On Mon, Dec 22, 2014 at 10:59:02AM +0000, Ard Biesheuvel wrote:
> In order to support kexec, the kernel needs to be able to deal with the
> state of the UEFI firmware after SetVirtualAddressMap() has been called.
> To avoid having separate code paths for non-kexec and kexec, let's move
> the call to SetVirtualAddressMap() to the stub: this will guarantee us
> that it will only be called once (since the stub is not executed during
> kexec), and ensures that the UEFI state is identical between kexec and
> normal boot.
>
> This implies that the layout of the virtual mapping needs to be created
> by the stub as well. All regions are rounded up to a naturally aligned
> multiple of 64 KB (for compatibility with 64k pages kernels) and recorded
> in the UEFI memory map. The kernel proper reads those values and installs
> the mappings in a dedicated set of page tables that are swapped in during
> UEFI Runtime Services calls.
>
> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@xxxxxxxxxx>
> ---
> arch/arm64/include/asm/efi.h | 20 +++-
> arch/arm64/kernel/efi.c | 223 ++++++++++++++++++++-----------------
> arch/arm64/kernel/setup.c | 1 +
> drivers/firmware/efi/libstub/fdt.c | 137 ++++++++++++++++++++++-
> 4 files changed, 270 insertions(+), 111 deletions(-)
>
> diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
> index 71291253114f..6cc668a378c5 100644
> --- a/arch/arm64/include/asm/efi.h
> +++ b/arch/arm64/include/asm/efi.h
> @@ -7,28 +7,36 @@
> #ifdef CONFIG_EFI
> extern void efi_init(void);
> extern void efi_idmap_init(void);
> +extern void efi_virtmap_init(void);
> #else
> #define efi_init()
> #define efi_idmap_init()
> +#define efi_virtmap_init
> #endif
>
> #define efi_call_virt(f, ...) \
> ({ \
> - efi_##f##_t *__f = efi.systab->runtime->f; \
> + efi_##f##_t *__f; \
> efi_status_t __s; \
> \
> - kernel_neon_begin(); \
> + kernel_neon_begin(); /* disables preemption */ \
Nitpick: adding comment to otherwise untouched source line.
> + efi_virtmap_load(); \
> + __f = efi.systab->runtime->f; \
> __s = __f(__VA_ARGS__); \
> + efi_virtmap_unload(); \
> kernel_neon_end(); \
> __s; \
> })
>
> #define __efi_call_virt(f, ...) \
> ({ \
> - efi_##f##_t *__f = efi.systab->runtime->f; \
> + efi_##f##_t *__f; \
> \
> - kernel_neon_begin(); \
> + kernel_neon_begin(); /* disables preemption */ \
Same nitpick.
> + efi_virtmap_load(); \
> + __f = efi.systab->runtime->f; \
> __f(__VA_ARGS__); \
> + efi_virtmap_unload(); \
> kernel_neon_end(); \
> })
>
> @@ -45,5 +53,9 @@ extern void efi_idmap_init(void);
> #define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__)
>
> #define EFI_ALLOC_ALIGN SZ_64K
> +#define EFI_VIRTMAP EFI_ARCH_1
> +
> +void efi_virtmap_load(void);
> +void efi_virtmap_unload(void);
>
> #endif /* _ASM_EFI_H */
> diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
> index 6fac253bc783..2ebe67ffb629 100644
> --- a/arch/arm64/kernel/efi.c
> +++ b/arch/arm64/kernel/efi.c
> @@ -11,25 +11,30 @@
> *
> */
>
> +#include <linux/atomic.h>
> #include <linux/dmi.h>
> #include <linux/efi.h>
> #include <linux/export.h>
> #include <linux/memblock.h>
> +#include <linux/mm_types.h>
> #include <linux/bootmem.h>
> #include <linux/of.h>
> #include <linux/of_fdt.h>
> +#include <linux/rbtree.h>
> +#include <linux/rwsem.h>
> #include <linux/sched.h>
> #include <linux/slab.h>
> +#include <linux/spinlock.h>
>
> #include <asm/cacheflush.h>
> #include <asm/efi.h>
> #include <asm/tlbflush.h>
> #include <asm/mmu_context.h>
> +#include <asm/mmu.h>
> +#include <asm/pgtable.h>
>
> struct efi_memory_map memmap;
>
> -static efi_runtime_services_t *runtime;
> -
> static u64 efi_system_table;
>
> static int uefi_debug __initdata;
> @@ -69,9 +74,33 @@ static void __init efi_setup_idmap(void)
> }
> }
>
> +/*
> + * Translate a EFI virtual address into a physical address: this is necessary,
> + * as some data members of the EFI system table are virtually remapped after
> + * SetVirtualAddressMap() has been called.
