linux_dsm_epyc7002/arch/x86/include/asm/x86_init.h

246 lines
7.8 KiB
C
Raw Normal View History

x86: Add x86_init infrastructure The upcoming Moorestown support brings the embedded world to x86. The setup code of x86 has already a couple of hooks which are either x86_quirks or paravirt ops. Some of those setup hooks are pretty convoluted like the timer setup and the tsc calibration code. But there are other places which could do with a cleanup. Instead of having inline functions/macros which are modified at compile time I decided to introduce x86_init ops which are unconditional in the code and make it clear that they can be changed either during compile time or in the early boot process. The function pointers are initialized by default functions which can be noops so that the pointer can be called unconditionally in the most cases. This also allows us to remove 32bit/64bit, paravirt and other #ifdeffery. paravirt guests are just a hardware platform in the setup code, so we should treat them as such and not hide all behind multiple layers of indirection and compile time dependencies. It's more obvious that x86_init.timers.timer_init() is a function pointer than the late_time_init = choose_time_init() obscurity. It's also way simpler to grep for x86_init.timers.timer_init and find all the places which modify that function pointer instead of analyzing weak functions, macros and paravirt indirections. Note. This is not a general paravirt_ops replacement. It just will move setup related hooks which are potentially useful for other platform setup purposes as well out of the paravirt domain. Add the base infrastructure without any functionality. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2009-08-19 19:48:38 +07:00
#ifndef _ASM_X86_PLATFORM_H
#define _ASM_X86_PLATFORM_H
#include <asm/bootparam.h>
struct mpc_bus;
struct mpc_cpu;
struct mpc_table;
struct cpuinfo_x86;
/**
* struct x86_init_mpparse - platform specific mpparse ops
* @mpc_record: platform specific mpc record accounting
* @setup_ioapic_ids: platform specific ioapic id override
* @mpc_apic_id: platform specific mpc apic id assignment
* @smp_read_mpc_oem: platform specific oem mpc table setup
* @mpc_oem_pci_bus: platform specific pci bus setup (default NULL)
* @mpc_oem_bus_info: platform specific mpc bus info
* @find_smp_config: find the smp configuration
* @get_smp_config: get the smp configuration
*/
struct x86_init_mpparse {
void (*mpc_record)(unsigned int mode);
void (*setup_ioapic_ids)(void);
int (*mpc_apic_id)(struct mpc_cpu *m);
void (*smp_read_mpc_oem)(struct mpc_table *mpc);
void (*mpc_oem_pci_bus)(struct mpc_bus *m);
void (*mpc_oem_bus_info)(struct mpc_bus *m, char *name);
void (*find_smp_config)(void);
void (*get_smp_config)(unsigned int early);
};
/**
* struct x86_init_resources - platform specific resource related ops
* @probe_roms: probe BIOS roms
* @reserve_resources: reserve the standard resources for the
* platform
* @memory_setup: platform specific memory setup
*
*/
struct x86_init_resources {
void (*probe_roms)(void);
void (*reserve_resources)(void);
char *(*memory_setup)(void);
};
/**
* struct x86_init_irqs - platform specific interrupt setup
* @pre_vector_init: init code to run before interrupt vectors
* are set up.
* @intr_init: interrupt init code
* @trap_init: platform specific trap setup
*/
struct x86_init_irqs {
void (*pre_vector_init)(void);
void (*intr_init)(void);
void (*trap_init)(void);
};
/**
* struct x86_init_oem - oem platform specific customizing functions
* @arch_setup: platform specific architecure setup
* @banner: print a platform specific banner
*/
struct x86_init_oem {
void (*arch_setup)(void);
void (*banner)(void);
};
/**
* struct x86_init_paging - platform specific paging functions
* @pagetable_init: platform specific paging initialization call to setup
* the kernel pagetables and prepare accessors functions.
* Callback must call paging_init(). Called once after the
* direct mapping for phys memory is available.
