diff options
396 files changed, 4317 insertions, 2031 deletions
@@ -159,6 +159,7 @@ Peter Oruba <peter@oruba.de> Peter Oruba <peter.oruba@amd.com> Pratyush Anand <pratyush.anand@gmail.com> <pratyush.anand@st.com> Praveen BP <praveenbp@ti.com> +Punit Agrawal <punitagrawal@gmail.com> <punit.agrawal@arm.com> Qais Yousef <qsyousef@gmail.com> <qais.yousef@imgtec.com> Oleksij Rempel <linux@rempel-privat.de> <bug-track@fisher-privat.net> Oleksij Rempel <linux@rempel-privat.de> <external.Oleksij.Rempel@de.bosch.com> @@ -2138,6 +2138,10 @@ E: paul@laufernet.com D: Soundblaster driver fixes, ISAPnP quirk S: California, USA +N: Jarkko Lavinen +E: jarkko.lavinen@nokia.com +D: OMAP MMC support + N: Jonathan Layes D: ARPD support diff --git a/Documentation/ABI/testing/sysfs-class-led-trigger-pattern b/Documentation/ABI/testing/sysfs-class-led-trigger-pattern index fb3d1e03b881..1e5d172e0646 100644 --- a/Documentation/ABI/testing/sysfs-class-led-trigger-pattern +++ b/Documentation/ABI/testing/sysfs-class-led-trigger-pattern @@ -37,8 +37,8 @@ Description: 0-| / \/ \/ +---0----1----2----3----4----5----6------------> time (s) - 2. To make the LED go instantly from one brigntess value to another, - we should use use zero-time lengths (the brightness must be same as + 2. To make the LED go instantly from one brightness value to another, + we should use zero-time lengths (the brightness must be same as the previous tuple's). So the format should be: "brightness_1 duration_1 brightness_1 0 brightness_2 duration_2 brightness_2 0 ...". For example: diff --git a/Documentation/admin-guide/pm/cpufreq.rst b/Documentation/admin-guide/pm/cpufreq.rst index 47153e64dfb5..7eca9026a9ed 100644 --- a/Documentation/admin-guide/pm/cpufreq.rst +++ b/Documentation/admin-guide/pm/cpufreq.rst @@ -150,7 +150,7 @@ data structures necessary to handle the given policy and, possibly, to add a governor ``sysfs`` interface to it. Next, the governor is started by invoking its ``->start()`` callback. -That callback it expected to register per-CPU utilization update callbacks for +That callback is expected to register per-CPU utilization update callbacks for all of the online CPUs belonging to the given policy with the CPU scheduler. The utilization update callbacks will be invoked by the CPU scheduler on important events, like task enqueue and dequeue, on every iteration of the diff --git a/Documentation/cpu-freq/cpufreq-stats.txt b/Documentation/cpu-freq/cpufreq-stats.txt index a873855c811d..14378cecb172 100644 --- a/Documentation/cpu-freq/cpufreq-stats.txt +++ b/Documentation/cpu-freq/cpufreq-stats.txt @@ -86,9 +86,11 @@ transitions. This will give a fine grained information about all the CPU frequency transitions. The cat output here is a two dimensional matrix, where an entry <i,j> (row i, column j) represents the count of number of transitions from -Freq_i to Freq_j. Freq_i is in descending order with increasing rows and -Freq_j is in descending order with increasing columns. The output here also -contains the actual freq values for each row and column for better readability. +Freq_i to Freq_j. Freq_i rows and Freq_j columns follow the sorting order in +which the driver has provided the frequency table initially to the cpufreq core +and so can be sorted (ascending or descending) or unsorted. The output here +also contains the actual freq values for each row and column for better +readability. If the transition table is bigger than PAGE_SIZE, reading this will return an -EFBIG error. diff --git a/Documentation/devicetree/bindings/cpufreq/arm_big_little_dt.txt b/Documentation/devicetree/bindings/cpufreq/arm_big_little_dt.txt deleted file mode 100644 index 2aa06ac0fac5..000000000000 --- a/Documentation/devicetree/bindings/cpufreq/arm_big_little_dt.txt +++ /dev/null @@ -1,65 +0,0 @@ -Generic ARM big LITTLE cpufreq driver's DT glue ------------------------------------------------ - -This is DT specific glue layer for generic cpufreq driver for big LITTLE -systems. - -Both required and optional properties listed below must be defined -under node /cpus/cpu@x. Where x is the first cpu inside a cluster. - -FIXME: Cpus should boot in the order specified in DT and all cpus for a cluster -must be present contiguously. Generic DT driver will check only node 'x' for -cpu:x. - -Required properties: -- operating-points: Refer to Documentation/devicetree/bindings/opp/opp.txt - for details - -Optional properties: -- clock-latency: Specify the possible maximum transition latency for clock, - in unit of nanoseconds. - -Examples: - -cpus { - #address-cells = <1>; - #size-cells = <0>; - - cpu@0 { - compatible = "arm,cortex-a15"; - reg = <0>; - next-level-cache = <&L2>; - operating-points = < - /* kHz uV */ - 792000 1100000 - 396000 950000 - 198000 850000 - >; - clock-latency = <61036>; /* two CLK32 periods */ - }; - - cpu@1 { - compatible = "arm,cortex-a15"; - reg = <1>; - next-level-cache = <&L2>; - }; - - cpu@100 { - compatible = "arm,cortex-a7"; - reg = <100>; - next-level-cache = <&L2>; - operating-points = < - /* kHz uV */ - 792000 950000 - 396000 750000 - 198000 450000 - >; - clock-latency = <61036>; /* two CLK32 periods */ - }; - - cpu@101 { - compatible = "arm,cortex-a7"; - reg = <101>; - next-level-cache = <&L2>; - }; -}; diff --git a/Documentation/devicetree/bindings/i2c/i2c-omap.txt b/Documentation/devicetree/bindings/i2c/i2c-omap.txt index 7e49839d4124..4b90ba9f31b7 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-omap.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-omap.txt @@ -1,8 +1,12 @@ I2C for OMAP platforms Required properties : -- compatible : Must be "ti,omap2420-i2c", "ti,omap2430-i2c", "ti,omap3-i2c" - or "ti,omap4-i2c" +- compatible : Must be + "ti,omap2420-i2c" for OMAP2420 SoCs + "ti,omap2430-i2c" for OMAP2430 SoCs + "ti,omap3-i2c" for OMAP3 SoCs + "ti,omap4-i2c" for OMAP4+ SoCs + "ti,am654-i2c", "ti,omap4-i2c" for AM654 SoCs - ti,hwmods : Must be "i2c<n>", n being the instance number (1-based) - #address-cells = <1>; - #size-cells = <0>; diff --git a/Documentation/i2c/busses/i2c-nvidia-gpu b/Documentation/i2c/busses/i2c-nvidia-gpu new file mode 100644 index 000000000000..31884d2b2eb5 --- /dev/null +++ b/Documentation/i2c/busses/i2c-nvidia-gpu @@ -0,0 +1,18 @@ +Kernel driver i2c-nvidia-gpu + +Datasheet: not publicly available. + +Authors: + Ajay Gupta <ajayg@nvidia.com> + +Description +----------- + +i2c-nvidia-gpu is a driver for I2C controller included in NVIDIA Turing +and later GPUs and it is used to communicate with Type-C controller on GPUs. + +If your 'lspci -v' listing shows something like the following, + +01:00.3 Serial bus controller [0c80]: NVIDIA Corporation Device 1ad9 (rev a1) + +then this driver should support the I2C controller of your GPU. diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt index 73aaaa3da436..804f9426ed17 100644 --- a/Documentation/x86/x86_64/mm.txt +++ b/Documentation/x86/x86_64/mm.txt @@ -34,23 +34,24 @@ __________________|____________|__________________|_________|___________________ ____________________________________________________________|___________________________________________________________ | | | | ffff800000000000 | -128 TB | ffff87ffffffffff | 8 TB | ... guard hole, also reserved for hypervisor - ffff880000000000 | -120 TB | ffffc7ffffffffff | 64 TB | direct mapping of all physical memory (page_offset_base) - ffffc80000000000 | -56 TB | ffffc8ffffffffff | 1 TB | ... unused hole + ffff880000000000 | -120 TB | ffff887fffffffff | 0.5 TB | LDT remap for PTI + ffff888000000000 | -119.5 TB | ffffc87fffffffff | 64 TB | direct mapping of all physical memory (page_offset_base) + ffffc88000000000 | -55.5 TB | ffffc8ffffffffff | 0.5 TB | ... unused hole ffffc90000000000 | -55 TB | ffffe8ffffffffff | 32 TB | vmalloc/ioremap space (vmalloc_base) ffffe90000000000 | -23 TB | ffffe9ffffffffff | 1 TB | ... unused hole ffffea0000000000 | -22 TB | ffffeaffffffffff | 1 TB | virtual memory map (vmemmap_base) ffffeb0000000000 | -21 TB | ffffebffffffffff | 1 TB | ... unused hole ffffec0000000000 | -20 TB | fffffbffffffffff | 16 TB | KASAN shadow memory - fffffc0000000000 | -4 TB | fffffdffffffffff | 2 TB | ... unused hole - | | | | vaddr_end for KASLR - fffffe0000000000 | -2 TB | fffffe7fffffffff | 0.5 TB | cpu_entry_area mapping - fffffe8000000000 | -1.5 TB | fffffeffffffffff | 0.5 TB | LDT remap for PTI - ffffff0000000000 | -1 TB | ffffff7fffffffff | 0.5 TB | %esp fixup stacks __________________|____________|__________________|_________|____________________________________________________________ | - | Identical layout to the 47-bit one from here on: + | Identical layout to the 56-bit one from here on: ____________________________________________________________|____________________________________________________________ | | | | + fffffc0000000000 | -4 TB | fffffdffffffffff | 2 TB | ... unused hole + | | | | vaddr_end for KASLR + fffffe0000000000 | -2 TB | fffffe7fffffffff | 0.5 TB | cpu_entry_area mapping + fffffe8000000000 | -1.5 TB | fffffeffffffffff | 0.5 TB | ... unused hole + ffffff0000000000 | -1 TB | ffffff7fffffffff | 0.5 TB | %esp fixup stacks ffffff8000000000 | -512 GB | ffffffeeffffffff | 444 GB | ... unused hole ffffffef00000000 | -68 GB | fffffffeffffffff | 64 GB | EFI region mapping space ffffffff00000000 | -4 GB | ffffffff7fffffff | 2 GB | ... unused hole @@ -83,7 +84,7 @@ Notes: __________________|____________|__________________|_________|___________________________________________________________ | | | | 0000800000000000 | +64 PB | ffff7fffffffffff | ~16K PB | ... huge, still almost 64 bits wide hole of non-canonical - | | | | virtual memory addresses up to the -128 TB + | | | | virtual memory addresses up to the -64 PB | | | | starting offset of kernel mappings. __________________|____________|__________________|_________|___________________________________________________________ | @@ -91,23 +92,24 @@ __________________|____________|__________________|_________|___________________ ____________________________________________________________|___________________________________________________________ | | | | ff00000000000000 | -64 PB | ff0fffffffffffff | 4 PB | ... guard hole, also reserved for hypervisor - ff10000000000000 | -60 PB | ff8fffffffffffff | 32 PB | direct mapping of all physical memory (page_offset_base) - ff90000000000000 | -28 PB | ff9fffffffffffff | 4 PB | LDT remap for PTI + ff10000000000000 | -60 PB | ff10ffffffffffff | 0.25 PB | LDT remap for PTI + ff11000000000000 | -59.75 PB | ff90ffffffffffff | 32 PB | direct mapping of all physical memory (page_offset_base) + ff91000000000000 | -27.75 PB | ff9fffffffffffff | 3.75 PB | ... unused hole ffa0000000000000 | -24 PB | ffd1ffffffffffff | 12.5 PB | vmalloc/ioremap space (vmalloc_base) ffd2000000000000 | -11.5 PB | ffd3ffffffffffff | 0.5 PB | ... unused hole ffd4000000000000 | -11 PB | ffd5ffffffffffff | 0.5 PB | virtual memory map (vmemmap_base) ffd6000000000000 | -10.5 PB | ffdeffffffffffff | 2.25 PB | ... unused hole ffdf000000000000 | -8.25 PB | fffffdffffffffff | ~8 PB | KASAN shadow memory - fffffc0000000000 | -4 TB | fffffdffffffffff | 2 TB | ... unused hole - | | | | vaddr_end for KASLR - fffffe0000000000 | -2 TB | fffffe7fffffffff | 0.5 TB | cpu_entry_area mapping - fffffe8000000000 | -1.5 TB | fffffeffffffffff | 0.5 TB | ... unused hole - ffffff0000000000 | -1 TB | ffffff7fffffffff | 0.5 TB | %esp fixup stacks __________________|____________|__________________|_________|____________________________________________________________ | | Identical layout to the 47-bit one from here on: ____________________________________________________________|____________________________________________________________ | | | | + fffffc0000000000 | -4 TB | fffffdffffffffff | 2 TB | ... unused hole + | | | | vaddr_end for KASLR + fffffe0000000000 | -2 TB | fffffe7fffffffff | 0.5 TB | cpu_entry_area mapping + fffffe8000000000 | -1.5 TB | fffffeffffffffff | 0.5 TB | ... unused hole + ffffff0000000000 | -1 TB | ffffff7fffffffff | 0.5 TB | %esp fixup stacks ffffff8000000000 | -512 GB | ffffffeeffffffff | 444 GB | ... unused hole ffffffef00000000 | -68 GB | fffffffeffffffff | 64 GB | EFI region mapping space ffffffff00000000 | -4 GB | ffffffff7fffffff | 2 GB | ... unused hole diff --git a/Documentation/x86/zero-page.txt b/Documentation/x86/zero-page.txt index 97b7adbceda4..68aed077f7b6 100644 --- a/Documentation/x86/zero-page.txt +++ b/Documentation/x86/zero-page.txt @@ -25,7 +25,7 @@ Offset Proto Name Meaning 0C8/004 ALL ext_cmd_line_ptr cmd_line_ptr high 32bits 140/080 ALL edid_info Video mode setup (struct edid_info) 1C0/020 ALL efi_info EFI 32 information (struct efi_info) -1E0/004 ALL alk_mem_k Alternative mem check, in KB +1E0/004 ALL alt_mem_k Alternative mem check, in KB 1E4/004 ALL scratch Scratch field for the kernel setup code 1E8/001 ALL e820_entries Number of entries in e820_table (below) 1E9/001 ALL eddbuf_entries Number of entries in eddbuf (below) diff --git a/MAINTAINERS b/MAINTAINERS index 2f3eba4484aa..b755a89fa325 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6861,6 +6861,13 @@ L: linux-acpi@vger.kernel.org S: Maintained F: drivers/i2c/i2c-core-acpi.c +I2C CONTROLLER DRIVER FOR NVIDIA GPU +M: Ajay Gupta <ajayg@nvidia.com> +L: linux-i2c@vger.kernel.org +S: Maintained +F: Documentation/i2c/busses/i2c-nvidia-gpu +F: drivers/i2c/busses/i2c-nvidia-gpu.c + I2C MUXES M: Peter Rosin <peda@axentia.se> L: linux-i2c@vger.kernel.org @@ -8367,7 +8374,7 @@ F: drivers/media/dvb-frontends/lgdt3305.* LIBATA PATA ARASAN COMPACT FLASH CONTROLLER M: Viresh Kumar <vireshk@kernel.org> L: linux-ide@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git S: Maintained F: include/linux/pata_arasan_cf_data.h F: drivers/ata/pata_arasan_cf.c @@ -8384,7 +8391,7 @@ F: drivers/ata/ata_generic.c LIBATA PATA FARADAY FTIDE010 AND GEMINI SATA BRIDGE DRIVERS M: Linus Walleij <linus.walleij@linaro.org> L: linux-ide@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git S: Maintained F: drivers/ata/pata_ftide010.c F: drivers/ata/sata_gemini.c @@ -8403,7 +8410,7 @@ F: include/linux/ahci_platform.h LIBATA SATA PROMISE TX2/TX4 CONTROLLER DRIVER M: Mikael Pettersson <mikpelinux@gmail.com> L: linux-ide@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git S: Maintained F: drivers/ata/sata_promise.* @@ -10784,6 +10791,14 @@ L: linux-omap@vger.kernel.org S: Maintained F: arch/arm/mach-omap2/omap_hwmod.* +OMAP I2C DRIVER +M: Vignesh R <vigneshr@ti.com> +L: linux-omap@vger.kernel.org +L: linux-i2c@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/i2c/i2c-omap.txt +F: drivers/i2c/busses/i2c-omap.c + OMAP IMAGING SUBSYSTEM (OMAP3 ISP and OMAP4 ISS) M: Laurent Pinchart <laurent.pinchart@ideasonboard.com> L: linux-media@vger.kernel.org @@ -10793,9 +10808,9 @@ F: drivers/media/platform/omap3isp/ F: drivers/staging/media/omap4iss/ OMAP MMC SUPPORT -M: Jarkko Lavinen <jarkko.lavinen@nokia.com> +M: Aaro Koskinen <aaro.koskinen@iki.fi> L: linux-omap@vger.kernel.org -S: Maintained +S: Odd Fixes F: drivers/mmc/host/omap.c OMAP POWER MANAGEMENT SUPPORT @@ -11730,6 +11745,7 @@ F: Documentation/devicetree/bindings/pinctrl/fsl,* PIN CONTROLLER - INTEL M: Mika Westerberg <mika.westerberg@linux.intel.com> M: Andy Shevchenko <andriy.shevchenko@linux.intel.com> +T: git git://git.kernel.org/pub/scm/linux/kernel/git/pinctrl/intel.git S: Maintained F: drivers/pinctrl/intel/ @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 20 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc3 NAME = "People's Front" # *DOCUMENTATION* diff --git a/arch/alpha/include/asm/termios.h b/arch/alpha/include/asm/termios.h index 6a8c53dec57e..b7c77bb1bfd2 100644 --- a/arch/alpha/include/asm/termios.h +++ b/arch/alpha/include/asm/termios.h @@ -73,9 +73,15 @@ }) #define user_termios_to_kernel_termios(k, u) \ - copy_from_user(k, u, sizeof(struct termios)) + copy_from_user(k, u, sizeof(struct termios2)) #define kernel_termios_to_user_termios(u, k) \ + copy_to_user(u, k, sizeof(struct termios2)) + +#define user_termios_to_kernel_termios_1(k, u) \ + copy_from_user(k, u, sizeof(struct termios)) + +#define kernel_termios_to_user_termios_1(u, k) \ copy_to_user(u, k, sizeof(struct termios)) #endif /* _ALPHA_TERMIOS_H */ diff --git a/arch/alpha/include/uapi/asm/ioctls.h b/arch/alpha/include/uapi/asm/ioctls.h index 1e9121c9b3c7..971311605288 100644 --- a/arch/alpha/include/uapi/asm/ioctls.h +++ b/arch/alpha/include/uapi/asm/ioctls.h @@ -32,6 +32,11 @@ #define TCXONC _IO('t', 30) #define TCFLSH _IO('t', 31) +#define TCGETS2 _IOR('T', 42, struct termios2) +#define TCSETS2 _IOW('T', 43, struct termios2) +#define TCSETSW2 _IOW('T', 44, struct termios2) +#define TCSETSF2 _IOW('T', 45, struct termios2) + #define TIOCSWINSZ _IOW('t', 103, struct winsize) #define TIOCGWINSZ _IOR('t', 104, struct winsize) #define TIOCSTART _IO('t', 110) /* start output, like ^Q */ diff --git a/arch/alpha/include/uapi/asm/termbits.h b/arch/alpha/include/uapi/asm/termbits.h index de6c8360fbe3..4575ba34a0ea 100644 --- a/arch/alpha/include/uapi/asm/termbits.h +++ b/arch/alpha/include/uapi/asm/termbits.h @@ -26,6 +26,19 @@ struct termios { speed_t c_ospeed; /* output speed */ }; +/* Alpha has identical termios and termios2 */ + +struct termios2 { + tcflag_t c_iflag; /* input mode flags */ + tcflag_t c_oflag; /* output mode flags */ + tcflag_t c_cflag; /* control mode flags */ + tcflag_t c_lflag; /* local mode flags */ + cc_t c_cc[NCCS]; /* control characters */ + cc_t c_line; /* line discipline (== c_cc[19]) */ + speed_t c_ispeed; /* input speed */ + speed_t c_ospeed; /* output speed */ +}; + /* Alpha has matching termios and ktermios */ struct ktermios { @@ -152,6 +165,7 @@ struct ktermios { #define B3000000 00034 #define B3500000 00035 #define B4000000 00036 +#define BOTHER 00037 #define CSIZE 00001400 #define CS5 00000000 @@ -169,6 +183,9 @@ struct ktermios { #define CMSPAR 010000000000 /* mark or space (stick) parity */ #define CRTSCTS 020000000000 /* flow control */ +#define CIBAUD 07600000 +#define IBSHIFT 16 + /* c_lflag bits */ #define ISIG 0x00000080 #define ICANON 0x00000100 diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h index 0d289240b6ca..775cac3c02bb 100644 --- a/arch/arm/include/asm/cputype.h +++ b/arch/arm/include/asm/cputype.h @@ -111,6 +111,7 @@ #include <linux/kernel.h> extern unsigned int processor_id; +struct proc_info_list *lookup_processor(u32 midr); #ifdef CONFIG_CPU_CP15 #define read_cpuid(reg) \ diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index 92fd2c8a9af0..12659ce5c1f3 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -10,7 +10,7 @@ #ifndef _ASM_PGTABLE_2LEVEL_H #define _ASM_PGTABLE_2LEVEL_H -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 /* * Hardware-wise, we have a two level page table structure, where the first diff --git a/arch/arm/include/asm/proc-fns.h b/arch/arm/include/asm/proc-fns.h index e25f4392e1b2..e1b6f280ab08 100644 --- a/arch/arm/include/asm/proc-fns.h +++ b/arch/arm/include/asm/proc-fns.h @@ -23,7 +23,7 @@ struct mm_struct; /* * Don't change this structure - ASM code relies on it. */ -extern struct processor { +struct processor { /* MISC * get data abort address/flags */ @@ -79,9 +79,13 @@ extern struct processor { unsigned int suspend_size; void (*do_suspend)(void *); void (*do_resume)(void *); -} processor; +}; #ifndef MULTI_CPU +static inline void init_proc_vtable(const struct processor *p) +{ +} + extern void cpu_proc_init(void); extern void cpu_proc_fin(void); extern int cpu_do_idle(void); @@ -98,17 +102,50 @@ extern void cpu_reset(unsigned long addr, bool hvc) __attribute__((noreturn)); extern void cpu_do_suspend(void *); extern void cpu_do_resume(void *); #else -#define cpu_proc_init processor._proc_init -#define cpu_proc_fin processor._proc_fin -#define cpu_reset processor.reset -#define cpu_do_idle processor._do_idle -#define cpu_dcache_clean_area processor.dcache_clean_area -#define cpu_set_pte_ext processor.set_pte_ext -#define cpu_do_switch_mm processor.switch_mm -/* These three are private to arch/arm/kernel/suspend.c */ -#define cpu_do_suspend processor.do_suspend -#define cpu_do_resume processor.do_resume +extern struct processor processor; +#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR) +#include <linux/smp.h> +/* + * This can't be a per-cpu variable because we need to access it before + * per-cpu has been initialised. We have a couple of functions that are + * called in a pre-emptible context, and so can't use smp_processor_id() + * there, hence PROC_TABLE(). We insist in init_proc_vtable() that the + * function pointers for these are identical across all CPUs. + */ +extern struct processor *cpu_vtable[]; +#define PROC_VTABLE(f) cpu_vtable[smp_processor_id()]->f +#define PROC_TABLE(f) cpu_vtable[0]->f +static inline void init_proc_vtable(const struct processor *p) +{ + unsigned int cpu = smp_processor_id(); + *cpu_vtable[cpu] = *p; + WARN_ON_ONCE(cpu_vtable[cpu]->dcache_clean_area != + cpu_vtable[0]->dcache_clean_area); + WARN_ON_ONCE(cpu_vtable[cpu]->set_pte_ext != + cpu_vtable[0]->set_pte_ext); +} +#else +#define PROC_VTABLE(f) processor.f +#define PROC_TABLE(f) processor.f +static inline void init_proc_vtable(const struct processor *p) +{ + processor = *p; +} +#endif + +#define cpu_proc_init PROC_VTABLE(_proc_init) +#define cpu_check_bugs PROC_VTABLE(check_bugs) +#define cpu_proc_fin PROC_VTABLE(_proc_fin) +#define cpu_reset PROC_VTABLE(reset) +#define cpu_do_idle PROC_VTABLE(_do_idle) +#define cpu_dcache_clean_area PROC_TABLE(dcache_clean_area) +#define cpu_set_pte_ext PROC_TABLE(set_pte_ext) +#define cpu_do_switch_mm PROC_VTABLE(switch_mm) + +/* These two are private to arch/arm/kernel/suspend.c */ +#define cpu_do_suspend PROC_VTABLE(do_suspend) +#define cpu_do_resume PROC_VTABLE(do_resume) #endif extern void cpu_resume(void); diff --git a/arch/arm/kernel/bugs.c b/arch/arm/kernel/bugs.c index 7be511310191..d41d3598e5e5 100644 --- a/arch/arm/kernel/bugs.c +++ b/arch/arm/kernel/bugs.c @@ -6,8 +6,8 @@ void check_other_bugs(void) { #ifdef MULTI_CPU - if (processor.check_bugs) - processor.check_bugs(); + if (cpu_check_bugs) + cpu_check_bugs(); #endif } diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S index 6e0375e7db05..997b02302c31 100644 --- a/arch/arm/kernel/head-common.S +++ b/arch/arm/kernel/head-common.S @@ -145,6 +145,9 @@ __mmap_switched_data: #endif .size __mmap_switched_data, . - __mmap_switched_data + __FINIT + .text + /* * This provides a C-API version of __lookup_processor_type */ @@ -156,9 +159,6 @@ ENTRY(lookup_processor_type) ldmfd sp!, {r4 - r6, r9, pc} ENDPROC(lookup_processor_type) - __FINIT - .text - /* * Read processor ID register (CP#15, CR0), and look up in the linker-built * supported processor list. Note that we can't use the absolute addresses diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index ac7e08886863..375b13f7e780 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -114,6 +114,11 @@ EXPORT_SYMBOL(elf_hwcap2); #ifdef MULTI_CPU struct processor processor __ro_after_init; +#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR) +struct processor *cpu_vtable[NR_CPUS] = { + [0] = &processor, +}; +#endif #endif #ifdef MULTI_TLB struct cpu_tlb_fns cpu_tlb __ro_after_init; @@ -666,28 +671,33 @@ static void __init smp_build_mpidr_hash(void) } #endif -static void __init setup_processor(void) +/* + * locate processor in the list of supported processor types. The linker + * builds this table for us from the entries in arch/arm/mm/proc-*.S + */ +struct proc_info_list *lookup_processor(u32 midr) { - struct proc_info_list *list; + struct proc_info_list *list = lookup_processor_type(midr); - /* - * locate processor in the list of supported processor - * types. The linker builds this table for us from the - * entries in arch/arm/mm/proc-*.S - */ - list = lookup_processor_type(read_cpuid_id()); if (!list) { - pr_err("CPU configuration botched (ID %08x), unable to continue.\n", - read_cpuid_id()); - while (1); + pr_err("CPU%u: configuration botched (ID %08x), CPU halted\n", + smp_processor_id(), midr); + while (1) + /* can't use cpu_relax() here as it may require MMU setup */; } + return list; +} + +static void __init setup_processor(void) +{ + unsigned int midr = read_cpuid_id(); + struct proc_info_list *list = lookup_processor(midr); + cpu_name = list->cpu_name; __cpu_architecture = __get_cpu_architecture(); -#ifdef MULTI_CPU - processor = *list->proc; -#endif + init_proc_vtable(list->proc); #ifdef MULTI_TLB cpu_tlb = *list->tlb; #endif @@ -699,7 +709,7 @@ static void __init setup_processor(void) #endif pr_info("CPU: %s [%08x] revision %d (ARMv%s), cr=%08lx\n", - cpu_name, read_cpuid_id(), read_cpuid_id() & 15, + list->cpu_name, midr, midr & 15, proc_arch[cpu_architecture()], get_cr()); snprintf(init_utsname()->machine, __NEW_UTS_LEN + 1, "%s%c", diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 0978282d5fc2..12a6172263c0 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -42,6 +42,7 @@ #include <asm/mmu_context.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> +#include <asm/procinfo.h> #include <asm/processor.h> #include <asm/sections.h> #include <asm/tlbflush.h> @@ -102,6 +103,30 @@ static unsigned long get_arch_pgd(pgd_t *pgd) #endif } +#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR) +static int secondary_biglittle_prepare(unsigned int cpu) +{ + if (!cpu_vtable[cpu]) + cpu_vtable[cpu] = kzalloc(sizeof(*cpu_vtable[cpu]), GFP_KERNEL); + + return cpu_vtable[cpu] ? 0 : -ENOMEM; +} + +static void secondary_biglittle_init(void) +{ + init_proc_vtable(lookup_processor(read_cpuid_id())->proc); +} +#else +static int secondary_biglittle_prepare(unsigned int cpu) +{ + return 0; +} + +static void secondary_biglittle_init(void) +{ +} +#endif + int __cpu_up(unsigned int cpu, struct task_struct *idle) { int ret; @@ -109,6 +134,10 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) if (!smp_ops.smp_boot_secondary) return -ENOSYS; + ret = secondary_biglittle_prepare(cpu); + if (ret) + return ret; + /* * We need to tell the secondary core where to find * its stack and the page tables. @@ -359,6 +388,8 @@ asmlinkage void secondary_start_kernel(void) struct mm_struct *mm = &init_mm; unsigned int cpu; + secondary_biglittle_init(); + /* * The identity mapping is uncached (strongly ordered), so * switch away from it before attempting any exclusive accesses. diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c index 9500b6e27380..f86b72d1d59e 100644 --- a/arch/arm/mach-omap2/display.c +++ b/arch/arm/mach-omap2/display.c @@ -209,11 +209,61 @@ static int __init omapdss_init_fbdev(void) return 0; } -#else -static inline int omapdss_init_fbdev(void) + +static const char * const omapdss_compat_names[] __initconst = { + "ti,omap2-dss", + "ti,omap3-dss", + "ti,omap4-dss", + "ti,omap5-dss", + "ti,dra7-dss", +}; + +static struct device_node * __init omapdss_find_dss_of_node(void) { - return 0; + struct device_node *node; + int i; + + for (i = 0; i < ARRAY_SIZE(omapdss_compat_names); ++i) { + node = of_find_compatible_node(NULL, NULL, + omapdss_compat_names[i]); + if (node) + return node; + } + + return NULL; } + +static int __init omapdss_init_of(void) +{ + int r; + struct device_node *node; + struct platform_device *pdev; + + /* only create dss helper devices if dss is enabled in the .dts */ + + node = omapdss_find_dss_of_node(); + if (!node) + return 0; + + if (!of_device_is_available(node)) + return 0; + + pdev = of_find_device_by_node(node); + + if (!pdev) { + pr_err("Unable to find DSS platform device\n"); + return -ENODEV; + } + + r = of_platform_populate(node, NULL, NULL, &pdev->dev); + if (r) { + pr_err("Unable to populate DSS submodule devices\n"); + return r; + } + + return omapdss_init_fbdev(); +} +omap_device_initcall(omapdss_init_of); #endif /* CONFIG_FB_OMAP2 */ static void dispc_disable_outputs(void) @@ -361,58 +411,3 @@ int omap_dss_reset(struct omap_hwmod *oh) return r; } - -static const char * const omapdss_compat_names[] __initconst = { - "ti,omap2-dss", - "ti,omap3-dss", - "ti,omap4-dss", - "ti,omap5-dss", - "ti,dra7-dss", -}; - -static struct device_node * __init omapdss_find_dss_of_node(void) -{ - struct device_node *node; - int i; - - for (i = 0; i < ARRAY_SIZE(omapdss_compat_names); ++i) { - node = of_find_compatible_node(NULL, NULL, - omapdss_compat_names[i]); - if (node) - return node; - } - - return NULL; -} - -static int __init omapdss_init_of(void) -{ - int r; - struct device_node *node; - struct platform_device *pdev; - - /* only create dss helper devices if dss is enabled in the .dts */ - - node = omapdss_find_dss_of_node(); - if (!node) - return 0; - - if (!of_device_is_available(node)) - return 0; - - pdev = of_find_device_by_node(node); - - if (!pdev) { - pr_err("Unable to find DSS platform device\n"); - return -ENODEV; - } - - r = of_platform_populate(node, NULL, NULL, &pdev->dev); - if (r) { - pr_err("Unable to populate DSS submodule devices\n"); - return r; - } - - return omapdss_init_fbdev(); -} -omap_device_initcall(omapdss_init_of); diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c index 5544b82a2e7a..9a07916af8dd 100644 --- a/arch/arm/mm/proc-v7-bugs.c +++ b/arch/arm/mm/proc-v7-bugs.c @@ -52,8 +52,6 @@ static void cpu_v7_spectre_init(void) case ARM_CPU_PART_CORTEX_A17: case ARM_CPU_PART_CORTEX_A73: case ARM_CPU_PART_CORTEX_A75: - if (processor.switch_mm != cpu_v7_bpiall_switch_mm) - goto bl_error; per_cpu(harden_branch_predictor_fn, cpu) = harden_branch_predictor_bpiall; spectre_v2_method = "BPIALL"; @@ -61,8 +59,6 @@ static void cpu_v7_spectre_init(void) case ARM_CPU_PART_CORTEX_A15: case ARM_CPU_PART_BRAHMA_B15: - if (processor.switch_mm != cpu_v7_iciallu_switch_mm) - goto bl_error; per_cpu(harden_branch_predictor_fn, cpu) = harden_branch_predictor_iciallu; spectre_v2_method = "ICIALLU"; @@ -88,11 +84,9 @@ static void cpu_v7_spectre_init(void) ARM_SMCCC_ARCH_WORKAROUND_1, &res); if ((int)res.a0 != 0) break; - if (processor.switch_mm != cpu_v7_hvc_switch_mm && cpu) - goto bl_error; per_cpu(harden_branch_predictor_fn, cpu) = call_hvc_arch_workaround_1; - processor.switch_mm = cpu_v7_hvc_switch_mm; + cpu_do_switch_mm = cpu_v7_hvc_switch_mm; spectre_v2_method = "hypervisor"; break; @@ -101,11 +95,9 @@ static void cpu_v7_spectre_init(void) ARM_SMCCC_ARCH_WORKAROUND_1, &res); if ((int)res.a0 != 0) break; - if (processor.switch_mm != cpu_v7_smc_switch_mm && cpu) - goto bl_error; per_cpu(harden_branch_predictor_fn, cpu) = call_smc_arch_workaround_1; - processor.switch_mm = cpu_v7_smc_switch_mm; + cpu_do_switch_mm = cpu_v7_smc_switch_mm; spectre_v2_method = "firmware"; break; @@ -119,11 +111,6 @@ static void cpu_v7_spectre_init(void) if (spectre_v2_method) pr_info("CPU%u: Spectre v2: using %s workaround\n", smp_processor_id(), spectre_v2_method); - return; - -bl_error: - pr_err("CPU%u: Spectre v2: incorrect context switching function, system vulnerable\n", - cpu); } #else static void cpu_v7_spectre_init(void) diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index aff6e6eadc70..ee7b07938dd5 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -573,7 +573,7 @@ int vfp_preserve_user_clear_hwstate(struct user_vfp *ufp, */ ufp_exc->fpexc = hwstate->fpexc; ufp_exc->fpinst = hwstate->fpinst; - ufp_exc->fpinst2 = ufp_exc->fpinst2; + ufp_exc->fpinst2 = hwstate->fpinst2; /* Ensure that VFP is disabled. */ vfp_flush_hwstate(thread); diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 3e2091708b8e..6b0d4dff5012 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -24,6 +24,14 @@ #define KERNEL_DS UL(-1) #define USER_DS (TASK_SIZE_64 - 1) +/* + * On arm64 systems, unaligned accesses by the CPU are cheap, and so there is + * no point in shifting all network buffers by 2 bytes just to make some IP + * header fields appear aligned in memory, potentially sacrificing some DMA + * performance on some platforms. + */ +#define NET_IP_ALIGN 0 + #ifndef __ASSEMBLY__ #ifdef __KERNEL__ diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 953e316521fc..f4fc1e0544b7 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -313,6 +313,7 @@ void __init setup_arch(char **cmdline_p) arm64_memblock_init(); paging_init(); + efi_apply_persistent_mem_reservations(); acpi_table_upgrade(); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 9d9582cac6c4..9b432d9fcada 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -483,8 +483,6 @@ void __init arm64_memblock_init(void) high_memory = __va(memblock_end_of_DRAM() - 1) + 1; dma_contiguous_reserve(arm64_dma_phys_limit); - - memblock_allow_resize(); } void __init bootmem_init(void) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 394b8d554def..d1d6601b385d 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -659,6 +659,8 @@ void __init paging_init(void) memblock_free(__pa_symbol(init_pg_dir), __pa_symbol(init_pg_end) - __pa_symbol(init_pg_dir)); + + memblock_allow_resize(); } /* diff --git a/arch/m68k/include/asm/pgtable_mm.h b/arch/m68k/include/asm/pgtable_mm.h index 6181e4134483..fe3ddd73a0cc 100644 --- a/arch/m68k/include/asm/pgtable_mm.h +++ b/arch/m68k/include/asm/pgtable_mm.h @@ -55,12 +55,12 @@ */ #ifdef CONFIG_SUN3 #define PTRS_PER_PTE 16 -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 #define PTRS_PER_PMD 1 #define PTRS_PER_PGD 2048 #elif defined(CONFIG_COLDFIRE) #define PTRS_PER_PTE 512 -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 #define PTRS_PER_PMD 1 #define PTRS_PER_PGD 1024 #else diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h index f64ebb9c9a41..e14b6621c933 100644 --- a/arch/microblaze/include/asm/pgtable.h +++ b/arch/microblaze/include/asm/pgtable.h @@ -63,7 +63,7 @@ extern int mem_init_done; #include <asm-generic/4level-fixup.h> -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 #ifdef __KERNEL__ #ifndef __ASSEMBLY__ diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper.c b/arch/mips/cavium-octeon/executive/cvmx-helper.c index 75108ec669eb..6c79e8a16a26 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-helper.c +++ b/arch/mips/cavium-octeon/executive/cvmx-helper.c @@ -67,7 +67,7 @@ void (*cvmx_override_pko_queue_priority) (int pko_port, void (*cvmx_override_ipd_port_setup) (int ipd_port); /* Port count per interface */ -static int interface_port_count[5]; +static int interface_port_count[9]; /** * Return the number of interfaces the chip has. Each interface diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c index e6c9485cadcf..cb38461391cb 100644 --- a/arch/mips/mm/dma-noncoherent.c +++ b/arch/mips/mm/dma-noncoherent.c @@ -50,7 +50,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, void *ret; ret = dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs); - if (!ret && !(attrs & DMA_ATTR_NON_CONSISTENT)) { + if (ret && !(attrs & DMA_ATTR_NON_CONSISTENT)) { dma_cache_wback_inv((unsigned long) ret, size); ret = (void *)UNCAC_ADDR(ret); } diff --git a/arch/nds32/include/asm/pgtable.h b/arch/nds32/include/asm/pgtable.h index d3e19a55cf53..9f52db930c00 100644 --- a/arch/nds32/include/asm/pgtable.h +++ b/arch/nds32/include/asm/pgtable.h @@ -4,7 +4,7 @@ #ifndef _ASMNDS32_PGTABLE_H #define _ASMNDS32_PGTABLE_H -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 #include <asm-generic/4level-fixup.h> #include <asm-generic/sizes.h> diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index b941ac7d4e70..c7bb74e22436 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -111,7 +111,7 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) #if CONFIG_PGTABLE_LEVELS == 3 #define BITS_PER_PMD (PAGE_SHIFT + PMD_ORDER - BITS_PER_PMD_ENTRY) #else -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 #define BITS_PER_PMD 0 #endif #define PTRS_PER_PMD (1UL << BITS_PER_PMD) diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h index 16aec9ba2580..8a63515f03bf 100644 --- a/arch/parisc/include/asm/spinlock.h +++ b/arch/parisc/include/asm/spinlock.h @@ -37,8 +37,8 @@ static inline void arch_spin_unlock(arch_spinlock_t *x) volatile unsigned int *a; a = __ldcw_align(x); - /* Release with ordered store. */ - __asm__ __volatile__("stw,ma %0,0(%1)" : : "r"(1), "r"(a) : "memory"); + mb(); + *a = 1; } static inline int arch_spin_trylock(arch_spinlock_t *x) diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 9505c317818d..a9bc90dc4ae7 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -640,7 +640,8 @@ cas_action: sub,<> %r28, %r25, %r0 2: stw %r24, 0(%r26) /* Free lock */ - stw,ma %r20, 0(%sr2,%r20) + sync + stw %r20, 0(%sr2,%r20) #if ENABLE_LWS_DEBUG /* Clear thread register indicator */ stw %r0, 4(%sr2,%r20) @@ -654,7 +655,8 @@ cas_action: 3: /* Error occurred on load or store */ /* Free lock */ - stw,ma %r20, 0(%sr2,%r20) + sync + stw %r20, 0(%sr2,%r20) #if ENABLE_LWS_DEBUG stw %r0, 4(%sr2,%r20) #endif @@ -855,7 +857,8 @@ cas2_action: cas2_end: /* Free lock */ - stw,ma %r20, 0(%sr2,%r20) + sync + stw %r20, 0(%sr2,%r20) /* Enable interrupts */ ssm PSW_SM_I, %r0 /* Return to userspace, set no error */ @@ -865,7 +868,8 @@ cas2_end: 22: /* Error occurred on load or store */ /* Free lock */ - stw,ma %r20, 0(%sr2,%r20) + sync + stw %r20, 0(%sr2,%r20) ssm PSW_SM_I, %r0 ldo 1(%r0),%r28 b lws_exit diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index 3ef40b703c4a..e746becd9d6f 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -268,19 +268,13 @@ extern void _memcpy_toio(volatile void __iomem *dest, const void *src, * their hooks, a bitfield is reserved for use by the platform near the * top of MMIO addresses (not PIO, those have to cope the hard way). * - * This bit field is 12 bits and is at the top of the IO virtual - * addresses PCI_IO_INDIRECT_TOKEN_MASK. + * The highest address in the kernel virtual space are: * - * The kernel virtual space is thus: + * d0003fffffffffff # with Hash MMU + * c00fffffffffffff # with Radix MMU * - * 0xD000000000000000 : vmalloc - * 0xD000080000000000 : PCI PHB IO space - * 0xD000080080000000 : ioremap - * 0xD0000fffffffffff : end of ioremap region - * - * Since the top 4 bits are reserved as the region ID, we use thus - * the next 12 bits and keep 4 bits available for the future if the - * virtual address space is ever to be extended. + * The top 4 bits are reserved as the region ID on hash, leaving us 8 bits + * that can be used for the field. * * The direct IO mapping operations will then mask off those bits * before doing the actual access, though that only happen when @@ -292,8 +286,8 @@ extern void _memcpy_toio(volatile void __iomem *dest, const void *src, */ #ifdef CONFIG_PPC_INDIRECT_MMIO -#define PCI_IO_IND_TOKEN_MASK 0x0fff000000000000ul -#define PCI_IO_IND_TOKEN_SHIFT 48 +#define PCI_IO_IND_TOKEN_SHIFT 52 +#define PCI_IO_IND_TOKEN_MASK (0xfful << PCI_IO_IND_TOKEN_SHIFT) #define PCI_FIX_ADDR(addr) \ ((PCI_IO_ADDR)(((unsigned long)(addr)) & ~PCI_IO_IND_TOKEN_MASK)) #define PCI_GET_ADDR_TOKEN(addr) \ diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 6093bc8f74e5..a6e9e314c707 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -493,6 +493,8 @@ __PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b)) #define PPC_SLBFEE_DOT(t, b) stringify_in_c(.long PPC_INST_SLBFEE | \ __PPC_RT(t) | __PPC_RB(b)) +#define __PPC_SLBFEE_DOT(t, b) stringify_in_c(.long PPC_INST_SLBFEE | \ + ___PPC_RT(t) | ___PPC_RB(b)) #define PPC_ICBT(c,a,b) stringify_in_c(.long PPC_INST_ICBT | \ __PPC_CT(c) | __PPC_RA0(a) | __PPC_RB(b)) /* PASemi instructions */ diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index f73886a1a7f5..0b8a735b6d85 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -54,6 +54,7 @@ struct pt_regs #ifdef CONFIG_PPC64 unsigned long ppr; + unsigned long __pad; /* Maintain 16 byte interrupt stack alignment */ #endif }; #endif diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 2a51e4cc8246..236c1151a3a7 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -636,6 +636,8 @@ static void *__init alloc_stack(unsigned long limit, int cpu) { unsigned long pa; + BUILD_BUG_ON(STACK_INT_FRAME_SIZE % 16); + pa = memblock_alloc_base_nid(THREAD_SIZE, THREAD_SIZE, limit, early_cpu_to_node(cpu), MEMBLOCK_NONE); if (!pa) { diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h index 491b0f715d6b..ea1d7c808319 100644 --- a/arch/powerpc/kvm/trace.h +++ b/arch/powerpc/kvm/trace.h @@ -6,8 +6,6 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm -#define TRACE_INCLUDE_PATH . -#define TRACE_INCLUDE_FILE trace /* * Tracepoint for guest mode entry. @@ -120,4 +118,10 @@ TRACE_EVENT(kvm_check_requests, #endif /* _TRACE_KVM_H */ /* This part must be outside protection */ +#undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE + +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE trace + #include <trace/define_trace.h> diff --git a/arch/powerpc/kvm/trace_booke.h b/arch/powerpc/kvm/trace_booke.h index ac640e81fdc5..3837842986aa 100644 --- a/arch/powerpc/kvm/trace_booke.h +++ b/arch/powerpc/kvm/trace_booke.h @@ -6,8 +6,6 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm_booke -#define TRACE_INCLUDE_PATH . -#define TRACE_INCLUDE_FILE trace_booke #define kvm_trace_symbol_exit \ {0, "CRITICAL"}, \ @@ -218,4 +216,11 @@ TRACE_EVENT(kvm_booke_queue_irqprio, #endif /* This part must be outside protection */ + +#undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE + +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE trace_booke + #include <trace/define_trace.h> diff --git a/arch/powerpc/kvm/trace_hv.h b/arch/powerpc/kvm/trace_hv.h index bcfe8a987f6a..8a1e3b0047f1 100644 --- a/arch/powerpc/kvm/trace_hv.h +++ b/arch/powerpc/kvm/trace_hv.h @@ -9,8 +9,6 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm_hv -#define TRACE_INCLUDE_PATH . -#define TRACE_INCLUDE_FILE trace_hv #define kvm_trace_symbol_hcall \ {H_REMOVE, "H_REMOVE"}, \ @@ -497,4 +495,11 @@ TRACE_EVENT(kvmppc_run_vcpu_exit, #endif /* _TRACE_KVM_HV_H */ /* This part must be outside protection */ + +#undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE + +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE trace_hv + #include <trace/define_trace.h> diff --git a/arch/powerpc/kvm/trace_pr.h b/arch/powerpc/kvm/trace_pr.h index 2f9a8829552b..46a46d328fbf 100644 --- a/arch/powerpc/kvm/trace_pr.h +++ b/arch/powerpc/kvm/trace_pr.h @@ -8,8 +8,6 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm_pr -#define TRACE_INCLUDE_PATH . -#define TRACE_INCLUDE_FILE trace_pr TRACE_EVENT(kvm_book3s_reenter, TP_PROTO(int r, struct kvm_vcpu *vcpu), @@ -257,4 +255,11 @@ TRACE_EVENT(kvm_exit, #endif /* _TRACE_KVM_H */ /* This part must be outside protection */ + +#undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE + +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE trace_pr + #include <trace/define_trace.h> diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 3a048e98a132..ce28ae5ca080 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1178,7 +1178,7 @@ static long vphn_get_associativity(unsigned long cpu, switch (rc) { case H_FUNCTION: - printk(KERN_INFO + printk_once(KERN_INFO "VPHN is not supported. Disabling polling...\n"); stop_topology_update(); break; diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c index c3fdf2969d9f..bc3914d54e26 100644 --- a/arch/powerpc/mm/slb.c +++ b/arch/powerpc/mm/slb.c @@ -19,6 +19,7 @@ #include <asm/mmu.h> #include <asm/mmu_context.h> #include <asm/paca.h> +#include <asm/ppc-opcode.h> #include <asm/cputable.h> #include <asm/cacheflush.h> #include <asm/smp.h> @@ -58,27 +59,19 @@ static inline unsigned long mk_vsid_data(unsigned long ea, int ssize, return __mk_vsid_data(get_kernel_vsid(ea, ssize), ssize, flags); } -static void assert_slb_exists(unsigned long ea) +static void assert_slb_presence(bool present, unsigned long ea) { #ifdef CONFIG_DEBUG_VM unsigned long tmp; WARN_ON_ONCE(mfmsr() & MSR_EE); - asm volatile("slbfee. %0, %1" : "=r"(tmp) : "r"(ea) : "cr0"); - WARN_ON(tmp == 0); -#endif -} - -static void assert_slb_notexists(unsigned long ea) -{ -#ifdef CONFIG_DEBUG_VM - unsigned long tmp; + if (!cpu_has_feature(CPU_FTR_ARCH_206)) + return; - WARN_ON_ONCE(mfmsr() & MSR_EE); + asm volatile(__PPC_SLBFEE_DOT(%0, %1) : "=r"(tmp) : "r"(ea) : "cr0"); - asm volatile("slbfee. %0, %1" : "=r"(tmp) : "r"(ea) : "cr0"); - WARN_ON(tmp != 0); + WARN_ON(present == (tmp == 0)); #endif } @@ -114,7 +107,7 @@ static inline void create_shadowed_slbe(unsigned long ea, int ssize, */ slb_shadow_update(ea, ssize, flags, index); - assert_slb_notexists(ea); + assert_slb_presence(false, ea); asm volatile("slbmte %0,%1" : : "r" (mk_vsid_data(ea, ssize, flags)), "r" (mk_esid_data(ea, ssize, index)) @@ -137,7 +130,7 @@ void __slb_restore_bolted_realmode(void) "r" (be64_to_cpu(p->save_area[index].esid))); } - assert_slb_exists(local_paca->kstack); + assert_slb_presence(true, local_paca->kstack); } /* @@ -185,7 +178,7 @@ void slb_flush_and_restore_bolted(void) :: "r" (be64_to_cpu(p->save_area[KSTACK_INDEX].vsid)), "r" (be64_to_cpu(p->save_area[KSTACK_INDEX].esid)) : "memory"); - assert_slb_exists(get_paca()->kstack); + assert_slb_presence(true, get_paca()->kstack); get_paca()->slb_cache_ptr = 0; @@ -443,9 +436,9 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm) ea = (unsigned long) get_paca()->slb_cache[i] << SID_SHIFT; /* - * Could assert_slb_exists here, but hypervisor - * or machine check could have come in and - * removed the entry at this point. + * Could assert_slb_presence(true) here, but + * hypervisor or machine check could have come + * in and removed the entry at this point. */ slbie_data = ea; @@ -676,7 +669,7 @@ static long slb_insert_entry(unsigned long ea, unsigned long context, * User preloads should add isync afterwards in case the kernel * accesses user memory before it returns to userspace with rfid. */ - assert_slb_notexists(ea); + assert_slb_presence(false, ea); asm volatile("slbmte %0, %1" : : "r" (vsid_data), "r" (esid_data)); barrier(); @@ -715,7 +708,7 @@ static long slb_allocate_kernel(unsigned long ea, unsigned long id) return -EFAULT; if (ea < H_VMALLOC_END) - flags = get_paca()->vmalloc_sllp; + flags = local_paca->vmalloc_sllp; else flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_io_psize].sllp; } else { diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c index 6f60e0931922..75b935252981 100644 --- a/arch/powerpc/platforms/powernv/npu-dma.c +++ b/arch/powerpc/platforms/powernv/npu-dma.c @@ -102,63 +102,6 @@ struct pci_dev *pnv_pci_get_npu_dev(struct pci_dev *gpdev, int index) } EXPORT_SYMBOL(pnv_pci_get_npu_dev); -#define NPU_DMA_OP_UNSUPPORTED() \ - dev_err_once(dev, "%s operation unsupported for NVLink devices\n", \ - __func__) - -static void *dma_npu_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag, - unsigned long attrs) -{ - NPU_DMA_OP_UNSUPPORTED(); - return NULL; -} - -static void dma_npu_free(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle, - unsigned long attrs) -{ - NPU_DMA_OP_UNSUPPORTED(); -} - -static dma_addr_t dma_npu_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction direction, - unsigned long attrs) -{ - NPU_DMA_OP_UNSUPPORTED(); - return 0; -} - -static int dma_npu_map_sg(struct device *dev, struct scatterlist *sglist, - int nelems, enum dma_data_direction direction, - unsigned long attrs) -{ - NPU_DMA_OP_UNSUPPORTED(); - return 0; -} - -static int dma_npu_dma_supported(struct device *dev, u64 mask) -{ - NPU_DMA_OP_UNSUPPORTED(); - return 0; -} - -static u64 dma_npu_get_required_mask(struct device *dev) -{ - NPU_DMA_OP_UNSUPPORTED(); - return 0; -} - -static const struct dma_map_ops dma_npu_ops = { - .map_page = dma_npu_map_page, - .map_sg = dma_npu_map_sg, - .alloc = dma_npu_alloc, - .free = dma_npu_free, - .dma_supported = dma_npu_dma_supported, - .get_required_mask = dma_npu_get_required_mask, -}; - /* * Returns the PE assoicated with the PCI device of the given * NPU. Returns the linked pci device if pci_dev != NULL. @@ -270,10 +213,11 @@ static void pnv_npu_dma_set_32(struct pnv_ioda_pe *npe) rc = pnv_npu_set_window(npe, 0, gpe->table_group.tables[0]); /* - * We don't initialise npu_pe->tce32_table as we always use - * dma_npu_ops which are nops. + * NVLink devices use the same TCE table configuration as + * their parent device so drivers shouldn't be doing DMA + * operations directly on these devices. */ - set_dma_ops(&npe->pdev->dev, &dma_npu_ops); + set_dma_ops(&npe->pdev->dev, NULL); } /* diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index d10146197533..4af153a182b0 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -77,4 +77,8 @@ core-y += arch/riscv/kernel/ arch/riscv/mm/ libs-y += arch/riscv/lib/ +PHONY += vdso_install +vdso_install: + $(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso $@ + all: vmlinux diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 07fa9ea75fea..ef4f15df9adf 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -76,4 +76,5 @@ CONFIG_NFS_V4_1=y CONFIG_NFS_V4_2=y CONFIG_ROOT_NFS=y CONFIG_CRYPTO_USER_API_HASH=y +CONFIG_PRINTK_TIME=y # CONFIG_RCU_TRACE is not set diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h index 2c5df945d43c..bbe1862e8f80 100644 --- a/arch/riscv/include/asm/ptrace.h +++ b/arch/riscv/include/asm/ptrace.h @@ -56,8 +56,8 @@ struct pt_regs { unsigned long sstatus; unsigned long sbadaddr; unsigned long scause; - /* a0 value before the syscall */ - unsigned long orig_a0; + /* a0 value before the syscall */ + unsigned long orig_a0; }; #ifdef CONFIG_64BIT diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c index 3303ed2cd419..7dd308129b40 100644 --- a/arch/riscv/kernel/module.c +++ b/arch/riscv/kernel/module.c @@ -21,7 +21,7 @@ static int apply_r_riscv_32_rela(struct module *me, u32 *location, Elf_Addr v) { if (v != (u32)v) { pr_err("%s: value %016llx out of range for 32-bit field\n", - me->name, v); + me->name, (long long)v); return -EINVAL; } *location = v; @@ -102,7 +102,7 @@ static int apply_r_riscv_pcrel_hi20_rela(struct module *me, u32 *location, if (offset != (s32)offset) { pr_err( "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n", - me->name, v, location); + me->name, (long long)v, location); return -EINVAL; } @@ -144,7 +144,7 @@ static int apply_r_riscv_hi20_rela(struct module *me, u32 *location, if (IS_ENABLED(CMODEL_MEDLOW)) { pr_err( "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n", - me->name, v, location); + me->name, (long long)v, location); return -EINVAL; } @@ -188,7 +188,7 @@ static int apply_r_riscv_got_hi20_rela(struct module *me, u32 *location, } else { pr_err( "%s: can not generate the GOT entry for symbol = %016llx from PC = %p\n", - me->name, v, location); + me->name, (long long)v, location); return -EINVAL; } @@ -212,7 +212,7 @@ static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location, } else { pr_err( "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n", - me->name, v, location); + me->name, (long long)v, location); return -EINVAL; } } @@ -234,7 +234,7 @@ static int apply_r_riscv_call_rela(struct module *me, u32 *location, if (offset != fill_v) { pr_err( "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n", - me->name, v, location); + me->name, (long long)v, location); return -EINVAL; } diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile index 5739bd05d289..4e2e600f7d53 100644 --- a/arch/riscv/lib/Makefile +++ b/arch/riscv/lib/Makefile @@ -3,6 +3,6 @@ lib-y += memcpy.o lib-y += memset.o lib-y += uaccess.o -lib-(CONFIG_64BIT) += tishift.o +lib-$(CONFIG_64BIT) += tishift.o lib-$(CONFIG_32BIT) += udivdi3.o diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 0b33577932c3..e21053e5e0da 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -27,7 +27,7 @@ KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-option,-ffreestanding) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,)) UTS_MACHINE := s390x -STACK_SIZE := $(if $(CONFIG_KASAN),32768,16384) +STACK_SIZE := $(if $(CONFIG_KASAN),65536,16384) CHECKFLAGS += -D__s390__ -D__s390x__ export LD_BFD diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile index 593039620487..b1bdd15e3429 100644 --- a/arch/s390/boot/compressed/Makefile +++ b/arch/s390/boot/compressed/Makefile @@ -22,10 +22,10 @@ OBJCOPYFLAGS := OBJECTS := $(addprefix $(obj)/,$(obj-y)) LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup -T -$(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS) +$(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS) FORCE $(call if_changed,ld) -OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info +OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info --set-section-flags .vmlinux.info=load $(obj)/info.bin: vmlinux FORCE $(call if_changed,objcopy) @@ -46,17 +46,17 @@ suffix-$(CONFIG_KERNEL_LZMA) := .lzma suffix-$(CONFIG_KERNEL_LZO) := .lzo suffix-$(CONFIG_KERNEL_XZ) := .xz -$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) FORCE $(call if_changed,gzip) -$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) FORCE $(call if_changed,bzip2) -$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y) FORCE $(call if_changed,lz4) -$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) FORCE $(call if_changed,lzma) -$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) FORCE $(call if_changed,lzo) -$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) FORCE $(call if_changed,xzkern) OBJCOPYFLAGS_piggy.o := -I binary -O elf64-s390 -B s390:64-bit --rename-section .data=.vmlinux.bin.compressed diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 259d1698ac50..c69cb04b7a59 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -64,6 +64,8 @@ CONFIG_NUMA=y CONFIG_PREEMPT=y CONFIG_HZ_100=y CONFIG_KEXEC_FILE=y +CONFIG_EXPOLINE=y +CONFIG_EXPOLINE_AUTO=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y @@ -84,9 +86,11 @@ CONFIG_PCI_DEBUG=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_CHSC_SCH=y +CONFIG_VFIO_AP=m CONFIG_CRASH_DUMP=y CONFIG_BINFMT_MISC=m CONFIG_HIBERNATION=y +CONFIG_PM_DEBUG=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=m @@ -161,8 +165,6 @@ CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_CT_NETLINK=m CONFIG_NF_CT_NETLINK_TIMEOUT=m CONFIG_NF_TABLES=m -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m CONFIG_NFT_CT=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m @@ -365,6 +367,8 @@ CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_CSUM=m CONFIG_DNS_RESOLVER=y CONFIG_OPENVSWITCH=m +CONFIG_VSOCKETS=m +CONFIG_VIRTIO_VSOCKETS=m CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y @@ -461,6 +465,7 @@ CONFIG_PPTP=m CONFIG_PPPOL2TP=m CONFIG_PPP_ASYNC=m CONFIG_PPP_SYNC_TTY=m +CONFIG_ISM=m CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set @@ -486,9 +491,12 @@ CONFIG_MLX4_INFINIBAND=m CONFIG_MLX5_INFINIBAND=m CONFIG_VFIO=m CONFIG_VFIO_PCI=m +CONFIG_VFIO_MDEV=m +CONFIG_VFIO_MDEV_DEVICE=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y +CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -615,7 +623,6 @@ CONFIG_DEBUG_CREDENTIALS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=300 CONFIG_NOTIFIER_ERROR_INJECTION=m -CONFIG_PM_NOTIFIER_ERROR_INJECT=m CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m CONFIG_FAULT_INJECTION=y CONFIG_FAILSLAB=y @@ -727,3 +734,4 @@ CONFIG_APPLDATA_BASE=y CONFIG_KVM=m CONFIG_KVM_S390_UCONTROL=y CONFIG_VHOST_NET=m +CONFIG_VHOST_VSOCK=m diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig index 37fd60c20e22..32f539dc9c19 100644 --- a/arch/s390/configs/performance_defconfig +++ b/arch/s390/configs/performance_defconfig @@ -65,6 +65,8 @@ CONFIG_NR_CPUS=512 