linux-stable/arch/arm64/mm/fixmap.c

173 lines
4.6 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Fixmap manipulation code
*/
#include <linux/bug.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/libfdt.h>
#include <linux/memory.h>
#include <linux/mm.h>
#include <linux/sizes.h>
#include <asm/fixmap.h>
#include <asm/kernel-pgtable.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
/* ensure that the fixmap region does not grow down into the PCI I/O region */
static_assert(FIXADDR_TOT_START > PCI_IO_END);
arm64: mm: always map fixmap at page granularity Today the fixmap code largely maps elements at PAGE_SIZE granularity, but we special-case the FDT mapping such that it can be mapped with 2M block mappings when 4K pages are in use. The original rationale for this was simplicity, but it has some unfortunate side-effects, and complicates portions of the fixmap code (i.e. is not so simple after all). The FDT can be up to 2M in size but is only required to have 8-byte alignment, and so it may straddle a 2M boundary. Thus when using 2M block mappings we may map up to 4M of memory surrounding the FDT. This is unfortunate as most of that memory will be unrelated to the FDT, and any pages which happen to share a 2M block with the FDT will by mapped with Normal Write-Back Cacheable attributes, which might not be what we want elsewhere (e.g. for carve-outs using Non-Cacheable attributes). The logic to handle mapping the FDT with 2M blocks requires some special cases in the fixmap code, and ties it to the early page table configuration by virtue of the SWAPPER_TABLE_SHIFT and SWAPPER_BLOCK_SIZE constants used to determine the granularity used to map the FDT. This patch simplifies the FDT logic and removes the unnecessary mappings of surrounding pages by always mapping the FDT at page granularity as with all other fixmap mappings. To do so we statically reserve multiple PTE tables to cover the fixmap VA range. Since the FDT can be at most 2M, for 4K pages we only need to allocate a single additional PTE table, and for 16K and 64K pages the existing single PTE table is sufficient. The PTE table allocation scales with the number of slots reserved in the fixmap, and so this also makes it easier to add more fixmap entries if we require those in future. Our VA layout means that the fixmap will always fall within a single PMD table (and consequently, within a single PUD/P4D/PGD entry), which we can verify at compile time with a static_assert(). With that assert a number of runtime warnings become impossible, and are removed. I've boot-tested this patch with both 4K and 64K pages. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Link: https://lore.kernel.org/r/20230406152759.4164229-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-04-06 15:27:59 +00:00
#define NR_BM_PTE_TABLES \
SPAN_NR_ENTRIES(FIXADDR_TOT_START, FIXADDR_TOP, PMD_SHIFT)
#define NR_BM_PMD_TABLES \
SPAN_NR_ENTRIES(FIXADDR_TOT_START, FIXADDR_TOP, PUD_SHIFT)
static_assert(NR_BM_PMD_TABLES == 1);
#define __BM_TABLE_IDX(addr, shift) \
(((addr) >> (shift)) - (FIXADDR_TOT_START >> (shift)))
#define BM_PTE_TABLE_IDX(addr) __BM_TABLE_IDX(addr, PMD_SHIFT)
static pte_t bm_pte[NR_BM_PTE_TABLES][PTRS_PER_PTE] __page_aligned_bss;
static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss __maybe_unused;
static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss __maybe_unused;
arm64: mm: always map fixmap at page granularity Today the fixmap code largely maps elements at PAGE_SIZE granularity, but we special-case the FDT mapping such that it can be mapped with 2M block mappings when 4K pages are in use. The original rationale for this was simplicity, but it has some unfortunate side-effects, and complicates portions of the fixmap code (i.e. is not so simple after all). The FDT can be up to 2M in size but is only required to have 8-byte alignment, and so it may straddle a 2M boundary. Thus when using 2M block mappings we may map up to 4M of memory surrounding the FDT. This is unfortunate as most of that memory will be unrelated to the FDT, and any pages which happen to share a 2M block with the FDT will by mapped with Normal Write-Back Cacheable attributes, which might not be what we want elsewhere (e.g. for carve-outs using Non-Cacheable attributes). The logic to handle mapping the FDT with 2M blocks requires some special cases in the fixmap code, and ties it to the early page table configuration by virtue of the SWAPPER_TABLE_SHIFT and SWAPPER_BLOCK_SIZE constants used to determine the granularity used to map the FDT. This patch simplifies the FDT logic and removes the unnecessary mappings of surrounding pages by always mapping the FDT at page granularity as with all other fixmap mappings. To do so we statically reserve multiple PTE tables to cover the fixmap VA range. Since the FDT can be at most 2M, for 4K pages we only need to allocate a single additional PTE table, and for 16K and 64K pages the existing single PTE table is sufficient. The PTE table allocation scales with the number of slots reserved in the fixmap, and so this also makes it easier to add more fixmap entries if we require those in future. Our VA layout means that the fixmap will always fall within a single PMD table (and consequently, within a single PUD/P4D/PGD entry), which we can verify at compile time with a static_assert(). With that assert a number of runtime warnings become impossible, and are removed. I've boot-tested this patch with both 4K and 64K pages. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Link: https://lore.kernel.org/r/20230406152759.4164229-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-04-06 15:27:59 +00:00
static inline pte_t *fixmap_pte(unsigned long addr)
{
