@@ -327,6 +327,10 @@ config PGTABLE_LEVELS
default 3 if ARM64_16K_PAGES && ARM64_VA_BITS_47
default 4 if !ARM64_64K_PAGES && ARM64_VA_BITS_48
+config IDMAP_PGTABLE_EXPAND
+ def_bool y
+ depends on (ARM64_16K_PAGES && ARM64_VA_BITS_36) || (ARM64_64K_PAGES && ARM64_VA_BITS_42) || (ARM64_4K_PAGES && ARM64_VA_BITS_39) || (ARM64_16K_PAGES && ARM64_VA_BITS_47)
+
config ARCH_SUPPORTS_UPROBES
def_bool y
@@ -3,6 +3,8 @@ obj-y := dma-mapping.o extable.o fault.o init.o \
cache.o copypage.o flush.o \
ioremap.o mmap.o pgd.o mmu.o \
context.o proc.o pageattr.o
+
+obj-$(CONFIG_IDMAP_PGTABLE_EXPAND) += idmap_mmu.o
obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
obj-$(CONFIG_PTDUMP_CORE) += ptdump.o
obj-$(CONFIG_PTDUMP_DEBUGFS) += ptdump_debugfs.o
new file mode 100644
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#ifdef CONFIG_IDMAP_PGTABLE_EXPAND
+
+#if CONFIG_PGTABLE_LEVELS == 2
+#define EXTEND_LEVEL 3
+#elif CONFIG_PGTABLE_LEVELS == 3
+#define EXTEND_LEVEL 4
+#endif
+
+#undef CONFIG_PGTABLE_LEVELS
+#define CONFIG_PGTABLE_LEVELS EXTEND_LEVEL
+
+#include <linux/errno.h>
+
+#include <asm/barrier.h>
+#include <asm/fixmap.h>
+#include <asm/kernel-pgtable.h>
+#include <asm/sections.h>
+#include <asm/pgalloc.h>
+
+#include "./mmu_include.c"
+
+void __create_pgd_mapping_extend(pgd_t *pgdir, phys_addr_t phys,
+ unsigned long virt, phys_addr_t size,
+ pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(int),
+ int flags)
+{
+ __create_pgd_mapping(pgdir, phys, virt, size, prot, pgtable_alloc, flags);
+}
+#endif
+
+
@@ -37,9 +37,6 @@
#include <asm/tlbflush.h>
#include <asm/pgalloc.h>
-#define NO_BLOCK_MAPPINGS BIT(0)
-#define NO_CONT_MAPPINGS BIT(1)
-
u64 idmap_t0sz = TCR_T0SZ(VA_BITS_MIN);
u64 idmap_ptrs_per_pgd = PTRS_PER_PGD;
@@ -116,264 +113,6 @@ static phys_addr_t __init early_pgtable_alloc(int shift)
return phys;
}
-static bool pgattr_change_is_safe(u64 old, u64 new)
-{
- /*
- * The following mapping attributes may be updated in live
- * kernel mappings without the need for break-before-make.
- */
- pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG;
-
- /* creating or taking down mappings is always safe */
- if (old == 0 || new == 0)
- return true;
-
- /* live contiguous mappings may not be manipulated at all */
- if ((old | new) & PTE_CONT)
- return false;
-
- /* Transitioning from Non-Global to Global is unsafe */
- if (old & ~new & PTE_NG)
- return false;
-
- /*
- * Changing the memory type between Normal and Normal-Tagged is safe
- * since Tagged is considered a permission attribute from the
- * mismatched attribute aliases perspective.
- */
- if (((old & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL) ||
- (old & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL_TAGGED)) &&
- ((new & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL) ||
- (new & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL_TAGGED)))
- mask |= PTE_ATTRINDX_MASK;
-
- return ((old ^ new) & ~mask) == 0;
-}
-
-static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end,
- phys_addr_t phys, pgprot_t prot)
-{
- pte_t *ptep;
-
- ptep = pte_set_fixmap_offset(pmdp, addr);
- do {
- pte_t old_pte = READ_ONCE(*ptep);
-
- set_pte(ptep, pfn_pte(__phys_to_pfn(phys), prot));
-
- /*
- * After the PTE entry has been populated once, we
- * only allow updates to the permission attributes.