CONFIG_NUMA=y CONFIG_HZ_100=y CONFIG_KEXEC_FILE=y +CONFIG_EXPOLINE=y +CONFIG_EXPOLINE_AUTO=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y @@ -82,9 +84,11 @@ CONFIG_PCI=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_CHSC_SCH=y +CONFIG_VFIO_AP=m CONFIG_CRASH_DUMP=y CONFIG_BINFMT_MISC=m CONFIG_HIBERNATION=y +CONFIG_PM_DEBUG=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=m @@ -159,8 +163,6 @@ CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_CT_NETLINK=m CONFIG_NF_CT_NETLINK_TIMEOUT=m CONFIG_NF_TABLES=m -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m CONFIG_NFT_CT=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m @@ -362,6 +364,8 @@ CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_CSUM=m CONFIG_DNS_RESOLVER=y CONFIG_OPENVSWITCH=m +CONFIG_VSOCKETS=m +CONFIG_VIRTIO_VSOCKETS=m CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y @@ -458,6 +462,7 @@ CONFIG_PPTP=m CONFIG_PPPOL2TP=m CONFIG_PPP_ASYNC=m CONFIG_PPP_SYNC_TTY=m +CONFIG_ISM=m CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set @@ -483,9 +488,12 @@ CONFIG_MLX4_INFINIBAND=m CONFIG_MLX5_INFINIBAND=m CONFIG_VFIO=m CONFIG_VFIO_PCI=m +CONFIG_VFIO_MDEV=m +CONFIG_VFIO_MDEV_DEVICE=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y +CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -666,3 +674,4 @@ CONFIG_APPLDATA_BASE=y CONFIG_KVM=m CONFIG_KVM_S390_UCONTROL=y CONFIG_VHOST_NET=m +CONFIG_VHOST_VSOCK=m diff --git a/arch/s390/defconfig b/arch/s390/defconfig index 7cb6a52f727d..4d58a92b5d97 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -26,14 +26,23 @@ CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_PERF=y CONFIG_NAMESPACES=y CONFIG_USER_NS=y +CONFIG_CHECKPOINT_RESTORE=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set -CONFIG_CHECKPOINT_RESTORE=y CONFIG_BPF_SYSCALL=y CONFIG_USERFAULTFD=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y +CONFIG_LIVEPATCH=y +CONFIG_NR_CPUS=256 +CONFIG_NUMA=y +CONFIG_HZ_100=y +CONFIG_KEXEC_FILE=y +CONFIG_CRASH_DUMP=y +CONFIG_HIBERNATION=y +CONFIG_PM_DEBUG=y +CONFIG_CMM=m CONFIG_OPROFILE=y CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y @@ -44,11 +53,7 @@ CONFIG_BLK_DEV_INTEGRITY=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_DEFAULT_DEADLINE=y -CONFIG_LIVEPATCH=y -CONFIG_NR_CPUS=256 -CONFIG_NUMA=y -CONFIG_HZ_100=y -CONFIG_KEXEC_FILE=y +CONFIG_BINFMT_MISC=m CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y @@ -60,9 +65,6 @@ CONFIG_ZBUD=m CONFIG_ZSMALLOC=m CONFIG_ZSMALLOC_STAT=y CONFIG_IDLE_PAGE_TRACKING=y -CONFIG_CRASH_DUMP=y -CONFIG_BINFMT_MISC=m -CONFIG_HIBERNATION=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -98,6 +100,7 @@ CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y CONFIG_VIRTIO_BLK=y CONFIG_SCSI=y +# CONFIG_SCSI_MQ_DEFAULT is not set CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y @@ -131,6 +134,7 @@ CONFIG_EQUALIZER=m CONFIG_TUN=m CONFIG_VIRTIO_NET=y # CONFIG_NET_VENDOR_ALACRITECH is not set +# CONFIG_NET_VENDOR_AURORA is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set @@ -157,33 +161,6 @@ CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_HUGETLBFS=y # CONFIG_NETWORK_FILESYSTEMS is not set -CONFIG_DEBUG_INFO=y -CONFIG_DEBUG_INFO_DWARF4=y -CONFIG_GDB_SCRIPTS=y -CONFIG_UNUSED_SYMBOLS=y -CONFIG_DEBUG_SECTION_MISMATCH=y -CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_DEBUG_PAGEALLOC=y -CONFIG_DETECT_HUNG_TASK=y -CONFIG_PANIC_ON_OOPS=y -CONFIG_PROVE_LOCKING=y -CONFIG_LOCK_STAT=y -CONFIG_DEBUG_LOCKDEP=y -CONFIG_DEBUG_ATOMIC_SLEEP=y -CONFIG_DEBUG_LIST=y -CONFIG_DEBUG_SG=y -CONFIG_DEBUG_NOTIFIERS=y -CONFIG_RCU_CPU_STALL_TIMEOUT=60 -CONFIG_LATENCYTOP=y -CONFIG_SCHED_TRACER=y -CONFIG_FTRACE_SYSCALLS=y -CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y -CONFIG_STACK_TRACER=y -CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_FUNCTION_PROFILER=y -# CONFIG_RUNTIME_TESTING_MENU is not set -CONFIG_S390_PTDUMP=y CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_AUTHENC=m CONFIG_CRYPTO_TEST=m @@ -193,6 +170,7 @@ CONFIG_CRYPTO_CBC=y CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m +CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m CONFIG_CRYPTO_CMAC=m @@ -231,7 +209,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_ZCRYPT=m -CONFIG_ZCRYPT_MULTIDEVNODES=y CONFIG_PKEY=m CONFIG_CRYPTO_PAES_S390=m CONFIG_CRYPTO_SHA1_S390=m @@ -247,4 +224,30 @@ CONFIG_CRC7=m # CONFIG_XZ_DEC_ARM is not set # CONFIG_XZ_DEC_ARMTHUMB is not set # CONFIG_XZ_DEC_SPARC is not set -CONFIG_CMM=m +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF4=y +CONFIG_GDB_SCRIPTS=y +CONFIG_UNUSED_SYMBOLS=y +CONFIG_DEBUG_SECTION_MISMATCH=y +CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_PAGEALLOC=y +CONFIG_DETECT_HUNG_TASK=y +CONFIG_PANIC_ON_OOPS=y +CONFIG_PROVE_LOCKING=y +CONFIG_LOCK_STAT=y +CONFIG_DEBUG_LOCKDEP=y +CONFIG_DEBUG_ATOMIC_SLEEP=y +CONFIG_DEBUG_LIST=y +CONFIG_DEBUG_SG=y +CONFIG_DEBUG_NOTIFIERS=y +CONFIG_RCU_CPU_STALL_TIMEOUT=60 +CONFIG_LATENCYTOP=y +CONFIG_SCHED_TRACER=y +CONFIG_FTRACE_SYSCALLS=y +CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y +CONFIG_STACK_TRACER=y +CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_FUNCTION_PROFILER=y +# CONFIG_RUNTIME_TESTING_MENU is not set +CONFIG_S390_PTDUMP=y diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index dbd689d556ce..ccbb53e22024 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -46,8 +46,6 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.asce_limit = STACK_TOP_MAX; mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | _ASCE_USER_BITS | _ASCE_TYPE_REGION3; - /* pgd_alloc() did not account this pud */ - mm_inc_nr_puds(mm); break; case -PAGE_SIZE: /* forked 5-level task, set new asce with new_mm->pgd */ @@ -63,9 +61,6 @@ static inline int init_new_context(struct task_struct *tsk, /* forked 2-level compat task, set new asce with new mm->pgd */ mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT; - /* pgd_alloc() did not account this pmd */ - mm_inc_nr_pmds(mm); - mm_inc_nr_puds(mm); } crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index f0f9bcf94c03..5ee733720a57 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -36,11 +36,11 @@ static inline void crst_table_init(unsigned long *crst, unsigned long entry) static inline unsigned long pgd_entry_type(struct mm_struct *mm) { - if (mm->context.asce_limit <= _REGION3_SIZE) + if (mm_pmd_folded(mm)) return _SEGMENT_ENTRY_EMPTY; - if (mm->context.asce_limit <= _REGION2_SIZE) + if (mm_pud_folded(mm)) return _REGION3_ENTRY_EMPTY; - if (mm->context.asce_limit <= _REGION1_SIZE) + if (mm_p4d_folded(mm)) return _REGION2_ENTRY_EMPTY; return _REGION1_ENTRY_EMPTY; } diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 411d435e7a7d..063732414dfb 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -493,6 +493,24 @@ static inline int is_module_addr(void *addr) _REGION_ENTRY_PROTECT | \ _REGION_ENTRY_NOEXEC) +static inline bool mm_p4d_folded(struct mm_struct *mm) +{ + return mm->context.asce_limit <= _REGION1_SIZE; +} +#define mm_p4d_folded(mm) mm_p4d_folded(mm) + +static inline bool mm_pud_folded(struct mm_struct *mm) +{ + return mm->context.asce_limit <= _REGION2_SIZE; +} +#define mm_pud_folded(mm) mm_pud_folded(mm) + +static inline bool mm_pmd_folded(struct mm_struct *mm) +{ + return mm->context.asce_limit <= _REGION3_SIZE; +} +#define mm_pmd_folded(mm) mm_pmd_folded(mm) + static inline int mm_has_pgste(struct mm_struct *mm) { #ifdef CONFIG_PGSTE diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index 27248f42a03c..ce4e17c9aad6 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -14,7 +14,7 @@ * General size of kernel stacks */ #ifdef CONFIG_KASAN -#define THREAD_SIZE_ORDER 3 +#define THREAD_SIZE_ORDER 4 #else #define THREAD_SIZE_ORDER 2 #endif diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index 457b7ba0fbb6..b31c779cf581 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -136,7 +136,7 @@ static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, unsigned long address) { - if (tlb->mm->context.asce_limit <= _REGION3_SIZE) + if (mm_pmd_folded(tlb->mm)) return; pgtable_pmd_page_dtor(virt_to_page(pmd)); tlb_remove_table(tlb, pmd); @@ -152,7 +152,7 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, unsigned long address) { - if (tlb->mm->context.asce_limit <= _REGION1_SIZE) + if (mm_p4d_folded(tlb->mm)) return; tlb_remove_table(tlb, p4d); } @@ -167,7 +167,7 @@ static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, unsigned long address) { - if (tlb->mm->context.asce_limit <= _REGION2_SIZE) + if (mm_pud_folded(tlb->mm)) return; tlb_remove_table(tlb, pud); } diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 724fba4d09d2..39191a0feed1 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -236,10 +236,10 @@ ENTRY(__switch_to) stmg %r6,%r15,__SF_GPRS(%r15) # store gprs of prev task lghi %r4,__TASK_stack lghi %r1,__TASK_thread - lg %r5,0(%r4,%r3) # start of kernel stack of next + llill %r5,STACK_INIT stg %r15,__THREAD_ksp(%r1,%r2) # store kernel stack of prev - lgr %r15,%r5 - aghi %r15,STACK_INIT # end of kernel stack of next + lg %r15,0(%r4,%r3) # start of kernel stack of next + agr %r15,%r5 # end of kernel stack of next stg %r3,__LC_CURRENT # store task struct of next stg %r15,__LC_KERNEL_STACK # store end of kernel stack lg %r15,__THREAD_ksp(%r1,%r3) # load kernel stack of next diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index cc085e2d2ce9..74091fd3101e 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -373,7 +373,7 @@ static int __hw_perf_event_init(struct perf_event *event) return -ENOENT; if (ev > PERF_CPUM_CF_MAX_CTR) - return -EINVAL; + return -ENOENT; /* Obtain the counter set to which the specified counter belongs */ set = get_counter_set(ev); diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 7bf604ff50a1..bfabeb1889cc 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1842,10 +1842,30 @@ static void cpumsf_pmu_del(struct perf_event *event, int flags) CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC, PERF_EVENT_CPUM_SF); CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC_DIAG, PERF_EVENT_CPUM_SF_DIAG); -static struct attribute *cpumsf_pmu_events_attr[] = { - CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC), - NULL, - NULL, +/* Attribute list for CPU_SF. + * + * The availablitiy depends on the CPU_MF sampling facility authorization + * for basic + diagnositic samples. This is determined at initialization + * time by the sampling facility device driver. + * If the authorization for basic samples is turned off, it should be + * also turned off for diagnostic sampling. + * + * During initialization of the device driver, check the authorization + * level for diagnostic sampling and installs the attribute + * file for diagnostic sampling if necessary. + * + * For now install a placeholder to reference all possible attributes: + * SF_CYCLES_BASIC and SF_CYCLES_BASIC_DIAG. + * Add another entry for the final NULL pointer. + */ +enum { + SF_CYCLES_BASIC_ATTR_IDX = 0, + SF_CYCLES_BASIC_DIAG_ATTR_IDX, + SF_CYCLES_ATTR_MAX +}; + +static struct attribute *cpumsf_pmu_events_attr[SF_CYCLES_ATTR_MAX + 1] = { + [SF_CYCLES_BASIC_ATTR_IDX] = CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC) }; PMU_FORMAT_ATTR(event, "config:0-63"); @@ -2040,7 +2060,10 @@ static int __init init_cpum_sampling_pmu(void) if (si.ad) { sfb_set_limits(CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB); - cpumsf_pmu_events_attr[1] = + /* Sampling of diagnostic data authorized, + * install event into attribute list of PMU device. + */ + cpumsf_pmu_events_attr[SF_CYCLES_BASIC_DIAG_ATTR_IDX] = CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG); } diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile index eb8aebea3ea7..e76309fbbcb3 100644 --- a/arch/s390/kernel/vdso32/Makefile +++ b/arch/s390/kernel/vdso32/Makefile @@ -37,7 +37,7 @@ KASAN_SANITIZE := n $(obj)/vdso32_wrapper.o : $(obj)/vdso32.so # link rule for the .so file, .lds has to be first -$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) +$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) FORCE $(call if_changed,vdso32ld) # strip rule for the .so file @@ -46,12 +46,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # assembly rules for the .S files -$(obj-vdso32): %.o: %.S +$(obj-vdso32): %.o: %.S FORCE $(call if_changed_dep,vdso32as) # actual build commands quiet_cmd_vdso32ld = VDSO32L $@ - cmd_vdso32ld = $(CC) $(c_flags) -Wl,-T $^ -o $@ + cmd_vdso32ld = $(CC) $(c_flags) -Wl,-T $(filter %.lds %.o,$^) -o $@ quiet_cmd_vdso32as = VDSO32A $@ cmd_vdso32as = $(CC) $(a_flags) -c -o $@ $< diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index a22b2cf86eec..f849ac61c5da 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -37,7 +37,7 @@ KASAN_SANITIZE := n $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so # link rule for the .so file, .lds has to be first -$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) +$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE $(call if_changed,vdso64ld) # strip rule for the .so file @@ -46,12 +46,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # assembly rules for the .S files -$(obj-vdso64): %.o: %.S +$(obj-vdso64): %.o: %.S FORCE $(call if_changed_dep,vdso64as) # actual build commands quiet_cmd_vdso64ld = VDSO64L $@ - cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $^ -o $@ + cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $(filter %.lds %.o,$^) -o $@ quiet_cmd_vdso64as = VDSO64A $@ cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $< diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 21eb7407d51b..8429ab079715 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -154,14 +154,14 @@ SECTIONS * uncompressed image info used by the decompressor * it should match struct vmlinux_info */ - .vmlinux.info 0 : { + .vmlinux.info 0 (INFO) : { QUAD(_stext) /* default_lma */ QUAD(startup_continue) /* entry */ QUAD(__bss_start - _stext) /* image_size */ QUAD(__bss_stop - __bss_start) /* bss_size */ QUAD(__boot_data_start) /* bootdata_off */ QUAD(__boot_data_end - __boot_data_start) /* bootdata_size */ - } + } :NONE /* Debugging sections. */ STABS_DEBUG diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 76d89ee8b428..814f26520aa2 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -101,6 +101,7 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long end) mm->context.asce_limit = _REGION1_SIZE; mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | _ASCE_USER_BITS | _ASCE_TYPE_REGION2; + mm_inc_nr_puds(mm); } else { crst_table_init(table, _REGION1_ENTRY_EMPTY); pgd_populate(mm, (pgd_t *) table, (p4d_t *) pgd); diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c index ae0d9e889534..d31bde0870d8 100644 --- a/arch/s390/numa/numa.c +++ b/arch/s390/numa/numa.c @@ -53,6 +53,7 @@ int __node_distance(int a, int b) { return mode->distance ? mode->distance(a, b) : 0; } +EXPORT_SYMBOL(__node_distance); int numa_debug_enabled; diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 74c002ddc0ce..28c40624bcb6 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1305,6 +1305,7 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req, io_req->fds[0] = dev->cow.fd; else io_req->fds[0] = dev->fd; + io_req->error = 0; if (req_op(req) == REQ_OP_FLUSH) { io_req->op = UBD_FLUSH; @@ -1313,9 +1314,7 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req, io_req->cow_offset = -1; io_req->offset = off; io_req->length = bvec->bv_len; - io_req->error = 0; io_req->sector_mask = 0; - io_req->op = rq_data_dir(req) == READ ? UBD_READ : UBD_WRITE; io_req->offsets[0] = 0; io_req->offsets[1] = dev->cow.data_offset; @@ -1341,11 +1340,14 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req, static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { + struct ubd *ubd_dev = hctx->queue->queuedata; struct request *req = bd->rq; int ret = 0; blk_mq_start_request(req); + spin_lock_irq(&ubd_dev->lock); + if (req_op(req) == REQ_OP_FLUSH) { ret = ubd_queue_one_vec(hctx, req, 0, NULL); } else { @@ -1361,9 +1363,11 @@ static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx, } } out: - if (ret < 0) { + spin_unlock_irq(&ubd_dev->lock); + + if (ret < 0) blk_mq_requeue_request(req, true); - } + return BLK_STS_OK; } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ba7e3464ee92..9d734f3c8234 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -525,7 +525,6 @@ config X86_VSMP bool "ScaleMP vSMP" select HYPERVISOR_GUEST select PARAVIRT - select PARAVIRT_XXL depends on X86_64 && PCI depends on X86_EXTENDED_PLATFORM depends on SMP diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 5b562e464009..88398fdf8129 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -213,8 +213,6 @@ ifdef CONFIG_X86_64 KBUILD_LDFLAGS += $(call ld-option, -z max-page-size=0x200000) endif -# Speed up the build -KBUILD_CFLAGS += -pipe # Workaround for a gcc prelease that unfortunately was shipped in a suse release KBUILD_CFLAGS += -Wno-sign-compare # @@ -239,7 +237,7 @@ archheaders: archmacros: $(Q)$(MAKE) $(build)=arch/x86/kernel arch/x86/kernel/macros.s -ASM_MACRO_FLAGS = -Wa,arch/x86/kernel/macros.s -Wa,- +ASM_MACRO_FLAGS = -Wa,arch/x86/kernel/macros.s export ASM_MACRO_FLAGS KBUILD_CFLAGS += $(ASM_MACRO_FLAGS) diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index e17ab885b1e9..cb46d602a6b8 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -129,8 +129,15 @@ struct intel_uncore_box { struct intel_uncore_extra_reg shared_regs[0]; }; -#define UNCORE_BOX_FLAG_INITIATED 0 -#define UNCORE_BOX_FLAG_CTL_OFFS8 1 /* event config registers are 8-byte apart */ +/* CFL uncore 8th cbox MSRs */ +#define CFL_UNC_CBO_7_PERFEVTSEL0 0xf70 +#define CFL_UNC_CBO_7_PER_CTR0 0xf76 + +#define UNCORE_BOX_FLAG_INITIATED 0 +/* event config registers are 8-byte apart */ +#define UNCORE_BOX_FLAG_CTL_OFFS8 1 +/* CFL 8th CBOX has different MSR space */ +#define UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS 2 struct uncore_event_desc { struct kobj_attribute attr; @@ -297,17 +304,27 @@ unsigned int uncore_freerunning_counter(struct intel_uncore_box *box, static inline unsigned uncore_msr_event_ctl(struct intel_uncore_box *box, int idx) { - return box->pmu->type->event_ctl + - (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) + - uncore_msr_box_offset(box); + if (test_bit(UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS, &box->flags)) { + return CFL_UNC_CBO_7_PERFEVTSEL0 + + (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx); + } else { + return box->pmu->type->event_ctl + + (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) + + uncore_msr_box_offset(box); + } } static inline unsigned uncore_msr_perf_ctr(struct intel_uncore_box *box, int idx) { - return box->pmu->type->perf_ctr + - (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) + - uncore_msr_box_offset(box); + if (test_bit(UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS, &box->flags)) { + return CFL_UNC_CBO_7_PER_CTR0 + + (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx); + } else { + return box->pmu->type->perf_ctr + + (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) + + uncore_msr_box_offset(box); + } } static inline diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 8527c3e1038b..2593b0d7aeee 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -15,6 +15,25 @@ #define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC 0x1910 #define PCI_DEVICE_ID_INTEL_SKL_SD_IMC 0x190f #define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC 0x191f +#define PCI_DEVICE_ID_INTEL_KBL_Y_IMC 0x590c +#define PCI_DEVICE_ID_INTEL_KBL_U_IMC 0x5904 +#define PCI_DEVICE_ID_INTEL_KBL_UQ_IMC 0x5914 +#define PCI_DEVICE_ID_INTEL_KBL_SD_IMC 0x590f +#define PCI_DEVICE_ID_INTEL_KBL_SQ_IMC 0x591f +#define PCI_DEVICE_ID_INTEL_CFL_2U_IMC 0x3ecc +#define PCI_DEVICE_ID_INTEL_CFL_4U_IMC 0x3ed0 +#define PCI_DEVICE_ID_INTEL_CFL_4H_IMC 0x3e10 +#define PCI_DEVICE_ID_INTEL_CFL_6H_IMC 0x3ec4 +#define PCI_DEVICE_ID_INTEL_CFL_2S_D_IMC 0x3e0f +#define PCI_DEVICE_ID_INTEL_CFL_4S_D_IMC 0x3e1f +#define PCI_DEVICE_ID_INTEL_CFL_6S_D_IMC 0x3ec2 +#define PCI_DEVICE_ID_INTEL_CFL_8S_D_IMC 0x3e30 +#define PCI_DEVICE_ID_INTEL_CFL_4S_W_IMC 0x3e18 +#define PCI_DEVICE_ID_INTEL_CFL_6S_W_IMC 0x3ec6 +#define PCI_DEVICE_ID_INTEL_CFL_8S_W_IMC 0x3e31 +#define PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC 0x3e33 +#define PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC 0x3eca +#define PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC 0x3e32 /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -202,6 +221,10 @@ static void skl_uncore_msr_init_box(struct intel_uncore_box *box) wrmsrl(SKL_UNC_PERF_GLOBAL_CTL, SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL); } + + /* The 8th CBOX has different MSR space */ + if (box->pmu->pmu_idx == 7) + __set_bit(UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS, &box->flags); } static void skl_uncore_msr_enable_box(struct intel_uncore_box *box) @@ -228,7 +251,7 @@ static struct intel_uncore_ops skl_uncore_msr_ops = { static struct intel_uncore_type skl_uncore_cbox = { .name = "cbox", .num_counters = 4, - .num_boxes = 5, + .num_boxes = 8, .perf_ctr_bits = 44, .fixed_ctr_bits = 48, .perf_ctr = SNB_UNC_CBO_0_PER_CTR0, @@ -569,7 +592,82 @@ static const struct pci_device_id skl_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SQ_IMC), .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), }, - + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_Y_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_U_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_UQ_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_SD_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_SQ_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_2U_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4U_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4H_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6H_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_2S_D_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_D_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_D_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_D_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_W_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_W_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_W_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, { /* end: all zeroes */ }, }; @@ -618,6 +716,25 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { IMC_DEV(SKL_HQ_IMC, &skl_uncore_pci_driver), /* 6th Gen Core H Quad Core */ IMC_DEV(SKL_SD_IMC, &skl_uncore_pci_driver), /* 6th Gen Core S Dual Core */ IMC_DEV(SKL_SQ_IMC, &skl_uncore_pci_driver), /* 6th Gen Core S Quad Core */ + IMC_DEV(KBL_Y_IMC, &skl_uncore_pci_driver), /* 7th Gen Core Y */ + IMC_DEV(KBL_U_IMC, &skl_uncore_pci_driver), /* 7th Gen Core U */ + IMC_DEV(KBL_UQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core U Quad Core */ + IMC_DEV(KBL_SD_IMC, &skl_uncore_pci_driver), /* 7th Gen Core S Dual Core */ + IMC_DEV(KBL_SQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core S Quad Core */ + IMC_DEV(CFL_2U_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U 2 Cores */ + IMC_DEV(CFL_4U_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U 4 Cores */ + IMC_DEV(CFL_4H_IMC, &skl_uncore_pci_driver), /* 8th Gen Core H 4 Cores */ + IMC_DEV(CFL_6H_IMC, &skl_uncore_pci_driver), /* 8th Gen Core H 6 Cores */ + IMC_DEV(CFL_2S_D_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 2 Cores Desktop */ + IMC_DEV(CFL_4S_D_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 4 Cores Desktop */ + IMC_DEV(CFL_6S_D_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 6 Cores Desktop */ + IMC_DEV(CFL_8S_D_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 8 Cores Desktop */ + IMC_DEV(CFL_4S_W_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 4 Cores Work Station */ + IMC_DEV(CFL_6S_W_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 6 Cores Work Station */ + IMC_DEV(CFL_8S_W_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 8 Cores Work Station */ + IMC_DEV(CFL_4S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 4 Cores Server */ + IMC_DEV(CFL_6S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 6 Cores Server */ + IMC_DEV(CFL_8S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 8 Cores Server */ { /* end marker */ } }; diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 4da9b1c58d28..c1a812bd5a27 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -221,6 +221,8 @@ static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_am int mce_available(struct cpuinfo_x86 *c); bool mce_is_memory_error(struct mce *m); +bool mce_is_correctable(struct mce *m); +int mce_usable_address(struct mce *m); DECLARE_PER_CPU(unsigned, mce_exception_count); DECLARE_PER_CPU(unsigned, mce_poll_count); diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 0d6271cce198..1d0a7778e163 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -232,7 +232,7 @@ static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2) : "cc"); } #endif - return hv_status; + return hv_status; } /* diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index cd0cf1c568b4..8f657286d599 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -33,12 +33,14 @@ /* * Set __PAGE_OFFSET to the most negative possible address + - * PGDIR_SIZE*16 (pgd slot 272). The gap is to allow a space for a - * hypervisor to fit. Choosing 16 slots here is arbitrary, but it's - * what Xen requires. + * PGDIR_SIZE*17 (pgd slot 273). + * + * The gap is to allow a space for LDT remap for PTI (1 pgd slot) and space for + * a hypervisor (16 slots). Choosing 16 slots for a hypervisor is arbitrary, + * but it's what Xen requires. */ -#define __PAGE_OFFSET_BASE_L5 _AC(0xff10000000000000, UL) -#define __PAGE_OFFSET_BASE_L4 _AC(0xffff880000000000, UL) +#define __PAGE_OFFSET_BASE_L5 _AC(0xff11000000000000, UL) +#define __PAGE_OFFSET_BASE_L4 _AC(0xffff888000000000, UL) #ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT #define __PAGE_OFFSET page_offset_base diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 04edd2d58211..84bd9bdc1987 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -111,9 +111,7 @@ extern unsigned int ptrs_per_p4d; */ #define MAXMEM (1UL << MAX_PHYSMEM_BITS) -#define LDT_PGD_ENTRY_L4 -3UL -#define LDT_PGD_ENTRY_L5 -112UL -#define LDT_PGD_ENTRY (pgtable_l5_enabled() ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4) +#define LDT_PGD_ENTRY -240UL #define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT) #define LDT_END_ADDR (LDT_BASE_ADDR + PGDIR_SIZE) diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h index 87623c6b13db..bd5ac6cc37db 100644 --- a/arch/x86/include/asm/qspinlock.h +++ b/arch/x86/include/asm/qspinlock.h @@ -13,12 +13,15 @@ #define queued_fetch_set_pending_acquire queued_fetch_set_pending_acquire static __always_inline u32 queued_fetch_set_pending_acquire(struct qspinlock *lock) { - u32 val = 0; - - if (GEN_BINARY_RMWcc(LOCK_PREFIX "btsl", lock->val.counter, c, - "I", _Q_PENDING_OFFSET)) - val |= _Q_PENDING_VAL; + u32 val; + /* + * We can't use GEN_BINARY_RMWcc() inside an if() stmt because asm goto + * and CONFIG_PROFILE_ALL_BRANCHES=y results in a label inside a + * statement expression, which GCC doesn't like. + */ + val = GEN_BINARY_RMWcc(LOCK_PREFIX "btsl", lock->val.counter, c, + "I", _Q_PENDING_OFFSET) * _Q_PENDING_VAL; val |= atomic_read(&lock->val) & ~_Q_PENDING_MASK; return val; diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 123e669bf363..790ce08e41f2 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -9,7 +9,7 @@ #include <linux/mm.h> #include <linux/device.h> -#include <linux/uaccess.h> +#include <asm/extable.h> #include <asm/page.h> #include <asm/pgtable.h> @@ -93,12 +93,39 @@ clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, */ static inline int xen_safe_write_ulong(unsigned long *addr, unsigned long val) { - return __put_user(val, (unsigned long __user *)addr); + int ret = 0; + + asm volatile("1: mov %[val], %[ptr]\n" + "2:\n" + ".section .fixup, \"ax\"\n" + "3: sub $1, %[ret]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [ret] "+r" (ret), [ptr] "=m" (*addr) + : [val] "r" (val)); + + return ret; } -static inline int xen_safe_read_ulong(unsigned long *addr, unsigned long *val) +static inline int xen_safe_read_ulong(const unsigned long *addr, + unsigned long *val) { - return __get_user(*val, (unsigned long __user *)addr); + int ret = 0; + unsigned long rval = ~0ul; + + asm volatile("1: mov %[ptr], %[rval]\n" + "2:\n" + ".section .fixup, \"ax\"\n" + "3: sub $1, %[ret]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [ret] "+r" (ret), [rval] "+r" (rval) + : [ptr] "m" (*addr)); + *val = rval; + + return ret; } #ifdef CONFIG_XEN_PV diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 8c66d2fc8f81..36d2696c9563 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -485,7 +485,7 @@ static void mce_report_event(struct pt_regs *regs) * be somewhat complicated (e.g. segment offset would require an instruction * parser). So only support physical addresses up to page granuality for now. */ -static int mce_usable_address(struct mce *m) +int mce_usable_address(struct mce *m) { if (!(m->status & MCI_STATUS_ADDRV)) return 0; @@ -505,6 +505,7 @@ static int mce_usable_address(struct mce *m) return 1; } +EXPORT_SYMBOL_GPL(mce_usable_address); bool mce_is_memory_error(struct mce *m) { @@ -534,7 +535,7 @@ bool mce_is_memory_error(struct mce *m) } EXPORT_SYMBOL_GPL(mce_is_memory_error); -static bool mce_is_correctable(struct mce *m) +bool mce_is_correctable(struct mce *m) { if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED) return false; @@ -547,6 +548,7 @@ static bool mce_is_correctable(struct mce *m) return true; } +EXPORT_SYMBOL_GPL(mce_is_correctable); static bool cec_add_mce(struct mce *m) { diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 1c72f3819eb1..e81a2db42df7 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -20,6 +20,7 @@ #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/kexec.h> +#include <linux/i8253.h> #include <asm/processor.h> #include <asm/hypervisor.h> #include <asm/hyperv-tlfs.h> @@ -295,6 +296,16 @@ static void __init ms_hyperv_init_platform(void) if (efi_enabled(EFI_BOOT)) x86_platform.get_nmi_reason = hv_get_nmi_reason; + /* + * Hyper-V VMs have a PIT emulation quirk such that zeroing the + * counter register during PIT shutdown restarts the PIT. So it + * continues to interrupt @18.2 HZ. Setting i8253_clear_counter + * to false tells pit_shutdown() not to zero the counter so that + * the PIT really is shutdown. Generation 2 VMs don't have a PIT, + * and setting this value has no effect. + */ + i8253_clear_counter_on_shutdown = false; + #if IS_ENABLED(CONFIG_HYPERV) /* * Setup the hook to get control post apic initialization. diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index d9ab49bed8af..0eda91f8eeac 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -77,7 +77,7 @@ static __init int setup_vmw_sched_clock(char *s) } early_param("no-vmw-sched-clock", setup_vmw_sched_clock); -static unsigned long long vmware_sched_clock(void) +static unsigned long long notrace vmware_sched_clock(void) { unsigned long long ns; diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index ab18e0884dc6..6135ae8ce036 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -199,14 +199,6 @@ static void sanity_check_ldt_mapping(struct mm_struct *mm) /* * If PTI is enabled, this maps the LDT into the kernelmode and * usermode tables for the given mm. - * - * There is no corresponding unmap function. Even if the LDT is freed, we - * leave the PTEs around until the slot is reused or the mm is destroyed. - * This is harmless: the LDT is always in ordinary memory, and no one will - * access the freed slot. - * - * If we wanted to unmap freed LDTs, we'd also need to do a flush to make - * it useful, and the flush would slow down modify_ldt(). */ static int map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) @@ -214,8 +206,7 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) unsigned long va; bool is_vmalloc; spinlock_t *ptl; - pgd_t *pgd; - int i; + int i, nr_pages; if (!static_cpu_has(X86_FEATURE_PTI)) return 0; @@ -229,16 +220,11 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) /* Check if the current mappings are sane */ sanity_check_ldt_mapping(mm); - /* - * Did we already have the top level entry allocated? We can't - * use pgd_none() for this because it doens't do anything on - * 4-level page table kernels. - */ - pgd = pgd_offset(mm, LDT_BASE_ADDR); - is_vmalloc = is_vmalloc_addr(ldt->entries); - for (i = 0; i * PAGE_SIZE < ldt->nr_entries * LDT_ENTRY_SIZE; i++) { + nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE); + + for (i = 0; i < nr_pages; i++) { unsigned long offset = i << PAGE_SHIFT; const void *src = (char *)ldt->entries + offset; unsigned long pfn; @@ -272,13 +258,39 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) /* Propagate LDT mapping to the user page-table */ map_ldt_struct_to_user(mm); - va = (unsigned long)ldt_slot_va(slot); - flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, PAGE_SHIFT, false); - ldt->slot = slot; return 0; } +static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt) +{ + unsigned long va; + int i, nr_pages; + + if (!ldt) + return; + + /* LDT map/unmap is only required for PTI */ + if (!static_cpu_has(X86_FEATURE_PTI)) + return; + + nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE); + + for (i = 0; i < nr_pages; i++) { + unsigned long offset = i << PAGE_SHIFT; + spinlock_t *ptl; + pte_t *ptep; + + va = (unsigned long)ldt_slot_va(ldt->slot) + offset; + ptep = get_locked_pte(mm, va, &ptl); + pte_clear(mm, va, ptep); + pte_unmap_unlock(ptep, ptl); + } + + va = (unsigned long)ldt_slot_va(ldt->slot); + flush_tlb_mm_range(mm, va, va + nr_pages * PAGE_SIZE, PAGE_SHIFT, false); +} + #else /* !CONFIG_PAGE_TABLE_ISOLATION */ static int @@ -286,6 +298,10 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) { return 0; } + +static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt) +{ +} #endif /* CONFIG_PAGE_TABLE_ISOLATION */ static void free_ldt_pgtables(struct mm_struct *mm) @@ -524,6 +540,7 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) } install_ldt(mm, new_ldt); + unmap_ldt_struct(mm, old_ldt); free_ldt_struct(old_ldt); error = 0; diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index 1eae5af491c2..891a75dbc131 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -26,65 +26,8 @@ #define TOPOLOGY_REGISTER_OFFSET 0x10 -#if defined CONFIG_PCI && defined CONFIG_PARAVIRT_XXL -/* - * Interrupt control on vSMPowered systems: - * ~AC is a shadow of IF. If IF is 'on' AC should be 'off' - * and vice versa. - */ - -asmlinkage __visible unsigned long vsmp_save_fl(void) -{ - unsigned long flags = native_save_fl(); - - if (!(flags & X86_EFLAGS_IF) || (flags & X86_EFLAGS_AC)) - flags &= ~X86_EFLAGS_IF; - return flags; -} -PV_CALLEE_SAVE_REGS_THUNK(vsmp_save_fl); - -__visible void vsmp_restore_fl(unsigned long flags) -{ - if (flags & X86_EFLAGS_IF) - flags &= ~X86_EFLAGS_AC; - else - flags |= X86_EFLAGS_AC; - native_restore_fl(flags); -} -PV_CALLEE_SAVE_REGS_THUNK(vsmp_restore_fl); - -asmlinkage __visible void vsmp_irq_disable(void) -{ - unsigned long flags = native_save_fl(); - - native_restore_fl((flags & ~X86_EFLAGS_IF) | X86_EFLAGS_AC); -} -PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_disable); - -asmlinkage __visible void vsmp_irq_enable(void) -{ - unsigned long flags = native_save_fl(); - - native_restore_fl((flags | X86_EFLAGS_IF) & (~X86_EFLAGS_AC)); -} -PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_enable); - -static unsigned __init vsmp_patch(u8 type, void *ibuf, - unsigned long addr, unsigned len) -{ - switch (type) { - case PARAVIRT_PATCH(irq.irq_enable): - case PARAVIRT_PATCH(irq.irq_disable): - case PARAVIRT_PATCH(irq.save_fl): - case PARAVIRT_PATCH(irq.restore_fl): - return paravirt_patch_default(type, ibuf, addr, len); - default: - return native_patch(type, ibuf, addr, len); - } - -} - -static void __init set_vsmp_pv_ops(void) +#ifdef CONFIG_PCI +static void __init set_vsmp_ctl(void) { void __iomem *address; unsigned int cap, ctl, cfg; @@ -109,28 +52,12 @@ static void __init set_vsmp_pv_ops(void) } #endif - if (cap & ctl & (1 << 4)) { - /* Setup irq ops and turn on vSMP IRQ fastpath handling */ - pv_ops.irq.irq_disable = PV_CALLEE_SAVE(vsmp_irq_disable); - pv_ops.irq.irq_enable = PV_CALLEE_SAVE(vsmp_irq_enable); - pv_ops.irq.save_fl = PV_CALLEE_SAVE(vsmp_save_fl); - pv_ops.irq.restore_fl = PV_CALLEE_SAVE(vsmp_restore_fl); - pv_ops.init.patch = vsmp_patch; - ctl &= ~(1 << 4); - } writel(ctl, address + 4); ctl = readl(address + 4); pr_info("vSMP CTL: control set to:0x%08x\n", ctl); early_iounmap(address, 8); } -#else -static void __init set_vsmp_pv_ops(void) -{ -} -#endif - -#ifdef CONFIG_PCI static int is_vsmp = -1; static void __init detect_vsmp_box(void) @@ -164,11 +91,14 @@ static int is_vsmp_box(void) { return 0; } +static void __init set_vsmp_ctl(void) +{ +} #endif static void __init vsmp_cap_cpus(void) { -#if !defined(CONFIG_X86_VSMP) && defined(CONFIG_SMP) +#if !defined(CONFIG_X86_VSMP) && defined(CONFIG_SMP) && defined(CONFIG_PCI) void __iomem *address; unsigned int cfg, topology, node_shift, maxcpus; @@ -221,6 +151,6 @@ void __init vsmp_init(void) vsmp_cap_cpus(); - set_vsmp_pv_ops(); + set_vsmp_ctl(); return; } diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 0d7b3ae4960b..a5d7ed125337 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1905,7 +1905,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) init_top_pgt[0] = __pgd(0); /* Pre-constructed entries are in pfn, so convert to mfn */ - /* L4[272] -> level3_ident_pgt */ + /* L4[273] -> level3_ident_pgt */ /* L4[511] -> level3_kernel_pgt */ convert_pfn_mfn(init_top_pgt); @@ -1925,8 +1925,8 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) addr[0] = (unsigned long)pgd; addr[1] = (unsigned long)l3; addr[2] = (unsigned long)l2; - /* Graft it onto L4[272][0]. Note that we creating an aliasing problem: - * Both L4[272][0] and L4[511][510] have entries that point to the same + /* Graft it onto L4[273][0]. Note that we creating an aliasing problem: + * Both L4[273][0] and L4[511][510] have entries that point to the same * L2 (PMD) tables. Meaning that if you modify it in __va space * it will be also modified in the __ka space! (But if you just * modify the PMD table to point to other PTE's or none, then you diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index b06731705529..055e37e43541 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -656,8 +656,7 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) /* * The interface requires atomic updates on p2m elements. - * xen_safe_write_ulong() is using __put_user which does an atomic - * store via asm(). + * xen_safe_write_ulong() is using an atomic store via asm(). */ if (likely(!xen_safe_write_ulong(xen_p2m_addr + pfn, mfn))) return true; diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 441c88262169..1c8a8816a402 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -9,6 +9,7 @@ #include <linux/log2.h> #include <linux/gfp.h> #include <linux/slab.h> +#include <linux/atomic.h> #include <asm/paravirt.h> #include <asm/qspinlock.h> @@ -21,6 +22,7 @@ static DEFINE_PER_CPU(int, lock_kicker_irq) = -1; static DEFINE_PER_CPU(char *, irq_name); +static DEFINE_PER_CPU(atomic_t, xen_qlock_wait_nest); static bool xen_pvspin = true; static void xen_qlock_kick(int cpu) @@ -39,25 +41,25 @@ static void xen_qlock_kick(int cpu) */ static void xen_qlock_wait(u8 *byte, u8 val) { - unsigned long flags; int irq = __this_cpu_read(lock_kicker_irq); + atomic_t *nest_cnt = this_cpu_ptr(&xen_qlock_wait_nest); /* If kicker interrupts not initialized yet, just spin */ if (irq == -1 || in_nmi()) return; - /* Guard against reentry. */ - local_irq_save(flags); + /* Detect reentry. */ + atomic_inc(nest_cnt); - /* If irq pending already clear it. */ - if (xen_test_irq_pending(irq)) { + /* If irq pending already and no nested call clear it. */ + if (atomic_read(nest_cnt) == 1 && xen_test_irq_pending(irq)) { xen_clear_irq_pending(irq); } else if (READ_ONCE(*byte) == val) { /* Block until irq becomes pending (or a spurious wakeup) */ xen_poll_irq(irq); } - local_irq_restore(flags); + atomic_dec(nest_cnt); } static irqreturn_t dummy_handler(int irq, void *dev_id) diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index be9bfd9aa865..34a23016dd14 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -23,7 +23,11 @@ # error Linux requires the Xtensa Windowed Registers Option. #endif -#define ARCH_SLAB_MINALIGN XCHAL_DATA_WIDTH +/* Xtensa ABI requires stack alignment to be at least 16 */ + +#define STACK_ALIGN (XCHAL_DATA_WIDTH > 16 ? XCHAL_DATA_WIDTH : 16) + +#define ARCH_SLAB_MINALIGN STACK_ALIGN /* * User space process size: 1 GB. diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S index 2f76118ecf62..9053a5622d2c 100644 --- a/arch/xtensa/kernel/head.S +++ b/arch/xtensa/kernel/head.S @@ -88,9 +88,12 @@ _SetupMMU: initialize_mmu #if defined(CONFIG_MMU) && XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY rsr a2, excsave1 - movi a3, 0x08000000 + movi a3, XCHAL_KSEG_PADDR + bltu a2, a3, 1f + sub a2, a2, a3 + movi a3, XCHAL_KSEG_SIZE bgeu a2, a3, 1f - movi a3, 0xd0000000 + movi a3, XCHAL_KSEG_CACHED_VADDR add a2, a2, a3 wsr a2, excsave1 1: diff --git a/block/bio.c b/block/bio.c index d5368a445561..4f4d9884443b 100644 --- a/block/bio.c +++ b/block/bio.c @@ -605,6 +605,7 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src) if (bio_flagged(bio_src, BIO_THROTTLED)) bio_set_flag(bio, BIO_THROTTLED); bio->bi_opf = bio_src->bi_opf; + bio->bi_ioprio = bio_src->bi_ioprio; bio->bi_write_hint = bio_src->bi_write_hint; bio->bi_iter = bio_src->bi_iter; bio->bi_io_vec = bio_src->bi_io_vec; @@ -1260,6 +1261,7 @@ struct bio *bio_copy_user_iov(struct request_queue *q, if (ret) goto cleanup; } else { + zero_fill_bio(bio); iov_iter_advance(iter, bio->bi_iter.bi_size); } diff --git a/block/blk-core.c b/block/blk-core.c index 0b684a520a11..d6e8ab9ca99d 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -352,9 +352,8 @@ void blk_cleanup_queue(struct request_queue *q) * dispatch may still be in-progress since we dispatch requests * from more than one contexts. * - * No need to quiesce queue if it isn't initialized yet since - * blk_freeze_queue() should be enough for cases of passthrough - * request. + * We rely on driver to deal with the race in case that queue + * initialization isn't done. */ if (queue_is_mq(q) && blk_queue_init_done(q)) blk_mq_quiesce_queue(q); diff --git a/block/blk-lib.c b/block/blk-lib.c index 76f867ea9a9b..5f2c429d4378 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -51,16 +51,14 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, if ((sector | nr_sects) & bs_mask) return -EINVAL; - while (nr_sects) { - unsigned int req_sects = nr_sects; - sector_t end_sect; + if (!nr_sects) + return -EINVAL; - if (!req_sects) - goto fail; - if (req_sects > UINT_MAX >> 9) - req_sects = UINT_MAX >> 9; + while (nr_sects) { + sector_t req_sects = min_t(sector_t, nr_sects, + bio_allowed_max_sectors(q)); - end_sect = sector + req_sects; + WARN_ON_ONCE((req_sects << 9) > UINT_MAX); bio = blk_next_bio(bio, 0, gfp_mask); bio->bi_iter.bi_sector = sector; @@ -68,8 +66,8 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, bio_set_op_attrs(bio, op, 0); bio->bi_iter.bi_size = req_sects << 9; + sector += req_sects; nr_sects -= req_sects; - sector = end_sect; /* * We can loop for a long time in here, if someone does @@ -82,14 +80,6 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, *biop = bio; return 0; - -fail: - if (bio) { - submit_bio_wait(bio); - bio_put(bio); - } - *biop = NULL; - return -EOPNOTSUPP; } EXPORT_SYMBOL(__blkdev_issue_discard); @@ -161,7 +151,7 @@ static int __blkdev_issue_write_same(struct block_device *bdev, sector_t sector, return -EOPNOTSUPP; /* Ensure that max_write_same_sectors doesn't overflow bi_size */ - max_write_same_sectors = UINT_MAX >> 9; + max_write_same_sectors = bio_allowed_max_sectors(q); while (nr_sects) { bio = blk_next_bio(bio, 1, gfp_mask); diff --git a/block/blk-merge.c b/block/blk-merge.c index da0217f321c4..b1df622cbd85 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -46,7 +46,7 @@ static inline bool bio_will_gap(struct request_queue *q, bio_get_first_bvec(prev_rq->bio, &pb); else bio_get_first_bvec(prev, &pb); - if (pb.bv_offset) + if (pb.bv_offset & queue_virt_boundary(q)) return true; /* @@ -90,7 +90,8 @@ static struct bio *blk_bio_discard_split(struct request_queue *q, /* Zero-sector (unknown) and one-sector granularities are the same. */ granularity = max(q->limits.discard_granularity >> 9, 1U); - max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9); + max_discard_sectors = min(q->limits.max_discard_sectors, + bio_allowed_max_sectors(q)); max_discard_sectors -= max_discard_sectors % granularity; if (unlikely(!max_discard_sectors)) { diff --git a/block/blk.h b/block/blk.h index 027a0ccc175e..816a9abb87cd 100644 --- a/block/blk.h +++ b/block/blk.h @@ -85,7 +85,7 @@ static inline bool biovec_phys_mergeable(struct request_queue *q, static inline bool __bvec_gap_to_prev(struct request_queue *q, struct bio_vec *bprv, unsigned int offset) { - return offset || + return (offset & queue_virt_boundary(q)) || ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); } @@ -234,6 +234,16 @@ static inline void req_set_nomerge(struct request_queue *q, struct request *req) } /* + * The max size one bio can handle is UINT_MAX becasue bvec_iter.bi_size + * is defined as 'unsigned int', meantime it has to aligned to with logical + * block size which is the minimum accepted unit by hardware. + */ +static inline unsigned int bio_allowed_max_sectors(struct request_queue *q) +{ + return round_down(UINT_MAX, queue_logical_block_size(q)) >> 9; +} + +/* * Internal io_context interface */ void get_io_context(struct io_context *ioc); diff --git a/block/bounce.c b/block/bounce.c index 36869afc258c..559c55bda040 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -248,6 +248,7 @@ static struct bio *bounce_clone_bio(struct bio *bio_src, gfp_t gfp_mask, return NULL; bio->bi_disk = bio_src->bi_disk; bio->bi_opf = bio_src->bi_opf; + bio->bi_ioprio = bio_src->bi_ioprio; bio->bi_write_hint = bio_src->bi_write_hint; bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; diff --git a/crypto/crypto_user_base.c b/crypto/crypto_user_base.c index e41f6cc33fff..784748dbb19f 100644 --- a/crypto/crypto_user_base.c +++ b/crypto/crypto_user_base.c @@ -84,7 +84,7 @@ static int crypto_report_cipher(struct sk_buff *skb, struct crypto_alg *alg) { struct crypto_report_cipher rcipher; - strlcpy(rcipher.type, "cipher", sizeof(rcipher.type)); + strncpy(rcipher.type, "cipher", sizeof(rcipher.type)); rcipher.blocksize = alg->cra_blocksize; rcipher.min_keysize = alg->cra_cipher.cia_min_keysize; @@ -103,7 +103,7 @@ static int crypto_report_comp(struct sk_buff *skb, struct crypto_alg *alg) { struct crypto_report_comp rcomp; - strlcpy(rcomp.type, "compression", sizeof(rcomp.type)); + strncpy(rcomp.type, "compression", sizeof(rcomp.type)); if (nla_put(skb, CRYPTOCFGA_REPORT_COMPRESS, sizeof(struct crypto_report_comp), &rcomp)) goto nla_put_failure; @@ -117,7 +117,7 @@ static int crypto_report_acomp(struct sk_buff *skb, struct crypto_alg *alg) { struct crypto_report_acomp racomp; - strlcpy(racomp.type, "acomp", sizeof(racomp.type)); + strncpy(racomp.type, "acomp", sizeof(racomp.type)); if (nla_put(skb, CRYPTOCFGA_REPORT_ACOMP, sizeof(struct crypto_report_acomp), &racomp)) @@ -132,7 +132,7 @@ static int crypto_report_akcipher(struct sk_buff *skb, struct crypto_alg *alg) { struct crypto_report_akcipher rakcipher; - strlcpy(rakcipher.type, "akcipher", sizeof(rakcipher.type)); + strncpy(rakcipher.type, "akcipher", sizeof(rakcipher.type)); if (nla_put(skb, CRYPTOCFGA_REPORT_AKCIPHER, sizeof(struct crypto_report_akcipher), &rakcipher)) @@ -147,7 +147,7 @@ static int crypto_report_kpp(struct sk_buff *skb, struct crypto_alg *alg) { struct crypto_report_kpp rkpp; - strlcpy(rkpp.type, "kpp", sizeof(rkpp.type)); + strncpy(rkpp.type, "kpp", sizeof(rkpp.type)); if (nla_put(skb, CRYPTOCFGA_REPORT_KPP, sizeof(struct crypto_report_kpp), &rkpp)) @@ -161,10 +161,10 @@ nla_put_failure: static int crypto_report_one(struct crypto_alg *alg, struct crypto_user_alg *ualg, struct sk_buff *skb) { - strlcpy(ualg->cru_name, alg->cra_name, sizeof(ualg->cru_name)); - strlcpy(ualg->cru_driver_name, alg->cra_driver_name, + strncpy(ualg->cru_name, alg->cra_name, sizeof(ualg->cru_name)); + strncpy(ualg->cru_driver_name, alg->cra_driver_name, sizeof(ualg->cru_driver_name)); - strlcpy(ualg->cru_module_name, module_name(alg->cra_module), + strncpy(ualg->cru_module_name, module_name(alg->cra_module), sizeof(ualg->cru_module_name)); ualg->cru_type = 0; @@ -177,7 +177,7 @@ static int crypto_report_one(struct crypto_alg *alg, if (alg->cra_flags & CRYPTO_ALG_LARVAL) { struct crypto_report_larval rl; - strlcpy(rl.type, "larval", sizeof(rl.type)); + strncpy(rl.type, "larval", sizeof(rl.type)); if (nla_put(skb, CRYPTOCFGA_REPORT_LARVAL, sizeof(struct crypto_report_larval), &rl)) goto nla_put_failure; diff --git a/crypto/crypto_user_stat.c b/crypto/crypto_user_stat.c index 021ad06bbb62..1dfaa0ccd555 100644 --- a/crypto/crypto_user_stat.c +++ b/crypto/crypto_user_stat.c @@ -37,6 +37,8 @@ static int crypto_report_aead(struct sk_buff *skb, struct crypto_alg *alg) u64 v64; u32 v32; + memset(&raead, 0, sizeof(raead)); + strncpy(raead.type, "aead", sizeof(raead.type)); v32 = atomic_read(&alg->encrypt_cnt); @@ -65,6 +67,8 @@ static int crypto_report_cipher(struct sk_buff *skb, struct crypto_alg *alg) u64 v64; u32 v32; + memset(&rcipher, 0, sizeof(rcipher)); + strlcpy(rcipher.type, "cipher", sizeof(rcipher.type)); v32 = atomic_read(&alg->encrypt_cnt); @@ -93,6 +97,8 @@ static int crypto_report_comp(struct sk_buff *skb, struct crypto_alg *alg) u64 v64; u32 v32; + memset(&rcomp, 0, sizeof(rcomp)); + strlcpy(rcomp.type, "compression", sizeof(rcomp.type)); v32 = atomic_read(&alg->compress_cnt); rcomp.stat_compress_cnt = v32; @@ -120,6 +126,8 @@ static int crypto_report_acomp(struct sk_buff *skb, struct crypto_alg *alg) u64 v64; u32 v32; + memset(&racomp, 0, sizeof(racomp)); + strlcpy(racomp.type, "acomp", sizeof(racomp.type)); v32 = atomic_read(&alg->compress_cnt); racomp.stat_compress_cnt = v32; @@ -147,6 +155,8 @@ static int crypto_report_akcipher(struct sk_buff *skb, struct crypto_alg *alg) u64 v64; u32 v32; + memset(&rakcipher, 0, sizeof(rakcipher)); + strncpy(rakcipher.type, "akcipher", sizeof(rakcipher.type)); v32 = atomic_read(&alg->encrypt_cnt); rakcipher.stat_encrypt_cnt = v32; @@ -177,6 +187,8 @@ static int crypto_report_kpp(struct sk_buff *skb, struct crypto_alg *alg) struct crypto_stat rkpp; u32 v; + memset(&rkpp, 0, sizeof(rkpp)); + strlcpy(rkpp.type, "kpp", sizeof(rkpp.type)); v = atomic_read(&alg->setsecret_cnt); @@ -203,6 +215,8 @@ static int crypto_report_ahash(struct sk_buff *skb, struct crypto_alg *alg) u64 v64; u32 v32; + memset(&rhash, 0, sizeof(rhash)); + strncpy(rhash.type, "ahash", sizeof(rhash.type)); v32 = atomic_read(&alg->hash_cnt); @@ -227,6 +241,8 @@ static int crypto_report_shash(struct sk_buff *skb, struct crypto_alg *alg) u64 v64; u32 v32; + memset(&rhash, 0, sizeof(rhash)); + strncpy(rhash.type, "shash", sizeof(rhash.type)); v32 = atomic_read(&alg->hash_cnt); @@ -251,6 +267,8 @@ static int crypto_report_rng(struct sk_buff *skb, struct crypto_alg *alg) u64 v64; u32 v32; + memset(&rrng, 0, sizeof(rrng)); + strncpy(rrng.type, "rng", sizeof(rrng.type)); v32 = atomic_read(&alg->generate_cnt); @@ -275,6 +293,8 @@ static int crypto_reportstat_one(struct crypto_alg *alg, struct crypto_user_alg *ualg, struct sk_buff *skb) { + memset(ualg, 0, sizeof(*ualg)); + strlcpy(ualg->cru_name, alg->cra_name, sizeof(ualg->cru_name)); strlcpy(ualg->cru_driver_name, alg->cra_driver_name, sizeof(ualg->cru_driver_name)); @@ -291,6 +311,7 @@ static int crypto_reportstat_one(struct crypto_alg *alg, if (alg->cra_flags & CRYPTO_ALG_LARVAL) { struct crypto_stat rl; + memset(&rl, 0, sizeof(rl)); strlcpy(rl.type, "larval", sizeof(rl.type)); if (nla_put(skb, CRYPTOCFGA_STAT_LARVAL, sizeof(struct crypto_stat), &rl)) diff --git a/crypto/simd.c b/crypto/simd.c index ea7240be3001..78e8d037ae2b 100644 --- a/crypto/simd.c +++ b/crypto/simd.c @@ -124,8 +124,9 @@ static int simd_skcipher_init(struct crypto_skcipher *tfm) ctx->cryptd_tfm = cryptd_tfm; - reqsize = sizeof(struct skcipher_request); - reqsize += crypto_skcipher_reqsize(&cryptd_tfm->base); + reqsize = crypto_skcipher_reqsize(cryptd_skcipher_child(cryptd_tfm)); + reqsize = max(reqsize, crypto_skcipher_reqsize(&cryptd_tfm->base)); + reqsize += sizeof(struct skcipher_request); crypto_skcipher_set_reqsize(tfm, reqsize); diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index 8f3a444c6ea9..7cea769c37df 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -512,7 +512,7 @@ config CRC_PMIC_OPREGION config XPOWER_PMIC_OPREGION bool "ACPI operation region support for XPower AXP288 PMIC" - depends on MFD_AXP20X_I2C && IOSF_MBI + depends on MFD_AXP20X_I2C && IOSF_MBI=y help This config adds ACPI operation region support for XPower AXP288 PMIC. diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index f8c638f3c946..14d9f5bea015 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -2928,9 +2928,9 @@ static int acpi_nfit_query_poison(struct acpi_nfit_desc *acpi_desc) return rc; if (ars_status_process_records(acpi_desc)) - return -ENOMEM; + dev_err(acpi_desc->dev, "Failed to process ARS records\n"); - return 0; + return rc; } static int ars_register(struct acpi_nfit_desc *acpi_desc, @@ -3341,8 +3341,6 @@ static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, unsigned int cmd) { struct acpi_nfit_desc *acpi_desc = to_acpi_nfit_desc(nd_desc); - struct nfit_spa *nfit_spa; - int rc = 0; if (nvdimm) return 0; @@ -3355,17 +3353,10 @@ static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc, * just needs guarantees that any ARS it initiates are not * interrupted by any intervening start requests from userspace. */ - mutex_lock(&acpi_desc->init_mutex); - list_for_each_entry(nfit_spa, &acpi_desc->spas, list) - if (acpi_desc->scrub_spa - || test_bit(ARS_REQ_SHORT, &nfit_spa->ars_state) - || test_bit(ARS_REQ_LONG, &nfit_spa->ars_state)) { - rc = -EBUSY; - break; - } - mutex_unlock(&acpi_desc->init_mutex); + if (work_busy(&acpi_desc->dwork.work)) + return -EBUSY; - return rc; + return 0; } int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc, diff --git a/drivers/acpi/nfit/mce.c b/drivers/acpi/nfit/mce.c index e9626bf6ca29..d6c1b10f6c25 100644 --- a/drivers/acpi/nfit/mce.c +++ b/drivers/acpi/nfit/mce.c @@ -25,8 +25,12 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val, struct acpi_nfit_desc *acpi_desc; struct nfit_spa *nfit_spa; - /* We only care about memory errors */ - if (!mce_is_memory_error(mce)) + /* We only care about uncorrectable memory errors */ + if (!mce_is_memory_error(mce) || mce_is_correctable(mce)) + return NOTIFY_DONE; + + /* Verify the address reported in the MCE is valid. */ + if (!mce_usable_address(mce)) return NOTIFY_DONE; /* diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 6e594644cb1d..a7f5202a4815 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4553,7 +4553,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { /* These specific Samsung models/firmware-revs do not handle LPM well */ { "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_HORKAGE_NOLPM, }, { "SAMSUNG SSD PM830 mSATA *", "CXM13D1Q", ATA_HORKAGE_NOLPM, }, - { "SAMSUNG MZ7TD256HAFV-000L9", "DXT02L5Q", ATA_HORKAGE_NOLPM, }, + { "SAMSUNG MZ7TD256HAFV-000L9", NULL, ATA_HORKAGE_NOLPM, }, /* devices that don't properly handle queued TRIM commands */ { "Micron_M500IT_*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c index 10ecb232245d..4b1ff5bc256a 100644 --- a/drivers/ata/sata_rcar.c +++ b/drivers/ata/sata_rcar.c @@ -1,14 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * Renesas R-Car SATA driver * * Author: Vladimir Barinov <source@cogentembedded.com> * Copyright (C) 2013-2015 Cogent Embedded, Inc. * Copyright (C) 2013-2015 Renesas Solutions Corp. - * - * 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. */ #include <linux/kernel.h> diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index cad339ec9c19..6f2856c6d0f2 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -4142,10 +4142,11 @@ static int __floppy_read_block_0(struct block_device *bdev, int drive) bio.bi_end_io = floppy_rb0_cb; bio_set_op_attrs(&bio, REQ_OP_READ, 0); + init_completion(&cbdata.complete); + submit_bio(&bio); process_fd_request(); - init_completion(&cbdata.complete); wait_for_completion(&cbdata.complete); __free_page(page); diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 56452cabce5b..0ed4b200fa58 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1919,6 +1919,7 @@ static int negotiate_mq(struct blkfront_info *info) GFP_KERNEL); if (!info->rinfo) { xenbus_dev_fatal(info->xbdev, -ENOMEM, "allocating ring_info structure"); + info->nr_rings = 0; return -ENOMEM; } diff --git a/drivers/clk/clk-fixed-factor.c b/drivers/clk/clk-fixed-factor.c index ef0ca9414f37..ff83e899df71 100644 --- a/drivers/clk/clk-fixed-factor.c +++ b/drivers/clk/clk-fixed-factor.c @@ -210,6 +210,7 @@ static int of_fixed_factor_clk_remove(struct platform_device *pdev) { struct clk *clk = platform_get_drvdata(pdev); + of_clk_del_provider(pdev->dev.of_node); clk_unregister_fixed_factor(clk); return 0; diff --git a/drivers/clk/meson/axg.c b/drivers/clk/meson/axg.c index c981159b02c0..792735d7e46e 100644 --- a/drivers/clk/meson/axg.c +++ b/drivers/clk/meson/axg.c @@ -325,6 +325,7 @@ static struct clk_regmap axg_fclk_div2 = { .ops = &clk_regmap_gate_ops, .parent_names = (const char *[]){ "fclk_div2_div" }, .num_parents = 1, + .flags = CLK_IS_CRITICAL, }, }; @@ -349,6 +350,18 @@ static struct clk_regmap axg_fclk_div3 = { .ops = &clk_regmap_gate_ops, .parent_names = (const char *[]){ "fclk_div3_div" }, .num_parents = 1, + /* + * FIXME: + * This clock, as fdiv2, is used by the SCPI FW and is required + * by the platform to operate correctly. + * Until the following condition are met, we need this clock to + * be marked as critical: + * a) The SCPI generic driver claims and enable all the clocks + * it needs + * b) CCF has a clock hand-off mechanism to make the sure the + * clock stays on until the proper driver comes along + */ + .flags = CLK_IS_CRITICAL, }, }; diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c index 9309cfaaa464..4ada9668fd49 100644 --- a/drivers/clk/meson/gxbb.c +++ b/drivers/clk/meson/gxbb.c @@ -506,6 +506,18 @@ static struct clk_regmap gxbb_fclk_div3 = { .ops = &clk_regmap_gate_ops, .parent_names = (const char *[]){ "fclk_div3_div" }, .num_parents = 1, + /* + * FIXME: + * This clock, as fdiv2, is used by the SCPI FW and is required + * by the platform to operate correctly. + * Until the following condition are met, we need this clock to + * be marked as critical: + * a) The SCPI generic driver claims and enable all the clocks + * it needs + * b) CCF has a clock hand-off mechanism to make the sure the + * clock stays on until the proper driver comes along + */ + .flags = CLK_IS_CRITICAL, }, }; diff --git a/drivers/clk/qcom/gcc-qcs404.c b/drivers/clk/qcom/gcc-qcs404.c index e4ca6a45f313..ef1b267cb058 100644 --- a/drivers/clk/qcom/gcc-qcs404.c +++ b/drivers/clk/qcom/gcc-qcs404.c @@ -265,7 +265,7 @@ static struct clk_fixed_factor cxo = { .div = 1, .hw.init = &(struct clk_init_data){ .name = "cxo", - .parent_names = (const char *[]){ "xo_board" }, + .parent_names = (const char *[]){ "xo-board" }, .num_parents = 1, .ops = &clk_fixed_factor_ops, }, diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c index 9c38895542f4..d4350bb10b83 100644 --- a/drivers/clocksource/i8253.c +++ b/drivers/clocksource/i8253.c @@ -20,6 +20,13 @@ DEFINE_RAW_SPINLOCK(i8253_lock); EXPORT_SYMBOL(i8253_lock); +/* + * Handle PIT quirk in pit_shutdown() where zeroing the counter register + * restarts the PIT, negating the shutdown. On platforms with the quirk, + * platform specific code can set this to false. + */ +bool i8253_clear_counter_on_shutdown __ro_after_init = true; + #ifdef CONFIG_CLKSRC_I8253 /* * Since the PIT overflows every tick, its not very useful @@ -109,8 +116,11 @@ static int pit_shutdown(struct clock_event_device *evt) raw_spin_lock(&i8253_lock); outb_p(0x30, PIT_MODE); - outb_p(0, PIT_CH0); - outb_p(0, PIT_CH0); + + if (i8253_clear_counter_on_shutdown) { + outb_p(0, PIT_CH0); + outb_p(0, PIT_CH0); + } raw_spin_unlock(&i8253_lock); return 0; diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c index 8cfee0ab804b..d8c3595e9023 100644 --- a/drivers/cpufreq/imx6q-cpufreq.c +++ b/drivers/cpufreq/imx6q-cpufreq.c @@ -160,8 +160,13 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index) /* Ensure the arm clock divider is what we expect */ ret = clk_set_rate(clks[ARM].clk, new_freq * 1000); if (ret) { + int ret1; + dev_err(cpu_dev, "failed to set clock rate: %d\n", ret); - regulator_set_voltage_tol(arm_reg, volt_old, 0); + ret1 = regulator_set_voltage_tol(arm_reg, volt_old, 0); + if (ret1) + dev_warn(cpu_dev, + "failed to restore vddarm voltage: %d\n", ret1); return ret; } diff --git a/drivers/cpuidle/cpuidle-arm.c b/drivers/cpuidle/cpuidle-arm.c index 073557f433eb..3a407a3ef22b 100644 --- a/drivers/cpuidle/cpuidle-arm.c +++ b/drivers/cpuidle/cpuidle-arm.c @@ -82,7 +82,6 @@ static int __init arm_idle_init_cpu(int cpu) { int ret; struct cpuidle_driver *drv; - struct cpuidle_device *dev; drv = kmemdup(&arm_idle_driver, sizeof(*drv), GFP_KERNEL); if (!drv) @@ -103,13 +102,6 @@ static int __init arm_idle_init_cpu(int cpu) goto out_kfree_drv; } - ret = cpuidle_register_driver(drv); - if (ret) { - if (ret != -EBUSY) - pr_err("Failed to register cpuidle driver\n"); - goto out_kfree_drv; - } - /* * Call arch CPU operations in order to initialize * idle states suspend back-end specific data @@ -117,37 +109,21 @@ static int __init arm_idle_init_cpu(int cpu) ret = arm_cpuidle_init(cpu); /* - * Skip the cpuidle device initialization if the reported + * Allow the initialization to continue for other CPUs, if the reported * failure is a HW misconfiguration/breakage (-ENXIO). */ - if (ret == -ENXIO) - return 0; - if (ret) { pr_err("CPU %d failed to init idle CPU ops\n", cpu); - goto out_unregister_drv; - } - - dev = kzalloc(sizeof(*dev), GFP_KERNEL); - if (!dev) { - ret = -ENOMEM; - goto out_unregister_drv; + ret = ret == -ENXIO ? 