linux_dsm_epyc7002/arch/x86/kernel/Makefile

134 lines
4.2 KiB
Makefile
Raw Normal View History

#
# Makefile for the linux kernel.
#
extra-y := head_$(BITS).o head$(BITS).o head.o init_task.o vmlinux.lds
CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
ifdef CONFIG_FUNCTION_TRACER
# Do not profile debug and lowlevel utilities
CFLAGS_REMOVE_tsc.o = -pg
CFLAGS_REMOVE_rtc.o = -pg
CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
CFLAGS_REMOVE_ftrace.o = -pg
CFLAGS_REMOVE_early_printk.o = -pg
endif
#
# vsyscalls (which work on the user stack) should have
# no stack-protector checks:
#
nostackp := $(call cc-option, -fno-stack-protector)
CFLAGS_vsyscall_64.o := $(PROFILING) -g0 $(nostackp)
CFLAGS_hpet.o := $(nostackp)
CFLAGS_tsc.o := $(nostackp)
CFLAGS_paravirt.o := $(nostackp)
GCOV_PROFILE_vsyscall_64.o := n
GCOV_PROFILE_hpet.o := n
GCOV_PROFILE_tsc.o := n
GCOV_PROFILE_paravirt.o := n
obj-y := process_$(BITS).o signal.o entry_$(BITS).o
obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
obj-y += time.o ioport.o ldt.o dumpstack.o
x86: Add x86_init infrastructure The upcoming Moorestown support brings the embedded world to x86. The setup code of x86 has already a couple of hooks which are either x86_quirks or paravirt ops. Some of those setup hooks are pretty convoluted like the timer setup and the tsc calibration code. But there are other places which could do with a cleanup. Instead of having inline functions/macros which are modified at compile time I decided to introduce x86_init ops which are unconditional in the code and make it clear that they can be changed either during compile time or in the early boot process. The function pointers are initialized by default functions which can be noops so that the pointer can be called unconditionally in the most cases. This also allows us to remove 32bit/64bit, paravirt and other #ifdeffery. paravirt guests are just a hardware platform in the setup code, so we should treat them as such and not hide all behind multiple layers of indirection and compile time dependencies. It's more obvious that x86_init.timers.timer_init() is a function pointer than the late_time_init = choose_time_init() obscurity. It's also way simpler to grep for x86_init.timers.timer_init and find all the places which modify that function pointer instead of analyzing weak functions, macros and paravirt indirections. Note. This is not a general paravirt_ops replacement. It just will move setup related hooks which are potentially useful for other platform setup purposes as well out of the paravirt domain. Add the base infrastructure without any functionality. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2009-08-19 19:48:38 +07:00
obj-y += setup.o x86_init.o i8259.o irqinit.o
obj-$(CONFIG_X86_VISWS) += visws_quirks.o
obj-$(CONFIG_X86_32) += probe_roms_32.o
obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o
obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o
obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o
obj-y += bootflag.o e820.o
obj-y += pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o
obj-y += tsc.o io_delay.o rtc.o
obj-$(CONFIG_X86_TRAMPOLINE) += trampoline.o
obj-y += process.o
obj-y += i387.o xsave.o
obj-y += ptrace.o
obj-$(CONFIG_X86_DS) += ds.o
obj-$(CONFIG_X86_DS_SELFTEST) += ds_selftest.o
obj-$(CONFIG_X86_32) += tls.o
obj-$(CONFIG_IA32_EMULATION) += tls.o
obj-y += step.o
x86, intel_txt: Intel TXT boot support This patch adds kernel configuration and boot support for Intel Trusted Execution Technology (Intel TXT). Intel's technology for safer computing, Intel Trusted Execution Technology (Intel TXT), defines platform-level enhancements that provide the building blocks for creating trusted platforms. Intel TXT was formerly known by the code name LaGrande Technology (LT). Intel TXT in Brief: o Provides dynamic root of trust for measurement (DRTM) o Data protection in case of improper shutdown o Measurement and verification of launched environment Intel TXT is part of the vPro(TM) brand and is also available some non-vPro systems. It is currently available on desktop systems based on the Q35, X38, Q45, and Q43 Express chipsets (e.g. Dell Optiplex 755, HP dc7800, etc.) and mobile systems based on the GM45, PM45, and GS45 Express chipsets. For more information, see http://www.intel.com/technology/security/. This site also has a link to the Intel TXT MLE Developers Manual, which has been updated for the new released platforms. A much more complete description of how these patches support TXT, how to configure a system for it, etc. is in the Documentation/intel_txt.txt file in this patch. This patch provides the TXT support routines for complete functionality, documentation for TXT support and for the changes to the boot_params structure, and boot detection of a TXT launch. Attempts to shutdown (reboot, Sx) the system will result in platform resets; subsequent patches will support these shutdown modes properly. Documentation/intel_txt.txt | 210 +++++++++++++++++++++ Documentation/x86/zero-page.txt | 1 arch/x86/include/asm/bootparam.h | 3 arch/x86/include/asm/fixmap.h | 3 arch/x86/include/asm/tboot.h | 197 ++++++++++++++++++++ arch/x86/kernel/Makefile | 1 arch/x86/kernel/setup.c | 4 arch/x86/kernel/tboot.c | 379 +++++++++++++++++++++++++++++++++++++++ security/Kconfig | 30 +++ 9 files changed, 827 insertions(+), 1 deletion(-) Signed-off-by: Joseph Cihula <joseph.cihula@intel.com> Signed-off-by: Shane Wang <shane.wang@intel.com> Signed-off-by: Gang Wei <gang.wei@intel.