diff --git a/Documentation/ABI/testing/sysfs-platform_profile b/Documentation/ABI/testing/sysfs-platform_profile new file mode 100644 index 000000000000..9d6b89b66cca --- /dev/null +++ b/Documentation/ABI/testing/sysfs-platform_profile @@ -0,0 +1,24 @@ +What: /sys/firmware/acpi/platform_profile_choices +Date: October 2020 +Contact: Hans de Goede +Description: This file contains a space-separated list of profiles supported for this device. + + Drivers must use the following standard profile-names: + + ============ ============================================ + low-power Low power consumption + cool Cooler operation + quiet Quieter operation + balanced Balance between low power consumption and performance + performance High performance operation + ============ ============================================ + + Userspace may expect drivers to offer more than one of these + standard profile names. + +What: /sys/firmware/acpi/platform_profile +Date: October 2020 +Contact: Hans de Goede +Description: Reading this file gives the current selected profile for this + device. Writing this file with one of the strings from + platform_profile_choices changes the profile to the new value. diff --git a/Documentation/firmware-guide/acpi/debug.rst b/Documentation/firmware-guide/acpi/debug.rst index 1a152dd1d765..03cd4e25fc45 100644 --- a/Documentation/firmware-guide/acpi/debug.rst +++ b/Documentation/firmware-guide/acpi/debug.rst @@ -52,19 +52,12 @@ shows the supported mask values, currently these:: ACPI_CA_DISASSEMBLER 0x00000800 ACPI_COMPILER 0x00001000 ACPI_TOOLS 0x00002000 - ACPI_BUS_COMPONENT 0x00010000 - ACPI_AC_COMPONENT 0x00020000 - ACPI_BATTERY_COMPONENT 0x00040000 - ACPI_BUTTON_COMPONENT 0x00080000 ACPI_SBS_COMPONENT 0x00100000 ACPI_FAN_COMPONENT 0x00200000 ACPI_PCI_COMPONENT 0x00400000 - ACPI_POWER_COMPONENT 0x00800000 ACPI_CONTAINER_COMPONENT 0x01000000 ACPI_SYSTEM_COMPONENT 0x02000000 - ACPI_THERMAL_COMPONENT 0x04000000 ACPI_MEMORY_DEVICE_COMPONENT 0x08000000 - ACPI_VIDEO_COMPONENT 0x10000000 ACPI_PROCESSOR_COMPONENT 0x20000000 debug_level @@ -118,15 +111,15 @@ currently these:: Examples ======== -For example, drivers/acpi/bus.c contains this:: +For example, drivers/acpi/acpica/evxfevnt.c contains this:: - #define _COMPONENT ACPI_BUS_COMPONENT + #define _COMPONENT ACPI_EVENTS ... - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device insertion detected\n")); + ACPI_DEBUG_PRINT((ACPI_DB_INIT, "ACPI mode disabled\n")); -To turn on this message, set the ACPI_BUS_COMPONENT bit in acpi.debug_layer -and the ACPI_LV_INFO bit in acpi.debug_level. (The ACPI_DEBUG_PRINT -statement uses ACPI_DB_INFO, which is macro based on the ACPI_LV_INFO +To turn on this message, set the ACPI_EVENTS bit in acpi.debug_layer +and the ACPI_LV_INIT bit in acpi.debug_level. (The ACPI_DEBUG_PRINT +statement uses ACPI_DB_INIT, which is a macro based on the ACPI_LV_INIT definition.) Enable all AML "Debug" output (stores to the Debug object while interpreting diff --git a/Documentation/firmware-guide/acpi/gpio-properties.rst b/Documentation/firmware-guide/acpi/gpio-properties.rst index b36aa3e743d8..4e264c16ddff 100644 --- a/Documentation/firmware-guide/acpi/gpio-properties.rst +++ b/Documentation/firmware-guide/acpi/gpio-properties.rst @@ -146,6 +146,7 @@ following rules (see also the examples): other words, it is not mandatory to fill all the GPIO lines - empty names are allowed (two quotation marks ``""`` correspond to an empty name) + - names inside one GPIO controller/expander must be unique Example of a GPIO controller of 16 lines, with an incomplete list with two empty names:: diff --git a/Documentation/power/index.rst b/Documentation/power/index.rst index ced8a8007434..a0f5244fb427 100644 --- a/Documentation/power/index.rst +++ b/Documentation/power/index.rst @@ -30,6 +30,7 @@ Power Management userland-swsusp powercap/powercap + powercap/dtpm regulator/consumer regulator/design diff --git a/Documentation/power/powercap/dtpm.rst b/Documentation/power/powercap/dtpm.rst new file mode 100644 index 000000000000..a38dee3d815b --- /dev/null +++ b/Documentation/power/powercap/dtpm.rst @@ -0,0 +1,212 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================================== +Dynamic Thermal Power Management framework +========================================== + +On the embedded world, the complexity of the SoC leads to an +increasing number of hotspots which need to be monitored and mitigated +as a whole in order to prevent the temperature to go above the +normative and legally stated 'skin temperature'. + +Another aspect is to sustain the performance for a given power budget, +for example virtual reality where the user can feel dizziness if the +performance is capped while a big CPU is processing something else. Or +reduce the battery charging because the dissipated power is too high +compared with the power consumed by other devices. + +The user space is the most adequate place to dynamically act on the +different devices by limiting their power given an application +profile: it has the knowledge of the platform. + +The Dynamic Thermal Power Management (DTPM) is a technique acting on +the device power by limiting and/or balancing a power budget among +different devices. + +The DTPM framework provides an unified interface to act on the +device power. + +Overview +======== + +The DTPM framework relies on the powercap framework to create the +powercap entries in the sysfs directory and implement the backend +driver to do the connection with the power manageable device. + +The DTPM is a tree representation describing the power constraints +shared between devices, not their physical positions. + +The nodes of the tree are a virtual description aggregating the power +characteristics of the children nodes and their power limitations. + +The leaves of the tree are the real power manageable devices. + +For instance:: + + SoC + | + `-- pkg + | + |-- pd0 (cpu0-3) + | + `-- pd1 (cpu4-5) + +The pkg power will be the sum of pd0 and pd1 power numbers:: + + SoC (400mW - 3100mW) + | + `-- pkg (400mW - 3100mW) + | + |-- pd0 (100mW - 700mW) + | + `-- pd1 (300mW - 2400mW) + +When the nodes are inserted in the tree, their power characteristics are propagated to the parents:: + + SoC (600mW - 5900mW) + | + |-- pkg (400mW - 3100mW) + | | + | |-- pd0 (100mW - 700mW) + | | + | `-- pd1 (300mW - 2400mW) + | + `-- pd2 (200mW - 2800mW) + +Each node have a weight on a 2^10 basis reflecting the percentage of power consumption along the siblings:: + + SoC (w=1024) + | + |-- pkg (w=538) + | | + | |-- pd0 (w=231) + | | + | `-- pd1 (w=794) + | + `-- pd2 (w=486) + + Note the sum of weights at the same level are equal to 1024. + +When a power limitation is applied to a node, then it is distributed along the children given their weights. For example, if we set a power limitation of 3200mW at the 'SoC' root node, the resulting tree will be:: + + SoC (w=1024) <--- power_limit = 3200mW + | + |-- pkg (w=538) --> power_limit = 1681mW + | | + | |-- pd0 (w=231) --> power_limit = 378mW + | | + | `-- pd1 (w=794) --> power_limit = 1303mW + | + `-- pd2 (w=486) --> power_limit = 1519mW + + +Flat description +---------------- + +A root node is created and it is the parent of all the nodes. This +description is the simplest one and it is supposed to give to user +space a flat representation of all the devices supporting the power +limitation without any power limitation distribution. + +Hierarchical description +------------------------ + +The different devices supporting the power limitation are represented +hierarchically. There is one root node, all intermediate nodes are +grouping the child nodes which can be intermediate nodes also or real +devices. + +The intermediate nodes aggregate the power information and allows to +set the power limit given the weight of the nodes. + +User space API +============== + +As stated in the overview, the DTPM framework is built on top of the +powercap framework. Thus the sysfs interface is the same, please refer +to the powercap documentation for further details. + + * power_uw: Instantaneous power consumption. If the node is an + intermediate node, then the power consumption will be the sum of all + children power consumption. + + * max_power_range_uw: The power range resulting of the maximum power + minus the minimum power. + + * name: The name of the node. This is implementation dependent. Even + if it is not recommended for the user space, several nodes can have + the same name. + + * constraint_X_name: The name of the constraint. + + * constraint_X_max_power_uw: The maximum power limit to be applicable + to the node. + + * constraint_X_power_limit_uw: The power limit to be applied to the + node. If the value contained in constraint_X_max_power_uw is set, + the constraint will be removed. + + * constraint_X_time_window_us: The meaning of this file will depend + on the constraint number. + +Constraints +----------- + + * Constraint 0: The power limitation is immediately applied, without + limitation in time. + +Kernel API +========== + +Overview +-------- + +The DTPM framework has no power limiting backend support. It is +generic and provides a set of API to let the different drivers to +implement the backend part for the power limitation and create the +power constraints tree. + +It is up to the platform to provide the initialization function to +allocate and link the different nodes of the tree. + +A special macro has the role of declaring a node and the corresponding +initialization function via a description structure. This one contains +an optional parent field allowing to hook different devices to an +already existing tree at boot time. + +For instance:: + + struct dtpm_descr my_descr = { + .name = "my_name", + .init = my_init_func, + }; + + DTPM_DECLARE(my_descr); + +The nodes of the DTPM tree are described with dtpm structure. The +steps to add a new power limitable device is done in three steps: + + * Allocate the dtpm node + * Set the power number of the dtpm node + * Register the dtpm node + +The registration of the dtpm node is done with the powercap +ops. Basically, it must implements the callbacks to get and set the +power and the limit. + +Alternatively, if the node to be inserted is an intermediate one, then +a simple function to insert it as a future parent is available. + +If a device has its power characteristics changing, then the tree must +be updated with the new power numbers and weights. + +Nomenclature +------------ + + * dtpm_alloc() : Allocate and initialize a dtpm structure + + * dtpm_register() : Add the dtpm node to the tree + + * dtpm_unregister() : Remove the dtpm node from the tree + + * dtpm_update_power() : Update the power characteristics of the dtpm node diff --git a/Documentation/power/runtime_pm.rst b/Documentation/power/runtime_pm.rst index 0553008b6279..d9c777b18f7a 100644 --- a/Documentation/power/runtime_pm.rst +++ b/Documentation/power/runtime_pm.rst @@ -579,7 +579,7 @@ should be used. Of course, for this purpose the device's runtime PM has to be enabled earlier by calling pm_runtime_enable(). Note, if the device may execute pm_runtime calls during the probe (such as -if it is registers with a subsystem that may call back in) then the +if it is registered with a subsystem that may call back in) then the pm_runtime_get_sync() call paired with a pm_runtime_put() call will be appropriate to ensure that the device is not put back to sleep during the probe. This can happen with systems such as the network device layer. @@ -587,11 +587,11 @@ probe. This can happen with systems such as the network device layer. It may be desirable to suspend the device once ->probe() has finished. Therefore the driver core uses the asynchronous pm_request_idle() to submit a request to execute the subsystem-level idle callback for the device at that -time. A driver that makes use of the runtime autosuspend feature, may want to +time. A driver that makes use of the runtime autosuspend feature may want to update the last busy mark before returning from ->probe(). Moreover, the driver core prevents runtime PM callbacks from racing with the bus -notifier callback in __device_release_driver(), which is necessary, because the +notifier callback in __device_release_driver(), which is necessary because the notifier is used by some subsystems to carry out operations affecting the runtime PM functionality. It does so by calling pm_runtime_get_sync() before driver_sysfs_remove() and the BUS_NOTIFY_UNBIND_DRIVER notifications. This @@ -603,7 +603,7 @@ calling pm_runtime_suspend() from their ->remove() routines, the driver core executes pm_runtime_put_sync() after running the BUS_NOTIFY_UNBIND_DRIVER notifications in __device_release_driver(). This requires bus types and drivers to make their ->remove() callbacks avoid races with runtime PM directly, -but also it allows of more flexibility in the handling of devices during the +but it also allows more flexibility in the handling of devices during the removal of their drivers. Drivers in ->remove() callback should undo the runtime PM changes done @@ -693,7 +693,7 @@ that the device appears to be runtime-suspended and its state is fine, so it may be left in runtime suspend provided that all of its descendants are also left in runtime suspend. If that happens, the PM core will not execute any system suspend and resume callbacks for all of those devices, except for the -complete callback, which is then entirely responsible for handling the device +.complete() callback, which is then entirely responsible for handling the device as appropriate. This only applies to system suspend transitions that are not related to hibernation (see Documentation/driver-api/pm/devices.rst for more information). @@ -706,7 +706,7 @@ out the following operations: right before executing the subsystem-level .prepare() callback for it and pm_runtime_barrier() is called for every device right before executing the subsystem-level .suspend() callback for it. In addition to that the PM core - calls __pm_runtime_disable() with 'false' as the second argument for every + calls __pm_runtime_disable() with 'false' as the second argument for every device right before executing the subsystem-level .suspend_late() callback for it. @@ -783,7 +783,7 @@ driver/base/power/generic_ops.c: `int pm_generic_restore_noirq(struct device *dev);` - invoke the ->restore_noirq() callback provided by the device's driver -These functions are the defaults used by the PM core, if a subsystem doesn't +These functions are the defaults used by the PM core if a subsystem doesn't provide its own callbacks for ->runtime_idle(), ->runtime_suspend(), ->runtime_resume(), ->suspend(), ->suspend_noirq(), ->resume(), ->resume_noirq(), ->freeze(), ->freeze_noirq(), ->thaw(), ->thaw_noirq(), diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst index acd2cc2a538d..d29b020e5622 100644 --- a/Documentation/userspace-api/index.rst +++ b/Documentation/userspace-api/index.rst @@ -24,6 +24,7 @@ place where this information is gathered. ioctl/index iommu media/index + sysfs-platform_profile .. only:: subproject and html diff --git a/Documentation/userspace-api/sysfs-platform_profile.rst b/Documentation/userspace-api/sysfs-platform_profile.rst new file mode 100644 index 000000000000..c33a71263d9e --- /dev/null +++ b/Documentation/userspace-api/sysfs-platform_profile.rst @@ -0,0 +1,42 @@ +===================================================================== +Platform Profile Selection (e.g. /sys/firmware/acpi/platform_profile) +===================================================================== + +On modern systems the platform performance, temperature, fan and other +hardware related characteristics are often dynamically configurable. The +platform configuration is often automatically adjusted to the current +conditions by some automatic mechanism (which may very well live outside +the kernel). + +These auto platform adjustment mechanisms often can be configured with +one of several platform profiles, with either a bias towards low power +operation or towards performance. + +The purpose of the platform_profile attribute is to offer a generic sysfs +API for selecting the platform profile of these automatic mechanisms. + +Note that this API is only for selecting the platform profile, it is +NOT a goal of this API to allow monitoring the resulting performance +characteristics. Monitoring performance is best done with device/vendor +specific tools such as e.g. turbostat. + +Specifically when selecting a high performance profile the actual achieved +performance may be limited by various factors such as: the heat generated +by other components, room temperature, free air flow at the bottom of a +laptop, etc. It is explicitly NOT a goal of this API to let userspace know +about any sub-optimal conditions which are impeding reaching the requested +performance level. + +Since numbers on their own cannot represent the multiple variables that a +profile will adjust (power consumption, heat generation, etc) this API +uses strings to describe the various profiles. To make sure that userspace +gets a consistent experience the sysfs-platform_profile ABI document defines +a fixed set of profile names. Drivers *must* map their internal profile +representation onto this fixed set. + +If there is no good match when mapping then a new profile name may be +added. Drivers which wish to introduce new profile names must: + + 1. Explain why the existing profile names canot be used. + 2. Add the new profile name, along with a clear description of the + expected behaviour, to the sysfs-platform_profile ABI documentation. diff --git a/MAINTAINERS b/MAINTAINERS index 5034ff660102..64320457e4cc 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4600,6 +4600,7 @@ L: linux-samsung-soc@vger.kernel.org S: Supported F: arch/arm/mach-exynos/pm.c F: drivers/cpuidle/cpuidle-exynos.c +F: include/linux/platform_data/cpuidle-exynos.h CPUIDLE DRIVER - ARM PSCI M: Lorenzo Pieralisi diff --git a/arch/Kconfig b/arch/Kconfig index 24862d15f3a3..b8bbfd3c66b8 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1111,6 +1111,9 @@ config ARCH_SPLIT_ARG64 If a 32-bit architecture requires 64-bit arguments to be split into pairs of 32-bit arguments, select this option. +config ARCH_HAS_ELFCORE_COMPAT + bool + source "kernel/gcov/Kconfig" source "scripts/gcc-plugins/Kconfig" diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 9487950ffce5..f15244a48957 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1213,7 +1213,6 @@ config ARM64_TAGGED_ADDR_ABI menuconfig COMPAT bool "Kernel support for 32-bit EL0" depends on ARM64_4K_PAGES || EXPERT - select COMPAT_BINFMT_ELF if BINFMT_ELF select HAVE_UID16 select OLD_SIGSUSPEND3 select COMPAT_OLD_SIGACTION diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c index fec70d662d0c..4f47741005d2 100644 --- a/arch/ia64/kernel/crash.c +++ b/arch/ia64/kernel/crash.c @@ -43,7 +43,7 @@ crash_save_this_cpu(void) elf_greg_t *dst = (elf_greg_t *)&(prstatus->pr_reg); memset(prstatus, 0, sizeof(*prstatus)); - prstatus->pr_pid = current->pid; + prstatus->common.pr_pid = current->pid; ia64_dump_cpu_regs(dst); cfm = dst[43]; diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 0a17bedf4f0d..f29ec95e3458 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -92,6 +92,7 @@ config MIPS select SET_FS select SYSCTL_EXCEPTION_TRACE select VIRT_TO_BUS + select ARCH_HAS_ELFCORE_COMPAT config MIPS_FIXUP_BIGPHYS_ADDR bool @@ -2182,7 +2183,7 @@ endchoice config KVM_GUEST bool "KVM Guest Kernel" depends on CPU_MIPS32_R2 - depends on BROKEN_ON_SMP + depends on !64BIT && BROKEN_ON_SMP help Select this option if building a guest kernel for KVM (Trap & Emulate) mode. @@ -3300,11 +3301,6 @@ config MIPS32_N32 If unsure, say N. -config BINFMT_ELF32 - bool - default y if MIPS32_O32 || MIPS32_N32 - select ELFCORE - menu "Power management options" config ARCH_HIBERNATION_POSSIBLE diff --git a/arch/mips/include/asm/elf.h b/arch/mips/include/asm/elf.h index 71c7622025d1..dc8d2863752c 100644 --- a/arch/mips/include/asm/elf.h +++ b/arch/mips/include/asm/elf.h @@ -201,7 +201,6 @@ struct mips_elf_abiflags_v0 { uint32_t flags2; }; -#ifndef ELF_ARCH /* ELF register definitions */ #define ELF_NGREG 45 #define ELF_NFPREG 33 @@ -219,7 +218,7 @@ void mips_dump_regs64(u64 *uregs, const struct pt_regs *regs); /* * This is used to ensure we don't load something for the wrong architecture. */ -#define elf_check_arch elfo32_check_arch +#define elf_check_arch elf32_check_arch /* * These are used to set parameters in the core dumps. @@ -235,7 +234,8 @@ void mips_dump_regs64(u64 *uregs, const struct pt_regs *regs); /* * This is used to ensure we don't load something for the wrong architecture. */ -#define elf_check_arch elfn64_check_arch +#define elf_check_arch elf64_check_arch +#define compat_elf_check_arch elf32_check_arch /* * These are used to set parameters in the core dumps. @@ -257,8 +257,6 @@ void mips_dump_regs64(u64 *uregs, const struct pt_regs *regs); #endif #define ELF_ARCH EM_MIPS -#endif /* !defined(ELF_ARCH) */ - /* * In order to be sure that we don't attempt to execute an O32 binary which * requires 64 bit FP (FR=1) on a system which does not support it we refuse @@ -277,9 +275,9 @@ void mips_dump_regs64(u64 *uregs, const struct pt_regs *regs); #define vmcore_elf64_check_arch mips_elf_check_machine /* - * Return non-zero if HDR identifies an o32 ELF binary. + * Return non-zero if HDR identifies an o32 or n32 ELF binary. */ -#define elfo32_check_arch(hdr) \ +#define elf32_check_arch(hdr) \ ({ \ int __res = 1; \ struct elfhdr *__h = (hdr); \ @@ -288,21 +286,26 @@ void mips_dump_regs64(u64 *uregs, const struct pt_regs *regs); __res = 0; \ if (__h->e_ident[EI_CLASS] != ELFCLASS32) \ __res = 0; \ - if ((__h->e_flags & EF_MIPS_ABI2) != 0) \ - __res = 0; \ - if (((__h->e_flags & EF_MIPS_ABI) != 0) && \ - ((__h->e_flags & EF_MIPS_ABI) != EF_MIPS_ABI_O32)) \ - __res = 0; \ - if (__h->e_flags & __MIPS_O32_FP64_MUST_BE_ZERO) \ - __res = 0; \ - \ + if ((__h->e_flags & EF_MIPS_ABI2) != 0) { \ + if (!IS_ENABLED(CONFIG_MIPS32_N32) || \ + (__h->e_flags & EF_MIPS_ABI)) \ + __res = 0; \ + } else { \ + if (IS_ENABLED(CONFIG_64BIT) && !IS_ENABLED(CONFIG_MIPS32_O32)) \ + __res = 0; \ + if (((__h->e_flags & EF_MIPS_ABI) != 0) && \ + ((__h->e_flags & EF_MIPS_ABI) != EF_MIPS_ABI_O32)) \ + __res = 0; \ + if (__h->e_flags & __MIPS_O32_FP64_MUST_BE_ZERO) \ + __res = 0; \ + } \ __res; \ }) /* * Return non-zero if HDR identifies an n64 ELF binary. */ -#define elfn64_check_arch(hdr) \ +#define elf64_check_arch(hdr) \ ({ \ int __res = 1; \ struct elfhdr *__h = (hdr); \ @@ -315,25 +318,6 @@ void mips_dump_regs64(u64 *uregs, const struct pt_regs *regs); __res; \ }) -/* - * Return non-zero if HDR identifies an n32 ELF binary. - */ -#define elfn32_check_arch(hdr) \ -({ \ - int __res = 1; \ - struct elfhdr *__h = (hdr); \ - \ - if (!mips_elf_check_machine(__h)) \ - __res = 0; \ - if (__h->e_ident[EI_CLASS] != ELFCLASS32) \ - __res = 0; \ - if (((__h->e_flags & EF_MIPS_ABI2) == 0) || \ - ((__h->e_flags & EF_MIPS_ABI) != 0)) \ - __res = 0; \ - \ - __res; \ -}) - struct mips_abi; extern struct mips_abi mips_abi; @@ -469,9 +453,7 @@ extern const char *__elf_base_platform; the loader. We need to make sure that it is out of the way of the program that it will "exec", and that there is sufficient room for the brk. */ -#ifndef ELF_ET_DYN_BASE #define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2) -#endif /* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */ #define ARCH_DLINFO \ diff --git a/arch/mips/include/asm/elfcore-compat.h b/arch/mips/include/asm/elfcore-compat.h new file mode 100644 index 000000000000..2f0f0103c75b --- /dev/null +++ b/arch/mips/include/asm/elfcore-compat.h @@ -0,0 +1,29 @@ +#ifndef _ASM_MIPS_ELFCORE_COMPAT_H +#define _ASM_MIPS_ELFCORE_COMPAT_H + +/* + * On mips we have two 32bit ABIs - o32 and n32. The latter + * has bigger registers, so we use it for compat_elf_regset_t. + * The former uses o32_elf_prstatus and PRSTATUS_SIZE/SET_PR_FPVALID + * are used to choose the size and location of ->pr_fpvalid of + * the layout actually used. + */ +typedef elf_gregset_t compat_elf_gregset_t; + +struct o32_elf_prstatus +{ + struct compat_elf_prstatus_common common; + unsigned int pr_reg[ELF_NGREG]; + compat_int_t pr_fpvalid; +}; + +#define PRSTATUS_SIZE \ + (!test_thread_flag(TIF_32BIT_REGS) \ + ? sizeof(struct compat_elf_prstatus) \ + : sizeof(struct o32_elf_prstatus)) +#define SET_PR_FPVALID(S) \ + (*(!test_thread_flag(TIF_32BIT_REGS) \ + ? &(S)->pr_fpvalid \ + : &((struct o32_elf_prstatus *)(S))->pr_fpvalid) = 1) + +#endif diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index 2a05b923f579..943eaeef73e9 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -80,8 +80,8 @@ obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_32BIT) += scall32-o32.o obj-$(CONFIG_64BIT) += scall64-n64.o obj-$(CONFIG_MIPS32_COMPAT) += linux32.o ptrace32.o signal32.o -obj-$(CONFIG_MIPS32_N32) += binfmt_elfn32.o scall64-n32.o signal_n32.o -obj-$(CONFIG_MIPS32_O32) += binfmt_elfo32.o scall64-o32.o signal_o32.o +obj-$(CONFIG_MIPS32_N32) += scall64-n32.o signal_n32.o +obj-$(CONFIG_MIPS32_O32) += scall64-o32.o signal_o32.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_PROC_FS) += proc.o diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c deleted file mode 100644 index c4441416e96b..000000000000 --- a/arch/mips/kernel/binfmt_elfn32.c +++ /dev/null @@ -1,113 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Support for n32 Linux/MIPS ELF binaries. - * Author: Ralf Baechle (ralf@linux-mips.org) - * - * Copyright (C) 1999, 2001 Ralf Baechle - * Copyright (C) 1999, 2001 Silicon Graphics, Inc. - * - * Heavily inspired by the 32-bit Sparc compat code which is - * Copyright (C) 1995, 1996, 1997, 1998 David S. Miller (davem@redhat.com) - * Copyright (C) 1995, 1996, 1997, 1998 Jakub Jelinek (jj@ultra.linux.cz) - */ - -#define ELF_ARCH EM_MIPS -#define ELF_CLASS ELFCLASS32 -#ifdef __MIPSEB__ -#define ELF_DATA ELFDATA2MSB; -#else /* __MIPSEL__ */ -#define ELF_DATA ELFDATA2LSB; -#endif - -/* ELF register definitions */ -#define ELF_NGREG 45 -#define ELF_NFPREG 33 - -typedef unsigned long elf_greg_t; -typedef elf_greg_t elf_gregset_t[ELF_NGREG]; - -typedef double elf_fpreg_t; -typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG]; - -/* - * This is used to ensure we don't load something for the wrong architecture. - */ -#define elf_check_arch elfn32_check_arch - -#define TASK32_SIZE 0x7fff8000UL -#undef ELF_ET_DYN_BASE -#define ELF_ET_DYN_BASE (TASK32_SIZE / 3 * 2) - -#include -#include -#include -#include - -#define elf_prstatus elf_prstatus32 -struct elf_prstatus32 -{ - struct elf_siginfo pr_info; /* Info associated with signal */ - short pr_cursig; /* Current signal */ - unsigned int pr_sigpend; /* Set of pending signals */ - unsigned int pr_sighold; /* Set of held signals */ - pid_t pr_pid; - pid_t pr_ppid; - pid_t pr_pgrp; - pid_t pr_sid; - struct old_timeval32 pr_utime; /* User time */ - struct old_timeval32 pr_stime; /* System time */ - struct old_timeval32 pr_cutime;/* Cumulative user time */ - struct old_timeval32 pr_cstime;/* Cumulative system time */ - elf_gregset_t pr_reg; /* GP registers */ - int pr_fpvalid; /* True if math co-processor being used. */ -}; - -#define elf_prpsinfo elf_prpsinfo32 -struct elf_prpsinfo32 -{ - char pr_state; /* numeric process state */ - char pr_sname; /* char for pr_state */ - char pr_zomb; /* zombie */ - char pr_nice; /* nice val */ - unsigned int pr_flag; /* flags */ - __kernel_uid_t pr_uid; - __kernel_gid_t pr_gid; - pid_t pr_pid, pr_ppid, pr_pgrp, pr_sid; - /* Lots missing */ - char pr_fname[16]; /* filename of executable */ - char pr_psargs[ELF_PRARGSZ]; /* initial part of arg list */ -}; - -#define elf_caddr_t u32 -#define init_elf_binfmt init_elfn32_binfmt - -#define jiffies_to_timeval jiffies_to_old_timeval32 -static __inline__ void -jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value) -{ - /* - * Convert jiffies to nanoseconds and separate with - * one divide. - */ - u64 nsec = (u64)jiffies * TICK_NSEC; - u32 rem; - value->tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem); - value->tv_usec = rem / NSEC_PER_USEC; -} - -#define ELF_CORE_EFLAGS EF_MIPS_ABI2 - -#undef TASK_SIZE -#define TASK_SIZE TASK_SIZE32 - -#undef ns_to_kernel_old_timeval -#define ns_to_kernel_old_timeval ns_to_old_timeval32 - -/* - * Some data types as stored in coredump. - */ -#define user_long_t compat_long_t -#define user_siginfo_t compat_siginfo_t -#define copy_siginfo_to_external copy_siginfo_to_external32 - -#include "../../../fs/binfmt_elf.c" diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c deleted file mode 100644 index 7b2a23f48c1a..000000000000 --- a/arch/mips/kernel/binfmt_elfo32.c +++ /dev/null @@ -1,116 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Support for o32 Linux/MIPS ELF binaries. - * Author: Ralf Baechle (ralf@linux-mips.org) - * - * Copyright (C) 1999, 2001 Ralf Baechle - * Copyright (C) 1999, 2001 Silicon Graphics, Inc. - * - * Heavily inspired by the 32-bit Sparc compat code which is - * Copyright (C) 1995, 1996, 1997, 1998 David S. Miller (davem@redhat.com) - * Copyright (C) 1995, 1996, 1997, 1998 Jakub Jelinek (jj@ultra.linux.cz) - */ - -#define ELF_ARCH EM_MIPS -#define ELF_CLASS ELFCLASS32 -#ifdef __MIPSEB__ -#define ELF_DATA ELFDATA2MSB; -#else /* __MIPSEL__ */ -#define ELF_DATA ELFDATA2LSB; -#endif - -/* ELF register definitions */ -#define ELF_NGREG 45 -#define ELF_NFPREG 33 - -typedef unsigned int elf_greg_t; -typedef elf_greg_t elf_gregset_t[ELF_NGREG]; - -typedef double elf_fpreg_t; -typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG]; - -/* - * This is used to ensure we don't load something for the wrong architecture. - */ -#define elf_check_arch elfo32_check_arch - -#ifdef CONFIG_KVM_GUEST -#define TASK32_SIZE 0x3fff8000UL -#else -#define TASK32_SIZE 0x7fff8000UL -#endif -#undef ELF_ET_DYN_BASE -#define ELF_ET_DYN_BASE (TASK32_SIZE / 3 * 2) - -#include - -#include -#include -#include - -#define elf_prstatus elf_prstatus32 -struct elf_prstatus32 -{ - struct elf_siginfo pr_info; /* Info associated with signal */ - short pr_cursig; /* Current signal */ - unsigned int pr_sigpend; /* Set of pending signals */ - unsigned int pr_sighold; /* Set of held signals */ - pid_t pr_pid; - pid_t pr_ppid; - pid_t pr_pgrp; - pid_t pr_sid; - struct old_timeval32 pr_utime; /* User time */ - struct old_timeval32 pr_stime; /* System time */ - struct old_timeval32 pr_cutime;/* Cumulative user time */ - struct old_timeval32 pr_cstime;/* Cumulative system time */ - elf_gregset_t pr_reg; /* GP registers */ - int pr_fpvalid; /* True if math co-processor being used. */ -}; - -#define elf_prpsinfo elf_prpsinfo32 -struct elf_prpsinfo32 -{ - char pr_state; /* numeric process state */ - char pr_sname; /* char for pr_state */ - char pr_zomb; /* zombie */ - char pr_nice; /* nice val */ - unsigned int pr_flag; /* flags */ - __kernel_uid_t pr_uid; - __kernel_gid_t pr_gid; - pid_t pr_pid, pr_ppid, pr_pgrp, pr_sid; - /* Lots missing */ - char pr_fname[16]; /* filename of executable */ - char pr_psargs[ELF_PRARGSZ]; /* initial part of arg list */ -}; - -#define elf_caddr_t u32 -#define init_elf_binfmt init_elf32_binfmt - -#define jiffies_to_timeval jiffies_to_old_timeval32 -static inline void -jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value) -{ - /* - * Convert jiffies to nanoseconds and separate with - * one divide. - */ - u64 nsec = (u64)jiffies * TICK_NSEC; - u32 rem; - value->tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem); - value->tv_usec = rem / NSEC_PER_USEC; -} - -#undef TASK_SIZE -#define TASK_SIZE TASK_SIZE32 - -#undef ns_to_kernel_old_timeval -#define ns_to_kernel_old_timeval ns_to_old_timeval32 - -/* - * Some data types as stored in coredump. - */ -#define user_long_t compat_long_t -#define user_siginfo_t compat_siginfo_t -#define copy_siginfo_to_external copy_siginfo_to_external32 - -#include "../../../fs/binfmt_elf.c" diff --git a/arch/mips/kernel/scall64-n64.S b/arch/mips/kernel/scall64-n64.S index 23b2e2b1609c..5e9c497ce099 100644 --- a/arch/mips/kernel/scall64-n64.S +++ b/arch/mips/kernel/scall64-n64.S @@ -20,7 +20,7 @@ #include #include -#ifndef CONFIG_BINFMT_ELF32 +#ifndef CONFIG_MIPS32_COMPAT /* Neither O32 nor N32, so define handle_sys here */ #define handle_sys64 handle_sys #endif diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 278462186ac4..b09d6923f156 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -335,7 +335,6 @@ source "kernel/Kconfig.hz" config COMPAT def_bool y depends on 64BIT - select COMPAT_BINFMT_ELF if BINFMT_ELF config SYSVIPC_COMPAT def_bool y diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 107bb4319e0e..d26a89cd8908 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -282,7 +282,6 @@ config COMPAT bool "Enable support for 32bit binaries" depends on PPC64 default y if !CPU_LITTLE_ENDIAN - select COMPAT_BINFMT_ELF select ARCH_WANT_OLD_COMPAT_IPC select COMPAT_OLD_SIGACTION diff --git a/arch/powerpc/platforms/powernv/opal-core.c b/arch/powerpc/platforms/powernv/opal-core.c index 23571f0b555a..0d9ba70f7251 100644 --- a/arch/powerpc/platforms/powernv/opal-core.c +++ b/arch/powerpc/platforms/powernv/opal-core.c @@ -119,8 +119,8 @@ static void fill_prstatus(struct elf_prstatus *prstatus, int pir, * As a PIR value could also be '0', add an offset of '100' * to every PIR to avoid misinterpretations in GDB. */ - prstatus->pr_pid = cpu_to_be32(100 + pir); - prstatus->pr_ppid = cpu_to_be32(1); + prstatus->common.pr_pid = cpu_to_be32(100 + pir); + prstatus->common.pr_ppid = cpu_to_be32(1); /* * Indicate SIGUSR1 for crash initiated from kernel. @@ -130,7 +130,7 @@ static void fill_prstatus(struct elf_prstatus *prstatus, int pir, short sig; sig = kernel_initiated ? SIGUSR1 : SIGTERM; - prstatus->pr_cursig = cpu_to_be16(sig); + prstatus->common.pr_cursig = cpu_to_be16(sig); } } diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index c72874f09741..73483614b66b 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -426,7 +426,6 @@ config 64BIT config COMPAT def_bool y prompt "Kernel support for 31 bit emulation" - select COMPAT_BINFMT_ELF if BINFMT_ELF select ARCH_WANT_OLD_COMPAT_IPC select COMPAT_OLD_SIGACTION select HAVE_UID16 diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index 205b2e2648aa..0e36dfc9ccd6 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -365,7 +365,7 @@ static void *fill_cpu_elf_notes(void *ptr, int cpu, struct save_area *sa) memcpy(&nt_prstatus.pr_reg.gprs, sa->gprs, sizeof(sa->gprs)); memcpy(&nt_prstatus.pr_reg.psw, sa->psw, sizeof(sa->psw)); memcpy(&nt_prstatus.pr_reg.acrs, sa->acrs, sizeof(sa->acrs)); - nt_prstatus.pr_pid = cpu; + nt_prstatus.common.pr_pid = cpu; /* Prepare fpregset (floating point) note */ memset(&nt_fpregset, 0, sizeof(nt_fpregset)); memcpy(&nt_fpregset.fpc, &sa->fpc, sizeof(sa->fpc)); diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index c9c34dc52b7d..1a2b5649d267 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -494,7 +494,6 @@ config COMPAT bool depends on SPARC64 default y - select COMPAT_BINFMT_ELF select HAVE_UID16 select ARCH_WANT_OLD_COMPAT_IPC select COMPAT_OLD_SIGACTION diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 3d498caca1ea..31d94448b4e1 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -32,6 +32,7 @@ config X86_64 select MODULES_USE_ELF_RELA select NEED_DMA_MAP_STATE select SWIOTLB + select ARCH_HAS_ELFCORE_COMPAT config FORCE_DYNAMIC_FTRACE def_bool y @@ -2860,7 +2861,6 @@ config IA32_EMULATION depends on X86_64 select ARCH_WANT_OLD_COMPAT_IPC select BINFMT_ELF - select COMPAT_BINFMT_ELF select COMPAT_OLD_SIGACTION help Include code to run legacy 32-bit programs under a diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index f145e3326c6d..be09c7eac89f 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -159,17 +159,6 @@ struct compat_shmid64_ds { compat_ulong_t __unused5; }; -/* - * The type of struct elf_prstatus.pr_reg in compatible core dumps. - */ -typedef struct user_regs_struct compat_elf_gregset_t; - -/* Full regset -- prstatus on x32, otherwise on ia32 */ -#define PRSTATUS_SIZE(S, R) (R != sizeof(S.pr_reg) ? 144 : 296) -#define SET_PR_FPVALID(S, V, R) \ - do { *(int *) (((void *) &((S)->pr_reg)) + R) = (V); } \ - while (0) - #ifdef CONFIG_X86_X32_ABI #define COMPAT_USE_64BIT_TIME \ (!!(task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT)) diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 66bdfe838d61..9224d40cdefe 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -364,7 +364,7 @@ do { \ #define COMPAT_ARCH_DLINFO \ if (exec->e_machine == EM_X86_64) \ ARCH_DLINFO_X32; \ -else \ +else if (IS_ENABLED(CONFIG_IA32_EMULATION)) \ ARCH_DLINFO_IA32 #define COMPAT_ELF_ET_DYN_BASE (TASK_UNMAPPED_BASE + 0x1000000) diff --git a/arch/x86/include/asm/elfcore-compat.h b/arch/x86/include/asm/elfcore-compat.h new file mode 100644 index 000000000000..f1b6c7a8d8fc --- /dev/null +++ b/arch/x86/include/asm/elfcore-compat.h @@ -0,0 +1,31 @@ +#ifndef _ASM_X86_ELFCORE_COMPAT_H +#define _ASM_X86_ELFCORE_COMPAT_H + +#include + +/* + * On amd64 we have two 32bit ABIs - i386 and x32. The latter + * has bigger registers, so we use it for compat_elf_regset_t. + * The former uses i386_elf_prstatus and PRSTATUS_SIZE/SET_PR_FPVALID + * are used to choose the size and location of ->pr_fpvalid of + * the layout actually used. + */ +typedef struct user_regs_struct compat_elf_gregset_t; + +struct i386_elf_prstatus +{ + struct compat_elf_prstatus_common common; + struct user_regs_struct32 pr_reg; + compat_int_t pr_fpvalid; +}; + +#define PRSTATUS_SIZE \ + (user_64bit_mode(task_pt_regs(current)) \ + ? sizeof(struct compat_elf_prstatus) \ + : sizeof(struct i386_elf_prstatus)) +#define SET_PR_FPVALID(S) \ + (*(user_64bit_mode(task_pt_regs(current)) \ + ? &(S)->pr_fpvalid \ + : &((struct i386_elf_prstatus *)(S))->pr_fpvalid) = 1) + +#endif diff --git a/block/bio.c b/block/bio.c index 1f2cc1fbe283..2f21d2958b60 100644 --- a/block/bio.c +++ b/block/bio.c @@ -851,6 +851,39 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, } EXPORT_SYMBOL(bio_add_pc_page); +/** + * bio_add_zone_append_page - attempt to add page to zone-append bio + * @bio: destination bio + * @page: page to add + * @len: vec entry length + * @offset: vec entry offset + * + * Attempt to add a page to the bio_vec maplist of a bio that will be submitted + * for a zone-append request. This can fail for a number of reasons, such as the + * bio being full or the target block device is not a zoned block device or + * other limitations of the target block device. The target block device must + * allow bio's up to PAGE_SIZE, so it is always possible to add a single page + * to an empty bio. + * + * Returns: number of bytes added to the bio, or 0 in case of a failure. + */ +int bio_add_zone_append_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int offset) +{ + struct request_queue *q = bio->bi_disk->queue; + bool same_page = false; + + if (WARN_ON_ONCE(bio_op(bio) != REQ_OP_ZONE_APPEND)) + return 0; + + if (WARN_ON_ONCE(!blk_queue_is_zoned(q))) + return 0; + + return bio_add_hw_page(q, bio, page, len, offset, + queue_max_zone_append_sectors(q), &same_page); +} +EXPORT_SYMBOL_GPL(bio_add_zone_append_page); + /** * __bio_try_merge_page - try appending data to an existing bvec. * @bio: destination bio diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index ebcf534514be..fc06945d3f99 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -326,6 +326,23 @@ config ACPI_THERMAL To compile this driver as a module, choose M here: the module will be called thermal. +config ACPI_PLATFORM_PROFILE + tristate "ACPI Platform Profile Driver" + default m + help + This driver adds support for platform-profiles on platforms that + support it. + + Platform-profiles can be used to control the platform behaviour. For + example whether to operate in a lower power mode, in a higher + power performance mode or between the two. + + This driver provides the sysfs interface and is used as the registration + point for platform specific drivers. + + Which profiles are supported is determined on a per-platform basis and + should be obtained from the platform specific driver. + config ACPI_CUSTOM_DSDT_FILE string "Custom DSDT Table file to include" default "" diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index 076894a3330f..52b627c7f977 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -79,6 +79,7 @@ obj-$(CONFIG_ACPI_PCI_SLOT) += pci_slot.o obj-$(CONFIG_ACPI_PROCESSOR) += processor.o obj-$(CONFIG_ACPI) += container.o obj-$(CONFIG_ACPI_THERMAL) += thermal.o +obj-$(CONFIG_ACPI_PLATFORM_PROFILE) += platform_profile.o obj-$(CONFIG_ACPI_NFIT) += nfit/ obj-$(CONFIG_ACPI_NUMA) += numa/ obj-$(CONFIG_ACPI) += acpi_memhotplug.o diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c index 46a64e9fa716..b41180330cc1 100644 --- a/drivers/acpi/ac.c +++ b/drivers/acpi/ac.c @@ -6,6 +6,8 @@ * Copyright (C) 2001, 2002 Paul Diefenbaugh */ +#define pr_fmt(fmt) "ACPI: AC: " fmt + #include #include #include @@ -18,8 +20,6 @@ #include #include -#define PREFIX "ACPI: " - #define ACPI_AC_CLASS "ac_adapter" #define ACPI_AC_DEVICE_NAME "AC Adapter" #define ACPI_AC_FILE_STATE "state" @@ -28,9 +28,6 @@ #define ACPI_AC_STATUS_ONLINE 0x01 #define ACPI_AC_STATUS_UNKNOWN 0xFF -#define _COMPONENT ACPI_AC_COMPONENT -ACPI_MODULE_NAME("ac"); - MODULE_AUTHOR("Paul Diefenbaugh"); MODULE_DESCRIPTION("ACPI AC Adapter Driver"); MODULE_LICENSE("GPL"); @@ -102,8 +99,9 @@ static int acpi_ac_get_state(struct acpi_ac *ac) status = acpi_evaluate_integer(ac->device->handle, "_PSR", NULL, &ac->state); if (ACPI_FAILURE(status)) { - ACPI_EXCEPTION((AE_INFO, status, - "Error reading AC Adapter state")); + acpi_handle_info(ac->device->handle, + "Error reading AC Adapter state: %s\n", + acpi_format_exception(status)); ac->state = ACPI_AC_STATUS_UNKNOWN; return -ENODEV; } @@ -153,8 +151,8 @@ static void acpi_ac_notify(struct acpi_device *device, u32 event) switch (event) { default: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Unsupported event [0x%x]\n", event)); + acpi_handle_debug(device->handle, "Unsupported event [0x%x]\n", + event); fallthrough; case ACPI_AC_NOTIFY_STATUS: case ACPI_NOTIFY_BUS_CHECK: @@ -278,9 +276,8 @@ static int acpi_ac_add(struct acpi_device *device) goto end; } - printk(KERN_INFO PREFIX "%s [%s] (%s)\n", - acpi_device_name(device), acpi_device_bid(device), - ac->state ? "on-line" : "off-line"); + pr_info("%s [%s] (%s)\n", acpi_device_name(device), + acpi_device_bid(device), ac->state ? "on-line" : "off-line"); ac->battery_nb.notifier_call = acpi_ac_battery_notify; register_acpi_notifier(&ac->battery_nb); @@ -348,7 +345,7 @@ static int __init acpi_ac_init(void) for (i = 0; i < ARRAY_SIZE(acpi_ac_blacklist); i++) if (acpi_dev_present(acpi_ac_blacklist[i].hid, "1", acpi_ac_blacklist[i].hrv)) { - pr_info(PREFIX "AC: found native %s PMIC, not loading\n", + pr_info("found native %s PMIC, not loading\n", acpi_ac_blacklist[i].hid); return -ENODEV; } diff --git a/drivers/acpi/acpi_configfs.c b/drivers/acpi/acpi_configfs.c index cf91f49101ea..3a14859dbb75 100644 --- a/drivers/acpi/acpi_configfs.c +++ b/drivers/acpi/acpi_configfs.c @@ -268,7 +268,12 @@ static int __init acpi_configfs_init(void) acpi_table_group = configfs_register_default_group(root, "table", &acpi_tables_type); - return PTR_ERR_OR_ZERO(acpi_table_group); + if (IS_ERR(acpi_table_group)) { + configfs_unregister_subsystem(&acpi_configfs); + return PTR_ERR(acpi_table_group); + } + + return 0; } module_init(acpi_configfs_init); diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c index b8745ce48a47..b84ab722feb4 100644 --- a/drivers/acpi/acpi_pad.c +++ b/drivers/acpi/acpi_pad.c @@ -261,7 +261,7 @@ static uint32_t acpi_pad_idle_cpus_num(void) return ps_tsk_num; } -static ssize_t acpi_pad_rrtime_store(struct device *dev, +static ssize_t rrtime_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { unsigned long num; @@ -275,16 +275,14 @@ static ssize_t acpi_pad_rrtime_store(struct device *dev, return count; } -static ssize_t acpi_pad_rrtime_show(struct device *dev, +static ssize_t rrtime_show(struct device *dev, struct device_attribute *attr, char *buf) { return scnprintf(buf, PAGE_SIZE, "%d\n", round_robin_time); } -static DEVICE_ATTR(rrtime, S_IRUGO|S_IWUSR, - acpi_pad_rrtime_show, - acpi_pad_rrtime_store); +static DEVICE_ATTR_RW(rrtime); -static ssize_t acpi_pad_idlepct_store(struct device *dev, +static ssize_t idlepct_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { unsigned long num; @@ -298,16 +296,14 @@ static ssize_t acpi_pad_idlepct_store(struct device *dev, return count; } -static ssize_t acpi_pad_idlepct_show(struct device *dev, +static ssize_t idlepct_show(struct device *dev, struct device_attribute *attr, char *buf) { return scnprintf(buf, PAGE_SIZE, "%d\n", idle_pct); } -static DEVICE_ATTR(idlepct, S_IRUGO|S_IWUSR, - acpi_pad_idlepct_show, - acpi_pad_idlepct_store); +static DEVICE_ATTR_RW(idlepct); -static ssize_t acpi_pad_idlecpus_store(struct device *dev, +static ssize_t idlecpus_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { unsigned long num; @@ -319,16 +315,14 @@ static ssize_t acpi_pad_idlecpus_store(struct device *dev, return count; } -static ssize_t acpi_pad_idlecpus_show(struct device *dev, +static ssize_t idlecpus_show(struct device *dev, struct device_attribute *attr, char *buf) { return cpumap_print_to_pagebuf(false, buf, to_cpumask(pad_busy_cpus_bits)); } -static DEVICE_ATTR(idlecpus, S_IRUGO|S_IWUSR, - acpi_pad_idlecpus_show, - acpi_pad_idlecpus_store); +static DEVICE_ATTR_RW(idlecpus); static int acpi_pad_add_sysfs(struct acpi_device *device) { diff --git a/drivers/acpi/acpi_tad.c b/drivers/acpi/acpi_tad.c index 7d45cce0c3c1..e9b8e8305e23 100644 --- a/drivers/acpi/acpi_tad.c +++ b/drivers/acpi/acpi_tad.c @@ -237,7 +237,7 @@ static ssize_t time_show(struct device *dev, struct device_attribute *attr, rt.tz, rt.daylight); } -static DEVICE_ATTR(time, S_IRUSR | S_IWUSR, time_show, time_store); +static DEVICE_ATTR_RW(time); static struct attribute *acpi_tad_time_attrs[] = { &dev_attr_time.attr, @@ -446,7 +446,7 @@ static ssize_t ac_alarm_show(struct device *dev, struct device_attribute *attr, return acpi_tad_alarm_read(dev, buf, ACPI_TAD_AC_TIMER); } -static DEVICE_ATTR(ac_alarm, S_IRUSR | S_IWUSR, ac_alarm_show, ac_alarm_store); +static DEVICE_ATTR_RW(ac_alarm); static ssize_t ac_policy_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) @@ -462,7 +462,7 @@ static ssize_t ac_policy_show(struct device *dev, struct device_attribute *attr, return acpi_tad_policy_read(dev, buf, ACPI_TAD_AC_TIMER); } -static DEVICE_ATTR(ac_policy, S_IRUSR | S_IWUSR, ac_policy_show, ac_policy_store); +static DEVICE_ATTR_RW(ac_policy); static ssize_t ac_status_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) @@ -478,7 +478,7 @@ static ssize_t ac_status_show(struct device *dev, struct device_attribute *attr, return acpi_tad_status_read(dev, buf, ACPI_TAD_AC_TIMER); } -static DEVICE_ATTR(ac_status, S_IRUSR | S_IWUSR, ac_status_show, ac_status_store); +static DEVICE_ATTR_RW(ac_status); static struct attribute *acpi_tad_attrs[] = { &dev_attr_caps.attr, @@ -505,7 +505,7 @@ static ssize_t dc_alarm_show(struct device *dev, struct device_attribute *attr, return acpi_tad_alarm_read(dev, buf, ACPI_TAD_DC_TIMER); } -static DEVICE_ATTR(dc_alarm, S_IRUSR | S_IWUSR, dc_alarm_show, dc_alarm_store); +static DEVICE_ATTR_RW(dc_alarm); static ssize_t dc_policy_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) @@ -521,7 +521,7 @@ static ssize_t dc_policy_show(struct device *dev, struct device_attribute *attr, return acpi_tad_policy_read(dev, buf, ACPI_TAD_DC_TIMER); } -static DEVICE_ATTR(dc_policy, S_IRUSR | S_IWUSR, dc_policy_show, dc_policy_store); +static DEVICE_ATTR_RW(dc_policy); static ssize_t dc_status_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) @@ -537,7 +537,7 @@ static ssize_t dc_status_show(struct device *dev, struct device_attribute *attr, return acpi_tad_status_read(dev, buf, ACPI_TAD_DC_TIMER); } -static DEVICE_ATTR(dc_status, S_IRUSR | S_IWUSR, dc_status_show, dc_status_store); +static DEVICE_ATTR_RW(dc_status); static struct attribute *acpi_tad_dc_attrs[] = { &dev_attr_dc_alarm.attr, diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index a322a7bd286b..2ea1781290cc 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -7,6 +7,8 @@ * Copyright (C) 2006 Thomas Tuttle */ +#define pr_fmt(fmt) "ACPI: video: " fmt + #include #include #include @@ -26,16 +28,11 @@ #include #include -#define PREFIX "ACPI: " - #define ACPI_VIDEO_BUS_NAME "Video Bus" #define ACPI_VIDEO_DEVICE_NAME "Video Device" #define MAX_NAME_LEN 20 -#define _COMPONENT ACPI_VIDEO_COMPONENT -ACPI_MODULE_NAME("video"); - MODULE_AUTHOR("Bruno Ducrot"); MODULE_DESCRIPTION("ACPI Video Driver"); MODULE_LICENSE("GPL"); @@ -326,11 +323,11 @@ acpi_video_device_lcd_query_levels(acpi_handle handle, *levels = NULL; status = acpi_evaluate_object(handle, "_BCL", NULL, &buffer); - if (!ACPI_SUCCESS(status)) + if (ACPI_FAILURE(status)) return status; obj = (union acpi_object *)buffer.pointer; if (!obj || (obj->type != ACPI_TYPE_PACKAGE)) { - printk(KERN_ERR PREFIX "Invalid _BCL data\n"); + acpi_handle_info(handle, "Invalid _BCL data\n"); status = -EFAULT; goto err; } @@ -354,7 +351,7 @@ acpi_video_device_lcd_set_level(struct acpi_video_device *device, int level) status = acpi_execute_simple_method(device->dev->handle, "_BCM", level); if (ACPI_FAILURE(status)) { - ACPI_ERROR((AE_INFO, "Evaluating _BCM failed")); + acpi_handle_info(device->dev->handle, "_BCM evaluation failed\n"); return -EIO; } @@ -368,7 +365,7 @@ acpi_video_device_lcd_set_level(struct acpi_video_device *device, int level) return 0; } - ACPI_ERROR((AE_INFO, "Current brightness invalid")); + acpi_handle_info(device->dev->handle, "Current brightness invalid\n"); return -EINVAL; } @@ -622,9 +619,8 @@ acpi_video_device_lcd_get_level_current(struct acpi_video_device *device, * BQC returned an invalid level. * Stop using it. */ - ACPI_WARNING((AE_INFO, - "%s returned an invalid level", - buf)); + acpi_handle_info(device->dev->handle, + "%s returned an invalid level", buf); device->cap._BQC = device->cap._BCQ = 0; } else { /* @@ -635,7 +631,8 @@ acpi_video_device_lcd_get_level_current(struct acpi_video_device *device, * ACPI video backlight still works w/ buggy _BQC. * http://bugzilla.kernel.org/show_bug.cgi?id=12233 */ - ACPI_WARNING((AE_INFO, "Evaluating %s failed", buf)); + acpi_handle_info(device->dev->handle, + "%s evaluation failed", buf); device->cap._BQC = device->cap._BCQ = 0; } } @@ -675,7 +672,7 @@ acpi_video_device_EDID(struct acpi_video_device *device, if (obj && obj->type == ACPI_TYPE_BUFFER) *edid = obj; else { - printk(KERN_ERR PREFIX "Invalid _DDC data\n"); + acpi_handle_info(device->dev->handle, "Invalid _DDC data\n"); status = -EFAULT; kfree(obj); } @@ -827,10 +824,9 @@ int acpi_video_get_levels(struct acpi_device *device, int result = 0; u32 value; - if (!ACPI_SUCCESS(acpi_video_device_lcd_query_levels(device->handle, - &obj))) { - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Could not query available " - "LCD brightness level\n")); + if (ACPI_FAILURE(acpi_video_device_lcd_query_levels(device->handle, &obj))) { + acpi_handle_debug(device->handle, + "Could not query available LCD brightness level\n"); result = -ENODEV; goto out; } @@ -842,7 +838,6 @@ int acpi_video_get_levels(struct acpi_device *device, br = kzalloc(sizeof(*br), GFP_KERNEL); if (!br) { - printk(KERN_ERR "can't allocate memory\n"); result = -ENOMEM; goto out; } @@ -863,7 +858,7 @@ int acpi_video_get_levels(struct acpi_device *device, for (i = 0; i < obj->package.count; i++) { o = (union acpi_object *)&obj->package.elements[i]; if (o->type != ACPI_TYPE_INTEGER) { - printk(KERN_ERR PREFIX "Invalid data\n"); + acpi_handle_info(device->handle, "Invalid data\n"); continue; } value = (u32) o->integer.value; @@ -900,7 +895,8 @@ int acpi_video_get_levels(struct acpi_device *device, br->levels[i] = br->levels[i - level_ac_battery]; count += level_ac_battery; } else if (level_ac_battery > ACPI_VIDEO_FIRST_LEVEL) - ACPI_ERROR((AE_INFO, "Too many duplicates in _BCL package")); + acpi_handle_info(device->handle, + "Too many duplicates in _BCL package"); /* Check if the _BCL package is in a reversed order */ if (max_level == br->levels[ACPI_VIDEO_FIRST_LEVEL]) { @@ -910,8 +906,8 @@ int acpi_video_get_levels(struct acpi_device *device, sizeof(br->levels[ACPI_VIDEO_FIRST_LEVEL]), acpi_video_cmp_level, NULL); } else if (max_level != br->levels[count - 1]) - ACPI_ERROR((AE_INFO, - "Found unordered _BCL package")); + acpi_handle_info(device->handle, + "Found unordered _BCL package"); br->count = count; *dev_br = br; @@ -989,9 +985,9 @@ set_level: if (result) goto out_free_levels; - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "found %d brightness levels\n", - br->count - ACPI_VIDEO_FIRST_LEVEL)); + acpi_handle_debug(device->dev->handle, "found %d brightness levels\n", + br->count - ACPI_VIDEO_FIRST_LEVEL); + return 0; out_free_levels: @@ -1023,7 +1019,8 @@ static void acpi_video_device_find_cap(struct acpi_video_device *device) if (acpi_has_method(device->dev->handle, "_BQC")) { device->cap._BQC = 1; } else if (acpi_has_method(device->dev->handle, "_BCQ")) { - printk(KERN_WARNING FW_BUG "_BCQ is used instead of _BQC\n"); + acpi_handle_info(device->dev->handle, + "_BCQ is used instead of _BQC\n"); device->cap._BCQ = 1; } @@ -1083,8 +1080,7 @@ static int acpi_video_bus_check(struct acpi_video_bus *video) /* Does this device support video switching? */ if (video->cap._DOS || video->cap._DOD) { if (!video->cap._DOS) { - printk(KERN_WARNING FW_BUG - "ACPI(%s) defines _DOD but not _DOS\n", + pr_info(FW_BUG "ACPI(%s) defines _DOD but not _DOS\n", acpi_device_bid(video->device)); } video->flags.multihead = 1; @@ -1272,7 +1268,8 @@ acpi_video_device_bind(struct acpi_video_bus *video, ids = &video->attached_array[i]; if (device->device_id == (ids->value.int_val & 0xffff)) { ids->bind_info = device; - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "device_bind %d\n", i)); + acpi_handle_debug(video->device->handle, "%s: %d\n", + __func__, i); } } } @@ -1324,20 +1321,22 @@ static int acpi_video_device_enumerate(struct acpi_video_bus *video) return AE_NOT_EXIST; status = acpi_evaluate_object(video->device->handle, "_DOD", NULL, &buffer); - if (!ACPI_SUCCESS(status)) { - ACPI_EXCEPTION((AE_INFO, status, "Evaluating _DOD")); + if (ACPI_FAILURE(status)) { + acpi_handle_info(video->device->handle, + "_DOD evaluation failed: %s\n", + acpi_format_exception(status)); return status; } dod = buffer.pointer; if (!dod || (dod->type != ACPI_TYPE_PACKAGE)) { - ACPI_EXCEPTION((AE_INFO, status, "Invalid _DOD data")); + acpi_handle_info(video->device->handle, "Invalid _DOD data\n"); status = -EFAULT; goto out; } - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found %d video heads in _DOD\n", - dod->package.count)); + acpi_handle_debug(video->device->handle, "Found %d video heads in _DOD\n", + dod->package.count); active_list = kcalloc(1 + dod->package.count, sizeof(struct acpi_video_enumerated_device), @@ -1352,15 +1351,18 @@ static int acpi_video_device_enumerate(struct acpi_video_bus *video) obj = &dod->package.elements[i]; if (obj->type != ACPI_TYPE_INTEGER) { - printk(KERN_ERR PREFIX - "Invalid _DOD data in element %d\n", i); + acpi_handle_info(video->device->handle, + "Invalid _DOD data in element %d\n", i); continue; } active_list[count].value.int_val = obj->integer.value; active_list[count].bind_info = NULL; - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "dod element[%d] = %d\n", i, - (int)obj->integer.value)); + + acpi_handle_debug(video->device->handle, + "_DOD element[%d] = %d\n", i, + (int)obj->integer.value); + count++; } @@ -1451,7 +1453,8 @@ acpi_video_switch_brightness(struct work_struct *work) out: if (result) - printk(KERN_ERR PREFIX "Failed to switch the brightness\n"); + acpi_handle_info(device->dev->handle, + "Failed to switch brightness\n"); } int acpi_video_get_edid(struct acpi_device *device, int type, int device_id, @@ -1601,8 +1604,8 @@ static void acpi_video_bus_notify(struct acpi_device *device, u32 event) break; default: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Unsupported event [0x%x]\n", event)); + acpi_handle_debug(device->handle, "Unsupported event [0x%x]\n", + event); break; } @@ -1675,8 +1678,7 @@ static void acpi_video_device_notify(acpi_handle handle, u32 event, void *data) keycode = KEY_DISPLAY_OFF; break; default: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Unsupported event [0x%x]\n", event)); + acpi_handle_debug(handle, "Unsupported event [0x%x]\n", event); break; } @@ -1812,11 +1814,12 @@ static void acpi_video_dev_register_backlight(struct acpi_video_device *device) &device->cooling_dev->device.kobj, "thermal_cooling"); if (result) - printk(KERN_ERR PREFIX "Create sysfs link\n"); + pr_info("sysfs link creation failed\n"); + result = sysfs_create_link(&device->cooling_dev->device.kobj, &device->dev->dev.kobj, "device"); if (result) - printk(KERN_ERR PREFIX "Create sysfs link\n"); + pr_info("Reverse sysfs link creation failed\n"); } static void acpi_video_run_bcl_for_osi(struct acpi_video_bus *video) @@ -2030,7 +2033,7 @@ static int acpi_video_bus_add(struct acpi_device *device) acpi_video_bus_match, NULL, device, NULL); if (status == AE_ALREADY_EXISTS) { - printk(KERN_WARNING FW_BUG + pr_info(FW_BUG "Duplicate ACPI video bus devices for the" " same VGA controller, please try module " "parameter \"video.allow_duplicates=1\"" @@ -2073,7 +2076,7 @@ static int acpi_video_bus_add(struct acpi_device *device) if (error) goto err_put_video; - printk(KERN_INFO PREFIX "%s [%s] (multi-head: %s rom: %s post: %s)\n", + pr_info("%s [%s] (multi-head: %s rom: %s post: %s)\n", ACPI_VIDEO_DEVICE_NAME, acpi_device_bid(device), video->flags.multihead ? "yes" : "no", video->flags.rom ? "yes" : "no", diff --git a/drivers/acpi/acpica/acapps.h b/drivers/acpi/acpica/acapps.h index 173447d50acf..725e2f65cdca 100644 --- a/drivers/acpi/acpica/acapps.h +++ b/drivers/acpi/acpica/acapps.h @@ -3,7 +3,7 @@ * * Module Name: acapps - common include for ACPI applications/tools * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ @@ -17,7 +17,7 @@ /* Common info for tool signons */ #define ACPICA_NAME "Intel ACPI Component Architecture" -#define ACPICA_COPYRIGHT "Copyright (c) 2000 - 2020 Intel Corporation" +#define ACPICA_COPYRIGHT "Copyright (c) 2000 - 2021 Intel Corporation" #if ACPI_MACHINE_WIDTH == 64 #define ACPI_WIDTH " (64-bit version)" diff --git a/drivers/acpi/acpica/accommon.h b/drivers/acpi/acpica/accommon.h index 94e18bb76556..be3826f46f88 100644 --- a/drivers/acpi/acpica/accommon.h +++ b/drivers/acpi/acpica/accommon.h @@ -3,7 +3,7 @@ * * Name: accommon.h - Common include files for generation of ACPICA source * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acconvert.h b/drivers/acpi/acpica/acconvert.h index cf85d66da6e7..53b41c7a6119 100644 --- a/drivers/acpi/acpica/acconvert.h +++ b/drivers/acpi/acpica/acconvert.h @@ -3,7 +3,7 @@ * * Module Name: acapps - common include for ACPI applications/tools * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acdebug.h b/drivers/acpi/acpica/acdebug.h index f8a3abdfe250..3ccc7b2a76f1 100644 --- a/drivers/acpi/acpica/acdebug.h +++ b/drivers/acpi/acpica/acdebug.h @@ -3,7 +3,7 @@ * * Name: acdebug.h - ACPI/AML debugger * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acdispat.h b/drivers/acpi/acpica/acdispat.h index 7ba6e308f146..3170a24fe505 100644 --- a/drivers/acpi/acpica/acdispat.h +++ b/drivers/acpi/acpica/acdispat.h @@ -3,7 +3,7 @@ * * Name: acdispat.h - dispatcher (parser to interpreter interface) * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h index 79f292687bd6..82a75964343b 100644 --- a/drivers/acpi/acpica/acevents.h +++ b/drivers/acpi/acpica/acevents.h @@ -3,7 +3,7 @@ * * Name: acevents.h - Event subcomponent prototypes and defines * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h index 2fee91f57b21..d41b810e367c 100644 --- a/drivers/acpi/acpica/acglobal.h +++ b/drivers/acpi/acpica/acglobal.h @@ -3,7 +3,7 @@ * * Name: acglobal.h - Declarations for global variables * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/achware.h b/drivers/acpi/acpica/achware.h index 6ab92e28330d..810de0b4c125 100644 --- a/drivers/acpi/acpica/achware.h +++ b/drivers/acpi/acpica/achware.h @@ -3,7 +3,7 @@ * * Name: achware.h -- hardware specific interfaces * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acinterp.h b/drivers/acpi/acpica/acinterp.h index a6d896cda2a5..816a16e1fc4c 100644 --- a/drivers/acpi/acpica/acinterp.h +++ b/drivers/acpi/acpica/acinterp.h @@ -3,7 +3,7 @@ * * Name: acinterp.h - Interpreter subcomponent prototypes and defines * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h index f83b98fa13ac..be57436182a1 100644 --- a/drivers/acpi/acpica/aclocal.h +++ b/drivers/acpi/acpica/aclocal.h @@ -3,7 +3,7 @@ * * Name: aclocal.h - Internal data types used across the ACPI subsystem * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acmacros.h b/drivers/acpi/acpica/acmacros.h index 168904ba3086..93bd2d19c156 100644 --- a/drivers/acpi/acpica/acmacros.h +++ b/drivers/acpi/acpica/acmacros.h @@ -3,7 +3,7 @@ * * Name: acmacros.h - C macros for the entire subsystem. * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acnamesp.h b/drivers/acpi/acpica/acnamesp.h index 40f6a3c33a15..199aabac3790 100644 --- a/drivers/acpi/acpica/acnamesp.h +++ b/drivers/acpi/acpica/acnamesp.h @@ -3,7 +3,7 @@ * * Name: acnamesp.h - Namespace subcomponent prototypes and defines * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acobject.h b/drivers/acpi/acpica/acobject.h index 9f0219a8cb98..af47a3ffd2a4 100644 --- a/drivers/acpi/acpica/acobject.h +++ b/drivers/acpi/acpica/acobject.h @@ -3,7 +3,7 @@ * * Name: acobject.h - Definition of union acpi_operand_object (Internal object only) * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acopcode.h b/drivers/acpi/acpica/acopcode.h index 8825394be9ab..c3f12ee9fc6f 100644 --- a/drivers/acpi/acpica/acopcode.h +++ b/drivers/acpi/acpica/acopcode.h @@ -3,7 +3,7 @@ * * Name: acopcode.h - AML opcode information for the AML parser and interpreter * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acparser.h b/drivers/acpi/acpica/acparser.h index bc00b85c0a8f..8e40e5909458 100644 --- a/drivers/acpi/acpica/acparser.h +++ b/drivers/acpi/acpica/acparser.h @@ -3,7 +3,7 @@ * * Module Name: acparser.h - AML Parser subcomponent prototypes and defines * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acpredef.h b/drivers/acpi/acpica/acpredef.h index 57ea2276790f..15cf904f0751 100644 --- a/drivers/acpi/acpica/acpredef.h +++ b/drivers/acpi/acpica/acpredef.h @@ -3,7 +3,7 @@ * * Name: acpredef - Information table for ACPI predefined methods and objects * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acresrc.h b/drivers/acpi/acpica/acresrc.h index 6de8a1650d3d..0cb975a3e01d 100644 --- a/drivers/acpi/acpica/acresrc.h +++ b/drivers/acpi/acpica/acresrc.h @@ -3,7 +3,7 @@ * * Name: acresrc.h - Resource Manager function prototypes * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acstruct.h b/drivers/acpi/acpica/acstruct.h index 4c900c108f3f..e3beb096c46d 100644 --- a/drivers/acpi/acpica/acstruct.h +++ b/drivers/acpi/acpica/acstruct.h @@ -3,7 +3,7 @@ * * Name: acstruct.h - Internal structs * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/actables.h b/drivers/acpi/acpica/actables.h index 734624facda3..e2d0046799a2 100644 --- a/drivers/acpi/acpica/actables.h +++ b/drivers/acpi/acpica/actables.h @@ -3,7 +3,7 @@ * * Name: actables.h - ACPI table management * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/acutils.h b/drivers/acpi/acpica/acutils.h index 7c89b470ec81..be6de7149e67 100644 --- a/drivers/acpi/acpica/acutils.h +++ b/drivers/acpi/acpica/acutils.h @@ -3,7 +3,7 @@ * * Name: acutils.h -- prototypes for the common (subsystem-wide) procedures * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/amlcode.h b/drivers/acpi/acpica/amlcode.h index 1d541bbac4a3..d6b088c5001f 100644 --- a/drivers/acpi/acpica/amlcode.h +++ b/drivers/acpi/acpica/amlcode.h @@ -5,7 +5,7 @@ * Declarations and definitions contained herein are derived * directly from the ACPI specification. * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/amlresrc.h b/drivers/acpi/acpica/amlresrc.h index e5234e001acf..a9d91a3c2994 100644 --- a/drivers/acpi/acpica/amlresrc.h +++ b/drivers/acpi/acpica/amlresrc.h @@ -3,7 +3,7 @@ * * Module Name: amlresrc.h - AML resource descriptors * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dbhistry.c b/drivers/acpi/acpica/dbhistry.c index f5fba14461a6..fd813c5d3952 100644 --- a/drivers/acpi/acpica/dbhistry.c +++ b/drivers/acpi/acpica/dbhistry.c @@ -3,7 +3,7 @@ * * Module Name: dbhistry - debugger HISTORY command * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dbinput.c b/drivers/acpi/acpica/dbinput.c index 2952856b8a67..b8a48923064f 100644 --- a/drivers/acpi/acpica/dbinput.c +++ b/drivers/acpi/acpica/dbinput.c @@ -473,7 +473,7 @@ char *acpi_db_get_next_token(char *string, /* Remove any spaces at the beginning, ignore blank lines */ - while (*string && isspace(*string)) { + while (*string && isspace((int)*string)) { string++; } @@ -571,7 +571,7 @@ char *acpi_db_get_next_token(char *string, /* Find end of token */ - while (*string && !isspace(*string)) { + while (*string && !isspace((int)*string)) { string++; } break; diff --git a/drivers/acpi/acpica/dbobject.c b/drivers/acpi/acpica/dbobject.c index 4b4c530a0654..95ab91b35f29 100644 --- a/drivers/acpi/acpica/dbobject.c +++ b/drivers/acpi/acpica/dbobject.c @@ -47,7 +47,7 @@ acpi_db_dump_method_info(acpi_status status, struct acpi_walk_state *walk_state) /* Ignore control codes, they are not errors */ - if ((status & AE_CODE_MASK) == AE_CODE_CONTROL) { + if (ACPI_CNTL_EXCEPTION(status)) { return; } diff --git a/drivers/acpi/acpica/dsargs.c b/drivers/acpi/acpica/dsargs.c index ad17f62e51d9..6630d6536fb0 100644 --- a/drivers/acpi/acpica/dsargs.c +++ b/drivers/acpi/acpica/dsargs.c @@ -4,7 +4,7 @@ * Module Name: dsargs - Support for execution of dynamic arguments for static * objects (regions, fields, buffer fields, etc.) * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dscontrol.c b/drivers/acpi/acpica/dscontrol.c index 4b5b6e859f62..a152f03135cd 100644 --- a/drivers/acpi/acpica/dscontrol.c +++ b/drivers/acpi/acpica/dscontrol.c @@ -4,7 +4,7 @@ * Module Name: dscontrol - Support for execution control opcodes - * if/else/while/return * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ @@ -62,7 +62,7 @@ acpi_ds_exec_begin_control_op(struct acpi_walk_state *walk_state, } } - /*lint -fallthrough */ + ACPI_FALLTHROUGH; case AML_IF_OP: /* diff --git a/drivers/acpi/acpica/dsdebug.c b/drivers/acpi/acpica/dsdebug.c index 63bc5f19fb82..b9b03d629930 100644 --- a/drivers/acpi/acpica/dsdebug.c +++ b/drivers/acpi/acpica/dsdebug.c @@ -3,7 +3,7 @@ * * Module Name: dsdebug - Parser/Interpreter interface - debugging * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ @@ -100,7 +100,7 @@ acpi_ds_dump_method_stack(acpi_status status, /* Ignore control codes, they are not errors */ - if ((status & AE_CODE_MASK) == AE_CODE_CONTROL) { + if (ACPI_CNTL_EXCEPTION(status)) { return_VOID; } diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c index fa768b3a989e..a16817767969 100644 --- a/drivers/acpi/acpica/dsfield.c +++ b/drivers/acpi/acpica/dsfield.c @@ -3,7 +3,7 @@ * * Module Name: dsfield - Dispatcher field routines * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dsinit.c b/drivers/acpi/acpica/dsinit.c index 9be2a309424c..ba6f882e83bc 100644 --- a/drivers/acpi/acpica/dsinit.c +++ b/drivers/acpi/acpica/dsinit.c @@ -3,7 +3,7 @@ * * Module Name: dsinit - Object initialization namespace walk * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c index cf67caff878a..8e011e59b9b4 100644 --- a/drivers/acpi/acpica/dsmethod.c +++ b/drivers/acpi/acpica/dsmethod.c @@ -3,7 +3,7 @@ * * Module Name: dsmethod - Parser/Interpreter interface - control method parsing * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dsobject.c b/drivers/acpi/acpica/dsobject.c index c0a14a6a2c20..3c0c31157e7e 100644 --- a/drivers/acpi/acpica/dsobject.c +++ b/drivers/acpi/acpica/dsobject.c @@ -3,7 +3,7 @@ * * Module Name: dsobject - Dispatcher object management routines * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dsopcode.c b/drivers/acpi/acpica/dsopcode.c index d9c26e720cb7..639635291ab7 100644 --- a/drivers/acpi/acpica/dsopcode.c +++ b/drivers/acpi/acpica/dsopcode.c @@ -3,7 +3,7 @@ * * Module Name: dsopcode - Dispatcher support for regions and fields * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dspkginit.c b/drivers/acpi/acpica/dspkginit.c index d869568d55c2..e642d65bcc66 100644 --- a/drivers/acpi/acpica/dspkginit.c +++ b/drivers/acpi/acpica/dspkginit.c @@ -3,7 +3,7 @@ * * Module Name: dspkginit - Completion of deferred package initialization * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dswexec.c b/drivers/acpi/acpica/dswexec.c index 1d4f8c81028c..41ba7773fd10 100644 --- a/drivers/acpi/acpica/dswexec.c +++ b/drivers/acpi/acpica/dswexec.c @@ -4,7 +4,7 @@ * Module Name: dswexec - Dispatcher method execution callbacks; * dispatch to interpreter. * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ @@ -598,8 +598,7 @@ acpi_status acpi_ds_exec_end_op(struct acpi_walk_state *walk_state) break; } - /* Fall through */ - /*lint -fallthrough */ + ACPI_FALLTHROUGH; case AML_INT_EVAL_SUBTREE_OP: diff --git a/drivers/acpi/acpica/dswload.c b/drivers/acpi/acpica/dswload.c index 27069325b6de..a377638e44f9 100644 --- a/drivers/acpi/acpica/dswload.c +++ b/drivers/acpi/acpica/dswload.c @@ -3,7 +3,7 @@ * * Module Name: dswload - Dispatcher first pass namespace load callbacks * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ @@ -224,7 +224,7 @@ acpi_ds_load1_begin_op(struct acpi_walk_state *walk_state, break; } - /*lint -fallthrough */ + ACPI_FALLTHROUGH; default: diff --git a/drivers/acpi/acpica/dswload2.c b/drivers/acpi/acpica/dswload2.c index edadbe146506..3625952c3957 100644 --- a/drivers/acpi/acpica/dswload2.c +++ b/drivers/acpi/acpica/dswload2.c @@ -3,7 +3,7 @@ * * Module Name: dswload2 - Dispatcher second pass namespace load callbacks * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ @@ -214,7 +214,7 @@ acpi_ds_load2_begin_op(struct acpi_walk_state *walk_state, break; } - /*lint -fallthrough */ + ACPI_FALLTHROUGH; default: diff --git a/drivers/acpi/acpica/dswscope.c b/drivers/acpi/acpica/dswscope.c index 9c397642fed7..9c123af08bc1 100644 --- a/drivers/acpi/acpica/dswscope.c +++ b/drivers/acpi/acpica/dswscope.c @@ -3,7 +3,7 @@ * * Module Name: dswscope - Scope stack manipulation * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/dswstate.c b/drivers/acpi/acpica/dswstate.c index 809a0c0536b5..fbe2ba05c82a 100644 --- a/drivers/acpi/acpica/dswstate.c +++ b/drivers/acpi/acpica/dswstate.c @@ -3,7 +3,7 @@ * * Module Name: dswstate - Dispatcher parse tree walk management routines * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evevent.c b/drivers/acpi/acpica/evevent.c index 9efca54c51ac..35385148fedb 100644 --- a/drivers/acpi/acpica/evevent.c +++ b/drivers/acpi/acpica/evevent.c @@ -3,7 +3,7 @@ * * Module Name: evevent - Fixed Event handling and dispatch * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evglock.c b/drivers/acpi/acpica/evglock.c index 0ced84ae13e4..de4eea606ccd 100644 --- a/drivers/acpi/acpica/evglock.c +++ b/drivers/acpi/acpica/evglock.c @@ -3,7 +3,7 @@ * * Module Name: evglock - Global Lock support * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evgpe.c b/drivers/acpi/acpica/evgpe.c index 06b9c8dd11c9..c5a06882bdf6 100644 --- a/drivers/acpi/acpica/evgpe.c +++ b/drivers/acpi/acpica/evgpe.c @@ -3,7 +3,7 @@ * * Module Name: evgpe - General Purpose Event handling and dispatch * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evgpeblk.c b/drivers/acpi/acpica/evgpeblk.c index f5298be4273a..e5f8245c2d93 100644 --- a/drivers/acpi/acpica/evgpeblk.c +++ b/drivers/acpi/acpica/evgpeblk.c @@ -3,7 +3,7 @@ * * Module Name: evgpeblk - GPE block creation and initialization. * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evgpeinit.c b/drivers/acpi/acpica/evgpeinit.c index 6d82d30d8f7b..b0724d6e6e80 100644 --- a/drivers/acpi/acpica/evgpeinit.c +++ b/drivers/acpi/acpica/evgpeinit.c @@ -3,7 +3,7 @@ * * Module Name: evgpeinit - System GPE initialization and update * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evgpeutil.c b/drivers/acpi/acpica/evgpeutil.c index 738873e876ca..2e74308d7725 100644 --- a/drivers/acpi/acpica/evgpeutil.c +++ b/drivers/acpi/acpica/evgpeutil.c @@ -3,7 +3,7 @@ * * Module Name: evgpeutil - GPE utilities * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evhandler.c b/drivers/acpi/acpica/evhandler.c index 5884eba047f7..ea9485e6a475 100644 --- a/drivers/acpi/acpica/evhandler.c +++ b/drivers/acpi/acpica/evhandler.c @@ -3,7 +3,7 @@ * * Module Name: evhandler - Support for Address Space handlers * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evmisc.c b/drivers/acpi/acpica/evmisc.c index ce1eda6beb84..f14ebcd610ab 100644 --- a/drivers/acpi/acpica/evmisc.c +++ b/drivers/acpi/acpica/evmisc.c @@ -3,7 +3,7 @@ * * Module Name: evmisc - Miscellaneous event manager support functions * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c index a8a4c8c9b9ef..3ed7d9ae95cf 100644 --- a/drivers/acpi/acpica/evregion.c +++ b/drivers/acpi/acpica/evregion.c @@ -3,7 +3,7 @@ * * Module Name: evregion - Operation Region support * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evrgnini.c b/drivers/acpi/acpica/evrgnini.c index 89be3ccdad53..984c172453bf 100644 --- a/drivers/acpi/acpica/evrgnini.c +++ b/drivers/acpi/acpica/evrgnini.c @@ -3,7 +3,7 @@ * * Module Name: evrgnini- ACPI address_space (op_region) init * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evxface.c b/drivers/acpi/acpica/evxface.c index e4e012297eee..ff5cf5b0705a 100644 --- a/drivers/acpi/acpica/evxface.c +++ b/drivers/acpi/acpica/evxface.c @@ -3,7 +3,7 @@ * * Module Name: evxface - External interfaces for ACPI events * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evxfevnt.c b/drivers/acpi/acpica/evxfevnt.c index 1a15b0087379..5445a361c621 100644 --- a/drivers/acpi/acpica/evxfevnt.c +++ b/drivers/acpi/acpica/evxfevnt.c @@ -3,7 +3,7 @@ * * Module Name: evxfevnt - External Interfaces, ACPI event disable/enable * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c index 3be60673e461..a6d53cf86450 100644 --- a/drivers/acpi/acpica/evxfgpe.c +++ b/drivers/acpi/acpica/evxfgpe.c @@ -3,7 +3,7 @@ * * Module Name: evxfgpe - External Interfaces for General Purpose Events (GPEs) * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c index da97fd0c6b51..7672d70da850 100644 --- a/drivers/acpi/acpica/evxfregn.c +++ b/drivers/acpi/acpica/evxfregn.c @@ -4,7 +4,7 @@ * Module Name: evxfregn - External Interfaces, ACPI Operation Regions and * Address Spaces. * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exconcat.c b/drivers/acpi/acpica/exconcat.c index 43711412722f..2d220d470c60 100644 --- a/drivers/acpi/acpica/exconcat.c +++ b/drivers/acpi/acpica/exconcat.c @@ -3,7 +3,7 @@ * * Module Name: exconcat - Concatenate-type AML operators * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exconfig.c b/drivers/acpi/acpica/exconfig.c index 68efd704e2dc..0cd9b3738e76 100644 --- a/drivers/acpi/acpica/exconfig.c +++ b/drivers/acpi/acpica/exconfig.c @@ -3,7 +3,7 @@ * * Module Name: exconfig - Namespace reconfiguration (Load/Unload opcodes) * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exconvrt.c b/drivers/acpi/acpica/exconvrt.c index 50c7aad2e86d..6b7498371eb0 100644 --- a/drivers/acpi/acpica/exconvrt.c +++ b/drivers/acpi/acpica/exconvrt.c @@ -3,7 +3,7 @@ * * Module Name: exconvrt - Object conversion routines * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/excreate.c b/drivers/acpi/acpica/excreate.c index a17482428b46..80b52ad55775 100644 --- a/drivers/acpi/acpica/excreate.c +++ b/drivers/acpi/acpica/excreate.c @@ -3,7 +3,7 @@ * * Module Name: excreate - Named object creation * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exdebug.c b/drivers/acpi/acpica/exdebug.c index a5223dcaee70..6a01e38b7d5a 100644 --- a/drivers/acpi/acpica/exdebug.c +++ b/drivers/acpi/acpica/exdebug.c @@ -3,7 +3,7 @@ * * Module Name: exdebug - Support for stores to the AML Debug Object * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exdump.c b/drivers/acpi/acpica/exdump.c index 47a4d9a40d6b..2aea44ecc37d 100644 --- a/drivers/acpi/acpica/exdump.c +++ b/drivers/acpi/acpica/exdump.c @@ -3,7 +3,7 @@ * * Module Name: exdump - Interpreter debug output routines * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exfield.c b/drivers/acpi/acpica/exfield.c index 3323a2ba6a31..32f03ee81785 100644 --- a/drivers/acpi/acpica/exfield.c +++ b/drivers/acpi/acpica/exfield.c @@ -3,7 +3,7 @@ * * Module Name: exfield - AML execution - field_unit read/write * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exfldio.c b/drivers/acpi/acpica/exfldio.c index ade35ff1c7ba..bdc7a30d1217 100644 --- a/drivers/acpi/acpica/exfldio.c +++ b/drivers/acpi/acpica/exfldio.c @@ -3,7 +3,7 @@ * * Module Name: exfldio - Aml Field I/O * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ @@ -434,7 +434,7 @@ acpi_ex_field_datum_io(union acpi_operand_object *obj_desc, * region_field case and write the datum to the Operation Region */ - /*lint -fallthrough */ + ACPI_FALLTHROUGH; case ACPI_TYPE_LOCAL_REGION_FIELD: /* diff --git a/drivers/acpi/acpica/exmisc.c b/drivers/acpi/acpica/exmisc.c index 717e3998fd77..ad19f914641b 100644 --- a/drivers/acpi/acpica/exmisc.c +++ b/drivers/acpi/acpica/exmisc.c @@ -3,7 +3,7 @@ * * Module Name: exmisc - ACPI AML (p-code) execution - specific opcodes * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exmutex.c b/drivers/acpi/acpica/exmutex.c index 9ff247cba571..6237ae8284b1 100644 --- a/drivers/acpi/acpica/exmutex.c +++ b/drivers/acpi/acpica/exmutex.c @@ -3,7 +3,7 @@ * * Module Name: exmutex - ASL Mutex Acquire/Release functions * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exnames.c b/drivers/acpi/acpica/exnames.c index 74f8b0d0452b..5283603d078d 100644 --- a/drivers/acpi/acpica/exnames.c +++ b/drivers/acpi/acpica/exnames.c @@ -3,7 +3,7 @@ * * Module Name: exnames - interpreter/scanner name load/execute * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exoparg1.c b/drivers/acpi/acpica/exoparg1.c index a46d685a3ffc..b639e930d642 100644 --- a/drivers/acpi/acpica/exoparg1.c +++ b/drivers/acpi/acpica/exoparg1.c @@ -3,7 +3,7 @@ * * Module Name: exoparg1 - AML execution - opcodes with 1 argument * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exoparg2.c b/drivers/acpi/acpica/exoparg2.c index 03241d18ac1d..10323ab186da 100644 --- a/drivers/acpi/acpica/exoparg2.c +++ b/drivers/acpi/acpica/exoparg2.c @@ -3,7 +3,7 @@ * * Module Name: exoparg2 - AML execution - opcodes with 2 arguments * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exoparg3.c b/drivers/acpi/acpica/exoparg3.c index c8d0d75fc450..140aae009690 100644 --- a/drivers/acpi/acpica/exoparg3.c +++ b/drivers/acpi/acpica/exoparg3.c @@ -3,7 +3,7 @@ * * Module Name: exoparg3 - AML execution - opcodes with 3 arguments * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exoparg6.c b/drivers/acpi/acpica/exoparg6.c index 55d0fa056fe7..2cf9f37a0ba8 100644 --- a/drivers/acpi/acpica/exoparg6.c +++ b/drivers/acpi/acpica/exoparg6.c @@ -3,7 +3,7 @@ * * Module Name: exoparg6 - AML execution - opcodes with 6 arguments * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c index 4a0f03157e08..d8c55dde191b 100644 --- a/drivers/acpi/acpica/exprep.c +++ b/drivers/acpi/acpica/exprep.c @@ -3,7 +3,7 @@ * * Module Name: exprep - ACPI AML field prep utilities * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exregion.c b/drivers/acpi/acpica/exregion.c index 4914dbc44517..82b713a9a193 100644 --- a/drivers/acpi/acpica/exregion.c +++ b/drivers/acpi/acpica/exregion.c @@ -3,7 +3,7 @@ * * Module Name: exregion - ACPI default op_region (address space) handlers * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exresnte.c b/drivers/acpi/acpica/exresnte.c index 3e4018678c09..d80b76455c50 100644 --- a/drivers/acpi/acpica/exresnte.c +++ b/drivers/acpi/acpica/exresnte.c @@ -3,7 +3,7 @@ * * Module Name: exresnte - AML Interpreter object resolution * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exresolv.c b/drivers/acpi/acpica/exresolv.c index 912a078c60a4..fa6a96242835 100644 --- a/drivers/acpi/acpica/exresolv.c +++ b/drivers/acpi/acpica/exresolv.c @@ -3,7 +3,7 @@ * * Module Name: exresolv - AML Interpreter object resolution * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exresop.c b/drivers/acpi/acpica/exresop.c index 4d1b22971d58..cbe2c88b1dc2 100644 --- a/drivers/acpi/acpica/exresop.c +++ b/drivers/acpi/acpica/exresop.c @@ -3,7 +3,7 @@ * * Module Name: exresop - AML Interpreter operand/object resolution * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ @@ -198,7 +198,7 @@ acpi_ex_resolve_operands(u16 opcode, target_op = AML_DEBUG_OP; - /*lint -fallthrough */ + ACPI_FALLTHROUGH; case ACPI_REFCLASS_ARG: case ACPI_REFCLASS_LOCAL: @@ -264,7 +264,7 @@ acpi_ex_resolve_operands(u16 opcode, * Else not a string - fall through to the normal Reference * case below */ - /*lint -fallthrough */ + ACPI_FALLTHROUGH; case ARGI_REFERENCE: /* References: */ case ARGI_INTEGER_REF: diff --git a/drivers/acpi/acpica/exserial.c b/drivers/acpi/acpica/exserial.c index 760bc7cef55a..8e8d95f7947b 100644 --- a/drivers/acpi/acpica/exserial.c +++ b/drivers/acpi/acpica/exserial.c @@ -3,7 +3,7 @@ * * Module Name: exserial - field_unit support for serial address spaces * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exstore.c b/drivers/acpi/acpica/exstore.c index 3adc0a29d890..12f4210ea085 100644 --- a/drivers/acpi/acpica/exstore.c +++ b/drivers/acpi/acpica/exstore.c @@ -3,7 +3,7 @@ * * Module Name: exstore - AML Interpreter object store support * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ @@ -96,7 +96,7 @@ acpi_ex_store(union acpi_operand_object *source_desc, return_ACPI_STATUS(AE_OK); } - /*lint -fallthrough */ + ACPI_FALLTHROUGH; default: @@ -422,7 +422,7 @@ acpi_ex_store_object_to_node(union acpi_operand_object *source_desc, break; } - /* Fallthrough */ + ACPI_FALLTHROUGH; case ACPI_TYPE_DEVICE: case ACPI_TYPE_EVENT: diff --git a/drivers/acpi/acpica/exstoren.c b/drivers/acpi/acpica/exstoren.c index 8c34f4e2ab8f..08469d37e73e 100644 --- a/drivers/acpi/acpica/exstoren.c +++ b/drivers/acpi/acpica/exstoren.c @@ -4,7 +4,7 @@ * Module Name: exstoren - AML Interpreter object store support, * Store to Node (namespace object) * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exstorob.c b/drivers/acpi/acpica/exstorob.c index dc66696080a5..a82628683329 100644 --- a/drivers/acpi/acpica/exstorob.c +++ b/drivers/acpi/acpica/exstorob.c @@ -3,7 +3,7 @@ * * Module Name: exstorob - AML object store support, store to object * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exsystem.c b/drivers/acpi/acpica/exsystem.c index f329b01672bb..1281c07112de 100644 --- a/drivers/acpi/acpica/exsystem.c +++ b/drivers/acpi/acpica/exsystem.c @@ -3,7 +3,7 @@ * * Module Name: exsystem - Interface to OS services * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/extrace.c b/drivers/acpi/acpica/extrace.c index 832a47885b99..8846f483fb02 100644 --- a/drivers/acpi/acpica/extrace.c +++ b/drivers/acpi/acpica/extrace.c @@ -3,7 +3,7 @@ * * Module Name: extrace - Support for interpreter execution tracing * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/exutils.c b/drivers/acpi/acpica/exutils.c index 8fefa6feac2f..4d41a866f633 100644 --- a/drivers/acpi/acpica/exutils.c +++ b/drivers/acpi/acpica/exutils.c @@ -3,7 +3,7 @@ * * Module Name: exutils - interpreter/scanner utilities * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwacpi.c b/drivers/acpi/acpica/hwacpi.c index 9b9aac27ff7e..96f55f079988 100644 --- a/drivers/acpi/acpica/hwacpi.c +++ b/drivers/acpi/acpica/hwacpi.c @@ -3,7 +3,7 @@ * * Module Name: hwacpi - ACPI Hardware Initialization/Mode Interface * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwesleep.c b/drivers/acpi/acpica/hwesleep.c index d9be5d0545d4..803402aefaeb 100644 --- a/drivers/acpi/acpica/hwesleep.c +++ b/drivers/acpi/acpica/hwesleep.c @@ -4,7 +4,7 @@ * Name: hwesleep.c - ACPI Hardware Sleep/Wake Support functions for the * extended FADT-V5 sleep registers. * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwgpe.c b/drivers/acpi/acpica/hwgpe.c index b13a4ed5bc63..0770aa176cd5 100644 --- a/drivers/acpi/acpica/hwgpe.c +++ b/drivers/acpi/acpica/hwgpe.c @@ -3,7 +3,7 @@ * * Module Name: hwgpe - Low level GPE enable/disable/clear functions * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ @@ -167,7 +167,7 @@ acpi_hw_low_set_gpe(struct acpi_gpe_event_info *gpe_event_info, u32 action) return (AE_BAD_PARAMETER); } - /*lint -fallthrough */ + ACPI_FALLTHROUGH; case ACPI_GPE_ENABLE: diff --git a/drivers/acpi/acpica/hwsleep.c b/drivers/acpi/acpica/hwsleep.c index 317ae870336b..14baa13bf848 100644 --- a/drivers/acpi/acpica/hwsleep.c +++ b/drivers/acpi/acpica/hwsleep.c @@ -4,7 +4,7 @@ * Name: hwsleep.c - ACPI Hardware Sleep/Wake Support functions for the * original/legacy sleep/PM registers. * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwtimer.c b/drivers/acpi/acpica/hwtimer.c index 07473ddfa9a9..63deadde9f48 100644 --- a/drivers/acpi/acpica/hwtimer.c +++ b/drivers/acpi/acpica/hwtimer.c @@ -3,7 +3,7 @@ * * Name: hwtimer.c - ACPI Power Management Timer Interface * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwvalid.c b/drivers/acpi/acpica/hwvalid.c index b2ca7dfd3fc9..e15badf4077a 100644 --- a/drivers/acpi/acpica/hwvalid.c +++ b/drivers/acpi/acpica/hwvalid.c @@ -3,7 +3,7 @@ * * Module Name: hwvalid - I/O request validation * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwxface.c b/drivers/acpi/acpica/hwxface.c index 134dbfadcd15..fb27aaad0dee 100644 --- a/drivers/acpi/acpica/hwxface.c +++ b/drivers/acpi/acpica/hwxface.c @@ -3,7 +3,7 @@ * * Module Name: hwxface - Public ACPICA hardware interfaces * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/hwxfsleep.c b/drivers/acpi/acpica/hwxfsleep.c index a4b66f4b2714..89b12afed564 100644 --- a/drivers/acpi/acpica/hwxfsleep.c +++ b/drivers/acpi/acpica/hwxfsleep.c @@ -3,7 +3,7 @@ * * Name: hwxfsleep.c - ACPI Hardware Sleep/Wake External Interfaces * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsarguments.c b/drivers/acpi/acpica/nsarguments.c index 6bbc7d350a16..c8a2747005c5 100644 --- a/drivers/acpi/acpica/nsarguments.c +++ b/drivers/acpi/acpica/nsarguments.c @@ -3,7 +3,7 @@ * * Module Name: nsarguments - Validation of args for ACPI predefined methods * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsconvert.c b/drivers/acpi/acpica/nsconvert.c index c86c82939ebb..597d0eed23c1 100644 --- a/drivers/acpi/acpica/nsconvert.c +++ b/drivers/acpi/acpica/nsconvert.c @@ -4,7 +4,7 @@ * Module Name: nsconvert - Object conversions for objects returned by * predefined methods * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsdump.c b/drivers/acpi/acpica/nsdump.c index 994f0b556c60..2f66f3ed1810 100644 --- a/drivers/acpi/acpica/nsdump.c +++ b/drivers/acpi/acpica/nsdump.c @@ -3,7 +3,7 @@ * * Module Name: nsdump - table dumping routines for debug * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsdumpdv.c b/drivers/acpi/acpica/nsdumpdv.c index b691fe20e384..d3dc6761bcdd 100644 --- a/drivers/acpi/acpica/nsdumpdv.c +++ b/drivers/acpi/acpica/nsdumpdv.c @@ -3,7 +3,7 @@ * * Module Name: nsdump - table dumping routines for debug * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsinit.c b/drivers/acpi/acpica/nsinit.c index e16f6a0c2c3f..4db81f8ba29b 100644 --- a/drivers/acpi/acpica/nsinit.c +++ b/drivers/acpi/acpica/nsinit.c @@ -3,7 +3,7 @@ * * Module Name: nsinit - namespace initialization * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsload.c b/drivers/acpi/acpica/nsload.c index 9ba17891edb6..7d77956ed790 100644 --- a/drivers/acpi/acpica/nsload.c +++ b/drivers/acpi/acpica/nsload.c @@ -3,7 +3,7 @@ * * Module Name: nsload - namespace loading/expanding/contracting procedures * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsparse.c b/drivers/acpi/acpica/nsparse.c index 7e74a765e785..778f80e624be 100644 --- a/drivers/acpi/acpica/nsparse.c +++ b/drivers/acpi/acpica/nsparse.c @@ -3,7 +3,7 @@ * * Module Name: nsparse - namespace interface to AML parser * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nspredef.c b/drivers/acpi/acpica/nspredef.c index 167a1c2495ab..e4e5f32da7dc 100644 --- a/drivers/acpi/acpica/nspredef.c +++ b/drivers/acpi/acpica/nspredef.c @@ -3,7 +3,7 @@ * * Module Name: nspredef - Validation of ACPI predefined methods and objects * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsprepkg.c b/drivers/acpi/acpica/nsprepkg.c index 1875b1cba202..6742b50836f7 100644 --- a/drivers/acpi/acpica/nsprepkg.c +++ b/drivers/acpi/acpica/nsprepkg.c @@ -3,7 +3,7 @@ * * Module Name: nsprepkg - Validation of package objects for predefined names * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsrepair.c b/drivers/acpi/acpica/nsrepair.c index 90db2d85e7f5..499067daa22c 100644 --- a/drivers/acpi/acpica/nsrepair.c +++ b/drivers/acpi/acpica/nsrepair.c @@ -3,7 +3,7 @@ * * Module Name: nsrepair - Repair for objects returned by predefined methods * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsrepair2.c b/drivers/acpi/acpica/nsrepair2.c index 24c197d91f29..14b71b41e845 100644 --- a/drivers/acpi/acpica/nsrepair2.c +++ b/drivers/acpi/acpica/nsrepair2.c @@ -4,7 +4,7 @@ * Module Name: nsrepair2 - Repair for objects returned by specific * predefined methods * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsutils.c b/drivers/acpi/acpica/nsutils.c index e66abdab8f31..83d0f276da4d 100644 --- a/drivers/acpi/acpica/nsutils.c +++ b/drivers/acpi/acpica/nsutils.c @@ -4,7 +4,7 @@ * Module Name: nsutils - Utilities for accessing ACPI namespace, accessing * parents and siblings and Scope manipulation * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nswalk.c b/drivers/acpi/acpica/nswalk.c index b7f3e8603ad8..915c2433463d 100644 --- a/drivers/acpi/acpica/nswalk.c +++ b/drivers/acpi/acpica/nswalk.c @@ -3,7 +3,7 @@ * * Module Name: nswalk - Functions for walking the ACPI namespace * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/nsxfname.c b/drivers/acpi/acpica/nsxfname.c index 0e6aba81605b..03487546da5a 100644 --- a/drivers/acpi/acpica/nsxfname.c +++ b/drivers/acpi/acpica/nsxfname.c @@ -4,7 +4,7 @@ * Module Name: nsxfname - Public interfaces to the ACPI subsystem * ACPI Namespace oriented interfaces * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psargs.c b/drivers/acpi/acpica/psargs.c index 3b40db4ad9f3..b9ff535aa02e 100644 --- a/drivers/acpi/acpica/psargs.c +++ b/drivers/acpi/acpica/psargs.c @@ -3,7 +3,7 @@ * * Module Name: psargs - Parse AML opcode arguments * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psloop.c b/drivers/acpi/acpica/psloop.c index 3cf0687b9915..4b51dd939f29 100644 --- a/drivers/acpi/acpica/psloop.c +++ b/drivers/acpi/acpica/psloop.c @@ -3,7 +3,7 @@ * * Module Name: psloop - Main AML parse loop * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ @@ -264,8 +264,7 @@ acpi_status acpi_ps_parse_loop(struct acpi_walk_state *walk_state) ACPI_TO_POINTER (TRUE)); if (ACPI_FAILURE(status) - && ((status & AE_CODE_MASK) != - AE_CODE_CONTROL)) { + && !ACPI_CNTL_EXCEPTION(status)) { if (status == AE_AML_NO_RETURN_VALUE) { ACPI_EXCEPTION((AE_INFO, status, "Invoked method did not return a value")); diff --git a/drivers/acpi/acpica/psobject.c b/drivers/acpi/acpica/psobject.c index 2480c26c5171..e4420cd6d281 100644 --- a/drivers/acpi/acpica/psobject.c +++ b/drivers/acpi/acpica/psobject.c @@ -3,7 +3,7 @@ * * Module Name: psobject - Support for parse objects * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psopcode.c b/drivers/acpi/acpica/psopcode.c index 28af49263ebf..3e80eb1a5f35 100644 --- a/drivers/acpi/acpica/psopcode.c +++ b/drivers/acpi/acpica/psopcode.c @@ -3,7 +3,7 @@ * * Module Name: psopcode - Parser/Interpreter opcode information table * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psopinfo.c b/drivers/acpi/acpica/psopinfo.c index ab9327f6a63c..476b00a121f3 100644 --- a/drivers/acpi/acpica/psopinfo.c +++ b/drivers/acpi/acpica/psopinfo.c @@ -3,7 +3,7 @@ * * Module Name: psopinfo - AML opcode information functions and dispatch tables * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psparse.c b/drivers/acpi/acpica/psparse.c index bd3caf735be3..7eb7a81619a3 100644 --- a/drivers/acpi/acpica/psparse.c +++ b/drivers/acpi/acpica/psparse.c @@ -3,7 +3,7 @@ * * Module Name: psparse - Parser top level AML parse routines * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ @@ -383,7 +383,7 @@ acpi_ps_next_parse_state(struct acpi_walk_state *walk_state, default: status = callback_status; - if ((callback_status & AE_CODE_MASK) == AE_CODE_CONTROL) { + if (ACPI_CNTL_EXCEPTION(callback_status)) { status = AE_OK; } break; diff --git a/drivers/acpi/acpica/psscope.c b/drivers/acpi/acpica/psscope.c index fceb311995e9..3f2eada44942 100644 --- a/drivers/acpi/acpica/psscope.c +++ b/drivers/acpi/acpica/psscope.c @@ -3,7 +3,7 @@ * * Module Name: psscope - Parser scope stack management routines * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/pstree.c b/drivers/acpi/acpica/pstree.c index c8aef0694864..ffb2a7bfc6d7 100644 --- a/drivers/acpi/acpica/pstree.c +++ b/drivers/acpi/acpica/pstree.c @@ -3,7 +3,7 @@ * * Module Name: pstree - Parser op tree manipulation/traversal/search * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psutils.c b/drivers/acpi/acpica/psutils.c index 00efae2f95ba..e6596051d548 100644 --- a/drivers/acpi/acpica/psutils.c +++ b/drivers/acpi/acpica/psutils.c @@ -3,7 +3,7 @@ * * Module Name: psutils - Parser miscellaneous utilities (Parser only) * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/pswalk.c b/drivers/acpi/acpica/pswalk.c index 0fe3adf6b0e5..7018a789debc 100644 --- a/drivers/acpi/acpica/pswalk.c +++ b/drivers/acpi/acpica/pswalk.c @@ -3,7 +3,7 @@ * * Module Name: pswalk - Parser routines to walk parsed op tree(s) * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/psxface.c b/drivers/acpi/acpica/psxface.c index 1bbfc8def388..fd0f28c7af1e 100644 --- a/drivers/acpi/acpica/psxface.c +++ b/drivers/acpi/acpica/psxface.c @@ -3,7 +3,7 @@ * * Module Name: psxface - Parser external interfaces * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbdata.c b/drivers/acpi/acpica/tbdata.c index 523b1e9b98d4..ebbca109edcb 100644 --- a/drivers/acpi/acpica/tbdata.c +++ b/drivers/acpi/acpica/tbdata.c @@ -3,7 +3,7 @@ * * Module Name: tbdata - Table manager data structure functions * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbfadt.c b/drivers/acpi/acpica/tbfadt.c index 907edc5edba7..5174abfa8af9 100644 --- a/drivers/acpi/acpica/tbfadt.c +++ b/drivers/acpi/acpica/tbfadt.c @@ -3,7 +3,7 @@ * * Module Name: tbfadt - FADT table utilities * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbfind.c b/drivers/acpi/acpica/tbfind.c index 56d81e490a5c..2c2c2b1f5a28 100644 --- a/drivers/acpi/acpica/tbfind.c +++ b/drivers/acpi/acpica/tbfind.c @@ -3,7 +3,7 @@ * * Module Name: tbfind - find table * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c index 0bb15add2245..8d1e5b572493 100644 --- a/drivers/acpi/acpica/tbinstal.c +++ b/drivers/acpi/acpica/tbinstal.c @@ -3,7 +3,7 @@ * * Module Name: tbinstal - ACPI table installation and removal * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbprint.c b/drivers/acpi/acpica/tbprint.c index 0b3494ad9a70..254823d494a2 100644 --- a/drivers/acpi/acpica/tbprint.c +++ b/drivers/acpi/acpica/tbprint.c @@ -3,7 +3,7 @@ * * Module Name: tbprint - Table output utilities * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c index dfe1ac3ae34a..4b9b329a5a92 100644 --- a/drivers/acpi/acpica/tbutils.c +++ b/drivers/acpi/acpica/tbutils.c @@ -3,7 +3,7 @@ * * Module Name: tbutils - ACPI Table utilities * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbxface.c b/drivers/acpi/acpica/tbxface.c index 7490429ddbf6..e6f51fedaf1a 100644 --- a/drivers/acpi/acpica/tbxface.c +++ b/drivers/acpi/acpica/tbxface.c @@ -3,7 +3,7 @@ * * Module Name: tbxface - ACPI table-oriented external interfaces * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbxfload.c b/drivers/acpi/acpica/tbxfload.c index bcba993d4dac..38623049b962 100644 --- a/drivers/acpi/acpica/tbxfload.c +++ b/drivers/acpi/acpica/tbxfload.c @@ -3,7 +3,7 @@ * * Module Name: tbxfload - Table load/unload external interfaces * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/tbxfroot.c b/drivers/acpi/acpica/tbxfroot.c index 0edc6ef5d46d..9fec3df6c3ba 100644 --- a/drivers/acpi/acpica/tbxfroot.c +++ b/drivers/acpi/acpica/tbxfroot.c @@ -3,7 +3,7 @@ * * Module Name: tbxfroot - Find the root ACPI table (RSDT) * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utaddress.c b/drivers/acpi/acpica/utaddress.c index 99fa48722cf6..7001f4b113f1 100644 --- a/drivers/acpi/acpica/utaddress.c +++ b/drivers/acpi/acpica/utaddress.c @@ -3,7 +3,7 @@ * * Module Name: utaddress - op_region address range check * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utalloc.c b/drivers/acpi/acpica/utalloc.c index 303ab51b4fcf..796fd9b33a7d 100644 --- a/drivers/acpi/acpica/utalloc.c +++ b/drivers/acpi/acpica/utalloc.c @@ -3,7 +3,7 @@ * * Module Name: utalloc - local memory allocation routines * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utascii.c b/drivers/acpi/acpica/utascii.c index d78656d960e8..e1b55575d5fb 100644 --- a/drivers/acpi/acpica/utascii.c +++ b/drivers/acpi/acpica/utascii.c @@ -3,7 +3,7 @@ * * Module Name: utascii - Utility ascii functions * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utbuffer.c b/drivers/acpi/acpica/utbuffer.c index f2ec427f4e29..8ab90f78825b 100644 --- a/drivers/acpi/acpica/utbuffer.c +++ b/drivers/acpi/acpica/utbuffer.c @@ -3,7 +3,7 @@ * * Module Name: utbuffer - Buffer dump routines * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utcache.c b/drivers/acpi/acpica/utcache.c index 1b03a2747401..814145019f95 100644 --- a/drivers/acpi/acpica/utcache.c +++ b/drivers/acpi/acpica/utcache.c @@ -3,7 +3,7 @@ * * Module Name: utcache - local cache allocation routines * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utcopy.c b/drivers/acpi/acpica/utcopy.c index 41bdd0278dd8..d9877153f400 100644 --- a/drivers/acpi/acpica/utcopy.c +++ b/drivers/acpi/acpica/utcopy.c @@ -3,7 +3,7 @@ * * Module Name: utcopy - Internal to external object translation utilities * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utdebug.c b/drivers/acpi/acpica/utdebug.c index 0c8cb0612414..09245945f319 100644 --- a/drivers/acpi/acpica/utdebug.c +++ b/drivers/acpi/acpica/utdebug.c @@ -3,7 +3,7 @@ * * Module Name: utdebug - Debug print/trace routines * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utdecode.c b/drivers/acpi/acpica/utdecode.c index ed9aedf604a1..bcd3871079d7 100644 --- a/drivers/acpi/acpica/utdecode.c +++ b/drivers/acpi/acpica/utdecode.c @@ -3,7 +3,7 @@ * * Module Name: utdecode - Utility decoding routines (value-to-string) * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utdelete.c b/drivers/acpi/acpica/utdelete.c index 4c0d4e434196..624a26794d55 100644 --- a/drivers/acpi/acpica/utdelete.c +++ b/drivers/acpi/acpica/utdelete.c @@ -112,7 +112,7 @@ static void acpi_ut_delete_internal_obj(union acpi_operand_object *object) gpe_block); } - /*lint -fallthrough */ + ACPI_FALLTHROUGH; case ACPI_TYPE_PROCESSOR: case ACPI_TYPE_THERMAL: diff --git a/drivers/acpi/acpica/uteval.c b/drivers/acpi/acpica/uteval.c index 8180d1a458f5..d2503920c620 100644 --- a/drivers/acpi/acpica/uteval.c +++ b/drivers/acpi/acpica/uteval.c @@ -3,7 +3,7 @@ * * Module Name: uteval - Object evaluation * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utglobal.c b/drivers/acpi/acpica/utglobal.c index e6dcbdc3fc6e..59a48371a7bc 100644 --- a/drivers/acpi/acpica/utglobal.c +++ b/drivers/acpi/acpica/utglobal.c @@ -3,7 +3,7 @@ * * Module Name: utglobal - Global variables for the ACPI subsystem * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/uthex.c b/drivers/acpi/acpica/uthex.c index 0e02f12513dc..b1e94c094f9a 100644 --- a/drivers/acpi/acpica/uthex.c +++ b/drivers/acpi/acpica/uthex.c @@ -3,7 +3,7 @@ * * Module Name: uthex -- Hex/ASCII support functions * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utids.c b/drivers/acpi/acpica/utids.c index 3e68864ef242..08e9f316cbde 100644 --- a/drivers/acpi/acpica/utids.c +++ b/drivers/acpi/acpica/utids.c @@ -3,7 +3,7 @@ * * Module Name: utids - support for device Ids - HID, UID, CID, SUB, CLS * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utinit.c b/drivers/acpi/acpica/utinit.c index fdbc397c038d..7b606a1e6986 100644 --- a/drivers/acpi/acpica/utinit.c +++ b/drivers/acpi/acpica/utinit.c @@ -3,7 +3,7 @@ * * Module Name: utinit - Common ACPI subsystem initialization * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utlock.c b/drivers/acpi/acpica/utlock.c index 46be549539e7..923dd15e7a16 100644 --- a/drivers/acpi/acpica/utlock.c +++ b/drivers/acpi/acpica/utlock.c @@ -3,7 +3,7 @@ * * Module Name: utlock - Reader/Writer lock interfaces * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utobject.c b/drivers/acpi/acpica/utobject.c index bbec04c291d2..84a210b49e3a 100644 --- a/drivers/acpi/acpica/utobject.c +++ b/drivers/acpi/acpica/utobject.c @@ -3,7 +3,7 @@ * * Module Name: utobject - ACPI object create/delete/size/cache routines * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utosi.c b/drivers/acpi/acpica/utosi.c index 0a01c08dad8a..7b8e8bf1e824 100644 --- a/drivers/acpi/acpica/utosi.c +++ b/drivers/acpi/acpica/utosi.c @@ -3,7 +3,7 @@ * * Module Name: utosi - Support for the _OSI predefined control method * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utpredef.c b/drivers/acpi/acpica/utpredef.c index dd277f7e9f10..a6f87a88c30e 100644 --- a/drivers/acpi/acpica/utpredef.c +++ b/drivers/acpi/acpica/utpredef.c @@ -3,7 +3,7 @@ * * Module Name: utpredef - support functions for predefined names * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utprint.c b/drivers/acpi/acpica/utprint.c index 681c11f4af4e..e37d612e8db5 100644 --- a/drivers/acpi/acpica/utprint.c +++ b/drivers/acpi/acpica/utprint.c @@ -3,7 +3,7 @@ * * Module Name: utprint - Formatted printing routines * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utstrsuppt.c b/drivers/acpi/acpica/utstrsuppt.c index 2d91003fcf26..199982a6fb16 100644 --- a/drivers/acpi/acpica/utstrsuppt.c +++ b/drivers/acpi/acpica/utstrsuppt.c @@ -104,7 +104,7 @@ acpi_status acpi_ut_convert_decimal_string(char *string, u64 *return_value_ptr) * 1) Runtime: terminate with no error, per the ACPI spec * 2) Compiler: return an error */ - if (!isdigit(*string)) { + if (!isdigit((int)*string)) { #ifdef ACPI_ASL_COMPILER status = AE_BAD_DECIMAL_CONSTANT; #endif @@ -158,7 +158,7 @@ acpi_status acpi_ut_convert_hex_string(char *string, u64 *return_value_ptr) * 1) Runtime: terminate with no error, per the ACPI spec * 2) Compiler: return an error */ - if (!isxdigit(*string)) { + if (!isxdigit((int)*string)) { #ifdef ACPI_ASL_COMPILER status = AE_BAD_HEX_CONSTANT; #endif diff --git a/drivers/acpi/acpica/uttrack.c b/drivers/acpi/acpica/uttrack.c index d366be431a84..2ce85fcfeb5b 100644 --- a/drivers/acpi/acpica/uttrack.c +++ b/drivers/acpi/acpica/uttrack.c @@ -3,7 +3,7 @@ * * Module Name: uttrack - Memory allocation tracking routines (debug only) * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utuuid.c b/drivers/acpi/acpica/utuuid.c index b8039954b0d1..090e44b6b6c7 100644 --- a/drivers/acpi/acpica/utuuid.c +++ b/drivers/acpi/acpica/utuuid.c @@ -3,7 +3,7 @@ * * Module Name: utuuid -- UUID support functions * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utxface.c b/drivers/acpi/acpica/utxface.c index ca7c9f0144ef..3285c1a92e40 100644 --- a/drivers/acpi/acpica/utxface.c +++ b/drivers/acpi/acpica/utxface.c @@ -3,7 +3,7 @@ * * Module Name: utxface - External interfaces, miscellaneous utility functions * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/acpica/utxfinit.c b/drivers/acpi/acpica/utxfinit.c index 653e3bb20036..91016366de1d 100644 --- a/drivers/acpi/acpica/utxfinit.c +++ b/drivers/acpi/acpica/utxfinit.c @@ -3,7 +3,7 @@ * * Module Name: utxfinit - External interfaces for ACPICA initialization * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c index 2e0b0fcad960..b9597216d021 100644 --- a/drivers/acpi/apei/erst.c +++ b/drivers/acpi/apei/erst.c @@ -688,7 +688,7 @@ static int __erst_read_from_storage(u64 record_id, u64 offset) break; if (erst_timedout(&timeout, SPIN_UNIT)) return -EIO; - }; + } rc = apei_exec_run(&ctx, ACPI_ERST_GET_COMMAND_STATUS); if (rc) return rc; diff --git a/drivers/acpi/apei/hest.c b/drivers/acpi/apei/hest.c index 6e980fe16772..f220bb00e91b 100644 --- a/drivers/acpi/apei/hest.c +++ b/drivers/acpi/apei/hest.c @@ -49,6 +49,12 @@ static const int hest_esrc_len_tab[ACPI_HEST_TYPE_RESERVED] = { [ACPI_HEST_TYPE_IA32_DEFERRED_CHECK] = -1, }; +static inline bool is_generic_error(struct acpi_hest_header *hest_hdr) +{ + return hest_hdr->type == ACPI_HEST_TYPE_GENERIC_ERROR || + hest_hdr->type == ACPI_HEST_TYPE_GENERIC_ERROR_V2; +} + static int hest_esrc_len(struct acpi_hest_header *hest_hdr) { u16 hest_type = hest_hdr->type; @@ -141,8 +147,7 @@ static int __init hest_parse_ghes_count(struct acpi_hest_header *hest_hdr, void { int *count = data; - if (hest_hdr->type == ACPI_HEST_TYPE_GENERIC_ERROR || - hest_hdr->type == ACPI_HEST_TYPE_GENERIC_ERROR_V2) + if (is_generic_error(hest_hdr)) (*count)++; return 0; } @@ -153,8 +158,7 @@ static int __init hest_parse_ghes(struct acpi_hest_header *hest_hdr, void *data) struct ghes_arr *ghes_arr = data; int rc, i; - if (hest_hdr->type != ACPI_HEST_TYPE_GENERIC_ERROR && - hest_hdr->type != ACPI_HEST_TYPE_GENERIC_ERROR_V2) + if (!is_generic_error(hest_hdr)) return 0; if (!((struct acpi_hest_generic *)hest_hdr)->enabled) diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index 08ee1c7b12e0..b822f77afba6 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -8,7 +8,7 @@ * Copyright (C) 2001, 2002 Paul Diefenbaugh */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#define pr_fmt(fmt) "ACPI: battery: " fmt #include #include @@ -29,8 +29,6 @@ #include -#define PREFIX "ACPI: " - #define ACPI_BATTERY_VALUE_UNKNOWN 0xFFFFFFFF #define ACPI_BATTERY_CAPACITY_VALID(capacity) \ ((capacity) != 0 && (capacity) != ACPI_BATTERY_VALUE_UNKNOWN) @@ -44,10 +42,6 @@ #define ACPI_BATTERY_STATE_CHARGING 0x2 #define ACPI_BATTERY_STATE_CRITICAL 0x4 -#define _COMPONENT ACPI_BATTERY_COMPONENT - -ACPI_MODULE_NAME("battery"); - MODULE_AUTHOR("Paul Diefenbaugh"); MODULE_AUTHOR("Alexey Starikovskiy "); MODULE_DESCRIPTION("ACPI Battery Driver"); @@ -466,7 +460,8 @@ static int extract_package(struct acpi_battery *battery, static int acpi_battery_get_status(struct acpi_battery *battery) { if (acpi_bus_get_status(battery->device)) { - ACPI_EXCEPTION((AE_INFO, AE_ERROR, "Evaluating _STA")); + acpi_handle_info(battery->device->handle, + "_STA evaluation failed\n"); return -ENODEV; } return 0; @@ -535,8 +530,10 @@ static int acpi_battery_get_info(struct acpi_battery *battery) mutex_unlock(&battery->lock); if (ACPI_FAILURE(status)) { - ACPI_EXCEPTION((AE_INFO, status, "Evaluating %s", - use_bix ? "_BIX":"_BIF")); + acpi_handle_info(battery->device->handle, + "%s evaluation failed: %s\n", + use_bix ?"_BIX":"_BIF", + acpi_format_exception(status)); } else { result = extract_battery_info(use_bix, battery, @@ -573,7 +570,9 @@ static int acpi_battery_get_state(struct acpi_battery *battery) mutex_unlock(&battery->lock); if (ACPI_FAILURE(status)) { - ACPI_EXCEPTION((AE_INFO, status, "Evaluating _BST")); + acpi_handle_info(battery->device->handle, + "_BST evaluation failed: %s", + acpi_format_exception(status)); return -ENODEV; } @@ -590,7 +589,7 @@ static int acpi_battery_get_state(struct acpi_battery *battery) battery->rate_now != ACPI_BATTERY_VALUE_UNKNOWN && (s16)(battery->rate_now) < 0) { battery->rate_now = abs((s16)battery->rate_now); - pr_warn_once(FW_BUG "battery: (dis)charge rate invalid.\n"); + pr_warn_once(FW_BUG "(dis)charge rate invalid.\n"); } if (test_bit(ACPI_BATTERY_QUIRK_PERCENTAGE_CAPACITY, &battery->flags) @@ -625,7 +624,9 @@ static int acpi_battery_set_alarm(struct acpi_battery *battery) if (ACPI_FAILURE(status)) return -ENODEV; - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Alarm set to %d\n", battery->alarm)); + acpi_handle_debug(battery->device->handle, "Alarm set to %d\n", + battery->alarm); + return 0; } @@ -1201,8 +1202,7 @@ static int acpi_battery_add(struct acpi_device *device) if (result) goto fail; - pr_info(PREFIX "%s Slot [%s] (battery %s)\n", - ACPI_BATTERY_DEVICE_NAME, acpi_device_bid(device), + pr_info("Slot [%s] (battery %s)\n", acpi_device_bid(device), device->status.battery_present ? "present" : "absent"); battery->pm_nb.notifier_call = battery_notify; @@ -1282,8 +1282,7 @@ static void __init acpi_battery_init_async(void *unused, async_cookie_t cookie) if (battery_check_pmic) { for (i = 0; i < ARRAY_SIZE(acpi_battery_blacklist); i++) if (acpi_dev_present(acpi_battery_blacklist[i], "1", -1)) { - pr_info(PREFIX ACPI_BATTERY_DEVICE_NAME - ": found native %s PMIC, not loading\n", + pr_info("found native %s PMIC, not loading\n", acpi_battery_blacklist[i]); return; } diff --git a/drivers/acpi/bgrt.c b/drivers/acpi/bgrt.c index 251f961c28cc..19bb7f870204 100644 --- a/drivers/acpi/bgrt.c +++ b/drivers/acpi/bgrt.c @@ -15,40 +15,40 @@ static void *bgrt_image; static struct kobject *bgrt_kobj; -static ssize_t show_version(struct device *dev, +static ssize_t version_show(struct device *dev, struct device_attribute *attr, char *buf) { return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.version); } -static DEVICE_ATTR(version, S_IRUGO, show_version, NULL); +static DEVICE_ATTR_RO(version); -static ssize_t show_status(struct device *dev, +static ssize_t status_show(struct device *dev, struct device_attribute *attr, char *buf) { return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.status); } -static DEVICE_ATTR(status, S_IRUGO, show_status, NULL); +static DEVICE_ATTR_RO(status); -static ssize_t show_type(struct device *dev, +static ssize_t type_show(struct device *dev, struct device_attribute *attr, char *buf) { return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.image_type); } -static DEVICE_ATTR(type, S_IRUGO, show_type, NULL); +static DEVICE_ATTR_RO(type); -static ssize_t show_xoffset(struct device *dev, +static ssize_t xoffset_show(struct device *dev, struct device_attribute *attr, char *buf) { return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.image_offset_x); } -static DEVICE_ATTR(xoffset, S_IRUGO, show_xoffset, NULL); +static DEVICE_ATTR_RO(xoffset); -static ssize_t show_yoffset(struct device *dev, +static ssize_t yoffset_show(struct device *dev, struct device_attribute *attr, char *buf) { return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.image_offset_y); } -static DEVICE_ATTR(yoffset, S_IRUGO, show_yoffset, NULL); +static DEVICE_ATTR_RO(yoffset); static ssize_t image_read(struct file *file, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 9c3fe08e8f18..be7da23fad76 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -5,6 +5,8 @@ * Copyright (C) 2001, 2002 Paul Diefenbaugh */ +#define pr_fmt(fmt) "ACPI: " fmt + #include #include #include @@ -31,9 +33,6 @@ #include "internal.h" -#define _COMPONENT ACPI_BUS_COMPONENT -ACPI_MODULE_NAME("bus"); - struct acpi_device *acpi_root; struct proc_dir_entry *acpi_root_dir; EXPORT_SYMBOL(acpi_root_dir); @@ -47,8 +46,7 @@ static inline int set_copy_dsdt(const struct dmi_system_id *id) #else static int set_copy_dsdt(const struct dmi_system_id *id) { - printk(KERN_NOTICE "%s detected - " - "force copy of DSDT to local memory\n", id->ident); + pr_notice("%s detected - force copy of DSDT to local memory\n", id->ident); acpi_gbl_copy_dsdt_locally = 1; return 0; } @@ -116,13 +114,11 @@ int acpi_bus_get_status(struct acpi_device *device) acpi_set_device_status(device, sta); if (device->status.functional && !device->status.present) { - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device [%s] status [%08x]: " - "functional but not present;\n", - device->pnp.bus_id, (u32)sta)); + pr_debug("Device [%s] status [%08x]: functional but not present\n", + device->pnp.bus_id, (u32)sta); } - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device [%s] status [%08x]\n", - device->pnp.bus_id, (u32)sta)); + pr_debug("Device [%s] status [%08x]\n", device->pnp.bus_id, (u32)sta); return 0; } EXPORT_SYMBOL(acpi_bus_get_status); @@ -1009,9 +1005,9 @@ static int acpi_device_probe(struct device *dev) return ret; acpi_dev->driver = acpi_drv; - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Driver [%s] successfully bound to device [%s]\n", - acpi_drv->name, acpi_dev->pnp.bus_id)); + + pr_debug("Driver [%s] successfully bound to device [%s]\n", + acpi_drv->name, acpi_dev->pnp.bus_id); if (acpi_drv->ops.notify) { ret = acpi_device_install_notify_handler(acpi_dev); @@ -1025,8 +1021,9 @@ static int acpi_device_probe(struct device *dev) } } - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found driver [%s] for device [%s]\n", - acpi_drv->name, acpi_dev->pnp.bus_id)); + pr_debug("Found driver [%s] for device [%s]\n", acpi_drv->name, + acpi_dev->pnp.bus_id); + get_device(dev); return 0; } @@ -1089,15 +1086,15 @@ static int __init acpi_bus_init_irq(void) message = "platform specific model"; break; default: - printk(KERN_WARNING PREFIX "Unknown interrupt routing model\n"); + pr_info("Unknown interrupt routing model\n"); return -ENODEV; } - printk(KERN_INFO PREFIX "Using %s for interrupt routing\n", message); + pr_info("Using %s for interrupt routing\n", message); status = acpi_execute_simple_method(NULL, "\\_PIC", acpi_irq_model); if (ACPI_FAILURE(status) && (status != AE_NOT_FOUND)) { - ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PIC")); + pr_info("_PIC evaluation failed: %s\n", acpi_format_exception(status)); return -ENODEV; } @@ -1121,7 +1118,7 @@ void __init acpi_early_init(void) if (acpi_disabled) return; - printk(KERN_INFO PREFIX "Core revision %08x\n", ACPI_CA_VERSION); + pr_info("Core revision %08x\n", ACPI_CA_VERSION); /* enable workarounds, unless strict ACPI spec. compliance */ if (!acpi_strict) @@ -1142,15 +1139,13 @@ void __init acpi_early_init(void) status = acpi_reallocate_root_table(); if (ACPI_FAILURE(status)) { - printk(KERN_ERR PREFIX - "Unable to reallocate ACPI tables\n"); + pr_err("Unable to reallocate ACPI tables\n"); goto error0; } status = acpi_initialize_subsystem(); if (ACPI_FAILURE(status)) { - printk(KERN_ERR PREFIX - "Unable to initialize the ACPI Interpreter\n"); + pr_err("Unable to initialize the ACPI Interpreter\n"); goto error0; } @@ -1196,7 +1191,7 @@ void __init acpi_subsystem_init(void) status = acpi_enable_subsystem(~ACPI_NO_ACPI_ENABLE); if (ACPI_FAILURE(status)) { - printk(KERN_ERR PREFIX "Unable to enable ACPI\n"); + pr_err("Unable to enable ACPI\n"); disable_acpi(); } else { /* @@ -1225,8 +1220,7 @@ static int __init acpi_bus_init(void) status = acpi_load_tables(); if (ACPI_FAILURE(status)) { - printk(KERN_ERR PREFIX - "Unable to load the System Description Tables\n"); + pr_err("Unable to load the System Description Tables\n"); goto error1; } @@ -1244,14 +1238,13 @@ static int __init acpi_bus_init(void) status = acpi_enable_subsystem(ACPI_NO_ACPI_ENABLE); if (ACPI_FAILURE(status)) { - printk(KERN_ERR PREFIX - "Unable to start the ACPI Interpreter\n"); + pr_err("Unable to start the ACPI Interpreter\n"); goto error1; } status = acpi_initialize_objects(ACPI_FULL_INITIALIZATION); if (ACPI_FAILURE(status)) { - printk(KERN_ERR PREFIX "Unable to initialize ACPI objects\n"); + pr_err("Unable to initialize ACPI objects\n"); goto error1; } @@ -1281,7 +1274,7 @@ static int __init acpi_bus_init(void) */ acpi_ec_dsdt_probe(); - printk(KERN_INFO PREFIX "Interpreter enabled\n"); + pr_info("Interpreter enabled\n"); /* Initialize sleep structures */ acpi_sleep_init(); @@ -1300,8 +1293,7 @@ static int __init acpi_bus_init(void) acpi_install_notify_handler(ACPI_ROOT_OBJECT, ACPI_SYSTEM_NOTIFY, &acpi_bus_notify, NULL); if (ACPI_FAILURE(status)) { - printk(KERN_ERR PREFIX - "Unable to register for device notifications\n"); + pr_err("Unable to register for system notifications\n"); goto error1; } @@ -1328,13 +1320,13 @@ static int __init acpi_init(void) int result; if (acpi_disabled) { - printk(KERN_INFO PREFIX "Interpreter disabled.\n"); + pr_info("Interpreter disabled.\n"); return -ENODEV; } acpi_kobj = kobject_create_and_add("acpi", firmware_kobj); if (!acpi_kobj) { - printk(KERN_WARNING "%s: kset create error\n", __func__); + pr_debug("%s: kset create error\n", __func__); acpi_kobj = NULL; } diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c index 0d93a5ef4d07..85e5e0328a2e 100644 --- a/drivers/acpi/button.c +++ b/drivers/acpi/button.c @@ -21,8 +21,6 @@ #include #include -#define PREFIX "ACPI: " - #define ACPI_BUTTON_CLASS "button" #define ACPI_BUTTON_FILE_STATE "state" #define ACPI_BUTTON_TYPE_UNKNOWN 0x00 @@ -54,9 +52,6 @@ static const char * const lid_init_state_str[] = { [ACPI_BUTTON_LID_INIT_DISABLED] = "disabled", }; -#define _COMPONENT ACPI_BUTTON_COMPONENT -ACPI_MODULE_NAME("button"); - MODULE_AUTHOR("Paul Diefenbaugh"); MODULE_DESCRIPTION("ACPI Button Driver"); MODULE_LICENSE("GPL"); @@ -285,7 +280,7 @@ static int acpi_button_add_fs(struct acpi_device *device) return 0; if (acpi_button_dir || acpi_lid_dir) { - printk(KERN_ERR PREFIX "More than one Lid device found!\n"); + pr_info("More than one Lid device found!\n"); return -EEXIST; } @@ -434,8 +429,8 @@ static void acpi_button_notify(struct acpi_device *device, u32 event) } break; default: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Unsupported event [0x%x]\n", event)); + acpi_handle_debug(device->handle, "Unsupported event [0x%x]\n", + event); break; } } @@ -523,7 +518,7 @@ static int acpi_button_add(struct acpi_device *device) ACPI_BUTTON_CLASS, ACPI_BUTTON_SUBCLASS_LID); input->open = acpi_lid_input_open; } else { - printk(KERN_ERR PREFIX "Unsupported hid [%s]\n", hid); + pr_info("Unsupported hid [%s]\n", hid); error = -ENODEV; goto err_free_input; } @@ -567,7 +562,7 @@ static int acpi_button_add(struct acpi_device *device) } device_init_wakeup(&device->dev, true); - printk(KERN_INFO PREFIX "%s [%s]\n", name, acpi_device_bid(device)); + pr_info("%s [%s]\n", name, acpi_device_bid(device)); return 0; err_remove_fs: diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 75aaf94ae0a9..69057fcd2c04 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -233,8 +233,8 @@ static int send_pcc_cmd(int pcc_ss_id, u16 cmd) { int ret = -EIO, i; struct cppc_pcc_data *pcc_ss_data = pcc_data[pcc_ss_id]; - struct acpi_pcct_shared_memory *generic_comm_base = - (struct acpi_pcct_shared_memory *)pcc_ss_data->pcc_comm_addr; + struct acpi_pcct_shared_memory __iomem *generic_comm_base = + pcc_ss_data->pcc_comm_addr; unsigned int time_delta; /* @@ -934,7 +934,7 @@ int __weak cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val) static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) { int ret_val = 0; - void __iomem *vaddr = 0; + void __iomem *vaddr = NULL; int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu); struct cpc_reg *reg = ®_res->cpc_entry.reg; @@ -979,7 +979,7 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) { int ret_val = 0; - void __iomem *vaddr = 0; + void __iomem *vaddr = NULL; int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu); struct cpc_reg *reg = ®_res->cpc_entry.reg; diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index 3586434d0ded..096153761ebc 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -10,6 +10,8 @@ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ +#define pr_fmt(fmt) "ACPI: PM: " fmt + #include #include #include @@ -20,9 +22,6 @@ #include "internal.h" -#define _COMPONENT ACPI_POWER_COMPONENT -ACPI_MODULE_NAME("device_pm"); - /** * acpi_power_state_string - String representation of ACPI device power state. * @state: ACPI device power state to return the string representation of. @@ -130,8 +129,8 @@ int acpi_device_get_power(struct acpi_device *device, int *state) *state = result; out: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device [%s] power state is %s\n", - device->pnp.bus_id, acpi_power_state_string(*state))); + dev_dbg(&device->dev, "Device power state is %s\n", + acpi_power_state_string(*state)); return 0; } @@ -174,9 +173,8 @@ int acpi_device_set_power(struct acpi_device *device, int state) /* There is a special case for D0 addressed below. */ if (state > ACPI_STATE_D0 && state == device->power.state) { - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device [%s] already in %s\n", - device->pnp.bus_id, - acpi_power_state_string(state))); + dev_dbg(&device->dev, "Device already in %s\n", + acpi_power_state_string(state)); return 0; } @@ -276,10 +274,8 @@ int acpi_device_set_power(struct acpi_device *device, int state) acpi_power_state_string(target_state)); } else { device->power.state = target_state; - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Device [%s] transitioned to %s\n", - device->pnp.bus_id, - acpi_power_state_string(target_state))); + dev_dbg(&device->dev, "Power state changed to %s\n", + acpi_power_state_string(target_state)); } return result; diff --git a/drivers/acpi/device_sysfs.c b/drivers/acpi/device_sysfs.c index bfca116482b8..da4ff2a8b06a 100644 --- a/drivers/acpi/device_sysfs.c +++ b/drivers/acpi/device_sysfs.c @@ -325,11 +325,11 @@ int acpi_device_modalias(struct device *dev, char *buf, int size) EXPORT_SYMBOL_GPL(acpi_device_modalias); static ssize_t -acpi_device_modalias_show(struct device *dev, struct device_attribute *attr, char *buf) +modalias_show(struct device *dev, struct device_attribute *attr, char *buf) { return __acpi_device_modalias(to_acpi_device(dev), buf, 1024); } -static DEVICE_ATTR(modalias, 0444, acpi_device_modalias_show, NULL); +static DEVICE_ATTR_RO(modalias); static ssize_t real_power_state_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -358,8 +358,8 @@ static ssize_t power_state_show(struct device *dev, static DEVICE_ATTR_RO(power_state); static ssize_t -acpi_eject_store(struct device *d, struct device_attribute *attr, - const char *buf, size_t count) +eject_store(struct device *d, struct device_attribute *attr, + const char *buf, size_t count) { struct acpi_device *acpi_device = to_acpi_device(d); acpi_object_type not_used; @@ -387,28 +387,28 @@ acpi_eject_store(struct device *d, struct device_attribute *attr, return status == AE_NO_MEMORY ? -ENOMEM : -EAGAIN; } -static DEVICE_ATTR(eject, 0200, NULL, acpi_eject_store); +static DEVICE_ATTR_WO(eject); static ssize_t -acpi_device_hid_show(struct device *dev, struct device_attribute *attr, char *buf) +hid_show(struct device *dev, struct device_attribute *attr, char *buf) { struct acpi_device *acpi_dev = to_acpi_device(dev); return sprintf(buf, "%s\n", acpi_device_hid(acpi_dev)); } -static DEVICE_ATTR(hid, 0444, acpi_device_hid_show, NULL); +static DEVICE_ATTR_RO(hid); -static ssize_t acpi_device_uid_show(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t uid_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct acpi_device *acpi_dev = to_acpi_device(dev); return sprintf(buf, "%s\n", acpi_dev->pnp.unique_id); } -static DEVICE_ATTR(uid, 0444, acpi_device_uid_show, NULL); +static DEVICE_ATTR_RO(uid); -static ssize_t acpi_device_adr_show(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t adr_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct acpi_device *acpi_dev = to_acpi_device(dev); @@ -417,16 +417,16 @@ static ssize_t acpi_device_adr_show(struct device *dev, else return sprintf(buf, "0x%08llx\n", acpi_dev->pnp.bus_address); } -static DEVICE_ATTR(adr, 0444, acpi_device_adr_show, NULL); +static DEVICE_ATTR_RO(adr); -static ssize_t acpi_device_path_show(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t path_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct acpi_device *acpi_dev = to_acpi_device(dev); return acpi_object_path(acpi_dev->handle, buf); } -static DEVICE_ATTR(path, 0444, acpi_device_path_show, NULL); +static DEVICE_ATTR_RO(path); /* sysfs file that shows description text from the ACPI _STR method */ static ssize_t description_show(struct device *dev, @@ -455,8 +455,8 @@ static ssize_t description_show(struct device *dev, static DEVICE_ATTR_RO(description); static ssize_t -acpi_device_sun_show(struct device *dev, struct device_attribute *attr, - char *buf) { +sun_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct acpi_device *acpi_dev = to_acpi_device(dev); acpi_status status; unsigned long long sun; @@ -467,11 +467,11 @@ acpi_device_sun_show(struct device *dev, struct device_attribute *attr, return sprintf(buf, "%llu\n", sun); } -static DEVICE_ATTR(sun, 0444, acpi_device_sun_show, NULL); +static DEVICE_ATTR_RO(sun); static ssize_t -acpi_device_hrv_show(struct device *dev, struct device_attribute *attr, - char *buf) { +hrv_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct acpi_device *acpi_dev = to_acpi_device(dev); acpi_status status; unsigned long long hrv; @@ -482,7 +482,7 @@ acpi_device_hrv_show(struct device *dev, struct device_attribute *attr, return sprintf(buf, "%llu\n", hrv); } -static DEVICE_ATTR(hrv, 0444, acpi_device_hrv_show, NULL); +static DEVICE_ATTR_RO(hrv); static ssize_t status_show(struct device *dev, struct device_attribute *attr, char *buf) { diff --git a/drivers/acpi/dock.c b/drivers/acpi/dock.c index 24e076f44d23..0937ceab052e 100644 --- a/drivers/acpi/dock.c +++ b/drivers/acpi/dock.c @@ -484,7 +484,7 @@ int dock_notify(struct acpi_device *adev, u32 event) /* * show_docked - read method for "docked" file in sysfs */ -static ssize_t show_docked(struct device *dev, +static ssize_t docked_show(struct device *dev, struct device_attribute *attr, char *buf) { struct dock_station *dock_station = dev->platform_data; @@ -493,25 +493,25 @@ static ssize_t show_docked(struct device *dev, acpi_bus_get_device(dock_station->handle, &adev); return snprintf(buf, PAGE_SIZE, "%u\n", acpi_device_enumerated(adev)); } -static DEVICE_ATTR(docked, S_IRUGO, show_docked, NULL); +static DEVICE_ATTR_RO(docked); /* * show_flags - read method for flags file in sysfs */ -static ssize_t show_flags(struct device *dev, +static ssize_t flags_show(struct device *dev, struct device_attribute *attr, char *buf) { struct dock_station *dock_station = dev->platform_data; return snprintf(buf, PAGE_SIZE, "%d\n", dock_station->flags); } -static DEVICE_ATTR(flags, S_IRUGO, show_flags, NULL); +static DEVICE_ATTR_RO(flags); /* * write_undock - write method for "undock" file in sysfs */ -static ssize_t write_undock(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t undock_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { int ret; struct dock_station *dock_station = dev->platform_data; @@ -525,13 +525,13 @@ static ssize_t write_undock(struct device *dev, struct device_attribute *attr, acpi_scan_lock_release(); return ret ? ret: count; } -static DEVICE_ATTR(undock, S_IWUSR, NULL, write_undock); +static DEVICE_ATTR_WO(undock); /* * show_dock_uid - read method for "uid" file in sysfs */ -static ssize_t show_dock_uid(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t uid_show(struct device *dev, + struct device_attribute *attr, char *buf) { unsigned long long lbuf; struct dock_station *dock_station = dev->platform_data; @@ -542,10 +542,10 @@ static ssize_t show_dock_uid(struct device *dev, return snprintf(buf, PAGE_SIZE, "%llx\n", lbuf); } -static DEVICE_ATTR(uid, S_IRUGO, show_dock_uid, NULL); +static DEVICE_ATTR_RO(uid); -static ssize_t show_dock_type(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t type_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct dock_station *dock_station = dev->platform_data; char *type; @@ -561,7 +561,7 @@ static ssize_t show_dock_type(struct device *dev, return snprintf(buf, PAGE_SIZE, "%s\n", type); } -static DEVICE_ATTR(type, S_IRUGO, show_dock_type, NULL); +static DEVICE_ATTR_RO(type); static struct attribute *dock_attributes[] = { &dev_attr_docked.attr, diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index 0418febc5cf2..327e1b4eb6b0 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -9,6 +9,8 @@ * Author: Matthew Wilcox */ +#define pr_fmt(fmt) "ACPI: OSL: " fmt + #include #include #include @@ -37,6 +39,7 @@ #include "acpica/acnamesp.h" #include "internal.h" +/* Definitions for ACPI_DEBUG_PRINT() */ #define _COMPONENT ACPI_OS_SERVICES ACPI_MODULE_NAME("osl"); @@ -327,7 +330,7 @@ void __iomem __ref acpi_size pg_sz; if (phys > ULONG_MAX) { - printk(KERN_ERR PREFIX "Cannot map memory that high\n"); + pr_err("Cannot map memory that high: 0x%llx\n", phys); return NULL; } @@ -528,13 +531,12 @@ acpi_os_predefined_override(const struct acpi_predefined_names *init_val, *new_val = NULL; if (!memcmp(init_val->name, "_OS_", 4) && strlen(acpi_os_name)) { - printk(KERN_INFO PREFIX "Overriding _OS definition to '%s'\n", - acpi_os_name); + pr_info("Overriding _OS definition to '%s'\n", acpi_os_name); *new_val = acpi_os_name; } if (!memcmp(init_val->name, "_REV", 4) && acpi_rev_override) { - printk(KERN_INFO PREFIX "Overriding _REV return value to 5\n"); + pr_info("Overriding _REV return value to 5\n"); *new_val = (char *)5; } @@ -575,15 +577,14 @@ acpi_os_install_interrupt_handler(u32 gsi, acpi_osd_handler handler, return AE_ALREADY_ACQUIRED; if (acpi_gsi_to_irq(gsi, &irq) < 0) { - printk(KERN_ERR PREFIX "SCI (ACPI GSI %d) not registered\n", - gsi); + pr_err("SCI (ACPI GSI %d) not registered\n", gsi); return AE_OK; } acpi_irq_handler = handler; acpi_irq_context = context; if (request_irq(irq, acpi_irq, IRQF_SHARED, "acpi", acpi_irq)) { - printk(KERN_ERR PREFIX "SCI (IRQ%d) allocation failed\n", irq); + pr_err("SCI (IRQ%d) allocation failed\n", irq); acpi_irq_handler = NULL; return AE_NOT_ACQUIRED; } @@ -1071,7 +1072,7 @@ acpi_status acpi_os_execute(acpi_execute_type type, if (type == OSL_DEBUGGER_MAIN_THREAD) { ret = acpi_debugger_create_thread(function, context); if (ret) { - pr_err("Call to kthread_create() failed.\n"); + pr_err("Kernel thread creation failed\n"); status = AE_ERROR; } goto out_thread; @@ -1121,8 +1122,7 @@ acpi_status acpi_os_execute(acpi_execute_type type, */ ret = queue_work_on(0, queue, &dpc->work); if (!ret) { - printk(KERN_ERR PREFIX - "Call to queue_work() failed.\n"); + pr_err("Unable to queue work\n"); status = AE_ERROR; } err_workqueue: @@ -1165,9 +1165,9 @@ acpi_status acpi_hotplug_schedule(struct acpi_device *adev, u32 src) { struct acpi_hp_work *hpw; - ACPI_DEBUG_PRINT((ACPI_DB_EXEC, - "Scheduling hotplug event (%p, %u) for deferred execution.\n", - adev, src)); + acpi_handle_debug(adev->handle, + "Scheduling hotplug event %u for deferred handling\n", + src); hpw = kmalloc(sizeof(*hpw), GFP_KERNEL); if (!hpw) @@ -1355,7 +1355,7 @@ acpi_status acpi_os_signal(u32 function, void *info) { switch (function) { case ACPI_SIGNAL_FATAL: - printk(KERN_ERR PREFIX "Fatal opcode executed\n"); + pr_err("Fatal opcode executed\n"); break; case ACPI_SIGNAL_BREAKPOINT: /* @@ -1407,7 +1407,7 @@ __setup("acpi_os_name=", acpi_os_name_setup); static int __init acpi_no_auto_serialize_setup(char *str) { acpi_gbl_auto_serialize_methods = FALSE; - pr_info("ACPI: auto-serialization disabled\n"); + pr_info("Auto-serialization disabled\n"); return 1; } @@ -1458,38 +1458,28 @@ __setup("acpi_enforce_resources=", acpi_enforce_resources_setup); int acpi_check_resource_conflict(const struct resource *res) { acpi_adr_space_type space_id; - acpi_size length; - u8 warn = 0; - int clash = 0; if (acpi_enforce_resources == ENFORCE_RESOURCES_NO) return 0; - if (!(res->flags & IORESOURCE_IO) && !(res->flags & IORESOURCE_MEM)) - return 0; if (res->flags & IORESOURCE_IO) space_id = ACPI_ADR_SPACE_SYSTEM_IO; - else + else if (res->flags & IORESOURCE_MEM) space_id = ACPI_ADR_SPACE_SYSTEM_MEMORY; + else + return 0; - length = resource_size(res); - if (acpi_enforce_resources != ENFORCE_RESOURCES_NO) - warn = 1; - clash = acpi_check_address_range(space_id, res->start, length, warn); + if (!acpi_check_address_range(space_id, res->start, resource_size(res), 1)) + return 0; + + pr_info("Resource conflict; ACPI support missing from driver?\n"); + + if (acpi_enforce_resources == ENFORCE_RESOURCES_STRICT) + return -EBUSY; + + if (acpi_enforce_resources == ENFORCE_RESOURCES_LAX) + pr_notice("Resource conflict: System may be unstable or behave erratically\n"); - if (clash) { - if (acpi_enforce_resources != ENFORCE_RESOURCES_NO) { - if (acpi_enforce_resources == ENFORCE_RESOURCES_LAX) - printk(KERN_NOTICE "ACPI: This conflict may" - " cause random problems and system" - " instability\n"); - printk(KERN_INFO "ACPI: If an ACPI driver is available" - " for this device, you should use it instead of" - " the native driver\n"); - } - if (acpi_enforce_resources == ENFORCE_RESOURCES_STRICT) - return -EBUSY; - } return 0; } EXPORT_SYMBOL(acpi_check_resource_conflict); @@ -1722,7 +1712,7 @@ acpi_status acpi_os_release_object(acpi_cache_t * cache, void *object) static int __init acpi_no_static_ssdt_setup(char *s) { acpi_gbl_disable_ssdt_table_install = TRUE; - pr_info("ACPI: static SSDT installation disabled\n"); + pr_info("Static SSDT installation disabled\n"); return 0; } @@ -1731,8 +1721,7 @@ early_param("acpi_no_static_ssdt", acpi_no_static_ssdt_setup); static int __init acpi_disable_return_repair(char *s) { - printk(KERN_NOTICE PREFIX - "ACPI: Predefined validation mechanism disabled\n"); + pr_notice("Predefined validation mechanism disabled\n"); acpi_gbl_disable_auto_repair = TRUE; return 1; @@ -1758,7 +1747,7 @@ acpi_status __init acpi_os_initialize(void) void *rv; rv = acpi_os_map_generic_address(&acpi_gbl_FADT.reset_register); - pr_debug(PREFIX "%s: map reset_reg %s\n", __func__, + pr_debug("%s: Reset register mapping %s\n", __func__, rv ? "successful" : "failed"); } acpi_os_initialized = true; diff --git a/drivers/acpi/platform_profile.c b/drivers/acpi/platform_profile.c new file mode 100644 index 000000000000..4a59c5993bde --- /dev/null +++ b/drivers/acpi/platform_profile.c @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +/* Platform profile sysfs interface */ + +#include +#include +#include +#include +#include +#include + +static struct platform_profile_handler *cur_profile; +static DEFINE_MUTEX(profile_lock); + +static const char * const profile_names[] = { + [PLATFORM_PROFILE_LOW_POWER] = "low-power", + [PLATFORM_PROFILE_COOL] = "cool", + [PLATFORM_PROFILE_QUIET] = "quiet", + [PLATFORM_PROFILE_BALANCED] = "balanced", + [PLATFORM_PROFILE_PERFORMANCE] = "performance", +}; +static_assert(ARRAY_SIZE(profile_names) == PLATFORM_PROFILE_LAST); + +static ssize_t platform_profile_choices_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + int len = 0; + int err, i; + + err = mutex_lock_interruptible(&profile_lock); + if (err) + return err; + + if (!cur_profile) { + mutex_unlock(&profile_lock); + return -ENODEV; + } + + for_each_set_bit(i, cur_profile->choices, PLATFORM_PROFILE_LAST) { + if (len == 0) + len += sysfs_emit_at(buf, len, "%s", profile_names[i]); + else + len += sysfs_emit_at(buf, len, " %s", profile_names[i]); + } + len += sysfs_emit_at(buf, len, "\n"); + mutex_unlock(&profile_lock); + return len; +} + +static ssize_t platform_profile_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + enum platform_profile_option profile = PLATFORM_PROFILE_BALANCED; + int err; + + err = mutex_lock_interruptible(&profile_lock); + if (err) + return err; + + if (!cur_profile) { + mutex_unlock(&profile_lock); + return -ENODEV; + } + + err = cur_profile->profile_get(cur_profile, &profile); + mutex_unlock(&profile_lock); + if (err) + return err; + + /* Check that profile is valid index */ + if (WARN_ON((profile < 0) || (profile >= ARRAY_SIZE(profile_names)))) + return -EIO; + + return sysfs_emit(buf, "%s\n", profile_names[profile]); +} + +static ssize_t platform_profile_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + int err, i; + + err = mutex_lock_interruptible(&profile_lock); + if (err) + return err; + + if (!cur_profile) { + mutex_unlock(&profile_lock); + return -ENODEV; + } + + /* Scan for a matching profile */ + i = sysfs_match_string(profile_names, buf); + if (i < 0) { + mutex_unlock(&profile_lock); + return -EINVAL; + } + + /* Check that platform supports this profile choice */ + if (!test_bit(i, cur_profile->choices)) { + mutex_unlock(&profile_lock); + return -EOPNOTSUPP; + } + + err = cur_profile->profile_set(cur_profile, i); + mutex_unlock(&profile_lock); + if (err) + return err; + return count; +} + +static DEVICE_ATTR_RO(platform_profile_choices); +static DEVICE_ATTR_RW(platform_profile); + +static struct attribute *platform_profile_attrs[] = { + &dev_attr_platform_profile_choices.attr, + &dev_attr_platform_profile.attr, + NULL +}; + +static const struct attribute_group platform_profile_group = { + .attrs = platform_profile_attrs +}; + +void platform_profile_notify(void) +{ + if (!cur_profile) + return; + sysfs_notify(acpi_kobj, NULL, "platform_profile"); +} +EXPORT_SYMBOL_GPL(platform_profile_notify); + +int platform_profile_register(struct platform_profile_handler *pprof) +{ + int err; + + mutex_lock(&profile_lock); + /* We can only have one active profile */ + if (cur_profile) { + mutex_unlock(&profile_lock); + return -EEXIST; + } + + /* Sanity check the profile handler field are set */ + if (!pprof || bitmap_empty(pprof->choices, PLATFORM_PROFILE_LAST) || + !pprof->profile_set || !pprof->profile_get) { + mutex_unlock(&profile_lock); + return -EINVAL; + } + + err = sysfs_create_group(acpi_kobj, &platform_profile_group); + if (err) { + mutex_unlock(&profile_lock); + return err; + } + + cur_profile = pprof; + mutex_unlock(&profile_lock); + return 0; +} +EXPORT_SYMBOL_GPL(platform_profile_register); + +int platform_profile_remove(void) +{ + sysfs_remove_group(acpi_kobj, &platform_profile_group); + + mutex_lock(&profile_lock); + cur_profile = NULL; + mutex_unlock(&profile_lock); + return 0; +} +EXPORT_SYMBOL_GPL(platform_profile_remove); + +MODULE_AUTHOR("Mark Pearson "); +MODULE_LICENSE("GPL"); diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index 189a0d4c6d06..9b608b55d2b2 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -21,6 +21,8 @@ * may be shared by multiple devices. */ +#define pr_fmt(fmt) "ACPI: PM: " fmt + #include #include #include @@ -32,8 +34,6 @@ #include "sleep.h" #include "internal.h" -#define _COMPONENT ACPI_POWER_COMPONENT -ACPI_MODULE_NAME("power"); #define ACPI_POWER_CLASS "power_resource" #define ACPI_POWER_DEVICE_NAME "Power Resource" #define ACPI_POWER_RESOURCE_STATE_OFF 0x00 @@ -181,9 +181,6 @@ static int acpi_power_get_state(acpi_handle handle, int *state) { acpi_status status = AE_OK; unsigned long long sta = 0; - char node_name[5]; - struct acpi_buffer buffer = { sizeof(node_name), node_name }; - if (!handle || !state) return -EINVAL; @@ -195,11 +192,8 @@ static int acpi_power_get_state(acpi_handle handle, int *state) *state = (sta & 0x01)?ACPI_POWER_RESOURCE_STATE_ON: ACPI_POWER_RESOURCE_STATE_OFF; - acpi_get_name(handle, ACPI_SINGLE_NAME, &buffer); - - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Resource [%s] is %s\n", - node_name, - *state ? "on" : "off")); + acpi_handle_debug(handle, "Power resource is %s\n", + *state ? "on" : "off"); return 0; } @@ -229,8 +223,7 @@ static int acpi_power_get_list_state(struct list_head *list, int *state) break; } - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Resource list is %s\n", - cur_state ? "on" : "off")); + pr_debug("Power resource list is %s\n", cur_state ? "on" : "off"); *state = cur_state; return 0; @@ -357,8 +350,7 @@ static int __acpi_power_on(struct acpi_power_resource *resource) if (ACPI_FAILURE(status)) return -ENODEV; - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Power resource [%s] turned on\n", - resource->name)); + pr_debug("Power resource [%s] turned on\n", resource->name); /* * If there are other dependents on this power resource we need to @@ -383,9 +375,7 @@ static int acpi_power_on_unlocked(struct acpi_power_resource *resource) int result = 0; if (resource->ref_count++) { - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Power resource [%s] already on\n", - resource->name)); + pr_debug("Power resource [%s] already on\n", resource->name); } else { result = __acpi_power_on(resource); if (result) @@ -413,8 +403,8 @@ static int __acpi_power_off(struct acpi_power_resource *resource) if (ACPI_FAILURE(status)) return -ENODEV; - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Power resource [%s] turned off\n", - resource->name)); + pr_debug("Power resource [%s] turned off\n", resource->name); + return 0; } @@ -423,16 +413,12 @@ static int acpi_power_off_unlocked(struct acpi_power_resource *resource) int result = 0; if (!resource->ref_count) { - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Power resource [%s] already off\n", - resource->name)); + pr_debug("Power resource [%s] already off\n", resource->name); return 0; } if (--resource->ref_count) { - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Power resource [%s] still in use\n", - resource->name)); + pr_debug("Power resource [%s] still in use\n", resource->name); } else { result = __acpi_power_off(resource); if (result) @@ -672,7 +658,7 @@ int acpi_device_sleep_wake(struct acpi_device *dev, if (ACPI_SUCCESS(status)) { return 0; } else if (status != AE_NOT_FOUND) { - printk(KERN_ERR PREFIX "_DSW execution failed\n"); + acpi_handle_info(dev->handle, "_DSW execution failed\n"); dev->wakeup.flags.valid = 0; return -ENODEV; } @@ -680,7 +666,7 @@ int acpi_device_sleep_wake(struct acpi_device *dev, /* Execute _PSW */ status = acpi_execute_simple_method(dev->handle, "_PSW", enable); if (ACPI_FAILURE(status) && (status != AE_NOT_FOUND)) { - printk(KERN_ERR PREFIX "_PSW execution failed\n"); + acpi_handle_info(dev->handle, "_PSW execution failed\n"); dev->wakeup.flags.valid = 0; return -ENODEV; } @@ -886,15 +872,16 @@ static void acpi_release_power_resource(struct device *dev) kfree(resource); } -static ssize_t acpi_power_in_use_show(struct device *dev, - struct device_attribute *attr, - char *buf) { +static ssize_t resource_in_use_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ struct acpi_power_resource *resource; resource = to_power_resource(to_acpi_device(dev)); return sprintf(buf, "%u\n", !!resource->ref_count); } -static DEVICE_ATTR(resource_in_use, 0444, acpi_power_in_use_show, NULL); +static DEVICE_ATTR_RO(resource_in_use); static void acpi_power_sysfs_remove(struct acpi_device *device) { @@ -960,8 +947,8 @@ int acpi_add_power_resource(acpi_handle handle) if (result) goto err; - printk(KERN_INFO PREFIX "%s [%s] (%s)\n", acpi_device_name(device), - acpi_device_bid(device), state ? "on" : "off"); + pr_info("%s [%s] (%s)\n", acpi_device_name(device), + acpi_device_bid(device), state ? "on" : "off"); device->flags.match_driver = true; result = acpi_device_add(device, acpi_release_power_resource); diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index 24e87b630573..e312ebaed8db 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -564,7 +564,7 @@ int acpi_node_prop_get(const struct fwnode_handle *fwnode, /** * acpi_data_get_property_array - return an ACPI array property with given name - * @adev: ACPI data object to get the property from + * @data: ACPI data object to get the property from * @name: Name of the property * @type: Expected type of array elements * @obj: Location to store a pointer to the property value (if not NULL) @@ -787,9 +787,6 @@ static int acpi_data_prop_read_single(const struct acpi_device_data *data, const union acpi_object *obj; int ret; - if (!val) - return -EINVAL; - if (proptype >= DEV_PROP_U8 && proptype <= DEV_PROP_U64) { ret = acpi_data_get_property(data, propname, ACPI_TYPE_INTEGER, &obj); if (ret) @@ -799,28 +796,43 @@ static int acpi_data_prop_read_single(const struct acpi_device_data *data, case DEV_PROP_U8: if (obj->integer.value > U8_MAX) return -EOVERFLOW; - *(u8 *)val = obj->integer.value; + + if (val) + *(u8 *)val = obj->integer.value; + break; case DEV_PROP_U16: if (obj->integer.value > U16_MAX) return -EOVERFLOW; - *(u16 *)val = obj->integer.value; + + if (val) + *(u16 *)val = obj->integer.value; + break; case DEV_PROP_U32: if (obj->integer.value > U32_MAX) return -EOVERFLOW; - *(u32 *)val = obj->integer.value; + + if (val) + *(u32 *)val = obj->integer.value; + break; default: - *(u64 *)val = obj->integer.value; + if (val) + *(u64 *)val = obj->integer.value; + break; } + + if (!val) + return 1; } else if (proptype == DEV_PROP_STRING) { ret = acpi_data_get_property(data, propname, ACPI_TYPE_STRING, &obj); if (ret) return ret; - *(char **)val = obj->string.pointer; + if (val) + *(char **)val = obj->string.pointer; return 1; } else { @@ -829,20 +841,6 @@ static int acpi_data_prop_read_single(const struct acpi_device_data *data, return ret; } -int acpi_dev_prop_read_single(struct acpi_device *adev, const char *propname, - enum dev_prop_type proptype, void *val) -{ - int ret; - - if (!adev) - return -EINVAL; - - ret = acpi_data_prop_read_single(&adev->data, propname, proptype, val); - if (ret < 0 || proptype != ACPI_TYPE_STRING) - return ret; - return 0; -} - static int acpi_copy_property_array_u8(const union acpi_object *items, u8 *val, size_t nval) { @@ -928,10 +926,20 @@ static int acpi_data_prop_read(const struct acpi_device_data *data, const union acpi_object *items; int ret; - if (val && nval == 1) { + if (nval == 1 || !val) { ret = acpi_data_prop_read_single(data, propname, proptype, val); - if (ret >= 0) + /* + * The overflow error means that the property is there and it is + * single-value, but its type does not match, so return. + */ + if (ret >= 0 || ret == -EOVERFLOW) return ret; + + /* + * Reading this property as a single-value one failed, but its + * value may still be represented as one-element array, so + * continue. + */ } ret = acpi_data_get_property_array(data, propname, ACPI_TYPE_ANY, &obj); @@ -973,12 +981,6 @@ static int acpi_data_prop_read(const struct acpi_device_data *data, return ret; } -int acpi_dev_prop_read(const struct acpi_device *adev, const char *propname, - enum dev_prop_type proptype, void *val, size_t nval) -{ - return adev ? acpi_data_prop_read(&adev->data, propname, proptype, val, nval) : -EINVAL; -} - /** * acpi_node_prop_read - retrieve the value of an ACPI property with given name. * @fwnode: Firmware node to get the property from. @@ -991,9 +993,9 @@ int acpi_dev_prop_read(const struct acpi_device *adev, const char *propname, * of the property. Otherwise, read at most @nval values to the array at the * location pointed to by @val. */ -int acpi_node_prop_read(const struct fwnode_handle *fwnode, - const char *propname, enum dev_prop_type proptype, - void *val, size_t nval) +static int acpi_node_prop_read(const struct fwnode_handle *fwnode, + const char *propname, enum dev_prop_type proptype, + void *val, size_t nval) { return acpi_data_prop_read(acpi_device_data_of_node(fwnode), propname, proptype, val, nval); @@ -1210,8 +1212,7 @@ static struct fwnode_handle *acpi_graph_get_child_prop_value( /** * acpi_graph_get_remote_endpoint - Parses and returns remote end of an endpoint - * @fwnode: Endpoint firmware node pointing to a remote device - * @endpoint: Firmware node of remote endpoint is filled here if not %NULL + * @__fwnode: Endpoint firmware node pointing to a remote device * * Returns the remote endpoint corresponding to @__fwnode. NULL on error. */ diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 22566b4b3150..a184529d8fa4 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -19,8 +19,6 @@ #include "internal.h" -#define _COMPONENT ACPI_BUS_COMPONENT -ACPI_MODULE_NAME("scan"); extern struct acpi_device *acpi_root; #define ACPI_BUS_CLASS "system_bus" @@ -265,8 +263,7 @@ static int acpi_scan_hot_remove(struct acpi_device *device) return error; } - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Hot-removing device %s...\n", dev_name(&device->dev))); + acpi_handle_debug(handle, "Ejecting\n"); acpi_bus_trim(device); @@ -578,29 +575,31 @@ static void acpi_scan_drop_device(acpi_handle handle, void *context) mutex_unlock(&acpi_device_del_lock); } -static int acpi_get_device_data(acpi_handle handle, struct acpi_device **device, - void (*callback)(void *)) +static struct acpi_device *handle_to_device(acpi_handle handle, + void (*callback)(void *)) { + struct acpi_device *adev = NULL; acpi_status status; - if (!device) - return -EINVAL; - - *device = NULL; - status = acpi_get_data_full(handle, acpi_scan_drop_device, - (void **)device, callback); - if (ACPI_FAILURE(status) || !*device) { - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "No context for object [%p]\n", - handle)); - return -ENODEV; + (void **)&adev, callback); + if (ACPI_FAILURE(status) || !adev) { + acpi_handle_debug(handle, "No context!\n"); + return NULL; } - return 0; + return adev; } int acpi_bus_get_device(acpi_handle handle, struct acpi_device **device) { - return acpi_get_device_data(handle, device, NULL); + if (!device) + return -EINVAL; + + *device = handle_to_device(handle, NULL); + if (!*device) + return -ENODEV; + + return 0; } EXPORT_SYMBOL(acpi_bus_get_device); @@ -612,10 +611,7 @@ static void get_acpi_device(void *dev) struct acpi_device *acpi_bus_get_acpi_device(acpi_handle handle) { - struct acpi_device *adev = NULL; - - acpi_get_device_data(handle, &adev, get_acpi_device); - return adev; + return handle_to_device(handle, get_acpi_device); } void acpi_bus_put_acpi_device(struct acpi_device *adev) @@ -623,12 +619,23 @@ void acpi_bus_put_acpi_device(struct acpi_device *adev) put_device(&adev->dev); } +static struct acpi_device_bus_id *acpi_device_bus_id_match(const char *dev_id) +{ + struct acpi_device_bus_id *acpi_device_bus_id; + + /* Find suitable bus_id and instance number in acpi_bus_id_list. */ + list_for_each_entry(acpi_device_bus_id, &acpi_bus_id_list, node) { + if (!strcmp(acpi_device_bus_id->bus_id, dev_id)) + return acpi_device_bus_id; + } + return NULL; +} + int acpi_device_add(struct acpi_device *device, void (*release)(struct device *)) { + struct acpi_device_bus_id *acpi_device_bus_id; int result; - struct acpi_device_bus_id *acpi_device_bus_id, *new_bus_id; - int found = 0; if (device->handle) { acpi_status status; @@ -654,38 +661,26 @@ int acpi_device_add(struct acpi_device *device, INIT_LIST_HEAD(&device->del_list); mutex_init(&device->physical_node_lock); - new_bus_id = kzalloc(sizeof(struct acpi_device_bus_id), GFP_KERNEL); - if (!new_bus_id) { - pr_err(PREFIX "Memory allocation error\n"); - result = -ENOMEM; - goto err_detach; - } - mutex_lock(&acpi_device_lock); - /* - * Find suitable bus_id and instance number in acpi_bus_id_list - * If failed, create one and link it into acpi_bus_id_list - */ - list_for_each_entry(acpi_device_bus_id, &acpi_bus_id_list, node) { - if (!strcmp(acpi_device_bus_id->bus_id, - acpi_device_hid(device))) { - acpi_device_bus_id->instance_no++; - found = 1; - kfree(new_bus_id); - break; + + acpi_device_bus_id = acpi_device_bus_id_match(acpi_device_hid(device)); + if (acpi_device_bus_id) { + acpi_device_bus_id->instance_no++; + } else { + acpi_device_bus_id = kzalloc(sizeof(*acpi_device_bus_id), + GFP_KERNEL); + if (!acpi_device_bus_id) { + result = -ENOMEM; + goto err_unlock; } - } - if (!found) { - acpi_device_bus_id = new_bus_id; acpi_device_bus_id->bus_id = kstrdup_const(acpi_device_hid(device), GFP_KERNEL); if (!acpi_device_bus_id->bus_id) { - pr_err(PREFIX "Memory allocation error for bus id\n"); + kfree(acpi_device_bus_id); result = -ENOMEM; - goto err_free_new_bus_id; + goto err_unlock; } - acpi_device_bus_id->instance_no = 0; list_add_tail(&acpi_device_bus_id->node, &acpi_bus_id_list); } dev_set_name(&device->dev, "%s:%02x", acpi_device_bus_id->bus_id, acpi_device_bus_id->instance_no); @@ -695,10 +690,12 @@ int acpi_device_add(struct acpi_device *device, if (device->wakeup.flags.valid) list_add_tail(&device->wakeup_list, &acpi_wakeup_device_list); + mutex_unlock(&acpi_device_lock); if (device->parent) device->dev.parent = &device->parent->dev; + device->dev.bus = &acpi_bus_type; device->dev.release = release; result = device_add(&device->dev); @@ -714,20 +711,19 @@ int acpi_device_add(struct acpi_device *device, return 0; - err: +err: mutex_lock(&acpi_device_lock); + if (device->parent) list_del(&device->node); + list_del(&device->wakeup_list); - err_free_new_bus_id: - if (!found) - kfree(new_bus_id); - +err_unlock: mutex_unlock(&acpi_device_lock); - err_detach: acpi_detach_data(device->handle, acpi_scan_drop_device); + return result; } @@ -830,7 +826,8 @@ static int acpi_bus_extract_wakeup_device_power_package(struct acpi_device *dev) /* _PRW */ status = acpi_evaluate_object(handle, "_PRW", NULL, &buffer); if (ACPI_FAILURE(status)) { - ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PRW")); + acpi_handle_info(handle, "_PRW evaluation failed: %s\n", + acpi_format_exception(status)); return err; } @@ -935,7 +932,7 @@ static void acpi_bus_get_wakeup_device_flags(struct acpi_device *device) err = acpi_bus_extract_wakeup_device_power_package(device); if (err) { - dev_err(&device->dev, "_PRW evaluation error: %d\n", err); + dev_err(&device->dev, "Unable to extract wakeup power resources"); return; } @@ -1171,8 +1168,7 @@ acpi_backlight_cap_match(acpi_handle handle, u32 level, void *context, if (acpi_has_method(handle, "_BCM") && acpi_has_method(handle, "_BCL")) { - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found generic backlight " - "support\n")); + acpi_handle_debug(handle, "Found generic backlight support\n"); *cap |= ACPI_VIDEO_BACKLIGHT; /* We have backlight support, no need to scan further */ return AE_CTRL_TERMINATE; @@ -1663,17 +1659,15 @@ static int acpi_add_single_object(struct acpi_device **child, acpi_handle handle, int type, unsigned long long sta) { - int result; - struct acpi_device *device; - struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; struct acpi_device_info *info = NULL; + struct acpi_device *device; + int result; if (handle != ACPI_ROOT_OBJECT && type == ACPI_BUS_TYPE_DEVICE) acpi_get_object_info(handle, &info); device = kzalloc(sizeof(struct acpi_device), GFP_KERNEL); if (!device) { - printk(KERN_ERR PREFIX "Memory allocation error\n"); kfree(info); return -ENOMEM; } @@ -1700,11 +1694,11 @@ static int acpi_add_single_object(struct acpi_device **child, acpi_power_add_remove_device(device, true); acpi_device_add_finalize(device); - acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer); - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Added %s [%s] parent %s\n", - dev_name(&device->dev), (char *) buffer.pointer, - device->parent ? dev_name(&device->parent->dev) : "(null)")); - kfree(buffer.pointer); + + acpi_handle_debug(handle, "Added as %s, parent %s\n", + dev_name(&device->dev), device->parent ? + dev_name(&device->parent->dev) : "(null)"); + *child = device; return 0; } diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c index a5cc4f3bb1e3..8baf7644a0d0 100644 --- a/drivers/acpi/sysfs.c +++ b/drivers/acpi/sysfs.c @@ -52,19 +52,12 @@ static const struct acpi_dlayer acpi_debug_layers[] = { ACPI_DEBUG_INIT(ACPI_COMPILER), ACPI_DEBUG_INIT(ACPI_TOOLS), - ACPI_DEBUG_INIT(ACPI_BUS_COMPONENT), - ACPI_DEBUG_INIT(ACPI_AC_COMPONENT), - ACPI_DEBUG_INIT(ACPI_BATTERY_COMPONENT), - ACPI_DEBUG_INIT(ACPI_BUTTON_COMPONENT), ACPI_DEBUG_INIT(ACPI_SBS_COMPONENT), ACPI_DEBUG_INIT(ACPI_FAN_COMPONENT), ACPI_DEBUG_INIT(ACPI_PCI_COMPONENT), - ACPI_DEBUG_INIT(ACPI_POWER_COMPONENT), ACPI_DEBUG_INIT(ACPI_CONTAINER_COMPONENT), ACPI_DEBUG_INIT(ACPI_SYSTEM_COMPONENT), - ACPI_DEBUG_INIT(ACPI_THERMAL_COMPONENT), ACPI_DEBUG_INIT(ACPI_MEMORY_DEVICE_COMPONENT), - ACPI_DEBUG_INIT(ACPI_VIDEO_COMPONENT), ACPI_DEBUG_INIT(ACPI_PROCESSOR_COMPONENT), }; diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c index 859b1de31ddc..4f906380b031 100644 --- a/drivers/acpi/thermal.c +++ b/drivers/acpi/thermal.c @@ -13,6 +13,8 @@ * concepts of 'multiple limiters', upper/lower limits, etc. */ +#define pr_fmt(fmt) "ACPI: thermal: " fmt + #include #include #include @@ -29,8 +31,6 @@ #include #include -#define PREFIX "ACPI: " - #define ACPI_THERMAL_CLASS "thermal_zone" #define ACPI_THERMAL_DEVICE_NAME "Thermal Zone" #define ACPI_THERMAL_NOTIFY_TEMPERATURE 0x80 @@ -43,9 +43,6 @@ #define ACPI_THERMAL_MAX_ACTIVE 10 #define ACPI_THERMAL_MAX_LIMIT_STR_LEN 65 -#define _COMPONENT ACPI_THERMAL_COMPONENT -ACPI_MODULE_NAME("thermal"); - MODULE_AUTHOR("Paul Diefenbaugh"); MODULE_DESCRIPTION("ACPI Thermal Zone Driver"); MODULE_LICENSE("GPL"); @@ -197,8 +194,9 @@ static int acpi_thermal_get_temperature(struct acpi_thermal *tz) return -ENODEV; tz->temperature = tmp; - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Temperature is %lu dK\n", - tz->temperature)); + + acpi_handle_debug(tz->device->handle, "Temperature is %lu dK\n", + tz->temperature); return 0; } @@ -216,8 +214,8 @@ static int acpi_thermal_get_polling_frequency(struct acpi_thermal *tz) return -ENODEV; tz->polling_frequency = tmp; - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Polling frequency is %lu dS\n", - tz->polling_frequency)); + acpi_handle_debug(tz->device->handle, "Polling frequency is %lu dS\n", + tz->polling_frequency); return 0; } @@ -254,12 +252,12 @@ static int acpi_thermal_set_cooling_mode(struct acpi_thermal *tz, int mode) * 2.TODO: Devices listed in _PSL, _ALx, _TZD may change. * We need to re-bind the cooling devices of a thermal zone when this occurs. */ -#define ACPI_THERMAL_TRIPS_EXCEPTION(flags, str) \ +#define ACPI_THERMAL_TRIPS_EXCEPTION(flags, tz, str) \ do { \ if (flags != ACPI_TRIPS_INIT) \ - ACPI_EXCEPTION((AE_INFO, AE_ERROR, \ + acpi_handle_info(tz->device->handle, \ "ACPI thermal trip point %s changed\n" \ - "Please send acpidump to linux-acpi@vger.kernel.org", str)); \ + "Please report to linux-acpi@vger.kernel.org\n", str); \ } while (0) static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag) @@ -283,17 +281,17 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag) */ if (ACPI_FAILURE(status)) { tz->trips.critical.flags.valid = 0; - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "No critical threshold\n")); + acpi_handle_debug(tz->device->handle, + "No critical threshold\n"); } else if (tmp <= 2732) { - pr_warn(FW_BUG "Invalid critical threshold (%llu)\n", + pr_info(FW_BUG "Invalid critical threshold (%llu)\n", tmp); tz->trips.critical.flags.valid = 0; } else { tz->trips.critical.flags.valid = 1; - ACPI_DEBUG_PRINT((ACPI_DB_INFO, + acpi_handle_debug(tz->device->handle, "Found critical threshold [%lu]\n", - tz->trips.critical.temperature)); + tz->trips.critical.temperature); } if (tz->trips.critical.flags.valid == 1) { if (crt == -1) { @@ -305,8 +303,8 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag) * Allow override critical threshold */ if (crt_k > tz->trips.critical.temperature) - pr_warn(PREFIX "Critical threshold %d C\n", - crt); + pr_info("Critical threshold %d C\n", crt); + tz->trips.critical.temperature = crt_k; } } @@ -318,14 +316,14 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag) "_HOT", NULL, &tmp); if (ACPI_FAILURE(status)) { tz->trips.hot.flags.valid = 0; - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "No hot threshold\n")); + acpi_handle_debug(tz->device->handle, + "No hot threshold\n"); } else { tz->trips.hot.temperature = tmp; tz->trips.hot.flags.valid = 1; - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Found hot threshold [%lu]\n", - tz->trips.hot.temperature)); + acpi_handle_debug(tz->device->handle, + "Found hot threshold [%lu]\n", + tz->trips.hot.temperature); } } @@ -378,7 +376,8 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag) status = acpi_evaluate_reference(tz->device->handle, "_PSL", NULL, &devices); if (ACPI_FAILURE(status)) { - pr_warn(PREFIX "Invalid passive threshold\n"); + acpi_handle_info(tz->device->handle, + "Invalid passive threshold\n"); tz->trips.passive.flags.valid = 0; } else @@ -388,12 +387,12 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag) sizeof(struct acpi_handle_list))) { memcpy(&tz->trips.passive.devices, &devices, sizeof(struct acpi_handle_list)); - ACPI_THERMAL_TRIPS_EXCEPTION(flag, "device"); + ACPI_THERMAL_TRIPS_EXCEPTION(flag, tz, "device"); } } if ((flag & ACPI_TRIPS_PASSIVE) || (flag & ACPI_TRIPS_DEVICES)) { if (valid != tz->trips.passive.flags.valid) - ACPI_THERMAL_TRIPS_EXCEPTION(flag, "state"); + ACPI_THERMAL_TRIPS_EXCEPTION(flag, tz, "state"); } /* Active (optional) */ @@ -440,8 +439,8 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag) status = acpi_evaluate_reference(tz->device->handle, name, NULL, &devices); if (ACPI_FAILURE(status)) { - pr_warn(PREFIX "Invalid active%d threshold\n", - i); + acpi_handle_info(tz->device->handle, + "Invalid active%d threshold\n", i); tz->trips.active[i].flags.valid = 0; } else @@ -451,12 +450,12 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag) sizeof(struct acpi_handle_list))) { memcpy(&tz->trips.active[i].devices, &devices, sizeof(struct acpi_handle_list)); - ACPI_THERMAL_TRIPS_EXCEPTION(flag, "device"); + ACPI_THERMAL_TRIPS_EXCEPTION(flag, tz, "device"); } } if ((flag & ACPI_TRIPS_ACTIVE) || (flag & ACPI_TRIPS_DEVICES)) if (valid != tz->trips.active[i].flags.valid) - ACPI_THERMAL_TRIPS_EXCEPTION(flag, "state"); + ACPI_THERMAL_TRIPS_EXCEPTION(flag, tz, "state"); if (!tz->trips.active[i].flags.valid) break; @@ -469,7 +468,7 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag) if (ACPI_SUCCESS(status) && memcmp(&tz->devices, &devices, sizeof(devices))) { tz->devices = devices; - ACPI_THERMAL_TRIPS_EXCEPTION(flag, "device"); + ACPI_THERMAL_TRIPS_EXCEPTION(flag, tz, "device"); } } @@ -925,8 +924,8 @@ static void acpi_thermal_notify(struct acpi_device *device, u32 event) dev_name(&device->dev), event, 0); break; default: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Unsupported event [0x%x]\n", event)); + acpi_handle_debug(device->handle, "Unsupported event [0x%x]\n", + event); break; } } @@ -1074,7 +1073,7 @@ static int acpi_thermal_add(struct acpi_device *device) mutex_init(&tz->thermal_check_lock); INIT_WORK(&tz->thermal_check_work, acpi_thermal_check_fn); - pr_info(PREFIX "%s [%s] (%ld C)\n", acpi_device_name(device), + pr_info("%s [%s] (%ld C)\n", acpi_device_name(device), acpi_device_bid(device), deci_kelvin_to_celsius(tz->temperature)); goto end; @@ -1146,24 +1145,24 @@ static int acpi_thermal_resume(struct device *dev) static int thermal_act(const struct dmi_system_id *d) { if (act == 0) { - pr_notice(PREFIX "%s detected: " - "disabling all active thermal trip points\n", d->ident); + pr_notice("%s detected: disabling all active thermal trip points\n", + d->ident); act = -1; } return 0; } static int thermal_nocrt(const struct dmi_system_id *d) { - pr_notice(PREFIX "%s detected: " - "disabling all critical thermal trip point actions.\n", d->ident); + pr_notice("%s detected: disabling all critical thermal trip point actions.\n", + d->ident); nocrt = 1; return 0; } static int thermal_tzp(const struct dmi_system_id *d) { if (tzp == 0) { - pr_notice(PREFIX "%s detected: " - "enabling thermal zone polling\n", d->ident); + pr_notice("%s detected: enabling thermal zone polling\n", + d->ident); tzp = 300; /* 300 dS = 30 Seconds */ } return 0; @@ -1171,8 +1170,8 @@ static int thermal_tzp(const struct dmi_system_id *d) { static int thermal_psv(const struct dmi_system_id *d) { if (psv == 0) { - pr_notice(PREFIX "%s detected: " - "disabling all passive thermal trip points\n", d->ident); + pr_notice("%s detected: disabling all passive thermal trip points\n", + d->ident); psv = -1; } return 0; @@ -1225,7 +1224,7 @@ static int __init acpi_thermal_init(void) dmi_check_system(thermal_dmi_table); if (off) { - pr_notice(PREFIX "thermal control disabled\n"); + pr_notice("thermal control disabled\n"); return -ENODEV; } diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c index d5411a166685..cdbc6bf9e4ef 100644 --- a/drivers/acpi/utils.c +++ b/drivers/acpi/utils.c @@ -6,6 +6,8 @@ * Copyright (C) 2001, 2002 Paul Diefenbaugh */ +#define pr_fmt(fmt) "ACPI: utils: " fmt + #include #include #include @@ -18,24 +20,12 @@ #include "internal.h" #include "sleep.h" -#define _COMPONENT ACPI_BUS_COMPONENT -ACPI_MODULE_NAME("utils"); - /* -------------------------------------------------------------------------- Object Evaluation Helpers -------------------------------------------------------------------------- */ -static void -acpi_util_eval_error(acpi_handle h, acpi_string p, acpi_status s) +static void acpi_util_eval_error(acpi_handle h, acpi_string p, acpi_status s) { -#ifdef ACPI_DEBUG_OUTPUT - char prefix[80] = {'\0'}; - struct acpi_buffer buffer = {sizeof(prefix), prefix}; - acpi_get_name(h, ACPI_FULL_PATHNAME, &buffer); - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Evaluate [%s.%s]: %s\n", - (char *) prefix, p, acpi_format_exception(s))); -#else - return; -#endif + acpi_handle_debug(h, "Evaluate [%s]: %s\n", p, acpi_format_exception(s)); } acpi_status @@ -53,25 +43,24 @@ acpi_extract_package(union acpi_object *package, if (!package || (package->type != ACPI_TYPE_PACKAGE) || (package->package.count < 1)) { - printk(KERN_WARNING PREFIX "Invalid package argument\n"); + pr_debug("Invalid package argument\n"); return AE_BAD_PARAMETER; } if (!format || !format->pointer || (format->length < 1)) { - printk(KERN_WARNING PREFIX "Invalid format argument\n"); + pr_debug("Invalid format argument\n"); return AE_BAD_PARAMETER; } if (!buffer) { - printk(KERN_WARNING PREFIX "Invalid buffer argument\n"); + pr_debug("Invalid buffer argument\n"); return AE_BAD_PARAMETER; } format_count = (format->length / sizeof(char)) - 1; if (format_count > package->package.count) { - printk(KERN_WARNING PREFIX "Format specifies more objects [%d]" - " than exist in package [%d].\n", - format_count, package->package.count); + pr_debug("Format specifies more objects [%d] than present [%d]\n", + format_count, package->package.count); return AE_BAD_DATA; } @@ -99,10 +88,8 @@ acpi_extract_package(union acpi_object *package, tail_offset += sizeof(char *); break; default: - printk(KERN_WARNING PREFIX "Invalid package element" - " [%d]: got number, expecting" - " [%c]\n", - i, format_string[i]); + pr_debug("Invalid package element [%d]: got number, expected [%c]\n", + i, format_string[i]); return AE_BAD_DATA; } break; @@ -123,10 +110,8 @@ acpi_extract_package(union acpi_object *package, tail_offset += sizeof(u8 *); break; default: - printk(KERN_WARNING PREFIX "Invalid package element" - " [%d] got string/buffer," - " expecting [%c]\n", - i, format_string[i]); + pr_debug("Invalid package element [%d] got string/buffer, expected [%c]\n", + i, format_string[i]); return AE_BAD_DATA; } break; @@ -137,19 +122,15 @@ acpi_extract_package(union acpi_object *package, tail_offset += sizeof(void *); break; default: - printk(KERN_WARNING PREFIX "Invalid package element" - " [%d] got reference," - " expecting [%c]\n", - i, format_string[i]); + pr_debug("Invalid package element [%d] got reference, expected [%c]\n", + i, format_string[i]); return AE_BAD_DATA; } break; case ACPI_TYPE_PACKAGE: default: - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Found unsupported element at index=%d\n", - i)); + pr_debug("Unsupported element at index=%d\n", i); /* TBD: handle nested packages... */ return AE_SUPPORT; } @@ -289,7 +270,7 @@ acpi_evaluate_integer(acpi_handle handle, *data = element.integer.value; - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Return value [%llu]\n", *data)); + acpi_handle_debug(handle, "Return value [%llu]\n", *data); return AE_OK; } @@ -363,8 +344,7 @@ acpi_evaluate_reference(acpi_handle handle, /* Get the acpi_handle. */ list->handles[i] = element->reference.handle; - ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found reference [%p]\n", - list->handles[i])); + acpi_handle_debug(list->handles[i], "Found in reference list\n"); } end: diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c index ced6863a16a5..84d5acb6301b 100644 --- a/drivers/base/power/clock_ops.c +++ b/drivers/base/power/clock_ops.c @@ -23,6 +23,7 @@ enum pce_status { PCE_STATUS_NONE = 0, PCE_STATUS_ACQUIRED, + PCE_STATUS_PREPARED, PCE_STATUS_ENABLED, PCE_STATUS_ERROR, }; @@ -32,8 +33,112 @@ struct pm_clock_entry { char *con_id; struct clk *clk; enum pce_status status; + bool enabled_when_prepared; }; +/** + * pm_clk_list_lock - ensure exclusive access for modifying the PM clock + * entry list. + * @psd: pm_subsys_data instance corresponding to the PM clock entry list + * and clk_op_might_sleep count to be modified. + * + * Get exclusive access before modifying the PM clock entry list and the + * clock_op_might_sleep count to guard against concurrent modifications. + * This also protects against a concurrent clock_op_might_sleep and PM clock + * entry list usage in pm_clk_suspend()/pm_clk_resume() that may or may not + * happen in atomic context, hence both the mutex and the spinlock must be + * taken here. + */ +static void pm_clk_list_lock(struct pm_subsys_data *psd) + __acquires(&psd->lock) +{ + mutex_lock(&psd->clock_mutex); + spin_lock_irq(&psd->lock); +} + +/** + * pm_clk_list_unlock - counterpart to pm_clk_list_lock(). + * @psd: the same pm_subsys_data instance previously passed to + * pm_clk_list_lock(). + */ +static void pm_clk_list_unlock(struct pm_subsys_data *psd) + __releases(&psd->lock) +{ + spin_unlock_irq(&psd->lock); + mutex_unlock(&psd->clock_mutex); +} + +/** + * pm_clk_op_lock - ensure exclusive access for performing clock operations. + * @psd: pm_subsys_data instance corresponding to the PM clock entry list + * and clk_op_might_sleep count being used. + * @flags: stored irq flags. + * @fn: string for the caller function's name. + * + * This is used by pm_clk_suspend() and pm_clk_resume() to guard + * against concurrent modifications to the clock entry list and the + * clock_op_might_sleep count. If clock_op_might_sleep is != 0 then + * only the mutex can be locked and those functions can only be used in + * non atomic context. If clock_op_might_sleep == 0 then these functions + * may be used in any context and only the spinlock can be locked. + * Returns -EINVAL if called in atomic context when clock ops might sleep. + */ +static int pm_clk_op_lock(struct pm_subsys_data *psd, unsigned long *flags, + const char *fn) + /* sparse annotations don't work here as exit state isn't static */ +{ + bool atomic_context = in_atomic() || irqs_disabled(); + +try_again: + spin_lock_irqsave(&psd->lock, *flags); + if (!psd->clock_op_might_sleep) { + /* the __release is there to work around sparse limitations */ + __release(&psd->lock); + return 0; + } + + /* bail out if in atomic context */ + if (atomic_context) { + pr_err("%s: atomic context with clock_ops_might_sleep = %d", + fn, psd->clock_op_might_sleep); + spin_unlock_irqrestore(&psd->lock, *flags); + might_sleep(); + return -EPERM; + } + + /* we must switch to the mutex */ + spin_unlock_irqrestore(&psd->lock, *flags); + mutex_lock(&psd->clock_mutex); + + /* + * There was a possibility for psd->clock_op_might_sleep + * to become 0 above. Keep the mutex only if not the case. + */ + if (likely(psd->clock_op_might_sleep)) + return 0; + + mutex_unlock(&psd->clock_mutex); + goto try_again; +} + +/** + * pm_clk_op_unlock - counterpart to pm_clk_op_lock(). + * @psd: the same pm_subsys_data instance previously passed to + * pm_clk_op_lock(). + * @flags: irq flags provided by pm_clk_op_lock(). + */ +static void pm_clk_op_unlock(struct pm_subsys_data *psd, unsigned long *flags) + /* sparse annotations don't work here as entry state isn't static */ +{ + if (psd->clock_op_might_sleep) { + mutex_unlock(&psd->clock_mutex); + } else { + /* the __acquire is there to work around sparse limitations */ + __acquire(&psd->lock); + spin_unlock_irqrestore(&psd->lock, *flags); + } +} + /** * pm_clk_enable - Enable a clock, reporting any errors * @dev: The device for the given clock @@ -43,14 +148,21 @@ static inline void __pm_clk_enable(struct device *dev, struct pm_clock_entry *ce { int ret; - if (ce->status < PCE_STATUS_ERROR) { + switch (ce->status) { + case PCE_STATUS_ACQUIRED: + ret = clk_prepare_enable(ce->clk); + break; + case PCE_STATUS_PREPARED: ret = clk_enable(ce->clk); - if (!ret) - ce->status = PCE_STATUS_ENABLED; - else - dev_err(dev, "%s: failed to enable clk %p, error %d\n", - __func__, ce->clk, ret); + break; + default: + return; } + if (!ret) + ce->status = PCE_STATUS_ENABLED; + else + dev_err(dev, "%s: failed to enable clk %p, error %d\n", + __func__, ce->clk, ret); } /** @@ -64,17 +176,20 @@ static void pm_clk_acquire(struct device *dev, struct pm_clock_entry *ce) ce->clk = clk_get(dev, ce->con_id); if (IS_ERR(ce->clk)) { ce->status = PCE_STATUS_ERROR; + return; + } else if (clk_is_enabled_when_prepared(ce->clk)) { + /* we defer preparing the clock in that case */ + ce->status = PCE_STATUS_ACQUIRED; + ce->enabled_when_prepared = true; + } else if (clk_prepare(ce->clk)) { + ce->status = PCE_STATUS_ERROR; + dev_err(dev, "clk_prepare() failed\n"); + return; } else { - if (clk_prepare(ce->clk)) { - ce->status = PCE_STATUS_ERROR; - dev_err(dev, "clk_prepare() failed\n"); - } else { - ce->status = PCE_STATUS_ACQUIRED; - dev_dbg(dev, - "Clock %pC con_id %s managed by runtime PM.