0 : ret; + goto out_kfree_drv; } - dev->cpu = cpu; - ret = cpuidle_register_device(dev); - if (ret) { - pr_err("Failed to register cpuidle device for CPU %d\n", - cpu); - goto out_kfree_dev; - } + ret = cpuidle_register(drv, NULL); + if (ret) + goto out_kfree_drv; return 0; -out_kfree_dev: - kfree(dev); -out_unregister_drv: - cpuidle_unregister_driver(drv); out_kfree_drv: kfree(drv); return ret; @@ -178,9 +154,7 @@ out_fail: while (--cpu >= 0) { dev = per_cpu(cpuidle_devices, cpu); drv = cpuidle_get_cpu_driver(dev); - cpuidle_unregister_device(dev); - cpuidle_unregister_driver(drv); - kfree(dev); + cpuidle_unregister(drv); kfree(drv); } diff --git a/drivers/crypto/hisilicon/sec/sec_algs.c b/drivers/crypto/hisilicon/sec/sec_algs.c index f7d6d690116e..cdc4f9a171d9 100644 --- a/drivers/crypto/hisilicon/sec/sec_algs.c +++ b/drivers/crypto/hisilicon/sec/sec_algs.c @@ -732,6 +732,7 @@ static int sec_alg_skcipher_crypto(struct skcipher_request *skreq, int *splits_in_nents; int *splits_out_nents = NULL; struct sec_request_el *el, *temp; + bool split = skreq->src != skreq->dst; mutex_init(&sec_req->lock); sec_req->req_base = &skreq->base; @@ -750,7 +751,7 @@ static int sec_alg_skcipher_crypto(struct skcipher_request *skreq, if (ret) goto err_free_split_sizes; - if (skreq->src != skreq->dst) { + if (split) { sec_req->len_out = sg_nents(skreq->dst); ret = sec_map_and_split_sg(skreq->dst, split_sizes, steps, &splits_out, &splits_out_nents, @@ -785,8 +786,9 @@ static int sec_alg_skcipher_crypto(struct skcipher_request *skreq, split_sizes[i], skreq->src != skreq->dst, splits_in[i], splits_in_nents[i], - splits_out[i], - splits_out_nents[i], info); + split ? splits_out[i] : NULL, + split ? splits_out_nents[i] : 0, + info); if (IS_ERR(el)) { ret = PTR_ERR(el); goto err_free_elements; @@ -806,13 +808,6 @@ static int sec_alg_skcipher_crypto(struct skcipher_request *skreq, * more refined but this is unlikely to happen so no need. */ - /* Cleanup - all elements in pointer arrays have been coppied */ - kfree(splits_in_nents); - kfree(splits_in); - kfree(splits_out_nents); - kfree(splits_out); - kfree(split_sizes); - /* Grab a big lock for a long time to avoid concurrency issues */ mutex_lock(&queue->queuelock); @@ -827,13 +822,13 @@ static int sec_alg_skcipher_crypto(struct skcipher_request *skreq, (!queue->havesoftqueue || kfifo_avail(&queue->softqueue) > steps)) || !list_empty(&ctx->backlog)) { + ret = -EBUSY; if ((skreq->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG)) { list_add_tail(&sec_req->backlog_head, &ctx->backlog); mutex_unlock(&queue->queuelock); - return -EBUSY; + goto out; } - ret = -EBUSY; mutex_unlock(&queue->queuelock); goto err_free_elements; } @@ -842,7 +837,15 @@ static int sec_alg_skcipher_crypto(struct skcipher_request *skreq, if (ret) goto err_free_elements; - return -EINPROGRESS; + ret = -EINPROGRESS; +out: + /* Cleanup - all elements in pointer arrays have been copied */ + kfree(splits_in_nents); + kfree(splits_in); + kfree(splits_out_nents); + kfree(splits_out); + kfree(split_sizes); + return ret; err_free_elements: list_for_each_entry_safe(el, temp, &sec_req->elements, head) { @@ -854,7 +857,7 @@ err_free_elements: crypto_skcipher_ivsize(atfm), DMA_BIDIRECTIONAL); err_unmap_out_sg: - if (skreq->src != skreq->dst) + if (split) sec_unmap_sg_on_err(skreq->dst, steps, splits_out, splits_out_nents, sec_req->len_out, info->dev); diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c index 388a929baf95..1a6a77df8a5e 100644 --- a/drivers/firmware/efi/arm-init.c +++ b/drivers/firmware/efi/arm-init.c @@ -265,6 +265,10 @@ void __init efi_init(void) (params.mmap & ~PAGE_MASK))); init_screen_info(); + + /* ARM does not permit early mappings to persist across paging_init() */ + if (IS_ENABLED(CONFIG_ARM)) + efi_memmap_unmap(); } static int __init register_gop_device(void) diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c index 922cfb813109..a00934d263c5 100644 --- a/drivers/firmware/efi/arm-runtime.c +++ b/drivers/firmware/efi/arm-runtime.c @@ -110,7 +110,7 @@ static int __init arm_enable_runtime_services(void) { u64 mapsize; - if (!efi_enabled(EFI_BOOT) || !efi_enabled(EFI_MEMMAP)) { + if (!efi_enabled(EFI_BOOT)) { pr_info("EFI services will not be available.\n"); return 0; } diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 249eb70691b0..fad7c62cfc0e 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -592,7 +592,11 @@ int __init efi_config_parse_tables(void *config_tables, int count, int sz, early_memunmap(tbl, sizeof(*tbl)); } + return 0; +} +int __init efi_apply_persistent_mem_reservations(void) +{ if (efi.mem_reserve != EFI_INVALID_TABLE_ADDR) { unsigned long prsv = efi.mem_reserve; @@ -963,36 +967,43 @@ bool efi_is_table_address(unsigned long phys_addr) } static DEFINE_SPINLOCK(efi_mem_reserve_persistent_lock); +static struct linux_efi_memreserve *efi_memreserve_root __ro_after_init; int efi_mem_reserve_persistent(phys_addr_t addr, u64 size) { - struct linux_efi_memreserve *rsv, *parent; + struct linux_efi_memreserve *rsv; - if (efi.mem_reserve == EFI_INVALID_TABLE_ADDR) + if (!efi_memreserve_root) return -ENODEV; - rsv = kmalloc(sizeof(*rsv), GFP_KERNEL); + rsv = kmalloc(sizeof(*rsv), GFP_ATOMIC); if (!rsv) return -ENOMEM; - parent = memremap(efi.mem_reserve, sizeof(*rsv), MEMREMAP_WB); - if (!parent) { - kfree(rsv); - return -ENOMEM; - } - rsv->base = addr; rsv->size = size; spin_lock(&efi_mem_reserve_persistent_lock); - rsv->next = parent->next; - parent->next = __pa(rsv); + rsv->next = efi_memreserve_root->next; + efi_memreserve_root->next = __pa(rsv); spin_unlock(&efi_mem_reserve_persistent_lock); - memunmap(parent); + return 0; +} +static int __init efi_memreserve_root_init(void) +{ + if (efi.mem_reserve == EFI_INVALID_TABLE_ADDR) + return -ENODEV; + + efi_memreserve_root = memremap(efi.mem_reserve, + sizeof(*efi_memreserve_root), + MEMREMAP_WB); + if (!efi_memreserve_root) + return -ENOMEM; return 0; } +early_initcall(efi_memreserve_root_init); #ifdef CONFIG_KEXEC static int update_efi_random_seed(struct notifier_block *nb, diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c index 30ac0c975f8a..3d36142cf812 100644 --- a/drivers/firmware/efi/libstub/arm-stub.c +++ b/drivers/firmware/efi/libstub/arm-stub.c @@ -75,6 +75,9 @@ void install_memreserve_table(efi_system_table_t *sys_table_arg) efi_guid_t memreserve_table_guid = LINUX_EFI_MEMRESERVE_TABLE_GUID; efi_status_t status; + if (IS_ENABLED(CONFIG_ARM)) + return; + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, sizeof(*rsv), (void **)&rsv); if (status != EFI_SUCCESS) { diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c index 8830fa601e45..0c0d2312f4a8 100644 --- a/drivers/firmware/efi/libstub/fdt.c +++ b/drivers/firmware/efi/libstub/fdt.c @@ -158,6 +158,10 @@ static efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt, return efi_status; } } + + /* shrink the FDT back to its minimum size */ + fdt_pack(fdt); + return EFI_SUCCESS; fdt_set_fail: diff --git a/drivers/firmware/efi/memmap.c b/drivers/firmware/efi/memmap.c index fa2904fb841f..38b686c67b17 100644 --- a/drivers/firmware/efi/memmap.c +++ b/drivers/firmware/efi/memmap.c @@ -118,6 +118,9 @@ int __init efi_memmap_init_early(struct efi_memory_map_data *data) void __init efi_memmap_unmap(void) { + if (!efi_enabled(EFI_MEMMAP)) + return; + if (!efi.memmap.late) { unsigned long size; diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c index a19d845bdb06..8903b9ccfc2b 100644 --- a/drivers/firmware/efi/runtime-wrappers.c +++ b/drivers/firmware/efi/runtime-wrappers.c @@ -67,7 +67,7 @@ struct efi_runtime_work efi_rts_work; } \ \ init_completion(&efi_rts_work.efi_rts_comp); \ - INIT_WORK_ONSTACK(&efi_rts_work.work, efi_call_rts); \ + INIT_WORK(&efi_rts_work.work, efi_call_rts); \ efi_rts_work.arg1 = _arg1; \ efi_rts_work.arg2 = _arg2; \ efi_rts_work.arg3 = _arg3; \ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index d0102cfc8efb..104b2e0d893b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -151,6 +151,7 @@ extern int amdgpu_compute_multipipe; extern int amdgpu_gpu_recovery; extern int amdgpu_emu_mode; extern uint amdgpu_smu_memory_pool_size; +extern uint amdgpu_dc_feature_mask; extern struct amdgpu_mgpu_info mgpu_info; #ifdef CONFIG_DRM_AMDGPU_SI diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 943dbf3c5da1..8de55f7f1a3a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -127,6 +127,9 @@ int amdgpu_compute_multipipe = -1; int amdgpu_gpu_recovery = -1; /* auto */ int amdgpu_emu_mode = 0; uint amdgpu_smu_memory_pool_size = 0; +/* FBC (bit 0) disabled by default*/ +uint amdgpu_dc_feature_mask = 0; + struct amdgpu_mgpu_info mgpu_info = { .mutex = __MUTEX_INITIALIZER(mgpu_info.mutex), }; @@ -631,6 +634,14 @@ module_param(halt_if_hws_hang, int, 0644); MODULE_PARM_DESC(halt_if_hws_hang, "Halt if HWS hang is detected (0 = off (default), 1 = on)"); #endif +/** + * DOC: dcfeaturemask (uint) + * Override display features enabled. See enum DC_FEATURE_MASK in drivers/gpu/drm/amd/include/amd_shared.h. + * The default is the current set of stable display features. + */ +MODULE_PARM_DESC(dcfeaturemask, "all stable DC features enabled (default))"); +module_param_named(dcfeaturemask, amdgpu_dc_feature_mask, uint, 0444); + static const struct pci_device_id pciidlist[] = { #ifdef CONFIG_DRM_AMDGPU_SI {0x1002, 0x6780, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI}, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 352b30409060..dad0e2342df9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1632,13 +1632,6 @@ static int amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params, continue; } - /* First check if the entry is already handled */ - if (cursor.pfn < frag_start) { - cursor.entry->huge = true; - amdgpu_vm_pt_next(adev, &cursor); - continue; - } - /* If it isn't already handled it can't be a huge page */ if (cursor.entry->huge) { /* Add the entry to the relocated list to update it. */ @@ -1701,8 +1694,17 @@ static int amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params, } } while (frag_start < entry_end); - if (frag >= shift) + if (amdgpu_vm_pt_descendant(adev, &cursor)) { + /* Mark all child entries as huge */ + while (cursor.pfn < frag_start) { + cursor.entry->huge = true; + amdgpu_vm_pt_next(adev, &cursor); + } + + } else if (frag >= shift) { + /* or just move on to the next on the same level. */ amdgpu_vm_pt_next(adev, &cursor); + } } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c index ceb7847b504f..bfa317ad20a9 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c @@ -72,7 +72,7 @@ static void gfxhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev) /* Program the system aperture low logical page number. */ WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR, - min(adev->gmc.vram_start, adev->gmc.agp_start) >> 18); + min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18); if (adev->asic_type == CHIP_RAVEN && adev->rev_id >= 0x8) /* @@ -82,11 +82,11 @@ static void gfxhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev) * to get rid of the VM fault and hardware hang. */ WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR, - max((adev->gmc.vram_end >> 18) + 0x1, + max((adev->gmc.fb_end >> 18) + 0x1, adev->gmc.agp_end >> 18)); else WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR, - max(adev->gmc.vram_end, adev->gmc.agp_end) >> 18); + max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18); /* Set default page address. */ value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c index fd23ba1226a5..a0db67adc34c 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c @@ -90,7 +90,7 @@ static void mmhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev) /* Program the system aperture low logical page number. */ WREG32_SOC15(MMHUB, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR, - min(adev->gmc.vram_start, adev->gmc.agp_start) >> 18); + min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18); if (adev->asic_type == CHIP_RAVEN && adev->rev_id >= 0x8) /* @@ -100,11 +100,11 @@ static void mmhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev) * to get rid of the VM fault and hardware hang. */ WREG32_SOC15(MMHUB, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR, - max((adev->gmc.vram_end >> 18) + 0x1, + max((adev->gmc.fb_end >> 18) + 0x1, adev->gmc.agp_end >> 18)); else WREG32_SOC15(MMHUB, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR, - max(adev->gmc.vram_end, adev->gmc.agp_end) >> 18); + max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18); /* Set default page address. */ value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start + diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c index a99f71797aa3..a0fda6f9252a 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c @@ -129,7 +129,7 @@ static int vega10_ih_irq_init(struct amdgpu_device *adev) else wptr_off = adev->wb.gpu_addr + (adev->irq.ih.wptr_offs * 4); WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR_ADDR_LO, lower_32_bits(wptr_off)); - WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR_ADDR_HI, upper_32_bits(wptr_off) & 0xFF); + WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR_ADDR_HI, upper_32_bits(wptr_off) & 0xFFFF); /* set rptr, wptr to 0 */ WREG32_SOC15(OSSSYS, 0, mmIH_RB_RPTR, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c b/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c index 2d4473557b0d..d13fc4fcb517 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c +++ b/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c @@ -49,6 +49,7 @@ int vega20_reg_base_init(struct amdgpu_device *adev) adev->reg_offset[SMUIO_HWIP][i] = (uint32_t *)(&(SMUIO_BASE.instance[i])); adev->reg_offset[NBIF_HWIP][i] = (uint32_t *)(&(NBIO_BASE.instance[i])); adev->reg_offset[THM_HWIP][i] = (uint32_t *)(&(THM_BASE.instance[i])); + adev->reg_offset[CLK_HWIP][i] = (uint32_t *)(&(CLK_BASE.instance[i])); } return 0; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index b0df6dc9a775..c1262f62cd9f 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -429,6 +429,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) adev->asic_type < CHIP_RAVEN) init_data.flags.gpu_vm_support = true; + if (amdgpu_dc_feature_mask & DC_FBC_MASK) + init_data.flags.fbc_support = true; + /* Display Core create. */ adev->dm.dc = dc_create(&init_data); @@ -1524,13 +1527,6 @@ static int amdgpu_dm_backlight_update_status(struct backlight_device *bd) { struct amdgpu_display_manager *dm = bl_get_data(bd); - /* - * PWM interperts 0 as 100% rather than 0% because of HW - * limitation for level 0.So limiting minimum brightness level - * to 1. - */ - if (bd->props.brightness < 1) - return 1; if (dc_link_set_backlight_level(dm->backlight_link, bd->props.brightness, 0, 0)) return 0; @@ -2707,18 +2703,11 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, drm_connector = &aconnector->base; if (!aconnector->dc_sink) { - /* - * Create dc_sink when necessary to MST - * Don't apply fake_sink to MST - */ - if (aconnector->mst_port) { - dm_dp_mst_dc_sink_create(drm_connector); - return stream; + if (!aconnector->mst_port) { + sink = create_fake_sink(aconnector); + if (!sink) + return stream; } - - sink = create_fake_sink(aconnector); - if (!sink) - return stream; } else { sink = aconnector->dc_sink; } @@ -3308,7 +3297,7 @@ void dm_drm_plane_destroy_state(struct drm_plane *plane, static const struct drm_plane_funcs dm_plane_funcs = { .update_plane = drm_atomic_helper_update_plane, .disable_plane = drm_atomic_helper_disable_plane, - .destroy = drm_plane_cleanup, + .destroy = drm_primary_helper_destroy, .reset = dm_drm_plane_reset, .atomic_duplicate_state = dm_drm_plane_duplicate_state, .atomic_destroy_state = dm_drm_plane_destroy_state, diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 978b34a5011c..924a38a1fc44 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -160,8 +160,6 @@ struct amdgpu_dm_connector { struct mutex hpd_lock; bool fake_enable; - - bool mst_connected; }; #define to_amdgpu_dm_connector(x) container_of(x, struct amdgpu_dm_connector, base) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 03601d717fed..d02c32a1039c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -205,40 +205,6 @@ static const struct drm_connector_funcs dm_dp_mst_connector_funcs = { .atomic_get_property = amdgpu_dm_connector_atomic_get_property }; -void dm_dp_mst_dc_sink_create(struct drm_connector *connector) -{ - struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); - struct dc_sink *dc_sink; - struct dc_sink_init_data init_params = { - .link = aconnector->dc_link, - .sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST }; - - /* FIXME none of this is safe. we shouldn't touch aconnector here in - * atomic_check - */ - - /* - * TODO: Need to further figure out why ddc.algo is NULL while MST port exists - */ - if (!aconnector->port || !aconnector->port->aux.ddc.algo) - return; - - ASSERT(aconnector->edid); - - dc_sink = dc_link_add_remote_sink( - aconnector->dc_link, - (uint8_t *)aconnector->edid, - (aconnector->edid->extensions + 1) * EDID_LENGTH, - &init_params); - - dc_sink->priv = aconnector; - aconnector->dc_sink = dc_sink; - - if (aconnector->dc_sink) - amdgpu_dm_update_freesync_caps( - connector, aconnector->edid); -} - static int dm_dp_mst_get_modes(struct drm_connector *connector) { struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); @@ -319,12 +285,7 @@ dm_dp_create_fake_mst_encoder(struct amdgpu_dm_connector *connector) struct amdgpu_device *adev = dev->dev_private; struct amdgpu_encoder *amdgpu_encoder; struct drm_encoder *encoder; - const struct drm_connector_helper_funcs *connector_funcs = - connector->base.helper_private; - struct drm_encoder *enc_master = - connector_funcs->best_encoder(&connector->base); - DRM_DEBUG_KMS("enc master is %p\n", enc_master); amdgpu_encoder = kzalloc(sizeof(*amdgpu_encoder), GFP_KERNEL); if (!amdgpu_encoder) return NULL; @@ -354,25 +315,6 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, struct amdgpu_device *adev = dev->dev_private; struct amdgpu_dm_connector *aconnector; struct drm_connector *connector; - struct drm_connector_list_iter conn_iter; - - drm_connector_list_iter_begin(dev, &conn_iter); - drm_for_each_connector_iter(connector, &conn_iter) { - aconnector = to_amdgpu_dm_connector(connector); - if (aconnector->mst_port == master - && !aconnector->port) { - DRM_INFO("DM_MST: reusing connector: %p [id: %d] [master: %p]\n", - aconnector, connector->base.id, aconnector->mst_port); - - aconnector->port = port; - drm_connector_set_path_property(connector, pathprop); - - drm_connector_list_iter_end(&conn_iter); - aconnector->mst_connected = true; - return &aconnector->base; - } - } - drm_connector_list_iter_end(&conn_iter); aconnector = kzalloc(sizeof(*aconnector), GFP_KERNEL); if (!aconnector) @@ -421,8 +363,6 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, */ amdgpu_dm_connector_funcs_reset(connector); - aconnector->mst_connected = true; - DRM_INFO("DM_MST: added connector: %p [id: %d] [master: %p]\n", aconnector, connector->base.id, aconnector->mst_port); @@ -434,6 +374,9 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, static void dm_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr, struct drm_connector *connector) { + struct amdgpu_dm_connector *master = container_of(mgr, struct amdgpu_dm_connector, mst_mgr); + struct drm_device *dev = master->base.dev; + struct amdgpu_device *adev = dev->dev_private; struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); DRM_INFO("DM_MST: Disabling connector: %p [id: %d] [master: %p]\n", @@ -447,7 +390,10 @@ static void dm_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr, aconnector->dc_sink = NULL; } - aconnector->mst_connected = false; + drm_connector_unregister(connector); + if (adev->mode_info.rfbdev) + drm_fb_helper_remove_one_connector(&adev->mode_info.rfbdev->helper, connector); + drm_connector_put(connector); } static void dm_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr) @@ -458,18 +404,10 @@ static void dm_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr) drm_kms_helper_hotplug_event(dev); } -static void dm_dp_mst_link_status_reset(struct drm_connector *connector) -{ - mutex_lock(&connector->dev->mode_config.mutex); - drm_connector_set_link_status_property(connector, DRM_MODE_LINK_STATUS_BAD); - mutex_unlock(&connector->dev->mode_config.mutex); -} - static void dm_dp_mst_register_connector(struct drm_connector *connector) { struct drm_device *dev = connector->dev; struct amdgpu_device *adev = dev->dev_private; - struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); if (adev->mode_info.rfbdev) drm_fb_helper_add_one_connector(&adev->mode_info.rfbdev->helper, connector); @@ -477,9 +415,6 @@ static void dm_dp_mst_register_connector(struct drm_connector *connector) DRM_ERROR("adev->mode_info.rfbdev is NULL\n"); drm_connector_register(connector); - - if (aconnector->mst_connected) - dm_dp_mst_link_status_reset(connector); } static const struct drm_dp_mst_topology_cbs dm_mst_cbs = { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h index 8cf51da26657..2da851b40042 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h @@ -31,6 +31,5 @@ struct amdgpu_dm_connector; void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm, struct amdgpu_dm_connector *aconnector); -void dm_dp_mst_dc_sink_create(struct drm_connector *connector); #endif diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index fb04a4ad141f..5da2186b3615 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -1722,7 +1722,7 @@ static void write_i2c_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); RETIMER_REDRIVER_INFO("retimer write to slave_address = 0x%x,\ - offset = 0x%d, reg_val = 0x%d, i2c_success = %d\n", + offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) /* Write failure */ @@ -1734,7 +1734,7 @@ static void write_i2c_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); RETIMER_REDRIVER_INFO("retimer write to slave_address = 0x%x,\ - offset = 0x%d, reg_val = 0x%d, i2c_success = %d\n", + offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) /* Write failure */ diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 199527171100..b57fa61b3034 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -169,6 +169,7 @@ struct link_training_settings; struct dc_config { bool gpu_vm_support; bool disable_disp_pll_sharing; + bool fbc_support; }; enum visual_confirm { diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index b75ede5f84f7..b459867a05b2 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -1736,7 +1736,12 @@ static void set_static_screen_control(struct pipe_ctx **pipe_ctx, if (events->force_trigger) value |= 0x1; - value |= 0x84; + if (num_pipes) { + struct dc *dc = pipe_ctx[0]->stream->ctx->dc; + + if (dc->fbc_compressor) + value |= 0x84; + } for (i = 0; i < num_pipes; i++) pipe_ctx[i]->stream_res.tg->funcs-> diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c index e3624ca24574..7c9fd9052ee2 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c @@ -1362,7 +1362,8 @@ static bool construct( pool->base.sw_i2cs[i] = NULL; } - dc->fbc_compressor = dce110_compressor_create(ctx); + if (dc->config.fbc_support) + dc->fbc_compressor = dce110_compressor_create(ctx); if (!underlay_create(ctx, &pool->base)) goto res_create_fail; diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index 2083c308007c..470d7b89071a 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -133,6 +133,10 @@ enum PP_FEATURE_MASK { PP_AVFS_MASK = 0x40000, }; +enum DC_FEATURE_MASK { + DC_FBC_MASK = 0x1, +}; + /** * struct amd_ip_funcs - general hooks for managing amdgpu IP Blocks */ diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h index d2e7c0fa96c2..8eb0bb241210 100644 --- a/drivers/gpu/drm/amd/include/atomfirmware.h +++ b/drivers/gpu/drm/amd/include/atomfirmware.h @@ -1325,7 +1325,7 @@ struct atom_smu_info_v3_3 { struct atom_common_table_header table_header; uint8_t smuip_min_ver; uint8_t smuip_max_ver; - uint8_t smu_rsd1; + uint8_t waflclk_ss_mode; uint8_t gpuclk_ss_mode; uint16_t sclk_ss_percentage; uint16_t sclk_ss_rate_10hz; @@ -1355,7 +1355,10 @@ struct atom_smu_info_v3_3 { uint32_t syspll3_1_vco_freq_10khz; uint32_t bootup_fclk_10khz; uint32_t bootup_waflclk_10khz; - uint32_t reserved[3]; + uint32_t smu_info_caps; + uint16_t waflclk_ss_percentage; // in unit of 0.001% + uint16_t smuinitoffset; + uint32_t reserved; }; /* diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c index 99a33c33a32c..101c09b212ad 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c @@ -713,20 +713,20 @@ int smu_set_watermarks_for_clocks_ranges(void *wt_table, for (i = 0; i < wm_with_clock_ranges->num_wm_dmif_sets; i++) { table->WatermarkRow[1][i].MinClock = cpu_to_le16((uint16_t) - (wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_min_dcfclk_clk_in_khz) / - 1000); + (wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_min_dcfclk_clk_in_khz / + 1000)); table->WatermarkRow[1][i].MaxClock = cpu_to_le16((uint16_t) - (wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_max_dcfclk_clk_in_khz) / - 1000); + (wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_max_dcfclk_clk_in_khz / + 1000)); table->WatermarkRow[1][i].MinUclk = cpu_to_le16((uint16_t) - (wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_min_mem_clk_in_khz) / - 1000); + (wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_min_mem_clk_in_khz / + 1000)); table->WatermarkRow[1][i].MaxUclk = cpu_to_le16((uint16_t) - (wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_max_mem_clk_in_khz) / - 1000); + (wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_max_mem_clk_in_khz / + 1000)); table->WatermarkRow[1][i].WmSetting = (uint8_t) wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_set_id; } @@ -734,20 +734,20 @@ int smu_set_watermarks_for_clocks_ranges(void *wt_table, for (i = 0; i < wm_with_clock_ranges->num_wm_mcif_sets; i++) { table->WatermarkRow[0][i].MinClock = cpu_to_le16((uint16_t) - (wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_min_socclk_clk_in_khz) / - 1000); + (wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_min_socclk_clk_in_khz / + 1000)); table->WatermarkRow[0][i].MaxClock = cpu_to_le16((uint16_t) - (wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_max_socclk_clk_in_khz) / - 1000); + (wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_max_socclk_clk_in_khz / + 1000)); table->WatermarkRow[0][i].MinUclk = cpu_to_le16((uint16_t) - (wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_min_mem_clk_in_khz) / - 1000); + (wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_min_mem_clk_in_khz / + 1000)); table->WatermarkRow[0][i].MaxUclk = cpu_to_le16((uint16_t) - (wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_max_mem_clk_in_khz) / - 1000); + (wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_max_mem_clk_in_khz / + 1000)); table->WatermarkRow[0][i].WmSetting = (uint8_t) wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_set_id; } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c index 57143d51e3ee..99861f32b1f9 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c @@ -120,6 +120,7 @@ static void vega20_set_default_registry_data(struct pp_hwmgr *hwmgr) data->registry_data.disable_auto_wattman = 1; data->registry_data.auto_wattman_debug = 0; data->registry_data.auto_wattman_sample_period = 100; + data->registry_data.fclk_gfxclk_ratio = 0x3F6CCCCD; data->registry_data.auto_wattman_threshold = 50; data->registry_data.gfxoff_controlled_by_driver = 1; data->gfxoff_allowed = false; @@ -829,6 +830,28 @@ static int vega20_enable_all_smu_features(struct pp_hwmgr *hwmgr) return 0; } +static int vega20_notify_smc_display_change(struct pp_hwmgr *hwmgr) +{ + struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); + + if (data->smu_features[GNLD_DPM_UCLK].enabled) + return smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_SetUclkFastSwitch, + 1); + + return 0; +} + +static int vega20_send_clock_ratio(struct pp_hwmgr *hwmgr) +{ + struct vega20_hwmgr *data = + (struct vega20_hwmgr *)(hwmgr->backend); + + return smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_SetFclkGfxClkRatio, + data->registry_data.fclk_gfxclk_ratio); +} + static int vega20_disable_all_smu_features(struct pp_hwmgr *hwmgr) { struct vega20_hwmgr *data = @@ -1532,6 +1555,16 @@ static int vega20_enable_dpm_tasks(struct pp_hwmgr *hwmgr) "[EnableDPMTasks] Failed to enable all smu features!", return result); + result = vega20_notify_smc_display_change(hwmgr); + PP_ASSERT_WITH_CODE(!result, + "[EnableDPMTasks] Failed to notify smc display change!", + return result); + + result = vega20_send_clock_ratio(hwmgr); + PP_ASSERT_WITH_CODE(!result, + "[EnableDPMTasks] Failed to send clock ratio!", + return result); + /* Initialize UVD/VCE powergating state */ vega20_init_powergate_state(hwmgr); @@ -1972,19 +2005,6 @@ static int vega20_read_sensor(struct pp_hwmgr *hwmgr, int idx, return ret; } -static int vega20_notify_smc_display_change(struct pp_hwmgr *hwmgr, - bool has_disp) -{ - struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); - - if (data->smu_features[GNLD_DPM_UCLK].enabled) - return smum_send_msg_to_smc_with_parameter(hwmgr, - PPSMC_MSG_SetUclkFastSwitch, - has_disp ? 1 : 0); - - return 0; -} - int vega20_display_clock_voltage_request(struct pp_hwmgr *hwmgr, struct pp_display_clock_request *clock_req) { @@ -2044,13 +2064,6 @@ static int vega20_notify_smc_display_config_after_ps_adjustment( struct pp_display_clock_request clock_req; int ret = 0; - if ((hwmgr->display_config->num_display > 1) && - !hwmgr->display_config->multi_monitor_in_sync && - !hwmgr->display_config->nb_pstate_switch_disable) - vega20_notify_smc_display_change(hwmgr, false); - else - vega20_notify_smc_display_change(hwmgr, true); - min_clocks.dcefClock = hwmgr->display_config->min_dcef_set_clk; min_clocks.dcefClockInSR = hwmgr->display_config->min_dcef_deep_sleep_set_clk; min_clocks.memoryClock = hwmgr->display_config->min_mem_set_clock; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h index 56fe6a0d42e8..25faaa5c5b10 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h @@ -328,6 +328,7 @@ struct vega20_registry_data { uint8_t disable_auto_wattman; uint32_t auto_wattman_debug; uint32_t auto_wattman_sample_period; + uint32_t fclk_gfxclk_ratio; uint8_t auto_wattman_threshold; uint8_t log_avfs_param; uint8_t enable_enginess; diff --git a/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h b/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h index 45d64a81e945..4f63a736ea0e 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h +++ b/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h @@ -105,7 +105,8 @@ #define PPSMC_MSG_SetSystemVirtualDramAddrHigh 0x4B #define PPSMC_MSG_SetSystemVirtualDramAddrLow 0x4C #define PPSMC_MSG_WaflTest 0x4D -// Unused ID 0x4E to 0x50 +#define PPSMC_MSG_SetFclkGfxClkRatio 0x4E +// Unused ID 0x4F to 0x50 #define PPSMC_MSG_AllowGfxOff 0x51 #define PPSMC_MSG_DisallowGfxOff 0x52 #define PPSMC_MSG_GetPptLimit 0x53 diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 5ff1d79b86c4..0e0df398222d 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -1275,6 +1275,9 @@ static struct drm_dp_mst_branch *drm_dp_get_mst_branch_device(struct drm_dp_mst_ mutex_lock(&mgr->lock); mstb = mgr->mst_primary; + if (!mstb) + goto out; + for (i = 0; i < lct - 1; i++) { int shift = (i % 2) ? 0 : 4; int port_num = (rad[i / 2] >> shift) & 0xf; diff --git a/drivers/gpu/drm/drm_fourcc.c b/drivers/gpu/drm/drm_fourcc.c index 90a1c846fc25..8aaa5e86a979 100644 --- a/drivers/gpu/drm/drm_fourcc.c +++ b/drivers/gpu/drm/drm_fourcc.c @@ -97,9 +97,9 @@ EXPORT_SYMBOL(drm_mode_legacy_fb_format); /** * drm_driver_legacy_fb_format - compute drm fourcc code from legacy description + * @dev: DRM device * @bpp: bits per pixels * @depth: bit depth per pixel - * @native: use host native byte order * * Computes a drm fourcc pixel format code for the given @bpp/@depth values. * Unlike drm_mode_legacy_fb_format() this looks at the drivers mode_config, diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index e7c3ed6c9a2e..9b476368aa31 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -93,7 +93,7 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) * If the GPU managed to complete this jobs fence, the timout is * spurious. Bail out. */ - if (fence_completed(gpu, submit->out_fence->seqno)) + if (dma_fence_is_signaled(submit->out_fence)) return; /* diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index 94529aa82339..aef487dd8731 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -164,13 +164,6 @@ static u32 decon_get_frame_count(struct decon_context *ctx, bool end) return frm; } -static u32 decon_get_vblank_counter(struct exynos_drm_crtc *crtc) -{ - struct decon_context *ctx = crtc->ctx; - - return decon_get_frame_count(ctx, false); -} - static void decon_setup_trigger(struct decon_context *ctx) { if (!ctx->crtc->i80_mode && !(ctx->out_type & I80_HW_TRG)) @@ -536,7 +529,6 @@ static const struct exynos_drm_crtc_ops decon_crtc_ops = { .disable = decon_disable, .enable_vblank = decon_enable_vblank, .disable_vblank = decon_disable_vblank, - .get_vblank_counter = decon_get_vblank_counter, .atomic_begin = decon_atomic_begin, .update_plane = decon_update_plane, .disable_plane = decon_disable_plane, @@ -554,7 +546,6 @@ static int decon_bind(struct device *dev, struct device *master, void *data) int ret; ctx->drm_dev = drm_dev; - drm_dev->max_vblank_count = 0xffffffff; for (win = ctx->first_win; win < WINDOWS_NR; win++) { ctx->configs[win].pixel_formats = decon_formats; diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c index eea90251808f..2696289ecc78 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c @@ -162,16 +162,6 @@ static void exynos_drm_crtc_disable_vblank(struct drm_crtc *crtc) exynos_crtc->ops->disable_vblank(exynos_crtc); } -static u32 exynos_drm_crtc_get_vblank_counter(struct drm_crtc *crtc) -{ - struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc); - - if (exynos_crtc->ops->get_vblank_counter) - return exynos_crtc->ops->get_vblank_counter(exynos_crtc); - - return 0; -} - static const struct drm_crtc_funcs exynos_crtc_funcs = { .set_config = drm_atomic_helper_set_config, .page_flip = drm_atomic_helper_page_flip, @@ -181,7 +171,6 @@ static const struct drm_crtc_funcs exynos_crtc_funcs = { .atomic_destroy_state = drm_atomic_helper_crtc_destroy_state, .enable_vblank = exynos_drm_crtc_enable_vblank, .disable_vblank = exynos_drm_crtc_disable_vblank, - .get_vblank_counter = exynos_drm_crtc_get_vblank_counter, }; struct exynos_drm_crtc *exynos_drm_crtc_create(struct drm_device *drm_dev, diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h index ec9604f1272b..5e61e707f955 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.h +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h @@ -135,7 +135,6 @@ struct exynos_drm_crtc_ops { void (*disable)(struct exynos_drm_crtc *crtc); int (*enable_vblank)(struct exynos_drm_crtc *crtc); void (*disable_vblank)(struct exynos_drm_crtc *crtc); - u32 (*get_vblank_counter)(struct exynos_drm_crtc *crtc); enum drm_mode_status (*mode_valid)(struct exynos_drm_crtc *crtc, const struct drm_display_mode *mode); bool (*mode_fixup)(struct exynos_drm_crtc *crtc, diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index 07af7758066d..d81e62ae286a 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -14,6 +14,7 @@ #include <drm/drmP.h> #include <drm/drm_crtc_helper.h> +#include <drm/drm_fb_helper.h> #include <drm/drm_mipi_dsi.h> #include <drm/drm_panel.h> #include <drm/drm_atomic_helper.h> @@ -1474,12 +1475,12 @@ static int exynos_dsi_create_connector(struct drm_encoder *encoder) { struct exynos_dsi *dsi = encoder_to_dsi(encoder); struct drm_connector *connector = &dsi->connector; + struct drm_device *drm = encoder->dev; int ret; connector->polled = DRM_CONNECTOR_POLL_HPD; - ret = drm_connector_init(encoder->dev, connector, - &exynos_dsi_connector_funcs, + ret = drm_connector_init(drm, connector, &exynos_dsi_connector_funcs, DRM_MODE_CONNECTOR_DSI); if (ret) { DRM_ERROR("Failed to initialize connector with drm\n"); @@ -1489,7 +1490,12 @@ static int exynos_dsi_create_connector(struct drm_encoder *encoder) connector->status = connector_status_disconnected; drm_connector_helper_add(connector, &exynos_dsi_connector_helper_funcs); drm_connector_attach_encoder(connector, encoder); + if (!drm->registered) + return 0; + connector->funcs->reset(connector); + drm_fb_helper_add_one_connector(drm->fb_helper, connector); + drm_connector_register(connector); return 0; } @@ -1527,7 +1533,9 @@ static int exynos_dsi_host_attach(struct mipi_dsi_host *host, } dsi->panel = of_drm_find_panel(device->dev.of_node); - if (dsi->panel) { + if (IS_ERR(dsi->panel)) { + dsi->panel = NULL; + } else { drm_panel_attach(dsi->panel, &dsi->connector); dsi->connector.status = connector_status_connected; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c index 918dd2c82209..01d182289efa 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c @@ -192,7 +192,7 @@ int exynos_drm_fbdev_init(struct drm_device *dev) struct drm_fb_helper *helper; int ret; - if (!dev->mode_config.num_crtc || !dev->mode_config.num_connector) + if (!dev->mode_config.num_crtc) return 0; fbdev = kzalloc(sizeof(*fbdev), GFP_KERNEL); diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 2402395a068d..58e166effa45 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -1905,7 +1905,6 @@ static struct intel_vgpu_mm *intel_vgpu_create_ggtt_mm(struct intel_vgpu *vgpu) vgpu_free_mm(mm); return ERR_PTR(-ENOMEM); } - mm->ggtt_mm.last_partial_off = -1UL; return mm; } @@ -1930,7 +1929,6 @@ void _intel_vgpu_mm_release(struct kref *mm_ref) invalidate_ppgtt_mm(mm); } else { vfree(mm->ggtt_mm.virtual_ggtt); - mm->ggtt_mm.last_partial_off = -1UL; } vgpu_free_mm(mm); @@ -2168,6 +2166,8 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, struct intel_gvt_gtt_entry e, m; dma_addr_t dma_addr; int ret; + struct intel_gvt_partial_pte *partial_pte, *pos, *n; + bool partial_update = false; if (bytes != 4 && bytes != 8) return -EINVAL; @@ -2178,68 +2178,57 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, if (!vgpu_gmadr_is_valid(vgpu, gma)) return 0; - ggtt_get_guest_entry(ggtt_mm, &e, g_gtt_index); - + e.type = GTT_TYPE_GGTT_PTE; memcpy((void *)&e.val64 + (off & (info->gtt_entry_size - 1)), p_data, bytes); /* If ggtt entry size is 8 bytes, and it's split into two 4 bytes - * write, we assume the two 4 bytes writes are consecutive. - * Otherwise, we abort and report error + * write, save the first 4 bytes in a list and update virtual + * PTE. Only update shadow PTE when the second 4 bytes comes. */ if (bytes < info->gtt_entry_size) { - if (ggtt_mm->ggtt_mm.last_partial_off == -1UL) { - /* the first partial part*/ - ggtt_mm->ggtt_mm.last_partial_off = off; - ggtt_mm->ggtt_mm.last_partial_data = e.val64; - return 0; - } else if ((g_gtt_index == - (ggtt_mm->ggtt_mm.last_partial_off >> - info->gtt_entry_size_shift)) && - (off != ggtt_mm->ggtt_mm.last_partial_off)) { - /* the second partial part */ - - int last_off = ggtt_mm->ggtt_mm.last_partial_off & - (info->gtt_entry_size - 1); - - memcpy((void *)&e.val64 + last_off, - (void *)&ggtt_mm->ggtt_mm.last_partial_data + - last_off, bytes); - - ggtt_mm->ggtt_mm.last_partial_off = -1UL; - } else { - int last_offset; - - gvt_vgpu_err("failed to populate guest ggtt entry: abnormal ggtt entry write sequence, last_partial_off=%lx, offset=%x, bytes=%d, ggtt entry size=%d\n", - ggtt_mm->ggtt_mm.last_partial_off, off, - bytes, info->gtt_entry_size); - - /* set host ggtt entry to scratch page and clear - * virtual ggtt entry as not present for last - * partially write offset - */ - last_offset = ggtt_mm->ggtt_mm.last_partial_off & - (~(info->gtt_entry_size - 1)); - - ggtt_get_host_entry(ggtt_mm, &m, last_offset); - ggtt_invalidate_pte(vgpu, &m); - ops->set_pfn(&m, gvt->gtt.scratch_mfn); - ops->clear_present(&m); - ggtt_set_host_entry(ggtt_mm, &m, last_offset); - ggtt_invalidate(gvt->dev_priv); - - ggtt_get_guest_entry(ggtt_mm, &e, last_offset); - ops->clear_present(&e); - ggtt_set_guest_entry(ggtt_mm, &e, last_offset); - - ggtt_mm->ggtt_mm.last_partial_off = off; - ggtt_mm->ggtt_mm.last_partial_data = e.val64; + bool found = false; + + list_for_each_entry_safe(pos, n, + &ggtt_mm->ggtt_mm.partial_pte_list, list) { + if (g_gtt_index == pos->offset >> + info->gtt_entry_size_shift) { + if (off != pos->offset) { + /* the second partial part*/ + int last_off = pos->offset & + (info->gtt_entry_size - 1); + + memcpy((void *)&e.val64 + last_off, + (void *)&pos->data + last_off, + bytes); + + list_del(&pos->list); + kfree(pos); + found = true; + break; + } + + /* update of the first partial part */ + pos->data = e.val64; + ggtt_set_guest_entry(ggtt_mm, &e, g_gtt_index); + return 0; + } + } - return 0; + if (!found) { + /* the first partial part */ + partial_pte = kzalloc(sizeof(*partial_pte), GFP_KERNEL); + if (!partial_pte) + return -ENOMEM; + partial_pte->offset = off; + partial_pte->data = e.val64; + list_add_tail(&partial_pte->list, + &ggtt_mm->ggtt_mm.partial_pte_list); + partial_update = true; } } - if (ops->test_present(&e)) { + if (!partial_update && (ops->test_present(&e))) { gfn = ops->get_pfn(&e); m = e; @@ -2263,16 +2252,18 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, } else ops->set_pfn(&m, dma_addr >> PAGE_SHIFT); } else { - ggtt_get_host_entry(ggtt_mm, &m, g_gtt_index); - ggtt_invalidate_pte(vgpu, &m); ops->set_pfn(&m, gvt->gtt.scratch_mfn); ops->clear_present(&m); } out: + ggtt_set_guest_entry(ggtt_mm, &e, g_gtt_index); + + ggtt_get_host_entry(ggtt_mm, &e, g_gtt_index); + ggtt_invalidate_pte(vgpu, &e); + ggtt_set_host_entry(ggtt_mm, &m, g_gtt_index); ggtt_invalidate(gvt->dev_priv); - ggtt_set_guest_entry(ggtt_mm, &e, g_gtt_index); return 0; } @@ -2430,6 +2421,8 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu) intel_vgpu_reset_ggtt(vgpu, false); + INIT_LIST_HEAD(>t->ggtt_mm->ggtt_mm.partial_pte_list); + return create_scratch_page_tree(vgpu); } @@ -2454,6 +2447,14 @@ static void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu) static void intel_vgpu_destroy_ggtt_mm(struct intel_vgpu *vgpu) { + struct intel_gvt_partial_pte *pos; + + list_for_each_entry(pos, + &vgpu->gtt.ggtt_mm->ggtt_mm.partial_pte_list, list) { + gvt_dbg_mm("partial PTE update on hold 0x%lx : 0x%llx\n", + pos->offset, pos->data); + kfree(pos); + } intel_vgpu_destroy_mm(vgpu->gtt.ggtt_mm); vgpu->gtt.ggtt_mm = NULL; } diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h index 7a9b36176efb..d8cb04cc946d 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.h +++ b/drivers/gpu/drm/i915/gvt/gtt.h @@ -35,7 +35,6 @@ #define _GVT_GTT_H_ #define I915_GTT_PAGE_SHIFT 12 -#define I915_GTT_PAGE_MASK (~(I915_GTT_PAGE_SIZE - 1)) struct intel_vgpu_mm; @@ -133,6 +132,12 @@ enum intel_gvt_mm_type { #define GVT_RING_CTX_NR_PDPS GEN8_3LVL_PDPES +struct intel_gvt_partial_pte { + unsigned long offset; + u64 data; + struct list_head list; +}; + struct intel_vgpu_mm { enum intel_gvt_mm_type type; struct intel_vgpu *vgpu; @@ -157,8 +162,7 @@ struct intel_vgpu_mm { } ppgtt_mm; struct { void *virtual_ggtt; - unsigned long last_partial_off; - u64 last_partial_data; + struct list_head partial_pte_list; } ggtt_mm; }; }; diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 90f50f67909a..aa280bb07125 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -1609,7 +1609,7 @@ static int bxt_gt_disp_pwron_write(struct intel_vgpu *vgpu, return 0; } -static int bxt_edp_psr_imr_iir_write(struct intel_vgpu *vgpu, +static int edp_psr_imr_iir_write(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes) { vgpu_vreg(vgpu, offset) = 0; @@ -2607,6 +2607,9 @@ static int init_generic_mmio_info(struct intel_gvt *gvt) MMIO_DFH(_MMIO(0x1a178), D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(_MMIO(0x1a17c), D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(_MMIO(0x2217c), D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); + + MMIO_DH(EDP_PSR_IMR, D_BDW_PLUS, NULL, edp_psr_imr_iir_write); + MMIO_DH(EDP_PSR_IIR, D_BDW_PLUS, NULL, edp_psr_imr_iir_write); return 0; } @@ -3205,9 +3208,6 @@ static int init_bxt_mmio_info(struct intel_gvt *gvt) MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_B), D_BXT); MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_C), D_BXT); - MMIO_DH(EDP_PSR_IMR, D_BXT, NULL, bxt_edp_psr_imr_iir_write); - MMIO_DH(EDP_PSR_IIR, D_BXT, NULL, bxt_edp_psr_imr_iir_write); - MMIO_D(RC6_CTX_BASE, D_BXT); MMIO_D(GEN8_PUSHBUS_CONTROL, D_BXT); diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index 10e63eea5492..36a5147cd01e 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -131,7 +131,7 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = { {RCS, GAMT_CHKN_BIT_REG, 0x0, false}, /* 0x4ab8 */ {RCS, GEN9_GAMT_ECO_REG_RW_IA, 0x0, false}, /* 0x4ab0 */ - {RCS, GEN9_CSFE_CHICKEN1_RCS, 0x0, false}, /* 0x20d4 */ + {RCS, GEN9_CSFE_CHICKEN1_RCS, 0xffff, false}, /* 0x20d4 */ {RCS, GEN8_GARBCNTL, 0x0, false}, /* 0xb004 */ {RCS, GEN7_FF_THREAD_MODE, 0x0, false}, /* 0x20a0 */ diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 44e2c0f5ec50..ffdbbac4400e 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1175,8 +1175,6 @@ skl_dram_get_channels_info(struct drm_i915_private *dev_priv) return -EINVAL; } - dram_info->valid_dimm = true; - /* * If any of the channel is single rank channel, worst case output * will be same as if single rank memory, so consider single rank @@ -1193,8 +1191,7 @@ skl_dram_get_channels_info(struct drm_i915_private *dev_priv) return -EINVAL; } - if (ch0.is_16gb_dimm || ch1.is_16gb_dimm) - dram_info->is_16gb_dimm = true; + dram_info->is_16gb_dimm = ch0.is_16gb_dimm || ch1.is_16gb_dimm; dev_priv->dram_info.symmetric_memory = intel_is_dram_symmetric(val_ch0, val_ch1, @@ -1314,7 +1311,6 @@ bxt_get_dram_info(struct drm_i915_private *dev_priv) return -EINVAL; } - dram_info->valid_dimm = true; dram_info->valid = true; return 0; } @@ -1327,12 +1323,17 @@ intel_get_dram_info(struct drm_i915_private *dev_priv) int ret; dram_info->valid = false; - dram_info->valid_dimm = false; - dram_info->is_16gb_dimm = false; dram_info->rank = I915_DRAM_RANK_INVALID; dram_info->bandwidth_kbps = 0; dram_info->num_channels = 0; + /* + * Assume 16Gb DIMMs are present until proven otherwise. + * This is only used for the level 0 watermark latency + * w/a which does not apply to bxt/glk. + */ + dram_info->is_16gb_dimm = !IS_GEN9_LP(dev_priv); + if (INTEL_GEN(dev_priv) < 9 || IS_GEMINILAKE(dev_priv)) return; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 8624b4bdc242..9102571e9692 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1948,7 +1948,6 @@ struct drm_i915_private { struct dram_info { bool valid; - bool valid_dimm; bool is_16gb_dimm; u8 num_channels; enum dram_rank { diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 09187286d346..1aaccbe7e1de 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -460,7 +460,7 @@ eb_validate_vma(struct i915_execbuffer *eb, * any non-page-aligned or non-canonical addresses. */ if (unlikely(entry->flags & EXEC_OBJECT_PINNED && - entry->offset != gen8_canonical_addr(entry->offset & PAGE_MASK))) + entry->offset != gen8_canonical_addr(entry->offset & I915_GTT_PAGE_MASK))) return -EINVAL; /* pad_to_size was once a reserved field, so sanitize it */ diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 56c7f8637311..47c302543799 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -1757,7 +1757,7 @@ static void gen6_dump_ppgtt(struct i915_hw_ppgtt *base, struct seq_file *m) if (i == 4) continue; - seq_printf(m, "\t\t(%03d, %04d) %08lx: ", + seq_printf(m, "\t\t(%03d, %04d) %08llx: ", pde, pte, (pde * GEN6_PTES + pte) * I915_GTT_PAGE_SIZE); for (i = 0; i < 4; i++) { diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h index 7e2af5f4f39b..28039290655c 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.h +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h @@ -42,13 +42,15 @@ #include "i915_selftest.h" #include "i915_timeline.h" -#define I915_GTT_PAGE_SIZE_4K BIT(12) -#define I915_GTT_PAGE_SIZE_64K BIT(16) -#define I915_GTT_PAGE_SIZE_2M BIT(21) +#define I915_GTT_PAGE_SIZE_4K BIT_ULL(12) +#define I915_GTT_PAGE_SIZE_64K BIT_ULL(16) +#define I915_GTT_PAGE_SIZE_2M BIT_ULL(21) #define I915_GTT_PAGE_SIZE I915_GTT_PAGE_SIZE_4K #define I915_GTT_MAX_PAGE_SIZE I915_GTT_PAGE_SIZE_2M +#define I915_GTT_PAGE_MASK -I915_GTT_PAGE_SIZE + #define I915_GTT_MIN_ALIGNMENT I915_GTT_PAGE_SIZE #define I915_FENCE_REG_NONE -1 @@ -659,20 +661,20 @@ int i915_gem_gtt_insert(struct i915_address_space *vm, u64 start, u64 end, unsigned int flags); /* Flags used by pin/bind&friends. */ -#define PIN_NONBLOCK BIT(0) -#define PIN_MAPPABLE BIT(1) -#define PIN_ZONE_4G BIT(2) -#define PIN_NONFAULT BIT(3) -#define PIN_NOEVICT BIT(4) - -#define PIN_MBZ BIT(5) /* I915_VMA_PIN_OVERFLOW */ -#define PIN_GLOBAL BIT(6) /* I915_VMA_GLOBAL_BIND */ -#define PIN_USER BIT(7) /* I915_VMA_LOCAL_BIND */ -#define PIN_UPDATE BIT(8) - -#define PIN_HIGH BIT(9) -#define PIN_OFFSET_BIAS BIT(10) -#define PIN_OFFSET_FIXED BIT(11) +#define PIN_NONBLOCK BIT_ULL(0) +#define PIN_MAPPABLE BIT_ULL(1) +#define PIN_ZONE_4G BIT_ULL(2) +#define PIN_NONFAULT BIT_ULL(3) +#define PIN_NOEVICT BIT_ULL(4) + +#define PIN_MBZ BIT_ULL(5) /* I915_VMA_PIN_OVERFLOW */ +#define PIN_GLOBAL BIT_ULL(6) /* I915_VMA_GLOBAL_BIND */ +#define PIN_USER BIT_ULL(7) /* I915_VMA_LOCAL_BIND */ +#define PIN_UPDATE BIT_ULL(8) + +#define PIN_HIGH BIT_ULL(9) +#define PIN_OFFSET_BIAS BIT_ULL(10) +#define PIN_OFFSET_FIXED BIT_ULL(11) #define PIN_OFFSET_MASK (-I915_GTT_PAGE_SIZE) #endif diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 7c491ea3d052..e31c27e45734 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2095,8 +2095,12 @@ enum i915_power_well_id { /* ICL PHY DFLEX registers */ #define PORT_TX_DFLEXDPMLE1 _MMIO(0x1638C0) -#define DFLEXDPMLE1_DPMLETC_MASK(n) (0xf << (4 * (n))) -#define DFLEXDPMLE1_DPMLETC(n, x) ((x) << (4 * (n))) +#define DFLEXDPMLE1_DPMLETC_MASK(tc_port) (0xf << (4 * (tc_port))) +#define DFLEXDPMLE1_DPMLETC_ML0(tc_port) (1 << (4 * (tc_port))) +#define DFLEXDPMLE1_DPMLETC_ML1_0(tc_port) (3 << (4 * (tc_port))) +#define DFLEXDPMLE1_DPMLETC_ML3(tc_port) (8 << (4 * (tc_port))) +#define DFLEXDPMLE1_DPMLETC_ML3_2(tc_port) (12 << (4 * (tc_port))) +#define DFLEXDPMLE1_DPMLETC_ML3_0(tc_port) (15 << (4 * (tc_port))) /* BXT PHY Ref registers */ #define _PORT_REF_DW3_A 0x16218C @@ -4593,12 +4597,12 @@ enum { #define DRM_DIP_ENABLE (1 << 28) #define PSR_VSC_BIT_7_SET (1 << 27) -#define VSC_SELECT_MASK (0x3 << 26) -#define VSC_SELECT_SHIFT 26 -#define VSC_DIP_HW_HEA_DATA (0 << 26) -#define VSC_DIP_HW_HEA_SW_DATA (1 << 26) -#define VSC_DIP_HW_DATA_SW_HEA (2 << 26) -#define VSC_DIP_SW_HEA_DATA (3 << 26) +#define VSC_SELECT_MASK (0x3 << 25) +#define VSC_SELECT_SHIFT 25 +#define VSC_DIP_HW_HEA_DATA (0 << 25) +#define VSC_DIP_HW_HEA_SW_DATA (1 << 25) +#define VSC_DIP_HW_DATA_SW_HEA (2 << 25) +#define VSC_DIP_SW_HEA_DATA (3 << 25) #define VDIP_ENABLE_PPS (1 << 24) /* Panel power sequencing */ diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index 769f3f586661..ee3ca2de983b 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -144,6 +144,9 @@ static const struct { /* HDMI N/CTS table */ #define TMDS_297M 297000 #define TMDS_296M 296703 +#define TMDS_594M 594000 +#define TMDS_593M 593407 + static const struct { int sample_rate; int clock; @@ -164,6 +167,20 @@ static const struct { { 176400, TMDS_297M, 18816, 247500 }, { 192000, TMDS_296M, 23296, 281250 }, { 192000, TMDS_297M, 20480, 247500 }, + { 44100, TMDS_593M, 8918, 937500 }, + { 44100, TMDS_594M, 9408, 990000 }, + { 48000, TMDS_593M, 5824, 562500 }, + { 48000, TMDS_594M, 6144, 594000 }, + { 32000, TMDS_593M, 5824, 843750 }, + { 32000, TMDS_594M, 3072, 445500 }, + { 88200, TMDS_593M, 17836, 937500 }, + { 88200, TMDS_594M, 18816, 990000 }, + { 96000, TMDS_593M, 11648, 562500 }, + { 96000, TMDS_594M, 12288, 594000 }, + { 176400, TMDS_593M, 35672, 937500 }, + { 176400, TMDS_594M, 37632, 990000 }, + { 192000, TMDS_593M, 23296, 562500 }, + { 192000, TMDS_594M, 24576, 594000 }, }; /* get AUD_CONFIG_PIXEL_CLOCK_HDMI_* value for mode */ diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c index 29075c763428..8d74276029e6 100644 --- a/drivers/gpu/drm/i915/intel_cdclk.c +++ b/drivers/gpu/drm/i915/intel_cdclk.c @@ -2138,16 +2138,8 @@ void intel_set_cdclk(struct drm_i915_private *dev_priv, static int intel_pixel_rate_to_cdclk(struct drm_i915_private *dev_priv, int pixel_rate) { - if (INTEL_GEN(dev_priv) >= 10) + if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) return DIV_ROUND_UP(pixel_rate, 2); - else if (IS_GEMINILAKE(dev_priv)) - /* - * FIXME: Avoid using a pixel clock that is more than 99% of the cdclk - * as a temporary workaround. Use a higher cdclk instead. (Note that - * intel_compute_max_dotclk() limits the max pixel clock to 99% of max - * cdclk.) - */ - return DIV_ROUND_UP(pixel_rate * 100, 2 * 99); else if (IS_GEN9(dev_priv) || IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) return pixel_rate; @@ -2543,14 +2535,8 @@ static int intel_compute_max_dotclk(struct drm_i915_private *dev_priv) { int max_cdclk_freq = dev_priv->max_cdclk_freq; - if (INTEL_GEN(dev_priv) >= 10) + if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) return 2 * max_cdclk_freq; - else if (IS_GEMINILAKE(dev_priv)) - /* - * FIXME: Limiting to 99% as a temporary workaround. See - * intel_min_cdclk() for details. - */ - return 2 * max_cdclk_freq * 99 / 100; else if (IS_GEN9(dev_priv) || IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) return max_cdclk_freq; diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c index 0ef0c6448d53..01fa98299bae 100644 --- a/drivers/gpu/drm/i915/intel_device_info.c +++ b/drivers/gpu/drm/i915/intel_device_info.c @@ -474,7 +474,7 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv) u8 eu_disabled_mask; u32 n_disabled; - if (!