2012-03-05 19:49:27 +08:00
|
|
|
/*
|
|
|
|
* Based on arch/arm/kernel/setup.c
|
|
|
|
*
|
|
|
|
* Copyright (C) 1995-2001 Russell King
|
|
|
|
* Copyright (C) 2012 ARM Ltd.
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or modify
|
|
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
|
|
* published by the Free Software Foundation.
|
|
|
|
*
|
|
|
|
* This program is distributed in the hope that it will be useful,
|
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
|
|
* GNU General Public License for more details.
|
|
|
|
*
|
|
|
|
* You should have received a copy of the GNU General Public License
|
|
|
|
* along with this program. If not, see <http://www.gnu.org/licenses/>.
|
|
|
|
*/
|
|
|
|
|
ARM64 / ACPI: Get RSDP and ACPI boot-time tables
As we want to get ACPI tables to parse and then use the information
for system initialization, we should get the RSDP (Root System
Description Pointer) first, it then locates Extended Root Description
Table (XSDT) which contains all the 64-bit physical address that
pointer to other boot-time tables.
Introduce acpi.c and its related head file in this patch to provide
fundamental needs of extern variables and functions for ACPI core,
and then get boot-time tables as needed.
- asm/acenv.h for arch specific ACPICA environments and
implementation, It is needed unconditionally by ACPI core;
- asm/acpi.h for arch specific variables and functions needed by
ACPI driver core;
- acpi.c for ARM64 related ACPI implementation for ACPI driver
core;
acpi_boot_table_init() is introduced to get RSDP and boot-time tables,
it will be called in setup_arch() before paging_init(), so we should
use eary_memremap() mechanism here to get the RSDP and all the table
pointers.
FADT Major.Minor version was introduced in ACPI 5.1, it is the same
as ACPI version.
In ACPI 5.1, some major gaps are fixed for ARM, such as updates in
MADT table for GIC and SMP init, without those updates, we can not
get the MPIDR for SMP init, and GICv2/3 related init information, so
we can't boot arm64 ACPI properly with table versions predating 5.1.
If firmware provides ACPI tables with ACPI version less than 5.1,
OS has no way to retrieve the configuration data that is necessary
to init SMP boot protocol and the GIC properly, so disable ACPI if
we get an FADT table with version less that 5.1 when acpi_boot_table_init()
called.
CC: Catalin Marinas <catalin.marinas@arm.com>
CC: Will Deacon <will.deacon@arm.com>
CC: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Tested-by: Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com>
Tested-by: Yijing Wang <wangyijing@huawei.com>
Tested-by: Mark Langsdorf <mlangsdo@redhat.com>
Tested-by: Jon Masters <jcm@redhat.com>
Tested-by: Timur Tabi <timur@codeaurora.org>
Tested-by: Robert Richter <rrichter@cavium.com>
Acked-by: Robert Richter <rrichter@cavium.com>
Acked-by: Olof Johansson <olof@lixom.net>
Acked-by: Grant Likely <grant.likely@linaro.org>
Signed-off-by: Al Stone <al.stone@linaro.org>
Signed-off-by: Graeme Gregory <graeme.gregory@linaro.org>
Signed-off-by: Tomasz Nowicki <tomasz.nowicki@linaro.org>
Signed-off-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
2015-03-24 22:02:37 +08:00
|
|
|
#include <linux/acpi.h>
|
2012-03-05 19:49:27 +08:00
|
|
|
#include <linux/export.h>
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/stddef.h>
|
|
|
|
#include <linux/ioport.h>
|
|
|
|
#include <linux/delay.h>
|
|
|
|
#include <linux/utsname.h>
|
|
|
|
#include <linux/initrd.h>
|
|
|
|
#include <linux/console.h>
|
2014-04-04 00:48:54 +08:00
|
|
|
#include <linux/cache.h>
|
2012-03-05 19:49:27 +08:00
|
|
|
#include <linux/bootmem.h>
|
|
|
|
#include <linux/screen_info.h>
|
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/kexec.h>
|
|
|
|
#include <linux/crash_dump.h>
|
|
|
|
#include <linux/root_dev.h>
|
|
|
|
#include <linux/cpu.h>
|
|
|
|
#include <linux/interrupt.h>
|
|
|
|
#include <linux/smp.h>
|
|
|
|
#include <linux/fs.h>
|
|
|
|
#include <linux/proc_fs.h>
|
|
|
|
#include <linux/memblock.h>
|
|
|
|
#include <linux/of_fdt.h>
|
2014-04-16 09:59:30 +08:00
|
|
|
#include <linux/efi.h>
|
2015-07-31 22:46:16 +08:00
|
|
|
#include <linux/psci.h>
|
2012-03-05 19:49:27 +08:00
|
|
|
|
ARM64 / ACPI: Get RSDP and ACPI boot-time tables
As we want to get ACPI tables to parse and then use the information
for system initialization, we should get the RSDP (Root System
Description Pointer) first, it then locates Extended Root Description
Table (XSDT) which contains all the 64-bit physical address that
pointer to other boot-time tables.
Introduce acpi.c and its related head file in this patch to provide
fundamental needs of extern variables and functions for ACPI core,
and then get boot-time tables as needed.