arm64: mm: always map fixmap at page granularity Today the fixmap code largely maps elements at PAGE_SIZE granularity, but we special-case the FDT mapping such that it can be mapped with 2M block mappings when 4K pages are in use. The original rationale for this was simplicity, but it has some unfortunate side-effects, and complicates portions of the fixmap code (i.e. is not so simple after all). The FDT can be up to 2M in size but is only required to have 8-byte alignment, and so it may straddle a 2M boundary. Thus when using 2M block mappings we may map up to 4M of memory surrounding the FDT. This is unfortunate as most of that memory will be unrelated to the FDT, and any pages which happen to share a 2M block with the FDT will by mapped with Normal Write-Back Cacheable attributes, which might not be what we want elsewhere (e.g. for carve-outs using Non-Cacheable attributes). The logic to handle mapping the FDT with 2M blocks requires some special cases in the fixmap code, and ties it to the early page table configuration by virtue of the SWAPPER_TABLE_SHIFT and SWAPPER_BLOCK_SIZE constants used to determine the granularity used to map the FDT. This patch simplifies the FDT logic and removes the unnecessary mappings of surrounding pages by always mapping the FDT at page granularity as with all other fixmap mappings. To do so we statically reserve multiple PTE tables to cover the fixmap VA range. Since the FDT can be at most 2M, for 4K pages we only need to allocate a single additional PTE table, and for 16K and 64K pages the existing single PTE table is sufficient. The PTE table allocation scales with the number of slots reserved in the fixmap, and so this also makes it easier to add more fixmap entries if we require those in future. Our VA layout means that the fixmap will always fall within a single PMD table (and consequently, within a single PUD/P4D/PGD entry), which we can verify at compile time with a static_assert(). With that assert a number of runtime warnings become impossible, and are removed. I've boot-tested this patch with both 4K and 64K pages. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Link: https://lore.kernel.org/r/20230406152759.4164229-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-04-06 15:27:59 +00:00
return &bm_pte[BM_PTE_TABLE_IDX(addr)][pte_index(addr)];
}
arm64: mm: always map fixmap at page granularity Today the fixmap code largely maps elements at PAGE_SIZE granularity, but we special-case the FDT mapping such that it can be mapped with 2M block mappings when 4K pages are in use. The original rationale for this was simplicity, but it has some unfortunate side-effects, and complicates portions of the fixmap code (i.e. is not so simple after all). The FDT can be up to 2M in size but is only required to have 8-byte alignment, and so it may straddle a 2M boundary. Thus when using 2M block mappings we may map up to 4M of memory surrounding the FDT. This is unfortunate as most of that memory will be unrelated to the FDT, and any pages which happen to share a 2M block with the FDT will by mapped with Normal Write-Back Cacheable attributes, which might not be what we want elsewhere (e.g. for carve-outs using Non-Cacheable attributes). The logic to handle mapping the FDT with 2M blocks requires some special cases in the fixmap code, and ties it to the early page table configuration by virtue of the SWAPPER_TABLE_SHIFT and SWAPPER_BLOCK_SIZE constants used to determine the granularity used to map the FDT. This patch simplifies the FDT logic and removes the unnecessary mappings of surrounding pages by always mapping the FDT at page granularity as with all other fixmap mappings. To do so we statically reserve multiple PTE tables to cover the fixmap VA range. Since the FDT can be at most 2M, for 4K pages we only need to allocate a single additional PTE table, and for 16K and 64K pages the existing single PTE table is sufficient. The PTE table allocation scales with the number of slots reserved in the fixmap, and so this also makes it easier to add more fixmap entries if we require those in future. Our VA layout means that the fixmap will always fall within a single PMD table (and consequently, within a single PUD/P4D/PGD entry), which we can verify at compile time with a static_assert(). With that assert a number of runtime warnings become impossible, and are removed. I've boot-tested this patch with both 4K and 64K pages. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Link: https://lore.kernel.org/r/20230406152759.4164229-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-04-06 15:27:59 +00:00
static void __init early_fixmap_init_pte(pmd_t *pmdp, unsigned long addr)
{
pmd_t pmd = READ_ONCE(*pmdp);
pte_t *ptep;
arm64: mm: always map fixmap at page granularity Today the fixmap code largely maps elements at PAGE_SIZE granularity, but we special-case the FDT mapping such that it can be mapped with 2M block mappings when 4K pages are in use. The original rationale for this was simplicity, but it has some unfortunate side-effects, and complicates portions of the fixmap code (i.e. is not so simple after all). The FDT can be up to 2M in size but is only required to have 8-byte alignment, and so it may straddle a 2M boundary. Thus when using 2M block mappings we may map up to 4M of memory surrounding the FDT. This is unfortunate as most of that memory will be unrelated to the FDT, and any pages which happen to share a 2M block with the FDT will by mapped with Normal Write-Back Cacheable attributes, which might not be what we want elsewhere (e.g. for carve-outs using Non-Cacheable attributes). The logic to handle mapping the FDT with 2M blocks requires some special cases in the fixmap code, and ties it to the early page table configuration by virtue of the SWAPPER_TABLE_SHIFT and SWAPPER_BLOCK_SIZE constants used to determine the granularity used to map the FDT. This patch simplifies the FDT logic and removes the unnecessary mappings of surrounding pages by always mapping the FDT at page granularity as with all other fixmap mappings. To do so we statically reserve multiple PTE tables to cover the fixmap VA range. Since the FDT can be at most 2M, for 4K pages we only need to allocate a single additional PTE table, and for 16K and 64K pages the existing single PTE table is sufficient. The PTE table allocation scales with the number of slots reserved in the fixmap, and so this also makes it easier to add more fixmap entries if we require those in future. Our VA layout means that the fixmap will always fall within a single PMD table (and consequently, within a single PUD/P4D/PGD entry), which we can verify at compile time with a static_assert(). With that assert a number of runtime warnings become impossible, and are removed. I've boot-tested this patch with both 4K and 64K pages. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Link: https://lore.kernel.org/r/20230406152759.4164229-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-04-06 15:27:59 +00:00
