summaryrefslogtreecommitdiff
path: root/arch/riscv/mm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/riscv/mm')
-rw-r--r--arch/riscv/mm/Makefile4
-rw-r--r--arch/riscv/mm/cacheflush.c69
-rw-r--r--arch/riscv/mm/fault.c6
-rw-r--r--arch/riscv/mm/hugetlbpage.c301
-rw-r--r--arch/riscv/mm/init.c272
-rw-r--r--arch/riscv/mm/kasan_init.c516
-rw-r--r--arch/riscv/mm/pageattr.c8
-rw-r--r--arch/riscv/mm/physaddr.c16
-rw-r--r--arch/riscv/mm/ptdump.c24
-rw-r--r--arch/riscv/mm/tlbflush.c93
10 files changed, 943 insertions, 366 deletions
diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
index 2ac177c05352..b85e9e82f082 100644
--- a/arch/riscv/mm/Makefile
+++ b/arch/riscv/mm/Makefile
@@ -1,6 +1,10 @@
# SPDX-License-Identifier: GPL-2.0-only
CFLAGS_init.o := -mcmodel=medany
+ifdef CONFIG_RELOCATABLE
+CFLAGS_init.o += -fno-pie
+endif
+
ifdef CONFIG_FTRACE
CFLAGS_REMOVE_init.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_cacheflush.o = $(CC_FLAGS_FTRACE)
diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
index fcd6145fbead..fca532ddf3ec 100644
--- a/arch/riscv/mm/cacheflush.c
+++ b/arch/riscv/mm/cacheflush.c
@@ -19,7 +19,7 @@ void flush_icache_all(void)
{
local_flush_icache_all();
- if (IS_ENABLED(CONFIG_RISCV_SBI))
+ if (IS_ENABLED(CONFIG_RISCV_SBI) && !riscv_use_ipi_for_rfence())
sbi_remote_fence_i(NULL);
else
on_each_cpu(ipi_remote_fence_i, NULL, 1);
@@ -67,7 +67,8 @@ void flush_icache_mm(struct mm_struct *mm, bool local)
* with flush_icache_deferred().
*/
smp_mb();
- } else if (IS_ENABLED(CONFIG_RISCV_SBI)) {
+ } else if (IS_ENABLED(CONFIG_RISCV_SBI) &&
+ !riscv_use_ipi_for_rfence()) {
sbi_remote_fence_i(&others);
} else {
on_each_cpu_mask(&others, ipi_remote_fence_i, NULL, 1);
@@ -100,36 +101,48 @@ void flush_icache_pte(pte_t pte)
unsigned int riscv_cbom_block_size;
EXPORT_SYMBOL_GPL(riscv_cbom_block_size);
-void riscv_init_cbom_blocksize(void)
+unsigned int riscv_cboz_block_size;
+EXPORT_SYMBOL_GPL(riscv_cboz_block_size);
+
+static void cbo_get_block_size(struct device_node *node,
+ const char *name, u32 *block_size,
+ unsigned long *first_hartid)
{
+ unsigned long hartid;
+ u32 val;
+
+ if (riscv_of_processor_hartid(node, &hartid))
+ return;
+
+ if (of_property_read_u32(node, name, &val))
+ return;
+
+ if (!*block_size) {
+ *block_size = val;
+ *first_hartid = hartid;
+ } else if (*block_size != val) {
+ pr_warn("%s mismatched between harts %lu and %lu\n",
+ name, *first_hartid, hartid);
+ }
+}
+
+void riscv_init_cbo_blocksizes(void)
+{
+ unsigned long cbom_hartid, cboz_hartid;
+ u32 cbom_block_size = 0, cboz_block_size = 0;
struct device_node *node;
- unsigned long cbom_hartid;
- u32 val, probed_block_size;
- int ret;
- probed_block_size = 0;
for_each_of_cpu_node(node) {
- unsigned long hartid;
-
- ret = riscv_of_processor_hartid(node, &hartid);
- if (ret)
- continue;
-
- /* set block-size for cbom extension if available */
- ret = of_property_read_u32(node, "riscv,cbom-block-size", &val);
- if (ret)
- continue;
-
- if (!probed_block_size) {
- probed_block_size = val;
- cbom_hartid = hartid;
- } else {
- if (probed_block_size != val)
- pr_warn("cbom-block-size mismatched between harts %lu and %lu\n",
- cbom_hartid, hartid);
- }
+ /* set block-size for cbom and/or cboz extension if available */
+ cbo_get_block_size(node, "riscv,cbom-block-size",
+ &cbom_block_size, &cbom_hartid);
+ cbo_get_block_size(node, "riscv,cboz-block-size",
+ &cboz_block_size, &cboz_hartid);
}
- if (probed_block_size)
- riscv_cbom_block_size = probed_block_size;
+ if (cbom_block_size)
+ riscv_cbom_block_size = cbom_block_size;
+
+ if (cboz_block_size)
+ riscv_cboz_block_size = cboz_block_size;
}
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index d5f3e501dffb..8685f85a7474 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -15,6 +15,7 @@
#include <linux/uaccess.h>
#include <linux/kprobes.h>
#include <linux/kfence.h>
+#include <linux/entry-common.h>
#include <asm/ptrace.h>
#include <asm/tlbflush.h>
@@ -209,7 +210,7 @@ static inline bool access_error(unsigned long cause, struct vm_area_struct *vma)
* This routine handles page faults. It determines the address and the
* problem, and then passes it off to one of the appropriate routines.
*/
-asmlinkage void do_page_fault(struct pt_regs *regs)
+void handle_page_fault(struct pt_regs *regs)
{
struct task_struct *tsk;
struct vm_area_struct *vma;
@@ -256,7 +257,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs)
}
#endif
/* Enable interrupts if they were enabled in the parent context. */
- if (likely(regs->status & SR_PIE))
+ if (!regs_irqs_disabled(regs))
local_irq_enable();
/*
@@ -361,4 +362,3 @@ good_area:
}
return;
}
-NOKPROBE_SYMBOL(do_page_fault);
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index 932dadfdca54..a163a3e0f0d4 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -2,6 +2,305 @@
#include <linux/hugetlb.h>
#include <linux/err.h>
+#ifdef CONFIG_RISCV_ISA_SVNAPOT
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ unsigned long addr,
+ unsigned long sz)
+{
+ unsigned long order;
+ pte_t *pte = NULL;
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ pgd = pgd_offset(mm, addr);
+ p4d = p4d_alloc(mm, pgd, addr);
+ if (!p4d)
+ return NULL;
+
+ pud = pud_alloc(mm, p4d, addr);
+ if (!pud)
+ return NULL;
+
+ if (sz == PUD_SIZE) {
+ pte = (pte_t *)pud;
+ goto out;
+ }
+
+ if (sz == PMD_SIZE) {
+ if (want_pmd_share(vma, addr) && pud_none(*pud))
+ pte = huge_pmd_share(mm, vma, addr, pud);
+ else
+ pte = (pte_t *)pmd_alloc(mm, pud, addr);
+ goto out;
+ }
+
+ pmd = pmd_alloc(mm, pud, addr);
+ if (!pmd)
+ return NULL;
+
+ for_each_napot_order(order) {
+ if (napot_cont_size(order) == sz) {
+ pte = pte_alloc_map(mm, pmd, addr & napot_cont_mask(order));
+ break;
+ }
+ }
+
+out:
+ WARN_ON_ONCE(pte && pte_present(*pte) && !pte_huge(*pte));
+ return pte;
+}
+
+pte_t *huge_pte_offset(struct mm_struct *mm,
+ unsigned long addr,
+ unsigned long sz)
+{
+ unsigned long order;
+ pte_t *pte = NULL;
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ pgd = pgd_offset(mm, addr);
+ if (!pgd_present(*pgd))
+ return NULL;
+
+ p4d = p4d_offset(pgd, addr);
+ if (!p4d_present(*p4d))
+ return NULL;
+
+ pud = pud_offset(p4d, addr);
+ if (sz == PUD_SIZE)
+ /* must be pud huge, non-present or none */
+ return (pte_t *)pud;
+
+ if (!pud_present(*pud))
+ return NULL;
+
+ pmd = pmd_offset(pud, addr);
+ if (sz == PMD_SIZE)
+ /* must be pmd huge, non-present or none */
+ return (pte_t *)pmd;
+
+ if (!pmd_present(*pmd))
+ return NULL;
+
+ for_each_napot_order(order) {
+ if (napot_cont_size(order) == sz) {
+ pte = pte_offset_kernel(pmd, addr & napot_cont_mask(order));
+ break;
+ }
+ }
+ return pte;
+}
+
+static pte_t get_clear_contig(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep,
