From a94e88cdd8057fe8ea84bbb6d9a89a823c7bc49b Mon Sep 17 00:00:00 2001 From: Lv Zheng Date: Fri, 4 Apr 2014 12:39:11 +0800 Subject: ACPICA: Tables: Avoid SSDT installation with acpi_gbl_disable_ssdt_table_load. It is reported that when acpi_gbl_disable_ssdt_table_load is specified, user still can see it installed into /sys/firmware/acpi/tables on Linux boxes. This is because the option only stops table "loading", but doesn't stop table "installing", thus it is still in the acpi_gbl_root_table_list. With previous cleanups, it is possible to prevent SSDT installations to make it not such confusing. The global variable is also renamed. Lv Zheng. Signed-off-by: Lv Zheng [rjw: Subject] Signed-off-by: Rafael J. Wysocki --- Documentation/kernel-parameters.txt | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'Documentation/kernel-parameters.txt') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 03e50b4883a8..fbb58d790ec7 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -237,7 +237,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted. This feature is enabled by default. This option allows to turn off the feature. - acpi_no_auto_ssdt [HW,ACPI] Disable automatic loading of SSDT + acpi_no_static_ssdt [HW,ACPI] + Disable installation of static SSDTs at early boot time + By default, SSDTs contained in the RSDT/XSDT will be + installed automatically and they will appear under + /sys/firmware/acpi/tables. + This option turns off this feature. + Note that specifying this option does not affect + dynamic table installation which will install SSDT + tables to /sys/firmware/acpi/tables/dynamic. acpica_no_return_repair [HW, ACPI] Disable AML predefined validation mechanism -- cgit v1.2.3 From 0d3c673e7881e691991b2a4745bd4f149603baa2 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 18 Apr 2014 17:19:57 -0500 Subject: tty/serial: pl011: add generic earlycon support Add earlycon support for the pl011 serial port. This allows enabling the pl011 for console when early_params are processed. This is based on the arm64 earlyprintk support and is intended to replace it. Signed-off-by: Rob Herring Cc: Russell King Cc: Jiri Slaby Signed-off-by: Greg Kroah-Hartman --- Documentation/kernel-parameters.txt | 7 +++++++ drivers/tty/serial/Kconfig | 1 + drivers/tty/serial/amba-pl011.c | 30 +++++++++++++++++++++++++++++- 3 files changed, 37 insertions(+), 1 deletion(-) (limited to 'Documentation/kernel-parameters.txt') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 43842177b771..2609ead7ff55 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -883,6 +883,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. which are not unmapped. earlycon= [KNL] Output early console device and options. + uart[8250],io,[,options] uart[8250],mmio,[,options] uart[8250],mmio32,[,options] @@ -892,6 +893,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted. (mmio) or 32-bit (mmio32). The options are the same as for ttyS, above. + pl011, + Start an early, polled-mode console on a pl011 serial + port at the specified address. The pl011 serial port + must already be setup and configured. Options are not + yet supported. + earlyprintk= [X86,SH,BLACKFIN,ARM] earlyprintk=vga earlyprintk=efi diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 9fb6028ad900..4290d05875b1 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -60,6 +60,7 @@ config SERIAL_AMBA_PL011_CONSOLE bool "Support for console on AMBA serial port" depends on SERIAL_AMBA_PL011=y select SERIAL_CORE_CONSOLE + select SERIAL_EARLYCON ---help--- Say Y here if you wish to use an AMBA PrimeCell UART as the system console (the system console is the device which receives all kernel diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index dacf0a09ab24..ee3d80346780 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -303,7 +303,7 @@ static void pl011_dma_probe_initcall(struct device *dev, struct uart_amba_port * /* Optionally make use of an RX channel as well */ chan = dma_request_slave_channel(dev, "rx"); - + if (!chan && plat->dma_rx_param) { chan = dma_request_channel(mask, plat->dma_filter, plat->dma_rx_param); @@ -2045,6 +2045,34 @@ static struct console amba_console = { }; #define AMBA_CONSOLE (&amba_console) + +static void pl011_putc(struct uart_port *port, int c) +{ + while (readl(port->membase + UART01x_FR) & UART01x_FR_TXFF) + ; + writeb(c, port->membase + UART01x_DR); + while (readl(port->membase + UART01x_FR) & UART01x_FR_BUSY) + ; +} + +static void pl011_early_write(struct console *con, const char *s, unsigned n) +{ + struct earlycon_device *dev = con->data; + + uart_console_write(&dev->port, s, n, pl011_putc); +} + +static int __init pl011_early_console_setup(struct earlycon_device *device, + const char *opt) +{ + if (!device->port.membase) + return -ENODEV; + + device->con->write = pl011_early_write; + return 0; +} +EARLYCON_DECLARE(pl011, pl011_early_console_setup); + #else #define AMBA_CONSOLE NULL #endif -- cgit v1.2.3 From d50d7269ebcb438afa346cdffce0f4e2a1b9e831 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 18 Apr 2014 17:19:58 -0500 Subject: tty/serial: add arm/arm64 semihosting earlycon Add earlycon support for the arm/arm64 semihosting debug serial interface. This allows enabling a debug console when early_params are processed. This is based on the arm64 earlyprintk smh support and is intended to replace it. Signed-off-by: Rob Herring Cc: Jiri Slaby Signed-off-by: Greg Kroah-Hartman --- Documentation/kernel-parameters.txt | 2 + drivers/tty/serial/Kconfig | 10 +++++ drivers/tty/serial/Makefile | 1 + drivers/tty/serial/earlycon-arm-semihost.c | 61 ++++++++++++++++++++++++++++++ 4 files changed, 74 insertions(+) create mode 100644 drivers/tty/serial/earlycon-arm-semihost.c (limited to 'Documentation/kernel-parameters.txt') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 2609ead7ff55..4946d8e58d53 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -899,6 +899,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted. must already be setup and configured. Options are not yet supported. + smh Use ARM semihosting calls for early console. + earlyprintk= [X86,SH,BLACKFIN,ARM] earlyprintk=vga earlyprintk=efi diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 4290d05875b1..988fa2b6243b 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -73,6 +73,16 @@ config SERIAL_AMBA_PL011_CONSOLE your boot loader (lilo or loadlin) about how to pass options to the kernel at boot time.) +config SERIAL_EARLYCON_ARM_SEMIHOST + bool "Early console using ARM semihosting" + depends on ARM64 || ARM + select SERIAL_EARLYCON + help + Support for early debug console using ARM semihosting. This enables + the console before standard serial driver is probed. This is enabled + with "earlycon=smh" on the kernel command line. The console is + enabled when early_param is processed. + config SERIAL_SB1250_DUART tristate "BCM1xxx on-chip DUART serial support" depends on SIBYTE_SB1xxx_SOC=y diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile index 28048178f308..3a5be4633333 100644 --- a/drivers/tty/serial/Makefile +++ b/drivers/tty/serial/Makefile @@ -6,6 +6,7 @@ obj-$(CONFIG_SERIAL_CORE) += serial_core.o obj-$(CONFIG_SERIAL_21285) += 21285.o obj-$(CONFIG_SERIAL_EARLYCON) += earlycon.o +obj-$(CONFIG_SERIAL_EARLYCON_ARM_SEMIHOST) += earlycon-arm-semihost.o # These Sparc drivers have to appear before others such as 8250 # which share ttySx minor node space. Otherwise console device diff --git a/drivers/tty/serial/earlycon-arm-semihost.c b/drivers/tty/serial/earlycon-arm-semihost.c new file mode 100644 index 000000000000..383db10fbb49 --- /dev/null +++ b/drivers/tty/serial/earlycon-arm-semihost.c @@ -0,0 +1,61 @@ +/* + * Copyright (C) 2012 ARM Ltd. + * Author: Marc Zyngier + * + * Adapted for ARM and earlycon: + * Copyright (C) 2014 Linaro Ltd. + * Author: Rob Herring + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ +#include +#include +#include +#include + +#ifdef CONFIG_THUMB2_KERNEL +#define SEMIHOST_SWI "0xab" +#else +#define SEMIHOST_SWI "0x123456" +#endif + +/* + * Semihosting-based debug console + */ +static void smh_putc(struct uart_port *port, int c) +{ +#ifdef CONFIG_ARM64 + asm volatile("mov x1, %0\n" + "mov x0, #3\n" + "hlt 0xf000\n" + : : "r" (&c) : "x0", "x1", "memory"); +#else + asm volatile("mov r1, %0\n" + "mov r0, #3\n" + "svc " SEMIHOST_SWI "\n" + : : "r" (&c) : "r0", "r1", "memory"); +#endif +} + +static void smh_write(struct console *con, const char *s, unsigned n) +{ + struct earlycon_device *dev = con->data; + uart_console_write(&dev->port, s, n, smh_putc); +} + +int __init early_smh_setup(struct earlycon_device *device, const char *opt) +{ + device->con->write = smh_write; + return 0; +} +EARLYCON_DECLARE(smh, early_smh_setup); -- cgit v1.2.3 From 886129a8eebebec260165741fe31421482371006 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 6 May 2014 14:46:23 +0200 Subject: ACPI / video: change acpi-video brightness_switch_enabled default to 0 acpi-video is unique in that it not only generates brightness up/down keypresses, but also (sometimes) actively changes the brightness itself. This presents an inconsistent kernel interface to userspace, basically there are 2 different scenarios, depending on the laptop model: 1) On some laptops a brightness up/down keypress means: show a brightness osd with the current brightness, iow it is a brightness has changed notification. 2) Where as on (a lot of) other laptops it means a brightness up/down key was pressed, deal with it. Most of the desktop environments interpret any press as in scenario 2, and change the brightness up / down as a response to the key events, causing it to be changed twice, once by acpi-video and once by the DE. With the new default for video.use_native_backlight we will be moving even more laptops over to behaving as in scenario 2. Making the remaining laptops even more of a weird exception. Also note that it is hard to detect scenario 1 properly in userspace, and AFAIK none of the DE-s deals with it. Therefor this commit changes the default of brightness_switch_enabled to 0 making its behavior consistent with all the other backlight drivers. Signed-off-by: Hans de Goede Reviewed-by: Aaron Lu Signed-off-by: Rafael J. Wysocki --- Documentation/kernel-parameters.txt | 2 +- drivers/acpi/video.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'Documentation/kernel-parameters.txt') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 43842177b771..cc2c243ac781 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3461,7 +3461,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. the allocated input device; If set to 0, video driver will only send out the event without touching backlight brightness level. - default: 1 + default: 0 virtio_mmio.device= [VMMIO] Memory mapped virtio (platform) device. diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c index 88393899a0bc..fced27d8e42f 100644 --- a/drivers/acpi/video.c +++ b/drivers/acpi/video.c @@ -68,7 +68,7 @@ MODULE_AUTHOR("Bruno Ducrot"); MODULE_DESCRIPTION("ACPI Video Driver"); MODULE_LICENSE("GPL"); -static bool brightness_switch_enabled = 1; +static bool brightness_switch_enabled; module_param(brightness_switch_enabled, bool, 0644); /* -- cgit v1.2.3 From 0399d4db3edf5c58b6ec7f672f089f5085e49ed5 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 26 May 2014 13:40:59 +0200 Subject: PM / sleep: Introduce command line argument for sleep state enumeration On some systems the platform doesn't support neither PM_SUSPEND_MEM nor PM_SUSPEND_STANDBY, so PM_SUSPEND_FREEZE is the only available system sleep state. However, some user space frameworks only use the "mem" and (sometimes) "standby" sleep state labels, so the users of those systems need to modify user space in order to be able to use system suspend at all and that is not always possible. For this reason, add a new kernel command line argument, relative_sleep_states, allowing the users of those systems to change the way in which the kernel assigns labels to system sleep states. Namely, for relative_sleep_states=1, the "mem", "standby" and "freeze" labels will enumerate the available system sleem states from the deepest to the shallowest, respectively, so that "mem" is always present in /sys/power/state and the other state strings may or may not be presend depending on what is supported by the platform. Update system sleep states documentation to reflect this change. Signed-off-by: Rafael J. Wysocki --- Documentation/ABI/testing/sysfs-power | 29 ++++++++---- Documentation/kernel-parameters.txt | 7 +++ Documentation/power/states.txt | 87 ++++++++++++++++++++++------------- kernel/power/main.c | 12 ++--- kernel/power/suspend.c | 32 ++++++++++++- 5 files changed, 119 insertions(+), 48 deletions(-) (limited to 'Documentation/kernel-parameters.txt') diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power index 64c9276e9421..f4551816329e 100644 --- a/Documentation/ABI/testing/sysfs-power +++ b/Documentation/ABI/testing/sysfs-power @@ -7,19 +7,30 @@ Description: subsystem. What: /sys/power/state -Date: August 2006 +Date: May 2014 Contact: Rafael J. Wysocki Description: - The /sys/power/state file controls the system power state. - Reading from this file returns what states are supported, - which is hard-coded to 'freeze' (Low-Power Idle), 'standby' - (Power-On Suspend), 'mem' (Suspend-to-RAM), and 'disk' - (Suspend-to-Disk). + The /sys/power/state file controls system sleep states. + Reading from this file returns the available sleep state + labels, which may be "mem", "standby", "freeze" and "disk" + (hibernation). The meanings of the first three labels depend on + the relative_sleep_states command line argument as follows: + 1) relative_sleep_states = 1 + "mem", "standby", "freeze" represent non-hibernation sleep + states from the deepest ("mem", always present) to the + shallowest ("freeze"). "standby" and "freeze" may or may + not be present depending on the capabilities of the + platform. "freeze" can only be present if "standby" is + present. + 2) relative_sleep_states = 0 (default) + "mem" - "suspend-to-RAM", present if supported. + "standby" - "power-on suspend", present if supported. + "freeze" - "suspend-to-idle", always present. Writing to this file one of these strings causes the system to - transition into that state. Please see the file - Documentation/power/states.txt for a description of each of - these states. + transition into the corresponding state, if available. See + Documentation/power/states.txt for a description of what + "suspend-to-RAM", "power-on suspend" and "suspend-to-idle" mean. What: /sys/power/disk Date: September 2006 diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 43842177b771..e19a88b63eeb 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2889,6 +2889,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted. [KNL, SMP] Set scheduler's default relax_domain_level. See Documentation/cgroups/cpusets.txt. + relative_sleep_states= + [SUSPEND] Use sleep state labeling where the deepest + state available other than hibernation is always "mem". + Format: { "0" | "1" } + 0 -- Traditional sleep state labels. + 1 -- Relative sleep state labels. + reserve= [KNL,BUGS] Force the kernel to ignore some iomem area reservetop= [X86-32] diff --git a/Documentation/power/states.txt b/Documentation/power/states.txt index 442d43df9b25..50f3ef9177c1 100644 --- a/Documentation/power/states.txt +++ b/Documentation/power/states.txt @@ -1,62 +1,87 @@ +System Power Management Sleep States -System Power Management States +(C) 2014 Intel Corp., Rafael J. Wysocki +The kernel supports up to four system sleep states generically, although three +of them depend on the platform support code to implement the low-level details +for each state. -The kernel supports four power management states generically, though -one is generic and the other three are dependent on platform support -code to implement the low-level details for each state. -This file describes each state, what they are -commonly called, what ACPI state they map to, and what string to write -to /sys/power/state to enter that state +The states are represented by strings that can be read or written to the +/sys/power/state file. Those strings may be "mem", "standby", "freeze" and +"disk", where the last one always represents hibernation (Suspend-To-Disk) and +the meaning of the remaining ones depends on the relative_sleep_states command +line argument. -state: Freeze / Low-Power Idle +For relative_sleep_states=1, the strings "mem", "standby" and "freeze" label the +available non-hibernation sleep states from the deepest to the shallowest, +respectively. In that case, "mem" is always present in /sys/power/state, +because there is at least one non-hibernation sleep state in every system. If +the given system supports two non-hibernation sleep states, "standby" is present +in /sys/power/state in addition to "mem". If the system supports three +non-hibernation sleep states, "freeze" will be present in /sys/power/state in +addition to "mem" and "standby". + +For relative_sleep_states=0, which is the default, the following descriptions +apply. + +state: Suspend-To-Idle ACPI state: S0 -String: "freeze" +Label: "freeze" -This state is a generic, pure software, light-weight, low-power state. -It allows more energy to be saved relative to idle by freezing user +This state is a generic, pure software, light-weight, system sleep state. +It allows more energy to be saved relative to runtime idle by freezing user space and putting all I/O devices into low-power states (possibly lower-power than available at run time), such that the processors can spend more time in their idle states. -This state can be used for platforms without Standby/Suspend-to-RAM + +This state can be used for platforms without Power-On Suspend/Suspend-to-RAM support, or it can be used in addition to Suspend-to-RAM (memory sleep) -to provide reduced resume latency. +to provide reduced resume latency. It is always supported. State: Standby / Power-On Suspend ACPI State: S1 -String: "standby" +Label: "standby" -This state offers minimal, though real, power savings, while providing -a very low-latency transition back to a working system. No operating -state is lost (the CPU retains power), so the system easily starts up +This state, if supported, offers moderate, though real, power savings, while +providing a relatively low-latency transition back to a working system. No +operating state is lost (the CPU retains power), so the system easily starts up again where it left off. -We try to put devices in a low-power state equivalent to D1, which -also offers low power savings, but low resume latency. Not all devices -support D1, and those that don't are left on. +In addition to freezing user space and putting all I/O devices into low-power +states, which is done for Suspend-To-Idle too, nonboot CPUs are taken offline +and all low-level system functions are suspended during transitions into this +state. For this reason, it should allow more energy to be saved relative to +Suspend-To-Idle, but the resume latency will generally be greater than for that +state. State: Suspend-to-RAM ACPI State: S3 -String: "mem" +Label: "mem" -This state offers significant power savings as everything in the -system is put into a low-power state, except for memory, which is -placed in self-refresh mode to retain its contents. +This state, if