\n", - ce->clk, ce->con_id); - } + ce->status = PCE_STATUS_PREPARED; } + dev_dbg(dev, "Clock %pC con_id %s managed by runtime PM.\n", + ce->clk, ce->con_id); } static int __pm_clk_add(struct device *dev, const char *con_id, @@ -106,9 +221,11 @@ static int __pm_clk_add(struct device *dev, const char *con_id, pm_clk_acquire(dev, ce); - spin_lock_irq(&psd->lock); + pm_clk_list_lock(psd); list_add_tail(&ce->node, &psd->clock_list); - spin_unlock_irq(&psd->lock); + if (ce->enabled_when_prepared) + psd->clock_op_might_sleep++; + pm_clk_list_unlock(psd); return 0; } @@ -239,14 +356,20 @@ static void __pm_clk_remove(struct pm_clock_entry *ce) if (!ce) return; - if (ce->status < PCE_STATUS_ERROR) { - if (ce->status == PCE_STATUS_ENABLED) - clk_disable(ce->clk); - - if (ce->status >= PCE_STATUS_ACQUIRED) { - clk_unprepare(ce->clk); + switch (ce->status) { + case PCE_STATUS_ENABLED: + clk_disable(ce->clk); + fallthrough; + case PCE_STATUS_PREPARED: + clk_unprepare(ce->clk); + fallthrough; + case PCE_STATUS_ACQUIRED: + case PCE_STATUS_ERROR: + if (!IS_ERR(ce->clk)) clk_put(ce->clk); - } + break; + default: + break; } kfree(ce->con_id); @@ -269,7 +392,7 @@ void pm_clk_remove(struct device *dev, const char *con_id) if (!psd) return; - spin_lock_irq(&psd->lock); + pm_clk_list_lock(psd); list_for_each_entry(ce, &psd->clock_list, node) { if (!con_id && !ce->con_id) @@ -280,12 +403,14 @@ void pm_clk_remove(struct device *dev, const char *con_id) goto remove; } - spin_unlock_irq(&psd->lock); + pm_clk_list_unlock(psd); return; remove: list_del(&ce->node); - spin_unlock_irq(&psd->lock); + if (ce->enabled_when_prepared) + psd->clock_op_might_sleep--; + pm_clk_list_unlock(psd); __pm_clk_remove(ce); } @@ -307,19 +432,21 @@ void pm_clk_remove_clk(struct device *dev, struct clk *clk) if (!psd || !clk) return; - spin_lock_irq(&psd->lock); + pm_clk_list_lock(psd); list_for_each_entry(ce, &psd->clock_list, node) { if (clk == ce->clk) goto remove; } - spin_unlock_irq(&psd->lock); + pm_clk_list_unlock(psd); return; remove: list_del(&ce->node); - spin_unlock_irq(&psd->lock); + if (ce->enabled_when_prepared) + psd->clock_op_might_sleep--; + pm_clk_list_unlock(psd); __pm_clk_remove(ce); } @@ -330,13 +457,16 @@ EXPORT_SYMBOL_GPL(pm_clk_remove_clk); * @dev: Device to initialize the list of PM clocks for. * * Initialize the lock and clock_list members of the device's pm_subsys_data - * object. + * object, set the count of clocks that might sleep to 0. */ void pm_clk_init(struct device *dev) { struct pm_subsys_data *psd = dev_to_psd(dev); - if (psd) + if (psd) { INIT_LIST_HEAD(&psd->clock_list); + mutex_init(&psd->clock_mutex); + psd->clock_op_might_sleep = 0; + } } EXPORT_SYMBOL_GPL(pm_clk_init); @@ -372,12 +502,13 @@ void pm_clk_destroy(struct device *dev) INIT_LIST_HEAD(&list); - spin_lock_irq(&psd->lock); + pm_clk_list_lock(psd); list_for_each_entry_safe_reverse(ce, c, &psd->clock_list, node) list_move(&ce->node, &list); + psd->clock_op_might_sleep = 0; - spin_unlock_irq(&psd->lock); + pm_clk_list_unlock(psd); dev_pm_put_subsys_data(dev); @@ -397,23 +528,30 @@ int pm_clk_suspend(struct device *dev) struct pm_subsys_data *psd = dev_to_psd(dev); struct pm_clock_entry *ce; unsigned long flags; + int ret; dev_dbg(dev, "%s()\n", __func__); if (!psd) return 0; - spin_lock_irqsave(&psd->lock, flags); + ret = pm_clk_op_lock(psd, &flags, __func__); + if (ret) + return ret; list_for_each_entry_reverse(ce, &psd->clock_list, node) { - if (ce->status < PCE_STATUS_ERROR) { - if (ce->status == PCE_STATUS_ENABLED) + if (ce->status == PCE_STATUS_ENABLED) { + if (ce->enabled_when_prepared) { + clk_disable_unprepare(ce->clk); + ce->status = PCE_STATUS_ACQUIRED; + } else { clk_disable(ce->clk); - ce->status = PCE_STATUS_ACQUIRED; + ce->status = PCE_STATUS_PREPARED; + } } } - spin_unlock_irqrestore(&psd->lock, flags); + pm_clk_op_unlock(psd, &flags); return 0; } @@ -428,18 +566,21 @@ int pm_clk_resume(struct device *dev) struct pm_subsys_data *psd = dev_to_psd(dev); struct pm_clock_entry *ce; unsigned long flags; + int ret; dev_dbg(dev, "%s()\n", __func__); if (!psd) return 0; - spin_lock_irqsave(&psd->lock, flags); + ret = pm_clk_op_lock(psd, &flags, __func__); + if (ret) + return ret; list_for_each_entry(ce, &psd->clock_list, node) __pm_clk_enable(dev, ce); - spin_unlock_irqrestore(&psd->lock, flags); + pm_clk_op_unlock(psd, &flags); return 0; } diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 9a14eedacb92..aaf6c83b5cf6 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -297,6 +297,18 @@ static int _genpd_reeval_performance_state(struct generic_pm_domain *genpd, return state; } +static int genpd_xlate_performance_state(struct generic_pm_domain *genpd, + struct generic_pm_domain *parent, + unsigned int pstate) +{ + if (!parent->set_performance_state) + return pstate; + + return dev_pm_opp_xlate_performance_state(genpd->opp_table, + parent->opp_table, + pstate); +} + static int _genpd_set_performance_state(struct generic_pm_domain *genpd, unsigned int state, int depth) { @@ -311,13 +323,8 @@ static int _genpd_set_performance_state(struct generic_pm_domain *genpd, list_for_each_entry(link, &genpd->child_links, child_node) { parent = link->parent; - if (!parent->set_performance_state) - continue; - /* Find parent's performance state */ - ret = dev_pm_opp_xlate_performance_state(genpd->opp_table, - parent->opp_table, - state); + ret = genpd_xlate_performance_state(genpd, parent, state); if (unlikely(ret < 0)) goto err; @@ -339,9 +346,11 @@ static int _genpd_set_performance_state(struct generic_pm_domain *genpd, goto err; } - ret = genpd->set_performance_state(genpd, state); - if (ret) - goto err; + if (genpd->set_performance_state) { + ret = genpd->set_performance_state(genpd, state); + if (ret) + goto err; + } genpd->performance_state = state; return 0; @@ -352,9 +361,6 @@ err: child_node) { parent = link->parent; - if (!parent->set_performance_state) - continue; - genpd_lock_nested(parent, depth + 1); parent_state = link->prev_performance_state; @@ -399,9 +405,6 @@ int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state) if (!genpd) return -ENODEV; - if (unlikely(!genpd->set_performance_state)) - return -EINVAL; - if (WARN_ON(!dev->power.subsys_data || !dev->power.subsys_data->domain_data)) return -EINVAL; @@ -423,6 +426,35 @@ int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state) } EXPORT_SYMBOL_GPL(dev_pm_genpd_set_performance_state); +/** + * dev_pm_genpd_set_next_wakeup - Notify PM framework of an impending wakeup. + * + * @dev: Device to handle + * @next: impending interrupt/wakeup for the device + * + * + * Allow devices to inform of the next wakeup. It's assumed that the users + * guarantee that the genpd wouldn't be detached while this routine is getting + * called. Additionally, it's also assumed that @dev isn't runtime suspended + * (RPM_SUSPENDED)." + * Although devices are expected to update the next_wakeup after the end of + * their usecase as well, it is possible the devices themselves may not know + * about that, so stale @next will be ignored when powering off the domain. + */ +void dev_pm_genpd_set_next_wakeup(struct device *dev, ktime_t next) +{ + struct generic_pm_domain_data *gpd_data; + struct generic_pm_domain *genpd; + + genpd = dev_to_genpd_safe(dev); + if (!genpd) + return; + + gpd_data = to_gpd_data(dev->power.subsys_data->domain_data); + gpd_data->next_wakeup = next; +} +EXPORT_SYMBOL_GPL(dev_pm_genpd_set_next_wakeup); + static int _genpd_power_on(struct generic_pm_domain *genpd, bool timed) { unsigned int state_idx = genpd->state_idx; @@ -934,8 +966,7 @@ static int genpd_runtime_resume(struct device *dev) err_stop: genpd_stop_dev(genpd, dev); err_poweroff: - if (!pm_runtime_is_irq_safe(dev) || - (pm_runtime_is_irq_safe(dev) && genpd_is_irq_safe(genpd))) { + if (!pm_runtime_is_irq_safe(dev) || genpd_is_irq_safe(genpd)) { genpd_lock(genpd); genpd_power_off(genpd, true, 0); genpd_unlock(genpd); @@ -1465,6 +1496,7 @@ static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev) gpd_data->td.constraint_changed = true; gpd_data->td.effective_constraint_ns = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS; gpd_data->nb.notifier_call = genpd_dev_pm_qos_notifier; + gpd_data->next_wakeup = KTIME_MAX; spin_lock_irq(&dev->power.lock); @@ -2463,7 +2495,7 @@ int of_genpd_add_subdomain(struct of_phandle_args *parent_spec, out: mutex_unlock(&gpd_list_lock); - return ret; + return ret == -ENOENT ? -EPROBE_DEFER : ret; } EXPORT_SYMBOL_GPL(of_genpd_add_subdomain); @@ -2952,7 +2984,15 @@ static void rtpm_status_str(struct seq_file *s, struct device *dev) else WARN_ON(1); - seq_puts(s, p); + seq_printf(s, "%-25s ", p); +} + +static void perf_status_str(struct seq_file *s, struct device *dev) +{ + struct generic_pm_domain_data *gpd_data; + + gpd_data = to_gpd_data(dev->power.subsys_data->domain_data); + seq_put_decimal_ull(s, "", gpd_data->performance_state); } static int genpd_summary_one(struct seq_file *s, @@ -2980,7 +3020,7 @@ static int genpd_summary_one(struct seq_file *s, else snprintf(state, sizeof(state), "%s", status_lookup[genpd->status]); - seq_printf(s, "%-30s %-15s ", genpd->name, state); + seq_printf(s, "%-30s %-50s %u", genpd->name, state, genpd->performance_state); /* * Modifications on the list require holding locks on both @@ -2988,6 +3028,8 @@ static int genpd_summary_one(struct seq_file *s, * Also genpd->name is immutable. */ list_for_each_entry(link, &genpd->parent_links, parent_node) { + if (list_is_first(&link->parent_node, &genpd->parent_links)) + seq_printf(s, "\n%48s", " "); seq_printf(s, "%s", link->child->name); if (!list_is_last(&link->parent_node, &genpd->parent_links)) seq_puts(s, ", "); @@ -3002,6 +3044,7 @@ static int genpd_summary_one(struct seq_file *s, seq_printf(s, "\n %-50s ", kobj_path); rtpm_status_str(s, pm_data->dev); + perf_status_str(s, pm_data->dev); kfree(kobj_path); } @@ -3017,9 +3060,9 @@ static int summary_show(struct seq_file *s, void *data) struct generic_pm_domain *genpd; int ret = 0; - seq_puts(s, "domain status children\n"); + seq_puts(s, "domain status children performance\n"); seq_puts(s, " /device runtime status\n"); - seq_puts(s, "----------------------------------------------------------------------\n"); + seq_puts(s, "----------------------------------------------------------------------------------------------\n"); ret = mutex_lock_interruptible(&gpd_list_lock); if (ret) diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c index 490ed7deb99a..c6c218758f0b 100644 --- a/drivers/base/power/domain_governor.c +++ b/drivers/base/power/domain_governor.c @@ -117,6 +117,55 @@ static bool default_suspend_ok(struct device *dev) return td->cached_suspend_ok; } +static void update_domain_next_wakeup(struct generic_pm_domain *genpd, ktime_t now) +{ + ktime_t domain_wakeup = KTIME_MAX; + ktime_t next_wakeup; + struct pm_domain_data *pdd; + struct gpd_link *link; + + if (!(genpd->flags & GENPD_FLAG_MIN_RESIDENCY)) + return; + + /* + * Devices that have a predictable wakeup pattern, may specify + * their next wakeup. Let's find the next wakeup from all the + * devices attached to this domain and from all the sub-domains. + * It is possible that component's a next wakeup may have become + * stale when we read that here. We will ignore to ensure the domain + * is able to enter its optimal idle state. + */ + list_for_each_entry(pdd, &genpd->dev_list, list_node) { + next_wakeup = to_gpd_data(pdd)->next_wakeup; + if (next_wakeup != KTIME_MAX && !ktime_before(next_wakeup, now)) + if (ktime_before(next_wakeup, domain_wakeup)) + domain_wakeup = next_wakeup; + } + + list_for_each_entry(link, &genpd->parent_links, parent_node) { + next_wakeup = link->child->next_wakeup; + if (next_wakeup != KTIME_MAX && !ktime_before(next_wakeup, now)) + if (ktime_before(next_wakeup, domain_wakeup)) + domain_wakeup = next_wakeup; + } + + genpd->next_wakeup = domain_wakeup; +} + +static bool next_wakeup_allows_state(struct generic_pm_domain *genpd, + unsigned int state, ktime_t now) +{ + ktime_t domain_wakeup = genpd->next_wakeup; + s64 idle_time_ns, min_sleep_ns; + + min_sleep_ns = genpd->states[state].power_off_latency_ns + + genpd->states[state].residency_ns; + + idle_time_ns = ktime_to_ns(ktime_sub(domain_wakeup, now)); + + return idle_time_ns >= min_sleep_ns; +} + static bool __default_power_down_ok(struct dev_pm_domain *pd, unsigned int state) { @@ -201,16 +250,41 @@ static bool __default_power_down_ok(struct dev_pm_domain *pd, } /** - * default_power_down_ok - Default generic PM domain power off governor routine. + * _default_power_down_ok - Default generic PM domain power off governor routine. * @pd: PM domain to check. * * This routine must be executed under the PM domain's lock. */ -static bool default_power_down_ok(struct dev_pm_domain *pd) +static bool _default_power_down_ok(struct dev_pm_domain *pd, ktime_t now) { struct generic_pm_domain *genpd = pd_to_genpd(pd); + int state_idx = genpd->state_count - 1; struct gpd_link *link; + /* + * Find the next wakeup from devices that can determine their own wakeup + * to find when the domain would wakeup and do it for every device down + * the hierarchy. It is not worth while to sleep if the state's residency + * cannot be met. + */ + update_domain_next_wakeup(genpd, now); + if ((genpd->flags & GENPD_FLAG_MIN_RESIDENCY) && (genpd->next_wakeup != KTIME_MAX)) { + /* Let's find out the deepest domain idle state, the devices prefer */ + while (state_idx >= 0) { + if (next_wakeup_allows_state(genpd, state_idx, now)) { + genpd->max_off_time_changed = true; + break; + } + state_idx--; + } + + if (state_idx < 0) { + state_idx = 0; + genpd->cached_power_down_ok = false; + goto done; + } + } + if (!genpd->max_off_time_changed) { genpd->state_idx = genpd->cached_power_down_state_idx; return genpd->cached_power_down_ok; @@ -228,21 +302,30 @@ static bool default_power_down_ok(struct dev_pm_domain *pd) genpd->max_off_time_ns = -1; genpd->max_off_time_changed = false; genpd->cached_power_down_ok = true; - genpd->state_idx = genpd->state_count - 1; - /* Find a state to power down to, starting from the deepest. */ - while (!__default_power_down_ok(pd, genpd->state_idx)) { - if (genpd->state_idx == 0) { + /* + * Find a state to power down to, starting from the state + * determined by the next wakeup. + */ + while (!__default_power_down_ok(pd, state_idx)) { + if (state_idx == 0) { genpd->cached_power_down_ok = false; break; } - genpd->state_idx--; + state_idx--; } +done: + genpd->state_idx = state_idx; genpd->cached_power_down_state_idx = genpd->state_idx; return genpd->cached_power_down_ok; } +static bool default_power_down_ok(struct dev_pm_domain *pd) +{ + return _default_power_down_ok(pd, ktime_get()); +} + static bool always_on_power_down_ok(struct dev_pm_domain *domain) { return false; @@ -254,11 +337,12 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd) struct generic_pm_domain *genpd = pd_to_genpd(pd); struct cpuidle_device *dev; ktime_t domain_wakeup, next_hrtimer; + ktime_t now = ktime_get(); s64 idle_duration_ns; int cpu, i; /* Validate dev PM QoS constraints. */ - if (!default_power_down_ok(pd)) + if (!_default_power_down_ok(pd, now)) return false; if (!(genpd->flags & GENPD_FLAG_CPU_DOMAIN)) @@ -280,7 +364,7 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd) } /* The minimum idle duration is from now - until the next wakeup. */ - idle_duration_ns = ktime_to_ns(ktime_sub(domain_wakeup, ktime_get())); + idle_duration_ns = ktime_to_ns(ktime_sub(domain_wakeup, now)); if (idle_duration_ns <= 0) return false; diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index bb3f92568217..920f1619c5e7 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -16,6 +16,7 @@ */ #define pr_fmt(fmt) "PM: " fmt +#define dev_fmt pr_fmt #include #include @@ -450,8 +451,8 @@ static void pm_dev_dbg(struct device *dev, pm_message_t state, const char *info) static void pm_dev_err(struct device *dev, pm_message_t state, const char *info, int error) { - pr_err("Device %s failed to %s%s: error %d\n", - dev_name(dev), pm_verb(state.event), info, error); + dev_err(dev, "failed to %s%s: error %d\n", pm_verb(state.event), info, + error); } static void dpm_show_time(ktime_t starttime, pm_message_t state, int error, @@ -1905,8 +1906,8 @@ int dpm_prepare(pm_message_t state) error = 0; continue; } - pr_info("Device %s not prepared for power transition: code %d\n", - dev_name(dev), error); + dev_info(dev, "not prepared for power transition: code %d\n", + error); log_suspend_abort_reason("Device %s not prepared for power transition: code %d", dev_name(dev), error); dpm_save_failed_dev(dev_name(dev)); diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index bfda153b1a41..a46a7e30881b 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -1100,7 +1100,7 @@ EXPORT_SYMBOL_GPL(__pm_runtime_resume); * suspending the device when both its runtime PM status is %RPM_ACTIVE and its * runtime PM usage counter is not zero. * - * The caller is resposible for decrementing the runtime PM usage counter of + * The caller is responsible for decrementing the runtime PM usage counter of * @dev after this function has returned a positive value for it. */ int pm_runtime_get_if_active(struct device *dev, bool ign_usage_count) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 34838de156fd..caf45680e06c 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1166,6 +1166,27 @@ int clk_enable(struct clk *clk) } EXPORT_SYMBOL_GPL(clk_enable); +/** + * clk_is_enabled_when_prepared - indicate if preparing a clock also enables it. + * @clk: clock source + * + * Returns true if clk_prepare() implicitly enables the clock, effectively + * making clk_enable()/clk_disable() no-ops, false otherwise. + * + * This is of interest mainly to power management code where actually + * disabling the clock also requires unpreparing it to have any material + * effect. + * + * Regardless of the value returned here, the caller must always invoke + * clk_enable() or clk_prepare_enable() and counterparts for usage counts + * to be right. + */ +bool clk_is_enabled_when_prepared(struct clk *clk) +{ + return clk && !(clk->core->ops->enable && clk->core->ops->disable); +} +EXPORT_SYMBOL_GPL(clk_is_enabled_when_prepared); + static int clk_core_prepare_enable(struct clk_core *core) { int ret; diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index 1f73fa75b1a0..e65e0a43be64 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -289,11 +289,6 @@ config ARM_STI_CPUFREQ this config option if you wish to add CPUFreq support for STi based SoCs. -config ARM_TANGO_CPUFREQ - bool - depends on CPUFREQ_DT && ARCH_TANGO - default y - config ARM_TEGRA20_CPUFREQ tristate "Tegra20/30 CPUFreq support" depends on ARCH_TEGRA && CPUFREQ_DT diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index b2f4531105fb..cd8d3a3304ca 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -84,7 +84,6 @@ obj-$(CONFIG_ARM_SCPI_CPUFREQ) += scpi-cpufreq.o obj-$(CONFIG_ARM_SPEAR_CPUFREQ) += spear-cpufreq.o obj-$(CONFIG_ARM_STI_CPUFREQ) += sti-cpufreq.o obj-$(CONFIG_ARM_ALLWINNER_SUN50I_CPUFREQ_NVMEM) += sun50i-cpufreq-nvmem.o -obj-$(CONFIG_ARM_TANGO_CPUFREQ) += tango-cpufreq.o obj-$(CONFIG_ARM_TEGRA20_CPUFREQ) += tegra20-cpufreq.o obj-$(CONFIG_ARM_TEGRA124_CPUFREQ) += tegra124-cpufreq.o obj-$(CONFIG_ARM_TEGRA186_CPUFREQ) += tegra186-cpufreq.o diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c index 3e31e5d28b79..4153150e20db 100644 --- a/drivers/cpufreq/brcmstb-avs-cpufreq.c +++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c @@ -597,6 +597,16 @@ unmap_base: return ret; } +static void brcm_avs_prepare_uninit(struct platform_device *pdev) +{ + struct private_data *priv; + + priv = platform_get_drvdata(pdev); + + iounmap(priv->avs_intr_base); + iounmap(priv->base); +} + static int brcm_avs_cpufreq_init(struct cpufreq_policy *policy) { struct cpufreq_frequency_table *freq_table; @@ -732,21 +742,21 @@ static int brcm_avs_cpufreq_probe(struct platform_device *pdev) brcm_avs_driver.driver_data = pdev; - return cpufreq_register_driver(&brcm_avs_driver); + ret = cpufreq_register_driver(&brcm_avs_driver); + if (ret) + brcm_avs_prepare_uninit(pdev); + + return ret; } static int brcm_avs_cpufreq_remove(struct platform_device *pdev) { - struct private_data *priv; int ret; ret = cpufreq_unregister_driver(&brcm_avs_driver); - if (ret) - return ret; + WARN_ON(ret); - priv = platform_get_drvdata(pdev); - iounmap(priv->base); - iounmap(priv->avs_intr_base); + brcm_avs_prepare_uninit(pdev); return 0; } diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index bd2db0188cbb..3ba2f716fe97 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -141,8 +141,6 @@ static const struct of_device_id blacklist[] __initconst = { { .compatible = "st,stih410", }, { .compatible = "st,stih418", }, - { .compatible = "sigma,tango4", }, - { .compatible = "ti,am33xx", }, { .compatible = "ti,am43", }, { .compatible = "ti,dra7", }, diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index ad4234518ef6..b1e1bdc63b01 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -175,7 +175,7 @@ static int cpufreq_exit(struct cpufreq_policy *policy) } static struct cpufreq_driver dt_cpufreq_driver = { - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK | + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_IS_COOLING_DEV, .verify = cpufreq_generic_frequency_table_verify, .target_index = set_target, diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 44f1699639b2..7b03beedbe4a 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2820,8 +2820,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) if (ret) goto err_boost_unreg; - if (!(cpufreq_driver->flags & CPUFREQ_STICKY) && - list_empty(&cpufreq_policy_list)) { + if (unlikely(list_empty(&cpufreq_policy_list))) { /* if all ->init() calls failed, unregister */ ret = -ENODEV; pr_debug("%s: No CPU initialized for driver %s\n", __func__, diff --git a/drivers/cpufreq/davinci-cpufreq.c b/drivers/cpufreq/davinci-cpufreq.c index 91f477a6cbc4..9e97f60f8199 100644 --- a/drivers/cpufreq/davinci-cpufreq.c +++ b/drivers/cpufreq/davinci-cpufreq.c @@ -95,7 +95,7 @@ static int davinci_cpu_init(struct cpufreq_policy *policy) } static struct cpufreq_driver davinci_driver = { - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK, + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK, .verify = cpufreq_generic_frequency_table_verify, .target_index = davinci_target, .get = cpufreq_generic_get, diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index be05e038d956..5175ae3cac44 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -819,13 +819,13 @@ static struct freq_attr *hwp_cpufreq_attrs[] = { NULL, }; -static void intel_pstate_get_hwp_max(unsigned int cpu, int *phy_max, +static void intel_pstate_get_hwp_max(struct cpudata *cpu, int *phy_max, int *current_max) { u64 cap; - rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap); - WRITE_ONCE(all_cpu_data[cpu]->hwp_cap_cached, cap); + rdmsrl_on_cpu(cpu->cpu, MSR_HWP_CAPABILITIES, &cap); + WRITE_ONCE(cpu->hwp_cap_cached, cap); if (global.no_turbo || global.turbo_disabled) *current_max = HWP_GUARANTEED_PERF(cap); else @@ -914,7 +914,7 @@ static void intel_pstate_hwp_offline(struct cpudata *cpu) } value &= ~GENMASK_ULL(31, 0); - min_perf = HWP_LOWEST_PERF(cpu->hwp_cap_cached); + min_perf = HWP_LOWEST_PERF(READ_ONCE(cpu->hwp_cap_cached)); /* Set hwp_max = hwp_min */ value |= HWP_MAX_PERF(min_perf); @@ -1213,7 +1213,7 @@ static void update_qos_request(enum freq_qos_req_type type) continue; if (hwp_active) - intel_pstate_get_hwp_max(i, &turbo_max, &max_state); + intel_pstate_get_hwp_max(cpu, &turbo_max, &max_state); else turbo_max = cpu->pstate.turbo_pstate; @@ -1714,21 +1714,22 @@ static void intel_pstate_max_within_limits(struct cpudata *cpu) static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) { cpu->pstate.min_pstate = pstate_funcs.get_min(); - cpu->pstate.max_pstate = pstate_funcs.get_max(); cpu->pstate.max_pstate_physical = pstate_funcs.get_max_physical(); cpu->pstate.turbo_pstate = pstate_funcs.get_turbo(); cpu->pstate.scaling = pstate_funcs.get_scaling(); - cpu->pstate.max_freq = cpu->pstate.max_pstate * cpu->pstate.scaling; if (hwp_active && !hwp_mode_bdw) { unsigned int phy_max, current_max; - intel_pstate_get_hwp_max(cpu->cpu, &phy_max, ¤t_max); + intel_pstate_get_hwp_max(cpu, &phy_max, ¤t_max); cpu->pstate.turbo_freq = phy_max * cpu->pstate.scaling; cpu->pstate.turbo_pstate = phy_max; + cpu->pstate.max_pstate = HWP_GUARANTEED_PERF(READ_ONCE(cpu->hwp_cap_cached)); } else { cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling; + cpu->pstate.max_pstate = pstate_funcs.get_max(); } + cpu->pstate.max_freq = cpu->pstate.max_pstate * cpu->pstate.scaling; if (pstate_funcs.get_aperf_mperf_shift) cpu->aperf_mperf_shift = pstate_funcs.get_aperf_mperf_shift(); @@ -1750,6 +1751,7 @@ static int hwp_boost_hold_time_ns = 3 * NSEC_PER_MSEC; static inline void intel_pstate_hwp_boost_up(struct cpudata *cpu) { u64 hwp_req = READ_ONCE(cpu->hwp_req_cached); + u64 hwp_cap = READ_ONCE(cpu->hwp_cap_cached); u32 max_limit = (hwp_req & 0xff00) >> 8; u32 min_limit = (hwp_req & 0xff); u32 boost_level1; @@ -1776,14 +1778,14 @@ static inline void intel_pstate_hwp_boost_up(struct cpudata *cpu) cpu->hwp_boost_min = min_limit; /* level at half way mark between min and guranteed */ - boost_level1 = (HWP_GUARANTEED_PERF(cpu->hwp_cap_cached) + min_limit) >> 1; + boost_level1 = (HWP_GUARANTEED_PERF(hwp_cap) + min_limit) >> 1; if (cpu->hwp_boost_min < boost_level1) cpu->hwp_boost_min = boost_level1; - else if (cpu->hwp_boost_min < HWP_GUARANTEED_PERF(cpu->hwp_cap_cached)) - cpu->hwp_boost_min = HWP_GUARANTEED_PERF(cpu->hwp_cap_cached); - else if (cpu->hwp_boost_min == HWP_GUARANTEED_PERF(cpu->hwp_cap_cached) && - max_limit != HWP_GUARANTEED_PERF(cpu->hwp_cap_cached)) + else if (cpu->hwp_boost_min < HWP_GUARANTEED_PERF(hwp_cap)) + cpu->hwp_boost_min = HWP_GUARANTEED_PERF(hwp_cap); + else if (cpu->hwp_boost_min == HWP_GUARANTEED_PERF(hwp_cap) && + max_limit != HWP_GUARANTEED_PERF(hwp_cap)) cpu->hwp_boost_min = max_limit; else return; @@ -2207,7 +2209,7 @@ static void intel_pstate_update_perf_limits(struct cpudata *cpu, * rather than pure ratios. */ if (hwp_active) { - intel_pstate_get_hwp_max(cpu->cpu, &turbo_max, &max_state); + intel_pstate_get_hwp_max(cpu, &turbo_max, &max_state); } else { max_state = global.no_turbo || global.turbo_disabled ? cpu->pstate.max_pstate : cpu->pstate.turbo_pstate; @@ -2322,7 +2324,7 @@ static void intel_pstate_verify_cpu_policy(struct cpudata *cpu, if (hwp_active) { int max_state, turbo_max; - intel_pstate_get_hwp_max(cpu->cpu, &turbo_max, &max_state); + intel_pstate_get_hwp_max(cpu, &turbo_max, &max_state); max_freq = max_state * cpu->pstate.scaling; } else { max_freq = intel_pstate_get_max_freq(cpu); @@ -2496,7 +2498,7 @@ static int intel_cpufreq_verify_policy(struct cpufreq_policy_data *policy) * driver call was via the normal or fast switch path. Various graphs * output from the intel_pstate_tracer.py utility that include core_busy * (or performance or core_avg_perf) have a fixed y-axis from 0 to 100%, - * so we use 10 to indicate the the normal path through the driver, and + * so we use 10 to indicate the normal path through the driver, and * 90 to indicate the fast switch path through the driver. * The scaled_busy field is not used, and is set to 0. */ @@ -2526,7 +2528,7 @@ static void intel_cpufreq_trace(struct cpudata *cpu, unsigned int trace_type, in fp_toint(cpu->iowait_boost * 100)); } -static void intel_cpufreq_adjust_hwp(struct cpudata *cpu, u32 min, u32 max, +static void intel_cpufreq_hwp_update(struct cpudata *cpu, u32 min, u32 max, u32 desired, bool fast_switch) { u64 prev = READ_ONCE(cpu->hwp_req_cached), value = prev; @@ -2550,7 +2552,7 @@ static void intel_cpufreq_adjust_hwp(struct cpudata *cpu, u32 min, u32 max, wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value); } -static void intel_cpufreq_adjust_perf_ctl(struct cpudata *cpu, +static void intel_cpufreq_perf_ctl_update(struct cpudata *cpu, u32 target_pstate, bool fast_switch) { if (fast_switch) @@ -2572,10 +2574,10 @@ static int intel_cpufreq_update_pstate(struct cpufreq_policy *policy, int max_pstate = policy->strict_target ? target_pstate : cpu->max_perf_ratio; - intel_cpufreq_adjust_hwp(cpu, target_pstate, max_pstate, 0, + intel_cpufreq_hwp_update(cpu, target_pstate, max_pstate, 0, fast_switch); } else if (target_pstate != old_pstate) { - intel_cpufreq_adjust_perf_ctl(cpu, target_pstate, fast_switch); + intel_cpufreq_perf_ctl_update(cpu, target_pstate, fast_switch); } cpu->pstate.current_pstate = target_pstate; @@ -2673,7 +2675,7 @@ static void intel_cpufreq_adjust_perf(unsigned int cpunum, target_pstate = clamp_t(int, target_pstate, min_pstate, max_pstate); - intel_cpufreq_adjust_hwp(cpu, min_pstate, max_pstate, target_pstate, true); + intel_cpufreq_hwp_update(cpu, min_pstate, max_pstate, target_pstate, true); cpu->pstate.current_pstate = target_pstate; intel_cpufreq_trace(cpu, INTEL_PSTATE_TRACE_FAST_SWITCH, old_pstate); @@ -2709,7 +2711,7 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy) if (hwp_active) { u64 value; - intel_pstate_get_hwp_max(policy->cpu, &turbo_max, &max_state); + intel_pstate_get_hwp_max(cpu, &turbo_max, &max_state); policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY_HWP; rdmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, &value); WRITE_ONCE(cpu->hwp_req_cached, value); diff --git a/drivers/cpufreq/loongson1-cpufreq.c b/drivers/cpufreq/loongson1-cpufreq.c index 86f612593e49..fb72d709db56 100644 --- a/drivers/cpufreq/loongson1-cpufreq.c +++ b/drivers/cpufreq/loongson1-cpufreq.c @@ -116,7 +116,7 @@ static int ls1x_cpufreq_exit(struct cpufreq_policy *policy) static struct cpufreq_driver ls1x_cpufreq_driver = { .name = "cpufreq-ls1x", - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK, + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK, .verify = cpufreq_generic_frequency_table_verify, .target_index = ls1x_cpufreq_target, .get = cpufreq_generic_get, diff --git a/drivers/cpufreq/mediatek-cpufreq.c b/drivers/cpufreq/mediatek-cpufreq.c index 022e3e966e71..f2e491b25b07 100644 --- a/drivers/cpufreq/mediatek-cpufreq.c +++ b/drivers/cpufreq/mediatek-cpufreq.c @@ -463,7 +463,7 @@ static int mtk_cpufreq_exit(struct cpufreq_policy *policy) } static struct cpufreq_driver mtk_cpufreq_driver = { - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK | + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_HAVE_GOVERNOR_PER_POLICY | CPUFREQ_IS_COOLING_DEV, .verify = cpufreq_generic_frequency_table_verify, diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c index 3694bb030df3..e035ee216b0f 100644 --- a/drivers/cpufreq/omap-cpufreq.c +++ b/drivers/cpufreq/omap-cpufreq.c @@ -144,7 +144,7 @@ static int omap_cpu_exit(struct cpufreq_policy *policy) } static struct cpufreq_driver omap_driver = { - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK, + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK, .verify = cpufreq_generic_frequency_table_verify, .target_index = omap_target, .get = cpufreq_generic_get, diff --git a/drivers/cpufreq/pmac32-cpufreq.c b/drivers/cpufreq/pmac32-cpufreq.c index 73621bc11976..4f20c6a9108d 100644 --- a/drivers/cpufreq/pmac32-cpufreq.c +++ b/drivers/cpufreq/pmac32-cpufreq.c @@ -439,8 +439,7 @@ static struct cpufreq_driver pmac_cpufreq_driver = { .init = pmac_cpufreq_cpu_init, .suspend = pmac_cpufreq_suspend, .resume = pmac_cpufreq_resume, - .flags = CPUFREQ_PM_NO_WARN | - CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING, + .flags = CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING, .attr = cpufreq_generic_attr, .name = "powermac", }; diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index 9ed5341dc515..356244510b18 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -54,7 +54,7 @@ static int qcom_cpufreq_set_bw(struct cpufreq_policy *policy, if (IS_ERR(opp)) return PTR_ERR(opp); - ret = dev_pm_opp_set_bw(dev, opp); + ret = dev_pm_opp_set_opp(dev, opp); dev_pm_opp_put(opp); return ret; } @@ -347,6 +347,12 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy) dev_pm_opp_of_register_em(cpu_dev, policy->cpus); + if (policy_has_boost_freq(policy)) { + ret = cpufreq_enable_boost_support(); + if (ret) + dev_warn(cpu_dev, "failed to enable boost: %d\n", ret); + } + return 0; error: devm_iounmap(dev, base); @@ -374,7 +380,7 @@ static struct freq_attr *qcom_cpufreq_hw_attr[] = { }; static struct cpufreq_driver cpufreq_qcom_hw_driver = { - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK | + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_HAVE_GOVERNOR_PER_POLICY | CPUFREQ_IS_COOLING_DEV, .verify = cpufreq_generic_frequency_table_verify, diff --git a/drivers/cpufreq/s3c24xx-cpufreq.c b/drivers/cpufreq/s3c24xx-cpufreq.c index 37efc0dc3f91..7380c32b238e 100644 --- a/drivers/cpufreq/s3c24xx-cpufreq.c +++ b/drivers/cpufreq/s3c24xx-cpufreq.c @@ -420,7 +420,7 @@ static int s3c_cpufreq_resume(struct cpufreq_policy *policy) #endif static struct cpufreq_driver s3c24xx_driver = { - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK, + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK, .target = s3c_cpufreq_target, .get = cpufreq_generic_get, .init = s3c_cpufreq_init, diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c index bed496cf8d24..69786e5bbf05 100644 --- a/drivers/cpufreq/s5pv210-cpufreq.c +++ b/drivers/cpufreq/s5pv210-cpufreq.c @@ -574,7 +574,7 @@ static int s5pv210_cpufreq_reboot_notifier_event(struct notifier_block *this, } static struct cpufreq_driver s5pv210_driver = { - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK, + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK, .verify = cpufreq_generic_frequency_table_verify, .target_index = s5pv210_target, .get = cpufreq_generic_get, diff --git a/drivers/cpufreq/sa1100-cpufreq.c b/drivers/cpufreq/sa1100-cpufreq.c index 5c075ef6adc0..252b9fc26124 100644 --- a/drivers/cpufreq/sa1100-cpufreq.c +++ b/drivers/cpufreq/sa1100-cpufreq.c @@ -186,7 +186,7 @@ static int __init sa1100_cpu_init(struct cpufreq_policy *policy) } static struct cpufreq_driver sa1100_driver __refdata = { - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK | + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING, .verify = cpufreq_generic_frequency_table_verify, .target_index = sa1100_target, diff --git a/drivers/cpufreq/sa1110-cpufreq.c b/drivers/cpufreq/sa1110-cpufreq.c index d9d04d935b3a..1a83c8678a63 100644 --- a/drivers/cpufreq/sa1110-cpufreq.c +++ b/drivers/cpufreq/sa1110-cpufreq.c @@ -310,7 +310,7 @@ static int __init sa1110_cpu_init(struct cpufreq_policy *policy) /* sa1110_driver needs __refdata because it must remain after init registers * it with cpufreq_register_driver() */ static struct cpufreq_driver sa1110_driver __refdata = { - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK | + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING, .verify = cpufreq_generic_frequency_table_verify, .target_index = sa1110_target, diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index 491a0a24fb1e..5bd03b59887f 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -217,7 +217,7 @@ static int scmi_cpufreq_exit(struct cpufreq_policy *policy) static struct cpufreq_driver scmi_cpufreq_driver = { .name = "scmi", - .flags = CPUFREQ_STICKY | CPUFREQ_HAVE_GOVERNOR_PER_POLICY | + .flags = CPUFREQ_HAVE_GOVERNOR_PER_POLICY | CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_IS_COOLING_DEV, .verify = cpufreq_generic_frequency_table_verify, diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c index e5140ad63db8..d6a698a1b5d1 100644 --- a/drivers/cpufreq/scpi-cpufreq.c +++ b/drivers/cpufreq/scpi-cpufreq.c @@ -191,7 +191,7 @@ static int scpi_cpufreq_exit(struct cpufreq_policy *policy) static struct cpufreq_driver scpi_cpufreq_driver = { .name = "scpi-cpufreq", - .flags = CPUFREQ_STICKY | CPUFREQ_HAVE_GOVERNOR_PER_POLICY | + .flags = CPUFREQ_HAVE_GOVERNOR_PER_POLICY | CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_IS_COOLING_DEV, .verify = cpufreq_generic_frequency_table_verify, diff --git a/drivers/cpufreq/spear-cpufreq.c b/drivers/cpufreq/spear-cpufreq.c index 73bd8dc47074..7d0d62a06bf3 100644 --- a/drivers/cpufreq/spear-cpufreq.c +++ b/drivers/cpufreq/spear-cpufreq.c @@ -160,7 +160,7 @@ static int spear_cpufreq_init(struct cpufreq_policy *policy) static struct cpufreq_driver spear_cpufreq_driver = { .name = "cpufreq-spear", - .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK, + .flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK, .verify = cpufreq_generic_frequency_table_verify, .target_index = spear_cpufreq_target, .get = cpufreq_generic_get, diff --git a/drivers/cpufreq/tango-cpufreq.c b/drivers/cpufreq/tango-cpufreq.c deleted file mode 100644 index 89a7f860bfe8..000000000000 --- a/drivers/cpufreq/tango-cpufreq.c +++ /dev/null @@ -1,38 +0,0 @@ -#include -#include -#include -#include -#include - -static const struct of_device_id machines[] __initconst = { - { .compatible = "sigma,tango4" }, - { /* sentinel */ } -}; - -static int __init tango_cpufreq_init(void) -{ - struct device *cpu_dev = get_cpu_device(0); - unsigned long max_freq; - struct clk *cpu_clk; - void *res; - - if (!of_match_node(machines, of_root)) - return -ENODEV; - - cpu_clk = clk_get(cpu_dev, NULL); - if (IS_ERR(cpu_clk)) - return -ENODEV; - - max_freq = clk_get_rate(cpu_clk); - - dev_pm_opp_add(cpu_dev, max_freq / 1, 0); - dev_pm_opp_add(cpu_dev, max_freq / 2, 0); - dev_pm_opp_add(cpu_dev, max_freq / 3, 0); - dev_pm_opp_add(cpu_dev, max_freq / 5, 0); - dev_pm_opp_add(cpu_dev, max_freq / 9, 0); - - res = platform_device_register_data(NULL, "cpufreq-dt", -1, NULL, 0); - - return PTR_ERR_OR_ZERO(res); -} -device_initcall(tango_cpufreq_init); diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c index e566ea298b59..5d1943e787b0 100644 --- a/drivers/cpufreq/tegra186-cpufreq.c +++ b/drivers/cpufreq/tegra186-cpufreq.c @@ -117,7 +117,7 @@ static unsigned int tegra186_cpufreq_get(unsigned int cpu) static struct cpufreq_driver tegra186_cpufreq_driver = { .name = "tegra186", - .flags = CPUFREQ_STICKY | CPUFREQ_HAVE_GOVERNOR_PER_POLICY | + .flags = CPUFREQ_HAVE_GOVERNOR_PER_POLICY | CPUFREQ_NEED_INITIAL_FREQ_CHECK, .get = tegra186_cpufreq_get, .verify = cpufreq_generic_frequency_table_verify, diff --git a/drivers/cpufreq/tegra194-cpufreq.c b/drivers/cpufreq/tegra194-cpufreq.c index 6a67f36f3b80..a9620e4489ae 100644 --- a/drivers/cpufreq/tegra194-cpufreq.c +++ b/drivers/cpufreq/tegra194-cpufreq.c @@ -272,8 +272,7 @@ static int tegra194_cpufreq_set_target(struct cpufreq_policy *policy, static struct cpufreq_driver tegra194_cpufreq_driver = { .name = "tegra194", - .flags = CPUFREQ_STICKY | CPUFREQ_CONST_LOOPS | - CPUFREQ_NEED_INITIAL_FREQ_CHECK, + .flags = CPUFREQ_CONST_LOOPS | CPUFREQ_NEED_INITIAL_FREQ_CHECK, .verify = cpufreq_generic_frequency_table_verify, .target_index = tegra194_cpufreq_set_target, .get = tegra194_get_speed, diff --git a/drivers/cpufreq/tegra20-cpufreq.c b/drivers/cpufreq/tegra20-cpufreq.c index 8c893043953e..e8db3d75be25 100644 --- a/drivers/cpufreq/tegra20-cpufreq.c +++ b/drivers/cpufreq/tegra20-cpufreq.c @@ -32,6 +32,16 @@ static bool cpu0_node_has_opp_v2_prop(void) return ret; } +static void tegra20_cpufreq_put_supported_hw(void *opp_table) +{ + dev_pm_opp_put_supported_hw(opp_table); +} + +static void tegra20_cpufreq_dt_unregister(void *cpufreq_dt) +{ + platform_device_unregister(cpufreq_dt); +} + static int tegra20_cpufreq_probe(struct platform_device *pdev) { struct platform_device *cpufreq_dt; @@ -68,42 +78,31 @@ static int tegra20_cpufreq_probe(struct platform_device *pdev) return err; } + err = devm_add_action_or_reset(&pdev->dev, + tegra20_cpufreq_put_supported_hw, + opp_table); + if (err) + return err; + cpufreq_dt = platform_device_register_simple("cpufreq-dt", -1, NULL, 0); err = PTR_ERR_OR_ZERO(cpufreq_dt); if (err) { dev_err(&pdev->dev, "failed to create cpufreq-dt device: %d\n", err); - goto err_put_supported_hw; + return err; } - platform_set_drvdata(pdev, cpufreq_dt); - - return 0; - -err_put_supported_hw: - dev_pm_opp_put_supported_hw(opp_table); - - return err; -} - -static int tegra20_cpufreq_remove(struct platform_device *pdev) -{ - struct platform_device *cpufreq_dt; - struct opp_table *opp_table; - - cpufreq_dt = platform_get_drvdata(pdev); - platform_device_unregister(cpufreq_dt); - - opp_table = dev_pm_opp_get_opp_table(get_cpu_device(0)); - dev_pm_opp_put_supported_hw(opp_table); - dev_pm_opp_put_opp_table(opp_table); + err = devm_add_action_or_reset(&pdev->dev, + tegra20_cpufreq_dt_unregister, + cpufreq_dt); + if (err) + return err; return 0; } static struct platform_driver tegra20_cpufreq_driver = { .probe = tegra20_cpufreq_probe, - .remove = tegra20_cpufreq_remove, .driver = { .name = "tegra20-cpufreq", }, diff --git a/drivers/cpufreq/vexpress-spc-cpufreq.c b/drivers/cpufreq/vexpress-spc-cpufreq.c index f711d8eaea6a..51dfa9ae6cf5 100644 --- a/drivers/cpufreq/vexpress-spc-cpufreq.c +++ b/drivers/cpufreq/vexpress-spc-cpufreq.c @@ -486,8 +486,7 @@ static void ve_spc_cpufreq_ready(struct cpufreq_policy *policy) static struct cpufreq_driver ve_spc_cpufreq_driver = { .name = "vexpress-spc", - .flags = CPUFREQ_STICKY | - CPUFREQ_HAVE_GOVERNOR_PER_POLICY | + .flags = CPUFREQ_HAVE_GOVERNOR_PER_POLICY | CPUFREQ_NEED_INITIAL_FREQ_CHECK, .verify = cpufreq_generic_frequency_table_verify, .target_index = ve_spc_cpufreq_set_target, diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 6aa10de792b3..bf3047896e41 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -757,6 +757,9 @@ static void devfreq_dev_release(struct device *dev) if (devfreq->profile->exit) devfreq->profile->exit(devfreq->dev.parent); + if (devfreq->opp_table) + dev_pm_opp_put_opp_table(devfreq->opp_table); + mutex_destroy(&devfreq->lock); kfree(devfreq); } @@ -844,6 +847,10 @@ struct devfreq *devfreq_add_device(struct device *dev, } devfreq->suspend_freq = dev_pm_opp_get_suspend_opp_freq(dev); + devfreq->opp_table = dev_pm_opp_get_opp_table(dev); + if (IS_ERR(devfreq->opp_table)) + devfreq->opp_table = NULL; + atomic_set(&devfreq->suspend_count, 0); dev_set_name(&devfreq->dev, "%s", dev_name(dev)); @@ -893,13 +900,13 @@ struct devfreq *devfreq_add_device(struct device *dev, goto err_devfreq; devfreq->nb_min.notifier_call = qos_min_notifier_call; - err = dev_pm_qos_add_notifier(devfreq->dev.parent, &devfreq->nb_min, + err = dev_pm_qos_add_notifier(dev, &devfreq->nb_min, DEV_PM_QOS_MIN_FREQUENCY); if (err) goto err_devfreq; devfreq->nb_max.notifier_call = qos_max_notifier_call; - err = dev_pm_qos_add_notifier(devfreq->dev.parent, &devfreq->nb_max, + err = dev_pm_qos_add_notifier(dev, &devfreq->nb_max, DEV_PM_QOS_MAX_FREQUENCY); if (err) goto err_devfreq; diff --git a/drivers/devfreq/governor.h b/drivers/devfreq/governor.h index 2a52f97b542d..70f44b3ca42e 100644 --- a/drivers/devfreq/governor.h +++ b/drivers/devfreq/governor.h @@ -40,7 +40,7 @@ /* * Definition of governor attribute flags except for common sysfs attributes * - DEVFREQ_GOV_ATTR_POLLING_INTERVAL - * : Indicate polling_interal sysfs attribute + * : Indicate polling_interval sysfs attribute * - DEVFREQ_GOV_ATTR_TIMER * : Indicate timer sysfs attribute */ diff --git a/drivers/devfreq/governor_passive.c b/drivers/devfreq/governor_passive.c index 63332e4a65ae..b094132bd20b 100644 --- a/drivers/devfreq/governor_passive.c +++ b/drivers/devfreq/governor_passive.c @@ -19,18 +19,16 @@ static int devfreq_passive_get_target_freq(struct devfreq *devfreq, = (struct devfreq_passive_data *)devfreq->data; struct devfreq *parent_devfreq = (struct devfreq *)p_data->parent; unsigned long child_freq = ULONG_MAX; - struct dev_pm_opp *opp; - int i, count, ret = 0; + struct dev_pm_opp *opp, *p_opp; + int i, count; /* * If the devfreq device with passive governor has the specific method * to determine the next frequency, should use the get_target_freq() * of struct devfreq_passive_data. */ - if (p_data->get_target_freq) { - ret = p_data->get_target_freq(devfreq, freq); - goto out; - } + if (p_data->get_target_freq) + return p_data->get_target_freq(devfreq, freq); /* * If the parent and passive devfreq device uses the OPP table, @@ -56,26 +54,35 @@ static int devfreq_passive_get_target_freq(struct devfreq *devfreq, * list of parent device. Because in this case, *freq is temporary * value which is decided by ondemand governor. */ - opp = devfreq_recommended_opp(parent_devfreq->dev.parent, freq, 0); - if (IS_ERR(opp)) { - ret = PTR_ERR(opp); - goto out; + if (devfreq->opp_table && parent_devfreq->opp_table) { + p_opp = devfreq_recommended_opp(parent_devfreq->dev.parent, + freq, 0); + if (IS_ERR(p_opp)) + return PTR_ERR(p_opp); + + opp = dev_pm_opp_xlate_required_opp(parent_devfreq->opp_table, + devfreq->opp_table, p_opp); + dev_pm_opp_put(p_opp); + + if (IS_ERR(opp)) + return PTR_ERR(opp); + + *freq = dev_pm_opp_get_freq(opp); + dev_pm_opp_put(opp); + + return 0; } - dev_pm_opp_put(opp); - /* - * Get the OPP table's index of decided freqeuncy by governor + * Get the OPP table's index of decided frequency by governor * of parent device. */ for (i = 0; i < parent_devfreq->profile->max_state; i++) if (parent_devfreq->profile->freq_table[i] == *freq) break; - if (i == parent_devfreq->profile->max_state) { - ret = -EINVAL; - goto out; - } + if (i == parent_devfreq->profile->max_state) + return -EINVAL; /* Get the suitable frequency by using index of parent device. */ if (i < devfreq->profile->max_state) { @@ -88,8 +95,7 @@ static int devfreq_passive_get_target_freq(struct devfreq *devfreq, /* Return the suitable frequency for passive device. */ *freq = child_freq; -out: - return ret; + return 0; } static int devfreq_passive_notifier_call(struct notifier_block *nb, diff --git a/drivers/devfreq/rk3399_dmc.c b/drivers/devfreq/rk3399_dmc.c index 2e912166a993..9e9d3b4c6d48 100644 --- a/drivers/devfreq/rk3399_dmc.c +++ b/drivers/devfreq/rk3399_dmc.c @@ -400,7 +400,7 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev) default: ret = -EINVAL; goto err_edev; - }; + } no_pmu: arm_smccc_smc(ROCKCHIP_SIP_DRAM_FREQ, 0, 0, diff --git a/drivers/devfreq/tegra30-devfreq.c b/drivers/devfreq/tegra30-devfreq.c index 117cad7968ab..ce83f883ca65 100644 --- a/drivers/devfreq/tegra30-devfreq.c +++ b/drivers/devfreq/tegra30-devfreq.c @@ -647,7 +647,7 @@ static int tegra_devfreq_target(struct device *dev, unsigned long *freq, return PTR_ERR(opp); } - ret = dev_pm_opp_set_bw(dev, opp); + ret = dev_pm_opp_set_opp(dev, opp); dev_pm_opp_put(opp); return ret; @@ -849,7 +849,7 @@ static int tegra_devfreq_probe(struct platform_device *pdev) return err; } - err = dev_pm_opp_of_add_table(&pdev->dev); + err = dev_pm_opp_of_add_table_noclk(&pdev->dev, 0); if (err) { dev_err(&pdev->dev, "Failed to add OPP table: %d\n", err); goto put_hw; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c index 6333cada1e09..055f600eeed8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c @@ -291,7 +291,7 @@ static bool amdgpu_atrm_get_bios(struct amdgpu_device *adev) continue; status = acpi_get_handle(dhandle, "ATRM", &atrm_handle); - if (!ACPI_FAILURE(status)) { + if (ACPI_SUCCESS(status)) { found = true; break; } @@ -304,7 +304,7 @@ static bool amdgpu_atrm_get_bios(struct amdgpu_device *adev) continue; status = acpi_get_handle(dhandle, "ATRM", &atrm_handle); - if (!ACPI_FAILURE(status)) { + if (ACPI_SUCCESS(status)) { found = true; break; } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index e6703ae98760..05e0ef58fe32 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -134,7 +134,7 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp) if (!gmu->legacy) { a6xx_hfi_set_freq(gmu, perf_index); - dev_pm_opp_set_bw(&gpu->pdev->dev, opp); + dev_pm_opp_set_opp(&gpu->pdev->dev, opp); pm_runtime_put(gmu->dev); return; } @@ -158,7 +158,7 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp) if (ret) dev_err(gmu->dev, "GMU set GPU frequency error: %d\n", ret); - dev_pm_opp_set_bw(&gpu->pdev->dev, opp); + dev_pm_opp_set_opp(&gpu->pdev->dev, opp); pm_runtime_put(gmu->dev); } @@ -866,7 +866,7 @@ static void a6xx_gmu_set_initial_bw(struct msm_gpu *gpu, struct a6xx_gmu *gmu) if (IS_ERR_OR_NULL(gpu_opp)) return; - dev_pm_opp_set_bw(&gpu->pdev->dev, gpu_opp); + dev_pm_opp_set_opp(&gpu->pdev->dev, gpu_opp); dev_pm_opp_put(gpu_opp); } @@ -1072,7 +1072,7 @@ int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu) a6xx_gmu_shutdown(gmu); /* Remove the bus vote */ - dev_pm_opp_set_bw(&gpu->pdev->dev, NULL); + dev_pm_opp_set_opp(&gpu->pdev->dev, NULL); /* * Make sure the GX domain is off before turning off the GMU (CX) diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c index bb29cf02974d..43bbbfd6ade8 100644 --- a/drivers/gpu/drm/radeon/radeon_bios.c +++ b/drivers/gpu/drm/radeon/radeon_bios.c @@ -205,7 +205,7 @@ static bool radeon_atrm_get_bios(struct radeon_device *rdev) continue; status = acpi_get_handle(dhandle, "ATRM", &atrm_handle); - if (!ACPI_FAILURE(status)) { + if (ACPI_SUCCESS(status)) { found = true; break; } @@ -218,7 +218,7 @@ static bool radeon_atrm_get_bios(struct radeon_device *rdev) continue; status = acpi_get_handle(dhandle, "ATRM", &atrm_handle); - if (!ACPI_FAILURE(status)) { + if (ACPI_SUCCESS(status)) { found = true; break; } diff --git a/drivers/hwmon/acpi_power_meter.c b/drivers/hwmon/acpi_power_meter.c index 848718ab7312..7d3ddcba34ce 100644 --- a/drivers/hwmon/acpi_power_meter.c +++ b/drivers/hwmon/acpi_power_meter.c @@ -161,7 +161,7 @@ static ssize_t set_avg_interval(struct device *dev, mutex_lock(&resource->lock); status = acpi_evaluate_integer(resource->acpi_dev->handle, "_PAI", &args, &data); - if (!ACPI_FAILURE(status)) + if (ACPI_SUCCESS(status)) resource->avg_interval = temp; mutex_unlock(&resource->lock); @@ -232,7 +232,7 @@ static ssize_t set_cap(struct device *dev, struct device_attribute *devattr, mutex_lock(&resource->lock); status = acpi_evaluate_integer(resource->acpi_dev->handle, "_SHL", &args, &data); - if (!ACPI_FAILURE(status)) + if (ACPI_SUCCESS(status)) resource->cap = temp; mutex_unlock(&resource->lock); diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 28f93b9aa51b..3273360f30f7 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -37,7 +37,7 @@ */ /* un-comment DEBUG to enable pr_debug() statements */ -#define DEBUG +/* #define DEBUG */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 8c905aabacc0..c3f3d9249cc5 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -27,6 +27,10 @@ * various states of availability. */ LIST_HEAD(opp_tables); + +/* OPP tables with uninitialized required OPPs */ +LIST_HEAD(lazy_opp_tables); + /* Lock to allow exclusive modification to the device and opp lists */ DEFINE_MUTEX(opp_table_lock); /* Flag indicating that opp_tables list is being updated at the moment */ @@ -145,6 +149,32 @@ unsigned int dev_pm_opp_get_level(struct dev_pm_opp *opp) } EXPORT_SYMBOL_GPL(dev_pm_opp_get_level); +/** + * dev_pm_opp_get_required_pstate() - Gets the required performance state + * corresponding to an available opp + * @opp: opp for which performance state has to be returned for + * @index: index of the required opp + * + * Return: performance state read from device tree corresponding to the + * required opp, else return 0. + */ +unsigned int dev_pm_opp_get_required_pstate(struct dev_pm_opp *opp, + unsigned int index) +{ + if (IS_ERR_OR_NULL(opp) || !opp->available || + index >= opp->opp_table->required_opp_count) { + pr_err("%s: Invalid parameters\n", __func__); + return 0; + } + + /* required-opps not fully initialized yet */ + if (lazy_linking_pending(opp->opp_table)) + return 0; + + return opp->required_opps[index]->pstate; +} +EXPORT_SYMBOL_GPL(dev_pm_opp_get_required_pstate); + /** * dev_pm_opp_is_turbo() - Returns if opp is turbo OPP or not * @opp: opp for which turbo mode is being verified @@ -449,6 +479,55 @@ struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev, } EXPORT_SYMBOL_GPL(dev_pm_opp_find_level_exact); +/** + * dev_pm_opp_find_level_ceil() - search for an rounded up level + * @dev: device for which we do this operation + * @level: level to search for + * + * Return: Searches for rounded up match in the opp table and returns pointer + * to the matching opp if found, else returns ERR_PTR in case of error and + * should be handled using IS_ERR. Error return values can be: + * EINVAL: for bad pointer + * ERANGE: no match found for search + * ENODEV: if device not found in list of registered devices + * + * The callers are required to call dev_pm_opp_put() for the returned OPP after + * use. + */ +struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev, + unsigned int *level) +{ + struct opp_table *opp_table; + struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE); + + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + int r = PTR_ERR(opp_table); + + dev_err(dev, "%s: OPP table not found (%d)\n", __func__, r); + return ERR_PTR(r); + } + + mutex_lock(&opp_table->lock); + + list_for_each_entry(temp_opp, &opp_table->opp_list, node) { + if (temp_opp->available && temp_opp->level >= *level) { + opp = temp_opp; + *level = opp->level; + + /* Increment the reference count of OPP */ + dev_pm_opp_get(opp); + break; + } + } + + mutex_unlock(&opp_table->lock); + dev_pm_opp_put_opp_table(opp_table); + + return opp; +} +EXPORT_SYMBOL_GPL(dev_pm_opp_find_level_ceil); + static noinline struct dev_pm_opp *_find_freq_ceil(struct opp_table *opp_table, unsigned long *freq) { @@ -655,6 +734,10 @@ static inline int _generic_set_opp_clk_only(struct device *dev, struct clk *clk, { int ret; + /* We may reach here for devices which don't change frequency */ + if (IS_ERR(clk)) + return 0; + ret = clk_set_rate(clk, freq); if (ret) { dev_err(dev, "%s: failed to set clock rate: %d\n", __func__, @@ -666,12 +749,12 @@ static inline int _generic_set_opp_clk_only(struct device *dev, struct clk *clk, static int _generic_set_opp_regulator(struct opp_table *opp_table, struct device *dev, - unsigned long old_freq, + struct dev_pm_opp *opp, unsigned long freq, - struct dev_pm_opp_supply *old_supply, - struct dev_pm_opp_supply *new_supply) + int scaling_down) { struct regulator *reg = opp_table->regulators[0]; + struct dev_pm_opp *old_opp = opp_table->current_opp; int ret; /* This function only supports single regulator per device */ @@ -681,8 +764,8 @@ static int _generic_set_opp_regulator(struct opp_table *opp_table, } /* Scaling up? Scale voltage before frequency */ - if (freq >= old_freq) { - ret = _set_opp_voltage(dev, reg, new_supply); + if (!scaling_down) { + ret = _set_opp_voltage(dev, reg, opp->supplies); if (ret) goto restore_voltage; } @@ -693,8 +776,8 @@ static int _generic_set_opp_regulator(struct opp_table *opp_table, goto restore_voltage; /* Scaling down? Scale voltage after frequency */ - if (freq < old_freq) { - ret = _set_opp_voltage(dev, reg, new_supply); + if (scaling_down) { + ret = _set_opp_voltage(dev, reg, opp->supplies); if (ret) goto restore_freq; } @@ -712,19 +795,18 @@ static int _generic_set_opp_regulator(struct opp_table *opp_table, return 0; restore_freq: - if (_generic_set_opp_clk_only(dev, opp_table->clk, old_freq)) + if (_generic_set_opp_clk_only(dev, opp_table->clk, old_opp->rate)) dev_err(dev, "%s: failed to restore old-freq (%lu Hz)\n", - __func__, old_freq); + __func__, old_opp->rate); restore_voltage: /* This shouldn't harm even if the voltages weren't updated earlier */ - if (old_supply) - _set_opp_voltage(dev, reg, old_supply); + _set_opp_voltage(dev, reg, old_opp->supplies); return ret; } static int _set_opp_bw(const struct opp_table *opp_table, - struct dev_pm_opp *opp, struct device *dev, bool remove) + struct dev_pm_opp *opp, struct device *dev) { u32 avg, peak; int i, ret; @@ -733,7 +815,7 @@ static int _set_opp_bw(const struct opp_table *opp_table, return 0; for (i = 0; i < opp_table->path_count; i++) { - if (remove) { + if (!opp) { avg = 0; peak = 0; } else { @@ -743,7 +825,7 @@ static int _set_opp_bw(const struct opp_table *opp_table, ret = icc_set_bw(opp_table->paths[i], avg, peak); if (ret) { dev_err(dev, "Failed to %s bandwidth[%d]: %d\n", - remove ? "remove" : "set", i, ret); + opp ? "set" : "remove", i, ret); return ret; } } @@ -752,29 +834,31 @@ static int _set_opp_bw(const struct opp_table *opp_table, } static int _set_opp_custom(const struct opp_table *opp_table, - struct device *dev, unsigned long old_freq, - unsigned long freq, - struct dev_pm_opp_supply *old_supply, - struct dev_pm_opp_supply *new_supply) + struct device *dev, struct dev_pm_opp *opp, + unsigned long freq) { - struct dev_pm_set_opp_data *data; + struct dev_pm_set_opp_data *data = opp_table->set_opp_data; + struct dev_pm_opp *old_opp = opp_table->current_opp; int size; - data = opp_table->set_opp_data; + /* + * We support this only if dev_pm_opp_set_regulators() was called + * earlier. + */ + if (opp_table->sod_supplies) { + size = sizeof(*old_opp->supplies) * opp_table->regulator_count; + memcpy(data->old_opp.supplies, old_opp->supplies, size); + memcpy(data->new_opp.supplies, opp->supplies, size); + data->regulator_count = opp_table->regulator_count; + } else { + data->regulator_count = 0; + } + data->regulators = opp_table->regulators; - data->regulator_count = opp_table->regulator_count; data->clk = opp_table->clk; data->dev = dev; - - data->old_opp.rate = old_freq; - size = sizeof(*old_supply) * opp_table->regulator_count; - if (!old_supply) - memset(data->old_opp.supplies, 0, size); - else - memcpy(data->old_opp.supplies, old_supply, size); - + data->old_opp.rate = old_opp->rate; data->new_opp.rate = freq; - memcpy(data->new_opp.supplies, new_supply, size); return opp_table->set_opp(data); } @@ -809,6 +893,10 @@ static int _set_required_opps(struct device *dev, if (!required_opp_tables) return 0; + /* required-opps not fully initialized yet */ + if (lazy_linking_pending(opp_table)) + return -EBUSY; + /* Single genpd case */ if (!genpd_virt_devs) return _set_required_opp(dev, dev, opp, 0); @@ -841,38 +929,32 @@ static int _set_required_opps(struct device *dev, return ret; } -/** - * dev_pm_opp_set_bw() - sets bandwidth levels corresponding to an opp - * @dev: device for which we do this operation - * @opp: opp based on which the bandwidth levels are to be configured - * - * This configures the bandwidth to the levels specified by the OPP. However - * if the OPP specified is NULL the bandwidth levels are cleared out. - * - * Return: 0 on success or a negative error value. - */ -int dev_pm_opp_set_bw(struct device *dev, struct dev_pm_opp *opp) +static void _find_current_opp(struct device *dev, struct opp_table *opp_table) { - struct opp_table *opp_table; - int ret; + struct dev_pm_opp *opp = ERR_PTR(-ENODEV); + unsigned long freq; - opp_table = _find_opp_table(dev); - if (IS_ERR(opp_table)) { - dev_err(dev, "%s: device opp table doesn't exist\n", __func__); - return PTR_ERR(opp_table); + if (!IS_ERR(opp_table->clk)) { + freq = clk_get_rate(opp_table->clk); + opp = _find_freq_ceil(opp_table, &freq); } - if (opp) - ret = _set_opp_bw(opp_table, opp, dev, false); - else - ret = _set_opp_bw(opp_table, NULL, dev, true); + /* + * Unable to find the current OPP ? Pick the first from the list since + * it is in ascending order, otherwise rest of the code will need to + * make special checks to validate current_opp. + */ + if (IS_ERR(opp)) { + mutex_lock(&opp_table->lock); + opp = list_first_entry(&opp_table->opp_list, struct dev_pm_opp, node); + dev_pm_opp_get(opp); + mutex_unlock(&opp_table->lock); + } - dev_pm_opp_put_opp_table(opp_table); - return ret; + opp_table->current_opp = opp; } -EXPORT_SYMBOL_GPL(dev_pm_opp_set_bw); -static int _opp_set_rate_zero(struct device *dev, struct opp_table *opp_table) +static int _disable_opp_table(struct device *dev, struct opp_table *opp_table) { int ret; @@ -887,7 +969,7 @@ static int _opp_set_rate_zero(struct device *dev, struct opp_table *opp_table) if (!_get_opp_count(opp_table)) return 0; - ret = _set_opp_bw(opp_table, NULL, dev, true); + ret = _set_opp_bw(opp_table, NULL, dev); if (ret) return ret; @@ -900,6 +982,89 @@ static int _opp_set_rate_zero(struct device *dev, struct opp_table *opp_table) return ret; } +static int _set_opp(struct device *dev, struct opp_table *opp_table, + struct dev_pm_opp *opp, unsigned long freq) +{ + struct dev_pm_opp *old_opp; + int scaling_down, ret; + + if (unlikely(!opp)) + return _disable_opp_table(dev, opp_table); + + /* Find the currently set OPP if we don't know already */ + if (unlikely(!opp_table->current_opp)) + _find_current_opp(dev, opp_table); + + old_opp = opp_table->current_opp; + + /* Return early if nothing to do */ + if (opp_table->enabled && old_opp == opp) { + dev_dbg(dev, "%s: OPPs are same, nothing to do\n", __func__); + return 0; + } + + dev_dbg(dev, "%s: switching OPP: Freq %lu -> %lu Hz, Level %u -> %u, Bw %u -> %u\n", + __func__, old_opp->rate, freq, old_opp->level, opp->level, + old_opp->bandwidth ? old_opp->bandwidth[0].peak : 0, + opp->bandwidth ? opp->bandwidth[0].peak : 0); + + scaling_down = _opp_compare_key(old_opp, opp); + if (scaling_down == -1) + scaling_down = 0; + + /* Scaling up? Configure required OPPs before frequency */ + if (!scaling_down) { + ret = _set_required_opps(dev, opp_table, opp, true); + if (ret) { + dev_err(dev, "Failed to set required opps: %d\n", ret); + return ret; + } + + ret = _set_opp_bw(opp_table, opp, dev); + if (ret) { + dev_err(dev, "Failed to set bw: %d\n", ret); + return ret; + } + } + + if (opp_table->set_opp) { + ret = _set_opp_custom(opp_table, dev, opp, freq); + } else if (opp_table->regulators) { + ret = _generic_set_opp_regulator(opp_table, dev, opp, freq, + scaling_down); + } else { + /* Only frequency scaling */ + ret = _generic_set_opp_clk_only(dev, opp_table->clk, freq); + } + + if (ret) + return ret; + + /* Scaling down? Configure required OPPs after frequency */ + if (scaling_down) { + ret = _set_opp_bw(opp_table, opp, dev); + if (ret) { + dev_err(dev, "Failed to set bw: %d\n", ret); + return ret; + } + + ret = _set_required_opps(dev, opp_table, opp, false); + if (ret) { + dev_err(dev, "Failed to set required opps: %d\n", ret); + return ret; + } + } + + opp_table->enabled = true; + dev_pm_opp_put(old_opp); + + /* Make sure current_opp doesn't get freed */ + dev_pm_opp_get(opp); + opp_table->current_opp = opp; + + return ret; +} + /** * dev_pm_opp_set_rate() - Configure new OPP based on frequency * @dev: device for which we do this operation @@ -914,9 +1079,71 @@ static int _opp_set_rate_zero(struct device *dev, struct opp_table *opp_table) int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) { struct opp_table *opp_table; - unsigned long freq, old_freq, temp_freq; - struct dev_pm_opp *old_opp, *opp; - struct clk *clk; + unsigned long freq = 0, temp_freq; + struct dev_pm_opp *opp = NULL; + int ret; + + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + dev_err(dev, "%s: device's opp table doesn't exist\n", __func__); + return PTR_ERR(opp_table); + } + + if (target_freq) { + /* + * For IO devices which require an OPP on some platforms/SoCs + * while just needing to scale the clock on some others + * we look for empty OPP tables with just a clock handle and + * scale only the clk. This makes dev_pm_opp_set_rate() + * equivalent to a clk_set_rate() + */ + if (!_get_opp_count(opp_table)) { + ret = _generic_set_opp_clk_only(dev, opp_table->clk, target_freq); + goto put_opp_table; + } + + freq = clk_round_rate(opp_table->clk, target_freq); + if ((long)freq <= 0) + freq = target_freq; + + /* + * The clock driver may support finer resolution of the + * frequencies than the OPP table, don't update the frequency we + * pass to clk_set_rate() here. + */ + temp_freq = freq; + opp = _find_freq_ceil(opp_table, &temp_freq); + if (IS_ERR(opp)) { + ret = PTR_ERR(opp); + dev_err(dev, "%s: failed to find OPP for freq %lu (%d)\n", + __func__, freq, ret); + goto put_opp_table; + } + } + + ret = _set_opp(dev, opp_table, opp, freq); + + if (target_freq) + dev_pm_opp_put(opp); +put_opp_table: + dev_pm_opp_put_opp_table(opp_table); + return ret; +} +EXPORT_SYMBOL_GPL(dev_pm_opp_set_rate); + +/** + * dev_pm_opp_set_opp() - Configure device for OPP + * @dev: device for which we do this operation + * @opp: OPP to set to + * + * This configures the device based on the properties of the OPP passed to this + * routine. + * + * Return: 0 on success, a negative error number otherwise. + */ +int dev_pm_opp_set_opp(struct device *dev, struct dev_pm_opp *opp) +{ + struct opp_table *opp_table; int ret; opp_table = _find_opp_table(dev); @@ -925,107 +1152,12 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) return PTR_ERR(opp_table); } - if (unlikely(!target_freq)) { - ret = _opp_set_rate_zero(dev, opp_table); - goto put_opp_table; - } - - clk = opp_table->clk; - if (IS_ERR(clk)) { - dev_err(dev, "%s: No clock available for the device\n", - __func__); - ret = PTR_ERR(clk); - goto put_opp_table; - } - - freq = clk_round_rate(clk, target_freq); - if ((long)freq <= 0) - freq = target_freq; - - old_freq = clk_get_rate(clk); - - /* Return early if nothing to do */ - if (opp_table->enabled && old_freq == freq) { - dev_dbg(dev, "%s: old/new frequencies (%lu Hz) are same, nothing to do\n", - __func__, freq); - ret = 0; - goto put_opp_table; - } - - /* - * For IO devices which require an OPP on some platforms/SoCs - * while just needing to scale the clock on some others - * we look for empty OPP tables with just a clock handle and - * scale only the clk. This makes dev_pm_opp_set_rate() - * equivalent to a clk_set_rate() - */ - if (!_get_opp_count(opp_table)) { - ret = _generic_set_opp_clk_only(dev, clk, freq); - goto put_opp_table; - } - - temp_freq = old_freq; - old_opp = _find_freq_ceil(opp_table, &temp_freq); - if (IS_ERR(old_opp)) { - dev_err(dev, "%s: failed to find current OPP for freq %lu (%ld)\n", - __func__, old_freq, PTR_ERR(old_opp)); - } - - temp_freq = freq; - opp = _find_freq_ceil(opp_table, &temp_freq); - if (IS_ERR(opp)) { - ret = PTR_ERR(opp); - dev_err(dev, "%s: failed to find OPP for freq %lu (%d)\n", - __func__, freq, ret); - goto put_old_opp; - } - - dev_dbg(dev, "%s: switching OPP: %lu Hz --> %lu Hz\n", __func__, - old_freq, freq); - - /* Scaling up? Configure required OPPs before frequency */ - if (freq >= old_freq) { - ret = _set_required_opps(dev, opp_table, opp, true); - if (ret) - goto put_opp; - } - - if (opp_table->set_opp) { - ret = _set_opp_custom(opp_table, dev, old_freq, freq, - IS_ERR(old_opp) ? NULL : old_opp->supplies, - opp->supplies); - } else if (opp_table->regulators) { - ret = _generic_set_opp_regulator(opp_table, dev, old_freq, freq, - IS_ERR(old_opp) ? NULL : old_opp->supplies, - opp->supplies); - } else { - /* Only frequency scaling */ - ret = _generic_set_opp_clk_only(dev, clk, freq); - } - - /* Scaling down? Configure required OPPs after frequency */ - if (!ret && freq < old_freq) { - ret = _set_required_opps(dev, opp_table, opp, false); - if (ret) - dev_err(dev, "Failed to set required opps: %d\n", ret); - } - - if (!ret) { - ret = _set_opp_bw(opp_table, opp, dev, false); - if (!ret) - opp_table->enabled = true; - } - -put_opp: - dev_pm_opp_put(opp); -put_old_opp: - if (!IS_ERR(old_opp)) - dev_pm_opp_put(old_opp); -put_opp_table: + ret = _set_opp(dev, opp_table, opp, opp ? opp->rate : 0); dev_pm_opp_put_opp_table(opp_table); + return ret; } -EXPORT_SYMBOL_GPL(dev_pm_opp_set_rate); +EXPORT_SYMBOL_GPL(dev_pm_opp_set_opp); /* OPP-dev Helpers */ static void _remove_opp_dev(struct opp_device *opp_dev, @@ -1075,6 +1207,7 @@ static struct opp_table *_allocate_opp_table(struct device *dev, int index) mutex_init(&opp_table->lock); mutex_init(&opp_table->genpd_virt_dev_lock); INIT_LIST_HEAD(&opp_table->dev_list); + INIT_LIST_HEAD(&opp_table->lazy); /* Mark regulator count uninitialized */ opp_table->regulator_count = -1; @@ -1087,21 +1220,11 @@ static struct opp_table *_allocate_opp_table(struct device *dev, int index) _of_init_opp_table(opp_table, dev, index); - /* Find clk for the device */ - opp_table->clk = clk_get(dev, NULL); - if (IS_ERR(opp_table->clk)) { - ret = PTR_ERR(opp_table->clk); - if (ret == -EPROBE_DEFER) - goto remove_opp_dev; - - dev_dbg(dev, "%s: Couldn't find clock: %d\n", __func__, ret); - } - /* Find interconnect path(s) for the device */ ret = dev_pm_opp_of_find_icc_paths(dev, opp_table); if (ret) { if (ret == -EPROBE_DEFER) - goto put_clk; + goto remove_opp_dev; dev_warn(dev, "%s: Error finding interconnect paths: %d\n", __func__, ret); @@ -1113,9 +1236,6 @@ static struct opp_table *_allocate_opp_table(struct device *dev, int index) return opp_table; -put_clk: - if (!IS_ERR(opp_table->clk)) - clk_put(opp_table->clk); remove_opp_dev: _remove_opp_dev(opp_dev, opp_table); err: @@ -1128,6 +1248,37 @@ void _get_opp_table_kref(struct opp_table *opp_table) kref_get(&opp_table->kref); } +static struct opp_table *_update_opp_table_clk(struct device *dev, + struct opp_table *opp_table, + bool getclk) +{ + int ret; + + /* + * Return early if we don't need to get clk or we have already tried it + * earlier. + */ + if (!getclk || IS_ERR(opp_table) || opp_table->clk) + return opp_table; + + /* Find clk for the device */ + opp_table->clk = clk_get(dev, NULL); + + ret = PTR_ERR_OR_ZERO(opp_table->clk); + if (!ret) + return opp_table; + + if (ret == -ENOENT) { + dev_dbg(dev, "%s: Couldn't find clock: %d\n", __func__, ret); + return opp_table; + } + + dev_pm_opp_put_opp_table(opp_table); + dev_err_probe(dev, ret, "Couldn't find clock\n"); + + return ERR_PTR(ret); +} + /* * We need to make sure that the OPP table for a device doesn't get added twice, * if this routine gets called in parallel with the same device pointer. @@ -1143,7 +1294,8 @@ void _get_opp_table_kref(struct opp_table *opp_table) * uses the opp_tables_busy flag to indicate if another creator is in the middle * of adding an OPP table and others should wait for it to finish. */ -struct opp_table *_add_opp_table_indexed(struct device *dev, int index) +struct opp_table *_add_opp_table_indexed(struct device *dev, int index, + bool getclk) { struct opp_table *opp_table; @@ -1190,12 +1342,12 @@ again: unlock: mutex_unlock(&opp_table_lock); - return opp_table; + return _update_opp_table_clk(dev, opp_table, getclk); } -struct opp_table *_add_opp_table(struct device *dev) +static struct opp_table *_add_opp_table(struct device *dev, bool getclk) { - return _add_opp_table_indexed(dev, 0); + return _add_opp_table_indexed(dev, 0, getclk); } struct opp_table *dev_pm_opp_get_opp_table(struct device *dev) @@ -1214,6 +1366,9 @@ static void _opp_table_kref_release(struct kref *kref) list_del(&opp_table->node); mutex_unlock(&opp_table_lock); + if (opp_table->current_opp) + dev_pm_opp_put(opp_table->current_opp); + _of_clear_opp_table(opp_table); /* Release clk */ @@ -1508,6 +1663,21 @@ static int _opp_is_duplicate(struct device *dev, struct dev_pm_opp *new_opp, return 0; } +void _required_opps_available(struct dev_pm_opp *opp, int count) +{ + int i; + + for (i = 0; i < count; i++) { + if (opp->required_opps[i]->available) + continue; + + opp->available = false; + pr_warn("%s: OPP not supported by required OPP %pOF (%lu)\n", + __func__, opp->required_opps[i]->np, opp->rate); + return; + } +} + /* * Returns: * 0: On success. And appropriate error message for duplicate OPPs. @@ -1527,12 +1697,10 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, mutex_lock(&opp_table->lock); head = &opp_table->opp_list; - if (likely(!rate_not_available)) { - ret = _opp_is_duplicate(dev, new_opp, opp_table, &head); - if (ret) { - mutex_unlock(&opp_table->lock); - return ret; - } + ret = _opp_is_duplicate(dev, new_opp, opp_table, &head); + if (ret) { + mutex_unlock(&opp_table->lock); + return ret; } list_add(&new_opp->node, head); @@ -1549,6 +1717,12 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, __func__, new_opp->rate); } + /* required-opps not fully initialized yet */ + if (lazy_linking_pending(opp_table)) + return 0; + + _required_opps_available(new_opp, opp_table->required_opp_count); + return 0; } @@ -1631,7 +1805,7 @@ struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev, { struct opp_table *opp_table; - opp_table = _add_opp_table(dev); + opp_table = _add_opp_table(dev, false); if (IS_ERR(opp_table)) return opp_table; @@ -1693,7 +1867,7 @@ struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name) { struct opp_table *opp_table; - opp_table = _add_opp_table(dev); + opp_table = _add_opp_table(dev, false); if (IS_ERR(opp_table)) return opp_table; @@ -1737,38 +1911,6 @@ void dev_pm_opp_put_prop_name(struct opp_table *opp_table) } EXPORT_SYMBOL_GPL(dev_pm_opp_put_prop_name); -static int _allocate_set_opp_data(struct opp_table *opp_table) -{ - struct dev_pm_set_opp_data *data; - int len, count = opp_table->regulator_count; - - if (WARN_ON(!opp_table->regulators)) - return -EINVAL; - - /* space for set_opp_data */ - len = sizeof(*data); - - /* space for old_opp.supplies and new_opp.supplies */ - len += 2 * sizeof(struct dev_pm_opp_supply) * count; - - data = kzalloc(len, GFP_KERNEL); - if (!data) - return -ENOMEM; - - data->old_opp.supplies = (void *)(data + 1); - data->new_opp.supplies = data->old_opp.supplies + count; - - opp_table->set_opp_data = data; - - return 0; -} - -static void _free_set_opp_data(struct opp_table *opp_table) -{ - kfree(opp_table->set_opp_data); - opp_table->set_opp_data = NULL; -} - /** * dev_pm_opp_set_regulators() - Set regulator names for the device * @dev: Device for which regulator name is being set. @@ -1785,11 +1927,12 @@ struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count) { + struct dev_pm_opp_supply *supplies; struct opp_table *opp_table; struct regulator *reg; int ret, i; - opp_table = _add_opp_table(dev); + opp_table = _add_opp_table(dev, false); if (IS_ERR(opp_table)) return opp_table; @@ -1826,10 +1969,19 @@ struct opp_table *dev_pm_opp_set_regulators(struct device *dev, opp_table->regulator_count = count; - /* Allocate block only once to pass to set_opp() routines */ - ret = _allocate_set_opp_data(opp_table); - if (ret) + supplies = kmalloc_array(count * 2, sizeof(*supplies), GFP_KERNEL); + if (!supplies) { + ret = -ENOMEM; goto free_regulators; + } + + mutex_lock(&opp_table->lock); + opp_table->sod_supplies = supplies; + if (opp_table->set_opp_data) { + opp_table->set_opp_data->old_opp.supplies = supplies; + opp_table->set_opp_data->new_opp.supplies = supplies + count; + } + mutex_unlock(&opp_table->lock); return opp_table; @@ -1872,7 +2024,15 @@ void dev_pm_opp_put_regulators(struct opp_table *opp_table) for (i = opp_table->regulator_count - 1; i >= 0; i--) regulator_put(opp_table->regulators[i]); - _free_set_opp_data(opp_table); + mutex_lock(&opp_table->lock); + if (opp_table->set_opp_data) { + opp_table->set_opp_data->old_opp.supplies = NULL; + opp_table->set_opp_data->new_opp.supplies = NULL; + } + + kfree(opp_table->sod_supplies); + opp_table->sod_supplies = NULL; + mutex_unlock(&opp_table->lock); kfree(opp_table->regulators); opp_table->regulators = NULL; @@ -1900,7 +2060,7 @@ struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char *name) struct opp_table *opp_table; int ret; - opp_table = _add_opp_table(dev); + opp_table = _add_opp_table(dev, false); if (IS_ERR(opp_table)) return opp_table; @@ -1910,9 +2070,11 @@ struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char *name) goto err; } - /* Already have default clk set, free it */ - if (!IS_ERR(opp_table->clk)) - clk_put(opp_table->clk); + /* clk shouldn't be initialized at this point */ + if (WARN_ON(opp_table->clk)) { + ret = -EBUSY; + goto err; + } /* Find clk for the device */ opp_table->clk = clk_get(dev, name); @@ -1966,12 +2128,13 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put_clkname); struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)) { + struct dev_pm_set_opp_data *data; struct opp_table *opp_table; if (!set_opp) return ERR_PTR(-EINVAL); - opp_table = _add_opp_table(dev); + opp_table = _add_opp_table(dev, false); if (IS_ERR(opp_table)) return opp_table; @@ -1982,8 +2145,23 @@ struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, } /* Another CPU that shares the OPP table has set the helper ? */ - if (!opp_table->set_opp) - opp_table->set_opp = set_opp; + if (opp_table->set_opp) + return opp_table; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return ERR_PTR(-ENOMEM); + + mutex_lock(&opp_table->lock); + opp_table->set_opp_data = data; + if (opp_table->sod_supplies) { + data->old_opp.supplies = opp_table->sod_supplies; + data->new_opp.supplies = opp_table->sod_supplies + + opp_table->regulator_count; + } + mutex_unlock(&opp_table->lock); + + opp_table->set_opp = set_opp; return opp_table; } @@ -2005,10 +2183,50 @@ void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table) WARN_ON(!list_empty(&opp_table->opp_list)); opp_table->set_opp = NULL; + + mutex_lock(&opp_table->lock); + kfree(opp_table->set_opp_data); + opp_table->set_opp_data = NULL; + mutex_unlock(&opp_table->lock); + dev_pm_opp_put_opp_table(opp_table); } EXPORT_SYMBOL_GPL(dev_pm_opp_unregister_set_opp_helper); +static void devm_pm_opp_unregister_set_opp_helper(void *data) +{ + dev_pm_opp_unregister_set_opp_helper(data); +} + +/** + * devm_pm_opp_register_set_opp_helper() - Register custom set OPP helper + * @dev: Device for which the helper is getting registered. + * @set_opp: Custom set OPP helper. + * + * This is a resource-managed version of dev_pm_opp_register_set_opp_helper(). + * + * Return: pointer to 'struct opp_table' on success and errorno otherwise. + */ +struct opp_table * +devm_pm_opp_register_set_opp_helper(struct device *dev, + int (*set_opp)(struct dev_pm_set_opp_data *data)) +{ + struct opp_table *opp_table; + int err; + + opp_table = dev_pm_opp_register_set_opp_helper(dev, set_opp); + if (IS_ERR(opp_table)) + return opp_table; + + err = devm_add_action_or_reset(dev, devm_pm_opp_unregister_set_opp_helper, + opp_table); + if (err) + return ERR_PTR(err); + + return opp_table; +} +EXPORT_SYMBOL_GPL(devm_pm_opp_register_set_opp_helper); + static void _opp_detach_genpd(struct opp_table *opp_table) { int index; @@ -2058,7 +2276,7 @@ struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, int index = 0, ret = -EINVAL; const char **name = names; - opp_table = _add_opp_table(dev); + opp_table = _add_opp_table(dev, false); if (IS_ERR(opp_table)) return opp_table; @@ -2144,6 +2362,97 @@ void dev_pm_opp_detach_genpd(struct opp_table *opp_table) } EXPORT_SYMBOL_GPL(dev_pm_opp_detach_genpd); +static void devm_pm_opp_detach_genpd(void *data) +{ + dev_pm_opp_detach_genpd(data); +} + +/** + * devm_pm_opp_attach_genpd - Attach genpd(s) for the device and save virtual + * device pointer + * @dev: Consumer device for which the genpd is getting attached. + * @names: Null terminated array of pointers containing names of genpd to attach. + * @virt_devs: Pointer to return the array of virtual devices. + * + * This is a resource-managed version of dev_pm_opp_attach_genpd(). + * + * Return: pointer to 'struct opp_table' on success and errorno otherwise. + */ +struct opp_table * +devm_pm_opp_attach_genpd(struct device *dev, const char **names, + struct device ***virt_devs) +{ + struct opp_table *opp_table; + int err; + + opp_table = dev_pm_opp_attach_genpd(dev, names, virt_devs); + if (IS_ERR(opp_table)) + return opp_table; + + err = devm_add_action_or_reset(dev, devm_pm_opp_detach_genpd, + opp_table); + if (err) + return ERR_PTR(err); + + return opp_table; +} +EXPORT_SYMBOL_GPL(devm_pm_opp_attach_genpd); + +/** + * dev_pm_opp_xlate_required_opp() - Find required OPP for @src_table OPP. + * @src_table: OPP table which has @dst_table as one of its required OPP table. + * @dst_table: Required OPP table of the @src_table. + * @src_opp: OPP from the @src_table. + * + * This function returns the OPP (present in @dst_table) pointed out by the + * "required-opps" property of the @src_opp (present in @src_table). + * + * The callers are required to call dev_pm_opp_put() for the returned OPP after + * use. + * + * Return: pointer to 'struct dev_pm_opp' on success and errorno otherwise. + */ +struct dev_pm_opp *dev_pm_opp_xlate_required_opp(struct opp_table *src_table, + struct opp_table *dst_table, + struct dev_pm_opp *src_opp) +{ + struct dev_pm_opp *opp, *dest_opp = ERR_PTR(-ENODEV); + int i; + + if (!src_table || !dst_table || !src_opp || + !src_table->required_opp_tables) + return ERR_PTR(-EINVAL); + + /* required-opps not fully initialized yet */ + if (lazy_linking_pending(src_table)) + return ERR_PTR(-EBUSY); + + for (i = 0; i < src_table->required_opp_count; i++) { + if (src_table->required_opp_tables[i] == dst_table) { + mutex_lock(&src_table->lock); + + list_for_each_entry(opp, &src_table->opp_list, node) { + if (opp == src_opp) { + dest_opp = opp->required_opps[i]; + dev_pm_opp_get(dest_opp); + break; + } + } + + mutex_unlock(&src_table->lock); + break; + } + } + + if (IS_ERR(dest_opp)) { + pr_err("%s: Couldn't find matching OPP (%p: %p)\n", __func__, + src_table, dst_table); + } + + return dest_opp; +} +EXPORT_SYMBOL_GPL(dev_pm_opp_xlate_required_opp); + /** * dev_pm_opp_xlate_performance_state() - Find required OPP's pstate for src_table. * @src_table: OPP table which has dst_table as one of its required OPP table. @@ -2172,9 +2481,13 @@ int dev_pm_opp_xlate_performance_state(struct opp_table *src_table, * and so none of them have the "required-opps" property set. Return the * pstate of the src_table as it is in such cases. */ - if (!src_table->required_opp_count) + if (!src_table || !src_table->required_opp_count) return pstate; + /* required-opps not fully initialized yet */ + if (lazy_linking_pending(src_table)) + return -EBUSY; + for (i = 0; i < src_table->required_opp_count; i++) { if (src_table->required_opp_tables[i]->np == dst_table->np) break; @@ -2226,7 +2539,7 @@ int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt) struct opp_table *opp_table; int ret; - opp_table = _add_opp_table(dev); + opp_table = _add_opp_table(dev, true); if (IS_ERR(opp_table)) return PTR_ERR(opp_table); @@ -2504,3 +2817,44 @@ void dev_pm_opp_remove_table(struct device *dev) dev_pm_opp_put_opp_table(opp_table); } EXPORT_SYMBOL_GPL(dev_pm_opp_remove_table); + +/** + * dev_pm_opp_sync_regulators() - Sync state of voltage regulators + * @dev: device for which we do this operation + * + * Sync voltage state of the OPP table regulators. + * + * Return: 0 on success or a negative error value. + */ +int dev_pm_opp_sync_regulators(struct device *dev) +{ + struct opp_table *opp_table; + struct regulator *reg; + int i, ret = 0; + + /* Device may not have OPP table */ + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) + return 0; + + /* Regulator may not be required for the device */ + if (unlikely(!opp_table->regulators)) + goto put_table; + + /* Nothing to sync if voltage wasn't changed */ + if (!opp_table->enabled) + goto put_table; + + for (i = 0; i < opp_table->regulator_count; i++) { + reg = opp_table->regulators[i]; + ret = regulator_sync_voltage(reg); + if (ret) + break; + } +put_table: + /* Drop reference taken by _find_opp_table() */ + dev_pm_opp_put_opp_table(opp_table); + + return ret; +} +EXPORT_SYMBOL_GPL(dev_pm_opp_sync_regulators); diff --git a/drivers/opp/of.c b/drivers/opp/of.c index 03cb387236c4..f480c10e6314 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -144,7 +144,7 @@ static void _opp_table_free_required_tables(struct opp_table *opp_table) for (i = 0; i < opp_table->required_opp_count; i++) { if (IS_ERR_OR_NULL(required_opp_tables[i])) - break; + continue; dev_pm_opp_put_opp_table(required_opp_tables[i]); } @@ -153,6 +153,7 @@ static void _opp_table_free_required_tables(struct opp_table *opp_table) opp_table->required_opp_count = 0; opp_table->required_opp_tables = NULL; + list_del(&opp_table->lazy); } /* @@ -165,6 +166,7 @@ static void _opp_table_alloc_required_tables(struct opp_table *opp_table, { struct opp_table **required_opp_tables; struct device_node *required_np, *np; + bool lazy = false; int count, i; /* Traversing the first OPP node is all we need */ @@ -195,8 +197,10 @@ static void _opp_table_alloc_required_tables(struct opp_table *opp_table, required_opp_tables[i] = _find_table_of_opp_np(required_np); of_node_put(required_np); - if (IS_ERR(required_opp_tables[i])) - goto free_required_tables; + if (IS_ERR(required_opp_tables[i])) { + lazy = true; + continue; + } /* * We only support genpd's OPPs in the "required-opps" for now, @@ -210,6 +214,10 @@ static void _opp_table_alloc_required_tables(struct opp_table *opp_table, } } + /* Let's do the linking later on */ + if (lazy) + list_add(&opp_table->lazy, &lazy_opp_tables); + goto put_np; free_required_tables: @@ -278,14 +286,14 @@ void _of_opp_free_required_opps(struct opp_table *opp_table, for (i = 0; i < opp_table->required_opp_count; i++) { if (!required_opps[i]) - break; + continue; /* Put the reference back */ dev_pm_opp_put(required_opps[i]); } - kfree(required_opps); opp->required_opps = NULL; + kfree(required_opps); } /* Populate all required OPPs which are part of "required-opps" list */ @@ -309,6 +317,10 @@ static int _of_opp_alloc_required_opps(struct opp_table *opp_table, for (i = 0; i < count; i++) { required_table = opp_table->required_opp_tables[i]; + /* Required table not added yet, we will link later */ + if (IS_ERR_OR_NULL(required_table)) + continue; + np = of_parse_required_opp(opp->np, i); if (unlikely(!np)) { ret = -ENODEV; @@ -334,6 +346,104 @@ free_required_opps: return ret; } +/* Link required OPPs for an individual OPP */ +static int lazy_link_required_opps(struct opp_table *opp_table, + struct opp_table *new_table, int index) +{ + struct device_node *required_np; + struct dev_pm_opp *opp; + + list_for_each_entry(opp, &opp_table->opp_list, node) { + required_np = of_parse_required_opp(opp->np, index); + if (unlikely(!required_np)) + return -ENODEV; + + opp->required_opps[index] = _find_opp_of_np(new_table, required_np); + of_node_put(required_np); + + if (!opp->required_opps[index]) { + pr_err("%s: Unable to find required OPP node: %pOF (%d)\n", + __func__, opp->np, index); + return -ENODEV; + } + } + + return 0; +} + +/* Link required OPPs for all OPPs of the newly added OPP table */ +static void lazy_link_required_opp_table(struct opp_table *new_table) +{ + struct opp_table *opp_table, *temp, **required_opp_tables; + struct device_node *required_np, *opp_np, *required_table_np; + struct dev_pm_opp *opp; + int i, ret; + + /* + * We only support genpd's OPPs in the "required-opps" for now, + * as we don't know much about other cases. + */ + if (!new_table->is_genpd) + return; + + mutex_lock(&opp_table_lock); + + list_for_each_entry_safe(opp_table, temp, &lazy_opp_tables, lazy) { + bool lazy = false; + + /* opp_np can't be invalid here */ + opp_np = of_get_next_available_child(opp_table->np, NULL); + + for (i = 0; i < opp_table->required_opp_count; i++) { + required_opp_tables = opp_table->required_opp_tables; + + /* Required opp-table is already parsed */ + if (!IS_ERR(required_opp_tables[i])) + continue; + + /* required_np can't be invalid here */ + required_np = of_parse_required_opp(opp_np, i); + required_table_np = of_get_parent(required_np); + + of_node_put(required_table_np); + of_node_put(required_np); + + /* + * Newly added table isn't the required opp-table for + * opp_table. + */ + if (required_table_np != new_table->np) { + lazy = true; + continue; + } + + required_opp_tables[i] = new_table; + _get_opp_table_kref(new_table); + + /* Link OPPs now */ + ret = lazy_link_required_opps(opp_table, new_table, i); + if (ret) { + /* The OPPs will be marked unusable */ + lazy = false; + break; + } + } + + of_node_put(opp_np); + + /* All required opp-tables found, remove from lazy list */ + if (!lazy) { + list_del(&opp_table->lazy); + INIT_LIST_HEAD(&opp_table->lazy); + + list_for_each_entry(opp, &opp_table->opp_list, node) + _required_opps_available(opp, opp_table->required_opp_count); + } + } + + mutex_unlock(&opp_table_lock); +} + static int _bandwidth_supported(struct device *dev, struct opp_table *opp_table) { struct device_node *np, *opp_np; @@ -755,7 +865,6 @@ static struct dev_pm_opp *_opp_add_static_v2(struct opp_table *opp_table, struct device *dev, struct device_node *np) { struct dev_pm_opp *new_opp; - u64 rate = 0; u32 val; int ret; bool rate_not_available = false; @@ -772,7 +881,8 @@ static struct dev_pm_opp *_opp_add_static_v2(struct opp_table *opp_table, /* Check if the OPP supports hardware's hierarchy of versions or not */ if (!