+ unsigned long pte_num)
+{
+ pte_t orig_pte = ptep_get(ptep);
+ unsigned long i;
+
+ for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++) {
+ pte_t pte = ptep_get_and_clear(mm, addr, ptep);
+
+ if (pte_dirty(pte))
+ orig_pte = pte_mkdirty(orig_pte);
+
+ if (pte_young(pte))
+ orig_pte = pte_mkyoung(orig_pte);
+ }
+
+ return orig_pte;
+}
+
+static pte_t get_clear_contig_flush(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep,
+ unsigned long pte_num)
+{
+ pte_t orig_pte = get_clear_contig(mm, addr, ptep, pte_num);
+ struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
+ bool valid = !pte_none(orig_pte);
+
+ if (valid)
+ flush_tlb_range(&vma, addr, addr + (PAGE_SIZE * pte_num));
+
+ return orig_pte;
+}
+
+pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
+{
+ unsigned long order;
+
+ for_each_napot_order(order) {
+ if (shift == napot_cont_shift(order)) {
+ entry = pte_mknapot(entry, order);
+ break;
+ }
+ }
+ if (order == NAPOT_ORDER_MAX)
+ entry = pte_mkhuge(entry);
+
+ return entry;
+}
+
+void set_huge_pte_at(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep,
+ pte_t pte)
+{
+ int i, pte_num;
+
+ if (!pte_napot(pte)) {
+ set_pte_at(mm, addr, ptep, pte);
+ return;
+ }
+
+ pte_num = napot_pte_num(napot_cont_order(pte));
+ for (i = 0; i < pte_num; i++, ptep++, addr += PAGE_SIZE)
+ set_pte_at(mm, addr, ptep, pte);
+}
+
+int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+ unsigned long addr,
+ pte_t *ptep,
+ pte_t pte,
+ int dirty)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ unsigned long order;
+ pte_t orig_pte;
+ int i, pte_num;
+
+ if (!pte_napot(pte))
+ return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+
+ order = napot_cont_order(pte);
+ pte_num = napot_pte_num(order);
+ ptep = huge_pte_offset(mm, addr, napot_cont_size(order));
+ orig_pte = get_clear_contig_flush(mm, addr, ptep, pte_num);
+
+ if (pte_dirty(orig_pte))
+ pte = pte_mkdirty(pte);
+
+ if (pte_young(orig_pte))
+ pte = pte_mkyoung(pte);
+
+ for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++)
+ set_pte_at(mm, addr, ptep, pte);
+
+ return true;
+}
+
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep)
+{
+ pte_t orig_pte = ptep_get(ptep);
+ int pte_num;
+
+ if (!pte_napot(orig_pte))
+ return ptep_get_and_clear(mm, addr, ptep);
+
+ pte_num = napot_pte_num(napot_cont_order(orig_pte));
+
+ return get_clear_contig(mm, addr, ptep, pte_num);
+}
+
+void huge_ptep_set_wrprotect(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep)
+{
+ pte_t pte = ptep_get(ptep);
+ unsigned long order;
+ int i, pte_num;
+
+ if (!pte_napot(pte)) {
+ ptep_set_wrprotect(mm, addr, ptep);
+ return;
+ }
+
+ order = napot_cont_order(pte);
+ pte_num = napot_pte_num(order);
+ ptep = huge_pte_offset(mm, addr, napot_cont_size(order));
+
+ for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++)
+ ptep_set_wrprotect(mm, addr, ptep);
+}
+
+pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+ unsigned long addr,
+ pte_t *ptep)
+{
+ pte_t pte = ptep_get(ptep);
+ int pte_num;
+
+ if (!pte_napot(pte))
+ return ptep_clear_flush(vma, addr, ptep);
+
+ pte_num = napot_pte_num(napot_cont_order(pte));
+
+ return get_clear_contig_flush(vma->vm_mm, addr, ptep, pte_num);
+}
+
+void huge_pte_clear(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep,
+ unsigned long sz)
+{
+ pte_t pte = READ_ONCE(*ptep);
+ int i, pte_num;
+
+ if (!pte_napot(pte)) {
+ pte_clear(mm, addr, ptep);
+ return;
+ }
+
+ pte_num = napot_pte_num(napot_cont_order(pte));
+ for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++)
+ pte_clear(mm, addr, ptep);
+}
+
+static __init bool is_napot_size(unsigned long size)
+{
+ unsigned long order;
+
+ if (!has_svnapot())
+ return false;
+
+ for_each_napot_order(order) {
+ if (size == napot_cont_size(order))
+ return true;
+ }
+ return false;
+}
+
+static __init int napot_hugetlbpages_init(void)
+{
+ if (has_svnapot()) {
+ unsigned long order;
+
+ for_each_napot_order(order)
+ hugetlb_add_hstate(order);
+ }
+ return 0;
+}
+arch_initcall(napot_hugetlbpages_init);
+
+#else
+
+static __init bool is_napot_size(unsigned long size)
+{
+ return false;
+}
+
+#endif /*CONFIG_RISCV_ISA_SVNAPOT*/
+
int pud_huge(pud_t pud)
{
return pud_leaf(pud);
@@ -18,6 +317,8 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
return true;
else if (IS_ENABLED(CONFIG_64BIT) && size == PUD_SIZE)
return true;
+ else if (is_napot_size(size))
+ return true;
else
return false;
}
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 478d6763a01a..747e5b1ef02d 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -20,6 +20,9 @@
#include <linux/dma-map-ops.h>
#include <linux/crash_dump.h>
#include <linux/hugetlb.h>
+#ifdef CONFIG_RELOCATABLE
+#include <linux/elf.h>
+#endif
#include <asm/fixmap.h>
#include <asm/tlbflush.h>
@@ -57,7 +60,6 @@ unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
EXPORT_SYMBOL(empty_zero_page);
extern char _start[];
-#define DTB_EARLY_BASE_VA PGDIR_SIZE
void *_dtb_early_va __initdata;
uintptr_t _dtb_early_pa __initdata;
@@ -146,7 +148,7 @@ static void __init print_vm_layout(void)
print_ml("kasan", KASAN_SHADOW_START, KASAN_SHADOW_END);
#endif
- print_ml("kernel", (unsigned long)KERNEL_LINK_ADDR,
+ print_ml("kernel", (unsigned long)kernel_map.virt_addr,
(unsigned long)ADDRESS_SPACE_END);
}
}
@@ -213,6 +215,14 @@ static void __init setup_bootmem(void)
phys_ram_end = memblock_end_of_DRAM();
if (!IS_ENABLED(CONFIG_XIP_KERNEL))
phys_ram_base = memblock_start_of_DRAM();
+
+ /*
+ * In 64-bit, any use of __va/__pa before this point is wrong as we
+ * did not know the start of DRAM before.
+ */
+ if (IS_ENABLED(CONFIG_64BIT))
+ kernel_map.va_pa_offset = PAGE_OFFSET - phys_ram_base;
+
/*
* memblock allocator is not aware of the fact that last 4K bytes of
* the addressable memory can not be mapped because of IS_ERR_VALUE
@@ -236,31 +246,22 @@ static void __init setup_bootmem(void)
set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET);
reserve_initrd_mem();
+
+ /*
+ * No allocation should be done before reserving the memory as defined
+ * in the device tree, otherwise the allocation could end up in a
+ * reserved region.
+ */
+ early_init_fdt_scan_reserved_mem();
+
/*
* If DTB is built in, no need to reserve its memblock.
* Otherwise, do reserve it but avoid using
* early_init_fdt_reserve_self() since __pa() does
* not work for DTB pointers that are fixmap addresses
*/
- if (!IS_ENABLED(CONFIG_BUILTIN_DTB)) {
- /*
- * In case the DTB is not located in a memory region we won't
- * be able to locate it later on via the linear mapping and
- * get a segfault when accessing it via __va(dtb_early_pa).
- * To avoid this situation copy DTB to a memory region.
- * Note that memblock_phys_alloc will also reserve DTB region.