> + */
> +static phys_addr_t efi_to_phys(unsigned long addr)
> +{
> + efi_memory_desc_t *md;
> +
> + for_each_efi_memory_desc(&memmap, md) {
> + if (!(md->attribute & EFI_MEMORY_RUNTIME))
> + continue;
> + if (md->virt_addr == 0)
> + /* no virtual mapping has been installed by the stub */
> + break;
> + if (md->virt_addr <= addr &&
> + (addr - md->virt_addr) < (md->num_pages << EFI_PAGE_SHIFT))
> + return md->phys_addr + addr - md->virt_addr;
> + }
> + return addr;
> +}
> +
> static int __init uefi_init(void)
> {
> efi_char16_t *c16;
> + void *config_tables;
> + u64 table_size;
> char vendor[100] = "unknown";
> int i, retval;
>
> @@ -99,7 +128,7 @@ static int __init uefi_init(void)
> efi.systab->hdr.revision & 0xffff);
>
> /* Show what we know for posterity */
> - c16 = early_memremap(efi.systab->fw_vendor,
> + c16 = early_memremap(efi_to_phys(efi.systab->fw_vendor),
> sizeof(vendor));
> if (c16) {
> for (i = 0; i < (int) sizeof(vendor) - 1 && *c16; ++i)
> @@ -112,8 +141,14 @@ static int __init uefi_init(void)
> efi.systab->hdr.revision >> 16,
> efi.systab->hdr.revision & 0xffff, vendor);
>
> - retval = efi_config_init(NULL);
> + table_size = sizeof(efi_config_table_64_t) * efi.systab->nr_tables;
> + config_tables = early_memremap(efi_to_phys(efi.systab->tables),
> + table_size);
> +
> + retval = efi_config_parse_tables(config_tables,
> + efi.systab->nr_tables, NULL);
>
> + early_memunmap(config_tables, table_size);
> out:
> early_memunmap(efi.systab, sizeof(efi_system_table_t));
> return retval;
> @@ -328,51 +363,9 @@ void __init efi_idmap_init(void)
> efi_setup_idmap();
> }
>
> -static int __init remap_region(efi_memory_desc_t *md, void **new)
> -{
> - u64 paddr, vaddr, npages, size;
> -
> - paddr = md->phys_addr;
> - npages = md->num_pages;
> - memrange_efi_to_native(&paddr, &npages);
> - size = npages << PAGE_SHIFT;
> -
> - if (is_normal_ram(md))
> - vaddr = (__force u64)ioremap_cache(paddr, size);
> - else
> - vaddr = (__force u64)ioremap(paddr, size);
> -
> - if (!vaddr) {
> - pr_err("Unable to remap 0x%llx pages @ %p\n",
> - npages, (void *)paddr);
> - return 0;
> - }
> -
> - /* adjust for any rounding when EFI and system pagesize differs */
> - md->virt_addr = vaddr + (md->phys_addr - paddr);
> -
> - if (uefi_debug)
> - pr_info(" EFI remap 0x%012llx => %p\n",
> - md->phys_addr, (void *)md->virt_addr);
> -
> - memcpy(*new, md, memmap.desc_size);
> - *new += memmap.desc_size;
> -
> - return 1;
> -}
> -
> -/*
> - * Switch UEFI from an identity map to a kernel virtual map
> - */
No function description at all?
Arguably this function could change name now as well, since UEFI will
already be in virtual mode. arm64_enable_runtime_map()?
