summaryrefslogtreecommitdiff
path: root/arch/arm64/mm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64/mm')
-rw-r--r--arch/arm64/mm/cache.S37
-rw-r--r--arch/arm64/mm/dma-mapping.c8
-rw-r--r--arch/arm64/mm/fault.c89
-rw-r--r--arch/arm64/mm/flush.c16
-rw-r--r--arch/arm64/mm/hugetlbpage.c314
-rw-r--r--arch/arm64/mm/mmu.c18
-rw-r--r--arch/arm64/mm/numa.c7
7 files changed, 356 insertions, 133 deletions
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 83c27b6e6dca..7f1dbe962cf5 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -109,20 +109,25 @@ ENTRY(__clean_dcache_area_pou)
ENDPROC(__clean_dcache_area_pou)
/*
- * __dma_inv_area(start, size)
- * - start - virtual start address of region
+ * __inval_dcache_area(kaddr, size)
+ *
+ * Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * are invalidated. Any partial lines at the ends of the interval are
+ * also cleaned to PoC to prevent data loss.
+ *
+ * - kaddr - kernel address
* - size - size in question
*/
-__dma_inv_area:
- add x1, x1, x0
+ENTRY(__inval_dcache_area)
/* FALLTHROUGH */
/*
- * __inval_cache_range(start, end)
- * - start - start address of region
- * - end - end address of region
+ * __dma_inv_area(start, size)
+ * - start - virtual start address of region
+ * - size - size in question
*/
-ENTRY(__inval_cache_range)
+__dma_inv_area:
+ add x1, x1, x0
dcache_line_size x2, x3
sub x3, x2, #1
tst x1, x3 // end cache line aligned?
@@ -140,7 +145,7 @@ ENTRY(__inval_cache_range)
b.lo 2b
dsb sy
ret
-ENDPIPROC(__inval_cache_range)
+ENDPIPROC(__inval_dcache_area)
ENDPROC(__dma_inv_area)
/*
@@ -167,6 +172,20 @@ ENDPIPROC(__clean_dcache_area_poc)
ENDPROC(__dma_clean_area)
/*
+ * __clean_dcache_area_pop(kaddr, size)
+ *
+ * Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * are cleaned to the PoP.
+ *
+ * - kaddr - kernel address
+ * - size - size in question
+ */
+ENTRY(__clean_dcache_area_pop)
+ dcache_by_line_op cvap, sy, x0, x1, x2, x3
+ ret
+ENDPIPROC(__clean_dcache_area_pop)
+
+/*
* __dma_flush_area(start, size)
*
* clean & invalidate D / U line
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index e90cd1db42a8..614af886b7ef 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -42,7 +42,7 @@ static pgprot_t __get_dma_pgprot(unsigned long attrs, pgprot_t prot,
return prot;
}
-static struct gen_pool *atomic_pool;
+static struct gen_pool *atomic_pool __ro_after_init;
#define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K
static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE;
@@ -329,7 +329,7 @@ static int __swiotlb_mmap(struct device *dev,
vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
is_device_dma_coherent(dev));
- if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+ if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
return ret;
return __swiotlb_mmap_pfn(vma, pfn, size);
@@ -425,7 +425,7 @@ static int __init atomic_pool_init(void)
gen_pool_set_algo(atomic_pool,
gen_pool_first_fit_order_align,
- (void *)PAGE_SHIFT);
+ NULL);
pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n",
atomic_pool_size / 1024);
@@ -706,7 +706,7 @@ static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
is_device_dma_coherent(dev));
- if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+ if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
return ret;
if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index c7861c9864e6..89993c4be1be 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -34,6 +34,7 @@
#include <linux/hugetlb.h>
#include <asm/bug.h>
+#include <asm/cmpxchg.h>
#include <asm/cpufeature.h>
#include <asm/exception.h>
#include <asm/debug-monitors.h>