- asm/acenv.h for arch specific ACPICA environments and
implementation, It is needed unconditionally by ACPI core;
- asm/acpi.h for arch specific variables and functions needed by
ACPI driver core;
- acpi.c for ARM64 related ACPI implementation for ACPI driver
core;
acpi_boot_table_init() is introduced to get RSDP and boot-time tables,
it will be called in setup_arch() before paging_init(), so we should
use eary_memremap() mechanism here to get the RSDP and all the table
pointers.
FADT Major.Minor version was introduced in ACPI 5.1, it is the same
as ACPI version.
In ACPI 5.1, some major gaps are fixed for ARM, such as updates in
MADT table for GIC and SMP init, without those updates, we can not
get the MPIDR for SMP init, and GICv2/3 related init information, so
we can't boot arm64 ACPI properly with table versions predating 5.1.
If firmware provides ACPI tables with ACPI version less than 5.1,
OS has no way to retrieve the configuration data that is necessary
to init SMP boot protocol and the GIC properly, so disable ACPI if
we get an FADT table with version less that 5.1 when acpi_boot_table_init()
called.
CC: Catalin Marinas <catalin.marinas@arm.com>
CC: Will Deacon <will.deacon@arm.com>
CC: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Tested-by: Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com>
Tested-by: Yijing Wang <wangyijing@huawei.com>
Tested-by: Mark Langsdorf <mlangsdo@redhat.com>
Tested-by: Jon Masters <jcm@redhat.com>
Tested-by: Timur Tabi <timur@codeaurora.org>
Tested-by: Robert Richter <rrichter@cavium.com>
Acked-by: Robert Richter <rrichter@cavium.com>
Acked-by: Olof Johansson <olof@lixom.net>
Acked-by: Grant Likely <grant.likely@linaro.org>
Signed-off-by: Al Stone <al.stone@linaro.org>
Signed-off-by: Graeme Gregory <graeme.gregory@linaro.org>
Signed-off-by: Tomasz Nowicki <tomasz.nowicki@linaro.org>
Signed-off-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
2015-03-24 22:02:37 +08:00
|
|
|
#include <asm/acpi.h>
|
2014-04-08 06:39:52 +08:00
|
|
|
#include <asm/fixmap.h>
|
2014-07-16 23:32:44 +08:00
|
|
|
#include <asm/cpu.h>
|
2012-03-05 19:49:27 +08:00
|
|
|
#include <asm/cputype.h>
|
|
|
|
#include <asm/elf.h>
|
2014-11-14 23:54:07 +08:00
|
|
|
#include <asm/cpufeature.h>
|
2013-10-25 03:30:17 +08:00
|
|
|
#include <asm/cpu_ops.h>
|
2015-10-12 23:52:58 +08:00
|
|
|
#include <asm/kasan.h>
|
2016-04-09 06:50:27 +08:00
|
|
|
#include <asm/numa.h>
|
2012-03-05 19:49:27 +08:00
|
|
|
#include <asm/sections.h>
|
|
|
|
#include <asm/setup.h>
|
2012-08-29 16:47:19 +08:00
|
|
|
#include <asm/smp_plat.h>
|
2012-03-05 19:49:27 +08:00
|
|
|
#include <asm/cacheflush.h>
|
|
|
|
#include <asm/tlbflush.h>
|
|
|
|
#include <asm/traps.h>
|
|
|
|
#include <asm/memblock.h>
|
2014-04-16 09:59:30 +08:00
|
|
|
#include <asm/efi.h>
|
2015-05-06 22:13:31 +08:00
|
|
|
#include <asm/xen/hypervisor.h>
|
2016-01-25 19:44:58 +08:00
|
|
|
#include <asm/mmu_context.h>
|
2012-03-05 19:49:27 +08:00
|
|
|
|
|
|
|
phys_addr_t __fdt_pointer __initdata;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Standard memory resources
|
|
|
|
*/
|
|
|
|
static struct resource mem_res[] = {
|
|
|
|
{
|
|
|
|
.name = "Kernel code",
|
|
|
|
.start = 0,
|
|
|
|
.end = 0,
|
2016-01-27 04:57:22 +08:00
|
|
|
.flags = IORESOURCE_SYSTEM_RAM
|
2012-03-05 19:49:27 +08:00
|
|
|
},
|
|
|
|
{
|
|
|
|
.name = "Kernel data",
|
|
|
|
.start = 0,
|
|
|
|
.end = 0,
|
2016-01-27 04:57:22 +08:00
|
|
|
.flags = IORESOURCE_SYSTEM_RAM
|
2012-03-05 19:49:27 +08:00
|
|
|
}
|
|
|
|
};
|
|
|
|
|
|
|
|
#define kernel_code mem_res[0]
|
|
|
|
#define kernel_data mem_res[1]
|
|
|
|
|
2015-03-17 17:55:12 +08:00
|
|
|
/*
|
|
|
|
* The recorded values of x0 .. x3 upon kernel entry.