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-07-01 09:30:59 +07:00
obj-$(CONFIG_INTEL_TXT) += tboot.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
obj-y += cpu/
obj-y += acpi/
obj-$(CONFIG_SFI) += sfi.o
obj-y += reboot.o
obj-$(CONFIG_MCA) += mca_32.o
obj-$(CONFIG_X86_MSR) += msr.o
obj-$(CONFIG_X86_CPUID) += cpuid.o
obj-$(CONFIG_PCI) += early-quirks.o
apm-y := apm_32.o
obj-$(CONFIG_APM) += apm.o
obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_SMP) += smpboot.o tsc_sync.o
obj-$(CONFIG_SMP) += setup_percpu.o
obj-$(CONFIG_X86_64_SMP) += tsc_sync.o
obj-$(CONFIG_X86_TRAMPOLINE) += trampoline_$(BITS).o
obj-$(CONFIG_X86_MPPARSE) += mpparse.o
obj-y += apic/
obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o
ftrace: dynamic enabling/disabling of function calls This patch adds a feature to dynamically replace the ftrace code with the jmps to allow a kernel with ftrace configured to run as fast as it can without it configured. The way this works, is on bootup (if ftrace is enabled), a ftrace function is registered to record the instruction pointer of all places that call the function. Later, if there's still any code to patch, a kthread is awoken (rate limited to at most once a second) that performs a stop_machine, and replaces all the code that was called with a jmp over the call to ftrace. It only replaces what was found the previous time. Typically the system reaches equilibrium quickly after bootup and there's no code patching needed at all. e.g. call ftrace /* 5 bytes */ is replaced with jmp 3f /* jmp is 2 bytes and we jump 3 forward */ 3: When we want to enable ftrace for function tracing, the IP recording is removed, and stop_machine is called again to replace all the locations of that were recorded back to the call of ftrace. When it is disabled, we replace the code back to the jmp. Allocation is done by the kthread. If the ftrace recording function is called, and we don't have any record slots available, then we simply skip that call. Once a second a new page (if needed) is allocated for recording new ftrace function calls. A large batch is allocated at boot up to get most of the calls there. Because we do this via stop_machine, we don't have to worry about another CPU executing a ftrace call as we modify it. But we do need to worry about NMI's so all functions that might be called via nmi must be annotated with notrace_nmi. When this code is configured in, the NMI code will not call notrace. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-13 02:20:42 +07:00
obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o
obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o
obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o
obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o
obj-$(CONFIG_KPROBES) += kprobes.o
obj-$(CONFIG_MODULES) += module.o
obj-$(CONFIG_EFI) += efi.o efi_$(BITS).o efi_stub_$(BITS).o
obj-$(CONFIG_DOUBLEFAULT) += doublefault_32.o
obj-$(CONFIG_KGDB) += kgdb.o
obj-$(CONFIG_VM86) += vm86_32.o
obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
obj-$(CONFIG_HPET_TIMER) += hpet.o
obj-$(CONFIG_APB_TIMER) += apb_timer.o
obj-$(CONFIG_K8_NB) += k8.o
obj-$(CONFIG_DEBUG_RODATA_TEST) += test_rodata.o
obj-$(CONFIG_DEBUG_NX_TEST) += test_nx.o
obj-$(CONFIG_VMI) += vmi_32.o vmiclock_32.o
obj-$(CONFIG_KVM_GUEST) += kvm.o
obj-$(CONFIG_KVM_CLOCK) += kvmclock.o
x86: Fix performance regression caused by paravirt_ops on native kernels Xiaohui Xin and some other folks at Intel have been looking into what's behind the performance hit of paravirt_ops when running native. It appears that the hit is entirely due to the paravirtualized spinlocks introduced by: | commit 8efcbab674de2bee45a2e4cdf97de16b8e609ac8 | Date: Mon Jul 7 12:07:51 2008 -0700 | | paravirt: introduce a "lock-byte" spinlock implementation The extra call/return in the spinlock path is somehow causing an increase in the cycles/instruction of somewhere around 2-7% (seems to vary quite a lot from test to test). The working theory is that the CPU's pipeline is getting upset about the call->call->locked-op->return->return, and seems to be failing to speculate (though I haven't seen