2.3 From 2e210bbb7429cdcf1a1a3ad00c1bf98bd9bf2452 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Tue, 3 Apr 2018 10:52:20 -0700 Subject: HID: input: fix battery level reporting on BT mice The commit 581c4484769e ("HID: input: map digitizer battery usage") assumed that devices having input (qas opposed to feature) report for battery strength would report the data on their own, without the need to be polled by the kernel; unfortunately it is not so. Many wireless mice do not send unsolicited reports with battery strength data and have to be polled explicitly. As a complication, stylus devices on digitizers are not normally connected to the base and thus can not be polled - the base can only determine battery strength in the stylus when it is in proximity. To solve this issue, we add a special flag that tells the kernel to avoid polling the device (and expect unsolicited reports) and set it when report field with physical usage of digitizer stylus (HID_DG_STYLUS). Unless this flag is set, and we have not seen the unsolicited reports, the kernel will attempt to poll the device when userspace attempts to read "capacity" and "state" attributes of power_supply object corresponding to the devices battery. Fixes: 581c4484769e ("HID: input: map digitizer battery usage") Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=198095 Cc: stable@vger.kernel.org Reported-and-tested-by: Martin van Es Signed-off-by: Dmitry Torokhov Signed-off-by: Jiri Kosina --- include/linux/hid.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 8da3e1f48195..26240a22978a 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -516,6 +516,12 @@ enum hid_type { HID_TYPE_USBNONE }; +enum hid_battery_status { + HID_BATTERY_UNKNOWN = 0, + HID_BATTERY_QUERIED, /* Kernel explicitly queried battery strength */ + HID_BATTERY_REPORTED, /* Device sent unsolicited battery strength report */ +}; + struct hid_driver; struct hid_ll_driver; @@ -558,7 +564,8 @@ struct hid_device { /* device report descriptor */ __s32 battery_max; __s32 battery_report_type; __s32 battery_report_id; - bool battery_reported; + enum hid_battery_status battery_status; + bool battery_avoid_query; #endif unsigned int status; /* see STAT flags above */ -- cgit v1.2.3 From e145242ea0df6b7d28fd7186e61d6840fa4bb06e Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Mon, 9 Apr 2018 12:51:42 +0200 Subject: syscalls/core, syscalls/x86: Clean up syscall stub naming convention Tidy the naming convention for compat syscall subs. Hints which describe the purpose of the stub go in front and receive a double underscore to denote that they are generated on-the-fly by the SYSCALL_DEFINEx() macro. For the generic case, this means (0xffffffff prefix removed): 810f08d0 t kernel_waitid # common C function (see kernel/exit.c) __do_sys_waitid # inlined helper doing the actual work # (takes original parameters as declared) 810f1aa0 T __se_sys_waitid # sign-extending C function calling inlined # helper (takes parameters of type long; # casts them to the declared type) 810f1aa0 T sys_waitid # alias to __se_sys_waitid() (taking # parameters as declared), to be included # in syscall table For x86, the naming is as follows: 810efc70 t kernel_waitid # common C function (see kernel/exit.c) __do_sys_waitid # inlined helper doing the actual work # (takes original parameters as declared) 810efd60 t __se_sys_waitid # sign-extending C function calling inlined # helper (takes parameters of type long; # casts them to the declared type) 810f1140 T __ia32_sys_waitid # IA32_EMULATION 32-bit-ptregs -> C stub, # calls __se_sys_waitid(); to be included # in syscall table 810f1110 T sys_waitid # x86 64-bit-ptregs -> C stub, calls # __se_sys_waitid(); to be included in # syscall table For x86, sys_waitid() will be re-named to __x64_sys_waitid in a follow-up patch. Suggested-by: Ingo Molnar Signed-off-by: Dominik Brodowski Cc: Al Viro Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180409105145.5364-2-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- include/linux/syscalls.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index d7168b3a4b4c..70fcda1a9049 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -223,21 +223,26 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) #define __PROTECT(...) asmlinkage_protect(__VA_ARGS__) +/* + * The asmlinkage stub is aliased to a function named __se_sys_*() which + * sign-extends 32-bit ints to longs whenever needed. The actual work is + * done within __do_sys_*(). + */ #ifndef __SYSCALL_DEFINEx #define __SYSCALL_DEFINEx(x, name, ...) \ asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \ - __attribute__((alias(__stringify(SyS##name)))); \ + __attribute__((alias(__stringify(__se_sys##name)))); \ ALLOW_ERROR_INJECTION(sys##name, ERRNO); \ - static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ - asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ - asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ + static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ + asmlinkage long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ + asmlinkage long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ { \ - long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \ + long ret = __do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__));\ __MAP(x,__SC_TEST,__VA_ARGS__); \ __PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \ return ret; \ } \ - static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) + static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) #endif /* __SYSCALL_DEFINEx */ /* -- cgit v1.2.3 From 5ac9efa3c50d7caff9f3933bb8a3ad1139d92d92 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Mon, 9 Apr 2018 12:51:43 +0200 Subject: syscalls/core, syscalls/x86: Clean up compat syscall stub naming convention Tidy the naming convention for compat syscall subs. Hints which describe the purpose of the stub go in front and receive a double underscore to denote that they are generated on-the-fly by the COMPAT_SYSCALL_DEFINEx() macro. For the generic case, this means: t kernel_waitid # common C function (see kernel/exit.c) __do_compat_sys_waitid # inlined helper doing the actual work # (takes original parameters as declared) T __se_compat_sys_waitid # sign-extending C function calling inlined # helper (takes parameters of type long, # casts them to unsigned long and then to # the declared type) T compat_sys_waitid # alias to __se_compat_sys_waitid() # (taking parameters as declared), to # be included in syscall table For x86, the naming is as follows: t kernel_waitid # common C function (see kernel/exit.c) __do_compat_sys_waitid # inlined helper doing the actual work # (takes original parameters as declared) t __se_compat_sys_waitid # sign-extending C function calling inlined # helper (takes parameters of type long, # casts them to unsigned long and then to # the declared type) T __ia32_compat_sys_waitid # IA32_EMULATION 32-bit-ptregs -> C stub, # calls __se_compat_sys_waitid(); to be # included in syscall table T __x32_compat_sys_waitid # x32 64-bit-ptregs -> C stub, calls # __se_compat_sys_waitid(); to be included # in syscall table If only one of IA32_EMULATION and x32 is enabled, __se_compat_sys_waitid() may be inlined into the stub __{ia32,x32}_compat_sys_waitid(). Suggested-by: Ingo Molnar Signed-off-by: Dominik Brodowski Cc: Al Viro Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180409105145.5364-3-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- include/linux/compat.h | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 2d85ec5cfda2..aca050aac7b6 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -63,19 +63,24 @@ #define COMPAT_SYSCALL_DEFINE6(name, ...) \ COMPAT_SYSCALL_DEFINEx(6, _##name, __VA_ARGS__) +/* + * The asmlinkage stub is aliased to a function named __se_compat_sys_*() which + * sign-extends 32-bit ints to longs whenever needed. The actual work is + * done within __do_compat_sys_*(). + */ #ifndef COMPAT_SYSCALL_DEFINEx -#define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ - asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ - asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))\ - __attribute__((alias(__stringify(compat_SyS##name)))); \ - ALLOW_ERROR_INJECTION(compat_sys##name, ERRNO); \ - static inline long C_SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ - asmlinkage long compat_SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__));\ - asmlinkage long compat_SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__))\ - { \ - return C_SYSC##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__)); \ - } \ - static inline long C_SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) +#define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ + asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ + asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \ + __attribute__((alias(__stringify(__se_compat_sys##name)))); \ + ALLOW_ERROR_INJECTION(compat_sys##name, ERRNO); \ + static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ + asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ + asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ + { \ + return __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));\ + } \ + static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) #endif /* COMPAT_SYSCALL_DEFINEx */ #ifndef compat_user_stack_pointer -- cgit v1.2.3 From a09acf4b43b90581bf53b0c03cc84ed693bf27e2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 9 Apr 2018 21:12:30 +0100 Subject: vfs: Remove the const from dir_context::actor Remove the const marking from the actor function pointer in the dir_context struct. The const prevents the structure from being used as part of a kmalloc'd object as it makes the compiler require that the actor member be set at object initialisation time (or not at all), incuring something like the following error if you try and set it later: fs/afs/dir.c:556:20: error: assignment of read-only member 'actor' Marking the member const like this adds very little in the way of sanity checking as the type checking system is likely to provide sufficient - and if not, the kernel is very likely to oops repeatably in this case. Fixes: ac6614b76478 ("[readdir] constify ->actor") Signed-off-by: David Howells Reviewed-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1ee7f592e239..3a5c19d9f651 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1667,7 +1667,7 @@ typedef int (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, unsigned); struct dir_context { - const filldir_t actor; + filldir_t actor; loff_t pos; }; -- cgit v1.2.3 From 96a938aa214e965d5b4a2f10443b29cad14289b9 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Tue, 20 Mar 2018 15:31:38 -0700 Subject: Input: atmel_mxt_ts - remove platform data support Now that there are no users of custom Atmel platform data, and everyone has switched to the generic device properties, we can remove support for the platform data. Acked-by: Nick Dyer Signed-off-by: Dmitry Torokhov Signed-off-by: Benson Leung --- include/linux/platform_data/atmel_mxt_ts.h | 31 ------------------------------ 1 file changed, 31 deletions(-) delete mode 100644 include/linux/platform_data/atmel_mxt_ts.h (limited to 'include/linux') diff --git a/include/linux/platform_data/atmel_mxt_ts.h b/include/linux/platform_data/atmel_mxt_ts.h deleted file mode 100644 index 695035a8d7fb..000000000000 --- a/include/linux/platform_data/atmel_mxt_ts.h +++ /dev/null @@ -1,31 +0,0 @@ -/* - * Atmel maXTouch Touchscreen driver - * - * Copyright (C) 2010 Samsung Electronics Co.Ltd - * Author: Joonyoung Shim - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ - -#ifndef __LINUX_PLATFORM_DATA_ATMEL_MXT_TS_H -#define __LINUX_PLATFORM_DATA_ATMEL_MXT_TS_H - -#include - -enum mxt_suspend_mode { - MXT_SUSPEND_DEEP_SLEEP = 0, - MXT_SUSPEND_T9_CTRL = 1, -}; - -/* The platform data for the Atmel maXTouch touchscreen driver */ -struct mxt_platform_data { - unsigned long irqflags; - u8 t19_num_keys; - const unsigned int *t19_keymap; - enum mxt_suspend_mode suspend_mode; -}; - -#endif /* __LINUX_PLATFORM_DATA_ATMEL_MXT_TS_H */ -- cgit v1.2.3 From 15fe8a90bb45b953ca36f074194fcb519a05fdec Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sun, 8 Apr 2018 17:48:11 +0800 Subject: blk-mq: remove blk_mq_delay_queue() No driver uses this interface any more, so remove it. Cc: Stefan Haberland Tested-by: Christian Borntraeger Reviewed-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 8efcf49796a3..e3986f4b3461 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -183,7 +183,6 @@ enum { BLK_MQ_S_STOPPED = 0, BLK_MQ_S_TAG_ACTIVE = 1, BLK_MQ_S_SCHED_RESTART = 2, - BLK_MQ_S_START_ON_RUN = 3, BLK_MQ_MAX_DEPTH = 10240, @@ -270,7 +269,6 @@ void blk_mq_unquiesce_queue(struct request_queue *q); void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_run_hw_queues(struct request_queue *q, bool async); -void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv); void blk_mq_freeze_queue(struct request_queue *q); -- cgit v1.2.3 From a93f00b3762026dd8231f473fae9346bda07db03 Mon Sep 17 00:00:00 2001 From: Mathieu Malaterre Date: Fri, 6 Apr 2018 22:14:51 +0200 Subject: backing: silence compiler warning using __printf MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit __printf marker was added in commit d2cc4dde9206 ("bdi_register: add __printf verification, fix arg mismatch") for function `bdi_register` since it is useful to verify format and arguments. Apply equivalent gcc attribute to `bdi_register_va`. Remove warning triggered with W=1: mm/backing-dev.c:881:2: warning: function might be possible candidate for ‘gnu_printf’ format attribute [-Wsuggest-attribute=format] Reviewed-by: Jan Kara Signed-off-by: Mathieu Malaterre Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 3e4ce54d84ab..0e9c0f71f726 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -28,6 +28,7 @@ void bdi_put(struct backing_dev_info *bdi); __printf(2, 3) int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...); +__printf(2, 0) int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args); int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner); -- cgit v1.2.3 From fb14ae8853e4f0347950f98e604fa2f4f3b3abe1 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 28 Feb 2018 15:30:54 -0500 Subject: xprtrdma: "Support" call-only RPCs RPC-over-RDMA version 1 credit accounting relies on there being a response message for every RPC Call. This means that RPC procedures that have no reply will disrupt credit accounting, just in the same way as a retransmit would (since it is sent because no reply has arrived). Deal with the "no reply" case the same way. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/linux/sunrpc/clnt.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index ed761f751ecb..9b11b6a0978c 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -217,5 +217,12 @@ void rpc_clnt_xprt_switch_add_xprt(struct rpc_clnt *, struct rpc_xprt *); bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt, const struct sockaddr *sap); void rpc_cleanup_clids(void); + +static inline int rpc_reply_expected(struct rpc_task *task) +{ + return (task->tk_msg.rpc_proc != NULL) && + (task->tk_msg.rpc_proc->p_decode != NULL); +} + #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_CLNT_H */ -- cgit v1.2.3 From ecd465ee88bb6648c06c82b1abae6ec28cf5fccb Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 5 Mar 2018 15:12:57 -0500 Subject: SUNRPC: Move xprt_update_rtt callsite Since commit 33849792cbcd ("xprtrdma: Detect unreachable NFS/RDMA servers more reliably"), the xprtrdma transport now has a ->timer callout. But xprtrdma does not need to compute RTT data, only UDP needs that. Move the xprt_update_rtt call into the UDP transport implementation. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 7fad83881ce1..ad322cec049a 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -373,6 +373,7 @@ void xprt_wait_for_buffer_space(struct rpc_task *task, rpc_action action); void xprt_write_space(struct rpc_xprt *xprt); void xprt_adjust_cwnd(struct rpc_xprt *xprt, struct rpc_task *task, int result); struct rpc_rqst * xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid); +void xprt_update_rtt(struct rpc_task *task); void xprt_complete_rqst(struct rpc_task *task, int copied); void xprt_pin_rqst(struct rpc_rqst *req); void xprt_unpin_rqst(struct rpc_rqst *req); -- cgit v1.2.3 From ff699ea8269a02d977c6ee42d58f76efe83a34f9 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 5 Mar 2018 15:13:13 -0500 Subject: SUNRPC: Make num_reqs a non-atomic integer If recording xprt->stat.max_slots is moved into xprt_alloc_slot, then xprt->num_reqs is never manipulated outside xprt->reserve_lock. There's no longer a need for xprt->num_reqs to be atomic. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/linux/sunrpc/xprt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index ad322cec049a..5fea0fb420df 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -197,7 +197,7 @@ struct rpc_xprt { struct list_head free; /* free slots */ unsigned int max_reqs; /* max number of slots */ unsigned int min_reqs; /* min number of slots */ - atomic_t num_reqs; /* total slots */ + unsigned int num_reqs; /* total slots */ unsigned long state; /* transport state */ unsigned char resvport : 1; /* use a reserved port */ atomic_t swapper; /* we're swapping over this -- cgit v1.2.3 From 912678dbc592db7ad618f383866ad23e43cd51f3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 20 Mar 2018 16:43:15 -0400 Subject: NFS: Move the delegation return down into nfs4_proc_remove() Move the delegation return out of generic code and down into the NFSv4 specific unlink code. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 6959968dc36a..3ebf14b3bf0b 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1590,7 +1590,7 @@ struct nfs_rpc_ops { unsigned int); int (*create) (struct inode *, struct dentry *, struct iattr *, int); - int (*remove) (struct inode *, const struct qstr *); + int (*remove) (struct inode *, struct dentry *); void (*unlink_setup) (struct rpc_message *, struct inode *dir); void (*unlink_rpc_prepare) (struct rpc_task *, struct nfs_unlinkdata *); int (*unlink_done) (struct rpc_task *, struct inode *); -- cgit v1.2.3 From f2c2c552f119db84d85a53a8bd76479f34df02b1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 20 Mar 2018 16:43:16 -0400 Subject: NFS: Move delegation recall into the NFSv4 callback for rename_setup() Move the delegation recall out of the generic code, and into the NFSv4 specific callback. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/nfs_xdr.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 3ebf14b3bf0b..4b87e2d726b1 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1594,7 +1594,9 @@ struct nfs_rpc_ops { void (*unlink_setup) (struct rpc_message *, struct inode *dir); void (*unlink_rpc_prepare) (struct rpc_task *, struct nfs_unlinkdata *); int (*unlink_done) (struct rpc_task *, struct inode *); - void (*rename_setup) (struct rpc_message *msg, struct inode *dir); + void (*rename_setup) (struct rpc_message *msg, + struct dentry *old_dentry, + struct dentry *new_dentry); void (*rename_rpc_prepare)(struct rpc_task *task, struct nfs_renamedata *); int (*rename_done) (struct rpc_task *task, struct inode *old_dir, struct inode *new_dir); int (*link) (struct inode *, struct inode *, const struct qstr *); -- cgit v1.2.3 From 977fcc2b0b41c1fc82e8349995695e207ccb6684 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 20 Mar 2018 16:43:17 -0400 Subject: NFS: Add a delegation return into nfs4_proc_unlink_setup() Ensure that when we do finally delete the file, then we return the delegation. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 4b87e2d726b1..c4ba58b3c0f8 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1591,7 +1591,7 @@ struct nfs_rpc_ops { int (*create) (struct inode *, struct dentry *, struct iattr *, int); int (*remove) (struct inode *, struct dentry *); - void (*unlink_setup) (struct rpc_message *, struct inode *dir); + void (*unlink_setup) (struct rpc_message *, struct dentry *); void (*unlink_rpc_prepare) (struct rpc_task *, struct nfs_unlinkdata *); int (*unlink_done) (struct rpc_task *, struct inode *); void (*rename_setup) (struct rpc_message *msg, -- cgit v1.2.3 From c135cb39a907b85aef5389c191b6f02cffbadb8a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 20 Mar 2018 16:43:19 -0400 Subject: NFS: Remove the unused return_delegation() callback Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/nfs_xdr.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index c4ba58b3c0f8..34d28564ecf3 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1635,7 +1635,6 @@ struct nfs_rpc_ops { struct iattr *iattr, int *); int (*have_delegation)(struct inode *, fmode_t); - int (*return_delegation)(struct inode *); struct nfs_client *(*alloc_client) (const struct nfs_client_initdata *); struct nfs_client *(*init_client) (struct nfs_client *, const struct nfs_client_initdata *); -- cgit v1.2.3 From 909728821e366599b899251e0a0f023c0ccf4fb0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 20 Mar 2018 16:53:27 -0400 Subject: NFS: Convert NFS_INO_INVALID flags to unsigned long The cache validity attribute is unsigned long, so make sure that the flags are too. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/nfs_fs.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 38187c68063d..4afb11be73f4 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -198,14 +198,14 @@ struct nfs_inode { /* * Cache validity bit flags */ -#define NFS_INO_INVALID_ATTR 0x0001 /* cached attrs are invalid */ -#define NFS_INO_INVALID_DATA 0x0002 /* cached data is invalid */ -#define NFS_INO_INVALID_ATIME 0x0004 /* cached atime is invalid */ -#define NFS_INO_INVALID_ACCESS 0x0008 /* cached access cred invalid */ -#define NFS_INO_INVALID_ACL 0x0010 /* cached acls are invalid */ -#define NFS_INO_REVAL_PAGECACHE 0x0020 /* must revalidate pagecache */ -#define NFS_INO_REVAL_FORCED 0x0040 /* force revalidation ignoring a delegation */ -#define NFS_INO_INVALID_LABEL 0x0080 /* cached label is invalid */ +#define NFS_INO_INVALID_ATTR BIT(0) /* cached attrs are invalid */ +#define NFS_INO_INVALID_DATA BIT(1) /* cached data is invalid */ +#define NFS_INO_INVALID_ATIME BIT(2) /* cached atime is invalid */ +#define NFS_INO_INVALID_ACCESS BIT(3) /* cached access cred invalid */ +#define NFS_INO_INVALID_ACL BIT(4) /* cached acls are invalid */ +#define NFS_INO_REVAL_PAGECACHE BIT(5) /* must revalidate pagecache */ +#define NFS_INO_REVAL_FORCED BIT(6) /* force revalidation ignoring a delegation */ +#define NFS_INO_INVALID_LABEL BIT(7) /* cached label is invalid */ /* * Bit offsets in flags field -- cgit v1.2.3 From 16e143751727471f9a565515344196693bbc8762 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 20 Mar 2018 16:53:31 -0400 Subject: NFS: More fine grained attribute tracking Currently, if the NFS_INO_INVALID_ATTR flag is set, for instance by a call to nfs_post_op_update_inode_locked(), then it will not be cleared until all the attributes have been revalidated. This means, for instance, that NFSv4 writes will always force a full attribute revalidation. Track the ctime, mtime, size and change attribute separately from the other attributes so that we can have nfs_post_op_update_inode_locked() set them correctly, and later have the cache consistency bitmask be able to clear them. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/nfs_fs.h | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 4afb11be73f4..2f129bbfaae8 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -198,7 +198,6 @@ struct nfs_inode { /* * Cache validity bit flags */ -#define NFS_INO_INVALID_ATTR BIT(0) /* cached attrs are invalid */ #define NFS_INO_INVALID_DATA BIT(1) /* cached data is invalid */ #define NFS_INO_INVALID_ATIME BIT(2) /* cached atime is invalid */ #define NFS_INO_INVALID_ACCESS BIT(3) /* cached access cred invalid */ @@ -206,6 +205,17 @@ struct nfs_inode { #define NFS_INO_REVAL_PAGECACHE BIT(5) /* must revalidate pagecache */ #define NFS_INO_REVAL_FORCED BIT(6) /* force revalidation ignoring a delegation */ #define NFS_INO_INVALID_LABEL BIT(7) /* cached label is invalid */ +#define NFS_INO_INVALID_CHANGE BIT(8) /* cached change is invalid */ +#define NFS_INO_INVALID_CTIME BIT(9) /* cached ctime is invalid */ +#define NFS_INO_INVALID_MTIME BIT(10) /* cached mtime is invalid */ +#define NFS_INO_INVALID_SIZE BIT(11) /* cached size is invalid */ +#define NFS_INO_INVALID_OTHER BIT(12) /* other attrs are invalid */ + +#define NFS_INO_INVALID_ATTR (NFS_INO_INVALID_CHANGE \ + | NFS_INO_INVALID_CTIME \ + | NFS_INO_INVALID_MTIME \ + | NFS_INO_INVALID_SIZE \ + | NFS_INO_INVALID_OTHER) /* inode metadata is invalid */ /* * Bit offsets in flags field @@ -292,10 +302,11 @@ static inline void nfs_mark_for_revalidate(struct inode *inode) struct nfs_inode *nfsi = NFS_I(inode); spin_lock(&inode->i_lock); - nfsi->cache_validity |= NFS_INO_INVALID_ATTR | - NFS_INO_REVAL_PAGECACHE | - NFS_INO_INVALID_ACCESS | - NFS_INO_INVALID_ACL; + nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL + | NFS_INO_INVALID_CHANGE + | NFS_INO_INVALID_CTIME; if (S_ISDIR(inode->i_mode)) nfsi->cache_validity |= NFS_INO_INVALID_DATA; spin_unlock(&inode->i_lock); -- cgit v1.2.3 From 0e779aa70308462e45f7cd1a54de418dfe101694 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 20 Mar 2018 17:03:05 -0400 Subject: SUNRPC: Add helpers for decoding opaque and string types Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/sunrpc/xdr.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index d950223c64b1..7e609de34d85 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -253,6 +253,12 @@ xdr_stream_remaining(const struct xdr_stream *xdr) return xdr->nwords << 2; } +ssize_t xdr_stream_decode_opaque(struct xdr_stream *xdr, void *ptr, + size_t size); +ssize_t xdr_stream_decode_opaque_dup(struct xdr_stream *xdr, void **ptr, + size_t maxlen, gfp_t gfp_flags); +ssize_t xdr_stream_decode_string(struct xdr_stream *xdr, char *str, + size_t size); ssize_t xdr_stream_decode_string_dup(struct xdr_stream *xdr, char **str, size_t maxlen, gfp_t gfp_flags); /** -- cgit v1.2.3 From 85e3dd44c514a8bed6c713df4af657be83d00f68 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 20 Mar 2018 17:03:06 -0400 Subject: SUNRPC: Add a helper for encoding opaque data inline Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/sunrpc/xdr.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 7e609de34d85..a43c3b6455b6 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -318,6 +318,31 @@ xdr_stream_encode_u64(struct xdr_stream *xdr, __u64 n) return len; } +/** + * xdr_stream_encode_opaque_inline - Encode opaque xdr data + * @xdr: pointer to xdr_stream + * @ptr: pointer to void pointer + * @len: size of object + * + * Return values: + * On success, returns length in bytes of XDR buffer consumed + * %-EMSGSIZE on XDR buffer overflow + */ +static inline ssize_t +xdr_stream_encode_opaque_inline(struct xdr_stream *xdr, void **ptr, size_t len) +{ + size_t count = sizeof(__u32) + xdr_align_size(len); + __be32 *p = xdr_reserve_space(xdr, count); + + if (unlikely(!p)) { + *ptr = NULL; + return -EMSGSIZE; + } + xdr_encode_opaque(p, NULL, len); + *ptr = ++p; + return count; +} + /** * xdr_stream_encode_opaque_fixed - Encode fixed length opaque xdr data * @xdr: pointer to xdr_stream -- cgit v1.2.3 From 37c88763def8474bc0972fbd1adb0d21670104b7 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 20 Mar 2018 17:03:08 -0400 Subject: NFSv4; Clean up XDR encoding of type bitmap4 Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/sunrpc/xdr.h | 63 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 63 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index a43c3b6455b6..2bd68177a442 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -386,6 +386,31 @@ xdr_stream_encode_opaque(struct xdr_stream *xdr, const void *ptr, size_t len) return count; } +/** + * xdr_stream_encode_uint32_array - Encode variable length array of integers + * @xdr: pointer to xdr_stream + * @array: array of integers + * @array_size: number of elements in @array + * + * Return values: + * On success, returns length in bytes of XDR buffer consumed + * %-EMSGSIZE on XDR buffer overflow + */ +static inline ssize_t +xdr_stream_encode_uint32_array(struct xdr_stream *xdr, + const __u32 *array, size_t array_size) +{ + ssize_t ret = (array_size+1) * sizeof(__u32); + __be32 *p = xdr_reserve_space(xdr, ret); + + if (unlikely(!p)) + return -EMSGSIZE; + *p++ = cpu_to_be32(array_size); + for (; array_size > 0; p++, array++, array_size--) + *p = cpu_to_be32p(array); + return ret; +} + /** * xdr_stream_decode_u32 - Decode a 32-bit integer * @xdr: pointer to xdr_stream @@ -463,6 +488,44 @@ xdr_stream_decode_opaque_inline(struct xdr_stream *xdr, void **ptr, size_t maxle } return len; } + +/** + * xdr_stream_decode_uint32_array - Decode variable length array of integers + * @xdr: pointer to xdr_stream + * @array: location to store the integer array or NULL + * @array_size: number of elements to store + * + * Return values: + * On success, returns number of elements stored in @array + * %-EBADMSG on XDR buffer overflow + * %-EMSGSIZE if the size of the array exceeds @array_size + */ +static inline ssize_t +xdr_stream_decode_uint32_array(struct xdr_stream *xdr, + __u32 *array, size_t array_size) +{ + __be32 *p; + __u32 len; + ssize_t retval; + + if (unlikely(xdr_stream_decode_u32(xdr, &len) < 0)) + return -EBADMSG; + p = xdr_inline_decode(xdr, len * sizeof(*p)); + if (unlikely(!p)) + return -EBADMSG; + if (array == NULL) + return len; + if (len <= array_size) { + if (len < array_size) + memset(array+len, 0, (array_size-len)*sizeof(*array)); + array_size = len; + retval = len; + } else + retval = -EMSGSIZE; + for (; array_size > 0; p++, array++, array_size--) + *array = be32_to_cpup(p); + return retval; +} #endif /* __KERNEL__ */ #endif /* _SUNRPC_XDR_H_ */ -- cgit v1.2.3 From b082b2e1454c3e0217d7cf70f2211966c3d54301 Mon Sep 17 00:00:00 2001 From: Shawn Nematbakhsh Date: Fri, 23 Mar 2018 18:42:46 +0100 Subject: platform/chrome: cros_ec_debugfs: Add PD port info to debugfs Add info useful for debugging USB-PD port state. Signed-off-by: Shawn Nematbakhsh Signed-off-by: Enric Balletbo i Serra Reviewed-by: Andy Shevchenko Acked-by: Lee Jones Signed-off-by: Benson Leung --- include/linux/mfd/cros_ec_commands.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index 2b96e630e3b6..f2edd9969b40 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -2948,6 +2948,9 @@ struct ec_response_usb_pd_control_v1 { #define EC_CMD_USB_PD_PORTS 0x102 +/* Maximum number of PD ports on a device, num_ports will be <= this */ +#define EC_USB_PD_MAX_PORTS 8 + struct ec_response_usb_pd_ports { uint8_t num_ports; } __packed; -- cgit v1.2.3 From c1d1e91aff3d1183d6b16a282c2575e3e006cee4 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Fri, 23 Mar 2018 18:42:47 +0100 Subject: platform/chrome: mfd/cros_ec_dev: Add sysfs entry to set keyboard wake lid angle This adds a sysfs attribute (/sys/class/chromeos/cros_ec/kb_wake_angle) used to set and get the keyboard wake lid angle. This attribute is present only if 2 accelerometers are controlled by the EC. This patch also moves the cros_ec features check before the device is added so the features map obtained from the EC is ready on time. Signed-off-by: Gwendal Grignou Signed-off-by: Enric Balletbo i Serra Reviewed-by: Andy Shevchenko Acked-by: Lee Jones Signed-off-by: Benson Leung --- include/linux/mfd/cros_ec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index c61535979b8f..2d4e23c9ea0a 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -183,6 +183,7 @@ struct cros_ec_debugfs; * @ec_dev: cros_ec_device structure to talk to the physical device * @dev: pointer to the platform device * @debug_info: cros_ec_debugfs structure for debugging information + * @has_kb_wake_angle: true if at least 2 accelerometer are connected to the EC. * @cmd_offset: offset to apply for each command. */ struct cros_ec_dev { @@ -191,6 +192,7 @@ struct cros_ec_dev { struct cros_ec_device *ec_dev; struct device *dev; struct cros_ec_debugfs *debug_info; + bool has_kb_wake_angle; u16 cmd_offset; u32 features[2]; }; -- cgit v1.2.3 From 450b1f6f56350c630e795f240dc5a77aa8aa2419 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 29 Mar 2018 08:07:46 +0100 Subject: lockref: Add lockref_put_not_zero Put a lockref unless the lockref is dead or its count would become zero. This is the same as lockref_put_or_lock except that the lock is never left held. Signed-off-by: Andreas Gruenbacher Signed-off-by: Bob Peterson --- include/linux/lockref.