@@ -82,6 +83,49 @@ static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
}
#endif
+static void data_abort_decode(unsigned int esr)
+{
+ pr_alert("Data abort info:\n");
+
+ if (esr & ESR_ELx_ISV) {
+ pr_alert(" Access size = %u byte(s)\n",
+ 1U << ((esr & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT));
+ pr_alert(" SSE = %lu, SRT = %lu\n",
+ (esr & ESR_ELx_SSE) >> ESR_ELx_SSE_SHIFT,
+ (esr & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT);
+ pr_alert(" SF = %lu, AR = %lu\n",
+ (esr & ESR_ELx_SF) >> ESR_ELx_SF_SHIFT,
+ (esr & ESR_ELx_AR) >> ESR_ELx_AR_SHIFT);
+ } else {
+ pr_alert(" ISV = 0, ISS = 0x%08lu\n", esr & ESR_ELx_ISS_MASK);
+ }
+
+ pr_alert(" CM = %lu, WnR = %lu\n",
+ (esr & ESR_ELx_CM) >> ESR_ELx_CM_SHIFT,
+ (esr & ESR_ELx_WNR) >> ESR_ELx_WNR_SHIFT);
+}
+
+/*
+ * Decode mem abort information
+ */
+static void mem_abort_decode(unsigned int esr)
+{
+ pr_alert("Mem abort info:\n");
+
+ pr_alert(" Exception class = %s, IL = %u bits\n",
+ esr_get_class_string(esr),
+ (esr & ESR_ELx_IL) ? 32 : 16);
+ pr_alert(" SET = %lu, FnV = %lu\n",
+ (esr & ESR_ELx_SET_MASK) >> ESR_ELx_SET_SHIFT,
+ (esr & ESR_ELx_FnV) >> ESR_ELx_FnV_SHIFT);
+ pr_alert(" EA = %lu, S1PTW = %lu\n",
+ (esr & ESR_ELx_EA) >> ESR_ELx_EA_SHIFT,
+ (esr & ESR_ELx_S1PTW) >> ESR_ELx_S1PTW_SHIFT);
+
+ if (esr_is_data_abort(esr))
+ data_abort_decode(esr);
+}
+
/*
* Dump out the page tables associated with 'addr' in the currently active mm.
*/
@@ -139,7 +183,6 @@ void show_pte(unsigned long addr)
pr_cont("\n");
}
-#ifdef CONFIG_ARM64_HW_AFDBM
/*
* This function sets the access flags (dirty, accessed), as well as write
* permission, and only to a more permissive setting.
@@ -154,40 +197,33 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep,
pte_t entry, int dirty)
{
- pteval_t old_pteval;
- unsigned int tmp;
+ pteval_t old_pteval, pteval;
if (pte_same(*ptep, entry))
return 0;
/* only preserve the access flags and write permission */
- pte_val(entry) &= PTE_AF | PTE_WRITE | PTE_DIRTY;
-
- /*
- * PTE_RDONLY is cleared by default in the asm below, so set it in
- * back if necessary (read-only or clean PTE).
- */
- if (!pte_write(entry) || !pte_sw_dirty(entry))
- pte_val(entry) |= PTE_RDONLY;
+ pte_val(entry) &= PTE_RDONLY | PTE_AF | PTE_WRITE | PTE_DIRTY;
/*
* Setting the flags must be done atomically to avoid racing with the
- * hardware update of the access/dirty state.
+ * hardware update of the access/dirty state. The PTE_RDONLY bit must
+ * be set to the most permissive (lowest value) of *ptep and entry
+ * (calculated as: a & b == ~(~a | ~b)).
*/
- asm volatile("// ptep_set_access_flags\n"
- " prfm pstl1strm, %2\n"
- "1: ldxr %0, %2\n"
- " and %0, %0, %3 // clear PTE_RDONLY\n"
- " orr %0, %0, %4 // set flags\n"
- " stxr %w1, %0, %2\n"
- " cbnz %w1, 1b\n"
- : "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))
- : "L" (~PTE_RDONLY), "r" (pte_val(entry)));
+ pte_val(entry) ^= PTE_RDONLY;
+ pteval = READ_ONCE(pte_val(*ptep));
+ do {
+ old_pteval = pteval;
+ pteval ^= PTE_RDONLY;
+ pteval |= pte_val(entry);
+ pteval ^= PTE_RDONLY;
+ pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval);
+ } while (pteval != old_pteval);
flush_tlb_fix_spurious_fault(vma, address);
return 1;
}
-#endif
static bool is_el1_instruction_abort(unsigned int esr)
{
@@ -247,6 +283,8 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr,
pr_alert("Unable to handle kernel %s at virtual address %08lx\n", msg,
addr);
+ mem_abort_decode(esr);
+
show_pte(addr);
die("Oops", regs, esr);
bust_spinlocks(0);
@@ -434,8 +472,11 @@ retry:
* the mmap_sem because it would already be released
* in __lock_page_or_retry in mm/filemap.c.