_opp_is_supported(dev, opp_table, np)) { - dev_dbg(dev, "OPP not supported by hardware: %llu\n", rate); + dev_dbg(dev, "OPP not supported by hardware: %lu\n", + new_opp->rate); goto free_opp; } @@ -822,10 +932,11 @@ static struct dev_pm_opp *_opp_add_static_v2(struct opp_table *opp_table, if (new_opp->clock_latency_ns > opp_table->clock_latency_ns_max) opp_table->clock_latency_ns_max = new_opp->clock_latency_ns; - pr_debug("%s: turbo:%d rate:%lu uv:%lu uvmin:%lu uvmax:%lu latency:%lu\n", + pr_debug("%s: turbo:%d rate:%lu uv:%lu uvmin:%lu uvmax:%lu latency:%lu level:%u\n", __func__, new_opp->turbo, new_opp->rate, new_opp->supplies[0].u_volt, new_opp->supplies[0].u_volt_min, - new_opp->supplies[0].u_volt_max, new_opp->clock_latency_ns); + new_opp->supplies[0].u_volt_max, new_opp->clock_latency_ns, + new_opp->level); /* * Notify the changes in the availability of the operable @@ -888,6 +999,8 @@ static int _of_add_opp_table_v2(struct device *dev, struct opp_table *opp_table) } } + lazy_link_required_opp_table(opp_table); + return 0; remove_static_opp: @@ -956,6 +1069,41 @@ remove_static_opp: return ret; } +static int _of_add_table_indexed(struct device *dev, int index, bool getclk) +{ + struct opp_table *opp_table; + int ret, count; + + if (index) { + /* + * If only one phandle is present, then the same OPP table + * applies for all index requests. + */ + count = of_count_phandle_with_args(dev->of_node, + "operating-points-v2", NULL); + if (count == 1) + index = 0; + } + + opp_table = _add_opp_table_indexed(dev, index, getclk); + if (IS_ERR(opp_table)) + return PTR_ERR(opp_table); + + /* + * OPPs have two version of bindings now. Also try the old (v1) + * bindings for backward compatibility with older dtbs. + */ + if (opp_table->np) + ret = _of_add_opp_table_v2(dev, opp_table); + else + ret = _of_add_opp_table_v1(dev, opp_table); + + if (ret) + dev_pm_opp_put_opp_table(opp_table); + + return ret; +} + /** * dev_pm_opp_of_add_table() - Initialize opp table from device tree * @dev: device pointer used to lookup OPP table. @@ -975,26 +1123,7 @@ remove_static_opp: */ int dev_pm_opp_of_add_table(struct device *dev) { - struct opp_table *opp_table; - int ret; - - opp_table = _add_opp_table_indexed(dev, 0); - if (IS_ERR(opp_table)) - return PTR_ERR(opp_table); - - /* - * OPPs have two version of bindings now. Also try the old (v1) - * bindings for backward compatibility with older dtbs. - */ - if (opp_table->np) - ret = _of_add_opp_table_v2(dev, opp_table); - else - ret = _of_add_opp_table_v1(dev, opp_table); - - if (ret) - dev_pm_opp_put_opp_table(opp_table); - - return ret; + return _of_add_table_indexed(dev, 0, true); } EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table); @@ -1006,45 +1135,32 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table); * Register the initial OPP table with the OPP library for given device only * using the "operating-points-v2" property. * - * Return: - * 0 On success OR - * Duplicate OPPs (both freq and volt are same) and opp->available - * -EEXIST Freq are same and volt are different OR - * Duplicate OPPs (both freq and volt are same) and !opp->available - * -ENOMEM Memory allocation failure - * -ENODEV when 'operating-points' property is not found or is invalid data - * in device node. - * -ENODATA when empty 'operating-points' property is found - * -EINVAL when invalid entries are found in opp-v2 table + * Return: Refer to dev_pm_opp_of_add_table() for return values. */ int dev_pm_opp_of_add_table_indexed(struct device *dev, int index) { - struct opp_table *opp_table; - int ret, count; - - if (index) { - /* - * If only one phandle is present, then the same OPP table - * applies for all index requests. - */ - count = of_count_phandle_with_args(dev->of_node, - "operating-points-v2", NULL); - if (count == 1) - index = 0; - } - - opp_table = _add_opp_table_indexed(dev, index); - if (IS_ERR(opp_table)) - return PTR_ERR(opp_table); - - ret = _of_add_opp_table_v2(dev, opp_table); - if (ret) - dev_pm_opp_put_opp_table(opp_table); - - return ret; + return _of_add_table_indexed(dev, index, true); } EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table_indexed); +/** + * dev_pm_opp_of_add_table_noclk() - Initialize indexed opp table from device + * tree without getting clk for device. + * @dev: device pointer used to lookup OPP table. + * @index: Index number. + * + * Register the initial OPP table with the OPP library for given device only + * using the "operating-points-v2" property. Do not try to get the clk for the + * device. + * + * Return: Refer to dev_pm_opp_of_add_table() for return values. + */ +int dev_pm_opp_of_add_table_noclk(struct device *dev, int index) +{ + return _of_add_table_indexed(dev, index, false); +} +EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table_noclk); + /* CPU device specific helpers */ /** diff --git a/drivers/opp/opp.h b/drivers/opp/opp.h index 4ced7ffa8158..9b9daf83b074 100644 --- a/drivers/opp/opp.h +++ b/drivers/opp/opp.h @@ -26,7 +26,7 @@ struct regulator; /* Lock to allow exclusive modification to the device and opp lists */ extern struct mutex opp_table_lock; -extern struct list_head opp_tables; +extern struct list_head opp_tables, lazy_opp_tables; /* * Internal data structure organization with the OPP layer library is as @@ -135,6 +135,7 @@ enum opp_table_access { * @clock_latency_ns_max: Max clock latency in nanoseconds. * @parsed_static_opps: Count of devices for which OPPs are initialized from DT. * @shared_opp: OPP is shared between multiple devices. + * @current_opp: Currently configured OPP for the table. * @suspend_opp: Pointer to OPP to be used during device suspend. * @genpd_virt_dev_lock: Mutex protecting the genpd virtual device pointers. * @genpd_virt_devs: List of virtual devices for multiple genpd support. @@ -155,6 +156,7 @@ enum opp_table_access { * @genpd_performance_state: Device's power domain support performance state. * @is_genpd: Marks if the OPP table belongs to a genpd. * @set_opp: Platform specific set_opp callback + * @sod_supplies: Set opp data supplies * @set_opp_data: Data to be passed to set_opp callback * @dentry: debugfs dentry pointer of the real device directory (not links). * @dentry_name: Name of the real dentry. @@ -166,7 +168,7 @@ enum opp_table_access { * meant for book keeping and private to OPP library. */ struct opp_table { - struct list_head node; + struct list_head node, lazy; struct blocking_notifier_head head; struct list_head dev_list; @@ -182,6 +184,7 @@ struct opp_table { unsigned int parsed_static_opps; enum opp_table_access shared_opp; + struct dev_pm_opp *current_opp; struct dev_pm_opp *suspend_opp; struct mutex genpd_virt_dev_lock; @@ -202,6 +205,7 @@ struct opp_table { bool is_genpd; int (*set_opp)(struct dev_pm_set_opp_data *data); + struct dev_pm_opp_supply *sod_supplies; struct dev_pm_set_opp_data *set_opp_data; #ifdef CONFIG_DEBUG_FS @@ -223,9 +227,14 @@ int _opp_compare_key(struct dev_pm_opp *opp1, struct dev_pm_opp *opp2); int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *opp_table, bool rate_not_available); int _opp_add_v1(struct opp_table *opp_table, struct device *dev, unsigned long freq, long u_volt, bool dynamic); void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, int last_cpu); -struct opp_table *_add_opp_table(struct device *dev); -struct opp_table *_add_opp_table_indexed(struct device *dev, int index); +struct opp_table *_add_opp_table_indexed(struct device *dev, int index, bool getclk); void _put_opp_list_kref(struct opp_table *opp_table); +void _required_opps_available(struct dev_pm_opp *opp, int count); + +static inline bool lazy_linking_pending(struct opp_table *opp_table) +{ + return unlikely(!list_empty(&opp_table->lazy)); +} #ifdef CONFIG_OF void _of_init_opp_table(struct opp_table *opp_table, struct device *dev, int index); diff --git a/drivers/platform/x86/asus-laptop.c b/drivers/platform/x86/asus-laptop.c index 0edafe687fa9..bfea656e910c 100644 --- a/drivers/platform/x86/asus-laptop.c +++ b/drivers/platform/x86/asus-laptop.c @@ -861,7 +861,7 @@ static ssize_t infos_show(struct device *dev, struct device_attribute *attr, * The significance of others is yet to be found. */ rv = acpi_evaluate_integer(asus->handle, "SFUN", NULL, &temp); - if (!ACPI_FAILURE(rv)) + if (ACPI_SUCCESS(rv)) len += sprintf(page + len, "SFUN value : %#x\n", (uint) temp); /* @@ -873,7 +873,7 @@ static ssize_t infos_show(struct device *dev, struct device_attribute *attr, * takes several seconds to run on some systems. */ rv = acpi_evaluate_integer(asus->handle, "HWRS", NULL, &temp); - if (!ACPI_FAILURE(rv)) + if (ACPI_SUCCESS(rv)) len += sprintf(page + len, "HWRS value : %#x\n", (uint) temp); /* @@ -884,7 +884,7 @@ static ssize_t infos_show(struct device *dev, struct device_attribute *attr, * silently ignored. */ rv = acpi_evaluate_integer(asus->handle, "ASYM", NULL, &temp); - if (!ACPI_FAILURE(rv)) + if (ACPI_SUCCESS(rv)) len += sprintf(page + len, "ASYM value : %#x\n", (uint) temp); if (asus->dsdt_info) { diff --git a/drivers/pnp/interface.c b/drivers/pnp/interface.c index 187e4a1175b0..602c46893e83 100644 --- a/drivers/pnp/interface.c +++ b/drivers/pnp/interface.c @@ -33,6 +33,7 @@ struct pnp_info_buffer { typedef struct pnp_info_buffer pnp_info_buffer_t; +__printf(2, 3) static int pnp_printf(pnp_info_buffer_t * buffer, char *fmt, ...) { va_list args; diff --git a/drivers/pnp/pnpbios/bioscalls.c b/drivers/pnp/pnpbios/bioscalls.c index ba5cfc3dbe11..ddc6f2163c8e 100644 --- a/drivers/pnp/pnpbios/bioscalls.c +++ b/drivers/pnp/pnpbios/bioscalls.c @@ -72,7 +72,7 @@ __visible u32 pnp_bios_fault_esp; __visible u32 pnp_bios_fault_eip; __visible u32 pnp_bios_is_utter_crap = 0; -static spinlock_t pnp_bios_lock; +static DEFINE_SPINLOCK(pnp_bios_lock); /* * Support Functions @@ -473,7 +473,6 @@ void pnpbios_calls_init(union pnp_bios_install_struct *header) { int i; - spin_lock_init(&pnp_bios_lock); pnp_bios_callpoint.offset = header->fields.pm16offset; pnp_bios_callpoint.segment = PNP_CS16; diff --git a/drivers/powercap/Kconfig b/drivers/powercap/Kconfig index bc228725346b..20b4325c6161 100644 --- a/drivers/powercap/Kconfig +++ b/drivers/powercap/Kconfig @@ -43,4 +43,17 @@ config IDLE_INJECT CPUs for power capping. Idle period can be injected synchronously on a set of specified CPUs or alternatively on a per CPU basis. + +config DTPM + bool "Power capping for Dynamic Thermal Power Management" + help + This enables support for the power capping for the dynamic + thermal power management userspace engine. + +config DTPM_CPU + bool "Add CPU power capping based on the energy model" + depends on DTPM && ENERGY_MODEL + help + This enables support for CPU power limitation based on + energy model. endif diff --git a/drivers/powercap/Makefile b/drivers/powercap/Makefile index 7255c94ec61c..fabcf388a8d3 100644 --- a/drivers/powercap/Makefile +++ b/drivers/powercap/Makefile @@ -1,4 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_DTPM) += dtpm.o +obj-$(CONFIG_DTPM_CPU) += dtpm_cpu.o obj-$(CONFIG_POWERCAP) += powercap_sys.o obj-$(CONFIG_INTEL_RAPL_CORE) += intel_rapl_common.o obj-$(CONFIG_INTEL_RAPL) += intel_rapl_msr.o diff --git a/drivers/powercap/dtpm.c b/drivers/powercap/dtpm.c new file mode 100644 index 000000000000..5a51cd34a7e8 --- /dev/null +++ b/drivers/powercap/dtpm.c @@ -0,0 +1,480 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2020 Linaro Limited + * + * Author: Daniel Lezcano + * + * The powercap based Dynamic Thermal Power Management framework + * provides to the userspace a consistent API to set the power limit + * on some devices. + * + * DTPM defines the functions to create a tree of constraints. Each + * parent node is a virtual description of the aggregation of the + * children. It propagates the constraints set at its level to its + * children and collect the children power information. The leaves of + * the tree are the real devices which have the ability to get their + * current power consumption and set their power limit. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include + +#define DTPM_POWER_LIMIT_FLAG 0 + +static const char *constraint_name[] = { + "Instantaneous", +}; + +static DEFINE_MUTEX(dtpm_lock); +static struct powercap_control_type *pct; +static struct dtpm *root; + +static int get_time_window_us(struct powercap_zone *pcz, int cid, u64 *window) +{ + return -ENOSYS; +} + +static int set_time_window_us(struct powercap_zone *pcz, int cid, u64 window) +{ + return -ENOSYS; +} + +static int get_max_power_range_uw(struct powercap_zone *pcz, u64 *max_power_uw) +{ + struct dtpm *dtpm = to_dtpm(pcz); + + mutex_lock(&dtpm_lock); + *max_power_uw = dtpm->power_max - dtpm->power_min; + mutex_unlock(&dtpm_lock); + + return 0; +} + +static int __get_power_uw(struct dtpm *dtpm, u64 *power_uw) +{ + struct dtpm *child; + u64 power; + int ret = 0; + + if (dtpm->ops) { + *power_uw = dtpm->ops->get_power_uw(dtpm); + return 0; + } + + *power_uw = 0; + + list_for_each_entry(child, &dtpm->children, sibling) { + ret = __get_power_uw(child, &power); + if (ret) + break; + *power_uw += power; + } + + return ret; +} + +static int get_power_uw(struct powercap_zone *pcz, u64 *power_uw) +{ + struct dtpm *dtpm = to_dtpm(pcz); + int ret; + + mutex_lock(&dtpm_lock); + ret = __get_power_uw(dtpm, power_uw); + mutex_unlock(&dtpm_lock); + + return ret; +} + +static void __dtpm_rebalance_weight(struct dtpm *dtpm) +{ + struct dtpm *child; + + list_for_each_entry(child, &dtpm->children, sibling) { + + pr_debug("Setting weight '%d' for '%s'\n", + child->weight, child->zone.name); + + child->weight = DIV64_U64_ROUND_CLOSEST( + child->power_max * 1024, dtpm->power_max); + + __dtpm_rebalance_weight(child); + } +} + +static void __dtpm_sub_power(struct dtpm *dtpm) +{ + struct dtpm *parent = dtpm->parent; + + while (parent) { + parent->power_min -= dtpm->power_min; + parent->power_max -= dtpm->power_max; + parent->power_limit -= dtpm->power_limit; + parent = parent->parent; + } + + __dtpm_rebalance_weight(root); +} + +static void __dtpm_add_power(struct dtpm *dtpm) +{ + struct dtpm *parent = dtpm->parent; + + while (parent) { + parent->power_min += dtpm->power_min; + parent->power_max += dtpm->power_max; + parent->power_limit += dtpm->power_limit; + parent = parent->parent; + } + + __dtpm_rebalance_weight(root); +} + +/** + * dtpm_update_power - Update the power on the dtpm + * @dtpm: a pointer to a dtpm structure to update + * @power_min: a u64 representing the new power_min value + * @power_max: a u64 representing the new power_max value + * + * Function to update the power values of the dtpm node specified in + * parameter. These new values will be propagated to the tree. + * + * Return: zero on success, -EINVAL if the values are inconsistent + */ +int dtpm_update_power(struct dtpm *dtpm, u64 power_min, u64 power_max) +{ + int ret = 0; + + mutex_lock(&dtpm_lock); + + if (power_min == dtpm->power_min && power_max == dtpm->power_max) + goto unlock; + + if (power_max < power_min) { + ret = -EINVAL; + goto unlock; + } + + __dtpm_sub_power(dtpm); + + dtpm->power_min = power_min; + dtpm->power_max = power_max; + if (!test_bit(DTPM_POWER_LIMIT_FLAG, &dtpm->flags)) + dtpm->power_limit = power_max; + + __dtpm_add_power(dtpm); + +unlock: + mutex_unlock(&dtpm_lock); + + return ret; +} + +/** + * dtpm_release_zone - Cleanup when the node is released + * @pcz: a pointer to a powercap_zone structure + * + * Do some housecleaning and update the weight on the tree. The + * release will be denied if the node has children. This function must + * be called by the specific release callback of the different + * backends. + * + * Return: 0 on success, -EBUSY if there are children + */ +int dtpm_release_zone(struct powercap_zone *pcz) +{ + struct dtpm *dtpm = to_dtpm(pcz); + struct dtpm *parent = dtpm->parent; + + mutex_lock(&dtpm_lock); + + if (!list_empty(&dtpm->children)) { + mutex_unlock(&dtpm_lock); + return -EBUSY; + } + + if (parent) + list_del(&dtpm->sibling); + + __dtpm_sub_power(dtpm); + + mutex_unlock(&dtpm_lock); + + if (dtpm->ops) + dtpm->ops->release(dtpm); + + kfree(dtpm); + + return 0; +} + +static int __get_power_limit_uw(struct dtpm *dtpm, int cid, u64 *power_limit) +{ + *power_limit = dtpm->power_limit; + return 0; +} + +static int get_power_limit_uw(struct powercap_zone *pcz, + int cid, u64 *power_limit) +{ + struct dtpm *dtpm = to_dtpm(pcz); + int ret; + + mutex_lock(&dtpm_lock); + ret = __get_power_limit_uw(dtpm, cid, power_limit); + mutex_unlock(&dtpm_lock); + + return ret; +} + +/* + * Set the power limit on the nodes, the power limit is distributed + * given the weight of the children. + * + * The dtpm node lock must be held when calling this function. + */ +static int __set_power_limit_uw(struct dtpm *dtpm, int cid, u64 power_limit) +{ + struct dtpm *child; + int ret = 0; + u64 power; + + /* + * A max power limitation means we remove the power limit, + * otherwise we set a constraint and flag the dtpm node. + */ + if (power_limit == dtpm->power_max) { + clear_bit(DTPM_POWER_LIMIT_FLAG, &dtpm->flags); + } else { + set_bit(DTPM_POWER_LIMIT_FLAG, &dtpm->flags); + } + + pr_debug("Setting power limit for '%s': %llu uW\n", + dtpm->zone.name, power_limit); + + /* + * Only leaves of the dtpm tree has ops to get/set the power + */ + if (dtpm->ops) { + dtpm->power_limit = dtpm->ops->set_power_uw(dtpm, power_limit); + } else { + dtpm->power_limit = 0; + + list_for_each_entry(child, &dtpm->children, sibling) { + + /* + * Integer division rounding will inevitably + * lead to a different min or max value when + * set several times. In order to restore the + * initial value, we force the child's min or + * max power every time if the constraint is + * at the boundaries. + */ + if (power_limit == dtpm->power_max) { + power = child->power_max; + } else if (power_limit == dtpm->power_min) { + power = child->power_min; + } else { + power = DIV_ROUND_CLOSEST_ULL( + power_limit * child->weight, 1024); + } + + pr_debug("Setting power limit for '%s': %llu uW\n", + child->zone.name, power); + + ret = __set_power_limit_uw(child, cid, power); + if (!ret) + ret = __get_power_limit_uw(child, cid, &power); + + if (ret) + break; + + dtpm->power_limit += power; + } + } + + return ret; +} + +static int set_power_limit_uw(struct powercap_zone *pcz, + int cid, u64 power_limit) +{ + struct dtpm *dtpm = to_dtpm(pcz); + int ret; + + mutex_lock(&dtpm_lock); + + /* + * Don't allow values outside of the power range previously + * set when initializing the power numbers. + */ + power_limit = clamp_val(power_limit, dtpm->power_min, dtpm->power_max); + + ret = __set_power_limit_uw(dtpm, cid, power_limit); + + pr_debug("%s: power limit: %llu uW, power max: %llu uW\n", + dtpm->zone.name, dtpm->power_limit, dtpm->power_max); + + mutex_unlock(&dtpm_lock); + + return ret; +} + +static const char *get_constraint_name(struct powercap_zone *pcz, int cid) +{ + return constraint_name[cid]; +} + +static int get_max_power_uw(struct powercap_zone *pcz, int id, u64 *max_power) +{ + struct dtpm *dtpm = to_dtpm(pcz); + + mutex_lock(&dtpm_lock); + *max_power = dtpm->power_max; + mutex_unlock(&dtpm_lock); + + return 0; +} + +static struct powercap_zone_constraint_ops constraint_ops = { + .set_power_limit_uw = set_power_limit_uw, + .get_power_limit_uw = get_power_limit_uw, + .set_time_window_us = set_time_window_us, + .get_time_window_us = get_time_window_us, + .get_max_power_uw = get_max_power_uw, + .get_name = get_constraint_name, +}; + +static struct powercap_zone_ops zone_ops = { + .get_max_power_range_uw = get_max_power_range_uw, + .get_power_uw = get_power_uw, + .release = dtpm_release_zone, +}; + +/** + * dtpm_alloc - Allocate and initialize a dtpm struct + * @name: a string specifying the name of the node + * + * Return: a struct dtpm pointer, NULL in case of error + */ +struct dtpm *dtpm_alloc(struct dtpm_ops *ops) +{ + struct dtpm *dtpm; + + dtpm = kzalloc(sizeof(*dtpm), GFP_KERNEL); + if (dtpm) { + INIT_LIST_HEAD(&dtpm->children); + INIT_LIST_HEAD(&dtpm->sibling); + dtpm->weight = 1024; + dtpm->ops = ops; + } + + return dtpm; +} + +/** + * dtpm_unregister - Unregister a dtpm node from the hierarchy tree + * @dtpm: a pointer to a dtpm structure corresponding to the node to be removed + * + * Call the underlying powercap unregister function. That will call + * the release callback of the powercap zone. + */ +void dtpm_unregister(struct dtpm *dtpm) +{ + powercap_unregister_zone(pct, &dtpm->zone); + + pr_info("Unregistered dtpm node '%s'\n", dtpm->zone.name); +} + +/** + * dtpm_register - Register a dtpm node in the hierarchy tree + * @name: a string specifying the name of the node + * @dtpm: a pointer to a dtpm structure corresponding to the new node + * @parent: a pointer to a dtpm structure corresponding to the parent node + * + * Create a dtpm node in the tree. If no parent is specified, the node + * is the root node of the hierarchy. If the root node already exists, + * then the registration will fail. The powercap controller must be + * initialized before calling this function. + * + * The dtpm structure must be initialized with the power numbers + * before calling this function. + * + * Return: zero on success, a negative value in case of error: + * -EAGAIN: the function is called before the framework is initialized. + * -EBUSY: the root node is already inserted + * -EINVAL: * there is no root node yet and @parent is specified + * * no all ops are defined + * * parent have ops which are reserved for leaves + * Other negative values are reported back from the powercap framework + */ +int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent) +{ + struct powercap_zone *pcz; + + if (!pct) + return -EAGAIN; + + if (root && !parent) + return -EBUSY; + + if (!root && parent) + return -EINVAL; + + if (parent && parent->ops) + return -EINVAL; + + if (!dtpm) + return -EINVAL; + + if (dtpm->ops && !(dtpm->ops->set_power_uw && + dtpm->ops->get_power_uw && + dtpm->ops->release)) + return -EINVAL; + + pcz = powercap_register_zone(&dtpm->zone, pct, name, + parent ? &parent->zone : NULL, + &zone_ops, MAX_DTPM_CONSTRAINTS, + &constraint_ops); + if (IS_ERR(pcz)) + return PTR_ERR(pcz); + + mutex_lock(&dtpm_lock); + + if (parent) { + list_add_tail(&dtpm->sibling, &parent->children); + dtpm->parent = parent; + } else { + root = dtpm; + } + + __dtpm_add_power(dtpm); + + pr_info("Registered dtpm node '%s' / %llu-%llu uW, \n", + dtpm->zone.name, dtpm->power_min, dtpm->power_max); + + mutex_unlock(&dtpm_lock); + + return 0; +} + +static int __init dtpm_init(void) +{ + struct dtpm_descr **dtpm_descr; + + pct = powercap_register_control_type(NULL, "dtpm", NULL); + if (IS_ERR(pct)) { + pr_err("Failed to register control type\n"); + return PTR_ERR(pct); + } + + for_each_dtpm_table(dtpm_descr) + (*dtpm_descr)->init(*dtpm_descr); + + return 0; +} +late_initcall(dtpm_init); diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c new file mode 100644 index 000000000000..51c366938acd --- /dev/null +++ b/drivers/powercap/dtpm_cpu.c @@ -0,0 +1,257 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2020 Linaro Limited + * + * Author: Daniel Lezcano + * + * The DTPM CPU is based on the energy model. It hooks the CPU in the + * DTPM tree which in turns update the power number by propagating the + * power number from the CPU energy model information to the parents. + * + * The association between the power and the performance state, allows + * to set the power of the CPU at the OPP granularity. + * + * The CPU hotplug is supported and the power numbers will be updated + * if a CPU is hot plugged / unplugged. + */ +#include +#include +#include +#include +#include +#include +#include +#include + +static struct dtpm *__parent; + +static DEFINE_PER_CPU(struct dtpm *, dtpm_per_cpu); + +struct dtpm_cpu { + struct freq_qos_request qos_req; + int cpu; +}; + +/* + * When a new CPU is inserted at hotplug or boot time, add the power + * contribution and update the dtpm tree. + */ +static int power_add(struct dtpm *dtpm, struct em_perf_domain *em) +{ + u64 power_min, power_max; + + power_min = em->table[0].power; + power_min *= MICROWATT_PER_MILLIWATT; + power_min += dtpm->power_min; + + power_max = em->table[em->nr_perf_states - 1].power; + power_max *= MICROWATT_PER_MILLIWATT; + power_max += dtpm->power_max; + + return dtpm_update_power(dtpm, power_min, power_max); +} + +/* + * When a CPU is unplugged, remove its power contribution from the + * dtpm tree. + */ +static int power_sub(struct dtpm *dtpm, struct em_perf_domain *em) +{ + u64 power_min, power_max; + + power_min = em->table[0].power; + power_min *= MICROWATT_PER_MILLIWATT; + power_min = dtpm->power_min - power_min; + + power_max = em->table[em->nr_perf_states - 1].power; + power_max *= MICROWATT_PER_MILLIWATT; + power_max = dtpm->power_max - power_max; + + return dtpm_update_power(dtpm, power_min, power_max); +} + +static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit) +{ + struct dtpm_cpu *dtpm_cpu = dtpm->private; + struct em_perf_domain *pd; + struct cpumask cpus; + unsigned long freq; + u64 power; + int i, nr_cpus; + + pd = em_cpu_get(dtpm_cpu->cpu); + + cpumask_and(&cpus, cpu_online_mask, to_cpumask(pd->cpus)); + + nr_cpus = cpumask_weight(&cpus); + + for (i = 0; i < pd->nr_perf_states; i++) { + + power = pd->table[i].power * MICROWATT_PER_MILLIWATT * nr_cpus; + + if (power > power_limit) + break; + } + + freq = pd->table[i - 1].frequency; + + freq_qos_update_request(&dtpm_cpu->qos_req, freq); + + power_limit = pd->table[i - 1].power * + MICROWATT_PER_MILLIWATT * nr_cpus; + + return power_limit; +} + +static u64 get_pd_power_uw(struct dtpm *dtpm) +{ + struct dtpm_cpu *dtpm_cpu = dtpm->private; + struct em_perf_domain *pd; + struct cpumask cpus; + unsigned long freq; + int i, nr_cpus; + + pd = em_cpu_get(dtpm_cpu->cpu); + freq = cpufreq_quick_get(dtpm_cpu->cpu); + cpumask_and(&cpus, cpu_online_mask, to_cpumask(pd->cpus)); + nr_cpus = cpumask_weight(&cpus); + + for (i = 0; i < pd->nr_perf_states; i++) { + + if (pd->table[i].frequency < freq) + continue; + + return pd->table[i].power * + MICROWATT_PER_MILLIWATT * nr_cpus; + } + + return 0; +} + +static void pd_release(struct dtpm *dtpm) +{ + struct dtpm_cpu *dtpm_cpu = dtpm->private; + + if (freq_qos_request_active(&dtpm_cpu->qos_req)) + freq_qos_remove_request(&dtpm_cpu->qos_req); + + kfree(dtpm_cpu); +} + +static struct dtpm_ops dtpm_ops = { + .set_power_uw = set_pd_power_limit, + .get_power_uw = get_pd_power_uw, + .release = pd_release, +}; + +static int cpuhp_dtpm_cpu_offline(unsigned int cpu) +{ + struct cpufreq_policy *policy; + struct em_perf_domain *pd; + struct dtpm *dtpm; + + policy = cpufreq_cpu_get(cpu); + + if (!policy) + return 0; + + pd = em_cpu_get(cpu); + if (!pd) + return -EINVAL; + + dtpm = per_cpu(dtpm_per_cpu, cpu); + + power_sub(dtpm, pd); + + if (cpumask_weight(policy->cpus) != 1) + return 0; + + for_each_cpu(cpu, policy->related_cpus) + per_cpu(dtpm_per_cpu, cpu) = NULL; + + dtpm_unregister(dtpm); + + return 0; +} + +static int cpuhp_dtpm_cpu_online(unsigned int cpu) +{ + struct dtpm *dtpm; + struct dtpm_cpu *dtpm_cpu; + struct cpufreq_policy *policy; + struct em_perf_domain *pd; + char name[CPUFREQ_NAME_LEN]; + int ret = -ENOMEM; + + policy = cpufreq_cpu_get(cpu); + + if (!policy) + return 0; + + pd = em_cpu_get(cpu); + if (!pd) + return -EINVAL; + + dtpm = per_cpu(dtpm_per_cpu, cpu); + if (dtpm) + return power_add(dtpm, pd); + + dtpm = dtpm_alloc(&dtpm_ops); + if (!dtpm) + return -EINVAL; + + dtpm_cpu = kzalloc(sizeof(*dtpm_cpu), GFP_KERNEL); + if (!dtpm_cpu) + goto out_kfree_dtpm; + + dtpm->private = dtpm_cpu; + dtpm_cpu->cpu = cpu; + + for_each_cpu(cpu, policy->related_cpus) + per_cpu(dtpm_per_cpu, cpu) = dtpm; + + sprintf(name, "cpu%d", dtpm_cpu->cpu); + + ret = dtpm_register(name, dtpm, __parent); + if (ret) + goto out_kfree_dtpm_cpu; + + ret = power_add(dtpm, pd); + if (ret) + goto out_dtpm_unregister; + + ret = freq_qos_add_request(&policy->constraints, + &dtpm_cpu->qos_req, FREQ_QOS_MAX, + pd->table[pd->nr_perf_states - 1].frequency); + if (ret) + goto out_power_sub; + + return 0; + +out_power_sub: + power_sub(dtpm, pd); + +out_dtpm_unregister: + dtpm_unregister(dtpm); + dtpm_cpu = NULL; + dtpm = NULL; + +out_kfree_dtpm_cpu: + for_each_cpu(cpu, policy->related_cpus) + per_cpu(dtpm_per_cpu, cpu) = NULL; + kfree(dtpm_cpu); + +out_kfree_dtpm: + kfree(dtpm); + return ret; +} + +int dtpm_register_cpu(struct dtpm *parent) +{ + __parent = parent; + + return cpuhp_setup_state(CPUHP_AP_DTPM_CPU_ONLINE, + "dtpm_cpu:online", + cpuhp_dtpm_cpu_online, + cpuhp_dtpm_cpu_offline); +} diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index c9e57237d778..fdda2a737186 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -547,7 +547,7 @@ static void rapl_init_domains(struct rapl_package *rp) if (i == RAPL_DOMAIN_PLATFORM && rp->id > 0) { snprintf(rd->name, RAPL_DOMAIN_NAME_LENGTH, "psys-%d", - cpu_data(rp->lead_cpu).phys_proc_id); + topology_physical_package_id(rp->lead_cpu)); } else snprintf(rd->name, RAPL_DOMAIN_NAME_LENGTH, "%s", rapl_domain_names[i]); @@ -1049,6 +1049,7 @@ static const struct x86_cpu_id rapl_ids[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &rapl_defaults_core), X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &rapl_defaults_core), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &rapl_defaults_core), + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &rapl_defaults_core), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &rapl_defaults_spr_server), X86_MATCH_INTEL_FAM6_MODEL(LAKEFIELD, &rapl_defaults_core), @@ -1309,7 +1310,6 @@ struct rapl_package *rapl_add_package(int cpu, struct rapl_if_priv *priv) { int id = topology_logical_die_id(cpu); struct rapl_package *rp; - struct cpuinfo_x86 *c = &cpu_data(cpu); int ret; if (!rapl_defaults) @@ -1326,10 +1326,11 @@ struct rapl_package *rapl_add_package(int cpu, struct rapl_if_priv *priv) if (topology_max_die_per_package() > 1) snprintf(rp->name, PACKAGE_DOMAIN_NAME_LENGTH, - "package-%d-die-%d", c->phys_proc_id, c->cpu_die_id); + "package-%d-die-%d", + topology_physical_package_id(cpu), topology_die_id(cpu)); else snprintf(rp->name, PACKAGE_DOMAIN_NAME_LENGTH, "package-%d", - c->phys_proc_id); + topology_physical_package_id(cpu)); /* check if the package contains valid domains */ if (rapl_detect_domains(rp, cpu) || rapl_defaults->check_unit(rp, cpu)) { diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 24dad17595dc..22e0203cbc00 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -2211,7 +2211,7 @@ static acpi_status acpi_register_spi_device(struct spi_controller *ctlr, return AE_OK; if (!lookup.max_speed_hz && - !ACPI_FAILURE(acpi_get_parent(adev->handle, &parent_handle)) && + ACPI_SUCCESS(acpi_get_parent(adev->handle, &parent_handle)) && ACPI_HANDLE(ctlr->dev.parent) == parent_handle) { /* Apple does not use _CRS but nested devices for SPI slaves */ acpi_spi_parse_apple_properties(adev, &lookup); diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index 647439c2c05a..c6f1c8c1934e 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -29,7 +29,7 @@ config BINFMT_ELF latest version). config COMPAT_BINFMT_ELF - bool + def_bool y depends on COMPAT && BINFMT_ELF select ELFCORE diff --git a/fs/affs/namei.c b/fs/affs/namei.c index 41c5749f4db7..5400a876d73f 100644 --- a/fs/affs/namei.c +++ b/fs/affs/namei.c @@ -460,8 +460,10 @@ affs_xrename(struct inode *old_dir, struct dentry *old_dentry, return -EIO; bh_new = affs_bread(sb, d_inode(new_dentry)->i_ino); - if (!bh_new) + if (!bh_new) { + affs_brelse(bh_old); return -EIO; + } /* Remove old header from its parent directory. */ affs_lock_dir(old_dir); diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 950bc177238a..4c1550b13899 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1495,7 +1495,7 @@ static void fill_note(struct memelfnote *note, const char *name, int type, * fill up all the fields in prstatus from the given task struct, except * registers which need to be filled up separately. */ -static void fill_prstatus(struct elf_prstatus *prstatus, +static void fill_prstatus(struct elf_prstatus_common *prstatus, struct task_struct *p, long signr) { prstatus->pr_info.si_signo = prstatus->pr_cursig = signr; @@ -1717,11 +1717,11 @@ static void do_thread_regset_writeback(struct task_struct *task, } #ifndef PRSTATUS_SIZE -#define PRSTATUS_SIZE(S, R) sizeof(S) +#define PRSTATUS_SIZE sizeof(struct elf_prstatus) #endif #ifndef SET_PR_FPVALID -#define SET_PR_FPVALID(S, V, R) ((S)->pr_fpvalid = (V)) +#define SET_PR_FPVALID(S) ((S)->pr_fpvalid = 1) #endif static int fill_thread_core_info(struct elf_thread_core_info *t, @@ -1729,7 +1729,6 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, long signr, size_t *total) { unsigned int i; - int regset0_size; /* * NT_PRSTATUS is the one special case, because the regset data @@ -1737,14 +1736,12 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, * than being the whole note contents. We fill the reset in here. * We assume that regset 0 is NT_PRSTATUS. */ - fill_prstatus(&t->prstatus, t->task, signr); - regset0_size = regset_get(t->task, &view->regsets[0], + fill_prstatus(&t->prstatus.common, t->task, signr); + regset_get(t->task, &view->regsets[0], sizeof(t->prstatus.pr_reg), &t->prstatus.pr_reg); - if (regset0_size < 0) - return 0; fill_note(&t->notes[0], "CORE", NT_PRSTATUS, - PRSTATUS_SIZE(t->prstatus, regset0_size), &t->prstatus); + PRSTATUS_SIZE, &t->prstatus); *total += notesize(&t->notes[0]); do_thread_regset_writeback(t->task, &view->regsets[0]); @@ -1772,7 +1769,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, continue; if (is_fpreg) - SET_PR_FPVALID(&t->prstatus, 1, regset0_size); + SET_PR_FPVALID(&t->prstatus); fill_note(&t->notes[i], is_fpreg ? "CORE" : "LINUX", note_type, ret, data); @@ -1961,7 +1958,7 @@ static int elf_dump_thread_status(long signr, struct elf_thread_status *t) struct task_struct *p = t->thread; t->num_notes = 0; - fill_prstatus(&t->prstatus, p, signr); + fill_prstatus(&t->prstatus.common, p, signr); elf_core_copy_task_regs(p, &t->prstatus.pr_reg); fill_note(&t->notes[0], "CORE", NT_PRSTATUS, sizeof(t->prstatus), @@ -2040,7 +2037,7 @@ static int fill_note_info(struct elfhdr *elf, int phdrs, } /* now collect the dump for the current */ memset(info->prstatus, 0, sizeof(*info->prstatus)); - fill_prstatus(info->prstatus, current, siginfo->si_signo); + fill_prstatus(&info->prstatus->common, current, siginfo->si_signo); elf_core_copy_regs(&info->prstatus->pr_reg, regs); /* Set up header */ diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index be4062b8ba75..03d81a14bcbf 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1191,18 +1191,7 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params, struct elf_prstatus_fdpic { - struct elf_siginfo pr_info; /* Info associated with signal */ - short pr_cursig; /* Current signal */ - unsigned long pr_sigpend; /* Set of pending signals */ - unsigned long pr_sighold; /* Set of held signals */ - pid_t pr_pid; - pid_t pr_ppid; - pid_t pr_pgrp; - pid_t pr_sid; - struct __kernel_old_timeval pr_utime; /* User time */ - struct __kernel_old_timeval pr_stime; /* System time */ - struct __kernel_old_timeval pr_cutime; /* Cumulative user time */ - struct __kernel_old_timeval pr_cstime; /* Cumulative system time */ + struct elf_prstatus_common common; elf_gregset_t pr_reg; /* GP registers */ /* When using FDPIC, the loadmap addresses need to be communicated * to GDB in order for GDB to do the necessary relocations. The @@ -1301,7 +1290,7 @@ static inline void fill_note(struct memelfnote *note, const char *name, int type * fill up all the fields in prstatus from the given task struct, except * registers which need to be filled up separately. */ -static void fill_prstatus(struct elf_prstatus_fdpic *prstatus, +static void fill_prstatus(struct elf_prstatus_common *prstatus, struct task_struct *p, long signr) { prstatus->pr_info.si_signo = prstatus->pr_cursig = signr; @@ -1332,9 +1321,6 @@ static void fill_prstatus(struct elf_prstatus_fdpic *prstatus, } prstatus->pr_cutime = ns_to_kernel_old_timeval(p->signal->cutime); prstatus->pr_cstime = ns_to_kernel_old_timeval(p->signal->cstime); - - prstatus->pr_exec_fdpic_loadmap = p->mm->context.exec_fdpic_loadmap; - prstatus->pr_interp_fdpic_loadmap = p->mm->context.interp_fdpic_loadmap; } static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p, @@ -1405,7 +1391,9 @@ static struct elf_thread_status *elf_dump_thread_status(long signr, struct task_ if (!t) return t; - fill_prstatus(&t->prstatus, p, signr); + fill_prstatus(&t->prstatus.common, p, signr); + t->prstatus.pr_exec_fdpic_loadmap = p->mm->context.exec_fdpic_loadmap; + t->prstatus.pr_interp_fdpic_loadmap = p->mm->context.interp_fdpic_loadmap; regset_get(p, &view->regsets[0], sizeof(t->prstatus.pr_reg), &t->prstatus.pr_reg); diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile index 9f1b1a88e317..b634c42115ea 100644 --- a/fs/btrfs/Makefile +++ b/fs/btrfs/Makefile @@ -1,5 +1,21 @@ # SPDX-License-Identifier: GPL-2.0 +# Subset of W=1 warnings +subdir-ccflags-y += -Wextra -Wunused -Wno-unused-parameter +subdir-ccflags-y += -Wmissing-declarations +subdir-ccflags-y += -Wmissing-format-attribute +subdir-ccflags-y += -Wmissing-prototypes +subdir-ccflags-y += -Wold-style-definition +subdir-ccflags-y += -Wmissing-include-dirs +subdir-ccflags-y += $(call cc-option, -Wunused-but-set-variable) +subdir-ccflags-y += $(call cc-option, -Wunused-const-variable) +subdir-ccflags-y += $(call cc-option, -Wpacked-not-aligned) +subdir-ccflags-y += $(call cc-option, -Wstringop-truncation) +# The following turn off the warnings enabled by -Wextra +subdir-ccflags-y += -Wno-missing-field-initializers +subdir-ccflags-y += -Wno-sign-compare +subdir-ccflags-y += -Wno-type-limits + obj-$(CONFIG_BTRFS_FS) := btrfs.o btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \ @@ -11,7 +27,8 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \ compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \ reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \ uuid-tree.o props.o free-space-tree.o tree-checker.o space-info.o \ - block-rsv.o delalloc-space.o block-group.o discard.o reflink.o + block-rsv.o delalloc-space.o block-group.o discard.o reflink.o \ + subpage.o btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 9cadacf3ec27..f47c1528eb9a 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1501,7 +1501,13 @@ int btrfs_find_all_roots(struct btrfs_trans_handle *trans, } /** - * btrfs_check_shared - tell us whether an extent is shared + * Check if an extent is shared or not + * + * @root: root inode belongs to + * @inum: inode number of the inode whose extent we are checking + * @bytenr: logical bytenr of the extent we are checking + * @roots: list of roots this extent is shared among + * @tmp: temporary list used for iteration * * btrfs_check_shared uses the backref walking code but will short * circuit as soon as it finds a root or inode that doesn't match the @@ -2541,13 +2547,6 @@ void btrfs_backref_cleanup_node(struct btrfs_backref_cache *cache, list_del(&edge->list[UPPER]); btrfs_backref_free_edge(cache, edge); - if (RB_EMPTY_NODE(&upper->rb_node)) { - BUG_ON(!list_empty(&node->upper)); - btrfs_backref_drop_node(cache, node); - node = upper; - node->lowest = 1; - continue; - } /* * Add the node to leaf node list if no other child block * cached. @@ -2624,7 +2623,7 @@ static int handle_direct_tree_backref(struct btrfs_backref_cache *cache, /* Only reloc backref cache cares about a specific root */ if (cache->is_reloc) { root = find_reloc_root(cache->fs_info, cur->bytenr); - if (WARN_ON(!root)) + if (!root) return -ENOENT; cur->root = root; } else { diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h index ff705cc564a9..17abde7f794c 100644 --- a/fs/btrfs/backref.h +++ b/fs/btrfs/backref.h @@ -296,6 +296,9 @@ static inline void btrfs_backref_free_node(struct btrfs_backref_cache *cache, struct btrfs_backref_node *node) { if (node) { + ASSERT(list_empty(&node->list)); + ASSERT(list_empty(&node->lower)); + ASSERT(node->eb == NULL); cache->nr_nodes--; btrfs_put_root(node->root); kfree(node); @@ -340,11 +343,11 @@ static inline void btrfs_backref_drop_node_buffer( static inline void btrfs_backref_drop_node(struct btrfs_backref_cache *tree, struct btrfs_backref_node *node) { - BUG_ON(!list_empty(&node->upper)); + ASSERT(list_empty(&node->upper)); btrfs_backref_drop_node_buffer(node); - list_del(&node->list); - list_del(&node->lower); + list_del_init(&node->list); + list_del_init(&node->lower); if (!RB_EMPTY_NODE(&node->rb_node)) rb_erase(&node->rb_node, &tree->rb_root); btrfs_backref_free_node(tree, node); diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 48ebc106a606..5064be59dac5 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -15,6 +15,7 @@ #include "delalloc-space.h" #include "discard.h" #include "raid56.h" +#include "zoned.h" /* * Return target flags in extended format or 0 if restripe for this chunk_type @@ -724,6 +725,10 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only struct btrfs_caching_control *caching_ctl = NULL; int ret = 0; + /* Allocator for zoned filesystems does not use the cache at all */ + if (btrfs_is_zoned(fs_info)) + return 0; + caching_ctl = kzalloc(sizeof(*caching_ctl), GFP_NOFS); if (!caching_ctl) return -ENOMEM; @@ -896,6 +901,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, btrfs_return_cluster_to_free_space(block_group, cluster); spin_unlock(&cluster->refill_lock); + btrfs_clear_treelog_bg(block_group); + path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; @@ -1008,12 +1015,17 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, WARN_ON(block_group->space_info->total_bytes < block_group->length); WARN_ON(block_group->space_info->bytes_readonly - < block_group->length); + < block_group->length - block_group->zone_unusable); + WARN_ON(block_group->space_info->bytes_zone_unusable + < block_group->zone_unusable); WARN_ON(block_group->space_info->disk_total < block_group->length * factor); } block_group->space_info->total_bytes -= block_group->length; - block_group->space_info->bytes_readonly -= block_group->length; + block_group->space_info->bytes_readonly -= + (block_group->length - block_group->zone_unusable); + block_group->space_info->bytes_zone_unusable -= + block_group->zone_unusable; block_group->space_info->disk_total -= block_group->length * factor; spin_unlock(&block_group->space_info->lock); @@ -1157,7 +1169,7 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force) } num_bytes = cache->length - cache->reserved - cache->pinned - - cache->bytes_super - cache->used; + cache->bytes_super - cache->zone_unusable - cache->used; /* * Data never overcommits, even in mixed mode, so do just the straight @@ -1188,6 +1200,12 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force) if (!ret) { sinfo->bytes_readonly += num_bytes; + if (btrfs_is_zoned(cache->fs_info)) { + /* Migrate zone_unusable bytes to readonly */ + sinfo->bytes_readonly += cache->zone_unusable; + sinfo->bytes_zone_unusable -= cache->zone_unusable; + cache->zone_unusable = 0; + } cache->ro++; list_add_tail(&cache->ro_list, &sinfo->ro_bgs); } @@ -1262,6 +1280,13 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags)) return; + /* + * Long running balances can keep us blocked here for eternity, so + * simply skip deletion if we're unable to get the mutex. + */ + if (!mutex_trylock(&fs_info->delete_unused_bgs_mutex)) + return; + spin_lock(&fs_info->unused_bgs_lock); while (!list_empty(&fs_info->unused_bgs)) { int trimming; @@ -1281,8 +1306,6 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) btrfs_discard_cancel_work(&fs_info->discard_ctl, block_group); - mutex_lock(&fs_info->delete_unused_bgs_mutex); - /* Don't want to race with allocators so take the groups_sem */ down_write(&space_info->groups_sem); @@ -1371,9 +1394,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) btrfs_space_info_update_bytes_pinned(fs_info, space_info, -block_group->pinned); space_info->bytes_readonly += block_group->pinned; - percpu_counter_add_batch(&space_info->total_bytes_pinned, - -block_group->pinned, - BTRFS_TOTAL_BYTES_PINNED_BATCH); + __btrfs_mod_total_bytes_pinned(space_info, -block_group->pinned); block_group->pinned = 0; spin_unlock(&block_group->lock); @@ -1389,8 +1410,12 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) if (!async_trim_enabled && btrfs_test_opt(fs_info, DISCARD_ASYNC)) goto flip_async; - /* DISCARD can flip during remount */ - trimming = btrfs_test_opt(fs_info, DISCARD_SYNC); + /* + * DISCARD can flip during remount. On zoned filesystems, we + * need to reset sequential-required zones. + */ + trimming = btrfs_test_opt(fs_info, DISCARD_SYNC) || + btrfs_is_zoned(fs_info); /* Implicit trim during transaction commit. */ if (trimming) @@ -1428,11 +1453,11 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) end_trans: btrfs_end_transaction(trans); next: - mutex_unlock(&fs_info->delete_unused_bgs_mutex); btrfs_put_block_group(block_group); spin_lock(&fs_info->unused_bgs_lock); } spin_unlock(&fs_info->unused_bgs_lock); + mutex_unlock(&fs_info->delete_unused_bgs_mutex); return; flip_async: @@ -1561,8 +1586,11 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags) } /** - * btrfs_rmap_block - Map a physical disk address to a list of logical addresses + * Map a physical disk address to a list of logical addresses + * + * @fs_info: the filesystem * @chunk_start: logical address of block group + * @bdev: physical device to resolve, can be NULL to indicate any device * @physical: physical address to map to logical addresses * @logical: return array of logical addresses which map to @physical * @naddrs: length of @logical @@ -1572,9 +1600,9 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags) * Used primarily to exclude those portions of a block group that contain super * block copies. */ -EXPORT_FOR_TESTS int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, - u64 physical, u64 **logical, int *naddrs, int *stripe_len) + struct block_device *bdev, u64 physical, u64 **logical, + int *naddrs, int *stripe_len) { struct extent_map *em; struct map_lookup *map; @@ -1592,6 +1620,7 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, map = em->map_lookup; data_stripe_length = em->orig_block_len; io_stripe_size = map->stripe_len; + chunk_start = em->start; /* For RAID5/6 adjust to a full IO stripe length */ if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) @@ -1606,14 +1635,18 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, for (i = 0; i < map->num_stripes; i++) { bool already_inserted = false; u64 stripe_nr; + u64 offset; int j; if (!in_range(physical, map->stripes[i].physical, data_stripe_length)) continue; + if (bdev && map->stripes[i].dev->bdev != bdev) + continue; + stripe_nr = physical - map->stripes[i].physical; - stripe_nr = div64_u64(stripe_nr, map->stripe_len); + stripe_nr = div64_u64_rem(stripe_nr, map->stripe_len, &offset); if (map->type & BTRFS_BLOCK_GROUP_RAID10) { stripe_nr = stripe_nr * map->num_stripes + i; @@ -1627,7 +1660,7 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, * instead of map->stripe_len */ - bytenr = chunk_start + stripe_nr * io_stripe_size; + bytenr = chunk_start + stripe_nr * io_stripe_size + offset; /* Ensure we don't add duplicate addresses */ for (j = 0; j < nr; j++) { @@ -1669,7 +1702,7 @@ static int exclude_super_stripes(struct btrfs_block_group *cache) for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) { bytenr = btrfs_sb_offset(i); - ret = btrfs_rmap_block(fs_info, cache->start, + ret = btrfs_rmap_block(fs_info, cache->start, NULL, bytenr, &logical, &nr, &stripe_len); if (ret) return ret; @@ -1805,24 +1838,8 @@ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info) return ret; } -static void read_block_group_item(struct btrfs_block_group *cache, - struct btrfs_path *path, - const struct btrfs_key *key) -{ - struct extent_buffer *leaf = path->nodes[0]; - struct btrfs_block_group_item bgi; - int slot = path->slots[0]; - - cache->length = key->offset; - - read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot), - sizeof(bgi)); - cache->used = btrfs_stack_block_group_used(&bgi); - cache->flags = btrfs_stack_block_group_flags(&bgi); -} - static int read_one_block_group(struct btrfs_fs_info *info, - struct btrfs_path *path, + struct btrfs_block_group_item *bgi, const struct btrfs_key *key, int need_clear) { @@ -1837,7 +1854,9 @@ static int read_one_block_group(struct btrfs_fs_info *info, if (!cache) return -ENOMEM; - read_block_group_item(cache, path, key); + cache->length = key->offset; + cache->used = btrfs_stack_block_group_used(bgi); + cache->flags = btrfs_stack_block_group_flags(bgi); set_free_space_tree_thresholds(cache); @@ -1864,6 +1883,13 @@ static int read_one_block_group(struct btrfs_fs_info *info, goto error; } + ret = btrfs_load_block_group_zone_info(cache, false); + if (ret) { + btrfs_err(info, "zoned: failed to load zone info of bg %llu", + cache->start); + goto error; + } + /* * We need to exclude the super stripes now so that the space info has * super bytes accounted for, otherwise we'll think we have more space @@ -1877,12 +1903,20 @@ static int read_one_block_group(struct btrfs_fs_info *info, } /* - * Check for two cases, either we are full, and therefore don't need - * to bother with the caching work since we won't find any space, or we - * are empty, and we can just add all the space in and be done with it. - * This saves us _a_lot_ of time, particularly in the full case. + * For zoned filesystem, space after the allocation offset is the only + * free space for a block group. So, we don't need any caching work. + * btrfs_calc_zone_unusable() will set the amount of free space and + * zone_unusable space. + * + * For regular filesystem, check for two cases, either we are full, and + * therefore don't need to bother with the caching work since we won't + * find any space, or we are empty, and we can just add all the space + * in and be done with it. This saves us _a_lot_ of time, particularly + * in the full case. */ - if (cache->length == cache->used) { + if (btrfs_is_zoned(info)) { + btrfs_calc_zone_unusable(cache); + } else if (cache->length == cache->used) { cache->last_byte_to_unpin = (u64)-1; cache->cached = BTRFS_CACHE_FINISHED; btrfs_free_excluded_extents(cache); @@ -1901,7 +1935,8 @@ static int read_one_block_group(struct btrfs_fs_info *info, } trace_btrfs_add_block_group(info, cache, 0); btrfs_update_space_info(info, cache->flags, cache->length, - cache->used, cache->bytes_super, &space_info); + cache->used, cache->bytes_super, + cache->zone_unusable, &space_info); cache->space_info = space_info; @@ -1957,7 +1992,7 @@ static int fill_dummy_bgs(struct btrfs_fs_info *fs_info) break; } btrfs_update_space_info(fs_info, bg->flags, em->len, em->len, - 0, &space_info); + 0, 0, &space_info); bg->space_info = space_info; link_block_group(bg); @@ -1996,19 +2031,29 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info) need_clear = 1; while (1) { + struct btrfs_block_group_item bgi; + struct extent_buffer *leaf; + int slot; + ret = find_first_block_group(info, path, &key); if (ret > 0) break; if (ret != 0) goto error; - btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); - ret = read_one_block_group(info, path, &key, need_clear); + leaf = path->nodes[0]; + slot = path->slots[0]; + + read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot), + sizeof(bgi)); + + btrfs_item_key_to_cpu(leaf, &key, slot); + btrfs_release_path(path); + ret = read_one_block_group(info, &bgi, &key, need_clear); if (ret < 0) goto error; key.objectid += key.offset; key.offset = 0; - btrfs_release_path(path); } btrfs_release_path(path); @@ -2140,6 +2185,13 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, cache->cached = BTRFS_CACHE_FINISHED; if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) cache->needs_free_space = 1; + + ret = btrfs_load_block_group_zone_info(cache, true); + if (ret) { + btrfs_put_block_group(cache); + return ret; + } + ret = exclude_super_stripes(cache); if (ret) { /* We may have excluded something, so call this just in case */ @@ -2181,7 +2233,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, */ trace_btrfs_add_block_group(fs_info, cache, 1); btrfs_update_space_info(fs_info, cache->flags, size, bytes_used, - cache->bytes_super, &cache->space_info); + cache->bytes_super, 0, &cache->space_info); btrfs_update_global_block_rsv(fs_info); link_block_group(cache); @@ -2289,8 +2341,15 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group *cache) spin_lock(&cache->lock); if (!--cache->ro) { num_bytes = cache->length - cache->reserved - - cache->pinned - cache->bytes_super - cache->used; + cache->pinned - cache->bytes_super - + cache->zone_unusable - cache->used; sinfo->bytes_readonly -= num_bytes; + if (btrfs_is_zoned(cache->fs_info)) { + /* Migrate zone_unusable bytes back */ + cache->zone_unusable = cache->alloc_offset - cache->used; + sinfo->bytes_zone_unusable += cache->zone_unusable; + sinfo->bytes_readonly -= cache->zone_unusable; + } list_del_init(&cache->ro_list); } spin_unlock(&cache->lock); @@ -2564,8 +2623,10 @@ again: if (!path) { path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; + if (!path) { + ret = -ENOMEM; + goto out; + } } /* @@ -2659,16 +2720,14 @@ again: btrfs_put_block_group(cache); if (drop_reserve) btrfs_delayed_refs_rsv_release(fs_info, 1); - - if (ret) - break; - /* * Avoid blocking other tasks for too long. It might even save * us from writing caches for block groups that are going to be * removed. */ mutex_unlock(&trans->transaction->cache_write_mutex); + if (ret) + goto out; mutex_lock(&trans->transaction->cache_write_mutex); } mutex_unlock(&trans->transaction->cache_write_mutex); @@ -2692,7 +2751,12 @@ again: goto again; } spin_unlock(&cur_trans->dirty_bgs_lock); - } else if (ret < 0) { + } +out: + if (ret < 0) { + spin_lock(&cur_trans->dirty_bgs_lock); + list_splice_init(&dirty, &cur_trans->dirty_bgs); + spin_unlock(&cur_trans->dirty_bgs_lock); btrfs_cleanup_dirty_bgs(cur_trans, fs_info); } @@ -2896,10 +2960,8 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans, spin_unlock(&cache->lock); spin_unlock(&cache->space_info->lock); - percpu_counter_add_batch( - &cache->space_info->total_bytes_pinned, - num_bytes, - BTRFS_TOTAL_BYTES_PINNED_BATCH); + __btrfs_mod_total_bytes_pinned(cache->space_info, + num_bytes); set_extent_dirty(&trans->transaction->pinned_extents, bytenr, bytenr + num_bytes - 1, GFP_NOFS | __GFP_NOFAIL); diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 8f74a96074f7..29678426247d 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -95,6 +95,8 @@ struct btrfs_block_group { unsigned int iref:1; unsigned int has_caching_ctl:1; unsigned int removed:1; + unsigned int to_copy:1; + unsigned int relocating_repair:1; int disk_cache_state; @@ -181,8 +183,19 @@ struct btrfs_block_group { */ int needs_free_space; + /* Flag indicating this block group is placed on a sequential zone */ + bool seq_zone; + /* Record locked full stripes for RAID5/6 block group */ struct btrfs_full_stripe_locks_tree full_stripe_locks_root; + + /* + * Allocation offset for the block group to implement sequential + * allocation. This is used only on a zoned filesystem. + */ + u64 alloc_offset; + u64 zone_unusable; + u64 meta_write_pointer; }; static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group) @@ -270,6 +283,9 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info); int btrfs_free_block_groups(struct btrfs_fs_info *info); void btrfs_wait_space_cache_v1_finished(struct btrfs_block_group *cache, struct btrfs_caching_control *caching_ctl); +int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, + struct block_device *bdev, u64 physical, u64 **logical, + int *naddrs, int *stripe_len); static inline u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info) { @@ -296,9 +312,4 @@ static inline int btrfs_block_group_done(struct btrfs_block_group *cache) void btrfs_freeze_block_group(struct btrfs_block_group *cache); void btrfs_unfreeze_block_group(struct btrfs_block_group *cache); -#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS -int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start, - u64 physical, u64 **logical, int *naddrs, int *stripe_len); -#endif - #endif /* BTRFS_BLOCK_GROUP_H */ diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index d9bf53d9ff90..28e202e89660 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -325,7 +325,8 @@ struct btrfs_dio_private { struct inode *inode; u64 logical_offset; u64 disk_bytenr; - u64 bytes; + /* Used for bio::bi_size */ + u32 bytes; /* * References to this structure. There is one reference per in-flight diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 5ae3fa0386b7..6d203acfdeb3 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -542,13 +542,19 @@ static noinline int add_ra_bio_pages(struct inode *inode, goto next; } - end = last_offset + PAGE_SIZE - 1; /* * at this point, we have a locked page in the page cache * for these bytes in the file. But, we have to make * sure they map to this compressed extent on disk. */ - set_page_extent_mapped(page); + ret = set_page_extent_mapped(page); + if (ret < 0) { + unlock_page(page); + put_page(page); + break; + } + + end = last_offset + PAGE_SIZE - 1; lock_extent(tree, last_offset, end); read_lock(&em_tree->lock); em = lookup_extent_mapping(em_tree, last_offset, diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index cc89b63d65a4..d56730a67885 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -221,9 +221,12 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, ret = btrfs_inc_ref(trans, root, cow, 1); else ret = btrfs_inc_ref(trans, root, cow, 0); - - if (ret) + if (ret) { + btrfs_tree_unlock(cow); + free_extent_buffer(cow); + btrfs_abort_transaction(trans, ret); return ret; + } btrfs_mark_buffer_dirty(cow); *cow_ret = cow; @@ -1494,6 +1497,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans, return ret; } +ALLOW_ERROR_INJECTION(btrfs_cow_block, ERRNO); /* * helper function for defrag to decide if two blocks pointed to by a @@ -2821,6 +2825,7 @@ done: btrfs_release_path(p); return ret; } +ALLOW_ERROR_INJECTION(btrfs_search_slot, ERRNO); /* * Like btrfs_search_slot, this looks for a key in the given tree. It uses the diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 4debdbdde2ab..3bc00aed13b2 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -298,7 +298,8 @@ struct btrfs_super_block { BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA | \ BTRFS_FEATURE_INCOMPAT_NO_HOLES | \ BTRFS_FEATURE_INCOMPAT_METADATA_UUID | \ - BTRFS_FEATURE_INCOMPAT_RAID1C34) + BTRFS_FEATURE_INCOMPAT_RAID1C34 | \ + BTRFS_FEATURE_INCOMPAT_ZONED) #define BTRFS_FEATURE_INCOMPAT_SAFE_SET \ (BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF) @@ -797,7 +798,7 @@ struct btrfs_fs_info { /* used to keep from writing metadata until there is a nice batch */ struct percpu_counter dirty_metadata_bytes; struct percpu_counter delalloc_bytes; - struct percpu_counter dio_bytes; + struct percpu_counter ordered_bytes; s32 dirty_metadata_batch; s32 delalloc_batch; @@ -933,6 +934,7 @@ struct btrfs_fs_info { /* Used to reclaim the metadata space in the background. */ struct work_struct async_reclaim_work; struct work_struct async_data_reclaim_work; + struct work_struct preempt_reclaim_work; spinlock_t unused_bgs_lock; struct list_head unused_bgs; @@ -974,6 +976,9 @@ struct btrfs_fs_info { /* Max size to emit ZONE_APPEND write command */ u64 max_zone_append_size; + struct mutex zoned_meta_io_lock; + spinlock_t treelog_bg_lock; + u64 treelog_bg; #ifdef CONFIG_BTRFS_FS_REF_VERIFY spinlock_t ref_verify_lock; @@ -1104,7 +1109,7 @@ struct btrfs_root { u32 type; - u64 highest_objectid; + u64 free_objectid; struct btrfs_key defrag_progress; struct btrfs_key defrag_max; @@ -2740,6 +2745,7 @@ enum btrfs_flush_state { ALLOC_CHUNK_FORCE = 8, RUN_DELAYED_IPUTS = 9, COMMIT_TRANS = 10, + FORCE_COMMIT_TRANS = 11, }; int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, @@ -3100,15 +3106,14 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, u32 min_type); int btrfs_start_delalloc_snapshot(struct btrfs_root *root); -int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr, +int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr, bool in_reclaim_context); int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end, unsigned int extra_bits, struct extent_state **cached_state); int btrfs_create_subvol_root(struct btrfs_trans_handle *trans, struct btrfs_root *new_root, - struct btrfs_root *parent_root, - u64 new_dirid); + struct btrfs_root *parent_root); void btrfs_set_delalloc_extent(struct inode *inode, struct extent_state *state, unsigned *bits); void btrfs_clear_delalloc_extent(struct inode *inode, @@ -3119,6 +3124,8 @@ void btrfs_split_delalloc_extent(struct inode *inode, struct extent_state *orig, u64 split); int btrfs_bio_fits_in_stripe(struct page *page, size_t size, struct bio *bio, unsigned long bio_flags); +bool btrfs_bio_fits_in_ordered_extent(struct page *page, struct bio *bio, + unsigned int size); void btrfs_set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end); vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf); int btrfs_readpage(struct file *file, struct page *page); diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index bacee09b7bfd..56642ca7af10 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -191,12 +191,14 @@ void btrfs_free_reserved_data_space(struct btrfs_inode *inode, } /** - * btrfs_inode_rsv_release - release any excessive reservation. - * @inode - the inode we need to release from. - * @qgroup_free - free or convert qgroup meta. - * Unlike normal operation, qgroup meta reservation needs to know if we are - * freeing qgroup reservation or just converting it into per-trans. Normally - * @qgroup_free is true for error handling, and false for normal release. + * Release any excessive reservation + * + * @inode: the inode we need to release from + * @qgroup_free: free or convert qgroup meta. Unlike normal operation, qgroup + * meta reservation needs to know if we are freeing qgroup + * reservation or just converting it into per-trans. Normally + * @qgroup_free is true for error handling, and false for normal + * release. * * This is the same as btrfs_block_rsv_release, except that it handles the * tracepoint for the reservation. @@ -361,7 +363,8 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes) } /** - * btrfs_delalloc_release_metadata - release a metadata reservation for an inode + * Release a metadata reservation for an inode + * * @inode: the inode to release the reservation for. * @num_bytes: the number of bytes we are releasing. * @qgroup_free: free qgroup reservation or convert it to per-trans reservation @@ -455,11 +458,13 @@ int btrfs_delalloc_reserve_space(struct btrfs_inode *inode, } /** - * btrfs_delalloc_release_space - release data and metadata space for delalloc - * @inode: inode we're releasing space for - * @start: start position of the space already reserved - * @len: the len of the space already reserved - * @release_bytes: the len of the space we consumed or didn't use + * Release data and metadata space for delalloc + * + * @inode: inode we're releasing space for + * @reserved: list of changed/reserved ranges + * @start: start position of the space already reserved + * @len: length of the space already reserved + * @qgroup_free: should qgroup reserved-space also be freed * * This function will release the metadata space that was not used and will * decrement ->delalloc_bytes and remove it from the fs_info delalloc_inodes diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 70c0340d839c..ec0b50b8c5d6 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1154,7 +1154,7 @@ static int __btrfs_run_delayed_items(struct btrfs_trans_handle *trans, int nr) delayed_root = fs_info->delayed_root; curr_node = btrfs_first_delayed_node(delayed_root); - while (curr_node && (!count || (count && nr--))) { + while (curr_node && (!count || nr--)) { ret = __btrfs_commit_inode_delayed_items(trans, path, curr_node); if (ret) { diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 353cc2994d10..63be7d01a9a3 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -69,9 +69,10 @@ int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans) } /** - * btrfs_delayed_refs_rsv_release - release a ref head's reservation. - * @fs_info - the fs_info for our fs. - * @nr - the number of items to drop. + * Release a ref head's reservation + * + * @fs_info: the filesystem + * @nr: number of items to drop * * This drops the delayed ref head's count from the delayed refs rsv and frees * any excess reservation we had. @@ -114,10 +115,11 @@ void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans) } /** - * btrfs_migrate_to_delayed_refs_rsv - transfer bytes to our delayed refs rsv. - * @fs_info - the fs info for our fs. - * @src - the source block rsv to transfer from. - * @num_bytes - the number of bytes to transfer. + * Transfer bytes to our delayed refs rsv + * + * @fs_info: the filesystem + * @src: source block rsv to transfer from + * @num_bytes: number of bytes to transfer * * This transfers up to the num_bytes amount from the src rsv to the * delayed_refs_rsv. Any extra bytes are returned to the space info. @@ -162,9 +164,10 @@ void btrfs_migrate_to_delayed_refs_rsv(struct btrfs_fs_info *fs_info, } /** - * btrfs_delayed_refs_rsv_refill - refill based on our delayed refs usage. - * @fs_info - the fs_info for our fs. - * @flush - control how we can flush for this reservation. + * Refill based on our delayed refs usage + * + * @fs_info: the filesystem + * @flush: control how we can flush for this reservation. * * This will refill the delayed block_rsv up to 1 items size worth of space and * will return -ENOSPC if we can't make the reservation. @@ -648,12 +651,12 @@ inserted: */ static noinline void update_existing_head_ref(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *existing, - struct btrfs_delayed_ref_head *update, - int *old_ref_mod_ret) + struct btrfs_delayed_ref_head *update) { struct btrfs_delayed_ref_root *delayed_refs = &trans->transaction->delayed_refs; struct btrfs_fs_info *fs_info = trans->fs_info; + u64 flags = btrfs_ref_head_to_space_flags(existing); int old_ref_mod; BUG_ON(existing->is_data != update->is_data); @@ -701,8 +704,6 @@ static noinline void update_existing_head_ref(struct btrfs_trans_handle *trans, * currently, for refs we just added we know we're a-ok. */ old_ref_mod = existing->total_ref_mod; - if (old_ref_mod_ret) - *old_ref_mod_ret = old_ref_mod; existing->ref_mod += update->ref_mod; existing->total_ref_mod += update->ref_mod; @@ -724,6 +725,27 @@ static noinline void update_existing_head_ref(struct btrfs_trans_handle *trans, trans->delayed_ref_updates += csum_leaves; } } + + /* + * This handles the following conditions: + * + * 1. We had a ref mod of 0 or more and went negative, indicating that + * we may be freeing space, so add our space to the + * total_bytes_pinned counter. + * 2. We were negative and went to 0 or positive, so no longer can say + * that the space would be pinned, decrement our counter from the + * total_bytes_pinned counter. + * 3. We are now at 0 and have ->must_insert_reserved set, which means + * this was a new allocation and then we dropped it, and thus must + * add our space to the total_bytes_pinned counter. + */ + if (existing->total_ref_mod < 0 && old_ref_mod >= 0) + btrfs_mod_total_bytes_pinned(fs_info, flags, existing->num_bytes); + else if (existing->total_ref_mod >= 0 && old_ref_mod < 0) + btrfs_mod_total_bytes_pinned(fs_info, flags, -existing->num_bytes); + else if (existing->total_ref_mod == 0 && existing->must_insert_reserved) + btrfs_mod_total_bytes_pinned(fs_info, flags, existing->num_bytes); + spin_unlock(&existing->lock); } @@ -798,8 +820,7 @@ static noinline struct btrfs_delayed_ref_head * add_delayed_ref_head(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *head_ref, struct btrfs_qgroup_extent_record *qrecord, - int action, int *qrecord_inserted_ret, - int *old_ref_mod, int *new_ref_mod) + int action, int *qrecord_inserted_ret) { struct btrfs_delayed_ref_head *existing; struct btrfs_delayed_ref_root *delayed_refs; @@ -821,8 +842,7 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans, existing = htree_insert(&delayed_refs->href_root, &head_ref->href_node); if (existing) { - update_existing_head_ref(trans, existing, head_ref, - old_ref_mod); + update_existing_head_ref(trans, existing, head_ref); /* * we've updated the existing ref, free the newly * allocated ref @@ -830,14 +850,17 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans, kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref); head_ref = existing; } else { - if (old_ref_mod) - *old_ref_mod = 0; + u64 flags = btrfs_ref_head_to_space_flags(head_ref); + if (head_ref->is_data && head_ref->ref_mod < 0) { delayed_refs->pending_csums += head_ref->num_bytes; trans->delayed_ref_updates += btrfs_csum_bytes_to_leaves(trans->fs_info, head_ref->num_bytes); } + if (head_ref->ref_mod < 0) + btrfs_mod_total_bytes_pinned(trans->fs_info, flags, + head_ref->num_bytes); delayed_refs->num_heads++; delayed_refs->num_heads_ready++; atomic_inc(&delayed_refs->num_entries); @@ -845,8 +868,6 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans, } if (qrecord_inserted_ret) *qrecord_inserted_ret = qrecord_inserted; - if (new_ref_mod) - *new_ref_mod = head_ref->total_ref_mod; return head_ref; } @@ -909,8 +930,7 @@ static void init_delayed_ref_common(struct btrfs_fs_info *fs_info, */ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref, - struct btrfs_delayed_extent_op *extent_op, - int *old_ref_mod, int *new_ref_mod) + struct btrfs_delayed_extent_op *extent_op) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_delayed_tree_ref *ref; @@ -977,8 +997,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, * the spin lock */ head_ref = add_delayed_ref_head(trans, head_ref, record, - action, &qrecord_inserted, - old_ref_mod, new_ref_mod); + action, &qrecord_inserted); ret = insert_delayed_ref(trans, delayed_refs, head_ref, &ref->node); spin_unlock(&delayed_refs->lock); @@ -1006,8 +1025,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, */ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref, - u64 reserved, int *old_ref_mod, - int *new_ref_mod) + u64 reserved) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_delayed_data_ref *ref; @@ -1073,8 +1091,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, * the spin lock */ head_ref = add_delayed_ref_head(trans, head_ref, record, - action, &qrecord_inserted, - old_ref_mod, new_ref_mod); + action, &qrecord_inserted); ret = insert_delayed_ref(trans, delayed_refs, head_ref, &ref->node); spin_unlock(&delayed_refs->lock); @@ -1117,7 +1134,7 @@ int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans, spin_lock(&delayed_refs->lock); add_delayed_ref_head(trans, head_ref, NULL, BTRFS_UPDATE_DELAYED_HEAD, - NULL, NULL, NULL); + NULL); spin_unlock(&delayed_refs->lock); diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index 1c977e6d45dc..e22fba272e4f 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -135,6 +135,11 @@ struct btrfs_delayed_data_ref { u64 offset; }; +enum btrfs_delayed_ref_flags { + /* Indicate that we are flushing delayed refs for the commit */ + BTRFS_DELAYED_REFS_FLUSHING, +}; + struct btrfs_delayed_ref_root { /* head ref rbtree */ struct rb_root_cached href_root; @@ -158,12 +163,7 @@ struct btrfs_delayed_ref_root { u64 pending_csums; - /* - * set when the tree is flushing before a transaction commit, - * used by the throttling code to decide if new updates need - * to be run right away - */ - int flushing; + unsigned long flags; u64 run_delayed_start; @@ -326,6 +326,16 @@ static inline void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref) } } +static inline u64 btrfs_ref_head_to_space_flags( + struct btrfs_delayed_ref_head *head_ref) +{ + if (head_ref->is_data) + return BTRFS_BLOCK_GROUP_DATA; + else if (head_ref->is_system) + return BTRFS_BLOCK_GROUP_SYSTEM; + return BTRFS_BLOCK_GROUP_METADATA; +} + static inline void btrfs_put_delayed_ref_head(struct btrfs_delayed_ref_head *head) { if (refcount_dec_and_test(&head->refs)) @@ -334,12 +344,10 @@ static inline void btrfs_put_delayed_ref_head(struct btrfs_delayed_ref_head *hea int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref, - struct btrfs_delayed_extent_op *extent_op, - int *old_ref_mod, int *new_ref_mod); + struct btrfs_delayed_extent_op *extent_op); int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref, - u64 reserved, int *old_ref_mod, - int *new_ref_mod); + u64 reserved); int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, struct btrfs_delayed_extent_op *extent_op); diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 324f646d6e5e..3a9c1e046ebe 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -22,6 +22,7 @@ #include "dev-replace.h" #include "sysfs.h" #include "zoned.h" +#include "block-group.h" /* * Device replace overview @@ -459,6 +460,185 @@ static char* btrfs_dev_name(struct btrfs_device *device) return rcu_str_deref(device->name); } +static int mark_block_group_to_copy(struct btrfs_fs_info *fs_info, + struct btrfs_device *src_dev) +{ + struct btrfs_path *path; + struct btrfs_key key; + struct btrfs_key found_key; + struct btrfs_root *root = fs_info->dev_root; + struct btrfs_dev_extent *dev_extent = NULL; + struct btrfs_block_group *cache; + struct btrfs_trans_handle *trans; + int ret = 0; + u64 chunk_offset; + + /* Do not use "to_copy" on non zoned filesystem for now */ + if (!btrfs_is_zoned(fs_info)) + return 0; + + mutex_lock(&fs_info->chunk_mutex); + + /* Ensure we don't have pending new block group */ + spin_lock(&fs_info->trans_lock); + while (fs_info->running_transaction && + !list_empty(&fs_info->running_transaction->dev_update_list)) { + spin_unlock(&fs_info->trans_lock); + mutex_unlock(&fs_info->chunk_mutex); + trans = btrfs_attach_transaction(root); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + mutex_lock(&fs_info->chunk_mutex); + if (ret == -ENOENT) { + spin_lock(&fs_info->trans_lock); + continue; + } else { + goto unlock; + } + } + + ret = btrfs_commit_transaction(trans); + mutex_lock(&fs_info->chunk_mutex); + if (ret) + goto unlock; + + spin_lock(&fs_info->trans_lock); + } + spin_unlock(&fs_info->trans_lock); + + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto unlock; + } + + path->reada = READA_FORWARD; + path->search_commit_root = 1; + path->skip_locking = 1; + + key.objectid = src_dev->devid; + key.type = BTRFS_DEV_EXTENT_KEY; + key.offset = 0; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) + goto free_path; + if (ret > 0) { + if (path->slots[0] >= + btrfs_header_nritems(path->nodes[0])) { + ret = btrfs_next_leaf(root, path); + if (ret < 0) + goto free_path; + if (ret > 0) { + ret = 0; + goto free_path; + } + } else { + ret = 0; + } + } + + while (1) { + struct extent_buffer *leaf = path->nodes[0]; + int slot = path->slots[0]; + + btrfs_item_key_to_cpu(leaf, &found_key, slot); + + if (found_key.objectid != src_dev->devid) + break; + + if (found_key.type != BTRFS_DEV_EXTENT_KEY) + break; + + if (found_key.offset < key.offset) + break; + + dev_extent = btrfs_item_ptr(leaf, slot, struct btrfs_dev_extent); + + chunk_offset = btrfs_dev_extent_chunk_offset(leaf, dev_extent); + + cache = btrfs_lookup_block_group(fs_info, chunk_offset); + if (!cache) + goto skip; + + spin_lock(&cache->lock); + cache->to_copy = 1; + spin_unlock(&cache->lock); + + btrfs_put_block_group(cache); + +skip: + ret = btrfs_next_item(root, path); + if (ret != 0) { + if (ret > 0) + ret = 0; + break; + } + } + +free_path: + btrfs_free_path(path); +unlock: + mutex_unlock(&fs_info->chunk_mutex); + + return ret; +} + +bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev, + struct btrfs_block_group *cache, + u64 physical) +{ + struct btrfs_fs_info *fs_info = cache->fs_info; + struct extent_map *em; + struct map_lookup *map; + u64 chunk_offset = cache->start; + int num_extents, cur_extent; + int i; + + /* Do not use "to_copy" on non zoned filesystem for now */ + if (!btrfs_is_zoned(fs_info)) + return true; + + spin_lock(&cache->lock); + if (cache->removed) { + spin_unlock(&cache->lock); + return true; + } + spin_unlock(&cache->lock); + + em = btrfs_get_chunk_map(fs_info, chunk_offset, 1); + ASSERT(!IS_ERR(em)); + map = em->map_lookup; + + num_extents = cur_extent = 0; + for (i = 0; i < map->num_stripes; i++) { + /* We have more device extent to copy */ + if (srcdev != map->stripes[i].dev) + continue; + + num_extents++; + if (physical == map->stripes[i].physical) + cur_extent = i; + } + + free_extent_map(em); + + if (num_extents > 1 && cur_extent < num_extents - 1) { + /* + * Has more stripes on this device. Keep this block group + * readonly until we finish all the stripes. + */ + return false; + } + + /* Last stripe on this device */ + spin_lock(&cache->lock); + cache->to_copy = 0; + spin_unlock(&cache->lock); + + return true; +} + static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, const char *tgtdev_name, u64 srcdevid, const char *srcdev_name, int read_src) @@ -500,6 +680,10 @@ static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, if (ret) return ret; + ret = mark_block_group_to_copy(fs_info, src_device); + if (ret) + return ret; + down_write(&dev_replace->rwsem); switch (dev_replace->replace_state) { case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED: @@ -715,7 +899,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, * flush all outstanding I/O and inode extent mappings before the * copy operation is declared as being finished */ - ret = btrfs_start_delalloc_roots(fs_info, U64_MAX, false); + ret = btrfs_start_delalloc_roots(fs_info, LONG_MAX, false); if (ret) { mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); return ret; diff --git a/fs/btrfs/dev-replace.h b/fs/btrfs/dev-replace.h index 60b70dacc299..3911049a5f23 100644 --- a/fs/btrfs/dev-replace.h +++ b/fs/btrfs/dev-replace.h @@ -18,5 +18,8 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info); void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info); int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info); int __pure btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace); +bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev, + struct btrfs_block_group *cache, + u64 physical); #endif diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c index 2b8383d41144..306ff20af70f 100644 --- a/fs/btrfs/discard.c +++ b/fs/btrfs/discard.c @@ -185,10 +185,12 @@ static struct btrfs_block_group *find_next_block_group( } /** - * peek_discard_list - wrap find_next_block_group() - * @discard_ctl: discard control + * Wrap find_next_block_group() + * + * @discard_ctl: discard control * @discard_state: the discard_state of the block_group after state management * @discard_index: the discard_index of the block_group after state management + * @now: time when discard was invoked, in ns * * This wraps find_next_block_group() and sets the block_group to be in use. * discard_state's control flow is managed here. Variables related to diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 07a2b4f69b10..41b718cfea40 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -459,6 +459,12 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct bio_vec *bvec return 0; found_start = btrfs_header_bytenr(eb); + + if (test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags)) { + WARN_ON(found_start != 0); + return 0; + } + /* * Please do not consolidate these warnings into a single if. * It is useful to know what went wrong. @@ -591,6 +597,59 @@ out: return ret; } +static int validate_subpage_buffer(struct page *page, u64 start, u64 end, + int mirror) +{ + struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb); + struct extent_buffer *eb; + bool reads_done; + int ret = 0; + + /* + * We don't allow bio merge for subpage metadata read, so we should + * only get one eb for each endio hook. + */ + ASSERT(end == start + fs_info->nodesize - 1); + ASSERT(PagePrivate(page)); + + eb = find_extent_buffer(fs_info, start); + /* + * When we are reading one tree block, eb must have been inserted into + * the radix tree. If not, something is wrong. + */ + ASSERT(eb); + + reads_done = atomic_dec_and_test(&eb->io_pages); + /* Subpage read must finish in page read */ + ASSERT(reads_done); + + eb->read_mirror = mirror; + if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) { + ret = -EIO; + goto err; + } + ret = validate_extent_buffer(eb); + if (ret < 0) + goto err; + + if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) + btree_readahead_hook(eb, ret); + + set_extent_buffer_uptodate(eb); + + free_extent_buffer(eb); + return