> static int __init arm64_enter_virtual_mode(void)
> {
> - efi_memory_desc_t *md;
> - phys_addr_t virtmap_phys;
> - void *virtmap, *virt_md;
> - efi_status_t status;
> u64 mapsize;
> - int count = 0;
> - unsigned long flags;
>
> if (!efi_enabled(EFI_BOOT)) {
> pr_info("EFI services will not be available.\n");
> @@ -395,79 +388,28 @@ static int __init arm64_enter_virtual_mode(void)
>
> efi.memmap = &memmap;
>
> - /* Map the runtime regions */
> - virtmap = kmalloc(mapsize, GFP_KERNEL);
> - if (!virtmap) {
> - pr_err("Failed to allocate EFI virtual memmap\n");
> - return -1;
> - }
> - virtmap_phys = virt_to_phys(virtmap);
> - virt_md = virtmap;
> -
> - for_each_efi_memory_desc(&memmap, md) {
> - if (!(md->attribute & EFI_MEMORY_RUNTIME))
> - continue;
> - if (!remap_region(md, &virt_md))
> - goto err_unmap;
> - ++count;
> - }
> -
> - efi.systab = (__force void *)efi_lookup_mapped_addr(efi_system_table);
> + efi.systab = (__force void *)ioremap_cache(efi_system_table,
> + sizeof(efi_system_table_t));
> if (!efi.systab) {
> - /*
> - * If we have no virtual mapping for the System Table at this
> - * point, the memory map doesn't cover the physical offset where
> - * it resides. This means the System Table will be inaccessible
> - * to Runtime Services themselves once the virtual mapping is
> - * installed.
> - */
> - pr_err("Failed to remap EFI System Table -- buggy firmware?\n");
> - goto err_unmap;
> + pr_err("Failed to remap EFI System Table\n");
> + return -1;
> }
> set_bit(EFI_SYSTEM_TABLES, &efi.flags);
>
> - local_irq_save(flags);
> - cpu_switch_mm(idmap_pg_dir, &init_mm);
> -
> - /* Call SetVirtualAddressMap with the physical address of the map */
> - runtime = efi.systab->runtime;
> - efi.set_virtual_address_map = runtime->set_virtual_address_map;
> -
> - status = efi.set_virtual_address_map(count * memmap.desc_size,
> - memmap.desc_size,
> - memmap.desc_version,
> - (efi_memory_desc_t *)virtmap_phys);
> - cpu_set_reserved_ttbr0();
> - flush_tlb_all();
> - local_irq_restore(flags);
> -
> - kfree(virtmap);
> -
> free_boot_services();
>
> - if (status != EFI_SUCCESS) {
> - pr_err("Failed to set EFI virtual address map! [%lx]\n",
> - status);
> + if (!efi_enabled(EFI_VIRTMAP)) {
> + pr_err("No UEFI virtual mapping was installed -- runtime services will not be available\n");
> return -1;
> }
>
> /* Set up runtime services function pointers */
> - runtime = efi.systab->runtime;
> efi_native_runtime_setup();
> set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
>
> efi.runtime_version = efi.systab->hdr.revision;
>
> return 0;
> -
> -err_unmap:
> - /* unmap all mappings that succeeded: there are 'count' of those */
> - for (virt_md = virtmap; count--; virt_md += memmap.desc_size) {
> - md = virt_md;
> - iounmap((__force void __iomem *)md->virt_addr);
> - }
> - kfree(virtmap);
> - return -1;
> }
> early_initcall(arm64_enter_virtual_mode);
>
> @@ -484,3 +426,78 @@ static int __init arm64_dmi_init(void)
> return 0;
> }
> core_initcall(arm64_dmi_init);
> +
> +static pgd_t efi_pgd[PTRS_PER_PGD] __page_aligned_bss;
> +
> +static struct mm_struct efi_mm = {
> + .mm_rb = RB_ROOT,
> + .pgd = efi_pgd,
> + .mm_users = ATOMIC_INIT(2),
> + .mm_count = ATOMIC_INIT(1),
> + .mmap_sem = __RWSEM_INITIALIZER(efi_mm.mmap_sem),
> + .page_table_lock = __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock),
> + .mmlist = LIST_HEAD_INIT(efi_mm.mmlist),
> + INIT_MM_CONTEXT(efi_mm)
> +};
> +
> +static void efi_set_pgd(struct mm_struct *mm)
> +{
> + cpu_switch_mm(mm->pgd, mm);
> + flush_tlb_all();
> + if (icache_is_aivivt())
> + __flush_icache_all();
> +}
> +
> +void efi_virtmap_load(void)
> +{
> + WARN_ON(preemptible());
> + efi_set_pgd(&efi_mm);
> +}
> +
> +void efi_virtmap_unload(void)
> +{
> + efi_set_pgd(current->active_mm);
> +}
> +
> +void __init efi_virtmap_init(void)
> +{
> + efi_memory_desc_t *md;
> +
> + if (!efi_enabled(EFI_BOOT))
> + return;
> +
> + for_each_efi_memory_desc(&memmap, md) {
> + u64 paddr, npages, size;
> + pgprot_t prot;
> +
> + if (!(md->attribute & EFI_MEMORY_RUNTIME))
> + continue;
> + if (WARN(md->virt_addr == 0,
> + "UEFI virtual mapping incomplete or missing -- no entry found for 0x%llx\n",
> + md->phys_addr))
> + return;
> +
> + paddr = md->phys_addr;
> + npages = md->num_pages;
> + memrange_efi_to_native(&paddr, &npages);
> + size = npages << PAGE_SHIFT;
> +
> + pr_info(" EFI remap 0x%012llx => %p\n",
> + md->phys_addr, (void *)md->virt_addr);
> +
> + /*
> + * Only regions of type EFI_RUNTIME_SERVICES_CODE need to be
> + * executable, everything else can be mapped with the XN bits
> + * set.