if (pmd_none(pmd)) {
ptep = bm_pte[BM_PTE_TABLE_IDX(addr)];
__pmd_populate(pmdp, __pa_symbol(ptep), PMD_TYPE_TABLE);
}
}
arm64: mm: always map fixmap at page granularity Today the fixmap code largely maps elements at PAGE_SIZE granularity, but we special-case the FDT mapping such that it can be mapped with 2M block mappings when 4K pages are in use. The original rationale for this was simplicity, but it has some unfortunate side-effects, and complicates portions of the fixmap code (i.e. is not so simple after all). The FDT can be up to 2M in size but is only required to have 8-byte alignment, and so it may straddle a 2M boundary. Thus when using 2M block mappings we may map up to 4M of memory surrounding the FDT. This is unfortunate as most of that memory will be unrelated to the FDT, and any pages which happen to share a 2M block with the FDT will by mapped with Normal Write-Back Cacheable attributes, which might not be what we want elsewhere (e.g. for carve-outs using Non-Cacheable attributes). The logic to handle mapping the FDT with 2M blocks requires some special cases in the fixmap code, and ties it to the early page table configuration by virtue of the SWAPPER_TABLE_SHIFT and SWAPPER_BLOCK_SIZE constants used to determine the granularity used to map the FDT. This patch simplifies the FDT logic and removes the unnecessary mappings of surrounding pages by always mapping the FDT at page granularity as with all other fixmap mappings. To do so we statically reserve multiple PTE tables to cover the fixmap VA range. Since the FDT can be at most 2M, for 4K pages we only need to allocate a single additional PTE table, and for 16K and 64K pages the existing single PTE table is sufficient. The PTE table allocation scales with the number of slots reserved in the fixmap, and so this also makes it easier to add more fixmap entries if we require those in future. Our VA layout means that the fixmap will always fall within a single PMD table (and consequently, within a single PUD/P4D/PGD entry), which we can verify at compile time with a static_assert(). With that assert a number of runtime warnings become impossible, and are removed. I've boot-tested this patch with both 4K and 64K pages. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Link: https://lore.kernel.org/r/20230406152759.4164229-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-04-06 15:27:59 +00:00
static void __init early_fixmap_init_pmd(pud_t *pudp, unsigned long addr,
unsigned long end)
{
arm64: mm: always map fixmap at page granularity Today the fixmap code largely maps elements at PAGE_SIZE granularity, but we special-case the FDT mapping such that it can be mapped with 2M block mappings when 4K pages are in use. The original rationale for this was simplicity, but it has some unfortunate side-effects, and complicates portions of the fixmap code (i.e. is not so simple after all). The FDT can be up to 2M in size but is only required to have 8-byte alignment, and so it may straddle a 2M boundary. Thus when using 2M block mappings we may map up to 4M of memory surrounding the FDT. This is unfortunate as most of that memory will be unrelated to the FDT, and any pages which happen to share a 2M block with the FDT will by mapped with Normal Write-Back Cacheable attributes, which might not be what we want elsewhere (e.g. for carve-outs using Non-Cacheable attributes). The logic to handle mapping the FDT with 2M blocks requires some special cases in the fixmap code, and ties it to the early page table configuration by virtue of the SWAPPER_TABLE_SHIFT and SWAPPER_BLOCK_SIZE constants used to determine the granularity used to map the FDT. This patch simplifies the FDT logic and removes the unnecessary mappings of surrounding pages by always mapping the FDT at page granularity as with all other fixmap mappings. To do so we statically reserve multiple PTE tables to cover the fixmap VA range. Since the FDT can be at most 2M, for 4K pages we only need to allocate a single additional PTE table, and for 16K and 64K pages the existing single PTE table is sufficient. The PTE table allocation scales with the number of slots reserved in the fixmap, and so this also makes it easier to add more fixmap entries if we require those in future. Our VA layout means that the fixmap will always fall within a single PMD table (and consequently, within a single PUD/P4D/PGD entry), which we can verify at compile time with a static_assert(). With that assert a number of runtime warnings become impossible, and are removed. I've boot-tested this patch with both 4K and 64K pages. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Link: https://lore.kernel.org/r/20230406152759.4164229-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-04-06 15:27:59 +00:00
unsigned long next;
pud_t pud = READ_ONCE(*pudp);