- */
- BUG_ON(!pgattr_change_is_safe(pte_val(old_pte),
- READ_ONCE(pte_val(*ptep))));
-
- phys += PAGE_SIZE;
- } while (ptep++, addr += PAGE_SIZE, addr != end);
-
- pte_clear_fixmap();
-}
-
-static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
- unsigned long end, phys_addr_t phys,
- pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(int),
- int flags)
-{
- unsigned long next;
- pmd_t pmd = READ_ONCE(*pmdp);
-
- BUG_ON(pmd_sect(pmd));
- if (pmd_none(pmd)) {
- phys_addr_t pte_phys;
- BUG_ON(!pgtable_alloc);
- pte_phys = pgtable_alloc(PAGE_SHIFT);
- __pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE);
- pmd = READ_ONCE(*pmdp);
- }
- BUG_ON(pmd_bad(pmd));
-
- do {
- pgprot_t __prot = prot;
-
- next = pte_cont_addr_end(addr, end);
-
- /* use a contiguous mapping if the range is suitably aligned */
- if ((((addr | next | phys) & ~CONT_PTE_MASK) == 0) &&
- (flags & NO_CONT_MAPPINGS) == 0)
- __prot = __pgprot(pgprot_val(prot) | PTE_CONT);
-
- init_pte(pmdp, addr, next, phys, __prot);
-
- phys += next - addr;
- } while (addr = next, addr != end);
-}
-
-static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
- phys_addr_t phys, pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(int), int flags)
-{
- unsigned long next;
- pmd_t *pmdp;
-
- pmdp = pmd_set_fixmap_offset(pudp, addr);
- do {
- pmd_t old_pmd = READ_ONCE(*pmdp);
-
- next = pmd_addr_end(addr, end);
-
- /* try section mapping first */
- if (((addr | next | phys) & ~SECTION_MASK) == 0 &&
- (flags & NO_BLOCK_MAPPINGS) == 0) {
- pmd_set_huge(pmdp, phys, prot);
-
- /*
- * After the PMD entry has been populated once, we
- * only allow updates to the permission attributes.
- */
- BUG_ON(!pgattr_change_is_safe(pmd_val(old_pmd),
- READ_ONCE(pmd_val(*pmdp))));
- } else {
- alloc_init_cont_pte(pmdp, addr, next, phys, prot,
- pgtable_alloc, flags);
-
- BUG_ON(pmd_val(old_pmd) != 0 &&
- pmd_val(old_pmd) != READ_ONCE(pmd_val(*pmdp)));
- }
- phys += next - addr;
- } while (pmdp++, addr = next, addr != end);
-
- pmd_clear_fixmap();
-}
-
-static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
- unsigned long end, phys_addr_t phys,
- pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(int), int flags)
-{
- unsigned long next;
- pud_t pud = READ_ONCE(*pudp);
-
- /*
- * Check for initial section mappings in the pgd/pud.
- */
- BUG_ON(pud_sect(pud));
- if (pud_none(pud)) {
- phys_addr_t pmd_phys;
- BUG_ON(!pgtable_alloc);
- pmd_phys = pgtable_alloc(PMD_SHIFT);
- __pud_populate(pudp, pmd_phys, PUD_TYPE_TABLE);
- pud = READ_ONCE(*pudp);
- }
- BUG_ON(pud_bad(pud));
-
- do {
- pgprot_t __prot = prot;
-
- next = pmd_cont_addr_end(addr, end);
-
- /* use a contiguous mapping if the range is suitably aligned */
- if ((((addr | next | phys) & ~CONT_PMD_MASK) == 0) &&
- (flags & NO_CONT_MAPPINGS) == 0)
- __prot = __pgprot(pgprot_val(prot) | PTE_CONT);
-
- init_pmd(pudp, addr, next, phys, __prot, pgtable_alloc, flags);
-
- phys += next - addr;
- } while (addr = next, addr != end);
-}
-
-static inline bool use_1G_block(unsigned long addr, unsigned long next,
- unsigned long phys)
-{
- if (PAGE_SHIFT != 12)
- return false;
-
- if (((addr | next | phys) & ~PUD_MASK) != 0)
- return false;
-
- return true;
-}
-
-static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
- phys_addr_t phys, pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(int),
- int flags)
-{
- unsigned long next;
- pud_t *pudp;
- p4d_t *p4dp = p4d_offset(pgdp, addr);
- p4d_t p4d = READ_ONCE(*p4dp);
-
- if (p4d_none(p4d)) {
- phys_addr_t pud_phys;
- BUG_ON(!pgtable_alloc);
- pud_phys = pgtable_alloc(PUD_SHIFT);
- __p4d_populate(p4dp, pud_phys, PUD_TYPE_TABLE);
- p4d = READ_ONCE(*p4dp);
- }
- BUG_ON(p4d_bad(p4d));
-
- pudp = pud_set_fixmap_offset(p4dp, addr);
- do {
- pud_t old_pud = READ_ONCE(*pudp);
-
- next = pud_addr_end(addr, end);
-
- /*
- * For 4K granule only, attempt to put down a 1GB block
- */
- if (use_1G_block(addr, next, phys) &&
- (flags & NO_BLOCK_MAPPINGS) == 0) {
- pud_set_huge(pudp, phys, prot);
-
- /*
- * After the PUD entry has been populated once, we
- * only allow updates to the permission attributes.
