diff options
Diffstat (limited to 'arch/arm64/kernel/acpi.c')
-rw-r--r-- | arch/arm64/kernel/acpi.c | 173 |
1 files changed, 148 insertions, 25 deletions
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index a100483b47c4..a5a256e3f9fe 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -19,16 +19,18 @@ #include <linux/init.h> #include <linux/irq.h> #include <linux/irqdomain.h> +#include <linux/irq_work.h> #include <linux/memblock.h> #include <linux/of_fdt.h> +#include <linux/libfdt.h> #include <linux/smp.h> #include <linux/serial_core.h> +#include <linux/pgtable.h> #include <acpi/ghes.h> #include <asm/cputype.h> #include <asm/cpu_ops.h> #include <asm/daifflags.h> -#include <asm/pgtable.h> #include <asm/smp_plat.h> int acpi_noirq = 1; /* skip ACPI IRQ initialization */ @@ -61,29 +63,22 @@ static int __init parse_acpi(char *arg) } early_param("acpi", parse_acpi); -static int __init dt_scan_depth1_nodes(unsigned long node, - const char *uname, int depth, - void *data) +static bool __init dt_is_stub(void) { - /* - * Ignore anything not directly under the root node; we'll - * catch its parent instead. - */ - if (depth != 1) - return 0; + int node; - if (strcmp(uname, "chosen") == 0) - return 0; + fdt_for_each_subnode(node, initial_boot_params, 0) { + const char *name = fdt_get_name(initial_boot_params, node, NULL); + if (strcmp(name, "chosen") == 0) + continue; + if (strcmp(name, "hypervisor") == 0 && + of_flat_dt_is_compatible(node, "xen,xen")) + continue; - if (strcmp(uname, "hypervisor") == 0 && - of_flat_dt_is_compatible(node, "xen,xen")) - return 0; + return false; + } - /* - * This node at depth 1 is neither a chosen node nor a xen node, - * which we do not expect. - */ - return 1; + return true; } /* @@ -204,8 +199,7 @@ void __init acpi_boot_table_init(void) * and ACPI has not been [force] enabled (acpi=on|force) */ if (param_acpi_off || - (!param_acpi_on && !param_acpi_force && - of_scan_flat_dt(dt_scan_depth1_nodes, NULL))) + (!param_acpi_on && !param_acpi_force && !dt_is_stub())) goto done; /* @@ -238,6 +232,18 @@ done: } } +static pgprot_t __acpi_get_writethrough_mem_attribute(void) +{ + /* + * Although UEFI specifies the use of Normal Write-through for + * EFI_MEMORY_WT, it is seldom used in practice and not implemented + * by most (all?) CPUs. Rather than allocate a MAIR just for this + * purpose, emit a warning and use Normal Non-cacheable instead. + */ + pr_warn_once("No MAIR allocation for EFI_MEMORY_WT; treating as Normal Non-cacheable\n"); + return __pgprot(PROT_NORMAL_NC); +} + pgprot_t __acpi_get_mem_attribute(phys_addr_t addr) { /* @@ -245,7 +251,7 @@ pgprot_t __acpi_get_mem_attribute(phys_addr_t addr) * types" of UEFI 2.5 section 2.3.6.1, each EFI memory type is * mapped to a corresponding MAIR attribute encoding. * The EFI memory attribute advises all possible capabilities - * of a memory region. We use the most efficient capability. + * of a memory region. */ u64 attr; @@ -253,13 +259,101 @@ pgprot_t __acpi_get_mem_attribute(phys_addr_t addr) attr = efi_mem_attributes(addr); if (attr & EFI_MEMORY_WB) return PAGE_KERNEL; - if (attr & EFI_MEMORY_WT) - return __pgprot(PROT_NORMAL_WT); if (attr & EFI_MEMORY_WC) return __pgprot(PROT_NORMAL_NC); + if (attr & EFI_MEMORY_WT) + return __acpi_get_writethrough_mem_attribute(); return __pgprot(PROT_DEVICE_nGnRnE); } +void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) +{ + efi_memory_desc_t *md, *region = NULL; + pgprot_t prot; + + if (WARN_ON_ONCE(!efi_enabled(EFI_MEMMAP))) + return NULL; + + for_each_efi_memory_desc(md) { + u64 end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT); + + if (phys < md->phys_addr || phys >= end) + continue; + + if (phys + size > end) { + pr_warn(FW_BUG "requested region covers multiple EFI memory regions\n"); + return NULL; + } + region = md; + break; + } + + /* + * It is fine for AML to remap regions that are not represented in the + * EFI memory map at all, as it only describes normal memory, and MMIO + * regions that require a virtual mapping to make them accessible to + * the EFI runtime services. + */ + prot = __pgprot(PROT_DEVICE_nGnRnE); + if (region) { + switch (region->type) { + case EFI_LOADER_CODE: + case EFI_LOADER_DATA: + case EFI_BOOT_SERVICES_CODE: + case EFI_BOOT_SERVICES_DATA: + case EFI_CONVENTIONAL_MEMORY: + case EFI_PERSISTENT_MEMORY: + if (memblock_is_map_memory(phys) || + !memblock_is_region_memory(phys, size)) { + pr_warn(FW_BUG "requested region covers kernel memory @ %pa\n", &phys); + return NULL; + } + /* + * Mapping kernel memory is permitted if the region in + * question is covered by a single memblock with the + * NOMAP attribute set: this enables the use of ACPI + * table overrides passed via initramfs, which are + * reserved in memory using arch_reserve_mem_area() + * below. As this particular use case only requires + * read access, fall through to the R/O mapping case. + */ + fallthrough; + + case EFI_RUNTIME_SERVICES_CODE: + /* + * This would be unusual, but not problematic per se, + * as long as we take care not to create a writable + * mapping for executable code. + */ + prot = PAGE_KERNEL_RO; + break; + + case EFI_ACPI_RECLAIM_MEMORY: + /* + * ACPI reclaim memory is used to pass firmware tables + * and other data that is intended for consumption by + * the OS only, which may decide it wants to reclaim + * that memory and use it for something else. We never + * do that, but we usually add it to the linear map + * anyway, in which case we should use the existing + * mapping. + */ + if (memblock_is_map_memory(phys)) + return (void __iomem *)__phys_to_virt(phys); + fallthrough; + + default: + if (region->attribute & EFI_MEMORY_WB) + prot = PAGE_KERNEL; + else if (region->attribute & EFI_MEMORY_WC) + prot = __pgprot(PROT_NORMAL_NC); + else if (region->attribute & EFI_MEMORY_WT) + prot = __acpi_get_writethrough_mem_attribute(); + } + } + return ioremap_prot(phys, size, pgprot_val(prot)); +} + /* * Claim Synchronous External Aborts as a firmware first notification. * @@ -269,6 +363,7 @@ pgprot_t __acpi_get_mem_attribute(phys_addr_t addr) int apei_claim_sea(struct pt_regs *regs) { int err = -ENOENT; + bool return_to_irqs_enabled; unsigned long current_flags; if (!IS_ENABLED(CONFIG_ACPI_APEI_GHES)) @@ -276,6 +371,12 @@ int apei_claim_sea(struct pt_regs *regs) current_flags = local_daif_save_flags(); + /* current_flags isn't useful here as daif doesn't tell us about pNMI */ + return_to_irqs_enabled = !irqs_disabled_flags(arch_local_save_flags()); + + if (regs) + return_to_irqs_enabled = interrupts_enabled(regs); + /* * SEA can interrupt SError, mask it and describe this as an NMI so * that APEI defers the handling. @@ -284,7 +385,29 @@ int apei_claim_sea(struct pt_regs *regs) nmi_enter(); err = ghes_notify_sea(); nmi_exit(); + + /* + * APEI NMI-like notifications are deferred to irq_work. Unless + * we interrupted irqs-masked code, we can do that now. + */ + if (!err) { + if (return_to_irqs_enabled) { + local_daif_restore(DAIF_PROCCTX_NOIRQ); + __irq_enter(); + irq_work_run(); + __irq_exit(); + } else { + pr_warn_ratelimited("APEI work queued but not completed"); + err = -EINPROGRESS; + } + } + local_daif_restore(current_flags); return err; } + +void arch_reserve_mem_area(acpi_physical_address addr, size_t size) +{ + memblock_mark_nomap(addr, size); +} |