- */
- if (!memblock_is_memory(dtb_early_pa)) {
- size_t fdt_size = fdt_totalsize(dtb_early_va);
- phys_addr_t new_dtb_early_pa = memblock_phys_alloc(fdt_size, PAGE_SIZE);
- void *new_dtb_early_va = early_memremap(new_dtb_early_pa, fdt_size);
-
- memcpy(new_dtb_early_va, dtb_early_va, fdt_size);
- early_memunmap(new_dtb_early_va, fdt_size);
- _dtb_early_pa = new_dtb_early_pa;
- } else
- memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va));
- }
+ if (!IS_ENABLED(CONFIG_BUILTIN_DTB))
+ memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va));
dma_contiguous_reserve(dma32_phys_limit);
if (IS_ENABLED(CONFIG_64BIT))
@@ -271,21 +272,14 @@ static void __init setup_bootmem(void)
#ifdef CONFIG_MMU
struct pt_alloc_ops pt_ops __initdata;
-unsigned long riscv_pfn_base __ro_after_init;
-EXPORT_SYMBOL(riscv_pfn_base);
-
pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
pgd_t trampoline_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
static pte_t fixmap_pte[PTRS_PER_PTE] __page_aligned_bss;
pgd_t early_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
-static p4d_t __maybe_unused early_dtb_p4d[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE);
-static pud_t __maybe_unused early_dtb_pud[PTRS_PER_PUD] __initdata __aligned(PAGE_SIZE);
-static pmd_t __maybe_unused early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);
#ifdef CONFIG_XIP_KERNEL
#define pt_ops (*(struct pt_alloc_ops *)XIP_FIXUP(&pt_ops))
-#define riscv_pfn_base (*(unsigned long *)XIP_FIXUP(&riscv_pfn_base))
#define trampoline_pg_dir ((pgd_t *)XIP_FIXUP(trampoline_pg_dir))
#define fixmap_pte ((pte_t *)XIP_FIXUP(fixmap_pte))
#define early_pg_dir ((pgd_t *)XIP_FIXUP(early_pg_dir))
@@ -626,9 +620,6 @@ static void __init create_p4d_mapping(p4d_t *p4dp,
#define trampoline_pgd_next (pgtable_l5_enabled ? \
(uintptr_t)trampoline_p4d : (pgtable_l4_enabled ? \
(uintptr_t)trampoline_pud : (uintptr_t)trampoline_pmd))
-#define early_dtb_pgd_next (pgtable_l5_enabled ? \
- (uintptr_t)early_dtb_p4d : (pgtable_l4_enabled ? \
- (uintptr_t)early_dtb_pud : (uintptr_t)early_dtb_pmd))
#else
#define pgd_next_t pte_t
#define alloc_pgd_next(__va) pt_ops.alloc_pte(__va)
@@ -636,7 +627,6 @@ static void __init create_p4d_mapping(p4d_t *p4dp,
#define create_pgd_next_mapping(__nextp, __va, __pa, __sz, __prot) \
create_pte_mapping(__nextp, __va, __pa, __sz, __prot)
#define fixmap_pgd_next ((uintptr_t)fixmap_pte)
-#define early_dtb_pgd_next ((uintptr_t)early_dtb_pmd)
#define create_p4d_mapping(__pmdp, __va, __pa, __sz, __prot) do {} while(0)
#define create_pud_mapping(__pmdp, __va, __pa, __sz, __prot) do {} while(0)
#define create_pmd_mapping(__pmdp, __va, __pa, __sz, __prot) do {} while(0)
@@ -671,9 +661,16 @@ void __init create_pgd_mapping(pgd_t *pgdp,
static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size)
{
- /* Upgrade to PMD_SIZE mappings whenever possible */
- base &= PMD_SIZE - 1;
- if (!base && size >= PMD_SIZE)
+ if (!(base & (PGDIR_SIZE - 1)) && size >= PGDIR_SIZE)
+ return PGDIR_SIZE;
+
+ if (!(base & (P4D_SIZE - 1)) && size >= P4D_SIZE)
+ return P4D_SIZE;
+
+ if (!(base & (PUD_SIZE - 1)) && size >= PUD_SIZE)
+ return PUD_SIZE;
+
+ if (!(base & (PMD_SIZE - 1)) && size >= PMD_SIZE)
return PMD_SIZE;
return PAGE_SIZE;
@@ -732,6 +729,8 @@ static __init pgprot_t pgprot_from_va(uintptr_t va)
#endif /* CONFIG_STRICT_KERNEL_RWX */
#if defined(CONFIG_64BIT) && !defined(CONFIG_XIP_KERNEL)
+u64 __pi_set_satp_mode_from_cmdline(uintptr_t dtb_pa);
+
static void __init disable_pgtable_l5(void)
{
pgtable_l5_enabled = false;
@@ -746,17 +745,39 @@ static void __init disable_pgtable_l4(void)
satp_mode = SATP_MODE_39;
}
+static int __init print_no4lvl(char *p)
+{
+ pr_info("Disabled 4-level and 5-level paging");
+ return 0;
+}
+early_param("no4lvl", print_no4lvl);
+
+static int __init print_no5lvl(char *p)
+{
+ pr_info("Disabled 5-level paging");
+ return 0;
+}
+early_param("no5lvl", print_no5lvl);
+
/*
* There is a simple way to determine if 4-level is supported by the
* underlying hardware: establish 1:1 mapping in 4-level page table mode
* then read SATP to see if the configuration was taken into account
* meaning sv48 is supported.
*/
-static __init void set_satp_mode(void)
+static __init void set_satp_mode(uintptr_t dtb_pa)
{
u64 identity_satp, hw_satp;
uintptr_t set_satp_mode_pmd = ((unsigned long)set_satp_mode) & PMD_MASK;
- bool check_l4 = false;
+ u64 satp_mode_cmdline = __pi_set_satp_mode_from_cmdline(dtb_pa);
+
+ if (satp_mode_cmdline == SATP_MODE_57) {
+ disable_pgtable_l5();
+ } else if (satp_mode_cmdline == SATP_MODE_48) {
+ disable_pgtable_l5();
+ disable_pgtable_l4();
+ return;
+ }
create_p4d_mapping(early_p4d,
set_satp_mode_pmd, (uintptr_t)early_pud,
@@ -775,7 +796,8 @@ static __init void set_satp_mode(void)
retry:
create_pgd_mapping(early_pg_dir,
set_satp_mode_pmd,
- check_l4 ? (uintptr_t)early_pud : (uintptr_t)early_p4d,
+ pgtable_l5_enabled ?
+ (uintptr_t)early_p4d : (uintptr_t)early_pud,
PGDIR_SIZE, PAGE_TABLE);
identity_satp = PFN_DOWN((uintptr_t)&early_pg_dir) | satp_mode;
@@ -786,9 +808,8 @@ retry:
local_flush_tlb_all();
if (hw_satp != identity_satp) {
- if (!check_l4) {
+ if (pgtable_l5_enabled) {
disable_pgtable_l5();
- check_l4 = true;
memset(early_pg_dir, 0, PAGE_SIZE);
goto retry;
}
@@ -820,6 +841,44 @@ retry:
#error "setup_vm() is called from head.S before relocate so it should not use absolute addressing."
#endif
+#ifdef CONFIG_RELOCATABLE
+extern unsigned long __rela_dyn_start, __rela_dyn_end;
+
+static void __init relocate_kernel(void)
+{
+ Elf64_Rela *rela = (Elf64_Rela *)&__rela_dyn_start;
+ /*
+ * This holds the offset between the linked virtual address and the
+ * relocated virtual address.
+ */
+ uintptr_t reloc_offset = kernel_map.virt_addr - KERNEL_LINK_ADDR;
+ /*
+ * This holds the offset between kernel linked virtual address and
+ * physical address.
+ */
+ uintptr_t va_kernel_link_pa_offset = KERNEL_LINK_ADDR - kernel_map.phys_addr;
+
+ for ( ; rela < (Elf64_Rela *)&__rela_dyn_end; rela++) {
+ Elf64_Addr addr = (rela->r_offset - va_kernel_link_pa_offset);
+ Elf64_Addr relocated_addr = rela->r_addend;
+
+ if (rela->r_info != R_RISCV_RELATIVE)
+ continue;
+
+ /*
+ * Make sure to not relocate vdso symbols like rt_sigreturn
+ * which are linked from the address 0 in vmlinux since
+ * vdso symbol addresses are actually used as an offset from
+ * mm->context.vdso in VDSO_OFFSET macro.
+ */
+ if (relocated_addr >= KERNEL_LINK_ADDR)
+ relocated_addr += reloc_offset;
+
+ *(Elf64_Addr *)addr = relocated_addr;
+ }
+}
+#endif /* CONFIG_RELOCATABLE */
+
#ifdef CONFIG_XIP_KERNEL
static void __init create_kernel_page_table(pgd_t *pgdir,
__always_unused bool early)
@@ -860,32 +919,27 @@ static void __init create_kernel_page_table(pgd_t *pgdir, bool early)
* this means 2 PMD entries whereas for 32-bit kernel, this is only 1 PGDIR
* entry.