- */
- BUG_ON(!pgattr_change_is_safe(pud_val(old_pud),
- READ_ONCE(pud_val(*pudp))));
- } else {
- alloc_init_cont_pmd(pudp, addr, next, phys, prot,
- pgtable_alloc, flags);
-
- BUG_ON(pud_val(old_pud) != 0 &&
- pud_val(old_pud) != READ_ONCE(pud_val(*pudp)));
- }
- phys += next - addr;
- } while (pudp++, addr = next, addr != end);
-
- pud_clear_fixmap();
-}
-
-static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
- unsigned long virt, phys_addr_t size,
- pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(int),
- int flags)
-{
- unsigned long addr, end, next;
- pgd_t *pgdp = pgd_offset_pgd(pgdir, virt);
-
- /*
- * If the virtual and physical address don't have the same offset
- * within a page, we cannot map the region as the caller expects.
- */
- if (WARN_ON((phys ^ virt) & ~PAGE_MASK))
- return;
-
- phys &= PAGE_MASK;
- addr = virt & PAGE_MASK;
- end = PAGE_ALIGN(virt + size);
-
- do {
- next = pgd_addr_end(addr, end);
- alloc_init_pud(pgdp, addr, next, phys, prot, pgtable_alloc,
- flags);
- phys += next - addr;
- } while (pgdp++, addr = next, addr != end);
-}
-
static phys_addr_t __pgd_pgtable_alloc(int shift)
{
void *ptr = (void *)__get_free_page(GFP_PGTABLE_KERNEL);
@@ -404,6 +143,8 @@ static phys_addr_t pgd_pgtable_alloc(int shift)
return pa;
}
+#include "./mmu_include.c"
+
/*
* This function can only be used to modify existing table entries,
* without allocating new levels of table. Note that this permits the
new file mode 100644
@@ -0,0 +1,270 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * This file is shared
+ * And these functions should be PIC because they are called under both MMU-disable
+ * and MMU-enable
+ */
+
+#define NO_BLOCK_MAPPINGS BIT(0)
+#define NO_CONT_MAPPINGS BIT(1)
+
+static bool pgattr_change_is_safe(u64 old, u64 new)
+{
+ /*
+ * The following mapping attributes may be updated in live
+ * kernel mappings without the need for break-before-make.
+ */
+ pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG;
+
+ /* creating or taking down mappings is always safe */
+ if (old == 0 || new == 0)
+ return true;
+
+ /* live contiguous mappings may not be manipulated at all */
+ if ((old | new) & PTE_CONT)
+ return false;
+
+ /* Transitioning from Non-Global to Global is unsafe */
+ if (old & ~new & PTE_NG)
+ return false;
+
+ /*
+ * Changing the memory type between Normal and Normal-Tagged is safe
+ * since Tagged is considered a permission attribute from the
+ * mismatched attribute aliases perspective.
+ */
+ if (((old & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL) ||
+ (old & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL_TAGGED)) &&
+ ((new & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL) ||
+ (new & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL_TAGGED)))
+ mask |= PTE_ATTRINDX_MASK;
+
+ return ((old ^ new) & ~mask) == 0;
+}
+
+static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end,
+ phys_addr_t phys, pgprot_t prot)
+{
+ pte_t *ptep;
+
+ ptep = pte_set_fixmap_offset(pmdp, addr);
+ do {
+ pte_t old_pte = READ_ONCE(*ptep);
+
+ set_pte(ptep, pfn_pte(__phys_to_pfn(phys), prot));
+
+ /*
+ * After the PTE entry has been populated once, we
+ * only allow updates to the permission attributes.
