linux-stable.git/arch/x86/kernel/head64.c, branch linux-5.2.y

x86/boot/64: Add missing fixup_pointer() for next_early_pgt access

2019-06-26T05:25:09+00:00

__startup_64() uses fixup_pointer() to access global variables in a
position-independent fashion. Access to next_early_pgt was wrapped into the
helper, but one instance in the 5-level paging branch was missed.

GCC generates a R_X86_64_PC32 PC-relative relocation for the access which
doesn't trigger the issue, but Clang emmits a R_X86_64_32S which leads to
an invalid memory access and system reboot.

Fixes: 187e91fe5e91 ("x86/boot/64/clang: Use fixup_pointer() to access 'next_early_pgt'")
Signed-off-by: Kirill A. Shutemov 
Signed-off-by: Thomas Gleixner 
Cc: Borislav Petkov 
Cc: "H. Peter Anvin" 
Cc: Dave Hansen 
Cc: Andy Lutomirski 
Cc: Peter Zijlstra 
Cc: Alexander Potapenko 
Link: https://lkml.kernel.org/r/20190620112422.29264-1-kirill.shutemov@linux.intel.com

x86/boot/64: Fix crash if kernel image crosses page table boundary

2019-06-26T05:25:09+00:00

A kernel which boots in 5-level paging mode crashes in a small percentage
of cases if KASLR is enabled.

This issue was tracked down to the case when the kernel image unpacks in a
way that it crosses an 1G boundary. The crash is caused by an overrun of
the PMD page table in __startup_64() and corruption of P4D page table
allocated next to it. This particular issue is not visible with 4-level
paging as P4D page tables are not used.

But the P4D and the PUD calculation have similar problems.

The PMD index calculation is wrong due to operator precedence, which fails
to confine the PMDs in the PMD array on wrap around.

The P4D calculation for 5-level paging and the PUD calculation calculate
the first index correctly, but then blindly increment it which causes the
same issue when a kernel image is located across a 512G and for 5-level
paging across a 46T boundary.

This wrap around mishandling was introduced when these parts moved from
assembly to C.

Restore it to the correct behaviour.

Fixes: c88d71508e36 ("x86/boot/64: Rewrite startup_64() in C")
Signed-off-by: Kirill A. Shutemov 
Signed-off-by: Thomas Gleixner 
Cc: Borislav Petkov 
Cc: "H. Peter Anvin" 
Cc: Dave Hansen 
Cc: Andy Lutomirski 
Cc: Peter Zijlstra 
Link: https://lkml.kernel.org/r/20190620112345.28833-1-kirill.shutemov@linux.intel.com

x86/boot: Mostly revert commit ae7e1238e68f2a ("Add ACPI RSDP address to setup_header")

2018-11-20T08:43:10+00:00

Peter Anvin pointed out that commit:

  ae7e1238e68f2a ("x86/boot: Add ACPI RSDP address to setup_header")

should be reverted as setup_header should only contain items set by the
legacy BIOS.

So revert said commit. Instead of fully reverting the dependent commit
of:

  e7b66d16fe4172 ("x86/acpi, x86/boot: Take RSDP address for boot params if available")

just remove the setup_header reference in order to replace it by
a boot_params in a followup patch.

Suggested-by: "H. Peter Anvin" 
Signed-off-by: Juergen Gross 
Cc: Linus Torvalds 
Cc: Peter Zijlstra 
Cc: Thomas Gleixner 
Cc: boris.ostrovsky@oracle.com
Cc: bp@alien8.de
Cc: daniel.kiper@oracle.com
Cc: sstabellini@kernel.org
Cc: xen-devel@lists.xenproject.org
Link: http://lkml.kernel.org/r/20181120072529.5489-2-jgross@suse.com
Signed-off-by: Ingo Molnar

x86: Clean up 'sizeof x' => 'sizeof(x)'

2018-10-29T06:13:28+00:00

"sizeof(x)" is the canonical coding style used in arch/x86 most of the time.
Fix the few places that didn't follow the convention.

(Also do some whitespace cleanups in a few places while at it.)

[ mingo: Rewrote the changelog. ]

Signed-off-by: Jordan Borgner 
Cc: Borislav Petkov 
Cc: H. Peter Anvin 
Cc: Linus Torvalds 
Cc: Peter Zijlstra 
Cc: Thomas Gleixner 
Link: http://lkml.kernel.org/r/20181028125828.7rgammkgzep2wpam@JordanDesktop
Signed-off-by: Ingo Molnar

x86/boot: Add ACPI RSDP address to setup_header

2018-10-10T08:44:22+00:00

Xen PVH guests receive the address of the RSDP table from Xen. In order
to support booting a Xen PVH guest via Grub2 using the standard x86
boot entry we need a way for Grub2 to pass the RSDP address to the
kernel.

For this purpose expand the struct setup_header to hold the physical
address of the RSDP address. Being zero means it isn't specified and
has to be located the legacy way (searching through low memory or
EBDA).

While documenting the new setup_header layout and protocol version
2.14 add the missing documentation of protocol version 2.13.

There are Grub2 versions in several distros with a downstream patch
violating the boot protocol by writing past the end of setup_header.
This requires another update of the boot protocol to enable the kernel
to distinguish between a specified RSDP address and one filled with
garbage by such a broken Grub2.

From protocol 2.14 on Grub2 will write the version it is supporting
(but never a higher value than found to be supported by the kernel)
ored with 0x8000 to the version field of setup_header. This enables
the kernel to know up to which field Grub2 has written information
to. All fields after that are supposed to be clobbered.