arm64: mm: always map fixmap at page granularity Today the fixmap code largely maps elements at PAGE_SIZE granularity, but we special-case the FDT mapping such that it can be mapped with 2M block mappings when 4K pages are in use. The original rationale for this was simplicity, but it has some unfortunate side-effects, and complicates portions of the fixmap code (i.e. is not so simple after all). The FDT can be up to 2M in size but is only required to have 8-byte alignment, and so it may straddle a 2M boundary. Thus when using 2M block mappings we may map up to 4M of memory surrounding the FDT. This is unfortunate as most of that memory will be unrelated to the FDT, and any pages which happen to share a 2M block with the FDT will by mapped with Normal Write-Back Cacheable attributes, which might not be what we want elsewhere (e.g. for carve-outs using Non-Cacheable attributes). The logic to handle mapping the FDT with 2M blocks requires some special cases in the fixmap code, and ties it to the early page table configuration by virtue of the SWAPPER_TABLE_SHIFT and SWAPPER_BLOCK_SIZE constants used to determine the granularity used to map the FDT. This patch simplifies the FDT logic and removes the unnecessary mappings of surrounding pages by always mapping the FDT at page granularity as with all other fixmap mappings. To do so we statically reserve multiple PTE tables to cover the fixmap VA range. Since the FDT can be at most 2M, for 4K pages we only need to allocate a single additional PTE table, and for 16K and 64K pages the existing single PTE table is sufficient. The PTE table allocation scales with the number of slots reserved in the fixmap, and so this also makes it easier to add more fixmap entries if we require those in future. Our VA layout means that the fixmap will always fall within a single PMD table (and consequently, within a single PUD/P4D/PGD entry), which we can verify at compile time with a static_assert(). With that assert a number of runtime warnings become impossible, and are removed. I've boot-tested this patch with both 4K and 64K pages. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Link: https://lore.kernel.org/r/20230406152759.4164229-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-04-06 15:27:59 +00:00
pmd_t *pmdp;
arm64: mm: always map fixmap at page granularity Today the fixmap code largely maps elements at PAGE_SIZE granularity, but we special-case the FDT mapping such that it can be mapped with 2M block mappings when 4K pages are in use. The original rationale for this was simplicity, but it has some unfortunate side-effects, and complicates portions of the fixmap code (i.e. is not so simple after all). The FDT can be up to 2M in size but is only required to have 8-byte alignment, and so it may straddle a 2M boundary. Thus when using 2M block mappings we may map up to 4M of memory surrounding the FDT. This is unfortunate as most of that memory will be unrelated to the FDT, and any pages which happen to share a 2M block with the FDT will by mapped with Normal Write-Back Cacheable attributes, which might not be what we want elsewhere (e.g. for carve-outs using Non-Cacheable attributes). The logic to handle mapping the FDT with 2M blocks requires some special cases in the fixmap code, and ties it to the early page table configuration by virtue of the SWAPPER_TABLE_SHIFT and SWAPPER_BLOCK_SIZE constants used to determine the granularity used to map the FDT. This patch simplifies the FDT logic and removes the unnecessary mappings of surrounding pages by always mapping the FDT at page granularity as with all other fixmap mappings. To do so we statically reserve multiple PTE tables to cover the fixmap VA range. Since the FDT can be at most 2M, for 4K pages we only need to allocate a single additional PTE table, and for 16K and 64K pages the existing single PTE table is sufficient. The PTE table allocation scales with the number of slots reserved in the fixmap, and so this also makes it easier to add more fixmap entries if we require those in future. Our VA layout means that the fixmap will always fall within a single PMD table (and consequently, within a single PUD/P4D/PGD entry), which we can verify at compile time with a static_assert(). With that assert a number of runtime warnings become impossible, and are removed. I've boot-tested this patch with both 4K and 64K pages. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Link: https://lore.kernel.org/r/20230406152759.4164229-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-04-06 15:27:59 +00:00
if (pud_none(pud))
__pud_populate(pudp, __pa_symbol(bm_pmd), PUD_TYPE_TABLE);
arm64: mm: always map fixmap at page granularity Today the fixmap code largely maps elements at PAGE_SIZE granularity, but we special-case the FDT mapping such that it can be mapped with 2M block mappings when 4K pages are in use. The original rationale for this was simplicity, but it has some unfortunate side-effects, and complicates portions of the fixmap code (i.e. is not so simple after all). The FDT can be up to 2M in size but is only required to have 8-byte alignment, and so it may straddle a 2M boundary. Thus when using 2M block mappings we may map up to 4M of memory surrounding the FDT. This is unfortunate as most of that memory will be unrelated to the FDT, and any pages which happen to share a 2M block with the FDT will by mapped with Normal Write-Back Cacheable attributes, which might not be what we want elsewhere (e.g. for carve-outs using Non-Cacheable attributes). The logic to handle mapping the FDT with 2M blocks requires some special cases in the fixmap code, and ties it to the early page table configuration by virtue of the SWAPPER_TABLE_SHIFT and SWAPPER_BLOCK_SIZE constants used to determine the granularity used to map the FDT. This patch simplifies the FDT logic and removes the unnecessary mappings of surrounding pages by always mapping the FDT at page granularity as with all other fixmap mappings. To do so we statically reserve multiple PTE tables to cover the fixmap VA range. Since the FDT can be at most 2M, for 4K pages we only need to allocate a single additional PTE table, and for 16K and 64K pages the existing single PTE table is sufficient. The PTE table allocation scales with the number of slots reserved in the fixmap, and so this also makes it easier to add more fixmap entries if we require those in future. Our VA layout means that the fixmap will always fall within a single PMD table (and consequently, within a single PUD/P4D/PGD entry), which we can verify at compile time with a static_assert(). With that assert a number of runtime warnings become impossible, and are removed. I've boot-tested this patch with both 4K and 64K pages. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Link: https://lore.kernel.org/r/20230406152759.4164229-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-04-06 15:27:59 +00:00