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/lockref.h b/include/linux/lockref.h index 2eac32095113..99f17cc8e163 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -37,6 +37,7 @@ struct lockref { extern void lockref_get(struct lockref *); extern int lockref_put_return(struct lockref *); extern int lockref_get_not_zero(struct lockref *); +extern int lockref_put_not_zero(struct lockref *); extern int lockref_get_or_lock(struct lockref *); extern int lockref_put_or_lock(struct lockref *); -- cgit v1.2.3 From 1c2734b31d72316e3faaad88c0c9c46fa92a4b20 Mon Sep 17 00:00:00 2001 From: Raghuram Chary J Date: Wed, 11 Apr 2018 20:36:36 +0530 Subject: lan78xx: PHY DSP registers initialization to address EEE link drop issues with long cables The patch is to configure DSP registers of PHY device to handle Gbe-EEE failures with >40m cable length. Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver") Signed-off-by: Raghuram Chary J Signed-off-by: David S. Miller --- include/linux/microchipphy.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/microchipphy.h b/include/linux/microchipphy.h index eb492d47f717..8f9c90379732 100644 --- a/include/linux/microchipphy.h +++ b/include/linux/microchipphy.h @@ -70,4 +70,12 @@ #define LAN88XX_MMD3_CHIP_ID (32877) #define LAN88XX_MMD3_CHIP_REV (32878) +/* DSP registers */ +#define PHY_ARDENNES_MMD_DEV_3_PHY_CFG (0x806A) +#define PHY_ARDENNES_MMD_DEV_3_PHY_CFG_ZD_DLY_EN_ (0x2000) +#define LAN88XX_EXT_PAGE_ACCESS_TR (0x52B5) +#define LAN88XX_EXT_PAGE_TR_CR 16 +#define LAN88XX_EXT_PAGE_TR_LOW_DATA 17 +#define LAN88XX_EXT_PAGE_TR_HIGH_DATA 18 + #endif /* _MICROCHIPPHY_H */ -- cgit v1.2.3 From de40614de997a388499f9a01d5eeb7cd8d3c34d1 Mon Sep 17 00:00:00 2001 From: Alex Hung Date: Fri, 13 Apr 2018 15:37:59 +0200 Subject: firmware: dmi_scan: Add DMI_OEM_STRING support to dmi_matches OEM strings are defined by each OEM and they contain customized and useful OEM information. Supporting it provides more flexible uses of the dmi_matches function. Signed-off-by: Alex Hung Signed-off-by: Jean Delvare --- include/linux/mod_devicetable.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 48fb2b43c35a..7d361be2e24f 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -502,6 +502,7 @@ enum dmi_field { DMI_CHASSIS_SERIAL, DMI_CHASSIS_ASSET_TAG, DMI_STRING_MAX, + DMI_OEM_STRING, /* special case - will not be in dmi_ident */ }; struct dmi_strmatch { -- cgit v1.2.3 From 8e984f8667ff4225092af734eef28a3d7bae8626 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 5 Apr 2018 16:18:04 +0300 Subject: fsnotify: fix typo in a comment about mark->g_list Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 9f1edb92c97e..e0c95c9f1e29 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -248,7 +248,7 @@ struct fsnotify_mark { /* Group this mark is for. Set on mark creation, stable until last ref * is dropped */ struct fsnotify_group *group; - /* List of marks by group->i_fsnotify_marks. Also reused for queueing + /* List of marks by group->marks_list. Also reused for queueing * mark into destroy_list when it's waiting for the end of SRCU period * before it can be freed. [group->mark_mutex] */ struct list_head g_list; -- cgit v1.2.3 From 9ec4ecef0af7790551109283ca039a7c52de343c Mon Sep 17 00:00:00 2001 From: AKASHI Takahiro Date: Fri, 13 Apr 2018 15:35:49 -0700 Subject: kexec_file,x86,powerpc: factor out kexec_file_ops functions As arch_kexec_kernel_image_{probe,load}(), arch_kimage_file_post_load_cleanup() and arch_kexec_kernel_verify_sig() are almost duplicated among architectures, they can be commonalized with an architecture-defined kexec_file_ops array. So let's factor them out. Link: http://lkml.kernel.org/r/20180306102303.9063-3-takahiro.akashi@linaro.org Signed-off-by: AKASHI Takahiro Acked-by: Dave Young Tested-by: Dave Young Cc: Vivek Goyal Cc: Baoquan He Cc: Michael Ellerman Cc: Thiago Jung Bauermann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 0ebcbeb21056..102c725421a1 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -135,6 +135,11 @@ struct kexec_file_ops { #endif }; +extern const struct kexec_file_ops * const kexec_file_loaders[]; + +int kexec_image_probe_default(struct kimage *image, void *buf, + unsigned long buf_len); + /** * struct kexec_buf - parameters for finding a place for a buffer in memory * @image: kexec image in which memory to search. @@ -209,7 +214,7 @@ struct kimage { unsigned long cmdline_buf_len; /* File operations provided by image loader */ - struct kexec_file_ops *fops; + const struct kexec_file_ops *fops; /* Image loader handling the kernel can store a pointer here */ void *image_loader_data; @@ -273,12 +278,6 @@ int crash_shrink_memory(unsigned long new_size); size_t crash_get_memory_size(void); void crash_free_reserved_phys_range(unsigned long begin, unsigned long end); -int __weak arch_kexec_kernel_image_probe(struct kimage *image, void *buf, - unsigned long buf_len); -void * __weak arch_kexec_kernel_image_load(struct kimage *image); -int __weak arch_kimage_file_post_load_cleanup(struct kimage *image); -int __weak arch_kexec_kernel_verify_sig(struct kimage *image, void *buf, - unsigned long buf_len); int __weak arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, unsigned int relsec); int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, -- cgit v1.2.3 From babac4a84a88842bec477a5bdada1460f3bc374c Mon Sep 17 00:00:00 2001 From: AKASHI Takahiro Date: Fri, 13 Apr 2018 15:36:06 -0700 Subject: kexec_file, x86: move re-factored code to generic side In the previous patches, commonly-used routines, exclude_mem_range() and prepare_elf64_headers(), were carved out. Now place them in kexec common code. A prefix "crash_" is given to each of their names to avoid possible name collisions. Link: http://lkml.kernel.org/r/20180306102303.9063-8-takahiro.akashi@linaro.org Signed-off-by: AKASHI Takahiro Acked-by: Dave Young Tested-by: Dave Young Cc: Vivek Goyal Cc: Baoquan He Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 102c725421a1..68865fd51aad 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -168,6 +168,25 @@ int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf, int (*func)(struct resource *, void *)); extern int kexec_add_buffer(struct kexec_buf *kbuf); int kexec_locate_mem_hole(struct kexec_buf *kbuf); + +/* Alignment required for elf header segment */ +#define ELF_CORE_HEADER_ALIGN 4096 + +struct crash_mem_range { + u64 start, end; +}; + +struct crash_mem { + unsigned int max_nr_ranges; + unsigned int nr_ranges; + struct crash_mem_range ranges[0]; +}; + +extern int crash_exclude_mem_range(struct crash_mem *mem, + unsigned long long mstart, + unsigned long long mend); +extern int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map, + void **addr, unsigned long *sz); #endif /* CONFIG_KEXEC_FILE */ struct kimage { -- cgit v1.2.3 From ee6ebeda8ddc350700168f2c8052a97bd9c11e5b Mon Sep 17 00:00:00 2001 From: Philipp Rudo Date: Fri, 13 Apr 2018 15:36:10 -0700 Subject: include/linux/kexec.h: silence compile warnings Patch series "kexec_file: Clean up purgatory load", v2. Following the discussion with Dave and AKASHI, here are the common code patches extracted from my recent patch set (Add kexec_file_load support to s390) [1]. The patches were extracted to allow upstream integration together with AKASHI's common code patches before the arch code gets adjusted to the new base. The reason for this series is to prepare common code for adding kexec_file_load to s390 as well as cleaning up the mis-use of the sh_offset field during purgatory load. In detail this series contains: Patch #1&2: Minor cleanups/fixes. Patch #3-9: Clean up the purgatory load/relocation code. Especially remove the mis-use of the purgatory_info->sechdrs->sh_offset field, currently holding a pointer into either kexec_purgatory (ro) or purgatory_buf (rw) depending on the section. With these patches the section address will be calculated verbosely and sh_offset will contain the offset of the section in the stripped purgatory binary (purgatory_buf). Patch #10: Allows architectures to set the purgatory load address. This patch is important for s390 as the kernel and purgatory have to be loaded to fixed addresses. In current code this is impossible as the purgatory load is opaque to the architecture. Patch #11: Moves x86 purgatories sha implementation to common lib/ directory to allow reuse in other architectures. This patch (of 11) When building the kernel with CONFIG_KEXEC_FILE enabled gcc prints a compile warning multiple times. In file included from /linux/init/initramfs.c:526:0: /include/linux/kexec.h:120:9: warning: `struct kimage' declared inside parameter list [enabled by default] unsigned long cmdline_len); ^ This is because the typedefs for kexec_file_load uses struct kimage before it is declared. Fix this by simply forward declaring struct kimage. Link: http://lkml.kernel.org/r/20180321112751.22196-2-prudo@linux.vnet.ibm.com Signed-off-by: Philipp Rudo Acked-by: Dave Young Cc: Eric Biederman Cc: Vivek Goyal Cc: Michael Ellerman Cc: Thiago Jung Bauermann Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: AKASHI Takahiro Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 68865fd51aad..08b8b9d00f97 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -114,6 +114,8 @@ struct purgatory_info { unsigned long purgatory_load_addr; }; +struct kimage; + typedef int (kexec_probe_t)(const char *kernel_buf, unsigned long kernel_size); typedef void *(kexec_load_t)(struct kimage *image, char *kernel_buf, unsigned long kernel_len, char *initrd, -- cgit v1.2.3 From 65c225d3280542f3ea145e052215ce0538f6bb69 Mon Sep 17 00:00:00 2001 From: Philipp Rudo Date: Fri, 13 Apr 2018 15:36:17 -0700 Subject: kernel/kexec_file.c: make purgatory_info->ehdr const The kexec_purgatory buffer is read-only. Thus all pointers into kexec_purgatory are read-only, too. Point this out by explicitly marking purgatory_info->ehdr as 'const' and update the comments in purgatory_info. Link: http://lkml.kernel.org/r/20180321112751.22196-4-prudo@linux.vnet.ibm.com Signed-off-by: Philipp Rudo Acked-by: Dave Young Cc: AKASHI Takahiro Cc: Eric Biederman Cc: Heiko Carstens Cc: Ingo Molnar Cc: Martin Schwidefsky Cc: Michael Ellerman Cc: Thiago Jung Bauermann Cc: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 08b8b9d00f97..8c5819d1a808 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -99,14 +99,19 @@ struct compat_kexec_segment { #ifdef CONFIG_KEXEC_FILE struct purgatory_info { - /* Pointer to elf header of read only purgatory */ - Elf_Ehdr *ehdr; - - /* Pointer to purgatory sechdrs which are modifiable */ + /* + * Pointer to elf header at the beginning of kexec_purgatory. + * Note: kexec_purgatory is read only + */ + const Elf_Ehdr *ehdr; + /* + * Temporary, modifiable buffer for sechdrs used for relocation. + * This memory can be freed post image load. + */ Elf_Shdr *sechdrs; /* - * Temporary buffer location where purgatory is loaded and relocated - * This memory can be freed post image load + * Temporary, modifiable buffer for stripped purgatory used for + * relocation. This memory can be freed post image load. */ void *purgatory_buf; -- cgit v1.2.3 From 8aec395b8478310521031157ef5d44ef19c2c581 Mon Sep 17 00:00:00 2001 From: Philipp Rudo Date: Fri, 13 Apr 2018 15:36:24 -0700 Subject: kernel/kexec_file.c: use read-only sections in arch_kexec_apply_relocations* When the relocations are applied to the purgatory only the section the relocations are applied to is writable. The other sections, i.e. the symtab and .rel/.rela, are in read-only kexec_purgatory. Highlight this by marking the corresponding variables as 'const'. While at it also change the signatures of arch_kexec_apply_relocations* to take section pointers instead of just the index of the relocation section. This removes the second lookup and sanity check of the sections in arch code. Link: http://lkml.kernel.org/r/20180321112751.22196-6-prudo@linux.vnet.ibm.com Signed-off-by: Philipp Rudo Acked-by: Dave Young Cc: AKASHI Takahiro Cc: Eric Biederman Cc: Heiko Carstens Cc: Ingo Molnar Cc: Martin Schwidefsky Cc: Michael Ellerman Cc: Thiago Jung Bauermann Cc: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 8c5819d1a808..0e389b9b7722 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -171,6 +171,15 @@ struct kexec_buf { bool top_down; }; +int __weak arch_kexec_apply_relocations_add(struct purgatory_info *pi, + Elf_Shdr *section, + const Elf_Shdr *relsec, + const Elf_Shdr *symtab); +int __weak arch_kexec_apply_relocations(struct purgatory_info *pi, + Elf_Shdr *section, + const Elf_Shdr *relsec, + const Elf_Shdr *symtab); + int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf, int (*func)(struct resource *, void *)); extern int kexec_add_buffer(struct kexec_buf *kbuf); @@ -304,10 +313,6 @@ int crash_shrink_memory(unsigned long new_size); size_t crash_get_memory_size(void); void crash_free_reserved_phys_range(unsigned long begin, unsigned long end); -int __weak arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr, - Elf_Shdr *sechdrs, unsigned int relsec); -int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, - unsigned int relsec); void arch_kexec_protect_crashkres(void); void arch_kexec_unprotect_crashkres(void); -- cgit v1.2.3 From 3be3f61d25e04ecf90d65d52fad632af5ba8805b Mon Sep 17 00:00:00 2001 From: Philipp Rudo Date: Fri, 13 Apr 2018 15:36:43 -0700 Subject: kernel/kexec_file.c: allow archs to set purgatory load address For s390 new kernels are loaded to fixed addresses in memory before they are booted. With the current code this is a problem as it assumes the kernel will be loaded to an 'arbitrary' address. In particular, kexec_locate_mem_hole searches for a large enough memory region and sets the load address (kexec_bufer->mem) to it. Luckily there is a simple workaround for this problem. By returning 1 in arch_kexec_walk_mem, kexec_locate_mem_hole is turned off. This allows the architecture to set kbuf->mem by hand. While the trick works fine for the kernel it does not for the purgatory as here the architectures don't have access to its kexec_buffer. Give architectures access to the purgatories kexec_buffer by changing kexec_load_purgatory to take a pointer to it. With this change architectures have access to the buffer and can edit it as they need. A nice side effect of this change is that we can get rid of the purgatory_info->purgatory_load_address field. As now the information stored there can directly be accessed from kbuf->mem. Link: http://lkml.kernel.org/r/20180321112751.22196-11-prudo@linux.vnet.ibm.com Signed-off-by: Philipp Rudo Reviewed-by: Martin Schwidefsky Acked-by: Dave Young Cc: AKASHI Takahiro Cc: Eric Biederman Cc: Heiko Carstens Cc: Ingo Molnar Cc: Michael Ellerman Cc: Thiago Jung Bauermann Cc: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 0e389b9b7722..9e4e638fb505 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -114,9 +114,6 @@ struct purgatory_info { * relocation. This memory can be freed post image load. */ void *purgatory_buf; - - /* Address where purgatory is finally loaded and is executed from */ - unsigned long purgatory_load_addr; }; struct kimage; @@ -171,6 +168,12 @@ struct kexec_buf { bool top_down; }; +int kexec_load_purgatory(struct kimage *image, struct kexec_buf *kbuf); +int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name, + void *buf, unsigned int size, + bool get_value); +void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name); + int __weak arch_kexec_apply_relocations_add(struct purgatory_info *pi, Elf_Shdr *section, const Elf_Shdr *relsec, @@ -266,14 +269,6 @@ extern void machine_kexec_cleanup(struct kimage *image); extern int kernel_kexec(void); extern