*/
-static void __init create_fdt_early_page_table(pgd_t *pgdir, uintptr_t dtb_pa)
+static void __init create_fdt_early_page_table(uintptr_t fix_fdt_va,
+ uintptr_t dtb_pa)
{
-#ifndef CONFIG_BUILTIN_DTB
uintptr_t pa = dtb_pa & ~(PMD_SIZE - 1);
- create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA,
- IS_ENABLED(CONFIG_64BIT) ? early_dtb_pgd_next : pa,
- PGDIR_SIZE,
- IS_ENABLED(CONFIG_64BIT) ? PAGE_TABLE : PAGE_KERNEL);
-
- if (pgtable_l5_enabled)
- create_p4d_mapping(early_dtb_p4d, DTB_EARLY_BASE_VA,
- (uintptr_t)early_dtb_pud, P4D_SIZE, PAGE_TABLE);
-
- if (pgtable_l4_enabled)
- create_pud_mapping(early_dtb_pud, DTB_EARLY_BASE_VA,
- (uintptr_t)early_dtb_pmd, PUD_SIZE, PAGE_TABLE);
+#ifndef CONFIG_BUILTIN_DTB
+ /* Make sure the fdt fixmap address is always aligned on PMD size */
+ BUILD_BUG_ON(FIX_FDT % (PMD_SIZE / PAGE_SIZE));
- if (IS_ENABLED(CONFIG_64BIT)) {
- create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA,
+ /* In 32-bit only, the fdt lies in its own PGD */
+ if (!IS_ENABLED(CONFIG_64BIT)) {
+ create_pgd_mapping(early_pg_dir, fix_fdt_va,
+ pa, MAX_FDT_SIZE, PAGE_KERNEL);
+ } else {
+ create_pmd_mapping(fixmap_pmd, fix_fdt_va,
pa, PMD_SIZE, PAGE_KERNEL);
- create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA + PMD_SIZE,
+ create_pmd_mapping(fixmap_pmd, fix_fdt_va + PMD_SIZE,
pa + PMD_SIZE, PMD_SIZE, PAGE_KERNEL);
}
- dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PMD_SIZE - 1));
+ dtb_early_va = (void *)fix_fdt_va + (dtb_pa & (PMD_SIZE - 1));
#else
/*
* For 64-bit kernel, __va can't be used since it would return a linear
@@ -979,14 +1033,25 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
#endif
#if defined(CONFIG_64BIT) && !defined(CONFIG_XIP_KERNEL)
- set_satp_mode();
+ set_satp_mode(dtb_pa);
#endif
- kernel_map.va_pa_offset = PAGE_OFFSET - kernel_map.phys_addr;
+ /*
+ * In 64-bit, we defer the setup of va_pa_offset to setup_bootmem,
+ * where we have the system memory layout: this allows us to align
+ * the physical and virtual mappings and then make use of PUD/P4D/PGD
+ * for the linear mapping. This is only possible because the kernel
+ * mapping lies outside the linear mapping.
+ * In 32-bit however, as the kernel resides in the linear mapping,
+ * setup_vm_final can not change the mapping established here,
+ * otherwise the same kernel addresses would get mapped to different
+ * physical addresses (if the start of dram is different from the
+ * kernel physical address start).
+ */
+ kernel_map.va_pa_offset = IS_ENABLED(CONFIG_64BIT) ?
+ 0UL : PAGE_OFFSET - kernel_map.phys_addr;
kernel_map.va_kernel_pa_offset = kernel_map.virt_addr - kernel_map.phys_addr;
- riscv_pfn_base = PFN_DOWN(kernel_map.phys_addr);
-
/*
* The default maximal physical memory size is KERN_VIRT_SIZE for 32-bit
* kernel, whereas for 64-bit kernel, the end of the virtual address
@@ -1007,6 +1072,17 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
BUG_ON((kernel_map.virt_addr + kernel_map.size) > ADDRESS_SPACE_END - SZ_4K);
#endif
+#ifdef CONFIG_RELOCATABLE
+ /*
+ * Early page table uses only one PUD, which makes it possible
+ * to map PUD_SIZE aligned on PUD_SIZE: if the relocation offset
+ * makes the kernel cross over a PUD_SIZE boundary, raise a bug
+ * since a part of the kernel would not get mapped.
+ */
+ BUG_ON(PUD_SIZE - (kernel_map.virt_addr & (PUD_SIZE - 1)) < kernel_map.size);
+ relocate_kernel();
+#endif
+
apply_early_boot_alternatives();
pt_ops_set_early();
@@ -1055,7 +1131,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
create_kernel_page_table(early_pg_dir, true);
/* Setup early mapping for FDT early scan */
- create_fdt_early_page_table(early_pg_dir, dtb_pa);
+ create_fdt_early_page_table(__fix_to_virt(FIX_FDT), dtb_pa);
/*
* Bootime fixmap only can handle PMD_SIZE mapping. Thus, boot-ioremap
@@ -1090,16 +1166,36 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
pt_ops_set_fixmap();
}
-static void __init setup_vm_final(void)
+static void __init create_linear_mapping_range(phys_addr_t start,
+ phys_addr_t end)
{
+ phys_addr_t pa;
uintptr_t va, map_size;
- phys_addr_t pa, start, end;
+
+ for (pa = start; pa < end; pa += map_size) {
+ va = (uintptr_t)__va(pa);
+ map_size = best_map_size(pa, end - pa);
+
+ create_pgd_mapping(swapper_pg_dir, va, pa, map_size,
+ pgprot_from_va(va));
+ }
+}
+
+static void __init create_linear_mapping_page_table(void)
+{
+ phys_addr_t start, end;
u64 i;
- /* Setup swapper PGD for fixmap */
- create_pgd_mapping(swapper_pg_dir, FIXADDR_START,
- __pa_symbol(fixmap_pgd_next),
- PGDIR_SIZE, PAGE_TABLE);
+#ifdef CONFIG_STRICT_KERNEL_RWX
+ phys_addr_t ktext_start = __pa_symbol(_start);
+ phys_addr_t ktext_size = __init_data_begin - _start;
+ phys_addr_t krodata_start = __pa_symbol(__start_rodata);
+ phys_addr_t krodata_size = _data - __start_rodata;
+
+ /* Isolate kernel text and rodata so they don't get mapped with a PUD */
+ memblock_mark_nomap(ktext_start, ktext_size);
+ memblock_mark_nomap(krodata_start, krodata_size);
+#endif
/* Map all memory banks in the linear mapping */
for_each_mem_range(i, &start, &end) {
@@ -1111,15 +1207,39 @@ static void __init setup_vm_final(void)
if (end >= __pa(PAGE_OFFSET) + memory_limit)
end = __pa(PAGE_OFFSET) + memory_limit;
- for (pa = start; pa < end; pa += map_size) {
- va = (uintptr_t)__va(pa);
- map_size = best_map_size(pa, end - pa);
-
- create_pgd_mapping(swapper_pg_dir, va, pa, map_size,
- pgprot_from_va(va));
- }
+ create_linear_mapping_range(start, end);
}
+#ifdef CONFIG_STRICT_KERNEL_RWX
+ create_linear_mapping_range(ktext_start, ktext_start + ktext_size);
+ create_linear_mapping_range(krodata_start,
+ krodata_start + krodata_size);
+
+ memblock_clear_nomap(ktext_start, ktext_size);
+ memblock_clear_nomap(krodata_start, krodata_size);
+#endif
+}
+
+static void __init setup_vm_final(void)
+{
+ /* Setup swapper PGD for fixmap */
+#if !defined(CONFIG_64BIT)
+ /*
+ * In 32-bit, the device tree lies in a pgd entry, so it must be copied
+ * directly in swapper_pg_dir in addition to the pgd entry that points
+ * to fixmap_pte.
+ */
+ unsigned long idx = pgd_index(__fix_to_virt(FIX_FDT));
+
+ set_pgd(&swapper_pg_dir[idx], early_pg_dir[idx]);
+#endif
+ create_pgd_mapping(swapper_pg_dir, FIXADDR_START,
+ __pa_symbol(fixmap_pgd_next),
+ PGDIR_SIZE, PAGE_TABLE);
+
+ /* Map the linear mapping */
+ create_linear_mapping_page_table();
+
/* Map the kernel */
if (IS_ENABLED(CONFIG_64BIT))
create_kernel_page_table(swapper_pg_dir, false);
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index e1226709490f..8fc0efcf905c 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -18,58 +18,48 @@
* For sv39, the region is aligned on PGDIR_SIZE so we only need to populate
* the page global directory with kasan_early_shadow_pmd.
*
- * For sv48 and sv57, the region is not aligned on PGDIR_SIZE so the mapping
- * must be divided as follows:
- * - the first PGD entry, although incomplete, is populated with
- * kasan_early_shadow_pud/p4d
- * - the PGD entries in the middle are populated with kasan_early_shadow_pud/p4d
- * - the last PGD entry is shared with the kernel mapping so populated at the
- * lower levels pud/p4d
- *
- * In addition, when shallow populating a kasan region (for example vmalloc),
- * this region may also not be aligned on PGDIR size, so we must go down to the
- * pud level too.
+ * For sv48 and sv57, the region start is aligned on PGDIR_SIZE whereas the end
+ * region is not and then we have to go down to the PUD level.
