mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-27 02:25:20 +07:00
714d8e7e27
The main change here is a significant head.S rework that allows us to boot on machines with physical memory at a really high address without having to increase our mapped VA range. Other changes include: - AES performance boost for Cortex-A57 - AArch32 (compat) userspace with 64k pages - Cortex-A53 erratum workaround for #845719 - defconfig updates (new platforms, PCI, ...) -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQEcBAABCgAGBQJVLnQpAAoJELescNyEwWM03RIH/iwcDc0MBZgkwfD5cnY+29p4 m89lMDo3SyGQT4NynHSw7P3R7c3zULmI+9hmJMw/yfjjjL6m7X+vVAF3xj1Am4Al OzCqYLHyFnlRktzJ6dWeF1Ese7tWqPpxn+OCXgYNpz/r5MfF/HhlyX/qNzAQPKrw ZpDvnt44DgUfweqjTbwQUg2wkyCRjmz57MQYxDcmJStdpHIu24jWOvDIo3OJGjyS L49I9DU6DGUhkISZmmBE0T7vmKMD1BcgI7OIzX2WIqn521QT+GSLMhRxaHmK1s1V A8gaMTwpo0xFhTAt7sbw/5+2663WmfRdZI+FtduvORsoxX6KdDn7DH1NQixIm8s= =+F0I -----END PGP SIGNATURE----- Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux Pull arm64 updates from Will Deacon: "Here are the core arm64 updates for 4.1. Highlights include a significant rework to head.S (allowing us to boot on machines with physical memory at a really high address), an AES performance boost on Cortex-A57 and the ability to run a 32-bit userspace with 64k pages (although this requires said userspace to be built with a recent binutils). The head.S rework spilt over into KVM, so there are some changes under arch/arm/ which have been acked by Marc Zyngier (KVM co-maintainer). In particular, the linker script changes caused us some issues in -next, so there are a few merge commits where we had to apply fixes on top of a stable branch. Other changes include: - AES performance boost for Cortex-A57 - AArch32 (compat) userspace with 64k pages - Cortex-A53 erratum workaround for #845719 - defconfig updates (new platforms, PCI, ...)" * tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (39 commits) arm64: fix midr range for Cortex-A57 erratum 832075 arm64: errata: add workaround for cortex-a53 erratum #845719 arm64: Use bool function return values of true/false not 1/0 arm64: defconfig: updates for 4.1 arm64: Extract feature parsing code from cpu_errata.c arm64: alternative: Allow immediate branch as alternative instruction arm64: insn: Add aarch64_insn_decode_immediate ARM: kvm: round HYP section to page size instead of log2 upper bound ARM: kvm: assert on HYP section boundaries not actual code size arm64: head.S: ensure idmap_t0sz is visible arm64: pmu: add support for interrupt-affinity property dt: pmu: extend ARM PMU binding to allow for explicit interrupt affinity arm64: head.S: ensure visibility of page tables arm64: KVM: use ID map with increased VA range if required arm64: mm: increase VA range of identity map ARM: kvm: implement replacement for ld's LOG2CEIL() arm64: proc: remove unused cpu_get_pgd macro arm64: enforce x1|x2|x3 == 0 upon kernel entry as per boot protocol arm64: remove __calc_phys_offset arm64: merge __enable_mmu and __turn_mmu_on ...
214 lines
5.2 KiB
C
214 lines
5.2 KiB
C
/*
|
|
* Based on arch/arm/include/asm/mmu_context.h
|
|
*
|
|
* Copyright (C) 1996 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/>.
|
|
*/
|
|
#ifndef __ASM_MMU_CONTEXT_H
|
|
#define __ASM_MMU_CONTEXT_H
|
|
|
|
#include <linux/compiler.h>
|
|
#include <linux/sched.h>
|
|
|
|
#include <asm/cacheflush.h>
|
|
#include <asm/proc-fns.h>
|
|
#include <asm-generic/mm_hooks.h>
|
|
#include <asm/cputype.h>
|
|
#include <asm/pgtable.h>
|
|
|
|
#define MAX_ASID_BITS 16
|
|
|
|
extern unsigned int cpu_last_asid;
|
|
|
|
void __init_new_context(struct task_struct *tsk, struct mm_struct *mm);
|
|
void __new_context(struct mm_struct *mm);
|
|
|
|
#ifdef CONFIG_PID_IN_CONTEXTIDR
|
|
static inline void contextidr_thread_switch(struct task_struct *next)
|
|
{
|
|
asm(
|
|
" msr contextidr_el1, %0\n"
|
|
" isb"
|
|
:
|
|
: "r" (task_pid_nr(next)));
|
|
}
|
|
#else
|
|
static inline void contextidr_thread_switch(struct task_struct *next)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* Set TTBR0 to empty_zero_page. No translations will be possible via TTBR0.
|
|
*/
|
|
static inline void cpu_set_reserved_ttbr0(void)
|
|
{
|
|
unsigned long ttbr = page_to_phys(empty_zero_page);
|
|
|
|
asm(
|
|
" msr ttbr0_el1, %0 // set TTBR0\n"
|
|
" isb"
|
|
:
|
|
: "r" (ttbr));
|
|
}
|
|
|
|
/*
|
|
* TCR.T0SZ value to use when the ID map is active. Usually equals
|
|
* TCR_T0SZ(VA_BITS), unless system RAM is positioned very high in
|
|
* physical memory, in which case it will be smaller.