*/
- if (fatal_signal_pending(current))
+ if (fatal_signal_pending(current)) {
+ if (!user_mode(regs))
+ goto no_context;
return 0;
+ }
/*
* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk of
@@ -701,6 +742,8 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
pr_alert("Unhandled fault: %s (0x%08x) at 0x%016lx\n",
inf->name, esr, addr);
+ mem_abort_decode(esr);
+
info.si_signo = inf->sig;
info.si_errno = 0;
info.si_code = inf->code;
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 21a8d828cbf4..e36ed5087b5c 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -83,3 +83,19 @@ EXPORT_SYMBOL(flush_dcache_page);
* Additional functions defined in assembly.
*/
EXPORT_SYMBOL(flush_icache_range);
+
+#ifdef CONFIG_ARCH_HAS_PMEM_API
+void arch_wb_cache_pmem(void *addr, size_t size)
+{
+ /* Ensure order against any prior non-cacheable writes */
+ dmb(osh);
+ __clean_dcache_area_pop(addr, size);
+}
+EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);
+
+void arch_invalidate_pmem(void *addr, size_t size)
+{
+ __inval_dcache_area(addr, size);
+}
+EXPORT_SYMBOL_GPL(arch_invalidate_pmem);
+#endif
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 656e0ece2289..6cb0fa92a651 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -41,6 +41,16 @@ int pud_huge(pud_t pud)
#endif
}
+/*
+ * Select all bits except the pfn
+ */
+static inline pgprot_t pte_pgprot(pte_t pte)
+{
+ unsigned long pfn = pte_pfn(pte);
+
+ return __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte));
+}
+
static int find_num_contig(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, size_t *pgsize)
{
@@ -58,15 +68,107 @@ static int find_num_contig(struct mm_struct *mm, unsigned long addr,
return CONT_PTES;
}
+static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
+{
+ int contig_ptes = 0;
+
+ *pgsize = size;
+
+ switch (size) {
+#ifdef CONFIG_ARM64_4K_PAGES
+ case PUD_SIZE:
+#endif
+ case PMD_SIZE:
+ contig_ptes = 1;
+ break;
+ case CONT_PMD_SIZE:
+ *pgsize = PMD_SIZE;
+ contig_ptes = CONT_PMDS;
+ break;
+ case CONT_PTE_SIZE:
+ *pgsize = PAGE_SIZE;
+ contig_ptes = CONT_PTES;
+ break;
+ }
+
+ return contig_ptes;
+}
+
+/*
+ * Changing some bits of contiguous entries requires us to follow a
+ * Break-Before-Make approach, breaking the whole contiguous set
+ * before we can change any entries. See ARM DDI 0487A.k_iss10775,
+ * "Misprogramming of the Contiguous bit", page D4-1762.
+ *
+ * This helper performs the break step.
+ */
+static pte_t get_clear_flush(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep,
+ unsigned long pgsize,
+ unsigned long ncontig)
+{
+ struct vm_area_struct vma = { .vm_mm = mm };
+ pte_t orig_pte = huge_ptep_get(ptep);
+ bool valid = pte_valid(orig_pte);
+ unsigned long i, saddr = addr;
+
+ for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) {
+ pte_t pte = ptep_get_and_clear(mm, addr, ptep);
+
+ /*
+ * If HW_AFDBM is enabled, then the HW could turn on
+ * the dirty bit for any page in the set, so check
+ * them all. All hugetlb entries are already young.