(sseu->subslice_mask[ss] & BIT(ss))) + if (!(sseu->subslice_mask[s] & BIT(ss))) /* skip disabled subslice */ continue; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 9741cc419e1b..a54843fdeb2f 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -4850,8 +4850,31 @@ static void cpt_verify_modeset(struct drm_device *dev, int pipe) * chroma samples for both of the luma samples, and thus we don't * actually get the expected MPEG2 chroma siting convention :( * The same behaviour is observed on pre-SKL platforms as well. + * + * Theory behind the formula (note that we ignore sub-pixel + * source coordinates): + * s = source sample position + * d = destination sample position + * + * Downscaling 4:1: + * -0.5 + * | 0.0 + * | | 1.5 (initial phase) + * | | | + * v v v + * | s | s | s | s | + * | d | + * + * Upscaling 1:4: + * -0.5 + * | -0.375 (initial phase) + * | | 0.0 + * | | | + * v v v + * | s | + * | d | d | d | d | */ -u16 skl_scaler_calc_phase(int sub, bool chroma_cosited) +u16 skl_scaler_calc_phase(int sub, int scale, bool chroma_cosited) { int phase = -0x8000; u16 trip = 0; @@ -4859,6 +4882,15 @@ u16 skl_scaler_calc_phase(int sub, bool chroma_cosited) if (chroma_cosited) phase += (sub - 1) * 0x8000 / sub; + phase += scale / (2 * sub); + + /* + * Hardware initial phase limited to [-0.5:1.5]. + * Since the max hardware scale factor is 3.0, we + * should never actually excdeed 1.0 here. + */ + WARN_ON(phase < -0x8000 || phase > 0x18000); + if (phase < 0) phase = 0x10000 + phase; else @@ -5067,13 +5099,20 @@ static void skylake_pfit_enable(struct intel_crtc *crtc) if (crtc->config->pch_pfit.enabled) { u16 uv_rgb_hphase, uv_rgb_vphase; + int pfit_w, pfit_h, hscale, vscale; int id; if (WARN_ON(crtc->config->scaler_state.scaler_id < 0)) return; - uv_rgb_hphase = skl_scaler_calc_phase(1, false); - uv_rgb_vphase = skl_scaler_calc_phase(1, false); + pfit_w = (crtc->config->pch_pfit.size >> 16) & 0xFFFF; + pfit_h = crtc->config->pch_pfit.size & 0xFFFF; + + hscale = (crtc->config->pipe_src_w << 16) / pfit_w; + vscale = (crtc->config->pipe_src_h << 16) / pfit_h; + + uv_rgb_hphase = skl_scaler_calc_phase(1, hscale, false); + uv_rgb_vphase = skl_scaler_calc_phase(1, vscale, false); id = scaler_state->scaler_id; I915_WRITE(SKL_PS_CTRL(pipe, id), PS_SCALER_EN | @@ -12768,17 +12807,12 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state) intel_check_cpu_fifo_underruns(dev_priv); intel_check_pch_fifo_underruns(dev_priv); - if (!new_crtc_state->active) { - /* - * Make sure we don't call initial_watermarks - * for ILK-style watermark updates. - * - * No clue what this is supposed to achieve. - */ - if (INTEL_GEN(dev_priv) >= 9) - dev_priv->display.initial_watermarks(intel_state, - to_intel_crtc_state(new_crtc_state)); - } + /* FIXME unify this for all platforms */ + if (!new_crtc_state->active && + !HAS_GMCH_DISPLAY(dev_priv) && + dev_priv->display.initial_watermarks) + dev_priv->display.initial_watermarks(intel_state, + to_intel_crtc_state(new_crtc_state)); } } @@ -14646,7 +14680,7 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb, fb->height < SKL_MIN_YUV_420_SRC_H || (fb->width % 4) != 0 || (fb->height % 4) != 0)) { DRM_DEBUG_KMS("src dimensions not correct for NV12\n"); - return -EINVAL; + goto err; } for (i = 0; i < fb->format->num_planes; i++) { diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c index 1b00f8ea145b..a911691dbd0f 100644 --- a/drivers/gpu/drm/i915/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/intel_dp_mst.c @@ -452,6 +452,10 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo if (!intel_connector) return NULL; + intel_connector->get_hw_state = intel_dp_mst_get_hw_state; + intel_connector->mst_port = intel_dp; + intel_connector->port = port; + connector = &intel_connector->base; ret = drm_connector_init(dev, connector, &intel_dp_mst_connector_funcs, DRM_MODE_CONNECTOR_DisplayPort); @@ -462,10 +466,6 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo drm_connector_helper_add(connector, &intel_dp_mst_connector_helper_funcs); - intel_connector->get_hw_state = intel_dp_mst_get_hw_state; - intel_connector->mst_port = intel_dp; - intel_connector->port = port; - for_each_pipe(dev_priv, pipe) { struct drm_encoder *enc = &intel_dp->mst_encoders[pipe]->base.base; diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index f8dc84b2d2d3..8b298e5f012d 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -1646,7 +1646,7 @@ void intel_mode_from_pipe_config(struct drm_display_mode *mode, void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state); -u16 skl_scaler_calc_phase(int sub, bool chroma_center); +u16 skl_scaler_calc_phase(int sub, int scale, bool chroma_center); int skl_update_scaler_crtc(struct intel_crtc_state *crtc_state); int skl_max_scale(const struct intel_crtc_state *crtc_state, u32 pixel_format); diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c index 648a13c6043c..9a8018130237 100644 --- a/drivers/gpu/drm/i915/intel_hotplug.c +++ b/drivers/gpu/drm/i915/intel_hotplug.c @@ -228,7 +228,9 @@ static void intel_hpd_irq_storm_reenable_work(struct work_struct *work) drm_for_each_connector_iter(connector, &conn_iter) { struct intel_connector *intel_connector = to_intel_connector(connector); - if (intel_connector->encoder->hpd_pin == pin) { + /* Don't check MST ports, they don't have pins */ + if (!intel_connector->mst_port && + intel_connector->encoder->hpd_pin == pin) { if (connector->polled != intel_connector->polled) DRM_DEBUG_DRIVER("Reenabling HPD on connector %s\n", connector->name); @@ -395,37 +397,54 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv, struct intel_encoder *encoder; bool storm_detected = false; bool queue_dig = false, queue_hp = false; + u32 long_hpd_pulse_mask = 0; + u32 short_hpd_pulse_mask = 0; + enum hpd_pin pin; if (!pin_mask) return; spin_lock(&dev_priv->irq_lock); + + /* + * Determine whether ->hpd_pulse() exists for each pin, and + * whether we have a short or a long pulse. This is needed + * as each pin may have up to two encoders (HDMI and DP) and + * only the one of them (DP) will have ->hpd_pulse(). + */ for_each_intel_encoder(&dev_priv->drm, encoder) { - enum hpd_pin pin = encoder->hpd_pin; bool has_hpd_pulse = intel_encoder_has_hpd_pulse(encoder); + enum port port = encoder->port; + bool long_hpd; + pin = encoder->hpd_pin; if (!(BIT(pin) & pin_mask)) continue; - if (has_hpd_pulse) { - bool long_hpd = long_mask & BIT(pin); - enum port port = encoder->port; + if (!has_hpd_pulse) + continue; - DRM_DEBUG_DRIVER("digital hpd port %c - %s\n", port_name(port), - long_hpd ? "long" : "short"); - /* - * For long HPD pulses we want to have the digital queue happen, - * but we still want HPD storm detection to function. - */ - queue_dig = true; - if (long_hpd) { - dev_priv->hotplug.long_port_mask |= (1 << port); - } else { - /* for short HPD just trigger the digital queue */ - dev_priv->hotplug.short_port_mask |= (1 << port); - continue; - } + long_hpd = long_mask & BIT(pin); + + DRM_DEBUG_DRIVER("digital hpd port %c - %s\n", port_name(port), + long_hpd ? "long" : "short"); + queue_dig = true; + + if (long_hpd) { + long_hpd_pulse_mask |= BIT(pin); + dev_priv->hotplug.long_port_mask |= BIT(port); + } else { + short_hpd_pulse_mask |= BIT(pin); + dev_priv->hotplug.short_port_mask |= BIT(port); } + } + + /* Now process each pin just once */ + for_each_hpd_pin(pin) { + bool long_hpd; + + if (!(BIT(pin) & pin_mask)) + continue; if (dev_priv->hotplug.stats[pin].state == HPD_DISABLED) { /* @@ -442,11 +461,22 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv, if (dev_priv->hotplug.stats[pin].state != HPD_ENABLED) continue; - if (!has_hpd_pulse) { + /* + * Delegate to ->hpd_pulse() if one of the encoders for this + * pin has it, otherwise let the hotplug_work deal with this + * pin directly. + */ + if (((short_hpd_pulse_mask | long_hpd_pulse_mask) & BIT(pin))) { + long_hpd = long_hpd_pulse_mask & BIT(pin); + } else { dev_priv->hotplug.event_bits |= BIT(pin); + long_hpd = true; queue_hp = true; } + if (!long_hpd) + continue; + if (intel_hpd_irq_storm_detect(dev_priv, pin)) { dev_priv->hotplug.event_bits &= ~BIT(pin); storm_detected = true; diff --git a/drivers/gpu/drm/i915/intel_lpe_audio.c b/drivers/gpu/drm/i915/intel_lpe_audio.c index cdf19553ffac..5d5336fbe7b0 100644 --- a/drivers/gpu/drm/i915/intel_lpe_audio.c +++ b/drivers/gpu/drm/i915/intel_lpe_audio.c @@ -297,8 +297,10 @@ void intel_lpe_audio_teardown(struct drm_i915_private *dev_priv) lpe_audio_platdev_destroy(dev_priv); irq_free_desc(dev_priv->lpe_audio.irq); -} + dev_priv->lpe_audio.irq = -1; + dev_priv->lpe_audio.platdev = NULL; +} /** * intel_lpe_audio_notify() - notify lpe audio event diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 43957bb37a42..37c94a54efcb 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -424,7 +424,8 @@ static u64 execlists_update_context(struct i915_request *rq) reg_state[CTX_RING_TAIL+1] = intel_ring_set_tail(rq->ring, rq->tail); - /* True 32b PPGTT with dynamic page allocation: update PDP + /* + * True 32b PPGTT with dynamic page allocation: update PDP * registers and point the unallocated PDPs to scratch page. * PML4 is allocated during ppgtt init, so this is not needed * in 48-bit mode. @@ -432,6 +433,17 @@ static u64 execlists_update_context(struct i915_request *rq) if (ppgtt && !i915_vm_is_48bit(&ppgtt->vm)) execlists_update_context_pdps(ppgtt, reg_state); + /* + * Make sure the context image is complete before we submit it to HW. + * + * Ostensibly, writes (including the WCB) should be flushed prior to + * an uncached write such as our mmio register access, the empirical + * evidence (esp. on Braswell) suggests that the WC write into memory + * may not be visible to the HW prior to the completion of the UC + * register write and that we may begin execution from the context + * before its image is complete leading to invalid PD chasing. + */ + wmb(); return ce->lrc_desc; } diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 1db9b8328275..245f0022bcfd 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -2881,8 +2881,7 @@ static void intel_read_wm_latency(struct drm_i915_private *dev_priv, * any underrun. If not able to get Dimm info assume 16GB dimm * to avoid any underrun. */ - if (!dev_priv->dram_info.valid_dimm || - dev_priv->dram_info.is_16gb_dimm) + if (dev_priv->dram_info.is_16gb_dimm) wm[0] += 1; } else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) { diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index d0ef50bf930a..187bb0ceb4ac 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -91,6 +91,7 @@ static int gen4_render_ring_flush(struct i915_request *rq, u32 mode) { u32 cmd, *cs; + int i; /* * read/write caches: @@ -127,12 +128,45 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode) cmd |= MI_INVALIDATE_ISP; } - cs = intel_ring_begin(rq, 2); + i = 2; + if (mode & EMIT_INVALIDATE) + i += 20; + + cs = intel_ring_begin(rq, i); if (IS_ERR(cs)) return PTR_ERR(cs); *cs++ = cmd; - *cs++ = MI_NOOP; + + /* + * A random delay to let the CS invalidate take effect? Without this + * delay, the GPU relocation path fails as the CS does not see + * the updated contents. Just as important, if we apply the flushes + * to the EMIT_FLUSH branch (i.e. immediately after the relocation + * write and before the invalidate on the next batch), the relocations + * still fail. This implies that is a delay following invalidation + * that is required to reset the caches as opposed to a delay to + * ensure the memory is written. + */ + if (mode & EMIT_INVALIDATE) { + *cs++ = GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE; + *cs++ = i915_ggtt_offset(rq->engine->scratch) | + PIPE_CONTROL_GLOBAL_GTT; + *cs++ = 0; + *cs++ = 0; + + for (i = 0; i < 12; i++) + *cs++ = MI_FLUSH; + + *cs++ = GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE; + *cs++ = i915_ggtt_offset(rq->engine->scratch) | + PIPE_CONTROL_GLOBAL_GTT; + *cs++ = 0; + *cs++ = 0; + } + + *cs++ = cmd; + intel_ring_advance(rq, cs); return 0; diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index 0fdabce647ab..44e4491a4918 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -2749,6 +2749,12 @@ static const struct i915_power_well_desc icl_power_wells[] = { }, }, { + .name = "DC off", + .domains = ICL_DISPLAY_DC_OFF_POWER_DOMAINS, + .ops = &gen9_dc_off_power_well_ops, + .id = DISP_PW_ID_NONE, + }, + { .name = "power well 2", .domains = ICL_PW_2_POWER_DOMAINS, .ops = &hsw_power_well_ops, @@ -2760,12 +2766,6 @@ static const struct i915_power_well_desc icl_power_wells[] = { }, }, { - .name = "DC off", - .domains = ICL_DISPLAY_DC_OFF_POWER_DOMAINS, - .ops = &gen9_dc_off_power_well_ops, - .id = DISP_PW_ID_NONE, - }, - { .name = "power well 3", .domains = ICL_PW_3_POWER_DOMAINS, .ops = &hsw_power_well_ops, @@ -3176,8 +3176,7 @@ static u8 intel_dbuf_max_slices(struct drm_i915_private *dev_priv) void icl_dbuf_slices_update(struct drm_i915_private *dev_priv, u8 req_slices) { - u8 hw_enabled_slices = dev_priv->wm.skl_hw.ddb.enabled_slices; - u32 val; + const u8 hw_enabled_slices = dev_priv->wm.skl_hw.ddb.enabled_slices; bool ret; if (req_slices > intel_dbuf_max_slices(dev_priv)) { @@ -3188,7 +3187,6 @@ void icl_dbuf_slices_update(struct drm_i915_private *dev_priv, if (req_slices == hw_enabled_slices || req_slices == 0) return; - val = I915_READ(DBUF_CTL_S2); if (req_slices > hw_enabled_slices) ret = intel_dbuf_slice_set(dev_priv, DBUF_CTL_S2, true); else diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index 5fd2f7bf3927..d3090a7537bb 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -302,13 +302,65 @@ skl_plane_max_stride(struct intel_plane *plane, return min(8192 * cpp, 32768); } +static void +skl_program_scaler(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) +{ + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + enum pipe pipe = plane->pipe; + int scaler_id = plane_state->scaler_id; + const struct intel_scaler *scaler = + &crtc_state->scaler_state.scalers[scaler_id]; + int crtc_x = plane_state->base.dst.x1; + int crtc_y = plane_state->base.dst.y1; + uint32_t crtc_w = drm_rect_width(&plane_state->base.dst); + uint32_t crtc_h = drm_rect_height(&plane_state->base.dst); + u16 y_hphase, uv_rgb_hphase; + u16 y_vphase, uv_rgb_vphase; + int hscale, vscale; + + hscale = drm_rect_calc_hscale(&plane_state->base.src, + &plane_state->base.dst, + 0, INT_MAX); + vscale = drm_rect_calc_vscale(&plane_state->base.src, + &plane_state->base.dst, + 0, INT_MAX); + + /* TODO: handle sub-pixel coordinates */ + if (plane_state->base.fb->format->format == DRM_FORMAT_NV12) { + y_hphase = skl_scaler_calc_phase(1, hscale, false); + y_vphase = skl_scaler_calc_phase(1, vscale, false); + + /* MPEG2 chroma siting convention */ + uv_rgb_hphase = skl_scaler_calc_phase(2, hscale, true); + uv_rgb_vphase = skl_scaler_calc_phase(2, vscale, false); + } else { + /* not used */ + y_hphase = 0; + y_vphase = 0; + + uv_rgb_hphase = skl_scaler_calc_phase(1, hscale, false); + uv_rgb_vphase = skl_scaler_calc_phase(1, vscale, false); + } + + I915_WRITE_FW(SKL_PS_CTRL(pipe, scaler_id), + PS_SCALER_EN | PS_PLANE_SEL(plane->id) | scaler->mode); + I915_WRITE_FW(SKL_PS_PWR_GATE(pipe, scaler_id), 0); + I915_WRITE_FW(SKL_PS_VPHASE(pipe, scaler_id), + PS_Y_PHASE(y_vphase) | PS_UV_RGB_PHASE(uv_rgb_vphase)); + I915_WRITE_FW(SKL_PS_HPHASE(pipe, scaler_id), + PS_Y_PHASE(y_hphase) | PS_UV_RGB_PHASE(uv_rgb_hphase)); + I915_WRITE_FW(SKL_PS_WIN_POS(pipe, scaler_id), (crtc_x << 16) | crtc_y); + I915_WRITE_FW(SKL_PS_WIN_SZ(pipe, scaler_id), (crtc_w << 16) | crtc_h); +} + void skl_update_plane(struct intel_plane *plane, const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); - const struct drm_framebuffer *fb = plane_state->base.fb; enum plane_id plane_id = plane->id; enum pipe pipe = plane->pipe; u32 plane_ctl = plane_state->ctl; @@ -318,8 +370,6 @@ skl_update_plane(struct intel_plane *plane, u32 aux_stride = skl_plane_stride(plane_state, 1); int crtc_x = plane_state->base.dst.x1; int crtc_y = plane_state->base.dst.y1; - uint32_t crtc_w = drm_rect_width(&plane_state->base.dst); - uint32_t crtc_h = drm_rect_height(&plane_state->base.dst); uint32_t x = plane_state->color_plane[0].x; uint32_t y = plane_state->color_plane[0].y; uint32_t src_w = drm_rect_width(&plane_state->base.src) >> 16; @@ -329,8 +379,6 @@ skl_update_plane(struct intel_plane *plane, /* Sizes are 0 based */ src_w--; src_h--; - crtc_w--; - crtc_h--; spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); @@ -353,41 +401,8 @@ skl_update_plane(struct intel_plane *plane, (plane_state->color_plane[1].y << 16) | plane_state->color_plane[1].x); - /* program plane scaler */ if (plane_state->scaler_id >= 0) { - int scaler_id = plane_state->scaler_id; - const struct intel_scaler *scaler = - &crtc_state->scaler_state.scalers[scaler_id]; - u16 y_hphase, uv_rgb_hphase; - u16 y_vphase, uv_rgb_vphase; - - /* TODO: handle sub-pixel coordinates */ - if (fb->format->format == DRM_FORMAT_NV12) { - y_hphase = skl_scaler_calc_phase(1, false); - y_vphase = skl_scaler_calc_phase(1, false); - - /* MPEG2 chroma siting convention */ - uv_rgb_hphase = skl_scaler_calc_phase(2, true); - uv_rgb_vphase = skl_scaler_calc_phase(2, false); - } else { - /* not used */ - y_hphase = 0; - y_vphase = 0; - - uv_rgb_hphase = skl_scaler_calc_phase(1, false); - uv_rgb_vphase = skl_scaler_calc_phase(1, false); - } - - I915_WRITE_FW(SKL_PS_CTRL(pipe, scaler_id), - PS_SCALER_EN | PS_PLANE_SEL(plane_id) | scaler->mode); - I915_WRITE_FW(SKL_PS_PWR_GATE(pipe, scaler_id), 0); - I915_WRITE_FW(SKL_PS_VPHASE(pipe, scaler_id), - PS_Y_PHASE(y_vphase) | PS_UV_RGB_PHASE(uv_rgb_vphase)); - I915_WRITE_FW(SKL_PS_HPHASE(pipe, scaler_id), - PS_Y_PHASE(y_hphase) | PS_UV_RGB_PHASE(uv_rgb_hphase)); - I915_WRITE_FW(SKL_PS_WIN_POS(pipe, scaler_id), (crtc_x << 16) | crtc_y); - I915_WRITE_FW(SKL_PS_WIN_SZ(pipe, scaler_id), - ((crtc_w + 1) << 16)|(crtc_h + 1)); + skl_program_scaler(plane, crtc_state, plane_state); I915_WRITE_FW(PLANE_POS(pipe, plane_id), 0); } else { diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c index 8d03f64eabd7..5c22f2c8d4cf 100644 --- a/drivers/gpu/drm/i915/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/selftests/huge_pages.c @@ -551,7 +551,7 @@ static int igt_mock_ppgtt_misaligned_dma(void *arg) err = igt_check_page_sizes(vma); if (vma->page_sizes.gtt != I915_GTT_PAGE_SIZE_4K) { - pr_err("page_sizes.gtt=%u, expected %lu\n", + pr_err("page_sizes.gtt=%u, expected %llu\n", vma->page_sizes.gtt, I915_GTT_PAGE_SIZE_4K); err = -EINVAL; } diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c index 8e2e269db97e..127d81513671 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c @@ -1337,7 +1337,7 @@ static int igt_gtt_reserve(void *arg) GEM_BUG_ON(!drm_mm_node_allocated(&vma->node)); if (vma->node.start != total || vma->node.size != 2*I915_GTT_PAGE_SIZE) { - pr_err("i915_gem_gtt_reserve (pass 1) placement failed, found (%llx + %llx), expected (%llx + %lx)\n", + pr_err("i915_gem_gtt_reserve (pass 1) placement failed, found (%llx + %llx), expected (%llx + %llx)\n", vma->node.start, vma->node.size, total, 2*I915_GTT_PAGE_SIZE); err = -EINVAL; @@ -1386,7 +1386,7 @@ static int igt_gtt_reserve(void *arg) GEM_BUG_ON(!drm_mm_node_allocated(&vma->node)); if (vma->node.start != total || vma->node.size != 2*I915_GTT_PAGE_SIZE) { - pr_err("i915_gem_gtt_reserve (pass 2) placement failed, found (%llx + %llx), expected (%llx + %lx)\n", + pr_err("i915_gem_gtt_reserve (pass 2) placement failed, found (%llx + %llx), expected (%llx + %llx)\n", vma->node.start, vma->node.size, total, 2*I915_GTT_PAGE_SIZE); err = -EINVAL; @@ -1430,7 +1430,7 @@ static int igt_gtt_reserve(void *arg) GEM_BUG_ON(!drm_mm_node_allocated(&vma->node)); if (vma->node.start != offset || vma->node.size != 2*I915_GTT_PAGE_SIZE) { - pr_err("i915_gem_gtt_reserve (pass 3) placement failed, found (%llx + %llx), expected (%llx + %lx)\n", + pr_err("i915_gem_gtt_reserve (pass 3) placement failed, found (%llx + %llx), expected (%llx + %llx)\n", vma->node.start, vma->node.size, offset, 2*I915_GTT_PAGE_SIZE); err = -EINVAL; diff --git a/drivers/gpu/drm/meson/meson_venc.c b/drivers/gpu/drm/meson/meson_venc.c index 514245e69b38..acbbad3e322c 100644 --- a/drivers/gpu/drm/meson/meson_venc.c +++ b/drivers/gpu/drm/meson/meson_venc.c @@ -854,6 +854,13 @@ void meson_venc_hdmi_mode_set(struct meson_drm *priv, int vic, unsigned int sof_lines; unsigned int vsync_lines; + /* Use VENCI for 480i and 576i and double HDMI pixels */ + if (mode->flags & DRM_MODE_FLAG_DBLCLK) { + hdmi_repeat = true; + use_enci = true; + venc_hdmi_latency = 1; + } + if (meson_venc_hdmi_supported_vic(vic)) { vmode = meson_venc_hdmi_get_vic_vmode(vic); if (!vmode) { @@ -865,13 +872,7 @@ void meson_venc_hdmi_mode_set(struct meson_drm *priv, int vic, } else { meson_venc_hdmi_get_dmt_vmode(mode, &vmode_dmt); vmode = &vmode_dmt; - } - - /* Use VENCI for 480i and 576i and double HDMI pixels */ - if (mode->flags & DRM_MODE_FLAG_DBLCLK) { - hdmi_repeat = true; - use_enci = true; - venc_hdmi_latency = 1; + use_enci = false; } /* Repeat VENC pixels for 480/576i/p, 720p50/60 and 1080p50/60 */ diff --git a/drivers/gpu/drm/omapdrm/dss/dsi.c b/drivers/gpu/drm/omapdrm/dss/dsi.c index 394c129cfb3b..0a485c5b982e 100644 --- a/drivers/gpu/drm/omapdrm/dss/dsi.c +++ b/drivers/gpu/drm/omapdrm/dss/dsi.c @@ -5409,11 +5409,14 @@ static int dsi_probe(struct platform_device *pdev) /* DSI on OMAP3 doesn't have register DSI_GNQ, set number * of data to 3 by default */ - if (dsi->data->quirks & DSI_QUIRK_GNQ) + if (dsi->data->quirks & DSI_QUIRK_GNQ) { + dsi_runtime_get(dsi); /* NB_DATA_LANES */ dsi->num_lanes_supported = 1 + REG_GET(dsi, DSI_GNQ, 11, 9); - else + dsi_runtime_put(dsi); + } else { dsi->num_lanes_supported = 3; + } r = dsi_init_output(dsi); if (r) @@ -5426,15 +5429,19 @@ static int dsi_probe(struct platform_device *pdev) } r = of_platform_populate(dev->of_node, NULL, NULL, dev); - if (r) + if (r) { DSSERR("Failed to populate DSI child devices: %d\n", r); + goto err_uninit_output; + } r = component_add(&pdev->dev, &dsi_component_ops); if (r) - goto err_uninit_output; + goto err_of_depopulate; return 0; +err_of_depopulate: + of_platform_depopulate(dev); err_uninit_output: dsi_uninit_output(dsi); err_pm_disable: @@ -5470,19 +5477,12 @@ static int dsi_runtime_suspend(struct device *dev) /* wait for current handler to finish before turning the DSI off */ synchronize_irq(dsi->irq); - dispc_runtime_put(dsi->dss->dispc); - return 0; } static int dsi_runtime_resume(struct device *dev) { struct dsi_data *dsi = dev_get_drvdata(dev); - int r; - - r = dispc_runtime_get(dsi->dss->dispc); - if (r) - return r; dsi->is_enabled = true; /* ensure the irq handler sees the is_enabled value */ diff --git a/drivers/gpu/drm/omapdrm/dss/dss.c b/drivers/gpu/drm/omapdrm/dss/dss.c index 1aaf260aa9b8..7553c7fc1c45 100644 --- a/drivers/gpu/drm/omapdrm/dss/dss.c +++ b/drivers/gpu/drm/omapdrm/dss/dss.c @@ -1484,16 +1484,23 @@ static int dss_probe(struct platform_device *pdev) dss); /* Add all the child devices as components. */ + r = of_platform_populate(pdev->dev.of_node, NULL, NULL, &pdev->dev); + if (r) + goto err_uninit_debugfs; + omapdss_gather_components(&pdev->dev); device_for_each_child(&pdev->dev, &match, dss_add_child_component); r = component_master_add_with_match(&pdev->dev, &dss_component_ops, match); if (r) - goto err_uninit_debugfs; + goto err_of_depopulate; return 0; +err_of_depopulate: + of_platform_depopulate(&pdev->dev); + err_uninit_debugfs: dss_debugfs_remove_file(dss->debugfs.clk); dss_debugfs_remove_file(dss->debugfs.dss); @@ -1522,6 +1529,8 @@ static int dss_remove(struct platform_device *pdev) { struct dss_device *dss = platform_get_drvdata(pdev); + of_platform_depopulate(&pdev->dev); + component_master_del(&pdev->dev, &dss_component_ops); dss_debugfs_remove_file(dss->debugfs.clk); diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi4.c b/drivers/gpu/drm/omapdrm/dss/hdmi4.c index cf6230eac31a..aabdda394c9c 100644 --- a/drivers/gpu/drm/omapdrm/dss/hdmi4.c +++ b/drivers/gpu/drm/omapdrm/dss/hdmi4.c @@ -635,10 +635,14 @@ static int hdmi4_bind(struct device *dev, struct device *master, void *data) hdmi->dss = dss; - r = hdmi_pll_init(dss, hdmi->pdev, &hdmi->pll, &hdmi->wp); + r = hdmi_runtime_get(hdmi); if (r) return r; + r = hdmi_pll_init(dss, hdmi->pdev, &hdmi->pll, &hdmi->wp); + if (r) + goto err_runtime_put; + r = hdmi4_cec_init(hdmi->pdev, &hdmi->core, &hdmi->wp); if (r) goto err_pll_uninit; @@ -652,12 +656,16 @@ static int hdmi4_bind(struct device *dev, struct device *master, void *data) hdmi->debugfs = dss_debugfs_create_file(dss, "hdmi", hdmi_dump_regs, hdmi); + hdmi_runtime_put(hdmi); + return 0; err_cec_uninit: hdmi4_cec_uninit(&hdmi->core); err_pll_uninit: hdmi_pll_uninit(&hdmi->pll); +err_runtime_put: + hdmi_runtime_put(hdmi); return r; } @@ -833,32 +841,6 @@ static int hdmi4_remove(struct platform_device *pdev) return 0; } -static int hdmi_runtime_suspend(struct device *dev) -{ - struct omap_hdmi *hdmi = dev_get_drvdata(dev); - - dispc_runtime_put(hdmi->dss->dispc); - - return 0; -} - -static int hdmi_runtime_resume(struct device *dev) -{ - struct omap_hdmi *hdmi = dev_get_drvdata(dev); - int r; - - r = dispc_runtime_get(hdmi->dss->dispc); - if (r < 0) - return r; - - return 0; -} - -static const struct dev_pm_ops hdmi_pm_ops = { - .runtime_suspend = hdmi_runtime_suspend, - .runtime_resume = hdmi_runtime_resume, -}; - static const struct of_device_id hdmi_of_match[] = { { .compatible = "ti,omap4-hdmi", }, {}, @@ -869,7 +851,6 @@ struct platform_driver omapdss_hdmi4hw_driver = { .remove = hdmi4_remove, .driver = { .name = "omapdss_hdmi", - .pm = &hdmi_pm_ops, .of_match_table = hdmi_of_match, .suppress_bind_attrs = true, }, diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi5.c b/drivers/gpu/drm/omapdrm/dss/hdmi5.c index b0e4a7463f8c..9e8556f67a29 100644 --- a/drivers/gpu/drm/omapdrm/dss/hdmi5.c +++ b/drivers/gpu/drm/omapdrm/dss/hdmi5.c @@ -825,32 +825,6 @@ static int hdmi5_remove(struct platform_device *pdev) return 0; } -static int hdmi_runtime_suspend(struct device *dev) -{ - struct omap_hdmi *hdmi = dev_get_drvdata(dev); - - dispc_runtime_put(hdmi->dss->dispc); - - return 0; -} - -static int hdmi_runtime_resume(struct device *dev) -{ - struct omap_hdmi *hdmi = dev_get_drvdata(dev); - int r; - - r = dispc_runtime_get(hdmi->dss->dispc); - if (r < 0) - return r; - - return 0; -} - -static const struct dev_pm_ops hdmi_pm_ops = { - .runtime_suspend = hdmi_runtime_suspend, - .runtime_resume = hdmi_runtime_resume, -}; - static const struct of_device_id hdmi_of_match[] = { { .compatible = "ti,omap5-hdmi", }, { .compatible = "ti,dra7-hdmi", }, @@ -862,7 +836,6 @@ struct platform_driver omapdss_hdmi5hw_driver = { .remove = hdmi5_remove, .driver = { .name = "omapdss_hdmi5", - .pm = &hdmi_pm_ops, .of_match_table = hdmi_of_match, .suppress_bind_attrs = true, }, diff --git a/drivers/gpu/drm/omapdrm/dss/venc.c b/drivers/gpu/drm/omapdrm/dss/venc.c index ff0b18c8e4ac..b5f52727f8b1 100644 --- a/drivers/gpu/drm/omapdrm/dss/venc.c +++ b/drivers/gpu/drm/omapdrm/dss/venc.c @@ -946,19 +946,12 @@ static int venc_runtime_suspend(struct device *dev) if (venc->tv_dac_clk) clk_disable_unprepare(venc->tv_dac_clk); - dispc_runtime_put(venc->dss->dispc); - return 0; } static int venc_runtime_resume(struct device *dev) { struct venc_device *venc = dev_get_drvdata(dev); - int r; - - r = dispc_runtime_get(venc->dss->dispc); - if (r < 0) - return r; if (venc->tv_dac_clk) clk_prepare_enable(venc->tv_dac_clk); diff --git a/drivers/gpu/drm/omapdrm/omap_crtc.c b/drivers/gpu/drm/omapdrm/omap_crtc.c index 62928ec0e7db..caffc547ef97 100644 --- a/drivers/gpu/drm/omapdrm/omap_crtc.c +++ b/drivers/gpu/drm/omapdrm/omap_crtc.c @@ -350,11 +350,14 @@ static void omap_crtc_arm_event(struct drm_crtc *crtc) static void omap_crtc_atomic_enable(struct drm_crtc *crtc, struct drm_crtc_state *old_state) { + struct omap_drm_private *priv = crtc->dev->dev_private; struct omap_crtc *omap_crtc = to_omap_crtc(crtc); int ret; DBG("%s", omap_crtc->name); + priv->dispc_ops->runtime_get(priv->dispc); + spin_lock_irq(&crtc->dev->event_lock); drm_crtc_vblank_on(crtc); ret = drm_crtc_vblank_get(crtc); @@ -367,6 +370,7 @@ static void omap_crtc_atomic_enable(struct drm_crtc *crtc, static void omap_crtc_atomic_disable(struct drm_crtc *crtc, struct drm_crtc_state *old_state) { + struct omap_drm_private *priv = crtc->dev->dev_private; struct omap_crtc *omap_crtc = to_omap_crtc(crtc); DBG("%s", omap_crtc->name); @@ -379,6 +383,8 @@ static void omap_crtc_atomic_disable(struct drm_crtc *crtc, spin_unlock_irq(&crtc->dev->event_lock); drm_crtc_vblank_off(crtc); + + priv->dispc_ops->runtime_put(priv->dispc); } static enum drm_mode_status omap_crtc_mode_valid(struct drm_crtc *crtc, diff --git a/drivers/gpu/drm/sun4i/sun4i_lvds.c b/drivers/gpu/drm/sun4i/sun4i_lvds.c index af7dcb6da351..e7eb0d1e17be 100644 --- a/drivers/gpu/drm/sun4i/sun4i_lvds.c +++ b/drivers/gpu/drm/sun4i/sun4i_lvds.c @@ -75,7 +75,7 @@ static void sun4i_lvds_encoder_enable(struct drm_encoder *encoder) DRM_DEBUG_DRIVER("Enabling LVDS output\n"); - if (!IS_ERR(tcon->panel)) { + if (tcon->panel) { drm_panel_prepare(tcon->panel); drm_panel_enable(tcon->panel); } @@ -88,7 +88,7 @@ static void sun4i_lvds_encoder_disable(struct drm_encoder *encoder) DRM_DEBUG_DRIVER("Disabling LVDS output\n"); - if (!IS_ERR(tcon->panel)) { + if (tcon->panel) { drm_panel_disable(tcon->panel); drm_panel_unprepare(tcon->panel); } diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c index bf068da6b12e..f4a22689eb54 100644 --- a/drivers/gpu/drm/sun4i/sun4i_rgb.c +++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c @@ -135,7 +135,7 @@ static void sun4i_rgb_encoder_enable(struct drm_encoder *encoder) DRM_DEBUG_DRIVER("Enabling RGB output\n"); - if (!IS_ERR(tcon->panel)) { + if (tcon->panel) { drm_panel_prepare(tcon->panel); drm_panel_enable(tcon->panel); } @@ -148,7 +148,7 @@ static void sun4i_rgb_encoder_disable(struct drm_encoder *encoder) DRM_DEBUG_DRIVER("Disabling RGB output\n"); - if (!IS_ERR(tcon->panel)) { + if (tcon->panel) { drm_panel_disable(tcon->panel); drm_panel_unprepare(tcon->panel); } diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index c78cd35a1294..f949287d926c 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -491,7 +491,8 @@ static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon, sun4i_tcon0_mode_set_common(tcon, mode); /* Set dithering if needed */ - sun4i_tcon0_mode_set_dithering(tcon, tcon->panel->connector); + if (tcon->panel) + sun4i_tcon0_mode_set_dithering(tcon, tcon->panel->connector); /* Adjust clock delay */ clk_delay = sun4i_tcon_get_clk_delay(mode, 0); @@ -555,7 +556,7 @@ static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon, * Following code is a way to avoid quirks all around TCON * and DOTCLOCK drivers. */ - if (!IS_ERR(tcon->panel)) { + if (tcon->panel) { struct drm_panel *panel = tcon->panel; struct drm_connector *connector = panel->connector; struct drm_display_info display_info = connector->display_info; diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c index cf2a18571d48..a132c37d7334 100644 --- a/drivers/gpu/vga/vga_switcheroo.c +++ b/drivers/gpu/vga/vga_switcheroo.c @@ -380,6 +380,9 @@ int vga_switcheroo_register_audio_client(struct pci_dev *pdev, mutex_unlock(&vgasr_mutex); return -EINVAL; } + /* notify if GPU has been already bound */ + if (ops->gpu_bound) + ops->gpu_bound(pdev, id); } mutex_unlock(&vgasr_mutex); diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index 56ccb1ea7da5..f2c681971201 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -224,6 +224,15 @@ config I2C_NFORCE2_S4985 This driver can also be built as a module. If so, the module will be called i2c-nforce2-s4985. +config I2C_NVIDIA_GPU + tristate "NVIDIA GPU I2C controller" + depends on PCI + help + If you say yes to this option, support will be included for the + NVIDIA GPU I2C controller which is used to communicate with the GPU's + Type-C controller. This driver can also be built as a module called + i2c-nvidia-gpu. + config I2C_SIS5595 tristate "SiS 5595" depends on PCI @@ -752,7 +761,7 @@ config I2C_OCORES config I2C_OMAP tristate "OMAP I2C adapter" - depends on ARCH_OMAP + depends on ARCH_OMAP || ARCH_K3 default y if MACH_OMAP_H3 || MACH_OMAP_OSK help If you say yes to this option, support will be included for the diff --git a/drivers/i2c/busses/Makefile b/drivers/i2c/busses/Makefile index 18b26af82b1c..5f0cb6915969 100644 --- a/drivers/i2c/busses/Makefile +++ b/drivers/i2c/busses/Makefile @@ -19,6 +19,7 @@ obj-$(CONFIG_I2C_ISCH) += i2c-isch.o obj-$(CONFIG_I2C_ISMT) += i2c-ismt.o obj-$(CONFIG_I2C_NFORCE2) += i2c-nforce2.o obj-$(CONFIG_I2C_NFORCE2_S4985) += i2c-nforce2-s4985.o +obj-$(CONFIG_I2C_NVIDIA_GPU) += i2c-nvidia-gpu.o obj-$(CONFIG_I2C_PIIX4) += i2c-piix4.o obj-$(CONFIG_I2C_SIS5595) += i2c-sis5595.o obj-$(CONFIG_I2C_SIS630) += i2c-sis630.o diff --git a/drivers/i2c/busses/i2c-nvidia-gpu.c b/drivers/i2c/busses/i2c-nvidia-gpu.c new file mode 100644 index 000000000000..8822357bca0c --- /dev/null +++ b/drivers/i2c/busses/i2c-nvidia-gpu.c @@ -0,0 +1,368 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Nvidia GPU I2C controller Driver + * + * Copyright (C) 2018 NVIDIA Corporation. All rights reserved. + * Author: Ajay Gupta <ajayg@nvidia.com> + */ +#include <linux/delay.h> +#include <linux/i2c.h> +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/pm.h> +#include <linux/pm_runtime.h> + +#include <asm/unaligned.h> + +/* I2C definitions */ +#define I2C_MST_CNTL 0x00 +#define I2C_MST_CNTL_GEN_START BIT(0) +#define I2C_MST_CNTL_GEN_STOP BIT(1) +#define I2C_MST_CNTL_CMD_READ (1 << 2) +#define I2C_MST_CNTL_CMD_WRITE (2 << 2) +#define I2C_MST_CNTL_BURST_SIZE_SHIFT 6 +#define I2C_MST_CNTL_GEN_NACK BIT(28) +#define I2C_MST_CNTL_STATUS GENMASK(30, 29) +#define I2C_MST_CNTL_STATUS_OKAY (0 << 29) +#define I2C_MST_CNTL_STATUS_NO_ACK (1 << 29) +#define I2C_MST_CNTL_STATUS_TIMEOUT (2 << 29) +#define I2C_MST_CNTL_STATUS_BUS_BUSY (3 << 29) +#define I2C_MST_CNTL_CYCLE_TRIGGER BIT(31) + +#define I2C_MST_ADDR 0x04 + +#define I2C_MST_I2C0_TIMING 0x08 +#define I2C_MST_I2C0_TIMING_SCL_PERIOD_100KHZ 0x10e +#define I2C_MST_I2C0_TIMING_TIMEOUT_CLK_CNT 16 +#define I2C_MST_I2C0_TIMING_TIMEOUT_CLK_CNT_MAX 255 +#define I2C_MST_I2C0_TIMING_TIMEOUT_CHECK BIT(24) + +#define I2C_MST_DATA 0x0c + +#define I2C_MST_HYBRID_PADCTL 0x20 +#define I2C_MST_HYBRID_PADCTL_MODE_I2C BIT(0) +#define I2C_MST_HYBRID_PADCTL_I2C_SCL_INPUT_RCV BIT(14) +#define I2C_MST_HYBRID_PADCTL_I2C_SDA_INPUT_RCV BIT(15) + +struct gpu_i2c_dev { + struct device *dev; + void __iomem *regs; + struct i2c_adapter adapter; + struct i2c_board_info *gpu_ccgx_ucsi; +}; + +static void gpu_enable_i2c_bus(struct gpu_i2c_dev *i2cd) +{ + u32 val; + + /* enable I2C */ + val = readl(i2cd->regs + I2C_MST_HYBRID_PADCTL); + val |= I2C_MST_HYBRID_PADCTL_MODE_I2C | + I2C_MST_HYBRID_PADCTL_I2C_SCL_INPUT_RCV | + I2C_MST_HYBRID_PADCTL_I2C_SDA_INPUT_RCV; + writel(val, i2cd->regs + I2C_MST_HYBRID_PADCTL); + + /* enable 100KHZ mode */ + val = I2C_MST_I2C0_TIMING_SCL_PERIOD_100KHZ; + val |= (I2C_MST_I2C0_TIMING_TIMEOUT_CLK_CNT_MAX + << I2C_MST_I2C0_TIMING_TIMEOUT_CLK_CNT); + val |= I2C_MST_I2C0_TIMING_TIMEOUT_CHECK; + writel(val, i2cd->regs + I2C_MST_I2C0_TIMING); +} + +static int gpu_i2c_check_status(struct gpu_i2c_dev *i2cd) +{ + unsigned long target = jiffies + msecs_to_jiffies(1000); + u32 val; + + do { + val = readl(i2cd->regs + I2C_MST_CNTL); + if (!(val & I2C_MST_CNTL_CYCLE_TRIGGER)) + break; + if ((val & I2C_MST_CNTL_STATUS) != + I2C_MST_CNTL_STATUS_BUS_BUSY) + break; + usleep_range(500, 600); + } while (time_is_after_jiffies(target)); + + if (time_is_before_jiffies(target)) { + dev_err(i2cd->dev, "i2c timeout error %x\n", val); + return -ETIME; + } + + val = readl(i2cd->regs + I2C_MST_CNTL); + switch (val & I2C_MST_CNTL_STATUS) { + case I2C_MST_CNTL_STATUS_OKAY: + return 0; + case I2C_MST_CNTL_STATUS_NO_ACK: + return -EIO; + case I2C_MST_CNTL_STATUS_TIMEOUT: + return -ETIME; + default: + return 0; + } +} + +static int gpu_i2c_read(struct gpu_i2c_dev *i2cd, u8 *data, u16 len) +{ + int status; + u32 val; + + val = I2C_MST_CNTL_GEN_START | I2C_MST_CNTL_CMD_READ | + (len << I2C_MST_CNTL_BURST_SIZE_SHIFT) | + I2C_MST_CNTL_CYCLE_TRIGGER | I2C_MST_CNTL_GEN_NACK; + writel(val, i2cd->regs + I2C_MST_CNTL); + + status = gpu_i2c_check_status(i2cd); + if (status < 0) + return status; + + val = readl(i2cd->regs + I2C_MST_DATA); + switch (len) { + case 1: + data[0] = val; + break; + case 2: + put_unaligned_be16(val, data); + break; + case 3: + put_unaligned_be16(val >> 8, data); + data[2] = val; + break; + case 4: + put_unaligned_be32(val, data); + break; + default: + break; + } + return status; +} + +static int gpu_i2c_start(struct gpu_i2c_dev *i2cd) +{ + writel(I2C_MST_CNTL_GEN_START, i2cd->regs + I2C_MST_CNTL); + return gpu_i2c_check_status(i2cd); +} + +static int gpu_i2c_stop(struct gpu_i2c_dev *i2cd) +{ + writel(I2C_MST_CNTL_GEN_STOP, i2cd->regs + I2C_MST_CNTL); + return gpu_i2c_check_status(i2cd); +} + +static int gpu_i2c_write(struct gpu_i2c_dev *i2cd, u8 data) +{ + u32 val; + + writel(data, i2cd->regs + I2C_MST_DATA); + + val = I2C_MST_CNTL_CMD_WRITE | (1 << I2C_MST_CNTL_BURST_SIZE_SHIFT); + writel(val, i2cd->regs + I2C_MST_CNTL); + + return gpu_i2c_check_status(i2cd); +} + +static int gpu_i2c_master_xfer(struct i2c_adapter *adap, + struct i2c_msg *msgs, int num) +{ + struct gpu_i2c_dev *i2cd = i2c_get_adapdata(adap); + int status, status2; + int i, j; + + /* + * The controller supports maximum 4 byte read due to known + * limitation of sending STOP after every read. + */ + for (i = 0; i < num; i++) { + if (msgs[i].flags & I2C_M_RD) { + /* program client address before starting read */ + writel(msgs[i].addr, i2cd->regs + I2C_MST_ADDR); + /* gpu_i2c_read has implicit start */ + status = gpu_i2c_read(i2cd, msgs[i].buf, msgs[i].len); + if (status < 0) + goto stop; + } else { + u8 addr = i2c_8bit_addr_from_msg(msgs + i); + + status = gpu_i2c_start(i2cd); + if (status < 0) { + if (i == 0) + return status; + goto stop; + } + + status = gpu_i2c_write(i2cd, addr); + if (status < 0) + goto stop; + + for (j = 0; j < msgs[i].len; j++) { + status = gpu_i2c_write(i2cd, msgs[i].buf[j]); + if (status < 0) + goto stop; + } + } + } + status = gpu_i2c_stop(i2cd); + if (status < 0) + return status; + + return i; +stop: + status2 = gpu_i2c_stop(i2cd); + if (status2 < 0) + dev_err(i2cd->dev, "i2c stop failed %d\n", status2); + return status; +} + +static const struct i2c_adapter_quirks gpu_i2c_quirks = { + .max_read_len = 4, + .flags = I2C_AQ_COMB_WRITE_THEN_READ, +}; + +static u32 gpu_i2c_functionality(struct i2c_adapter *adap) +{ + return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL; +} + +static const struct i2c_algorithm gpu_i2c_algorithm = { + .master_xfer = gpu_i2c_master_xfer, + .functionality = gpu_i2c_functionality, +}; + +/* + * This driver is for Nvidia GPU cards with USB Type-C interface. + * We want to identify the cards using vendor ID and class code only + * to avoid dependency of adding product id for any new card which + * requires this driver. + * Currently there is no class code defined for UCSI device over PCI + * so using UNKNOWN class for now and it will be updated when UCSI + * over PCI gets a class code. + * There is no other NVIDIA cards with UNKNOWN class code. Even if the + * driver gets loaded for an undesired card then eventually i2c_read() + * (initiated from UCSI i2c_client) will timeout or UCSI commands will + * timeout. + */ +#define PCI_CLASS_SERIAL_UNKNOWN 0x0c80 +static const struct pci_device_id gpu_i2c_ids[] = { + { PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_SERIAL_UNKNOWN << 8, 0xffffff00}, + { } +}; +MODULE_DEVICE_TABLE(pci, gpu_i2c_ids); + +static int gpu_populate_client(struct gpu_i2c_dev *i2cd, int irq) +{ + struct i2c_client *ccgx_client; + + i2cd->gpu_ccgx_ucsi = devm_kzalloc(i2cd->dev, + sizeof(*i2cd->gpu_ccgx_ucsi), + GFP_KERNEL); + if (!i2cd->gpu_ccgx_ucsi) + return -ENOMEM; + + strlcpy(i2cd->gpu_ccgx_ucsi->type, "ccgx-ucsi", + sizeof(i2cd->gpu_ccgx_ucsi->type)); + i2cd->gpu_ccgx_ucsi->addr = 0x8; + i2cd->gpu_ccgx_ucsi->irq = irq; + ccgx_client = i2c_new_device(&i2cd->adapter, i2cd->gpu_ccgx_ucsi); + if (!ccgx_client) + return -ENODEV; + + return 0; +} + +static int gpu_i2c_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct gpu_i2c_dev *i2cd; + int status; + + i2cd = devm_kzalloc(&pdev->dev, sizeof(*i2cd), GFP_KERNEL); + if (!i2cd) + return -ENOMEM; + + i2cd->dev = &pdev->dev; + dev_set_drvdata(&pdev->dev, i2cd); + + status = pcim_enable_device(pdev); + if (status < 0) { + dev_err(&pdev->dev, "pcim_enable_device failed %d\n", status); + return status; + } + + pci_set_master(pdev); + + i2cd->regs = pcim_iomap(pdev, 0, 0); + if (!i2cd->regs) { + dev_err(&pdev->dev, "pcim_iomap failed\n"); + return -ENOMEM; + } + + status = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI); + if (status < 0) { + dev_err(&pdev->dev, "pci_alloc_irq_vectors err %d\n", status); + return status; + } + + gpu_enable_i2c_bus(i2cd); + + i2c_set_adapdata(&i2cd->adapter, i2cd); + i2cd->adapter.owner = THIS_MODULE; + strlcpy(i2cd->adapter.name, "NVIDIA GPU I2C adapter", + sizeof(i2cd->adapter.name)); + i2cd->adapter.algo = &gpu_i2c_algorithm; + i2cd->adapter.quirks = &gpu_i2c_quirks; + i2cd->adapter.dev.parent = &pdev->dev; + status = i2c_add_adapter(&i2cd->adapter); + if (status < 0) + goto free_irq_vectors; + + status = gpu_populate_client(i2cd, pdev->irq); + if (status < 0) { + dev_err(&pdev->dev, "gpu_populate_client failed %d\n", status); + goto del_adapter; + } + + return 0; + +del_adapter: + i2c_del_adapter(&i2cd->adapter); +free_irq_vectors: + pci_free_irq_vectors(pdev); + return status; +} + +static void gpu_i2c_remove(struct pci_dev *pdev) +{ + struct gpu_i2c_dev *i2cd = dev_get_drvdata(&pdev->dev); + + i2c_del_adapter(&i2cd->adapter); + pci_free_irq_vectors(pdev); +} + +static int gpu_i2c_resume(struct device *dev) +{ + struct gpu_i2c_dev *i2cd = dev_get_drvdata(dev); + + gpu_enable_i2c_bus(i2cd); + return 0; +} + +static UNIVERSAL_DEV_PM_OPS(gpu_i2c_driver_pm, NULL, gpu_i2c_resume, NULL); + +static struct pci_driver gpu_i2c_driver = { + .name = "nvidia-gpu", + .id_table = gpu_i2c_ids, + .probe = gpu_i2c_probe, + .remove = gpu_i2c_remove, + .driver = { + .pm = &gpu_i2c_driver_pm, + }, +}; + +module_pci_driver(gpu_i2c_driver); + +MODULE_AUTHOR("Ajay Gupta <ajayg@nvidia.com>"); +MODULE_DESCRIPTION("Nvidia GPU I2C controller Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 527f55c8c4c7..db075bc0d952 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -571,18 +571,19 @@ static int geni_i2c_probe(struct platform_device *pdev) dev_dbg(&pdev->dev, "i2c fifo/se-dma mode. fifo depth:%d\n", tx_depth); - ret = i2c_add_adapter(&gi2c->adap); - if (ret) { - dev_err(&pdev->dev, "Error adding i2c adapter %d\n", ret); - return ret; - } - gi2c->suspended = 1; pm_runtime_set_suspended(gi2c->se.dev); pm_runtime_set_autosuspend_delay(gi2c->se.dev, I2C_AUTO_SUSPEND_DELAY); pm_runtime_use_autosuspend(gi2c->se.dev); pm_runtime_enable(gi2c->se.dev); + ret = i2c_add_adapter(&gi2c->adap); + if (ret) { + dev_err(&pdev->dev, "Error adding i2c adapter %d\n", ret); + pm_runtime_disable(gi2c->se.dev); + return ret; + } + return 0; } @@ -590,8 +591,8 @@ static int geni_i2c_remove(struct platform_device *pdev) { struct geni_i2c_dev *gi2c = platform_get_drvdata(pdev); - pm_runtime_disable(gi2c->se.dev); i2c_del_adapter(&gi2c->adap); + pm_runtime_disable(gi2c->se.dev); return 0; } diff --git a/drivers/leds/trigger/ledtrig-pattern.c b/drivers/leds/trigger/ledtrig-pattern.c index ce7acd115dd8..1870cf87afe1 100644 --- a/drivers/leds/trigger/ledtrig-pattern.c +++ b/drivers/leds/trigger/ledtrig-pattern.c @@ -75,8 +75,6 @@ static void pattern_trig_timer_function(struct timer_list *t) { struct pattern_trig_data *data = from_timer(data, t, timer); - mutex_lock(&data->lock); - for (;;) { if (!data->is_indefinite && !data->repeat) break; @@ -87,9 +85,10 @@ static void pattern_trig_timer_function(struct timer_list *t) data->curr->brightness); mod_timer(&data->timer, jiffies + msecs_to_jiffies(data->curr->delta_t)); - - /* Skip the tuple with zero duration */ - pattern_trig_update_patterns(data); + if (!data->next->delta_t) { + /* Skip the tuple with zero duration */ + pattern_trig_update_patterns(data); + } /* Select next tuple */ pattern_trig_update_patterns(data); } else { @@ -116,8 +115,6 @@ static void pattern_trig_timer_function(struct timer_list *t) break; } - - mutex_unlock(&data->lock); } static int pattern_trig_start_pattern(struct led_classdev *led_cdev) @@ -176,14 +173,10 @@ static ssize_t repeat_store(struct device *dev, struct device_attribute *attr, if (res < -1 || res == 0) return -EINVAL; - /* - * Clear previous patterns' performence firstly, and remove the timer - * without mutex lock to avoid dead lock. - */ - del_timer_sync(&data->timer); - mutex_lock(&data->lock); + del_timer_sync(&data->timer); + if (data->is_hw_pattern) led_cdev->pattern_clear(led_cdev); @@ -234,14 +227,10 @@ static ssize_t pattern_trig_store_patterns(struct led_classdev *led_cdev, struct pattern_trig_data *data = led_cdev->trigger_data; int ccount, cr, offset = 0, err = 0; - /* - * Clear previous patterns' performence firstly, and remove the timer - * without mutex lock to avoid dead lock. - */ - del_timer_sync(&data->timer); - mutex_lock(&data->lock); + del_timer_sync(&data->timer); + if (data->is_hw_pattern) led_cdev->pattern_clear(led_cdev); diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig index e514d57a0419..aa983422aa97 100644 --- a/drivers/mtd/devices/Kconfig +++ b/drivers/mtd/devices/Kconfig @@ -207,7 +207,7 @@ comment "Disk-On-Chip Device Drivers" config MTD_DOCG3 tristate "M-Systems Disk-On-Chip G3" select BCH - select BCH_CONST_PARAMS + select BCH_CONST_PARAMS if !MTD_NAND_BCH select BITREVERSE help This provides an MTD device driver for the M-Systems DiskOnChip diff --git a/drivers/mtd/maps/sa1100-flash.c b/drivers/mtd/maps/sa1100-flash.c index 784c6e1a0391..fd5fe12d7461 100644 --- a/drivers/mtd/maps/sa1100-flash.c +++ b/drivers/mtd/maps/sa1100-flash.c @@ -221,7 +221,14 @@ static struct sa_info *sa1100_setup_mtd(struct platform_device *pdev, info->mtd = info->subdev[0].mtd; ret = 0; } else if (info->num_subdev > 1) { - struct mtd_info *cdev[nr]; + struct mtd_info **cdev; + + cdev = kmalloc_array(nr, sizeof(*cdev), GFP_KERNEL); + if (!cdev) { + ret = -ENOMEM; + goto err; + } + /* * We detected multiple devices. Concatenate them together. */ @@ -230,6 +237,7 @@ static struct sa_info *sa1100_setup_mtd(struct platform_device *pdev, info->mtd = mtd_concat_create(cdev, info->num_subdev, plat->name); + kfree(cdev); if (info->mtd == NULL) { ret = -ENXIO; goto err; diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 05bd0779fe9b..71050a0b31df 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -590,7 +590,6 @@ retry: /** * panic_nand_wait - [GENERIC] wait until the command is done - * @mtd: MTD device structure * @chip: NAND chip structure * @timeo: timeout * diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c index e24db817154e..d846428ef038 100644 --- a/drivers/mtd/spi-nor/cadence-quadspi.c +++ b/drivers/mtd/spi-nor/cadence-quadspi.c @@ -996,7 +996,7 @@ static int cqspi_direct_read_execute(struct spi_nor *nor, u_char *buf, err_unmap: dma_unmap_single(nor->dev, dma_dst, len, DMA_FROM_DEVICE); - return 0; + return ret; } static ssize_t cqspi_read(struct spi_nor *nor, loff_t from, diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 9407ca5f9443..3e54e31889c7 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -3250,12 +3250,14 @@ static int spi_nor_init_params(struct spi_nor *nor, memcpy(&sfdp_params, params, sizeof(sfdp_params)); memcpy(&prev_map, &nor->erase_map, sizeof(prev_map)); - if (spi_nor_parse_sfdp(nor, &sfdp_params)) + if (spi_nor_parse_sfdp(nor, &sfdp_params)) { + nor->addr_width = 0; /* restore previous erase map */ memcpy(&nor->erase_map, &prev_map, sizeof(nor->erase_map)); - else + } else { memcpy(params, &sfdp_params, sizeof(*params)); + } } return 0; diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c index d721ccf7d8be..38e399e0f30e 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.c +++ b/drivers/net/dsa/mv88e6xxx/global1.c @@ -567,6 +567,8 @@ int mv88e6xxx_g1_stats_clear(struct mv88e6xxx_chip *chip) if (err) return err; + /* Keep the histogram mode bits */ + val &= MV88E6XXX_G1_STATS_OP_HIST_RX_TX; val |= MV88E6XXX_G1_STATS_OP_BUSY | MV88E6XXX_G1_STATS_OP_FLUSH_ALL; err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_STATS_OP, val); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index 6a633c70f603..99ef1daaa4d8 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -407,13 +407,13 @@ static void aq_ethtool_get_pauseparam(struct net_device *ndev, struct ethtool_pauseparam *pause) { struct aq_nic_s *aq_nic = netdev_priv(ndev); + u32 fc = aq_nic->aq_nic_cfg.flow_control; pause->autoneg = 0; - if (aq_nic->aq_hw->aq_nic_cfg->flow_control & AQ_NIC_FC_RX) - pause->rx_pause = 1; - if (aq_nic->aq_hw->aq_nic_cfg->flow_control & AQ_NIC_FC_TX) - pause->tx_pause = 1; + pause->rx_pause = !!(fc & AQ_NIC_FC_RX); + pause->tx_pause = !!