pmdp = pmd_offset_kimg(pudp, addr);
do {
next = pmd_addr_end(addr, end);
early_fixmap_init_pte(pmdp, addr);
} while (pmdp++, addr = next, addr != end);
}
arm64: mm: always map fixmap at page granularity Today the fixmap code largely maps elements at PAGE_SIZE granularity, but we special-case the FDT mapping such that it can be mapped with 2M block mappings when 4K pages are in use. The original rationale for this was simplicity, but it has some unfortunate side-effects, and complicates portions of the fixmap code (i.e. is not so simple after all). The FDT can be up to 2M in size but is only required to have 8-byte alignment, and so it may straddle a 2M boundary. Thus when using 2M block mappings we may map up to 4M of memory surrounding the FDT. This is unfortunate as most of that memory will be unrelated to the FDT, and any pages which happen to share a 2M block with the FDT will by mapped with Normal Write-Back Cacheable attributes, which might not be what we want elsewhere (e.g. for carve-outs using Non-Cacheable attributes). The logic to handle mapping the FDT with 2M blocks requires some special cases in the fixmap code, and ties it to the early page table configuration by virtue of the SWAPPER_TABLE_SHIFT and SWAPPER_BLOCK_SIZE constants used to determine the granularity used to map the FDT. This patch simplifies the FDT logic and removes the unnecessary mappings of surrounding pages by always mapping the FDT at page granularity as with all other fixmap mappings. To do so we statically reserve multiple PTE tables to cover the fixmap VA range. Since the FDT can be at most 2M, for 4K pages we only need to allocate a single additional PTE table, and for 16K and 64K pages the existing single PTE table is sufficient. The PTE table allocation scales with the number of slots reserved in the fixmap, and so this also makes it easier to add more fixmap entries if we require those in future. Our VA layout means that the fixmap will always fall within a single PMD table (and consequently, within a single PUD/P4D/PGD entry), which we can verify at compile time with a static_assert(). With that assert a number of runtime warnings become impossible, and are removed. I've boot-tested this patch with both 4K and 64K pages. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Link: https://lore.kernel.org/r/20230406152759.4164229-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-04-06 15:27:59 +00:00
static void __init early_fixmap_init_pud(p4d_t *p4dp, unsigned long addr,
unsigned long end)
{
arm64: mm: always map fixmap at page granularity Today the fixmap code largely maps elements at PAGE_SIZE granularity, but we special-case the FDT mapping such that it can be mapped with 2M block mappings when 4K pages are in use. The original rationale for this was simplicity, but it has some unfortunate side-effects, and complicates portions of the fixmap code (i.e. is not so simple after all). The FDT can be up to 2M in size but is only required to have 8-byte alignment, and so it may straddle a 2M boundary. Thus when using 2M block mappings we may map up to 4M of memory surrounding the FDT. This is unfortunate as most of that memory will be unrelated to the FDT, and any pages which happen to share a 2M block with the FDT will by mapped with Normal Write-Back Cacheable attributes, which might not be what we want elsewhere (e.g. for carve-outs using Non-Cacheable attributes). The logic to handle mapping the FDT with 2M blocks requires some special cases in the fixmap code, and ties it to the early page table configuration by virtue of the SWAPPER_TABLE_SHIFT and SWAPPER_BLOCK_SIZE constants used to determine the granularity used to map the FDT. This patch simplifies the FDT logic and removes the unnecessary mappings of surrounding pages by always mapping the FDT at page granularity as with all other fixmap mappings. To do so we statically reserve multiple PTE tables to cover the fixmap VA range. Since the FDT can be at most 2M, for 4K pages we only need to allocate a single additional PTE table, and for 16K and 64K pages the existing single PTE table is sufficient. The PTE table allocation scales with the number of slots reserved in the fixmap, and so this also makes it easier to add more fixmap entries if we require those in future. Our VA layout means that the fixmap will always fall within a single PMD table (and consequently, within a single PUD/P4D/PGD entry), which we can verify at compile time with a static_assert(). With that assert a number of runtime warnings become impossible, and are removed. I've boot-tested this patch with both 4K and 64K pages. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Link: https://lore.kernel.org/r/20230406152759.4164229-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-04-06 15:27:59 +00:00
p4d_t p4d = READ_ONCE(*p4dp);
pud_t *pudp;
if (CONFIG_PGTABLE_LEVELS > 3 && !p4d_none(p4d) &&
p4d_page_paddr(p4d) != __pa_symbol(bm_pud)) {
/*
* We only end up here if the kernel mapping and the fixmap
* share the top level pgd entry, which should only happen on
* 16k/4 levels configurations.
*/
BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
}
if (p4d_none(p4d))
__p4d_populate(p4dp, __pa_symbol(bm_pud), P4D_TYPE_TABLE);
pudp = pud_offset_kimg(p4dp, addr);
early_fixmap_init_pmd(pudp, addr, end);
}
/*
* The p*d_populate functions call virt_to_phys implicitly so they can't be used
* directly on kernel symbols (bm_p*d). This function is called too early to use
* lm_alias so __p*d_populate functions must be used to populate with the
* physical address from __pa_symbol.
