linux/arch/x86/kernel/cpu/bugs.c

116 lines
2.4 KiB
C
Raw Normal View History

/*
* Copyright (C) 1994 Linus Torvalds
*
* Cyrix stuff, June 1998 by:
* - Rafael R. Reilova (moved everything from head.S),
* <rreilova@ececs.uc.edu>
* - Channing Corn (tests & fixes),
* - Andrew D. Balsa (code cleanup).
*/
#include <linux/init.h>
#include <linux/utsname.h>
#include <asm/bugs.h>
#include <asm/processor.h>
#include <asm/processor-flags.h>
#include <asm/i387.h>
#include <asm/msr.h>
#include <asm/paravirt.h>
#include <asm/alternative.h>
static int __init no_387(char *s)
{
boot_cpu_data.hard_math = 0;
write_cr0(X86_CR0_TS | X86_CR0_EM | X86_CR0_MP | read_cr0());
return 1;
}
__setup("no387", no_387);
static double __initdata x = 4195835.0;
static double __initdata y = 3145727.0;
/*
* This used to check for exceptions..
* However, it turns out that to support that,
* the XMM trap handlers basically had to
* be buggy. So let's have a correct XMM trap
* handler, and forget about printing out
* some status at boot.
*
* We should really only care about bugs here
* anyway. Not features.
*/
static void __init check_fpu(void)
{
s32 fdiv_bug;
if (!boot_cpu_data.hard_math) {
#ifndef CONFIG_MATH_EMULATION
pr_emerg("No coprocessor found and no math emulation present\n");
pr_emerg("Giving up\n");
for (;;) ;
#endif
return;
}
kernel_fpu_begin();
/*
* trap_init() enabled FXSR and company _before_ testing for FP
* problems here.
*
* Test for the divl bug..
*/
__asm__("fninit\n\t"
"fldl %1\n\t"
"fdivl %2\n\t"
"fmull %2\n\t"
"fldl %1\n\t"
"fsubp %%st,%%st(1)\n\t"
"fistpl %0\n\t"
"fwait\n\t"
"fninit"
: "=m" (*&fdiv_bug)
: "m" (*&x), "m" (*&y));
kernel_fpu_end();
boot_cpu_data.fdiv_bug = fdiv_bug;
if (boot_cpu_data.fdiv_bug)
pr_warn("Hmm, FPU with FDIV bug\n");
}
/*
* Check whether we are able to run this kernel safely on SMP.
*
* - i386 is no longer supported.
* - In order to run on anything without a TSC, we need to be
* compiled for a i486.
x86: APIC: remove apic_write_around(); use alternatives Use alternatives to select the workaround for the 11AP Pentium erratum for the affected steppings on the fly rather than build time. Remove the X86_GOOD_APIC configuration option and replace all the calls to apic_write_around() with plain apic_write(), protecting accesses to the ESR as appropriate due to the 3AP Pentium erratum. Remove apic_read_around() and all its invocations altogether as not needed. Remove apic_write_atomic() and all its implementing backends. The use of ASM_OUTPUT2() is not strictly needed for input constraints, but I have used it for readability's sake. I had the feeling no one else was brave enough to do it, so I went ahead and here it is. Verified by checking the generated assembly and tested with both a 32-bit and a 64-bit configuration, also with the 11AP "feature" forced on and verified with gdb on /proc/kcore to work as expected (as an 11AP machines are quite hard to get hands on these days). Some script complained about the use of "volatile", but apic_write() needs it for the same reason and is effectively a replacement for writel(), so I have disregarded it. I am not sure what the policy wrt defconfig files is, they are generated and there is risk of a conflict resulting from an unrelated change, so I have left changes to them out. The option will get removed from them at the next run. Some testing with machines other than mine will be needed to avoid some stupid mistake, but despite its volume, the change is not really that intrusive, so I am fairly confident that because it works for me, it will everywhere. Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-17 02:15:30 +08:00
*/
static void __init check_config(void)
{
if (boot_cpu_data.x86 < 4)
panic("Kernel requires i486+ for 'invlpg' and other features");
}
void __init check_bugs(void)
{
identify_boot_cpu();
#ifndef CONFIG_SMP
pr_info("CPU: ");
print_cpu_info(&boot_cpu_data);
#endif
check_config();
init_utsname()->machine[1] =
'0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
alternative_instructions();
x86, fpu: use non-lazy fpu restore for processors supporting xsave Fundamental model of the current Linux kernel is to lazily init and restore FPU instead of restoring the task state during context switch. This changes that fundamental lazy model to the non-lazy model for the processors supporting xsave feature. Reasons driving this model change are: i. Newer processors support optimized state save/restore using xsaveopt and xrstor by tracking the INIT state and MODIFIED state during context-switch. This is faster than modifying the cr0.TS bit which has serializing semantics. ii. Newer glibc versions use SSE for some of the optimized copy/clear routines. With certain workloads (like boot, kernel-compilation etc), application completes its work with in the first 5 task switches, thus taking upto 5 #DNA traps with the kernel not getting a chance to apply the above mentioned pre-load heuristic. iii. Some xstate features (like AMD's LWP feature) don't honor the cr0.TS bit and thus will not work correctly in the presence of lazy restore. Non-lazy state restore is needed for enabling such features. Some data on a two socket SNB system: * Saved 20K DNA exceptions during boot on a two socket SNB system. * Saved 50K DNA exceptions during kernel-compilation workload. * Improved throughput of the AVX based checksumming function inside the kernel by ~15% as xsave/xrstor is faster than the serializing clts/stts pair. Also now kernel_fpu_begin/end() relies on the patched alternative instructions. So move check_fpu() which uses the kernel_fpu_begin/end() after alternative_instructions(). Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Link: http://lkml.kernel.org/r/1345842782-24175-7-git-send-email-suresh.b.siddha@intel.com Merge 32-bit boot fix from, Link: http://lkml.kernel.org/r/1347300665-6209-4-git-send-email-suresh.b.siddha@intel.com Cc: Jim Kukunas <james.t.kukunas@linux.intel.com> Cc: NeilBrown <neilb@suse.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2012-08-25 05:13:02 +08:00
/*
* kernel_fpu_begin/end() in check_fpu() relies on the patched
* alternative instructions.
*/
check_fpu();
}