supported, offers significant power savings as everything in the +system is put into a low-power state, except for memory, which should be placed +into the self-refresh mode to retain its contents. All of the steps carried out +when entering Power-On Suspend are also carried out during transitions to STR. +Additional operations may take place depending on the platform capabilities. In +particular, on ACPI systems the kernel passes control to the BIOS (platform +firmware) as the last step during STR transitions and that usually results in +powering down some more low-level components that aren't directly controlled by +the kernel. -System and device state is saved and kept in memory. All devices are -suspended and put into D3. In many cases, all peripheral buses lose -power when entering STR, so devices must be able to handle the -transition back to the On state. +System and device state is saved and kept in memory. All devices are suspended +and put into low-power states. In many cases, all peripheral buses lose power +when entering STR, so devices must be able to handle the transition back to the +"on" state. -For at least ACPI, STR requires some minimal boot-strapping code to -resume the system from STR. This may be true on other platforms. +For at least ACPI, STR requires some minimal boot-strapping code to resume the +system from it. This may be the case on other platforms too. State: Suspend-to-disk ACPI State: S4 -String: "disk" +Label: "disk" This state offers the greatest power savings, and can be used even in the absence of low-level platform support for power management. This diff --git a/kernel/power/main.c b/kernel/power/main.c index 9f51f0ab3d86..573410d6647e 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -279,14 +279,14 @@ static inline void pm_print_times_init(void) {} struct kobject *power_kobj; /** - * state - control system power state. + * state - control system sleep states. * - * show() returns what states are supported, which is hard-coded to - * 'freeze' (Low-Power Idle), 'standby' (Power-On Suspend), - * 'mem' (Suspend-to-RAM), and 'disk' (Suspend-to-Disk). + * show() returns available sleep state labels, which may be "mem", "standby", + * "freeze" and "disk" (hibernation). See Documentation/power/states.txt for a + * description of what they mean. * - * store() accepts one of those strings, translates it into the - * proper enumerated value, and initiates a suspend transition. + * store() accepts one of those strings, translates it into the proper + * enumerated value, and initiates a suspend transition. */ static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 00aca60904b0..338a6f147974 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -78,6 +78,26 @@ static bool valid_state(suspend_state_t state) return suspend_ops && suspend_ops->valid && suspend_ops->valid(state); } +/* + * If this is set, the "mem" label always corresponds to the deepest sleep state + * available, the "standby" label corresponds to the second deepest sleep state + * available (if any), and the "freeze" label corresponds to the remaining + * available sleep state (if there is one). + */ +static bool relative_states; + +static int __init sleep_states_setup(char *str) +{ + relative_states = !strncmp(str, "1", 1); + if (relative_states) { + pm_states[PM_SUSPEND_MEM].state = PM_SUSPEND_FREEZE; + pm_states[PM_SUSPEND_FREEZE].state = 0; + } + return 1; +} + +__setup("relative_sleep_states=", sleep_states_setup); + /** * suspend_set_ops - Set the global suspend method table. * @ops: Suspend operations to use. @@ -85,12 +105,20 @@ static bool valid_state(suspend_state_t state) void suspend_set_ops(const struct platform_suspend_ops *ops) { suspend_state_t i; + int j = PM_SUSPEND_MAX - 1; lock_system_sleep(); suspend_ops = ops; - for (i = PM_SUSPEND_STANDBY; i <= PM_SUSPEND_MEM; i++) - pm_states[i].state = valid_state(i) ? i : 0; + for (i = PM_SUSPEND_MEM; i >= PM_SUSPEND_STANDBY; i--) + if (valid_state(i)) + pm_states[j--].state = i; + else if (!relative_states) + pm_states[j--].state = 0; + + pm_states[j--].state = PM_SUSPEND_FREEZE; + while (j >= PM_SUSPEND_MIN) + pm_states[j--].state = 0; unlock_system_sleep(); } -- cgit v1.2.3 From 7913ad1ad83409e7f9ed5758bb4324bf64c95a73 Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Sat, 12 Apr 2014 23:48:56 +1000 Subject: m68k: Multi-platform EARLY_PRINTK Make the boot console available to more m68k platforms by leveraging the head.S debug console. The boot console is enabled by the "earlyprintk" command line argument which is how most other architectures do this. This is a change of behaviour for the Mac but does not negatively impact the common use-case which is not debugging. This is also a change of behaviour for other platforms because it means the serial port stays quiet when CONFIG_EARLY_PRINTK is not enabled. This is also an improvement for the common use-case. Signed-off-by: Finn Thain Tested-by: Stephen N Chivers [Geert: CONSOLE_DEBUG should depend on CONFIG_FONT_SUPPORT] Reported-by: kbuild test robot Signed-off-by: Geert Uytterhoeven --- Documentation/kernel-parameters.txt | 2 +- arch/m68k/Kconfig.debug | 9 ++++-- arch/m68k/kernel/Makefile | 2 ++ arch/m68k/kernel/early_printk.c | 62 +++++++++++++++++++++++++++++++++++++ arch/m68k/kernel/head.S | 36 +++++++-------------- arch/m68k/mac/config.c | 29 ----------------- 6 files changed, 84 insertions(+), 56 deletions(-) create mode 100644 arch/m68k/kernel/early_printk.c (limited to 'Documentation/kernel-parameters.txt') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 30a8ad0dae53..7da289ee0589 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -892,7 +892,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. (mmio) or 32-bit (mmio32). The options are the same as for ttyS, above. - earlyprintk= [X86,SH,BLACKFIN,ARM] + earlyprintk= [X86,SH,BLACKFIN,ARM,M68k] earlyprintk=vga earlyprintk=efi earlyprintk=xen diff --git a/arch/m68k/Kconfig.debug b/arch/m68k/Kconfig.debug index 229682721240..64776d7ac199 100644 --- a/arch/m68k/Kconfig.debug +++ b/arch/m68k/Kconfig.debug @@ -12,12 +12,17 @@ config BOOTPARAM_STRING config EARLY_PRINTK bool "Early printk" - depends on MVME16x || MAC + depends on !