*/
struct x86_init_paging {
void (*pagetable_init)(void);
};
/**
* struct x86_init_timers - platform specific timer setup
* @setup_perpcu_clockev: set up the per cpu clock event device for the
* boot cpu
* @timer_init: initialize the platform timer (default PIT/HPET)
* @wallclock_init: init the wallclock device
*/
struct x86_init_timers {
void (*setup_percpu_clockev)(void);
void (*timer_init)(void);
void (*wallclock_init)(void);
};
/**
* struct x86_init_iommu - platform specific iommu setup
* @iommu_init: platform specific iommu setup
*/
struct x86_init_iommu {
int (*iommu_init)(void);
};
/**
* struct x86_init_pci - platform specific pci init functions
* @arch_init: platform specific pci arch init call
* @init: platform specific pci subsystem init
* @init_irq: platform specific pci irq init
* @fixup_irqs: platform specific pci irq fixup
*/
struct x86_init_pci {
int (*arch_init)(void);
int (*init)(void);
void (*init_irq)(void);
void (*fixup_irqs)(void);
};
x86: Add x86_init infrastructure The upcoming Moorestown support brings the embedded world to x86. The setup code of x86 has already a couple of hooks which are either x86_quirks or paravirt ops. Some of those setup hooks are pretty convoluted like the timer setup and the tsc calibration code. But there are other places which could do with a cleanup. Instead of having inline functions/macros which are modified at compile time I decided to introduce x86_init ops which are unconditional in the code and make it clear that they can be changed either during compile time or in the early boot process. The function pointers are initialized by default functions which can be noops so that the pointer can be called unconditionally in the most cases. This also allows us to remove 32bit/64bit, paravirt and other #ifdeffery. paravirt guests are just a hardware platform in the setup code, so we should treat them as such and not hide all behind multiple layers of indirection and compile time dependencies. It's more obvious that x86_init.timers.timer_init() is a function pointer than the late_time_init = choose_time_init() obscurity. It's also way simpler to grep for x86_init.timers.timer_init and find all the places which modify that function pointer instead of analyzing weak functions, macros and paravirt indirections. Note. This is not a general paravirt_ops replacement. It just will move setup related hooks which are potentially useful for other platform setup purposes as well out of the paravirt domain. Add the base infrastructure without any functionality. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2009-08-19 19:48:38 +07:00
/**
* struct x86_init_ops - functions for platform specific setup
*
*/
struct x86_init_ops {
struct x86_init_resources resources;
struct x86_init_mpparse mpparse;
struct x86_init_irqs irqs;
struct x86_init_oem oem;
struct x86_init_paging paging;
struct x86_init_timers timers;
struct x86_init_iommu iommu;
struct x86_init_pci pci;
};
/**
* struct x86_cpuinit_ops - platform specific cpu hotplug setups
* @setup_percpu_clockev: set up the per cpu clock event device
x86: Introduce x86_cpuinit.early_percpu_clock_init hook When kvm guest uses kvmclock, it may hang on vcpu hot-plug. This is caused by an overflow in pvclock_get_nsec_offset, u64 delta = tsc - shadow->tsc_timestamp; which in turn is caused by an undefined values from percpu hv_clock that hasn't been initialized yet. Uninitialized clock on being booted cpu is accessed from start_secondary -> smp_callin -> smp_store_cpu_info -> identify_secondary_cpu -> mtrr_ap_init -> mtrr_restore -> stop_machine_from_inactive_cpu -> queue_stop_cpus_work ... -> sched_clock -> kvm_clock_read which is well before x86_cpuinit.setup_percpu_clockev call in start_secondary, where percpu clock is initialized. This patch introduces a hook that allows to setup/initialize per_cpu clock early and avoid overflow due to reading - undefined values - old values if cpu was offlined and then onlined again Another possible early user of this clock source is ftrace that accesses it to get timestamps for ring buffer entries. So if mtrr_ap_init is moved from identify_secondary_cpu to past x86_cpuinit.setup_percpu_clockev in start_secondary, ftrace may cause the same overflow/hang on cpu hot-plug anyway. More complete description of the problem: https://lkml.org/lkml/2012/2/2/101 Credits to Marcelo Tosatti <mtosatti@redhat.com> for hook idea. Acked-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Igor Mammedov <imammedo@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-07 21:52:44 +07:00
* @early_percpu_clock_init: early init of the per cpu clock event device
*/
struct x86_cpuinit_ops {
void (*setup_percpu_clockev)(void);
x86: Introduce x86_cpuinit.early_percpu_clock_init hook When kvm guest uses kvmclock, it may hang on vcpu hot-plug. This is caused by an overflow in pvclock_get_nsec_offset, u64 delta = tsc - shadow->tsc_timestamp; which in turn is caused by an undefined values from percpu hv_clock that hasn't been initialized yet. Uninitialized clock on being booted cpu is accessed from start_secondary -> smp_callin -> smp_store_cpu_info -> identify_secondary_cpu -> mtrr_ap_init -> mtrr_restore -> stop_machine_from_inactive_cpu -> queue_stop_cpus_work ... -> sched_clock -> kvm_clock_read which is well before x86_cpuinit.setup_percpu_clockev call in start_secondary, where percpu clock is initialized. This patch introduces a hook that allows to setup/initialize per_cpu clock early and avoid overflow due to reading - undefined values - old values if cpu was offlined and then onlined again Another possible early user of this clock source is ftrace that accesses it to get timestamps for ring buffer entries. So if mtrr_ap_init is moved from identify_secondary_cpu to past x86_cpuinit.setup_percpu_clockev in start_secondary, ftrace may cause the same overflow/hang on cpu hot-plug anyway. More complete description of the problem: https://lkml.org/lkml/2012/2/2/101 Credits to Marcelo Tosatti <mtosatti@redhat.com> for hook idea. Acked-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Igor Mammedov <imammedo@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
2012-02-07 21:52:44 +07:00
void (*early_percpu_clock_init)(void);
void (*fixup_cpu_id)(struct cpuinfo_x86 *c, int node);