*/
extern pgd_t early_pg_dir[PTRS_PER_PGD];
+pgd_t tmp_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
+p4d_t tmp_p4d[PTRS_PER_P4D] __page_aligned_bss;
+pud_t tmp_pud[PTRS_PER_PUD] __page_aligned_bss;
static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned long end)
{
phys_addr_t phys_addr;
- pte_t *ptep, *base_pte;
+ pte_t *ptep, *p;
- if (pmd_none(*pmd))
- base_pte = memblock_alloc(PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE);
- else
- base_pte = (pte_t *)pmd_page_vaddr(*pmd);
+ if (pmd_none(*pmd)) {
+ p = memblock_alloc(PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE);
+ set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(p)), PAGE_TABLE));
+ }
- ptep = base_pte + pte_index(vaddr);
+ ptep = pte_offset_kernel(pmd, vaddr);
do {
if (pte_none(*ptep)) {
phys_addr = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
set_pte(ptep, pfn_pte(PFN_DOWN(phys_addr), PAGE_KERNEL));
+ memset(__va(phys_addr), KASAN_SHADOW_INIT, PAGE_SIZE);
}
} while (ptep++, vaddr += PAGE_SIZE, vaddr != end);
-
- set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(base_pte)), PAGE_TABLE));
}
static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned long end)
{
phys_addr_t phys_addr;
- pmd_t *pmdp, *base_pmd;
+ pmd_t *pmdp, *p;
unsigned long next;
if (pud_none(*pud)) {
- base_pmd = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE);
- } else {
- base_pmd = (pmd_t *)pud_pgtable(*pud);
- if (base_pmd == lm_alias(kasan_early_shadow_pmd))
- base_pmd = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE);
+ p = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE);
+ set_pud(pud, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE));
}
- pmdp = base_pmd + pmd_index(vaddr);
+ pmdp = pmd_offset(pud, vaddr);
do {
next = pmd_addr_end(vaddr, end);
@@ -78,157 +68,77 @@ static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned
phys_addr = memblock_phys_alloc(PMD_SIZE, PMD_SIZE);
if (phys_addr) {
set_pmd(pmdp, pfn_pmd(PFN_DOWN(phys_addr), PAGE_KERNEL));
+ memset(__va(phys_addr), KASAN_SHADOW_INIT, PMD_SIZE);
continue;
}
}
kasan_populate_pte(pmdp, vaddr, next);
} while (pmdp++, vaddr = next, vaddr != end);
-
- /*
- * Wait for the whole PGD to be populated before setting the PGD in
- * the page table, otherwise, if we did set the PGD before populating
- * it entirely, memblock could allocate a page at a physical address
- * where KASAN is not populated yet and then we'd get a page fault.
- */
- set_pud(pud, pfn_pud(PFN_DOWN(__pa(base_pmd)), PAGE_TABLE));
}
-static void __init kasan_populate_pud(pgd_t *pgd,
- unsigned long vaddr, unsigned long end,
- bool early)
+static void __init kasan_populate_pud(p4d_t *p4d,
+ unsigned long vaddr, unsigned long end)
{
phys_addr_t phys_addr;
- pud_t *pudp, *base_pud;
+ pud_t *pudp, *p;
unsigned long next;
- if (early) {
- /*
- * We can't use pgd_page_vaddr here as it would return a linear
- * mapping address but it is not mapped yet, but when populating
- * early_pg_dir, we need the physical address and when populating
- * swapper_pg_dir, we need the kernel virtual address so use
- * pt_ops facility.
- */
- base_pud = pt_ops.get_pud_virt(pfn_to_phys(_pgd_pfn(*pgd)));
- } else if (pgd_none(*pgd)) {
- base_pud = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE);
- memcpy(base_pud, (void *)kasan_early_shadow_pud,
- sizeof(pud_t) * PTRS_PER_PUD);
- } else {
- base_pud = (pud_t *)pgd_page_vaddr(*pgd);
- if (base_pud == lm_alias(kasan_early_shadow_pud)) {
- base_pud = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE);
- memcpy(base_pud, (void *)kasan_early_shadow_pud,
- sizeof(pud_t) * PTRS_PER_PUD);
- }
+ if (p4d_none(*p4d)) {
+ p = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE);
+ set_p4d(p4d, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE));
}
- pudp = base_pud + pud_index(vaddr);
+ pudp = pud_offset(p4d, vaddr);
do {
next = pud_addr_end(vaddr, end);
if (pud_none(*pudp) && IS_ALIGNED(vaddr, PUD_SIZE) && (next - vaddr) >= PUD_SIZE) {
- if (early) {
- phys_addr = __pa(((uintptr_t)kasan_early_shadow_pmd));
- set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_TABLE));
+ phys_addr = memblock_phys_alloc(PUD_SIZE, PUD_SIZE);
+ if (phys_addr) {
+ set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_KERNEL));
+ memset(__va(phys_addr), KASAN_SHADOW_INIT, PUD_SIZE);
continue;
- } else {
- phys_addr = memblock_phys_alloc(PUD_SIZE, PUD_SIZE);
- if (phys_addr) {
- set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_KERNEL));
- continue;
- }
}
}
kasan_populate_pmd(pudp, vaddr, next);
} while (pudp++, vaddr = next, vaddr != end);
-
- /*
- * Wait for the whole PGD to be populated before setting the PGD in
- * the page table, otherwise, if we did set the PGD before populating
- * it entirely, memblock could allocate a page at a physical address
- * where KASAN is not populated yet and then we'd get a page fault.
- */
- if (!early)
- set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(base_pud)), PAGE_TABLE));
}
static void __init kasan_populate_p4d(pgd_t *pgd,
- unsigned long vaddr, unsigned long end,
- bool early)
+ unsigned long vaddr, unsigned long end)
{
phys_addr_t phys_addr;
- p4d_t *p4dp, *base_p4d;
+ p4d_t *p4dp, *p;
unsigned long next;
- if (early) {
- /*
- * We can't use pgd_page_vaddr here as it would return a linear
- * mapping address but it is not mapped yet, but when populating
- * early_pg_dir, we need the physical address and when populating
- * swapper_pg_dir, we need the kernel virtual address so use
- * pt_ops facility.
- */
- base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgd)));
- } else {
- base_p4d = (p4d_t *)pgd_page_vaddr(*pgd);
- if (base_p4d == lm_alias(kasan_early_shadow_p4d)) {
- base_p4d = memblock_alloc(PTRS_PER_PUD * sizeof(p4d_t), PAGE_SIZE);
- memcpy(base_p4d, (void *)kasan_early_shadow_p4d,
- sizeof(p4d_t) * PTRS_PER_P4D);
- }
+ if (pgd_none(*pgd)) {
+ p = memblock_alloc(PTRS_PER_P4D * sizeof(p4d_t), PAGE_SIZE);
+ set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE));
}
- p4dp = base_p4d + p4d_index(vaddr);
+ p4dp = p4d_offset(pgd, vaddr);
do {
next = p4d_addr_end(vaddr, end);
if (p4d_none(*p4dp) && IS_ALIGNED(vaddr, P4D_SIZE) && (next - vaddr) >= P4D_SIZE) {
- if (early) {
- phys_addr = __pa(((uintptr_t)kasan_early_shadow_pud));
- set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_TABLE));
+ phys_addr = memblock_phys_alloc(P4D_SIZE, P4D_SIZE);
+ if (phys_addr) {
+ set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_KERNEL));
+ memset(__va(phys_addr), KASAN_SHADOW_INIT, P4D_SIZE);
continue;
- } else {
- phys_addr = memblock_phys_alloc(P4D_SIZE, P4D_SIZE);
- if (phys_addr) {
- set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_KERNEL));
- continue;
- }
}
}
- kasan_populate_pud((pgd_t *)p4dp, vaddr, next, early);
+ kasan_populate_pud(p4dp, vaddr, next);
} while (p4dp++, vaddr = next, vaddr != end);
-
- /*
- * Wait for the whole P4D to be populated before setting the P4D in
- * the page table, otherwise, if we did set the P4D before populating
- * it entirely, memblock could allocate a page at a physical address
- * where KASAN is not populated yet and then we'd get a page fault.
- */
- if (!early)
- set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(base_p4d)), PAGE_TABLE));
}
-#define kasan_early_shadow_pgd_next (pgtable_l5_enabled ? \
- (uintptr_t)kasan_early_shadow_p4d : \
- (pgtable_l4_enabled ? \
- (uintptr_t)kasan_early_shadow_pud : \
- (uintptr_t)kasan_early_shadow_pmd))
-#define kasan_populate_pgd_next(pgdp, vaddr, next, early) \
- (pgtable_l5_enabled ? \
- kasan_populate_p4d(pgdp, vaddr, next, early) : \
- (pgtable_l4_enabled ? \
- kasan_populate_pud(pgdp, vaddr, next, early) : \
- kasan_populate_pmd((pud_t *)pgdp, vaddr, next)))
-
static void __init kasan_populate_pgd(pgd_t *pgdp,
- unsigned long vaddr, unsigned long end,
- bool early)
+ unsigned long vaddr, unsigned long end)
{
phys_addr_t phys_addr;
unsigned long next;
@@ -236,29 +146,174 @@ static void __init kasan_populate_pgd(pgd_t *pgdp,
do {
next = pgd_addr_end(vaddr, end);
- if (IS_ALIGNED(vaddr, PGDIR_SIZE) && (next - vaddr) >= PGDIR_SIZE) {
- if (early) {
- phys_addr = __pa((uintptr_t)kasan_early_shadow_pgd_next);
- set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_TABLE));
+ if (pgd_none(*pgdp) && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
+ (next - vaddr) >= PGDIR_SIZE) {
+ phys_addr = memblock_phys_alloc(PGDIR_SIZE, PGDIR_SIZE);
+ if (phys_addr) {
+ set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_KERNEL));
+ memset(__va(phys_addr), KASAN_SHADOW_INIT, PGDIR_SIZE);
continue;
- } else if (pgd_page_vaddr(*pgdp) ==
- (unsigned long)lm_alias(kasan_early_shadow_pgd_next)) {
- /*
- * pgdp can't be none since kasan_early_init
- * initialized all KASAN shadow region with
- * kasan_early_shadow_pud: if this is still the
- * case, that means we can try to allocate a
- * hugepage as a replacement.