(SUN3 || M68360 || M68000 || COLDFIRE) help Write kernel log output directly to a serial port. + Where implemented, output goes to the framebuffer as well. + PROM console functionality on Sun 3x is not affected by this option. + + Pass "earlyprintk" on the kernel command line to get a + boot console. This is useful for kernel debugging when your machine crashes very - early before the console code is initialized. + early, i.e. before the normal console driver is loaded. You should normally say N here, unless you want to debug such a crash. if !MMU diff --git a/arch/m68k/kernel/Makefile b/arch/m68k/kernel/Makefile index 2d5d9be16273..e47778f8588d 100644 --- a/arch/m68k/kernel/Makefile +++ b/arch/m68k/kernel/Makefile @@ -25,3 +25,5 @@ obj-$(CONFIG_HAS_DMA) += dma.o obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o obj-$(CONFIG_BOOTINFO_PROC) += bootinfo_proc.o +obj-$(CONFIG_EARLY_PRINTK) += early_printk.o + diff --git a/arch/m68k/kernel/early_printk.c b/arch/m68k/kernel/early_printk.c new file mode 100644 index 000000000000..919b83794545 --- /dev/null +++ b/arch/m68k/kernel/early_printk.c @@ -0,0 +1,62 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (c) 2014 Finn Thain + */ + +#include +#include +#include +#include +#include + +asmlinkage void __init debug_cons_nputs(const char *s, unsigned n); + +static void debug_cons_write(struct console *c, + const char *s, unsigned n) +{ + debug_cons_nputs(s, n); +} + +static struct console early_console_instance = { + .name = "debug", + .write = debug_cons_write, + .flags = CON_PRINTBUFFER | CON_BOOT, + .index = -1 +}; + +static int __init setup_early_printk(char *buf) +{ + /* MVME16x registers an early console after interrupt setup. */ + if (MACH_IS_MVME16x) + return 0; + + if (early_console || buf) + return 0; + + early_console = &early_console_instance; + register_console(early_console); + + return 0; +} +early_param("earlyprintk", setup_early_printk); + +/* + * debug_cons_nputs() defined in arch/m68k/kernel/head.S cannot be called + * after init sections are discarded (for platforms that use it). + */ +#if !(defined(CONFIG_SUN3) || defined(CONFIG_M68360) || \ + defined(CONFIG_M68000) || defined(CONFIG_COLDFIRE)) + +static int __init unregister_early_console(void) +{ + if (!early_console) + return 0; + + return unregister_console(early_console); +} +late_initcall(unregister_early_console); + +#endif diff --git a/arch/m68k/kernel/head.S b/arch/m68k/kernel/head.S index 81e610bfa237..a3cfada88368 100644 --- a/arch/m68k/kernel/head.S +++ b/arch/m68k/kernel/head.S @@ -221,7 +221,7 @@ * MMU_PRINT: There is a routine built into head.S that can display the * MMU data structures. It outputs its result through the serial_putc * interface. So where ever that winds up driving data, that's where the - * mmu struct will appear. On the Macintosh that's typically the console. + * mmu struct will appear. * * SERIAL_DEBUG: There are a series of putc() macro statements * scattered through out the code to give progress of status to the @@ -249,8 +249,8 @@ * USE_MFP: Use the ST-MFP port (Modem1) for serial debug. * * Macintosh constants: - * MAC_USE_SCC_A: Use SCC port A (modem) for serial debug and early console. - * MAC_USE_SCC_B: Use SCC port B (printer) for serial debug and early console. + * MAC_USE_SCC_A: Use SCC port A (modem) for serial debug. + * MAC_USE_SCC_B: Use SCC port B (printer) for serial debug. */ #include @@ -267,27 +267,17 @@ #include #include #include - #ifdef CONFIG_MAC - -#include - -#ifdef CONFIG_FRAMEBUFFER_CONSOLE -#define CONSOLE_DEBUG +# include #endif #ifdef CONFIG_EARLY_PRINTK -#define SERIAL_DEBUG -#else -#undef SERIAL_DEBUG +# define SERIAL_DEBUG +# if defined(CONFIG_MAC) && defined(CONFIG_FONT_SUPPORT) +# define CONSOLE_DEBUG +# endif #endif -#else /* !CONFIG_MAC */ - -#define SERIAL_DEBUG - -#endif /* !CONFIG_MAC */ - #undef MMU_PRINT #undef MMU_NOCACHE_KERNEL #undef DEBUG @@ -3213,21 +3203,19 @@ func_start putn,%d0-%d2 func_return putn -#ifdef CONFIG_MAC +#ifdef CONFIG_EARLY_PRINTK /* - * mac_early_print - * * This routine takes its parameters on the stack. It then * turns around and calls the internal routines. This routine * is used by the boot console. * * The calling parameters are: - * void mac_early_print(const char *str, unsigned length); + * void debug_cons_nputs(const char *str, unsigned length) * * This routine does NOT understand variable arguments only * simple strings! */ -ENTRY(mac_early_print) +ENTRY(debug_cons_nputs) moveml %d0/%d1/%a0,%sp@- movew %sr,%sp@- ori #0x0700,%sr @@ -3249,7 +3237,7 @@ ENTRY(mac_early_print) movew %sp@+,%sr moveml %sp@+,%d0/%d1/%a0 rts -#endif /* CONFIG_MAC */ +#endif /* CONFIG_EARLY_PRINTK */ #if defined(CONFIG_HP300) || defined(CONFIG_APOLLO) func_start set_leds,%d0/%a0 diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c index 982c3fe73c4a..a471eab1a4dd 100644 --- a/arch/m68k/mac/config.c +++ b/arch/m68k/mac/config.c @@ -71,31 +71,6 @@ static void mac_get_model(char *str); static void mac_identify(void); static void mac_report_hardware(void); -#ifdef CONFIG_EARLY_PRINTK -asmlinkage void __init mac_early_print(const char *s, unsigned n); - -static void __init mac_early_cons_write(struct console *con, - const char *s, unsigned n) -{ - mac_early_print(s, n); -} - -static struct console __initdata mac_early_cons = { - .name = "early", - .write = mac_early_cons_write, - .flags = CON_PRINTBUFFER | CON_BOOT, - .index = -1 -}; - -int __init mac_unregister_early_cons(void) -{ - /* mac_early_print can't be used after init sections are discarded */ - return unregister_console(&mac_early_cons); -} - -late_initcall(mac_unregister_early_cons); -#endif - static void __init mac_sched_init(irq_handler_t vector) { via_init_clock(vector); @@ -190,10 +165,6 @@ void __init config_mac(void) mach_beep = mac_mksound; #endif -#ifdef CONFIG_EARLY_PRINTK - register_console(&mac_early_cons); -#endif - /* * Determine hardware present */ -- cgit v1.2.3 From 4fc0a7e889e5540305926e41931cf3bc0a60abb2 Mon Sep 17 00:00:00 2001 From: Lv Zheng Date: Sat, 31 May 2014 08:15:02 +0800 Subject: ACPI: Fix x86 regression related to early mapping size limitation The following warning message is triggered: WARNING: CPU: 0 PID: 0 at mm/early_ioremap.c:136 __early_ioremap+0x11f/0x1f2() Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 3.15.0-rc1-00017-g86dfc6f3-dirty #298 Hardware name: Intel Corporation S2600CP/S2600CP, BIOS SE5C600.86B.99.99.x036.091920111209 09/19/2011 0000000000000009 ffffffff81b75c40 ffffffff817c627b 0000000000000000 ffffffff81b75c78 ffffffff81067b5d 000000000000007b 8000000000000563 00000000b96b20dc 0000000000000001 ffffffffff300e0c ffffffff81b75c88 Call Trace: [] dump_stack+0x45/0x56 [] warn_slowpath_common+0x7d/0xa0 [] warn_slowpath_null+0x1a/0x20 [] __early_ioremap+0x11f/0x1f2 [] early_ioremap+0x13/0x15 [] __acpi_map_table+0x13/0x18 [] acpi_os_map_memory+0x26/0x14e [] acpi_tb_acquire_table+0x42/0x70 [] acpi_tb_validate_table+0x27/0x37 [] acpi_tb_verify_table+0x22/0xd8 [] acpi_tb_install_non_fixed_table+0x60/0x1c9 [] acpi_tb_parse_root_table+0x218/0x26a [] ? early_idt_handlers+0x120/0x120 [] acpi_initialize_tables+0x57/0x59 [] acpi_table_init+0x1b/0x99 [] acpi_boot_table_init+0x1e/0x85 [] setup_arch+0x99d/0xcc6 [] ? early_idt_handlers+0x120/0x120 [] start_kernel+0x8b/0x415 [] ? early_idt_handlers+0x120/0x120 [] x86_64_start_reservations+0x2a/0x2c [] x86_64_start_kernel+0x13e/0x14d ---[ end trace 11ae599a1898f4e7 ]--- when installing the following table during early stage: ACPI: SSDT 0x00000000B9638018 07A0C4 (v02 INTEL S2600CP 00004000 INTL 20100331) The regression is caused by the size limitation of the x86 early IO mapping. The root cause is: 1. ACPICA doesn't split IO memory mapping and table mapping; 2. Linux x86 OSL implements acpi_os_map_memory() using a size limited fix-map mechanism during early boot stage, which is more suitable for only IO mappings. This patch fixes this issue by utilizing acpi_gbl_verify_table_checksum to disable the table mapping during early stage and enabling it again for the late stage. In this way, the normal code path is not affected. Then after the code related to the root cause is cleaned up, the early checksum verification can be easily re-enabled. A new boot parameter - acpi_force_table_verification is introduced for the platforms that require the checksum verification to stop loading bad tables. This fix also covers the checksum verification for the table overrides. Now large tables can also be overridden using the initrd override mechanism. Signed-off-by: Lv Zheng Reported-and-tested-by: Yuanhan Liu Signed-off-by: Rafael J. Wysocki --- Documentation/kernel-parameters.txt | 5 +++++ drivers/acpi/bus.c | 3 +++ drivers/acpi/tables.c | 23 +++++++++++++++++++++++ 3 files changed, 31 insertions(+) (limited to 'Documentation/kernel-parameters.txt') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 60a278948652..4b7cc1481436 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -214,6 +214,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. unusable. The "log_buf_len" parameter may be useful if you need to capture more output. + acpi_force_table_verification [HW,ACPI] + Enable table checksum verification during early stage. + By default, this is disabled due to x86 early mapping + size limitation. + acpi_irq_balance [HW,ACPI] ACPI will balance active IRQs default in APIC mode diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index cf925c4f36b7..cf0b5ecf55b6 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -466,6 +466,9 @@ void __init acpi_early_init(void) printk(KERN_INFO PREFIX "Core revision %08x\n", ACPI_CA_VERSION); + /* It's safe to verify table checksums during late stage */ + acpi_gbl_verify_table_checksum = TRUE; + /* enable workarounds, unless strict ACPI spec. compliance */ if (!acpi_strict) acpi_gbl_enable_interpreter_slack = TRUE; diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c index 21782290df41..05550ba44d32 100644 --- a/drivers/acpi/tables.c +++ b/drivers/acpi/tables.c @@ -44,6 +44,12 @@ static struct acpi_table_desc initial_tables[ACPI_MAX_TABLES] __initdata; static int acpi_apic_instance __initdata; +/* + * Disable table checksum verification for the early stage due to the size + * limitation of the current x86 early mapping implementation. + */ +static bool acpi_verify_table_checksum __initdata = false; + void acpi_table_print_madt_entry(struct acpi_subtable_header *header) { if (!header) @@ -333,6 +339,14 @@ int __init acpi_table_init(void) { acpi_status status; + if (acpi_verify_table_checksum) { + pr_info("Early table checksum verification enabled\n"); + acpi_gbl_verify_table_checksum = TRUE; + } else { + pr_info("Early table checksum verification disabled\n"); + acpi_gbl_verify_table_checksum = FALSE; + } + status = acpi_initialize_tables(initial_tables, ACPI_MAX_TABLES, 0); if (ACPI_FAILURE(status)) return -EINVAL; @@ -354,3 +368,12 @@ static int __init acpi_parse_apic_instance(char *str) } early_param("acpi_apic_instance", acpi_parse_apic_instance); + +static int __init acpi_force_table_verification_setup(char *s) +{ + acpi_verify_table_checksum = true; + + return 0; +} + +early_param("acpi_force_table_verification", acpi_force_table_verification_setup); -- cgit v1.2.3 From 5ea3b1b2f8ad9162684431ce6188102ca4c64b7a Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Wed, 4 Jun 2014 16:06:54 -0700 Subject: cma: add placement specifier for "cma=" kernel parameter Currently, "cma=" kernel parameter is used to specify the size of CMA, but we can't specify where it is located. We want to locate CMA below 4GB for devices only supporting 32-bit addressing on 64-bit systems without iommu. This enables to specify the placement of CMA by extending "cma=" kernel parameter. Examples: 1. locate 64MB CMA below 4GB by "cma=64M@0-4G" 2. locate 64MB CMA exact at 512MB by "cma=64M@512M" Note that the DMA contiguous memory allocator on x86 assumes that page_address() works for the pages to allocate. So this change requires to limit end address of contiguous memory area upto max_pfn_mapped to prevent from locating it on highmem area by the argument of dma_contiguous_reserve(). Signed-off-by: Akinobu Mita Cc: Marek Szyprowski Cc: Konrad Rzeszutek Wilk Cc: David Woodhouse Cc: Don Dutile Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Andi Kleen Cc: Yinghai Lu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 7 +++++-- arch/x86/kernel/setup.c | 2 +- drivers/base/dma-contiguous.c | 42 ++++++++++++++++++++++++++++--------- include/linux/dma-contiguous.h | 9 +++++--- 4 files changed, 44 insertions(+), 16 deletions(-) (limited to 'Documentation/kernel-parameters.txt') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index af55e13ace8f..adea3a22fa00 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -630,8 +630,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Also note the kernel might malfunction if you disable some critical bits. - cma=nn[MG] [ARM,KNL] - Sets the size of kernel global memory area for contiguous + cma=nn[MG]@[start[MG][-end[MG]]] + [ARM,X86,KNL] + Sets the size of kernel global memory area for + contiguous memory allocations and optionally the + placement constraint by the physical address range of memory