(fc & AQ_NIC_FC_TX); + } static int aq_ethtool_set_pauseparam(struct net_device *ndev, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h index e8689241204e..a1e70da358ca 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h @@ -204,6 +204,10 @@ struct aq_hw_ops { int (*hw_get_fw_version)(struct aq_hw_s *self, u32 *fw_version); + int (*hw_set_offload)(struct aq_hw_s *self, + struct aq_nic_cfg_s *aq_nic_cfg); + + int (*hw_set_fc)(struct aq_hw_s *self, u32 fc, u32 tc); }; struct aq_fw_ops { @@ -226,6 +230,8 @@ struct aq_fw_ops { int (*update_stats)(struct aq_hw_s *self); + u32 (*get_flow_control)(struct aq_hw_s *self, u32 *fcmode); + int (*set_flow_control)(struct aq_hw_s *self); int (*set_power)(struct aq_hw_s *self, unsigned int power_state, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c index e3ae29e523f0..7c07eef275eb 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c @@ -99,8 +99,11 @@ static int aq_ndev_set_features(struct net_device *ndev, struct aq_nic_s *aq_nic = netdev_priv(ndev); struct aq_nic_cfg_s *aq_cfg = aq_nic_get_cfg(aq_nic); bool is_lro = false; + int err = 0; + + aq_cfg->features = features; - if (aq_cfg->hw_features & NETIF_F_LRO) { + if (aq_cfg->aq_hw_caps->hw_features & NETIF_F_LRO) { is_lro = features & NETIF_F_LRO; if (aq_cfg->is_lro != is_lro) { @@ -112,8 +115,11 @@ static int aq_ndev_set_features(struct net_device *ndev, } } } + if ((aq_nic->ndev->features ^ features) & NETIF_F_RXCSUM) + err = aq_nic->aq_hw_ops->hw_set_offload(aq_nic->aq_hw, + aq_cfg); - return 0; + return err; } static int aq_ndev_set_mac_address(struct net_device *ndev, void *addr) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 5fed24446687..7abdc0952425 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -118,12 +118,13 @@ void aq_nic_cfg_start(struct aq_nic_s *self) } cfg->link_speed_msk &= cfg->aq_hw_caps->link_speed_msk; - cfg->hw_features = cfg->aq_hw_caps->hw_features; + cfg->features = cfg->aq_hw_caps->hw_features; } static int aq_nic_update_link_status(struct aq_nic_s *self) { int err = self->aq_fw_ops->update_link_status(self->aq_hw); + u32 fc = 0; if (err) return err; @@ -133,6 +134,15 @@ static int aq_nic_update_link_status(struct aq_nic_s *self) AQ_CFG_DRV_NAME, self->link_status.mbps, self->aq_hw->aq_link_status.mbps); aq_nic_update_interrupt_moderation_settings(self); + + /* Driver has to update flow control settings on RX block + * on any link event. + * We should query FW whether it negotiated FC. + */ + if (self->aq_fw_ops->get_flow_control) + self->aq_fw_ops->get_flow_control(self->aq_hw, &fc); + if (self->aq_hw_ops->hw_set_fc) + self->aq_hw_ops->hw_set_fc(self->aq_hw, fc, 0); } self->link_status = self->aq_hw->aq_link_status; @@ -590,7 +600,7 @@ int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev) } } - if (i > 0 && i < AQ_HW_MULTICAST_ADDRESS_MAX) { + if (i > 0 && i <= AQ_HW_MULTICAST_ADDRESS_MAX) { packet_filter |= IFF_MULTICAST; self->mc_list.count = i; self->aq_hw_ops->hw_multicast_list_set(self->aq_hw, @@ -772,7 +782,9 @@ void aq_nic_get_link_ksettings(struct aq_nic_s *self, ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause); - if (self->aq_nic_cfg.flow_control & AQ_NIC_FC_TX) + /* Asym is when either RX or TX, but not both */ + if (!!(self->aq_nic_cfg.flow_control & AQ_NIC_FC_TX) ^ + !!(self->aq_nic_cfg.flow_control & AQ_NIC_FC_RX)) ethtool_link_ksettings_add_link_mode(cmd, advertising, Asym_Pause); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h index c1582f4e8e1b..44ec47a3d60a 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h @@ -23,7 +23,7 @@ struct aq_vec_s; struct aq_nic_cfg_s { const struct aq_hw_caps_s *aq_hw_caps; - u64 hw_features; + u64 features; u32 rxds; /* rx ring size, descriptors # */ u32 txds; /* tx ring size, descriptors # */ u32 vecs; /* vecs==allocated irqs */ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 3db91446cc67..74550ccc7a20 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -172,6 +172,27 @@ bool aq_ring_tx_clean(struct aq_ring_s *self) return !!budget; } +static void aq_rx_checksum(struct aq_ring_s *self, + struct aq_ring_buff_s *buff, + struct sk_buff *skb) +{ + if (!(self->aq_nic->ndev->features & NETIF_F_RXCSUM)) + return; + + if (unlikely(buff->is_cso_err)) { + ++self->stats.rx.errors; + skb->ip_summed = CHECKSUM_NONE; + return; + } + if (buff->is_ip_cso) { + __skb_incr_checksum_unnecessary(skb); + if (buff->is_udp_cso || buff->is_tcp_cso) + __skb_incr_checksum_unnecessary(skb); + } else { + skb->ip_summed = CHECKSUM_NONE; + } +} + #define AQ_SKB_ALIGN SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) int aq_ring_rx_clean(struct aq_ring_s *self, struct napi_struct *napi, @@ -267,18 +288,8 @@ int aq_ring_rx_clean(struct aq_ring_s *self, } skb->protocol = eth_type_trans(skb, ndev); - if (unlikely(buff->is_cso_err)) { - ++self->stats.rx.errors; - skb->ip_summed = CHECKSUM_NONE; - } else { - if (buff->is_ip_cso) { - __skb_incr_checksum_unnecessary(skb); - if (buff->is_udp_cso || buff->is_tcp_cso) - __skb_incr_checksum_unnecessary(skb); - } else { - skb->ip_summed = CHECKSUM_NONE; - } - } + + aq_rx_checksum(self, buff, skb); skb_set_hash(skb, buff->rss_hash, buff->is_hash_l4 ? PKT_HASH_TYPE_L4 : diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 76d25d594a0f..f02592f43fe3 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -100,12 +100,17 @@ static int hw_atl_b0_hw_reset(struct aq_hw_s *self) return err; } +static int hw_atl_b0_set_fc(struct aq_hw_s *self, u32 fc, u32 tc) +{ + hw_atl_rpb_rx_xoff_en_per_tc_set(self, !!(fc & AQ_NIC_FC_RX), tc); + return 0; +} + static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self) { u32 tc = 0U; u32 buff_size = 0U; unsigned int i_priority = 0U; - bool is_rx_flow_control = false; /* TPS Descriptor rate init */ hw_atl_tps_tx_pkt_shed_desc_rate_curr_time_res_set(self, 0x0U); @@ -138,7 +143,6 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self) /* QoS Rx buf size per TC */ tc = 0; - is_rx_flow_control = (AQ_NIC_FC_RX & self->aq_nic_cfg->flow_control); buff_size = HW_ATL_B0_RXBUF_MAX; hw_atl_rpb_rx_pkt_buff_size_per_tc_set(self, buff_size, tc); @@ -150,7 +154,8 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self) (buff_size * (1024U / 32U) * 50U) / 100U, tc); - hw_atl_rpb_rx_xoff_en_per_tc_set(self, is_rx_flow_control ? 1U : 0U, tc); + + hw_atl_b0_set_fc(self, self->aq_nic_cfg->flow_control, tc); /* QoS 802.1p priority -> TC mapping */ for (i_priority = 8U; i_priority--;) @@ -229,8 +234,10 @@ static int hw_atl_b0_hw_offload_set(struct aq_hw_s *self, hw_atl_tpo_tcp_udp_crc_offload_en_set(self, 1); /* RX checksums offloads*/ - hw_atl_rpo_ipv4header_crc_offload_en_set(self, 1); - hw_atl_rpo_tcp_udp_crc_offload_en_set(self, 1); + hw_atl_rpo_ipv4header_crc_offload_en_set(self, !!(aq_nic_cfg->features & + NETIF_F_RXCSUM)); + hw_atl_rpo_tcp_udp_crc_offload_en_set(self, !!(aq_nic_cfg->features & + NETIF_F_RXCSUM)); /* LSO offloads*/ hw_atl_tdm_large_send_offload_en_set(self, 0xFFFFFFFFU); @@ -655,9 +662,9 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self, struct hw_atl_rxd_wb_s *rxd_wb = (struct hw_atl_rxd_wb_s *) &ring->dx_ring[ring->hw_head * HW_ATL_B0_RXD_SIZE]; - unsigned int is_err = 1U; unsigned int is_rx_check_sum_enabled = 0U; unsigned int pkt_type = 0U; + u8 rx_stat = 0U; if (!(rxd_wb->status & 0x1U)) { /* RxD is not done */ break; @@ -665,35 +672,35 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self, buff = &ring->buff_ring[ring->hw_head]; - is_err = (0x0000003CU & rxd_wb->status); + rx_stat = (0x0000003CU & rxd_wb->status) >> 2; is_rx_check_sum_enabled = (rxd_wb->type) & (0x3U << 19); - is_err &= ~0x20U; /* exclude validity bit */ pkt_type = 0xFFU & (rxd_wb->type >> 4); - if (is_rx_check_sum_enabled) { - if (0x0U == (pkt_type & 0x3U)) - buff->is_ip_cso = (is_err & 0x08U) ? 0U : 1U; + if (is_rx_check_sum_enabled & BIT(0) && + (0x0U == (pkt_type & 0x3U))) + buff->is_ip_cso = (rx_stat & BIT(1)) ? 0U : 1U; + if (is_rx_check_sum_enabled & BIT(1)) { if (0x4U == (pkt_type & 0x1CU)) - buff->is_udp_cso = buff->is_cso_err ? 0U : 1U; + buff->is_udp_cso = (rx_stat & BIT(2)) ? 0U : + !!(rx_stat & BIT(3)); else if (0x0U == (pkt_type & 0x1CU)) - buff->is_tcp_cso = buff->is_cso_err ? 0U : 1U; - - /* Checksum offload workaround for small packets */ - if (rxd_wb->pkt_len <= 60) { - buff->is_ip_cso = 0U; - buff->is_cso_err = 0U; - } + buff->is_tcp_cso = (rx_stat & BIT(2)) ? 0U : + !!(rx_stat & BIT(3)); + } + buff->is_cso_err = !!(rx_stat & 0x6); + /* Checksum offload workaround for small packets */ + if (unlikely(rxd_wb->pkt_len <= 60)) { + buff->is_ip_cso = 0U; + buff->is_cso_err = 0U; } - - is_err &= ~0x18U; dma_unmap_page(ndev, buff->pa, buff->len, DMA_FROM_DEVICE); - if (is_err || rxd_wb->type & 0x1000U) { - /* status error or DMA error */ + if ((rx_stat & BIT(0)) || rxd_wb->type & 0x1000U) { + /* MAC error or DMA error */ buff->is_error = 1U; } else { if (self->aq_nic_cfg->is_rss) { @@ -915,6 +922,12 @@ static int hw_atl_b0_hw_interrupt_moderation_set(struct aq_hw_s *self) static int hw_atl_b0_hw_stop(struct aq_hw_s *self) { hw_atl_b0_hw_irq_disable(self, HW_ATL_B0_INT_MASK); + + /* Invalidate Descriptor Cache to prevent writing to the cached + * descriptors and to the data pointer of those descriptors + */ + hw_atl_rdm_rx_dma_desc_cache_init_set(self, 1); + return aq_hw_err_from_flags(self); } @@ -963,4 +976,6 @@ const struct aq_hw_ops hw_atl_ops_b0 = { .hw_get_regs = hw_atl_utils_hw_get_regs, .hw_get_hw_stats = hw_atl_utils_get_hw_stats, .hw_get_fw_version = hw_atl_utils_get_fw_version, + .hw_set_offload = hw_atl_b0_hw_offload_set, + .hw_set_fc = hw_atl_b0_set_fc, }; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c index be0a3a90dfad..5502ec5f0f69 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c @@ -619,6 +619,14 @@ void hw_atl_rpb_rx_flow_ctl_mode_set(struct aq_hw_s *aq_hw, u32 rx_flow_ctl_mode HW_ATL_RPB_RX_FC_MODE_SHIFT, rx_flow_ctl_mode); } +void hw_atl_rdm_rx_dma_desc_cache_init_set(struct aq_hw_s *aq_hw, u32 init) +{ + aq_hw_write_reg_bit(aq_hw, HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_ADR, + HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_MSK, + HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_SHIFT, + init); +} + void hw_atl_rpb_rx_pkt_buff_size_per_tc_set(struct aq_hw_s *aq_hw, u32 rx_pkt_buff_size_per_tc, u32 buffer) { diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h index 7056c7342afc..41f239928c15 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h @@ -325,6 +325,9 @@ void hw_atl_rpb_rx_pkt_buff_size_per_tc_set(struct aq_hw_s *aq_hw, u32 rx_pkt_buff_size_per_tc, u32 buffer); +/* set rdm rx dma descriptor cache init */ +void hw_atl_rdm_rx_dma_desc_cache_init_set(struct aq_hw_s *aq_hw, u32 init); + /* set rx xoff enable (per tc) */ void hw_atl_rpb_rx_xoff_en_per_tc_set(struct aq_hw_s *aq_hw, u32 rx_xoff_en_per_tc, u32 buffer); diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h index 716674a9b729..a715fa317b1c 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h @@ -293,6 +293,24 @@ /* default value of bitfield desc{d}_reset */ #define HW_ATL_RDM_DESCDRESET_DEFAULT 0x0 +/* rdm_desc_init_i bitfield definitions + * preprocessor definitions for the bitfield rdm_desc_init_i. + * port="pif_rdm_desc_init_i" + */ + +/* register address for bitfield rdm_desc_init_i */ +#define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_ADR 0x00005a00 +/* bitmask for bitfield rdm_desc_init_i */ +#define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_MSK 0xffffffff +/* inverted bitmask for bitfield rdm_desc_init_i */ +#define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_MSKN 0x00000000 +/* lower bit position of bitfield rdm_desc_init_i */ +#define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_SHIFT 0 +/* width of bitfield rdm_desc_init_i */ +#define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_WIDTH 32 +/* default value of bitfield rdm_desc_init_i */ +#define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_DEFAULT 0x0 + /* rx int_desc_wrb_en bitfield definitions * preprocessor definitions for the bitfield "int_desc_wrb_en". * port="pif_rdm_int_desc_wrb_en_i" diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c index 096ca5730887..7de3220d9cab 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c @@ -30,6 +30,8 @@ #define HW_ATL_FW2X_MPI_STATE_ADDR 0x370 #define HW_ATL_FW2X_MPI_STATE2_ADDR 0x374 +#define HW_ATL_FW2X_CAP_PAUSE BIT(CAPS_HI_PAUSE) +#define HW_ATL_FW2X_CAP_ASYM_PAUSE BIT(CAPS_HI_ASYMMETRIC_PAUSE) #define HW_ATL_FW2X_CAP_SLEEP_PROXY BIT(CAPS_HI_SLEEP_PROXY) #define HW_ATL_FW2X_CAP_WOL BIT(CAPS_HI_WOL) @@ -451,6 +453,24 @@ static int aq_fw2x_set_flow_control(struct aq_hw_s *self) return 0; } +static u32 aq_fw2x_get_flow_control(struct aq_hw_s *self, u32 *fcmode) +{ + u32 mpi_state = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR); + + if (mpi_state & HW_ATL_FW2X_CAP_PAUSE) + if (mpi_state & HW_ATL_FW2X_CAP_ASYM_PAUSE) + *fcmode = AQ_NIC_FC_RX; + else + *fcmode = AQ_NIC_FC_RX | AQ_NIC_FC_TX; + else + if (mpi_state & HW_ATL_FW2X_CAP_ASYM_PAUSE) + *fcmode = AQ_NIC_FC_TX; + else + *fcmode = 0; + + return 0; +} + const struct aq_fw_ops aq_fw_2x_ops = { .init = aq_fw2x_init, .deinit = aq_fw2x_deinit, @@ -465,4 +485,5 @@ const struct aq_fw_ops aq_fw_2x_ops = { .set_eee_rate = aq_fw2x_set_eee_rate, .get_eee_rate = aq_fw2x_get_eee_rate, .set_flow_control = aq_fw2x_set_flow_control, + .get_flow_control = aq_fw2x_get_flow_control }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 3f96aa30068e..20fcf0d1c2ce 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -3760,7 +3760,8 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle) /* Hardware table is only clear when pf resets */ if (!(handle->flags & HNAE3_SUPPORT_VF)) { ret = hns3_restore_vlan(netdev); - return ret; + if (ret) + return ret; } ret = hns3_restore_fd_rules(netdev); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 7893beffcc71..c9d5d0a7fbf1 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1545,7 +1545,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_crq.v1.sge_len = cpu_to_be32(skb->len); tx_crq.v1.ioba = cpu_to_be64(data_dma_addr); - if (adapter->vlan_header_insertion) { + if (adapter->vlan_header_insertion && skb_vlan_tag_present(skb)) { tx_crq.v1.flags2 |= IBMVNIC_TX_VLAN_INSERT; tx_crq.v1.vlan_id = cpu_to_be16(skb->vlan_tci); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index bc71a21c1dc2..21c2688d6308 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -12249,6 +12249,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) NETIF_F_GSO_GRE | NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_PARTIAL | + NETIF_F_GSO_IPXIP4 | + NETIF_F_GSO_IPXIP6 | NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_SCTP_CRC | @@ -12266,13 +12268,13 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) /* record features VLANs can make use of */ netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID; - if (!(pf->flags & I40E_FLAG_MFP_ENABLED)) - netdev->hw_features |= NETIF_F_NTUPLE | NETIF_F_HW_TC; - hw_features = hw_enc_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; + if (!(pf->flags & I40E_FLAG_MFP_ENABLED)) + hw_features |= NETIF_F_NTUPLE | NETIF_F_HW_TC; + netdev->hw_features |= hw_features; netdev->features |= hw_features | NETIF_F_HW_VLAN_CTAG_FILTER; diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 4c4b5717a627..b8548370f1c7 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -76,6 +76,8 @@ extern const char ice_drv_ver[]; #define ICE_MIN_INTR_PER_VF (ICE_MIN_QS_PER_VF + 1) #define ICE_DFLT_INTR_PER_VF (ICE_DFLT_QS_PER_VF + 1) +#define ICE_MAX_RESET_WAIT 20 + #define ICE_VSIQF_HKEY_ARRAY_SIZE ((VSIQF_HKEY_MAX_INDEX + 1) * 4) #define ICE_DFLT_NETIF_M (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK) @@ -189,7 +191,6 @@ struct ice_vsi { u64 tx_linearize; DECLARE_BITMAP(state, __ICE_STATE_NBITS); DECLARE_BITMAP(flags, ICE_VSI_FLAG_NBITS); - unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; unsigned int current_netdev_flags; u32 tx_restart; u32 tx_busy; @@ -369,5 +370,6 @@ int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size); int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size); void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size); void ice_print_link_msg(struct ice_vsi *vsi, bool isup); +void ice_napi_del(struct ice_vsi *vsi); #endif /* _ICE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 8cd6a2401fd9..554fd707a6d6 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -811,6 +811,9 @@ void ice_deinit_hw(struct ice_hw *hw) /* Attempt to disable FW logging before shutting down control queues */ ice_cfg_fw_log(hw, false); ice_shutdown_all_ctrlq(hw); + + /* Clear VSI contexts if not already cleared */ + ice_clear_all_vsi_ctx(hw); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 96923580f2a6..648acdb4c644 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -1517,10 +1517,15 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) } if (!test_bit(__ICE_DOWN, pf->state)) { - /* Give it a little more time to try to come back */ + /* Give it a little more time to try to come back. If still + * down, restart autoneg link or reinitialize the interface. + */ msleep(75); if (!test_bit(__ICE_DOWN, pf->state)) return ice_nway_reset(netdev); + + ice_down(vsi); + ice_up(vsi); } return err; diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 5fdea6ec7675..596b9fb1c510 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -242,6 +242,8 @@ #define GLNVM_ULD 0x000B6008 #define GLNVM_ULD_CORER_DONE_M BIT(3) #define GLNVM_ULD_GLOBR_DONE_M BIT(4) +#define GLPCI_CNF2 0x000BE004 +#define GLPCI_CNF2_CACHELINE_SIZE_M BIT(1) #define PF_FUNC_RID 0x0009E880 #define PF_FUNC_RID_FUNC_NUM_S 0 #define PF_FUNC_RID_FUNC_NUM_M ICE_M(0x7, 0) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 5bacad01f0c9..1041fa2a7767 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1997,7 +1997,7 @@ int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena) status = ice_update_vsi(&vsi->back->hw, vsi->idx, ctxt, NULL); if (status) { netdev_err(vsi->netdev, "%sabling VLAN pruning on VSI handle: %d, VSI HW ID: %d failed, err = %d, aq_err = %d\n", - ena ? "Ena" : "Dis", vsi->idx, vsi->vsi_num, status, + ena ? "En" : "Dis", vsi->idx, vsi->vsi_num, status, vsi->back->hw.adminq.sq_last_status); goto err_out; } @@ -2458,6 +2458,7 @@ int ice_vsi_release(struct ice_vsi *vsi) * on this wq */ if (vsi->netdev && !ice_is_reset_in_progress(pf->state)) { + ice_napi_del(vsi); unregister_netdev(vsi->netdev); free_netdev(vsi->netdev); vsi->netdev = NULL; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 05993451147a..333312a1d595 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -1465,7 +1465,7 @@ skip_req_irq: * ice_napi_del - Remove NAPI handler for the VSI * @vsi: VSI for which NAPI handler is to be removed */ -static void ice_napi_del(struct ice_vsi *vsi) +void ice_napi_del(struct ice_vsi *vsi) { int v_idx; @@ -1622,7 +1622,6 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev, { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; - int ret; if (vid >= VLAN_N_VID) { netdev_err(netdev, "VLAN id requested %d is out of range %d\n", @@ -1635,7 +1634,8 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev, /* Enable VLAN pruning when VLAN 0 is added */ if (unlikely(!vid)) { - ret = ice_cfg_vlan_pruning(vsi, true); + int ret = ice_cfg_vlan_pruning(vsi, true); + if (ret) return ret; } @@ -1644,12 +1644,7 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev, * needed to continue allowing all untagged packets since VLAN prune * list is applied to all packets by the switch */ - ret = ice_vsi_add_vlan(vsi, vid); - - if (!ret) - set_bit(vid, vsi->active_vlans); - - return ret; + return ice_vsi_add_vlan(vsi, vid); } /** @@ -1677,8 +1672,6 @@ static int ice_vlan_rx_kill_vid(struct net_device *netdev, if (status) return status; - clear_bit(vid, vsi->active_vlans); - /* Disable VLAN pruning when VLAN 0 is removed */ if (unlikely(!vid)) status = ice_cfg_vlan_pruning(vsi, false); @@ -2002,6 +1995,22 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf) } /** + * ice_verify_cacheline_size - verify driver's assumption of 64 Byte cache lines + * @pf: pointer to the PF structure + * + * There is no error returned here because the driver should be able to handle + * 128 Byte cache lines, so we only print a warning in case issues are seen, + * specifically with Tx. + */ +static void ice_verify_cacheline_size(struct ice_pf *pf) +{ + if (rd32(&pf->hw, GLPCI_CNF2) & GLPCI_CNF2_CACHELINE_SIZE_M) + dev_warn(&pf->pdev->dev, + "%d Byte cache line assumption is invalid, driver may have Tx timeouts!\n", + ICE_CACHE_LINE_BYTES); +} + +/** * ice_probe - Device initialization routine * @pdev: PCI device information struct * @ent: entry in ice_pci_tbl @@ -2151,6 +2160,8 @@ static int ice_probe(struct pci_dev *pdev, /* since everything is good, start the service timer */ mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period)); + ice_verify_cacheline_size(pf); + return 0; err_alloc_sw_unroll: @@ -2182,6 +2193,12 @@ static void ice_remove(struct pci_dev *pdev) if (!pf) return; + for (i = 0; i < ICE_MAX_RESET_WAIT; i++) { + if (!ice_is_reset_in_progress(pf->state)) + break; + msleep(100); + } + set_bit(__ICE_DOWN, pf->state); ice_service_task_stop(pf); @@ -2510,31 +2527,6 @@ static int ice_vsi_vlan_setup(struct ice_vsi *vsi) } /** - * ice_restore_vlan - Reinstate VLANs when vsi/netdev comes back up - * @vsi: the VSI being brought back up - */ -static int ice_restore_vlan(struct ice_vsi *vsi) -{ - int err; - u16 vid; - - if (!vsi->netdev) - return -EINVAL; - - err = ice_vsi_vlan_setup(vsi); - if (err) - return err; - - for_each_set_bit(vid, vsi->active_vlans, VLAN_N_VID) { - err = ice_vlan_rx_add_vid(vsi->netdev, htons(ETH_P_8021Q), vid); - if (err) - break; - } - - return err; -} - -/** * ice_vsi_cfg - Setup the VSI * @vsi: the VSI being configured * @@ -2546,7 +2538,9 @@ static int ice_vsi_cfg(struct ice_vsi *vsi) if (vsi->netdev) { ice_set_rx_mode(vsi->netdev); - err = ice_restore_vlan(vsi); + + err = ice_vsi_vlan_setup(vsi); + if (err) return err; } @@ -3296,7 +3290,7 @@ static void ice_rebuild(struct ice_pf *pf) struct device *dev = &pf->pdev->dev; struct ice_hw *hw = &pf->hw; enum ice_status ret; - int err; + int err, i; if (test_bit(__ICE_DOWN, pf->state)) goto clear_recovery; @@ -3370,6 +3364,22 @@ static void ice_rebuild(struct ice_pf *pf) } ice_reset_all_vfs(pf, true); + + for (i = 0; i < pf->num_alloc_vsi; i++) { + bool link_up; + + if (!pf->vsi[i] || pf->vsi[i]->type != ICE_VSI_PF) + continue; + ice_get_link_status(pf->vsi[i]->port_info, &link_up); + if (link_up) { + netif_carrier_on(pf->vsi[i]->netdev); + netif_tx_wake_all_queues(pf->vsi[i]->netdev); + } else { + netif_carrier_off(pf->vsi[i]->netdev); + netif_tx_stop_all_queues(pf->vsi[i]->netdev); + } + } + /* if we get here, reset flow is successful */ clear_bit(__ICE_RESET_FAILED, pf->state); return; diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 33403f39f1b3..40c9c6558956 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -348,6 +348,18 @@ static void ice_clear_vsi_ctx(struct ice_hw *hw, u16 vsi_handle) } /** + * ice_clear_all_vsi_ctx - clear all the VSI context entries + * @hw: pointer to the hw struct + */ +void ice_clear_all_vsi_ctx(struct ice_hw *hw) +{ + u16 i; + + for (i = 0; i < ICE_MAX_VSI; i++) + ice_clear_vsi_ctx(hw, i); +} + +/** * ice_add_vsi - add VSI context to the hardware and VSI handle list * @hw: pointer to the hw struct * @vsi_handle: unique VSI handle provided by drivers diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index b88d96a1ef69..d5ef0bd58bf9 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -190,6 +190,8 @@ ice_update_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, struct ice_sq_cd *cd); bool ice_is_vsi_valid(struct ice_hw *hw, u16 vsi_handle); struct ice_vsi_ctx *ice_get_vsi_ctx(struct ice_hw *hw, u16 vsi_handle); +void ice_clear_all_vsi_ctx(struct ice_hw *hw); +/* Switch config */ enum ice_status ice_get_initial_sw_cfg(struct ice_hw *hw); /* Switch/bridge related commands */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 5dae968d853e..fe5bbabbb41e 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1520,7 +1520,7 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off) /* update gso_segs and bytecount */ first->gso_segs = skb_shinfo(skb)->gso_segs; - first->bytecount = (first->gso_segs - 1) * off->header_len; + first->bytecount += (first->gso_segs - 1) * off->header_len; cd_tso_len = skb->len - off->header_len; cd_mss = skb_shinfo(skb)->gso_size; @@ -1556,15 +1556,15 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off) * magnitude greater than our largest possible GSO size. * * This would then be implemented as: - * return (((size >> 12) * 85) >> 8) + 1; + * return (((size >> 12) * 85) >> 8) + ICE_DESCS_FOR_SKB_DATA_PTR; * * Since multiplication and division are commutative, we can reorder * operations into: - * return ((size * 85) >> 20) + 1; + * return ((size * 85) >> 20) + ICE_DESCS_FOR_SKB_DATA_PTR; */ static unsigned int ice_txd_use_count(unsigned int size) { - return ((size * 85) >> 20) + 1; + return ((size * 85) >> 20) + ICE_DESCS_FOR_SKB_DATA_PTR; } /** @@ -1706,7 +1706,8 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring) * + 1 desc for context descriptor, * otherwise try next time */ - if (ice_maybe_stop_tx(tx_ring, count + 4 + 1)) { + if (ice_maybe_stop_tx(tx_ring, count + ICE_DESCS_PER_CACHE_LINE + + ICE_DESCS_FOR_CTX_DESC)) { tx_ring->tx_stats.tx_busy++; return NETDEV_TX_BUSY; } diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 1d0f58bd389b..75d0eaf6c9dd 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -22,8 +22,21 @@ #define ICE_RX_BUF_WRITE 16 /* Must be power of 2 */ #define ICE_MAX_TXQ_PER_TXQG 128 -/* Tx Descriptors needed, worst case */ -#define DESC_NEEDED (MAX_SKB_FRAGS + 4) +/* We are assuming that the cache line is always 64 Bytes here for ice. + * In order to make sure that is a correct assumption there is a check in probe + * to print a warning if the read from GLPCI_CNF2 tells us that the cache line + * size is 128 bytes. We do it this way because we do not want to read the + * GLPCI_CNF2 register or a variable containing the value on every pass through + * the Tx path. + */ +#define ICE_CACHE_LINE_BYTES 64 +#define ICE_DESCS_PER_CACHE_LINE (ICE_CACHE_LINE_BYTES / \ + sizeof(struct ice_tx_desc)) +#define ICE_DESCS_FOR_CTX_DESC 1 +#define ICE_DESCS_FOR_SKB_DATA_PTR 1 +/* Tx descriptors needed, worst case */ +#define DESC_NEEDED (MAX_SKB_FRAGS + ICE_DESCS_FOR_CTX_DESC + \ + ICE_DESCS_PER_CACHE_LINE + ICE_DESCS_FOR_SKB_DATA_PTR) #define ICE_DESC_UNUSED(R) \ ((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ (R)->next_to_clean - (R)->next_to_use - 1) diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 12f9432abf11..f4dbc81c1988 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -92,12 +92,12 @@ struct ice_link_status { u64 phy_type_low; u16 max_frame_size; u16 link_speed; + u16 req_speeds; u8 lse_ena; /* Link Status Event notification */ u8 link_info; u8 an_info; u8 ext_info; u8 pacing; - u8 req_speeds; /* Refer to #define from module_type[ICE_MODULE_TYPE_TOTAL_BYTE] of * ice_aqc_get_phy_caps structure */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 45f10f8f01dc..e71065f9d391 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -348,7 +348,7 @@ static int ice_vsi_set_pvid(struct ice_vsi *vsi, u16 vid) struct ice_vsi_ctx ctxt = { 0 }; enum ice_status status; - ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_TAGGED | + ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_UNTAGGED | ICE_AQ_VSI_PVLAN_INSERT_PVID | ICE_AQ_VSI_VLAN_EMOD_STR; ctxt.info.pvid = cpu_to_le16(vid); @@ -2171,7 +2171,6 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) if (!ice_vsi_add_vlan(vsi, vid)) { vf->num_vlan++; - set_bit(vid, vsi->active_vlans); /* Enable VLAN pruning when VLAN 0 is added */ if (unlikely(!vid)) @@ -2190,7 +2189,6 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) */ if (!ice_vsi_kill_vlan(vsi, vid)) { vf->num_vlan--; - clear_bit(vid, vsi->active_vlans); /* Disable VLAN pruning when removing VLAN 0 */ if (unlikely(!vid)) diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 29ced6b74d36..2b95dc9c7a6a 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -53,13 +53,15 @@ * 2^40 * 10^-9 / 60 = 18.3 minutes. * * SYSTIM is converted to real time using a timecounter. As - * timecounter_cyc2time() allows old timestamps, the timecounter - * needs to be updated at least once per half of the SYSTIM interval. - * Scheduling of delayed work is not very accurate, so we aim for 8 - * minutes to be sure the actual interval is shorter than 9.16 minutes. + * timecounter_cyc2time() allows old timestamps, the timecounter needs + * to be updated at least once per half of the SYSTIM interval. + * Scheduling of delayed work is not very accurate, and also the NIC + * clock can be adjusted to run up to 6% faster and the system clock + * up to 10% slower, so we aim for 6 minutes to be sure the actual + * interval in the NIC time is shorter than 9.16 minutes. */ -#define IGB_SYSTIM_OVERFLOW_PERIOD (HZ * 60 * 8) +#define IGB_SYSTIM_OVERFLOW_PERIOD (HZ * 60 * 6) #define IGB_PTP_TX_TIMEOUT (HZ * 15) #define INCPERIOD_82576 BIT(E1000_TIMINCA_16NS_SHIFT) #define INCVALUE_82576_MASK GENMASK(E1000_TIMINCA_16NS_SHIFT - 1, 0) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 5bfd349bf41a..3ba672e9e353 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -494,7 +494,7 @@ struct mvneta_port { #if defined(__LITTLE_ENDIAN) struct mvneta_tx_desc { u32 command; /* Options used by HW for packet transmitting.*/ - u16 reserverd1; /* csum_l4 (for future use) */ + u16 reserved1; /* csum_l4 (for future use) */ u16 data_size; /* Data size of transmitted packet in bytes */ u32 buf_phys_addr; /* Physical addr of transmitted buffer */ u32 reserved2; /* hw_cmd - (for future use, PMT) */ @@ -519,7 +519,7 @@ struct mvneta_rx_desc { #else struct mvneta_tx_desc { u16 data_size; /* Data size of transmitted packet in bytes */ - u16 reserverd1; /* csum_l4 (for future use) */ + u16 reserved1; /* csum_l4 (for future use) */ u32 command; /* Options used by HW for packet transmitting.*/ u32 reserved2; /* hw_cmd - (for future use, PMT) */ u32 buf_phys_addr; /* Physical addr of transmitted buffer */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c index cc1b373c0ace..46dc93d3b9b5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c +++ b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c @@ -147,7 +147,8 @@ qed_sp_fcoe_func_start(struct qed_hwfn *p_hwfn, "Cannot satisfy CQ amount. CQs requested %d, CQs available %d. Aborting function start\n", fcoe_pf_params->num_cqs, p_hwfn->hw_info.feat_num[QED_FCOE_CQ]); - return -EINVAL; + rc = -EINVAL; + goto err; } p_data->mtu = cpu_to_le16(fcoe_pf_params->mtu); @@ -156,14 +157,14 @@ qed_sp_fcoe_func_start(struct qed_hwfn *p_hwfn, rc = qed_cxt_acquire_cid(p_hwfn, PROTOCOLID_FCOE, &dummy_cid); if (rc) - return rc; + goto err; cxt_info.iid = dummy_cid; rc = qed_cxt_get_cid_info(p_hwfn, &cxt_info); if (rc) { DP_NOTICE(p_hwfn, "Cannot find context info for dummy cid=%d\n", dummy_cid); - return rc; + goto err; } p_cxt = cxt_info.p_cxt; SET_FIELD(p_cxt->tstorm_ag_context.flags3, @@ -240,6 +241,10 @@ qed_sp_fcoe_func_start(struct qed_hwfn *p_hwfn, rc = qed_spq_post(p_hwfn, p_ent, NULL); return rc; + +err: + qed_sp_destroy_request(p_hwfn, p_ent); + return rc; } static int diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c index 1135387bd99d..4f8a685d1a55 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c @@ -200,6 +200,7 @@ qed_sp_iscsi_func_start(struct qed_hwfn *p_hwfn, "Cannot satisfy CQ amount. Queues requested %d, CQs available %d. Aborting function start\n", p_params->num_queues, p_hwfn->hw_info.feat_num[QED_ISCSI_CQ]); + qed_sp_destroy_request(p_hwfn, p_ent); return -EINVAL; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 82a1bd1f8a8c..67c02ea93906 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -740,8 +740,7 @@ int qed_sp_vport_update(struct qed_hwfn *p_hwfn, rc = qed_sp_vport_update_rss(p_hwfn, p_ramrod, p_rss_params); if (rc) { - /* Return spq entry which is taken in qed_sp_init_request()*/ - qed_spq_return_entry(p_hwfn, p_ent); + qed_sp_destroy_request(p_hwfn, p_ent); return rc; } @@ -1355,6 +1354,7 @@ qed_filter_ucast_common(struct qed_hwfn *p_hwfn, DP_NOTICE(p_hwfn, "%d is not supported yet\n", p_filter_cmd->opcode); + qed_sp_destroy_request(p_hwfn, *pp_ent); return -EINVAL; } @@ -2056,13 +2056,13 @@ qed_configure_rfs_ntuple_filter(struct qed_hwfn *p_hwfn, } else { rc = qed_fw_vport(p_hwfn, p_params->vport_id, &abs_vport_id); if (rc) - return rc; + goto err; if (p_params->qid != QED_RFS_NTUPLE_QID_RSS) { rc = qed_fw_l2_queue(p_hwfn, p_params->qid, &abs_rx_q_id); if (rc) - return rc; + goto err; p_ramrod->rx_qid_valid = 1; p_ramrod->rx_qid = cpu_to_le16(abs_rx_q_id); @@ -2083,6 +2083,10 @@ qed_configure_rfs_ntuple_filter(struct qed_hwfn *p_hwfn, (u64)p_params->addr, p_params->length); return qed_spq_post(p_hwfn, p_ent, NULL); + +err: + qed_sp_destroy_request(p_hwfn, p_ent); + return rc; } int qed_get_rxq_coalesce(struct qed_hwfn *p_hwfn, diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index c71391b9c757..62113438c880 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -1514,6 +1514,7 @@ qed_rdma_register_tid(void *rdma_cxt, default: rc = -EINVAL; DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "rc = %d\n", rc); + qed_sp_destroy_request(p_hwfn, p_ent); return rc; } SET_FIELD(p_ramrod->flags1, diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c index f9167d1354bb..e49fada85410 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_roce.c +++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c @@ -745,6 +745,7 @@ static int qed_roce_sp_destroy_qp_responder(struct qed_hwfn *p_hwfn, DP_NOTICE(p_hwfn, "qed destroy responder failed: cannot allocate memory (ramrod). rc = %d\n", rc); + qed_sp_destroy_request(p_hwfn, p_ent); return rc; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h index e95431f6acd4..3157c0d99441 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h @@ -167,6 +167,9 @@ struct qed_spq_entry { enum spq_mode comp_mode; struct qed_spq_comp_cb comp_cb; struct qed_spq_comp_done comp_done; /* SPQ_MODE_EBLOCK */ + + /* Posted entry for unlimited list entry in EBLOCK mode */ + struct qed_spq_entry *post_ent; }; struct qed_eq { @@ -396,6 +399,17 @@ struct qed_sp_init_data { struct qed_spq_comp_cb *p_comp_data; }; +/** + * @brief Returns a SPQ entry to the pool / frees the entry if allocated. + * Should be called on in error flows after initializing the SPQ entry + * and before posting it. + * + * @param p_hwfn + * @param p_ent + */ +void qed_sp_destroy_request(struct qed_hwfn *p_hwfn, + struct qed_spq_entry *p_ent); + int qed_sp_init_request(struct qed_hwfn *p_hwfn, struct qed_spq_entry **pp_ent, u8 cmd, diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c index 77b6248ad3b9..888274fa208b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c @@ -47,6 +47,19 @@ #include "qed_sp.h" #include "qed_sriov.h" +void qed_sp_destroy_request(struct qed_hwfn *p_hwfn, + struct qed_spq_entry *p_ent) +{ + /* qed_spq_get_entry() can either get an entry from the free_pool, + * or, if no entries are left, allocate a new entry and add it to + * the unlimited_pending list. + */ + if (p_ent->queue == &p_hwfn->p_spq->unlimited_pending) + kfree(p_ent); + else + qed_spq_return_entry(p_hwfn, p_ent); +} + int qed_sp_init_request(struct qed_hwfn *p_hwfn, struct qed_spq_entry **pp_ent, u8 cmd, u8 protocol, struct qed_sp_init_data *p_data) @@ -80,7 +93,7 @@ int qed_sp_init_request(struct qed_hwfn *p_hwfn, case QED_SPQ_MODE_BLOCK: if (!p_data->p_comp_data) - return -EINVAL; + goto err; p_ent->comp_cb.cookie = p_data->p_comp_data->cookie; break; @@ -95,7 +108,7 @@ int qed_sp_init_request(struct qed_hwfn *p_hwfn, default: DP_NOTICE(p_hwfn, "Unknown SPQE completion mode %d\n", p_ent->comp_mode); - return -EINVAL; + goto err; } DP_VERBOSE(p_hwfn, QED_MSG_SPQ, @@ -109,6 +122,11 @@ int qed_sp_init_request(struct qed_hwfn *p_hwfn, memset(&p_ent->ramrod, 0, sizeof(p_ent->ramrod)); return 0; + +err: + qed_sp_destroy_request(p_hwfn, p_ent); + + return -EINVAL; } static enum tunnel_clss qed_tunn_clss_to_fw_clss(u8 type) diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index c4a6274dd625..0a9c5bb0fa48 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -142,6 +142,7 @@ static int qed_spq_block(struct qed_hwfn *p_hwfn, DP_INFO(p_hwfn, "Ramrod is stuck, requesting MCP drain\n"); rc = qed_mcp_drain(p_hwfn, p_ptt); + qed_ptt_release(p_hwfn, p_ptt); if (rc) { DP_NOTICE(p_hwfn, "MCP drain failed\n"); goto err; @@ -150,18 +151,15 @@ static int qed_spq_block(struct qed_hwfn *p_hwfn, /* Retry after drain */ rc = __qed_spq_block(p_hwfn, p_ent, p_fw_ret, true); if (!rc) - goto out; + return 0; comp_done = (struct qed_spq_comp_done *)p_ent->comp_cb.cookie; - if (comp_done->done == 1) + if (comp_done->done == 1) { if (p_fw_ret) *p_fw_ret = comp_done->fw_return_code; -out: - qed_ptt_release(p_hwfn, p_ptt); - return 0; - + return 0; + } err: - qed_ptt_release(p_hwfn, p_ptt); DP_NOTICE(p_hwfn, "Ramrod is stuck [CID %08x cmd %02x protocol %02x echo %04x]\n", le32_to_cpu(p_ent->elem.hdr.cid), @@ -685,6 +683,8 @@ static int qed_spq_add_entry(struct qed_hwfn *p_hwfn, /* EBLOCK responsible to free the allocated p_ent */ if (p_ent->comp_mode != QED_SPQ_MODE_EBLOCK) kfree(p_ent); + else + p_ent->post_ent = p_en2; p_ent = p_en2; } @@ -767,6 +767,25 @@ static int qed_spq_pend_post(struct qed_hwfn *p_hwfn) SPQ_HIGH_PRI_RESERVE_DEFAULT); } +/* Avoid overriding of SPQ entries when getting out-of-order completions, by + * marking the completions in a bitmap and increasing the chain consumer only + * for the first successive completed entries. + */ +static void qed_spq_comp_bmap_update(struct qed_hwfn *p_hwfn, __le16 echo) +{ + u16 pos = le16_to_cpu(echo) % SPQ_RING_SIZE; + struct qed_spq *p_spq = p_hwfn->p_spq; + + __set_bit(pos, p_spq->p_comp_bitmap); + while (test_bit(p_spq->comp_bitmap_idx, + p_spq->p_comp_bitmap)) { + __clear_bit(p_spq->comp_bitmap_idx, + p_spq->p_comp_bitmap); + p_spq->comp_bitmap_idx++; + qed_chain_return_produced(&p_spq->chain); + } +} + int qed_spq_post(struct qed_hwfn *p_hwfn, struct qed_spq_entry *p_ent, u8 *fw_return_code) { @@ -824,11 +843,12 @@ int qed_spq_post(struct qed_hwfn *p_hwfn, p_ent->queue == &p_spq->unlimited_pending); if (p_ent->queue == &p_spq->unlimited_pending) { - /* This is an allocated p_ent which does not need to - * return to pool. - */ + struct qed_spq_entry *p_post_ent = p_ent->post_ent; + kfree(p_ent); - return rc; + + /* Return the entry which was actually posted */ + p_ent = p_post_ent; } if (rc) @@ -842,7 +862,7 @@ int qed_spq_post(struct qed_hwfn *p_hwfn, spq_post_fail2: spin_lock_bh(&p_spq->lock); list_del(&p_ent->list); - qed_chain_return_produced(&p_spq->chain); + qed_spq_comp_bmap_update(p_hwfn, p_ent->elem.hdr.echo); spq_post_fail: /* return to the free pool */ @@ -874,25 +894,8 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, spin_lock_bh(&p_spq->lock); list_for_each_entry_safe(p_ent, tmp, &p_spq->completion_pending, list) { if (p_ent->elem.hdr.echo == echo) { - u16 pos = le16_to_cpu(echo) % SPQ_RING_SIZE; - list_del(&p_ent->list); - - /* Avoid overriding of SPQ entries when getting - * out-of-order completions, by marking the completions - * in a bitmap and increasing the chain consumer only - * for the first successive completed entries. - */ - __set_bit(pos, p_spq->p_comp_bitmap); - - while (test_bit(p_spq->comp_bitmap_idx, - p_spq->p_comp_bitmap)) { - __clear_bit(p_spq->comp_bitmap_idx, - p_spq->p_comp_bitmap); - p_spq->comp_bitmap_idx++; - qed_chain_return_produced(&p_spq->chain); - } - + qed_spq_comp_bmap_update(p_hwfn, echo); p_spq->comp_count++; found = p_ent; break; @@ -931,11 +934,9 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, QED_MSG_SPQ, "Got a completion without a callback function\n"); - if ((found->comp_mode != QED_SPQ_MODE_EBLOCK) || - (found->queue == &p_spq->unlimited_pending)) + if (found->comp_mode != QED_SPQ_MODE_EBLOCK) /* EBLOCK is responsible for returning its own entry into the - * free list, unless it originally added the entry into the - * unlimited pending list. + * free list. */ qed_spq_return_entry(p_hwfn, found); diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index 9b08a9d9e151..ca6290fa0f30 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -101,6 +101,7 @@ static int qed_sp_vf_start(struct qed_hwfn *p_hwfn, struct qed_vf_info *p_vf) default: DP_NOTICE(p_hwfn, "Unknown VF personality %d\n", p_hwfn->hw_info.personality); + qed_sp_destroy_request(p_hwfn, p_ent); return -EINVAL; } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index 9647578cbe6a..14f26bf3b388 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@ -459,7 +459,7 @@ static int qlcnic_tx_pkt(struct qlcnic_adapter *adapter, struct cmd_desc_type0 *first_desc, struct sk_buff *skb, struct qlcnic_host_tx_ring *tx_ring) { - u8 l4proto, opcode = 0, hdr_len = 0; + u8 l4proto, opcode = 0, hdr_len = 0, tag_vlan = 0; u16 flags = 0, vlan_tci = 0; int copied, offset, copy_len, size; struct cmd_desc_type0 *hwdesc; @@ -472,14 +472,16 @@ static int qlcnic_tx_pkt(struct qlcnic_adapter *adapter, flags = QLCNIC_FLAGS_VLAN_TAGGED; vlan_tci = ntohs(vh->h_vlan_TCI); protocol = ntohs(vh->h_vlan_encapsulated_proto); + tag_vlan = 1; } else if (skb_vlan_tag_present(skb)) { flags = QLCNIC_FLAGS_VLAN_OOB; vlan_tci = skb_vlan_tag_get(skb); + tag_vlan = 1; } if (unlikely(adapter->tx_pvid)) { - if (vlan_tci && !(adapter->flags & QLCNIC_TAGGING_ENABLED)) + if (tag_vlan && !(adapter->flags & QLCNIC_TAGGING_ENABLED)) return -EIO; - if (vlan_tci && (adapter->flags & QLCNIC_TAGGING_ENABLED)) + if (tag_vlan && (adapter->flags & QLCNIC_TAGGING_ENABLED)) goto set_flags; flags = QLCNIC_FLAGS_VLAN_OOB; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index 0afc3d335d56..d11c16aeb19a 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -234,7 +234,7 @@ int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev, struct net_device *real_dev, struct rmnet_endpoint *ep) { - struct rmnet_priv *priv; + struct rmnet_priv *priv = netdev_priv(rmnet_dev); int rc; if (ep->egress_dev) @@ -247,6 +247,8 @@ int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev, rmnet_dev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; rmnet_dev->hw_features |= NETIF_F_SG; + priv->real_dev = real_dev; + rc = register_netdevice(rmnet_dev); if (!rc) { ep->egress_dev = rmnet_dev; @@ -255,9 +257,7 @@ int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev, rmnet_dev->rtnl_link_ops = &rmnet_link_ops; - priv = netdev_priv(rmnet_dev); priv->mux_id = id; - priv->real_dev = real_dev; netdev_dbg(rmnet_dev, "rmnet dev created\n"); } diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index b1b305f8f414..272b9ca66314 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -365,7 +365,8 @@ struct dma_features { /* GMAC TX FIFO is 8K, Rx FIFO is 16K */ #define BUF_SIZE_16KiB 16384 -#define BUF_SIZE_8KiB 8192 +/* RX Buffer size must be < 8191 and multiple of 4/8/16 bytes */ +#define BUF_SIZE_8KiB 8188 #define BUF_SIZE_4KiB 4096 #define BUF_SIZE_2KiB 2048 diff --git a/drivers/net/ethernet/stmicro/stmmac/descs_com.h b/drivers/net/ethernet/stmicro/stmmac/descs_com.h index ca9d7e48034c..40d6356a7e73 100644 --- a/drivers/net/ethernet/stmicro/stmmac/descs_com.h +++ b/drivers/net/ethernet/stmicro/stmmac/descs_com.h @@ -31,7 +31,7 @@ /* Enhanced descriptors */ static inline void ehn_desc_rx_set_on_ring(struct dma_desc *p, int end) { - p->des1 |= cpu_to_le32(((BUF_SIZE_8KiB - 1) + p->des1 |= cpu_to_le32((BUF_SIZE_8KiB << ERDES1_BUFFER2_SIZE_SHIFT) & ERDES1_BUFFER2_SIZE_MASK); diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c index 77914c89d749..5ef91a790f9d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c @@ -262,7 +262,7 @@ static void enh_desc_init_rx_desc(struct dma_desc *p, int disable_rx_ic, int mode, int end) { p->des0 |= cpu_to_le32(RDES0_OWN); - p->des1 |= cpu_to_le32((BUF_SIZE_8KiB - 1) & ERDES1_BUFFER1_SIZE_MASK); + p->des1 |= cpu_to_le32(BUF_SIZE_8KiB & ERDES1_BUFFER1_SIZE_MASK); if (mode == STMMAC_CHAIN_MODE) ehn_desc_rx_set_on_chain(p); diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c index abc3f85270cd..d8c5bc412219 100644 --- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c @@ -140,7 +140,7 @@ static void clean_desc3(void *priv_ptr, struct dma_desc *p) static int set_16kib_bfsize(int mtu) { int ret = 0; - if (unlikely(mtu >= BUF_SIZE_8KiB)) + if (unlikely(mtu > BUF_SIZE_8KiB)) ret = BUF_SIZE_16KiB; return ret; } diff --git a/drivers/net/fddi/defza.c b/drivers/net/fddi/defza.c index 3b7f10a5f06a..c5cae8e74dc4 100644 --- a/drivers/net/fddi/defza.c +++ b/drivers/net/fddi/defza.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: GPL-2.0+ /* FDDI network adapter driver for DEC FDDIcontroller 700/700-C devices. * * Copyright (c) 2018 Maciej W. Rozycki @@ -56,7 +56,7 @@ #define DRV_VERSION "v.1.1.4" #define DRV_RELDATE "Oct 6 2018" -static char version[] = +static const char version[] = DRV_NAME ": " DRV_VERSION " " DRV_RELDATE " Maciej W. Rozycki\n"; MODULE_AUTHOR("Maciej W. Rozycki <macro@linux-mips.org>"); @@ -784,7 +784,7 @@ err_rx: static void fza_tx_smt(struct net_device *dev) { struct fza_private *fp = netdev_priv(dev); - struct fza_buffer_tx __iomem *smt_tx_ptr, *skb_data_ptr; + struct fza_buffer_tx __iomem *smt_tx_ptr; int i, len; u32 own; @@ -799,6 +799,7 @@ static void fza_tx_smt(struct net_device *dev) if (!netif_queue_stopped(dev)) { if (dev_nit_active(dev)) { + struct fza_buffer_tx *skb_data_ptr; struct sk_buff *skb; /* Length must be a multiple of 4 as only word diff --git a/drivers/net/fddi/defza.h b/drivers/net/fddi/defza.h index b06acf32738e..93bda61be8e3 100644 --- a/drivers/net/fddi/defza.h +++ b/drivers/net/fddi/defza.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0+ */ /* FDDI network adapter driver for DEC FDDIcontroller 700/700-C devices. * * Copyright (c) 2018 Maciej W. Rozycki @@ -235,6 +235,7 @@ struct fza_ring_cmd { #define FZA_RING_CMD 0x200400 /* command ring address */ #define FZA_RING_CMD_SIZE 0x40 /* command descriptor ring * size + */ /* Command constants. */ #define FZA_RING_CMD_MASK 0x7fffffff #define FZA_RING_CMD_NOP 0x00000000 /* nop */ diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index e86ea105c802..704537010453 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -92,7 +92,7 @@ static int bcm54612e_config_init(struct phy_device *phydev) return 0; } -static int bcm5481x_config(struct phy_device *phydev) +static int bcm54xx_config_clock_delay(struct phy_device *phydev) { int rc, val; @@ -429,7 +429,7 @@ static int bcm5481_config_aneg(struct phy_device *phydev) ret = genphy_config_aneg(phydev); /* Then we can set up the delay. */ - bcm5481x_config(phydev); + bcm54xx_config_clock_delay(phydev); if (of_property_read_bool(np, "enet-phy-lane-swap")) { /* Lane Swap - Undocumented register...magic! */ @@ -442,6 +442,19 @@ static int bcm5481_config_aneg(struct phy_device *phydev) return ret; } +static int bcm54616s_config_aneg(struct phy_device *phydev) +{ + int ret; + + /* Aneg firsly. */ + ret = genphy_config_aneg(phydev); + + /* Then we can set up the delay. */ + bcm54xx_config_clock_delay(phydev); + + return ret; +} + static int brcm_phy_setbits(struct phy_device *phydev, int reg, int set) { int val; @@ -636,6 +649,7 @@ static struct phy_driver broadcom_drivers[] = { .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, .config_init = bcm54xx_config_init, + .config_aneg = bcm54616s_config_aneg, .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, }, { diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 2d17f3b9bb16..f2d01cb6f958 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -1321,6 +1321,8 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf) dev->net->ethtool_ops = &smsc95xx_ethtool_ops; dev->net->flags |= IFF_MULTICAST; dev->net->hard_header_len += SMSC95XX_TX_OVERHEAD_CSUM; + dev->net->min_mtu = ETH_MIN_MTU; + dev->net->max_mtu = ETH_DATA_LEN; dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len; pdata->dev = dev; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index f172d63db2b5..91474b3c566c 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1519,8 +1519,10 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) if (ns->ndev) nvme_nvm_update_nvm_info(ns); #ifdef CONFIG_NVME_MULTIPATH - if (ns->head->disk) + if (ns->head->disk) { nvme_update_disk_info(ns->head->disk, ns, id); + blk_queue_stack_limits(ns->head->disk->queue, ns->queue); + } #endif } diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index b82b0d3ca39a..8b841f39734c 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -285,6 +285,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) blk_queue_flag_set(QUEUE_FLAG_NONROT, q); /* set to a default value for 512 until disk is validated */ blk_queue_logical_block_size(q, 512); + blk_set_stacking_limits(&q->limits); /* we need to propagate up the VMC settings */ if (ctrl->vwc & NVME_CTRL_VWC_PRESENT) diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index f4efe289dc7b..a5f9bbce863f 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -420,7 +420,7 @@ static void nvmet_p2pmem_ns_add_p2p(struct nvmet_ctrl *ctrl, struct pci_dev *p2p_dev; int ret; - if (!ctrl->p2p_client) + if (!ctrl->p2p_client || !ns->use_p2pmem) return; if (ns->p2p_dev) { diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index ddce100be57a..3f7971d3706d 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -122,7 +122,6 @@ struct nvmet_rdma_device { int inline_page_count; }; -static struct workqueue_struct *nvmet_rdma_delete_wq; static bool nvmet_rdma_use_srq; module_param_named(use_srq, nvmet_rdma_use_srq, bool, 0444); MODULE_PARM_DESC(use_srq, "Use shared receive queue."); @@ -1274,12 +1273,12 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id, if (queue->host_qid == 0) { /* Let inflight controller teardown complete */ - flush_workqueue(nvmet_rdma_delete_wq); + flush_scheduled_work(); } ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn); if (ret) { - queue_work(nvmet_rdma_delete_wq, &queue->release_work); + schedule_work(&queue->release_work); /* Destroying rdma_cm id is not needed here */ return 0; } @@ -1344,7 +1343,7 @@ static void __nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue) if (disconnect) { rdma_disconnect(queue->cm_id); - queue_work(nvmet_rdma_delete_wq, &queue->release_work); + schedule_work(&queue->release_work); } } @@ -1374,7 +1373,7 @@ static void nvmet_rdma_queue_connect_fail(struct rdma_cm_id *cm_id, mutex_unlock(&nvmet_rdma_queue_mutex); pr_err("failed to connect queue %d\n", queue->idx); - queue_work(nvmet_rdma_delete_wq, &queue->release_work); + schedule_work(&queue->release_work); } /** @@ -1656,17 +1655,8 @@ static int __init nvmet_rdma_init(void) if (ret) goto err_ib_client; - nvmet_rdma_delete_wq = alloc_workqueue("nvmet-rdma-delete-wq", - WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0); - if (!nvmet_rdma_delete_wq) { - ret = -ENOMEM; - goto err_unreg_transport; - } - return 0; -err_unreg_transport: - nvmet_unregister_transport(&nvmet_rdma_ops); err_ib_client: ib_unregister_client(&nvmet_rdma_ib_client); return ret; @@ -1674,7 +1664,6 @@ err_ib_client: static void __exit nvmet_rdma_exit(void) { - destroy_workqueue(nvmet_rdma_delete_wq); nvmet_unregister_transport(&nvmet_rdma_ops); ib_unregister_client(&nvmet_rdma_ib_client); WARN_ON_ONCE(!list_empty(&nvmet_rdma_queue_list)); diff --git a/drivers/of/device.c b/drivers/of/device.c index 0f27fad9fe94..5592437bb3d1 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -149,9 +149,11 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma) * set by the driver. */ mask = DMA_BIT_MASK(ilog2(dma_addr + size - 1) + 1); - dev->bus_dma_mask = mask; dev->coherent_dma_mask &= mask; *dev->dma_mask &= mask; + /* ...but only set bus mask if we found valid dma-ranges earlier */ + if (!ret) + dev->bus_dma_mask = mask; coherent = of_dma_is_coherent(np); dev_dbg(dev, "device is%sdma coherent\n", diff --git a/drivers/of/of_numa.c b/drivers/of/of_numa.c index 35c64a4295e0..fe6b13608e51 100644 --- a/drivers/of/of_numa.c +++ b/drivers/of/of_numa.c @@ -104,9 +104,14 @@ static int __init of_numa_parse_distance_map_v1(struct device_node *map) distance = of_read_number(matrix, 1); matrix++; + if ((nodea == nodeb && distance != LOCAL_DISTANCE) || + (nodea != nodeb && distance <= LOCAL_DISTANCE)) { + pr_err("Invalid distance[node%d -> node%d] = %d\n", + nodea, nodeb, distance); + return -EINVAL; + } + numa_set_distance(nodea, nodeb, distance); - pr_debug("distance[node%d -> node%d] = %d\n", - nodea, nodeb, distance); /* Set default distance of node B->A same as A->B */ if (nodeb > nodea) diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index 2a4aa6468579..921db6f80340 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -793,15 +793,10 @@ static void pci_acpi_setup(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); struct acpi_device *adev = ACPI_COMPANION(dev); - int node; if (!adev) return; - node = acpi_get_node(adev->handle); - if (node != NUMA_NO_NODE) - set_dev_node(dev, node); - pci_acpi_optimize_delay(pci_dev, adev->handle); pci_acpi_add_pm_notifier(adev, pci_dev); diff --git a/drivers/pinctrl/meson/pinctrl-meson-gxbb.c b/drivers/pinctrl/meson/pinctrl-meson-gxbb.c index 4ceb06f8a33c..4edeb4cae72a 100644 --- a/drivers/pinctrl/meson/pinctrl-meson-gxbb.c +++ b/drivers/pinctrl/meson/pinctrl-meson-gxbb.c @@ -830,7 +830,7 @@ static struct meson_bank meson_gxbb_periphs_banks[] = { static struct meson_bank meson_gxbb_aobus_banks[] = { /* name first last irq pullen pull dir out in */ - BANK("AO", GPIOAO_0, GPIOAO_13, 0, 13, 0, 0, 0, 16, 0, 0, 0, 16, 1, 0), + BANK("AO", GPIOAO_0, GPIOAO_13, 0, 13, 0, 16, 0, 0, 0, 0, 0, 16, 1, 0), }; static struct meson_pinctrl_data meson_gxbb_periphs_pinctrl_data = { diff --git a/drivers/pinctrl/meson/pinctrl-meson-gxl.c b/drivers/pinctrl/meson/pinctrl-meson-gxl.c index 7dae1d7bf6b0..158f618f1695 100644 --- a/drivers/pinctrl/meson/pinctrl-meson-gxl.c +++ b/drivers/pinctrl/meson/pinctrl-meson-gxl.c @@ -807,7 +807,7 @@ static struct meson_bank meson_gxl_periphs_banks[] = { static struct meson_bank meson_gxl_aobus_banks[] = { /* name first last irq pullen pull dir out in */ - BANK("AO", GPIOAO_0, GPIOAO_9, 0, 9, 0, 0, 0, 16, 0, 0, 0, 16, 1, 0), + BANK("AO", GPIOAO_0, GPIOAO_9, 0, 9, 0, 16, 0, 0, 0, 0, 0, 16, 1, 0), }; static struct meson_pinctrl_data meson_gxl_periphs_pinctrl_data = { diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c index f8b778a7d471..53d449076dee 100644 --- a/drivers/pinctrl/meson/pinctrl-meson.c +++ b/drivers/pinctrl/meson/pinctrl-meson.c @@ -192,7 +192,7 @@ static int meson_pinconf_set(struct pinctrl_dev *pcdev, unsigned int pin, dev_dbg(pc->dev, "pin %u: disable bias\n", pin); meson_calc_reg_and_bit(bank, pin, REG_PULL, ®, &bit); - ret = regmap_update_bits(pc->reg_pull, reg, + ret = regmap_update_bits(pc->reg_pullen, reg, BIT(bit), 0); if (ret) return ret; diff --git a/drivers/pinctrl/meson/pinctrl-meson8.c b/drivers/pinctrl/meson/pinctrl-meson8.c index c6d79315218f..86466173114d 100644 --- a/drivers/pinctrl/meson/pinctrl-meson8.c +++ b/drivers/pinctrl/meson/pinctrl-meson8.c @@ -1053,7 +1053,7 @@ static struct meson_bank meson8_cbus_banks[] = { static struct meson_bank meson8_aobus_banks[] = { /* name first last irq pullen pull dir out in */ - BANK("AO", GPIOAO_0, GPIO_TEST_N, 0, 13, 0, 0, 0, 16, 0, 0, 0, 16, 1, 0), + BANK("AO", GPIOAO_0, GPIO_TEST_N, 0, 13, 0, 16, 0, 0, 0, 0, 0, 16, 1, 0), }; static struct meson_pinctrl_data meson8_cbus_pinctrl_data = { diff --git a/drivers/pinctrl/meson/pinctrl-meson8b.c b/drivers/pinctrl/meson/pinctrl-meson8b.c index bb2a30964fc6..647ad15d5c3c 100644 --- a/drivers/pinctrl/meson/pinctrl-meson8b.c +++ b/drivers/pinctrl/meson/pinctrl-meson8b.c @@ -906,7 +906,7 @@ static struct meson_bank meson8b_cbus_banks[] = { static struct meson_bank meson8b_aobus_banks[] = { /* name first lastc irq pullen pull dir out in */ - BANK("AO", GPIOAO_0, GPIO_TEST_N, 0, 13, 0, 0, 0, 16, 0, 0, 0, 16, 1, 0), + BANK("AO", GPIOAO_0, GPIO_TEST_N, 0, 13, 0, 16, 0, 0, 0, 0, 0, 16, 1, 0), }; static struct meson_pinctrl_data meson8b_cbus_pinctrl_data = { diff --git a/drivers/rtc/hctosys.c b/drivers/rtc/hctosys.c index e79f2a181ad2..b9ec4a16db1f 100644 --- a/drivers/rtc/hctosys.c +++ b/drivers/rtc/hctosys.c @@ -50,8 +50,10 @@ static int __init rtc_hctosys(void) tv64.tv_sec = rtc_tm_to_time64(&tm); #if BITS_PER_LONG == 32 - if (tv64.tv_sec > INT_MAX) + if (tv64.tv_sec > INT_MAX) { + err = -ERANGE; goto err_read; + } #endif err = do_settimeofday64(&tv64); diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index df0c5776d49b..a5a19ff10535 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -257,6 +257,7 @@ static int cmos_read_alarm(struct device *dev, struct rtc_wkalrm *t) struct cmos_rtc *cmos = dev_get_drvdata(dev); unsigned char rtc_control; + /* This not only a rtc_op, but also called directly */ if (!is_valid_irq(cmos->irq)) return -EIO; @@ -452,6 +453,7 @@ static int cmos_set_alarm(struct device *dev, struct rtc_wkalrm *t) unsigned char mon, mday, hrs, min, sec, rtc_control; int ret; + /* This not only a rtc_op, but also called directly */ if (!is_valid_irq(cmos->irq)) return -EIO; @@ -516,9 +518,6 @@ static int cmos_alarm_irq_enable(struct device *dev, unsigned int enabled) struct cmos_rtc *cmos = dev_get_drvdata(dev); unsigned long flags; - if (!is_valid_irq(cmos->irq)) - return -EINVAL; - spin_lock_irqsave(&rtc_lock, flags); if (enabled) @@ -579,6 +578,12 @@ static const struct rtc_class_ops cmos_rtc_ops = { .alarm_irq_enable = cmos_alarm_irq_enable, }; +static const struct rtc_class_ops cmos_rtc_ops_no_alarm = { + .read_time = cmos_read_time, + .set_time = cmos_set_time, + .proc = cmos_procfs, +}; + /*----------------------------------------------------------------*/ /* @@ -855,9 +860,12 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq) dev_dbg(dev, "IRQ %d is already in use\n", rtc_irq); goto cleanup1; } + + cmos_rtc.rtc->ops = &cmos_rtc_ops; + } else { + cmos_rtc.rtc->ops = &cmos_rtc_ops_no_alarm; } - cmos_rtc.rtc->ops = &cmos_rtc_ops; cmos_rtc.rtc->nvram_old_abi = true; retval = rtc_register_device(cmos_rtc.rtc); if (retval) diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c index 9f99a0966550..7cb786d76e3c 100644 --- a/drivers/rtc/rtc-pcf2127.c +++ b/drivers/rtc/rtc-pcf2127.c @@ -303,6 +303,9 @@ static int pcf2127_i2c_gather_write(void *context, memcpy(buf + 1, val, val_size); ret = i2c_master_send(client, buf, val_size + 1); + + kfree(buf); + if (ret != val_size + 1) return ret < 0 ? ret : -EIO; diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index dfdc6940de2f..f38882f6f37d 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -566,6 +566,7 @@ config SCSI_MYRB config SCSI_MYRS tristate "Mylex DAC960/DAC1100 PCI RAID Controller (SCSI Interface)" depends on PCI + depends on !CPU_BIG_ENDIAN || COMPILE_TEST select RAID_ATTRS help This driver adds support for the Mylex DAC960, AcceleRAID, and diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c index 8429c855701f..01c23d27f290 100644 --- a/drivers/scsi/NCR5380.c +++ b/drivers/scsi/NCR5380.c @@ -1198,7 +1198,7 @@ static bool NCR5380_select(struct Scsi_Host *instance, struct scsi_cmnd *cmd) out: if (!hostdata->selecting) - return NULL; + return false; hostdata->selecting = NULL; return ret; } diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c index f0e457e6884e..8df822a4a1bd 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c @@ -904,11 +904,9 @@ static void start_delivery_v1_hw(struct hisi_sas_dq *dq) { struct hisi_hba *hisi_hba = dq->hisi_hba; struct hisi_sas_slot *s, *s1, *s2 = NULL; - struct list_head *dq_list; int dlvry_queue = dq->id; int wp; - dq_list = &dq->list; list_for_each_entry_safe(s, s1, &dq->list, delivery) { if (!s->ready) break; diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c index cc36b6473e98..77a85ead483e 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c @@ -1670,11 +1670,9 @@ static void start_delivery_v2_hw(struct hisi_sas_dq *dq) { struct hisi_hba *hisi_hba = dq->hisi_hba; struct hisi_sas_slot *s, *s1, *s2 = NULL; - struct list_head *dq_list; int dlvry_queue = dq->id; int wp; - dq_list = &dq->list; list_for_each_entry_safe(s, s1, &dq->list, delivery) { if (!s->ready) break; diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index bd4ce38b98d2..a369450a1fa7 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -886,11 +886,9 @@ static void start_delivery_v3_hw(struct hisi_sas_dq *dq) { struct hisi_hba *hisi_hba = dq->hisi_hba; struct hisi_sas_slot *s, *s1, *s2 = NULL; - struct list_head *dq_list; int dlvry_queue = dq->id; int wp; - dq_list = &dq->list; list_for_each_entry_safe(s, s1, &dq->list, delivery) { if (!s->ready) break; diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c index 0c8005bb0f53..34d311a7dbef 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.c +++ b/drivers/scsi/lpfc/lpfc_debugfs.c @@ -698,6 +698,8 @@ lpfc_debugfs_nodelist_data(struct lpfc_vport *vport, char *buf, int size) rport = lpfc_ndlp_get_nrport(ndlp); if (rport) nrport = rport->remoteport; + else + nrport = NULL; spin_unlock(&phba->hbalock); if (!nrport) continue; diff --git a/drivers/scsi/myrb.c b/drivers/scsi/myrb.c index aeb282f617c5..0642f2d0a3bb 100644 --- a/drivers/scsi/myrb.c +++ b/drivers/scsi/myrb.c @@ -1049,7 +1049,8 @@ static int myrb_get_hba_config(struct myrb_hba *cb) enquiry2->fw.firmware_type = '0'; enquiry2->fw.turn_id = 0; } - sprintf(cb->fw_version, "%d.