linux-stable/arch/x86/platform/pvh/head.S
Linus Torvalds c6536676c7 - turn the stack canary into a normal __percpu variable on 32-bit which
gets rid of the LAZY_GS stuff and a lot of code.
 
 - Add an insn_decode() API which all users of the instruction decoder
 should preferrably use. Its goal is to keep the details of the
 instruction decoder away from its users and simplify and streamline how
 one decodes insns in the kernel. Convert its users to it.
 
 - kprobes improvements and fixes
 
 - Set the maximum DIE per package variable on Hygon
 
 - Rip out the dynamic NOP selection and simplify all the machinery around
 selecting NOPs. Use the simplified NOPs in objtool now too.
 
 - Add Xeon Sapphire Rapids to list of CPUs that support PPIN
 
 - Simplify the retpolines by folding the entire thing into an
 alternative now that objtool can handle alternatives with stack
 ops. Then, have objtool rewrite the call to the retpoline with the
 alternative which then will get patched at boot time.
 
 - Document Intel uarch per models in intel-family.h
 
 - Make Sub-NUMA Clustering topology the default and Cluster-on-Die the
 exception on Intel.
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEzv7L6UO9uDPlPSfHEsHwGGHeVUoFAmCHyJQACgkQEsHwGGHe
 VUpjiRAAwPZdwwp08ypZuMHR4EhLNru6gYhbAoALGgtYnQjLtn5onQhIeieK+R4L
 cmZpxHT9OFp5dXHk4kwygaQBsD4pPOiIpm60kye1dN3cSbOORRdkwEoQMpKMZ+5Y
 kvVsmn7lrwRbp600KdE4G6L5+N6gEgr0r6fMFWWGK3mgVAyCzPexVHgydcp131ch
 iYMo6/pPDcNkcV/hboVKgx7GISdQ7L356L1MAIW/Sxtw6uD/X4qGYW+kV2OQg9+t
 nQDaAo7a8Jqlop5W5TQUdMLKQZ1xK8SFOSX/nTS15DZIOBQOGgXR7Xjywn1chBH/
 PHLwM5s4XF6NT5VlIA8tXNZjWIZTiBdldr1kJAmdDYacrtZVs2LWSOC0ilXsd08Z
 EWtvcpHfHEqcuYJlcdALuXY8xDWqf6Q2F7BeadEBAxwnnBg+pAEoLXI/1UwWcmsj
 wpaZTCorhJpYo2pxXckVdHz2z0LldDCNOXOjjaWU8tyaOBKEK6MgAaYU7e0yyENv
 mVc9n5+WuvXuivC6EdZ94Pcr/KQsd09ezpJYcVfMDGv58YZrb6XIEELAJIBTu2/B
 Ua8QApgRgetx+1FKb8X6eGjPl0p40qjD381TADb4rgETPb1AgKaQflmrSTIik+7p
 O+Eo/4x/GdIi9jFk3K+j4mIznRbUX0cheTJgXoiI4zXML9Jv94w=
 =bm4S
 -----END PGP SIGNATURE-----

Merge tag 'x86_core_for_v5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 updates from Borislav Petkov:

 - Turn the stack canary into a normal __percpu variable on 32-bit which
   gets rid of the LAZY_GS stuff and a lot of code.

 - Add an insn_decode() API which all users of the instruction decoder
   should preferrably use. Its goal is to keep the details of the
   instruction decoder away from its users and simplify and streamline
   how one decodes insns in the kernel. Convert its users to it.

 - kprobes improvements and fixes

 - Set the maximum DIE per package variable on Hygon

 - Rip out the dynamic NOP selection and simplify all the machinery
   around selecting NOPs. Use the simplified NOPs in objtool now too.

 - Add Xeon Sapphire Rapids to list of CPUs that support PPIN

 - Simplify the retpolines by folding the entire thing into an
   alternative now that objtool can handle alternatives with stack ops.
   Then, have objtool rewrite the call to the retpoline with the
   alternative which then will get patched at boot time.

 - Document Intel uarch per models in intel-family.h

 - Make Sub-NUMA Clustering topology the default and Cluster-on-Die the
   exception on Intel.

* tag 'x86_core_for_v5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (53 commits)
  x86, sched: Treat Intel SNC topology as default, COD as exception
  x86/cpu: Comment Skylake server stepping too
  x86/cpu: Resort and comment Intel models
  objtool/x86: Rewrite retpoline thunk calls
  objtool: Skip magical retpoline .altinstr_replacement
  objtool: Cache instruction relocs
  objtool: Keep track of retpoline call sites
  objtool: Add elf_create_undef_symbol()
  objtool: Extract elf_symbol_add()
  objtool: Extract elf_strtab_concat()
  objtool: Create reloc sections implicitly
  objtool: Add elf_create_reloc() helper
  objtool: Rework the elf_rebuild_reloc_section() logic
  objtool: Fix static_call list generation
  objtool: Handle per arch retpoline naming
  objtool: Correctly handle retpoline thunk calls
  x86/retpoline: Simplify retpolines
  x86/alternatives: Optimize optimize_nops()
  x86: Add insn_decode_kernel()
  x86/kprobes: Move 'inline' to the beginning of the kprobe_is_ss() declaration
  ...
2021-04-27 17:45:09 -07:00