> + */
> + if (!is_normal_ram(md))
> + prot = __pgprot(PROT_DEVICE_nGnRE);
> + else if (md->type == EFI_RUNTIME_SERVICES_CODE)
> + prot = PAGE_KERNEL_EXEC;
> + else
> + prot = PAGE_KERNEL;
> +
> + create_pgd_mapping(&efi_mm, paddr, md->virt_addr, size, prot);
> + }
> + set_bit(EFI_VIRTMAP, &efi.flags);
> +}
> diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
> index b80991166754..d8390f507da0 100644
> --- a/arch/arm64/kernel/setup.c
> +++ b/arch/arm64/kernel/setup.c
> @@ -402,6 +402,7 @@ void __init setup_arch(char **cmdline_p)
> request_standard_resources();
>
> efi_idmap_init();
> + efi_virtmap_init();
Could these two be merged together into one function?
Say efi_memmap_init()?
>
> unflatten_device_tree();
>
> diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c
> index c846a9608cbd..76bc8abf41d1 100644
> --- a/drivers/firmware/efi/libstub/fdt.c
> +++ b/drivers/firmware/efi/libstub/fdt.c
> @@ -167,6 +167,94 @@ fdt_set_fail:
> #define EFI_FDT_ALIGN EFI_PAGE_SIZE
> #endif
>
> +static efi_status_t get_memory_map(efi_system_table_t *sys_table_arg,
> + efi_memory_desc_t **map,
> + unsigned long *map_size,
> + unsigned long *desc_size,
> + u32 *desc_ver, unsigned long *key_ptr)
> +{
> + efi_status_t status;
> +
> + /*
> + * Call get_memory_map() with 0 size to retrieve the size of the
> + * required allocation.
> + */
> + *map_size = 0;
> + status = efi_call_early(get_memory_map, map_size, NULL,
> + key_ptr, desc_size, desc_ver);
> + if (status != EFI_BUFFER_TOO_SMALL)
> + return EFI_LOAD_ERROR;
> +
> + /*
> + * Add an additional efi_memory_desc_t to map_size because we're doing
> + * an allocation which may be in a new descriptor region. Then double it
> + * to give us some scratch space to prepare the input virtmap to give
> + * to SetVirtualAddressMap(). Note that this is EFI_LOADER_DATA memory,
> + * and the kernel memblock_reserve()'s only the size of the actual
> + * memory map, so the scratch space is freed again automatically.
> + */
> + *map_size += *desc_size;
> + status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
> + *map_size * 2, (void **)map);
> + if (status != EFI_SUCCESS)
> + return status;
> +
> + status = efi_call_early(get_memory_map, map_size, *map,
> + key_ptr, desc_size, desc_ver);
> + if (status != EFI_SUCCESS)
> + efi_call_early(free_pool, *map);
> + return status;
> +}
> +
> +/*
> + * This is the base address at which to start allocating virtual memory ranges
> + * for UEFI Runtime Services. This is a userland range so that we can use any
> + * allocation we choose, and eliminate the risk of a conflict after kexec.