*/
void __init early_fixmap_init(void)
{
unsigned long addr = FIXADDR_TOT_START;
arm64: mm: always map fixmap at page granularity Today the fixmap code largely maps elements at PAGE_SIZE granularity, but we special-case the FDT mapping such that it can be mapped with 2M block mappings when 4K pages are in use. The original rationale for this was simplicity, but it has some unfortunate side-effects, and complicates portions of the fixmap code (i.e. is not so simple after all). The FDT can be up to 2M in size but is only required to have 8-byte alignment, and so it may straddle a 2M boundary. Thus when using 2M block mappings we may map up to 4M of memory surrounding the FDT. This is unfortunate as most of that memory will be unrelated to the FDT, and any pages which happen to share a 2M block with the FDT will by mapped with Normal Write-Back Cacheable attributes, which might not be what we want elsewhere (e.g. for carve-outs using Non-Cacheable attributes). The logic to handle mapping the FDT with 2M blocks requires some special cases in the fixmap code, and ties it to the early page table configuration by virtue of the SWAPPER_TABLE_SHIFT and SWAPPER_BLOCK_SIZE constants used to determine the granularity used to map the FDT. This patch simplifies the FDT logic and removes the unnecessary mappings of surrounding pages by always mapping the FDT at page granularity as with all other fixmap mappings. To do so we statically reserve multiple PTE tables to cover the fixmap VA range. Since the FDT can be at most 2M, for 4K pages we only need to allocate a single additional PTE table, and for 16K and 64K pages the existing single PTE table is sufficient. The PTE table allocation scales with the number of slots reserved in the fixmap, and so this also makes it easier to add more fixmap entries if we require those in future. Our VA layout means that the fixmap will always fall within a single PMD table (and consequently, within a single PUD/P4D/PGD entry), which we can verify at compile time with a static_assert(). With that assert a number of runtime warnings become impossible, and are removed. I've boot-tested this patch with both 4K and 64K pages. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Link: https://lore.kernel.org/r/20230406152759.4164229-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-04-06 15:27:59 +00:00
unsigned long end = FIXADDR_TOP;
arm64: mm: always map fixmap at page granularity Today the fixmap code largely maps elements at PAGE_SIZE granularity, but we special-case the FDT mapping such that it can be mapped with 2M block mappings when 4K pages are in use. The original rationale for this was simplicity, but it has some unfortunate side-effects, and complicates portions of the fixmap code (i.e. is not so simple after all). The FDT can be up to 2M in size but is only required to have 8-byte alignment, and so it may straddle a 2M boundary. Thus when using 2M block mappings we may map up to 4M of memory surrounding the FDT. This is unfortunate as most of that memory will be unrelated to the FDT, and any pages which happen to share a 2M block with the FDT will by mapped with Normal Write-Back Cacheable attributes, which might not be what we want elsewhere (e.g. for carve-outs using Non-Cacheable attributes). The logic to handle mapping the FDT with 2M blocks requires some special cases in the fixmap code, and ties it to the early page table configuration by virtue of the SWAPPER_TABLE_SHIFT and SWAPPER_BLOCK_SIZE constants used to determine the granularity used to map the FDT. This patch simplifies the FDT logic and removes the unnecessary mappings of surrounding pages by always mapping the FDT at page granularity as with all other fixmap mappings. To do so we statically reserve multiple PTE tables to cover the fixmap VA range. Since the FDT can be at most 2M, for 4K pages we only need to allocate a single additional PTE table, and for 16K and 64K pages the existing single PTE table is sufficient. The PTE table allocation scales with the number of slots reserved in the fixmap, and so this also makes it easier to add more fixmap entries if we require those in future. Our VA layout means that the fixmap will always fall within a single PMD table (and consequently, within a single PUD/P4D/PGD entry), which we can verify at compile time with a static_assert(). With that assert a number of runtime warnings become impossible, and are removed. I've boot-tested this patch with both 4K and 64K pages. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Link: https://lore.kernel.org/r/20230406152759.4164229-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-04-06 15:27:59 +00:00
pgd_t *pgdp = pgd_offset_k(addr);
p4d_t *p4dp = p4d_offset_kimg(pgdp, addr);
arm64: mm: always map fixmap at page granularity Today the fixmap code largely maps elements at PAGE_SIZE granularity, but we special-case the FDT mapping such that it can be mapped with 2M block mappings when 4K pages are in use. The original rationale for this was simplicity, but it has some unfortunate side-effects, and complicates portions of the fixmap code (i.e. is not so simple after all). The FDT can be up to 2M in size but is only required to have 8-byte alignment, and so it may straddle a 2M boundary. Thus when using 2M block mappings we may map up to 4M of memory surrounding the FDT. This is unfortunate as most of that memory will be unrelated to the FDT, and any pages which happen to share a 2M block with the FDT will by mapped with Normal Write-Back Cacheable attributes, which might not be what we want elsewhere (e.g. for carve-outs using Non-Cacheable attributes). The logic to handle mapping the FDT with 2M blocks requires some special cases in the fixmap code, and ties it to the early page table configuration by virtue of the SWAPPER_TABLE_SHIFT and SWAPPER_BLOCK_SIZE constants used to determine the granularity used to map the FDT. This patch simplifies the FDT logic and removes the unnecessary mappings of surrounding pages by always mapping the FDT at page granularity as with all other fixmap mappings. To do so we statically reserve multiple PTE tables to cover the fixmap VA range. Since the FDT can be at most 2M, for 4K pages we only need to allocate a single additional PTE table, and for 16K and 64K pages the existing single PTE table is sufficient. The PTE table allocation scales with the number of slots reserved in the fixmap, and so this also makes it easier to add more fixmap entries if we require those in future. Our VA layout means that the fixmap will always fall within a single PMD table (and consequently, within a single PUD/P4D/PGD entry), which we can verify at compile time with a static_assert(). With that assert a number of runtime warnings become impossible, and are removed. I've boot-tested this patch with both 4K and 64K pages. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Link: https://lore.kernel.org/r/20230406152759.4164229-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-04-06 15:27:59 +00:00
early_fixmap_init_pud(p4dp, addr, end);
}
/*
* Unusually, this is also called in IRQ context (ghes_iounmap_irq) so if we
* ever need to use IPIs for TLB broadcasting, then we're in trouble here.