- */
- phys_addr = memblock_phys_alloc(PGDIR_SIZE, PGDIR_SIZE);
- if (phys_addr) {
- set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_KERNEL));
- continue;
- }
}
}
- kasan_populate_pgd_next(pgdp, vaddr, next, early);
+ kasan_populate_p4d(pgdp, vaddr, next);
+ } while (pgdp++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_early_clear_pud(p4d_t *p4dp,
+ unsigned long vaddr, unsigned long end)
+{
+ pud_t *pudp, *base_pud;
+ unsigned long next;
+
+ if (!pgtable_l4_enabled) {
+ pudp = (pud_t *)p4dp;
+ } else {
+ base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(*p4dp)));
+ pudp = base_pud + pud_index(vaddr);
+ }
+
+ do {
+ next = pud_addr_end(vaddr, end);
+
+ if (IS_ALIGNED(vaddr, PUD_SIZE) && (next - vaddr) >= PUD_SIZE) {
+ pud_clear(pudp);
+ continue;
+ }
+
+ BUG();
+ } while (pudp++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_early_clear_p4d(pgd_t *pgdp,
+ unsigned long vaddr, unsigned long end)
+{
+ p4d_t *p4dp, *base_p4d;
+ unsigned long next;
+
+ if (!pgtable_l5_enabled) {
+ p4dp = (p4d_t *)pgdp;
+ } else {
+ base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgdp)));
+ p4dp = base_p4d + p4d_index(vaddr);
+ }
+
+ do {
+ next = p4d_addr_end(vaddr, end);
+
+ if (pgtable_l4_enabled && IS_ALIGNED(vaddr, P4D_SIZE) &&
+ (next - vaddr) >= P4D_SIZE) {
+ p4d_clear(p4dp);
+ continue;
+ }
+
+ kasan_early_clear_pud(p4dp, vaddr, next);
+ } while (p4dp++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_early_clear_pgd(pgd_t *pgdp,
+ unsigned long vaddr, unsigned long end)
+{
+ unsigned long next;
+
+ do {
+ next = pgd_addr_end(vaddr, end);
+
+ if (pgtable_l5_enabled && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
+ (next - vaddr) >= PGDIR_SIZE) {
+ pgd_clear(pgdp);
+ continue;
+ }
+
+ kasan_early_clear_p4d(pgdp, vaddr, next);
+ } while (pgdp++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_early_populate_pud(p4d_t *p4dp,
+ unsigned long vaddr,
+ unsigned long end)
+{
+ pud_t *pudp, *base_pud;
+ phys_addr_t phys_addr;
+ unsigned long next;
+
+ if (!pgtable_l4_enabled) {
+ pudp = (pud_t *)p4dp;
+ } else {
+ base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(*p4dp)));
+ pudp = base_pud + pud_index(vaddr);
+ }
+
+ do {
+ next = pud_addr_end(vaddr, end);
+
+ if (pud_none(*pudp) && IS_ALIGNED(vaddr, PUD_SIZE) &&
+ (next - vaddr) >= PUD_SIZE) {
+ phys_addr = __pa((uintptr_t)kasan_early_shadow_pmd);
+ set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_TABLE));
+ continue;
+ }
+
+ BUG();
+ } while (pudp++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_early_populate_p4d(pgd_t *pgdp,
+ unsigned long vaddr,
+ unsigned long end)
+{
+ p4d_t *p4dp, *base_p4d;
+ phys_addr_t phys_addr;
+ unsigned long next;
+
+ /*
+ * We can't use pgd_page_vaddr here as it would return a linear
+ * mapping address but it is not mapped yet, but when populating
+ * early_pg_dir, we need the physical address and when populating
+ * swapper_pg_dir, we need the kernel virtual address so use
+ * pt_ops facility.
+ * Note that this test is then completely equivalent to
+ * p4dp = p4d_offset(pgdp, vaddr)
+ */
+ if (!pgtable_l5_enabled) {
+ p4dp = (p4d_t *)pgdp;
+ } else {
+ base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgdp)));
+ p4dp = base_p4d + p4d_index(vaddr);
+ }
+
+ do {
+ next = p4d_addr_end(vaddr, end);
+
+ if (p4d_none(*p4dp) && IS_ALIGNED(vaddr, P4D_SIZE) &&
+ (next - vaddr) >= P4D_SIZE) {
+ phys_addr = __pa((uintptr_t)kasan_early_shadow_pud);
+ set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_TABLE));
+ continue;
+ }
+
+ kasan_early_populate_pud(p4dp, vaddr, next);
+ } while (p4dp++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_early_populate_pgd(pgd_t *pgdp,
+ unsigned long vaddr,
+ unsigned long end)
+{
+ phys_addr_t phys_addr;
+ unsigned long next;
+
+ do {
+ next = pgd_addr_end(vaddr, end);
+
+ if (pgd_none(*pgdp) && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
+ (next - vaddr) >= PGDIR_SIZE) {
+ phys_addr = __pa((uintptr_t)kasan_early_shadow_p4d);
+ set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_TABLE));
+ continue;
+ }
+
+ kasan_early_populate_p4d(pgdp, vaddr, next);
} while (pgdp++, vaddr = next, vaddr != end);
}
@@ -295,16 +350,16 @@ asmlinkage void __init kasan_early_init(void)
PAGE_TABLE));
}
- kasan_populate_pgd(early_pg_dir + pgd_index(KASAN_SHADOW_START),
- KASAN_SHADOW_START, KASAN_SHADOW_END, true);
+ kasan_early_populate_pgd(early_pg_dir + pgd_index(KASAN_SHADOW_START),
+ KASAN_SHADOW_START, KASAN_SHADOW_END);
local_flush_tlb_all();
}
void __init kasan_swapper_init(void)
{
- kasan_populate_pgd(pgd_offset_k(KASAN_SHADOW_START),
- KASAN_SHADOW_START, KASAN_SHADOW_END, true);
+ kasan_early_populate_pgd(pgd_offset_k(KASAN_SHADOW_START),
+ KASAN_SHADOW_START, KASAN_SHADOW_END);
local_flush_tlb_all();
}
@@ -314,118 +369,65 @@ static void __init kasan_populate(void *start, void *end)
unsigned long vaddr = (unsigned long)start & PAGE_MASK;
unsigned long vend = PAGE_ALIGN((unsigned long)end);
- kasan_populate_pgd(pgd_offset_k(vaddr), vaddr, vend, false);
-
- local_flush_tlb_all();
- memset(start, KASAN_SHADOW_INIT, end - start);
+ kasan_populate_pgd(pgd_offset_k(vaddr), vaddr, vend);
}
-static void __init kasan_shallow_populate_pmd(pgd_t *pgdp,
+static void __init kasan_shallow_populate_pud(p4d_t *p4d,
unsigned long vaddr, unsigned long end)
{
unsigned long next;
- pmd_t *pmdp, *base_pmd;
- bool is_kasan_pte;
-
- base_pmd = (pmd_t *)pgd_page_vaddr(*pgdp);
- pmdp = base_pmd + pmd_index(vaddr);
-
- do {
- next = pmd_addr_end(vaddr, end);
- is_kasan_pte = (pmd_pgtable(*pmdp) == lm_alias(kasan_early_shadow_pte));
-
- if (is_kasan_pte)
- pmd_clear(pmdp);
- } while (pmdp++, vaddr = next, vaddr != end);
-}
-
-static void __init kasan_shallow_populate_pud(pgd_t *pgdp,
- unsigned long vaddr, unsigned long end)
-{
- unsigned long next;
- pud_t *pudp, *base_pud;
- pmd_t *base_pmd;
- bool is_kasan_pmd;
-
- base_pud = (pud_t *)pgd_page_vaddr(*pgdp);
- pudp = base_pud + pud_index(vaddr);
+ void *p;
+ pud_t *pud_k = pud_offset(p4d, vaddr);
do {
next = pud_addr_end(vaddr, end);
- is_kasan_pmd = (pud_pgtable(*pudp) == lm_alias(kasan_early_shadow_pmd));
-
- if (!is_kasan_pmd)
- continue;
-
- base_pmd = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
- set_pud(pudp, pfn_pud(PFN_DOWN(__pa(base_pmd)), PAGE_TABLE));
- if (IS_ALIGNED(vaddr, PUD_SIZE) && (next - vaddr) >= PUD_SIZE)
+ if (pud_none(*pud_k)) {