allocations. For more information, see include/linux/dma-contiguous.h diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 09c76d265550..78a0e6298922 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1119,7 +1119,7 @@ void __init setup_arch(char **cmdline_p) setup_real_mode(); memblock_set_current_limit(get_max_mapped()); - dma_contiguous_reserve(0); + dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT); /* * NOTE: On x86-32, only from this point on, fixmaps are ready for use. diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c index c34ec3364243..83969f8c5727 100644 --- a/drivers/base/dma-contiguous.c +++ b/drivers/base/dma-contiguous.c @@ -60,11 +60,22 @@ struct cma *dma_contiguous_default_area; */ static const phys_addr_t size_bytes = CMA_SIZE_MBYTES * SZ_1M; static phys_addr_t size_cmdline = -1; +static phys_addr_t base_cmdline; +static phys_addr_t limit_cmdline; static int __init early_cma(char *p) { pr_debug("%s(%s)\n", __func__, p); size_cmdline = memparse(p, &p); + if (*p != '@') + return 0; + base_cmdline = memparse(p + 1, &p); + if (*p != '-') { + limit_cmdline = base_cmdline + size_cmdline; + return 0; + } + limit_cmdline = memparse(p + 1, &p); + return 0; } early_param("cma", early_cma); @@ -108,11 +119,18 @@ static inline __maybe_unused phys_addr_t cma_early_percent_memory(void) void __init dma_contiguous_reserve(phys_addr_t limit) { phys_addr_t selected_size = 0; + phys_addr_t selected_base = 0; + phys_addr_t selected_limit = limit; + bool fixed = false; pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit); if (size_cmdline != -1) { selected_size = size_cmdline; + selected_base = base_cmdline; + selected_limit = min_not_zero(limit_cmdline, limit); + if (base_cmdline + size_cmdline == limit_cmdline) + fixed = true; } else { #ifdef CONFIG_CMA_SIZE_SEL_MBYTES selected_size = size_bytes; @@ -129,10 +147,12 @@ void __init dma_contiguous_reserve(phys_addr_t limit) pr_debug("%s: reserving %ld MiB for global area\n", __func__, (unsigned long)selected_size / SZ_1M); - dma_contiguous_reserve_area(selected_size, 0, limit, - &dma_contiguous_default_area); + dma_contiguous_reserve_area(selected_size, selected_base, + selected_limit, + &dma_contiguous_default_area, + fixed); } -}; +} static DEFINE_MUTEX(cma_mutex); @@ -189,15 +209,20 @@ core_initcall(cma_init_reserved_areas); * @base: Base address of the reserved area optional, use 0 for any * @limit: End address of the reserved memory (optional, 0 for any). * @res_cma: Pointer to store the created cma region. + * @fixed: hint about where to place the reserved area * * This function reserves memory from early allocator. It should be * called by arch specific code once the early allocator (memblock or bootmem) * has been activated and all other subsystems have already allocated/reserved * memory. This function allows to create custom reserved areas for specific * devices. + * + * If @fixed is true, reserve contiguous area at exactly @base. If false, + * reserve in range from @base to @limit. */ int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base, - phys_addr_t limit, struct cma **res_cma) + phys_addr_t limit, struct cma **res_cma, + bool fixed) { struct cma *cma = &cma_areas[cma_area_count]; phys_addr_t alignment; @@ -223,18 +248,15 @@ int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base, limit &= ~(alignment - 1); /* Reserve memory */ - if (base) { + if (base && fixed) { if (memblock_is_region_reserved(base, size) || memblock_reserve(base, size) < 0) { ret = -EBUSY; goto err; } } else { - /* - * Use __memblock_alloc_base() since - * memblock_alloc_base() panic()s. - */ - phys_addr_t addr = __memblock_alloc_base(size, alignment, limit); + phys_addr_t addr = memblock_alloc_range(size, alignment, base, + limit); if (!addr) { ret = -ENOMEM; goto err; diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h index 3b28f937d959..772eab5d524a 100644 --- a/include/linux/dma-contiguous.h +++ b/include/linux/dma-contiguous.h @@ -88,7 +88,8 @@ static inline void dma_contiguous_set_default(struct cma *cma) void dma_contiguous_reserve(phys_addr_t addr_limit); int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base, - phys_addr_t limit, struct cma **res_cma); + phys_addr_t limit, struct cma **res_cma, + bool fixed); /** * dma_declare_contiguous() - reserve area for contiguous memory handling @@ -108,7 +109,7 @@ static inline int dma_declare_contiguous(struct device *dev, phys_addr_t size, { struct cma *cma; int ret; - ret = dma_contiguous_reserve_area(size, base, limit, &cma); + ret = dma_contiguous_reserve_area(size, base, limit, &cma, true); if (ret == 0) dev_set_cma_area(dev, cma); @@ -136,7 +137,9 @@ static inline void dma_contiguous_set_default(struct cma *cma) { } static inline void dma_contiguous_reserve(phys_addr_t limit) { } static inline int dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base, - phys_addr_t limit, struct cma **res_cma) { + phys_addr_t limit, struct cma **res_cma, + bool fixed) +{ return -ENOSYS; } -- cgit v1.2.3 From 7b0b73d76651e5f88c88b76efa18d719f832bf6f Mon Sep 17 00:00:00 2001 From: Prarit Bhargava Date: Wed, 4 Jun 2014 16:12:17 -0700 Subject: init/main.c: add initcall_blacklist kernel parameter When a module is built into the kernel the module_init() function becomes an initcall. Sometimes debugging through dynamic debug can help, however, debugging built in kernel modules is typically done by changing the .config, recompiling, and booting the new kernel in an effort to determine exactly which module caused a problem. This patchset can be useful stand-alone or combined with initcall_debug. There are cases where some initcalls can hang the machine before the console can be flushed, which can make initcall_debug output inaccurate. Having the ability to skip initcalls can help further debugging of these scenarios. Usage: initcall_blacklist= ex) added "initcall_blacklist=sgi_uv_sysfs_init" as a kernel parameter and the log contains: blacklisting initcall sgi_uv_sysfs_init ... ... initcall sgi_uv_sysfs_init blacklisted ex) added "initcall_blacklist=foo_bar,sgi_uv_sysfs_init" as a kernel parameter and the log contains: blacklisting initcall foo_bar blacklisting initcall sgi_uv_sysfs_init ... ... initcall sgi_uv_sysfs_init blacklisted [akpm@linux-foundation.org: tweak printk text] Signed-off-by: Prarit Bhargava Cc: Richard Weinberger Cc: Andi Kleen Cc: Josh Boyer Cc: Rob Landley Cc: Steven Rostedt Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Frederic