*/
void __set_fixmap(enum fixed_addresses idx,
phys_addr_t phys, pgprot_t flags)
{
unsigned long addr = __fix_to_virt(idx);
pte_t *ptep;
BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses);
ptep = fixmap_pte(addr);
if (pgprot_val(flags)) {
arm64/mm: new ptep layer to manage contig bit Create a new layer for the in-table PTE manipulation APIs. For now, The existing API is prefixed with double underscore to become the arch-private API and the public API is just a simple wrapper that calls the private API. The public API implementation will subsequently be used to transparently manipulate the contiguous bit where appropriate. But since there are already some contig-aware users (e.g. hugetlb, kernel mapper), we must first ensure those users use the private API directly so that the future contig-bit manipulations in the public API do not interfere with those existing uses. The following APIs are treated this way: - ptep_get - set_pte - set_ptes - pte_clear - ptep_get_and_clear - ptep_test_and_clear_young - ptep_clear_flush_young - ptep_set_wrprotect - ptep_set_access_flags Link: https://lkml.kernel.org/r/20240215103205.2607016-11-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Tested-by: John Hubbard <jhubbard@nvidia.com> Acked-by: Mark Rutland <mark.rutland@arm.com> Acked-by: Catalin Marinas <catalin.marinas@arm.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Barry Song <21cnbao@gmail.com> Cc: Borislav Petkov (AMD) <bp@alien8.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Morse <james.morse@arm.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will@kernel.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-02-15 10:31:57 +00:00
__set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, flags));
} else {
arm64/mm: new ptep layer to manage contig bit Create a new layer for the in-table PTE manipulation APIs. For now, The existing API is prefixed with double underscore to become the arch-private API and the public API is just a simple wrapper that calls the private API. The public API implementation will subsequently be used to transparently manipulate the contiguous bit where appropriate. But since there are already some contig-aware users (e.g. hugetlb, kernel mapper), we must first ensure those users use the private API directly so that the future contig-bit manipulations in the public API do not interfere with those existing uses. The following APIs are treated this way: - ptep_get - set_pte - set_ptes - pte_clear - ptep_get_and_clear - ptep_test_and_clear_young - ptep_clear_flush_young - ptep_set_wrprotect - ptep_set_access_flags Link: https://lkml.kernel.org/r/20240215103205.2607016-11-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Tested-by: John Hubbard <jhubbard@nvidia.com> Acked-by: Mark Rutland <mark.rutland@arm.com> Acked-by: Catalin Marinas <catalin.marinas@arm.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Barry Song <21cnbao@gmail.com> Cc: Borislav Petkov (AMD) <bp@alien8.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Morse <james.morse@arm.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will@kernel.org> Cc: Yang Shi <shy828301@gmail.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-02-15 10:31:57 +00:00
__pte_clear(&init_mm, addr, ptep);
flush_tlb_kernel_range(addr, addr+PAGE_SIZE);
}
}
void *__init fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot)
{
const u64 dt_virt_base = __fix_to_virt(FIX_FDT);
arm64: mm: always map fixmap at page granularity Today the fixmap code largely maps elements at PAGE_SIZE granularity, but we special-case the FDT mapping such that it can be mapped with 2M block mappings when 4K pages are in use. The original rationale for this was simplicity, but it has some unfortunate side-effects, and complicates portions of the fixmap code (i.e. is not so simple after all). The FDT can be up to 2M in size but is only required to have 8-byte alignment, and so it may straddle a 2M boundary. Thus when using 2M block mappings we may map up to 4M of memory surrounding the FDT. This is unfortunate as most of that memory will be unrelated to the FDT, and any pages which happen to share a 2M block with the FDT will by mapped with Normal Write-Back Cacheable attributes, which might not be what we want elsewhere (e.g. for carve-outs using Non-Cacheable attributes). The logic to handle mapping the FDT with 2M blocks requires some special cases in the fixmap code, and ties it to the early page table configuration by virtue of the SWAPPER_TABLE_SHIFT and SWAPPER_BLOCK_SIZE constants used to determine the granularity used to map the FDT. This patch simplifies the FDT logic and removes the unnecessary mappings of surrounding pages by always mapping the FDT at page granularity as with all other fixmap mappings. To do so we statically reserve multiple PTE tables to cover the fixmap VA range. Since the FDT can be at most 2M, for 4K pages we only need to allocate a single additional PTE table, and for 16K and 64K pages the existing single PTE table is sufficient. The PTE table allocation scales with the number of slots reserved in the fixmap, and so this also makes it easier to add more fixmap entries if we require those in future. Our VA layout means that the fixmap will always fall within a single PMD table (and consequently, within a single PUD/P4D/PGD entry), which we can verify at compile time with a static_assert(). With that assert a number of runtime warnings become impossible, and are removed. I've boot-tested this patch with both 4K and 64K pages. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Link: https://lore.kernel.org/r/20230406152759.4164229-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-04-06 15:27:59 +00:00
phys_addr_t dt_phys_base;
int offset;
void *dt_virt;
/*
* Check whether the physical FDT address is set and meets the minimum
* alignment requirement. Since we are relying on MIN_FDT_ALIGN to be
* at least 8 bytes so that we can always access the magic and size
* fields of the FDT header after mapping the first chunk, double check
* here if that is indeed the case.