> + */
> +#define EFI_RT_VIRTUAL_BASE 0x40000000
> +
> +static void update_memory_map(efi_memory_desc_t *memory_map,
> + unsigned long map_size, unsigned long desc_size,
> + int *count)
> +{
> + u64 efi_virt_base = EFI_RT_VIRTUAL_BASE;
> + efi_memory_desc_t *out = (void *)memory_map + map_size;
> + int l;
> +
> + for (l = 0; l < map_size; l += desc_size) {
> + efi_memory_desc_t *in = (void *)memory_map + l;
> + u64 paddr, size;
> +
> + if (!(in->attribute & EFI_MEMORY_RUNTIME))
> + continue;
> +
> + /*
> + * Make the mapping compatible with 64k pages: this allows
> + * a 4k page size kernel to kexec a 64k page size kernel and
> + * vice versa.
> + */
> + paddr = round_down(in->phys_addr, SZ_64K);
> + size = round_up(in->num_pages * EFI_PAGE_SIZE +
> + in->phys_addr - paddr, SZ_64K);
> +
> + /*
> + * Avoid wasting memory on PTEs by choosing a virtual base that
> + * is compatible with section mappings if this region has the
> + * appropriate size and physical alignment. (Sections are 2 MB
> + * on 4k granule kernels)
> + */
> + if (IS_ALIGNED(in->phys_addr, SZ_2M) && size >= SZ_2M)
> + efi_virt_base = round_up(efi_virt_base, SZ_2M);
> +
> + in->virt_addr = efi_virt_base + in->phys_addr - paddr;
> + efi_virt_base += size;
> +
> + memcpy(out, in, desc_size);
> + out = (void *)out + desc_size;
> + ++*count;
> + }
> +}
> +
> /*
> * Allocate memory for a new FDT, then add EFI, commandline, and
> * initrd related fields to the FDT. This routine increases the
> @@ -196,6 +284,7 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
> efi_memory_desc_t *memory_map;
> unsigned long new_fdt_size;
> efi_status_t status;
> + int runtime_entry_count = 0;
>
> /*
> * Estimate size of new FDT, and allocate memory for it. We
> @@ -216,8 +305,8 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
> * we can get the memory map key needed for
> * exit_boot_services().
> */
> - status = efi_get_memory_map(sys_table, &memory_map, &map_size,
> - &desc_size, &desc_ver, &mmap_key);
> + status = get_memory_map(sys_table, &memory_map, &map_size,
> + &desc_size, &desc_ver, &mmap_key);
> if (status != EFI_SUCCESS)
> goto fail_free_new_fdt;
>
> @@ -248,12 +337,52 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
> }
> }
>
> + /*
> + * Update the memory map with virtual addresses. The function will also
> + * populate the spare second half of the memory_map allocation with
> + * copies of just the EFI_MEMORY_RUNTIME entries so that we can pass it
> + * straight into SetVirtualAddressMap()
> + */
> + update_memory_map(memory_map, map_size, desc_size,
> + &runtime_entry_count);
> +
> + pr_efi(sys_table,
> + "Exiting boot services and installing virtual address map...\n");
> +
> /* Now we are ready to exit_boot_services.*/
> status = sys_table->boottime->exit_boot_services(handle, mmap_key);
>
> + if (status == EFI_SUCCESS) {
> + efi_set_virtual_address_map_t *svam;
>
> - if (status == EFI_SUCCESS)
> - return status;
> + /* Install the new virtual address map */
> + svam = sys_table->runtime->set_virtual_address_map;
> + status = svam(runtime_entry_count * desc_size, desc_size,
> + desc_ver, (void *)memory_map + map_size);
> +
> + /*
> + * We are beyond the point of no return here, so if the call to
> + * SetVirtualAddressMap() failed, we need to signal that to the
> + * incoming kernel but proceed normally otherwise.
> + */
> + if (status != EFI_SUCCESS) {
> + int l;
> +
> + /*
> + * Set the virtual address field of all
> + * EFI_MEMORY_RUNTIME entries to 0. This will signal
> + * the incoming kernel that no virtual translation has
> + * been installed.
> + */
> + for (l = 0; l < map_size; l += desc_size) {
> + efi_memory_desc_t *p = (void *)memory_map + l;
> +
> + if (p->attribute & EFI_MEMORY_RUNTIME)
> + p->virt_addr = 0;
> + }
> + }
> + return EFI_SUCCESS;
> + }
>
> pr_efi_err(sys_table, "Exit boot services failed.\n");
>
> --
> 1.8.3.2
Apart from this, and other comments in the thread, looks good.
/
Leif
--
To unsubscribe from this list: send the line "unsubscribe linux-efi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