+ */
+ if (pte_dirty(pte))
+ orig_pte = pte_mkdirty(orig_pte);
+ }
+
+ if (valid)
+ flush_tlb_range(&vma, saddr, addr);
+ return orig_pte;
+}
+
+/*
+ * Changing some bits of contiguous entries requires us to follow a
+ * Break-Before-Make approach, breaking the whole contiguous set
+ * before we can change any entries. See ARM DDI 0487A.k_iss10775,
+ * "Misprogramming of the Contiguous bit", page D4-1762.
+ *
+ * This helper performs the break step for use cases where the
+ * original pte is not needed.
+ */
+static void clear_flush(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep,
+ unsigned long pgsize,
+ unsigned long ncontig)
+{
+ struct vm_area_struct vma = { .vm_mm = mm };
+ unsigned long i, saddr = addr;
+
+ for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
+ pte_clear(mm, addr, ptep);
+
+ flush_tlb_range(&vma, saddr, addr);
+}
+
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte)
{
size_t pgsize;
int i;
int ncontig;
- unsigned long pfn;
+ unsigned long pfn, dpfn;
pgprot_t hugeprot;
+ /*
+ * Code needs to be expanded to handle huge swap and migration
+ * entries. Needed for HUGETLB and MEMORY_FAILURE.
+ */
+ WARN_ON(!pte_present(pte));
+
if (!pte_cont(pte)) {
set_pte_at(mm, addr, ptep, pte);
return;
@@ -74,17 +176,30 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
ncontig = find_num_contig(mm, addr, ptep, &pgsize);
pfn = pte_pfn(pte);
- hugeprot = __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte));
- for (i = 0; i < ncontig; i++) {
+ dpfn = pgsize >> PAGE_SHIFT;
+ hugeprot = pte_pgprot(pte);
+
+ clear_flush(mm, addr, ptep, pgsize, ncontig);
+
+ for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) {
pr_debug("%s: set pte %p to 0x%llx\n", __func__, ptep,
pte_val(pfn_pte(pfn, hugeprot)));
set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
- ptep++;
- pfn += pgsize >> PAGE_SHIFT;
- addr += pgsize;
}
}
+void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte, unsigned long sz)
+{
+ int i, ncontig;
+ size_t pgsize;
+
+ ncontig = num_contig_ptes(sz, &pgsize);
+
+ for (i = 0; i < ncontig; i++, ptep++)
+ set_pte(ptep, pte);
+}
+
pte_t *huge_pte_alloc(struct mm_struct *mm,
unsigned long addr, unsigned long sz)
{
@@ -144,19 +259,28 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
return NULL;
pud = pud_offset(pgd, addr);
- if (pud_none(*pud))
+ if (sz != PUD_SIZE && pud_none(*pud))
return NULL;
- /* swap or huge page */
- if (!pud_present(*pud) || pud_huge(*pud))
+ /* hugepage or swap? */
+ if (pud_huge(*pud) || !pud_present(*pud))
return (pte_t *)pud;
/* table; check the next level */
+ if (sz == CONT_PMD_SIZE)
+ addr &= CONT_PMD_MASK;
+
pmd = pmd_offset(pud, addr);
- if (pmd_none(*pmd))
+ if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) &&
+ pmd_none(*pmd))
return NULL;
- if (!pmd_present(*pmd) || pmd_huge(*pmd))
+ if (pmd_huge(*pmd) || !pmd_present(*pmd))
return (pte_t *)pmd;
+ if (sz == CONT_PTE_SIZE) {
+ pte_t *pte = pte_offset_kernel(pmd, (addr & CONT_PTE_MASK));
+ return pte;
+ }
+
return NULL;
}
@@ -176,111 +300,133 @@ pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
return entry;
}
+void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, unsigned long sz)
+{
+ int i, ncontig;
+ size_t pgsize;
+
+ ncontig = num_contig_ptes(sz, &pgsize);
+
+ for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
+ pte_clear(mm, addr, ptep);
+}
+
pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
- pte_t pte;
+ int ncontig;
+ size_t pgsize;
+ pte_t orig_pte = huge_ptep_get(ptep);
- if (pte_cont(*ptep)) {
- int ncontig, i;
- size_t pgsize;
- bool is_dirty = false;
-
- ncontig = find_num_contig(mm, addr, ptep, &pgsize);
- /* save the 1st pte to return */
- pte = ptep_get_and_clear(mm, addr, ptep);
- for (i = 1, addr += pgsize; i < ncontig; ++i, addr += pgsize) {
- /*
- * If HW_AFDBM is enabled, then the HW could
- * turn on the dirty bit for any of the page
- * in the set, so check them all.