+ p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+ set_pud(pud_k, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE));
continue;
+ }
- memcpy(base_pmd, (void *)kasan_early_shadow_pmd, PAGE_SIZE);
- kasan_shallow_populate_pmd((pgd_t *)pudp, vaddr, next);
- } while (pudp++, vaddr = next, vaddr != end);
+ BUG();
+ } while (pud_k++, vaddr = next, vaddr != end);
}
-static void __init kasan_shallow_populate_p4d(pgd_t *pgdp,
+static void __init kasan_shallow_populate_p4d(pgd_t *pgd,
unsigned long vaddr, unsigned long end)
{
unsigned long next;
- p4d_t *p4dp, *base_p4d;
- pud_t *base_pud;
- bool is_kasan_pud;
-
- base_p4d = (p4d_t *)pgd_page_vaddr(*pgdp);
- p4dp = base_p4d + p4d_index(vaddr);
+ void *p;
+ p4d_t *p4d_k = p4d_offset(pgd, vaddr);
do {
next = p4d_addr_end(vaddr, end);
- is_kasan_pud = (p4d_pgtable(*p4dp) == lm_alias(kasan_early_shadow_pud));
- if (!is_kasan_pud)
- continue;
-
- base_pud = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
- set_p4d(p4dp, pfn_p4d(PFN_DOWN(__pa(base_pud)), PAGE_TABLE));
-
- if (IS_ALIGNED(vaddr, P4D_SIZE) && (next - vaddr) >= P4D_SIZE)
+ if (p4d_none(*p4d_k)) {
+ p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+ set_p4d(p4d_k, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE));
continue;
+ }
- memcpy(base_pud, (void *)kasan_early_shadow_pud, PAGE_SIZE);
- kasan_shallow_populate_pud((pgd_t *)p4dp, vaddr, next);
- } while (p4dp++, vaddr = next, vaddr != end);
+ kasan_shallow_populate_pud(p4d_k, vaddr, end);
+ } while (p4d_k++, vaddr = next, vaddr != end);
}
-#define kasan_shallow_populate_pgd_next(pgdp, vaddr, next) \
- (pgtable_l5_enabled ? \
- kasan_shallow_populate_p4d(pgdp, vaddr, next) : \
- (pgtable_l4_enabled ? \
- kasan_shallow_populate_pud(pgdp, vaddr, next) : \
- kasan_shallow_populate_pmd(pgdp, vaddr, next)))
-
static void __init kasan_shallow_populate_pgd(unsigned long vaddr, unsigned long end)
{
unsigned long next;
void *p;
pgd_t *pgd_k = pgd_offset_k(vaddr);
- bool is_kasan_pgd_next;
do {
next = pgd_addr_end(vaddr, end);
- is_kasan_pgd_next = (pgd_page_vaddr(*pgd_k) ==
- (unsigned long)lm_alias(kasan_early_shadow_pgd_next));
- if (is_kasan_pgd_next) {
+ if (pgd_none(*pgd_k)) {
p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
set_pgd(pgd_k, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE));
- }
-
- if (IS_ALIGNED(vaddr, PGDIR_SIZE) && (next - vaddr) >= PGDIR_SIZE)
continue;
+ }
- memcpy(p, (void *)kasan_early_shadow_pgd_next, PAGE_SIZE);
- kasan_shallow_populate_pgd_next(pgd_k, vaddr, next);
+ kasan_shallow_populate_p4d(pgd_k, vaddr, next);
} while (pgd_k++, vaddr = next, vaddr != end);
}
@@ -435,7 +437,37 @@ static void __init kasan_shallow_populate(void *start, void *end)
unsigned long vend = PAGE_ALIGN((unsigned long)end);
kasan_shallow_populate_pgd(vaddr, vend);
- local_flush_tlb_all();
+}
+
+static void create_tmp_mapping(void)
+{
+ void *ptr;
+ p4d_t *base_p4d;
+
+ /*
+ * We need to clean the early mapping: this is hard to achieve "in-place",
+ * so install a temporary mapping like arm64 and x86 do.
+ */
+ memcpy(tmp_pg_dir, swapper_pg_dir, sizeof(pgd_t) * PTRS_PER_PGD);
+
+ /* Copy the last p4d since it is shared with the kernel mapping. */
+ if (pgtable_l5_enabled) {
+ ptr = (p4d_t *)pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_END));
+ memcpy(tmp_p4d, ptr, sizeof(p4d_t) * PTRS_PER_P4D);
+ set_pgd(&tmp_pg_dir[pgd_index(KASAN_SHADOW_END)],
+ pfn_pgd(PFN_DOWN(__pa(tmp_p4d)), PAGE_TABLE));
+ base_p4d = tmp_p4d;
+ } else {
+ base_p4d = (p4d_t *)tmp_pg_dir;
+ }
+
+ /* Copy the last pud since it is shared with the kernel mapping. */
+ if (pgtable_l4_enabled) {
+ ptr = (pud_t *)p4d_page_vaddr(*(base_p4d + p4d_index(KASAN_SHADOW_END)));
+ memcpy(tmp_pud, ptr, sizeof(pud_t) * PTRS_PER_PUD);
+ set_p4d(&base_p4d[p4d_index(KASAN_SHADOW_END)],
+ pfn_p4d(PFN_DOWN(__pa(tmp_pud)), PAGE_TABLE));
+ }
}
void __init kasan_init(void)
@@ -443,10 +475,27 @@ void __init kasan_init(void)
phys_addr_t p_start, p_end;
u64 i;
- if (IS_ENABLED(CONFIG_KASAN_VMALLOC))
+ create_tmp_mapping();
+ csr_write(CSR_SATP, PFN_DOWN(__pa(tmp_pg_dir)) | satp_mode);
+
+ kasan_early_clear_pgd(pgd_offset_k(KASAN_SHADOW_START),
+ KASAN_SHADOW_START, KASAN_SHADOW_END);
+
+ kasan_populate_early_shadow((void *)kasan_mem_to_shadow((void *)FIXADDR_START),
+ (void *)kasan_mem_to_shadow((void *)VMALLOC_START));
+
+ if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
kasan_shallow_populate(
(void *)kasan_mem_to_shadow((void *)VMALLOC_START),
(void *)kasan_mem_to_shadow((void *)VMALLOC_END));
+ /* Shallow populate modules and BPF which are vmalloc-allocated */
+ kasan_shallow_populate(
+ (void *)kasan_mem_to_shadow((void *)MODULES_VADDR),
+ (void *)kasan_mem_to_shadow((void *)MODULES_END));
+ } else {
+ kasan_populate_early_shadow((void *)kasan_mem_to_shadow((void *)VMALLOC_START),
+ (void *)kasan_mem_to_shadow((void *)VMALLOC_END));
+ }
/* Populate the linear mapping */
for_each_mem_range(i, &p_start, &p_end) {
@@ -459,8 +508,8 @@ void __init kasan_init(void)
kasan_populate(kasan_mem_to_shadow(start), kasan_mem_to_shadow(end));
}
- /* Populate kernel, BPF, modules mapping */
- kasan_populate(kasan_mem_to_shadow((const void *)MODULES_VADDR),
+ /* Populate kernel */
+ kasan_populate(kasan_mem_to_shadow((const void *)MODULES_END),
kasan_mem_to_shadow((const void *)MODULES_VADDR + SZ_2G));
for (i = 0; i < PTRS_PER_PTE; i++)
@@ -471,4 +520,7 @@ void __init kasan_init(void)
memset(kasan_early_shadow_page, KASAN_SHADOW_INIT, PAGE_SIZE);
init_task.kasan_depth = 0;
+
+ csr_write(CSR_SATP, PFN_DOWN(__pa(swapper_pg_dir)) | satp_mode);
+ local_flush_tlb_all();
}
diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c
index 86c56616e5de..ea3d61de065b 100644
--- a/arch/riscv/mm/pageattr.c
+++ b/arch/riscv/mm/pageattr.c
@@ -217,18 +217,26 @@ bool kernel_page_present(struct page *page)
pgd = pgd_offset_k(addr);
if (!pgd_present(*pgd))
return false;
+ if (pgd_leaf(*pgd))
+ return true;
p4d = p4d_offset(pgd, addr);
if (!p4d_present(*p4d))
return false;
+ if (p4d_leaf(*p4d))
+ return true;
pud = pud_offset(p4d, addr);
if (!pud_present(*pud))
return false;
+ if (pud_leaf(*pud))
+ return true;
pmd = pmd_offset(pud, addr);
if (!pmd_present(*pmd))
return false;
+ if (pmd_leaf(*pmd))
+ return true;
pte = pte_offset_kernel(pmd, addr);
return pte_present(*pte);
diff --git a/arch/riscv/mm/physaddr.c b/arch/riscv/mm/physaddr.c
index 9b18bda74154..18706f457da7 100644
--- a/arch/riscv/mm/physaddr.c