x86: Add x86_init infrastructure The upcoming Moorestown support brings the embedded world to x86. The setup code of x86 has already a couple of hooks which are either x86_quirks or paravirt ops. Some of those setup hooks are pretty convoluted like the timer setup and the tsc calibration code. But there are other places which could do with a cleanup. Instead of having inline functions/macros which are modified at compile time I decided to introduce x86_init ops which are unconditional in the code and make it clear that they can be changed either during compile time or in the early boot process. The function pointers are initialized by default functions which can be noops so that the pointer can be called unconditionally in the most cases. This also allows us to remove 32bit/64bit, paravirt and other #ifdeffery. paravirt guests are just a hardware platform in the setup code, so we should treat them as such and not hide all behind multiple layers of indirection and compile time dependencies. It's more obvious that x86_init.timers.timer_init() is a function pointer than the late_time_init = choose_time_init() obscurity. It's also way simpler to grep for x86_init.timers.timer_init and find all the places which modify that function pointer instead of analyzing weak functions, macros and paravirt indirections. Note. This is not a general paravirt_ops replacement. It just will move setup related hooks which are potentially useful for other platform setup purposes as well out of the paravirt domain. Add the base infrastructure without any functionality. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2009-08-19 19:48:38 +07:00
};
struct timespec;
x86, drivers/pnpbios: Replace paravirt_enabled() check with legacy device check Since we are removing paravirt_enabled() replace it with a logical equivalent. Even though PNPBIOS is x86 specific we add an arch-specific type call, which can be implemented by any architecture to show how other legacy attribute devices can later be also checked for with other ACPI legacy attribute flags. This implicates the first ACPI 5.2.9.3 IA-PC Boot Architecture ACPI_FADT_LEGACY_DEVICES flag device, and shows how to add more. The reason pnpbios gets a defined structure and as such uses a different approach than the RTC legacy quirk is that ACPI has a respective RTC flag, while pnpbios does not. We fold the pnpbios quirk under ACPI_FADT_LEGACY_DEVICES ACPI flag use case, and use a struct of possible devices to enable future extensions of this. As per 0-day, this bumps the vmlinux size using i386-tinyconfig as follows: TOTAL TEXT init.text x86_early_init_platform_quirks() +32 +28 +28 +28 That's 4 byte overhead total, the rest is cleared out on init as its all __init text. v2: split out subarch handlng on switch to make it easier later to add other subarchs. The 'fall-through' switch handling can be confusing and we'll remove it later when we add handling for X86_SUBARCH_CE4100. v3: document vmlinux size impact as per 0-day, and also explain why pnpbios is treated differently than the RTC legacy feature. Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: andrew.cooper3@citrix.com Cc: andriy.shevchenko@linux.intel.com Cc: bigeasy@linutronix.de Cc: boris.ostrovsky@oracle.com Cc: david.vrabel@citrix.com Cc: ffainelli@freebox.fr Cc: george.dunlap@citrix.com Cc: glin@suse.com Cc: jgross@suse.com Cc: jlee@suse.com Cc: josh@joshtriplett.org Cc: julien.grall@linaro.org Cc: konrad.wilk@oracle.com Cc: kozerkov@parallels.com Cc: lenb@kernel.org Cc: lguest@lists.ozlabs.org Cc: linux-acpi@vger.kernel.org Cc: lv.zheng@intel.com Cc: matt@codeblueprint.co.uk Cc: mbizon@freebox.fr Cc: rjw@rjwysocki.net Cc: robert.moore@intel.com Cc: rusty@rustcorp.com.au Cc: tiwai@suse.de Cc: toshi.kani@hp.com Cc: xen-devel@lists.xensource.com Link: http://lkml.kernel.org/r/1460592286-300-12-git-send-email-mcgrof@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-04-14 07:04:41 +07:00
/**
* struct x86_legacy_devices - legacy x86 devices
*
* @pnpbios: this platform can have a PNPBIOS. If this is disabled the platform
* is known to never have a PNPBIOS.
*
* These are devices known to require LPC or ISA bus. The definition of legacy
* devices adheres to the ACPI 5.2.9.3 IA-PC Boot Architecture flag
* ACPI_FADT_LEGACY_DEVICES. These devices consist of user visible devices on
* the LPC or ISA bus. User visible devices are devices that have end-user
* accessible connectors (for example, LPT parallel port). Legacy devices on
* the LPC bus consist for example of serial and parallel ports, PS/2 keyboard
* / mouse, and the floppy disk controller. A system that lacks all known
* legacy devices can assume all devices can be detected exclusively via
* standard device enumeration mechanisms including the ACPI namespace.
*
* A system which has does not have ACPI_FADT_LEGACY_DEVICES enabled must not
* have any of the legacy devices enumerated below present.
*/
struct x86_legacy_devices {
int pnpbios;
};
x86/rtc: Replace paravirt rtc check with platform legacy quirk We have 4 types of x86 platforms that disable RTC: * Intel MID * Lguest - uses paravirt * Xen dom-U - uses paravirt * x86 on legacy systems annotated with an ACPI legacy flag We can consolidate all of these into a platform specific legacy quirk set early in boot through i386_start_kernel() and through x86_64_start_reservations(). This deals with the RTC quirks which we can rely on through the hardware subarch, the ACPI check can be dealt with separately. For Xen things are bit more complex given that the @X86_SUBARCH_XEN x86_hardware_subarch is shared on for Xen which uses the PV path for both domU and dom0. Since the semantics for differentiating between the two are Xen specific we provide a platform helper to help override default legacy features -- x86_platform.set_legacy_features(). Use of this helper is highly discouraged, its only purpose should be to account for the lack of semantics available within your given x86_hardware_subarch. As per 0-day, this bumps the vmlinux size using i386-tinyconfig as follows: TOTAL TEXT init.text x86_early_init_platform_quirks() +70 +62 +62 +43 Only 8 bytes overhead total, as the main increase in size is all removed via __init. Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Reviewed-by: Juergen Gross <jgross@suse.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: andrew.cooper3@citrix.com Cc: andriy.shevchenko@linux.intel.com Cc: bigeasy@linutronix.de Cc: boris.ostrovsky@oracle.com Cc: david.vrabel@citrix.com Cc: ffainelli@freebox.fr Cc: george.dunlap@citrix.com Cc: glin@suse.com Cc: jlee@suse.com Cc: josh@joshtriplett.org Cc: julien.grall@linaro.org Cc: konrad.wilk@oracle.com Cc: kozerkov@parallels.com Cc: lenb@kernel.org Cc: lguest@lists.ozlabs.org Cc: linux-acpi@vger.kernel.org Cc: lv.zheng@intel.com Cc: matt@codeblueprint.co.uk Cc: mbizon@freebox.fr Cc: rjw@rjwysocki.net Cc: robert.moore@intel.com Cc: rusty@rustcorp.com.au Cc: tiwai@suse.de Cc: toshi.kani@hp.com Cc: xen-devel@lists.xensource.com Link: http://lkml.kernel.org/r/1460592286-300-5-git-send-email-mcgrof@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-04-14 07:04:34 +07:00
/**
* struct x86_legacy_features - legacy x86 features
*
* @rtc: this device has a CMOS real-time clock present
* @reserve_bios_regions: boot code will search for the EBDA address and the
* start of the 640k - 1M BIOS region. If false, the platform must
* ensure that its memory map correctly reserves sub-1MB regions as needed.