ret; +err: + /* + * end_bio_extent_readpage decrements io_pages in case of error, + * make sure it has something to decrement. + */ + atomic_inc(&eb->io_pages); + clear_extent_buffer_uptodate(eb); + free_extent_buffer(eb); + return ret; +} + int btrfs_validate_metadata_buffer(struct btrfs_io_bio *io_bio, struct page *page, u64 start, u64 end, int mirror) @@ -600,6 +659,10 @@ int btrfs_validate_metadata_buffer(struct btrfs_io_bio *io_bio, int reads_done; ASSERT(page->private); + + if (btrfs_sb(page->mapping->host->i_sb)->sectorsize < PAGE_SIZE) + return validate_subpage_buffer(page, start, end, mirror); + eb = (struct extent_buffer *)page->private; /* @@ -646,7 +709,7 @@ static void end_workqueue_bio(struct bio *bio) fs_info = end_io_wq->info; end_io_wq->status = bio->bi_status; - if (bio_op(bio) == REQ_OP_WRITE) { + if (btrfs_op(bio) == BTRFS_MAP_WRITE) { if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) wq = fs_info->endio_meta_write_workers; else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE) @@ -808,6 +871,8 @@ static blk_status_t btree_submit_bio_start(struct inode *inode, struct bio *bio, static int check_async_write(struct btrfs_fs_info *fs_info, struct btrfs_inode *bi) { + if (btrfs_is_zoned(fs_info)) + return 0; if (atomic_read(&bi->sync_writers)) return 0; if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags)) @@ -822,7 +887,7 @@ blk_status_t btrfs_submit_metadata_bio(struct inode *inode, struct bio *bio, int async = check_async_write(fs_info, BTRFS_I(inode)); blk_status_t ret; - if (bio_op(bio) != REQ_OP_WRITE) { + if (btrfs_op(bio) != BTRFS_MAP_WRITE) { /* * called for a read, do the setup so that checksum validation * can happen in the async kernel threads @@ -1016,7 +1081,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, root->orphan_cleanup_state = 0; root->last_trans = 0; - root->highest_objectid = 0; + root->free_objectid = 0; root->nr_delalloc_inodes = 0; root->nr_ordered_extents = 0; root->inode_tree = RB_ROOT; @@ -1189,7 +1254,6 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info) { struct btrfs_root *root; - struct extent_buffer *leaf; root = btrfs_alloc_root(fs_info, BTRFS_TREE_LOG_OBJECTID, GFP_NOFS); if (!root) @@ -1199,6 +1263,14 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, root->root_key.type = BTRFS_ROOT_ITEM_KEY; root->root_key.offset = BTRFS_TREE_LOG_OBJECTID; + return root; +} + +int btrfs_alloc_log_tree_node(struct btrfs_trans_handle *trans, + struct btrfs_root *root) +{ + struct extent_buffer *leaf; + /* * DON'T set SHAREABLE bit for log trees. * @@ -1211,16 +1283,15 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, leaf = btrfs_alloc_tree_block(trans, root, 0, BTRFS_TREE_LOG_OBJECTID, NULL, 0, 0, 0, BTRFS_NESTING_NORMAL); - if (IS_ERR(leaf)) { - btrfs_put_root(root); - return ERR_CAST(leaf); - } + if (IS_ERR(leaf)) + return PTR_ERR(leaf); root->node = leaf; btrfs_mark_buffer_dirty(root->node); btrfs_tree_unlock(root->node); - return root; + + return 0; } int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, @@ -1231,6 +1302,16 @@ int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, log_root = alloc_log_tree(trans, fs_info); if (IS_ERR(log_root)) return PTR_ERR(log_root); + + if (!btrfs_is_zoned(fs_info)) { + int ret = btrfs_alloc_log_tree_node(trans, log_root); + + if (ret) { + btrfs_put_root(log_root); + return ret; + } + } + WARN_ON(fs_info->log_root_tree); fs_info->log_root_tree = log_root; return 0; @@ -1242,11 +1323,18 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *log_root; struct btrfs_inode_item *inode_item; + int ret; log_root = alloc_log_tree(trans, fs_info); if (IS_ERR(log_root)) return PTR_ERR(log_root); + ret = btrfs_alloc_log_tree_node(trans, log_root); + if (ret) { + btrfs_put_root(log_root); + return ret; + } + log_root->last_trans = trans->transid; log_root->root_key.offset = root->root_key.objectid; @@ -1367,14 +1455,13 @@ static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev) } mutex_lock(&root->objectid_mutex); - ret = btrfs_find_highest_objectid(root, - &root->highest_objectid); + ret = btrfs_init_root_free_objectid(root); if (ret) { mutex_unlock(&root->objectid_mutex); goto fail; } - ASSERT(root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID); + ASSERT(root->free_objectid <= BTRFS_LAST_FREE_OBJECTID); mutex_unlock(&root->objectid_mutex); @@ -1470,7 +1557,7 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) { percpu_counter_destroy(&fs_info->dirty_metadata_bytes); percpu_counter_destroy(&fs_info->delalloc_bytes); - percpu_counter_destroy(&fs_info->dio_bytes); + percpu_counter_destroy(&fs_info->ordered_bytes); percpu_counter_destroy(&fs_info->dev_replace.bio_counter); btrfs_free_csum_hash(fs_info); btrfs_free_stripe_hash_table(fs_info); @@ -2427,13 +2514,21 @@ static int validate_super(struct btrfs_fs_info *fs_info, btrfs_err(fs_info, "invalid sectorsize %llu", sectorsize); ret = -EINVAL; } - /* Only PAGE SIZE is supported yet */ - if (sectorsize != PAGE_SIZE) { + + /* + * For 4K page size, we only support 4K sector size. + * For 64K page size, we support read-write for 64K sector size, and + * read-only for 4K sector size. + */ + if ((PAGE_SIZE == SZ_4K && sectorsize != PAGE_SIZE) || + (PAGE_SIZE == SZ_64K && (sectorsize != SZ_4K && + sectorsize != SZ_64K))) { btrfs_err(fs_info, - "sectorsize %llu not supported yet, only support %lu", + "sectorsize %llu not yet supported for page size %lu", sectorsize, PAGE_SIZE); ret = -EINVAL; } + if (!is_power_of_2(nodesize) || nodesize < sectorsize || nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) { btrfs_err(fs_info, "invalid nodesize %llu", nodesize); @@ -2646,14 +2741,13 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info) * No need to hold btrfs_root::objectid_mutex since the fs * hasn't been fully initialised and we are the only user */ - ret = btrfs_find_highest_objectid(tree_root, - &tree_root->highest_objectid); + ret = btrfs_init_root_free_objectid(tree_root); if (ret < 0) { handle_error = true; continue; } - ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID); + ASSERT(tree_root->free_objectid <= BTRFS_LAST_FREE_OBJECTID); ret = btrfs_read_roots(fs_info); if (ret < 0) { @@ -2695,11 +2789,13 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) spin_lock_init(&fs_info->super_lock); spin_lock_init(&fs_info->buffer_lock); spin_lock_init(&fs_info->unused_bgs_lock); + spin_lock_init(&fs_info->treelog_bg_lock); rwlock_init(&fs_info->tree_mod_log_lock); mutex_init(&fs_info->unused_bg_unpin_mutex); mutex_init(&fs_info->delete_unused_bgs_mutex); mutex_init(&fs_info->reloc_mutex); mutex_init(&fs_info->delalloc_root_mutex); + mutex_init(&fs_info->zoned_meta_io_lock); seqlock_init(&fs_info->profiles_lock); INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots); @@ -2804,7 +2900,7 @@ static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block sb->s_blocksize = BTRFS_BDEV_BLOCKSIZE; sb->s_blocksize_bits = blksize_bits(BTRFS_BDEV_BLOCKSIZE); - ret = percpu_counter_init(&fs_info->dio_bytes, 0, GFP_KERNEL); + ret = percpu_counter_init(&fs_info->ordered_bytes, 0, GFP_KERNEL); if (ret) return ret; @@ -3140,8 +3236,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA) btrfs_info(fs_info, "has skinny extents"); - fs_info->zoned = (features & BTRFS_FEATURE_INCOMPAT_ZONED); - /* * flag our filesystem as having big metadata blocks if * they are bigger than the page size @@ -3194,6 +3288,17 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_alloc; } + /* For 4K sector size support, it's only read-only */ + if (PAGE_SIZE == SZ_64K && sectorsize == SZ_4K) { + if (!sb_rdonly(sb) || btrfs_super_log_root(disk_super)) { + btrfs_err(fs_info, + "subpage sectorsize %u only supported read-only for page size %lu", + sectorsize, PAGE_SIZE); + err = -EINVAL; + goto fail_alloc; + } + } + ret = btrfs_init_workqueues(fs_info, fs_devices); if (ret) { err = ret; @@ -3260,6 +3365,19 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device if (ret) goto fail_tree_roots; + /* + * Get zone type information of zoned block devices. This will also + * handle emulation of a zoned filesystem if a regular device has the + * zoned incompat feature flag set. + */ + ret = btrfs_get_dev_zone_info_all_devices(fs_info); + if (ret) { + btrfs_err(fs_info, + "zoned: failed to read device zone info: %d", + ret); + goto fail_block_groups; + } + /* * If we have a uuid root and we're not being told to rescan we need to * check the generation here so we can set the @@ -4114,6 +4232,7 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) cancel_work_sync(&fs_info->async_reclaim_work); cancel_work_sync(&fs_info->async_data_reclaim_work); + cancel_work_sync(&fs_info->preempt_reclaim_work); /* Cancel or finish ongoing discard work */ btrfs_discard_cleanup(fs_info); @@ -4166,9 +4285,9 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) percpu_counter_sum(&fs_info->delalloc_bytes)); } - if (percpu_counter_sum(&fs_info->dio_bytes)) + if (percpu_counter_sum(&fs_info->ordered_bytes)) btrfs_info(fs_info, "at unmount dio bytes count %lld", - percpu_counter_sum(&fs_info->dio_bytes)); + percpu_counter_sum(&fs_info->ordered_bytes)); btrfs_sysfs_remove_mounted(fs_info); btrfs_sysfs_remove_fsid(fs_info->fs_devices); @@ -4689,6 +4808,8 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, EXTENT_DIRTY); btrfs_destroy_pinned_extent(fs_info, &cur_trans->pinned_extents); + btrfs_free_redirty_list(cur_trans); + cur_trans->state =TRANS_STATE_COMPLETED; wake_up(&cur_trans->commit_wait); } @@ -4746,7 +4867,7 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info) return 0; } -int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid) +int btrfs_init_root_free_objectid(struct btrfs_root *root) { struct btrfs_path *path; int ret; @@ -4770,10 +4891,10 @@ int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid) slot = path->slots[0] - 1; l = path->nodes[0]; btrfs_item_key_to_cpu(l, &found_key, slot); - *objectid = max_t(u64, found_key.objectid, - BTRFS_FIRST_FREE_OBJECTID - 1); + root->free_objectid = max_t(u64, found_key.objectid + 1, + BTRFS_FIRST_FREE_OBJECTID); } else { - *objectid = BTRFS_FIRST_FREE_OBJECTID - 1; + root->free_objectid = BTRFS_FIRST_FREE_OBJECTID; } ret = 0; error: @@ -4781,12 +4902,12 @@ error: return ret; } -int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid) +int btrfs_get_free_objectid(struct btrfs_root *root, u64 *objectid) { int ret; mutex_lock(&root->objectid_mutex); - if (unlikely(root->highest_objectid >= BTRFS_LAST_FREE_OBJECTID)) { + if (unlikely(root->free_objectid >= BTRFS_LAST_FREE_OBJECTID)) { btrfs_warn(root->fs_info, "the objectid of root %llu reaches its highest value", root->root_key.objectid); @@ -4794,7 +4915,7 @@ int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid) goto out; } - *objectid = ++root->highest_objectid; + *objectid = root->free_objectid++; ret = 0; out: mutex_unlock(&root->objectid_mutex); diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index e45057c0c016..0e7e9526b6a8 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -120,6 +120,8 @@ blk_status_t btrfs_wq_submit_bio(struct inode *inode, struct bio *bio, extent_submit_bio_start_t *submit_bio_start); blk_status_t btrfs_submit_bio_done(void *private_data, struct bio *bio, int mirror_num); +int btrfs_alloc_log_tree_node(struct btrfs_trans_handle *trans, + struct btrfs_root *root); int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); int btrfs_add_log_tree(struct btrfs_trans_handle *trans, @@ -133,8 +135,8 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, int btree_lock_page_hook(struct page *page, void *data, void (*flush_fn)(void *)); int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags); -int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid); -int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid); +int btrfs_get_free_objectid(struct btrfs_root *root, u64 *objectid); +int btrfs_init_root_free_objectid(struct btrfs_root *root); int __init btrfs_end_io_wq_init(void); void __cold btrfs_end_io_wq_exit(void); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 0c335dae5af7..78ad31a59e59 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -34,6 +34,8 @@ #include "block-group.h" #include "discard.h" #include "rcu-string.h" +#include "zoned.h" +#include "dev-replace.h" #undef SCRAMBLE_DELAYED_REFS @@ -82,41 +84,6 @@ void btrfs_free_excluded_extents(struct btrfs_block_group *cache) EXTENT_UPTODATE); } -static u64 generic_ref_to_space_flags(struct btrfs_ref *ref) -{ - if (ref->type == BTRFS_REF_METADATA) { - if (ref->tree_ref.root == BTRFS_CHUNK_TREE_OBJECTID) - return BTRFS_BLOCK_GROUP_SYSTEM; - else - return BTRFS_BLOCK_GROUP_METADATA; - } - return BTRFS_BLOCK_GROUP_DATA; -} - -static void add_pinned_bytes(struct btrfs_fs_info *fs_info, - struct btrfs_ref *ref) -{ - struct btrfs_space_info *space_info; - u64 flags = generic_ref_to_space_flags(ref); - - space_info = btrfs_find_space_info(fs_info, flags); - ASSERT(space_info); - percpu_counter_add_batch(&space_info->total_bytes_pinned, ref->len, - BTRFS_TOTAL_BYTES_PINNED_BATCH); -} - -static void sub_pinned_bytes(struct btrfs_fs_info *fs_info, - struct btrfs_ref *ref) -{ - struct btrfs_space_info *space_info; - u64 flags = generic_ref_to_space_flags(ref); - - space_info = btrfs_find_space_info(fs_info, flags); - ASSERT(space_info); - percpu_counter_add_batch(&space_info->total_bytes_pinned, -ref->len, - BTRFS_TOTAL_BYTES_PINNED_BATCH); -} - /* simple helper to search for an existing data extent at a given offset */ int btrfs_lookup_data_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len) { @@ -1299,6 +1266,46 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len, return ret; } +static int do_discard_extent(struct btrfs_bio_stripe *stripe, u64 *bytes) +{ + struct btrfs_device *dev = stripe->dev; + struct btrfs_fs_info *fs_info = dev->fs_info; + struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; + u64 phys = stripe->physical; + u64 len = stripe->length; + u64 discarded = 0; + int ret = 0; + + /* Zone reset on a zoned filesystem */ + if (btrfs_can_zone_reset(dev, phys, len)) { + u64 src_disc; + + ret = btrfs_reset_device_zone(dev, phys, len, &discarded); + if (ret) + goto out; + + if (!btrfs_dev_replace_is_ongoing(dev_replace) || + dev != dev_replace->srcdev) + goto out; + + src_disc = discarded; + + /* Send to replace target as well */ + ret = btrfs_reset_device_zone(dev_replace->tgtdev, phys, len, + &discarded); + discarded += src_disc; + } else if (blk_queue_discard(bdev_get_queue(stripe->dev->bdev))) { + ret = btrfs_issue_discard(dev->bdev, phys, len, &discarded); + } else { + ret = 0; + *bytes = 0; + } + +out: + *bytes = discarded; + return ret; +} + int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes, u64 *actual_bytes) { @@ -1333,20 +1340,13 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, stripe = bbio->stripes; for (i = 0; i < bbio->num_stripes; i++, stripe++) { u64 bytes; - struct request_queue *req_q; if (!stripe->dev->bdev) { ASSERT(btrfs_test_opt(fs_info, DEGRADED)); continue; } - req_q = bdev_get_queue(stripe->dev->bdev); - if (!blk_queue_discard(req_q)) - continue; - ret = btrfs_issue_discard(stripe->dev->bdev, - stripe->physical, - stripe->length, - &bytes); + ret = do_discard_extent(stripe, &bytes); if (!ret) { discarded_bytes += bytes; } else if (ret != -EOPNOTSUPP) { @@ -1388,7 +1388,6 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, struct btrfs_ref *generic_ref) { struct btrfs_fs_info *fs_info = trans->fs_info; - int old_ref_mod, new_ref_mod; int ret; ASSERT(generic_ref->type != BTRFS_REF_NOT_SET && @@ -1397,17 +1396,12 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, generic_ref->tree_ref.root == BTRFS_TREE_LOG_OBJECTID); if (generic_ref->type == BTRFS_REF_METADATA) - ret = btrfs_add_delayed_tree_ref(trans, generic_ref, - NULL, &old_ref_mod, &new_ref_mod); + ret = btrfs_add_delayed_tree_ref(trans, generic_ref, NULL); else - ret = btrfs_add_delayed_data_ref(trans, generic_ref, 0, - &old_ref_mod, &new_ref_mod); + ret = btrfs_add_delayed_data_ref(trans, generic_ref, 0); btrfs_ref_tree_mod(fs_info, generic_ref); - if (ret == 0 && old_ref_mod < 0 && new_ref_mod >= 0) - sub_pinned_bytes(fs_info, generic_ref); - return ret; } @@ -1795,34 +1789,28 @@ void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info, { int nr_items = 1; /* Dropping this ref head update. */ - if (head->total_ref_mod < 0) { - struct btrfs_space_info *space_info; - u64 flags; + /* + * We had csum deletions accounted for in our delayed refs rsv, we need + * to drop the csum leaves for this update from our delayed_refs_rsv. + */ + if (head->total_ref_mod < 0 && head->is_data) { + spin_lock(&delayed_refs->lock); + delayed_refs->pending_csums -= head->num_bytes; + spin_unlock(&delayed_refs->lock); + nr_items += btrfs_csum_bytes_to_leaves(fs_info, head->num_bytes); + } - if (head->is_data) - flags = BTRFS_BLOCK_GROUP_DATA; - else if (head->is_system) - flags = BTRFS_BLOCK_GROUP_SYSTEM; - else - flags = BTRFS_BLOCK_GROUP_METADATA; - space_info = btrfs_find_space_info(fs_info, flags); - ASSERT(space_info); - percpu_counter_add_batch(&space_info->total_bytes_pinned, - -head->num_bytes, - BTRFS_TOTAL_BYTES_PINNED_BATCH); + /* + * We were dropping refs, or had a new ref and dropped it, and thus must + * adjust down our total_bytes_pinned, the space may or may not have + * been pinned and so is accounted for properly in the pinned space by + * now. + */ + if (head->total_ref_mod < 0 || + (head->total_ref_mod == 0 && head->must_insert_reserved)) { + u64 flags = btrfs_ref_head_to_space_flags(head); - /* - * We had csum deletions accounted for in our delayed refs rsv, - * we need to drop the csum leaves for this update from our - * delayed_refs_rsv. - */ - if (head->is_data) { - spin_lock(&delayed_refs->lock); - delayed_refs->pending_csums -= head->num_bytes; - spin_unlock(&delayed_refs->lock); - nr_items += btrfs_csum_bytes_to_leaves(fs_info, - head->num_bytes); - } + btrfs_mod_total_bytes_pinned(fs_info, flags, -head->num_bytes); } btrfs_delayed_refs_rsv_release(fs_info, nr_items); @@ -2160,7 +2148,7 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, delayed_refs = &trans->transaction->delayed_refs; if (count == 0) - count = atomic_read(&delayed_refs->num_entries) * 2; + count = delayed_refs->num_heads_ready; again: #ifdef SCRAMBLE_DELAYED_REFS @@ -2572,8 +2560,7 @@ static int pin_down_extent(struct btrfs_trans_handle *trans, spin_unlock(&cache->lock); spin_unlock(&cache->space_info->lock); - percpu_counter_add_batch(&cache->space_info->total_bytes_pinned, - num_bytes, BTRFS_TOTAL_BYTES_PINNED_BATCH); + __btrfs_mod_total_bytes_pinned(cache->space_info, num_bytes); set_extent_dirty(&trans->transaction->pinned_extents, bytenr, bytenr + num_bytes - 1, GFP_NOFS | __GFP_NOFAIL); return 0; @@ -2784,11 +2771,14 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info, cache->pinned -= len; btrfs_space_info_update_bytes_pinned(fs_info, space_info, -len); space_info->max_extent_size = 0; - percpu_counter_add_batch(&space_info->total_bytes_pinned, - -len, BTRFS_TOTAL_BYTES_PINNED_BATCH); + __btrfs_mod_total_bytes_pinned(space_info, -len); if (cache->ro) { space_info->bytes_readonly += len; readonly = true; + } else if (btrfs_is_zoned(fs_info)) { + /* Need reset before reusing in a zoned block group */ + space_info->bytes_zone_unusable += len; + readonly = true; } spin_unlock(&cache->lock); if (!readonly && return_free_space && @@ -3318,7 +3308,6 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_ref generic_ref = { 0 }; - int pin = 1; int ret; btrfs_init_generic_ref(&generic_ref, BTRFS_DROP_DELAYED_REF, @@ -3327,13 +3316,9 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, root->root_key.objectid); if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { - int old_ref_mod, new_ref_mod; - btrfs_ref_tree_mod(fs_info, &generic_ref); - ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, NULL, - &old_ref_mod, &new_ref_mod); + ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, NULL); BUG_ON(ret); /* -ENOMEM */ - pin = old_ref_mod >= 0 && new_ref_mod < 0; } if (last_ref && btrfs_header_generation(buf) == trans->transid) { @@ -3341,11 +3326,12 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { ret = check_ref_cleanup(trans, buf->start); - if (!ret) + if (!ret) { + btrfs_redirty_list_add(trans->transaction, buf); goto out; + } } - pin = 0; cache = btrfs_lookup_block_group(fs_info, buf->start); if (btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN)) { @@ -3354,6 +3340,13 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, goto out; } + if (btrfs_is_zoned(fs_info)) { + btrfs_redirty_list_add(trans->transaction, buf); + pin_down_extent(trans, cache, buf->start, buf->len, 1); + btrfs_put_block_group(cache); + goto out; + } + WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)); btrfs_add_free_space(cache, buf->start, buf->len); @@ -3362,9 +3355,6 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, trace_btrfs_reserved_extent_free(fs_info, buf->start, buf->len); } out: - if (pin) - add_pinned_bytes(fs_info, &generic_ref); - if (last_ref) { /* * Deleting the buffer, clear the corrupt flag since it doesn't @@ -3378,7 +3368,6 @@ out: int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref) { struct btrfs_fs_info *fs_info = trans->fs_info; - int old_ref_mod, new_ref_mod; int ret; if (btrfs_is_testing(fs_info)) @@ -3394,14 +3383,11 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref) ref->data_ref.ref_root == BTRFS_TREE_LOG_OBJECTID)) { /* unlocks the pinned mutex */ btrfs_pin_extent(trans, ref->bytenr, ref->len, 1); - old_ref_mod = new_ref_mod = 0; ret = 0; } else if (ref->type == BTRFS_REF_METADATA) { - ret = btrfs_add_delayed_tree_ref(trans, ref, NULL, - &old_ref_mod, &new_ref_mod); + ret = btrfs_add_delayed_tree_ref(trans, ref, NULL); } else { - ret = btrfs_add_delayed_data_ref(trans, ref, 0, - &old_ref_mod, &new_ref_mod); + ret = btrfs_add_delayed_data_ref(trans, ref, 0); } if (!((ref->type == BTRFS_REF_METADATA && @@ -3410,9 +3396,6 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref) ref->data_ref.ref_root == BTRFS_TREE_LOG_OBJECTID))) btrfs_ref_tree_mod(fs_info, ref); - if (ret == 0 && old_ref_mod >= 0 && new_ref_mod < 0) - add_pinned_bytes(fs_info, ref); - return ret; } @@ -3489,6 +3472,7 @@ btrfs_release_block_group(struct btrfs_block_group *cache, enum btrfs_extent_allocation_policy { BTRFS_EXTENT_ALLOC_CLUSTERED, + BTRFS_EXTENT_ALLOC_ZONED, }; /* @@ -3513,6 +3497,9 @@ struct find_free_extent_ctl { bool have_caching_bg; bool orig_have_caching_bg; + /* Allocation is called for tree-log */ + bool for_treelog; + /* RAID index, converted from flags */ int index; @@ -3741,6 +3728,118 @@ static int do_allocation_clustered(struct btrfs_block_group *block_group, return find_free_extent_unclustered(block_group, ffe_ctl); } +/* + * Tree-log block group locking + * ============================ + * + * fs_info::treelog_bg_lock protects the fs_info::treelog_bg which + * indicates the starting address of a block group, which is reserved only + * for tree-log metadata. + * + * Lock nesting + * ============ + * + * space_info::lock + * block_group::lock + * fs_info::treelog_bg_lock + */ + +/* + * Simple allocator for sequential-only block group. It only allows sequential + * allocation. No need to play with trees. This function also reserves the + * bytes as in btrfs_add_reserved_bytes. + */ +static int do_allocation_zoned(struct btrfs_block_group *block_group, + struct find_free_extent_ctl *ffe_ctl, + struct btrfs_block_group **bg_ret) +{ + struct btrfs_fs_info *fs_info = block_group->fs_info; + struct btrfs_space_info *space_info = block_group->space_info; + struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; + u64 start = block_group->start; + u64 num_bytes = ffe_ctl->num_bytes; + u64 avail; + u64 bytenr = block_group->start; + u64 log_bytenr; + int ret = 0; + bool skip; + + ASSERT(btrfs_is_zoned(block_group->fs_info)); + + /* + * Do not allow non-tree-log blocks in the dedicated tree-log block + * group, and vice versa. + */ + spin_lock(&fs_info->treelog_bg_lock); + log_bytenr = fs_info->treelog_bg; + skip = log_bytenr && ((ffe_ctl->for_treelog && bytenr != log_bytenr) || + (!ffe_ctl->for_treelog && bytenr == log_bytenr)); + spin_unlock(&fs_info->treelog_bg_lock); + if (skip) + return 1; + + spin_lock(&space_info->lock); + spin_lock(&block_group->lock); + spin_lock(&fs_info->treelog_bg_lock); + + ASSERT(!ffe_ctl->for_treelog || + block_group->start == fs_info->treelog_bg || + fs_info->treelog_bg == 0); + + if (block_group->ro) { + ret = 1; + goto out; + } + + /* + * Do not allow currently using block group to be tree-log dedicated + * block group. + */ + if (ffe_ctl->for_treelog && !fs_info->treelog_bg && + (block_group->used || block_group->reserved)) { + ret = 1; + goto out; + } + + avail = block_group->length - block_group->alloc_offset; + if (avail < num_bytes) { + if (ffe_ctl->max_extent_size < avail) { + /* + * With sequential allocator, free space is always + * contiguous + */ + ffe_ctl->max_extent_size = avail; + ffe_ctl->total_free_space = avail; + } + ret = 1; + goto out; + } + + if (ffe_ctl->for_treelog && !fs_info->treelog_bg) + fs_info->treelog_bg = block_group->start; + + ffe_ctl->found_offset = start + block_group->alloc_offset; + block_group->alloc_offset += num_bytes; + spin_lock(&ctl->tree_lock); + ctl->free_space -= num_bytes; + spin_unlock(&ctl->tree_lock); + + /* + * We do not check if found_offset is aligned to stripesize. The + * address is anyway rewritten when using zone append writing. + */ + + ffe_ctl->search_start = ffe_ctl->found_offset; + +out: + if (ret && ffe_ctl->for_treelog) + fs_info->treelog_bg = 0; + spin_unlock(&fs_info->treelog_bg_lock); + spin_unlock(&block_group->lock); + spin_unlock(&space_info->lock); + return ret; +} + static int do_allocation(struct btrfs_block_group *block_group, struct find_free_extent_ctl *ffe_ctl, struct btrfs_block_group **bg_ret) @@ -3748,6 +3847,8 @@ static int do_allocation(struct btrfs_block_group *block_group, switch (ffe_ctl->policy) { case BTRFS_EXTENT_ALLOC_CLUSTERED: return do_allocation_clustered(block_group, ffe_ctl, bg_ret); + case BTRFS_EXTENT_ALLOC_ZONED: + return do_allocation_zoned(block_group, ffe_ctl, bg_ret); default: BUG(); } @@ -3762,6 +3863,9 @@ static void release_block_group(struct btrfs_block_group *block_group, ffe_ctl->retry_clustered = false; ffe_ctl->retry_unclustered = false; break; + case BTRFS_EXTENT_ALLOC_ZONED: + /* Nothing to do */ + break; default: BUG(); } @@ -3790,6 +3894,9 @@ static void found_extent(struct find_free_extent_ctl *ffe_ctl, case BTRFS_EXTENT_ALLOC_CLUSTERED: found_extent_clustered(ffe_ctl, ins); break; + case BTRFS_EXTENT_ALLOC_ZONED: + /* Nothing to do */ + break; default: BUG(); } @@ -3805,6 +3912,9 @@ static int chunk_allocation_failed(struct find_free_extent_ctl *ffe_ctl) */ ffe_ctl->loop = LOOP_NO_EMPTY_SIZE; return 0; + case BTRFS_EXTENT_ALLOC_ZONED: + /* Give up here */ + return -ENOSPC; default: BUG(); } @@ -3973,6 +4083,14 @@ static int prepare_allocation(struct btrfs_fs_info *fs_info, case BTRFS_EXTENT_ALLOC_CLUSTERED: return prepare_allocation_clustered(fs_info, ffe_ctl, space_info, ins); + case BTRFS_EXTENT_ALLOC_ZONED: + if (ffe_ctl->for_treelog) { + spin_lock(&fs_info->treelog_bg_lock); + if (fs_info->treelog_bg) + ffe_ctl->hint_byte = fs_info->treelog_bg; + spin_unlock(&fs_info->treelog_bg_lock); + } + return 0; default: BUG(); } @@ -4015,6 +4133,7 @@ static noinline int find_free_extent(struct btrfs_root *root, struct find_free_extent_ctl ffe_ctl = {0}; struct btrfs_space_info *space_info; bool full_search = false; + bool for_treelog = (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID); WARN_ON(num_bytes < fs_info->sectorsize); @@ -4028,6 +4147,7 @@ static noinline int find_free_extent(struct btrfs_root *root, ffe_ctl.orig_have_caching_bg = false; ffe_ctl.found_offset = 0; ffe_ctl.hint_byte = hint_byte_orig; + ffe_ctl.for_treelog = for_treelog; ffe_ctl.policy = BTRFS_EXTENT_ALLOC_CLUSTERED; /* For clustered allocation */ @@ -4036,6 +4156,9 @@ static noinline int find_free_extent(struct btrfs_root *root, ffe_ctl.last_ptr = NULL; ffe_ctl.use_cluster = true; + if (btrfs_is_zoned(fs_info)) + ffe_ctl.policy = BTRFS_EXTENT_ALLOC_ZONED; + ins->type = BTRFS_EXTENT_ITEM_KEY; ins->objectid = 0; ins->offset = 0; @@ -4099,8 +4222,11 @@ search: struct btrfs_block_group *bg_ret; /* If the block group is read-only, we can skip it entirely. */ - if (unlikely(block_group->ro)) + if (unlikely(block_group->ro)) { + if (for_treelog) + btrfs_clear_treelog_bg(block_group); continue; + } btrfs_grab_block_group(block_group, delalloc); ffe_ctl.search_start = block_group->start; @@ -4178,20 +4304,21 @@ have_block_group: /* move on to the next group */ if (ffe_ctl.search_start + num_bytes > block_group->start + block_group->length) { - btrfs_add_free_space(block_group, ffe_ctl.found_offset, - num_bytes); + btrfs_add_free_space_unused(block_group, + ffe_ctl.found_offset, num_bytes); goto loop; } if (ffe_ctl.found_offset < ffe_ctl.search_start) - btrfs_add_free_space(block_group, ffe_ctl.found_offset, - ffe_ctl.search_start - ffe_ctl.found_offset); + btrfs_add_free_space_unused(block_group, + ffe_ctl.found_offset, + ffe_ctl.search_start - ffe_ctl.found_offset); ret = btrfs_add_reserved_bytes(block_group, ram_bytes, num_bytes, delalloc); if (ret == -EAGAIN) { - btrfs_add_free_space(block_group, ffe_ctl.found_offset, - num_bytes); + btrfs_add_free_space_unused(block_group, + ffe_ctl.found_offset, num_bytes); goto loop; } btrfs_inc_block_group_reservations(block_group); @@ -4285,6 +4412,7 @@ int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, bool final_tried = num_bytes == min_alloc_size; u64 flags; int ret; + bool for_treelog = (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID); flags = get_alloc_profile_by_root(root, is_data); again: @@ -4308,8 +4436,8 @@ again: sinfo = btrfs_find_space_info(fs_info, flags); btrfs_err(fs_info, - "allocation failed flags %llu, wanted %llu", - flags, num_bytes); + "allocation failed flags %llu, wanted %llu tree-log %d", + flags, num_bytes, for_treelog); if (sinfo) btrfs_dump_space_info(fs_info, sinfo, num_bytes, 1); @@ -4491,7 +4619,6 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans, } if (node->type == BTRFS_SHARED_BLOCK_REF_KEY) { - BUG_ON(!(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)); btrfs_set_extent_inline_ref_type(leaf, iref, BTRFS_SHARED_BLOCK_REF_KEY); btrfs_set_extent_inline_ref_offset(leaf, iref, ref->parent); @@ -4528,7 +4655,6 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans, struct btrfs_key *ins) { struct btrfs_ref generic_ref = { 0 }; - int ret; BUG_ON(root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID); @@ -4536,9 +4662,8 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans, ins->objectid, ins->offset, 0); btrfs_init_data_ref(&generic_ref, root->root_key.objectid, owner, offset); btrfs_ref_tree_mod(root->fs_info, &generic_ref); - ret = btrfs_add_delayed_data_ref(trans, &generic_ref, - ram_bytes, NULL, NULL); - return ret; + + return btrfs_add_delayed_data_ref(trans, &generic_ref, ram_bytes); } /* @@ -4620,6 +4745,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, __btrfs_tree_lock(buf, nest); btrfs_clean_tree_block(buf); clear_bit(EXTENT_BUFFER_STALE, &buf->bflags); + clear_bit(EXTENT_BUFFER_NO_CHECK, &buf->bflags); set_extent_buffer_uptodate(buf); @@ -4730,8 +4856,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, generic_ref.real_root = root->root_key.objectid; btrfs_init_tree_ref(&generic_ref, level, root_objectid); btrfs_ref_tree_mod(fs_info, &generic_ref); - ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, - extent_op, NULL, NULL); + ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, extent_op); if (ret) goto out_free_delayed; } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index c9cee458e001..4dfb3ead1175 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -24,6 +24,9 @@ #include "rcu-string.h" #include "backref.h" #include "disk-io.h" +#include "subpage.h" +#include "zoned.h" +#include "block-group.h" static struct kmem_cache *extent_state_cache; static struct kmem_cache *extent_buffer_cache; @@ -389,16 +392,16 @@ do_insert: } /** - * __etree_search - searche @tree for an entry that contains @offset. Such - * entry would have entry->start <= offset && entry->end >= offset. + * Search @tree for an entry that contains @offset. Such entry would have + * entry->start <= offset && entry->end >= offset. * - * @tree - the tree to search - * @offset - offset that should fall within an entry in @tree - * @next_ret - pointer to the first entry whose range ends after @offset - * @prev - pointer to the first entry whose range begins before @offset - * @p_ret - pointer where new node should be anchored (used when inserting an - * entry in the tree) - * @parent_ret - points to entry which would have been the parent of the entry, + * @tree: the tree to search + * @offset: offset that should fall within an entry in @tree + * @next_ret: pointer to the first entry whose range ends after @offset + * @prev_ret: pointer to the first entry whose range begins before @offset + * @p_ret: pointer where new node should be anchored (used when inserting an + * entry in the tree) + * @parent_ret: points to entry which would have been the parent of the entry, * containing @offset * * This function returns a pointer to the entry that contains @offset byte @@ -1588,12 +1591,13 @@ out: } /** - * find_contiguous_extent_bit: find a contiguous area of bits - * @tree - io tree to check - * @start - offset to start the search from - * @start_ret - the first offset we found with the bits set - * @end_ret - the final contiguous range of the bits that were set - * @bits - bits to look for + * Find a contiguous area of bits + * + * @tree: io tree to check + * @start: offset to start the search from + * @start_ret: the first offset we found with the bits set + * @end_ret: the final contiguous range of the bits that were set + * @bits: bits to look for * * set_extent_bit and clear_extent_bit can temporarily split contiguous ranges * to set bits appropriately, and then merge them again. During this time it @@ -1625,14 +1629,14 @@ int find_contiguous_extent_bit(struct extent_io_tree *tree, u64 start, } /** - * find_first_clear_extent_bit - find the first range that has @bits not set. - * This range could start before @start. + * Find the first range that has @bits not set. This range could start before + * @start. * - * @tree - the tree to search - * @start - the offset at/after which the found extent should start - * @start_ret - records the beginning of the range - * @end_ret - records the end of the range (inclusive) - * @bits - the set of bits which must be unset + * @tree: the tree to search + * @start: offset at/after which the found extent should start + * @start_ret: records the beginning of the range + * @end_ret: records the end of the range (inclusive) + * @bits: the set of bits which must be unset * * Since unallocated range is also considered one which doesn't have the bits * set it's possible that @end_ret contains -1, this happens in case the range @@ -1975,10 +1979,10 @@ static int __process_pages_contig(struct address_space *mapping, pages_processed++; continue; } - if (page_ops & PAGE_CLEAR_DIRTY) + if (page_ops & PAGE_START_WRITEBACK) { clear_page_dirty_for_io(pages[i]); - if (page_ops & PAGE_SET_WRITEBACK) set_page_writeback(pages[i]); + } if (page_ops & PAGE_SET_ERROR) SetPageError(pages[i]); if (page_ops & PAGE_END_WRITEBACK) @@ -2256,6 +2260,9 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start, ASSERT(!(fs_info->sb->s_flags & SB_RDONLY)); BUG_ON(!mirror_num); + if (btrfs_is_zoned(fs_info)) + return btrfs_repair_one_zone(fs_info, logical); + bio = btrfs_io_bio_alloc(1); bio->bi_iter.bi_size = 0; map_length = length; @@ -2732,6 +2739,7 @@ static void end_bio_extent_writepage(struct bio *bio) u64 start; u64 end; struct bvec_iter_all iter_all; + bool first_bvec = true; ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, iter_all) { @@ -2758,6 +2766,11 @@ static void end_bio_extent_writepage(struct bio *bio) start = page_offset(page); end = start + bvec->bv_offset + bvec->bv_len - 1; + if (first_bvec) { + btrfs_record_physical_zoned(inode, start, bio); + first_bvec = false; + } + end_extent_writepage(page, error, start, end); end_page_writeback(page); } @@ -2775,7 +2788,7 @@ struct processed_extent { struct btrfs_inode *inode; /* Start of the range in @inode */ u64 start; - /* End of the range in in @inode */ + /* End of the range in @inode */ u64 end; bool uptodate; }; @@ -2838,15 +2851,38 @@ update: processed->uptodate = uptodate; } -static void endio_readpage_update_page_status(struct page *page, bool uptodate) +static void begin_page_read(struct btrfs_fs_info *fs_info, struct page *page) { + ASSERT(PageLocked(page)); + if (fs_info->sectorsize == PAGE_SIZE) + return; + + ASSERT(PagePrivate(page)); + btrfs_subpage_start_reader(fs_info, page, page_offset(page), PAGE_SIZE); +} + +static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len) +{ + struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb); + + ASSERT(page_offset(page) <= start && + start + len <= page_offset(page) + PAGE_SIZE); + if (uptodate) { - SetPageUptodate(page); + btrfs_page_set_uptodate(fs_info, page, start, len); } else { - ClearPageUptodate(page); - SetPageError(page); + btrfs_page_clear_uptodate(fs_info, page, start, len); + btrfs_page_set_error(fs_info, page, start, len); } - unlock_page(page); + + if (fs_info->sectorsize == PAGE_SIZE) + unlock_page(page); + else if (is_data_inode(page->mapping->host)) + /* + * For subpage data, unlock the page if we're the last reader. + * For subpage metadata, page lock is not utilized for read. + */ + btrfs_subpage_end_reader(fs_info, page, start, len); } /* @@ -2983,7 +3019,7 @@ readpage_ok: bio_offset += len; /* Update page status and unlock */ - endio_readpage_update_page_status(page, uptodate); + end_page_read(page, uptodate, start, len); endio_readpage_release_extent(&processed, BTRFS_I(inode), start, end, uptodate); } @@ -3058,14 +3094,67 @@ struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size) return bio; } +/** + * Attempt to add a page to bio + * + * @bio: destination bio + * @page: page to add to the bio + * @disk_bytenr: offset of the new bio or to check whether we are adding + * a contiguous page to the previous one + * @pg_offset: starting offset in the page + * @size: portion of page that we want to write + * @prev_bio_flags: flags of previous bio to see if we can merge the current one + * @bio_flags: flags of the current bio to see if we can merge them + * @return: true if page was added, false otherwise + * + * Attempt to add a page to bio considering stripe alignment etc. + * + * Return true if successfully page added. Otherwise, return false. + */ +static bool btrfs_bio_add_page(struct bio *bio, struct page *page, + u64 disk_bytenr, unsigned int size, + unsigned int pg_offset, + unsigned long prev_bio_flags, + unsigned long bio_flags) +{ + const sector_t sector = disk_bytenr >> SECTOR_SHIFT; + bool contig; + int ret; + + if (prev_bio_flags != bio_flags) + return false; + + if (prev_bio_flags & EXTENT_BIO_COMPRESSED) + contig = bio->bi_iter.bi_sector == sector; + else + contig = bio_end_sector(bio) == sector; + if (!contig) + return false; + + if (btrfs_bio_fits_in_stripe(page, size, bio, bio_flags)) + return false; + + if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + struct page *first_page = bio_first_bvec_all(bio)->bv_page; + + if (!btrfs_bio_fits_in_ordered_extent(first_page, bio, size)) + return false; + ret = bio_add_zone_append_page(bio, page, size, pg_offset); + } else { + ret = bio_add_page(bio, page, size, pg_offset); + } + + return ret == size; +} + /* * @opf: bio REQ_OP_* and REQ_* flags as one value * @wbc: optional writeback control for io accounting * @page: page to add to the bio + * @disk_bytenr: logical bytenr where the write will be + * @size: portion of page that we want to write to * @pg_offset: offset of the new bio or to check whether we are adding * a contiguous page to the previous one - * @size: portion of page that we want to write - * @offset: starting offset in the page * @bio_ret: must be valid pointer, newly allocated bio will be stored there * @end_io_func: end_io callback for new bio * @mirror_num: desired mirror to read/write @@ -3074,7 +3163,7 @@ struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size) */ static int submit_extent_page(unsigned int opf, struct writeback_control *wbc, - struct page *page, u64 offset, + struct page *page, u64 disk_bytenr, size_t size, unsigned long pg_offset, struct bio **bio_ret, bio_end_io_t end_io_func, @@ -3086,27 +3175,17 @@ static int submit_extent_page(unsigned int opf, int ret = 0; struct bio *bio; size_t io_size = min_t(size_t, size, PAGE_SIZE); - sector_t sector = offset >> 9; - struct extent_io_tree *tree = &BTRFS_I(page->mapping->host)->io_tree; + struct btrfs_inode *inode = BTRFS_I(page->mapping->host); + struct extent_io_tree *tree = &inode->io_tree; + struct btrfs_fs_info *fs_info = inode->root->fs_info; ASSERT(bio_ret); if (*bio_ret) { - bool contig; - bool can_merge = true; - bio = *bio_ret; - if (prev_bio_flags & EXTENT_BIO_COMPRESSED) - contig = bio->bi_iter.bi_sector == sector; - else - contig = bio_end_sector(bio) == sector; - - if (btrfs_bio_fits_in_stripe(page, io_size, bio, bio_flags)) - can_merge = false; - - if (prev_bio_flags != bio_flags || !contig || !can_merge || - force_bio_submit || - bio_add_page(bio, page, io_size, pg_offset) < io_size) { + if (force_bio_submit || + !btrfs_bio_add_page(bio, page, disk_bytenr, io_size, + pg_offset, prev_bio_flags, bio_flags)) { ret = submit_one_bio(bio, mirror_num, prev_bio_flags); if (ret < 0) { *bio_ret = NULL; @@ -3120,7 +3199,7 @@ static int submit_extent_page(unsigned int opf, } } - bio = btrfs_bio_alloc(offset); + bio = btrfs_bio_alloc(disk_bytenr); bio_add_page(bio, page, io_size, pg_offset); bio->bi_end_io = end_io_func; bio->bi_private = tree; @@ -3129,20 +3208,39 @@ static int submit_extent_page(unsigned int opf, if (wbc) { struct block_device *bdev; - bdev = BTRFS_I(page->mapping->host)->root->fs_info->fs_devices->latest_bdev; + bdev = fs_info->fs_devices->latest_bdev; bio_set_dev(bio, bdev); wbc_init_bio(wbc, bio); wbc_account_cgroup_owner(wbc, page, io_size); } + if (btrfs_is_zoned(fs_info) && bio_op(bio) == REQ_OP_ZONE_APPEND) { + struct extent_map *em; + struct map_lookup *map; + + em = btrfs_get_chunk_map(fs_info, disk_bytenr, io_size); + if (IS_ERR(em)) + return PTR_ERR(em); + + map = em->map_lookup; + /* We only support single profile for now */ + ASSERT(map->num_stripes == 1); + btrfs_io_bio(bio)->device = map->stripes[0].dev; + + free_extent_map(em); + } *bio_ret = bio; return ret; } -static void attach_extent_buffer_page(struct extent_buffer *eb, - struct page *page) +static int attach_extent_buffer_page(struct extent_buffer *eb, + struct page *page, + struct btrfs_subpage *prealloc) { + struct btrfs_fs_info *fs_info = eb->fs_info; + int ret = 0; + /* * If the page is mapped to btree inode, we should hold the private * lock to prevent race. @@ -3152,16 +3250,62 @@ static void attach_extent_buffer_page(struct extent_buffer *eb, if (page->mapping) lockdep_assert_held(&page->mapping->private_lock); - if (!PagePrivate(page)) - attach_page_private(page, eb); + if (fs_info->sectorsize == PAGE_SIZE) { + if (!PagePrivate(page)) + attach_page_private(page, eb); + else + WARN_ON(page->private != (unsigned long)eb); + return 0; + } + + /* Already mapped, just free prealloc */ + if (PagePrivate(page)) { + btrfs_free_subpage(prealloc); + return 0; + } + + if (prealloc) + /* Has preallocated memory for subpage */ + attach_page_private(page, prealloc); else - WARN_ON(page->private != (unsigned long)eb); + /* Do new allocation to attach subpage */ + ret = btrfs_attach_subpage(fs_info, page, + BTRFS_SUBPAGE_METADATA); + return ret; } -void set_page_extent_mapped(struct page *page) +int set_page_extent_mapped(struct page *page) { + struct btrfs_fs_info *fs_info; + + ASSERT(page->mapping); + + if (PagePrivate(page)) + return 0; + + fs_info = btrfs_sb(page->mapping->host->i_sb); + + if (fs_info->sectorsize < PAGE_SIZE) + return btrfs_attach_subpage(fs_info, page, BTRFS_SUBPAGE_DATA); + + attach_page_private(page, (void *)EXTENT_PAGE_PRIVATE); + return 0; +} + +void clear_page_extent_mapped(struct page *page) +{ + struct btrfs_fs_info *fs_info; + + ASSERT(page->mapping); + if (!PagePrivate(page)) - attach_page_private(page, (void *)EXTENT_PAGE_PRIVATE); + return; + + fs_info = btrfs_sb(page->mapping->host->i_sb); + if (fs_info->sectorsize < PAGE_SIZE) + return btrfs_detach_subpage(fs_info, page); + + detach_page_private(page); } static struct extent_map * @@ -3202,6 +3346,7 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, unsigned int read_flags, u64 *prev_em_start) { struct inode *inode = page->mapping->host; + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); u64 start = page_offset(page); const u64 end = start + PAGE_SIZE - 1; u64 cur = start; @@ -3218,12 +3363,19 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, unsigned long this_bio_flag = 0; struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; - set_page_extent_mapped(page); + ret = set_page_extent_mapped(page); + if (ret < 0) { + unlock_extent(tree, start, end); + btrfs_page_set_error(fs_info, page, start, PAGE_SIZE); + unlock_page(page); + goto out; + } if (!PageUptodate(page)) { if (cleancache_get_page(page) == 0) { BUG_ON(blocksize != PAGE_SIZE); unlock_extent(tree, start, end); + unlock_page(page); goto out; } } @@ -3240,9 +3392,10 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, kunmap_atomic(userpage); } } + begin_page_read(fs_info, page); while (cur <= end) { bool force_bio_submit = false; - u64 offset; + u64 disk_bytenr; if (cur >= last_byte) { char *userpage; @@ -3257,13 +3410,14 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, &cached, GFP_NOFS); unlock_extent_cached(tree, cur, cur + iosize - 1, &cached); + end_page_read(page, true, cur, iosize); break; } em = __get_extent_map(inode, page, pg_offset, cur, end - cur + 1, em_cached); if (IS_ERR_OR_NULL(em)) { - SetPageError(page); unlock_extent(tree, cur, end); + end_page_read(page, false, cur, end + 1 - cur); break; } extent_offset = cur - em->start; @@ -3280,9 +3434,9 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, cur_end = min(extent_map_end(em) - 1, end); iosize = ALIGN(iosize, blocksize); if (this_bio_flag & EXTENT_BIO_COMPRESSED) - offset = em->block_start; + disk_bytenr = em->block_start; else - offset = em->block_start + extent_offset; + disk_bytenr = em->block_start + extent_offset; block_start = em->block_start; if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) block_start = EXTENT_MAP_HOLE; @@ -3346,6 +3500,7 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, &cached, GFP_NOFS); unlock_extent_cached(tree, cur, cur + iosize - 1, &cached); + end_page_read(page, true, cur, iosize); cur = cur + iosize; pg_offset += iosize; continue; @@ -3355,6 +3510,7 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, EXTENT_UPTODATE, 1, NULL)) { check_page_uptodate(tree, page); unlock_extent(tree, cur, cur + iosize - 1); + end_page_read(page, true, cur, iosize); cur = cur + iosize; pg_offset += iosize; continue; @@ -3363,15 +3519,15 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, * to date. Error out */ if (block_start == EXTENT_MAP_INLINE) { - SetPageError(page); unlock_extent(tree, cur, cur + iosize - 1); + end_page_read(page, false, cur, iosize); cur = cur + iosize; pg_offset += iosize; continue; } ret = submit_extent_page(REQ_OP_READ | read_flags, NULL, - page, offset, iosize, + page, disk_bytenr, iosize, pg_offset, bio, end_bio_extent_readpage, 0, *bio_flags, @@ -3381,19 +3537,14 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, nr++; *bio_flags = this_bio_flag; } else { - SetPageError(page); unlock_extent(tree, cur, cur + iosize - 1); + end_page_read(page, false, cur, iosize); goto out; } cur = cur + iosize; pg_offset += iosize; } out: - if (!nr) { - if (!PageError(page)) - SetPageUptodate(page); - unlock_page(page); - } return ret; } @@ -3513,23 +3664,21 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, unsigned long nr_written, int *nr_ret) { + struct btrfs_fs_info *fs_info = inode->root->fs_info; struct extent_io_tree *tree = &inode->io_tree; u64 start = page_offset(page); - u64 page_end = start + PAGE_SIZE - 1; - u64 end; + u64 end = start + PAGE_SIZE - 1; u64 cur = start; u64 extent_offset; u64 block_start; - u64 iosize; struct extent_map *em; - size_t pg_offset = 0; - size_t blocksize; int ret = 0; int nr = 0; + u32 opf = REQ_OP_WRITE; const unsigned int write_flags = wbc_to_write_flags(wbc); bool compressed; - ret = btrfs_writepage_cow_fixup(page, start, page_end); + ret = btrfs_writepage_cow_fixup(page, start, end); if (ret) { /* Fixup worker will requeue */ redirty_page_for_writepage(wbc, page); @@ -3544,16 +3693,13 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, */ update_nr_written(wbc, nr_written + 1); - end = page_end; - blocksize = inode->vfs_inode.i_sb->s_blocksize; - while (cur <= end) { + u64 disk_bytenr; u64 em_end; - u64 offset; + u32 iosize; if (cur >= i_size) { - btrfs_writepage_endio_finish_ordered(page, cur, - page_end, 1); + btrfs_writepage_endio_finish_ordered(page, cur, end, 1); break; } em = btrfs_get_extent(inode, NULL, 0, cur, end - cur + 1); @@ -3565,13 +3711,20 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, extent_offset = cur - em->start; em_end = extent_map_end(em); - BUG_ON(em_end <= cur); - BUG_ON(end < cur); - iosize = min(em_end - cur, end - cur + 1); - iosize = ALIGN(iosize, blocksize); - offset = em->block_start + extent_offset; + ASSERT(cur <= em_end); + ASSERT(cur < end); + ASSERT(IS_ALIGNED(em->start, fs_info->sectorsize)); + ASSERT(IS_ALIGNED(em->len, fs_info->sectorsize)); block_start = em->block_start; compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags); + disk_bytenr = em->block_start + extent_offset; + + /* Note that em_end from extent_map_end() is exclusive */ + iosize = min(em_end, end + 1) - cur; + + if (btrfs_use_zone_append(inode, em)) + opf = REQ_OP_ZONE_APPEND; + free_extent_map(em); em = NULL; @@ -3587,7 +3740,6 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, btrfs_writepage_endio_finish_ordered(page, cur, cur + iosize - 1, 1); cur += iosize; - pg_offset += iosize; continue; } @@ -3598,9 +3750,9 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, page->index, cur, end); } - ret = submit_extent_page(REQ_OP_WRITE | write_flags, wbc, - page, offset, iosize, pg_offset, - &epd->bio, + ret = submit_extent_page(opf | write_flags, wbc, page, + disk_bytenr, iosize, + cur - page_offset(page), &epd->bio, end_bio_extent_writepage, 0, 0, 0, false); if (ret) { @@ -3609,8 +3761,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, end_page_writeback(page); } - cur = cur + iosize; - pg_offset += iosize; + cur += iosize; nr++; } *nr_ret = nr; @@ -3663,7 +3814,11 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc, flush_dcache_page(page); } - set_page_extent_mapped(page); + ret = set_page_extent_mapped(page); + if (ret < 0) { + SetPageError(page); + goto done; + } if (!epd->extent_locked) { ret = writepage_delalloc(BTRFS_I(inode), page, wbc, start, @@ -3923,7 +4078,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, struct writeback_control *wbc, struct extent_page_data *epd) { - u64 offset = eb->start; + u64 disk_bytenr = eb->start; u32 nritems; int i, num_pages; unsigned long start, end; @@ -3956,7 +4111,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, clear_page_dirty_for_io(p); set_page_writeback(p); ret = submit_extent_page(REQ_OP_WRITE | write_flags, wbc, - p, offset, PAGE_SIZE, 0, + p, disk_bytenr, PAGE_SIZE, 0, &epd->bio, end_bio_extent_buffer_writepage, 0, 0, 0, false); @@ -3969,7 +4124,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, ret = -EIO; break; } - offset += PAGE_SIZE; + disk_bytenr += PAGE_SIZE; update_nr_written(wbc, 1); unlock_page(p); } @@ -4010,6 +4165,7 @@ static int submit_eb_page(struct page *page, struct writeback_control *wbc, struct extent_buffer **eb_context) { struct address_space *mapping = page->mapping; + struct btrfs_block_group *cache = NULL; struct extent_buffer *eb; int ret; @@ -4042,13 +4198,31 @@ static int submit_eb_page(struct page *page, struct writeback_control *wbc, if (!ret) return 0; + if (!btrfs_check_meta_write_pointer(eb->fs_info, eb, &cache)) { + /* + * If for_sync, this hole will be filled with + * trasnsaction commit. + */ + if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) + ret = -EAGAIN; + else + ret = 0; + free_extent_buffer(eb); + return ret; + } + *eb_context = eb; ret = lock_extent_buffer_for_io(eb, epd); if (ret <= 0) { + btrfs_revert_meta_write_pointer(cache, eb); + if (cache) + btrfs_put_block_group(cache); free_extent_buffer(eb); return ret; } + if (cache) + btrfs_put_block_group(cache); ret = write_one_eb(eb, wbc, epd); free_extent_buffer(eb); if (ret < 0) @@ -4094,6 +4268,7 @@ int btree_write_cache_pages(struct address_space *mapping, tag = PAGECACHE_TAG_TOWRITE; else tag = PAGECACHE_TAG_DIRTY; + btrfs_zoned_meta_io_lock(fs_info); retry: if (wbc->sync_mode == WB_SYNC_ALL) tag_pages_for_writeback(mapping, index, end); @@ -4134,7 +4309,7 @@ retry: } if (ret < 0) { end_write_bio(&epd, ret); - return ret; + goto out; } /* * If something went wrong, don't allow any metadata write bio to be @@ -4169,14 +4344,17 @@ retry: ret = -EROFS; end_write_bio(&epd, ret); } +out: + btrfs_zoned_meta_io_unlock(fs_info); return ret; } /** - * write_cache_pages - walk the list of dirty pages of the given address space and write all of them. + * Walk the list of dirty pages of the given address space and write all of them. + * * @mapping: address space structure to write - * @wbc: subtract the number of written pages from *@wbc->nr_to_write - * @data: data passed to __extent_writepage function + * @wbc: subtract the number of written pages from *@wbc->nr_to_write + * @epd: holds context for the write, namely the bio * * If a page is already under I/O, write_cache_pages() skips it, even * if it's dirty. This is desirable behaviour for memory-cleaning writeback, @@ -4975,25 +5153,39 @@ int extent_buffer_under_io(const struct extent_buffer *eb) test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); } -/* - * Release all pages attached to the extent buffer. - */ -static void btrfs_release_extent_buffer_pages(struct extent_buffer *eb) +static bool page_range_has_eb(struct btrfs_fs_info *fs_info, struct page *page) { - int i; - int num_pages; - int mapped = !test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags); + struct btrfs_subpage *subpage; - BUG_ON(extent_buffer_under_io(eb)); + lockdep_assert_held(&page->mapping->private_lock); - num_pages = num_extent_pages(eb); - for (i = 0; i < num_pages; i++) { - struct page *page = eb->pages[i]; + if (PagePrivate(page)) { + subpage = (struct btrfs_subpage *)page->private; + if (atomic_read(&subpage->eb_refs)) + return true; + } + return false; +} - if (!page) - continue; +static void detach_extent_buffer_page(struct extent_buffer *eb, struct page *page) +{ + struct btrfs_fs_info *fs_info = eb->fs_info; + const bool mapped = !test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags); + + /* + * For mapped eb, we're going to change the page private, which should + * be done under the private_lock. + */ + if (mapped) + spin_lock(&page->mapping->private_lock); + + if (!PagePrivate(page)) { if (mapped) - spin_lock(&page->mapping->private_lock); + spin_unlock(&page->mapping->private_lock); + return; + } + + if (fs_info->sectorsize == PAGE_SIZE) { /* * We do this since we'll remove the pages after we've * removed the eb from the radix tree, so we could race @@ -5012,9 +5204,49 @@ static void btrfs_release_extent_buffer_pages(struct extent_buffer *eb) */ detach_page_private(page); } - if (mapped) spin_unlock(&page->mapping->private_lock); + return; + } + + /* + * For subpage, we can have dummy eb with page private. In this case, + * we can directly detach the private as such page is only attached to + * one dummy eb, no sharing. + */ + if (!mapped) { + btrfs_detach_subpage(fs_info, page); + return; + } + + btrfs_page_dec_eb_refs(fs_info, page); + + /* + * We can only detach the page private if there are no other ebs in the + * page range. + */ + if (!page_range_has_eb(fs_info, page)) + btrfs_detach_subpage(fs_info, page); + + spin_unlock(&page->mapping->private_lock); +} + +/* Release all pages attached to the extent buffer */ +static void btrfs_release_extent_buffer_pages(struct extent_buffer *eb) +{ + int i; + int num_pages; + + ASSERT(!extent_buffer_under_io(eb)); + + num_pages = num_extent_pages(eb); + for (i = 0; i < num_pages; i++) { + struct page *page = eb->pages[i]; + + if (!page) + continue; + + detach_extent_buffer_page(eb, page); /* One for when we allocated the page */ put_page(page); @@ -5046,6 +5278,7 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start, btrfs_leak_debug_add(&fs_info->eb_leak_lock, &eb->leak_list, &fs_info->allocated_ebs); + INIT_LIST_HEAD(&eb->release_list); spin_lock_init(&eb->refs_lock); atomic_set(&eb->refs, 1); @@ -5067,21 +5300,32 @@ struct extent_buffer *btrfs_clone_extent_buffer(const struct extent_buffer *src) if (new == NULL) return NULL; + /* + * Set UNMAPPED before calling btrfs_release_extent_buffer(), as + * btrfs_release_extent_buffer() have different behavior for + * UNMAPPED subpage extent buffer. + */ + set_bit(EXTENT_BUFFER_UNMAPPED, &new->bflags); + for (i = 0; i < num_pages; i++) { + int ret; + p = alloc_page(GFP_NOFS); if (!p) { btrfs_release_extent_buffer(new); return NULL; } - attach_extent_buffer_page(new, p); + ret = attach_extent_buffer_page(new, p, NULL); + if (ret < 0) { + put_page(p); + btrfs_release_extent_buffer(new); + return NULL; + } WARN_ON(PageDirty(p)); - SetPageUptodate(p); new->pages[i] = p; copy_page(page_address(p), page_address(src->pages[i])); } - - set_bit(EXTENT_BUFFER_UPTODATE, &new->bflags); - set_bit(EXTENT_BUFFER_UNMAPPED, &new->bflags); + set_extent_buffer_uptodate(new); return new; } @@ -5099,9 +5343,14 @@ struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info, num_pages = num_extent_pages(eb); for (i = 0; i < num_pages; i++) { + int ret; + eb->pages[i] = alloc_page(GFP_NOFS); if (!eb->pages[i]) goto err; + ret = attach_extent_buffer_page(eb, eb->pages[i], NULL); + if (ret < 0) + goto err; } set_extent_buffer_uptodate(eb); btrfs_set_header_nritems(eb, 0); @@ -5109,8 +5358,10 @@ struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info, return eb; err: - for (; i > 0; i--) + for (; i > 0; i--) { + detach_extent_buffer_page(eb, eb->pages[i - 1]); __free_page(eb->pages[i - 1]); + } __free_extent_buffer(eb); return NULL; } @@ -5252,6 +5503,38 @@ free_eb: } #endif +static struct extent_buffer *grab_extent_buffer( + struct btrfs_fs_info *fs_info, struct page *page) +{ + struct extent_buffer *exists; + + /* + * For subpage case, we completely rely on radix tree to ensure we + * don't try to insert two ebs for the same bytenr. So here we always + * return NULL and just continue. + */ + if (fs_info->sectorsize < PAGE_SIZE) + return NULL; + + /* Page not yet attached to an extent buffer */ + if (!PagePrivate(page)) + return NULL; + + /* + * We could have already allocated an eb for this page and attached one + * so lets see if we can get a ref on the existing eb, and if we can we + * know it's good and we can just return that one, else we know we can + * just overwrite page->private. + */ + exists = (struct extent_buffer *)page->private; + if (atomic_inc_not_zero(&exists->refs)) + return exists; + + WARN_ON(PageDirty(page)); + detach_page_private(page); + return NULL; +} + struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start, u64 owner_root, int level) { @@ -5290,36 +5573,58 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, num_pages = num_extent_pages(eb); for (i = 0; i < num_pages; i++, index++) { + struct btrfs_subpage *prealloc = NULL; + p = find_or_create_page(mapping, index, GFP_NOFS|__GFP_NOFAIL); if (!p) { exists = ERR_PTR(-ENOMEM); goto free_eb; } - spin_lock(&mapping->private_lock); - if (PagePrivate(p)) { - /* - * We could have already allocated an eb for this page - * and attached one so lets see if we can get a ref on - * the existing eb, and if we can we know it's good and - * we can just return that one, else we know we can just - * overwrite page->private. - */ - exists = (struct extent_buffer *)p->private; - if (atomic_inc_not_zero(&exists->refs)) { - spin_unlock(&mapping->private_lock); - unlock_page(p); - put_page(p); - mark_extent_buffer_accessed(exists, p); - goto free_eb; - } - exists = NULL; - - WARN_ON(PageDirty(p)); - detach_page_private(p); + /* + * Preallocate page->private for subpage case, so that we won't + * allocate memory with private_lock hold. The memory will be + * freed by attach_extent_buffer_page() or freed manually if + * we exit earlier. + * + * Although we have ensured one subpage eb can only have one + * page, but it may change in the future for 16K page size + * support, so we still preallocate the memory in the loop. + */ + ret = btrfs_alloc_subpage(fs_info, &prealloc, + BTRFS_SUBPAGE_METADATA); + if (ret < 0) { + unlock_page(p); + put_page(p); + exists = ERR_PTR(ret); + goto free_eb; } - attach_extent_buffer_page(eb, p); + + spin_lock(&mapping->private_lock); + exists = grab_extent_buffer(fs_info, p); + if (exists) { + spin_unlock(&mapping->private_lock); + unlock_page(p); + put_page(p); + mark_extent_buffer_accessed(exists, p); + btrfs_free_subpage(prealloc); + goto free_eb; + } + /* Should not fail, as we have preallocated the memory */ + ret = attach_extent_buffer_page(eb, p, prealloc); + ASSERT(!ret); + /* + * To inform we have extra eb under allocation, so that + * detach_extent_buffer_page() won't release the page private + * when the eb hasn't yet been inserted into radix tree. + * + * The ref will be decreased when the eb released the page, in + * detach_extent_buffer_page(). + * Thus needs no special handling in error path. + */ + btrfs_page_inc_eb_refs(fs_info, p); spin_unlock(&mapping->private_lock); + WARN_ON(PageDirty(p)); eb->pages[i] = p; if (!PageUptodate(p)) @@ -5525,33 +5830,103 @@ bool set_extent_buffer_dirty(struct extent_buffer *eb) void clear_extent_buffer_uptodate(struct extent_buffer *eb) { - int i; + struct btrfs_fs_info *fs_info = eb->fs_info; struct page *page; int num_pages; + int i; clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); num_pages = num_extent_pages(eb); for (i = 0; i < num_pages; i++) { page = eb->pages[i]; if (page) - ClearPageUptodate(page); + btrfs_page_clear_uptodate(fs_info, page, + eb->start, eb->len); } } void set_extent_buffer_uptodate(struct extent_buffer *eb) { - int i; + struct btrfs_fs_info *fs_info = eb->fs_info; struct page *page; int num_pages; + int i; set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); num_pages = num_extent_pages(eb); for (i = 0; i < num_pages; i++) { page = eb->pages[i]; - SetPageUptodate(page); + btrfs_page_set_uptodate(fs_info, page, eb->start, eb->len); } } +static int read_extent_buffer_subpage(struct extent_buffer *eb, int wait, + int mirror_num) +{ + struct btrfs_fs_info *fs_info = eb->fs_info; + struct extent_io_tree *io_tree; + struct page *page = eb->pages[0]; + struct bio *bio = NULL; + int ret = 0; + + ASSERT(!test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags)); + ASSERT(PagePrivate(page)); + io_tree = &BTRFS_I(fs_info->btree_inode)->io_tree; + + if (wait == WAIT_NONE) { + ret = try_lock_extent(io_tree, eb->start, + eb->start + eb->len - 1); + if (ret <= 0) + return ret; + } else { + ret = lock_extent(io_tree, eb->start, eb->start + eb->len - 1); + if (ret < 0) + return ret; + } + + ret = 0; + if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags) || + PageUptodate(page) || + btrfs_subpage_test_uptodate(fs_info, page, eb->start, eb->len)) { + set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); + unlock_extent(io_tree, eb->start, eb->start + eb->len - 1); + return ret; + } + + clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags); + eb->read_mirror = 0; + atomic_set(&eb->io_pages, 1); + check_buffer_tree_ref(eb); + btrfs_subpage_clear_error(fs_info, page, eb->start, eb->len); + + ret = submit_extent_page(REQ_OP_READ | REQ_META, NULL, page, eb->start, + eb->len, eb->start - page_offset(page), &bio, + end_bio_extent_readpage, mirror_num, 0, 0, + true); + if (ret) { + /* + * In the endio function, if we hit something wrong we will + * increase the io_pages, so here we need to decrease it for + * error path. + */ + atomic_dec(&eb->io_pages); + } + if (bio) { + int tmp; + + tmp = submit_one_bio(bio, mirror_num, 0); + if (tmp < 0) + return tmp; + } + if (ret || wait != WAIT_COMPLETE) + return ret; + + wait_extent_bit(io_tree, eb->start, eb->start + eb->len - 1, EXTENT_LOCKED); + if (!test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) + ret = -EIO; + return ret; +} + int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num) { int i; @@ -5568,10 +5943,20 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num) if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) return 0; + if (eb->fs_info->sectorsize < PAGE_SIZE) + return read_extent_buffer_subpage(eb, wait, mirror_num); + num_pages = num_extent_pages(eb); for (i = 0; i < num_pages; i++) { page = eb->pages[i]; if (wait == WAIT_NONE) { + /* + * WAIT_NONE is only utilized by readahead. If we can't + * acquire the lock atomically it means either the eb + * is being read out or under modification. + * Either way the eb will be or has been cached, + * readahead can exit safely. + */ if (!trylock_page(page)) goto unlock_exit; } else { @@ -5823,6 +6208,8 @@ void write_extent_buffer(const struct extent_buffer *eb, const void *srcv, char *src = (char *)srcv; unsigned long i = get_eb_page_index(start); + WARN_ON(test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags)); + if (check_eb_range(eb, start, len)) return; @@ -6169,13 +6556,115 @@ void memmove_extent_buffer(const struct extent_buffer *dst, } } +static struct extent_buffer *get_next_extent_buffer( + struct btrfs_fs_info *fs_info, struct page *page, u64 bytenr) +{ + struct extent_buffer *gang[BTRFS_SUBPAGE_BITMAP_SIZE]; + struct extent_buffer *found = NULL; + u64 page_start = page_offset(page); + int ret; + int i; + + ASSERT(in_range(bytenr, page_start, PAGE_SIZE)); + ASSERT(PAGE_SIZE / fs_info->nodesize <= BTRFS_SUBPAGE_BITMAP_SIZE); + lockdep_assert_held(&fs_info->buffer_lock); + + ret = radix_tree_gang_lookup(&fs_info->buffer_radix, (void **)gang, + bytenr >> fs_info->sectorsize_bits, + PAGE_SIZE / fs_info->nodesize); + for (i = 0; i < ret; i++) { + /* Already beyond page end */ + if (gang[i]->start >= page_start + PAGE_SIZE) + break; + /* Found one */ + if (gang[i]->start >= bytenr) { + found = gang[i]; + break; + } + } + return found; +} + +static int try_release_subpage_extent_buffer(struct page *page) +{ + struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb); + u64 cur = page_offset(page); + const u64 end = page_offset(page) + PAGE_SIZE; + int ret; + + while (cur < end) { + struct extent_buffer *eb = NULL; + + /* + * Unlike try_release_extent_buffer() which uses page->private + * to grab buffer, for subpage case we rely on radix tree, thus + * we need to ensure radix tree consistency. + * + * We also want an atomic snapshot of the radix tree, thus go + * with spinlock rather than RCU. + */ + spin_lock(&fs_info->buffer_lock); + eb = get_next_extent_buffer(fs_info, page, cur); + if (!eb) { + /* No more eb in the page range after or at cur */ + spin_unlock(&fs_info->buffer_lock); + break; + } + cur = eb->start + eb->len; + + /* + * The same as try_release_extent_buffer(), to ensure the eb + * won't disappear out from under us. + */ + spin_lock(&eb->refs_lock); + if (atomic_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) { + spin_unlock(&eb->refs_lock); + spin_unlock(&fs_info->buffer_lock); + break; + } + spin_unlock(&fs_info->buffer_lock); + + /* + * If tree ref isn't set then we know the ref on this eb is a + * real ref, so just return, this eb will likely be freed soon + * anyway. + */ + if (!test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) { + spin_unlock(&eb->refs_lock); + break; + } + + /* + * Here we don't care about the return value, we will always + * check the page private at the end. And + * release_extent_buffer() will release the refs_lock. + */ + release_extent_buffer(eb); + } + /* + * Finally to check if we have cleared page private, as if we have + * released all ebs in the page, the page private should be cleared now. + */ + spin_lock(&page->mapping->private_lock); + if (!PagePrivate(page)) + ret = 1; + else + ret = 0; + spin_unlock(&page->mapping->private_lock); + return ret; + +} + int try_release_extent_buffer(struct page *page) { struct extent_buffer *eb; + if (btrfs_sb(page->mapping->host->i_sb)->sectorsize < PAGE_SIZE) + return try_release_subpage_extent_buffer(page); + /* - * We need to make sure nobody is attaching this page to an eb right - * now. + * We need to make sure nobody is changing page->private, as we rely on + * page->private as the pointer to extent buffer. */ spin_lock(&page->mapping->private_lock); if (!PagePrivate(page)) { diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 19221095c635..824640cb0ace 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -31,16 +31,17 @@ enum { EXTENT_BUFFER_IN_TREE, /* write IO error */ EXTENT_BUFFER_WRITE_ERR, + EXTENT_BUFFER_NO_CHECK, }; /* these are flags for __process_pages_contig */ #define PAGE_UNLOCK (1 << 0) -#define PAGE_CLEAR_DIRTY (1 << 1) -#define PAGE_SET_WRITEBACK (1 << 2) -#define PAGE_END_WRITEBACK (1 << 3) -#define PAGE_SET_PRIVATE2 (1 << 4) -#define PAGE_SET_ERROR (1 << 5) -#define PAGE_LOCK (1 << 6) +/* Page starts writeback, clear dirty bit and set writeback bit */ +#define PAGE_START_WRITEBACK (1 << 1) +#define PAGE_END_WRITEBACK (1 << 2) +#define PAGE_SET_PRIVATE2 (1 << 3) +#define PAGE_SET_ERROR (1 << 4) +#define PAGE_LOCK (1 << 5) /* * page->private values. Every page that is controlled by the extent @@ -93,6 +94,7 @@ struct extent_buffer { struct rw_semaphore lock; struct page *pages[INLINE_EXTENT_BUFFER_PAGES]; + struct list_head release_list; #ifdef CONFIG_BTRFS_DEBUG struct list_head leak_list; #endif @@ -178,7 +180,8 @@ int btree_write_cache_pages(struct address_space *mapping, void extent_readahead(struct readahead_control *rac); int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len); -void set_page_extent_mapped(struct page *page); +int set_page_extent_mapped(struct page *page); +void clear_page_extent_mapped(struct page *page); struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start, u64 owner_root, int level); diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index bd6229fb2b6f..4a8e02f7b6c7 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -385,9 +385,12 @@ static void extent_map_device_clear_bits(struct extent_map *em, unsigned bits) } /** - * add_extent_mapping - add new extent map to the extent tree + * Add new extent map to the extent tree + * * @tree: tree to insert new map in * @em: map to insert + * @modified: indicate whether the given @em should be added to the + * modified list, which indicates the extent needs to be logged * * Insert @em into @tree or perform a simple forward/backward merge with * existing mappings. The extent_map struct passed in will be inserted @@ -574,12 +577,13 @@ static noinline int merge_extent_mapping(struct extent_map_tree *em_tree, } /** - * btrfs_add_extent_mapping - add extent mapping into em_tree - * @fs_info - used for tracepoint - * @em_tree - the extent tree into which we want to insert the extent mapping - * @em_in - extent we are inserting - * @start - start of the logical range btrfs_get_extent() is requesting - * @len - length of the logical range btrfs_get_extent() is requesting + * Add extent mapping into em_tree + * + * @fs_info: the filesystem + * @em_tree: extent tree into which we want to insert the extent mapping + * @em_in: extent we are inserting + * @start: start of the logical range btrfs_get_extent() is requesting + * @len: length of the logical range btrfs_get_extent() is requesting * * Note that @em_in's range may be different from [start, start+len), * but they must be overlapped. diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 6ccfc019ad90..47cd3a6dc635 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -24,8 +24,10 @@ PAGE_SIZE)) /** - * @inode - the inode we want to update the disk_i_size for - * @new_i_size - the i_size we want to set to, 0 if we use i_size + * Set inode's size according to filesystem options + * + * @inode: inode we want to update the disk_i_size for + * @new_i_size: i_size we want to set to, 0 if we use i_size * * With NO_HOLES set this simply sets the disk_is_size to whatever i_size_read() * returns as it is perfectly fine with a file that has holes without hole file @@ -62,9 +64,11 @@ void btrfs_inode_safe_disk_i_size_write(struct btrfs_inode *inode, u64 new_i_siz } /** - * @inode - the inode we're modifying - * @start - the start file offset of the file extent we've inserted - * @len - the logical length of the file extent item + * Mark range within a file as having a new extent inserted + * + * @inode: inode being modified + * @start: start file offset of the file extent we've inserted + * @len: logical length of the file extent item * * Call when we are inserting a new file extent where there was none before. * Does not need to call this in the case where we're replacing an existing file @@ -88,9 +92,11 @@ int btrfs_inode_set_file_extent_range(struct btrfs_inode *inode, u64 start, } /** - * @inode - the inode we're modifying - * @start - the start file offset of the file extent we've inserted - * @len - the logical length of the file extent item + * Marks an inode range as not having a backing extent + * + * @inode: inode being modified + * @start: start file offset of the file extent we've inserted + * @len: logical length of the file extent item * * Called when we drop a file extent, for example when we truncate. Doesn't * need to be called for cases where we're replacing a file extent, like when diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 0e41459b8de6..01a72f53fb5d 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -453,12 +453,11 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages) } /* - * after copy_from_user, pages need to be dirtied and we need to make - * sure holes are created between the current EOF and the start of - * any next extents (if required). - * - * this also makes the decision about creating an inline extent vs - * doing real data extents, marking pages dirty and delalloc as required. + * After btrfs_copy_from_user(), update the following things for delalloc: + * - Mark newly dirtied pages as DELALLOC in the io tree. + * Used to advise which range is to be written back. + * - Mark modified pages as Uptodate/Dirty and not needing COW fixup + * - Update inode size for past EOF write */ int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages, size_t num_pages, loff_t pos, size_t write_bytes, @@ -1370,6 +1369,12 @@ again: goto fail; } + err = set_page_extent_mapped(pages[i]); + if (err < 0) { + faili = i; + goto fail; + } + if (i == 0) err = prepare_uptodate_page(inode, pages[i], pos, force_uptodate); @@ -1454,23 +1459,11 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, } /* - * It's possible the pages are dirty right now, but we don't want - * to clean them yet because copy_from_user may catch a page fault - * and we might have to fall back to one page at a time. If that - * happens, we'll unlock these pages and we'd have a window where - * reclaim could sneak in and drop the once-dirty page on the floor - * without writing it. - * - * We have the pages locked and the extent range locked, so there's - * no way someone can start IO on any dirty pages in this range. - * - * We'll call btrfs_dirty_pages() later on, and that will flip around - * delalloc bits and dirty the pages as required. + * We should be called after prepare_pages() which should have locked + * all pages in the range. */ - for (i = 0; i < num_pages; i++) { - set_page_extent_mapped(pages[i]); + for (i = 0; i < num_pages; i++) WARN_ON(!PageLocked(pages[i])); - } return ret; } @@ -1997,9 +1990,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; - struct inode *inode = file_inode(file); - struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_inode *inode = BTRFS_I(file_inode(file)); ssize_t num_written = 0; const bool sync = iocb->ki_flags & IOCB_DSYNC; @@ -2008,7 +1999,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, * have opened a file as writable, we have to stop this write operation * to ensure consistency. */ - if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) + if (test_bit(BTRFS_FS_STATE_ERROR, &inode->root->fs_info->fs_state)) return -EROFS; if (!