|
|
|
|
*/
|
|
|
|
u64 __cacheline_aligned boot_args[4];
|
|
|
|
|
2013-11-06 02:10:47 +08:00
|
|
|
void __init smp_setup_processor_id(void)
|
|
|
|
{
|
2014-11-04 18:50:16 +08:00
|
|
|
u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
|
|
|
|
cpu_logical_map(0) = mpidr;
|
|
|
|
|
2013-11-06 02:10:47 +08:00
|
|
|
/*
|
|
|
|
* clear __my_cpu_offset on boot CPU to avoid hang caused by
|
|
|
|
* using percpu variable early, for example, lockdep will
|
|
|
|
* access percpu variable inside lock_release
|
|
|
|
*/
|
|
|
|
set_my_cpu_offset(0);
|
2014-11-04 18:50:16 +08:00
|
|
|
pr_info("Booting Linux on physical CPU 0x%lx\n", (unsigned long)mpidr);
|
2013-11-06 02:10:47 +08:00
|
|
|
}
|
|
|
|
|
2013-10-21 20:29:42 +08:00
|
|
|
bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
|
|
|
|
{
|
|
|
|
return phys_id == cpu_logical_map(cpu);
|
|
|
|
}
|
|
|
|
|
arm64: kernel: build MPIDR_EL1 hash function data structure
On ARM64 SMP systems, cores are identified by their MPIDR_EL1 register.
The MPIDR_EL1 guidelines in the ARM ARM do not provide strict enforcement of
MPIDR_EL1 layout, only recommendations that, if followed, split the MPIDR_EL1
on ARM 64 bit platforms in four affinity levels. In multi-cluster
systems like big.LITTLE, if the affinity guidelines are followed, the
MPIDR_EL1 can not be considered a linear index. This means that the
association between logical CPU in the kernel and the HW CPU identifier
becomes somewhat more complicated requiring methods like hashing to
associate a given MPIDR_EL1 to a CPU logical index, in order for the look-up
to be carried out in an efficient and scalable way.
This patch provides a function in the kernel that starting from the
cpu_logical_map, implement collision-free hashing of MPIDR_EL1 values by
checking all significative bits of MPIDR_EL1 affinity level bitfields.
The hashing can then be carried out through bits shifting and ORing; the
resulting hash algorithm is a collision-free though not minimal hash that can
be executed with few assembly instructions. The mpidr_el1 is filtered through a
mpidr mask that is built by checking all bits that toggle in the set of
MPIDR_EL1s corresponding to possible CPUs. Bits that do not toggle do not
carry information so they do not contribute to the resulting hash.
Pseudo code:
/* check all bits that toggle, so they are required */
for (i = 1, mpidr_el1_mask = 0; i < num_possible_cpus(); i++)
mpidr_el1_mask |= (cpu_logical_map(i) ^ cpu_logical_map(0));
/*
* Build shifts to be applied to aff0, aff1, aff2, aff3 values to hash the
* mpidr_el1
* fls() returns the last bit set in a word, 0 if none
* ffs() returns the first bit set in a word, 0 if none
*/
fs0 = mpidr_el1_mask[7:0] ? ffs(mpidr_el1_mask[7:0]) - 1 : 0;
fs1 = mpidr_el1_mask[15:8] ? ffs(mpidr_el1_mask[15:8]) - 1 : 0;
fs2 = mpidr_el1_mask[23:16] ? ffs(mpidr_el1_mask[23:16]) - 1 : 0;
fs3 = mpidr_el1_mask[39:32] ? ffs(mpidr_el1_mask[39:32]) - 1 : 0;
ls0 = fls(mpidr_el1_mask[7:0]);
ls1 = fls(mpidr_el1_mask[15:8]);
ls2 = fls(mpidr_el1_mask[23:16]);
ls3 = fls(mpidr_el1_mask[39:32]);
bits0 = ls0 - fs0;
bits1 = ls1 - fs1;
bits2 = ls2 - fs2;
bits3 = ls3 - fs3;
aff0_shift = fs0;
aff1_shift = 8 + fs1 - bits0;
aff2_shift = 16 + fs2 - (bits0 + bits1);
aff3_shift = 32 + fs3 - (bits0 + bits1 + bits2);
u32 hash(u64 mpidr_el1) {
u32 l[4];
u64 mpidr_el1_masked = mpidr_el1 & mpidr_el1_mask;
l[0] = mpidr_el1_masked & 0xff;
l[1] = mpidr_el1_masked & 0xff00;
l[2] = mpidr_el1_masked & 0xff0000;
l[3] = mpidr_el1_masked & 0xff00000000;
return (l[0] >> aff0_shift | l[1] >> aff1_shift | l[2] >> aff2_shift |
l[3] >> aff3_shift);
}
The hashing algorithm relies on the inherent properties set in the ARM ARM
recommendations for the MPIDR_EL1. Exotic configurations, where for instance
the MPIDR_EL1 values at a given affinity level have large holes, can end up
requiring big hash tables since the compression of values that can be achieved
through shifting is somewhat crippled when holes are present. Kernel warns if
the number of buckets of the resulting hash table exceeds the number of
possible CPUs by a factor of 4, which is a symptom of a very sparse HW
MPIDR_EL1 configuration.