%02d-%c-%02d", + snprintf(cb->fw_version, sizeof(cb->fw_version), + "%d.%02d-%c-%02d", enquiry2->fw.major_version, enquiry2->fw.minor_version, enquiry2->fw.firmware_type, diff --git a/drivers/scsi/myrs.c b/drivers/scsi/myrs.c index 0264a2e2bc19..b8d54ef8cf6d 100644 --- a/drivers/scsi/myrs.c +++ b/drivers/scsi/myrs.c @@ -163,9 +163,12 @@ static unsigned char myrs_get_ctlr_info(struct myrs_hba *cs) dma_addr_t ctlr_info_addr; union myrs_sgl *sgl; unsigned char status; - struct myrs_ctlr_info old; + unsigned short ldev_present, ldev_critical, ldev_offline; + + ldev_present = cs->ctlr_info->ldev_present; + ldev_critical = cs->ctlr_info->ldev_critical; + ldev_offline = cs->ctlr_info->ldev_offline; - memcpy(&old, cs->ctlr_info, sizeof(struct myrs_ctlr_info)); ctlr_info_addr = dma_map_single(&cs->pdev->dev, cs->ctlr_info, sizeof(struct myrs_ctlr_info), DMA_FROM_DEVICE); @@ -198,9 +201,9 @@ static unsigned char myrs_get_ctlr_info(struct myrs_hba *cs) cs->ctlr_info->rbld_active + cs->ctlr_info->exp_active != 0) cs->needs_update = true; - if (cs->ctlr_info->ldev_present != old.ldev_present || - cs->ctlr_info->ldev_critical != old.ldev_critical || - cs->ctlr_info->ldev_offline != old.ldev_offline) + if (cs->ctlr_info->ldev_present != ldev_present || + cs->ctlr_info->ldev_critical != ldev_critical || + cs->ctlr_info->ldev_offline != ldev_offline) shost_printk(KERN_INFO, cs->host, "Logical drive count changes (%d/%d/%d)\n", cs->ctlr_info->ldev_critical, diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 6fe20c27acc1..eb59c796a795 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -4763,6 +4763,7 @@ qla2x00_alloc_fcport(scsi_qla_host_t *vha, gfp_t flags) fcport->loop_id = FC_NO_LOOP_ID; qla2x00_set_fcport_state(fcport, FCS_UNCONFIGURED); fcport->supported_classes = FC_COS_UNSPECIFIED; + fcport->fp_speed = PORT_SPEED_UNKNOWN; fcport->ct_desc.ct_sns = dma_alloc_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), &fcport->ct_desc.ct_sns_dma, diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index fdf3e52ee908..2c9efcc71a41 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -67,7 +67,7 @@ module_param(ql2xplogiabsentdevice, int, S_IRUGO|S_IWUSR); MODULE_PARM_DESC(ql2xplogiabsentdevice, "Option to enable PLOGI to devices that are not present after " "a Fabric scan. This is needed for several broken switches. " - "Default is 0 - no PLOGI. 1 - perfom PLOGI."); + "Default is 0 - no PLOGI. 1 - perform PLOGI."); int ql2xloginretrycount = 0; module_param(ql2xloginretrycount, int, S_IRUGO); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 5d83a162d03b..0df15cb738d2 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -610,6 +610,12 @@ static bool scsi_end_request(struct request *req, blk_status_t error, */ scsi_mq_uninit_cmd(cmd); + /* + * queue is still alive, so grab the ref for preventing it + * from being cleaned up during running queue. + */ + percpu_ref_get(&q->q_usage_counter); + __blk_mq_end_request(req, error); if (scsi_target(sdev)->single_lun || @@ -618,6 +624,7 @@ static bool scsi_end_request(struct request *req, blk_status_t error, else blk_mq_run_hw_queues(q, true); + percpu_ref_put(&q->q_usage_counter); put_device(&sdev->sdev_gendev); return false; } diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index fb308ea8e9a5..27db55b0ca7f 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -8099,7 +8099,6 @@ int ufshcd_alloc_host(struct device *dev, struct ufs_hba **hba_handle) err = -ENOMEM; goto out_error; } - hba = shost_priv(host); hba->host = host; hba->dev = dev; diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index e31e4fc31aa1..2cfd61d62e97 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1778,7 +1778,7 @@ EXPORT_SYMBOL(target_submit_tmr); void transport_generic_request_failure(struct se_cmd *cmd, sense_reason_t sense_reason) { - int ret = 0; + int ret = 0, post_ret; pr_debug("-----[ Storage Engine Exception; sense_reason %d\n", sense_reason); @@ -1790,7 +1790,7 @@ void transport_generic_request_failure(struct se_cmd *cmd, transport_complete_task_attr(cmd); if (cmd->transport_complete_callback) - cmd->transport_complete_callback(cmd, false, NULL); + cmd->transport_complete_callback(cmd, false, &post_ret); if (transport_check_aborted_status(cmd, 1)) return; diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index ff6ba6d86cd8..cc56cb3b3eca 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -1614,10 +1614,10 @@ static void sci_request_dma(struct uart_port *port) hrtimer_init(&s->rx_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); s->rx_timer.function = rx_timer_fn; + s->chan_rx_saved = s->chan_rx = chan; + if (port->type == PORT_SCIFA || port->type == PORT_SCIFB) sci_submit_rx(s); - - s->chan_rx_saved = s->chan_rx = chan; } } @@ -3102,6 +3102,7 @@ static struct uart_driver sci_uart_driver = { static int sci_remove(struct platform_device *dev) { struct sci_port *port = platform_get_drvdata(dev); + unsigned int type = port->port.type; /* uart_remove_... clears it */ sci_ports_in_use &= ~BIT(port->port.line); uart_remove_one_port(&sci_uart_driver, &port->port); @@ -3112,8 +3113,7 @@ static int sci_remove(struct platform_device *dev) sysfs_remove_file(&dev->dev.kobj, &dev_attr_rx_fifo_trigger.attr); } - if (port->port.type == PORT_SCIFA || port->port.type == PORT_SCIFB || - port->port.type == PORT_HSCIF) { + if (type == PORT_SCIFA || type == PORT_SCIFB || type == PORT_HSCIF) { sysfs_remove_file(&dev->dev.kobj, &dev_attr_rx_fifo_timeout.attr); } diff --git a/drivers/tty/tty_baudrate.c b/drivers/tty/tty_baudrate.c index 7576ceace571..f438eaa68246 100644 --- a/drivers/tty/tty_baudrate.c +++ b/drivers/tty/tty_baudrate.c @@ -77,7 +77,7 @@ speed_t tty_termios_baud_rate(struct ktermios *termios) else cbaud += 15; } - return baud_table[cbaud]; + return cbaud >= n_baud_table ? 0 : baud_table[cbaud]; } EXPORT_SYMBOL(tty_termios_baud_rate); @@ -113,7 +113,7 @@ speed_t tty_termios_input_baud_rate(struct ktermios *termios) else cbaud += 15; } - return baud_table[cbaud]; + return cbaud >= n_baud_table ? 0 : baud_table[cbaud]; #else /* IBSHIFT */ return tty_termios_baud_rate(termios); #endif /* IBSHIFT */ diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 55370e651db3..41ec8e5010f3 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -1548,7 +1548,7 @@ static void csi_K(struct vc_data *vc, int vpar) scr_memsetw(start + offset, vc->vc_video_erase_char, 2 * count); vc->vc_need_wrap = 0; if (con_should_update(vc)) - do_update_region(vc, (unsigned long) start, count); + do_update_region(vc, (unsigned long)(start + offset), count); } static void csi_X(struct vc_data *vc, int vpar) /* erase the following vpar positions */ diff --git a/drivers/usb/typec/ucsi/Kconfig b/drivers/usb/typec/ucsi/Kconfig index e36d6c73c4a4..78118883f96c 100644 --- a/drivers/usb/typec/ucsi/Kconfig +++ b/drivers/usb/typec/ucsi/Kconfig @@ -23,6 +23,16 @@ config TYPEC_UCSI if TYPEC_UCSI +config UCSI_CCG + tristate "UCSI Interface Driver for Cypress CCGx" + depends on I2C + help + This driver enables UCSI support on platforms that expose a + Cypress CCGx Type-C controller over I2C interface. + + To compile the driver as a module, choose M here: the module will be + called ucsi_ccg. + config UCSI_ACPI tristate "UCSI ACPI Interface Driver" depends on ACPI diff --git a/drivers/usb/typec/ucsi/Makefile b/drivers/usb/typec/ucsi/Makefile index 7afbea512207..2f4900b26210 100644 --- a/drivers/usb/typec/ucsi/Makefile +++ b/drivers/usb/typec/ucsi/Makefile @@ -8,3 +8,5 @@ typec_ucsi-y := ucsi.o typec_ucsi-$(CONFIG_TRACING) += trace.o obj-$(CONFIG_UCSI_ACPI) += ucsi_acpi.o + +obj-$(CONFIG_UCSI_CCG) += ucsi_ccg.o diff --git a/drivers/usb/typec/ucsi/ucsi_ccg.c b/drivers/usb/typec/ucsi/ucsi_ccg.c new file mode 100644 index 000000000000..de8a43bdff68 --- /dev/null +++ b/drivers/usb/typec/ucsi/ucsi_ccg.c @@ -0,0 +1,307 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * UCSI driver for Cypress CCGx Type-C controller + * + * Copyright (C) 2017-2018 NVIDIA Corporation. All rights reserved. + * Author: Ajay Gupta <ajayg@nvidia.com> + * + * Some code borrowed from drivers/usb/typec/ucsi/ucsi_acpi.c + */ +#include <linux/acpi.h> +#include <linux/delay.h> +#include <linux/i2c.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/platform_device.h> + +#include <asm/unaligned.h> +#include "ucsi.h" + +struct ucsi_ccg { + struct device *dev; + struct ucsi *ucsi; + struct ucsi_ppm ppm; + struct i2c_client *client; +}; + +#define CCGX_RAB_INTR_REG 0x06 +#define CCGX_RAB_UCSI_CONTROL 0x39 +#define CCGX_RAB_UCSI_CONTROL_START BIT(0) +#define CCGX_RAB_UCSI_CONTROL_STOP BIT(1) +#define CCGX_RAB_UCSI_DATA_BLOCK(offset) (0xf000 | ((offset) & 0xff)) + +static int ccg_read(struct ucsi_ccg *uc, u16 rab, u8 *data, u32 len) +{ + struct i2c_client *client = uc->client; + const struct i2c_adapter_quirks *quirks = client->adapter->quirks; + unsigned char buf[2]; + struct i2c_msg msgs[] = { + { + .addr = client->addr, + .flags = 0x0, + .len = sizeof(buf), + .buf = buf, + }, + { + .addr = client->addr, + .flags = I2C_M_RD, + .buf = data, + }, + }; + u32 rlen, rem_len = len, max_read_len = len; + int status; + + /* check any max_read_len limitation on i2c adapter */ + if (quirks && quirks->max_read_len) + max_read_len = quirks->max_read_len; + + while (rem_len > 0) { + msgs[1].buf = &data[len - rem_len]; + rlen = min_t(u16, rem_len, max_read_len); + msgs[1].len = rlen; + put_unaligned_le16(rab, buf); + status = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); + if (status < 0) { + dev_err(uc->dev, "i2c_transfer failed %d\n", status); + return status; + } + rab += rlen; + rem_len -= rlen; + } + + return 0; +} + +static int ccg_write(struct ucsi_ccg *uc, u16 rab, u8 *data, u32 len) +{ + struct i2c_client *client = uc->client; + unsigned char *buf; + struct i2c_msg msgs[] = { + { + .addr = client->addr, + .flags = 0x0, + } + }; + int status; + + buf = kzalloc(len + sizeof(rab), GFP_KERNEL); + if (!buf) + return -ENOMEM; + + put_unaligned_le16(rab, buf); + memcpy(buf + sizeof(rab), data, len); + + msgs[0].len = len + sizeof(rab); + msgs[0].buf = buf; + + status = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); + if (status < 0) { + dev_err(uc->dev, "i2c_transfer failed %d\n", status); + kfree(buf); + return status; + } + + kfree(buf); + return 0; +} + +static int ucsi_ccg_init(struct ucsi_ccg *uc) +{ + unsigned int count = 10; + u8 data; + int status; + + data = CCGX_RAB_UCSI_CONTROL_STOP; + status = ccg_write(uc, CCGX_RAB_UCSI_CONTROL, &data, sizeof(data)); + if (status < 0) + return status; + + data = CCGX_RAB_UCSI_CONTROL_START; + status = ccg_write(uc, CCGX_RAB_UCSI_CONTROL, &data, sizeof(data)); + if (status < 0) + return status; + + /* + * Flush CCGx RESPONSE queue by acking interrupts. Above ucsi control + * register write will push response which must be cleared. + */ + do { + status = ccg_read(uc, CCGX_RAB_INTR_REG, &data, sizeof(data)); + if (status < 0) + return status; + + if (!data) + return 0; + + status = ccg_write(uc, CCGX_RAB_INTR_REG, &data, sizeof(data)); + if (status < 0) + return status; + + usleep_range(10000, 11000); + } while (--count); + + return -ETIMEDOUT; +} + +static int ucsi_ccg_send_data(struct ucsi_ccg *uc) +{ + u8 *ppm = (u8 *)uc->ppm.data; + int status; + u16 rab; + + rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, message_out)); + status = ccg_write(uc, rab, ppm + + offsetof(struct ucsi_data, message_out), + sizeof(uc->ppm.data->message_out)); + if (status < 0) + return status; + + rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, ctrl)); + return ccg_write(uc, rab, ppm + offsetof(struct ucsi_data, ctrl), + sizeof(uc->ppm.data->ctrl)); +} + +static int ucsi_ccg_recv_data(struct ucsi_ccg *uc) +{ + u8 *ppm = (u8 *)uc->ppm.data; + int status; + u16 rab; + + rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, cci)); + status = ccg_read(uc, rab, ppm + offsetof(struct ucsi_data, cci), + sizeof(uc->ppm.data->cci)); + if (status < 0) + return status; + + rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, message_in)); + return ccg_read(uc, rab, ppm + offsetof(struct ucsi_data, message_in), + sizeof(uc->ppm.data->message_in)); +} + +static int ucsi_ccg_ack_interrupt(struct ucsi_ccg *uc) +{ + int status; + unsigned char data; + + status = ccg_read(uc, CCGX_RAB_INTR_REG, &data, sizeof(data)); + if (status < 0) + return status; + + return ccg_write(uc, CCGX_RAB_INTR_REG, &data, sizeof(data)); +} + +static int ucsi_ccg_sync(struct ucsi_ppm *ppm) +{ + struct ucsi_ccg *uc = container_of(ppm, struct ucsi_ccg, ppm); + int status; + + status = ucsi_ccg_recv_data(uc); + if (status < 0) + return status; + + /* ack interrupt to allow next command to run */ + return ucsi_ccg_ack_interrupt(uc); +} + +static int ucsi_ccg_cmd(struct ucsi_ppm *ppm, struct ucsi_control *ctrl) +{ + struct ucsi_ccg *uc = container_of(ppm, struct ucsi_ccg, ppm); + + ppm->data->ctrl.raw_cmd = ctrl->raw_cmd; + return ucsi_ccg_send_data(uc); +} + +static irqreturn_t ccg_irq_handler(int irq, void *data) +{ + struct ucsi_ccg *uc = data; + + ucsi_notify(uc->ucsi); + + return IRQ_HANDLED; +} + +static int ucsi_ccg_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct device *dev = &client->dev; + struct ucsi_ccg *uc; + int status; + u16 rab; + + uc = devm_kzalloc(dev, sizeof(*uc), GFP_KERNEL); + if (!uc) + return -ENOMEM; + + uc->ppm.data = devm_kzalloc(dev, sizeof(struct ucsi_data), GFP_KERNEL); + if (!uc->ppm.data) + return -ENOMEM; + + uc->ppm.cmd = ucsi_ccg_cmd; + uc->ppm.sync = ucsi_ccg_sync; + uc->dev = dev; + uc->client = client; + + /* reset ccg device and initialize ucsi */ + status = ucsi_ccg_init(uc); + if (status < 0) { + dev_err(uc->dev, "ucsi_ccg_init failed - %d\n", status); + return status; + } + + status = devm_request_threaded_irq(dev, client->irq, NULL, + ccg_irq_handler, + IRQF_ONESHOT | IRQF_TRIGGER_HIGH, + dev_name(dev), uc); + if (status < 0) { + dev_err(uc->dev, "request_threaded_irq failed - %d\n", status); + return status; + } + + uc->ucsi = ucsi_register_ppm(dev, &uc->ppm); + if (IS_ERR(uc->ucsi)) { + dev_err(uc->dev, "ucsi_register_ppm failed\n"); + return PTR_ERR(uc->ucsi); + } + + rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, version)); + status = ccg_read(uc, rab, (u8 *)(uc->ppm.data) + + offsetof(struct ucsi_data, version), + sizeof(uc->ppm.data->version)); + if (status < 0) { + ucsi_unregister_ppm(uc->ucsi); + return status; + } + + i2c_set_clientdata(client, uc); + return 0; +} + +static int ucsi_ccg_remove(struct i2c_client *client) +{ + struct ucsi_ccg *uc = i2c_get_clientdata(client); + + ucsi_unregister_ppm(uc->ucsi); + + return 0; +} + +static const struct i2c_device_id ucsi_ccg_device_id[] = { + {"ccgx-ucsi", 0}, + {} +}; +MODULE_DEVICE_TABLE(i2c, ucsi_ccg_device_id); + +static struct i2c_driver ucsi_ccg_driver = { + .driver = { + .name = "ucsi_ccg", + }, + .probe = ucsi_ccg_probe, + .remove = ucsi_ccg_remove, + .id_table = ucsi_ccg_device_id, +}; + +module_i2c_driver(ucsi_ccg_driver); + +MODULE_AUTHOR("Ajay Gupta <ajayg@nvidia.com>"); +MODULE_DESCRIPTION("UCSI driver for Cypress CCGx Type-C controller"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index f15f89df1f36..7ea6fb6a2e5d 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -914,7 +914,7 @@ int gnttab_dma_free_pages(struct gnttab_dma_alloc_args *args) ret = xenmem_reservation_increase(args->nr_pages, args->frames); if (ret != args->nr_pages) { - pr_debug("Failed to decrease reservation for DMA buffer\n"); + pr_debug("Failed to increase reservation for DMA buffer\n"); ret = -EFAULT; } else { ret = 0; diff --git a/drivers/xen/privcmd-buf.c b/drivers/xen/privcmd-buf.c index df1ed37c3269..de01a6d0059d 100644 --- a/drivers/xen/privcmd-buf.c +++ b/drivers/xen/privcmd-buf.c @@ -21,15 +21,9 @@ MODULE_LICENSE("GPL"); -static unsigned int limit = 64; -module_param(limit, uint, 0644); -MODULE_PARM_DESC(limit, "Maximum number of pages that may be allocated by " - "the privcmd-buf device per open file"); - struct privcmd_buf_private { struct mutex lock; struct list_head list; - unsigned int allocated; }; struct privcmd_buf_vma_private { @@ -60,13 +54,10 @@ static void privcmd_buf_vmapriv_free(struct privcmd_buf_vma_private *vma_priv) { unsigned int i; - vma_priv->file_priv->allocated -= vma_priv->n_pages; - list_del(&vma_priv->list); for (i = 0; i < vma_priv->n_pages; i++) - if (vma_priv->pages[i]) - __free_page(vma_priv->pages[i]); + __free_page(vma_priv->pages[i]); kfree(vma_priv); } @@ -146,8 +137,7 @@ static int privcmd_buf_mmap(struct file *file, struct vm_area_struct *vma) unsigned int i; int ret = 0; - if (!(vma->vm_flags & VM_SHARED) || count > limit || - file_priv->allocated + count > limit) + if (!(vma->vm_flags & VM_SHARED)) return -EINVAL; vma_priv = kzalloc(sizeof(*vma_priv) + count * sizeof(void *), @@ -155,19 +145,15 @@ static int privcmd_buf_mmap(struct file *file, struct vm_area_struct *vma) if (!vma_priv) return -ENOMEM; - vma_priv->n_pages = count; - count = 0; - for (i = 0; i < vma_priv->n_pages; i++) { + for (i = 0; i < count; i++) { vma_priv->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!vma_priv->pages[i]) break; - count++; + vma_priv->n_pages++; } mutex_lock(&file_priv->lock); - file_priv->allocated += count; - vma_priv->file_priv = file_priv; vma_priv->users = 1; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 80953528572d..68f322f600a0 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3163,6 +3163,9 @@ void btrfs_destroy_inode(struct inode *inode); int btrfs_drop_inode(struct inode *inode); int __init btrfs_init_cachep(void); void __cold btrfs_destroy_cachep(void); +struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location, + struct btrfs_root *root, int *new, + struct btrfs_path *path); struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, struct btrfs_root *root, int *was_new); struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b0ab41da91d1..3f0b6d1936e8 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1664,9 +1664,8 @@ static int cleaner_kthread(void *arg) struct btrfs_root *root = arg; struct btrfs_fs_info *fs_info = root->fs_info; int again; - struct btrfs_trans_handle *trans; - do { + while (1) { again = 0; /* Make the cleaner go to sleep early. */ @@ -1715,42 +1714,16 @@ static int cleaner_kthread(void *arg) */ btrfs_delete_unused_bgs(fs_info); sleep: + if (kthread_should_park()) + kthread_parkme(); + if (kthread_should_stop()) + return 0; if (!again) { set_current_state(TASK_INTERRUPTIBLE); - if (!kthread_should_stop()) - schedule(); + schedule(); __set_current_state(TASK_RUNNING); } - } while (!kthread_should_stop()); - - /* - * Transaction kthread is stopped before us and wakes us up. - * However we might have started a new transaction and COWed some - * tree blocks when deleting unused block groups for example. So - * make sure we commit the transaction we started to have a clean - * shutdown when evicting the btree inode - if it has dirty pages - * when we do the final iput() on it, eviction will trigger a - * writeback for it which will fail with null pointer dereferences - * since work queues and other resources were already released and - * destroyed by the time the iput/eviction/writeback is made. - */ - trans = btrfs_attach_transaction(root); - if (IS_ERR(trans)) { - if (PTR_ERR(trans) != -ENOENT) - btrfs_err(fs_info, - "cleaner transaction attach returned %ld", - PTR_ERR(trans)); - } else { - int ret; - - ret = btrfs_commit_transaction(trans); - if (ret) - btrfs_err(fs_info, - "cleaner open transaction commit returned %d", - ret); } - - return 0; } static int transaction_kthread(void *arg) @@ -3931,6 +3904,13 @@ void close_ctree(struct btrfs_fs_info *fs_info) int ret; set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags); + /* + * We don't want the cleaner to start new transactions, add more delayed + * iputs, etc. while we're closing. We can't use kthread_stop() yet + * because that frees the task_struct, and the transaction kthread might + * still try to wake up the cleaner. + */ + kthread_park(fs_info->cleaner_kthread); /* wait for the qgroup rescan worker to stop */ btrfs_qgroup_wait_for_completion(fs_info, false); @@ -3958,9 +3938,8 @@ void close_ctree(struct btrfs_fs_info *fs_info) if (!sb_rdonly(fs_info->sb)) { /* - * If the cleaner thread is stopped and there are - * block groups queued for removal, the deletion will be - * skipped when we quit the cleaner thread. + * The cleaner kthread is stopped, so do one final pass over + * unused block groups. */ btrfs_delete_unused_bgs(fs_info); @@ -4359,13 +4338,23 @@ static int btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info, unpin = pinned_extents; again: while (1) { + /* + * The btrfs_finish_extent_commit() may get the same range as + * ours between find_first_extent_bit and clear_extent_dirty. + * Hence, hold the unused_bg_unpin_mutex to avoid double unpin + * the same extent range. + */ + mutex_lock(&fs_info->unused_bg_unpin_mutex); ret = find_first_extent_bit(unpin, 0, &start, &end, EXTENT_DIRTY, NULL); - if (ret) + if (ret) { + mutex_unlock(&fs_info->unused_bg_unpin_mutex); break; + } clear_extent_dirty(unpin, start, end); btrfs_error_unpin_extent_range(fs_info, start, end); + mutex_unlock(&fs_info->unused_bg_unpin_mutex); cond_resched(); } diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 4ba0aedc878b..74aa552f4793 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -75,7 +75,8 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root, * sure NOFS is set to keep us from deadlocking. */ nofs_flag = memalloc_nofs_save(); - inode = btrfs_iget(fs_info->sb, &location, root, NULL); + inode = btrfs_iget_path(fs_info->sb, &location, root, NULL, path); + btrfs_release_path(path); memalloc_nofs_restore(nofs_flag); if (IS_ERR(inode)) return inode; @@ -838,6 +839,25 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info, path->search_commit_root = 1; path->skip_locking = 1; + /* + * We must pass a path with search_commit_root set to btrfs_iget in + * order to avoid a deadlock when allocating extents for the tree root. + * + * When we are COWing an extent buffer from the tree root, when looking + * for a free extent, at extent-tree.c:find_free_extent(), we can find + * block group without its free space cache loaded. When we find one + * we must load its space cache which requires reading its free space + * cache's inode item from the root tree. If this inode item is located + * in the same leaf that we started COWing before, then we end up in + * deadlock on the extent buffer (trying to read lock it when we + * previously write locked it). + * + * It's safe to read the inode item using the commit root because + * block groups, once loaded, stay in memory forever (until they are + * removed) as well as their space caches once loaded. New block groups + * once created get their ->cached field set to BTRFS_CACHE_FINISHED so + * we will never try to read their inode item while the fs is mounted. + */ inode = lookup_free_space_inode(fs_info, block_group, path); if (IS_ERR(inode)) { btrfs_free_path(path); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d3df5b52278c..9ea4c6f0352f 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1531,12 +1531,11 @@ out_check: } btrfs_release_path(path); - if (cur_offset <= end && cow_start == (u64)-1) { + if (cur_offset <= end && cow_start == (u64)-1) cow_start = cur_offset; - cur_offset = end; - } if (cow_start != (u64)-1) { + cur_offset = end; ret = cow_file_range(inode, locked_page, cow_start, end, end, page_started, nr_written, 1, NULL); if (ret) @@ -3570,10 +3569,11 @@ static noinline int acls_after_inode_item(struct extent_buffer *leaf, /* * read an inode from the btree into the in-memory inode */ -static int btrfs_read_locked_inode(struct inode *inode) +static int btrfs_read_locked_inode(struct inode *inode, + struct btrfs_path *in_path) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_path *path; + struct btrfs_path *path = in_path; struct extent_buffer *leaf; struct btrfs_inode_item *inode_item; struct btrfs_root *root = BTRFS_I(inode)->root; @@ -3589,15 +3589,18 @@ static int btrfs_read_locked_inode(struct inode *inode) if (!ret) filled = true; - path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; + if (!path) { + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + } memcpy(&location, &BTRFS_I(inode)->location, sizeof(location)); ret = btrfs_lookup_inode(NULL, root, path, &location, 0); if (ret) { - btrfs_free_path(path); + if (path != in_path) + btrfs_free_path(path); return ret; } @@ -3722,7 +3725,8 @@ cache_acl: btrfs_ino(BTRFS_I(inode)), root->root_key.objectid, ret); } - btrfs_free_path(path); + if (path != in_path) + btrfs_free_path(path); if (!maybe_acls) cache_no_acl(inode); @@ -5644,8 +5648,9 @@ static struct inode *btrfs_iget_locked(struct super_block *s, /* Get an inode object given its location and corresponding root. * Returns in *is_new if the inode was read from disk */ -struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, - struct btrfs_root *root, int *new) +struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location, + struct btrfs_root *root, int *new, + struct btrfs_path *path) { struct inode *inode; @@ -5656,7 +5661,7 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, if (inode->i_state & I_NEW) { int ret; - ret = btrfs_read_locked_inode(inode); + ret = btrfs_read_locked_inode(inode, path); if (!ret) { inode_tree_add(inode); unlock_new_inode(inode); @@ -5678,6 +5683,12 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, return inode; } +struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, + struct btrfs_root *root, int *new) +{ + return btrfs_iget_path(s, location, root, new, NULL); +} + static struct inode *new_simple_dir(struct super_block *s, struct btrfs_key *key, struct btrfs_root *root) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 3ca6943827ef..802a628e9f7d 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3488,6 +3488,8 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen, const u64 sz = BTRFS_I(src)->root->fs_info->sectorsize; len = round_down(i_size_read(src), sz) - loff; + if (len == 0) + return 0; olen = len; } } @@ -4257,9 +4259,17 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src, goto out_unlock; if (len == 0) olen = len = src->i_size - off; - /* if we extend to eof, continue to block boundary */ - if (off + len == src->i_size) + /* + * If we extend to eof, continue to block boundary if and only if the + * destination end offset matches the destination file's size, otherwise + * we would be corrupting data by placing the eof block into the middle + * of a file. + */ + if (off + len == src->i_size) { + if (!IS_ALIGNED(len, bs) && destoff + len < inode->i_size) + goto out_unlock; len = ALIGN(src->i_size, bs) - off; + } if (len == 0) { ret = 0; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index b362b45dd757..cbc9d0d2c12d 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1916,7 +1916,7 @@ restore: } /* Used to sort the devices by max_avail(descending sort) */ -static int btrfs_cmp_device_free_bytes(const void *dev_info1, +static inline int btrfs_cmp_device_free_bytes(const void *dev_info1, const void *dev_info2) { if (((struct btrfs_device_info *)dev_info1)->max_avail > @@ -1945,8 +1945,8 @@ static inline void btrfs_descending_sort_devices( * The helper to calc the free space on the devices that can be used to store * file data. */ -static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, - u64 *free_bytes) +static inline int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, + u64 *free_bytes) { struct btrfs_device_info *devices_info; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index cab0b1f1f741..efcf89a8ba44 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -440,7 +440,7 @@ static int check_block_group_item(struct btrfs_fs_info *fs_info, type != (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA)) { block_group_err(fs_info, leaf, slot, -"invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llu or 0x%llx", +"invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llx or 0x%llx", type, hweight64(type), BTRFS_BLOCK_GROUP_DATA, BTRFS_BLOCK_GROUP_METADATA, BTRFS_BLOCK_GROUP_SYSTEM, diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index e07f3376b7df..a5ce99a6c936 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4396,6 +4396,23 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, logged_end = end; list_for_each_entry_safe(em, n, &tree->modified_extents, list) { + /* + * Skip extents outside our logging range. It's important to do + * it for correctness because if we don't ignore them, we may + * log them before their ordered extent completes, and therefore + * we could log them without logging their respective checksums + * (the checksum items are added to the csum tree at the very + * end of btrfs_finish_ordered_io()). Also leave such extents + * outside of our range in the list, since we may have another + * ranged fsync in the near future that needs them. If an extent + * outside our range corresponds to a hole, log it to avoid + * leaving gaps between extents (fsck will complain when we are + * not using the NO_HOLES feature). + */ + if ((em->start > end || em->start + em->len <= start) && + em->block_start != EXTENT_MAP_HOLE) + continue; + list_del_init(&em->list); /* * Just an arbitrary number, this can be really CPU intensive diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 27cad84dab23..189df668b6a0 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1931,10 +1931,17 @@ static ssize_t ceph_copy_file_range(struct file *src_file, loff_t src_off, if (!prealloc_cf) return -ENOMEM; - /* Start by sync'ing the source file */ + /* Start by sync'ing the source and destination files */ ret = file_write_and_wait_range(src_file, src_off, (src_off + len)); - if (ret < 0) + if (ret < 0) { + dout("failed to write src file (%zd)\n", ret); + goto out; + } + ret = file_write_and_wait_range(dst_file, dst_off, (dst_off + len)); + if (ret < 0) { + dout("failed to write dst file (%zd)\n", ret); goto out; + } /* * We need FILE_WR caps for dst_ci and FILE_RD for src_ci as other diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 67a9aeb2f4ec..bd13a3267ae0 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -80,12 +80,8 @@ static int parse_reply_info_in(void **p, void *end, info->symlink = *p; *p += info->symlink_len; - if (features & CEPH_FEATURE_DIRLAYOUTHASH) - ceph_decode_copy_safe(p, end, &info->dir_layout, - sizeof(info->dir_layout), bad); - else - memset(&info->dir_layout, 0, sizeof(info->dir_layout)); - + ceph_decode_copy_safe(p, end, &info->dir_layout, + sizeof(info->dir_layout), bad); ceph_decode_32_safe(p, end, info->xattr_len, bad); ceph_decode_need(p, end, info->xattr_len, bad); info->xattr_data = *p; @@ -3182,10 +3178,8 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, recon_state.pagelist = pagelist; if (session->s_con.peer_features & CEPH_FEATURE_MDSENC) recon_state.msg_version = 3; - else if (session->s_con.peer_features & CEPH_FEATURE_FLOCK) - recon_state.msg_version = 2; else - recon_state.msg_version = 1; + recon_state.msg_version = 2; err = iterate_session_caps(session, encode_caps_cb, &recon_state); if (err < 0) goto fail; diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c index 32d4f13784ba..03f4d24db8fe 100644 --- a/fs/ceph/quota.c +++ b/fs/ceph/quota.c @@ -237,7 +237,8 @@ static bool check_quota_exceeded(struct inode *inode, enum quota_check_op op, ceph_put_snap_realm(mdsc, realm); realm = next; } - ceph_put_snap_realm(mdsc, realm); + if (realm) + ceph_put_snap_realm(mdsc, realm); up_read(&mdsc->snap_rwsem); return exceeded; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 05f01fbd9c7f..22a9d8159720 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5835,9 +5835,10 @@ int ext4_mark_iloc_dirty(handle_t *handle, { int err = 0; - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) { + put_bh(iloc->bh); return -EIO; - + } if (IS_I_VERSION(inode)) inode_inc_iversion(inode); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 17adcb16a9c8..437f71fe83ae 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -126,6 +126,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, if (!is_dx_block && type == INDEX) { ext4_error_inode(inode, func, line, block, "directory leaf block found instead of index block"); + brelse(bh); return ERR_PTR(-EFSCORRUPTED); } if (!ext4_has_metadata_csum(inode->i_sb) || @@ -2811,7 +2812,9 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) list_del_init(&EXT4_I(inode)->i_orphan); mutex_unlock(&sbi->s_orphan_lock); } - } + } else + brelse(iloc.bh); + jbd_debug(4, "superblock will point to %lu\n", inode->i_ino); jbd_debug(4, "orphan inode %lu will point to %d\n", inode->i_ino, NEXT_ORPHAN(inode)); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index ebbc663d0798..a5efee34415f 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -459,16 +459,18 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle, BUFFER_TRACE(bh, "get_write_access"); err = ext4_journal_get_write_access(handle, bh); - if (err) + if (err) { + brelse(bh); return err; + } ext4_debug("mark block bitmap %#04llx (+%llu/%u)\n", first_cluster, first_cluster - start, count2); ext4_set_bits(bh->b_data, first_cluster - start, count2); err = ext4_handle_dirty_metadata(handle, NULL, bh); + brelse(bh); if (unlikely(err)) return err; - brelse(bh); } return 0; @@ -605,7 +607,6 @@ handle_bb: bh = bclean(handle, sb, block); if (IS_ERR(bh)) { err = PTR_ERR(bh); - bh = NULL; goto out; } overhead = ext4_group_overhead_blocks(sb, group); @@ -618,9 +619,9 @@ handle_bb: ext4_mark_bitmap_end(EXT4_B2C(sbi, group_data[i].blocks_count), sb->s_blocksize * 8, bh->b_data); err = ext4_handle_dirty_metadata(handle, NULL, bh); + brelse(bh); if (err) goto out; - brelse(bh); handle_ib: if (bg_flags[i] & EXT4_BG_INODE_UNINIT) @@ -635,18 +636,16 @@ handle_ib: bh = bclean(handle, sb, block); if (IS_ERR(bh)) { err = PTR_ERR(bh); - bh = NULL; goto out; } ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8, bh->b_data); err = ext4_handle_dirty_metadata(handle, NULL, bh); + brelse(bh); if (err) goto out; - brelse(bh); } - bh = NULL; /* Mark group tables in block bitmap */ for (j = 0; j < GROUP_TABLE_COUNT; j++) { @@ -685,7 +684,6 @@ handle_ib: } out: - brelse(bh); err2 = ext4_journal_stop(handle); if (err2 && !err) err = err2; @@ -873,6 +871,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh); if (unlikely(err)) { ext4_std_error(sb, err); + iloc.bh = NULL; goto exit_inode; } brelse(dind); @@ -924,6 +923,7 @@ static int add_new_gdb_meta_bg(struct super_block *sb, sizeof(struct buffer_head *), GFP_NOFS); if (!n_group_desc) { + brelse(gdb_bh); err = -ENOMEM; ext4_warning(sb, "not enough memory for %lu groups", gdb_num + 1); @@ -939,8 +939,6 @@ static int add_new_gdb_meta_bg(struct super_block *sb, kvfree(o_group_desc); BUFFER_TRACE(gdb_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, gdb_bh); - if (unlikely(err)) - brelse(gdb_bh); return err; } @@ -1124,8 +1122,10 @@ static void update_backups(struct super_block *sb, sector_t blk_off, char *data, backup_block, backup_block - ext4_group_first_block_no(sb, group)); BUFFER_TRACE(bh, "get_write_access"); - if ((err = ext4_journal_get_write_access(handle, bh))) + if ((err = ext4_journal_get_write_access(handle, bh))) { + brelse(bh); break; + } lock_buffer(bh); memcpy(bh->b_data, data, size); if (rest) @@ -2023,7 +2023,7 @@ retry: err = ext4_alloc_flex_bg_array(sb, n_group + 1); if (err) - return err; + goto out; err = ext4_mb_alloc_groupinfo(sb, n_group + 1); if (err) @@ -2059,6 +2059,10 @@ retry: n_blocks_count_retry = 0; free_flex_gd(flex_gd); flex_gd = NULL; + if (resize_inode) { + iput(resize_inode); + resize_inode = NULL; + } goto retry; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a221f1cdf704..53ff6c2a26ed 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4075,6 +4075,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_groups_count = blocks_count; sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count, (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb))); + if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) != + le32_to_cpu(es->s_inodes_count)) { + ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu", + le32_to_cpu(es->s_inodes_count), + ((u64)sbi->s_groups_count * sbi->s_inodes_per_group)); + ret = -EINVAL; + goto failed_mount; + } db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb); if (ext4_has_feature_meta_bg(sb)) { @@ -4094,14 +4102,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ret = -ENOMEM; goto failed_mount; } - if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) != - le32_to_cpu(es->s_inodes_count)) { - ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu", - le32_to_cpu(es->s_inodes_count), - ((u64)sbi->s_groups_count * sbi->s_inodes_per_group)); - ret = -EINVAL; - goto failed_mount; - } bgl_lock_init(sbi->s_blockgroup_lock); @@ -4510,6 +4510,7 @@ failed_mount6: percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); percpu_counter_destroy(&sbi->s_dirtyclusters_counter); + percpu_free_rwsem(&sbi->s_journal_flag_rwsem); failed_mount5: ext4_ext_release(sb); ext4_release_system_zone(sb); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index f36fc5d5b257..7643d52c776c 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1031,10 +1031,8 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, inode_lock(ea_inode); ret = ext4_reserve_inode_write(handle, ea_inode, &iloc); - if (ret) { - iloc.bh = NULL; + if (ret) goto out; - } ref_count = ext4_xattr_inode_get_ref(ea_inode); ref_count += ref_change; @@ -1080,12 +1078,10 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, } ret = ext4_mark_iloc_dirty(handle, ea_inode, &iloc); - iloc.bh = NULL; if (ret) ext4_warning_inode(ea_inode, "ext4_mark_iloc_dirty() failed ret=%d", ret); out: - brelse(iloc.bh); inode_unlock(ea_inode); return ret; } @@ -1388,6 +1384,12 @@ retry: bh = ext4_getblk(handle, ea_inode, block, 0); if (IS_ERR(bh)) return PTR_ERR(bh); + if (!bh) { + WARN_ON_ONCE(1); + EXT4_ERROR_INODE(ea_inode, + "ext4_getblk() return bh = NULL"); + return -EFSCORRUPTED; + } ret = ext4_journal_get_write_access(handle, bh); if (ret) goto out; @@ -2276,8 +2278,10 @@ static struct buffer_head *ext4_xattr_get_block(struct inode *inode) if (!bh) return ERR_PTR(-EIO); error = ext4_xattr_check_block(inode, bh); - if (error) + if (error) { + brelse(bh); return ERR_PTR(error); + } return bh; } @@ -2397,6 +2401,8 @@ retry_inode: error = ext4_xattr_block_set(handle, inode, &i, &bs); } else if (error == -ENOSPC) { if (EXT4_I(inode)->i_file_acl && !bs.s.base) { + brelse(bs.bh); + bs.bh = NULL; error = ext4_xattr_block_find(inode, &i, &bs); if (error) goto cleanup; @@ -2617,6 +2623,8 @@ out: kfree(buffer); if (is) brelse(is->iloc.bh); + if (bs) + brelse(bs->bh); kfree(is); kfree(bs); @@ -2696,7 +2704,6 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, struct ext4_inode *raw_inode, handle_t *handle) { struct ext4_xattr_ibody_header *header; - struct buffer_head *bh; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); static unsigned int mnt_count; size_t min_offs; @@ -2737,13 +2744,17 @@ retry: * EA block can hold new_extra_isize bytes. */ if (EXT4_I(inode)->i_file_acl) { + struct buffer_head *bh; + bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl); error = -EIO; if (!bh) goto cleanup; error = ext4_xattr_check_block(inode, bh); - if (error) + if (error) { + brelse(bh); goto cleanup; + } base = BHDR(bh); end = bh->b_data + bh->b_size; min_offs = end - base; diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index ae813e609932..a5e516a40e7a 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -165,9 +165,13 @@ static bool fuse_block_alloc(struct fuse_conn *fc, bool for_background) static void fuse_drop_waiting(struct fuse_conn *fc) { - if (fc->connected) { - atomic_dec(&fc->num_waiting); - } else if (atomic_dec_and_test(&fc->num_waiting)) { + /* + * lockess check of fc->connected is okay, because atomic_dec_and_test() + * provides a memory barrier mached with the one in fuse_wait_aborted() + * to ensure no wake-up is missed. + */ + if (atomic_dec_and_test(&fc->num_waiting) && + !READ_ONCE(fc->connected)) { /* wake up aborters */ wake_up_all(&fc->blocked_waitq); } @@ -1768,8 +1772,10 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, req->in.args[1].size = total_len; err = fuse_request_send_notify_reply(fc, req, outarg->notify_unique); - if (err) + if (err) { fuse_retrieve_end(fc, req); + fuse_put_request(fc, req); + } return err; } @@ -2219,6 +2225,8 @@ EXPORT_SYMBOL_GPL(fuse_abort_conn); void fuse_wait_aborted(struct fuse_conn *fc) { + /* matches implicit memory barrier in fuse_drop_waiting() */ + smp_mb(); wait_event(fc->blocked_waitq, atomic_read(&fc->num_waiting) == 0); } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index cc2121b37bf5..b52f9baaa3e7 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2924,10 +2924,12 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) } if (io->async) { + bool blocking = io->blocking; + fuse_aio_complete(io, ret < 0 ? ret : 0, -1); /* we have a non-extending, async request, so return */ - if (!io->blocking) + if (!blocking) return -EIOCBQUEUED; wait_for_completion(&wait); diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index a683d9b27d76..9a4a15d646eb 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -826,7 +826,7 @@ static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length, ret = gfs2_meta_inode_buffer(ip, &dibh); if (ret) goto unlock; - iomap->private = dibh; + mp->mp_bh[0] = dibh; if (gfs2_is_stuffed(ip)) { if (flags & IOMAP_WRITE) { @@ -863,9 +863,6 @@ unstuff: len = lblock_stop - lblock + 1; iomap->length = len << inode->i_blkbits; - get_bh(dibh); - mp->mp_bh[0] = dibh; - height = ip->i_height; while ((lblock + 1) * sdp->sd_sb.sb_bsize > sdp->sd_heightsize[height]) height++; @@ -898,8 +895,6 @@ out: iomap->bdev = inode->i_sb->s_bdev; unlock: up_read(&ip->i_rw_mutex); - if (ret && dibh) - brelse(dibh); return ret; do_alloc: @@ -980,9 +975,9 @@ static void gfs2_iomap_journaled_page_done(struct inode *inode, loff_t pos, static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, loff_t length, unsigned flags, - struct iomap *iomap) + struct iomap *iomap, + struct metapath *mp) { - struct metapath mp = { .mp_aheight = 1, }; struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); unsigned int data_blocks = 0, ind_blocks = 0, rblocks; @@ -996,9 +991,9 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, unstuff = gfs2_is_stuffed(ip) && pos + length > gfs2_max_stuffed_size(ip); - ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp); + ret = gfs2_iomap_get(inode, pos, length, flags, iomap, mp); if (ret) - goto out_release; + goto out_unlock; alloc_required = unstuff || iomap->type == IOMAP_HOLE; @@ -1013,7 +1008,7 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, ret = gfs2_quota_lock_check(ip, &ap); if (ret) - goto out_release; + goto out_unlock; ret = gfs2_inplace_reserve(ip, &ap); if (ret) @@ -1038,17 +1033,15 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, ret = gfs2_unstuff_dinode(ip, NULL); if (ret) goto out_trans_end; - release_metapath(&mp); - brelse(iomap->private); - iomap->private = NULL; + release_metapath(mp); ret = gfs2_iomap_get(inode, iomap->offset, iomap->length, - flags, iomap, &mp); + flags, iomap, mp); if (ret) goto out_trans_end; } if (iomap->type == IOMAP_HOLE) { - ret = gfs2_iomap_alloc(inode, iomap, flags, &mp); + ret = gfs2_iomap_alloc(inode, iomap, flags, mp); if (ret) { gfs2_trans_end(sdp); gfs2_inplace_release(ip); @@ -1056,7 +1049,6 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, goto out_qunlock; } } - release_metapath(&mp); if (!gfs2_is_stuffed(ip) && gfs2_is_jdata(ip)) iomap->page_done = gfs2_iomap_journaled_page_done; return 0; @@ -1069,10 +1061,7 @@ out_trans_fail: out_qunlock: if (alloc_required) gfs2_quota_unlock(ip); -out_release: - if (iomap->private) - brelse(iomap->private); - release_metapath(&mp); +out_unlock: gfs2_write_unlock(inode); return ret; } @@ -1088,10 +1077,10 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length, trace_gfs2_iomap_start(ip, pos, length, flags); if ((flags & IOMAP_WRITE) && !(flags & IOMAP_DIRECT)) { - ret = gfs2_iomap_begin_write(inode, pos, length, flags, iomap); + ret = gfs2_iomap_begin_write(inode, pos, length, flags, iomap, &mp); } else { ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp); - release_metapath(&mp); + /* * Silently fall back to buffered I/O for stuffed files or if * we've hot a hole (see gfs2_file_direct_write). @@ -1100,6 +1089,11 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length, iomap->type != IOMAP_MAPPED) ret = -ENOTBLK; } + if (!ret) { + get_bh(mp.mp_bh[0]); + iomap->private = mp.mp_bh[0]; + } + release_metapath(&mp); trace_gfs2_iomap_end(ip, iomap, ret); return ret; } @@ -1908,10 +1902,16 @@ static int punch_hole(struct gfs2_inode *ip, u64 offset, u64 length) if (ret < 0) goto out; - /* issue read-ahead on metadata */ - if (mp.mp_aheight > 1) { - for (; ret > 1; ret--) { - metapointer_range(&mp, mp.mp_aheight - ret, + /* On the first pass, issue read-ahead on metadata. */ + if (mp.mp_aheight > 1 && strip_h == ip->i_height - 1) { + unsigned int height = mp.mp_aheight - 1; + + /* No read-ahead for data blocks. */ + if (mp.mp_aheight - 1 == strip_h) + height--; + + for (; height >= mp.mp_aheight - ret; height--) { + metapointer_range(&mp, height, start_list, start_aligned, end_list, end_aligned, &start, &end); diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index ffe3032b1043..b08a530433ad 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -733,6 +733,7 @@ void gfs2_clear_rgrpd(struct gfs2_sbd *sdp) if (gl) { glock_clear_object(gl, rgd); + gfs2_rgrp_brelse(rgd); gfs2_glock_put(gl); } @@ -1174,7 +1175,7 @@ static u32 count_unlinked(struct gfs2_rgrpd *rgd) * @rgd: the struct gfs2_rgrpd describing the RG to read in * * Read in all of a Resource Group's header and bitmap blocks. - * Caller must eventually call gfs2_rgrp_relse() to free the bitmaps. + * Caller must eventually call gfs2_rgrp_brelse() to free the bitmaps. * * Returns: errno */ diff --git a/fs/inode.c b/fs/inode.c index 9e198f00b64c..35d2108d567c 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -730,8 +730,11 @@ static enum lru_status inode_lru_isolate(struct list_head *item, return LRU_REMOVED; } - /* recently referenced inodes get one more pass */ - if (inode->i_state & I_REFERENCED) { + /* + * Recently referenced inodes and inodes with many attached pages + * get one more pass. + */ + if (inode->i_state & I_REFERENCED || inode->i_data.nrpages > 1) { inode->i_state &= ~I_REFERENCED; spin_unlock(&inode->i_lock); return LRU_ROTATE; diff --git a/fs/namespace.c b/fs/namespace.c index 98d27da43304..a7f91265ea67 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -695,9 +695,6 @@ static struct mountpoint *lookup_mountpoint(struct dentry *dentry) hlist_for_each_entry(mp, chain, m_hash) { if (mp->m_dentry == dentry) { - /* might be worth a WARN_ON() */ - if (d_unlinked(dentry)) - return ERR_PTR(-ENOENT); mp->m_count++; return mp; } @@ -711,6 +708,9 @@ static struct mountpoint *get_mountpoint(struct dentry *dentry) int ret; if (d_mountpoint(dentry)) { + /* might be worth a WARN_ON() */ + if (d_unlinked(dentry)) + return ERR_PTR(-ENOENT); mountpoint: read_seqlock_excl(&mount_lock); mp = lookup_mountpoint(dentry); @@ -1540,8 +1540,13 @@ static int do_umount(struct mount *mnt, int flags) namespace_lock(); lock_mount_hash(); - event++; + /* Recheck MNT_LOCKED with the locks held */ + retval = -EINVAL; + if (mnt->mnt.mnt_flags & MNT_LOCKED) + goto out; + + event++; if (flags & MNT_DETACH) { if (!list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE); @@ -1555,6 +1560,7 @@ static int do_umount(struct mount *mnt, int flags) retval = 0; } } +out: unlock_mount_hash(); namespace_unlock(); return retval; @@ -1645,7 +1651,7 @@ int ksys_umount(char __user *name, int flags) goto dput_and_out; if (!check_mnt(mnt)) goto dput_and_out; - if (mnt->mnt.mnt_flags & MNT_LOCKED) + if (mnt->mnt.mnt_flags & MNT_LOCKED) /* Check optimistically */ goto dput_and_out; retval = -EPERM; if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN)) @@ -1728,8 +1734,14 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, for (s = r; s; s = next_mnt(s, r)) { if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(s)) { - s = skip_mnt_tree(s); - continue; + if (s->mnt.mnt_flags & MNT_LOCKED) { + /* Both unbindable and locked. */ + q = ERR_PTR(-EPERM); + goto out; + } else { + s = skip_mnt_tree(s); + continue; + } } if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(s->mnt.mnt_root)) { @@ -1782,7 +1794,7 @@ void drop_collected_mounts(struct vfsmount *mnt) { namespace_lock(); lock_mount_hash(); - umount_tree(real_mount(mnt), UMOUNT_SYNC); + umount_tree(real_mount(mnt), 0); unlock_mount_hash(); namespace_unlock(); } diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index fa515d5ea5ba..7b861bbc0b43 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -66,7 +66,7 @@ __be32 nfs4_callback_getattr(void *argp, void *resp, out_iput: rcu_read_unlock(); trace_nfs4_cb_getattr(cps->clp, &args->fh, inode, -ntohl(res->status)); - iput(inode); + nfs_iput_and_deactive(inode); out: dprintk("%s: exit with status = %d\n", __func__, ntohl(res->status)); return res->status; @@ -108,7 +108,7 @@ __be32 nfs4_callback_recall(void *argp, void *resp, } trace_nfs4_cb_recall(cps->clp, &args->fh, inode, &args->stateid, -ntohl(res)); - iput(inode); + nfs_iput_and_deactive(inode); out: dprintk("%s: exit with status = %d\n", __func__, ntohl(res)); return res; diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 07b839560576..6ec2f78c1e19 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -850,16 +850,23 @@ nfs_delegation_find_inode_server(struct nfs_server *server, const struct nfs_fh *fhandle) { struct nfs_delegation *delegation; - struct inode *res = NULL; + struct inode *freeme, *res = NULL; list_for_each_entry_rcu(delegation, &server->delegations, super_list) { spin_lock(&delegation->lock); if (delegation->inode != NULL && nfs_compare_fh(fhandle, &NFS_I(delegation->inode)->fh) == 0) { - res = igrab(delegation->inode); + freeme = igrab(delegation->inode); + if (freeme && nfs_sb_active(freeme->i_sb)) + res = freeme; spin_unlock(&delegation->lock); if (res != NULL) return res; + if (freeme) { + rcu_read_unlock(); + iput(freeme); + rcu_read_lock(); + } return ERR_PTR(-EAGAIN); } spin_unlock(&delegation->lock); diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 62ae0fd345ad..ffea57885394 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -2601,11 +2601,12 @@ static void nfs4_state_manager(struct nfs_client *clp) nfs4_clear_state_manager_bit(clp); /* Did we race with an attempt to give us more work? */ if (clp->cl_state == 0) - break; + return; if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0) - break; - } while (refcount_read(&clp->cl_count) > 1); - return; + return; + } while (refcount_read(&clp->cl_count) > 1 && !signalled()); + goto out_drain; + out_error: if (strlen(section)) section_sep = ": "; @@ -2613,6 +2614,7 @@ out_error: " with error %d\n", section_sep, section, clp->cl_hostname, -status); ssleep(1); +out_drain: nfs4_end_drain_session(clp); nfs4_clear_state_manager_bit(clp); } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index edff074d38c7..d505990dac7c 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1038,6 +1038,9 @@ nfsd4_verify_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, { __be32 status; + if (!cstate->save_fh.fh_dentry) + return nfserr_nofilehandle; + status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh, src_stateid, RD_STATE, src, NULL); if (status) { diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 5769cf3ff035..e08a6647267b 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -115,12 +115,12 @@ static bool fanotify_should_send_event(struct fsnotify_iter_info *iter_info, continue; mark = iter_info->marks[type]; /* - * if the event is for a child and this inode doesn't care about - * events on the child, don't send it! + * If the event is for a child and this mark doesn't care about + * events on a child, don't send it! */ - if (type == FSNOTIFY_OBJ_TYPE_INODE && - (event_mask & FS_EVENT_ON_CHILD) && - !