(iocb->ki_flags & IOCB_DIRECT) && @@ -2016,7 +2007,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, return -EOPNOTSUPP; if (sync) - atomic_inc(&BTRFS_I(inode)->sync_writers); + atomic_inc(&inode->sync_writers); if (iocb->ki_flags & IOCB_DIRECT) num_written = btrfs_direct_write(iocb, from); @@ -2028,14 +2019,14 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, * otherwise subsequent syncs to a file that's been synced in this * transaction will appear to have already occurred. */ - spin_lock(&BTRFS_I(inode)->lock); - BTRFS_I(inode)->last_sub_trans = root->log_transid; - spin_unlock(&BTRFS_I(inode)->lock); + spin_lock(&inode->lock); + inode->last_sub_trans = inode->root->log_transid; + spin_unlock(&inode->lock); if (num_written > 0) num_written = generic_write_sync(iocb, num_written); if (sync) - atomic_dec(&BTRFS_I(inode)->sync_writers); + atomic_dec(&inode->sync_writers); current->backing_dev_info = NULL; return num_written; @@ -2177,8 +2168,12 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) * commit waits for their completion, to avoid data loss if we fsync, * the current transaction commits before the ordered extents complete * and a power failure happens right after that. + * + * For zoned filesystem, if a write IO uses a ZONE_APPEND command, the + * logical address recorded in the ordered extent may change. We need + * to wait for the IO to stabilize the logical address. */ - if (full_sync) { + if (full_sync || btrfs_is_zoned(fs_info)) { ret = btrfs_wait_ordered_range(inode, start, len); } else { /* @@ -2241,6 +2236,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) ret = PTR_ERR(trans); goto out_release_extents; } + trans->in_fsync = true; ret = btrfs_log_dentry_safe(trans, dentry, &ctx); btrfs_release_log_ctx_extents(&ctx); diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 4d8897879c9c..5400294bd271 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -198,7 +198,7 @@ int create_free_space_inode(struct btrfs_trans_handle *trans, int ret; u64 ino; - ret = btrfs_find_free_objectid(trans->fs_info->tree_root, &ino); + ret = btrfs_get_free_objectid(trans->fs_info->tree_root, &ino); if (ret < 0) return ret; @@ -431,11 +431,22 @@ static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, bool uptodate) int i; for (i = 0; i < io_ctl->num_pages; i++) { + int ret; + page = find_or_create_page(inode->i_mapping, i, mask); if (!page) { io_ctl_drop_pages(io_ctl); return -ENOMEM; } + + ret = set_page_extent_mapped(page); + if (ret < 0) { + unlock_page(page); + put_page(page); + io_ctl_drop_pages(io_ctl); + return ret; + } + io_ctl->pages[i] = page; if (uptodate && !PageUptodate(page)) { btrfs_readpage(NULL, page); @@ -455,10 +466,8 @@ static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, bool uptodate) } } - for (i = 0; i < io_ctl->num_pages; i++) { + for (i = 0; i < io_ctl->num_pages; i++) clear_page_dirty_for_io(io_ctl->pages[i]); - set_page_extent_mapped(io_ctl->pages[i]); - } return 0; } @@ -775,8 +784,10 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, while (num_entries) { e = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS); - if (!e) + if (!e) { + ret = -ENOMEM; goto free_cache; + } ret = io_ctl_read_entry(&io_ctl, e, &type); if (ret) { @@ -785,6 +796,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, } if (!e->bytes) { + ret = -1; kmem_cache_free(btrfs_free_space_cachep, e); goto free_cache; } @@ -805,6 +817,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, e->bitmap = kmem_cache_zalloc( btrfs_free_space_bitmap_cachep, GFP_NOFS); if (!e->bitmap) { + ret = -ENOMEM; kmem_cache_free( btrfs_free_space_cachep, e); goto free_cache; @@ -1295,11 +1308,14 @@ int btrfs_wait_cache_io(struct btrfs_trans_handle *trans, } /** - * __btrfs_write_out_cache - write out cached info to an inode - * @root - the root the inode belongs to - * @ctl - the free space cache we are going to write out - * @block_group - the block_group for this cache if it belongs to a block_group - * @trans - the trans handle + * Write out cached info to an inode + * + * @root: root the inode belongs to + * @inode: freespace inode we are writing out + * @ctl: free space cache we are going to write out + * @block_group: block_group for this cache if it belongs to a block_group + * @io_ctl: holds context for the io + * @trans: the trans handle * * This function writes out a free space cache struct to disk for quick recovery * on mount. This will return 0 if it was successful in writing the cache out, @@ -2461,6 +2477,8 @@ int __btrfs_add_free_space(struct btrfs_fs_info *fs_info, int ret = 0; u64 filter_bytes = bytes; + ASSERT(!btrfs_is_zoned(fs_info)); + info = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS); if (!info) return -ENOMEM; @@ -2518,11 +2536,49 @@ out: return ret; } +static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, + u64 bytenr, u64 size, bool used) +{ + struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; + u64 offset = bytenr - block_group->start; + u64 to_free, to_unusable; + + spin_lock(&ctl->tree_lock); + if (!used) + to_free = size; + else if (offset >= block_group->alloc_offset) + to_free = size; + else if (offset + size <= block_group->alloc_offset) + to_free = 0; + else + to_free = offset + size - block_group->alloc_offset; + to_unusable = size - to_free; + + ctl->free_space += to_free; + block_group->zone_unusable += to_unusable; + spin_unlock(&ctl->tree_lock); + if (!used) { + spin_lock(&block_group->lock); + block_group->alloc_offset -= size; + spin_unlock(&block_group->lock); + } + + /* All the region is now unusable. Mark it as unused and reclaim */ + if (block_group->zone_unusable == block_group->length) + btrfs_mark_bg_unused(block_group); + + return 0; +} + int btrfs_add_free_space(struct btrfs_block_group *block_group, u64 bytenr, u64 size) { enum btrfs_trim_state trim_state = BTRFS_TRIM_STATE_UNTRIMMED; + if (btrfs_is_zoned(block_group->fs_info)) + return __btrfs_add_free_space_zoned(block_group, bytenr, size, + true); + if (btrfs_test_opt(block_group->fs_info, DISCARD_SYNC)) trim_state = BTRFS_TRIM_STATE_TRIMMED; @@ -2531,6 +2587,16 @@ int btrfs_add_free_space(struct btrfs_block_group *block_group, bytenr, size, trim_state); } +int btrfs_add_free_space_unused(struct btrfs_block_group *block_group, + u64 bytenr, u64 size) +{ + if (btrfs_is_zoned(block_group->fs_info)) + return __btrfs_add_free_space_zoned(block_group, bytenr, size, + false); + + return btrfs_add_free_space(block_group, bytenr, size); +} + /* * This is a subtle distinction because when adding free space back in general, * we want it to be added as untrimmed for async. But in the case where we add @@ -2541,6 +2607,10 @@ int btrfs_add_free_space_async_trimmed(struct btrfs_block_group *block_group, { enum btrfs_trim_state trim_state = BTRFS_TRIM_STATE_UNTRIMMED; + if (btrfs_is_zoned(block_group->fs_info)) + return __btrfs_add_free_space_zoned(block_group, bytenr, size, + true); + if (btrfs_test_opt(block_group->fs_info, DISCARD_SYNC) || btrfs_test_opt(block_group->fs_info, DISCARD_ASYNC)) trim_state = BTRFS_TRIM_STATE_TRIMMED; @@ -2558,6 +2628,23 @@ int btrfs_remove_free_space(struct btrfs_block_group *block_group, int ret; bool re_search = false; + if (btrfs_is_zoned(block_group->fs_info)) { + /* + * This can happen with conventional zones when replaying log. + * Since the allocation info of tree-log nodes are not recorded + * to the extent-tree, calculate_alloc_pointer() failed to + * advance the allocation pointer after last allocated tree log + * node blocks. + * + * This function is called from + * btrfs_pin_extent_for_log_replay() when replaying the log. + * Advance the pointer not to overwrite the tree-log nodes. + */ + if (block_group->alloc_offset < offset + bytes) + block_group->alloc_offset = offset + bytes; + return 0; + } + spin_lock(&ctl->tree_lock); again: @@ -2652,6 +2739,16 @@ void btrfs_dump_free_space(struct btrfs_block_group *block_group, struct rb_node *n; int count = 0; + /* + * Zoned btrfs does not use free space tree and cluster. Just print + * out the free space after the allocation offset. + */ + if (btrfs_is_zoned(fs_info)) { + btrfs_info(fs_info, "free space %llu", + block_group->length - block_group->alloc_offset); + return; + } + spin_lock(&ctl->tree_lock); for (n = rb_first(&ctl->free_space_offset); n; n = rb_next(n)) { info = rb_entry(n, struct btrfs_free_space, offset_index); @@ -2845,6 +2942,8 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group, u64 align_gap_len = 0; enum btrfs_trim_state align_gap_trim_state = BTRFS_TRIM_STATE_UNTRIMMED; + ASSERT(!btrfs_is_zoned(block_group->fs_info)); + spin_lock(&ctl->tree_lock); entry = find_free_space(ctl, &offset, &bytes_search, block_group->full_stripe_len, max_extent_size); @@ -2976,6 +3075,8 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group *block_group, struct rb_node *node; u64 ret = 0; + ASSERT(!btrfs_is_zoned(block_group->fs_info)); + spin_lock(&cluster->lock); if (bytes > cluster->max_size) goto out; @@ -3752,6 +3853,8 @@ int btrfs_trim_block_group(struct btrfs_block_group *block_group, int ret; u64 rem = 0; + ASSERT(!btrfs_is_zoned(block_group->fs_info)); + *trimmed = 0; spin_lock(&block_group->lock); diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h index ecb09a02d544..1f23088d43f9 100644 --- a/fs/btrfs/free-space-cache.h +++ b/fs/btrfs/free-space-cache.h @@ -107,6 +107,8 @@ int __btrfs_add_free_space(struct btrfs_fs_info *fs_info, enum btrfs_trim_state trim_state); int btrfs_add_free_space(struct btrfs_block_group *block_group, u64 bytenr, u64 size); +int btrfs_add_free_space_unused(struct btrfs_block_group *block_group, + u64 bytenr, u64 size); int btrfs_add_free_space_async_trimmed(struct btrfs_block_group *block_group, u64 bytenr, u64 size); int btrfs_remove_free_space(struct btrfs_block_group *block_group, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a8e0a6b038d3..535abf898225 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -50,6 +50,7 @@ #include "delalloc-space.h" #include "block-group.h" #include "space-info.h" +#include "zoned.h" struct btrfs_iget_args { u64 ino; @@ -692,8 +693,7 @@ cont: NULL, clear_flags, PAGE_UNLOCK | - PAGE_CLEAR_DIRTY | - PAGE_SET_WRITEBACK | + PAGE_START_WRITEBACK | page_error_op | PAGE_END_WRITEBACK); @@ -917,7 +917,6 @@ retry: ins.objectid, async_extent->ram_size, ins.offset, - BTRFS_ORDERED_COMPRESSED, async_extent->compress_type); if (ret) { btrfs_drop_extent_cache(inode, async_extent->start, @@ -934,8 +933,7 @@ retry: async_extent->start + async_extent->ram_size - 1, NULL, EXTENT_LOCKED | EXTENT_DELALLOC, - PAGE_UNLOCK | PAGE_CLEAR_DIRTY | - PAGE_SET_WRITEBACK); + PAGE_UNLOCK | PAGE_START_WRITEBACK); if (btrfs_submit_compressed_write(inode, async_extent->start, async_extent->ram_size, ins.objectid, @@ -971,9 +969,8 @@ out_free: NULL, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING, - PAGE_UNLOCK | PAGE_CLEAR_DIRTY | - PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK | - PAGE_SET_ERROR); + PAGE_UNLOCK | PAGE_START_WRITEBACK | + PAGE_END_WRITEBACK | PAGE_SET_ERROR); free_async_extent_pages(async_extent); kfree(async_extent); goto again; @@ -1071,8 +1068,7 @@ static noinline int cow_file_range(struct btrfs_inode *inode, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING, PAGE_UNLOCK | - PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK | - PAGE_END_WRITEBACK); + PAGE_START_WRITEBACK | PAGE_END_WRITEBACK); *nr_written = *nr_written + (end - start + PAGE_SIZE) / PAGE_SIZE; *page_started = 1; @@ -1127,7 +1123,8 @@ static noinline int cow_file_range(struct btrfs_inode *inode, free_extent_map(em); ret = btrfs_add_ordered_extent(inode, start, ins.objectid, - ram_size, cur_alloc_size, 0); + ram_size, cur_alloc_size, + BTRFS_ORDERED_REGULAR); if (ret) goto out_drop_extent_cache; @@ -1194,8 +1191,7 @@ out_reserve: out_unlock: clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV; - page_ops = PAGE_UNLOCK | PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK | - PAGE_END_WRITEBACK; + page_ops = PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK; /* * If we reserved an extent for our delalloc range (or a subrange) and * failed to create the respective ordered extent, then it means that @@ -1320,9 +1316,8 @@ static int cow_file_range_async(struct btrfs_inode *inode, unsigned clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING; - unsigned long page_ops = PAGE_UNLOCK | PAGE_CLEAR_DIRTY | - PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK | - PAGE_SET_ERROR; + unsigned long page_ops = PAGE_UNLOCK | PAGE_START_WRITEBACK | + PAGE_END_WRITEBACK | PAGE_SET_ERROR; extent_clear_unlock_delalloc(inode, start, end, locked_page, clear_bits, page_ops); @@ -1399,6 +1394,29 @@ static int cow_file_range_async(struct btrfs_inode *inode, return 0; } +static noinline int run_delalloc_zoned(struct btrfs_inode *inode, + struct page *locked_page, u64 start, + u64 end, int *page_started, + unsigned long *nr_written) +{ + int ret; + + ret = cow_file_range(inode, locked_page, start, end, page_started, + nr_written, 0); + if (ret) + return ret; + + if (*page_started) + return 0; + + __set_page_dirty_nobuffers(locked_page); + account_page_redirty(locked_page); + extent_write_locked_range(&inode->vfs_inode, start, end, WB_SYNC_ALL); + *page_started = 1; + + return 0; +} + static noinline int csum_exist_in_range(struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes) { @@ -1519,8 +1537,7 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, PAGE_UNLOCK | - PAGE_CLEAR_DIRTY | - PAGE_SET_WRITEBACK | + PAGE_START_WRITEBACK | PAGE_END_WRITEBACK); return -ENOMEM; } @@ -1842,8 +1859,7 @@ error: locked_page, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING, PAGE_UNLOCK | - PAGE_CLEAR_DIRTY | - PAGE_SET_WRITEBACK | + PAGE_START_WRITEBACK | PAGE_END_WRITEBACK); btrfs_free_path(path); return ret; @@ -1878,17 +1894,24 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page { int ret; int force_cow = need_force_cow(inode, start, end); + const bool zoned = btrfs_is_zoned(inode->root->fs_info); if (inode->flags & BTRFS_INODE_NODATACOW && !force_cow) { + ASSERT(!zoned); ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, 1, nr_written); } else if (inode->flags & BTRFS_INODE_PREALLOC && !force_cow) { + ASSERT(!zoned); ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, 0, nr_written); } else if (!inode_can_compress(inode) || !inode_need_compress(inode, start, end)) { - ret = cow_file_range(inode, locked_page, start, end, - page_started, nr_written, 1); + if (zoned) + ret = run_delalloc_zoned(inode, locked_page, start, end, + page_started, nr_written); + else + ret = cow_file_range(inode, locked_page, start, end, + page_started, nr_written, 1); } else { set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, &inode->runtime_flags); ret = cow_file_range_async(inode, wbc, locked_page, start, end, @@ -2183,9 +2206,10 @@ int btrfs_bio_fits_in_stripe(struct page *page, size_t size, struct bio *bio, struct inode *inode = page->mapping->host; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); u64 logical = bio->bi_iter.bi_sector << 9; + struct extent_map *em; u64 length = 0; u64 map_length; - int ret; + int ret = 0; struct btrfs_io_geometry geom; if (bio_flags & EXTENT_BIO_COMPRESSED) @@ -2193,14 +2217,19 @@ int btrfs_bio_fits_in_stripe(struct page *page, size_t size, struct bio *bio, length = bio->bi_iter.bi_size; map_length = length; - ret = btrfs_get_io_geometry(fs_info, btrfs_op(bio), logical, map_length, - &geom); + em = btrfs_get_chunk_map(fs_info, logical, map_length); + if (IS_ERR(em)) + return PTR_ERR(em); + ret = btrfs_get_io_geometry(fs_info, em, btrfs_op(bio), logical, + map_length, &geom); if (ret < 0) - return ret; + goto out; if (geom.len < length + size) - return 1; - return 0; + ret = 1; +out: + free_extent_map(em); + return ret; } /* @@ -2217,6 +2246,119 @@ static blk_status_t btrfs_submit_bio_start(struct inode *inode, struct bio *bio, return btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0); } +bool btrfs_bio_fits_in_ordered_extent(struct page *page, struct bio *bio, + unsigned int size) +{ + struct btrfs_inode *inode = BTRFS_I(page->mapping->host); + struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct btrfs_ordered_extent *ordered; + u64 len = bio->bi_iter.bi_size + size; + bool ret = true; + + ASSERT(btrfs_is_zoned(fs_info)); + ASSERT(fs_info->max_zone_append_size > 0); + ASSERT(bio_op(bio) == REQ_OP_ZONE_APPEND); + + /* Ordered extent not yet created, so we're good */ + ordered = btrfs_lookup_ordered_extent(inode, page_offset(page)); + if (!ordered) + return ret; + + if ((bio->bi_iter.bi_sector << SECTOR_SHIFT) + len > + ordered->disk_bytenr + ordered->disk_num_bytes) + ret = false; + + btrfs_put_ordered_extent(ordered); + + return ret; +} + +static blk_status_t extract_ordered_extent(struct btrfs_inode *inode, + struct bio *bio, loff_t file_offset) +{ + struct btrfs_ordered_extent *ordered; + struct extent_map *em = NULL, *em_new = NULL; + struct extent_map_tree *em_tree = &inode->extent_tree; + u64 start = (u64)bio->bi_iter.bi_sector << SECTOR_SHIFT; + u64 len = bio->bi_iter.bi_size; + u64 end = start + len; + u64 ordered_end; + u64 pre, post; + int ret = 0; + + ordered = btrfs_lookup_ordered_extent(inode, file_offset); + if (WARN_ON_ONCE(!ordered)) + return BLK_STS_IOERR; + + /* No need to split */ + if (ordered->disk_num_bytes == len) + goto out; + + /* We cannot split once end_bio'd ordered extent */ + if (WARN_ON_ONCE(ordered->bytes_left != ordered->disk_num_bytes)) { + ret = -EINVAL; + goto out; + } + + /* We cannot split a compressed ordered extent */ + if (WARN_ON_ONCE(ordered->disk_num_bytes != ordered->num_bytes)) { + ret = -EINVAL; + goto out; + } + + ordered_end = ordered->disk_bytenr + ordered->disk_num_bytes; + /* bio must be in one ordered extent */ + if (WARN_ON_ONCE(start < ordered->disk_bytenr || end > ordered_end)) { + ret = -EINVAL; + goto out; + } + + /* Checksum list should be empty */ + if (WARN_ON_ONCE(!list_empty(&ordered->list))) { + ret = -EINVAL; + goto out; + } + + pre = start - ordered->disk_bytenr; + post = ordered_end - end; + + ret = btrfs_split_ordered_extent(ordered, pre, post); + if (ret) + goto out; + + read_lock(&em_tree->lock); + em = lookup_extent_mapping(em_tree, ordered->file_offset, len); + if (!em) { + read_unlock(&em_tree->lock); + ret = -EIO; + goto out; + } + read_unlock(&em_tree->lock); + + ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)); + /* + * We cannot reuse em_new here but have to create a new one, as + * unpin_extent_cache() expects the start of the extent map to be the + * logical offset of the file, which does not hold true anymore after + * splitting. + */ + em_new = create_io_em(inode, em->start + pre, len, + em->start + pre, em->block_start + pre, len, + len, len, BTRFS_COMPRESS_NONE, + BTRFS_ORDERED_REGULAR); + if (IS_ERR(em_new)) { + ret = PTR_ERR(em_new); + goto out; + } + free_extent_map(em_new); + +out: + free_extent_map(em); + btrfs_put_ordered_extent(ordered); + + return errno_to_blk_status(ret); +} + /* * extent_io.c submission hook. This does the right thing for csum calculation * on write, or reading the csums from the tree before a read. @@ -2252,7 +2394,16 @@ blk_status_t btrfs_submit_data_bio(struct inode *inode, struct bio *bio, if (btrfs_is_free_space_inode(BTRFS_I(inode))) metadata = BTRFS_WQ_ENDIO_FREE_SPACE; - if (bio_op(bio) != REQ_OP_WRITE) { + if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + struct page *page = bio_first_bvec_all(bio)->bv_page; + loff_t file_offset = page_offset(page); + + ret = extract_ordered_extent(BTRFS_I(inode), bio, file_offset); + if (ret) + goto out; + } + + if (btrfs_op(bio) != BTRFS_MAP_WRITE) { ret = btrfs_bio_wq_end_io(fs_info, bio, metadata); if (ret) goto out; @@ -2754,6 +2905,9 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) goto out; } + if (ordered_extent->disk) + btrfs_rewrite_logical_zoned(ordered_extent); + btrfs_free_io_failure_record(inode, start, end); if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered_extent->flags)) { @@ -3103,14 +3257,16 @@ void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info) } /** - * btrfs_wait_on_delayed_iputs - wait on the delayed iputs to be done running - * @fs_info - the fs_info for this fs - * @return - EINTR if we were killed, 0 if nothing's pending + * Wait for flushing all delayed iputs + * + * @fs_info: the filesystem * * This will wait on any delayed iputs that are currently running with KILLABLE * set. Once they are all done running we will return, unless we are killed in * which case we return EINTR. This helps in user operations like fallocate etc * that might get blocked on the iputs. + * + * Return EINTR if we were killed, 0 if nothing's pending */ int btrfs_wait_on_delayed_iputs(struct btrfs_fs_info *fs_info) { @@ -4720,6 +4876,9 @@ again: ret = -ENOMEM; goto out; } + ret = set_page_extent_mapped(page); + if (ret < 0) + goto out_unlock; if (!PageUptodate(page)) { ret = btrfs_readpage(NULL, page); @@ -4737,7 +4896,6 @@ again: wait_on_page_writeback(page); lock_extent_bits(io_tree, block_start, block_end, &cached_state); - set_page_extent_mapped(page); ordered = btrfs_lookup_ordered_extent(inode, block_start); if (ordered) { @@ -5011,6 +5169,15 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) btrfs_drew_write_unlock(&root->snapshot_lock); btrfs_end_transaction(trans); } else { + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + + if (btrfs_is_zoned(fs_info)) { + ret = btrfs_wait_ordered_range(inode, + ALIGN(newsize, fs_info->sectorsize), + (u64)-1); + if (ret) + return ret; + } /* * We're truncating a file that used to have good data down to @@ -6371,7 +6538,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry, if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_objectid(root, &objectid); + err = btrfs_get_free_objectid(root, &objectid); if (err) goto out_unlock; @@ -6435,7 +6602,7 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry, if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_objectid(root, &objectid); + err = btrfs_get_free_objectid(root, &objectid); if (err) goto out_unlock; @@ -6579,7 +6746,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_objectid(root, &objectid); + err = btrfs_get_free_objectid(root, &objectid); if (err) goto out_fail; @@ -7103,9 +7270,6 @@ static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode, * @strict: if true, omit optimizations that might force us into unnecessary * cow. e.g., don't trust generation number. * - * This function will flush ordered extents in the range to ensure proper - * nocow checks for (nowait == false) case. - * * Return: * >0 and update @len if we can do nocow write * 0 if we can't do nocow write @@ -7613,6 +7777,9 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, iomap->bdev = fs_info->fs_devices->latest_bdev; iomap->length = len; + if (write && btrfs_use_zone_append(BTRFS_I(inode), em)) + iomap->flags |= IOMAP_F_ZONE_APPEND; + free_extent_map(em); return 0; @@ -7682,7 +7849,7 @@ static void btrfs_dio_private_put(struct btrfs_dio_private *dip) if (!refcount_dec_and_test(&dip->refs)) return; - if (bio_op(dip->dio_bio) == REQ_OP_WRITE) { + if (btrfs_op(dip->dio_bio) == BTRFS_MAP_WRITE) { __endio_write_update_ordered(BTRFS_I(dip->inode), dip->logical_offset, dip->bytes, @@ -7797,10 +7964,8 @@ static void __endio_write_update_ordered(struct btrfs_inode *inode, NULL); btrfs_queue_work(wq, &ordered->work); } - /* - * If btrfs_dec_test_ordered_pending does not find any ordered - * extent in the range, we can exit. - */ + + /* No ordered extent found in the range, exit */ if (ordered_offset == last_offset) return; /* @@ -7841,6 +8006,8 @@ static void btrfs_end_dio_bio(struct bio *bio) if (err) dip->dio_bio->bi_status = err; + btrfs_record_physical_zoned(dip->inode, dip->logical_offset, bio); + bio_put(bio); btrfs_dio_private_put(dip); } @@ -7850,7 +8017,7 @@ static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio, { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_dio_private *dip = bio->bi_private; - bool write = bio_op(bio) == REQ_OP_WRITE; + bool write = btrfs_op(bio) == BTRFS_MAP_WRITE; blk_status_t ret; /* Check btrfs_submit_bio_hook() for rules about async submit. */ @@ -7900,7 +8067,7 @@ static struct btrfs_dio_private *btrfs_create_dio_private(struct bio *dio_bio, struct inode *inode, loff_t file_offset) { - const bool write = (bio_op(dio_bio) == REQ_OP_WRITE); + const bool write = (btrfs_op(dio_bio) == BTRFS_MAP_WRITE); const bool csum = !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM); size_t dip_size; struct btrfs_dio_private *dip; @@ -7930,7 +8097,7 @@ static struct btrfs_dio_private *btrfs_create_dio_private(struct bio *dio_bio, static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap, struct bio *dio_bio, loff_t file_offset) { - const bool write = (bio_op(dio_bio) == REQ_OP_WRITE); + const bool write = (btrfs_op(dio_bio) == BTRFS_MAP_WRITE); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); const bool raid56 = (btrfs_data_alloc_profile(fs_info) & BTRFS_BLOCK_GROUP_RAID56_MASK); @@ -7941,10 +8108,12 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap, u64 submit_len; int clone_offset = 0; int clone_len; + u64 logical; int ret; blk_status_t status; struct btrfs_io_geometry geom; struct btrfs_dio_data *dio_data = iomap->private; + struct extent_map *em = NULL; dip = btrfs_create_dio_private(dio_bio, inode, file_offset); if (!dip) { @@ -7973,12 +8142,18 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap, submit_len = dio_bio->bi_iter.bi_size; do { - ret = btrfs_get_io_geometry(fs_info, btrfs_op(dio_bio), - start_sector << 9, submit_len, - &geom); + logical = start_sector << 9; + em = btrfs_get_chunk_map(fs_info, logical, submit_len); + if (IS_ERR(em)) { + status = errno_to_blk_status(PTR_ERR(em)); + em = NULL; + goto out_err_em; + } + ret = btrfs_get_io_geometry(fs_info, em, btrfs_op(dio_bio), + logical, submit_len, &geom); if (ret) { status = errno_to_blk_status(ret); - goto out_err; + goto out_err_em; } ASSERT(geom.len <= INT_MAX); @@ -7993,6 +8168,19 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap, bio->bi_end_io = btrfs_end_dio_bio; btrfs_io_bio(bio)->logical = file_offset; + WARN_ON_ONCE(write && btrfs_is_zoned(fs_info) && + fs_info->max_zone_append_size && + bio_op(bio) != REQ_OP_ZONE_APPEND); + + if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + status = extract_ordered_extent(BTRFS_I(inode), bio, + file_offset); + if (status) { + bio_put(bio); + goto out_err; + } + } + ASSERT(submit_len >= clone_len); submit_len -= clone_len; @@ -8023,19 +8211,24 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap, bio_put(bio); if (submit_len > 0) refcount_dec(&dip->refs); - goto out_err; + goto out_err_em; } dio_data->submitted += clone_len; clone_offset += clone_len; start_sector += clone_len >> 9; file_offset += clone_len; + + free_extent_map(em); } while (submit_len > 0); return BLK_QC_T_NONE; +out_err_em: + free_extent_map(em); out_err: dip->dio_bio->bi_status = status; btrfs_dio_private_put(dip); + return BLK_QC_T_NONE; } @@ -8117,7 +8310,7 @@ static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags) { int ret = try_release_extent_mapping(page, gfp_flags); if (ret == 1) - detach_page_private(page); + clear_page_extent_mapped(page); return ret; } @@ -8186,8 +8379,9 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset, if (!inode_evicting) lock_extent_bits(tree, page_start, page_end, &cached_state); -again: + start = page_start; +again: ordered = btrfs_lookup_ordered_range(inode, start, page_end - start + 1); if (ordered) { found_ordered = true; @@ -8276,7 +8470,7 @@ again: } ClearPageChecked(page); - detach_page_private(page); + clear_page_extent_mapped(page); } /* @@ -8355,7 +8549,12 @@ again: wait_on_page_writeback(page); lock_extent_bits(io_tree, page_start, page_end, &cached_state); - set_page_extent_mapped(page); + ret2 = set_page_extent_mapped(page); + if (ret2 < 0) { + ret = vmf_error(ret2); + unlock_extent_cached(io_tree, page_start, page_end, &cached_state); + goto out_unlock; + } /* * we can't set the delalloc bits if there are pending ordered @@ -8592,15 +8791,18 @@ out: */ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans, struct btrfs_root *new_root, - struct btrfs_root *parent_root, - u64 new_dirid) + struct btrfs_root *parent_root) { struct inode *inode; int err; u64 index = 0; + u64 ino; - inode = btrfs_new_inode(trans, new_root, NULL, "..", 2, - new_dirid, new_dirid, + err = btrfs_get_free_objectid(new_root, &ino); + if (err < 0) + return err; + + inode = btrfs_new_inode(trans, new_root, NULL, "..", 2, ino, ino, S_IFDIR | (~current_umask() & S_IRWXUGO), &index); if (IS_ERR(inode)) @@ -9079,7 +9281,7 @@ static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans, u64 objectid; u64 index; - ret = btrfs_find_free_objectid(root, &objectid); + ret = btrfs_get_free_objectid(root, &objectid); if (ret) return ret; @@ -9486,11 +9688,11 @@ int btrfs_start_delalloc_snapshot(struct btrfs_root *root) return start_delalloc_inodes(root, &wbc, true, false); } -int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr, +int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr, bool in_reclaim_context) { struct writeback_control wbc = { - .nr_to_write = (nr == U64_MAX) ? LONG_MAX : (unsigned long)nr, + .nr_to_write = nr, .sync_mode = WB_SYNC_NONE, .range_start = 0, .range_end = LLONG_MAX, @@ -9507,12 +9709,12 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr, mutex_lock(&fs_info->delalloc_root_mutex); spin_lock(&fs_info->delalloc_root_lock); list_splice_init(&fs_info->delalloc_roots, &splice); - while (!list_empty(&splice) && nr) { + while (!list_empty(&splice)) { /* * Reset nr_to_write here so we know that we're doing a full * flush. */ - if (nr == U64_MAX) + if (nr == LONG_MAX) wbc.nr_to_write = LONG_MAX; root = list_first_entry(&splice, struct btrfs_root, @@ -9575,7 +9777,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_objectid(root, &objectid); + err = btrfs_get_free_objectid(root, &objectid); if (err) goto out_unlock; @@ -9909,7 +10111,7 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) if (IS_ERR(trans)) return PTR_ERR(trans); - ret = btrfs_find_free_objectid(root, &objectid); + ret = btrfs_get_free_objectid(root, &objectid); if (ret) goto out; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index dde49a791f3e..a8c60d46d19c 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -527,6 +527,14 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info, if (!capable(CAP_SYS_ADMIN)) return -EPERM; + /* + * btrfs_trim_block_group() depends on space cache, which is not + * available in zoned filesystem. So, disallow fitrim on a zoned + * filesystem for now. + */ + if (btrfs_is_zoned(fs_info)) + return -EOPNOTSUPP; + /* * If the fs is mounted with nologreplay, which requires it to be * mounted in RO mode as well, we can not allow discard on free space @@ -606,14 +614,13 @@ static noinline int create_subvol(struct inode *dir, int err; dev_t anon_dev = 0; u64 objectid; - u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID; u64 index = 0; root_item = kzalloc(sizeof(*root_item), GFP_KERNEL); if (!root_item) return -ENOMEM; - ret = btrfs_find_free_objectid(fs_info->tree_root, &objectid); + ret = btrfs_get_free_objectid(fs_info->tree_root, &objectid); if (ret) goto fail_free; @@ -693,7 +700,7 @@ static noinline int create_subvol(struct inode *dir, free_extent_buffer(leaf); leaf = NULL; - btrfs_set_root_dirid(root_item, new_dirid); + btrfs_set_root_dirid(root_item, BTRFS_FIRST_FREE_OBJECTID); key.objectid = objectid; key.offset = 0; @@ -716,7 +723,7 @@ static noinline int create_subvol(struct inode *dir, btrfs_record_root_in_trans(trans, new_root); - ret = btrfs_create_subvol_root(trans, new_root, root, new_dirid); + ret = btrfs_create_subvol_root(trans, new_root, root); btrfs_put_root(new_root); if (ret) { /* We potentially lose an unused inode item here */ @@ -724,10 +731,6 @@ static noinline int create_subvol(struct inode *dir, goto fail; } - mutex_lock(&new_root->objectid_mutex); - new_root->highest_objectid = new_dirid; - mutex_unlock(&new_root->objectid_mutex); - /* * insert the directory item */ @@ -1319,6 +1322,13 @@ again: if (!page) break; + ret = set_page_extent_mapped(page); + if (ret < 0) { + unlock_page(page); + put_page(page); + break; + } + page_start = page_offset(page); page_end = page_start + PAGE_SIZE - 1; while (1) { @@ -1440,7 +1450,6 @@ again: for (i = 0; i < i_done; i++) { clear_page_dirty_for_io(pages[i]); ClearPageChecked(pages[i]); - set_page_extent_mapped(pages[i]); set_page_dirty(pages[i]); unlock_page(pages[i]); put_page(pages[i]); @@ -4951,7 +4960,7 @@ long btrfs_ioctl(struct file *file, unsigned int case BTRFS_IOC_SYNC: { int ret; - ret = btrfs_start_delalloc_roots(fs_info, U64_MAX, false); + ret = btrfs_start_delalloc_roots(fs_info, LONG_MAX, false); if (ret) return ret; ret = btrfs_sync_fs(inode->i_sb, 1); diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 79d366a36223..985a21558437 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -199,14 +199,21 @@ static int __btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset entry->compress_type = compress_type; entry->truncated_len = (u64)-1; entry->qgroup_rsv = ret; - if (type != BTRFS_ORDERED_IO_DONE && type != BTRFS_ORDERED_COMPLETE) - set_bit(type, &entry->flags); + entry->physical = (u64)-1; + entry->disk = NULL; + entry->partno = (u8)-1; - if (dio) { - percpu_counter_add_batch(&fs_info->dio_bytes, num_bytes, - fs_info->delalloc_batch); + ASSERT(type == BTRFS_ORDERED_REGULAR || + type == BTRFS_ORDERED_NOCOW || + type == BTRFS_ORDERED_PREALLOC || + type == BTRFS_ORDERED_COMPRESSED); + set_bit(type, &entry->flags); + + percpu_counter_add_batch(&fs_info->ordered_bytes, num_bytes, + fs_info->delalloc_batch); + + if (dio) set_bit(BTRFS_ORDERED_DIRECT, &entry->flags); - } /* one ref for the tree */ refcount_set(&entry->refs, 1); @@ -256,6 +263,9 @@ int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset, u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes, int type) { + ASSERT(type == BTRFS_ORDERED_REGULAR || + type == BTRFS_ORDERED_NOCOW || + type == BTRFS_ORDERED_PREALLOC); return __btrfs_add_ordered_extent(inode, file_offset, disk_bytenr, num_bytes, disk_num_bytes, type, 0, BTRFS_COMPRESS_NONE); @@ -265,6 +275,9 @@ int btrfs_add_ordered_extent_dio(struct btrfs_inode *inode, u64 file_offset, u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes, int type) { + ASSERT(type == BTRFS_ORDERED_REGULAR || + type == BTRFS_ORDERED_NOCOW || + type == BTRFS_ORDERED_PREALLOC); return __btrfs_add_ordered_extent(inode, file_offset, disk_bytenr, num_bytes, disk_num_bytes, type, 1, BTRFS_COMPRESS_NONE); @@ -272,11 +285,12 @@ int btrfs_add_ordered_extent_dio(struct btrfs_inode *inode, u64 file_offset, int btrfs_add_ordered_extent_compress(struct btrfs_inode *inode, u64 file_offset, u64 disk_bytenr, u64 num_bytes, - u64 disk_num_bytes, int type, - int compress_type) + u64 disk_num_bytes, int compress_type) { + ASSERT(compress_type != BTRFS_COMPRESS_NONE); return __btrfs_add_ordered_extent(inode, file_offset, disk_bytenr, - num_bytes, disk_num_bytes, type, 0, + num_bytes, disk_num_bytes, + BTRFS_ORDERED_COMPRESSED, 0, compress_type); } @@ -297,26 +311,33 @@ void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry, } /* - * this is used to account for finished IO across a given range - * of the file. The IO may span ordered extents. If - * a given ordered_extent is completely done, 1 is returned, otherwise - * 0. + * Finish IO for one ordered extent across a given range. The range can + * contain several ordered extents. * - * test_and_set_bit on a flag in the struct btrfs_ordered_extent is used - * to make sure this function only returns 1 once for a given ordered extent. + * @found_ret: Return the finished ordered extent + * @file_offset: File offset for the finished IO + * Will also be updated to one byte past the range that is + * recordered as finished. This allows caller to walk forward. + * @io_size: Length of the finish IO range + * @uptodate: If the IO finished without problem * - * file_offset is updated to one byte past the range that is recorded as - * complete. This allows you to walk forward in the file. + * Return true if any ordered extent is finished in the range, and update + * @found_ret and @file_offset. + * Return false otherwise. + * + * NOTE: Although The range can cross multiple ordered extents, only one + * ordered extent will be updated during one call. The caller is responsible to + * iterate all ordered extents in the range. */ -int btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode, - struct btrfs_ordered_extent **cached, +bool btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode, + struct btrfs_ordered_extent **finished_ret, u64 *file_offset, u64 io_size, int uptodate) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree; struct rb_node *node; struct btrfs_ordered_extent *entry = NULL; - int ret; + bool finished = false; unsigned long flags; u64 dec_end; u64 dec_start; @@ -324,16 +345,12 @@ int btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode, spin_lock_irqsave(&tree->lock, flags); node = tree_search(tree, *file_offset); - if (!node) { - ret = 1; + if (!node) goto out; - } entry = rb_entry(node, struct btrfs_ordered_extent, rb_node); - if (!offset_in_entry(entry, *file_offset)) { - ret = 1; + if (!offset_in_entry(entry, *file_offset)) goto out; - } dec_start = max(*file_offset, entry->file_offset); dec_end = min(*file_offset + io_size, @@ -354,39 +371,50 @@ int btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode, set_bit(BTRFS_ORDERED_IOERR, &entry->flags); if (entry->bytes_left == 0) { - ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags); + /* + * Ensure only one caller can set the flag and finished_ret + * accordingly + */ + finished = !test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags); /* test_and_set_bit implies a barrier */ cond_wake_up_nomb(&entry->wait); - } else { - ret = 1; } out: - if (!ret && cached && entry) { - *cached = entry; + if (finished && finished_ret && entry) { + *finished_ret = entry; refcount_inc(&entry->refs); } spin_unlock_irqrestore(&tree->lock, flags); - return ret == 0; + return finished; } /* - * this is used to account for finished IO across a given range - * of the file. The IO should not span ordered extents. If - * a given ordered_extent is completely done, 1 is returned, otherwise - * 0. + * Finish IO for one ordered extent across a given range. The range can only + * contain one ordered extent. * - * test_and_set_bit on a flag in the struct btrfs_ordered_extent is used - * to make sure this function only returns 1 once for a given ordered extent. + * @cached: The cached ordered extent. If not NULL, we can skip the tree + * search and use the ordered extent directly. + * Will be also used to store the finished ordered extent. + * @file_offset: File offset for the finished IO + * @io_size: Length of the finish IO range + * @uptodate: If the IO finishes without problem + * + * Return true if the ordered extent is finished in the range, and update + * @cached. + * Return false otherwise. + * + * NOTE: The range can NOT cross multiple ordered extents. + * Thus caller should ensure the range doesn't cross ordered extents. */ -int btrfs_dec_test_ordered_pending(struct btrfs_inode *inode, - struct btrfs_ordered_extent **cached, - u64 file_offset, u64 io_size, int uptodate) +bool btrfs_dec_test_ordered_pending(struct btrfs_inode *inode, + struct btrfs_ordered_extent **cached, + u64 file_offset, u64 io_size, int uptodate) { struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree; struct rb_node *node; struct btrfs_ordered_extent *entry = NULL; unsigned long flags; - int ret; + bool finished = false; spin_lock_irqsave(&tree->lock, flags); if (cached && *cached) { @@ -395,41 +423,39 @@ int btrfs_dec_test_ordered_pending(struct btrfs_inode *inode, } node = tree_search(tree, file_offset); - if (!node) { - ret = 1; + if (!node) goto out; - } entry = rb_entry(node, struct btrfs_ordered_extent, rb_node); have_entry: - if (!offset_in_entry(entry, file_offset)) { - ret = 1; + if (!offset_in_entry(entry, file_offset)) goto out; - } - if (io_size > entry->bytes_left) { + if (io_size > entry->bytes_left) btrfs_crit(inode->root->fs_info, "bad ordered accounting left %llu size %llu", entry->bytes_left, io_size); - } + entry->bytes_left -= io_size; if (!uptodate) set_bit(BTRFS_ORDERED_IOERR, &entry->flags); if (entry->bytes_left == 0) { - ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags); + /* + * Ensure only one caller can set the flag and finished_ret + * accordingly + */ + finished = !test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags); /* test_and_set_bit implies a barrier */ cond_wake_up_nomb(&entry->wait); - } else { - ret = 1; } out: - if (!ret && cached && entry) { + if (finished && cached && entry) { *cached = entry; refcount_inc(&entry->refs); } spin_unlock_irqrestore(&tree->lock, flags); - return ret == 0; + return finished; } /* @@ -480,9 +506,8 @@ void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode, btrfs_delalloc_release_metadata(btrfs_inode, entry->num_bytes, false); - if (test_bit(BTRFS_ORDERED_DIRECT, &entry->flags)) - percpu_counter_add_batch(&fs_info->dio_bytes, -entry->num_bytes, - fs_info->delalloc_batch); + percpu_counter_add_batch(&fs_info->ordered_bytes, -entry->num_bytes, + fs_info->delalloc_batch); tree = &btrfs_inode->ordered_tree; spin_lock_irq(&tree->lock); @@ -745,9 +770,10 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct btrfs_inode *ino struct btrfs_ordered_inode_tree *tree; struct rb_node *node; struct btrfs_ordered_extent *entry = NULL; + unsigned long flags; tree = &inode->ordered_tree; - spin_lock_irq(&tree->lock); + spin_lock_irqsave(&tree->lock, flags); node = tree_search(tree, file_offset); if (!node) goto out; @@ -758,7 +784,7 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct btrfs_inode *ino if (entry) refcount_inc(&entry->refs); out: - spin_unlock_irq(&tree->lock); + spin_unlock_irqrestore(&tree->lock, flags); return entry; } @@ -898,6 +924,84 @@ void btrfs_lock_and_flush_ordered_range(struct btrfs_inode *inode, u64 start, } } +static int clone_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pos, + u64 len) +{ + struct inode *inode = ordered->inode; + u64 file_offset = ordered->file_offset + pos; + u64 disk_bytenr = ordered->disk_bytenr + pos; + u64 num_bytes = len; + u64 disk_num_bytes = len; + int type; + unsigned long flags_masked = ordered->flags & ~(1 << BTRFS_ORDERED_DIRECT); + int compress_type = ordered->compress_type; + unsigned long weight; + int ret; + + weight = hweight_long(flags_masked); + WARN_ON_ONCE(weight > 1); + if (!weight) + type = 0; + else + type = __ffs(flags_masked); + + if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered->flags)) { + WARN_ON_ONCE(1); + ret = btrfs_add_ordered_extent_compress(BTRFS_I(inode), + file_offset, disk_bytenr, num_bytes, + disk_num_bytes, compress_type); + } else if (test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) { + ret = btrfs_add_ordered_extent_dio(BTRFS_I(inode), file_offset, + disk_bytenr, num_bytes, disk_num_bytes, type); + } else { + ret = btrfs_add_ordered_extent(BTRFS_I(inode), file_offset, + disk_bytenr, num_bytes, disk_num_bytes, type); + } + + return ret; +} + +int btrfs_split_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pre, + u64 post) +{ + struct inode *inode = ordered->inode; + struct btrfs_ordered_inode_tree *tree = &BTRFS_I(inode)->ordered_tree; + struct rb_node *node; + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + int ret = 0; + + spin_lock_irq(&tree->lock); + /* Remove from tree once */ + node = &ordered->rb_node; + rb_erase(node, &tree->tree); + RB_CLEAR_NODE(node); + if (tree->last == node) + tree->last = NULL; + + ordered->file_offset += pre; + ordered->disk_bytenr += pre; + ordered->num_bytes -= (pre + post); + ordered->disk_num_bytes -= (pre + post); + ordered->bytes_left -= (pre + post); + + /* Re-insert the node */ + node = tree_insert(&tree->tree, ordered->file_offset, &ordered->rb_node); + if (node) + btrfs_panic(fs_info, -EEXIST, + "zoned: inconsistency in ordered tree at offset %llu", + ordered->file_offset); + + spin_unlock_irq(&tree->lock); + + if (pre) + ret = clone_ordered_extent(ordered, 0, pre); + if (post) + ret = clone_ordered_extent(ordered, pre + ordered->disk_num_bytes, + post); + + return ret; +} + int __init ordered_data_init(void) { btrfs_ordered_extent_cache = kmem_cache_create("btrfs_ordered_extent", diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index 0bfa82b58e23..99e0853e4d3b 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -27,7 +27,7 @@ struct btrfs_ordered_sum { }; /* - * bits for the flags field: + * Bits for btrfs_ordered_extent::flags. * * BTRFS_ORDERED_IO_DONE is set when all of the blocks are written. * It is used to make sure metadata is inserted into the tree only once @@ -38,24 +38,36 @@ struct btrfs_ordered_sum { * IO is done and any metadata is inserted into the tree. */ enum { + /* + * Different types for direct io, one and only one of the 4 type can + * be set when creating ordered extent. + * + * REGULAR: For regular non-compressed COW write + * NOCOW: For NOCOW write into existing non-hole extent + * PREALLOC: For NOCOW write into preallocated extent + * COMPRESSED: For compressed COW write + */ + BTRFS_ORDERED_REGULAR, + BTRFS_ORDERED_NOCOW, + BTRFS_ORDERED_PREALLOC, + BTRFS_ORDERED_COMPRESSED, + + /* + * Extra bit for direct io, can only be set for + * REGULAR/NOCOW/PREALLOC. No direct io for compressed extent. + */ + BTRFS_ORDERED_DIRECT, + + /* Extra status bits for ordered extents */ + /* set when all the pages are written */ BTRFS_ORDERED_IO_DONE, /* set when removed from the tree */ BTRFS_ORDERED_COMPLETE, - /* set when we want to write in place */ - BTRFS_ORDERED_NOCOW, - /* writing a zlib compressed extent */ - BTRFS_ORDERED_COMPRESSED, - /* set when writing to preallocated extent */ - BTRFS_ORDERED_PREALLOC, - /* set when we're doing DIO with this extent */ - BTRFS_ORDERED_DIRECT, /* We had an io error when writing this out */ BTRFS_ORDERED_IOERR, /* Set when we have to truncate an extent */ BTRFS_ORDERED_TRUNCATED, - /* Regular IO for COW */ - BTRFS_ORDERED_REGULAR, /* Used during fsync to track already logged extents */ BTRFS_ORDERED_LOGGED, /* We have already logged all the csums of the ordered extent */ @@ -127,6 +139,14 @@ struct btrfs_ordered_extent { struct completion completion; struct btrfs_work flush_work; struct list_head work_list; + + /* + * Used to reverse-map physical address returned from ZONE_APPEND write + * command in a workqueue context + */ + u64 physical; + struct gendisk *disk; + u8 partno; }; /* @@ -152,11 +172,11 @@ btrfs_ordered_inode_tree_init(struct btrfs_ordered_inode_tree *t) void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry); void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode, struct btrfs_ordered_extent *entry); -int btrfs_dec_test_ordered_pending(struct btrfs_inode *inode, - struct btrfs_ordered_extent **cached, - u64 file_offset, u64 io_size, int uptodate); -int btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode, - struct btrfs_ordered_extent **cached, +bool btrfs_dec_test_ordered_pending(struct btrfs_inode *inode, + struct btrfs_ordered_extent **cached, + u64 file_offset, u64 io_size, int uptodate); +bool btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode, + struct btrfs_ordered_extent **finished_ret, u64 *file_offset, u64 io_size, int uptodate); int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset, @@ -167,8 +187,7 @@ int btrfs_add_ordered_extent_dio(struct btrfs_inode *inode, u64 file_offset, u64 disk_num_bytes, int type); int btrfs_add_ordered_extent_compress(struct btrfs_inode *inode, u64 file_offset, u64 disk_bytenr, u64 num_bytes, - u64 disk_num_bytes, int type, - int compress_type); + u64 disk_num_bytes, int compress_type); void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry, struct btrfs_ordered_sum *sum); struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct btrfs_inode *inode, @@ -190,6 +209,8 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr, void btrfs_lock_and_flush_ordered_range(struct btrfs_inode *inode, u64 start, u64 end, struct extent_state **cached_state); +int btrfs_split_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pre, + u64 post); int __init ordered_data_init(void); void __cold ordered_data_exit(void); diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 93fbf87bdc8d..5394641541f7 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -233,8 +233,7 @@ int btrfs_alloc_stripe_hash_table(struct btrfs_fs_info *info) } x = cmpxchg(&info->stripe_hash_table, NULL, table); - if (x) - kvfree(x); + kvfree(x); return 0; } diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index 4b9b6c52a83b..2b490becbe67 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -495,14 +495,15 @@ static int process_extent_item(struct btrfs_fs_info *fs_info, } static int process_leaf(struct btrfs_root *root, - struct btrfs_path *path, u64 *bytenr, u64 *num_bytes) + struct btrfs_path *path, u64 *bytenr, u64 *num_bytes, + int *tree_block_level) { struct btrfs_fs_info *fs_info = root->fs_info; struct extent_buffer *leaf = path->nodes[0]; struct btrfs_extent_data_ref *dref; struct btrfs_shared_data_ref *sref; u32 count; - int i = 0, tree_block_level = 0, ret = 0; + int i = 0, ret = 0; struct btrfs_key key; int nritems = btrfs_header_nritems(leaf); @@ -515,15 +516,15 @@ static int process_leaf(struct btrfs_root *root, case BTRFS_METADATA_ITEM_KEY: *bytenr = key.objectid; ret = process_extent_item(fs_info, path, &key, i, - &tree_block_level); + tree_block_level); break; case BTRFS_TREE_BLOCK_REF_KEY: ret = add_tree_block(fs_info, key.offset, 0, - key.objectid, tree_block_level); + key.objectid, *tree_block_level); break; case BTRFS_SHARED_BLOCK_REF_KEY: ret = add_tree_block(fs_info, 0, key.offset, - key.objectid, tree_block_level); + key.objectid, *tree_block_level); break; case BTRFS_EXTENT_DATA_REF_KEY: dref = btrfs_item_ptr(leaf, i, @@ -549,7 +550,8 @@ static int process_leaf(struct btrfs_root *root, /* Walk down to the leaf from the given level */ static int walk_down_tree(struct btrfs_root *root, struct btrfs_path *path, - int level, u64 *bytenr, u64 *num_bytes) + int level, u64 *bytenr, u64 *num_bytes, + int *tree_block_level) { struct extent_buffer *eb; int ret = 0; @@ -565,7 +567,8 @@ static int walk_down_tree(struct btrfs_root *root, struct btrfs_path *path, path->slots[level-1] = 0; path->locks[level-1] = BTRFS_READ_LOCK; } else { - ret = process_leaf(root, path, bytenr, num_bytes); + ret = process_leaf(root, path, bytenr, num_bytes, + tree_block_level); if (ret) break; } @@ -666,18 +669,18 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, u64 bytenr = generic_ref->bytenr; u64 num_bytes = generic_ref->len; u64 parent = generic_ref->parent; - u64 ref_root; - u64 owner; - u64 offset; + u64 ref_root = 0; + u64 owner = 0; + u64 offset = 0; if (!btrfs_test_opt(fs_info, REF_VERIFY)) return 0; if (generic_ref->type == BTRFS_REF_METADATA) { - ref_root = generic_ref->tree_ref.root; + if (!parent) + ref_root = generic_ref->tree_ref.root; owner = generic_ref->tree_ref.level; - offset = 0; - } else { + } else if (!parent) { ref_root = generic_ref->data_ref.ref_root; owner = generic_ref->data_ref.ino; offset = generic_ref->data_ref.offset; @@ -693,13 +696,10 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, goto out; } - if (parent) { - ref->parent = parent; - } else { - ref->root_objectid = ref_root; - ref->owner = owner; - ref->offset = offset; - } + ref->parent = parent; + ref->owner = owner; + ref->root_objectid = ref_root; + ref->offset = offset; ref->num_refs = (action == BTRFS_DROP_DELAYED_REF) ? -1 : 1; memcpy(&ra->ref, ref, sizeof(struct ref_entry)); @@ -974,6 +974,7 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info) { struct btrfs_path *path; struct extent_buffer *eb; + int tree_block_level = 0; u64 bytenr = 0, num_bytes = 0; int ret, level; @@ -998,7 +999,7 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info) * different leaf from the original extent item. */ ret = walk_down_tree(fs_info->extent_root, path, level, - &bytenr, &num_bytes); + &bytenr, &num_bytes, &tree_block_level); if (ret) break; ret = walk_up_tree(path, &level); diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c index b03e7891394e..b24396cf2f99 100644 --- a/fs/btrfs/reflink.c +++ b/fs/btrfs/reflink.c @@ -81,7 +81,10 @@ static int copy_inline_to_page(struct btrfs_inode *inode, goto out_unlock; } - set_page_extent_mapped(page); + ret = set_page_extent_mapped(page); + if (ret < 0) + goto out_unlock; + clear_extent_bit(&inode->io_tree, file_offset, range_end, EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, NULL); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index df63ef64c5c0..232d5da7b7be 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -97,6 +97,7 @@ struct tree_block { struct rb_node rb_node; u64 bytenr; }; /* Use rb_simple_node for search/insert */ + u64 owner; struct btrfs_key key; unsigned int level:8; unsigned int key_ready:1; @@ -668,9 +669,7 @@ static void __del_reloc_root(struct btrfs_root *root) RB_CLEAR_NODE(&node->rb_node); } spin_unlock(&rc->reloc_root_tree.lock); - if (!node) - return; - BUG_ON((struct btrfs_root *)node->data != root); + ASSERT(!node || (struct btrfs_root *)node->data == root); } /* @@ -2393,8 +2392,8 @@ static int get_tree_block_key(struct btrfs_fs_info *fs_info, { struct extent_buffer *eb; - eb = read_tree_block(fs_info, block->bytenr, 0, block->key.offset, - block->level, NULL); + eb = read_tree_block(fs_info, block->bytenr, block->owner, + block->key.offset, block->level, NULL); if (IS_ERR(eb)) { return PTR_ERR(eb); } else if (!extent_buffer_uptodate(eb)) { @@ -2493,7 +2492,8 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans, /* Kick in readahead for tree blocks with missing keys */ rbtree_postorder_for_each_entry_safe(block, next, blocks, rb_node) { if (!block->key_ready) - btrfs_readahead_tree_block(fs_info, block->bytenr, 0, 0, + btrfs_readahead_tree_block(fs_info, block->bytenr, + block->owner, 0, block->level); } @@ -2553,6 +2553,31 @@ static noinline_for_stack int prealloc_file_extent_cluster( if (ret) return ret; + /* + * On a zoned filesystem, we cannot preallocate the file region. + * Instead, we dirty and fiemap_write the region. + */ + if (btrfs_is_zoned(inode->root->fs_info)) { + struct btrfs_root *root = inode->root; + struct btrfs_trans_handle *trans; + + end = cluster->end - offset + 1; + trans = btrfs_start_transaction(root, 1); + if (IS_ERR(trans)) + return PTR_ERR(trans); + + inode->vfs_inode.i_ctime = current_time(&inode->vfs_inode); + i_size_write(&inode->vfs_inode, end); + ret = btrfs_update_inode(trans, root, inode); + if (ret) { + btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); + return ret; + } + + return btrfs_end_transaction(trans); + } + inode_lock(&inode->vfs_inode); for (nr = 0; nr < cluster->nr; nr++) { start = cluster->boundary[nr] - offset; @@ -2615,7 +2640,7 @@ int setup_extent_mapping(struct inode *inode, u64 start, u64 end, /* * Allow error injection to test balance cancellation */ -int btrfs_should_cancel_balance(struct btrfs_fs_info *fs_info) +noinline int btrfs_should_cancel_balance(struct btrfs_fs_info *fs_info) { return atomic_read(&fs_info->balance_cancel_req) || fatal_signal_pending(current); @@ -2679,6 +2704,15 @@ static int relocate_file_extent_cluster(struct inode *inode, goto out; } } + ret = set_page_extent_mapped(page); + if (ret < 0) { + btrfs_delalloc_release_metadata(BTRFS_I(inode), + PAGE_SIZE, true); + btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE); + unlock_page(page); + put_page(page); + goto out; + } if (PageReadahead(page)) { page_cache_async_readahead(inode->i_mapping, @@ -2706,8 +2740,6 @@ static int relocate_file_extent_cluster(struct inode *inode, lock_extent(&BTRFS_I(inode)->io_tree, page_start, page_end); - set_page_extent_mapped(page); - if (nr < cluster->nr && page_start + offset == cluster->boundary[nr]) { set_extent_bits(&BTRFS_I(inode)->io_tree, @@ -2749,6 +2781,8 @@ static int relocate_file_extent_cluster(struct inode *inode, } } WARN_ON(nr != cluster->nr); + if (btrfs_is_zoned(fs_info) && !ret) + ret = btrfs_wait_ordered_range(inode, 0, (u64)-1); out: kfree(ra); return ret; @@ -2801,21 +2835,58 @@ static int add_tree_block(struct reloc_control *rc, u32 item_size; int level = -1; u64 generation; + u64 owner = 0; eb = path->nodes[0]; item_size = btrfs_item_size_nr(eb, path->slots[0]); if (extent_key->type == BTRFS_METADATA_ITEM_KEY || item_size >= sizeof(*ei) + sizeof(*bi)) { + unsigned long ptr = 0, end; + ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item); + end = (unsigned long)ei + item_size; if (extent_key->type == BTRFS_EXTENT_ITEM_KEY) { bi = (struct btrfs_tree_block_info *)(ei + 1); level = btrfs_tree_block_level(eb, bi); + ptr = (unsigned long)(bi + 1); } else { level = (int)extent_key->offset; + ptr = (unsigned long)(ei + 1); } generation = btrfs_extent_generation(eb, ei); + + /* + * We're reading random blocks without knowing their owner ahead + * of time. This is ok most of the time, as all reloc roots and + * fs roots have the same lock type. However normal trees do + * not, and the only way to know ahead of time is to read the + * inline ref offset. We know it's an fs root if + * + * 1. There's more than one ref. + * 2. There's a SHARED_DATA_REF_KEY set. + * 3. FULL_BACKREF is set on the flags. + * + * Otherwise it's safe to assume that the ref offset == the + * owner of this block, so we can use that when calling + * read_tree_block. + */ + if (btrfs_extent_refs(eb, ei) == 1 && + !(btrfs_extent_flags(eb, ei) & + BTRFS_BLOCK_FLAG_FULL_BACKREF) && + ptr < end) { + struct btrfs_extent_inline_ref *iref; + int type; + + iref = (struct btrfs_extent_inline_ref *)ptr; + type = btrfs_get_extent_inline_ref_type(eb, iref, + BTRFS_REF_TYPE_BLOCK); + if (type == BTRFS_REF_TYPE_INVALID) + return -EINVAL; + if (type == BTRFS_TREE_BLOCK_REF_KEY) + owner = btrfs_extent_inline_ref_offset(eb, iref); + } } else if (unlikely(item_size == sizeof(struct btrfs_extent_item_v0))) { btrfs_print_v0_err(eb->fs_info); btrfs_handle_fs_error(eb->fs_info, -EINVAL, NULL); @@ -2837,6 +2908,7 @@ static int add_tree_block(struct reloc_control *rc, block->key.offset = generation; block->level = level; block->key_ready = 0; + block->owner = owner; rb_node = rb_simple_insert(blocks, block->bytenr, &block->rb_node); if (rb_node) @@ -3389,8 +3461,12 @@ static int __insert_orphan_inode(struct btrfs_trans_handle *trans, struct btrfs_path *path; struct btrfs_inode_item *item; struct extent_buffer *leaf; + u64 flags = BTRFS_INODE_NOCOMPRESS | BTRFS_INODE_PREALLOC; int ret; + if (btrfs_is_zoned(trans->fs_info)) + flags &= ~BTRFS_INODE_PREALLOC; + path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -3405,8 +3481,7 @@ static int __insert_orphan_inode(struct btrfs_trans_handle *trans, btrfs_set_inode_generation(leaf, item, 1); btrfs_set_inode_size(leaf, item, 0); btrfs_set_inode_mode(leaf, item, S_IFREG | 0600); - btrfs_set_inode_flags(leaf, item, BTRFS_INODE_NOCOMPRESS | - BTRFS_INODE_PREALLOC); + btrfs_set_inode_flags(leaf, item, flags); btrfs_mark_buffer_dirty(leaf); out: btrfs_free_path(path); @@ -3434,7 +3509,7 @@ struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info, return ERR_CAST(trans); } - err = btrfs_find_free_objectid(root, &objectid); + err = btrfs_get_free_objectid(root, &objectid); if (err) goto out; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 5f4f88a4d2c8..310fce00fcda 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -166,6 +166,7 @@ struct scrub_ctx { int pages_per_rd_bio; int is_dev_replace; + u64 write_pointer; struct scrub_bio *wr_curr_bio; struct mutex wr_lock; @@ -856,6 +857,9 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) have_csum = sblock_to_check->pagev[0]->have_csum; dev = sblock_to_check->pagev[0]->dev; + if (btrfs_is_zoned(fs_info) && !sctx->is_dev_replace) + return btrfs_repair_one_zone(fs_info, logical); + /* * We must use GFP_NOFS because the scrub task might be waiting for a * worker task executing this function and in turn a transaction commit @@ -1619,6 +1623,28 @@ static int scrub_write_page_to_dev_replace(struct scrub_block *sblock, return scrub_add_page_to_wr_bio(sblock->sctx, spage); } +static int fill_writer_pointer_gap(struct scrub_ctx *sctx, u64 physical) +{ + int ret = 0; + u64 length; + + if (!btrfs_is_zoned(sctx->fs_info)) + return 0; + + if (!btrfs_dev_is_sequential(sctx->wr_tgtdev, physical)) + return 0; + + if (sctx->write_pointer < physical) { + length = physical - sctx->write_pointer; + + ret = btrfs_zoned_issue_zeroout(sctx->wr_tgtdev, + sctx->write_pointer, length); + if (!ret) + sctx->write_pointer = physical; + } + return ret; +} + static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx, struct scrub_page *spage) { @@ -1641,6 +1667,13 @@ again: if (sbio->page_count == 0) { struct bio *bio; + ret = fill_writer_pointer_gap(sctx, + spage->physical_for_dev_replace); + if (ret) { + mutex_unlock(&sctx->wr_lock); + return ret; + } + sbio->physical = spage->physical_for_dev_replace; sbio->logical = spage->logical; sbio->dev = sctx->wr_tgtdev; @@ -1702,6 +1735,9 @@ static void scrub_wr_submit(struct scrub_ctx *sctx) * doubled the write performance on spinning disks when measured * with Linux 3.5 */ btrfsic_submit_bio(sbio->bio); + + if (btrfs_is_zoned(sctx->fs_info)) + sctx->write_pointer = sbio->physical + sbio->page_count * PAGE_SIZE; } static void scrub_wr_bio_end_io(struct bio *bio) @@ -3025,6 +3061,46 @@ out: return ret < 0 ? ret : 0; } +static void sync_replace_for_zoned(struct scrub_ctx *sctx) +{ + if (!btrfs_is_zoned(sctx->fs_info)) + return; + + sctx->flush_all_writes = true; + scrub_submit(sctx); + mutex_lock(&sctx->wr_lock); + scrub_wr_submit(sctx); + mutex_unlock(&sctx->wr_lock); + + wait_event(sctx->list_wait, atomic_read(&sctx->bios_in_flight) == 0); +} + +static int sync_write_pointer_for_zoned(struct scrub_ctx *sctx, u64 logical, + u64 physical, u64 physical_end) +{ + struct btrfs_fs_info *fs_info = sctx->fs_info; + int ret = 0; + + if (!btrfs_is_zoned(fs_info)) + return 0; + + wait_event(sctx->list_wait, atomic_read(&sctx->bios_in_flight) == 0); + + mutex_lock(&sctx->wr_lock); + if (sctx->write_pointer < physical_end) { + ret = btrfs_sync_zone_write_pointer(sctx->wr_tgtdev, logical, + physical, + sctx->write_pointer); + if (ret) + btrfs_err(fs_info, + "zoned: failed to recover write pointer"); + } + mutex_unlock(&sctx->wr_lock); + btrfs_dev_clear_zone_empty(sctx->wr_tgtdev, physical); + + return ret; +} + static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, struct map_lookup *map, struct btrfs_device *scrub_dev, @@ -3165,6 +3241,14 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, */ blk_start_plug(&plug); + if (sctx->is_dev_replace && + btrfs_dev_is_sequential(sctx->wr_tgtdev, physical)) { + mutex_lock(&sctx->wr_lock); + sctx->write_pointer = physical; + mutex_unlock(&sctx->wr_lock); + sctx->flush_all_writes = true; + } + /* * now find all extents for each stripe and scrub them */ @@ -3353,6 +3437,9 @@ again: if (ret) goto out; + if (sctx->is_dev_replace) + sync_replace_for_zoned(sctx); + if (extent_logical + extent_len < key.objectid + bytes) { if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) { @@ -3420,6 +3507,17 @@ out: blk_finish_plug(&plug); btrfs_free_path(path); btrfs_free_path(ppath); + + if (sctx->is_dev_replace && ret >= 0) { + int ret2; + + ret2 = sync_write_pointer_for_zoned(sctx, base + offset, + map->stripes[num].physical, + physical_end); + if (ret2) + ret = ret2; + } + return ret < 0 ? ret : 0; } @@ -3475,6 +3573,25 @@ out: return ret; } +static int finish_extent_writes_for_zoned(struct btrfs_root *root, + struct btrfs_block_group *cache) +{ + struct btrfs_fs_info *fs_info = cache->fs_info; + struct btrfs_trans_handle *trans; + + if (!btrfs_is_zoned(fs_info)) + return 0; + + btrfs_wait_block_group_reservations(cache); + btrfs_wait_nocow_writers(cache); + btrfs_wait_ordered_roots(fs_info, U64_MAX, cache->start, cache->length); + + trans = btrfs_join_transaction(root); + if (IS_ERR(trans)) + return PTR_ERR(trans); + return btrfs_commit_transaction(trans); +} + static noinline_for_stack int scrub_enumerate_chunks(struct scrub_ctx *sctx, struct btrfs_device *scrub_dev, u64 start, u64 end) @@ -3561,6 +3678,16 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, if (!cache) goto skip; + if (sctx->is_dev_replace && btrfs_is_zoned(fs_info)) { + spin_lock(&cache->lock); + if (!cache->to_copy) { + spin_unlock(&cache->lock); + ro_set = 0; + goto done; + } + spin_unlock(&cache->lock); + } + /* * Make sure that while we are scrubbing the corresponding block * group doesn't get its logical address and its device extents @@ -3619,6 +3746,16 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, * group is not RO. */ ret = btrfs_inc_block_group_ro(cache, sctx->is_dev_replace); + if (!ret && sctx->is_dev_replace) { + ret = finish_extent_writes_for_zoned(root, cache); + if (ret) { + btrfs_dec_block_group_ro(cache); + scrub_pause_off(fs_info); + btrfs_put_block_group(cache); + break; + } + } + if (ret == 0) { ro_set = 1; } else if (ret == -ENOSPC && !sctx->is_dev_replace) { @@ -3692,6 +3829,12 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, scrub_pause_off(fs_info); + if (sctx->is_dev_replace && + !btrfs_finish_block_group_to_copy(dev_replace->srcdev, + cache, found_key.offset)) + ro_set = 0; + +done: down_write(&dev_replace->rwsem); dev_replace->cursor_left = dev_replace->cursor_right; dev_replace->item_needs_writeback = 1; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 78a35374d492..f87878274e9f 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1191,9 +1191,6 @@ struct backref_ctx { /* may be truncated in case it's the last extent in a file */ u64 extent_len; - /* data offset in the file extent item */ - u64 data_offset; - /* Just to check for bugs in backref resolving */ int found_itself; }; @@ -1401,19 +1398,6 @@ static int find_extent_clone(struct send_ctx *sctx, backref_ctx->cur_offset = data_offset; backref_ctx->found_itself = 0; backref_ctx->extent_len = num_bytes; - /* - * For non-compressed extents iterate_extent_inodes() gives us extent - * offsets that already take into account the data offset, but not for - * compressed extents, since the offset is logical and not relative to - * the physical extent locations. We must take this into account to - * avoid sending clone offsets that go beyond the source file's size, - * which would result in the clone ioctl failing with -EINVAL on the - * receiving end. - */ - if (compressed == BTRFS_COMPRESS_NONE) - backref_ctx->data_offset = 0; - else - backref_ctx->data_offset = btrfs_file_extent_offset(eb, fi); /* * The last extent of a file may be too large due to page alignment. @@ -6607,10 +6591,9 @@ static int changed_cb(struct btrfs_path *left_path, struct btrfs_path *right_path, struct btrfs_key *key, enum btrfs_compare_tree_result result, - void *ctx) + struct send_ctx *sctx) { int ret = 0; - struct send_ctx *sctx = ctx; if (result == BTRFS_COMPARE_TREE_SAME) { if (key->type == BTRFS_INODE_REF_KEY || @@ -6815,7 +6798,7 @@ static int tree_compare_item(struct btrfs_path *left_path, * If it detects a change, it aborts immediately. */ static int btrfs_compare_trees(struct btrfs_root *left_root, - struct btrfs_root *right_root, void *ctx) + struct btrfs_root *right_root, struct send_ctx *sctx) { struct btrfs_fs_info *fs_info = left_root->fs_info; int ret; @@ -6967,7 +6950,7 @@ static int btrfs_compare_trees(struct btrfs_root *left_root, ret = changed_cb(left_path, right_path, &right_key, BTRFS_COMPARE_TREE_DELETED, - ctx); + sctx); if (ret < 0) goto out; } @@ -6978,7 +6961,7 @@ static int btrfs_compare_trees(struct btrfs_root *left_root, ret = changed_cb(left_path, right_path, &left_key, BTRFS_COMPARE_TREE_NEW, - ctx); + sctx); if (ret < 0) goto out; } @@ -6992,7 +6975,7 @@ static int btrfs_compare_trees(struct btrfs_root *left_root, ret = changed_cb(left_path, right_path, &left_key, BTRFS_COMPARE_TREE_NEW, - ctx); + sctx); if (ret < 0) goto out; advance_left = ADVANCE; @@ -7000,7 +6983,7 @@ static int btrfs_compare_trees(struct btrfs_root *left_root, ret = changed_cb(left_path, right_path, &right_key, BTRFS_COMPARE_TREE_DELETED, - ctx); + sctx); if (ret < 0) goto out; advance_right = ADVANCE; @@ -7015,7 +6998,7 @@ static int btrfs_compare_trees(struct btrfs_root *left_root, else result = BTRFS_COMPARE_TREE_SAME; ret = changed_cb(left_path, right_path, - &left_key, result, ctx); + &left_key, result, sctx); if (ret < 0) goto out; advance_left = ADVANCE; diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index e8347461c8dd..2da6177f4b0b 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -140,6 +140,12 @@ * be freed, plus any delayed work we may not have gotten rid of in the case * of metadata. * + * FORCE_COMMIT_TRANS + * For use by the preemptive flusher. We use this to bypass the ticketing + * checks in may_commit_transaction, as we have more information about the + * overall state of the system and may want to commit the transaction ahead + * of actual ENOSPC conditions. + * * OVERCOMMIT * * Because we hold so many reservations for metadata we will allow you to @@ -163,6 +169,7 @@ u64 __pure btrfs_space_info_used(struct btrfs_space_info *s_info, ASSERT(s_info); return s_info->bytes_used + s_info->bytes_reserved + s_info->bytes_pinned + s_info->bytes_readonly + + s_info->bytes_zone_unusable + (may_use_included ? s_info->bytes_may_use : 0); } @@ -206,6 +213,7 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags) INIT_LIST_HEAD(&space_info->ro_bgs); INIT_LIST_HEAD(&space_info->tickets); INIT_LIST_HEAD(&space_info->priority_tickets); + space_info->clamp = 1; ret = btrfs_sysfs_add_space_info_type(info, space_info); if (ret) @@ -257,7 +265,7 @@ out: void btrfs_update_space_info(struct btrfs_fs_info *info, u64 flags, u64 total_bytes, u64 bytes_used, - u64 bytes_readonly, + u64 bytes_readonly, u64 bytes_zone_unusable, struct btrfs_space_info **space_info) { struct btrfs_space_info *found; @@ -273,6 +281,7 @@ void btrfs_update_space_info(struct btrfs_fs_info *info, u64 flags, found->bytes_used += bytes_used; found->disk_used += bytes_used * factor; found->bytes_readonly += bytes_readonly; + found->bytes_zone_unusable += bytes_zone_unusable; if (total_bytes > 0) found->full = 0; btrfs_try_granting_tickets(info, found); @@ -422,10 +431,10 @@ static void __btrfs_dump_space_info(struct btrfs_fs_info *fs_info, info->total_bytes - btrfs_space_info_used(info, true), info->full ? "" : "not "); btrfs_info(fs_info, - "space_info total=%llu, used=%llu, pinned=%llu, reserved=%llu, may_use=%llu, readonly=%llu", + "space_info total=%llu, used=%llu, pinned=%llu, reserved=%llu, may_use=%llu, readonly=%llu zone_unusable=%llu", info->total_bytes, info->bytes_used, info->bytes_pinned, info->bytes_reserved, info->bytes_may_use, - info->bytes_readonly); + info->bytes_readonly, info->bytes_zone_unusable); DUMP_BLOCK_RSV(fs_info, global_block_rsv); DUMP_BLOCK_RSV(fs_info, trans_block_rsv); @@ -454,9 +463,10 @@ again: list_for_each_entry(cache, &info->block_groups[index], list) { spin_lock(&cache->lock); btrfs_info(fs_info, - "block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %s", + "block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %llu zone_unusable %s", cache->start, cache->length, cache->used, cache->pinned, - cache->reserved, cache->ro ? "[readonly]" : ""); + cache->reserved, cache->zone_unusable, + cache->ro ? "[readonly]" : ""); spin_unlock(&cache->lock); btrfs_dump_free_space(cache, bytes); } @@ -489,7 +499,7 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info, { struct btrfs_trans_handle *trans; u64 delalloc_bytes; - u64 dio_bytes; + u64 ordered_bytes; u64 items; long time_left; int loops; @@ -513,26 +523,22 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info, delalloc_bytes = percpu_counter_sum_positive( &fs_info->delalloc_bytes); - dio_bytes = percpu_counter_sum_positive(&fs_info->dio_bytes); - if (delalloc_bytes == 0 && dio_bytes == 0) { - if (trans) - return; - if (wait_ordered) - btrfs_wait_ordered_roots(fs_info, items, 0, (u64)-1); + ordered_bytes = percpu_counter_sum_positive(&fs_info->ordered_bytes); + if (delalloc_bytes == 0 && ordered_bytes == 0) return; - } /* * If we are doing more ordered than delalloc we need to just wait on * ordered extents, otherwise we'll waste time trying to flush delalloc * that likely won't give us the space back we need. */ - if (dio_bytes > delalloc_bytes) + if (ordered_bytes > delalloc_bytes) wait_ordered = true; loops = 0; - while ((delalloc_bytes || dio_bytes) && loops < 3) { - u64 nr_pages = min(delalloc_bytes, to_reclaim) >> PAGE_SHIFT; + while ((delalloc_bytes || ordered_bytes) && loops < 3) { + u64 temp = min(delalloc_bytes, to_reclaim) >> PAGE_SHIFT; + long nr_pages = min_t(u64, temp, LONG_MAX); btrfs_start_delalloc_roots(fs_info, nr_pages, true); @@ -555,15 +561,16 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info, delalloc_bytes = percpu_counter_sum_positive( &fs_info->delalloc_bytes); - dio_bytes = percpu_counter_sum_positive(&fs_info->dio_bytes); + ordered_bytes = percpu_counter_sum_positive( + &fs_info->ordered_bytes); } } /** - * maybe_commit_transaction - possibly commit the transaction if its ok to - * @root - the root we're allocating for - * @bytes - the number of bytes we want to reserve - * @force - force the commit + * Possibly commit the transaction if its ok to + * + * @fs_info: the filesystem + * @space_info: space_info we are checking for commit, either data or metadata * * This will check to make sure that committing the transaction will actually * get us somewhere and then commit the transaction if it does. Otherwise it @@ -669,7 +676,7 @@ enospc: */ static void flush_space(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 num_bytes, - int state) + enum btrfs_flush_state state, bool for_preempt) { struct btrfs_root *root = fs_info->extent_root; struct btrfs_trans_handle *trans; @@ -738,13 +745,21 @@ static void flush_space(struct btrfs_fs_info *fs_info, case COMMIT_TRANS: ret = may_commit_transaction(fs_info, space_info); break; + case FORCE_COMMIT_TRANS: + trans = btrfs_join_transaction(root); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + break; + } + ret = btrfs_commit_transaction(trans); + break; default: ret = -ENOSPC; break; } trace_btrfs_flush_space(fs_info, space_info->flags, num_bytes, state, - ret); + ret, for_preempt); return; } @@ -754,7 +769,6 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, { u64 used; u64 avail; - u64 expected; u64 to_reclaim = space_info->reclaim_size; lockdep_assert_held(&space_info->lock); @@ -772,43 +786,88 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, if (space_info->total_bytes + avail < used) to_reclaim += used - (space_info->total_bytes + avail); - if (to_reclaim) - return to_reclaim; - - to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M); - if (btrfs_can_overcommit(fs_info, space_info, to_reclaim, - BTRFS_RESERVE_FLUSH_ALL)) - return 0; - - used = btrfs_space_info_used(space_info, true); - - if (btrfs_can_overcommit(fs_info, space_info, SZ_1M, - BTRFS_RESERVE_FLUSH_ALL)) - expected = div_factor_fine(space_info->total_bytes, 95); - else - expected = div_factor_fine(space_info->total_bytes, 90); - - if (used > expected) - to_reclaim = used - expected; - else - to_reclaim = 0; - to_reclaim = min(to_reclaim, space_info->bytes_may_use + - space_info->bytes_reserved); return to_reclaim; } -static inline int need_do_async_reclaim(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *space_info, - u64 used) +static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info, + struct btrfs_space_info *space_info) { + u64 ordered, delalloc; u64 thresh = div_factor_fine(space_info->total_bytes, 98); + u64 used; /* If we're just plain full then async reclaim just slows us down. */ if ((space_info->bytes_used + space_info->bytes_reserved) >= thresh) - return 0; + return false; - if (!btrfs_calc_reclaim_metadata_size(fs_info, space_info)) - return 0; + /* + * We have tickets queued, bail so we don't compete with the async + * flushers. + */ + if (space_info->reclaim_size) + return false; + + /* + * If we have over half of the free space occupied by reservations or + * pinned then we want to start flushing. + * + * We do not do the traditional thing here, which is to say + * + * if (used >= ((total_bytes + avail) / 2)) + * return 1; + * + * because this doesn't quite work how we want. If we had more than 50% + * of the space_info used by bytes_used and we had 0 available we'd just + * constantly run the background flusher. Instead we want it to kick in + * if our reclaimable space exceeds our clamped free space. + * + * Our clamping range is 2^1 -> 2^8. Practically speaking that means + * the following: + * + * Amount of RAM Minimum threshold Maximum threshold + * + * 256GiB 1GiB 128GiB + * 128GiB 512MiB 64GiB + * 64GiB 256MiB 32GiB + * 32GiB 128MiB 16GiB + * 16GiB 64MiB 8GiB + * + * These are the range our thresholds will fall in, corresponding to how + * much delalloc we need for the background flusher to kick in. + */ + + thresh = calc_available_free_space(fs_info, space_info, + BTRFS_RESERVE_FLUSH_ALL); + thresh += (space_info->total_bytes - space_info->bytes_used - + space_info->bytes_reserved - space_info->bytes_readonly); + thresh >>= space_info->clamp; + + used = space_info->bytes_pinned; + + /* + * If we have more ordered bytes than delalloc bytes then we're either + * doing a lot of DIO, or we simply don't have a lot of delalloc waiting + * around. Preemptive flushing is only useful in that it can free up + * space before tickets need to wait for things to finish. In the case + * of ordered extents, preemptively waiting on ordered extents gets us + * nothing, if our reservations are tied up in ordered extents we'll + * simply have to slow down writers by forcing them to wait on ordered + * extents. + * + * In the case that ordered is larger than delalloc, only include the + * block reserves that we would actually be able to directly reclaim + * from. In this case if we're heavy on metadata operations this will + * clearly be heavy enough to warrant preemptive flushing. In the case + * of heavy DIO or ordered reservations, preemptive flushing will just + * waste time and cause us to slow down. + */ + ordered = percpu_counter_sum_positive(&fs_info->ordered_bytes); + delalloc = percpu_counter_sum_positive(&fs_info->delalloc_bytes); + if (ordered >= delalloc) + used += fs_info->delayed_refs_rsv.reserved + + fs_info->delayed_block_rsv.reserved; + else + used += space_info->bytes_may_use; return (used >= thresh && !btrfs_fs_closing(fs_info) && !test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state)); @@ -922,7 +981,7 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) struct btrfs_fs_info *fs_info; struct btrfs_space_info *space_info; u64 to_reclaim; - int flush_state; + enum btrfs_flush_state flush_state; int commit_cycles = 0; u64 last_tickets_id; @@ -941,7 +1000,7 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) flush_state = FLUSH_DELAYED_ITEMS_NR; do { - flush_space(fs_info, space_info, to_reclaim, flush_state); + flush_space(fs_info, space_info, to_reclaim, flush_state, false); spin_lock(&space_info->lock); if (list_empty(&space_info->tickets)) { space_info->flush = 0; @@ -989,6 +1048,105 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) } while (flush_state <= COMMIT_TRANS); } +/* + * This handles pre-flushing of metadata space before we get to the point that + * we need to start blocking threads on tickets. The logic here is different + * from the other flush paths because it doesn't rely on tickets to tell us how + * much we need to flush, instead it attempts to keep us below the 80% full + * watermark of space by flushing whichever reservation pool is currently the + * largest. + */ +static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work) +{ + struct btrfs_fs_info *fs_info; + struct btrfs_space_info *space_info; + struct btrfs_block_rsv *delayed_block_rsv; + struct btrfs_block_rsv *delayed_refs_rsv; + struct btrfs_block_rsv *global_rsv; + struct btrfs_block_rsv *trans_rsv; + int loops = 0; + + fs_info = container_of(work, struct btrfs_fs_info, + preempt_reclaim_work); + space_info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA); + delayed_block_rsv = &fs_info->delayed_block_rsv; + delayed_refs_rsv = &fs_info->delayed_refs_rsv; + global_rsv = &fs_info->global_block_rsv; + trans_rsv = &fs_info->trans_block_rsv; + + spin_lock(&space_info->lock); + while (need_preemptive_reclaim(fs_info, space_info)) { + enum btrfs_flush_state flush; + u64 delalloc_size = 0; + u64 to_reclaim, block_rsv_size; + u64 global_rsv_size = global_rsv->reserved; + + loops++; + + /* + * We don't have a precise counter for the metadata being + * reserved for delalloc, so we'll approximate it by subtracting + * out the block rsv's space from the bytes_may_use. If that + * amount is higher than the individual reserves, then we can + * assume it's tied up in delalloc reservations. + */ + block_rsv_size = global_rsv_size + + delayed_block_rsv->reserved + + delayed_refs_rsv->reserved + + trans_rsv->reserved; + if (block_rsv_size < space_info->bytes_may_use) + delalloc_size = space_info->bytes_may_use - block_rsv_size; + spin_unlock(&space_info->lock); + + /* + * We don't want to include the global_rsv in our calculation, + * because that's space we can't touch. Subtract it from the + * block_rsv_size for the next checks. + */ + block_rsv_size -= global_rsv_size; + + /* + * We really want to avoid flushing delalloc too much, as it + * could result in poor allocation patterns, so only flush it if + * it's larger than the rest of the pools combined. + */ + if (delalloc_size > block_rsv_size) { + to_reclaim = delalloc_size; + flush = FLUSH_DELALLOC; + } else if (space_info->bytes_pinned > + (delayed_block_rsv->reserved + + delayed_refs_rsv->reserved)) { + to_reclaim = space_info->bytes_pinned; + flush = FORCE_COMMIT_TRANS; + } else if (delayed_block_rsv->reserved > + delayed_refs_rsv->reserved) { + to_reclaim = delayed_block_rsv->reserved; + flush = FLUSH_DELAYED_ITEMS_NR; + } else { + to_reclaim = delayed_refs_rsv->reserved; + flush = FLUSH_DELAYED_REFS_NR; + } + + /* + * We don't want to reclaim everything, just a portion, so scale + * down the to_reclaim by 1/4. If it takes us down to 0, + * reclaim 1 items worth. + */ + to_reclaim >>= 2; + if (!to_reclaim) + to_reclaim = btrfs_calc_insert_metadata_size(fs_info, 1); + flush_space(fs_info, space_info, to_reclaim, flush, true); + cond_resched(); + spin_lock(&space_info->lock); + } + + /* We only went through once, back off our clamping. */ + if (loops == 1 && !space_info->reclaim_size) + space_info->clamp = max(1, space_info->clamp - 1); + trace_btrfs_done_preemptive_reclaim(fs_info, space_info); + spin_unlock(&space_info->lock); +} + /* * FLUSH_DELALLOC_WAIT: * Space is freed from flushing delalloc in one of two ways. @@ -1054,7 +1212,7 @@ static void btrfs_async_reclaim_data_space(struct work_struct *work) struct btrfs_fs_info *fs_info; struct btrfs_space_info *space_info; u64 last_tickets_id; - int flush_state = 0; + enum btrfs_flush_state flush_state = 0; fs_info = container_of(work, struct btrfs_fs_info, async_data_reclaim_work); space_info = fs_info->data_sinfo; @@ -1069,7 +1227,7 @@ static void btrfs_async_reclaim_data_space(struct work_struct *work) spin_unlock(&space_info->lock); while (!space_info->full) { - flush_space(fs_info, space_info, U64_MAX, ALLOC_CHUNK_FORCE); + flush_space(fs_info, space_info, U64_MAX, ALLOC_CHUNK_FORCE, false); spin_lock(&space_info->lock); if (list_empty(&space_info->tickets)) { space_info->flush = 0; @@ -1082,7 +1240,7 @@ static void btrfs_async_reclaim_data_space(struct work_struct *work) while (flush_state < ARRAY_SIZE(data_flush_states)) { flush_space(fs_info, space_info, U64_MAX, - data_flush_states[flush_state]); + data_flush_states[flush_state], false); spin_lock(&space_info->lock); if (list_empty(&space_info->tickets)) { space_info->flush = 0; @@ -1115,6 +1273,8 @@ void btrfs_init_async_reclaim_work(struct btrfs_fs_info *fs_info) { INIT_WORK(&fs_info->async_reclaim_work, btrfs_async_reclaim_metadata_space); INIT_WORK(&fs_info->async_data_reclaim_work, btrfs_async_reclaim_data_space); + INIT_WORK(&fs_info->preempt_reclaim_work, + btrfs_preempt_reclaim_metadata_space); } static const enum btrfs_flush_state priority_flush_states[] = { @@ -1153,7 +1313,8 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info, flush_state = 0; do { - flush_space(fs_info, space_info, to_reclaim, states[flush_state]); + flush_space(fs_info, space_info, to_reclaim, states[flush_state], + false); flush_state++; spin_lock(&space_info->lock); if (ticket->bytes == 0) { @@ -1169,7 +1330,7 @@ static void priority_reclaim_data_space(struct btrfs_fs_info *fs_info, struct reserve_ticket *ticket) { while (!space_info->full) { - flush_space(fs_info, space_info, U64_MAX, ALLOC_CHUNK_FORCE); + flush_space(fs_info, space_info, U64_MAX, ALLOC_CHUNK_FORCE, false); spin_lock(&space_info->lock); if (ticket->bytes == 0) { spin_unlock(&space_info->lock); @@ -1214,11 +1375,14 @@ static void wait_reserve_ticket(struct btrfs_fs_info *fs_info, } /** - * handle_reserve_ticket - do the appropriate flushing and waiting for a ticket - * @fs_info - the fs - * @space_info - the space_info for the reservation - * @ticket - the ticket for the reservation - * @flush - how much we can flush + * Do the appropriate flushing and waiting for a ticket + * + * @fs_info: the filesystem + * @space_info: space info for the reservation + * @ticket: ticket for the reservation + * @start_ns: timestamp when the reservation started + * @orig_bytes: amount of bytes originally reserved + * @flush: how much we can flush * * This does the work of figuring out how to flush for the ticket, waiting for * the reservation, and returning the appropriate error if there is one. @@ -1226,6 +1390,7 @@ static void wait_reserve_ticket(struct btrfs_fs_info *fs_info, static int handle_reserve_ticket(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, struct reserve_ticket *ticket, + u64 start_ns, u64 orig_bytes, enum btrfs_reserve_flush_enum flush) { int ret; @@ -1281,6 +1446,8 @@ static int handle_reserve_ticket(struct btrfs_fs_info *fs_info, * space wasn't reserved at all). */ ASSERT(!(ticket->bytes == 0 && ticket->error)); + trace_btrfs_reserve_ticket(fs_info, space_info->flags, orig_bytes, + start_ns, flush, ticket->error); return ret; } @@ -1294,12 +1461,31 @@ static inline bool is_normal_flushing(enum btrfs_reserve_flush_enum flush) (flush == BTRFS_RESERVE_FLUSH_ALL_STEAL); } +static inline void maybe_clamp_preempt(struct btrfs_fs_info *fs_info, + struct btrfs_space_info *space_info) +{ + u64 ordered = percpu_counter_sum_positive(&fs_info->ordered_bytes); + u64 delalloc = percpu_counter_sum_positive(&fs_info->delalloc_bytes); + + /* + * If we're heavy on ordered operations then clamping won't help us. We + * need to clamp specifically to keep up with dirty'ing buffered + * writers, because there's not a 1:1 correlation of writing delalloc + * and freeing space, like there is with flushing delayed refs or + * delayed nodes. If we're already more ordered than delalloc then + * we're keeping up, otherwise we aren't and should probably clamp. + */ + if (ordered < delalloc) + space_info->clamp = min(space_info->clamp + 1, 8); +} + /** - * reserve_metadata_bytes - try to reserve bytes from the block_rsv's space - * @root - the root we're allocating for - * @space_info - the space info we want to allocate from - * @orig_bytes - the number of bytes we want - * @flush - whether or not we can flush to make our reservation + * Try to reserve bytes from the block_rsv's space + * + * @fs_info: the filesystem + * @space_info: space info we want to allocate from + * @orig_bytes: number of bytes we want + * @flush: whether or not we can flush to make our reservation * * This will reserve orig_bytes number of bytes from the space info associated * with the block_rsv. If there is not enough space it will make an attempt to @@ -1314,6 +1500,7 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, { struct work_struct *async_work; struct reserve_ticket ticket; + u64 start_ns = 0; u64 used; int ret = 0; bool pending_tickets; @@ -1366,6 +1553,9 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, space_info->reclaim_size += ticket.bytes; init_waitqueue_head(&ticket.wait); ticket.steal = (flush == BTRFS_RESERVE_FLUSH_ALL_STEAL); + if (trace_btrfs_reserve_ticket_enabled()) + start_ns = ktime_get_ns(); + if (flush == BTRFS_RESERVE_FLUSH_ALL || flush == BTRFS_RESERVE_FLUSH_ALL_STEAL || flush == BTRFS_RESERVE_FLUSH_DATA) { @@ -1382,6 +1572,14 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, list_add_tail(&ticket.list, &space_info->priority_tickets); } + + /* + * We were forced to add a reserve ticket, so our preemptive + * flushing is unable to keep up. Clamp down on the threshold + * for the preemptive flushing in order to keep up with the + * workload. + */ + maybe_clamp_preempt(fs_info, space_info); } else if (!ret && space_info->flags & BTRFS_BLOCK_GROUP_METADATA) { used += orig_bytes; /* @@ -1390,27 +1588,29 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, * the async reclaim as we will panic. */ if (!test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags) && - need_do_async_reclaim(fs_info, space_info, used) && - !work_busy(&fs_info->async_reclaim_work)) { + need_preemptive_reclaim(fs_info, space_info) && + !work_busy(&fs_info->preempt_reclaim_work)) { trace_btrfs_trigger_flush(fs_info, space_info->flags, orig_bytes, flush, "preempt"); queue_work(system_unbound_wq, - &fs_info->async_reclaim_work); + &fs_info->preempt_reclaim_work); } } spin_unlock(&space_info->lock); if (!ret || flush == BTRFS_RESERVE_NO_FLUSH) return ret; - return handle_reserve_ticket(fs_info, space_info, &ticket, flush); + return handle_reserve_ticket(fs_info, space_info, &ticket, start_ns, + orig_bytes, flush); } /** - * reserve_metadata_bytes - try to reserve bytes from the block_rsv's space - * @root - the root we're allocating for - * @block_rsv - the block_rsv we're allocating for - * @orig_bytes - the number of bytes we want - * @flush - whether or not we can flush to make our reservation + * Trye to reserve metadata bytes from the block_rsv's space + * + * @root: the root we're allocating for + * @block_rsv: block_rsv we're allocating for + * @orig_bytes: number of bytes we want + * @flush: whether or not we can flush to make our reservation * * This will reserve orig_bytes number of bytes from the space info associated * with the block_rsv. If there is not enough space it will make an attempt to @@ -1448,10 +1648,11 @@ int btrfs_reserve_metadata_bytes(struct btrfs_root *root, } /** - * btrfs_reserve_data_bytes - try to reserve data bytes for an allocation - * @fs_info - the filesystem - * @bytes - the number of bytes we need - * @flush - how we are allowed to flush + * Try to reserve data bytes for an allocation + * + * @fs_info: the filesystem + * @bytes: number of bytes we need + * @flush: how we are allowed to flush * * This will reserve bytes from the data space info. If there is not enough * space then we will attempt to flush space as specified by flush. diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h index 5646393b928c..b1a8ffb03b3e 100644 --- a/fs/btrfs/space-info.h +++ b/fs/btrfs/space-info.h @@ -17,11 +17,17 @@ struct btrfs_space_info { u64 bytes_may_use; /* number of bytes that may be used for delalloc/allocations */ u64 bytes_readonly; /* total bytes that are read only */ + u64 bytes_zone_unusable; /* total bytes that are unusable until + resetting the device zone */ u64 max_extent_size; /* This will hold the maximum extent size of the space info if we had an ENOSPC in the allocator. */ + int clamp; /* Used to scale our threshold for preemptive + flushing. The value is >> clamp, so turns + out to be a 2^clamp divisor. */ + unsigned int full:1; /* indicates that we cannot allocate any more chunks for this space */ unsigned int chunk_alloc:1; /* set if we are allocating a chunk */ @@ -119,7 +125,7 @@ DECLARE_SPACE_INFO_UPDATE(bytes_pinned, "pinned"); int btrfs_init_space_info(struct btrfs_fs_info *fs_info); void btrfs_update_space_info(struct btrfs_fs_info *info, u64 flags, u64 total_bytes, u64 bytes_used, - u64 bytes_readonly, + u64 bytes_readonly, u64 bytes_zone_unusable, struct btrfs_space_info **space_info); struct btrfs_space_info *btrfs_find_space_info(struct btrfs_fs_info *info, u64 flags); @@ -152,4 +158,21 @@ static inline void btrfs_space_info_free_bytes_may_use( int btrfs_reserve_data_bytes(struct btrfs_fs_info *fs_info, u64 bytes, enum btrfs_reserve_flush_enum flush); +static inline void __btrfs_mod_total_bytes_pinned( + struct btrfs_space_info *space_info, + s64 mod) +{ + percpu_counter_add_batch(&space_info->total_bytes_pinned, mod, + BTRFS_TOTAL_BYTES_PINNED_BATCH); +} + +static inline void btrfs_mod_total_bytes_pinned(struct btrfs_fs_info *fs_info, + u64 flags, s64 mod) +{ + struct btrfs_space_info *space_info = btrfs_find_space_info(fs_info, flags); + + ASSERT(space_info); + __btrfs_mod_total_bytes_pinned(space_info, mod); +} + #endif /* BTRFS_SPACE_INFO_H */ diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c new file mode 100644 index 000000000000..c69049e7daa9 --- /dev/null +++ b/fs/btrfs/subpage.c @@ -0,0 +1,278 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include "ctree.h" +#include "subpage.h" + +int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info, + struct page *page, enum btrfs_subpage_type type) +{ + struct btrfs_subpage *subpage = NULL; + int ret; + + /* + * We have cases like a dummy extent buffer page, which is not mappped + * and doesn't need to be locked. + */ + if (page->mapping) + ASSERT(PageLocked(page)); + /* Either not subpage, or the page already has private attached */ + if (fs_info->sectorsize == PAGE_SIZE || PagePrivate(page)) + return 0; + + ret = btrfs_alloc_subpage(fs_info, &subpage, type); + if (ret < 0) + return ret; + attach_page_private(page, subpage); + return 0; +} + +void btrfs_detach_subpage(const struct btrfs_fs_info *fs_info, + struct page *page) +{ + struct btrfs_subpage *subpage; + + /* Either not subpage, or already detached */ + if (fs_info->sectorsize == PAGE_SIZE || !PagePrivate(page)) + return; + + subpage = (struct btrfs_subpage *)detach_page_private(page); + ASSERT(subpage); + btrfs_free_subpage(subpage); +} + +int btrfs_alloc_subpage(const struct btrfs_fs_info *fs_info, + struct btrfs_subpage **ret, + enum btrfs_subpage_type type) +{ + if (fs_info->sectorsize == PAGE_SIZE) + return 0; + + *ret = kzalloc(sizeof(struct btrfs_subpage), GFP_NOFS); + if (!