The hash algorithm is quite simple and can easily be implemented in assembly
code, to be used in code paths where the kernel virtual address space is
not set-up (ie cpu_resume) and instruction and data fetches are strongly
ordered so code must be compact and must carry out few data accesses.
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
2013-05-16 17:32:09 +08:00
|
|
|
struct mpidr_hash mpidr_hash;
|
|
|
|
/**
|
|
|
|
* smp_build_mpidr_hash - Pre-compute shifts required at each affinity
|
|
|
|
* level in order to build a linear index from an
|
|
|
|
* MPIDR value. Resulting algorithm is a collision
|
|
|
|
* free hash carried out through shifting and ORing
|
|
|
|
*/
|
|
|
|
static void __init smp_build_mpidr_hash(void)
|
|
|
|
{
|
|
|
|
u32 i, affinity, fs[4], bits[4], ls;
|
|
|
|
u64 mask = 0;
|
|
|
|
/*
|
|
|
|
* Pre-scan the list of MPIDRS and filter out bits that do
|
|
|
|
* not contribute to affinity levels, ie they never toggle.
|
|
|
|
*/
|
|
|
|
for_each_possible_cpu(i)
|
|
|
|
mask |= (cpu_logical_map(i) ^ cpu_logical_map(0));
|
|
|
|
pr_debug("mask of set bits %#llx\n", mask);
|
|
|
|
/*
|
|
|
|
* Find and stash the last and first bit set at all affinity levels to
|
|
|
|
* check how many bits are required to represent them.
|
|
|
|
*/
|
|
|
|
for (i = 0; i < 4; i++) {
|
|
|
|
affinity = MPIDR_AFFINITY_LEVEL(mask, i);
|
|
|
|
/*
|
|
|
|
* Find the MSB bit and LSB bits position
|
|
|
|
* to determine how many bits are required
|
|
|
|
* to express the affinity level.
|
|
|
|
*/
|
|
|
|
ls = fls(affinity);
|
|
|
|
fs[i] = affinity ? ffs(affinity) - 1 : 0;
|
|
|
|
bits[i] = ls - fs[i];
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* An index can be created from the MPIDR_EL1 by isolating the
|
|
|
|
* significant bits at each affinity level and by shifting
|
|
|
|
* them in order to compress the 32 bits values space to a
|
|
|
|
* compressed set of values. This is equivalent to hashing
|
|
|
|
* the MPIDR_EL1 through shifting and ORing. It is a collision free
|
|
|
|
* hash though not minimal since some levels might contain a number
|
|
|
|
* of CPUs that is not an exact power of 2 and their bit
|
|
|
|
* representation might contain holes, eg MPIDR_EL1[7:0] = {0x2, 0x80}.
|
|
|
|
*/
|
|
|
|
mpidr_hash.shift_aff[0] = MPIDR_LEVEL_SHIFT(0) + fs[0];
|
|
|
|
mpidr_hash.shift_aff[1] = MPIDR_LEVEL_SHIFT(1) + fs[1] - bits[0];
|
|
|
|
mpidr_hash.shift_aff[2] = MPIDR_LEVEL_SHIFT(2) + fs[2] -
|
|
|
|
(bits[1] + bits[0]);
|
|
|
|
mpidr_hash.shift_aff[3] = MPIDR_LEVEL_SHIFT(3) +
|
|
|
|
fs[3] - (bits[2] + bits[1] + bits[0]);
|
|
|
|
mpidr_hash.mask = mask;
|
|
|
|
mpidr_hash.bits = bits[3] + bits[2] + bits[1] + bits[0];
|
|
|
|
pr_debug("MPIDR hash: aff0[%u] aff1[%u] aff2[%u] aff3[%u] mask[%#llx] bits[%u]\n",
|
|
|
|
mpidr_hash.shift_aff[0],
|
|
|
|
mpidr_hash.shift_aff[1],
|
|
|
|
mpidr_hash.shift_aff[2],
|
|
|
|
mpidr_hash.shift_aff[3],
|
|
|
|
mpidr_hash.mask,
|
|
|
|
mpidr_hash.bits);
|
|
|
|
/*
|
|
|
|
* 4x is an arbitrary value used to warn on a hash table much bigger
|
|
|
|
* than expected on most systems.
|
|
|
|
*/
|
|
|
|
if (mpidr_hash_size() > 4 * num_possible_cpus())
|
|
|
|
pr_warn("Large number of MPIDR hash buckets detected\n");
|
|
|
|
}
|
2015-03-14 00:14:34 +08:00
|
|
|
|
2012-03-05 19:49:27 +08:00
|
|
|
static void __init setup_machine_fdt(phys_addr_t dt_phys)
|
|
|
|
{
|
2015-06-01 19:40:32 +08:00
|
|
|
void *dt_virt = fixmap_remap_fdt(dt_phys);
|
|
|
|
|
|
|
|
if (!dt_virt || !early_init_dt_scan(dt_virt)) {
|
|
|
|
pr_crit("\n"
|
|
|
|
"Error: invalid device tree blob at physical address %pa (virtual address 0x%p)\n"
|
|
|
|
"The dtb must be 8-byte aligned and must not exceed 2 MB in size\n"
|
|
|
|
"\nPlease check your bootloader.",
|
|
|
|
&dt_phys, dt_virt);
|
2012-03-05 19:49:27 +08:00
|
|
|
|
|
|
|
while (true)
|
|
|
|
cpu_relax();
|
|
|
|
}
|
2014-09-01 22:47:19 +08:00
|
|
|
|
arm64: Fix up /proc/cpuinfo
Commit d7a49086f263164a (arm64: cpuinfo: print info for all CPUs)
attempted to clean up /proc/cpuinfo, but due to concerns regarding
further changes was reverted in commit 5e39977edf6500fd (Revert "arm64:
cpuinfo: print info for all CPUs").