x86, drivers/pnpbios: Replace paravirt_enabled() check with legacy device check Since we are removing paravirt_enabled() replace it with a logical equivalent. Even though PNPBIOS is x86 specific we add an arch-specific type call, which can be implemented by any architecture to show how other legacy attribute devices can later be also checked for with other ACPI legacy attribute flags. This implicates the first ACPI 5.2.9.3 IA-PC Boot Architecture ACPI_FADT_LEGACY_DEVICES flag device, and shows how to add more. The reason pnpbios gets a defined structure and as such uses a different approach than the RTC legacy quirk is that ACPI has a respective RTC flag, while pnpbios does not. We fold the pnpbios quirk under ACPI_FADT_LEGACY_DEVICES ACPI flag use case, and use a struct of possible devices to enable future extensions of this. As per 0-day, this bumps the vmlinux size using i386-tinyconfig as follows: TOTAL TEXT init.text x86_early_init_platform_quirks() +32 +28 +28 +28 That's 4 byte overhead total, the rest is cleared out on init as its all __init text. v2: split out subarch handlng on switch to make it easier later to add other subarchs. The 'fall-through' switch handling can be confusing and we'll remove it later when we add handling for X86_SUBARCH_CE4100. v3: document vmlinux size impact as per 0-day, and also explain why pnpbios is treated differently than the RTC legacy feature. Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: andrew.cooper3@citrix.com Cc: andriy.shevchenko@linux.intel.com Cc: bigeasy@linutronix.de Cc: boris.ostrovsky@oracle.com Cc: david.vrabel@citrix.com Cc: ffainelli@freebox.fr Cc: george.dunlap@citrix.com Cc: glin@suse.com Cc: jgross@suse.com Cc: jlee@suse.com Cc: josh@joshtriplett.org Cc: julien.grall@linaro.org Cc: konrad.wilk@oracle.com Cc: kozerkov@parallels.com Cc: lenb@kernel.org Cc: lguest@lists.ozlabs.org Cc: linux-acpi@vger.kernel.org Cc: lv.zheng@intel.com Cc: matt@codeblueprint.co.uk Cc: mbizon@freebox.fr Cc: rjw@rjwysocki.net Cc: robert.moore@intel.com Cc: rusty@rustcorp.com.au Cc: tiwai@suse.de Cc: toshi.kani@hp.com Cc: xen-devel@lists.xensource.com Link: http://lkml.kernel.org/r/1460592286-300-12-git-send-email-mcgrof@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-04-14 07:04:41 +07:00
* @devices: legacy x86 devices, refer to struct x86_legacy_devices
* documentation for further details.