+++ b/arch/riscv/mm/physaddr.c
@@ -33,3 +33,19 @@ phys_addr_t __phys_addr_symbol(unsigned long x)
return __va_to_pa_nodebug(x);
}
EXPORT_SYMBOL(__phys_addr_symbol);
+
+phys_addr_t linear_mapping_va_to_pa(unsigned long x)
+{
+ BUG_ON(!kernel_map.va_pa_offset);
+
+ return ((unsigned long)(x) - kernel_map.va_pa_offset);
+}
+EXPORT_SYMBOL(linear_mapping_va_to_pa);
+
+void *linear_mapping_pa_to_va(unsigned long x)
+{
+ BUG_ON(!kernel_map.va_pa_offset);
+
+ return ((void *)((unsigned long)(x) + kernel_map.va_pa_offset));
+}
+EXPORT_SYMBOL(linear_mapping_pa_to_va);
diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c
index 830e7de65e3a..20a9f991a6d7 100644
--- a/arch/riscv/mm/ptdump.c
+++ b/arch/riscv/mm/ptdump.c
@@ -59,10 +59,6 @@ struct ptd_mm_info {
};
enum address_markers_idx {
-#ifdef CONFIG_KASAN
- KASAN_SHADOW_START_NR,
- KASAN_SHADOW_END_NR,
-#endif
FIXMAP_START_NR,
FIXMAP_END_NR,
PCI_IO_START_NR,
@@ -74,6 +70,10 @@ enum address_markers_idx {
VMALLOC_START_NR,
VMALLOC_END_NR,
PAGE_OFFSET_NR,
+#ifdef CONFIG_KASAN
+ KASAN_SHADOW_START_NR,
+ KASAN_SHADOW_END_NR,
+#endif
#ifdef CONFIG_64BIT
MODULES_MAPPING_NR,
KERNEL_MAPPING_NR,
@@ -82,10 +82,6 @@ enum address_markers_idx {
};
static struct addr_marker address_markers[] = {
-#ifdef CONFIG_KASAN
- {0, "Kasan shadow start"},
- {0, "Kasan shadow end"},
-#endif
{0, "Fixmap start"},
{0, "Fixmap end"},
{0, "PCI I/O start"},
@@ -97,6 +93,10 @@ static struct addr_marker address_markers[] = {
{0, "vmalloc() area"},
{0, "vmalloc() end"},
{0, "Linear mapping"},
+#ifdef CONFIG_KASAN
+ {0, "Kasan shadow start"},
+ {0, "Kasan shadow end"},
+#endif
#ifdef CONFIG_64BIT
{0, "Modules/BPF mapping"},
{0, "Kernel mapping"},
@@ -362,10 +362,6 @@ static int __init ptdump_init(void)
{
unsigned int i, j;
-#ifdef CONFIG_KASAN
- address_markers[KASAN_SHADOW_START_NR].start_address = KASAN_SHADOW_START;
- address_markers[KASAN_SHADOW_END_NR].start_address = KASAN_SHADOW_END;
-#endif
address_markers[FIXMAP_START_NR].start_address = FIXADDR_START;
address_markers[FIXMAP_END_NR].start_address = FIXADDR_TOP;
address_markers[PCI_IO_START_NR].start_address = PCI_IO_START;
@@ -377,6 +373,10 @@ static int __init ptdump_init(void)
address_markers[VMALLOC_START_NR].start_address = VMALLOC_START;
address_markers[VMALLOC_END_NR].start_address = VMALLOC_END;
address_markers[PAGE_OFFSET_NR].start_address = PAGE_OFFSET;
+#ifdef CONFIG_KASAN
+ address_markers[KASAN_SHADOW_START_NR].start_address = KASAN_SHADOW_START;
+ address_markers[KASAN_SHADOW_END_NR].start_address = KASAN_SHADOW_END;
+#endif
#ifdef CONFIG_64BIT
address_markers[MODULES_MAPPING_NR].start_address = MODULES_VADDR;
address_markers[KERNEL_MAPPING_NR].start_address = kernel_map.virt_addr;
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index ef701fa83f36..77be59aadc73 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -23,14 +23,62 @@ static inline void local_flush_tlb_page_asid(unsigned long addr,
: "memory");
}
+static inline void local_flush_tlb_range(unsigned long start,
+ unsigned long size, unsigned long stride)
+{
+ if (size <= stride)
+ local_flush_tlb_page(start);
+ else
+ local_flush_tlb_all();
+}
+
+static inline void local_flush_tlb_range_asid(unsigned long start,
+ unsigned long size, unsigned long stride, unsigned long asid)
+{
+ if (size <= stride)
+ local_flush_tlb_page_asid(start, asid);
+ else
+ local_flush_tlb_all_asid(asid);
+}
+
+static void __ipi_flush_tlb_all(void *info)
+{
+ local_flush_tlb_all();
+}
+
void flush_tlb_all(void)
{
- sbi_remote_sfence_vma(NULL, 0, -1);
+ if (riscv_use_ipi_for_rfence())
+ on_each_cpu(__ipi_flush_tlb_all, NULL, 1);
+ else
+ sbi_remote_sfence_vma(NULL, 0, -1);
+}
+
+struct flush_tlb_range_data {
+ unsigned long asid;
+ unsigned long start;
+ unsigned long size;
+ unsigned long stride;
+};
+
+static void __ipi_flush_tlb_range_asid(void *info)
+{
+ struct flush_tlb_range_data *d = info;
+
+ local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid);
+}
+
+static void __ipi_flush_tlb_range(void *info)
+{
+ struct flush_tlb_range_data *d = info;
+
+ local_flush_tlb_range(d->start, d->size, d->stride);
}
-static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
- unsigned long size, unsigned long stride)
+static void __flush_tlb_range(struct mm_struct *mm, unsigned long start,
+ unsigned long size, unsigned long stride)
{
+ struct flush_tlb_range_data ftd;
struct cpumask *cmask = mm_cpumask(mm);
unsigned int cpuid;
bool broadcast;
@@ -45,19 +93,34 @@ static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
unsigned long asid = atomic_long_read(&mm->context.id) & asid_mask;
if (broadcast) {
- sbi_remote_sfence_vma_asid(cmask, start, size, asid);
- } else if (size <= stride) {
- local_flush_tlb_page_asid(start, asid);
+ if (riscv_use_ipi_for_rfence()) {
+ ftd.asid = asid;
+ ftd.start = start;
+ ftd.size = size;
+ ftd.stride = stride;
+ on_each_cpu_mask(cmask,
+ __ipi_flush_tlb_range_asid,
+ &ftd, 1);
+ } else
+ sbi_remote_sfence_vma_asid(cmask,
+ start, size, asid);
} else {
- local_flush_tlb_all_asid(asid);
+ local_flush_tlb_range_asid(start, size, stride, asid);
}
} else {
if (broadcast) {
- sbi_remote_sfence_vma(cmask, start, size);
- } else if (size <= stride) {
- local_flush_tlb_page(start);
+ if (riscv_use_ipi_for_rfence()) {
+ ftd.asid = 0;
+ ftd.start = start;
+ ftd.size = size;
+ ftd.stride = stride;
+ on_each_cpu_mask(cmask,
+ __ipi_flush_tlb_range,
+ &ftd, 1);
+ } else
+ sbi_remote_sfence_vma(cmask, start, size);
} else {
- local_flush_tlb_all();
+ local_flush_tlb_range(start, size, stride);
}
}
@@ -66,23 +129,23 @@ static void __sbi_tlb_flush_range(struct mm_struct *mm, unsigned long start,
void flush_tlb_mm(struct mm_struct *mm)
{
- __sbi_tlb_flush_range(mm, 0, -1, PAGE_SIZE);
+ __flush_tlb_range(mm, 0, -1, PAGE_SIZE);
}
void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
{
- __sbi_tlb_flush_range(vma->vm_mm, addr, PAGE_SIZE, PAGE_SIZE);
+ __flush_tlb_range(vma->vm_mm, addr, PAGE_SIZE, PAGE_SIZE);
}
void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end)
{
- __sbi_tlb_flush_range(vma->vm_mm, start, end - start, PAGE_SIZE);
+ __flush_tlb_range(vma->vm_mm, start, end - start, PAGE_SIZE);
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end)
{
- __sbi_tlb_flush_range(vma->vm_mm, start, end - start, PMD_SIZE);
+ __flush_tlb_range(vma->vm_mm, start, end - start, PMD_SIZE);
}
#endif
generated by cgit v1.2.3 (git 2.46.0) at 2025-07-06 10:16:48 +0000