mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-16 07:46:51 +07:00
145ff1ec09
- Removal of the tremendously unpopular read_barrier_depends() barrier, which is a NOP on all architectures apart from Alpha, in favour of allowing architectures to override READ_ONCE() and do whatever dance they need to do to ensure address dependencies provide LOAD -> LOAD/STORE ordering. This work also offers a potential solution if compilers are shown to convert LOAD -> LOAD address dependencies into control dependencies (e.g. under LTO), as weakly ordered architectures will effectively be able to upgrade READ_ONCE() to smp_load_acquire(). The latter case is not used yet, but will be discussed further at LPC. - Make the MSI/IOMMU input/output ID translation PCI agnostic, augment the MSI/IOMMU ACPI/OF ID mapping APIs to accept an input ID bus-specific parameter and apply the resulting changes to the device ID space provided by the Freescale FSL bus. - arm64 support for TLBI range operations and translation table level hints (part of the ARMv8.4 architecture version). - Time namespace support for arm64. - Export the virtual and physical address sizes in vmcoreinfo for makedumpfile and crash utilities. - CPU feature handling cleanups and checks for programmer errors (overlapping bit-fields). - ACPI updates for arm64: disallow AML accesses to EFI code regions and kernel memory. - perf updates for arm64. - Miscellaneous fixes and cleanups, most notably PLT counting optimisation for module loading, recordmcount fix to ignore relocations other than R_AARCH64_CALL26, CMA areas reserved for gigantic pages on 16K and 64K configurations. - Trivial typos, duplicate words. -----BEGIN PGP SIGNATURE----- iQIzBAABCgAdFiEE5RElWfyWxS+3PLO2a9axLQDIXvEFAl8oTcsACgkQa9axLQDI XvEj6hAAkn39mO5xrR/Vhpg3DyFPk63ZlMSX9SsOeVyaLbovT6stTs1XAZXPpnkt rV3gwACyGSrqH6+uey9pHgHJuPF2TdrGEVK08yVKo9KGW/6yXSIncdKFE4jUJ/WJ wF5j7eMET2aGzcpm5AlzMmq6HOrKB8nZac9H8/x6H+Ox2WdgJkEjOkDvyqACUyum N3FsTZkWj2pIkTXHNgDZ8KjxVLO8HlFaB2hkxFDl9NPlX2UTCQJ8Tg1KiPLafKaK gUvH4usQDFdb5RU/UWogre37J4emO0ZTApZOyju+U+PMMWlWVHjZ4isUIS9zz/AE JNZ23dnKZX2HrYa5p8HZx175zwj/vXUqUHCZPLvQXaAudCEhF8BVljPiG0e80FV5 GHFUgUbylKspp01I/9L+2JvsG96Mr0e+P3Sx7L2HTI42cmtoSa14+MpoSRj7zlft Qcl8hfrVOjCjUnFRHa/1y1cGvnD9GbgnKJR7zgVxl9bD/Jd48r1HUtwRORZCzWFr mRPVbPS72fWxMzMV9DZYJm02jJY9kLX2BMl49njbB8MhAhzOvrMVzoVVtMMeRFLR XHeJpmg36W09FiRGe7LRXlkXIhCQzQG2bJfiphuupCfhjRAitPoq8I925G6Pig60 c8RWaXGU7PrEsdMNrL83vekvGKgqrkoFkRVtsCoQ2X6Hvu/XdYI= =mh79 -----END PGP SIGNATURE----- Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux Pull arm64 and cross-arch updates from Catalin Marinas: "Here's a slightly wider-spread set of updates for 5.9. Going outside the usual arch/arm64/ area is the removal of read_barrier_depends() series from Will and the MSI/IOMMU ID translation series from Lorenzo. The notable arm64 updates include ARMv8.4 TLBI range operations and translation level hint, time namespace support, and perf. Summary: - Removal of the tremendously unpopular read_barrier_depends() barrier, which is a NOP on all architectures apart from Alpha, in favour of allowing architectures to override READ_ONCE() and do whatever dance they need to do to ensure address dependencies provide LOAD -> LOAD/STORE ordering. This work also offers a potential solution if compilers are shown to convert LOAD -> LOAD address dependencies into control dependencies (e.g. under LTO), as weakly ordered architectures will effectively be able to upgrade READ_ONCE() to smp_load_acquire(). The