(mark->mask & FS_EVENT_ON_CHILD)) + if (event_mask & FS_EVENT_ON_CHILD && + (type != FSNOTIFY_OBJ_TYPE_INODE || + !(mark->mask & FS_EVENT_ON_CHILD))) continue; marks_mask |= mark->mask; diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 2172ba516c61..d2c34900ae05 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -167,9 +167,9 @@ int __fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask parent = dget_parent(dentry); p_inode = parent->d_inode; - if (unlikely(!fsnotify_inode_watches_children(p_inode))) + if (unlikely(!fsnotify_inode_watches_children(p_inode))) { __fsnotify_update_child_dentry_flags(p_inode); - else if (p_inode->i_fsnotify_mask & mask) { + } else if (p_inode->i_fsnotify_mask & mask & ALL_FSNOTIFY_EVENTS) { struct name_snapshot name; /* we are notifying a parent so come up with the new mask which @@ -339,6 +339,9 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is, sb = mnt->mnt.mnt_sb; mnt_or_sb_mask = mnt->mnt_fsnotify_mask | sb->s_fsnotify_mask; } + /* An event "on child" is not intended for a mount/sb mark */ + if (mask & FS_EVENT_ON_CHILD) + mnt_or_sb_mask = 0; /* * Optimization: srcu_read_lock() has a memory barrier which can diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index da578ad4c08f..eb1ce30412dc 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2411,8 +2411,16 @@ static int ocfs2_dio_end_io(struct kiocb *iocb, /* this io's submitter should not have unlocked this before we could */ BUG_ON(!ocfs2_iocb_is_rw_locked(iocb)); - if (bytes > 0 && private) - ret = ocfs2_dio_end_io_write(inode, private, offset, bytes); + if (bytes <= 0) + mlog_ratelimited(ML_ERROR, "Direct IO failed, bytes = %lld", + (long long)bytes); + if (private) { + if (bytes > 0) + ret = ocfs2_dio_end_io_write(inode, private, offset, + bytes); + else + ocfs2_dio_free_write_ctx(inode, private); + } ocfs2_iocb_clear_rw_locked(iocb); diff --git a/fs/ocfs2/cluster/masklog.h b/fs/ocfs2/cluster/masklog.h index 308ea0eb35fd..a396096a5099 100644 --- a/fs/ocfs2/cluster/masklog.h +++ b/fs/ocfs2/cluster/masklog.h @@ -178,6 +178,15 @@ do { \ ##__VA_ARGS__); \ } while (0) +#define mlog_ratelimited(mask, fmt, ...) \ +do { \ + static DEFINE_RATELIMIT_STATE(_rs, \ + DEFAULT_RATELIMIT_INTERVAL, \ + DEFAULT_RATELIMIT_BURST); \ + if (__ratelimit(&_rs)) \ + mlog(mask, fmt, ##__VA_ARGS__); \ +} while (0) + #define mlog_errno(st) ({ \ int _st = (st); \ if (_st != -ERESTARTSYS && _st != -EINTR && \ diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 6fc5425b1474..2652d00842d6 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -243,7 +243,7 @@ xfs_attr3_leaf_verify( struct xfs_mount *mp = bp->b_target->bt_mount; struct xfs_attr_leafblock *leaf = bp->b_addr; struct xfs_attr_leaf_entry *entries; - uint16_t end; + uint32_t end; /* must be 32bit - see below */ int i; xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf); @@ -293,6 +293,11 @@ xfs_attr3_leaf_verify( /* * Quickly check the freemap information. Attribute data has to be * aligned to 4-byte boundaries, and likewise for the free space. + * + * Note that for 64k block size filesystems, the freemap entries cannot + * overflow as they are only be16 fields. However, when checking end + * pointer of the freemap, we have to be careful to detect overflows and + * so use uint32_t for those checks. */ for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) { if (ichdr.freemap[i].base > mp->m_attr_geo->blksize) @@ -303,7 +308,9 @@ xfs_attr3_leaf_verify( return __this_address; if (ichdr.freemap[i].size & 0x3) return __this_address; - end = ichdr.freemap[i].base + ichdr.freemap[i].size; + + /* be care of 16 bit overflows here */ + end = (uint32_t)ichdr.freemap[i].base + ichdr.freemap[i].size; if (end < ichdr.freemap[i].base) return __this_address; if (end > mp->m_attr_geo->blksize) diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 6e2c08f30f60..6ecdbb3af7de 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1608,7 +1608,7 @@ xfs_ioc_getbmap( error = 0; out_free_buf: kmem_free(buf); - return 0; + return error; } struct getfsmap_info { diff --git a/fs/xfs/xfs_message.c b/fs/xfs/xfs_message.c index 576c375ce12a..6b736ea58d35 100644 --- a/fs/xfs/xfs_message.c +++ b/fs/xfs/xfs_message.c @@ -107,5 +107,5 @@ assfail(char *expr, char *file, int line) void xfs_hex_dump(void *p, int length) { - print_hex_dump(KERN_ALERT, "", DUMP_PREFIX_ADDRESS, 16, 1, p, length, 1); + print_hex_dump(KERN_ALERT, "", DUMP_PREFIX_OFFSET, 16, 1, p, length, 1); } diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h index 89f3b03b1445..e3667c9a33a5 100644 --- a/include/asm-generic/4level-fixup.h +++ b/include/asm-generic/4level-fixup.h @@ -3,7 +3,7 @@ #define _4LEVEL_FIXUP_H #define __ARCH_HAS_4LEVEL_HACK -#define __PAGETABLE_PUD_FOLDED +#define __PAGETABLE_PUD_FOLDED 1 #define PUD_SHIFT PGDIR_SHIFT #define PUD_SIZE PGDIR_SIZE diff --git a/include/asm-generic/5level-fixup.h b/include/asm-generic/5level-fixup.h index 9c2e0708eb82..73474bb52344 100644 --- a/include/asm-generic/5level-fixup.h +++ b/include/asm-generic/5level-fixup.h @@ -3,7 +3,7 @@ #define _5LEVEL_FIXUP_H #define __ARCH_HAS_5LEVEL_HACK -#define __PAGETABLE_P4D_FOLDED +#define __PAGETABLE_P4D_FOLDED 1 #define P4D_SHIFT PGDIR_SHIFT #define P4D_SIZE PGDIR_SIZE diff --git a/include/asm-generic/pgtable-nop4d-hack.h b/include/asm-generic/pgtable-nop4d-hack.h index 0c34215263b8..1d6dd38c0e5e 100644 --- a/include/asm-generic/pgtable-nop4d-hack.h +++ b/include/asm-generic/pgtable-nop4d-hack.h @@ -5,7 +5,7 @@ #ifndef __ASSEMBLY__ #include <asm-generic/5level-fixup.h> -#define __PAGETABLE_PUD_FOLDED +#define __PAGETABLE_PUD_FOLDED 1 /* * Having the pud type consist of a pgd gets the size right, and allows diff --git a/include/asm-generic/pgtable-nop4d.h b/include/asm-generic/pgtable-nop4d.h index 1a29b2a0282b..04cb913797bc 100644 --- a/include/asm-generic/pgtable-nop4d.h +++ b/include/asm-generic/pgtable-nop4d.h @@ -4,7 +4,7 @@ #ifndef __ASSEMBLY__ -#define __PAGETABLE_P4D_FOLDED +#define __PAGETABLE_P4D_FOLDED 1 typedef struct { pgd_t pgd; } p4d_t; diff --git a/include/asm-generic/pgtable-nopmd.h b/include/asm-generic/pgtable-nopmd.h index f35f6e8149e4..b85b8271a73d 100644 --- a/include/asm-generic/pgtable-nopmd.h +++ b/include/asm-generic/pgtable-nopmd.h @@ -8,7 +8,7 @@ struct mm_struct; -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 /* * Having the pmd type consist of a pud gets the size right, and allows diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h index e950b9c50f34..9bef475db6fe 100644 --- a/include/asm-generic/pgtable-nopud.h +++ b/include/asm-generic/pgtable-nopud.h @@ -9,7 +9,7 @@ #else #include <asm-generic/pgtable-nop4d.h> -#define __PAGETABLE_PUD_FOLDED +#define __PAGETABLE_PUD_FOLDED 1 /* * Having the pud type consist of a p4d gets the size right, and allows diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 5657a20e0c59..359fb935ded6 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -1127,4 +1127,20 @@ static inline bool arch_has_pfn_modify_check(void) #endif #endif +/* + * On some architectures it depends on the mm if the p4d/pud or pmd + * layer of the page table hierarchy is folded or not. + */ +#ifndef mm_p4d_folded +#define mm_p4d_folded(mm) __is_defined(__PAGETABLE_P4D_FOLDED) +#endif + +#ifndef mm_pud_folded +#define mm_pud_folded(mm) __is_defined(__PAGETABLE_PUD_FOLDED) +#endif + +#ifndef mm_pmd_folded +#define mm_pmd_folded(mm) __is_defined(__PAGETABLE_PMD_FOLDED) +#endif + #endif /* _ASM_GENERIC_PGTABLE_H */ diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 6b92b3395fa9..65a38c4a02a1 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -213,12 +213,6 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING | \ CEPH_FEATURE_CEPHX_V2) -#define CEPH_FEATURES_REQUIRED_DEFAULT \ - (CEPH_FEATURE_NOSRCADDR | \ - CEPH_FEATURE_SUBSCRIBE2 | \ - CEPH_FEATURE_RECONNECT_SEQ | \ - CEPH_FEATURE_PGID64 | \ - CEPH_FEATURE_PGPOOL3 | \ - CEPH_FEATURE_OSDENC) +#define CEPH_FEATURES_REQUIRED_DEFAULT 0 #endif diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 6b28c1b7310c..f8c400ba1929 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -4,22 +4,26 @@ /* * The attributes in this file are unconditionally defined and they directly - * map to compiler attribute(s) -- except those that are optional. + * map to compiler attribute(s), unless one of the compilers does not support + * the attribute. In that case, __has_attribute is used to check for support + * and the reason is stated in its comment ("Optional: ..."). * * Any other "attributes" (i.e. those that depend on a configuration option, * on a compiler, on an architecture, on plugins, on other attributes...) * should be defined elsewhere (e.g. compiler_types.h or compiler-*.h). + * The intention is to keep this file as simple as possible, as well as + * compiler- and version-agnostic (e.g. avoiding GCC_VERSION checks). * * This file is meant to be sorted (by actual attribute name, * not by #define identifier). Use the __attribute__((__name__)) syntax * (i.e. with underscores) to avoid future collisions with other macros. - * If an attribute is optional, state the reason in the comment. + * Provide links to the documentation of each supported compiler, if it exists. */ /* - * To check for optional attributes, we use __has_attribute, which is supported - * on gcc >= 5, clang >= 2.9 and icc >= 17. In the meantime, to support - * 4.6 <= gcc < 5, we implement __has_attribute by hand. + * __has_attribute is supported on gcc >= 5, clang >= 2.9 and icc >= 17. + * In the meantime, to support 4.6 <= gcc < 5, we implement __has_attribute + * by hand. * * sparse does not support __has_attribute (yet) and defines __GNUC_MINOR__ * depending on the compiler used to build it; however, these attributes have diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3439d7d0249a..4a3f9c09c92d 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -130,6 +130,10 @@ struct ftrace_likely_data { # define randomized_struct_fields_end #endif +#ifndef asm_volatile_goto +#define asm_volatile_goto(x...) asm goto(x) +#endif + /* Are two types/vars the same type (ignoring qualifiers)? */ #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) diff --git a/include/linux/efi.h b/include/linux/efi.h index 845174e113ce..100ce4a4aff6 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1167,6 +1167,8 @@ static inline bool efi_enabled(int feature) extern void efi_reboot(enum reboot_mode reboot_mode, const char *__unused); extern bool efi_is_table_address(unsigned long phys_addr); + +extern int efi_apply_persistent_mem_reservations(void); #else static inline bool efi_enabled(int feature) { @@ -1185,6 +1187,11 @@ static inline bool efi_is_table_address(unsigned long phys_addr) { return false; } + +static inline int efi_apply_persistent_mem_reservations(void) +{ + return 0; +} #endif extern int efi_status_to_err(efi_status_t status); diff --git a/include/linux/i8253.h b/include/linux/i8253.h index e6bb36a97519..8336b2f6f834 100644 --- a/include/linux/i8253.h +++ b/include/linux/i8253.h @@ -21,6 +21,7 @@ #define PIT_LATCH ((PIT_TICK_RATE + HZ/2) / HZ) extern raw_spinlock_t i8253_lock; +extern bool i8253_clear_counter_on_shutdown; extern struct clock_event_device i8253_clockevent; extern void clockevent_i8253_init(bool oneshot); diff --git a/include/linux/mm.h b/include/linux/mm.h index fcf9cc9d535f..5411de93a363 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1744,11 +1744,15 @@ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address); static inline void mm_inc_nr_puds(struct mm_struct *mm) { + if (mm_pud_folded(mm)) + return; atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_puds(struct mm_struct *mm) { + if (mm_pud_folded(mm)) + return; atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } #endif @@ -1768,11 +1772,15 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); static inline void mm_inc_nr_pmds(struct mm_struct *mm) { + if (mm_pmd_folded(mm)) + return; atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_pmds(struct mm_struct *mm) { + if (mm_pmd_folded(mm)) + return; atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } #endif diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index abe975c87b90..7f53ece2c039 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -324,9 +324,8 @@ static inline unsigned int nanddev_ntargets(const struct nand_device *nand) */ static inline unsigned int nanddev_neraseblocks(const struct nand_device *nand) { - return (u64)nand->memorg.luns_per_target * - nand->memorg.eraseblocks_per_lun * - nand->memorg.pages_per_eraseblock; + return nand->memorg.ntargets * nand->memorg.luns_per_target * + nand->memorg.eraseblocks_per_lun; } /** @@ -569,7 +568,7 @@ static inline void nanddev_pos_next_eraseblock(struct nand_device *nand, } /** - * nanddev_pos_next_eraseblock() - Move a position to the next page + * nanddev_pos_next_page() - Move a position to the next page * @nand: NAND device * @pos: the position to update * diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 08f9247e9827..9003e29cde46 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -119,6 +119,8 @@ static inline int hardlockup_detector_perf_init(void) { return 0; } void watchdog_nmi_stop(void); void watchdog_nmi_start(void); int watchdog_nmi_probe(void); +int watchdog_nmi_enable(unsigned int cpu); +void watchdog_nmi_disable(unsigned int cpu); /** * touch_nmi_watchdog - restart NMI watchdog timeout. diff --git a/include/trace/events/kyber.h b/include/trace/events/kyber.h index a9834c37ac40..c0e7d24ca256 100644 --- a/include/trace/events/kyber.h +++ b/include/trace/events/kyber.h @@ -31,8 +31,8 @@ TRACE_EVENT(kyber_latency, TP_fast_assign( __entry->dev = disk_devt(dev_to_disk(kobj_to_dev(q->kobj.parent))); - strlcpy(__entry->domain, domain, DOMAIN_LEN); - strlcpy(__entry->type, type, DOMAIN_LEN); + strlcpy(__entry->domain, domain, sizeof(__entry->domain)); + strlcpy(__entry->type, type, sizeof(__entry->type)); __entry->percentile = percentile; __entry->numerator = numerator; __entry->denominator = denominator; @@ -60,7 +60,7 @@ TRACE_EVENT(kyber_adjust, TP_fast_assign( __entry->dev = disk_devt(dev_to_disk(kobj_to_dev(q->kobj.parent))); - strlcpy(__entry->domain, domain, DOMAIN_LEN); + strlcpy(__entry->domain, domain, sizeof(__entry->domain)); __entry->depth = depth; ), @@ -82,7 +82,7 @@ TRACE_EVENT(kyber_throttled, TP_fast_assign( __entry->dev = disk_devt(dev_to_disk(kobj_to_dev(q->kobj.parent))); - strlcpy(__entry->domain, domain, DOMAIN_LEN); + strlcpy(__entry->domain, domain, sizeof(__entry->domain)); ), TP_printk("%d,%d %s", MAJOR(__entry->dev), MINOR(__entry->dev), diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index f5ff8a76e208..b01eb502d49c 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -83,11 +83,11 @@ struct kfd_ioctl_set_cu_mask_args { }; struct kfd_ioctl_get_queue_wave_state_args { - uint64_t ctl_stack_address; /* to KFD */ - uint32_t ctl_stack_used_size; /* from KFD */ - uint32_t save_area_used_size; /* from KFD */ - uint32_t queue_id; /* to KFD */ - uint32_t pad; + __u64 ctl_stack_address; /* to KFD */ + __u32 ctl_stack_used_size; /* from KFD */ + __u32 save_area_used_size; /* from KFD */ + __u32 queue_id; /* to KFD */ + __u32 pad; }; /* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */ @@ -255,10 +255,10 @@ struct kfd_hsa_memory_exception_data { /* hw exception data */ struct kfd_hsa_hw_exception_data { - uint32_t reset_type; - uint32_t reset_cause; - uint32_t memory_lost; - uint32_t gpu_id; + __u32 reset_type; + __u32 reset_cause; + __u32 memory_lost; + __u32 gpu_id; }; /* Event data */ diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 18803ff76e27..4969817124a8 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -42,16 +42,12 @@ int xen_setup_shutdown_event(void); extern unsigned long *xen_contiguous_bitmap; -#ifdef CONFIG_XEN_PV +#if defined(CONFIG_XEN_PV) || defined(CONFIG_ARM) || defined(CONFIG_ARM64) int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, unsigned int address_bits, dma_addr_t *dma_handle); void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order); - -int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, - xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, - unsigned int domid, bool no_translate, struct page **pages); #else static inline int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, @@ -63,7 +59,13 @@ static inline int xen_create_contiguous_region(phys_addr_t pstart, static inline void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) { } +#endif +#if defined(CONFIG_XEN_PV) +int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, + xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, + unsigned int domid, bool no_translate, struct page **pages); +#else static inline int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, unsigned int domid, diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c index 6ad4a9fcbd6f..7921ae4fca8d 100644 --- a/kernel/debug/kdb/kdb_bt.c +++ b/kernel/debug/kdb/kdb_bt.c @@ -179,14 +179,14 @@ kdb_bt(int argc, const char **argv) kdb_printf("no process for cpu %ld\n", cpu); return 0; } - sprintf(buf, "btt 0x%p\n", KDB_TSK(cpu)); + sprintf(buf, "btt 0x%px\n", KDB_TSK(cpu)); kdb_parse(buf); return 0; } kdb_printf("btc: cpu status: "); kdb_parse("cpu\n"); for_each_online_cpu(cpu) { - sprintf(buf, "btt 0x%p\n", KDB_TSK(cpu)); + sprintf(buf, "btt 0x%px\n", KDB_TSK(cpu)); kdb_parse(buf); touch_nmi_watchdog(); } diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index ed5d34925ad0..6a4b41484afe 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -216,7 +216,7 @@ static char *kdb_read(char *buffer, size_t bufsize) int count; int i; int diag, dtab_count; - int key; + int key, buf_size, ret; diag = kdbgetintenv("DTABCOUNT", &dtab_count); @@ -336,9 +336,8 @@ poll_again: else p_tmp = tmpbuffer; len = strlen(p_tmp); - count = kallsyms_symbol_complete(p_tmp, - sizeof(tmpbuffer) - - (p_tmp - tmpbuffer)); + buf_size = sizeof(tmpbuffer) - (p_tmp - tmpbuffer); + count = kallsyms_symbol_complete(p_tmp, buf_size); if (tab == 2 && count > 0) { kdb_printf("\n%d symbols are found.", count); if (count > dtab_count) { @@ -350,9 +349,13 @@ poll_again: } kdb_printf("\n"); for (i = 0; i < count; i++) { - if (WARN_ON(!kallsyms_symbol_next(p_tmp, i))) + ret = kallsyms_symbol_next(p_tmp, i, buf_size); + if (WARN_ON(!ret)) break; - kdb_printf("%s ", p_tmp); + if (ret != -E2BIG) + kdb_printf("%s ", p_tmp); + else + kdb_printf("%s... ", p_tmp); *(p_tmp + len) = '\0'; } if (i >= dtab_count) diff --git a/kernel/debug/kdb/kdb_keyboard.c b/kernel/debug/kdb/kdb_keyboard.c index 118527aa60ea..750497b0003a 100644 --- a/kernel/debug/kdb/kdb_keyboard.c +++ b/kernel/debug/kdb/kdb_keyboard.c @@ -173,11 +173,11 @@ int kdb_get_kbd_char(void) case KT_LATIN: if (isprint(keychar)) break; /* printable characters */ - /* drop through */ + /* fall through */ case KT_SPEC: if (keychar == K_ENTER) break; - /* drop through */ + /* fall through */ default: return -1; /* ignore unprintables */ } diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index bb4fe4e1a601..d72b32c66f7d 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -1192,7 +1192,7 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs, if (reason == KDB_REASON_DEBUG) { /* special case below */ } else { - kdb_printf("\nEntering kdb (current=0x%p, pid %d) ", + kdb_printf("\nEntering kdb (current=0x%px, pid %d) ", kdb_current, kdb_current ? kdb_current->pid : 0); #if defined(CONFIG_SMP) kdb_printf("on processor %d ", raw_smp_processor_id()); @@ -1208,7 +1208,7 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs, */ switch (db_result) { case KDB_DB_BPT: - kdb_printf("\nEntering kdb (0x%p, pid %d) ", + kdb_printf("\nEntering kdb (0x%px, pid %d) ", kdb_current, kdb_current->pid); #if defined(CONFIG_SMP) kdb_printf("on processor %d ", raw_smp_processor_id()); @@ -1493,6 +1493,7 @@ static void kdb_md_line(const char *fmtstr, unsigned long addr, char cbuf[32]; char *c = cbuf; int i; + int j; unsigned long word; memset(cbuf, '\0', sizeof(cbuf)); @@ -1538,25 +1539,9 @@ static void kdb_md_line(const char *fmtstr, unsigned long addr, wc.word = word; #define printable_char(c) \ ({unsigned char __c = c; isascii(__c) && isprint(__c) ? __c : '.'; }) - switch (bytesperword) { - case 8: + for (j = 0; j < bytesperword; j++) *c++ = printable_char(*cp++); - *c++ = printable_char(*cp++); - *c++ = printable_char(*cp++); - *c++ = printable_char(*cp++); - addr += 4; - case 4: - *c++ = printable_char(*cp++); - *c++ = printable_char(*cp++); - addr += 2; - case 2: - *c++ = printable_char(*cp++); - addr++; - case 1: - *c++ = printable_char(*cp++); - addr++; - break; - } + addr += bytesperword; #undef printable_char } } @@ -2048,7 +2033,7 @@ static int kdb_lsmod(int argc, const char **argv) if (mod->state == MODULE_STATE_UNFORMED) continue; - kdb_printf("%-20s%8u 0x%p ", mod->name, + kdb_printf("%-20s%8u 0x%px ", mod->name, mod->core_layout.size, (void *)mod); #ifdef CONFIG_MODULE_UNLOAD kdb_printf("%4d ", module_refcount(mod)); @@ -2059,7 +2044,7 @@ static int kdb_lsmod(int argc, const char **argv) kdb_printf(" (Loading)"); else kdb_printf(" (Live)"); - kdb_printf(" 0x%p", mod->core_layout.base); + kdb_printf(" 0x%px", mod->core_layout.base); #ifdef CONFIG_MODULE_UNLOAD { @@ -2341,7 +2326,7 @@ void kdb_ps1(const struct task_struct *p) return; cpu = kdb_process_cpu(p); - kdb_printf("0x%p %8d %8d %d %4d %c 0x%p %c%s\n", + kdb_printf("0x%px %8d %8d %d %4d %c 0x%px %c%s\n", (void *)p, p->pid, p->parent->pid, kdb_task_has_cpu(p), kdb_process_cpu(p), kdb_task_state_char(p), @@ -2354,7 +2339,7 @@ void kdb_ps1(const struct task_struct *p) } else { if (KDB_TSK(cpu) != p) kdb_printf(" Error: does not match running " - "process table (0x%p)\n", KDB_TSK(cpu)); + "process table (0x%px)\n", KDB_TSK(cpu)); } } } @@ -2687,7 +2672,7 @@ int kdb_register_flags(char *cmd, for_each_kdbcmd(kp, i) { if (kp->cmd_name && (strcmp(kp->cmd_name, cmd) == 0)) { kdb_printf("Duplicate kdb command registered: " - "%s, func %p help %s\n", cmd, func, help); + "%s, func %px help %s\n", cmd, func, help); return 1; } } diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index 1e5a502ba4a7..2118d8258b7c 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -83,7 +83,7 @@ typedef struct __ksymtab { unsigned long sym_start; unsigned long sym_end; } kdb_symtab_t; -extern int kallsyms_symbol_next(char *prefix_name, int flag); +extern int kallsyms_symbol_next(char *prefix_name, int flag, int buf_size); extern int kallsyms_symbol_complete(char *prefix_name, int max_len); /* Exported Symbols for kernel loadable modules to use. */ diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c index 990b3cc526c8..50bf9b119bad 100644 --- a/kernel/debug/kdb/kdb_support.c +++ b/kernel/debug/kdb/kdb_support.c @@ -40,7 +40,7 @@ int kdbgetsymval(const char *symname, kdb_symtab_t *symtab) { if (KDB_DEBUG(AR)) - kdb_printf("kdbgetsymval: symname=%s, symtab=%p\n", symname, + kdb_printf("kdbgetsymval: symname=%s, symtab=%px\n", symname, symtab); memset(symtab, 0, sizeof(*symtab)); symtab->sym_start = kallsyms_lookup_name(symname); @@ -88,7 +88,7 @@ int kdbnearsym(unsigned long addr, kdb_symtab_t *symtab) char *knt1 = NULL; if (KDB_DEBUG(AR)) - kdb_printf("kdbnearsym: addr=0x%lx, symtab=%p\n", addr, symtab); + kdb_printf("kdbnearsym: addr=0x%lx, symtab=%px\n", addr, symtab); memset(symtab, 0, sizeof(*symtab)); if (addr < 4096) @@ -149,7 +149,7 @@ int kdbnearsym(unsigned long addr, kdb_symtab_t *symtab) symtab->mod_name = "kernel"; if (KDB_DEBUG(AR)) kdb_printf("kdbnearsym: returns %d symtab->sym_start=0x%lx, " - "symtab->mod_name=%p, symtab->sym_name=%p (%s)\n", ret, + "symtab->mod_name=%px, symtab->sym_name=%px (%s)\n", ret, symtab->sym_start, symtab->mod_name, symtab->sym_name, symtab->sym_name); @@ -221,11 +221,13 @@ int kallsyms_symbol_complete(char *prefix_name, int max_len) * Parameters: * prefix_name prefix of a symbol name to lookup * flag 0 means search from the head, 1 means continue search. + * buf_size maximum length that can be written to prefix_name + * buffer * Returns: * 1 if a symbol matches the given prefix. * 0 if no string found */ -int kallsyms_symbol_next(char *prefix_name, int flag) +int kallsyms_symbol_next(char *prefix_name, int flag, int buf_size) { int prefix_len = strlen(prefix_name); static loff_t pos; @@ -235,10 +237,8 @@ int kallsyms_symbol_next(char *prefix_name, int flag) pos = 0; while ((name = kdb_walk_kallsyms(&pos))) { - if (strncmp(name, prefix_name, prefix_len) == 0) { - strncpy(prefix_name, name, strlen(name)+1); - return 1; - } + if (!strncmp(name, prefix_name, prefix_len)) + return strscpy(prefix_name, name, buf_size); } return 0; } @@ -432,7 +432,7 @@ int kdb_getphysword(unsigned long *word, unsigned long addr, size_t size) *word = w8; break; } - /* drop through */ + /* fall through */ default: diag = KDB_BADWIDTH; kdb_printf("kdb_getphysword: bad width %ld\n", (long) size); @@ -481,7 +481,7 @@ int kdb_getword(unsigned long *word, unsigned long addr, size_t size) *word = w8; break; } - /* drop through */ + /* fall through */ default: diag = KDB_BADWIDTH; kdb_printf("kdb_getword: bad width %ld\n", (long) size); @@ -525,7 +525,7 @@ int kdb_putword(unsigned long addr, unsigned long word, size_t size) diag = kdb_putarea(addr, w8); break; } - /* drop through */ + /* fall through */ default: diag = KDB_BADWIDTH; kdb_printf("kdb_putword: bad width %ld\n", (long) size); @@ -887,13 +887,13 @@ void debug_kusage(void) __func__, dah_first); if (dah_first) { h_used = (struct debug_alloc_header *)debug_alloc_pool; - kdb_printf("%s: h_used %p size %d\n", __func__, h_used, + kdb_printf("%s: h_used %px size %d\n", __func__, h_used, h_used->size); } do { h_used = (struct debug_alloc_header *) ((char *)h_free + dah_overhead + h_free->size); - kdb_printf("%s: h_used %p size %d caller %p\n", + kdb_printf("%s: h_used %px size %d caller %px\n", __func__, h_used, h_used->size, h_used->caller); h_free = (struct debug_alloc_header *) (debug_alloc_pool + h_free->next); @@ -902,7 +902,7 @@ void debug_kusage(void) ((char *)h_free + dah_overhead + h_free->size); if ((char *)h_used - debug_alloc_pool != sizeof(debug_alloc_pool_aligned)) - kdb_printf("%s: h_used %p size %d caller %p\n", + kdb_printf("%s: h_used %px size %d caller %px\n", __func__, h_used, h_used->size, h_used->caller); out: spin_unlock(&dap_lock); diff --git a/kernel/resource.c b/kernel/resource.c index b3a3a1fc499e..b0fbf685c77a 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -319,16 +319,23 @@ int release_resource(struct resource *old) EXPORT_SYMBOL(release_resource); /** - * Finds the lowest iomem resource that covers part of [start..end]. The - * caller must specify start, end, flags, and desc (which may be + * Finds the lowest iomem resource that covers part of [@start..@end]. The + * caller must specify @start, @end, @flags, and @desc (which may be * IORES_DESC_NONE). * - * If a resource is found, returns 0 and *res is overwritten with the part - * of the resource that's within [start..end]; if none is found, returns - * -1. + * If a resource is found, returns 0 and @*res is overwritten with the part + * of the resource that's within [@start..@end]; if none is found, returns + * -1 or -EINVAL for other invalid parameters. * * This function walks the whole tree and not just first level children * unless @first_lvl is true. + * + * @start: start address of the resource searched for + * @end: end address of same resource + * @flags: flags which the resource must have + * @desc: descriptor the resource must have + * @first_lvl: walk only the first level children, if set + * @res: return ptr, if resource found */ static int find_next_iomem_res(resource_size_t start, resource_size_t end, unsigned long flags, unsigned long desc, @@ -399,6 +406,8 @@ static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end, * @flags: I/O resource flags * @start: start addr * @end: end addr + * @arg: function argument for the callback @func + * @func: callback function that is called for each qualifying resource area * * NOTE: For a new descriptor search, define a new IORES_DESC in * <linux/ioport.h> and set it in 'desc' of a target resource entry. diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f12225f26b70..091e089063be 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5851,11 +5851,14 @@ void __init sched_init_smp(void) /* * There's no userspace yet to cause hotplug operations; hence all the * CPU masks are stable and all blatant races in the below code cannot - * happen. + * happen. The hotplug lock is nevertheless taken to satisfy lockdep, + * but there won't be any contention on it. */ + cpus_read_lock(); mutex_lock(&sched_domains_mutex); sched_init_domains(cpu_active_mask); mutex_unlock(&sched_domains_mutex); + cpus_read_unlock(); /* Move init over to a non-isolated CPU */ if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ee271bb661cc..ac855b2f4774 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2400,8 +2400,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) local = 1; /* - * Retry task to preferred node migration periodically, in case it - * case it previously failed, or the scheduler moved us. + * Retry to migrate task to preferred node periodically, in case it + * previously failed, or the scheduler moved us. */ if (time_after(jiffies, p->numa_migrate_retry)) { task_numa_placement(p); @@ -5674,11 +5674,11 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, return target; } -static unsigned long cpu_util_wake(int cpu, struct task_struct *p); +static unsigned long cpu_util_without(int cpu, struct task_struct *p); -static unsigned long capacity_spare_wake(int cpu, struct task_struct *p) +static unsigned long capacity_spare_without(int cpu, struct task_struct *p) { - return max_t(long, capacity_of(cpu) - cpu_util_wake(cpu, p), 0); + return max_t(long, capacity_of(cpu) - cpu_util_without(cpu, p), 0); } /* @@ -5738,7 +5738,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs); - spare_cap = capacity_spare_wake(i, p); + spare_cap = capacity_spare_without(i, p); if (spare_cap > max_spare_cap) max_spare_cap = spare_cap; @@ -5889,8 +5889,8 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p return prev_cpu; /* - * We need task's util for capacity_spare_wake, sync it up to prev_cpu's - * last_update_time. + * We need task's util for capacity_spare_without, sync it up to + * prev_cpu's last_update_time. */ if (!(sd_flag & SD_BALANCE_FORK)) sync_entity_load_avg(&p->se); @@ -6216,10 +6216,19 @@ static inline unsigned long cpu_util(int cpu) } /* - * cpu_util_wake: Compute CPU utilization with any contributions from - * the waking task p removed. + * cpu_util_without: compute cpu utilization without any contributions from *p + * @cpu: the CPU which utilization is requested + * @p: the task which utilization should be discounted + * + * The utilization of a CPU is defined by the utilization of tasks currently + * enqueued on that CPU as well as tasks which are currently sleeping after an + * execution on that CPU. + * + * This method returns the utilization of the specified CPU by discounting the + * utilization of the specified task, whenever the task is currently + * contributing to the CPU utilization. */ -static unsigned long cpu_util_wake(int cpu, struct task_struct *p) +static unsigned long cpu_util_without(int cpu, struct task_struct *p) { struct cfs_rq *cfs_rq; unsigned int util; @@ -6231,7 +6240,7 @@ static unsigned long cpu_util_wake(int cpu, struct task_struct *p) cfs_rq = &cpu_rq(cpu)->cfs; util = READ_ONCE(cfs_rq->avg.util_avg); - /* Discount task's blocked util from CPU's util */ + /* Discount task's util from CPU's util */ util -= min_t(unsigned int, util, task_util(p)); /* @@ -6240,14 +6249,14 @@ static unsigned long cpu_util_wake(int cpu, struct task_struct *p) * a) if *p is the only task sleeping on this CPU, then: * cpu_util (== task_util) > util_est (== 0) * and thus we return: - * cpu_util_wake = (cpu_util - task_util) = 0 + * cpu_util_without = (cpu_util - task_util) = 0 * * b) if other tasks are SLEEPING on this CPU, which is now exiting * IDLE, then: * cpu_util >= task_util * cpu_util > util_est (== 0) * and thus we discount *p's blocked utilization to return: - * cpu_util_wake = (cpu_util - task_util) >= 0 + * cpu_util_without = (cpu_util - task_util) >= 0 * * c) if other tasks are RUNNABLE on that CPU and * util_est > cpu_util @@ -6260,8 +6269,33 @@ static unsigned long cpu_util_wake(int cpu, struct task_struct *p) * covered by the following code when estimated utilization is * enabled. */ - if (sched_feat(UTIL_EST)) - util = max(util, READ_ONCE(cfs_rq->avg.util_est.enqueued)); + if (sched_feat(UTIL_EST)) { + unsigned int estimated = + READ_ONCE(cfs_rq->avg.util_est.enqueued); + + /* + * Despite the following checks we still have a small window + * for a possible race, when an execl's select_task_rq_fair() + * races with LB's detach_task(): + * + * detach_task() + * p->on_rq = TASK_ON_RQ_MIGRATING; + * ---------------------------------- A + * deactivate_task() \ + * dequeue_task() + RaceTime + * util_est_dequeue() / + * ---------------------------------- B + * + * The additional check on "current == p" it's required to + * properly fix the execl regression and it helps in further + * reducing the chances for the above race. + */ + if (unlikely(task_on_rq_queued(p) || current == p)) { + estimated -= min_t(unsigned int, estimated, + (_task_util_est(p) | UTIL_AVG_UNCHANGED)); + } + util = max(util, estimated); + } /* * Utilization (estimated) can exceed the CPU capacity, thus let's diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 7cdecfc010af..3d7355d7c3e3 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -633,38 +633,39 @@ void psi_cgroup_free(struct cgroup *cgroup) */ void cgroup_move_task(struct task_struct *task, struct css_set *to) { - bool move_psi = !psi_disabled; unsigned int task_flags = 0; struct rq_flags rf; struct rq *rq; - if (move_psi) { - rq = task_rq_lock(task, &rf); + if (psi_disabled) { + /* + * Lame to do this here, but the scheduler cannot be locked + * from the outside, so we move cgroups from inside sched/. + */ + rcu_assign_pointer(task->cgroups, to); + return; + } - if (task_on_rq_queued(task)) - task_flags = TSK_RUNNING; - else if (task->in_iowait) - task_flags = TSK_IOWAIT; + rq = task_rq_lock(task, &rf); - if (task->flags & PF_MEMSTALL) - task_flags |= TSK_MEMSTALL; + if (task_on_rq_queued(task)) + task_flags = TSK_RUNNING; + else if (task->in_iowait) + task_flags = TSK_IOWAIT; - if (task_flags) - psi_task_change(task, task_flags, 0); - } + if (task->flags & PF_MEMSTALL) + task_flags |= TSK_MEMSTALL; - /* - * Lame to do this here, but the scheduler cannot be locked - * from the outside, so we move cgroups from inside sched/. - */ + if (task_flags) + psi_task_change(task, task_flags, 0); + + /* See comment above */ rcu_assign_pointer(task->cgroups, to); - if (move_psi) { - if (task_flags) - psi_task_change(task, 0, task_flags); + if (task_flags) + psi_task_change(task, 0, task_flags); - task_rq_unlock(rq, task, &rf); - } + task_rq_unlock(rq, task, &rf); } #endif /* CONFIG_CGROUPS */ diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index ce32cf741b25..8f0644af40be 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -917,9 +917,6 @@ static void check_process_timers(struct task_struct *tsk, struct task_cputime cputime; unsigned long soft; - if (dl_task(tsk)) - check_dl_overrun(tsk); - /* * If cputimer is not running, then there are no active * process wide timers (POSIX 1.b, itimers, RLIMIT_CPU). diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index e5222b5fb4fe..923414a246e9 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -974,10 +974,6 @@ static ssize_t map_write(struct file *file, const char __user *buf, if (!new_idmap_permitted(file, ns, cap_setid, &new_map)) goto out; - ret = sort_idmaps(&new_map); - if (ret < 0) - goto out; - ret = -EPERM; /* Map the lower ids from the parent user namespace to the * kernel global id space. @@ -1004,6 +1000,14 @@ static ssize_t map_write(struct file *file, const char __user *buf, e->lower_first = lower_first; } + /* + * If we want to use binary search for lookup, this clones the extent + * array and sorts both copies. + */ + ret = sort_idmaps(&new_map); + if (ret < 0) + goto out; + /* Install the map */ if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) { memcpy(map->extent, new_map.extent, diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile index 5d73f5cb4d8a..79777645cac9 100644 --- a/lib/raid6/test/Makefile +++ b/lib/raid6/test/Makefile @@ -27,7 +27,7 @@ ifeq ($(ARCH),arm) CFLAGS += -I../../../arch/arm/include -mfpu=neon HAS_NEON = yes endif -ifeq ($(ARCH),arm64) +ifeq ($(ARCH),aarch64) CFLAGS += -I../../../arch/arm64/include HAS_NEON = yes endif @@ -41,7 +41,7 @@ ifeq ($(IS_X86),yes) gcc -c -x assembler - >&/dev/null && \ rm ./-.o && echo -DCONFIG_AS_AVX512=1) else ifeq ($(HAS_NEON),yes) - OBJS += neon.o neon1.o neon2.o neon4.o neon8.o + OBJS += neon.o neon1.o neon2.o neon4.o neon8.o recov_neon.o recov_neon_inner.o CFLAGS += -DCONFIG_KERNEL_MODE_NEON=1 else HAS_ALTIVEC := $(shell printf '\#include <altivec.h>\nvector int a;\n' |\ diff --git a/lib/ubsan.c b/lib/ubsan.c index 59fee96c29a0..e4162f59a81c 100644 --- a/lib/ubsan.c +++ b/lib/ubsan.c @@ -427,8 +427,7 @@ void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data, EXPORT_SYMBOL(__ubsan_handle_shift_out_of_bounds); -void __noreturn -__ubsan_handle_builtin_unreachable(struct unreachable_data *data) +void __ubsan_handle_builtin_unreachable(struct unreachable_data *data) { unsigned long flags; @@ -385,11 +385,17 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma, * @vma: vm_area_struct mapping @address * @address: virtual address to look up * @flags: flags modifying lookup behaviour - * @page_mask: on output, *page_mask is set according to the size of the page + * @ctx: contains dev_pagemap for %ZONE_DEVICE memory pinning and a + * pointer to output page_mask * * @flags can have FOLL_ flags set, defined in <linux/mm.h> * - * Returns the mapped (struct page *), %NULL if no mapping exists, or + * When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches + * the device's dev_pagemap metadata to avoid repeating expensive lookups. + * + * On output, the @ctx->page_mask is set according to the size of the page. + * + * Return: the mapped (struct page *), %NULL if no mapping exists, or * an error pointer if there is a mapping to something not represented * by a page descriptor (see also vm_normal_page()). */ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index c007fb5fb8d5..7f2a28ab46d5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3233,7 +3233,7 @@ static int is_hugetlb_entry_hwpoisoned(pte_t pte) int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma) { - pte_t *src_pte, *dst_pte, entry; + pte_t *src_pte, *dst_pte, entry, dst_entry; struct page *ptepage; unsigned long addr; int cow; @@ -3261,15 +3261,30 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, break; } - /* If the pagetables are shared don't copy or take references */ - if (dst_pte == src_pte) + /* + * If the pagetables are shared don't copy or take references. + * dst_pte == src_pte is the common case of src/dest sharing. + * + * However, src could have 'unshared' and dst shares with + * another vma. If dst_pte !none, this implies sharing. + * Check here before taking page table lock, and once again + * after taking the lock below. + */ + dst_entry = huge_ptep_get(dst_pte); + if ((dst_pte == src_pte) || !huge_pte_none(dst_entry)) continue; dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_pte); - if (huge_pte_none(entry)) { /* skip none entry */ + dst_entry = huge_ptep_get(dst_pte); + if (huge_pte_none(entry) || !huge_pte_none(dst_entry)) { + /* + * Skip if src entry none. Also, skip in the + * unlikely case dst entry !none as this implies + * sharing with another vma. + */ ; } else if (unlikely(is_hugetlb_entry_migration(entry) || is_hugetlb_entry_hwpoisoned(entry))) { diff --git a/mm/memblock.c b/mm/memblock.c index 7df468c8ebc8..9a2d5ae81ae1 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1179,7 +1179,7 @@ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP /* - * Common iterator interface used to define for_each_mem_range(). + * Common iterator interface used to define for_each_mem_pfn_range(). */ void __init_memblock __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a919ba5cb3c8..6847177dc4a1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4061,17 +4061,6 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, int reserve_flags; /* - * In the slowpath, we sanity check order to avoid ever trying to - * reclaim >= MAX_ORDER areas which will never succeed. Callers may - * be using allocators in order of preference for an area that is - * too large. - */ - if (order >= MAX_ORDER) { - WARN_ON_ONCE(!(gfp_mask & __GFP_NOWARN)); - return NULL; - } - - /* * We also sanity check to catch abuse of atomic reserves being used by * callers that are not in atomic context. */ @@ -4364,6 +4353,15 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid, gfp_t alloc_mask; /* The gfp_t that was actually used for allocation */ struct alloc_context ac = { }; + /* + * There are several places where we assume that the order value is sane + * so bail out early if the request is out of bound. + */ + if (unlikely(order >= MAX_ORDER)) { + WARN_ON_ONCE(!(gfp_mask & __GFP_NOWARN)); + return NULL; + } + gfp_mask &= gfp_allowed_mask; alloc_mask = gfp_mask; if (!prepare_alloc_pages(gfp_mask, order, preferred_nid, nodemask, &ac, &alloc_mask, &alloc_flags)) @@ -7789,6 +7787,14 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, goto unmovable; /* + * If the zone is movable and we have ruled out all reserved + * pages then it should be reasonably safe to assume the rest + * is movable. + */ + if (zone_idx(zone) == ZONE_MOVABLE) + continue; + + /* * Hugepages are not in LRU lists, but they're movable. * We need not scan over tail pages bacause we don't * handle each tail page individually in migration. diff --git a/mm/shmem.c b/mm/shmem.c index ea26d7a0342d..d44991ea5ed4 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2563,9 +2563,7 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence) inode_lock(inode); /* We're holding i_mutex so we can access i_size directly */ - if (offset < 0) - offset = -EINVAL; - else if (offset >= inode->i_size) + if (offset < 0 || offset >= inode->i_size) offset = -ENXIO; else { start = offset >> PAGE_SHIFT; diff --git a/mm/swapfile.c b/mm/swapfile.c index 644f746e167a..8688ae65ef58 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2813,7 +2813,7 @@ static struct swap_info_struct *alloc_swap_info(void) unsigned int type; int i; - p = kzalloc(sizeof(*p), GFP_KERNEL); + p = kvzalloc(sizeof(*p), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); @@ -2824,7 +2824,7 @@ static struct swap_info_struct *alloc_swap_info(void) } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); - kfree(p); + kvfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { @@ -2838,7 +2838,7 @@ static struct swap_info_struct *alloc_swap_info(void) smp_wmb(); nr_swapfiles++; } else { - kfree(p); + kvfree(p); p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() diff --git a/mm/vmstat.c b/mm/vmstat.c index 6038ce593ce3..9c624595e904 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1827,12 +1827,13 @@ static bool need_update(int cpu) /* * The fast way of checking if there are any vmstat diffs. - * This works because the diffs are byte sized items. */ - if (memchr_inv(p->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS)) + if (memchr_inv(p->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS * + sizeof(p->vm_stat_diff[0]))) return true; #ifdef CONFIG_NUMA - if (memchr_inv(p->vm_numa_stat_diff, 0, NR_VM_NUMA_STAT_ITEMS)) + if (memchr_inv(p->vm_numa_stat_diff, 0, NR_VM_NUMA_STAT_ITEMS * + sizeof(p->vm_numa_stat_diff[0]))) return true; #endif } diff --git a/mm/z3fold.c b/mm/z3fold.c index 4b366d181f35..aee9b0b8d907 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -99,6 +99,7 @@ struct z3fold_header { #define NCHUNKS ((PAGE_SIZE - ZHDR_SIZE_ALIGNED) >> CHUNK_SHIFT) #define BUDDY_MASK (0x3) +#define BUDDY_SHIFT 2 /** * struct z3fold_pool - stores metadata for each z3fold pool @@ -145,7 +146,7 @@ enum z3fold_page_flags { MIDDLE_CHUNK_MAPPED, NEEDS_COMPACTING, PAGE_STALE, - UNDER_RECLAIM + PAGE_CLAIMED, /* by either reclaim or free */ }; /***************** @@ -174,7 +175,7 @@ static struct z3fold_header *init_z3fold_page(struct page *page, clear_bit(MIDDLE_CHUNK_MAPPED, &page->private); clear_bit(NEEDS_COMPACTING, &page->private); clear_bit(PAGE_STALE, &page->private); - clear_bit(UNDER_RECLAIM, &page->private); + clear_bit(PAGE_CLAIMED, &page->private); spin_lock_init(&zhdr->page_lock); kref_init(&zhdr->refcount); @@ -223,8 +224,11 @@ static unsigned long encode_handle(struct z3fold_header *zhdr, enum buddy bud) unsigned long handle; handle = (unsigned long)zhdr; - if (bud != HEADLESS) - handle += (bud + zhdr->first_num) & BUDDY_MASK; + if (bud != HEADLESS) { + handle |= (bud + zhdr->first_num) & BUDDY_MASK; + if (bud == LAST) + handle |= (zhdr->last_chunks << BUDDY_SHIFT); + } return handle; } @@ -234,6 +238,12 @@ static struct z3fold_header *handle_to_z3fold_header(unsigned long handle) return (struct z3fold_header *)(handle & PAGE_MASK); } +/* only for LAST bud, returns zero otherwise */ +static unsigned short handle_to_chunks(unsigned long handle) +{ + return (handle & ~PAGE_MASK) >> BUDDY_SHIFT; +} + /* * (handle & BUDDY_MASK) < zhdr->first_num is possible in encode_handle * but that doesn't matter. because the masking will result in the @@ -720,37 +730,39 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) page = virt_to_page(zhdr); if (test_bit(PAGE_HEADLESS, &page->private)) { - /* HEADLESS page stored */ - bud = HEADLESS; - } else { - z3fold_page_lock(zhdr); - bud = handle_to_buddy(handle); - - switch (bud) { - case FIRST: - zhdr->first_chunks = 0; - break; - case MIDDLE: - zhdr->middle_chunks = 0; - zhdr->start_middle = 0; - break; - case LAST: - zhdr->last_chunks = 0; - break; - default: - pr_err("%s: unknown bud %d\n", __func__, bud); - WARN_ON(1); - z3fold_page_unlock(zhdr); - return; + /* if a headless page is under reclaim, just leave. + * NB: we use test_and_set_bit for a reason: if the bit + * has not been set before, we release this page + * immediately so we don't care about its value any more. + */ + if (!test_and_set_bit(PAGE_CLAIMED, &page->private)) { + spin_lock(&pool->lock); + list_del(&page->lru); + spin_unlock(&pool->lock); + free_z3fold_page(page); + atomic64_dec(&pool->pages_nr); } + return; } - if (bud == HEADLESS) { - spin_lock(&pool->lock); - list_del(&page->lru); - spin_unlock(&pool->lock); - free_z3fold_page(page); - atomic64_dec(&pool->pages_nr); + /* Non-headless case */ + z3fold_page_lock(zhdr); + bud = handle_to_buddy(handle); + + switch (bud) { + case FIRST: + zhdr->first_chunks = 0; + break; + case MIDDLE: + zhdr->middle_chunks = 0; + break; + case LAST: + zhdr->last_chunks = 0; + break; + default: + pr_err("%s: unknown bud %d\n", __func__, bud); + WARN_ON(1); + z3fold_page_unlock(zhdr); return; } @@ -758,7 +770,7 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) atomic64_dec(&pool->pages_nr); return; } - if (test_bit(UNDER_RECLAIM, &page->private)) { + if (test_bit(PAGE_CLAIMED, &page->private)) { z3fold_page_unlock(zhdr); return; } @@ -836,20 +848,30 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) } list_for_each_prev(pos, &pool->lru) { page = list_entry(pos, struct page, lru); + + /* this bit could have been set by free, in which case + * we pass over to the next page in the pool. + */ + if (test_and_set_bit(PAGE_CLAIMED, &page->private)) + continue; + + zhdr = page_address(page); if (test_bit(PAGE_HEADLESS, &page->private)) - /* candidate found */ break; - zhdr = page_address(page); - if (!z3fold_page_trylock(zhdr)) + if (!z3fold_page_trylock(zhdr)) { + zhdr = NULL; continue; /* can't evict at this point */ + } kref_get(&zhdr->refcount); list_del_init(&zhdr->buddy); zhdr->cpu = -1; - set_bit(UNDER_RECLAIM, &page->private); break; } + if (!zhdr) + break; + list_del_init(&page->lru); spin_unlock(&pool->lock); @@ -898,6 +920,7 @@ next: if (test_bit(PAGE_HEADLESS, &page->private)) { if (ret == 0) { free_z3fold_page(page); + atomic64_dec(&pool->pages_nr); return 0; } spin_lock(&pool->lock); @@ -905,7 +928,7 @@ next: spin_unlock(&pool->lock); } else { z3fold_page_lock(zhdr); - clear_bit(UNDER_RECLAIM, &page->private); + clear_bit(PAGE_CLAIMED, &page->private); if (kref_put(&zhdr->refcount, release_z3fold_page_locked)) { atomic64_dec(&pool->pages_nr); @@ -964,7 +987,7 @@ static void *z3fold_map(struct z3fold_pool *pool, unsigned long handle) set_bit(MIDDLE_CHUNK_MAPPED, &page->private); break; case LAST: - addr += PAGE_SIZE - (zhdr->last_chunks << CHUNK_SHIFT); + addr += PAGE_SIZE - (handle_to_chunks(handle) << CHUNK_SHIFT); break; default: pr_err("unknown buddy id %d\n", buddy); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 676f3ad629f9..588f475019d4 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1166,8 +1166,8 @@ ip_proto_again: break; } - if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS)) { + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS) && + !