*ret) + return -ENOMEM; + spin_lock_init(&(*ret)->lock); + if (type == BTRFS_SUBPAGE_METADATA) + atomic_set(&(*ret)->eb_refs, 0); + else + atomic_set(&(*ret)->readers, 0); + return 0; +} + +void btrfs_free_subpage(struct btrfs_subpage *subpage) +{ + kfree(subpage); +} + +/* + * Increase the eb_refs of current subpage. + * + * This is important for eb allocation, to prevent race with last eb freeing + * of the same page. + * With the eb_refs increased before the eb inserted into radix tree, + * detach_extent_buffer_page() won't detach the page private while we're still + * allocating the extent buffer. + */ +void btrfs_page_inc_eb_refs(const struct btrfs_fs_info *fs_info, + struct page *page) +{ + struct btrfs_subpage *subpage; + + if (fs_info->sectorsize == PAGE_SIZE) + return; + + ASSERT(PagePrivate(page) && page->mapping); + lockdep_assert_held(&page->mapping->private_lock); + + subpage = (struct btrfs_subpage *)page->private; + atomic_inc(&subpage->eb_refs); +} + +void btrfs_page_dec_eb_refs(const struct btrfs_fs_info *fs_info, + struct page *page) +{ + struct btrfs_subpage *subpage; + + if (fs_info->sectorsize == PAGE_SIZE) + return; + + ASSERT(PagePrivate(page) && page->mapping); + lockdep_assert_held(&page->mapping->private_lock); + + subpage = (struct btrfs_subpage *)page->private; + ASSERT(atomic_read(&subpage->eb_refs)); + atomic_dec(&subpage->eb_refs); +} + +static void btrfs_subpage_assert(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + /* Basic checks */ + ASSERT(PagePrivate(page) && page->private); + ASSERT(IS_ALIGNED(start, fs_info->sectorsize) && + IS_ALIGNED(len, fs_info->sectorsize)); + /* + * The range check only works for mapped page, we can still have + * unmapped page like dummy extent buffer pages. + */ + if (page->mapping) + ASSERT(page_offset(page) <= start && + start + len <= page_offset(page) + PAGE_SIZE); +} + +void btrfs_subpage_start_reader(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; + const int nbits = len >> fs_info->sectorsize_bits; + int ret; + + btrfs_subpage_assert(fs_info, page, start, len); + + ret = atomic_add_return(nbits, &subpage->readers); + ASSERT(ret == nbits); +} + +void btrfs_subpage_end_reader(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; + const int nbits = len >> fs_info->sectorsize_bits; + + btrfs_subpage_assert(fs_info, page, start, len); + ASSERT(atomic_read(&subpage->readers) >= nbits); + if (atomic_sub_and_test(nbits, &subpage->readers)) + unlock_page(page); +} + +/* + * Convert the [start, start + len) range into a u16 bitmap + * + * For example: if start == page_offset() + 16K, len = 16K, we get 0x00f0. + */ +static u16 btrfs_subpage_calc_bitmap(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + const int bit_start = offset_in_page(start) >> fs_info->sectorsize_bits; + const int nbits = len >> fs_info->sectorsize_bits; + + btrfs_subpage_assert(fs_info, page, start, len); + + /* + * Here nbits can be 16, thus can go beyond u16 range. We make the + * first left shift to be calculate in unsigned long (at least u32), + * then truncate the result to u16. + */ + return (u16)(((1UL << nbits) - 1) << bit_start); +} + +void btrfs_subpage_set_uptodate(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; + const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len); + unsigned long flags; + + spin_lock_irqsave(&subpage->lock, flags); + subpage->uptodate_bitmap |= tmp; + if (subpage->uptodate_bitmap == U16_MAX) + SetPageUptodate(page); + spin_unlock_irqrestore(&subpage->lock, flags); +} + +void btrfs_subpage_clear_uptodate(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; + const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len); + unsigned long flags; + + spin_lock_irqsave(&subpage->lock, flags); + subpage->uptodate_bitmap &= ~tmp; + ClearPageUptodate(page); + spin_unlock_irqrestore(&subpage->lock, flags); +} + +void btrfs_subpage_set_error(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; + const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len); + unsigned long flags; + + spin_lock_irqsave(&subpage->lock, flags); + subpage->error_bitmap |= tmp; + SetPageError(page); + spin_unlock_irqrestore(&subpage->lock, flags); +} + +void btrfs_subpage_clear_error(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len) +{ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; + const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len); + unsigned long flags; + + spin_lock_irqsave(&subpage->lock, flags); + subpage->error_bitmap &= ~tmp; + if (subpage->error_bitmap == 0) + ClearPageError(page); + spin_unlock_irqrestore(&subpage->lock, flags); +} + +/* + * Unlike set/clear which is dependent on each page status, for test all bits + * are tested in the same way. + */ +#define IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(name) \ +bool btrfs_subpage_test_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len) \ +{ \ + struct btrfs_subpage *subpage = (struct btrfs_subpage *)page->private; \ + const u16 tmp = btrfs_subpage_calc_bitmap(fs_info, page, start, len); \ + unsigned long flags; \ + bool ret; \ + \ + spin_lock_irqsave(&subpage->lock, flags); \ + ret = ((subpage->name##_bitmap & tmp) == tmp); \ + spin_unlock_irqrestore(&subpage->lock, flags); \ + return ret; \ +} +IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(uptodate); +IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(error); + +/* + * Note that, in selftests (extent-io-tests), we can have empty fs_info passed + * in. We only test sectorsize == PAGE_SIZE cases so far, thus we can fall + * back to regular sectorsize branch. + */ +#define IMPLEMENT_BTRFS_PAGE_OPS(name, set_page_func, clear_page_func, \ + test_page_func) \ +void btrfs_page_set_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len) \ +{ \ + if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) { \ + set_page_func(page); \ + return; \ + } \ + btrfs_subpage_set_##name(fs_info, page, start, len); \ +} \ +void btrfs_page_clear_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len) \ +{ \ + if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) { \ + clear_page_func(page); \ + return; \ + } \ + btrfs_subpage_clear_##name(fs_info, page, start, len); \ +} \ +bool btrfs_page_test_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len) \ +{ \ + if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) \ + return test_page_func(page); \ + return btrfs_subpage_test_##name(fs_info, page, start, len); \ +} +IMPLEMENT_BTRFS_PAGE_OPS(uptodate, SetPageUptodate, ClearPageUptodate, + PageUptodate); +IMPLEMENT_BTRFS_PAGE_OPS(error, SetPageError, ClearPageError, PageError); diff --git a/fs/btrfs/subpage.h b/fs/btrfs/subpage.h new file mode 100644 index 000000000000..b86a4881475d --- /dev/null +++ b/fs/btrfs/subpage.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef BTRFS_SUBPAGE_H +#define BTRFS_SUBPAGE_H + +#include + +/* + * Maximum page size we support is 64K, minimum sector size is 4K, u16 bitmap + * is sufficient. Regular bitmap_* is not used due to size reasons. + */ +#define BTRFS_SUBPAGE_BITMAP_SIZE 16 + +/* + * Structure to trace status of each sector inside a page, attached to + * page::private for both data and metadata inodes. + */ +struct btrfs_subpage { + /* Common members for both data and metadata pages */ + spinlock_t lock; + u16 uptodate_bitmap; + u16 error_bitmap; + union { + /* + * Structures only used by metadata + * + * @eb_refs should only be operated under private_lock, as it + * manages whether the subpage can be detached. + */ + atomic_t eb_refs; + /* Structures only used by data */ + struct { + atomic_t readers; + }; + }; +}; + +enum btrfs_subpage_type { + BTRFS_SUBPAGE_METADATA, + BTRFS_SUBPAGE_DATA, +}; + +int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info, + struct page *page, enum btrfs_subpage_type type); +void btrfs_detach_subpage(const struct btrfs_fs_info *fs_info, + struct page *page); + +/* Allocate additional data where page represents more than one sector */ +int btrfs_alloc_subpage(const struct btrfs_fs_info *fs_info, + struct btrfs_subpage **ret, + enum btrfs_subpage_type type); +void btrfs_free_subpage(struct btrfs_subpage *subpage); + +void btrfs_page_inc_eb_refs(const struct btrfs_fs_info *fs_info, + struct page *page); +void btrfs_page_dec_eb_refs(const struct btrfs_fs_info *fs_info, + struct page *page); + +void btrfs_subpage_start_reader(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len); +void btrfs_subpage_end_reader(const struct btrfs_fs_info *fs_info, + struct page *page, u64 start, u32 len); + +/* + * Template for subpage related operations. + * + * btrfs_subpage_*() are for call sites where the page has subpage attached and + * the range is ensured to be inside the page. + * + * btrfs_page_*() are for call sites where the page can either be subpage + * specific or regular page. The function will handle both cases. + * But the range still needs to be inside the page. + */ +#define DECLARE_BTRFS_SUBPAGE_OPS(name) \ +void btrfs_subpage_set_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len); \ +void btrfs_subpage_clear_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len); \ +bool btrfs_subpage_test_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len); \ +void btrfs_page_set_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len); \ +void btrfs_page_clear_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len); \ +bool btrfs_page_test_##name(const struct btrfs_fs_info *fs_info, \ + struct page *page, u64 start, u32 len); + +DECLARE_BTRFS_SUBPAGE_OPS(uptodate); +DECLARE_BTRFS_SUBPAGE_OPS(error); + +#endif diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 12d7d3be7cd4..f8435641b912 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -48,7 +48,6 @@ #include "tests/btrfs-tests.h" #include "block-group.h" #include "discard.h" - #include "qgroup.h" #define CREATE_TRACE_POINTS #include @@ -2028,6 +2027,13 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) ret = -EINVAL; goto restore; } + if (fs_info->sectorsize < PAGE_SIZE) { + btrfs_warn(fs_info, + "read-write mount is not yet allowed for sectorsize %u page size %lu", + fs_info->sectorsize, PAGE_SIZE); + ret = -EINVAL; + goto restore; + } /* * NOTE: when remounting with a change that does writes, don't diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 19b9fffa2c9c..6eb1c50fa98c 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -666,6 +666,7 @@ SPACE_INFO_ATTR(bytes_pinned); SPACE_INFO_ATTR(bytes_reserved); SPACE_INFO_ATTR(bytes_may_use); SPACE_INFO_ATTR(bytes_readonly); +SPACE_INFO_ATTR(bytes_zone_unusable); SPACE_INFO_ATTR(disk_used); SPACE_INFO_ATTR(disk_total); BTRFS_ATTR(space_info, total_bytes_pinned, @@ -679,6 +680,7 @@ static struct attribute *space_info_attrs[] = { BTRFS_ATTR_PTR(space_info, bytes_reserved), BTRFS_ATTR_PTR(space_info, bytes_may_use), BTRFS_ATTR_PTR(space_info, bytes_readonly), + BTRFS_ATTR_PTR(space_info, bytes_zone_unusable), BTRFS_ATTR_PTR(space_info, disk_used), BTRFS_ATTR_PTR(space_info, disk_total), BTRFS_ATTR_PTR(space_info, total_bytes_pinned), diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c index 57379e96ccc9..c0aefe6dee0b 100644 --- a/fs/btrfs/tests/extent-map-tests.c +++ b/fs/btrfs/tests/extent-map-tests.c @@ -507,7 +507,7 @@ static int test_rmap_block(struct btrfs_fs_info *fs_info, goto out_free; } - ret = btrfs_rmap_block(fs_info, em->start, btrfs_sb_offset(1), + ret = btrfs_rmap_block(fs_info, em->start, NULL, btrfs_sb_offset(1), &logical, &out_ndaddrs, &out_stripe_len); if (ret || (out_ndaddrs == 0 && test->expected_mapped_addr)) { test_err("didn't rmap anything but expected %d", diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 6af7f2bf92de..acff6bb49a97 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -21,6 +21,7 @@ #include "qgroup.h" #include "block-group.h" #include "space-info.h" +#include "zoned.h" #define BTRFS_ROOT_TRANS_TAG 0 @@ -107,6 +108,11 @@ static const unsigned int btrfs_blocked_trans_types[TRANS_STATE_MAX] = { __TRANS_JOIN | __TRANS_JOIN_NOLOCK | __TRANS_JOIN_NOSTART), + [TRANS_STATE_SUPER_COMMITTED] = (__TRANS_START | + __TRANS_ATTACH | + __TRANS_JOIN | + __TRANS_JOIN_NOLOCK | + __TRANS_JOIN_NOSTART), [TRANS_STATE_COMPLETED] = (__TRANS_START | __TRANS_ATTACH | __TRANS_JOIN | @@ -375,6 +381,8 @@ loop: spin_lock_init(&cur_trans->dirty_bgs_lock); INIT_LIST_HEAD(&cur_trans->deleted_bgs); spin_lock_init(&cur_trans->dropped_roots_lock); + INIT_LIST_HEAD(&cur_trans->releasing_ebs); + spin_lock_init(&cur_trans->releasing_ebs_lock); list_add_tail(&cur_trans->list, &fs_info->trans_list); extent_io_tree_init(fs_info, &cur_trans->dirty_pages, IO_TREE_TRANS_DIRTY_PAGES, fs_info->btree_inode); @@ -826,10 +834,11 @@ btrfs_attach_transaction_barrier(struct btrfs_root *root) return trans; } -/* wait for a transaction commit to be fully complete */ -static noinline void wait_for_commit(struct btrfs_transaction *commit) +/* Wait for a transaction commit to reach at least the given state. */ +static noinline void wait_for_commit(struct btrfs_transaction *commit, + const enum btrfs_trans_state min_state) { - wait_event(commit->commit_wait, commit->state == TRANS_STATE_COMPLETED); + wait_event(commit->commit_wait, commit->state >= min_state); } int btrfs_wait_for_commit(struct btrfs_fs_info *fs_info, u64 transid) @@ -884,7 +893,7 @@ int btrfs_wait_for_commit(struct btrfs_fs_info *fs_info, u64 transid) goto out; /* nothing committing|committed */ } - wait_for_commit(cur_trans); + wait_for_commit(cur_trans, TRANS_STATE_COMPLETED); btrfs_put_transaction(cur_trans); out: return ret; @@ -909,9 +918,8 @@ bool btrfs_should_end_transaction(struct btrfs_trans_handle *trans) { struct btrfs_transaction *cur_trans = trans->transaction; - smp_mb(); if (cur_trans->state >= TRANS_STATE_COMMIT_START || - cur_trans->delayed_refs.flushing) + test_bit(BTRFS_DELAYED_REFS_FLUSHING, &cur_trans->delayed_refs.flags)) return true; return should_end_transaction(trans); @@ -1227,10 +1235,6 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans) btrfs_tree_unlock(eb); free_extent_buffer(eb); - if (ret) - return ret; - - ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); if (ret) return ret; @@ -1248,10 +1252,6 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans) if (ret) return ret; - /* run_qgroups might have added some more refs */ - ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); - if (ret) - return ret; again: while (!list_empty(&fs_info->dirty_cowonly_roots)) { struct btrfs_root *root; @@ -1266,15 +1266,24 @@ again: ret = update_cowonly_root(trans, root); if (ret) return ret; - ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); - if (ret) - return ret; } + /* Now flush any delayed refs generated by updating all of the roots */ + ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); + if (ret) + return ret; + while (!list_empty(dirty_bgs) || !list_empty(io_bgs)) { ret = btrfs_write_dirty_block_groups(trans); if (ret) return ret; + + /* + * We're writing the dirty block groups, which could generate + * delayed refs, which could generate more dirty block groups, + * so we want to keep this flushing in this loop to make sure + * everything gets run. + */ ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); if (ret) return ret; @@ -1319,7 +1328,6 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) struct btrfs_root *gang[8]; int i; int ret; - int err = 0; spin_lock(&fs_info->fs_roots_radix_lock); while (1) { @@ -1331,6 +1339,8 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) break; for (i = 0; i < ret; i++) { struct btrfs_root *root = gang[i]; + int ret2; + radix_tree_tag_clear(&fs_info->fs_roots_radix, (unsigned long)root->root_key.objectid, BTRFS_ROOT_TRANS_TAG); @@ -1350,17 +1360,17 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) root->node); } - err = btrfs_update_root(trans, fs_info->tree_root, + ret2 = btrfs_update_root(trans, fs_info->tree_root, &root->root_key, &root->root_item); + if (ret2) + return ret2; spin_lock(&fs_info->fs_roots_radix_lock); - if (err) - break; btrfs_qgroup_free_meta_all_pertrans(root); } } spin_unlock(&fs_info->fs_roots_radix_lock); - return err; + return 0; } /* @@ -1432,6 +1442,23 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans, */ record_root_in_trans(trans, src, 1); + /* + * btrfs_qgroup_inherit relies on a consistent view of the usage for the + * src root, so we must run the delayed refs here. + * + * However this isn't particularly fool proof, because there's no + * synchronization keeping us from changing the tree after this point + * before we do the qgroup_inherit, or even from making changes while + * we're doing the qgroup_inherit. But that's a problem for the future, + * for now flush the delayed refs to narrow the race window where the + * qgroup counters could end up wrong. + */ + ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out; + } + /* * We are going to commit transaction, see btrfs_commit_transaction() * comment for reason locking tree_log_mutex @@ -1525,7 +1552,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, ASSERT(pending->root_item); new_root_item = pending->root_item; - pending->error = btrfs_find_free_objectid(tree_root, &objectid); + pending->error = btrfs_get_free_objectid(tree_root, &objectid); if (pending->error) goto no_free_objectid; @@ -1685,12 +1712,6 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, goto fail; } - ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); - if (ret) { - btrfs_abort_transaction(trans, ret); - goto fail; - } - /* * Do special qgroup accounting for snapshot, as we do some qgroup * snapshot hack to do fast snapshot. @@ -1738,12 +1759,6 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, } } - ret = btrfs_run_delayed_refs(trans, (unsigned long)-1); - if (ret) { - btrfs_abort_transaction(trans, ret); - goto fail; - } - fail: pending->error = ret; dir_item_existed: @@ -2042,32 +2057,25 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) btrfs_trans_release_metadata(trans); trans->block_rsv = NULL; - /* make a pass through all the delayed refs we have so far - * any runnings procs may add more while we are here - */ - ret = btrfs_run_delayed_refs(trans, 0); - if (ret) { - btrfs_end_transaction(trans); - return ret; - } - - cur_trans = trans->transaction; - /* - * set the flushing flag so procs in this transaction have to - * start sending their work down. + * We only want one transaction commit doing the flushing so we do not + * waste a bunch of time on lock contention on the extent root node. */ - cur_trans->delayed_refs.flushing = 1; - smp_wmb(); + if (!test_and_set_bit(BTRFS_DELAYED_REFS_FLUSHING, + &cur_trans->delayed_refs.flags)) { + /* + * Make a pass through all the delayed refs we have so far. + * Any running threads may add more while we are here. + */ + ret = btrfs_run_delayed_refs(trans, 0); + if (ret) { + btrfs_end_transaction(trans); + return ret; + } + } btrfs_create_pending_block_groups(trans); - ret = btrfs_run_delayed_refs(trans, 0); - if (ret) { - btrfs_end_transaction(trans); - return ret; - } - if (!test_bit(BTRFS_TRANS_DIRTY_BG_RUN, &cur_trans->flags)) { int run_it = 0; @@ -2101,11 +2109,15 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) spin_lock(&fs_info->trans_lock); if (cur_trans->state >= TRANS_STATE_COMMIT_START) { + enum btrfs_trans_state want_state = TRANS_STATE_COMPLETED; + spin_unlock(&fs_info->trans_lock); refcount_inc(&cur_trans->use_count); - ret = btrfs_end_transaction(trans); - wait_for_commit(cur_trans); + if (trans->in_fsync) + want_state = TRANS_STATE_SUPER_COMMITTED; + ret = btrfs_end_transaction(trans); + wait_for_commit(cur_trans, want_state); if (TRANS_ABORTED(cur_trans)) ret = cur_trans->aborted; @@ -2119,13 +2131,19 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) wake_up(&fs_info->transaction_blocked_wait); if (cur_trans->list.prev != &fs_info->trans_list) { + enum btrfs_trans_state want_state = TRANS_STATE_COMPLETED; + + if (trans->in_fsync) + want_state = TRANS_STATE_SUPER_COMMITTED; + prev_trans = list_entry(cur_trans->list.prev, struct btrfs_transaction, list); - if (prev_trans->state != TRANS_STATE_COMPLETED) { + if (prev_trans->state < want_state) { refcount_inc(&prev_trans->use_count); spin_unlock(&fs_info->trans_lock); - wait_for_commit(prev_trans); + wait_for_commit(prev_trans, want_state); + ret = READ_ONCE(prev_trans->aborted); btrfs_put_transaction(prev_trans); @@ -2335,6 +2353,13 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) goto scrub_continue; } + /* + * At this point, we should have written all the tree blocks allocated + * in this transaction. So it's now safe to free the redirtyied extent + * buffers. + */ + btrfs_free_redirty_list(cur_trans); + ret = write_all_supers(fs_info, 0); /* * the super is written, we can safely allow the tree-loggers @@ -2344,6 +2369,13 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) if (ret) goto scrub_continue; + /* + * We needn't acquire the lock here because there is no other task + * which can change it. + */ + cur_trans->state = TRANS_STATE_SUPER_COMMITTED; + wake_up(&cur_trans->commit_wait); + btrfs_finish_extent_commit(trans); if (test_bit(BTRFS_TRANS_HAVE_FREE_BGS, &cur_trans->flags)) diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 31ca81bad822..6335716e513f 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -16,6 +16,7 @@ enum btrfs_trans_state { TRANS_STATE_COMMIT_START, TRANS_STATE_COMMIT_DOING, TRANS_STATE_UNBLOCKED, + TRANS_STATE_SUPER_COMMITTED, TRANS_STATE_COMPLETED, TRANS_STATE_MAX, }; @@ -92,6 +93,9 @@ struct btrfs_transaction { */ atomic_t pending_ordered; wait_queue_head_t pending_wait; + + spinlock_t releasing_ebs_lock; + struct list_head releasing_ebs; }; #define __TRANS_FREEZABLE (1U << 0) @@ -133,6 +137,7 @@ struct btrfs_trans_handle { bool can_flush_pending_bgs; bool reloc_reserved; bool dirty; + bool in_fsync; struct btrfs_root *root; struct btrfs_fs_info *fs_info; struct list_head new_bgs; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 254c2ee43aae..d90695c1ab6c 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -19,6 +19,7 @@ #include "qgroup.h" #include "block-group.h" #include "space-info.h" +#include "zoned.h" /* magic values for the inode_only field in btrfs_log_inode: * @@ -104,6 +105,7 @@ static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, u64 dirid, int del_all); +static void wait_log_commit(struct btrfs_root *root, int transid); /* * tree logging is a special write ahead log used to make sure that @@ -139,7 +141,9 @@ static int start_log_trans(struct btrfs_trans_handle *trans, { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *tree_root = fs_info->tree_root; + const bool zoned = btrfs_is_zoned(fs_info); int ret = 0; + bool created = false; /* * First check if the log root tree was already created. If not, create @@ -149,8 +153,10 @@ static int start_log_trans(struct btrfs_trans_handle *trans, mutex_lock(&tree_root->log_mutex); if (!fs_info->log_root_tree) { ret = btrfs_init_log_root_tree(trans, fs_info); - if (!ret) + if (!ret) { set_bit(BTRFS_ROOT_HAS_LOG_TREE, &tree_root->state); + created = true; + } } mutex_unlock(&tree_root->log_mutex); if (ret) @@ -159,12 +165,20 @@ static int start_log_trans(struct btrfs_trans_handle *trans, mutex_lock(&root->log_mutex); +again: if (root->log_root) { + int index = (root->log_transid + 1) % 2; + if (btrfs_need_log_full_commit(trans)) { ret = -EAGAIN; goto out; } + if (zoned && atomic_read(&root->log_commit[index])) { + wait_log_commit(root, root->log_transid - 1); + goto again; + } + if (!root->log_start_pid) { clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state); root->log_start_pid = current->pid; @@ -172,6 +186,17 @@ static int start_log_trans(struct btrfs_trans_handle *trans, set_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state); } } else { + /* + * This means fs_info->log_root_tree was already created + * for some other FS trees. Do the full commit not to mix + * nodes from multiple log transactions to do sequential + * writing. + */ + if (zoned && !created) { + ret = -EAGAIN; + goto out; + } + ret = btrfs_add_log_tree(trans, root); if (ret) goto out; @@ -200,14 +225,22 @@ out: */ static int join_running_log_trans(struct btrfs_root *root) { + const bool zoned = btrfs_is_zoned(root->fs_info); int ret = -ENOENT; if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state)) return ret; mutex_lock(&root->log_mutex); +again: if (root->log_root) { + int index = (root->log_transid + 1) % 2; + ret = 0; + if (zoned && atomic_read(&root->log_commit[index])) { + wait_log_commit(root, root->log_transid - 1); + goto again; + } atomic_inc(&root->log_writers); } mutex_unlock(&root->log_mutex); @@ -2752,6 +2785,8 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, free_extent_buffer(next); return ret; } + btrfs_redirty_list_add( + trans->transaction, next); } else { if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags)) clear_extent_buffer_dirty(next); @@ -3085,6 +3120,17 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, */ blk_start_plug(&plug); ret = btrfs_write_marked_extents(fs_info, &log->dirty_log_pages, mark); + /* + * -EAGAIN happens when someone, e.g., a concurrent transaction + * commit, writes a dirty extent in this tree-log commit. This + * concurrent write will create a hole writing out the extents, + * and we cannot proceed on a zoned filesystem, requiring + * sequential writing. While we can bail out to a full commit + * here, but we can continue hoping the concurrent writing fills + * the hole. + */ + if (ret == -EAGAIN && btrfs_is_zoned(fs_info)) + ret = 0; if (ret) { blk_finish_plug(&plug); btrfs_abort_transaction(trans, ret); @@ -3127,6 +3173,19 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]); root_log_ctx.log_transid = log_root_tree->log_transid; + if (btrfs_is_zoned(fs_info)) { + mutex_lock(&fs_info->tree_root->log_mutex); + if (!log_root_tree->node) { + ret = btrfs_alloc_log_tree_node(trans, log_root_tree); + if (ret) { + mutex_unlock(&fs_info->tree_log_mutex); + mutex_unlock(&log_root_tree->log_mutex); + goto out; + } + } + mutex_unlock(&fs_info->tree_root->log_mutex); + } + /* * Now we are safe to update the log_root_tree because we're under the * log_mutex, and we're a current writer so we're holding the commit @@ -3194,7 +3253,17 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, &log_root_tree->dirty_log_pages, EXTENT_DIRTY | EXTENT_NEW); blk_finish_plug(&plug); - if (ret) { + /* + * As described above, -EAGAIN indicates a hole in the extents. We + * cannot wait for these write outs since the waiting cause a + * deadlock. Bail out to the full commit instead. + */ + if (ret == -EAGAIN && btrfs_is_zoned(fs_info)) { + btrfs_set_log_full_commit(trans); + btrfs_wait_tree_log_extents(log, mark); + mutex_unlock(&log_root_tree->log_mutex); + goto out_wake_log_root; + } else if (ret) { btrfs_set_log_full_commit(trans); btrfs_abort_transaction(trans, ret); mutex_unlock(&log_root_tree->log_mutex); @@ -3285,17 +3354,22 @@ static void free_log_tree(struct btrfs_trans_handle *trans, .process_func = process_one_buffer }; - ret = walk_log_tree(trans, log, &wc); - if (ret) { - if (trans) - btrfs_abort_transaction(trans, ret); - else - btrfs_handle_fs_error(log->fs_info, ret, NULL); + if (log->node) { + ret = walk_log_tree(trans, log, &wc); + if (ret) { + if (trans) + btrfs_abort_transaction(trans, ret); + else + btrfs_handle_fs_error(log->fs_info, ret, NULL); + } } clear_extent_bits(&log->dirty_log_pages, 0, (u64)-1, EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT); extent_io_tree_release(&log->log_csum_range); + + if (trans && log->node) + btrfs_redirty_list_add(trans->transaction, log->node); btrfs_put_root(log); } @@ -3379,7 +3453,6 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, struct btrfs_path *path; int ret; int err = 0; - int bytes_del = 0; u64 dir_ino = btrfs_ino(dir); if (!inode_logged(trans, dir)) @@ -3406,7 +3479,6 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, } if (di) { ret = btrfs_delete_one_dir_name(trans, log, path, di); - bytes_del += name_len; if (ret) { err = ret; goto fail; @@ -3421,46 +3493,17 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, } if (di) { ret = btrfs_delete_one_dir_name(trans, log, path, di); - bytes_del += name_len; if (ret) { err = ret; goto fail; } } - /* update the directory size in the log to reflect the names - * we have removed + /* + * We do not need to update the size field of the directory's inode item + * because on log replay we update the field to reflect all existing + * entries in the directory (see overwrite_item()). */ - if (bytes_del) { - struct btrfs_key key; - - key.objectid = dir_ino; - key.offset = 0; - key.type = BTRFS_INODE_ITEM_KEY; - btrfs_release_path(path); - - ret = btrfs_search_slot(trans, log, &key, path, 0, 1); - if (ret < 0) { - err = ret; - goto fail; - } - if (ret == 0) { - struct btrfs_inode_item *item; - u64 i_size; - - item = btrfs_item_ptr(path->nodes[0], path->slots[0], - struct btrfs_inode_item); - i_size = btrfs_inode_size(path->nodes[0], item); - if (i_size > bytes_del) - i_size -= bytes_del; - else - i_size = 0; - btrfs_set_inode_size(path->nodes[0], item, i_size); - btrfs_mark_buffer_dirty(path->nodes[0]); - } else - ret = 0; - btrfs_release_path(path); - } fail: btrfs_free_path(path); out_unlock: @@ -3889,7 +3932,14 @@ static void fill_inode_item(struct btrfs_trans_handle *trans, btrfs_set_token_timespec_nsec(&token, &item->ctime, inode->i_ctime.tv_nsec); - btrfs_set_token_inode_nbytes(&token, item, inode_get_bytes(inode)); + /* + * We do not need to set the nbytes field, in fact during a fast fsync + * its value may not even be correct, since a fast fsync does not wait + * for ordered extent completion, which is where we update nbytes, it + * only waits for writeback to complete. During log replay as we find + * file extent items and replay them, we adjust the nbytes field of the + * inode item in subvolume tree as needed (see overwrite_item()). + */ btrfs_set_token_inode_sequence(&token, item, inode_peek_iversion(inode)); btrfs_set_token_inode_transid(&token, item, trans->transid); @@ -5289,6 +5339,21 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, mutex_lock(&inode->log_mutex); } + /* + * This is for cases where logging a directory could result in losing a + * a file after replaying the log. For example, if we move a file from a + * directory A to a directory B, then fsync directory A, we have no way + * to known the file was moved from A to B, so logging just A would + * result in losing the file after a log replay. + */ + if (S_ISDIR(inode->vfs_inode.i_mode) && + inode_only == LOG_INODE_ALL && + inode->last_unlink_trans >= trans->transid) { + btrfs_set_log_full_commit(trans); + err = 1; + goto out_unlock; + } + /* * a brute force approach to making sure we get the most uptodate * copies of everything. @@ -5296,6 +5361,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, if (S_ISDIR(inode->vfs_inode.i_mode)) { int max_key_type = BTRFS_DIR_LOG_INDEX_KEY; + clear_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags); if (inode_only == LOG_INODE_EXISTS) max_key_type = BTRFS_XATTR_ITEM_KEY; ret = drop_objectid_items(trans, log, path, ino, max_key_type); @@ -5452,96 +5518,31 @@ out_unlock: } /* - * Check if we must fallback to a transaction commit when logging an inode. - * This must be called after logging the inode and is used only in the context - * when fsyncing an inode requires the need to log some other inode - in which - * case we can't lock the i_mutex of each other inode we need to log as that - * can lead to deadlocks with concurrent fsync against other inodes (as we can - * log inodes up or down in the hierarchy) or rename operations for example. So - * we take the log_mutex of the inode after we have logged it and then check for - * its last_unlink_trans value - this is safe because any task setting - * last_unlink_trans must take the log_mutex and it must do this before it does - * the actual unlink operation, so if we do this check before a concurrent task - * sets last_unlink_trans it means we've logged a consistent version/state of - * all the inode items, otherwise we are not sure and must do a transaction - * commit (the concurrent task might have only updated last_unlink_trans before - * we logged the inode or it might have also done the unlink). + * Check if we need to log an inode. This is used in contexts where while + * logging an inode we need to log another inode (either that it exists or in + * full mode). This is used instead of btrfs_inode_in_log() because the later + * requires the inode to be in the log and have the log transaction committed, + * while here we do not care if the log transaction was already committed - our + * caller will commit the log later - and we want to avoid logging an inode + * multiple times when multiple tasks have joined the same log transaction. */ -static bool btrfs_must_commit_transaction(struct btrfs_trans_handle *trans, - struct btrfs_inode *inode) +static bool need_log_inode(struct btrfs_trans_handle *trans, + struct btrfs_inode *inode) { - bool ret = false; - - mutex_lock(&inode->log_mutex); - if (inode->last_unlink_trans >= trans->transid) { - /* - * Make sure any commits to the log are forced to be full - * commits. - */ - btrfs_set_log_full_commit(trans); - ret = true; - } - mutex_unlock(&inode->log_mutex); - - return ret; -} - -/* - * follow the dentry parent pointers up the chain and see if any - * of the directories in it require a full commit before they can - * be logged. Returns zero if nothing special needs to be done or 1 if - * a full commit is required. - */ -static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, - struct btrfs_inode *inode, - struct dentry *parent, - struct super_block *sb) -{ - int ret = 0; - struct dentry *old_parent = NULL; - /* - * for regular files, if its inode is already on disk, we don't - * have to worry about the parents at all. This is because - * we can use the last_unlink_trans field to record renames - * and other fun in this file. + * If this inode does not have new/updated/deleted xattrs since the last + * time it was logged and is flagged as logged in the current transaction, + * we can skip logging it. As for new/deleted names, those are updated in + * the log by link/unlink/rename operations. + * In case the inode was logged and then evicted and reloaded, its + * logged_trans will be 0, in which case we have to fully log it since + * logged_trans is a transient field, not persisted. */ - if (S_ISREG(inode->vfs_inode.i_mode) && - inode->generation < trans->transid && - inode->last_unlink_trans < trans->transid) - goto out; + if (inode->logged_trans == trans->transid && + !test_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags)) + return false; - if (!S_ISDIR(inode->vfs_inode.i_mode)) { - if (!parent || d_really_is_negative(parent) || sb != parent->d_sb) - goto out; - inode = BTRFS_I(d_inode(parent)); - } - - while (1) { - if (btrfs_must_commit_transaction(trans, inode)) { - ret = 1; - break; - } - - if (!parent || d_really_is_negative(parent) || sb != parent->d_sb) - break; - - if (IS_ROOT(parent)) { - inode = BTRFS_I(d_inode(parent)); - if (btrfs_must_commit_transaction(trans, inode)) - ret = 1; - break; - } - - parent = dget_parent(parent); - dput(old_parent); - old_parent = parent; - inode = BTRFS_I(d_inode(parent)); - - } - dput(old_parent); -out: - return ret; + return true; } struct btrfs_dir_list { @@ -5671,7 +5672,7 @@ process_leaf: goto next_dir_inode; } - if (btrfs_inode_in_log(BTRFS_I(di_inode), trans->transid)) { + if (!need_log_inode(trans, BTRFS_I(di_inode))) { btrfs_add_delayed_iput(di_inode); break; } @@ -5681,9 +5682,6 @@ process_leaf: log_mode = LOG_INODE_ALL; ret = btrfs_log_inode(trans, root, BTRFS_I(di_inode), log_mode, ctx); - if (!ret && - btrfs_must_commit_transaction(trans, BTRFS_I(di_inode))) - ret = 1; btrfs_add_delayed_iput(di_inode); if (ret) goto next_dir_inode; @@ -5821,13 +5819,15 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans, goto out; } + if (!need_log_inode(trans, BTRFS_I(dir_inode))) { + btrfs_add_delayed_iput(dir_inode); + continue; + } + if (ctx) ctx->log_new_dentries = false; ret = btrfs_log_inode(trans, root, BTRFS_I(dir_inode), LOG_INODE_ALL, ctx); - if (!ret && - btrfs_must_commit_transaction(trans, BTRFS_I(dir_inode))) - ret = 1; if (!ret && ctx && ctx->log_new_dentries) ret = log_new_dir_dentries(trans, root, BTRFS_I(dir_inode), ctx); @@ -5872,7 +5872,8 @@ static int log_new_ancestors(struct btrfs_trans_handle *trans, if (IS_ERR(inode)) return PTR_ERR(inode); - if (BTRFS_I(inode)->generation >= trans->transid) + if (BTRFS_I(inode)->generation >= trans->transid && + need_log_inode(trans, BTRFS_I(inode))) ret = btrfs_log_inode(trans, root, BTRFS_I(inode), LOG_INODE_EXISTS, ctx); btrfs_add_delayed_iput(inode); @@ -5926,7 +5927,8 @@ static int log_new_ancestors_fast(struct btrfs_trans_handle *trans, if (root != inode->root) break; - if (inode->generation >= trans->transid) { + if (inode->generation >= trans->transid && + need_log_inode(trans, inode)) { ret = btrfs_log_inode(trans, root, inode, LOG_INODE_EXISTS, ctx); if (ret) @@ -6041,12 +6043,9 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, { struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; - struct super_block *sb; int ret = 0; bool log_dentries = false; - sb = inode->vfs_inode.i_sb; - if (btrfs_test_opt(fs_info, NOTREELOG)) { ret = 1; goto end_no_trans; @@ -6057,10 +6056,6 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, goto end_no_trans; } - ret = check_parent_dirs_for_sync(trans, inode, parent, sb); - if (ret) - goto end_no_trans; - /* * Skip already logged inodes or inodes corresponding to tmpfiles * (since logging them is pointless, a link count of 0 means they @@ -6307,8 +6302,7 @@ again: * root->objectid_mutex is not acquired as log replay * could only happen during mount. */ - ret = btrfs_find_highest_objectid(root, - &root->highest_objectid); + ret = btrfs_init_root_free_objectid(root); } wc.replay_dest->log_root = NULL; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index d6c24c8ad749..b8fab44394f5 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -669,10 +669,6 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); device->mode = flags; - ret = btrfs_get_dev_zone_info(device); - if (ret != 0) - goto error_free_page; - fs_devices->open_devices++; if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) && device->devid != BTRFS_DEV_REPLACE_DEVID) { @@ -1418,11 +1414,62 @@ static u64 dev_extent_search_start(struct btrfs_device *device, u64 start) * make sure to start at an offset of at least 1MB. */ return max_t(u64, start, SZ_1M); + case BTRFS_CHUNK_ALLOC_ZONED: + /* + * We don't care about the starting region like regular + * allocator, because we anyway use/reserve the first two zones + * for superblock logging. + */ + return ALIGN(start, device->zone_info->zone_size); default: BUG(); } } +static bool dev_extent_hole_check_zoned(struct btrfs_device *device, + u64 *hole_start, u64 *hole_size, + u64 num_bytes) +{ + u64 zone_size = device->zone_info->zone_size; + u64 pos; + int ret; + bool changed = false; + + ASSERT(IS_ALIGNED(*hole_start, zone_size)); + + while (*hole_size > 0) { + pos = btrfs_find_allocatable_zones(device, *hole_start, + *hole_start + *hole_size, + num_bytes); + if (pos != *hole_start) { + *hole_size = *hole_start + *hole_size - pos; + *hole_start = pos; + changed = true; + if (*hole_size < num_bytes) + break; + } + + ret = btrfs_ensure_empty_zones(device, pos, num_bytes); + + /* Range is ensured to be empty */ + if (!ret) + return changed; + + /* Given hole range was invalid (outside of device) */ + if (ret == -ERANGE) { + *hole_start += *hole_size; + *hole_size = 0; + return 1; + } + + *hole_start += zone_size; + *hole_size -= zone_size; + changed = true; + } + + return changed; +} + /** * dev_extent_hole_check - check if specified hole is suitable for allocation * @device: the device which we have the hole @@ -1430,7 +1477,7 @@ static u64 dev_extent_search_start(struct btrfs_device *device, u64 start) * @hole_size: the size of the hole * @num_bytes: the size of the free space that we need * - * This function may modify @hole_start and @hole_end to reflect the suitable + * This function may modify @hole_start and @hole_size to reflect the suitable * position for allocation. Returns 1 if hole position is updated, 0 otherwise. */ static bool dev_extent_hole_check(struct btrfs_device *device, u64 *hole_start, @@ -1439,24 +1486,39 @@ static bool dev_extent_hole_check(struct btrfs_device *device, u64 *hole_start, bool changed = false; u64 hole_end = *hole_start + *hole_size; - /* - * Check before we set max_hole_start, otherwise we could end up - * sending back this offset anyway. - */ - if (contains_pending_extent(device, hole_start, *hole_size)) { - if (hole_end >= *hole_start) - *hole_size = hole_end - *hole_start; - else - *hole_size = 0; - changed = true; - } + for (;;) { + /* + * Check before we set max_hole_start, otherwise we could end up + * sending back this offset anyway. + */ + if (contains_pending_extent(device, hole_start, *hole_size)) { + if (hole_end >= *hole_start) + *hole_size = hole_end - *hole_start; + else + *hole_size = 0; + changed = true; + } + + switch (device->fs_devices->chunk_alloc_policy) { + case BTRFS_CHUNK_ALLOC_REGULAR: + /* No extra check */ + break; + case BTRFS_CHUNK_ALLOC_ZONED: + if (dev_extent_hole_check_zoned(device, hole_start, + hole_size, num_bytes)) { + changed = true; + /* + * The changed hole can contain pending extent. + * Loop again to check that. + */ + continue; + } + break; + default: + BUG(); + } - switch (device->fs_devices->chunk_alloc_policy) { - case BTRFS_CHUNK_ALLOC_REGULAR: - /* No extra check */ break; - default: - BUG(); } return changed; @@ -1509,6 +1571,9 @@ static int find_free_dev_extent_start(struct btrfs_device *device, search_start = dev_extent_search_start(device, search_start); + WARN_ON(device->zone_info && + !IS_ALIGNED(num_bytes, device->zone_info->zone_size)); + path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -4668,11 +4733,10 @@ again: } ret = btrfs_previous_item(root, path, 0, key.type); - if (ret) - mutex_unlock(&fs_info->delete_unused_bgs_mutex); - if (ret < 0) - goto done; if (ret) { + mutex_unlock(&fs_info->delete_unused_bgs_mutex); + if (ret < 0) + goto done; ret = 0; btrfs_release_path(path); break; @@ -4904,6 +4968,37 @@ static void init_alloc_chunk_ctl_policy_regular( ctl->dev_extent_min = BTRFS_STRIPE_LEN * ctl->dev_stripes; } +static void init_alloc_chunk_ctl_policy_zoned( + struct btrfs_fs_devices *fs_devices, + struct alloc_chunk_ctl *ctl) +{ + u64 zone_size = fs_devices->fs_info->zone_size; + u64 limit; + int min_num_stripes = ctl->devs_min * ctl->dev_stripes; + int min_data_stripes = (min_num_stripes - ctl->nparity) / ctl->ncopies; + u64 min_chunk_size = min_data_stripes * zone_size; + u64 type = ctl->type; + + ctl->max_stripe_size = zone_size; + if (type & BTRFS_BLOCK_GROUP_DATA) { + ctl->max_chunk_size = round_down(BTRFS_MAX_DATA_CHUNK_SIZE, + zone_size); + } else if (type & BTRFS_BLOCK_GROUP_METADATA) { + ctl->max_chunk_size = ctl->max_stripe_size; + } else if (type & BTRFS_BLOCK_GROUP_SYSTEM) { + ctl->max_chunk_size = 2 * ctl->max_stripe_size; + ctl->devs_max = min_t(int, ctl->devs_max, + BTRFS_MAX_DEVS_SYS_CHUNK); + } + + /* We don't want a chunk larger than 10% of writable space */ + limit = max(round_down(div_factor(fs_devices->total_rw_bytes, 1), + zone_size), + min_chunk_size); + ctl->max_chunk_size = min(limit, ctl->max_chunk_size); + ctl->dev_extent_min = zone_size * ctl->dev_stripes; +} + static void init_alloc_chunk_ctl(struct btrfs_fs_devices *fs_devices, struct alloc_chunk_ctl *ctl) { @@ -4924,6 +5019,9 @@ static void init_alloc_chunk_ctl(struct btrfs_fs_devices *fs_devices, case BTRFS_CHUNK_ALLOC_REGULAR: init_alloc_chunk_ctl_policy_regular(fs_devices, ctl); break; + case BTRFS_CHUNK_ALLOC_ZONED: + init_alloc_chunk_ctl_policy_zoned(fs_devices, ctl); + break; default: BUG(); } @@ -5050,6 +5148,38 @@ static int decide_stripe_size_regular(struct alloc_chunk_ctl *ctl, return 0; } +static int decide_stripe_size_zoned(struct alloc_chunk_ctl *ctl, + struct btrfs_device_info *devices_info) +{ + u64 zone_size = devices_info[0].dev->zone_info->zone_size; + /* Number of stripes that count for block group size */ + int data_stripes; + + /* + * It should hold because: + * dev_extent_min == dev_extent_want == zone_size * dev_stripes + */ + ASSERT(devices_info[ctl->ndevs - 1].max_avail == ctl->dev_extent_min); + + ctl->stripe_size = zone_size; + ctl->num_stripes = ctl->ndevs * ctl->dev_stripes; + data_stripes = (ctl->num_stripes - ctl->nparity) / ctl->ncopies; + + /* stripe_size is fixed in zoned filesysmte. Reduce ndevs instead. */ + if (ctl->stripe_size * data_stripes > ctl->max_chunk_size) { + ctl->ndevs = div_u64(div_u64(ctl->max_chunk_size * ctl->ncopies, + ctl->stripe_size) + ctl->nparity, + ctl->dev_stripes); + ctl->num_stripes = ctl->ndevs * ctl->dev_stripes; + data_stripes = (ctl->num_stripes - ctl->nparity) / ctl->ncopies; + ASSERT(ctl->stripe_size * data_stripes <= ctl->max_chunk_size); + } + + ctl->chunk_size = ctl->stripe_size * data_stripes; + + return 0; +} + static int decide_stripe_size(struct btrfs_fs_devices *fs_devices, struct alloc_chunk_ctl *ctl, struct btrfs_device_info *devices_info) @@ -5077,6 +5207,8 @@ static int decide_stripe_size(struct btrfs_fs_devices *fs_devices, switch (fs_devices->chunk_alloc_policy) { case BTRFS_CHUNK_ALLOC_REGULAR: return decide_stripe_size_regular(ctl, devices_info); + case BTRFS_CHUNK_ALLOC_ZONED: + return decide_stripe_size_zoned(ctl, devices_info); default: BUG(); } @@ -5841,9 +5973,29 @@ static int get_extra_mirror_from_replace(struct btrfs_fs_info *fs_info, return ret; } +static bool is_block_group_to_copy(struct btrfs_fs_info *fs_info, u64 logical) +{ + struct btrfs_block_group *cache; + bool ret; + + /* Non zoned filesystem does not use "to_copy" flag */ + if (!btrfs_is_zoned(fs_info)) + return false; + + cache = btrfs_lookup_block_group(fs_info, logical); + + spin_lock(&cache->lock); + ret = cache->to_copy; + spin_unlock(&cache->lock); + + btrfs_put_block_group(cache); + return ret; +} + static void handle_ops_on_dev_replace(enum btrfs_map_op op, struct btrfs_bio **bbio_ret, struct btrfs_dev_replace *dev_replace, + u64 logical, int *num_stripes_ret, int *max_errors_ret) { struct btrfs_bio *bbio = *bbio_ret; @@ -5856,6 +6008,13 @@ static void handle_ops_on_dev_replace(enum btrfs_map_op op, if (op == BTRFS_MAP_WRITE) { int index_where_to_add; + /* + * A block group which have "to_copy" set will eventually + * copied by dev-replace process. We can avoid cloning IO here. + */ + if (is_block_group_to_copy(dev_replace->srcdev->fs_info, logical)) + return; + /* * duplicate the write operations while the dev replace * procedure is running. Since the copying of the old disk to @@ -5941,23 +6100,24 @@ static bool need_full_stripe(enum btrfs_map_op op) } /* - * btrfs_get_io_geometry - calculates the geomery of a particular (address, len) - * tuple. This information is used to calculate how big a - * particular bio can get before it straddles a stripe. + * Calculate the geometry of a particular (address, len) tuple. This + * information is used to calculate how big a particular bio can get before it + * straddles a stripe. * - * @fs_info - the filesystem - * @logical - address that we want to figure out the geometry of - * @len - the length of IO we are going to perform, starting at @logical - * @op - type of operation - write or read - * @io_geom - pointer used to return values + * @fs_info: the filesystem + * @em: mapping containing the logical extent + * @op: type of operation - write or read + * @logical: address that we want to figure out the geometry of + * @len: the length of IO we are going to perform, starting at @logical + * @io_geom: pointer used to return values * * Returns < 0 in case a chunk for the given logical address cannot be found, * usually shouldn't happen unless @logical is corrupted, 0 otherwise. */ -int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, - u64 logical, u64 len, struct btrfs_io_geometry *io_geom) +int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, struct extent_map *em, + enum btrfs_map_op op, u64 logical, u64 len, + struct btrfs_io_geometry *io_geom) { - struct extent_map *em; struct map_lookup *map; u64 offset; u64 stripe_offset; @@ -5965,14 +6125,9 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, u64 stripe_len; u64 raid56_full_stripe_start = (u64)-1; int data_stripes; - int ret = 0; ASSERT(op != BTRFS_MAP_DISCARD); - em = btrfs_get_chunk_map(fs_info, logical, len); - if (IS_ERR(em)) - return PTR_ERR(em); - map = em->map_lookup; /* Offset of this logical address in the chunk */ offset = logical - em->start; @@ -5986,8 +6141,7 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, btrfs_crit(fs_info, "stripe math has gone wrong, stripe_offset=%llu offset=%llu start=%llu logical=%llu stripe_len=%llu", stripe_offset, offset, em->start, logical, stripe_len); - ret = -EINVAL; - goto out; + return -EINVAL; } /* stripe_offset is the offset of this block in its stripe */ @@ -6034,10 +6188,7 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, io_geom->stripe_offset = stripe_offset; io_geom->raid56_stripe_offset = raid56_full_stripe_start; -out: - /* once for us */ - free_extent_map(em); - return ret; + return 0; } static int __btrfs_map_block(struct btrfs_fs_info *fs_info, @@ -6070,12 +6221,13 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, ASSERT(bbio_ret); ASSERT(op != BTRFS_MAP_DISCARD); - ret = btrfs_get_io_geometry(fs_info, op, logical, *length, &geom); + em = btrfs_get_chunk_map(fs_info, logical, *length); + ASSERT(!IS_ERR(em)); + + ret = btrfs_get_io_geometry(fs_info, em, op, logical, *length, &geom); if (ret < 0) return ret; - em = btrfs_get_chunk_map(fs_info, logical, *length); - ASSERT(!IS_ERR(em)); map = em->map_lookup; *length = geom.len; @@ -6251,8 +6403,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL && need_full_stripe(op)) { - handle_ops_on_dev_replace(op, &bbio, dev_replace, &num_stripes, - &max_errors); + handle_ops_on_dev_replace(op, &bbio, dev_replace, logical, + &num_stripes, &max_errors); } *bbio_ret = bbio; @@ -6323,7 +6475,7 @@ static void btrfs_end_bio(struct bio *bio) struct btrfs_device *dev = btrfs_io_bio(bio)->device; ASSERT(dev->bdev); - if (bio_op(bio) == REQ_OP_WRITE) + if (btrfs_op(bio) == BTRFS_MAP_WRITE) btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS); else if (!(bio->bi_opf & REQ_RAHEAD)) @@ -6375,6 +6527,20 @@ static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio, btrfs_io_bio(bio)->device = dev; bio->bi_end_io = btrfs_end_bio; bio->bi_iter.bi_sector = physical >> 9; + /* + * For zone append writing, bi_sector must point the beginning of the + * zone + */ + if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + if (btrfs_dev_is_sequential(dev, physical)) { + u64 zone_start = round_down(physical, fs_info->zone_size); + + bio->bi_iter.bi_sector = zone_start >> SECTOR_SHIFT; + } else { + bio->bi_opf &= ~REQ_OP_ZONE_APPEND; + bio->bi_opf |= REQ_OP_WRITE; + } + } btrfs_debug_in_rcu(fs_info, "btrfs_map_bio: rw %d 0x%x, sector=%llu, dev=%lu (%s id %llu), size=%u", bio_op(bio), bio->bi_opf, bio->bi_iter.bi_sector, @@ -6436,10 +6602,10 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, atomic_set(&bbio->stripes_pending, bbio->num_stripes); if ((bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) && - ((bio_op(bio) == REQ_OP_WRITE) || (mirror_num > 1))) { + ((btrfs_op(bio) == BTRFS_MAP_WRITE) || (mirror_num > 1))) { /* In this case, map_length has been set to the length of a single stripe; not the whole write */ - if (bio_op(bio) == REQ_OP_WRITE) { + if (btrfs_op(bio) == BTRFS_MAP_WRITE) { ret = raid56_parity_write(fs_info, bio, bbio, map_length); } else { @@ -6462,7 +6628,7 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, dev = bbio->stripes[dev_nr].dev; if (!dev || !dev->bdev || test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state) || - (bio_op(first_bio) == REQ_OP_WRITE && + (btrfs_op(first_bio) == BTRFS_MAP_WRITE && !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state))) { bbio_error(bbio, first_bio, logical); continue; @@ -7644,6 +7810,20 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info, ret = -EUCLEAN; goto out; } + + if (dev->zone_info) { + u64 zone_size = dev->zone_info->zone_size; + + if (!IS_ALIGNED(physical_offset, zone_size) || + !IS_ALIGNED(physical_len, zone_size)) { + btrfs_err(fs_info, +"zoned: dev extent devid %llu physical offset %llu len %llu is not aligned to device zone", + devid, physical_offset, physical_len); + ret = -EUCLEAN; + goto out; + } + } + out: free_extent_map(em); return ret; @@ -7800,3 +7980,75 @@ bool btrfs_pinned_by_swapfile(struct btrfs_fs_info *fs_info, void *ptr) spin_unlock(&fs_info->swapfile_pins_lock); return node != NULL; } + +static int relocating_repair_kthread(void *data) +{ + struct btrfs_block_group *cache = (struct btrfs_block_group *)data; + struct btrfs_fs_info *fs_info = cache->fs_info; + u64 target; + int ret = 0; + + target = cache->start; + btrfs_put_block_group(cache); + + if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE)) { + btrfs_info(fs_info, + "zoned: skip relocating block group %llu to repair: EBUSY", + target); + return -EBUSY; + } + + mutex_lock(&fs_info->delete_unused_bgs_mutex); + + /* Ensure block group still exists */ + cache = btrfs_lookup_block_group(fs_info, target); + if (!cache) + goto out; + + if (!cache->relocating_repair) + goto out; + + ret = btrfs_may_alloc_data_chunk(fs_info, target); + if (ret < 0) + goto out; + + btrfs_info(fs_info, + "zoned: relocating block group %llu to repair IO failure", + target); + ret = btrfs_relocate_chunk(fs_info, target); + +out: + if (cache) + btrfs_put_block_group(cache); + mutex_unlock(&fs_info->delete_unused_bgs_mutex); + btrfs_exclop_finish(fs_info); + + return ret; +} + +int btrfs_repair_one_zone(struct btrfs_fs_info *fs_info, u64 logical) +{ + struct btrfs_block_group *cache; + + /* Do not attempt to repair in degraded state */ + if (btrfs_test_opt(fs_info, DEGRADED)) + return 0; + + cache = btrfs_lookup_block_group(fs_info, logical); + if (!cache) + return 0; + + spin_lock(&cache->lock); + if (cache->relocating_repair) { + spin_unlock(&cache->lock); + btrfs_put_block_group(cache); + return 0; + } + cache->relocating_repair = 1; + spin_unlock(&cache->lock); + + kthread_run(relocating_repair_kthread, cache, + "btrfs-relocating-repair"); + + return 0; +} diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index c43663d9c22e..d4c3e0dd32b8 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -214,6 +214,7 @@ BTRFS_DEVICE_GETSET_FUNCS(bytes_used); enum btrfs_chunk_allocation_policy { BTRFS_CHUNK_ALLOC_REGULAR, + BTRFS_CHUNK_ALLOC_ZONED, }; /* @@ -423,6 +424,7 @@ static inline enum btrfs_map_op btrfs_op(struct bio *bio) case REQ_OP_DISCARD: return BTRFS_MAP_DISCARD; case REQ_OP_WRITE: + case REQ_OP_ZONE_APPEND: return BTRFS_MAP_WRITE; default: WARN_ON_ONCE(1); @@ -440,8 +442,9 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, u64 logical, u64 *length, struct btrfs_bio **bbio_ret); -int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, - u64 logical, u64 len, struct btrfs_io_geometry *io_geom); +int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, struct extent_map *map, + enum btrfs_map_op op, u64 logical, u64 len, + struct btrfs_io_geometry *io_geom); int btrfs_read_sys_array(struct btrfs_fs_info *fs_info); int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info); int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type); @@ -596,5 +599,6 @@ void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info, int btrfs_bg_type_to_factor(u64 flags); const char *btrfs_bg_type_to_raid_name(u64 flags); int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info); +int btrfs_repair_one_zone(struct btrfs_fs_info *fs_info, u64 logical); #endif diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index c38846659019..9a5cf153da89 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1,14 +1,25 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include #include +#include #include "ctree.h" #include "volumes.h" #include "zoned.h" #include "rcu-string.h" +#include "disk-io.h" +#include "block-group.h" +#include "transaction.h" +#include "dev-replace.h" +#include "space-info.h" /* Maximum number of zones to report per blkdev_report_zones() call */ #define BTRFS_REPORT_NR_ZONES 4096 +/* Invalid allocation pointer value for missing devices */ +#define WP_MISSING_DEV ((u64)-1) +/* Pseudo write pointer value for conventional zone */ +#define WP_CONVENTIONAL ((u64)-2) /* Number of superblock log zones */ #define BTRFS_NR_SB_LOG_ZONES 2 @@ -119,6 +130,36 @@ static inline u32 sb_zone_number(int shift, int mirror) return 0; } +/* + * Emulate blkdev_report_zones() for a non-zoned device. It slices up the block + * device into static sized chunks and fake a conventional zone on each of + * them. + */ +static int emulate_report_zones(struct btrfs_device *device, u64 pos, + struct blk_zone *zones, unsigned int nr_zones) +{ + const sector_t zone_sectors = device->fs_info->zone_size >> SECTOR_SHIFT; + sector_t bdev_size = bdev_nr_sectors(device->bdev); + unsigned int i; + + pos >>= SECTOR_SHIFT; + for (i = 0; i < nr_zones; i++) { + zones[i].start = i * zone_sectors + pos; + zones[i].len = zone_sectors; + zones[i].capacity = zone_sectors; + zones[i].wp = zones[i].start + zone_sectors; + zones[i].type = BLK_ZONE_TYPE_CONVENTIONAL; + zones[i].cond = BLK_ZONE_COND_NOT_WP; + + if (zones[i].wp >= bdev_size) { + i++; + break; + } + } + + return i; +} + static int btrfs_get_dev_zones(struct btrfs_device *device, u64 pos, struct blk_zone *zones, unsigned int *nr_zones) { @@ -127,6 +168,12 @@ static int btrfs_get_dev_zones(struct btrfs_device *device, u64 pos, if (!*nr_zones) return 0; + if (!bdev_is_zoned(device->bdev)) { + ret = emulate_report_zones(device, pos, zones, *nr_zones); + *nr_zones = ret; + return 0; + } + ret = blkdev_report_zones(device->bdev, pos >> SECTOR_SHIFT, *nr_zones, copy_zone_info_cb, zones); if (ret < 0) { @@ -143,8 +190,78 @@ static int btrfs_get_dev_zones(struct btrfs_device *device, u64 pos, return 0; } +/* The emulated zone size is determined from the size of device extent */ +static int calculate_emulated_zone_size(struct btrfs_fs_info *fs_info) +{ + struct btrfs_path *path; + struct btrfs_root *root = fs_info->dev_root; + struct btrfs_key key; + struct extent_buffer *leaf; + struct btrfs_dev_extent *dext; + int ret = 0; + + key.objectid = 1; + key.type = BTRFS_DEV_EXTENT_KEY; + key.offset = 0; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) + goto out; + + if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { + ret = btrfs_next_item(root, path); + if (ret < 0) + goto out; + /* No dev extents at all? Not good */ + if (ret > 0) { + ret = -EUCLEAN; + goto out; + } + } + + leaf = path->nodes[0]; + dext = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dev_extent); + fs_info->zone_size = btrfs_dev_extent_length(leaf, dext); + ret = 0; + +out: + btrfs_free_path(path); + + return ret; +} + +int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info) +{ + struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; + struct btrfs_device *device; + int ret = 0; + + /* fs_info->zone_size might not set yet. Use the incomapt flag here. */ + if (!btrfs_fs_incompat(fs_info, ZONED)) + return 0; + + mutex_lock(&fs_devices->device_list_mutex); + list_for_each_entry(device, &fs_devices->devices, dev_list) { + /* We can skip reading of zone info for missing devices */ + if (!device->bdev) + continue; + + ret = btrfs_get_dev_zone_info(device); + if (ret) + break; + } + mutex_unlock(&fs_devices->device_list_mutex); + + return ret; +} + int btrfs_get_dev_zone_info(struct btrfs_device *device) { + struct btrfs_fs_info *fs_info = device->fs_info; struct btrfs_zoned_device_info *zone_info = NULL; struct block_device *bdev = device->bdev; struct request_queue *queue = bdev_get_queue(bdev); @@ -153,9 +270,14 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device) struct blk_zone *zones = NULL; unsigned int i, nreported = 0, nr_zones; unsigned int zone_sectors; + char *model, *emulated; int ret; - if (!bdev_is_zoned(bdev)) + /* + * Cannot use btrfs_is_zoned here, since fs_info::zone_size might not + * yet be set. + */ + if (!btrfs_fs_incompat(fs_info, ZONED)) return 0; if (device->zone_info) @@ -165,8 +287,20 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device) if (!zone_info) return -ENOMEM; + if (!bdev_is_zoned(bdev)) { + if (!fs_info->zone_size) { + ret = calculate_emulated_zone_size(fs_info); + if (ret) + goto out; + } + + ASSERT(fs_info->zone_size); + zone_sectors = fs_info->zone_size >> SECTOR_SHIFT; + } else { + zone_sectors = bdev_zone_sectors(bdev); + } + nr_sectors = bdev_nr_sectors(bdev); - zone_sectors = bdev_zone_sectors(bdev); /* Check if it's power of 2 (see is_power_of_2) */ ASSERT(zone_sectors != 0 && (zone_sectors & (zone_sectors - 1)) == 0); zone_info->zone_size = zone_sectors << SECTOR_SHIFT; @@ -272,20 +406,42 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device) device->zone_info = zone_info; - /* device->fs_info is not safe to use for printing messages */ - btrfs_info_in_rcu(NULL, - "host-%s zoned block device %s, %u zones of %llu bytes", - bdev_zoned_model(bdev) == BLK_ZONED_HM ? "managed" : "aware", - rcu_str_deref(device->name), zone_info->nr_zones, - zone_info->zone_size); + switch (bdev_zoned_model(bdev)) { + case BLK_ZONED_HM: + model = "host-managed zoned"; + emulated = ""; + break; + case BLK_ZONED_HA: + model = "host-aware zoned"; + emulated = ""; + break; + case BLK_ZONED_NONE: + model = "regular"; + emulated = "emulated "; + break; + default: + /* Just in case */ + btrfs_err_in_rcu(fs_info, "zoned: unsupported model %d on %s", + bdev_zoned_model(bdev), + rcu_str_deref(device->name)); + ret = -EOPNOTSUPP; + goto out_free_zone_info; + } + + btrfs_info_in_rcu(fs_info, + "%s block device %s, %u %szones of %llu bytes", + model, rcu_str_deref(device->name), zone_info->nr_zones, + emulated, zone_info->zone_size); return 0; out: kfree(zones); +out_free_zone_info: bitmap_free(zone_info->empty_zones); bitmap_free(zone_info->seq_zones); kfree(zone_info); + device->zone_info = NULL; return ret; } @@ -324,7 +480,7 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info) u64 nr_devices = 0; u64 zone_size = 0; u64 max_zone_append_size = 0; - const bool incompat_zoned = btrfs_is_zoned(fs_info); + const bool incompat_zoned = btrfs_fs_incompat(fs_info, ZONED); int ret = 0; /* Count zoned devices */ @@ -335,9 +491,17 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info) continue; model = bdev_zoned_model(device->bdev); + /* + * A Host-Managed zoned device must be used as a zoned device. + * A Host-Aware zoned device and a non-zoned devices can be + * treated as a zoned device, if ZONED flag is enabled in the + * superblock. + */ if (model == BLK_ZONED_HM || - (model == BLK_ZONED_HA && incompat_zoned)) { - struct btrfs_zoned_device_info *zone_info; + (model == BLK_ZONED_HA && incompat_zoned) || + (model == BLK_ZONED_NONE && incompat_zoned)) { + struct btrfs_zoned_device_info *zone_info = + device->zone_info; zone_info = device->zone_info; zoned_devices++; @@ -406,6 +570,15 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info) fs_info->zone_size = zone_size; fs_info->max_zone_append_size = max_zone_append_size; + fs_info->fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_ZONED; + + /* + * Check mount options here, because we might change fs_info->zoned + * from fs_info->zone_size. + */ + ret = btrfs_check_mountopts_zoned(fs_info); + if (ret) + goto out; btrfs_info(fs_info, "zoned mode enabled with zone size %llu", zone_size); out: @@ -488,7 +661,6 @@ int btrfs_sb_log_location_bdev(struct block_device *bdev, int mirror, int rw, unsigned int zone_sectors; u32 sb_zone; int ret; - u64 zone_size; u8 zone_sectors_shift; sector_t nr_sectors; u32 nr_zones; @@ -503,7 +675,6 @@ int btrfs_sb_log_location_bdev(struct block_device *bdev, int mirror, int rw, zone_sectors = bdev_zone_sectors(bdev); if (!is_power_of_2(zone_sectors)) return -EINVAL; - zone_size = zone_sectors << SECTOR_SHIFT; zone_sectors_shift = ilog2(zone_sectors); nr_sectors = bdev_nr_sectors(bdev); nr_zones = nr_sectors >> zone_sectors_shift; @@ -529,7 +700,13 @@ int btrfs_sb_log_location(struct btrfs_device *device, int mirror, int rw, struct btrfs_zoned_device_info *zinfo = device->zone_info; u32 zone_num; - if (!zinfo) { + /* + * For a zoned filesystem on a non-zoned block device, use the same + * super block locations as regular filesystem. Doing so, the super + * block can always be retrieved and the zoned flag of the volume + * detected from the super block information. + */ + if (!bdev_is_zoned(device->bdev)) { *bytenr_ret = btrfs_sb_offset(mirror); return 0; } @@ -614,3 +791,671 @@ int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror) sb_zone << zone_sectors_shift, zone_sectors * BTRFS_NR_SB_LOG_ZONES, GFP_NOFS); } + +/** + * btrfs_find_allocatable_zones - find allocatable zones within a given region + * + * @device: the device to allocate a region on + * @hole_start: the position of the hole to allocate the region + * @num_bytes: size of wanted region + * @hole_end: the end of the hole + * @return: position of allocatable zones + * + * Allocatable region should not contain any superblock locations. + */ +u64 btrfs_find_allocatable_zones(struct btrfs_device *device, u64 hole_start, + u64 hole_end, u64 num_bytes) +{ + struct btrfs_zoned_device_info *zinfo = device->zone_info; + const u8 shift = zinfo->zone_size_shift; + u64 nzones = num_bytes >> shift; + u64 pos = hole_start; + u64 begin, end; + bool have_sb; + int i; + + ASSERT(IS_ALIGNED(hole_start, zinfo->zone_size)); + ASSERT(IS_ALIGNED(num_bytes, zinfo->zone_size)); + + while (pos < hole_end) { + begin = pos >> shift; + end = begin + nzones; + + if (end > zinfo->nr_zones) + return hole_end; + + /* Check if zones in the region are all empty */ + if (btrfs_dev_is_sequential(device, pos) && + find_next_zero_bit(zinfo->empty_zones, end, begin) != end) { + pos += zinfo->zone_size; + continue; + } + + have_sb = false; + for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) { + u32 sb_zone; + u64 sb_pos; + + sb_zone = sb_zone_number(shift, i); + if (!(end <= sb_zone || + sb_zone + BTRFS_NR_SB_LOG_ZONES <= begin)) { + have_sb = true; + pos = ((u64)sb_zone + BTRFS_NR_SB_LOG_ZONES) << shift; + break; + } + + /* We also need to exclude regular superblock positions */ + sb_pos = btrfs_sb_offset(i); + if (!(pos + num_bytes <= sb_pos || + sb_pos + BTRFS_SUPER_INFO_SIZE <= pos)) { + have_sb = true; + pos = ALIGN(sb_pos + BTRFS_SUPER_INFO_SIZE, + zinfo->zone_size); + break; + } + } + if (!have_sb) + break; + } + + return pos; +} + +int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical, + u64 length, u64 *bytes) +{ + int ret; + + *bytes = 0; + ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_RESET, + physical >> SECTOR_SHIFT, length >> SECTOR_SHIFT, + GFP_NOFS); + if (ret) + return ret; + + *bytes = length; + while (length) { + btrfs_dev_set_zone_empty(device, physical); + physical += device->zone_info->zone_size; + length -= device->zone_info->zone_size; + } + + return 0; +} + +int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size) +{ + struct btrfs_zoned_device_info *zinfo = device->zone_info; + const u8 shift = zinfo->zone_size_shift; + unsigned long begin = start >> shift; + unsigned long end = (start + size) >> shift; + u64 pos; + int ret; + + ASSERT(IS_ALIGNED(start, zinfo->zone_size)); + ASSERT(IS_ALIGNED(size, zinfo->zone_size)); + + if (end > zinfo->nr_zones) + return -ERANGE; + + /* All the zones are conventional */ + if (find_next_bit(zinfo->seq_zones, begin, end) == end) + return 0; + + /* All the zones are sequential and empty */ + if (find_next_zero_bit(zinfo->seq_zones, begin, end) == end && + find_next_zero_bit(zinfo->empty_zones, begin, end) == end) + return 0; + + for (pos = start; pos < start + size; pos += zinfo->zone_size) { + u64 reset_bytes; + + if (!btrfs_dev_is_sequential(device, pos) || + btrfs_dev_is_empty_zone(device, pos)) + continue; + + /* Free regions should be empty */ + btrfs_warn_in_rcu( + device->fs_info, + "zoned: resetting device %s (devid %llu) zone %llu for allocation", + rcu_str_deref(device->name), device->devid, pos >> shift); + WARN_ON_ONCE(1); + + ret = btrfs_reset_device_zone(device, pos, zinfo->zone_size, + &reset_bytes); + if (ret) + return ret; + } + + return 0; +} + +/* + * Calculate an allocation pointer from the extent allocation information + * for a block group consist of conventional zones. It is pointed to the + * end of the highest addressed extent in the block group as an allocation + * offset. + */ +static int calculate_alloc_pointer(struct btrfs_block_group *cache, + u64 *offset_ret) +{ + struct btrfs_fs_info *fs_info = cache->fs_info; + struct btrfs_root *root = fs_info->extent_root; + struct btrfs_path *path; + struct btrfs_key key; + struct btrfs_key found_key; + int ret; + u64 length; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + key.objectid = cache->start + cache->length; + key.type = 0; + key.offset = 0; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + /* We should not find the exact match */ + if (!ret) + ret = -EUCLEAN; + if (ret < 0) + goto out; + + ret = btrfs_previous_extent_item(root, path, cache->start); + if (ret) { + if (ret == 1) { + ret = 0; + *offset_ret = 0; + } + goto out; + } + + btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); + + if (found_key.type == BTRFS_EXTENT_ITEM_KEY) + length = found_key.offset; + else + length = fs_info->nodesize; + + if (!(found_key.objectid >= cache->start && + found_key.objectid + length <= cache->start + cache->length)) { + ret = -EUCLEAN; + goto out; + } + *offset_ret = found_key.objectid + length - cache->start; + ret = 0; + +out: + btrfs_free_path(path); + return ret; +} + +int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) +{ + struct btrfs_fs_info *fs_info = cache->fs_info; + struct extent_map_tree *em_tree = &fs_info->mapping_tree; + struct extent_map *em; + struct map_lookup *map; + struct btrfs_device *device; + u64 logical = cache->start; + u64 length = cache->length; + u64 physical = 0; + int ret; + int i; + unsigned int nofs_flag; + u64 *alloc_offsets = NULL; + u64 last_alloc = 0; + u32 num_sequential = 0, num_conventional = 0; + + if (!btrfs_is_zoned(fs_info)) + return 0; + + /* Sanity check */ + if (!IS_ALIGNED(length, fs_info->zone_size)) { + btrfs_err(fs_info, + "zoned: block group %llu len %llu unaligned to zone size %llu", + logical, length, fs_info->zone_size); + return -EIO; + } + + /* Get the chunk mapping */ + read_lock(&em_tree->lock); + em = lookup_extent_mapping(em_tree, logical, length); + read_unlock(&em_tree->lock); + + if (!em) + return -EINVAL; + + map = em->map_lookup; + + alloc_offsets = kcalloc(map->num_stripes, sizeof(*alloc_offsets), GFP_NOFS); + if (!alloc_offsets) { + free_extent_map(em); + return -ENOMEM; + } + + for (i = 0; i < map->num_stripes; i++) { + bool is_sequential; + struct blk_zone zone; + struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; + int dev_replace_is_ongoing = 0; + + device = map->stripes[i].dev; + physical = map->stripes[i].physical; + + if (device->bdev == NULL) { + alloc_offsets[i] = WP_MISSING_DEV; + continue; + } + + is_sequential = btrfs_dev_is_sequential(device, physical); + if (is_sequential) + num_sequential++; + else + num_conventional++; + + if (!is_sequential) { + alloc_offsets[i] = WP_CONVENTIONAL; + continue; + } + + /* + * This zone will be used for allocation, so mark this zone + * non-empty. + */ + btrfs_dev_clear_zone_empty(device, physical); + + down_read(&dev_replace->rwsem); + dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(dev_replace); + if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL) + btrfs_dev_clear_zone_empty(dev_replace->tgtdev, physical); + up_read(&dev_replace->rwsem); + + /* + * The group is mapped to a sequential zone. Get the zone write + * pointer to determine the allocation offset within the zone. + */ + WARN_ON(!IS_ALIGNED(physical, fs_info->zone_size)); + nofs_flag = memalloc_nofs_save(); + ret = btrfs_get_dev_zone(device, physical, &zone); + memalloc_nofs_restore(nofs_flag); + if (ret == -EIO || ret == -EOPNOTSUPP) { + ret = 0; + alloc_offsets[i] = WP_MISSING_DEV; + continue; + } else if (ret) { + goto out; + } + + switch (zone.cond) { + case BLK_ZONE_COND_OFFLINE: + case BLK_ZONE_COND_READONLY: + btrfs_err(fs_info, + "zoned: offline/readonly zone %llu on device %s (devid %llu)", + physical >> device->zone_info->zone_size_shift, + rcu_str_deref(device->name), device->devid); + alloc_offsets[i] = WP_MISSING_DEV; + break; + case BLK_ZONE_COND_EMPTY: + alloc_offsets[i] = 0; + break; + case BLK_ZONE_COND_FULL: + alloc_offsets[i] = fs_info->zone_size; + break; + default: + /* Partially used zone */ + alloc_offsets[i] = + ((zone.wp - zone.start) << SECTOR_SHIFT); + break; + } + } + + if (num_sequential > 0) + cache->seq_zone = true; + + if (num_conventional > 0) { + /* + * Avoid calling calculate_alloc_pointer() for new BG. It + * is no use for new BG. It must be always 0. + * + * Also, we have a lock chain of extent buffer lock -> + * chunk mutex. For new BG, this function is called from + * btrfs_make_block_group() which is already taking the + * chunk mutex. Thus, we cannot call + * calculate_alloc_pointer() which takes extent buffer + * locks to avoid deadlock. + */ + if (new) { + cache->alloc_offset = 0; + goto out; + } + ret = calculate_alloc_pointer(cache, &last_alloc); + if (ret || map->num_stripes == num_conventional) { + if (!ret) + cache->alloc_offset = last_alloc; + else + btrfs_err(fs_info, + "zoned: failed to determine allocation offset of bg %llu", + cache->start); + goto out; + } + } + + switch (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) { + case 0: /* single */ + cache->alloc_offset = alloc_offsets[0]; + break; + case BTRFS_BLOCK_GROUP_DUP: + case BTRFS_BLOCK_GROUP_RAID1: + case BTRFS_BLOCK_GROUP_RAID0: + case BTRFS_BLOCK_GROUP_RAID10: + case BTRFS_BLOCK_GROUP_RAID5: + case BTRFS_BLOCK_GROUP_RAID6: + /* non-single profiles are not supported yet */ + default: + btrfs_err(fs_info, "zoned: profile %s not yet supported", + btrfs_bg_type_to_raid_name(map->type)); + ret = -EINVAL; + goto out; + } + +out: + /* An extent is allocated after the write pointer */ + if (!ret && num_conventional && last_alloc > cache->alloc_offset) { + btrfs_err(fs_info, + "zoned: got wrong write pointer in BG %llu: %llu > %llu", + logical, last_alloc, cache->alloc_offset); + ret = -EIO; + } + + if (!ret) + cache->meta_write_pointer = cache->alloc_offset + cache->start; + + kfree(alloc_offsets); + free_extent_map(em); + + return ret; +} + +void btrfs_calc_zone_unusable(struct btrfs_block_group *cache) +{ + u64 unusable, free; + + if (!btrfs_is_zoned(cache->fs_info)) + return; + + WARN_ON(cache->bytes_super != 0); + unusable = cache->alloc_offset - cache->used; + free = cache->length - cache->alloc_offset; + + /* We only need ->free_space in ALLOC_SEQ block groups */ + cache->last_byte_to_unpin = (u64)-1; + cache->cached = BTRFS_CACHE_FINISHED; + cache->free_space_ctl->free_space = free; + cache->zone_unusable = unusable; + + /* Should not have any excluded extents. Just in case, though */ + btrfs_free_excluded_extents(cache); +} + +void btrfs_redirty_list_add(struct btrfs_transaction *trans, + struct extent_buffer *eb) +{ + struct btrfs_fs_info *fs_info = eb->fs_info; + + if (!btrfs_is_zoned(fs_info) || + btrfs_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN) || + !list_empty(&eb->release_list)) + return; + + set_extent_buffer_dirty(eb); + set_extent_bits_nowait(&trans->dirty_pages, eb->start, + eb->start + eb->len - 1, EXTENT_DIRTY); + memzero_extent_buffer(eb, 0, eb->len); + set_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags); + + spin_lock(&trans->releasing_ebs_lock); + list_add_tail(&eb->release_list, &trans->releasing_ebs); + spin_unlock(&trans->releasing_ebs_lock); + atomic_inc(&eb->refs); +} + +void btrfs_free_redirty_list(struct btrfs_transaction *trans) +{ + spin_lock(&trans->releasing_ebs_lock); + while (!list_empty(&trans->releasing_ebs)) { + struct extent_buffer *eb; + + eb = list_first_entry(&trans->releasing_ebs, + struct extent_buffer, release_list); + list_del_init(&eb->release_list); + free_extent_buffer(eb); + } + spin_unlock(&trans->releasing_ebs_lock); +} + +bool btrfs_use_zone_append(struct btrfs_inode *inode, struct extent_map *em) +{ + struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct btrfs_block_group *cache; + bool ret = false; + + if (!btrfs_is_zoned(fs_info)) + return false; + + if (!fs_info->max_zone_append_size) + return false; + + if (!is_data_inode(&inode->vfs_inode)) + return false; + + cache = btrfs_lookup_block_group(fs_info, em->block_start); + ASSERT(cache); + if (!cache) + return false; + + ret = cache->seq_zone; + btrfs_put_block_group(cache); + + return ret; +} + +void btrfs_record_physical_zoned(struct inode *inode, u64 file_offset, + struct bio *bio) +{ + struct btrfs_ordered_extent *ordered; + const u64 physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; + + if (bio_op(bio) != REQ_OP_ZONE_APPEND) + return; + + ordered = btrfs_lookup_ordered_extent(BTRFS_I(inode), file_offset); + if (WARN_ON(!ordered)) + return; + + ordered->physical = physical; + ordered->disk = bio->bi_disk; + ordered->partno = bio->bi_partno; + + btrfs_put_ordered_extent(ordered); +} + +void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered) +{ + struct btrfs_inode *inode = BTRFS_I(ordered->inode); + struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct extent_map_tree *em_tree; + struct extent_map *em; + struct btrfs_ordered_sum *sum; + struct block_device *bdev; + u64 orig_logical = ordered->disk_bytenr; + u64 *logical = NULL; + int nr, stripe_len; + + /* Zoned devices should not have partitions. So, we can assume it is 0 */ + ASSERT(ordered->partno == 0); + bdev = bdgrab(ordered->disk->part0); + if (WARN_ON(!bdev)) + return; + + if (WARN_ON(btrfs_rmap_block(fs_info, orig_logical, bdev, + ordered->physical, &logical, &nr, + &stripe_len))) + goto out; + + WARN_ON(nr != 1); + + if (orig_logical == *logical) + goto out; + + ordered->disk_bytenr = *logical; + + em_tree = &inode->extent_tree; + write_lock(&em_tree->lock); + em = search_extent_mapping(em_tree, ordered->file_offset, + ordered->num_bytes); + em->block_start = *logical; + free_extent_map(em); + write_unlock(&em_tree->lock); + + list_for_each_entry(sum, &ordered->list, list) { + if (*logical < orig_logical) + sum->bytenr -= orig_logical - *logical; + else + sum->bytenr += *logical - orig_logical; + } + +out: + kfree(logical); + bdput(bdev); +} + +bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info, + struct extent_buffer *eb, + struct btrfs_block_group **cache_ret) +{ + struct btrfs_block_group *cache; + bool ret = true; + + if (!btrfs_is_zoned(fs_info)) + return true; + + cache = *cache_ret; + + if (cache && (eb->start < cache->start || + cache->start + cache->length <= eb->start)) { + btrfs_put_block_group(cache); + cache = NULL; + *cache_ret = NULL; + } + + if (!cache) + cache = btrfs_lookup_block_group(fs_info, eb->start); + + if (cache) { + if (cache->meta_write_pointer != eb->start) { + btrfs_put_block_group(cache); + cache = NULL; + ret = false; + } else { + cache->meta_write_pointer = eb->start + eb->len; + } + + *cache_ret = cache; + } + + return ret; +} + +void btrfs_revert_meta_write_pointer(struct btrfs_block_group *cache, + struct extent_buffer *eb) +{ + if (!btrfs_is_zoned(eb->fs_info) || !cache) + return; + + ASSERT(cache->meta_write_pointer == eb->start + eb->len); + cache->meta_write_pointer = eb->start; +} + +int btrfs_zoned_issue_zeroout(struct btrfs_device *device, u64 physical, u64 length) +{ + if (!btrfs_dev_is_sequential(device, physical)) + return -EOPNOTSUPP; + + return blkdev_issue_zeroout(device->bdev, physical >> SECTOR_SHIFT, + length >> SECTOR_SHIFT, GFP_NOFS, 0); +} + +static int read_zone_info(struct btrfs_fs_info *fs_info, u64 logical, + struct blk_zone *zone) +{ + struct btrfs_bio *bbio = NULL; + u64 mapped_length = PAGE_SIZE; + unsigned int nofs_flag; + int nmirrors; + int i, ret; + + ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical, + &mapped_length, &bbio); + if (ret || !bbio || mapped_length < PAGE_SIZE) { + btrfs_put_bbio(bbio); + return -EIO; + } + + if (bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) + return -EINVAL; + + nofs_flag = memalloc_nofs_save(); + nmirrors = (int)bbio->num_stripes; + for (i = 0; i < nmirrors; i++) { + u64 physical = bbio->stripes[i].physical; + struct btrfs_device *dev = bbio->stripes[i].dev; + + /* Missing device */ + if (!dev->bdev) + continue; + + ret = btrfs_get_dev_zone(dev, physical, zone); + /* Failing device */ + if (ret == -EIO || ret == -EOPNOTSUPP) + continue; + break; + } + memalloc_nofs_restore(nofs_flag); + + return ret; +} + +/* + * Synchronize write pointer in a zone at @physical_start on @tgt_dev, by + * filling zeros between @physical_pos to a write pointer of dev-replace + * source device. + */ +int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev, u64 logical, + u64 physical_start, u64 physical_pos) +{ + struct btrfs_fs_info *fs_info = tgt_dev->fs_info; + struct blk_zone zone; + u64 length; + u64 wp; + int ret; + + if (!btrfs_dev_is_sequential(tgt_dev, physical_pos)) + return 0; + + ret = read_zone_info(fs_info, logical, &zone); + if (ret) + return ret; + + wp = physical_start + ((zone.wp - zone.start) << SECTOR_SHIFT); + + if (physical_pos == wp) + return 0; + + if (physical_pos > wp) + return -EUCLEAN; + + length = wp - physical_pos; + return btrfs_zoned_issue_zeroout(tgt_dev, physical_pos, length); +} diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h index 8abe2f83272b..61e969652fe1 100644 --- a/fs/btrfs/zoned.h +++ b/fs/btrfs/zoned.h @@ -7,6 +7,7 @@ #include #include "volumes.h" #include "disk-io.h" +#include "block-group.h" struct btrfs_zoned_device_info { /* @@ -25,6 +26,7 @@ struct btrfs_zoned_device_info { #ifdef CONFIG_BLK_DEV_ZONED int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, struct blk_zone *zone); +int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info); int btrfs_get_dev_zone_info(struct btrfs_device *device); void btrfs_destroy_dev_zone_info(struct btrfs_device *device); int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info); @@ -35,6 +37,28 @@ int btrfs_sb_log_location(struct btrfs_device *device, int mirror, int rw, u64 *bytenr_ret); void btrfs_advance_sb_log(struct btrfs_device *device, int mirror); int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror); +u64 btrfs_find_allocatable_zones(struct btrfs_device *device, u64 hole_start, + u64 hole_end, u64 num_bytes); +int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical, + u64 length, u64 *bytes); +int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size); +int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new); +void btrfs_calc_zone_unusable(struct btrfs_block_group *cache); +void btrfs_redirty_list_add(struct btrfs_transaction *trans, + struct extent_buffer *eb); +void btrfs_free_redirty_list(struct btrfs_transaction *trans); +bool btrfs_use_zone_append(struct btrfs_inode *inode, struct extent_map *em); +void btrfs_record_physical_zoned(struct inode *inode, u64 file_offset, + struct bio *bio); +void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered); +bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info, + struct extent_buffer *eb, + struct btrfs_block_group **cache_ret); +void btrfs_revert_meta_write_pointer(struct btrfs_block_group *cache, + struct extent_buffer *eb); +int btrfs_zoned_issue_zeroout(struct btrfs_device *device, u64 physical, u64 length); +int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev, u64 logical, + u64 physical_start, u64 physical_pos); #else /* CONFIG_BLK_DEV_ZONED */ static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, struct blk_zone *zone) @@ -42,6 +66,11 @@ static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, return 0; } +static inline int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info) +{ + return 0; +} + static inline int btrfs_get_dev_zone_info(struct btrfs_device *device) { return 0; @@ -85,6 +114,78 @@ static inline int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror return 0; } +static inline u64 btrfs_find_allocatable_zones(struct btrfs_device *device, + u64 hole_start, u64 hole_end, + u64 num_bytes) +{ + return hole_start; +} + +static inline int btrfs_reset_device_zone(struct btrfs_device *device, + u64 physical, u64 length, u64 *bytes) +{ + *bytes = 0; + return 0; +} + +static inline int btrfs_ensure_empty_zones(struct btrfs_device *device, + u64 start, u64 size) +{ + return 0; +} + +static inline int btrfs_load_block_group_zone_info( + struct btrfs_block_group *cache, bool new) +{ + return 0; +} + +static inline void btrfs_calc_zone_unusable(struct btrfs_block_group *cache) { } + +static inline void btrfs_redirty_list_add(struct btrfs_transaction *trans, + struct extent_buffer *eb) { } +static inline void btrfs_free_redirty_list(struct btrfs_transaction *trans) { } + +static inline bool btrfs_use_zone_append(struct btrfs_inode *inode, + struct extent_map *em) +{ + return false; +} + +static inline void btrfs_record_physical_zoned(struct inode *inode, + u64 file_offset, struct bio *bio) +{ +} + +static inline void btrfs_rewrite_logical_zoned( + struct btrfs_ordered_extent *ordered) { } + +static inline bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info, + struct extent_buffer *eb, + struct btrfs_block_group **cache_ret) +{ + return true; +} + +static inline void btrfs_revert_meta_write_pointer( + struct btrfs_block_group *cache, + struct extent_buffer *eb) +{ +} + +static inline int btrfs_zoned_issue_zeroout(struct btrfs_device *device, + u64 physical, u64 length) +{ + return -EOPNOTSUPP; +} + +static inline int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev, + u64 logical, u64 physical_start, + u64 physical_pos) +{ + return -EOPNOTSUPP; +} + #endif static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos) @@ -136,12 +237,16 @@ static inline void btrfs_dev_clear_zone_empty(struct btrfs_device *device, u64 p static inline bool btrfs_check_device_zone_type(const struct btrfs_fs_info *fs_info, struct block_device *bdev) { - u64 zone_size; - if (btrfs_is_zoned(fs_info)) { - zone_size = bdev_zone_sectors(bdev) << SECTOR_SHIFT; - /* Do not allow non-zoned device */ - return bdev_is_zoned(bdev) && fs_info->zone_size == zone_size; + /* + * We can allow a regular device on a zoned filesystem, because + * we will emulate the zoned capabilities. + */ + if (!bdev_is_zoned(bdev)) + return true; + + return fs_info->zone_size == + (bdev_zone_sectors(bdev) << SECTOR_SHIFT); } /* Do not allow Host Manged zoned device */ @@ -157,4 +262,46 @@ static inline bool btrfs_check_super_location(struct btrfs_device *device, u64 p return device->zone_info == NULL || !btrfs_dev_is_sequential(device, pos); } +static inline bool btrfs_can_zone_reset(struct btrfs_device *device, + u64 physical, u64 length) +{ + u64 zone_size; + + if (!btrfs_dev_is_sequential(device, physical)) + return false; + + zone_size = device->zone_info->zone_size; + if (!IS_ALIGNED(physical, zone_size) || !IS_ALIGNED(length, zone_size)) + return false; + + return true; +} + +static inline void btrfs_zoned_meta_io_lock(struct btrfs_fs_info *fs_info) +{ + if (!btrfs_is_zoned(fs_info)) + return; + mutex_lock(&fs_info->zoned_meta_io_lock); +} + +static inline void btrfs_zoned_meta_io_unlock(struct btrfs_fs_info *fs_info) +{ + if (!btrfs_is_zoned(fs_info)) + return; + mutex_unlock(&fs_info->zoned_meta_io_lock); +} + +static inline void btrfs_clear_treelog_bg(struct btrfs_block_group *bg) +{ + struct btrfs_fs_info *fs_info = bg->fs_info; + + if (!btrfs_is_zoned(fs_info)) + return; + + spin_lock(&fs_info->treelog_bg_lock); + if (fs_info->treelog_bg == bg->start) + fs_info->treelog_bg = 0; + spin_unlock(&fs_info->treelog_bg_lock); +} + #endif diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c index 2c557229696a..95e72d271b95 100644 --- a/fs/compat_binfmt_elf.c +++ b/fs/compat_binfmt_elf.c @@ -50,6 +50,7 @@ * which requires asm/elf.h to define compat_elf_gregset_t et al. */ #define elf_prstatus compat_elf_prstatus +#define elf_prstatus_common compat_elf_prstatus_common #define elf_prpsinfo compat_elf_prpsinfo #undef ns_to_kernel_old_timeval @@ -61,7 +62,6 @@ * differ from the native ones, or omitted when they match. */ -#undef ELF_ARCH #undef elf_check_arch #define elf_check_arch compat_elf_check_arch @@ -90,11 +90,6 @@ #define ELF_ET_DYN_BASE COMPAT_ELF_ET_DYN_BASE #endif -#ifdef COMPAT_ELF_EXEC_PAGESIZE -#undef ELF_EXEC_PAGESIZE -#define ELF_EXEC_PAGESIZE COMPAT_ELF_EXEC_PAGESIZE -#endif - #ifdef COMPAT_ELF_PLAT_INIT #undef ELF_PLAT_INIT #define ELF_PLAT_INIT COMPAT_ELF_PLAT_INIT diff --git a/fs/fcntl.c b/fs/fcntl.c index 05b36b28f2e8..483ef8861376 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -148,11 +148,15 @@ void f_delown(struct file *filp) pid_t f_getown(struct file *filp) { - pid_t pid; + pid_t pid = 0; read_lock(&filp->f_owner.lock); - pid = pid_vnr(filp->f_owner.pid); - if (filp->f_owner.pid_type == PIDTYPE_PGID) - pid = -pid; + rcu_read_lock(); + if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) { + pid = pid_vnr(filp->f_owner.pid); + if (filp->f_owner.pid_type == PIDTYPE_PGID) + pid = -pid; + } + rcu_read_unlock(); read_unlock(&filp->f_owner.lock); return pid; } @@ -200,11 +204,14 @@ static int f_setown_ex(struct file *filp, unsigned long arg) static int f_getown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; - struct f_owner_ex owner; + struct f_owner_ex owner = {}; int ret = 0; read_lock(&filp->f_owner.lock); - owner.pid = pid_vnr(filp->f_owner.pid); + rcu_read_lock(); + if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) + owner.pid = pid_vnr(filp->f_owner.pid); + rcu_read_unlock(); switch (filp->f_owner.pid_type) { case PIDTYPE_PID: owner.type = F_OWNER_TID; diff --git a/fs/internal.h b/fs/internal.h index 77c50befbfbe..cff1f30cfefb 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -15,6 +15,7 @@ struct mount; struct shrink_control; struct fs_context; struct user_namespace; +struct pipe_inode_info; /* * block_dev.c @@ -193,3 +194,11 @@ int sb_init_dio_done_wq(struct super_block *sb); */ int do_statx(int dfd, const char __user *filename, unsigned flags, unsigned int mask, struct statx __user *buffer); + +/* + * fs/splice.c: + */ +long splice_file_to_pipe(struct file *in, + struct pipe_inode_info *opipe, + loff_t *offset, + size_t len, unsigned int flags); diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 70488904a778..1ef1f7795bce 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -205,6 +205,34 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos, iomap_dio_submit_bio(dio, iomap, bio, pos); } +/* + * Figure out the bio's operation flags from the dio request, the + * mapping, and whether or not we want FUA. Note that we can end up + * clearing the WRITE_FUA flag in the dio request. + */ +static inline unsigned int +iomap_dio_bio_opflags(struct iomap_dio *dio, struct iomap *iomap, bool use_fua) +{ + unsigned int opflags = REQ_SYNC | REQ_IDLE; + + if (!