Signed-off-by: Juergen Gross 
Cc: Linus Torvalds 
Cc: Peter Zijlstra 
Cc: Thomas Gleixner 
Cc: boris.ostrovsky@oracle.com
Cc: bp@alien8.de
Cc: corbet@lwn.net
Cc: linux-doc@vger.kernel.org
Cc: xen-devel@lists.xenproject.org
Link: http://lkml.kernel.org/r/20181010061456.22238-3-jgross@suse.com
Signed-off-by: Ingo Molnar

x86/mm: Expand static page table for fixmap space

2018-09-20T21:17:22+00:00

We met a kernel panic when enabling earlycon, which is due to the fixmap
address of earlycon is not statically setup.

Currently the static fixmap setup in head_64.S only covers 2M virtual
address space, while it actually could be in 4M space with different
kernel configurations, e.g. when VSYSCALL emulation is disabled.

So increase the static space to 4M for now by defining FIXMAP_PMD_NUM to 2,
and add a build time check to ensure that the fixmap is covered by the
initial static page tables.

Fixes: 1ad83c858c7d ("x86_64,vsyscall: Make vsyscall emulation configurable")
Suggested-by: Thomas Gleixner 
Signed-off-by: Feng Tang 
Signed-off-by: Thomas Gleixner 
Tested-by: kernel test robot 
Reviewed-by: Juergen Gross  (Xen parts)
Cc: H Peter Anvin 
Cc: Peter Zijlstra 
Cc: Michal Hocko 
Cc: Yinghai Lu 
Cc: Dave Hansen 
Cc: Andi Kleen 
Cc: Andy Lutomirsky 
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20180920025828.23699-1-feng.tang@intel.com

x86/mm: Add .bss..decrypted section to hold shared variables

2018-09-15T18:48:45+00:00

kvmclock defines few static variables which are shared with the
hypervisor during the kvmclock initialization.

When SEV is active, memory is encrypted with a guest-specific key, and
if the guest OS wants to share the memory region with the hypervisor
then it must clear the C-bit before sharing it.

Currently, we use kernel_physical_mapping_init() to split large pages
before clearing the C-bit on shared pages. But it fails when called from
the kvmclock initialization (mainly because the memblock allocator is
not ready that early during boot).

Add a __bss_decrypted section attribute which can be used when defining
such shared variable. The so-defined variables will be placed in the
.bss..decrypted section. This section will be mapped with C=0 early
during boot.

The .bss..decrypted section has a big chunk of memory that may be unused
when memory encryption is not active, free it when memory encryption is
not active.

Suggested-by: Thomas Gleixner 
Signed-off-by: Brijesh Singh 
Signed-off-by: Thomas Gleixner 
Cc: Tom Lendacky 
Cc: Borislav Petkov 
Cc: "H. Peter Anvin" 
Cc: Paolo Bonzini 
Cc: Sean Christopherson 
Cc: Radim Krčmář
Cc: kvm@vger.kernel.org
Link: https://lkml.kernel.org/r/1536932759-12905-2-git-send-email-brijesh.singh@amd.com

Revert "x86/mm: Mark __pgtable_l5_enabled __initdata"

2018-06-23T12:20:37+00:00

This reverts commit e4e961e36f063484c48bed919013c106d178995d.

We need to use early version of pgtable_l5_enabled() in
early_identify_cpu() as this code runs before cpu_feature_enabled() is
usable.

But it leads to section mismatch:

cpu_init()
  load_mm_ldt()
    ldt_slot_va()
      LDT_BASE_ADDR
        LDT_PGD_ENTRY
	  pgtable_l5_enabled()
	    __pgtable_l5_enabled

__pgtable_l5_enabled marked as __initdata, but cpu_init() is not __init.

It's fixable: early code can be isolated into a separate translation unit,
but such change collides with other work in the area.  That's too much
hassle to save 4 bytes of memory.

Return __pgtable_l5_enabled back to be __ro_after_init.

Signed-off-by: Kirill A. Shutemov 
Signed-off-by: Thomas Gleixner 
Cc: "H. Peter Anvin" 
Link: https://lkml.kernel.org/r/20180622220841.54135-2-kirill.shutemov@linux.intel.com

x86/mm: Mark __pgtable_l5_enabled __initdata

2018-05-19T09:56:58+00:00

__pgtable_l5_enabled shouldn't be needed after system has booted.
All preparation is done. We can now mark it as __initdata.

Signed-off-by: Kirill A. Shutemov 
Reviewed-by: Thomas Gleixner 
Cc: Hugh Dickins 
Cc: Linus Torvalds 
Cc: Peter Zijlstra 
Link: http://lkml.kernel.org/r/20180518103528.59260-8-kirill.shutemov@linux.intel.com
Signed-off-by: Ingo Molnar

x86/mm: Introduce the 'no5lvl' kernel parameter

2018-05-19T09:56:57+00:00

This kernel parameter allows to force kernel to use 4-level paging even
if hardware and kernel support 5-level paging.

The option may be useful to work around regressions related to 5-level
paging.

Signed-off-by: Kirill A. Shutemov 
Reviewed-by: Thomas Gleixner 
Cc: Hugh Dickins 
Cc: Linus Torvalds 
Cc: Peter Zijlstra 
Link: http://lkml.kernel.org/r/20180518103528.59260-5-kirill.shutemov@linux.intel.com
Signed-off-by: Ingo Molnar