struct page *kimage_alloc_control_pages(struct kimage *image, unsigned int order); -extern int kexec_load_purgatory(struct kimage *image, unsigned long min, - unsigned long max, int top_down, - unsigned long *load_addr); -extern int kexec_purgatory_get_set_symbol(struct kimage *image, - const char *name, void *buf, - unsigned int size, bool get_value); -extern void *kexec_purgatory_get_symbol_addr(struct kimage *image, - const char *name); extern void __crash_kexec(struct pt_regs *); extern void crash_kexec(struct pt_regs *); int kexec_should_crash(struct task_struct *); -- cgit v1.2.3 From df6f2801f511b07c08c110fe9f047a34cb40286f Mon Sep 17 00:00:00 2001 From: Philipp Rudo Date: Fri, 13 Apr 2018 15:36:46 -0700 Subject: kernel/kexec_file.c: move purgatories sha256 to common code The code to verify the new kernels sha digest is applicable for all architectures. Move it to common code. One problem is the string.c implementation on x86. Currently sha256 includes x86/boot/string.h which defines memcpy and memset to be gcc builtins. By moving the sha256 implementation to common code and changing the include to linux/string.h both functions are no longer defined. Thus definitions have to be provided in x86/purgatory/string.c Link: http://lkml.kernel.org/r/20180321112751.22196-12-prudo@linux.vnet.ibm.com Signed-off-by: Philipp Rudo Acked-by: Dave Young Cc: AKASHI Takahiro Cc: Eric Biederman Cc: Heiko Carstens Cc: Ingo Molnar Cc: Martin Schwidefsky Cc: Michael Ellerman Cc: Thiago Jung Bauermann Cc: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sha256.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) create mode 100644 include/linux/sha256.h (limited to 'include/linux') diff --git a/include/linux/sha256.h b/include/linux/sha256.h new file mode 100644 index 000000000000..244fe01a65fb --- /dev/null +++ b/include/linux/sha256.h @@ -0,0 +1,30 @@ +/* + * Copyright (C) 2014 Red Hat Inc. + * + * Author: Vivek Goyal + * + * This source code is licensed under the GNU General Public License, + * Version 2. See the file COPYING for more details. + */ + +#ifndef SHA256_H +#define SHA256_H + +#include +#include + +/* + * Stand-alone implementation of the SHA256 algorithm. It is designed to + * have as little dependencies as possible so it can be used in the + * kexec_file purgatory. In other cases you should use the implementation in + * crypto/. + * + * For details see lib/sha256.c + */ + +extern int sha256_init(struct sha256_state *sctx); +extern int sha256_update(struct sha256_state *sctx, const u8 *input, + unsigned int length); +extern int sha256_final(struct sha256_state *sctx, u8 *hash); + +#endif /* SHA256_H */ -- cgit v1.2.3 From 8e04944f0ea8b838399049bdcda920ab36ae3b04 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Wed, 4 Apr 2018 19:53:07 +0900 Subject: mm,vmscan: Allow preallocating memory for register_shrinker(). syzbot is catching so many bugs triggered by commit 9ee332d99e4d5a97 ("sget(): handle failures of register_shrinker()"). That commit expected that calling kill_sb() from deactivate_locked_super() without successful fill_super() is safe, but the reality was different; some callers assign attributes which are needed for kill_sb() after sget() succeeds. For example, [1] is a report where sb->s_mode (which seems to be either FMODE_READ | FMODE_EXCL | FMODE_WRITE or FMODE_READ | FMODE_EXCL) is not assigned unless sget() succeeds. But it does not worth complicate sget() so that register_shrinker() failure path can safely call kill_block_super() via kill_sb(). Making alloc_super() fail if memory allocation for register_shrinker() failed is much simpler. Let's avoid calling deactivate_locked_super() from sget_userns() by preallocating memory for the shrinker and making register_shrinker() in sget_userns() never fail. [1] https://syzkaller.appspot.com/bug?id=588996a25a2587be2e3a54e8646728fb9cae44e7 Signed-off-by: Tetsuo Handa Reported-by: syzbot Cc: Al Viro Cc: Michal Hocko Signed-off-by: Al Viro --- include/linux/shrinker.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 388ff2936a87..6794490f25b2 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -75,6 +75,9 @@ struct shrinker { #define SHRINKER_NUMA_AWARE (1 << 0) #define SHRINKER_MEMCG_AWARE (1 << 1) -extern int register_shrinker(struct shrinker *); -extern void unregister_shrinker(struct shrinker *); +extern int prealloc_shrinker(struct shrinker *shrinker); +extern void register_shrinker_prepared(struct shrinker *shrinker); +extern int register_shrinker(struct shrinker *shrinker); +extern void unregister_shrinker(struct shrinker *shrinker); +extern void free_prealloced_shrinker(struct shrinker *shrinker); #endif -- cgit v1.2.3 From 5968a70d7af5f2abbd9d9f9c8e86da51f0a6b16d Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 16 Apr 2018 12:32:55 -0700 Subject: textsearch: fix kernel-doc warnings and add kernel-api section Make lib/textsearch.c usable as kernel-doc. Add textsearch() function family to kernel-api documentation. Fix kernel-doc warnings in : ../include/linux/textsearch.h:65: warning: Incorrect use of kernel-doc format: * get_next_block - fetch next block of data ../include/linux/textsearch.h:82: warning: Incorrect use of kernel-doc format: * finish - finalize/clean a series of get_next_block() calls Signed-off-by: Randy Dunlap Signed-off-by: David S. Miller --- include/linux/textsearch.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/textsearch.h b/include/linux/textsearch.h index 0494db3fd9e8..13770cfe33ad 100644 --- a/include/linux/textsearch.h +++ b/include/linux/textsearch.h @@ -62,7 +62,7 @@ struct ts_config int flags; /** - * get_next_block - fetch next block of data + * @get_next_block: fetch next block of data * @consumed: number of bytes consumed by the caller * @dst: destination buffer * @conf: search configuration @@ -79,7 +79,7 @@ struct ts_config struct ts_state *state); /** - * finish - finalize/clean a series of get_next_block() calls + * @finish: finalize/clean a series of get_next_block() calls * @conf: search configuration * @state: search state * -- cgit v1.2.3 From e91c2518a5d22a07642f35d85f39001ad379dae4 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Mon, 16 Apr 2018 13:36:46 +0200 Subject: livepatch: Initialize shadow variables safely by a custom callback The existing API allows to pass a sample data to initialize the shadow data. It works well when the data are position independent. But it fails miserably when we need to set a pointer to the shadow structure itself. Unfortunately, we might need to initialize the pointer surprisingly often because of struct list_head. It is even worse because the list might be hidden in other common structures, for example, struct mutex, struct wait_queue_head. For example, this was needed to fix races in ALSA sequencer. It required to add mutex into struct snd_seq_client. See commit b3defb791b26ea06 ("ALSA: seq: Make ioctls race-free") and commit d15d662e89fc667b9 ("ALSA: seq: Fix racy pool initializations") This patch makes the API more safe. A custom constructor function and data are passed to klp_shadow_*alloc() functions instead of the sample data. Note that ctor_data are no longer a template for shadow->data. It might point to any data that might be necessary when the constructor is called. Also note that the constructor is called under klp_shadow_lock. It is an internal spin_lock that synchronizes alloc() vs. get() operations, see klp_shadow_get_or_alloc(). On one hand, this adds a risk of ABBA deadlocks. On the other hand, it allows to do some operations safely. For example, we could add the new structure into an existing list. This must be done only once when the structure is allocated. Reported-by: Nicolai Stange Signed-off-by: Petr Mladek Acked-by: Josh Poimboeuf Acked-by: Miroslav Benes Signed-off-by: Jiri Kosina --- include/linux/livepatch.