There are two major issues with the arm64 /proc/cpuinfo format
currently:
* The "Features" line describes (only) the 64-bit hwcaps, which is
problematic for some 32-bit applications which attempt to parse it. As
the same names are used for analogous ISA features (e.g. aes) despite
these generally being architecturally unrelated, it is not possible to
simply append the 64-bit and 32-bit hwcaps in a manner that might not
be misleading to some applications.
Various potential solutions have appeared in vendor kernels. Typically
the format of the Features line varies depending on whether the task
is 32-bit.
* Information is only printed regarding a single CPU. This does not
match the ARM format, and does not provide sufficient information in
big.LITTLE systems where CPUs are heterogeneous. The CPU information
printed is queried from the current CPU's registers, which is racy
w.r.t. cross-cpu migration.
This patch attempts to solve these issues. The following changes are
made:
* When a task with a LINUX32 personality attempts to read /proc/cpuinfo,
the "Features" line contains the decoded 32-bit hwcaps, as with the
arm port. Otherwise, the decoded 64-bit hwcaps are shown. This aligns
with the behaviour of COMPAT_UTS_MACHINE and COMPAT_ELF_PLATFORM. In
the absense of compat support, the Features line is empty.
The set of hwcaps injected into a task's auxval are unaffected.
* Properties are printed per-cpu, as with the ARM port. The per-cpu
information is queried from pre-recorded cpu information (as used by
the sanity checks).
* As with the previous attempt at fixing up /proc/cpuinfo, the hardware
field is removed. The only users so far are 32-bit applications tied
to particular boards, so no portable applications should be affected,
and this should prevent future tying to particular boards.
The following differences remain:
* No model_name is printed, as this cannot be queried from the hardware
and cannot be provided in a stable fashion. Use of the CPU
{implementor,variant,part,revision} fields is sufficient to identify a
CPU and is portable across arm and arm64.
* The following system-wide properties are not provided, as they are not
possible to provide generally. Programs relying on these are already
tied to particular (32-bit only) boards:
- Hardware
- Revision
- Serial
No software has yet been identified for which these remaining
differences are problematic.
Cc: Greg Hackmann <ghackmann@google.com>
Cc: Ian Campbell <ijc@hellion.org.uk>
Cc: Serban Constantinescu <serban.constantinescu@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: cross-distro@lists.linaro.org
Cc: linux-api@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
2014-10-24 21:56:40 +08:00
|
|
|
dump_stack_set_arch_desc("%s (DT)", of_flat_dt_get_machine_name());
|
2012-03-05 19:49:27 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static void __init request_standard_resources(void)
|
|
|
|
{
|
|
|
|
struct memblock_region *region;
|
|
|
|
struct resource *res;
|
|
|
|
|
|
|
|
kernel_code.start = virt_to_phys(_text);
|
arm64: mm: fix location of _etext
As Kees Cook notes in the ARM counterpart of this patch [0]:
The _etext position is defined to be the end of the kernel text code,
and should not include any part of the data segments. This interferes
with things that might check memory ranges and expect executable code
up to _etext.
In particular, Kees is referring to the HARDENED_USERCOPY patch set [1],
which rejects attempts to call copy_to_user() on kernel ranges containing
executable code, but does allow access to the .rodata segment. Regardless
of whether one may or may not agree with the distinction, it makes sense
for _etext to have the same meaning across architectures.
So let's put _etext where it belongs, between .text and .rodata, and fix
up existing references to use __init_begin instead, which unlike _end_rodata
includes the exception and notes sections as well.
The _etext references in kaslr.c are left untouched, since its references
to [_stext, _etext) are meant to capture potential jump instruction targets,
and so disregarding .rodata is actually an improvement here.