x86/rtc: Replace paravirt rtc check with platform legacy quirk We have 4 types of x86 platforms that disable RTC: * Intel MID * Lguest - uses paravirt * Xen dom-U - uses paravirt * x86 on legacy systems annotated with an ACPI legacy flag We can consolidate all of these into a platform specific legacy quirk set early in boot through i386_start_kernel() and through x86_64_start_reservations(). This deals with the RTC quirks which we can rely on through the hardware subarch, the ACPI check can be dealt with separately. For Xen things are bit more complex given that the @X86_SUBARCH_XEN x86_hardware_subarch is shared on for Xen which uses the PV path for both domU and dom0. Since the semantics for differentiating between the two are Xen specific we provide a platform helper to help override default legacy features -- x86_platform.set_legacy_features(). Use of this helper is highly discouraged, its only purpose should be to account for the lack of semantics available within your given x86_hardware_subarch. As per 0-day, this bumps the vmlinux size using i386-tinyconfig as follows: TOTAL TEXT init.text x86_early_init_platform_quirks() +70 +62 +62 +43 Only 8 bytes overhead total, as the main increase in size is all removed via __init. Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Reviewed-by: Juergen Gross <jgross@suse.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: andrew.cooper3@citrix.com Cc: andriy.shevchenko@linux.intel.com Cc: bigeasy@linutronix.de Cc: boris.ostrovsky@oracle.com Cc: david.vrabel@citrix.com Cc: ffainelli@freebox.fr Cc: george.dunlap@citrix.com Cc: glin@suse.com Cc: jlee@suse.com Cc: josh@joshtriplett.org Cc: julien.grall@linaro.org Cc: konrad.wilk@oracle.com Cc: kozerkov@parallels.com Cc: lenb@kernel.org Cc: lguest@lists.ozlabs.org Cc: linux-acpi@vger.kernel.org Cc: lv.zheng@intel.com Cc: matt@codeblueprint.co.uk Cc: mbizon@freebox.fr Cc: rjw@rjwysocki.net Cc: robert.moore@intel.com Cc: rusty@rustcorp.com.au Cc: tiwai@suse.de Cc: toshi.kani@hp.com Cc: xen-devel@lists.xensource.com Link: http://lkml.kernel.org/r/1460592286-300-5-git-send-email-mcgrof@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-04-14 07:04:34 +07:00
*/
struct x86_legacy_features {
int rtc;
x86/boot: Reorganize and clean up the BIOS area reservation code So the reserve_ebda_region() code has accumulated a number of problems over the years that make it really difficult to read and understand: - The calculation of 'lowmem' and 'ebda_addr' is an unnecessarily interleaved mess of first lowmem, then ebda_addr, then lowmem tweaks... - 'lowmem' here means 'super low mem' - i.e. 16-bit addressable memory. In other parts of the x86 code 'lowmem' means 32-bit addressable memory... This makes it super confusing to read. - It does not help at all that we have various memory range markers, half of which are 'start of range', half of which are 'end of range' - but this crucial property is not obvious in the naming at all ... gave me a headache trying to understand all this. - Also, the 'ebda_addr' name sucks: it highlights that it's an address (which is obvious, all values here are addresses!), while it does not highlight that it's the _start_ of the EBDA region ... - 'BIOS_LOWMEM_KILOBYTES' says a lot of things, except that this is the only value that is a pointer to a value, not a memory range address! - The function name itself is a misnomer: it says 'reserve_ebda_region()' while its main purpose is to reserve all the firmware ROM typically between 640K and 1MB, while the 'EBDA' part is only a small part of that ... - Likewise, the paravirt quirk flag name 'ebda_search' is misleading as well: this too should be about whether to reserve firmware areas in the paravirt case. - In fact thinking about this as 'end of RAM' is confusing: what this function *really* wants to reserve is firmware data and code areas! Once the thinking is inverted from a mixed 'ram' and 'reserved firmware area' notion to a pure 'reserved area' notion everything becomes a lot clearer. To improve all this rewrite the whole code (without changing the logic): - Firstly invert the naming from 'lowmem end' to 'BIOS reserved area start' and propagate this concept through all the variable names and constants. BIOS_RAM_SIZE_KB_PTR // was: BIOS_LOWMEM_KILOBYTES BIOS_START_MIN // was: INSANE_CUTOFF ebda_start // was: ebda_addr bios_start // was: lowmem BIOS_START_MAX // was: LOWMEM_CAP - Then clean up the name of the function itself by renaming it to reserve_bios_regions() and renaming the ::ebda_search paravirt flag to ::reserve_bios_regions. - Fix up all the comments (fix typos), harmonize and simplify their formulation and remove comments that become unnecessary due to the much better naming all around. Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-07-21 14:53:52 +07:00
int reserve_bios_regions;
x86, drivers/pnpbios: Replace paravirt_enabled() check with legacy device check Since we are removing paravirt_enabled() replace it with a logical equivalent. Even though PNPBIOS is x86 specific we add an arch-specific type call, which can be implemented by any architecture to show how other legacy attribute devices can later be also checked for with other ACPI legacy attribute flags. This implicates the first ACPI 5.2.9.3 IA-PC Boot Architecture ACPI_FADT_LEGACY_DEVICES flag device, and shows how to add more. The reason pnpbios gets a defined structure and as such uses a different approach than the RTC legacy quirk is that ACPI has a respective RTC flag, while pnpbios does not. We fold the pnpbios quirk under ACPI_FADT_LEGACY_DEVICES ACPI flag use case, and use a struct of possible devices to enable future extensions of this. As per 0-day, this bumps the vmlinux size using i386-tinyconfig as follows: TOTAL TEXT init.text x86_early_init_platform_quirks() +32 +28 +28 +28 That's 4 byte overhead total, the rest is cleared out on init as its all __init text. v2: split out subarch handlng on switch to make it easier later to add other subarchs. The 'fall-through' switch handling can be confusing and we'll remove it later when we add handling for X86_SUBARCH_CE4100. v3: document vmlinux size impact as per 0-day, and also explain why pnpbios is treated differently than the RTC legacy feature. Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: andrew.cooper3@citrix.com Cc: andriy.shevchenko@linux.intel.com Cc: bigeasy@linutronix.de Cc: boris.ostrovsky@oracle.com Cc: david.vrabel@citrix.com Cc: ffainelli@freebox.fr Cc: george.dunlap@citrix.com Cc: glin@suse.com Cc: jgross@suse.com Cc: jlee@suse.com Cc: josh@joshtriplett.org Cc: julien.grall@linaro.org Cc: konrad.wilk@oracle.com Cc: kozerkov@parallels.com Cc: lenb@kernel.org Cc: lguest@lists.ozlabs.org Cc: linux-acpi@vger.kernel.org Cc: lv.zheng@intel.com Cc: matt@codeblueprint.co.uk Cc: mbizon@freebox.fr Cc: rjw@rjwysocki.net Cc: robert.moore@intel.com Cc: rusty@rustcorp.com.au Cc: tiwai@suse.de Cc: toshi.kani@hp.com Cc: xen-devel@lists.xensource.com Link: http://lkml.kernel.org/r/1460592286-300-12-git-send-email-mcgrof@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-04-14 07:04:41 +07:00