+ */
+ BUG_ON(!pgattr_change_is_safe(pte_val(old_pte),
+ READ_ONCE(pte_val(*ptep))));
+
+ phys += PAGE_SIZE;
+ } while (ptep++, addr += PAGE_SIZE, addr != end);
+
+ pte_clear_fixmap();
+}
+
+static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
+ unsigned long end, phys_addr_t phys,
+ pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(int),
+ int flags)
+{
+ unsigned long next;
+ pmd_t pmd = READ_ONCE(*pmdp);
+
+ BUG_ON(pmd_sect(pmd));
+ if (pmd_none(pmd)) {
+ phys_addr_t pte_phys;
+
+ BUG_ON(!pgtable_alloc);
+ pte_phys = pgtable_alloc(PAGE_SHIFT);
+ __pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE);
+ pmd = READ_ONCE(*pmdp);
+ }
+ BUG_ON(pmd_bad(pmd));
+
+ do {
+ pgprot_t __prot = prot;
+
+ next = pte_cont_addr_end(addr, end);
+
+ /* use a contiguous mapping if the range is suitably aligned */
+ if ((((addr | next | phys) & ~CONT_PTE_MASK) == 0) &&
+ (flags & NO_CONT_MAPPINGS) == 0)
+ __prot = __pgprot(pgprot_val(prot) | PTE_CONT);
+
+ init_pte(pmdp, addr, next, phys, __prot);
+
+ phys += next - addr;
+ } while (addr = next, addr != end);
+}
+
+static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
+ phys_addr_t phys, pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(int), int flags)
+{
+ unsigned long next;
+ pmd_t *pmdp;
+
+ pmdp = pmd_set_fixmap_offset(pudp, addr);
+ do {
+ pmd_t old_pmd = READ_ONCE(*pmdp);
+
+ next = pmd_addr_end(addr, end);
+
+ /* try section mapping first */
+ if (((addr | next | phys) & ~SECTION_MASK) == 0 &&
+ (flags & NO_BLOCK_MAPPINGS) == 0) {
+ pmd_set_huge(pmdp, phys, prot);
+
+ /*
+ * After the PMD entry has been populated once, we
+ * only allow updates to the permission attributes.
+ */
+ BUG_ON(!pgattr_change_is_safe(pmd_val(old_pmd),
+ READ_ONCE(pmd_val(*pmdp))));
+ } else {
+ alloc_init_cont_pte(pmdp, addr, next, phys, prot,
+ pgtable_alloc, flags);
+
+ BUG_ON(pmd_val(old_pmd) != 0 &&
+ pmd_val(old_pmd) != READ_ONCE(pmd_val(*pmdp)));
+ }
+ phys += next - addr;
+ } while (pmdp++, addr = next, addr != end);
+
+ pmd_clear_fixmap();
+}
+
+static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
+ unsigned long end, phys_addr_t phys,
+ pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(int), int flags)
+{
+ unsigned long next;
+ pud_t pud = READ_ONCE(*pudp);
+
+ /*
+ * Check for initial section mappings in the pgd/pud.
+ */
+ BUG_ON(pud_sect(pud));
+ if (pud_none(pud)) {
+ phys_addr_t pmd_phys;
+
+ BUG_ON(!pgtable_alloc);
+ pmd_phys = pgtable_alloc(PMD_SHIFT);
+ __pud_populate(pudp, pmd_phys, PUD_TYPE_TABLE);
+ pud = READ_ONCE(*pudp);
+ }
+ BUG_ON(pud_bad(pud));
+
+ do {
+ pgprot_t __prot = prot;
+
+ next = pmd_cont_addr_end(addr, end);
+
+ /* use a contiguous mapping if the range is suitably aligned */
+ if ((((addr | next | phys) & ~CONT_PMD_MASK) == 0) &&
+ (flags & NO_CONT_MAPPINGS) == 0)
+ __prot = __pgprot(pgprot_val(prot) | PTE_CONT);
+
+ init_pmd(pudp, addr, next, phys, __prot, pgtable_alloc, flags);
+
+ phys += next - addr;
+ } while (addr = next, addr != end);
+}
+
+static inline bool use_1G_block(unsigned long addr, unsigned long next,
+ unsigned long phys)
+{
+ if (PAGE_SHIFT != 12)
+ return false;
+
+ if (((addr | next | phys) & ~PUD_MASK) != 0)
+ return false;
+
+ return true;
+}
+
+static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
+ phys_addr_t phys, pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(int),
+ int flags)
+{
+ unsigned long next;
+ pud_t *pudp;
+ p4d_t *p4dp = p4d_offset(pgdp, addr);
+ p4d_t p4d = READ_ONCE(*p4dp);
+
+ if (p4d_none(p4d)) {
+ phys_addr_t pud_phys;
+
+ BUG_ON(!pgtable_alloc);
+ pud_phys = pgtable_alloc(PUD_SHIFT);
+ __p4d_populate(p4dp, pud_phys, PUD_TYPE_TABLE);
+ p4d = READ_ONCE(*p4dp);
+ }
+ BUG_ON(p4d_bad(p4d));
+
+ pudp = pud_set_fixmap_offset(p4dp, addr);
+ do {
+ pud_t old_pud = READ_ONCE(*pudp);
+
+ next = pud_addr_end(addr, end);
+
+ /*
+ * For 4K granule only, attempt to put down a 1GB block
+ */
+ if (use_1G_block(addr, next, phys) &&
+ (flags & NO_BLOCK_MAPPINGS) == 0) {
+ pud_set_huge(pudp, phys, prot);
+
+ /*
+ * After the PUD entry has been populated once, we
+ * only allow updates to the permission attributes.