(key_control->flags & FLOW_DIS_IS_FRAGMENT)) { key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS, target_container); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index bcb11f3a27c0..760a9e52e02b 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -178,21 +178,22 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, } static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, - void *arg) + void *arg, + struct inet_frag_queue **prev) { struct inet_frags *f = nf->f; struct inet_frag_queue *q; - int err; q = inet_frag_alloc(nf, f, arg); - if (!q) + if (!q) { + *prev = ERR_PTR(-ENOMEM); return NULL; - + } mod_timer(&q->timer, jiffies + nf->timeout); - err = rhashtable_insert_fast(&nf->rhashtable, &q->node, - f->rhash_params); - if (err < 0) { + *prev = rhashtable_lookup_get_insert_key(&nf->rhashtable, &q->key, + &q->node, f->rhash_params); + if (*prev) { q->flags |= INET_FRAG_COMPLETE; inet_frag_kill(q); inet_frag_destroy(q); @@ -204,22 +205,22 @@ static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, /* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key) { - struct inet_frag_queue *fq; + struct inet_frag_queue *fq = NULL, *prev; if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) return NULL; rcu_read_lock(); - fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params); - if (fq) { + prev = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params); + if (!prev) + fq = inet_frag_create(nf, key, &prev); + if (prev && !IS_ERR(prev)) { + fq = prev; if (!refcount_inc_not_zero(&fq->refcnt)) fq = NULL; - rcu_read_unlock(); - return fq; } rcu_read_unlock(); - - return inet_frag_create(nf, key); + return fq; } EXPORT_SYMBOL(inet_frag_find); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 1dae5f2b358f..c8cf4d10c435 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -258,7 +258,8 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, if (is_redirect) { skb2->tc_redirected = 1; skb2->tc_from_ingress = skb2->tc_at_ingress; - + if (skb2->tc_from_ingress) + skb2->tstamp = 0; /* let's the caller reinsert the packet, if possible */ if (use_reinsert) { res->ingress = want_ingress; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 9aada2d0ef06..c6c327874abc 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -709,11 +709,23 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, struct netlink_ext_ack *extack) { const struct nlattr *nla_enc_key, *nla_opt_key, *nla_opt_msk = NULL; - int option_len, key_depth, msk_depth = 0; + int err, option_len, key_depth, msk_depth = 0; + + err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS], + TCA_FLOWER_KEY_ENC_OPTS_MAX, + enc_opts_policy, extack); + if (err) + return err; nla_enc_key = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS]); if (tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]) { + err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK], + TCA_FLOWER_KEY_ENC_OPTS_MAX, + enc_opts_policy, extack); + if (err) + return err; + nla_opt_msk = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]); msk_depth = nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]); } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 57b3ad9394ad..2c38e3d07924 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -648,15 +648,6 @@ deliver: */ skb->dev = qdisc_dev(sch); -#ifdef CONFIG_NET_CLS_ACT - /* - * If it's at ingress let's pretend the delay is - * from the network (tstamp will be updated). - */ - if (skb->tc_redirected && skb->tc_from_ingress) - skb->tstamp = 0; -#endif - if (q->slot.slot_next) { q->slot.packets_left--; q->slot.bytes_left -= qdisc_pkt_len(skb); diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c index d8831b988b1e..ab4a3be1542a 100644 --- a/net/sunrpc/auth_generic.c +++ b/net/sunrpc/auth_generic.c @@ -281,13 +281,7 @@ static bool generic_key_to_expire(struct rpc_cred *cred) { struct auth_cred *acred = &container_of(cred, struct generic_cred, gc_base)->acred; - bool ret; - - get_rpccred(cred); - ret = test_bit(RPC_CRED_KEY_EXPIRE_SOON, &acred->ac_flags); - put_rpccred(cred); - - return ret; + return test_bit(RPC_CRED_KEY_EXPIRE_SOON, &acred->ac_flags); } static const struct rpc_credops generic_credops = { diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 30f970cdc7f6..5d3f252659f1 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1239,36 +1239,59 @@ gss_create(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) return &gss_auth->rpc_auth; } +static struct gss_cred * +gss_dup_cred(struct gss_auth *gss_auth, struct gss_cred *gss_cred) +{ + struct gss_cred *new; + + /* Make a copy of the cred so that we can reference count it */ + new = kzalloc(sizeof(*gss_cred), GFP_NOIO); + if (new) { + struct auth_cred acred = { + .uid = gss_cred->gc_base.cr_uid, + }; + struct gss_cl_ctx *ctx = + rcu_dereference_protected(gss_cred->gc_ctx, 1); + + rpcauth_init_cred(&new->gc_base, &acred, + &gss_auth->rpc_auth, + &gss_nullops); + new->gc_base.cr_flags = 1UL << RPCAUTH_CRED_UPTODATE; + new->gc_service = gss_cred->gc_service; + new->gc_principal = gss_cred->gc_principal; + kref_get(&gss_auth->kref); + rcu_assign_pointer(new->gc_ctx, ctx); + gss_get_ctx(ctx); + } + return new; +} + /* - * gss_destroying_context will cause the RPCSEC_GSS to send a NULL RPC call + * gss_send_destroy_context will cause the RPCSEC_GSS to send a NULL RPC call * to the server with the GSS control procedure field set to * RPC_GSS_PROC_DESTROY. This should normally cause the server to release * all RPCSEC_GSS state associated with that context. */ -static int -gss_destroying_context(struct rpc_cred *cred) +static void +gss_send_destroy_context(struct rpc_cred *cred) { struct gss_cred *gss_cred = container_of(cred, struct gss_cred, gc_base); struct gss_auth *gss_auth = container_of(cred->cr_auth, struct gss_auth, rpc_auth); struct gss_cl_ctx *ctx = rcu_dereference_protected(gss_cred->gc_ctx, 1); + struct gss_cred *new; struct rpc_task *task; - if (test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) == 0) - return 0; - - ctx->gc_proc = RPC_GSS_PROC_DESTROY; - cred->cr_ops = &gss_nullops; - - /* Take a reference to ensure the cred will be destroyed either - * by the RPC call or by the put_rpccred() below */ - get_rpccred(cred); + new = gss_dup_cred(gss_auth, gss_cred); + if (new) { + ctx->gc_proc = RPC_GSS_PROC_DESTROY; - task = rpc_call_null(gss_auth->client, cred, RPC_TASK_ASYNC|RPC_TASK_SOFT); - if (!IS_ERR(task)) - rpc_put_task(task); + task = rpc_call_null(gss_auth->client, &new->gc_base, + RPC_TASK_ASYNC|RPC_TASK_SOFT); + if (!IS_ERR(task)) + rpc_put_task(task); - put_rpccred(cred); - return 1; + put_rpccred(&new->gc_base); + } } /* gss_destroy_cred (and gss_free_ctx) are used to clean up after failure @@ -1330,8 +1353,8 @@ static void gss_destroy_cred(struct rpc_cred *cred) { - if (gss_destroying_context(cred)) - return; + if (test_and_clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) != 0) + gss_send_destroy_context(cred); gss_destroy_nullcred(cred); } diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 2bbb8d38d2bf..f302c6eb8779 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -546,7 +546,7 @@ EXPORT_SYMBOL_GPL(xdr_commit_encode); static __be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr, size_t nbytes) { - static __be32 *p; + __be32 *p; int space_left; int frag1bytes, frag2bytes; @@ -673,11 +673,10 @@ void xdr_truncate_encode(struct xdr_stream *xdr, size_t len) WARN_ON_ONCE(xdr->iov); return; } - if (fraglen) { + if (fraglen) xdr->end = head->iov_base + head->iov_len; - xdr->page_ptr--; - } /* (otherwise assume xdr->end is already set) */ + xdr->page_ptr--; head->iov_len = len; buf->len = len; xdr->p = head->iov_base + head->iov_len; diff --git a/net/tipc/link.c b/net/tipc/link.c index 201c3b5bc96b..836727e363c4 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1594,14 +1594,17 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI)) l->priority = peers_prio; - /* ACTIVATE_MSG serves as PEER_RESET if link is already down */ - if (msg_peer_stopping(hdr)) + /* If peer is going down we want full re-establish cycle */ + if (msg_peer_stopping(hdr)) { rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT); - else if ((mtyp == RESET_MSG) || !link_is_up(l)) + break; + } + /* ACTIVATE_MSG serves as PEER_RESET if link is already down */ + if (mtyp == RESET_MSG || !link_is_up(l)) rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT); /* ACTIVATE_MSG takes up link if it was already locally reset */ - if ((mtyp == ACTIVATE_MSG) && (l->state == LINK_ESTABLISHING)) + if (mtyp == ACTIVATE_MSG && l->state == LINK_ESTABLISHING) rc = TIPC_LINK_UP_EVT; l->peer_session = msg_session(hdr); diff --git a/scripts/faddr2line b/scripts/faddr2line index a0149db00be7..6c6439f69a72 100755 --- a/scripts/faddr2line +++ b/scripts/faddr2line @@ -71,7 +71,7 @@ die() { # Try to figure out the source directory prefix so we can remove it from the # addr2line output. HACK ALERT: This assumes that start_kernel() is in -# kernel/init.c! This only works for vmlinux. Otherwise it falls back to +# init/main.c! This only works for vmlinux. Otherwise it falls back to # printing the absolute path. find_dir_prefix() { local objfile=$1 diff --git a/scripts/kconfig/merge_config.sh b/scripts/kconfig/merge_config.sh index da66e7742282..0ef906499646 100755 --- a/scripts/kconfig/merge_config.sh +++ b/scripts/kconfig/merge_config.sh @@ -102,7 +102,8 @@ if [ ! -r "$INITFILE" ]; then fi MERGE_LIST=$* -SED_CONFIG_EXP="s/^\(# \)\{0,1\}\(${CONFIG_PREFIX}[a-zA-Z0-9_]*\)[= ].*/\2/p" +SED_CONFIG_EXP1="s/^\(${CONFIG_PREFIX}[a-zA-Z0-9_]*\)=.*/\1/p" +SED_CONFIG_EXP2="s/^# \(${CONFIG_PREFIX}[a-zA-Z0-9_]*\) is not set$/\1/p" TMP_FILE=$(mktemp ./.tmp.config.XXXXXXXXXX) @@ -116,7 +117,7 @@ for MERGE_FILE in $MERGE_LIST ; do echo "The merge file '$MERGE_FILE' does not exist. Exit." >&2 exit 1 fi - CFG_LIST=$(sed -n "$SED_CONFIG_EXP" $MERGE_FILE) + CFG_LIST=$(sed -n -e "$SED_CONFIG_EXP1" -e "$SED_CONFIG_EXP2" $MERGE_FILE) for CFG in $CFG_LIST ; do grep -q -w $CFG $TMP_FILE || continue @@ -159,7 +160,7 @@ make KCONFIG_ALLCONFIG=$TMP_FILE $OUTPUT_ARG $ALLTARGET # Check all specified config values took (might have missed-dependency issues) -for CFG in $(sed -n "$SED_CONFIG_EXP" $TMP_FILE); do +for CFG in $(sed -n -e "$SED_CONFIG_EXP1" -e "$SED_CONFIG_EXP2" $TMP_FILE); do REQUESTED_VAL=$(grep -w -e "$CFG" $TMP_FILE) ACTUAL_VAL=$(grep -w -e "$CFG" "$KCONFIG_CONFIG") diff --git a/scripts/package/builddeb b/scripts/package/builddeb index 90c9a8ac7adb..f43a274f4f1d 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -81,11 +81,11 @@ else cp System.map "$tmpdir/boot/System.map-$version" cp $KCONFIG_CONFIG "$tmpdir/boot/config-$version" fi -cp "$($MAKE -s image_name)" "$tmpdir/$installed_image_path" +cp "$($MAKE -s -f $srctree/Makefile image_name)" "$tmpdir/$installed_image_path" -if grep -q "^CONFIG_OF=y" $KCONFIG_CONFIG ; then +if grep -q "^CONFIG_OF_EARLY_FLATTREE=y" $KCONFIG_CONFIG ; then # Only some architectures with OF support have this target - if grep -q dtbs_install "${srctree}/arch/$SRCARCH/Makefile"; then + if [ -d "${srctree}/arch/$SRCARCH/boot/dts" ]; then $MAKE KBUILD_SRC= INSTALL_DTBS_PATH="$tmpdir/usr/lib/$packagename" dtbs_install fi fi diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian index 663a7f343b42..edcad61fe3cd 100755 --- a/scripts/package/mkdebian +++ b/scripts/package/mkdebian @@ -88,6 +88,7 @@ set_debarch() { version=$KERNELRELEASE if [ -n "$KDEB_PKGVERSION" ]; then packageversion=$KDEB_PKGVERSION + revision=${packageversion##*-} else revision=$(cat .version 2>/dev/null||echo 1) packageversion=$version-$revision @@ -205,10 +206,12 @@ cat <<EOF > debian/rules #!$(command -v $MAKE) -f build: - \$(MAKE) KERNELRELEASE=${version} ARCH=${ARCH} KBUILD_SRC= + \$(MAKE) KERNELRELEASE=${version} ARCH=${ARCH} \ + KBUILD_BUILD_VERSION=${revision} KBUILD_SRC= binary-arch: - \$(MAKE) KERNELRELEASE=${version} ARCH=${ARCH} KBUILD_SRC= intdeb-pkg + \$(MAKE) KERNELRELEASE=${version} ARCH=${ARCH} \ + KBUILD_BUILD_VERSION=${revision} KBUILD_SRC= intdeb-pkg clean: rm -rf debian/*tmp debian/files diff --git a/scripts/package/mkspec b/scripts/package/mkspec index e05646dc24dc..009147d4718e 100755 --- a/scripts/package/mkspec +++ b/scripts/package/mkspec @@ -12,6 +12,7 @@ # how we were called determines which rpms we build and how we build them if [ "$1" = prebuilt ]; then S=DEL + MAKE="$MAKE -f $srctree/Makefile" else S= fi @@ -78,19 +79,19 @@ $S %prep $S %setup -q $S $S %build -$S make %{?_smp_mflags} KBUILD_BUILD_VERSION=%{release} +$S $MAKE %{?_smp_mflags} KBUILD_BUILD_VERSION=%{release} $S %install mkdir -p %{buildroot}/boot %ifarch ia64 mkdir -p %{buildroot}/boot/efi - cp \$(make image_name) %{buildroot}/boot/efi/vmlinuz-$KERNELRELEASE + cp \$($MAKE image_name) %{buildroot}/boot/efi/vmlinuz-$KERNELRELEASE ln -s efi/vmlinuz-$KERNELRELEASE %{buildroot}/boot/ %else - cp \$(make image_name) %{buildroot}/boot/vmlinuz-$KERNELRELEASE + cp \$($MAKE image_name) %{buildroot}/boot/vmlinuz-$KERNELRELEASE %endif -$M make %{?_smp_mflags} INSTALL_MOD_PATH=%{buildroot} KBUILD_SRC= modules_install - make %{?_smp_mflags} INSTALL_HDR_PATH=%{buildroot}/usr KBUILD_SRC= headers_install +$M $MAKE %{?_smp_mflags} INSTALL_MOD_PATH=%{buildroot} modules_install + $MAKE %{?_smp_mflags} INSTALL_HDR_PATH=%{buildroot}/usr headers_install cp System.map %{buildroot}/boot/System.map-$KERNELRELEASE cp .config %{buildroot}/boot/config-$KERNELRELEASE bzip2 -9 --keep vmlinux diff --git a/scripts/setlocalversion b/scripts/setlocalversion index 79f7dd57d571..71f39410691b 100755 --- a/scripts/setlocalversion +++ b/scripts/setlocalversion @@ -74,7 +74,7 @@ scm_version() fi # Check for uncommitted changes - if git status -uno --porcelain | grep -qv '^.. scripts/package'; then + if git diff-index --name-only HEAD | grep -qv "^scripts/package"; then printf '%s' -dirty fi diff --git a/scripts/spdxcheck.py b/scripts/spdxcheck.py index 839e190bbd7a..5056fb3b897d 100755 --- a/scripts/spdxcheck.py +++ b/scripts/spdxcheck.py @@ -168,7 +168,6 @@ class id_parser(object): self.curline = 0 try: for line in fd: - line = line.decode(locale.getpreferredencoding(False), errors='ignore') self.curline += 1 if self.curline > maxlines: break diff --git a/security/integrity/digsig_asymmetric.c b/security/integrity/digsig_asymmetric.c index 6dc075144508..d775e03fbbcc 100644 --- a/security/integrity/digsig_asymmetric.c +++ b/security/integrity/digsig_asymmetric.c @@ -106,6 +106,7 @@ int asymmetric_verify(struct key *keyring, const char *sig, pks.pkey_algo = "rsa"; pks.hash_algo = hash_algo_name[hdr->hash_algo]; + pks.encoding = "pkcs1"; pks.digest = (u8 *)data; pks.digest_size = datalen; pks.s = hdr->sig; diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 7ce683259357..a67459eb62d5 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -5318,6 +5318,9 @@ static int selinux_sctp_bind_connect(struct sock *sk, int optname, addr_buf = address; while (walk_size < addrlen) { + if (walk_size + sizeof(sa_family_t) > addrlen) + return -EINVAL; + addr = addr_buf; switch (addr->sa_family) { case AF_UNSPEC: diff --git a/security/selinux/ss/mls.c b/security/selinux/ss/mls.c index 2fe459df3c85..b7efa2296969 100644 --- a/security/selinux/ss/mls.c +++ b/security/selinux/ss/mls.c @@ -245,9 +245,13 @@ int mls_context_to_sid(struct policydb *pol, char *rangep[2]; if (!pol->mls_enabled) { - if ((def_sid != SECSID_NULL && oldc) || (*scontext) == '\0') - return 0; - return -EINVAL; + /* + * With no MLS, only return -EINVAL if there is a MLS field + * and it did not come from an xattr. + */ + if (oldc && def_sid == SECSID_NULL) + return -EINVAL; + return 0; } /* diff --git a/sound/pci/hda/thinkpad_helper.c b/sound/pci/hda/thinkpad_helper.c index 97f49b751e6e..568575b72f2f 100644 --- a/sound/pci/hda/thinkpad_helper.c +++ b/sound/pci/hda/thinkpad_helper.c @@ -58,8 +58,8 @@ static void hda_fixup_thinkpad_acpi(struct hda_codec *codec, removefunc = false; } if (led_set_func(TPACPI_LED_MICMUTE, false) >= 0 && - snd_hda_gen_add_micmute_led(codec, - update_tpacpi_micmute) > 0) + !snd_hda_gen_add_micmute_led(codec, + update_tpacpi_micmute)) removefunc = false; } diff --git a/tools/arch/arm64/include/asm/barrier.h b/tools/arch/arm64/include/asm/barrier.h index 12835ea0e417..378c051fa177 100644 --- a/tools/arch/arm64/include/asm/barrier.h +++ b/tools/arch/arm64/include/asm/barrier.h @@ -14,74 +14,75 @@ #define wmb() asm volatile("dmb ishst" ::: "memory") #define rmb() asm volatile("dmb ishld" ::: "memory") -#define smp_store_release(p, v) \ -do { \ - union { typeof(*p) __val; char __c[1]; } __u = \ - { .__val = (__force typeof(*p)) (v) }; \ - \ - switch (sizeof(*p)) { \ - case 1: \ - asm volatile ("stlrb %w1, %0" \ - : "=Q" (*p) \ - : "r" (*(__u8 *)__u.__c) \ - : "memory"); \ - break; \ - case 2: \ - asm volatile ("stlrh %w1, %0" \ - : "=Q" (*p) \ - : "r" (*(__u16 *)__u.__c) \ - : "memory"); \ - break; \ - case 4: \ - asm volatile ("stlr %w1, %0" \ - : "=Q" (*p) \ - : "r" (*(__u32 *)__u.__c) \ - : "memory"); \ - break; \ - case 8: \ - asm volatile ("stlr %1, %0" \ - : "=Q" (*p) \ - : "r" (*(__u64 *)__u.__c) \ - : "memory"); \ - break; \ - default: \ - /* Only to shut up gcc ... */ \ - mb(); \ - break; \ - } \ +#define smp_store_release(p, v) \ +do { \ + union { typeof(*p) __val; char __c[1]; } __u = \ + { .__val = (v) }; \ + \ + switch (sizeof(*p)) { \ + case 1: \ + asm volatile ("stlrb %w1, %0" \ + : "=Q" (*p) \ + : "r" (*(__u8_alias_t *)__u.__c) \ + : "memory"); \ + break; \ + case 2: \ + asm volatile ("stlrh %w1, %0" \ + : "=Q" (*p) \ + : "r" (*(__u16_alias_t *)__u.__c) \ + : "memory"); \ + break; \ + case 4: \ + asm volatile ("stlr %w1, %0" \ + : "=Q" (*p) \ + : "r" (*(__u32_alias_t *)__u.__c) \ + : "memory"); \ + break; \ + case 8: \ + asm volatile ("stlr %1, %0" \ + : "=Q" (*p) \ + : "r" (*(__u64_alias_t *)__u.__c) \ + : "memory"); \ + break; \ + default: \ + /* Only to shut up gcc ... */ \ + mb(); \ + break; \ + } \ } while (0) -#define smp_load_acquire(p) \ -({ \ - union { typeof(*p) __val; char __c[1]; } __u; \ - \ - switch (sizeof(*p)) { \ - case 1: \ - asm volatile ("ldarb %w0, %1" \ - : "=r" (*(__u8 *)__u.__c) \ - : "Q" (*p) : "memory"); \ - break; \ - case 2: \ - asm volatile ("ldarh %w0, %1" \ - : "=r" (*(__u16 *)__u.__c) \ - : "Q" (*p) : "memory"); \ - break; \ - case 4: \ - asm volatile ("ldar %w0, %1" \ - : "=r" (*(__u32 *)__u.__c) \ - : "Q" (*p) : "memory"); \ - break; \ - case 8: \ - asm volatile ("ldar %0, %1" \ - : "=r" (*(__u64 *)__u.__c) \ - : "Q" (*p) : "memory"); \ - break; \ - default: \ - /* Only to shut up gcc ... */ \ - mb(); \ - break; \ - } \ - __u.__val; \ +#define smp_load_acquire(p) \ +({ \ + union { typeof(*p) __val; char __c[1]; } __u = \ + { .__c = { 0 } }; \ + \ + switch (sizeof(*p)) { \ + case 1: \ + asm volatile ("ldarb %w0, %1" \ + : "=r" (*(__u8_alias_t *)__u.__c) \ + : "Q" (*p) : "memory"); \ + break; \ + case 2: \ + asm volatile ("ldarh %w0, %1" \ + : "=r" (*(__u16_alias_t *)__u.__c) \ + : "Q" (*p) : "memory"); \ + break; \ + case 4: \ + asm volatile ("ldar %w0, %1" \ + : "=r" (*(__u32_alias_t *)__u.__c) \ + : "Q" (*p) : "memory"); \ + break; \ + case 8: \ + asm volatile ("ldar %0, %1" \ + : "=r" (*(__u64_alias_t *)__u.__c) \ + : "Q" (*p) : "memory"); \ + break; \ + default: \ + /* Only to shut up gcc ... */ \ + mb(); \ + break; \ + } \ + __u.__val; \ }) #endif /* _TOOLS_LINUX_ASM_AARCH64_BARRIER_H */ diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 236b9b97dfdb..667c14e56031 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -55,7 +55,6 @@ counted. The following modifiers exist: S - read sample value (PERF_SAMPLE_READ) D - pin the event to the PMU W - group is weak and will fallback to non-group if not schedulable, - only supported in 'perf stat' for now. The 'p' modifier can be used for specifying how precise the instruction address should be. The 'p' modifier can be specified multiple times: diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 3ccb4f0bf088..d95655489f7e 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -387,7 +387,7 @@ SHELL = $(SHELL_PATH) linux_uapi_dir := $(srctree)/tools/include/uapi/linux asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic -arch_asm_uapi_dir := $(srctree)/tools/arch/$(ARCH)/include/uapi/asm/ +arch_asm_uapi_dir := $(srctree)/tools/arch/$(SRCARCH)/include/uapi/asm/ beauty_outdir := $(OUTPUT)trace/beauty/generated beauty_ioctl_outdir := $(beauty_outdir)/ioctl diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 10cf889c6d75..488779bc4c8d 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -391,7 +391,12 @@ try_again: ui__warning("%s\n", msg); goto try_again; } - + if ((errno == EINVAL || errno == EBADF) && + pos->leader != pos && + pos->weak_group) { + pos = perf_evlist__reset_weak_group(evlist, pos); + goto try_again; + } rc = -errno; perf_evsel__open_strerror(pos, &opts->target, errno, msg, sizeof(msg)); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index d1028d7755bb..a635abfa77b6 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -383,32 +383,6 @@ static bool perf_evsel__should_store_id(struct perf_evsel *counter) return STAT_RECORD || counter->attr.read_format & PERF_FORMAT_ID; } -static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel) -{ - struct perf_evsel *c2, *leader; - bool is_open = true; - - leader = evsel->leader; - pr_debug("Weak group for %s/%d failed\n", - leader->name, leader->nr_members); - - /* - * for_each_group_member doesn't work here because it doesn't - * include the first entry. - */ - evlist__for_each_entry(evsel_list, c2) { - if (c2 == evsel) - is_open = false; - if (c2->leader == leader) { - if (is_open) - perf_evsel__close(c2); - c2->leader = c2; - c2->nr_members = 0; - } - } - return leader; -} - static bool is_target_alive(struct target *_target, struct thread_map *threads) { @@ -477,7 +451,7 @@ try_again: if ((errno == EINVAL || errno == EBADF) && counter->leader != counter && counter->weak_group) { - counter = perf_evsel__reset_weak_group(counter); + counter = perf_evlist__reset_weak_group(evsel_list, counter); goto try_again; } diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index b2838de13de0..aa0c73e57924 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1429,6 +1429,9 @@ int cmd_top(int argc, const char **argv) } } + if (opts->branch_stack && callchain_param.enabled) + symbol_conf.show_branchflag_count = true; + sort__mode = SORT_MODE__TOP; /* display thread wants entries to be collapsed in a different tree */ perf_hpp_list.need_collapse = 1; diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index dc8a6c4986ce..835619476370 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -108,6 +108,7 @@ struct trace { } stats; unsigned int max_stack; unsigned int min_stack; + bool raw_augmented_syscalls; bool not_ev_qualifier; bool live; bool full_time; @@ -1724,13 +1725,28 @@ static int trace__fprintf_sample(struct trace *trace, struct perf_evsel *evsel, return printed; } -static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size) +static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size, bool raw_augmented) { void *augmented_args = NULL; + /* + * For now with BPF raw_augmented we hook into raw_syscalls:sys_enter + * and there we get all 6 syscall args plus the tracepoint common + * fields (sizeof(long)) and the syscall_nr (another long). So we check + * if that is the case and if so don't look after the sc->args_size, + * but always after the full raw_syscalls:sys_enter payload, which is + * fixed. + * + * We'll revisit this later to pass s->args_size to the BPF augmenter + * (now tools/perf/examples/bpf/augmented_raw_syscalls.c, so that it + * copies only what we need for each syscall, like what happens when we + * use syscalls:sys_enter_NAME, so that we reduce the kernel/userspace + * traffic to just what is needed for each syscall. + */ + int args_size = raw_augmented ? (8 * (int)sizeof(long)) : sc->args_size; - *augmented_args_size = sample->raw_size - sc->args_size; + *augmented_args_size = sample->raw_size - args_size; if (*augmented_args_size > 0) - augmented_args = sample->raw_data + sc->args_size; + augmented_args = sample->raw_data + args_size; return augmented_args; } @@ -1780,7 +1796,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, * here and avoid using augmented syscalls when the evsel is the raw_syscalls one. */ if (evsel != trace->syscalls.events.sys_enter) - augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size); + augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls); ttrace->entry_time = sample->time; msg = ttrace->entry_str; printed += scnprintf(msg + printed, trace__entry_str_size - printed, "%s(", sc->name); @@ -1833,7 +1849,7 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse goto out_put; args = perf_evsel__sc_tp_ptr(evsel, args, sample); - augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size); + augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls); syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread); fprintf(trace->output, "%s", msg); err = 0; @@ -3501,7 +3517,15 @@ int cmd_trace(int argc, const char **argv) evsel->handler = trace__sys_enter; evlist__for_each_entry(trace.evlist, evsel) { + bool raw_syscalls_sys_exit = strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_exit") == 0; + + if (raw_syscalls_sys_exit) { + trace.raw_augmented_syscalls = true; + goto init_augmented_syscall_tp; + } + if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) { +init_augmented_syscall_tp: perf_evsel__init_augmented_syscall_tp(evsel); perf_evsel__init_augmented_syscall_tp_ret(evsel); evsel->handler = trace__sys_exit; diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c new file mode 100644 index 000000000000..90a19336310b --- /dev/null +++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c @@ -0,0 +1,131 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Augment the raw_syscalls tracepoints with the contents of the pointer arguments. + * + * Test it with: + * + * perf trace -e tools/perf/examples/bpf/augmented_raw_syscalls.c cat /etc/passwd > /dev/null + * + * This exactly matches what is marshalled into the raw_syscall:sys_enter + * payload expected by the 'perf trace' beautifiers. + * + * For now it just uses the existing tracepoint augmentation code in 'perf + * trace', in the next csets we'll hook up these with the sys_enter/sys_exit + * code that will combine entry/exit in a strace like way. + */ + +#include <stdio.h> +#include <linux/socket.h> + +/* bpf-output associated map */ +struct bpf_map SEC("maps") __augmented_syscalls__ = { + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(u32), + .max_entries = __NR_CPUS__, +}; + +struct syscall_enter_args { + unsigned long long common_tp_fields; + long syscall_nr; + unsigned long args[6]; +}; + +struct syscall_exit_args { + unsigned long long common_tp_fields; + long syscall_nr; + long ret; +}; + +struct augmented_filename { + unsigned int size; + int reserved; + char value[256]; +}; + +#define SYS_OPEN 2 +#define SYS_OPENAT 257 + +SEC("raw_syscalls:sys_enter") +int sys_enter(struct syscall_enter_args *args) +{ + struct { + struct syscall_enter_args args; + struct augmented_filename filename; + } augmented_args; + unsigned int len = sizeof(augmented_args); + const void *filename_arg = NULL; + + probe_read(&augmented_args.args, sizeof(augmented_args.args), args); + /* + * Yonghong and Edward Cree sayz: + * + * https://www.spinics.net/lists/netdev/msg531645.html + * + * >> R0=inv(id=0) R1=inv2 R6=ctx(id=0,off=0,imm=0) R7=inv64 R10=fp0,call_-1 + * >> 10: (bf) r1 = r6 + * >> 11: (07) r1 += 16 + * >> 12: (05) goto pc+2 + * >> 15: (79) r3 = *(u64 *)(r1 +0) + * >> dereference of modified ctx ptr R1 off=16 disallowed + * > Aha, we at least got a different error message this time. + * > And indeed llvm has done that optimisation, rather than the more obvious + * > 11: r3 = *(u64 *)(r1 +16) + * > because it wants to have lots of reads share a single insn. You may be able + * > to defeat that optimisation by adding compiler barriers, idk. Maybe someone + * > with llvm knowledge can figure out how to stop it (ideally, llvm would know + * > when it's generating for bpf backend and not do that). -O0? ¯\_(ツ)_/¯ + * + * The optimization mostly likes below: + * + * br1: + * ... + * r1 += 16 + * goto merge + * br2: + * ... + * r1 += 20 + * goto merge + * merge: + * *(u64 *)(r1 + 0) + * + * The compiler tries to merge common loads. There is no easy way to + * stop this compiler optimization without turning off a lot of other + * optimizations. The easiest way is to add barriers: + * + * __asm__ __volatile__("": : :"memory") + * + * after the ctx memory access to prevent their down stream merging. + */ + switch (augmented_args.args.syscall_nr) { + case SYS_OPEN: filename_arg = (const void *)args->args[0]; + __asm__ __volatile__("": : :"memory"); + break; + case SYS_OPENAT: filename_arg = (const void *)args->args[1]; + break; + } + + if (filename_arg != NULL) { + augmented_args.filename.reserved = 0; + augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, + sizeof(augmented_args.filename.value), + filename_arg); + if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) { + len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size; + len &= sizeof(augmented_args.filename.value) - 1; + } + } else { + len = sizeof(augmented_args.args); + } + + perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len); + return 0; +} + +SEC("raw_syscalls:sys_exit") +int sys_exit(struct syscall_exit_args *args) +{ + return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */ +} + +license(GPL); diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c index ac1bcdc17dae..f7eb63cbbc65 100644 --- a/tools/perf/jvmti/jvmti_agent.c +++ b/tools/perf/jvmti/jvmti_agent.c @@ -125,7 +125,7 @@ perf_get_timestamp(void) } static int -debug_cache_init(void) +create_jit_cache_dir(void) { char str[32]; char *base, *p; @@ -144,8 +144,13 @@ debug_cache_init(void) strftime(str, sizeof(str), JIT_LANG"-jit-%Y%m%d", &tm); - snprintf(jit_path, PATH_MAX - 1, "%s/.debug/", base); - + ret = snprintf(jit_path, PATH_MAX, "%s/.debug/", base); + if (ret >= PATH_MAX) { + warnx("jvmti: cannot generate jit cache dir because %s/.debug/" + " is too long, please check the cwd, JITDUMPDIR, and" + " HOME variables", base); + return -1; + } ret = mkdir(jit_path, 0755); if (ret == -1) { if (errno != EEXIST) { @@ -154,20 +159,32 @@ debug_cache_init(void) } } - snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit", base); + ret = snprintf(jit_path, PATH_MAX, "%s/.debug/jit", base); + if (ret >= PATH_MAX) { + warnx("jvmti: cannot generate jit cache dir because" + " %s/.debug/jit is too long, please check the cwd," + " JITDUMPDIR, and HOME variables", base); + return -1; + } ret = mkdir(jit_path, 0755); if (ret == -1) { if (errno != EEXIST) { - warn("cannot create jit cache dir %s", jit_path); + warn("jvmti: cannot create jit cache dir %s", jit_path); return -1; } } - snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit/%s.XXXXXXXX", base, str); - + ret = snprintf(jit_path, PATH_MAX, "%s/.debug/jit/%s.XXXXXXXX", base, str); + if (ret >= PATH_MAX) { + warnx("jvmti: cannot generate jit cache dir because" + " %s/.debug/jit/%s.XXXXXXXX is too long, please check" + " the cwd, JITDUMPDIR, and HOME variables", + base, str); + return -1; + } p = mkdtemp(jit_path); if (p != jit_path) { - warn("cannot create jit cache dir %s", jit_path); + warn("jvmti: cannot create jit cache dir %s", jit_path); return -1; } @@ -228,7 +245,7 @@ void *jvmti_open(void) { char dump_path[PATH_MAX]; struct jitheader header; - int fd; + int fd, ret; FILE *fp; init_arch_timestamp(); @@ -245,12 +262,22 @@ void *jvmti_open(void) memset(&header, 0, sizeof(header)); - debug_cache_init(); + /* + * jitdump file dir + */ + if (create_jit_cache_dir() < 0) + return NULL; /* * jitdump file name */ - scnprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid()); + ret = snprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid()); + if (ret >= PATH_MAX) { + warnx("jvmti: cannot generate jitdump file full path because" + " %s/jit-%i.dump is too long, please check the cwd," + " JITDUMPDIR, and HOME variables", jit_path, getpid()); + return NULL; + } fd = open(dump_path, O_CREAT|O_TRUNC|O_RDWR, 0666); if (fd == -1) diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index 24cb0bd56afa..f278ce5ebab7 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -119,6 +119,14 @@ def dsoname(name): return "[kernel]" return name +def findnth(s, sub, n, offs=0): + pos = s.find(sub) + if pos < 0: + return pos + if n <= 1: + return offs + pos + return findnth(s[pos + 1:], sub, n - 1, offs + pos + 1) + # Percent to one decimal place def PercentToOneDP(n, d): @@ -1464,6 +1472,317 @@ class BranchWindow(QMdiSubWindow): else: self.find_bar.NotFound() +# Dialog data item converted and validated using a SQL table + +class SQLTableDialogDataItem(): + + def __init__(self, glb, label, placeholder_text, table_name, match_column, column_name1, column_name2, parent): + self.glb = glb + self.label = label + self.placeholder_text = placeholder_text + self.table_name = table_name + self.match_column = match_column + self.column_name1 = column_name1 + self.column_name2 = column_name2 + self.parent = parent + + self.value = "" + + self.widget = QLineEdit() + self.widget.editingFinished.connect(self.Validate) + self.widget.textChanged.connect(self.Invalidate) + self.red = False + self.error = "" + self.validated = True + + self.last_id = 0 + self.first_time = 0 + self.last_time = 2 ** 64 + if self.table_name == "<timeranges>": + query = QSqlQuery(self.glb.db) + QueryExec(query, "SELECT id, time FROM samples ORDER BY id DESC LIMIT 1") + if query.next(): + self.last_id = int(query.value(0)) + self.last_time = int(query.value(1)) + QueryExec(query, "SELECT time FROM samples WHERE time != 0 ORDER BY id LIMIT 1") + if query.next(): + self.first_time = int(query.value(0)) + if placeholder_text: + placeholder_text += ", between " + str(self.first_time) + " and " + str(self.last_time) + + if placeholder_text: + self.widget.setPlaceholderText(placeholder_text) + + def ValueToIds(self, value): + ids = [] + query = QSqlQuery(self.glb.db) + stmt = "SELECT id FROM " + self.table_name + " WHERE " + self.match_column + " = '" + value + "'" + ret = query.exec_(stmt) + if ret: + while query.next(): + ids.append(str(query.value(0))) + return ids + + def IdBetween(self, query, lower_id, higher_id, order): + QueryExec(query, "SELECT id FROM samples WHERE id > " + str(lower_id) + " AND id < " + str(higher_id) + " ORDER BY id " + order + " LIMIT 1") + if query.next(): + return True, int(query.value(0)) + else: + return False, 0 + + def BinarySearchTime(self, lower_id, higher_id, target_time, get_floor): + query = QSqlQuery(self.glb.db) + while True: + next_id = int((lower_id + higher_id) / 2) + QueryExec(query, "SELECT time FROM samples WHERE id = " + str(next_id)) + if not query.next(): + ok, dbid = self.IdBetween(query, lower_id, next_id, "DESC") + if not ok: + ok, dbid = self.IdBetween(query, next_id, higher_id, "") + if not ok: + return str(higher_id) + next_id = dbid + QueryExec(query, "SELECT time FROM samples WHERE id = " + str(next_id)) + next_time = int(query.value(0)) + if get_floor: + if target_time > next_time: + lower_id = next_id + else: + higher_id = next_id + if higher_id <= lower_id + 1: + return str(higher_id) + else: + if target_time >= next_time: + lower_id = next_id + else: + higher_id = next_id + if higher_id <= lower_id + 1: + return str(lower_id) + + def ConvertRelativeTime(self, val): + print "val ", val + mult = 1 + suffix = val[-2:] + if suffix == "ms": + mult = 1000000 + elif suffix == "us": + mult = 1000 + elif suffix == "ns": + mult = 1 + else: + return val + val = val[:-2].strip() + if not self.IsNumber(val): + return val + val = int(val) * mult + if val >= 0: + val += self.first_time + else: + val += self.last_time + return str(val) + + def ConvertTimeRange(self, vrange): + print "vrange ", vrange + if vrange[0] == "": + vrange[0] = str(self.first_time) + if vrange[1] == "": + vrange[1] = str(self.last_time) + vrange[0] = self.ConvertRelativeTime(vrange[0]) + vrange[1] = self.ConvertRelativeTime(vrange[1]) + print "vrange2 ", vrange + if not self.IsNumber(vrange[0]) or not self.IsNumber(vrange[1]): + return False + print "ok1" + beg_range = max(int(vrange[0]), self.first_time) + end_range = min(int(vrange[1]), self.last_time) + if beg_range > self.last_time or end_range < self.first_time: + return False + print "ok2" + vrange[0] = self.BinarySearchTime(0, self.last_id, beg_range, True) + vrange[1] = self.BinarySearchTime(1, self.last_id + 1, end_range, False) + print "vrange3 ", vrange + return True + + def AddTimeRange(self, value, ranges): + print "value ", value + n = value.count("-") + if n == 1: + pass + elif n == 2: + if value.split("-")[1].strip() == "": + n = 1 + elif n == 3: + n = 2 + else: + return False + pos = findnth(value, "-", n) + vrange = [value[:pos].strip() ,value[pos+1:].strip()] + if self.ConvertTimeRange(vrange): + ranges.append(vrange) + return True + return False + + def InvalidValue(self, value): + self.value = "" + palette = QPalette() + palette.setColor(QPalette.Text,Qt.red) + self.widget.setPalette(palette) + self.red = True + self.error = self.label + " invalid value '" + value + "'" + self.parent.ShowMessage(self.error) + + def IsNumber(self, value): + try: + x = int(value) + except: + x = 0 + return str(x) == value + + def Invalidate(self): + self.validated = False + + def Validate(self): + input_string = self.widget.text() + self.validated = True + if self.red: + palette = QPalette() + self.widget.setPalette(palette) + self.red = False + if not len(input_string.strip()): + self.error = "" + self.value = "" + return + if self.table_name == "<timeranges>": + ranges = [] + for value in [x.strip() for x in input_string.split(",")]: + if not self.AddTimeRange(value, ranges): + return self.InvalidValue(value) + ranges = [("(" + self.column_name1 + " >= " + r[0] + " AND " + self.column_name1 + " <= " + r[1] + ")") for r in ranges] + self.value = " OR ".join(ranges) + elif self.table_name == "<ranges>": + singles = [] + ranges = [] + for value in [x.strip() for x in input_string.split(",")]: + if "-" in value: + vrange = value.split("-") + if len(vrange) != 2 or not self.IsNumber(vrange[0]) or not self.IsNumber(vrange[1]): + return self.InvalidValue(value) + ranges.append(vrange) + else: + if not self.IsNumber(value): + return self.InvalidValue(value) + singles.append(value) + ranges = [("(" + self.column_name1 + " >= " + r[0] + " AND " + self.column_name1 + " <= " + r[1] + ")") for r in ranges] + if len(singles): + ranges.append(self.column_name1 + " IN (" + ",".join(singles) + ")") + self.value = " OR ".join(ranges) + elif self.table_name: + all_ids = [] + for value in [x.strip() for x in input_string.split(",")]: + ids = self.ValueToIds(value) + if len(ids): + all_ids.extend(ids) + else: + return self.InvalidValue(value) + self.value = self.column_name1 + " IN (" + ",".join(all_ids) + ")" + if self.column_name2: + self.value = "( " + self.value + " OR " + self.column_name2 + " IN (" + ",".join(all_ids) + ") )" + else: + self.value = input_string.strip() + self.error = "" + self.parent.ClearMessage() + + def IsValid(self): + if not self.validated: + self.Validate() + if len(self.error): + self.parent.ShowMessage(self.error) + return False + return True + +# Selected branch report creation dialog + +class SelectedBranchDialog(QDialog): + + def __init__(self, glb, parent=None): + super(SelectedBranchDialog, self).__init__(parent) + + self.glb = glb + + self.name = "" + self.where_clause = "" + + self.setWindowTitle("Selected Branches") + self.setMinimumWidth(600) + + items = ( + ("Report name:", "Enter a name to appear in the window title bar", "", "", "", ""), + ("Time ranges:", "Enter time ranges", "<timeranges>", "", "samples.id", ""), + ("CPUs:", "Enter CPUs or ranges e.g. 0,5-6", "<ranges>", "", "cpu", ""), + ("Commands:", "Only branches with these commands will be included", "comms", "comm", "comm_id", ""), + ("PIDs:", "Only branches with these process IDs will be included", "threads", "pid", "thread_id", ""), + ("TIDs:", "Only branches with these thread IDs will be included", "threads", "tid", "thread_id", ""), + ("DSOs:", "Only branches with these DSOs will be included", "dsos", "short_name", "samples.dso_id", "to_dso_id"), + ("Symbols:", "Only branches with these symbols will be included", "symbols", "name", "symbol_id", "to_symbol_id"), + ("Raw SQL clause: ", "Enter a raw SQL WHERE clause", "", "", "", ""), + ) + self.data_items = [SQLTableDialogDataItem(glb, *x, parent=self) for x in items] + + self.grid = QGridLayout() + + for row in xrange(len(self.data_items)): + self.grid.addWidget(QLabel(self.data_items[row].label), row, 0) + self.grid.addWidget(self.data_items[row].widget, row, 1) + + self.status = QLabel() + + self.ok_button = QPushButton("Ok", self) + self.ok_button.setDefault(True) + self.ok_button.released.connect(self.Ok) + self.ok_button.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed) + + self.cancel_button = QPushButton("Cancel", self) + self.cancel_button.released.connect(self.reject) + self.cancel_button.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed) + + self.hbox = QHBoxLayout() + #self.hbox.addStretch() + self.hbox.addWidget(self.status) + self.hbox.addWidget(self.ok_button) + self.hbox.addWidget(self.cancel_button) + + self.vbox = QVBoxLayout() + self.vbox.addLayout(self.grid) + self.vbox.addLayout(self.hbox) + + self.setLayout(self.vbox); + + def Ok(self): + self.name = self.data_items[0].value + if not self.name: + self.ShowMessage("Report name is required") + return + for d in self.data_items: + if not d.IsValid(): + return + for d in self.data_items[1:]: + if len(d.value): + if len(self.where_clause): + self.where_clause += " AND " + self.where_clause += d.value + if len(self.where_clause): + self.where_clause = " AND ( " + self.where_clause + " ) " + else: + self.ShowMessage("No selection") + return + self.accept() + + def ShowMessage(self, msg): + self.status.setText("<font color=#FF0000>" + msg) + + def ClearMessage(self): + self.status.setText("") + # Event list def GetEventList(db): @@ -1656,7 +1975,7 @@ class TableWindow(QMdiSubWindow, ResizeColumnsToContentsBase): def FindDone(self, row): self.find_bar.Idle() if row >= 0: - self.view.setCurrentIndex(self.model.index(row, 0, QModelIndex())) + self.view.setCurrentIndex(self.model.mapFromSource(self.data_model.index(row, 0, QModelIndex()))) else: self.find_bar.NotFound() @@ -1765,6 +2084,149 @@ class WindowMenu(): def setActiveSubWindow(self, nr): self.mdi_area.setActiveSubWindow(self.mdi_area.subWindowList()[nr - 1]) +# Help text + +glb_help_text = """ +<h1>Contents</h1> +<style> +p.c1 { + text-indent: 40px; +} +p.c2 { + text-indent: 80px; +} +} +</style> +<p class=c1><a href=#reports>1. Reports</a></p> +<p class=c2><a href=#callgraph>1.1 Context-Sensitive Call Graph</a></p> +<p class=c2><a href=#allbranches>1.2 All branches</a></p> +<p class=c2><a href=#selectedbranches>1.3 Selected branches</a></p> +<p class=c1><a href=#tables>2. Tables</a></p> +<h1 id=reports>1. Reports</h1> +<h2 id=callgraph>1.1 Context-Sensitive Call Graph</h2> +The result is a GUI window with a tree representing a context-sensitive +call-graph. Expanding a couple of levels of the tree and adjusting column +widths to suit will display something like: +<pre> + Call Graph: pt_example +Call Path Object Count Time(ns) Time(%) Branch Count Branch Count(%) +v- ls + v- 2638:2638 + v- _start ld-2.19.so 1 10074071 100.0 211135 100.0 + |- unknown unknown 1 13198 0.1 1 0.0 + >- _dl_start ld-2.19.so 1 1400980 13.9 19637 9.3 + >- _d_linit_internal ld-2.19.so 1 448152 4.4 11094 5.3 + v-__libc_start_main@plt ls 1 8211741 81.5 180397 85.4 + >- _dl_fixup ld-2.19.so 1 7607 0.1 108 0.1 + >- __cxa_atexit libc-2.19.so 1 11737 0.1 10 0.0 + >- __libc_csu_init ls 1 10354 0.1 10 0.0 + |- _setjmp libc-2.19.so 1 0 0.0 4 0.0 + v- main ls 1 8182043 99.6 180254 99.9 +</pre> +<h3>Points to note:</h3> +<ul> +<li>The top level is a command name (comm)</li> +<li>The next level is a thread (pid:tid)</li> +<li>Subsequent levels are functions</li> +<li>'Count' is the number of calls</li> +<li>'Time' is the elapsed time until the function returns</li> +<li>Percentages are relative to the level above</li> +<li>'Branch Count' is the total number of branches for that function and all functions that it calls +</ul> +<h3>Find</h3> +Ctrl-F displays a Find bar which finds function names by either an exact match or a pattern match. +The pattern matching symbols are ? for any character and * for zero or more characters. +<h2 id=allbranches>1.2 All branches</h2> +The All branches report displays all branches in chronological order. +Not all data is fetched immediately. More records can be fetched using the Fetch bar provided. +<h3>Disassembly</h3> +Open a branch to display disassembly. This only works if: +<ol> +<li>The disassembler is available. Currently, only Intel XED is supported - see <a href=#xed>Intel XED Setup</a></li> +<li>The object code is available. Currently, only the perf build ID cache is searched for object code. +The default directory ~/.debug can be overridden by setting environment variable PERF_BUILDID_DIR. +One exception is kcore where the DSO long name is used (refer dsos_view on the Tables menu), +or alternatively, set environment variable PERF_KCORE to the kcore file name.</li> +</ol> +<h4 id=xed>Intel XED Setup</h4> +To use Intel XED, libxed.so must be present. To build and install libxed.so: +<pre> +git clone https://github.com/intelxed/mbuild.git mbuild +git clone https://github.com/intelxed/xed +cd xed +./mfile.py --share +sudo ./mfile.py --prefix=/usr/local install +sudo ldconfig +</pre> +<h3>Find</h3> +Ctrl-F displays a Find bar which finds substrings by either an exact match or a regular expression match. +Refer to Python documentation for the regular expression syntax. +All columns are searched, but only currently fetched rows are searched. +<h2 id=selectedbranches>1.3 Selected branches</h2> +This is the same as the <a href=#allbranches>All branches</a> report but with the data reduced +by various selection criteria. A dialog box displays available criteria which are AND'ed together. +<h3>1.3.1 Time ranges</h3> +The time ranges hint text shows the total time range. Relative time ranges can also be entered in +ms, us or ns. Also, negative values are relative to the end of trace. Examples: +<pre> + 81073085947329-81073085958238 From 81073085947329 to 81073085958238 + 100us-200us From 100us to 200us + 10ms- From 10ms to the end + -100ns The first 100ns + -10ms- The last 10ms +</pre> +N.B. Due to the granularity of timestamps, there could be no branches in any given time range. +<h1 id=tables>2. Tables</h1> +The Tables menu shows all tables and views in the database. Most tables have an associated view +which displays the information in a more friendly way. Not all data for large tables is fetched +immediately. More records can be fetched using the Fetch bar provided. Columns can be sorted, +but that can be slow for large tables. +<p>There are also tables of database meta-information. +For SQLite3 databases, the sqlite_master table is included. +For PostgreSQL databases, information_schema.tables/views/columns are included. +<h3>Find</h3> +Ctrl-F displays a Find bar which finds substrings by either an exact match or a regular expression match. +Refer to Python documentation for the regular expression syntax. +All columns are searched, but only currently fetched rows are searched. +<p>N.B. Results are found in id order, so if the table is re-ordered, find-next and find-previous +will go to the next/previous result in id order, instead of display order. +""" + +# Help window + +class HelpWindow(QMdiSubWindow): + + def __init__(self, glb, parent=None): + super(HelpWindow, self).__init__(parent) + + self.text = QTextBrowser() + self.text.setHtml(glb_help_text) + self.text.setReadOnly(True) + self.text.setOpenExternalLinks(True) + + self.setWidget(self.text) + + AddSubWindow(glb.mainwindow.mdi_area, self, "Exported SQL Viewer Help") + +# Main window that only displays the help text + +class HelpOnlyWindow(QMainWindow): + + def __init__(self, parent=None): + super(HelpOnlyWindow, self).__init__(parent) + + self.setMinimumSize(200, 100) + self.resize(800, 600) + self.setWindowTitle("Exported SQL Viewer Help") + self.setWindowIcon(self.style().standardIcon(QStyle.SP_MessageBoxInformation)) + + self.text = QTextBrowser() + self.text.setHtml(glb_help_text) + self.text.setReadOnly(True) + self.text.setOpenExternalLinks(True) + + self.setCentralWidget(self.text) + # Font resize def ResizeFont(widget, diff): @@ -1851,6 +2313,9 @@ class MainWindow(QMainWindow): self.window_menu = WindowMenu(self.mdi_area, menu) + help_menu = menu.addMenu("&Help") + help_menu.addAction(CreateAction("&Exported SQL Viewer Help", "Helpful information", self.Help, self, QKeySequence.HelpContents)) + def Find(self): win = self.mdi_area.activeSubWindow() if win: @@ -1888,6 +2353,8 @@ class MainWindow(QMainWindow): if event == "branches": label = "All branches" if branches_events == 1 else "All branches " + "(id=" + dbid + ")" reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewBranchView(x), self)) + label = "Selected branches" if branches_events == 1 else "Selected branches " + "(id=" + dbid + ")" + reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewSelectedBranchView(x), self)) def TableMenu(self, tables, menu): table_menu = menu.addMenu("&Tables") @@ -1900,9 +2367,18 @@ class MainWindow(QMainWindow): def NewBranchView(self, event_id): BranchWindow(self.glb, event_id, "", "", self) + def NewSelectedBranchView(self, event_id): + dialog = SelectedBranchDialog(self.glb, self) + ret = dialog.exec_() + if ret: + BranchWindow(self.glb, event_id, dialog.name, dialog.where_clause, self) + def NewTableView(self, table_name): TableWindow(self.glb, table_name, self) + def Help(self): + HelpWindow(self.glb, self) + # XED Disassembler class xed_state_t(Structure): @@ -1929,7 +2405,12 @@ class XEDInstruction(): class LibXED(): def __init__(self): - self.libxed = CDLL("libxed.so") + try: + self.libxed = CDLL("libxed.so") + except: + self.libxed = None + if not self.libxed: + self.libxed = CDLL("/usr/local/lib/libxed.so") self.xed_tables_init = self.libxed.xed_tables_init self.xed_tables_init.restype = None @@ -2097,10 +2578,16 @@ class DBRef(): def Main(): if (len(sys.argv) < 2): - print >> sys.stderr, "Usage is: exported-sql-viewer.py <database name>" + print >> sys.stderr, "Usage is: exported-sql-viewer.py {<database name> | --help-only}" raise Exception("Too few arguments") dbname = sys.argv[1] + if dbname == "--help-only": + app = QApplication(sys.argv) + mainwindow = HelpOnlyWindow() + mainwindow.show() + err = app.exec_() + sys.exit(err) is_sqlite3 = False try: diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling index 8a33ca4f9e1f..f0729c454f16 100644 --- a/tools/perf/tests/attr/test-record-group-sampling +++ b/tools/perf/tests/attr/test-record-group-sampling @@ -37,4 +37,3 @@ sample_freq=0 sample_period=0 freq=0 write_backward=0 -sample_id_all=0 diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index e88e6f9b1463..668d2a9ef0f4 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1810,3 +1810,30 @@ void perf_evlist__force_leader(struct perf_evlist *evlist) leader->forced_leader = true; } } + +struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evsel_list, + struct perf_evsel *evsel) +{ + struct perf_evsel *c2, *leader; + bool is_open = true; + + leader = evsel->leader; + pr_debug("Weak group for %s/%d failed\n", + leader->name, leader->nr_members); + + /* + * for_each_group_member doesn't work here because it doesn't + * include the first entry. + */ + evlist__for_each_entry(evsel_list, c2) { + if (c2 == evsel) + is_open = false; + if (c2->leader == leader) { + if (is_open) + perf_evsel__close(c2); + c2->leader = c2; + c2->nr_members = 0; + } + } + return leader; +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index dc66436add98..9919eed6d15b 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -312,4 +312,7 @@ bool perf_evlist__exclude_kernel(struct perf_evlist *evlist); void perf_evlist__force_leader(struct perf_evlist *evlist); +struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evlist, + struct perf_evsel *evsel); + #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 6d187059a373..d37bb1566cd9 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -956,7 +956,6 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, attr->sample_freq = 0; attr->sample_period = 0; attr->write_backward = 0; - attr->sample_id_all = 0; } if (opts->no_samples) diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 58f6a9ceb590..4503f3ca45ab 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -1474,6 +1474,8 @@ static void intel_pt_calc_mtc_timestamp(struct intel_pt_decoder *decoder) decoder->have_calc_cyc_to_tsc = false; intel_pt_calc_cyc_to_tsc(decoder, true); } + + intel_pt_log_to("Setting timestamp", decoder->timestamp); } static void intel_pt_calc_cbr(struct intel_pt_decoder *decoder) @@ -1514,6 +1516,8 @@ static void intel_pt_calc_cyc_timestamp(struct intel_pt_decoder *decoder) decoder->timestamp = timestamp; decoder->timestamp_insn_cnt = 0; + + intel_pt_log_to("Setting timestamp", decoder->timestamp); } /* Walk PSB+ packets when already in sync. */ diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.c b/tools/perf/util/intel-pt-decoder/intel-pt-log.c index e02bc7b166a0..5e64da270f97 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-log.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.c @@ -31,6 +31,11 @@ static FILE *f; static char log_name[MAX_LOG_NAME]; bool intel_pt_enable_logging; +void *intel_pt_log_fp(void) +{ + return f; +} + void intel_pt_log_enable(void) { intel_pt_enable_logging = true; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.h b/tools/perf/util/intel-pt-decoder/intel-pt-log.h index 45b64f93f358..cc084937f701 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-log.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.h @@ -22,6 +22,7 @@ struct intel_pt_pkt; +void *intel_pt_log_fp(void); void intel_pt_log_enable(void); void intel_pt_log_disable(void); void intel_pt_log_set_name(const char *name); diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 86cc9a64e982..149ff361ca78 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -206,6 +206,16 @@ static void intel_pt_dump_event(struct intel_pt *pt, unsigned char *buf, intel_pt_dump(pt, buf, len); } +static void intel_pt_log_event(union perf_event *event) +{ + FILE *f = intel_pt_log_fp(); + + if (!intel_pt_enable_logging || !f) + return; + + perf_event__fprintf(event, f); +} + static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a, struct auxtrace_buffer *b) { @@ -2010,9 +2020,9 @@ static int intel_pt_process_event(struct perf_session *session, event->header.type == PERF_RECORD_SWITCH_CPU_WIDE) err = intel_pt_context_switch(pt, event, sample); - intel_pt_log("event %s (%u): cpu %d time %"PRIu64" tsc %#"PRIx64"\n", - perf_event__name(event->header.type), event->header.type, - sample->cpu, sample->time, timestamp); + intel_pt_log("event %u: cpu %d time %"PRIu64" tsc %#"PRIx64" ", + event->header.type, sample->cpu, sample->time, timestamp); + intel_pt_log_event(event); return err; } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 7799788f662f..7e49baad304d 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -773,7 +773,7 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) if (!is_arm_pmu_core(name)) { pname = pe->pmu ? pe->pmu : "cpu"; - if (strncmp(pname, name, strlen(pname))) + if (strcmp(pname, name)) continue; } diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 9527d47a1070..01ec04bf91b5 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -140,8 +140,8 @@ static u32 handle[] = { [6] = NFIT_DIMM_HANDLE(1, 0, 0, 0, 1), }; -static unsigned long dimm_fail_cmd_flags[NUM_DCR]; -static int dimm_fail_cmd_code[NUM_DCR]; +static unsigned long dimm_fail_cmd_flags[ARRAY_SIZE(handle)]; +static int dimm_fail_cmd_code[ARRAY_SIZE(handle)]; static const struct nd_intel_smart smart_def = { .flags = ND_INTEL_SMART_HEALTH_VALID @@ -205,7 +205,7 @@ struct nfit_test { unsigned long deadline; spinlock_t lock; } ars_state; - struct device *dimm_dev[NUM_DCR]; + struct device *dimm_dev[ARRAY_SIZE(handle)]; struct nd_intel_smart *smart; struct nd_intel_smart_threshold *smart_threshold; struct badrange badrange; @@ -2680,7 +2680,7 @@ static int nfit_test_probe(struct platform_device *pdev) u32 nfit_handle = __to_nfit_memdev(nfit_mem)->device_handle; int i; - for (i = 0; i < NUM_DCR; i++) + for (i = 0; i < ARRAY_SIZE(handle); i++) if (nfit_handle == handle[i]) dev_set_drvdata(nfit_test->dimm_dev[i], nfit_mem); diff --git a/tools/testing/selftests/powerpc/mm/wild_bctr.c b/tools/testing/selftests/powerpc/mm/wild_bctr.c index 1b0e9e9a2ddc..f2fa101c5a6a 100644 --- a/tools/testing/selftests/powerpc/mm/wild_bctr.c +++ b/tools/testing/selftests/powerpc/mm/wild_bctr.c @@ -47,8 +47,9 @@ static int ok(void) return 0; } -#define REG_POISON 0x5a5aUL -#define POISONED_REG(n) ((REG_POISON << 48) | ((n) << 32) | (REG_POISON << 16) | (n)) +#define REG_POISON 0x5a5a +#define POISONED_REG(n) ((((unsigned long)REG_POISON) << 48) | ((n) << 32) | \ + (((unsigned long)REG_POISON) << 16) | (n)) static inline void poison_regs(void) { @@ -105,6 +106,20 @@ static void dump_regs(void) } } +#ifdef _CALL_AIXDESC +struct opd { + unsigned long ip; + unsigned long toc; + unsigned long env; +}; +static struct opd bad_opd = { + .ip = BAD_NIP, +}; +#define BAD_FUNC (&bad_opd) +#else +#define BAD_FUNC BAD_NIP +#endif + int test_wild_bctr(void) { int (*func_ptr)(void); @@ -133,7 +148,7 @@ int test_wild_bctr(void) poison_regs(); - func_ptr = (int (*)(void))BAD_NIP; + func_ptr = (int (*)(void))BAD_FUNC; func_ptr(); FAIL_IF(1); /* we didn't segv? */ |