struct x86_legacy_devices devices;
x86/rtc: Replace paravirt rtc check with platform legacy quirk We have 4 types of x86 platforms that disable RTC: * Intel MID * Lguest - uses paravirt * Xen dom-U - uses paravirt * x86 on legacy systems annotated with an ACPI legacy flag We can consolidate all of these into a platform specific legacy quirk set early in boot through i386_start_kernel() and through x86_64_start_reservations(). This deals with the RTC quirks which we can rely on through the hardware subarch, the ACPI check can be dealt with separately. For Xen things are bit more complex given that the @X86_SUBARCH_XEN x86_hardware_subarch is shared on for Xen which uses the PV path for both domU and dom0. Since the semantics for differentiating between the two are Xen specific we provide a platform helper to help override default legacy features -- x86_platform.set_legacy_features(). Use of this helper is highly discouraged, its only purpose should be to account for the lack of semantics available within your given x86_hardware_subarch. As per 0-day, this bumps the vmlinux size using i386-tinyconfig as follows: TOTAL TEXT init.text x86_early_init_platform_quirks() +70 +62 +62 +43 Only 8 bytes overhead total, as the main increase in size is all removed via __init. Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Reviewed-by: Juergen Gross <jgross@suse.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: andrew.cooper3@citrix.com Cc: andriy.shevchenko@linux.intel.com Cc: bigeasy@linutronix.de Cc: boris.ostrovsky@oracle.com Cc: david.vrabel@citrix.com Cc: ffainelli@freebox.fr Cc: george.dunlap@citrix.com Cc: glin@suse.com Cc: jlee@suse.com Cc: josh@joshtriplett.org Cc: julien.grall@linaro.org Cc: konrad.wilk@oracle.com Cc: kozerkov@parallels.com Cc: lenb@kernel.org Cc: lguest@lists.ozlabs.org Cc: linux-acpi@vger.kernel.org Cc: lv.zheng@intel.com Cc: matt@codeblueprint.co.uk Cc: mbizon@freebox.fr Cc: rjw@rjwysocki.net Cc: robert.moore@intel.com Cc: rusty@rustcorp.com.au Cc: tiwai@suse.de Cc: toshi.kani@hp.com Cc: xen-devel@lists.xensource.com Link: http://lkml.kernel.org/r/1460592286-300-5-git-send-email-mcgrof@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-04-14 07:04:34 +07:00
};
/**
* struct x86_platform_ops - platform specific runtime functions
* @calibrate_cpu: calibrate CPU
* @calibrate_tsc: calibrate TSC, if different from CPU
* @get_wallclock: get time from HW clock like RTC etc.
* @set_wallclock: set time back to HW clock
* @is_untracked_pat_range exclude from PAT logic
* @nmi_init enable NMI on cpus
* @i8042_detect pre-detect if i8042 controller exists
* @save_sched_clock_state: save state for sched_clock() on suspend
* @restore_sched_clock_state: restore state for sched_clock() on resume
* @apic_post_init: adjust apic if neeeded
x86/rtc: Replace paravirt rtc check with platform legacy quirk We have 4 types of x86 platforms that disable RTC: * Intel MID * Lguest - uses paravirt * Xen dom-U - uses paravirt * x86 on legacy systems annotated with an ACPI legacy flag We can consolidate all of these into a platform specific legacy quirk set early in boot through i386_start_kernel() and through x86_64_start_reservations(). This deals with the RTC quirks which we can rely on through the hardware subarch, the ACPI check can be dealt with separately. For Xen things are bit more complex given that the @X86_SUBARCH_XEN x86_hardware_subarch is shared on for Xen which uses the PV path for both domU and dom0. Since the semantics for differentiating between the two are Xen specific we provide a platform helper to help override default legacy features -- x86_platform.set_legacy_features(). Use of this helper is highly discouraged, its only purpose should be to account for the lack of semantics available within your given x86_hardware_subarch. As per 0-day, this bumps the vmlinux size using i386-tinyconfig as follows: TOTAL TEXT init.text x86_early_init_platform_quirks() +70 +62 +62 +43 Only 8 bytes overhead total, as the main increase in size is all removed via __init. Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Reviewed-by: Juergen Gross <jgross@suse.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: andrew.cooper3@citrix.com Cc: andriy.shevchenko@linux.intel.com Cc: bigeasy@linutronix.de Cc: boris.ostrovsky@oracle.com Cc: david.vrabel@citrix.com Cc: ffainelli@freebox.fr Cc: george.dunlap@citrix.com Cc: glin@suse.com Cc: jlee@suse.com Cc: josh@joshtriplett.org Cc: julien.grall@linaro.org Cc: konrad.wilk@oracle.com Cc: kozerkov@parallels.com Cc: lenb@kernel.org Cc: lguest@lists.ozlabs.org Cc: linux-acpi@vger.kernel.org Cc: lv.zheng@intel.com Cc: matt@codeblueprint.co.uk Cc: mbizon@freebox.fr Cc: rjw@rjwysocki.net Cc: robert.moore@intel.com Cc: rusty@rustcorp.com.au Cc: tiwai@suse.de Cc: toshi.kani@hp.com Cc: xen-devel@lists.xensource.com Link: http://lkml.kernel.org/r/1460592286-300-5-git-send-email-mcgrof@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-04-14 07:04:34 +07:00
* @legacy: legacy features
* @set_legacy_features: override legacy features. Use of this callback
* is highly discouraged. You should only need
* this if your hardware platform requires further
* custom fine tuning far beyong what may be
* possible in x86_early_init_platform_quirks() by
* only using the current x86_hardware_subarch
* semantics.