+ */
+ BUG_ON(!pgattr_change_is_safe(pud_val(old_pud),
+ READ_ONCE(pud_val(*pudp))));
+ } else {
+ alloc_init_cont_pmd(pudp, addr, next, phys, prot,
+ pgtable_alloc, flags);
+
+ BUG_ON(pud_val(old_pud) != 0 &&
+ pud_val(old_pud) != READ_ONCE(pud_val(*pudp)));
+ }
+ phys += next - addr;
+ } while (pudp++, addr = next, addr != end);
+
+ pud_clear_fixmap();
+}
+
+static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
+ unsigned long virt, phys_addr_t size,
+ pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(int),
+ int flags)
+{
+ unsigned long addr, end, next;
+ pgd_t *pgdp = pgd_offset_pgd(pgdir, virt);
+
+ /*
+ * If the virtual and physical address don't have the same offset
+ * within a page, we cannot map the region as the caller expects.
+ */
+ if (WARN_ON((phys ^ virt) & ~PAGE_MASK))
+ return;
+
+ phys &= PAGE_MASK;
+ addr = virt & PAGE_MASK;
+ end = PAGE_ALIGN(virt + size);
+
+ do {
+ next = pgd_addr_end(addr, end);
+ alloc_init_pud(pgdp, addr, next, phys, prot, pgtable_alloc,
+ flags);
+ phys += next - addr;
+ } while (pgdp++, addr = next, addr != end);
+}
If VA_BITS < 48, an additional table level should be used to allow an ID mapping to cover system RAM. At present, it is done by macro create_table_entry in head.S. But with second thoughts, this expansion can be easily achieved by redefinition of CONFIG_PGTABLE_LEVELS. Split out the routines for __create_pgd_mapping(), so that two sets of code will be generated to manipulate pgtable under two different CONFIG_PGTABLE_LEVELS. Later the one generated under 'CONFIG_PGTABLE_LEVELS + 1' can be used for idmap. Signed-off-by: Pingfan Liu <kernelfans@gmail.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will@kernel.org> Cc: Marc Zyngier <maz@kernel.org> Cc: Kristina Martsenko <kristina.martsenko@arm.com> Cc: James Morse <james.morse@arm.com> Cc: Steven Price <steven.price@arm.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Atish Patra <atish.patra@wdc.com> Cc: Mike Rapoport <rppt@kernel.org> Cc: Logan Gunthorpe <logang@deltatee.com> Cc: Mark Brown <broonie@kernel.org> To: linux-arm-kernel@lists.infradead.org --- RFC -> v2: consider the config ARM64_16K_PAGES && ARM64_VA_BITS_36 and move redefinition of CONFIG_PGTABLE_LEVELS to the head of idmap_mmu.c --- arch/arm64/Kconfig | 4 + arch/arm64/mm/Makefile | 2 + arch/arm64/mm/idmap_mmu.c | 34 +++++ arch/arm64/mm/mmu.c | 263 +---------------------------------- arch/arm64/mm/mmu_include.c | 270 ++++++++++++++++++++++++++++++++++++ 5 files changed, 312 insertions(+), 261 deletions(-) create mode 100644 arch/arm64/mm/idmap_mmu.c create mode 100644 arch/arm64/mm/mmu_include.c