(dio->flags & IOMAP_DIO_WRITE)) { + WARN_ON_ONCE(iomap->flags & IOMAP_F_ZONE_APPEND); + return REQ_OP_READ; + } + + if (iomap->flags & IOMAP_F_ZONE_APPEND) + opflags |= REQ_OP_ZONE_APPEND; + else + opflags |= REQ_OP_WRITE; + + if (use_fua) + opflags |= REQ_FUA; + else + dio->flags &= ~IOMAP_DIO_WRITE_FUA; + + return opflags; +} + static loff_t iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, struct iomap_dio *dio, struct iomap *iomap) @@ -212,6 +240,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, unsigned int blkbits = blksize_bits(bdev_logical_block_size(iomap->bdev)); unsigned int fs_block_size = i_blocksize(inode), pad; unsigned int align = iov_iter_alignment(dio->submit.iter); + unsigned int bio_opf; struct bio *bio; bool need_zeroout = false; bool use_fua = false; @@ -268,6 +297,13 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, iomap_dio_zero(dio, iomap, pos - pad, pad); } + /* + * Set the operation flags early so that bio_iov_iter_get_pages + * can set up the page vector appropriately for a ZONE_APPEND + * operation. + */ + bio_opf = iomap_dio_bio_opflags(dio, iomap, use_fua); + do { size_t n; if (dio->error) { @@ -285,6 +321,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, bio->bi_ioprio = dio->iocb->ki_ioprio; bio->bi_private = dio; bio->bi_end_io = iomap_dio_bio_end_io; + bio->bi_opf = bio_opf; ret = bio_iov_iter_get_pages(bio, dio->submit.iter); if (unlikely(ret)) { @@ -300,14 +337,8 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, n = bio->bi_iter.bi_size; if (dio->flags & IOMAP_DIO_WRITE) { - bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE; - if (use_fua) - bio->bi_opf |= REQ_FUA; - else - dio->flags &= ~IOMAP_DIO_WRITE_FUA; task_io_account_write(n); } else { - bio->bi_opf = REQ_OP_READ; if (dio->flags & IOMAP_DIO_DIRTY) bio_set_pages_dirty(bio); } diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index 94b7c1cb5ceb..7aee15608619 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -1656,7 +1656,7 @@ s64 dbDiscardAG(struct inode *ip, int agno, s64 minlen) } else if (rc == -ENOSPC) { /* search for next smaller log2 block */ l2nb = BLKSTOL2(nblocks) - 1; - nblocks = 1 << l2nb; + nblocks = 1LL << l2nb; } else { /* Trim any already allocated blocks */ jfs_error(bmp->db_ipbmap->i_sb, "-EIO\n"); diff --git a/fs/jfs/jfs_filsys.h b/fs/jfs/jfs_filsys.h index 1e899298f7f0..b5d702df7111 100644 --- a/fs/jfs/jfs_filsys.h +++ b/fs/jfs/jfs_filsys.h @@ -268,5 +268,6 @@ * fsck() must be run to repair */ #define FM_EXTENDFS 0x00000008 /* file system extendfs() in progress */ +#define FM_STATE_MAX 0x0000000f /* max value of s_state */ #endif /* _H_JFS_FILSYS */ diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c index 2935d4c776ec..5d7d7170c03c 100644 --- a/fs/jfs/jfs_mount.c +++ b/fs/jfs/jfs_mount.c @@ -37,6 +37,7 @@ #include #include #include +#include #include "jfs_incore.h" #include "jfs_filsys.h" @@ -366,6 +367,15 @@ static int chkSuper(struct super_block *sb) sbi->bsize = bsize; sbi->l2bsize = le16_to_cpu(j_sb->s_l2bsize); + /* check some fields for possible corruption */ + if (sbi->l2bsize != ilog2((u32)bsize) || + j_sb->pad != 0 || + le32_to_cpu(j_sb->s_state) > FM_STATE_MAX) { + rc = -EINVAL; + jfs_err("jfs_mount: Mount Failure: superblock is corrupt!"); + goto out; + } + /* * For now, ignore s_pbsize, l2bfactor. All I/O going through buffer * cache. diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index dca8edd2378c..053295cd7bc6 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -148,10 +148,10 @@ static struct { /* * forward references */ -static int diLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, - struct tlock * tlck, struct commit * cd); -static int dataLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, - struct tlock * tlck); +static void diLog(struct jfs_log *log, struct tblock *tblk, struct lrd *lrd, + struct tlock *tlck, struct commit *cd); +static void dataLog(struct jfs_log *log, struct tblock *tblk, struct lrd *lrd, + struct tlock *tlck); static void dtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, struct tlock * tlck); static void mapLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, @@ -159,8 +159,8 @@ static void mapLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, static void txAllocPMap(struct inode *ip, struct maplock * maplock, struct tblock * tblk); static void txForce(struct tblock * tblk); -static int txLog(struct jfs_log * log, struct tblock * tblk, - struct commit * cd); +static void txLog(struct jfs_log *log, struct tblock *tblk, + struct commit *cd); static void txUpdateMap(struct tblock * tblk); static void txRelease(struct tblock * tblk); static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, @@ -1256,8 +1256,7 @@ int txCommit(tid_t tid, /* transaction identifier */ * * txUpdateMap() resets XAD_NEW in XAD. */ - if ((rc = txLog(log, tblk, &cd))) - goto TheEnd; + txLog(log, tblk, &cd); /* * Ensure that inode isn't reused before @@ -1365,9 +1364,8 @@ int txCommit(tid_t tid, /* transaction identifier */ * * RETURN : */ -static int txLog(struct jfs_log * log, struct tblock * tblk, struct commit * cd) +static void txLog(struct jfs_log *log, struct tblock *tblk, struct commit *cd) { - int rc = 0; struct inode *ip; lid_t lid; struct tlock *tlck; @@ -1414,7 +1412,7 @@ static int txLog(struct jfs_log * log, struct tblock * tblk, struct commit * cd) } } - return rc; + return; } /* @@ -1422,10 +1420,9 @@ static int txLog(struct jfs_log * log, struct tblock * tblk, struct commit * cd) * * function: log inode tlock and format maplock to update bmap; */ -static int diLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, - struct tlock * tlck, struct commit * cd) +static void diLog(struct jfs_log *log, struct tblock *tblk, struct lrd *lrd, + struct tlock *tlck, struct commit *cd) { - int rc = 0; struct metapage *mp; pxd_t *pxd; struct pxd_lock *pxdlock; @@ -1527,7 +1524,7 @@ static int diLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, } #endif /* _JFS_WIP */ - return rc; + return; } /* @@ -1535,8 +1532,8 @@ static int diLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, * * function: log data tlock */ -static int dataLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, - struct tlock * tlck) +static void dataLog(struct jfs_log *log, struct tblock *tblk, struct lrd *lrd, + struct tlock *tlck) { struct metapage *mp; pxd_t *pxd; @@ -1562,7 +1559,7 @@ static int dataLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, metapage_homeok(mp); discard_metapage(mp); tlck->mp = NULL; - return 0; + return; } PXDaddress(pxd, mp->index); @@ -1573,7 +1570,7 @@ static int dataLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, /* mark page as homeward bound */ tlck->flag |= tlckWRITEPAGE; - return 0; + return; } /* diff --git a/fs/namei.c b/fs/namei.c index 44bc01aac801..8bf667880779 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -633,6 +633,11 @@ static inline bool legitimize_path(struct nameidata *nd, static bool legitimize_links(struct nameidata *nd) { int i; + if (unlikely(nd->flags & LOOKUP_CACHED)) { + drop_links(nd); + nd->depth = 0; + return false; + } for (i = 0; i < nd->depth; i++) { struct saved *last = nd->stack + i; if (unlikely(!legitimize_path(nd, &last->link, last->seq))) { @@ -672,17 +677,17 @@ static bool legitimize_root(struct nameidata *nd) */ /** - * unlazy_walk - try to switch to ref-walk mode. + * try_to_unlazy - try to switch to ref-walk mode. * @nd: nameidata pathwalk data - * Returns: 0 on success, -ECHILD on failure + * Returns: true on success, false on failure * - * unlazy_walk attempts to legitimize the current nd->path and nd->root + * try_to_unlazy attempts to legitimize the current nd->path and nd->root * for ref-walk mode. * Must be called from rcu-walk context. - * Nothing should touch nameidata between unlazy_walk() failure and + * Nothing should touch nameidata between try_to_unlazy() failure and * terminate_walk(). */ -static int unlazy_walk(struct nameidata *nd) +static bool try_to_unlazy(struct nameidata *nd) { struct dentry *parent = nd->path.dentry; @@ -697,30 +702,30 @@ static int unlazy_walk(struct nameidata *nd) goto out; rcu_read_unlock(); BUG_ON(nd->inode != parent->d_inode); - return 0; + return true; out1: nd->path.mnt = NULL; nd->path.dentry = NULL; out: rcu_read_unlock(); - return -ECHILD; + return false; } /** - * unlazy_child - try to switch to ref-walk mode. + * try_to_unlazy_next - try to switch to ref-walk mode. * @nd: nameidata pathwalk data - * @dentry: child of nd->path.dentry - * @seq: seq number to check dentry against - * Returns: 0 on success, -ECHILD on failure + * @dentry: next dentry to step into + * @seq: seq number to check @dentry against + * Returns: true on success, false on failure * - * unlazy_child attempts to legitimize the current nd->path, nd->root and dentry - * for ref-walk mode. @dentry must be a path found by a do_lookup call on - * @nd. Must be called from rcu-walk context. - * Nothing should touch nameidata between unlazy_child() failure and + * Similar to to try_to_unlazy(), but here we have the next dentry already + * picked by rcu-walk and want to legitimize that in addition to the current + * nd->path and nd->root for ref-walk mode. Must be called from rcu-walk context. + * Nothing should touch nameidata between try_to_unlazy_next() failure and * terminate_walk(). */ -static int unlazy_child(struct nameidata *nd, struct dentry *dentry, unsigned seq) +static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry, unsigned seq) { BUG_ON(!(nd->flags & LOOKUP_RCU)); @@ -750,7 +755,7 @@ static int unlazy_child(struct nameidata *nd, struct dentry *dentry, unsigned se if (unlikely(!legitimize_root(nd))) goto out_dput; rcu_read_unlock(); - return 0; + return true; out2: nd->path.mnt = NULL; @@ -758,11 +763,11 @@ out1: nd->path.dentry = NULL; out: rcu_read_unlock(); - return -ECHILD; + return false; out_dput: rcu_read_unlock(); dput(dentry); - return -ECHILD; + return false; } static inline int d_revalidate(struct dentry *dentry, unsigned int flags) @@ -870,7 +875,8 @@ static int complete_walk(struct nameidata *nd) */ if (!(nd->flags & (LOOKUP_ROOT | LOOKUP_IS_SCOPED))) nd->root.mnt = NULL; - if (unlikely(unlazy_walk(nd))) + nd->flags &= ~LOOKUP_CACHED; + if (!try_to_unlazy(nd)) return -ECHILD; } @@ -1456,7 +1462,7 @@ static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry, return -ENOENT; if (likely(__follow_mount_rcu(nd, path, inode, seqp))) return 0; - if (unlazy_child(nd, dentry, seq)) + if (!try_to_unlazy_next(nd, dentry, seq)) return -ECHILD; // *path might've been clobbered by __follow_mount_rcu() path->mnt = nd->path.mnt; @@ -1550,7 +1556,7 @@ static struct dentry *lookup_fast(struct nameidata *nd, unsigned seq; dentry = __d_lookup_rcu(parent, &nd->last, &seq); if (unlikely(!dentry)) { - if (unlazy_walk(nd)) + if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); return NULL; } @@ -1577,9 +1583,9 @@ static struct dentry *lookup_fast(struct nameidata *nd, status = d_revalidate(dentry, nd->flags); if (likely(status > 0)) return dentry; - if (unlazy_child(nd, dentry, seq)) + if (!try_to_unlazy_next(nd, dentry, seq)) return ERR_PTR(-ECHILD); - if (unlikely(status == -ECHILD)) + if (status == -ECHILD) /* we'd been told to redo it in non-rcu mode */ status = d_revalidate(dentry, nd->flags); } else { @@ -1651,10 +1657,8 @@ static inline int may_lookup(struct nameidata *nd) { if (nd->flags & LOOKUP_RCU) { int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK); - if (err != -ECHILD) + if (err != -ECHILD || !try_to_unlazy(nd)) return err; - if (unlazy_walk(nd)) - return -ECHILD; } return inode_permission(nd->inode, MAY_EXEC); } @@ -1676,7 +1680,7 @@ static int reserve_stack(struct nameidata *nd, struct path *link, unsigned seq) // unlazy even if we fail to grab the link - cleanup needs it bool grabbed_link = legitimize_path(nd, link, seq); - if (unlazy_walk(nd) != 0 || !grabbed_link) + if (!try_to_unlazy(nd) != 0 || !grabbed_link) return -ECHILD; if (nd_alloc_stack(nd)) @@ -1718,7 +1722,7 @@ static const char *pick_link(struct nameidata *nd, struct path *link, touch_atime(&last->link); cond_resched(); } else if (atime_needs_update(&last->link, inode)) { - if (unlikely(unlazy_walk(nd))) + if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); touch_atime(&last->link); } @@ -1735,11 +1739,8 @@ static const char *pick_link(struct nameidata *nd, struct path *link, get = inode->i_op->get_link; if (nd->flags & LOOKUP_RCU) { res = get(NULL, inode, &last->done); - if (res == ERR_PTR(-ECHILD)) { - if (unlikely(unlazy_walk(nd))) - return ERR_PTR(-ECHILD); + if (res == ERR_PTR(-ECHILD) && try_to_unlazy(nd)) res = get(link->dentry, inode, &last->done); - } } else { res = get(link->dentry, inode, &last->done); } @@ -2279,7 +2280,7 @@ OK: } if (unlikely(!d_can_lookup(nd->path.dentry))) { if (nd->flags & LOOKUP_RCU) { - if (unlazy_walk(nd)) + if (!try_to_unlazy(nd)) return -ECHILD; } return -ENOTDIR; @@ -2293,6 +2294,10 @@ static const char *path_init(struct nameidata *nd, unsigned flags) int error; const char *s = nd->name->name; + /* LOOKUP_CACHED requires RCU, ask caller to retry */ + if ((flags & (LOOKUP_RCU | LOOKUP_CACHED)) == LOOKUP_CACHED) + return ERR_PTR(-EAGAIN); + if (!*s) flags &= ~LOOKUP_RCU; if (flags & LOOKUP_RCU) @@ -3213,7 +3218,6 @@ static const char *open_last_lookups(struct nameidata *nd, struct inode *inode; struct dentry *dentry; const char *res; - int error; nd->flags |= op->intent; @@ -3237,9 +3241,8 @@ static const char *open_last_lookups(struct nameidata *nd, } else { /* create side of things */ if (nd->flags & LOOKUP_RCU) { - error = unlazy_walk(nd); - if (unlikely(error)) - return ERR_PTR(error); + if (!try_to_unlazy(nd)) + return ERR_PTR(-ECHILD); } audit_inode(nd->name, dir, AUDIT_INODE_PARENT); /* trailing slashes? */ @@ -3248,9 +3251,7 @@ static const char *open_last_lookups(struct nameidata *nd, } if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) { - error = mnt_want_write(nd->path.mnt); - if (!error) - got_write = true; + got_write = !mnt_want_write(nd->path.mnt); /* * do _not_ fail yet - we might not need that or fail with * a different error; let lookup_open() decide; we'll be @@ -3409,10 +3410,8 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags, audit_inode(nd->name, child, 0); /* Don't check for other permissions, the inode was just created */ error = may_open(&path, 0, op->open_flag); - if (error) - goto out2; - file->f_path.mnt = path.mnt; - error = finish_open(file, child, NULL); + if (!error) + error = vfs_open(&path, file); out2: mnt_drop_write(path.mnt); out: diff --git a/fs/open.c b/fs/open.c index 1e06e443a565..ca5444733acd 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1091,6 +1091,12 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op) lookup_flags |= LOOKUP_BENEATH; if (how->resolve & RESOLVE_IN_ROOT) lookup_flags |= LOOKUP_IN_ROOT; + if (how->resolve & RESOLVE_CACHED) { + /* Don't bother even trying for create/truncate/tmpfile open */ + if (flags & (O_TRUNC | O_CREAT | O_TMPFILE)) + return -EAGAIN; + lookup_flags |= LOOKUP_CACHED; + } op->lookup_flags = lookup_flags; return 0; diff --git a/fs/read_write.c b/fs/read_write.c index 75f764b43418..9db7adf160d2 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1188,6 +1188,7 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, { struct fd in, out; struct inode *in_inode, *out_inode; + struct pipe_inode_info *opipe; loff_t pos; loff_t out_pos; ssize_t retval; @@ -1228,9 +1229,6 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, in_inode = file_inode(in.file); out_inode = file_inode(out.file); out_pos = out.file->f_pos; - retval = rw_verify_area(WRITE, out.file, &out_pos, count); - if (retval < 0) - goto fput_out; if (!max) max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes); @@ -1253,9 +1251,18 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, if (in.file->f_flags & O_NONBLOCK) fl = SPLICE_F_NONBLOCK; #endif - file_start_write(out.file); - retval = do_splice_direct(in.file, &pos, out.file, &out_pos, count, fl); - file_end_write(out.file); + opipe = get_pipe_info(out.file, true); + if (!opipe) { + retval = rw_verify_area(WRITE, out.file, &out_pos, count); + if (retval < 0) + goto fput_out; + file_start_write(out.file); + retval = do_splice_direct(in.file, &pos, out.file, &out_pos, + count, fl); + file_end_write(out.file); + } else { + retval = splice_file_to_pipe(in.file, opipe, &pos, count, fl); + } if (retval > 0) { add_rchar(current, retval); diff --git a/fs/splice.c b/fs/splice.c index 866d5c2367b2..b06846f1e6ee 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -771,11 +771,16 @@ static long do_splice_to(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { + unsigned int p_space; int ret; if (unlikely(!(in->f_mode & FMODE_READ))) return -EBADF; + /* Don't try to read more the pipe has space for. */ + p_space = pipe->max_usage - pipe_occupancy(pipe->head, pipe->tail); + len = min_t(size_t, len, p_space << PAGE_SHIFT); + ret = rw_verify_area(READ, in, ppos, len); if (unlikely(ret < 0)) return ret; @@ -856,15 +861,10 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, WARN_ON_ONCE(!pipe_empty(pipe->head, pipe->tail)); while (len) { - unsigned int p_space; size_t read_len; loff_t pos = sd->pos, prev_pos = pos; - /* Don't try to read more the pipe has space for. */ - p_space = pipe->max_usage - - pipe_occupancy(pipe->head, pipe->tail); - read_len = min_t(size_t, len, p_space << PAGE_SHIFT); - ret = do_splice_to(in, &pos, pipe, read_len, flags); + ret = do_splice_to(in, &pos, pipe, len, flags); if (unlikely(ret <= 0)) goto out_release; @@ -1002,6 +1002,23 @@ static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe, struct pipe_inode_info *opipe, size_t len, unsigned int flags); +long splice_file_to_pipe(struct file *in, + struct pipe_inode_info *opipe, + loff_t *offset, + size_t len, unsigned int flags) +{ + long ret; + + pipe_lock(opipe); + ret = wait_for_space(opipe, flags); + if (!ret) + ret = do_splice_to(in, offset, opipe, len, flags); + pipe_unlock(opipe); + if (ret > 0) + wakeup_pipe_readers(opipe); + return ret; +} + /* * Determine where to splice to/from. */ @@ -1081,20 +1098,7 @@ long do_splice(struct file *in, loff_t *off_in, struct file *out, if (out->f_flags & O_NONBLOCK) flags |= SPLICE_F_NONBLOCK; - pipe_lock(opipe); - ret = wait_for_space(opipe, flags); - if (!ret) { - unsigned int p_space; - - /* Don't try to read more the pipe has space for. */ - p_space = opipe->max_usage - pipe_occupancy(opipe->head, opipe->tail); - len = min_t(size_t, len, p_space << PAGE_SHIFT); - - ret = do_splice_to(in, &offset, opipe, len, flags); - } - pipe_unlock(opipe); - if (ret > 0) - wakeup_pipe_readers(opipe); + ret = splice_file_to_pipe(in, opipe, &offset, len, flags); if (!off_in) in->f_pos = offset; else diff --git a/include/acpi/acbuffer.h b/include/acpi/acbuffer.h index 531c1e9a7d10..18197c16149f 100644 --- a/include/acpi/acbuffer.h +++ b/include/acpi/acbuffer.h @@ -3,7 +3,7 @@ * * Name: acbuffer.h - Support for buffers returned by ACPI predefined names * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acconfig.h b/include/acpi/acconfig.h index a225eff499c8..e92f84fa8c68 100644 --- a/include/acpi/acconfig.h +++ b/include/acpi/acconfig.h @@ -3,7 +3,7 @@ * * Name: acconfig.h - Global configuration constants * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acexcep.h b/include/acpi/acexcep.h index 2fc624a61769..ea3b1c41bc79 100644 --- a/include/acpi/acexcep.h +++ b/include/acpi/acexcep.h @@ -3,7 +3,7 @@ * * Name: acexcep.h - Exception codes returned by the ACPI subsystem * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ @@ -59,11 +59,11 @@ struct acpi_exception_info { #define AE_OK (acpi_status) 0x0000 -#define ACPI_ENV_EXCEPTION(status) (status & AE_CODE_ENVIRONMENTAL) -#define ACPI_AML_EXCEPTION(status) (status & AE_CODE_AML) -#define ACPI_PROG_EXCEPTION(status) (status & AE_CODE_PROGRAMMER) -#define ACPI_TABLE_EXCEPTION(status) (status & AE_CODE_ACPI_TABLES) -#define ACPI_CNTL_EXCEPTION(status) (status & AE_CODE_CONTROL) +#define ACPI_ENV_EXCEPTION(status) (((status) & AE_CODE_MASK) == AE_CODE_ENVIRONMENTAL) +#define ACPI_AML_EXCEPTION(status) (((status) & AE_CODE_MASK) == AE_CODE_AML) +#define ACPI_PROG_EXCEPTION(status) (((status) & AE_CODE_MASK) == AE_CODE_PROGRAMMER) +#define ACPI_TABLE_EXCEPTION(status) (((status) & AE_CODE_MASK) == AE_CODE_ACPI_TABLES) +#define ACPI_CNTL_EXCEPTION(status) (((status) & AE_CODE_MASK) == AE_CODE_CONTROL) /* * Environmental exceptions diff --git a/include/acpi/acnames.h b/include/acpi/acnames.h index 8922edb32730..a2bc381c7ce7 100644 --- a/include/acpi/acnames.h +++ b/include/acpi/acnames.h @@ -3,7 +3,7 @@ * * Name: acnames.h - Global names and strings * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acoutput.h b/include/acpi/acoutput.h index c5d900c0ecda..1538a6853822 100644 --- a/include/acpi/acoutput.h +++ b/include/acpi/acoutput.h @@ -3,7 +3,7 @@ * * Name: acoutput.h -- debug output * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acpi.h b/include/acpi/acpi.h index e3e8051d4812..6f6282a862bc 100644 --- a/include/acpi/acpi.h +++ b/include/acpi/acpi.h @@ -3,7 +3,7 @@ * * Name: acpi.h - Master public include file used to interface to ACPICA * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acpi_drivers.h b/include/acpi/acpi_drivers.h index d4f39a20aa2a..94d356fcc483 100644 --- a/include/acpi/acpi_drivers.h +++ b/include/acpi/acpi_drivers.h @@ -15,19 +15,12 @@ * Please update drivers/acpi/debug.c and Documentation/firmware-guide/acpi/debug.rst * if you add to this list. */ -#define ACPI_BUS_COMPONENT 0x00010000 -#define ACPI_AC_COMPONENT 0x00020000 -#define ACPI_BATTERY_COMPONENT 0x00040000 -#define ACPI_BUTTON_COMPONENT 0x00080000 #define ACPI_SBS_COMPONENT 0x00100000 #define ACPI_FAN_COMPONENT 0x00200000 #define ACPI_PCI_COMPONENT 0x00400000 -#define ACPI_POWER_COMPONENT 0x00800000 #define ACPI_CONTAINER_COMPONENT 0x01000000 #define ACPI_SYSTEM_COMPONENT 0x02000000 -#define ACPI_THERMAL_COMPONENT 0x04000000 #define ACPI_MEMORY_DEVICE_COMPONENT 0x08000000 -#define ACPI_VIDEO_COMPONENT 0x10000000 #define ACPI_PROCESSOR_COMPONENT 0x20000000 /* diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h index 33bb8c9a089d..690c369b717a 100644 --- a/include/acpi/acpiosxf.h +++ b/include/acpi/acpiosxf.h @@ -5,7 +5,7 @@ * interfaces must be implemented by OSL to interface the * ACPI components to the host operating system. * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 0bba8b8c350e..370293ee8399 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -3,7 +3,7 @@ * * Name: acpixf.h - External interfaces to the ACPI subsystem * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ @@ -12,7 +12,7 @@ /* Current ACPICA subsystem version in YYYYMMDD format */ -#define ACPI_CA_VERSION 0x20201113 +#define ACPI_CA_VERSION 0x20210105 #include #include diff --git a/include/acpi/acrestyp.h b/include/acpi/acrestyp.h index d3521894ce6a..9bccac9becd7 100644 --- a/include/acpi/acrestyp.h +++ b/include/acpi/acrestyp.h @@ -3,7 +3,7 @@ * * Name: acrestyp.h - Defines, types, and structures for resource descriptors * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h index 5007c41f4d54..f9cda909f92c 100644 --- a/include/acpi/actbl.h +++ b/include/acpi/actbl.h @@ -3,7 +3,7 @@ * * Name: actbl.h - Basic ACPI Table Definitions * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index 43549547ed3e..ea1c2998d54e 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -3,7 +3,7 @@ * * Name: actbl1.h - Additional ACPI table definitions * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index ec66779cb193..d6478c430c99 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -3,7 +3,7 @@ * * Name: actbl2.h - ACPI Table Definitions (tables not in ACPI spec) * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ @@ -33,7 +33,6 @@ #define ACPI_SIG_MPST "MPST" /* Memory Power State Table */ #define ACPI_SIG_MSCT "MSCT" /* Maximum System Characteristics Table */ #define ACPI_SIG_MSDM "MSDM" /* Microsoft Data Management Table */ -#define ACPI_SIG_MTMR "MTMR" /* MID Timer table */ #define ACPI_SIG_NFIT "NFIT" /* NVDIMM Firmware Interface Table */ #define ACPI_SIG_PCCT "PCCT" /* Platform Communications Channel Table */ #define ACPI_SIG_PDTT "PDTT" /* Platform Debug Trigger Table */ @@ -935,29 +934,6 @@ struct acpi_table_msdm { struct acpi_table_header header; /* Common ACPI table header */ }; -/******************************************************************************* - * - * MTMR - MID Timer Table - * Version 1 - * - * Conforms to "Simple Firmware Interface Specification", - * Draft 0.8.2, Oct 19, 2010 - * NOTE: The ACPI MTMR is equivalent to the SFI MTMR table. - * - ******************************************************************************/ - -struct acpi_table_mtmr { - struct acpi_table_header header; /* Common ACPI table header */ -}; - -/* MTMR entry */ - -struct acpi_mtmr_entry { - struct acpi_generic_address physical_address; - u32 frequency; - u32 irq; -}; - /******************************************************************************* * * NFIT - NVDIMM Interface Table (ACPI 6.0+) diff --git a/include/acpi/actbl3.h b/include/acpi/actbl3.h index bdcac69fa6bd..df5f4b27f3aa 100644 --- a/include/acpi/actbl3.h +++ b/include/acpi/actbl3.h @@ -3,7 +3,7 @@ * * Name: actbl3.h - ACPI Table Definitions * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ @@ -33,7 +33,6 @@ #define ACPI_SIG_TCPA "TCPA" /* Trusted Computing Platform Alliance table */ #define ACPI_SIG_TPM2 "TPM2" /* Trusted Platform Module 2.0 H/W interface table */ #define ACPI_SIG_UEFI "UEFI" /* Uefi Boot Optimization Table */ -#define ACPI_SIG_VRTC "VRTC" /* Virtual Real Time Clock Table */ #define ACPI_SIG_WAET "WAET" /* Windows ACPI Emulated devices Table */ #define ACPI_SIG_WDAT "WDAT" /* Watchdog Action Table */ #define ACPI_SIG_WDDT "WDDT" /* Watchdog Timer Description Table */ @@ -484,28 +483,6 @@ struct acpi_table_uefi { u16 data_offset; /* Offset of remaining data in table */ }; -/******************************************************************************* - * - * VRTC - Virtual Real Time Clock Table - * Version 1 - * - * Conforms to "Simple Firmware Interface Specification", - * Draft 0.8.2, Oct 19, 2010 - * NOTE: The ACPI VRTC is equivalent to The SFI MRTC table. - * - ******************************************************************************/ - -struct acpi_table_vrtc { - struct acpi_table_header header; /* Common ACPI table header */ -}; - -/* VRTC entry */ - -struct acpi_vrtc_entry { - struct acpi_generic_address physical_address; - u32 irq; -}; - /******************************************************************************* * * WAET - Windows ACPI Emulated devices Table diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index 647cb11d0a0a..92c71dfce0d5 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -3,7 +3,7 @@ * * Name: actypes.h - Common data types for the entire ACPI subsystem * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ @@ -1286,4 +1286,10 @@ typedef enum { #define ACPI_OPT_END -1 +/* Definitions for explicit fallthrough */ + +#ifndef ACPI_FALLTHROUGH +#define ACPI_FALLTHROUGH do {} while(0) +#endif + #endif /* __ACTYPES_H__ */ diff --git a/include/acpi/acuuid.h b/include/acpi/acuuid.h index fb7d8d1fd93c..a5c2ca019a12 100644 --- a/include/acpi/acuuid.h +++ b/include/acpi/acuuid.h @@ -3,7 +3,7 @@ * * Name: acuuid.h - ACPI-related UUID/GUID definitions * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h index 232838d28f50..c7fc4524e151 100644 --- a/include/acpi/cppc_acpi.h +++ b/include/acpi/cppc_acpi.h @@ -39,7 +39,7 @@ struct cpc_reg { u8 bit_width; u8 bit_offset; u8 access_width; - u64 __iomem address; + u64 address; } __packed; /* diff --git a/include/acpi/platform/acenv.h b/include/acpi/platform/acenv.h index 8f6b2654c0b3..e8958e0d1646 100644 --- a/include/acpi/platform/acenv.h +++ b/include/acpi/platform/acenv.h @@ -3,7 +3,7 @@ * * Name: acenv.h - Host and compiler configuration * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acenvex.h b/include/acpi/platform/acenvex.h index c3facf5f8495..277fe2fa4d9b 100644 --- a/include/acpi/platform/acenvex.h +++ b/include/acpi/platform/acenvex.h @@ -3,7 +3,7 @@ * * Name: acenvex.h - Extra host and compiler configuration * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acgcc.h b/include/acpi/platform/acgcc.h index 7d63d03cf507..0cd4f61d4248 100644 --- a/include/acpi/platform/acgcc.h +++ b/include/acpi/platform/acgcc.h @@ -3,7 +3,7 @@ * * Name: acgcc.h - GCC specific defines, etc. * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ @@ -54,4 +54,19 @@ typedef __builtin_va_list va_list; #define ACPI_USE_NATIVE_MATH64 +/* GCC did not support __has_attribute until 5.1. */ + +#ifndef __has_attribute +#define __has_attribute(x) 0 +#endif + +/* + * Explictly mark intentional explicit fallthrough to silence + * -Wimplicit-fallthrough in GCC 7.1+. + */ + +#if __has_attribute(__fallthrough__) +#define ACPI_FALLTHROUGH __attribute__((__fallthrough__)) +#endif + #endif /* __ACGCC_H__ */ diff --git a/include/acpi/platform/acgccex.h b/include/acpi/platform/acgccex.h index 7c88fd1de955..738d52865e0a 100644 --- a/include/acpi/platform/acgccex.h +++ b/include/acpi/platform/acgccex.h @@ -3,7 +3,7 @@ * * Name: acgccex.h - Extra GCC specific defines, etc. * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acintel.h b/include/acpi/platform/acintel.h index e7fd5e71be62..550fe9a8cd6c 100644 --- a/include/acpi/platform/acintel.h +++ b/include/acpi/platform/acintel.h @@ -3,7 +3,7 @@ * * Name: acintel.h - VC specific defines, etc. * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h index 72f52a1342a0..b3ffb9bbf664 100644 --- a/include/acpi/platform/aclinux.h +++ b/include/acpi/platform/aclinux.h @@ -3,7 +3,7 @@ * * Name: aclinux.h - OS specific defines, etc. for Linux * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/aclinuxex.h b/include/acpi/platform/aclinuxex.h index 04f88f2de781..5f642b07ad64 100644 --- a/include/acpi/platform/aclinuxex.h +++ b/include/acpi/platform/aclinuxex.h @@ -3,7 +3,7 @@ * * Name: aclinuxex.h - Extra OS specific defines, etc. for Linux * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index b97c628ad91f..52dbd58f6810 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -316,6 +316,16 @@ #define THERMAL_TABLE(name) #endif +#ifdef CONFIG_DTPM +#define DTPM_TABLE() \ + . = ALIGN(8); \ + __dtpm_table = .; \ + KEEP(*(__dtpm_table)) \ + __dtpm_table_end = .; +#else +#define DTPM_TABLE() +#endif + #define KERNEL_DTB() \ STRUCT_ALIGN(); \ __dtb_start = .; \ @@ -733,6 +743,7 @@ ACPI_PROBE_TABLE(irqchip) \ ACPI_PROBE_TABLE(timer) \ THERMAL_TABLE(governor) \ + DTPM_TABLE() \ EARLYCON_TABLE() \ LSM_TABLE() \ EARLY_LSM_TABLE() \ diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 68eef9e67dcb..d33c3cfb1794 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1124,14 +1124,6 @@ acpi_data_add_props(struct acpi_device_data *data, const guid_t *guid, int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr); -int acpi_dev_prop_read_single(struct acpi_device *adev, - const char *propname, enum dev_prop_type proptype, - void *val); -int acpi_node_prop_read(const struct fwnode_handle *fwnode, - const char *propname, enum dev_prop_type proptype, - void *val, size_t nval); -int acpi_dev_prop_read(const struct acpi_device *adev, const char *propname, - enum dev_prop_type proptype, void *val, size_t nval); struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child); @@ -1233,30 +1225,6 @@ static inline int acpi_node_prop_get(const struct fwnode_handle *fwnode, return -ENXIO; } -static inline int acpi_dev_prop_read_single(const struct acpi_device *adev, - const char *propname, - enum dev_prop_type proptype, - void *val) -{ - return -ENXIO; -} - -static inline int acpi_node_prop_read(const struct fwnode_handle *fwnode, - const char *propname, - enum dev_prop_type proptype, - void *val, size_t nval) -{ - return -ENXIO; -} - -static inline int acpi_dev_prop_read(const struct acpi_device *adev, - const char *propname, - enum dev_prop_type proptype, - void *val, size_t nval) -{ - return -ENXIO; -} - static inline struct fwnode_handle * acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child) diff --git a/include/linux/bio.h b/include/linux/bio.h index 1edda614f7ce..de62911473bb 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -455,6 +455,8 @@ void bio_chain(struct bio *, struct bio *); extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); +int bio_add_zone_append_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int offset); bool __bio_try_merge_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off, bool *same_page); void __bio_add_page(struct bio *bio, struct page *page, diff --git a/include/linux/clk.h b/include/linux/clk.h index 31ff1bf1b79f..a4a86aa8b11a 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -238,6 +238,7 @@ static inline bool clk_is_match(const struct clk *p, const struct clk *q) #endif +#ifdef CONFIG_HAVE_CLK_PREPARE /** * clk_prepare - prepare a clock source * @clk: clock source @@ -246,10 +247,26 @@ static inline bool clk_is_match(const struct clk *p, const struct clk *q) * * Must not be called from within atomic context. */ -#ifdef CONFIG_HAVE_CLK_PREPARE int clk_prepare(struct clk *clk); int __must_check clk_bulk_prepare(int num_clks, const struct clk_bulk_data *clks); + +/** + * clk_is_enabled_when_prepared - indicate if preparing a clock also enables it. + * @clk: clock source + * + * Returns true if clk_prepare() implicitly enables the clock, effectively + * making clk_enable()/clk_disable() no-ops, false otherwise. + * + * This is of interest mainly to the power management code where actually + * disabling the clock also requires unpreparing it to have any material + * effect. + * + * Regardless of the value returned here, the caller must always invoke + * clk_enable() or clk_prepare_enable() and counterparts for usage counts + * to be right. + */ +bool clk_is_enabled_when_prepared(struct clk *clk); #else static inline int clk_prepare(struct clk *clk) { @@ -263,6 +280,11 @@ clk_bulk_prepare(int num_clks, const struct clk_bulk_data *clks) might_sleep(); return 0; } + +static inline bool clk_is_enabled_when_prepared(struct clk *clk) +{ + return false; +} #endif /** diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 03393dc30f20..41710d07ac6a 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -387,14 +387,22 @@ struct cpufreq_driver { /* flags */ -/* driver isn't removed even if all ->init() calls failed */ -#define CPUFREQ_STICKY BIT(0) +/* + * Set by drivers that need to update internale upper and lower boundaries along + * with the target frequency and so the core and governors should also invoke + * the diver if the target frequency does not change, but the policy min or max + * may have changed. + */ +#define CPUFREQ_NEED_UPDATE_LIMITS BIT(0) /* loops_per_jiffy or other kernel "constants" aren't affected by frequency transitions */ #define CPUFREQ_CONST_LOOPS BIT(1) -/* don't warn on suspend/resume speed mismatches */ -#define CPUFREQ_PM_NO_WARN BIT(2) +/* + * Set by drivers that want the core to automatically register the cpufreq + * driver as a thermal cooling device. + */ +#define CPUFREQ_IS_COOLING_DEV BIT(2) /* * This should be set by platforms having multiple clock-domains, i.e. @@ -426,20 +434,6 @@ struct cpufreq_driver { */ #define CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING BIT(6) -/* - * Set by drivers that want the core to automatically register the cpufreq - * driver as a thermal cooling device. - */ -#define CPUFREQ_IS_COOLING_DEV BIT(7) - -/* - * Set by drivers that need to update internale upper and lower boundaries along - * with the target frequency and so the core and governors should also invoke - * the diver if the target frequency does not change, but the policy min or max - * may have changed. - */ -#define CPUFREQ_NEED_UPDATE_LIMITS BIT(8) - int cpufreq_register_driver(struct cpufreq_driver *driver_data); int cpufreq_unregister_driver(struct cpufreq_driver *driver_data); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 0042ef362511..ee09a39627d6 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -193,6 +193,7 @@ enum cpuhp_state { CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, CPUHP_AP_X86_HPET_ONLINE, CPUHP_AP_X86_KVM_CLK_ONLINE, + CPUHP_AP_DTPM_CPU_ONLINE, CPUHP_AP_ACTIVE, CPUHP_ONLINE, }; diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index b6d3bae1c74d..26ea0850be9b 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -137,6 +137,7 @@ struct devfreq_stats { * using devfreq. * @profile: device-specific devfreq profile * @governor: method how to choose frequency based on the usage. + * @opp_table: Reference to OPP table of dev.parent, if one exists. * @nb: notifier block used to notify devfreq object that it should * reevaluate operable frequencies. Devfreq users may use * devfreq.nb to the corresponding register notifier call chain. @@ -173,6 +174,7 @@ struct devfreq { struct device dev; struct devfreq_dev_profile *profile; const struct devfreq_governor *governor; + struct opp_table *opp_table; struct notifier_block nb; struct delayed_work work; diff --git a/include/linux/dtpm.h b/include/linux/dtpm.h new file mode 100644 index 000000000000..e80a332e3d8a --- /dev/null +++ b/include/linux/dtpm.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Linaro Ltd + * + * Author: Daniel Lezcano + */ +#ifndef ___DTPM_H__ +#define ___DTPM_H__ + +#include + +#define MAX_DTPM_DESCR 8 +#define MAX_DTPM_CONSTRAINTS 1 + +struct dtpm { + struct powercap_zone zone; + struct dtpm *parent; + struct list_head sibling; + struct list_head children; + struct dtpm_ops *ops; + unsigned long flags; + u64 power_limit; + u64 power_max; + u64 power_min; + int weight; + void *private; +}; + +struct dtpm_ops { + u64 (*set_power_uw)(struct dtpm *, u64); + u64 (*get_power_uw)(struct dtpm *); + void (*release)(struct dtpm *); +}; + +struct dtpm_descr; + +typedef int (*dtpm_init_t)(struct dtpm_descr *); + +struct dtpm_descr { + struct dtpm *parent; + const char *name; + dtpm_init_t init; +}; + +/* Init section thermal table */ +extern struct dtpm_descr *__dtpm_table[]; +extern struct dtpm_descr *__dtpm_table_end[]; + +#define DTPM_TABLE_ENTRY(name) \ + static typeof(name) *__dtpm_table_entry_##name \ + __used __section("__dtpm_table") = &name + +#define DTPM_DECLARE(name) DTPM_TABLE_ENTRY(name) + +#define for_each_dtpm_table(__dtpm) \ + for (__dtpm = __dtpm_table; \ + __dtpm < __dtpm_table_end; \ + __dtpm++) + +static inline struct dtpm *to_dtpm(struct powercap_zone *zone) +{ + return container_of(zone, struct dtpm, zone); +} + +int dtpm_update_power(struct dtpm *dtpm, u64 power_min, u64 power_max); + +int dtpm_release_zone(struct powercap_zone *pcz); + +struct dtpm *dtpm_alloc(struct dtpm_ops *ops); + +void dtpm_unregister(struct dtpm *dtpm); + +int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent); + +int dtpm_register_cpu(struct dtpm *parent); + +#endif diff --git a/include/linux/elfcore-compat.h b/include/linux/elfcore-compat.h index 10485f0c9740..e272c3d452ce 100644 --- a/include/linux/elfcore-compat.h +++ b/include/linux/elfcore-compat.h @@ -17,7 +17,7 @@ struct compat_elf_siginfo compat_int_t si_errno; }; -struct compat_elf_prstatus +struct compat_elf_prstatus_common { struct compat_elf_siginfo pr_info; short pr_cursig; @@ -31,8 +31,6 @@ struct compat_elf_prstatus struct old_timeval32 pr_stime; struct old_timeval32 pr_cutime; struct old_timeval32 pr_cstime; - compat_elf_gregset_t pr_reg; - compat_int_t pr_fpvalid; }; struct compat_elf_prpsinfo @@ -49,4 +47,15 @@ struct compat_elf_prpsinfo char pr_psargs[ELF_PRARGSZ]; }; +#ifdef CONFIG_ARCH_HAS_ELFCORE_COMPAT +#include +#endif + +struct compat_elf_prstatus +{ + struct compat_elf_prstatus_common common; + compat_elf_gregset_t pr_reg; + compat_int_t pr_fpvalid; +}; + #endif /* _LINUX_ELFCORE_COMPAT_H */ diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index de51c1bef27d..2aaa15779d50 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -29,7 +29,7 @@ struct elf_siginfo * the SVR4 structure, but more Linuxy, with things that Linux does * not support and which gdb doesn't really use excluded. */ -struct elf_prstatus +struct elf_prstatus_common { struct elf_siginfo pr_info; /* Info associated with signal */ short pr_cursig; /* Current signal */ @@ -43,6 +43,11 @@ struct elf_prstatus struct __kernel_old_timeval pr_stime; /* System time */ struct __kernel_old_timeval pr_cutime; /* Cumulative user time */ struct __kernel_old_timeval pr_cstime; /* Cumulative system time */ +}; + +struct elf_prstatus +{ + struct elf_prstatus_common common; elf_gregset_t pr_reg; /* GP registers */ int pr_fpvalid; /* True if math co-processor being used. */ }; diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h index 921e750843e6..766fcd973beb 100644 --- a/include/linux/fcntl.h +++ b/include/linux/fcntl.h @@ -19,7 +19,7 @@ /* List of all valid flags for the how->resolve argument: */ #define VALID_RESOLVE_FLAGS \ (RESOLVE_NO_XDEV | RESOLVE_NO_MAGICLINKS | RESOLVE_NO_SYMLINKS | \ - RESOLVE_BENEATH | RESOLVE_IN_ROOT) + RESOLVE_BENEATH | RESOLVE_IN_ROOT | RESOLVE_CACHED) /* List of all open_how "versions". */ #define OPEN_HOW_SIZE_VER0 24 /* sizeof first published struct */ diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 5bd3cac4df9c..8ebb1fa6f3b7 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -55,6 +55,7 @@ struct vm_fault; #define IOMAP_F_SHARED 0x04 #define IOMAP_F_MERGED 0x08 #define IOMAP_F_BUFFER_HEAD 0x10 +#define IOMAP_F_ZONE_APPEND 0x20 /* * Flags set by the core iomap code during operations: diff --git a/include/linux/namei.h b/include/linux/namei.h index a4bb992623c4..b9605b2b46e7 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -46,6 +46,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; #define LOOKUP_NO_XDEV 0x040000 /* No mountpoint crossing. */ #define LOOKUP_BENEATH 0x080000 /* No escaping from starting point. */ #define LOOKUP_IN_ROOT 0x100000 /* Treat dirfd as fs root. */ +#define LOOKUP_CACHED 0x200000 /* Only do cached lookup */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) diff --git a/include/linux/platform_profile.h b/include/linux/platform_profile.h new file mode 100644 index 000000000000..a26542d53058 --- /dev/null +++ b/include/linux/platform_profile.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Platform profile sysfs interface + * + * See Documentation/ABI/testing/sysfs-platform_profile.rst for more + * information. + */ + +#ifndef _PLATFORM_PROFILE_H_ +#define _PLATFORM_PROFILE_H_ + +#include + +/* + * If more options are added please update profile_names + * array in platform-profile.c and sysfs-platform-profile.rst + * documentation. + */ + +enum platform_profile_option { + PLATFORM_PROFILE_LOW_POWER, + PLATFORM_PROFILE_COOL, + PLATFORM_PROFILE_QUIET, + PLATFORM_PROFILE_BALANCED, + PLATFORM_PROFILE_PERFORMANCE, + PLATFORM_PROFILE_LAST, /*must always be last */ +}; + +struct platform_profile_handler { + unsigned long choices[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)]; + int (*profile_get)(struct platform_profile_handler *pprof, + enum platform_profile_option *profile); + int (*profile_set)(struct platform_profile_handler *pprof, + enum platform_profile_option profile); +}; + +int platform_profile_register(struct platform_profile_handler *pprof); +int platform_profile_remove(void); +void platform_profile_notify(void); + +#endif /*_PLATFORM_PROFILE_H_*/ diff --git a/include/linux/pm.h b/include/linux/pm.h index 47aca6bac1d6..482313a8ccfc 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -537,6 +537,8 @@ struct pm_subsys_data { spinlock_t lock; unsigned int refcount; #ifdef CONFIG_PM_CLK + unsigned int clock_op_might_sleep; + struct mutex clock_mutex; struct list_head clock_list; #endif #ifdef CONFIG_PM_GENERIC_DOMAINS diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 2ca919ae8d36..dfcfbcecc34b 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -9,6 +9,7 @@ #define _LINUX_PM_DOMAIN_H #include +#include #include #include #include @@ -55,6 +56,10 @@ * * GENPD_FLAG_RPM_ALWAYS_ON: Instructs genpd to always keep the PM domain * powered on except for system suspend. + * + * GENPD_FLAG_MIN_RESIDENCY: Enable the genpd governor to consider its + * components' next wakeup when determining the + * optimal idle state. */ #define GENPD_FLAG_PM_CLK (1U << 0) #define GENPD_FLAG_IRQ_SAFE (1U << 1) @@ -62,6 +67,7 @@ #define GENPD_FLAG_ACTIVE_WAKEUP (1U << 3) #define GENPD_FLAG_CPU_DOMAIN (1U << 4) #define GENPD_FLAG_RPM_ALWAYS_ON (1U << 5) +#define GENPD_FLAG_MIN_RESIDENCY (1U << 6) enum gpd_status { GENPD_STATE_ON = 0, /* PM domain is on */ @@ -129,6 +135,7 @@ struct generic_pm_domain { unsigned int state); struct gpd_dev_ops dev_ops; s64 max_off_time_ns; /* Maximum allowed "suspended" time. */ + ktime_t next_wakeup; /* Maintained by the domain governor */ bool max_off_time_changed; bool cached_power_down_ok; bool cached_power_down_state_idx; @@ -191,6 +198,7 @@ struct generic_pm_domain_data { struct notifier_block *power_nb; int cpu; unsigned int performance_state; + ktime_t next_wakeup; void *data; }; @@ -217,6 +225,7 @@ int pm_genpd_remove(struct generic_pm_domain *genpd); int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state); int dev_pm_genpd_add_notifier(struct device *dev, struct notifier_block *nb); int dev_pm_genpd_remove_notifier(struct device *dev); +void dev_pm_genpd_set_next_wakeup(struct device *dev, ktime_t next); extern struct dev_power_governor simple_qos_governor; extern struct dev_power_governor pm_domain_always_on_gov; @@ -275,6 +284,9 @@ static inline int dev_pm_genpd_remove_notifier(struct device *dev) return -EOPNOTSUPP; } +static inline void dev_pm_genpd_set_next_wakeup(struct device *dev, ktime_t next) +{ } + #define simple_qos_governor (*(struct dev_power_governor *)(NULL)) #define pm_domain_always_on_gov (*(struct dev_power_governor *)(NULL)) #endif diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 1435c054016a..c0371efa4a0f 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -98,6 +98,9 @@ unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp); unsigned int dev_pm_opp_get_level(struct dev_pm_opp *opp); +unsigned int dev_pm_opp_get_required_pstate(struct dev_pm_opp *opp, + unsigned int index); + bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp); int dev_pm_opp_get_opp_count(struct device *dev); @@ -111,6 +114,8 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, bool available); struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev, unsigned int level); +struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev, + unsigned int *level); struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, unsigned long *freq); @@ -143,28 +148,32 @@ struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name) void dev_pm_opp_put_prop_name(struct opp_table *opp_table); struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count); void dev_pm_opp_put_regulators(struct opp_table *opp_table); -struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char * name); +struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char *name); void dev_pm_opp_put_clkname(struct opp_table *opp_table); struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table); +struct opp_table *devm_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs); void dev_pm_opp_detach_genpd(struct opp_table *opp_table); +struct opp_table *devm_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs); +struct dev_pm_opp *dev_pm_opp_xlate_required_opp(struct opp_table *src_table, struct opp_table *dst_table, struct dev_pm_opp *src_opp); int dev_pm_opp_xlate_performance_state(struct opp_table *src_table, struct opp_table *dst_table, unsigned int pstate); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); -int dev_pm_opp_set_bw(struct device *dev, struct dev_pm_opp *opp); +int dev_pm_opp_set_opp(struct device *dev, struct dev_pm_opp *opp); int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask); int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask); void dev_pm_opp_remove_table(struct device *dev); void dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask); +int dev_pm_opp_sync_regulators(struct device *dev); #else static inline struct opp_table *dev_pm_opp_get_opp_table(struct device *dev) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline struct opp_table *dev_pm_opp_get_opp_table_indexed(struct device *dev, int index) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline void dev_pm_opp_put_opp_table(struct opp_table *opp_table) {} @@ -184,6 +193,13 @@ static inline unsigned int dev_pm_opp_get_level(struct dev_pm_opp *opp) return 0; } +static inline +unsigned int dev_pm_opp_get_required_pstate(struct dev_pm_opp *opp, + unsigned int index) +{ + return 0; +} + static inline bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp) { return false; @@ -217,31 +233,37 @@ static inline unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev) static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq, bool available) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev, unsigned int level) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); +} + +static inline struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev, + unsigned int *level) +{ + return ERR_PTR(-EOPNOTSUPP); } static inline struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, unsigned long *freq) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline struct dev_pm_opp *dev_pm_opp_find_freq_ceil_by_volt(struct device *dev, unsigned long u_volt) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev, unsigned long *freq) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline void dev_pm_opp_put(struct dev_pm_opp *opp) {} @@ -249,7 +271,7 @@ static inline void dev_pm_opp_put(struct dev_pm_opp *opp) {} static inline int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline void dev_pm_opp_remove(struct device *dev, unsigned long freq) @@ -280,19 +302,19 @@ static inline int dev_pm_opp_disable(struct device *dev, unsigned long freq) static inline int dev_pm_opp_register_notifier(struct device *dev, struct notifier_block *nb) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int dev_pm_opp_unregister_notifier(struct device *dev, struct notifier_block *nb) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions, unsigned int count) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline void dev_pm_opp_put_supported_hw(struct opp_table *opp_table) {} @@ -300,57 +322,76 @@ static inline void dev_pm_opp_put_supported_hw(struct opp_table *opp_table) {} static inline struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table) {} +static inline struct opp_table * +devm_pm_opp_register_set_opp_helper(struct device *dev, + int (*set_opp)(struct dev_pm_set_opp_data *data)) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline void dev_pm_opp_put_prop_name(struct opp_table *opp_table) {} static inline struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline void dev_pm_opp_put_regulators(struct opp_table *opp_table) {} -static inline struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char * name) +static inline struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char *name) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline void dev_pm_opp_put_clkname(struct opp_table *opp_table) {} static inline struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline void dev_pm_opp_detach_genpd(struct opp_table *opp_table) {} +static inline struct opp_table *devm_pm_opp_attach_genpd(struct device *dev, + const char **names, struct device ***virt_devs) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline struct dev_pm_opp *dev_pm_opp_xlate_required_opp(struct opp_table *src_table, + struct opp_table *dst_table, struct dev_pm_opp *src_opp) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline int dev_pm_opp_xlate_performance_state(struct opp_table *src_table, struct opp_table *dst_table, unsigned int pstate) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) { - return -ENOTSUPP; + return -EOPNOTSUPP; } -static inline int dev_pm_opp_set_bw(struct device *dev, struct dev_pm_opp *opp) +static inline int dev_pm_opp_set_opp(struct device *dev, struct dev_pm_opp *opp) { return -EOPNOTSUPP; } static inline int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask) @@ -366,11 +407,17 @@ static inline void dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask { } +static inline int dev_pm_opp_sync_regulators(struct device *dev) +{ + return -EOPNOTSUPP; +} + #endif /* CONFIG_PM_OPP */ #if defined(CONFIG_PM_OPP) && defined(CONFIG_OF) int dev_pm_opp_of_add_table(struct device *dev); int dev_pm_opp_of_add_table_indexed(struct device *dev, int index); +int dev_pm_opp_of_add_table_noclk(struct device *dev, int index); void dev_pm_opp_of_remove_table(struct device *dev); int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask); void dev_pm_opp_of_cpumask_remove_table(const struct cpumask *cpumask); @@ -387,12 +434,17 @@ static inline void dev_pm_opp_of_unregister_em(struct device *dev) #else static inline int dev_pm_opp_of_add_table(struct device *dev) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int dev_pm_opp_of_add_table_indexed(struct device *dev, int index) { - return -ENOTSUPP; + return -EOPNOTSUPP; +} + +static inline int dev_pm_opp_of_add_table_noclk(struct device *dev, int index) +{ + return -EOPNOTSUPP; } static inline void dev_pm_opp_of_remove_table(struct device *dev) @@ -401,7 +453,7 @@ static inline void dev_pm_opp_of_remove_table(struct device *dev) static inline int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline void dev_pm_opp_of_cpumask_remove_table(const struct cpumask *cpumask) @@ -410,7 +462,7 @@ static inline void dev_pm_opp_of_cpumask_remove_table(const struct cpumask *cpum static inline int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev) @@ -426,7 +478,7 @@ static inline struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp) static inline int dev_pm_opp_of_register_em(struct device *dev, struct cpumask *cpus) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline void dev_pm_opp_of_unregister_em(struct device *dev) @@ -435,12 +487,12 @@ static inline void dev_pm_opp_of_unregister_em(struct device *dev) static inline int of_get_required_opp_performance_state(struct device_node *np, int index) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int dev_pm_opp_of_find_icc_paths(struct device *dev, struct opp_table *opp_table) { - return -ENOTSUPP; + return -EOPNOTSUPP; } #endif diff --git a/include/linux/units.h b/include/linux/units.h index 5c115c809507..dcc30a53fa93 100644 --- a/include/linux/units.h +++ b/include/linux/units.h @@ -4,6 +4,10 @@ #include +#define MILLIWATT_PER_WATT 1000L +#define MICROWATT_PER_MILLIWATT 1000L +#define MICROWATT_PER_WATT 1000000L + #define ABSOLUTE_ZERO_MILLICELSIUS -273150 static inline long milli_kelvin_to_millicelsius(long t) diff --git a/include/linux/zstd.h b/include/linux/zstd.h index 249575e2485f..e87f78c9b19c 100644 --- a/include/linux/zstd.h +++ b/include/linux/zstd.h @@ -791,11 +791,11 @@ size_t ZSTD_DStreamOutSize(void); /* for static allocation */ #define ZSTD_FRAMEHEADERSIZE_MAX 18 #define ZSTD_FRAMEHEADERSIZE_MIN 6 -static const size_t ZSTD_frameHeaderSize_prefix = 5; -static const size_t ZSTD_frameHeaderSize_min = ZSTD_FRAMEHEADERSIZE_MIN; -static const size_t ZSTD_frameHeaderSize_max = ZSTD_FRAMEHEADERSIZE_MAX; +#define ZSTD_frameHeaderSize_prefix 5 +#define ZSTD_frameHeaderSize_min ZSTD_FRAMEHEADERSIZE_MIN +#define ZSTD_frameHeaderSize_max ZSTD_FRAMEHEADERSIZE_MAX /* magic number + skippable frame length */ -static const size_t ZSTD_skippableHeaderSize = 8; +#define ZSTD_skippableHeaderSize 8 /*-************************************* diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index ecd24c719de4..0551ea65374f 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -99,7 +99,8 @@ struct btrfs_space_info; EM( ALLOC_CHUNK, "ALLOC_CHUNK") \ EM( ALLOC_CHUNK_FORCE, "ALLOC_CHUNK_FORCE") \ EM( RUN_DELAYED_IPUTS, "RUN_DELAYED_IPUTS") \ - EMe(COMMIT_TRANS, "COMMIT_TRANS") + EM( COMMIT_TRANS, "COMMIT_TRANS") \ + EMe(FORCE_COMMIT_TRANS, "FORCE_COMMIT_TRANS") /* * First define the enums in the above macros to be exported to userspace via @@ -499,12 +500,13 @@ DEFINE_EVENT( #define show_ordered_flags(flags) \ __print_flags(flags, "|", \ + { (1 << BTRFS_ORDERED_REGULAR), "REGULAR" }, \ + { (1 << BTRFS_ORDERED_NOCOW), "NOCOW" }, \ + { (1 << BTRFS_ORDERED_PREALLOC), "PREALLOC" }, \ + { (1 << BTRFS_ORDERED_COMPRESSED), "COMPRESSED" }, \ + { (1 << BTRFS_ORDERED_DIRECT), "DIRECT" }, \ { (1 << BTRFS_ORDERED_IO_DONE), "IO_DONE" }, \ { (1 << BTRFS_ORDERED_COMPLETE), "COMPLETE" }, \ - { (1 << BTRFS_ORDERED_NOCOW), "NOCOW" }, \ - { (1 << BTRFS_ORDERED_COMPRESSED), "COMPRESSED" }, \ - { (1 << BTRFS_ORDERED_PREALLOC), "PREALLOC" }, \ - { (1 << BTRFS_ORDERED_DIRECT), "DIRECT" }, \ { (1 << BTRFS_ORDERED_IOERR), "IOERR" }, \ { (1 << BTRFS_ORDERED_TRUNCATED), "TRUNCATED" }) @@ -1111,15 +1113,16 @@ TRACE_EVENT(btrfs_trigger_flush, TRACE_EVENT(btrfs_flush_space, TP_PROTO(const struct btrfs_fs_info *fs_info, u64 flags, u64 num_bytes, - int state, int ret), + int state, int ret, bool for_preempt), - TP_ARGS(fs_info, flags, num_bytes, state, ret), + TP_ARGS(fs_info, flags, num_bytes, state, ret, for_preempt), TP_STRUCT__entry_btrfs( __field( u64, flags ) __field( u64, num_bytes ) __field( int, state ) __field( int, ret ) + __field( bool, for_preempt ) ), TP_fast_assign_btrfs(fs_info, @@ -1127,15 +1130,16 @@ TRACE_EVENT(btrfs_flush_space, __entry->num_bytes = num_bytes; __entry->state = state; __entry->ret = ret; + __entry->for_preempt = for_preempt; ), - TP_printk_btrfs("state=%d(%s) flags=%llu(%s) num_bytes=%llu ret=%d", + TP_printk_btrfs("state=%d(%s) flags=%llu(%s) num_bytes=%llu ret=%d for_preempt=%d", __entry->state, __print_symbolic(__entry->state, FLUSH_STATES), __entry->flags, __print_flags((unsigned long)__entry->flags, "|", BTRFS_GROUP_FLAGS), - __entry->num_bytes, __entry->ret) + __entry->num_bytes, __entry->ret, __entry->for_preempt) ); DECLARE_EVENT_CLASS(btrfs__reserved_extent, @@ -2025,6 +2029,97 @@ TRACE_EVENT(btrfs_convert_extent_bit, __print_flags(__entry->clear_bits, "|", EXTENT_FLAGS)) ); +DECLARE_EVENT_CLASS(btrfs_dump_space_info, + TP_PROTO(const struct btrfs_fs_info *fs_info, + const struct btrfs_space_info *sinfo), + + TP_ARGS(fs_info, sinfo), + + TP_STRUCT__entry_btrfs( + __field( u64, flags ) + __field( u64, total_bytes ) + __field( u64, bytes_used ) + __field( u64, bytes_pinned ) + __field( u64, bytes_reserved ) + __field( u64, bytes_may_use ) + __field( u64, bytes_readonly ) + __field( u64, reclaim_size ) + __field( int, clamp ) + __field( u64, global_reserved ) + __field( u64, trans_reserved ) + __field( u64, delayed_refs_reserved ) + __field( u64, delayed_reserved ) + __field( u64, free_chunk_space ) + ), + + TP_fast_assign_btrfs(fs_info, + __entry->flags = sinfo->flags; + __entry->total_bytes = sinfo->total_bytes; + __entry->bytes_used = sinfo->bytes_used; + __entry->bytes_pinned = sinfo->bytes_pinned; + __entry->bytes_reserved = sinfo->bytes_reserved; + __entry->bytes_may_use = sinfo->bytes_may_use; + __entry->bytes_readonly = sinfo->bytes_readonly; + __entry->reclaim_size = sinfo->reclaim_size; + __entry->clamp = sinfo->clamp; + __entry->global_reserved = fs_info->global_block_rsv.reserved; + __entry->trans_reserved = fs_info->trans_block_rsv.reserved; + __entry->delayed_refs_reserved = fs_info->delayed_refs_rsv.reserved; + __entry->delayed_reserved = fs_info->delayed_block_rsv.reserved; + __entry->free_chunk_space = atomic64_read(&fs_info->free_chunk_space); + ), + + TP_printk_btrfs("flags=%s total_bytes=%llu bytes_used=%llu " + "bytes_pinned=%llu bytes_reserved=%llu " + "bytes_may_use=%llu bytes_readonly=%llu " + "reclaim_size=%llu clamp=%d global_reserved=%llu " + "trans_reserved=%llu delayed_refs_reserved=%llu " + "delayed_reserved=%llu chunk_free_space=%llu", + __print_flags(__entry->flags, "|", BTRFS_GROUP_FLAGS), + __entry->total_bytes, __entry->bytes_used, + __entry->bytes_pinned, __entry->bytes_reserved, + __entry->bytes_may_use, __entry->bytes_readonly, + __entry->reclaim_size, __entry->clamp, + __entry->global_reserved, __entry->trans_reserved, + __entry->delayed_refs_reserved, + __entry->delayed_reserved, __entry->free_chunk_space) +); + +DEFINE_EVENT(btrfs_dump_space_info, btrfs_done_preemptive_reclaim, + TP_PROTO(const struct btrfs_fs_info *fs_info, + const struct btrfs_space_info *sinfo), + TP_ARGS(fs_info, sinfo) +); + +TRACE_EVENT(btrfs_reserve_ticket, + TP_PROTO(const struct btrfs_fs_info *fs_info, u64 flags, u64 bytes, + u64 start_ns, int flush, int error), + + TP_ARGS(fs_info, flags, bytes, start_ns, flush, error), + + TP_STRUCT__entry_btrfs( + __field( u64, flags ) + __field( u64, bytes ) + __field( u64, start_ns ) + __field( int, flush ) + __field( int, error ) + ), + + TP_fast_assign_btrfs(fs_info, + __entry->flags = flags; + __entry->bytes = bytes; + __entry->start_ns = start_ns; + __entry->flush = flush; + __entry->error = error; + ), + + TP_printk_btrfs("flags=%s bytes=%llu start_ns=%llu flush=%s error=%d", + __print_flags(__entry->flags, "|", BTRFS_GROUP_FLAGS), + __entry->bytes, __entry->start_ns, + __print_symbolic(__entry->flush, FLUSH_ACTIONS), + __entry->error) +); + DECLARE_EVENT_CLASS(btrfs_sleep_tree_lock, TP_PROTO(const struct extent_buffer *eb, u64 start_ns), diff --git a/include/uapi/linux/openat2.h b/include/uapi/linux/openat2.h index 58b1eb711360..a5feb7604948 100644 --- a/include/uapi/linux/openat2.h +++ b/include/uapi/linux/openat2.h @@ -35,5 +35,9 @@ struct open_how { #define RESOLVE_IN_ROOT 0x10 /* Make all jumps to "/" and ".." be scoped inside the dirfd (similar to chroot(2)). */ +#define RESOLVE_CACHED 0x20 /* Only complete if resolution can be + completed through cached lookup. May + return -EAGAIN if that's not + possible. */ #endif /* _UAPI_LINUX_OPENAT2_H */ diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index aa919585c24b..a0b6780740c8 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -1076,7 +1076,7 @@ void crash_save_cpu(struct pt_regs *regs, int cpu) if (!buf) return; memset(&prstatus, 0, sizeof(prstatus)); - prstatus.pr_pid = current->pid; + prstatus.common.pr_pid = current->pid; elf_core_copy_kernel_regs(&prstatus.pr_reg, regs); buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS, &prstatus, sizeof(prstatus)); diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index a7320f07689d..6bfe3ead10ad 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -139,7 +139,6 @@ config PM_SLEEP_SMP_NONZERO_CPU config PM_AUTOSLEEP bool "Opportunistic sleep" depends on PM_SLEEP - default n help Allow the kernel to trigger a system transition into a global sleep state automatically whenever there are no active wakeup sources. @@ -147,7 +146,6 @@ config PM_AUTOSLEEP config PM_WAKELOCKS bool "User space wakeup sources interface" depends on PM_SLEEP - default n help Allow user space to create, activate and deactivate wakeup source objects with the help of a sysfs-based interface. @@ -293,7 +291,6 @@ config PM_GENERIC_DOMAINS config WQ_POWER_EFFICIENT_DEFAULT bool "Enable workqueue power-efficient mode by default" depends on PM - default n help Per-cpu workqueues are generally preferred because they show better performance thanks to cache locality; unfortunately, @@ -322,15 +319,14 @@ config CPU_PM bool config ENERGY_MODEL - bool "Energy Model for CPUs" + bool "Energy Model for devices with DVFS (CPUs, GPUs, etc)" depends on SMP depends on CPU_FREQ - default n help Several subsystems (thermal and/or the task scheduler for example) - can leverage information about the energy consumed by CPUs to make - smarter decisions. This config option enables the framework from - which subsystems can access the energy models. + can leverage information about the energy consumed by devices to + make smarter decisions. This config option enables the framework + from which subsystems can access the energy models. The exact usage of the energy model is subsystem-dependent. diff --git a/kernel/power/main.c b/kernel/power/main.c index 0aefd6f57e0a..12c7e1bb442f 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -387,7 +387,7 @@ static struct attribute *suspend_attrs[] = { NULL, }; -static struct attribute_group suspend_attr_group = { +static const struct attribute_group suspend_attr_group = { .name = "suspend_stats", .attrs = suspend_attrs, }; diff --git a/kernel/power/process.c b/kernel/power/process.c index cc062308092b..8bd2bcc09392 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -238,7 +238,7 @@ void thaw_kernel_threads(void) read_lock(&tasklist_lock); for_each_process_thread(g, p) { - if (p->flags & (PF_KTHREAD | PF_WQ_WORKER)) + if (p->flags & PF_KTHREAD) __thaw_task(p); } read_unlock(&tasklist_lock); diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 5a50d3a46445..068847e263e8 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -1444,7 +1444,7 @@ static bool atpx_present(void) dhandle = ACPI_HANDLE(&pdev->dev); if (dhandle) { status = acpi_get_handle(dhandle, "ATPX", &atpx_handle); - if (!ACPI_FAILURE(status)) { + if (ACPI_SUCCESS(status)) { pci_dev_put(pdev); return true; } @@ -1454,7 +1454,7 @@ static bool atpx_present(void) dhandle = ACPI_HANDLE(&pdev->dev); if (dhandle) { status = acpi_get_handle(dhandle, "ATPX", &atpx_handle); - if (!ACPI_FAILURE(status)) { + if (ACPI_SUCCESS(status)) { pci_dev_put(pdev); return true; } diff --git a/tools/power/acpi/common/cmfsize.c b/tools/power/acpi/common/cmfsize.c index d1d18ff5c911..9ea2c0aeb86c 100644 --- a/tools/power/acpi/common/cmfsize.c +++ b/tools/power/acpi/common/cmfsize.c @@ -3,7 +3,7 @@ * * Module Name: cfsize - Common get file size function * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/common/getopt.c b/tools/power/acpi/common/getopt.c index c3708f30ab3a..3c265bc917a1 100644 --- a/tools/power/acpi/common/getopt.c +++ b/tools/power/acpi/common/getopt.c @@ -3,7 +3,7 @@ * * Module Name: getopt * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c index 11c5046dce16..ccabdbaae6a4 100644 --- a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c +++ b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c @@ -3,7 +3,7 @@ * * Module Name: oslinuxtbl - Linux OSL for obtaining ACPI tables * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/os_specific/service_layers/osunixdir.c b/tools/power/acpi/os_specific/service_layers/osunixdir.c index fd05ddee240f..edd99274cd12 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixdir.c +++ b/tools/power/acpi/os_specific/service_layers/osunixdir.c @@ -3,7 +3,7 @@ * * Module Name: osunixdir - Unix directory access interfaces * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/os_specific/service_layers/osunixmap.c b/tools/power/acpi/os_specific/service_layers/osunixmap.c index c565546e85bc..fee0022560d5 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixmap.c +++ b/tools/power/acpi/os_specific/service_layers/osunixmap.c @@ -3,7 +3,7 @@ * * Module Name: osunixmap - Unix OSL for file mappings * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/os_specific/service_layers/osunixxf.c b/tools/power/acpi/os_specific/service_layers/osunixxf.c index 5b2fd968535f..0861728da562 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixxf.c +++ b/tools/power/acpi/os_specific/service_layers/osunixxf.c @@ -3,7 +3,7 @@ * * Module Name: osunixxf - UNIX OSL interfaces * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/tools/acpidump/acpidump.h b/tools/power/acpi/tools/acpidump/acpidump.h index 26a5eae9f87f..e0ebc1dab1cc 100644 --- a/tools/power/acpi/tools/acpidump/acpidump.h +++ b/tools/power/acpi/tools/acpidump/acpidump.h @@ -3,7 +3,7 @@ * * Module Name: acpidump.h - Include file for acpi_dump utility * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/tools/acpidump/apdump.c b/tools/power/acpi/tools/acpidump/apdump.c index 76433296055d..444e3d78bd89 100644 --- a/tools/power/acpi/tools/acpidump/apdump.c +++ b/tools/power/acpi/tools/acpidump/apdump.c @@ -3,7 +3,7 @@ * * Module Name: apdump - Dump routines for ACPI tables (acpidump) * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/tools/acpidump/apfiles.c b/tools/power/acpi/tools/acpidump/apfiles.c index a682bae4e6f6..da0c6e13042b 100644 --- a/tools/power/acpi/tools/acpidump/apfiles.c +++ b/tools/power/acpi/tools/acpidump/apfiles.c @@ -3,7 +3,7 @@ * * Module Name: apfiles - File-related functions for acpidump utility * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/tools/acpidump/apmain.c b/tools/power/acpi/tools/acpidump/apmain.c index 046e6b8d6baa..a4cf6042fcfd 100644 --- a/tools/power/acpi/tools/acpidump/apmain.c +++ b/tools/power/acpi/tools/acpidump/apmain.c @@ -3,7 +3,7 @@ * * Module Name: apmain - Main module for the acpidump utility * - * Copyright (C) 2000 - 2020, Intel Corp. + * Copyright (C) 2000 - 2021, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile index c7bcddbd486d..3b1594447f29 100644 --- a/tools/power/cpupower/Makefile +++ b/tools/power/cpupower/Makefile @@ -270,14 +270,14 @@ clean: $(MAKE) -C bench O=$(OUTPUT) clean -install-lib: +install-lib: libcpupower $(INSTALL) -d $(DESTDIR)${libdir} $(CP) $(OUTPUT)libcpupower.so* $(DESTDIR)${libdir}/ $(INSTALL) -d $(DESTDIR)${includedir} $(INSTALL_DATA) lib/cpufreq.h $(DESTDIR)${includedir}/cpufreq.h $(INSTALL_DATA) lib/cpuidle.h $(DESTDIR)${includedir}/cpuidle.h -install-tools: +install-tools: $(OUTPUT)cpupower $(INSTALL) -d $(DESTDIR)${bindir} $(INSTALL_PROGRAM) $(OUTPUT)cpupower $(DESTDIR)${bindir} $(INSTALL) -d $(DESTDIR)${bash_completion_dir} @@ -293,14 +293,14 @@ install-man: $(INSTALL_DATA) -D man/cpupower-info.1 $(DESTDIR)${mandir}/man1/cpupower-info.1 $(INSTALL_DATA) -D man/cpupower-monitor.1 $(DESTDIR)${mandir}/man1/cpupower-monitor.1 -install-gmo: +install-gmo: create-gmo $(INSTALL) -d $(DESTDIR)${localedir} for HLANG in $(LANGUAGES); do \ echo '$(INSTALL_DATA) -D $(OUTPUT)po/$$HLANG.gmo $(DESTDIR)${localedir}/$$HLANG/LC_MESSAGES/cpupower.mo'; \ $(INSTALL_DATA) -D $(OUTPUT)po/$$HLANG.gmo $(DESTDIR)${localedir}/$$HLANG/LC_MESSAGES/cpupower.mo; \ done; -install-bench: +install-bench: compile-bench @#DESTDIR must be set from outside to survive @sbindir=$(sbindir) bindir=$(bindir) docdir=$(docdir) confdir=$(confdir) $(MAKE) -C bench O=$(OUTPUT) install diff --git a/tools/power/cpupower/bench/Makefile b/tools/power/cpupower/bench/Makefile index f68b4bc55273..d9d9923af85c 100644 --- a/tools/power/cpupower/bench/Makefile +++ b/tools/power/cpupower/bench/Makefile @@ -27,7 +27,7 @@ $(OUTPUT)cpufreq-bench: $(OBJS) all: $(OUTPUT)cpufreq-bench -install: +install: $(OUTPUT)cpufreq-bench mkdir -p $(DESTDIR)/$(sbindir) mkdir -p $(DESTDIR)/$(bindir) mkdir -p $(DESTDIR)/$(docdir) diff --git a/tools/power/cpupower/utils/cpufreq-info.c b/tools/power/cpupower/utils/cpufreq-info.c index 6efc0f6b1b11..f9895e31ff5a 100644 --- a/tools/power/cpupower/utils/cpufreq-info.c +++ b/tools/power/cpupower/utils/cpufreq-info.c @@ -186,8 +186,7 @@ static int get_boost_mode_x86(unsigned int cpu) if ((cpupower_cpu_info.vendor == X86_VENDOR_AMD && cpupower_cpu_info.family >= 0x10) || cpupower_cpu_info.vendor == X86_VENDOR_HYGON) { - ret = decode_pstates(cpu, cpupower_cpu_info.family, b_states, - pstates, &pstate_no); + ret = decode_pstates(cpu, b_states, pstates, &pstate_no); if (ret) return ret; diff --git a/tools/power/cpupower/utils/helpers/amd.c b/tools/power/cpupower/utils/helpers/amd.c index 7c4f83a8c973..97f2c857048e 100644 --- a/tools/power/cpupower/utils/helpers/amd.c +++ b/tools/power/cpupower/utils/helpers/amd.c @@ -13,7 +13,8 @@ #define MSR_AMD_PSTATE 0xc0010064 #define MSR_AMD_PSTATE_LIMIT 0xc0010061 -union msr_pstate { +union core_pstate { + /* pre fam 17h: */ struct { unsigned fid:6; unsigned did:3; @@ -26,7 +27,8 @@ union msr_pstate { unsigned idddiv:2; unsigned res3:21; unsigned en:1; - } bits; + } pstate; + /* since fam 17h: */ struct { unsigned fid:8; unsigned did:6; @@ -35,37 +37,37 @@ union msr_pstate { unsigned idddiv:2; unsigned res1:31; unsigned en:1; - } fam17h_bits; + } pstatedef; unsigned long long val; }; -static int get_did(int family, union msr_pstate pstate) +static int get_did(union core_pstate pstate) { int t; - if (family == 0x12) + if (cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_PSTATEDEF) + t = pstate.pstatedef.did; + else if (cpupower_cpu_info.family == 0x12) t = pstate.val & 0xf; - else if (family == 0x17 || family == 0x18) - t = pstate.fam17h_bits.did; else - t = pstate.bits.did; + t = pstate.pstate.did; return t; } -static int get_cof(int family, union msr_pstate pstate) +static int get_cof(union core_pstate pstate) { int t; int fid, did, cof; - did = get_did(family, pstate); - if (family == 0x17 || family == 0x18) { - fid = pstate.fam17h_bits.fid; + did = get_did(pstate); + if (cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_PSTATEDEF) { + fid = pstate.pstatedef.fid; cof = 200 * fid / did; } else { t = 0x10; - fid = pstate.bits.fid; - if (family == 0x11) + fid = pstate.pstate.fid; + if (cpupower_cpu_info.family == 0x11) t = 0x8; cof = (100 * (fid + t)) >> did; } @@ -74,8 +76,7 @@ static int get_cof(int family, union msr_pstate pstate) /* Needs: * cpu -> the cpu that gets evaluated - * cpu_family -> The cpu's family (0x10, 0x12,...) - * boots_states -> how much boost states the machines support + * boost_states -> how much boost states the machines support * * Fills up: * pstates -> a pointer to an array of size MAX_HW_PSTATES @@ -85,31 +86,23 @@ static int get_cof(int family, union msr_pstate pstate) * * returns zero on success, -1 on failure */ -int decode_pstates(unsigned int cpu, unsigned int cpu_family, - int boost_states, unsigned long *pstates, int *no) +int decode_pstates(unsigned int cpu, int boost_states, + unsigned long *pstates, int *no) { - int i, psmax, pscur; - union msr_pstate pstate; + int i, psmax; + union core_pstate pstate; unsigned long long val; - /* Only read out frequencies from HW when CPU might be boostable - to keep the code as short and clean as possible. - Otherwise frequencies are exported via ACPI tables. - */ - if (cpu_family < 0x10 || cpu_family == 0x14) + /* Only read out frequencies from HW if HW Pstate is supported, + * otherwise frequencies are exported via ACPI tables. + */ + if (!(cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_HW_PSTATE)) return -1; if (read_msr(cpu, MSR_AMD_PSTATE_LIMIT, &val)) return -1; psmax = (val >> 4) & 0x7; - - if (read_msr(cpu, MSR_AMD_PSTATE_STATUS, &val)) - return -1; - - pscur = val & 0x7; - - pscur += boost_states; psmax += boost_states; for (i = 0; i <= psmax; i++) { if (i >= MAX_HW_PSTATES) { @@ -119,12 +112,12 @@ int decode_pstates(unsigned int cpu, unsigned int cpu_family, } if (read_msr(cpu, MSR_AMD_PSTATE + i, &pstate.val)) return -1; - if ((cpu_family == 0x17) && (!pstate.fam17h_bits.en)) - continue; - else if (!pstate.bits.en) + + /* The enabled bit (bit 63) is common for all families */ + if (!pstate.pstatedef.en) continue; - pstates[i] = get_cof(cpu_family, pstate); + pstates[i] = get_cof(pstate); } *no = i; return 0; diff --git a/tools/power/cpupower/utils/helpers/cpuid.c b/tools/power/cpupower/utils/helpers/cpuid.c index 73bfafc60e9b..72eb43593180 100644 --- a/tools/power/cpupower/utils/helpers/cpuid.c +++ b/tools/power/cpupower/utils/helpers/cpuid.c @@ -128,9 +128,23 @@ out: /* AMD or Hygon Boost state enable/disable register */ if (cpu_info->vendor == X86_VENDOR_AMD || cpu_info->vendor == X86_VENDOR_HYGON) { - if (ext_cpuid_level >= 0x80000007 && - (cpuid_edx(0x80000007) & (1 << 9))) - cpu_info->caps |= CPUPOWER_CAP_AMD_CBP; + if (ext_cpuid_level >= 0x80000007) { + if (cpuid_edx(0x80000007) & (1 << 9)) { + cpu_info->caps |= CPUPOWER_CAP_AMD_CPB; + + if (cpu_info->family >= 0x17) + cpu_info->caps |= CPUPOWER_CAP_AMD_CPB_MSR; + } + + if ((cpuid_edx(0x80000007) & (1 << 7)) && + cpu_info->family != 0x14) { + /* HW pstate was not implemented in family 0x14 */ + cpu_info->caps |= CPUPOWER_CAP_AMD_HW_PSTATE; + + if (cpu_info->family >= 0x17) + cpu_info->caps |= CPUPOWER_CAP_AMD_PSTATEDEF; + } + } if (ext_cpuid_level >= 0x80000008 && cpuid_ebx(0x80000008) & (1 << 4)) diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h index 0642e60a6ce1..33ffacee7fcb 100644 --- a/tools/power/cpupower/utils/helpers/helpers.h +++ b/tools/power/cpupower/utils/helpers/helpers.h @@ -64,12 +64,15 @@ enum cpupower_cpu_vendor {X86_VENDOR_UNKNOWN = 0, X86_VENDOR_INTEL, #define CPUPOWER_CAP_INV_TSC 0x00000001 #define CPUPOWER_CAP_APERF 0x00000002 -#define CPUPOWER_CAP_AMD_CBP 0x00000004 +#define CPUPOWER_CAP_AMD_CPB 0x00000004 #define CPUPOWER_CAP_PERF_BIAS 0x00000008 #define CPUPOWER_CAP_HAS_TURBO_RATIO 0x00000010 #define CPUPOWER_CAP_IS_SNB 0x00000020 #define CPUPOWER_CAP_INTEL_IDA 0x00000040 #define CPUPOWER_CAP_AMD_RDPRU 0x00000080 +#define CPUPOWER_CAP_AMD_HW_PSTATE 0x00000100 +#define CPUPOWER_CAP_AMD_PSTATEDEF 0x00000200 +#define CPUPOWER_CAP_AMD_CPB_MSR 0x00000400 #define CPUPOWER_AMD_CPBDIS 0x02000000 @@ -125,8 +128,8 @@ extern struct pci_dev *pci_slot_func_init(struct pci_access **pacc, /* AMD HW pstate decoding **************************/ -extern int decode_pstates(unsigned int cpu, unsigned int cpu_family, - int boost_states, unsigned long *pstates, int *no); +extern int decode_pstates(unsigned int cpu, int boost_states, + unsigned long *pstates, int *no); /* AMD HW pstate decoding **************************/ @@ -143,9 +146,8 @@ unsigned int cpuid_edx(unsigned int op); /* cpuid and cpuinfo helpers **************************/ /* X86 ONLY ********************************************/ #else -static inline int decode_pstates(unsigned int cpu, unsigned int cpu_family, - int boost_states, unsigned long *pstates, - int *no) +static inline int decode_pstates(unsigned int cpu, int boost_states, + unsigned long *pstates, int *no) { return -1; }; static inline int read_msr(int cpu, unsigned int idx, unsigned long long *val) diff --git a/tools/power/cpupower/utils/helpers/misc.c b/tools/power/cpupower/utils/helpers/misc.c index 650b9a9a6584..fc6e34511721 100644 --- a/tools/power/cpupower/utils/helpers/misc.c +++ b/tools/power/cpupower/utils/helpers/misc.c @@ -16,17 +16,12 @@ int cpufreq_has_boost_support(unsigned int cpu, int *support, int *active, int *states) { - struct cpupower_cpu_info cpu_info; int ret; unsigned long long val; *support = *active = *states = 0; - ret = get_cpu_info(&cpu_info); - if (ret) - return ret; - - if (cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_CBP) { + if (cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_CPB) { *support = 1; /* AMD Family 0x17 does not utilize PCI D18F4 like prior @@ -34,7 +29,7 @@ int cpufreq_has_boost_support(unsigned int cpu, int *support, int *active, * has Hardware determined variable increments instead. */ - if (cpu_info.family == 0x17 || cpu_info.family == 0x18) { + if (cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_CPB_MSR) { if (!read_msr(cpu, MSR_AMD_HWCR, &val)) { if (!(val & CPUPOWER_AMD_CPBDIS)) *active = 1;