*/
struct x86_platform_ops {
unsigned long (*calibrate_cpu)(void);
unsigned long (*calibrate_tsc)(void);
void (*get_wallclock)(struct timespec *ts);
int (*set_wallclock)(const struct timespec *ts);
void (*iommu_shutdown)(void);
bool (*is_untracked_pat_range)(u64 start, u64 end);
void (*nmi_init)(void);
unsigned char (*get_nmi_reason)(void);
int (*i8042_detect)(void);
void (*save_sched_clock_state)(void);
void (*restore_sched_clock_state)(void);
void (*apic_post_init)(void);
x86/rtc: Replace paravirt rtc check with platform legacy quirk We have 4 types of x86 platforms that disable RTC: * Intel MID * Lguest - uses paravirt * Xen dom-U - uses paravirt * x86 on legacy systems annotated with an ACPI legacy flag We can consolidate all of these into a platform specific legacy quirk set early in boot through i386_start_kernel() and through x86_64_start_reservations(). This deals with the RTC quirks which we can rely on through the hardware subarch, the ACPI check can be dealt with separately. For Xen things are bit more complex given that the @X86_SUBARCH_XEN x86_hardware_subarch is shared on for Xen which uses the PV path for both domU and dom0. Since the semantics for differentiating between the two are Xen specific we provide a platform helper to help override default legacy features -- x86_platform.set_legacy_features(). Use of this helper is highly discouraged, its only purpose should be to account for the lack of semantics available within your given x86_hardware_subarch. As per 0-day, this bumps the vmlinux size using i386-tinyconfig as follows: TOTAL TEXT init.text x86_early_init_platform_quirks() +70 +62 +62 +43 Only 8 bytes overhead total, as the main increase in size is all removed via __init. Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Reviewed-by: Juergen Gross <jgross@suse.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: andrew.cooper3@citrix.com Cc: andriy.shevchenko@linux.intel.com Cc: bigeasy@linutronix.de Cc: boris.ostrovsky@oracle.com Cc: david.vrabel@citrix.com Cc: ffainelli@freebox.fr Cc: george.dunlap@citrix.com Cc: glin@suse.com Cc: jlee@suse.com Cc: josh@joshtriplett.org Cc: julien.grall@linaro.org Cc: konrad.wilk@oracle.com Cc: kozerkov@parallels.com Cc: lenb@kernel.org Cc: lguest@lists.ozlabs.org Cc: linux-acpi@vger.kernel.org Cc: lv.zheng@intel.com Cc: matt@codeblueprint.co.uk Cc: mbizon@freebox.fr Cc: rjw@rjwysocki.net Cc: robert.moore@intel.com Cc: rusty@rustcorp.com.au Cc: tiwai@suse.de Cc: toshi.kani@hp.com Cc: xen-devel@lists.xensource.com Link: http://lkml.kernel.org/r/1460592286-300-5-git-send-email-mcgrof@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-04-14 07:04:34 +07:00
struct x86_legacy_features legacy;
void (*set_legacy_features)(void);
};
struct pci_dev;
struct x86_msi_ops {
int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type);
void (*teardown_msi_irq)(unsigned int irq);
void (*teardown_msi_irqs)(struct pci_dev *dev);
void (*restore_msi_irqs)(struct pci_dev *dev);
};
struct x86_io_apic_ops {
unsigned int (*read) (unsigned int apic, unsigned int reg);
void (*disable)(void);
};
x86: Add x86_init infrastructure The upcoming Moorestown support brings the embedded world to x86. The setup code of x86 has already a couple of hooks which are either x86_quirks or paravirt ops. Some of those setup hooks are pretty convoluted like the timer setup and the tsc calibration code. But there are other places which could do with a cleanup. Instead of having inline functions/macros which are modified at compile time I decided to introduce x86_init ops which are unconditional in the code and make it clear that they can be changed either during compile time or in the early boot process. The function pointers are initialized by default functions which can be noops so that the pointer can be called unconditionally in the most cases. This also allows us to remove 32bit/64bit, paravirt and other #ifdeffery. paravirt guests are just a hardware platform in the setup code, so we should treat them as such and not hide all behind multiple layers of indirection and compile time dependencies. It's more obvious that x86_init.timers.timer_init() is a function pointer than the late_time_init = choose_time_init() obscurity. It's also way simpler to grep for x86_init.timers.timer_init and find all the places which modify that function pointer instead of analyzing weak functions, macros and paravirt indirections. Note. This is not a general paravirt_ops replacement. It just will move setup related hooks which are potentially useful for other platform setup purposes as well out of the paravirt domain. Add the base infrastructure without any functionality. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2009-08-19 19:48:38 +07:00
extern struct x86_init_ops x86_init;
extern struct x86_cpuinit_ops x86_cpuinit;
extern struct x86_platform_ops x86_platform;
extern struct x86_msi_ops x86_msi;
extern struct x86_io_apic_ops x86_io_apic_ops;