Weisbecker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 4 +++ init/main.c | 68 +++++++++++++++++++++++++++++++++++++ 2 files changed, 72 insertions(+) (limited to 'Documentation/kernel-parameters.txt') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index adea3a22fa00..9973a7e2e0ac 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1312,6 +1312,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. for working out where the kernel is dying during startup. + initcall_blacklist= [KNL] Do not execute a comma-separated list of + initcall functions. Useful for debugging built-in + modules and initcalls. + initrd= [BOOT] Specify the location of the initial ramdisk inport.irq= [HW] Inport (ATI XL and Microsoft) busmouse driver diff --git a/init/main.c b/init/main.c index 9d3a7b84de5c..8ac3833f2bdf 100644 --- a/init/main.c +++ b/init/main.c @@ -77,6 +77,7 @@ #include #include #include +#include #include #include @@ -665,6 +666,70 @@ static void __init do_ctors(void) bool initcall_debug; core_param(initcall_debug, initcall_debug, bool, 0644); +#ifdef CONFIG_KALLSYMS +struct blacklist_entry { + struct list_head next; + char *buf; +}; + +static __initdata_or_module LIST_HEAD(blacklisted_initcalls); + +static int __init initcall_blacklist(char *str) +{ + char *str_entry; + struct blacklist_entry *entry; + + /* str argument is a comma-separated list of functions */ + do { + str_entry = strsep(&str, ","); + if (str_entry) { + pr_debug("blacklisting initcall %s\n", str_entry); + entry = alloc_bootmem(sizeof(*entry)); + entry->buf = alloc_bootmem(strlen(str_entry) + 1); + strcpy(entry->buf, str_entry); + list_add(&entry->next, &blacklisted_initcalls); + } + } while (str_entry); + + return 0; +} + +static bool __init_or_module initcall_blacklisted(initcall_t fn) +{ + struct list_head *tmp; + struct blacklist_entry *entry; + char *fn_name; + + fn_name = kasprintf(GFP_KERNEL, "%pf", fn); + if (!fn_name) + return false; + + list_for_each(tmp, &blacklisted_initcalls) { + entry = list_entry(tmp, struct blacklist_entry, next); + if (!strcmp(fn_name, entry->buf)) { + pr_debug("initcall %s blacklisted\n", fn_name); + kfree(fn_name); + return true; + } + } + + kfree(fn_name); + return false; +} +#else +static int __init initcall_blacklist(char *str) +{ + pr_warn("initcall_blacklist requires CONFIG_KALLSYMS\n"); + return 0; +} + +static bool __init_or_module initcall_blacklisted(initcall_t fn) +{ + return false; +} +#endif +__setup("initcall_blacklist=", initcall_blacklist); + static int __init_or_module do_one_initcall_debug(initcall_t fn) { ktime_t calltime, delta, rettime; @@ -689,6 +754,9 @@ int __init_or_module do_one_initcall(initcall_t fn) int ret; char msgbuf[64]; + if (initcall_blacklisted(fn)) + return -EPERM; + if (initcall_debug) ret = do_one_initcall_debug(fn); else -- cgit v1.2.3 From f06e5153f4ae2e2f3b0300f0e260e40cb7fefd45 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 6 Jun 2014 14:37:07 -0700 Subject: kernel/panic.c: add "crash_kexec_post_notifiers" option for kdump after panic_notifers Add a "crash_kexec_post_notifiers" boot option to run kdump after running panic_notifiers and dump kmsg. This can help rare situations where kdump fails because of unstable crashed kernel or hardware failure (memory corruption on critical data/code), or the 2nd kernel is already broken by the 1st kernel (it's a broken behavior, but who can guarantee that the "crashed" kernel works correctly?). Usage: add "crash_kexec_post_notifiers" to kernel boot option. Note that this actually increases risks of the failure of kdump. This option should be set only if you worry about the rare case of kdump failure rather than increasing the chance of success. Signed-off-by: Masami Hiramatsu Acked-by: Motohiro Kosaki Acked-by: Vivek Goyal Cc: Eric Biederman Cc: Yoshihiro YUNOMAE Cc: Satoru MORIYA Cc: Tomoki Sekiyama Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 8 ++++++++ kernel/panic.c | 23 +++++++++++++++++++++-- 2 files changed, 29 insertions(+), 2 deletions(-) (limited to 'Documentation/kernel-parameters.txt') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 9973a7e2e0ac..b9f67781c577 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2361,6 +2361,14 @@ bytes respectively. Such letter suffixes can also be entirely omitted. timeout < 0: reboot immediately Format: + crash_kexec_post_notifiers + Run kdump after running panic-notifiers and dumping + kmsg. This only for the users who doubt kdump always + succeeds in any situation. + Note that this also increases risks of kdump failure, + because some panic notifiers can make the crashed + kernel more unstable. + parkbd.port= [HW] Parallel port number the keyboard adapter is connected to, default is 0. Format: diff --git a/kernel/panic.c b/kernel/panic.c index d02fa9fef46a..62e16cef9cc2 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -32,6 +32,7 @@ static unsigned long tainted_mask; static int pause_on_oops; static int pause_on_oops_flag; static DEFINE_SPINLOCK(pause_on_oops_lock); +static bool crash_kexec_post_notifiers; int panic_timeout = CONFIG_PANIC_TIMEOUT; EXPORT_SYMBOL_GPL(panic_timeout); @@ -112,9 +113,11 @@ void panic(const char *fmt, ...) /* * If we have crashed and we have a crash kernel loaded let it handle * everything else. - * Do we want to call this before we try to display a message? + * If we want to run this after calling panic_notifiers, pass + * the "crash_kexec_post_notifiers" option to the kernel. */ - crash_kexec(NULL); + if (!crash_kexec_post_notifiers) + crash_kexec(NULL); /* * Note smp_send_stop is the usual smp shutdown function, which @@ -131,6 +134,15 @@ void panic(const char *fmt, ...) kmsg_dump(KMSG_DUMP_PANIC); + /* + * If you doubt kdump always works fine in any situation, + * "crash_kexec_post_notifiers" offers you a chance to run + * panic_notifiers and dumping kmsg before kdump. + * Note: since some panic_notifiers can make crashed kernel + * more unstable, it can increase risks of the kdump failure too. + */ + crash_kexec(NULL); + bust_spinlocks(0); if (!panic_blink) @@ -472,6 +484,13 @@ EXPORT_SYMBOL(__stack_chk_fail); core_param(panic, panic_timeout, int, 0644); core_param(pause_on_oops, pause_on_oops, int, 0644); +static int __init setup_crash_kexec_post_notifiers(char *s) +{ + crash_kexec_post_notifiers = true; + return 0; +} +early_param("crash_kexec_post_notifiers", setup_crash_kexec_post_notifiers); + static int __init oops_setup(char *s) { if (!s) -- cgit v1.2.3