[0] http://article.gmane.org/gmane.linux.kernel/2245084
[1] http://thread.gmane.org/gmane.linux.kernel.hardened.devel/2502
Reported-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-06-23 21:53:17 +08:00
|
|
|
kernel_code.end = virt_to_phys(__init_begin - 1);
|
2012-03-05 19:49:27 +08:00
|
|
|
kernel_data.start = virt_to_phys(_sdata);
|
|
|
|
kernel_data.end = virt_to_phys(_end - 1);
|
|
|
|
|
|
|
|
for_each_memblock(memory, region) {
|
|
|
|
res = alloc_bootmem_low(sizeof(*res));
|
2016-08-22 14:55:24 +08:00
|
|
|
if (memblock_is_nomap(region)) {
|
|
|
|
res->name = "reserved";
|
|
|
|
res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
|
|
|
|
} else {
|
|
|
|
res->name = "System RAM";
|
|
|
|
res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
|
|
|
|
}
|
2012-03-05 19:49:27 +08:00
|
|
|
res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
|
|
|
|
res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
|
|
|
|
|
|
|
|
request_resource(&iomem_resource, res);
|
|
|
|
|
|
|
|
if (kernel_code.start >= res->start &&
|
|
|
|
kernel_code.end <= res->end)
|
|
|
|
request_resource(res, &kernel_code);
|
|
|
|
if (kernel_data.start >= res->start &&
|
|
|
|
kernel_data.end <= res->end)
|
|
|
|
request_resource(res, &kernel_data);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2012-08-29 16:47:19 +08:00
|
|
|
u64 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };
|
|
|
|
|
2012-03-05 19:49:27 +08:00
|
|
|
void __init setup_arch(char **cmdline_p)
|
|
|
|
{
|
2015-10-19 21:24:40 +08:00
|
|
|
pr_info("Boot CPU: AArch64 Processor [%08x]\n", read_cpuid_id());
|
2012-03-05 19:49:27 +08:00
|
|
|
|
2015-10-19 21:24:40 +08:00
|
|
|
sprintf(init_utsname()->machine, ELF_PLATFORM);
|
2012-03-05 19:49:27 +08:00
|
|
|
init_mm.start_code = (unsigned long) _text;
|
|
|
|
init_mm.end_code = (unsigned long) _etext;
|
|
|
|
init_mm.end_data = (unsigned long) _edata;
|
|
|
|
init_mm.brk = (unsigned long) _end;
|
|
|
|
|
|
|
|
*cmdline_p = boot_command_line;
|
|
|
|
|
2014-11-22 05:50:42 +08:00
|
|
|
early_fixmap_init();
|
2014-04-08 06:39:52 +08:00
|
|
|
early_ioremap_init();
|
2014-04-08 06:39:51 +08:00
|
|
|
|
2015-06-01 19:40:32 +08:00
|
|
|
setup_machine_fdt(__fdt_pointer);
|
|
|
|
|
2012-03-05 19:49:27 +08:00
|
|
|
parse_early_param();
|
|
|
|
|
2014-08-27 04:23:38 +08:00
|
|
|
/*
|
|
|
|
* Unmask asynchronous aborts after bringing up possible earlycon.
|
|
|
|
* (Report possible System Errors once we can report this occurred)
|
|
|
|
*/
|
|
|
|
local_async_enable();
|
|
|
|
|
2016-01-25 19:44:59 +08:00
|
|
|
/*
|
|
|
|
* TTBR0 is only used for the identity mapping at this stage. Make it
|
|
|
|
* point to zero page to avoid speculatively fetching new entries.
|
|
|
|
*/
|
|
|
|
cpu_uninstall_idmap();
|
|
|
|
|
2016-04-07 20:03:28 +08:00
|
|
|
xen_early_init();
|
2014-04-16 09:59:30 +08:00
|
|
|
efi_init();
|
2012-03-05 19:49:27 +08:00
|
|
|
arm64_memblock_init();
|
|
|
|
|
2016-06-20 18:56:13 +08:00
|
|
|
paging_init();
|
|
|
|
|
|
|
|
acpi_table_upgrade();
|
|
|
|
|
ARM64 / ACPI: Get RSDP and ACPI boot-time tables
As we want to get ACPI tables to parse and then use the information
for system initialization, we should get the RSDP (Root System
Description Pointer) first, it then locates Extended Root Description
Table (XSDT) which contains all the 64-bit physical address that
pointer to other boot-time tables.
Introduce acpi.c and its related head file in this patch to provide
fundamental needs of extern variables and functions for ACPI core,
and then get boot-time tables as needed.
- asm/acenv.h for arch specific ACPICA environments and
implementation, It is needed unconditionally by ACPI core;
- asm/acpi.h for arch specific variables and functions needed by
ACPI driver core;
- acpi.c for ARM64 related ACPI implementation for ACPI driver
core;
acpi_boot_table_init() is introduced to get RSDP and boot-time tables,
it will be called in setup_arch() before paging_init(), so we should
use eary_memremap() mechanism here to get the RSDP and all the table
pointers.
FADT Major.Minor version was introduced in ACPI 5.1, it is the same
as ACPI version.
In ACPI 5.1, some major gaps are fixed for ARM, such as updates in
MADT table for GIC and SMP init, without those updates, we can not
get the MPIDR for SMP init, and GICv2/3 related init information, so
we can't boot arm64 ACPI properly with table versions predating 5.1.
If firmware provides ACPI tables with ACPI version less than 5.1,
OS has no way to retrieve the configuration data that is necessary
to init SMP boot protocol and the GIC properly, so disable ACPI if
we get an FADT table with version less that 5.1 when acpi_boot_table_init()
called.