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 4754f01c1abb..7e084321b146 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -186,11 +186,17 @@ static inline bool klp_have_reliable_stack(void) IS_ENABLED(CONFIG_HAVE_RELIABLE_STACKTRACE); } +typedef int (*klp_shadow_ctor_t)(void *obj, + void *shadow_data, + void *ctor_data); + void *klp_shadow_get(void *obj, unsigned long id); -void *klp_shadow_alloc(void *obj, unsigned long id, void *data, - size_t size, gfp_t gfp_flags); -void *klp_shadow_get_or_alloc(void *obj, unsigned long id, void *data, - size_t size, gfp_t gfp_flags); +void *klp_shadow_alloc(void *obj, unsigned long id, + size_t size, gfp_t gfp_flags, + klp_shadow_ctor_t ctor, void *ctor_data); +void *klp_shadow_get_or_alloc(void *obj, unsigned long id, + size_t size, gfp_t gfp_flags, + klp_shadow_ctor_t ctor, void *ctor_data); void klp_shadow_free(void *obj, unsigned long id); void klp_shadow_free_all(unsigned long id); -- cgit v1.2.3 From 3b2c77d000fe9f7d02e9e726e00dccf9f92b256f Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Mon, 16 Apr 2018 13:36:47 +0200 Subject: livepatch: Allow to call a custom callback when freeing shadow variables We might need to do some actions before the shadow variable is freed. For example, we might need to remove it from a list or free some data that it points to. This is already possible now. The user can get the shadow variable by klp_shadow_get(), do the necessary actions, and then call klp_shadow_free(). This patch allows to do it a more elegant way. The user could implement the needed actions in a callback that is passed to klp_shadow_free() as a parameter. The callback usually does reverse operations to the constructor callback that can be called by klp_shadow_*alloc(). It is especially useful for klp_shadow_free_all(). There we need to do these extra actions for each found shadow variable with the given ID. Note that the memory used by the shadow variable itself is still released later by rcu callback. It is needed to protect internal structures that keep all shadow variables. But the destructor is called immediately. The shadow variable must not be access anyway after klp_shadow_free() is called. The user is responsible to protect this any suitable way. Be aware that the destructor is called under klp_shadow_lock. It is the same as for the contructor in klp_shadow_alloc(). Signed-off-by: Petr Mladek Acked-by: Josh Poimboeuf Acked-by: Miroslav Benes Signed-off-by: Jiri Kosina --- include/linux/livepatch.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 7e084321b146..aec44b1d9582 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -189,6 +189,7 @@ static inline bool klp_have_reliable_stack(void) typedef int (*klp_shadow_ctor_t)(void *obj, void *shadow_data, void *ctor_data); +typedef void (*klp_shadow_dtor_t)(void *obj, void *shadow_data); void *klp_shadow_get(void *obj, unsigned long id); void *klp_shadow_alloc(void *obj, unsigned long id, @@ -197,8 +198,8 @@ void *klp_shadow_alloc(void *obj, unsigned long id, void *klp_shadow_get_or_alloc(void *obj, unsigned long id, size_t size, gfp_t gfp_flags, klp_shadow_ctor_t ctor, void *ctor_data); -void klp_shadow_free(void *obj, unsigned long id); -void klp_shadow_free_all(unsigned long id); +void klp_shadow_free(void *obj, unsigned long id, klp_shadow_dtor_t dtor); +void klp_shadow_free_all(unsigned long id, klp_shadow_dtor_t dtor); #else /* !CONFIG_LIVEPATCH */ -- cgit v1.2.3 From 7ce2367254e84753bceb07327aaf5c953cfce117 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Tue, 17 Apr 2018 18:46:14 +0900 Subject: vlan: Fix reading memory beyond skb->tail in skb_vlan_tagged_multi Syzkaller spotted an old bug which leads to reading skb beyond tail by 4 bytes on vlan tagged packets. This is caused because skb_vlan_tagged_multi() did not check skb_headlen. BUG: KMSAN: uninit-value in eth_type_vlan include/linux/if_vlan.h:283 [inline] BUG: KMSAN: uninit-value in skb_vlan_tagged_multi include/linux/if_vlan.h:656 [inline] BUG: KMSAN: uninit-value in vlan_features_check include/linux/if_vlan.h:672 [inline] BUG: KMSAN: uninit-value in dflt_features_check net/core/dev.c:2949 [inline] BUG: KMSAN: uninit-value in netif_skb_features+0xd1b/0xdc0 net/core/dev.c:3009 CPU: 1 PID: 3582 Comm: syzkaller435149 Not tainted 4.16.0+ #82 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:53 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676 eth_type_vlan include/linux/if_vlan.h:283 [inline] skb_vlan_tagged_multi include/linux/if_vlan.h:656 [inline] vlan_features_check include/linux/if_vlan.h:672 [inline] dflt_features_check net/core/dev.c:2949 [inline] netif_skb_features+0xd1b/0xdc0 net/core/dev.c:3009 validate_xmit_skb+0x89/0x1320 net/core/dev.c:3084 __dev_queue_xmit+0x1cb2/0x2b60 net/core/dev.c:3549 dev_queue_xmit+0x4b/0x60 net/core/dev.c:3590 packet_snd net/packet/af_packet.c:2944 [inline] packet_sendmsg+0x7c57/0x8a10 net/packet/af_packet.c:2969 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] sock_write_iter+0x3b9/0x470 net/socket.c:909 do_iter_readv_writev+0x7bb/0x970 include/linux/fs.h:1776 do_iter_write+0x30d/0xd40 fs/read_write.c:932 vfs_writev fs/read_write.c:977 [inline] do_writev+0x3c9/0x830 fs/read_write.c:1012 SYSC_writev+0x9b/0xb0 fs/read_write.c:1085 SyS_writev+0x56/0x80 fs/read_write.c:1082 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 RIP: 0033:0x43ffa9 RSP: 002b:00007fff2cff3948 EFLAGS: 00000217 ORIG_RAX: 0000000000000014 RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043ffa9 RDX: 0000000000000001 RSI: 0000000020000080 RDI: 0000000000000003 RBP: 00000000006cb018 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000217 R12: 00000000004018d0 R13: 0000000000401960 R14: 0000000000000000 R15: 0000000000000000 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline] kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314 kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321 slab_post_alloc_hook mm/slab.h:445 [inline] slab_alloc_node mm/slub.c:2737 [inline] __kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369 __kmalloc_reserve net/core/skbuff.c:138 [inline] __alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206 alloc_skb include/linux/skbuff.h:984 [inline] alloc_skb_with_frags+0x1d4/0xb20 net/core/skbuff.c:5234 sock_alloc_send_pskb+0xb56/0x1190 net/core/sock.c:2085 packet_alloc_skb net/packet/af_packet.c:2803 [inline] packet_snd net/packet/af_packet.c:2894 [inline] packet_sendmsg+0x6444/0x8a10 net/packet/af_packet.c:2969 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] sock_write_iter+0x3b9/0x470 net/socket.c:909 do_iter_readv_writev+0x7bb/0x970 include/linux/fs.h:1776 do_iter_write+0x30d/0xd40 fs/read_write.c:932 vfs_writev fs/read_write.c:977 [inline] do_writev+0x3c9/0x830 fs/read_write.c:1012 SYSC_writev+0x9b/0xb0 fs/read_write.c:1085 SyS_writev+0x56/0x80 fs/read_write.c:1082 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 Fixes: 58e998c6d239 ("offloading: Force software GSO for multiple vlan tags.") Reported-and-tested-by: syzbot+0bbe42c764feafa82c5a@syzkaller.appspotmail.com Signed-off-by: Toshiaki Makita Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index d11f41d5269f..78a5a90b4267 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -663,7 +663,7 @@ static inline bool skb_vlan_tagged(const struct sk_buff *skb) * Returns true if the skb is tagged with multiple vlan headers, regardless * of whether it is hardware accelerated or not. */ -static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb) +static inline bool skb_vlan_tagged_multi(struct sk_buff *skb) { __be16 protocol = skb->protocol; @@ -673,6 +673,9 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb) if (likely(!eth_type_vlan(protocol))) return false; + if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN))) + return false; + veh = (struct vlan_ethhdr *)skb->data; protocol = veh->h_vlan_encapsulated_proto; } @@ -690,7 +693,7 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb) * * Returns features without unsafe ones if the skb has multiple tags. */ -static inline netdev_features_t vlan_features_check(const struct sk_buff *skb, +static inline netdev_features_t vlan_features_check(struct sk_buff *skb, netdev_features_t features) { if (skb_vlan_tagged_multi(skb)) { -- cgit v1.2.3