anything definitive about the precise reasons). This doesn't entirely make sense, because the performance hit is also visible on unlock and other operations which don't involve locked instructions. But spinlock operations clearly swamp all the other pvops operations, even though I can't imagine that they're nearly as common (there's only a .05% increase in instructions executed). If I disable just the pv-spinlock calls, my tests show that pvops is identical to non-pvops performance on native (my measurements show that it is actually about .1% faster, but Xiaohui shows a .05% slowdown). Summary of results, averaging 10 runs of the "mmperf" test, using a no-pvops build as baseline: nopv Pv-nospin Pv-spin CPU cycles 100.00% 99.89% 102.18% instructions 100.00% 100.10% 100.15% CPI 100.00% 99.79% 102.03% cache ref 100.00% 100.84% 100.28% cache miss 100.00% 90.47% 88.56% cache miss rate 100.00% 89.72% 88.31% branches 100.00% 99.93% 100.04% branch miss 100.00% 103.66% 107.72% branch miss rt 100.00% 103.73% 107.67% wallclock 100.00% 99.90% 102.20% The clear effect here is that the 2% increase in CPI is directly reflected in the final wallclock time. (The other interesting effect is that the more ops are out of line calls via pvops, the lower the cache access and miss rates. Not too surprising, but it suggests that the non-pvops kernel is over-inlined. On the flipside, the branch misses go up correspondingly...) So, what's the fix? Paravirt patching turns all the pvops calls into direct calls, so _spin_lock etc do end up having direct calls. For example, the compiler generated code for paravirtualized _spin_lock is: <_spin_lock+0>: mov %gs:0xb4c8,%rax <_spin_lock+9>: incl 0xffffffffffffe044(%rax) <_spin_lock+15>: callq *0xffffffff805a5b30 <_spin_lock+22>: retq The indirect call will get patched to: <_spin_lock+0>: mov %gs:0xb4c8,%rax <_spin_lock+9>: incl 0xffffffffffffe044(%rax) <_spin_lock+15>: callq <__ticket_spin_lock> <_spin_lock+20>: nop; nop /* or whatever 2-byte nop */ <_spin_lock+22>: retq One possibility is to inline _spin_lock, etc, when building an optimised kernel (ie, when there's no spinlock/preempt instrumentation/debugging enabled). That will remove the outer call/return pair, returning the instruction stream to a single call/return, which will presumably execute the same as the non-pvops case. The downsides arel 1) it will replicate the preempt_disable/enable code at eack lock/unlock callsite; this code is fairly small, but not nothing; and 2) the spinlock definitions are already a very heavily tangled mass of #ifdefs and other preprocessor magic, and making any changes will be non-trivial. The other obvious answer is to disable pv-spinlocks. Making them a separate config option is fairly easy, and it would be trivial to enable them only when Xen is enabled (as the only non-default user). But it doesn't really address the common case of a distro build which is going to have Xen support enabled, and leaves the open question of whether the native performance cost of pv-spinlocks is worth the performance improvement on a loaded Xen system (10% saving of overall system CPU when guests block rather than spin). Still it is a reasonable short-term workaround. [ Impact: fix pvops performance regression when running native ] Analysed-by: "Xin Xiaohui" <xiaohui.xin@intel.com> Analysed-by: "Li Xin" <xin.li@intel.com> Analysed-by: "Nakajima Jun" <jun.nakajima@intel.com> Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Acked-by: H. Peter Anvin <hpa@zytor.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Xen-devel <xen-devel@lists.xensource.com> LKML-Reference: <4A0B62F7.5030802@goop.org> [ fixed the help text ] Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-05-14 07:16:55 +07:00
obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o
obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o
obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o
obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o
obj-$(CONFIG_SCx200) += scx200.o
scx200-y += scx200_32.o
obj-$(CONFIG_OLPC) += olpc.o
obj-$(CONFIG_X86_MRST) += mrst.o
microcode-y := microcode_core.o
microcode-$(CONFIG_MICROCODE_INTEL) += microcode_intel.o
microcode-$(CONFIG_MICROCODE_AMD) += microcode_amd.o
obj-$(CONFIG_MICROCODE) += microcode.o
obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o
obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o
###
# 64 bit specific files
ifeq ($(CONFIG_X86_64),y)
obj-$(CONFIG_X86_UV) += tlb_uv.o bios_uv.o uv_irq.o uv_sysfs.o uv_time.o
obj-$(CONFIG_X86_PM_TIMER) += pmtimer_64.o
obj-$(CONFIG_AUDIT) += audit_64.o
obj-$(CONFIG_GART_IOMMU) += pci-gart_64.o aperture_64.o
obj-$(CONFIG_CALGARY_IOMMU) += pci-calgary_64.o tce_64.o
obj-$(CONFIG_AMD_IOMMU) += amd_iommu_init.o amd_iommu.o
obj-$(CONFIG_PCI_MMCONFIG) += mmconf-fam10h_64.o
obj-y += vsmp_64.o
endif