CC: Catalin Marinas <catalin.marinas@arm.com>
CC: Will Deacon <will.deacon@arm.com>
CC: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Tested-by: Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com>
Tested-by: Yijing Wang <wangyijing@huawei.com>
Tested-by: Mark Langsdorf <mlangsdo@redhat.com>
Tested-by: Jon Masters <jcm@redhat.com>
Tested-by: Timur Tabi <timur@codeaurora.org>
Tested-by: Robert Richter <rrichter@cavium.com>
Acked-by: Robert Richter <rrichter@cavium.com>
Acked-by: Olof Johansson <olof@lixom.net>
Acked-by: Grant Likely <grant.likely@linaro.org>
Signed-off-by: Al Stone <al.stone@linaro.org>
Signed-off-by: Graeme Gregory <graeme.gregory@linaro.org>
Signed-off-by: Tomasz Nowicki <tomasz.nowicki@linaro.org>
Signed-off-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
2015-03-24 22:02:37 +08:00
|
|
|
/* Parse the ACPI tables for possible boot-time configuration */
|
|
|
|
acpi_boot_table_init();
|
|
|
|
|
2016-04-09 06:50:26 +08:00
|
|
|
if (acpi_disabled)
|
|
|
|
unflatten_device_tree();
|
|
|
|
|
|
|
|
bootmem_init();
|
|
|
|
|
2015-10-12 23:52:58 +08:00
|
|
|
kasan_init();
|
|
|
|
|
2012-03-05 19:49:27 +08:00
|
|
|
request_standard_resources();
|
|
|
|
|
2015-01-08 17:54:58 +08:00
|
|
|
early_ioremap_reset();
|
2014-04-16 09:59:30 +08:00
|
|
|
|
2016-04-09 06:50:26 +08:00
|
|
|
if (acpi_disabled)
|
2015-03-24 22:02:43 +08:00
|
|
|
psci_dt_init();
|
2016-04-09 06:50:26 +08:00
|
|
|
else
|
2015-03-24 22:02:43 +08:00
|
|
|
psci_acpi_init();
|
2016-04-09 06:50:26 +08:00
|
|
|
|
2015-05-13 21:12:47 +08:00
|
|
|
cpu_read_bootcpu_ops();
|
|
|
|
smp_init_cpus();
|
arm64: kernel: build MPIDR_EL1 hash function data structure
On ARM64 SMP systems, cores are identified by their MPIDR_EL1 register.
The MPIDR_EL1 guidelines in the ARM ARM do not provide strict enforcement of
MPIDR_EL1 layout, only recommendations that, if followed, split the MPIDR_EL1
on ARM 64 bit platforms in four affinity levels. In multi-cluster
systems like big.LITTLE, if the affinity guidelines are followed, the
MPIDR_EL1 can not be considered a linear index. This means that the
association between logical CPU in the kernel and the HW CPU identifier
becomes somewhat more complicated requiring methods like hashing to
associate a given MPIDR_EL1 to a CPU logical index, in order for the look-up
to be carried out in an efficient and scalable way.
This patch provides a function in the kernel that starting from the
cpu_logical_map, implement collision-free hashing of MPIDR_EL1 values by
checking all significative bits of MPIDR_EL1 affinity level bitfields.
The hashing can then be carried out through bits shifting and ORing; the
resulting hash algorithm is a collision-free though not minimal hash that can
be executed with few assembly instructions. The mpidr_el1 is filtered through a
mpidr mask that is built by checking all bits that toggle in the set of
MPIDR_EL1s corresponding to possible CPUs. Bits that do not toggle do not
carry information so they do not contribute to the resulting hash.
Pseudo code:
/* check all bits that toggle, so they are required */
for (i = 1, mpidr_el1_mask = 0; i < num_possible_cpus(); i++)
mpidr_el1_mask |= (cpu_logical_map(i) ^ cpu_logical_map(0));
/*
* Build shifts to be applied to aff0, aff1, aff2, aff3 values to hash the
* mpidr_el1
* fls() returns the last bit set in a word, 0 if none
* ffs() returns the first bit set in a word, 0 if none
*/
fs0 = mpidr_el1_mask[7:0] ? ffs(mpidr_el1_mask[7:0]) - 1 : 0;
fs1 = mpidr_el1_mask[15:8] ? ffs(mpidr_el1_mask[15:8]) - 1 : 0;
fs2 = mpidr_el1_mask[23:16] ? ffs(mpidr_el1_mask[23:16]) - 1 : 0;
fs3 = mpidr_el1_mask[39:32] ? ffs(mpidr_el1_mask[39:32]) - 1 : 0;
ls0 = fls(mpidr_el1_mask[7:0]);
ls1 = fls(mpidr_el1_mask[15:8]);
ls2 = fls(mpidr_el1_mask[23:16]);
ls3 = fls(mpidr_el1_mask[39:32]);
bits0 = ls0 - fs0;
bits1 = ls1 - fs1;
bits2 = ls2 - fs2;
bits3 = ls3 - fs3;
aff0_shift = fs0;
aff1_shift = 8 + fs1 - bits0;
aff2_shift = 16 + fs2 - (bits0 + bits1);
aff3_shift = 32 + fs3 - (bits0 + bits1 + bits2);
u32 hash(u64 mpidr_el1) {
u32 l[4];
u64 mpidr_el1_masked = mpidr_el1 & mpidr_el1_mask;
l[0] = mpidr_el1_masked & 0xff;
l[1] = mpidr_el1_masked & 0xff00;
l[2] = mpidr_el1_masked & 0xff0000;
l[3] = mpidr_el1_masked & 0xff00000000;
return (l[0] >> aff0_shift | l[1] >> aff1_shift | l[2] >> aff2_shift |
l[3] >> aff3_shift);
}
The hashing algorithm relies on the inherent properties set in the ARM ARM
recommendations for the MPIDR_EL1. Exotic configurations, where for instance
the MPIDR_EL1 values at a given affinity level have large holes, can end up
requiring big hash tables since the compression of values that can be achieved
through shifting is somewhat crippled when holes are present. Kernel warns if
the number of buckets of the resulting hash table exceeds the number of
possible CPUs by a factor of 4, which is a symptom of a very sparse HW
MPIDR_EL1 configuration.