latter case is not used yet, but will be discussed further at LPC. - Make the MSI/IOMMU input/output ID translation PCI agnostic, augment the MSI/IOMMU ACPI/OF ID mapping APIs to accept an input ID bus-specific parameter and apply the resulting changes to the device ID space provided by the Freescale FSL bus. - arm64 support for TLBI range operations and translation table level hints (part of the ARMv8.4 architecture version). - Time namespace support for arm64. - Export the virtual and physical address sizes in vmcoreinfo for makedumpfile and crash utilities. - CPU feature handling cleanups and checks for programmer errors (overlapping bit-fields). - ACPI updates for arm64: disallow AML accesses to EFI code regions and kernel memory. - perf updates for arm64. - Miscellaneous fixes and cleanups, most notably PLT counting optimisation for module loading, recordmcount fix to ignore relocations other than R_AARCH64_CALL26, CMA areas reserved for gigantic pages on 16K and 64K configurations. - Trivial typos, duplicate words" Link: http://lkml.kernel.org/r/20200710165203.31284-1-will@kernel.org Link: http://lkml.kernel.org/r/20200619082013.13661-1-lorenzo.pieralisi@arm.com * tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (82 commits) arm64: use IRQ_STACK_SIZE instead of THREAD_SIZE for irq stack arm64/mm: save memory access in check_and_switch_context() fast switch path arm64: sigcontext.h: delete duplicated word arm64: ptrace.h: delete duplicated word arm64: pgtable-hwdef.h: delete duplicated words bus: fsl-mc: Add ACPI support for fsl-mc bus/fsl-mc: Refactor the MSI domain creation in the DPRC driver of/irq: Make of_msi_map_rid() PCI bus agnostic of/irq: make of_msi_map_get_device_domain() bus agnostic dt-bindings: arm: fsl: Add msi-map device-tree binding for fsl-mc bus of/device: Add input id to of_dma_configure() of/iommu: Make of_map_rid() PCI agnostic ACPI/IORT: Add an input ID to acpi_dma_configure() ACPI/IORT: Remove useless PCI bus walk ACPI/IORT: Make iort_msi_map_rid() PCI agnostic ACPI/IORT: Make iort_get_device_domain IRQ domain agnostic ACPI/IORT: Make iort_match_node_callback walk the ACPI namespace for NC arm64: enable time namespace support arm64/vdso: Restrict splitting VVAR VMA arm64/vdso: Handle faults on timens page ...
168 lines
3.7 KiB
ArmAsm
168 lines
3.7 KiB
ArmAsm
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
* Copyright (C) 2012,2013 - ARM Ltd
|
|
* Author: Marc Zyngier <marc.zyngier@arm.com>
|
|
*/
|
|
|
|
#include <linux/linkage.h>
|
|
|
|
#include <asm/alternative.h>
|
|
#include <asm/assembler.h>
|
|
#include <asm/kvm_arm.h>
|
|
#include <asm/kvm_mmu.h>
|
|
#include <asm/pgtable-hwdef.h>
|
|
#include <asm/sysreg.h>
|
|
#include <asm/virt.h>
|
|
|
|
.text
|
|
.pushsection .hyp.idmap.text, "ax"
|
|
|
|
.align 11
|
|
|
|
SYM_CODE_START(__kvm_hyp_init)
|
|
ventry __invalid // Synchronous EL2t
|
|
ventry __invalid // IRQ EL2t
|
|
ventry __invalid // FIQ EL2t
|
|
ventry __invalid // Error EL2t
|
|
|
|
ventry __invalid // Synchronous EL2h
|
|
ventry __invalid // IRQ EL2h
|
|
ventry __invalid // FIQ EL2h
|
|
ventry __invalid // Error EL2h
|
|
|
|
ventry __do_hyp_init // Synchronous 64-bit EL1
|
|
ventry __invalid // IRQ 64-bit EL1
|
|
ventry __invalid // FIQ 64-bit EL1
|
|
ventry __invalid // Error 64-bit EL1
|
|
|
|
ventry __invalid // Synchronous 32-bit EL1
|
|
ventry __invalid // IRQ 32-bit EL1
|
|
ventry __invalid // FIQ 32-bit EL1
|
|
ventry __invalid // Error 32-bit EL1
|
|
|
|
__invalid:
|
|
b .