*/
BUILD_BUG_ON(MIN_FDT_ALIGN < 8);
if (!dt_phys || dt_phys % MIN_FDT_ALIGN)
return NULL;
arm64: mm: always map fixmap at page granularity Today the fixmap code largely maps elements at PAGE_SIZE granularity, but we special-case the FDT mapping such that it can be mapped with 2M block mappings when 4K pages are in use. The original rationale for this was simplicity, but it has some unfortunate side-effects, and complicates portions of the fixmap code (i.e. is not so simple after all). The FDT can be up to 2M in size but is only required to have 8-byte alignment, and so it may straddle a 2M boundary. Thus when using 2M block mappings we may map up to 4M of memory surrounding the FDT. This is unfortunate as most of that memory will be unrelated to the FDT, and any pages which happen to share a 2M block with the FDT will by mapped with Normal Write-Back Cacheable attributes, which might not be what we want elsewhere (e.g. for carve-outs using Non-Cacheable attributes). The logic to handle mapping the FDT with 2M blocks requires some special cases in the fixmap code, and ties it to the early page table configuration by virtue of the SWAPPER_TABLE_SHIFT and SWAPPER_BLOCK_SIZE constants used to determine the granularity used to map the FDT. This patch simplifies the FDT logic and removes the unnecessary mappings of surrounding pages by always mapping the FDT at page granularity as with all other fixmap mappings. To do so we statically reserve multiple PTE tables to cover the fixmap VA range. Since the FDT can be at most 2M, for 4K pages we only need to allocate a single additional PTE table, and for 16K and 64K pages the existing single PTE table is sufficient. The PTE table allocation scales with the number of slots reserved in the fixmap, and so this also makes it easier to add more fixmap entries if we require those in future. Our VA layout means that the fixmap will always fall within a single PMD table (and consequently, within a single PUD/P4D/PGD entry), which we can verify at compile time with a static_assert(). With that assert a number of runtime warnings become impossible, and are removed. I've boot-tested this patch with both 4K and 64K pages. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Link: https://lore.kernel.org/r/20230406152759.4164229-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-04-06 15:27:59 +00:00
dt_phys_base = round_down(dt_phys, PAGE_SIZE);
offset = dt_phys % PAGE_SIZE;
dt_virt = (void *)dt_virt_base + offset;
/* map the first chunk so we can read the size from the header */
arm64: mm: always map fixmap at page granularity Today the fixmap code largely maps elements at PAGE_SIZE granularity, but we special-case the FDT mapping such that it can be mapped with 2M block mappings when 4K pages are in use. The original rationale for this was simplicity, but it has some unfortunate side-effects, and complicates portions of the fixmap code (i.e. is not so simple after all). The FDT can be up to 2M in size but is only required to have 8-byte alignment, and so it may straddle a 2M boundary. Thus when using 2M block mappings we may map up to 4M of memory surrounding the FDT. This is unfortunate as most of that memory will be unrelated to the FDT, and any pages which happen to share a 2M block with the FDT will by mapped with Normal Write-Back Cacheable attributes, which might not be what we want elsewhere (e.g. for carve-outs using Non-Cacheable attributes). The logic to handle mapping the FDT with 2M blocks requires some special cases in the fixmap code, and ties it to the early page table configuration by virtue of the SWAPPER_TABLE_SHIFT and SWAPPER_BLOCK_SIZE constants used to determine the granularity used to map the FDT. This patch simplifies the FDT logic and removes the unnecessary mappings of surrounding pages by always mapping the FDT at page granularity as with all other fixmap mappings. To do so we statically reserve multiple PTE tables to cover the fixmap VA range. Since the FDT can be at most 2M, for 4K pages we only need to allocate a single additional PTE table, and for 16K and 64K pages the existing single PTE table is sufficient. The PTE table allocation scales with the number of slots reserved in the fixmap, and so this also makes it easier to add more fixmap entries if we require those in future. Our VA layout means that the fixmap will always fall within a single PMD table (and consequently, within a single PUD/P4D/PGD entry), which we can verify at compile time with a static_assert(). With that assert a number of runtime warnings become impossible, and are removed. I've boot-tested this patch with both 4K and 64K pages. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Link: https://lore.kernel.org/r/20230406152759.4164229-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-04-06 15:27:59 +00:00
create_mapping_noalloc(dt_phys_base, dt_virt_base, PAGE_SIZE, prot);
if (fdt_magic(dt_virt) != FDT_MAGIC)
return NULL;
*size = fdt_totalsize(dt_virt);
if (*size > MAX_FDT_SIZE)
return NULL;
arm64: mm: always map fixmap at page granularity Today the fixmap code largely maps elements at PAGE_SIZE granularity, but we special-case the FDT mapping such that it can be mapped with 2M block mappings when 4K pages are in use. The original rationale for this was simplicity, but it has some unfortunate side-effects, and complicates portions of the fixmap code (i.e. is not so simple after all). The FDT can be up to 2M in size but is only required to have 8-byte alignment, and so it may straddle a 2M boundary. Thus when using 2M block mappings we may map up to 4M of memory surrounding the FDT. This is unfortunate as most of that memory will be unrelated to the FDT, and any pages which happen to share a 2M block with the FDT will by mapped with Normal Write-Back Cacheable attributes, which might not be what we want elsewhere (e.g. for carve-outs using Non-Cacheable attributes). The logic to handle mapping the FDT with 2M blocks requires some special cases in the fixmap code, and ties it to the early page table configuration by virtue of the SWAPPER_TABLE_SHIFT and SWAPPER_BLOCK_SIZE constants used to determine the granularity used to map the FDT. This patch simplifies the FDT logic and removes the unnecessary mappings of surrounding pages by always mapping the FDT at page granularity as with all other fixmap mappings. To do so we statically reserve multiple PTE tables to cover the fixmap VA range. Since the FDT can be at most 2M, for 4K pages we only need to allocate a single additional PTE table, and for 16K and 64K pages the existing single PTE table is sufficient. The PTE table allocation scales with the number of slots reserved in the fixmap, and so this also makes it easier to add more fixmap entries if we require those in future. Our VA layout means that the fixmap will always fall within a single PMD table (and consequently, within a single PUD/P4D/PGD entry), which we can verify at compile time with a static_assert(). With that assert a number of runtime warnings become impossible, and are removed. I've boot-tested this patch with both 4K and 64K pages. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Will Deacon <will@kernel.org> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com> Link: https://lore.kernel.org/r/20230406152759.4164229-4-mark.rutland@arm.com Signed-off-by: Will Deacon <will@kernel.org>
2023-04-06 15:27:59 +00:00
if (offset + *size > PAGE_SIZE) {
create_mapping_noalloc(dt_phys_base, dt_virt_base,
offset + *size, prot);
}
return dt_virt;
}