165 lines
3.9 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright C 2016, Oracle and/or its affiliates. All rights reserved.
*/
.code32
.text
#define _pa(x) ((x) - __START_KERNEL_map)
#include <linux/elfnote.h>
#include <linux/init.h>
#include <linux/linkage.h>
#include <asm/segment.h>
#include <asm/asm.h>
#include <asm/boot.h>
#include <asm/processor-flags.h>
#include <asm/msr.h>
#include <asm/nospec-branch.h>
#include <xen/interface/elfnote.h>
__HEAD
/*
* Entry point for PVH guests.
*
* Xen ABI specifies the following register state when we come here:
*
* - `ebx`: contains the physical memory address where the loader has placed
* the boot start info structure.
* - `cr0`: bit 0 (PE) must be set. All the other writeable bits are cleared.
* - `cr4`: all bits are cleared.
* - `cs `: must be a 32-bit read/execute code segment with a base of `0`
* and a limit of `0xFFFFFFFF`. The selector value is unspecified.
* - `ds`, `es`: must be a 32-bit read/write data segment with a base of
* `0` and a limit of `0xFFFFFFFF`. The selector values are all
* unspecified.
* - `tr`: must be a 32-bit TSS (active) with a base of '0' and a limit
* of '0x67'.
* - `eflags`: bit 17 (VM) must be cleared. Bit 9 (IF) must be cleared.
* Bit 8 (TF) must be cleared. Other bits are all unspecified.
*
* All other processor registers and flag bits are unspecified. The OS is in
* charge of setting up it's own stack, GDT and IDT.
*/
#define PVH_GDT_ENTRY_CS 1
#define PVH_GDT_ENTRY_DS 2
#define PVH_CS_SEL (PVH_GDT_ENTRY_CS * 8)
#define PVH_DS_SEL (PVH_GDT_ENTRY_DS * 8)
SYM_CODE_START_LOCAL(pvh_start_xen)
cld
lgdt (_pa(gdt))
mov $PVH_DS_SEL,%eax
mov %eax,%ds
mov %eax,%es
mov %eax,%ss
/* Stash hvm_start_info. */
mov $_pa(pvh_start_info), %edi
mov %ebx, %esi
mov _pa(pvh_start_info_sz), %ecx
shr $2,%ecx
rep
movsl
mov $_pa(early_stack_end), %esp
/* Enable PAE mode. */
mov %cr4, %eax
orl $X86_CR4_PAE, %eax
mov %eax, %cr4
#ifdef CONFIG_X86_64
/* Enable Long mode. */
mov $MSR_EFER, %ecx
rdmsr
btsl $_EFER_LME, %eax
wrmsr
/* Enable pre-constructed page tables. */
mov $_pa(init_top_pgt), %eax
mov %eax, %cr3
mov $(X86_CR0_PG | X86_CR0_PE), %eax
mov %eax, %cr0
/* Jump to 64-bit mode. */
ljmp $PVH_CS_SEL, $_pa(1f)
/* 64-bit entry point. */
.code64
1:
/* Set base address in stack canary descriptor. */
mov $MSR_GS_BASE,%ecx
mov $_pa(canary), %eax
xor %edx, %edx
wrmsr
call xen_prepare_pvh
/* startup_64 expects boot_params in %rsi. */
mov $_pa(pvh_bootparams), %rsi
mov $_pa(startup_64), %rax
ANNOTATE_RETPOLINE_SAFE
jmp *%rax
#else /* CONFIG_X86_64 */
call mk_early_pgtbl_32
mov $_pa(initial_page_table), %eax
mov %eax, %cr3
mov %cr0, %eax
or $(X86_CR0_PG | X86_CR0_PE), %eax
mov %eax, %cr0
ljmp $PVH_CS_SEL, $1f
1:
call xen_prepare_pvh
mov $_pa(pvh_bootparams), %esi
/* startup_32 doesn't expect paging and PAE to be on. */
ljmp $PVH_CS_SEL, $_pa(2f)
2:
mov %cr0, %eax
and $~X86_CR0_PG, %eax
mov %eax, %cr0
mov %cr4, %eax
and $~X86_CR4_PAE, %eax
mov %eax, %cr4
ljmp $PVH_CS_SEL, $_pa(startup_32)
#endif
SYM_CODE_END(pvh_start_xen)
.section ".init.data","aw"
.balign 8
SYM_DATA_START_LOCAL(gdt)
.word gdt_end - gdt_start
.long _pa(gdt_start)
.word 0
SYM_DATA_END(gdt)
SYM_DATA_START_LOCAL(gdt_start)
.quad 0x0000000000000000 /* NULL descriptor */
#ifdef CONFIG_X86_64
.quad GDT_ENTRY(0xa09a, 0, 0xfffff) /* PVH_CS_SEL */
#else
.quad GDT_ENTRY(0xc09a, 0, 0xfffff) /* PVH_CS_SEL */
#endif
.quad GDT_ENTRY(0xc092, 0, 0xfffff) /* PVH_DS_SEL */
SYM_DATA_END_LABEL(gdt_start, SYM_L_LOCAL, gdt_end)
.balign 16
SYM_DATA_LOCAL(canary, .fill 48, 1, 0)
SYM_DATA_START_LOCAL(early_stack)
.fill BOOT_STACK_SIZE, 1, 0
SYM_DATA_END_LABEL(early_stack, SYM_L_LOCAL, early_stack_end)
ELFNOTE(Xen, XEN_ELFNOTE_PHYS32_ENTRY,
_ASM_PTR (pvh_start_xen - __START_KERNEL_map))