|
|
|
|
/*
|
|
* x0: HYP pgd
|
|
* x1: HYP stack
|
|
* x2: HYP vectors
|
|
* x3: per-CPU offset
|
|
*/
|
|
__do_hyp_init:
|
|
/* Check for a stub HVC call */
|
|
cmp x0, #HVC_STUB_HCALL_NR
|
|
b.lo __kvm_handle_stub_hvc
|
|
|
|
phys_to_ttbr x4, x0
|
|
alternative_if ARM64_HAS_CNP
|
|
orr x4, x4, #TTBR_CNP_BIT
|
|
alternative_else_nop_endif
|
|
msr ttbr0_el2, x4
|
|
|
|
mrs x4, tcr_el1
|
|
mov_q x5, TCR_EL2_MASK
|
|
and x4, x4, x5
|
|
mov x5, #TCR_EL2_RES1
|
|
orr x4, x4, x5
|
|
|
|
/*
|
|
* The ID map may be configured to use an extended virtual address
|
|
* range. This is only the case if system RAM is out of range for the
|
|
* currently configured page size and VA_BITS, in which case we will
|
|
* also need the extended virtual range for the HYP ID map, or we won't
|
|
* be able to enable the EL2 MMU.
|
|
*
|
|
* However, at EL2, there is only one TTBR register, and we can't switch
|
|
* between translation tables *and* update TCR_EL2.T0SZ at the same
|
|
* time. Bottom line: we need to use the extended range with *both* our
|
|
* translation tables.
|
|
*
|
|
* So use the same T0SZ value we use for the ID map.
|
|
*/
|
|
ldr_l x5, idmap_t0sz
|
|
bfi x4, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
|
|
|
|
/*
|
|
* Set the PS bits in TCR_EL2.
|
|
*/
|
|
tcr_compute_pa_size x4, #TCR_EL2_PS_SHIFT, x5, x6
|
|
|
|
msr tcr_el2, x4
|
|
|
|
mrs x4, mair_el1
|
|
msr mair_el2, x4
|
|
isb
|
|
|
|
/* Invalidate the stale TLBs from Bootloader */
|
|
tlbi alle2
|
|
dsb sy
|
|
|
|
/*
|
|
* Preserve all the RES1 bits while setting the default flags,
|
|
* as well as the EE bit on BE. Drop the A flag since the compiler
|
|
* is allowed to generate unaligned accesses.
|
|
*/
|
|
mov_q x4, (SCTLR_EL2_RES1 | (SCTLR_ELx_FLAGS & ~SCTLR_ELx_A))
|
|
CPU_BE( orr x4, x4, #SCTLR_ELx_EE)
|
|
msr sctlr_el2, x4
|
|
isb
|
|
|
|
/* Set the stack and new vectors */
|
|
kern_hyp_va x1
|
|
mov sp, x1
|
|
msr vbar_el2, x2
|
|
|
|
/* Set tpidr_el2 for use by HYP */
|
|
msr tpidr_el2, x3
|
|
|
|
/* Hello, World! */
|
|
eret
|
|
SYM_CODE_END(__kvm_hyp_init)
|
|
|
|
SYM_CODE_START(__kvm_handle_stub_hvc)
|
|
cmp x0, #HVC_SOFT_RESTART
|
|
b.ne 1f
|
|
|
|
/* This is where we're about to jump, staying at EL2 */
|
|
msr elr_el2, x1
|
|
mov x0, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT | PSR_MODE_EL2h)
|
|
msr spsr_el2, x0
|
|
|
|
/* Shuffle the arguments, and don't come back */
|
|
mov x0, x2
|
|
mov x1, x3
|
|
mov x2, x4
|
|
b reset
|
|
|
|
1: cmp x0, #HVC_RESET_VECTORS
|
|
b.ne 1f
|
|
|
|
/*
|
|
* Set the HVC_RESET_VECTORS return code before entering the common
|
|
* path so that we do not clobber x0-x2 in case we are coming via
|
|
* HVC_SOFT_RESTART.
|
|
*/
|
|
mov x0, xzr
|
|
reset:
|
|
/* Reset kvm back to the hyp stub. */
|
|
mrs x5, sctlr_el2
|
|
mov_q x6, SCTLR_ELx_FLAGS
|
|
bic x5, x5, x6 // Clear SCTL_M and etc
|
|
pre_disable_mmu_workaround
|
|
msr sctlr_el2, x5
|
|
isb
|
|
|
|
/* Install stub vectors */
|
|
adr_l x5, __hyp_stub_vectors
|
|
msr vbar_el2, x5
|
|
eret
|
|
|
|
1: /* Bad stub call */
|
|
mov_q x0, HVC_STUB_ERR
|
|
eret
|
|
|
|
SYM_CODE_END(__kvm_handle_stub_hvc)
|
|
|
|
.popsection
|