x86/rtc: Replace paravirt rtc check with platform legacy quirk We have 4 types of x86 platforms that disable RTC: * Intel MID * Lguest - uses paravirt * Xen dom-U - uses paravirt * x86 on legacy systems annotated with an ACPI legacy flag We can consolidate all of these into a platform specific legacy quirk set early in boot through i386_start_kernel() and through x86_64_start_reservations(). This deals with the RTC quirks which we can rely on through the hardware subarch, the ACPI check can be dealt with separately. For Xen things are bit more complex given that the @X86_SUBARCH_XEN x86_hardware_subarch is shared on for Xen which uses the PV path for both domU and dom0. Since the semantics for differentiating between the two are Xen specific we provide a platform helper to help override default legacy features -- x86_platform.set_legacy_features(). Use of this helper is highly discouraged, its only purpose should be to account for the lack of semantics available within your given x86_hardware_subarch. As per 0-day, this bumps the vmlinux size using i386-tinyconfig as follows: TOTAL TEXT init.text x86_early_init_platform_quirks() +70 +62 +62 +43 Only 8 bytes overhead total, as the main increase in size is all removed via __init. Suggested-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org> Reviewed-by: Juergen Gross <jgross@suse.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: andrew.cooper3@citrix.com Cc: andriy.shevchenko@linux.intel.com Cc: bigeasy@linutronix.de Cc: boris.ostrovsky@oracle.com Cc: david.vrabel@citrix.com Cc: ffainelli@freebox.fr Cc: george.dunlap@citrix.com Cc: glin@suse.com Cc: jlee@suse.com Cc: josh@joshtriplett.org Cc: julien.grall@linaro.org Cc: konrad.wilk@oracle.com Cc: kozerkov@parallels.com Cc: lenb@kernel.org Cc: lguest@lists.ozlabs.org Cc: linux-acpi@vger.kernel.org Cc: lv.zheng@intel.com Cc: matt@codeblueprint.co.uk Cc: mbizon@freebox.fr Cc: rjw@rjwysocki.net Cc: robert.moore@intel.com Cc: rusty@rustcorp.com.au Cc: tiwai@suse.de Cc: toshi.kani@hp.com Cc: xen-devel@lists.xensource.com Link: http://lkml.kernel.org/r/1460592286-300-5-git-send-email-mcgrof@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-04-14 07:04:34 +07:00
extern void x86_early_init_platform_quirks(void);
x86: Add x86_init infrastructure The upcoming Moorestown support brings the embedded world to x86. The setup code of x86 has already a couple of hooks which are either x86_quirks or paravirt ops. Some of those setup hooks are pretty convoluted like the timer setup and the tsc calibration code. But there are other places which could do with a cleanup. Instead of having inline functions/macros which are modified at compile time I decided to introduce x86_init ops which are unconditional in the code and make it clear that they can be changed either during compile time or in the early boot process. The function pointers are initialized by default functions which can be noops so that the pointer can be called unconditionally in the most cases. This also allows us to remove 32bit/64bit, paravirt and other #ifdeffery. paravirt guests are just a hardware platform in the setup code, so we should treat them as such and not hide all behind multiple layers of indirection and compile time dependencies. It's more obvious that x86_init.timers.timer_init() is a function pointer than the late_time_init = choose_time_init() obscurity. It's also way simpler to grep for x86_init.timers.timer_init and find all the places which modify that function pointer instead of analyzing weak functions, macros and paravirt indirections. Note. This is not a general paravirt_ops replacement. It just will move setup related hooks which are potentially useful for other platform setup purposes as well out of the paravirt domain. Add the base infrastructure without any functionality. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2009-08-19 19:48:38 +07:00
extern void x86_init_noop(void);
extern void x86_init_uint_noop(unsigned int unused);
x86: Add x86_init infrastructure The upcoming Moorestown support brings the embedded world to x86. The setup code of x86 has already a couple of hooks which are either x86_quirks or paravirt ops. Some of those setup hooks are pretty convoluted like the timer setup and the tsc calibration code. But there are other places which could do with a cleanup. Instead of having inline functions/macros which are modified at compile time I decided to introduce x86_init ops which are unconditional in the code and make it clear that they can be changed either during compile time or in the early boot process. The function pointers are initialized by default functions which can be noops so that the pointer can be called unconditionally in the most cases. This also allows us to remove 32bit/64bit, paravirt and other #ifdeffery. paravirt guests are just a hardware platform in the setup code, so we should treat them as such and not hide all behind multiple layers of indirection and compile time dependencies. It's more obvious that x86_init.timers.timer_init() is a function pointer than the late_time_init = choose_time_init() obscurity. It's also way simpler to grep for x86_init.timers.timer_init and find all the places which modify that function pointer instead of analyzing weak functions, macros and paravirt indirections. Note. This is not a general paravirt_ops replacement. It just will move setup related hooks which are potentially useful for other platform setup purposes as well out of the paravirt domain. Add the base infrastructure without any functionality. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2009-08-19 19:48:38 +07:00
#endif