The hash algorithm is quite simple and can easily be implemented in assembly
code, to be used in code paths where the kernel virtual address space is
not set-up (ie cpu_resume) and instruction and data fetches are strongly
ordered so code must be compact and must carry out few data accesses.
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
2013-05-16 17:32:09 +08:00
|
|
|
smp_build_mpidr_hash();
|
2012-03-05 19:49:27 +08:00
|
|
|
|
|
|
|
#ifdef CONFIG_VT
|
|
|
|
#if defined(CONFIG_VGA_CONSOLE)
|
|
|
|
conswitchp = &vga_con;
|
|
|
|
#elif defined(CONFIG_DUMMY_CONSOLE)
|
|
|
|
conswitchp = &dummy_con;
|
|
|
|
#endif
|
|
|
|
#endif
|
2015-03-17 17:55:12 +08:00
|
|
|
if (boot_args[1] || boot_args[2] || boot_args[3]) {
|
|
|
|
pr_err("WARNING: x1-x3 nonzero in violation of boot protocol:\n"
|
|
|
|
"\tx1: %016llx\n\tx2: %016llx\n\tx3: %016llx\n"
|
|
|
|
"This indicates a broken bootloader or old kernel\n",
|
|
|
|
boot_args[1], boot_args[2], boot_args[3]);
|
|
|
|
}
|
2012-03-05 19:49:27 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static int __init topology_init(void)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
2016-04-09 06:50:27 +08:00
|
|
|
for_each_online_node(i)
|
|
|
|
register_one_node(i);
|
|
|
|
|
2012-03-05 19:49:27 +08:00
|
|
|
for_each_possible_cpu(i) {
|
2014-07-16 23:32:44 +08:00
|
|
|
struct cpu *cpu = &per_cpu(cpu_data.cpu, i);
|
2012-03-05 19:49:27 +08:00
|
|
|
cpu->hotpluggable = 1;
|
|
|
|
register_cpu(cpu, i);
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
subsys_initcall(topology_init);
|
arm64: add support for kernel ASLR
This adds support for KASLR is implemented, based on entropy provided by
the bootloader in the /chosen/kaslr-seed DT property. Depending on the size
of the address space (VA_BITS) and the page size, the entropy in the
virtual displacement is up to 13 bits (16k/2 levels) and up to 25 bits (all
4 levels), with the sidenote that displacements that result in the kernel
image straddling a 1GB/32MB/512MB alignment boundary (for 4KB/16KB/64KB
granule kernels, respectively) are not allowed, and will be rounded up to
an acceptable value.
If CONFIG_RANDOMIZE_MODULE_REGION_FULL is enabled, the module region is
randomized independently from the core kernel. This makes it less likely
that the location of core kernel data structures can be determined by an
adversary, but causes all function calls from modules into the core kernel
to be resolved via entries in the module PLTs.
If CONFIG_RANDOMIZE_MODULE_REGION_FULL is not enabled, the module region is
randomized by choosing a page aligned 128 MB region inside the interval
[_etext - 128 MB, _stext + 128 MB). This gives between 10 and 14 bits of
entropy (depending on page size), independently of the kernel randomization,
but still guarantees that modules are within the range of relative branch
and jump instructions (with the caveat that, since the module region is
shared with other uses of the vmalloc area, modules may need to be loaded
further away if the module region is exhausted)
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2016-01-26 21:12:01 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Dump out kernel offset information on panic.
|
|
|
|
*/
|
|
|
|
static int dump_kernel_offset(struct notifier_block *self, unsigned long v,
|
|
|
|
void *p)
|
|
|
|
{
|
|
|
|
u64 const kaslr_offset = kimage_vaddr - KIMAGE_VADDR;
|
|
|
|
|
|
|
|
if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_offset > 0) {
|
|
|
|
pr_emerg("Kernel Offset: 0x%llx from 0x%lx\n",
|
|
|
|
kaslr_offset, KIMAGE_VADDR);
|
|
|
|
} else {
|
|
|
|
pr_emerg("Kernel Offset: disabled\n");
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct notifier_block kernel_offset_notifier = {
|
|
|
|
.notifier_call = dump_kernel_offset
|
|
|
|
};
|
|
|
|
|
|
|
|
static int __init register_kernel_offset_dumper(void)
|
|
|
|
{
|
|
|
|
atomic_notifier_chain_register(&panic_notifier_list,
|
|
|
|
&kernel_offset_notifier);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
__initcall(register_kernel_offset_dumper);
|