|
|
*/
|
|
extern u64 idmap_t0sz;
|
|
|
|
static inline bool __cpu_uses_extended_idmap(void)
|
|
{
|
|
return (!IS_ENABLED(CONFIG_ARM64_VA_BITS_48) &&
|
|
unlikely(idmap_t0sz != TCR_T0SZ(VA_BITS)));
|
|
}
|
|
|
|
static inline void __cpu_set_tcr_t0sz(u64 t0sz)
|
|
{
|
|
unsigned long tcr;
|
|
|
|
if (__cpu_uses_extended_idmap())
|
|
asm volatile (
|
|
" mrs %0, tcr_el1 ;"
|
|
" bfi %0, %1, %2, %3 ;"
|
|
" msr tcr_el1, %0 ;"
|
|
" isb"
|
|
: "=&r" (tcr)
|
|
: "r"(t0sz), "I"(TCR_T0SZ_OFFSET), "I"(TCR_TxSZ_WIDTH));
|
|
}
|
|
|
|
/*
|
|
* Set TCR.T0SZ to the value appropriate for activating the identity map.
|
|
*/
|
|
static inline void cpu_set_idmap_tcr_t0sz(void)
|
|
{
|
|
__cpu_set_tcr_t0sz(idmap_t0sz);
|
|
}
|
|
|
|
/*
|
|
* Set TCR.T0SZ to its default value (based on VA_BITS)
|
|
*/
|
|
static inline void cpu_set_default_tcr_t0sz(void)
|
|
{
|
|
__cpu_set_tcr_t0sz(TCR_T0SZ(VA_BITS));
|
|
}
|
|
|
|
static inline void switch_new_context(struct mm_struct *mm)
|
|
{
|
|
unsigned long flags;
|
|
|
|
__new_context(mm);
|
|
|
|
local_irq_save(flags);
|
|
cpu_switch_mm(mm->pgd, mm);
|
|
local_irq_restore(flags);
|
|
}
|
|
|
|
static inline void check_and_switch_context(struct mm_struct *mm,
|
|
struct task_struct *tsk)
|
|
{
|
|
/*
|
|
* Required during context switch to avoid speculative page table
|
|
* walking with the wrong TTBR.
|
|
*/
|
|
cpu_set_reserved_ttbr0();
|
|
|
|
if (!((mm->context.id ^ cpu_last_asid) >> MAX_ASID_BITS))
|
|
/*
|
|
* The ASID is from the current generation, just switch to the
|
|
* new pgd. This condition is only true for calls from
|
|
* context_switch() and interrupts are already disabled.
|
|
*/
|
|
cpu_switch_mm(mm->pgd, mm);
|
|
else if (irqs_disabled())
|
|
/*
|
|
* Defer the new ASID allocation until after the context
|
|
* switch critical region since __new_context() cannot be
|
|
* called with interrupts disabled.
|
|
*/
|
|
set_ti_thread_flag(task_thread_info(tsk), TIF_SWITCH_MM);
|
|
else
|
|
/*
|
|
* That is a direct call to switch_mm() or activate_mm() with
|
|
* interrupts enabled and a new context.
|
|
*/
|
|
switch_new_context(mm);
|
|
}
|
|
|
|
#define init_new_context(tsk,mm) (__init_new_context(tsk,mm),0)
|
|
#define destroy_context(mm) do { } while(0)
|
|
|
|
#define finish_arch_post_lock_switch \
|
|
finish_arch_post_lock_switch
|
|
static inline void finish_arch_post_lock_switch(void)
|
|
{
|
|
if (test_and_clear_thread_flag(TIF_SWITCH_MM)) {
|
|
struct mm_struct *mm = current->mm;
|
|
unsigned long flags;
|
|
|
|
__new_context(mm);
|
|
|
|
local_irq_save(flags);
|
|
cpu_switch_mm(mm->pgd, mm);
|
|
local_irq_restore(flags);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* This is called when "tsk" is about to enter lazy TLB mode.
|
|
*
|
|
* mm: describes the currently active mm context
|
|
* tsk: task which is entering lazy tlb
|
|
* cpu: cpu number which is entering lazy tlb
|
|
*
|
|
* tsk->mm will be NULL
|
|
*/
|
|
static inline void
|
|
enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
|
|
{
|
|
}
|
|
|
|
/*
|
|
* This is the actual mm switch as far as the scheduler
|
|
* is concerned. No registers are touched. We avoid
|
|
* calling the CPU specific function when the mm hasn't
|
|
* actually changed.
|
|
*/
|
|
static inline void
|
|
switch_mm(struct mm_struct *prev, struct mm_struct *next,
|
|
struct task_struct *tsk)
|
|
{
|
|
unsigned int cpu = smp_processor_id();
|
|
|
|
/*
|
|
* init_mm.pgd does not contain any user mappings and it is always
|
|
* active for kernel addresses in TTBR1. Just set the reserved TTBR0.
|
|
*/
|
|
if (next == &init_mm) {
|
|
cpu_set_reserved_ttbr0();
|
|
return;
|
|
}
|
|
|
|
if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next)
|
|
check_and_switch_context(next, tsk);
|
|
}
|
|
|
|
#define deactivate_mm(tsk,mm) do { } while (0)
|
|
#define activate_mm(prev,next) switch_mm(prev, next, NULL)
|
|
|
|
#endif
|