- */
- ++ptep;
- if (pte_dirty(ptep_get_and_clear(mm, addr, ptep)))
- is_dirty = true;
- }
- if (is_dirty)
- return pte_mkdirty(pte);
- else
- return pte;
- } else {
+ if (!pte_cont(orig_pte))
return ptep_get_and_clear(mm, addr, ptep);
- }
+
+ ncontig = find_num_contig(mm, addr, ptep, &pgsize);
+
+ return get_clear_flush(mm, addr, ptep, pgsize, ncontig);
}
int huge_ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t pte, int dirty)
{
- if (pte_cont(pte)) {
- int ncontig, i, changed = 0;
- size_t pgsize = 0;
- unsigned long pfn = pte_pfn(pte);
- /* Select all bits except the pfn */
- pgprot_t hugeprot =
- __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^
- pte_val(pte));
-
- pfn = pte_pfn(pte);
- ncontig = find_num_contig(vma->vm_mm, addr, ptep,
- &pgsize);
- for (i = 0; i < ncontig; ++i, ++ptep, addr += pgsize) {
- changed |= ptep_set_access_flags(vma, addr, ptep,
- pfn_pte(pfn,
- hugeprot),
- dirty);
- pfn += pgsize >> PAGE_SHIFT;
- }
- return changed;
- } else {
+ int ncontig, i, changed = 0;
+ size_t pgsize = 0;
+ unsigned long pfn = pte_pfn(pte), dpfn;
+ pgprot_t hugeprot;
+ pte_t orig_pte;
+
+ if (!pte_cont(pte))
return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
- }
+
+ ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
+ dpfn = pgsize >> PAGE_SHIFT;
+
+ orig_pte = get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
+ if (!pte_same(orig_pte, pte))
+ changed = 1;
+
+ /* Make sure we don't lose the dirty state */
+ if (pte_dirty(orig_pte))
+ pte = pte_mkdirty(pte);
+
+ hugeprot = pte_pgprot(pte);
+ for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
+ set_pte_at(vma->vm_mm, addr, ptep, pfn_pte(pfn, hugeprot));
+
+ return changed;
}
void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
- if (pte_cont(*ptep)) {
- int ncontig, i;
- size_t pgsize = 0;
-
- ncontig = find_num_contig(mm, addr, ptep, &pgsize);
- for (i = 0; i < ncontig; ++i, ++ptep, addr += pgsize)
- ptep_set_wrprotect(mm, addr, ptep);
- } else {
+ unsigned long pfn, dpfn;
+ pgprot_t hugeprot;
+ int ncontig, i;
+ size_t pgsize;
+ pte_t pte;
+
+ if (!pte_cont(*ptep)) {
ptep_set_wrprotect(mm, addr, ptep);
+ return;
}
+
+ ncontig = find_num_contig(mm, addr, ptep, &pgsize);
+ dpfn = pgsize >> PAGE_SHIFT;
+
+ pte = get_clear_flush(mm, addr, ptep, pgsize, ncontig);
+ pte = pte_wrprotect(pte);
+
+ hugeprot = pte_pgprot(pte);
+ pfn = pte_pfn(pte);
+
+ for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
+ set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
}
void huge_ptep_clear_flush(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
- if (pte_cont(*ptep)) {
- int ncontig, i;
- size_t pgsize = 0;
-
- ncontig = find_num_contig(vma->vm_mm, addr, ptep,
- &pgsize);
- for (i = 0; i < ncontig; ++i, ++ptep, addr += pgsize)
- ptep_clear_flush(vma, addr, ptep);
- } else {
+ size_t pgsize;
+ int ncontig;
+
+ if (!pte_cont(*ptep)) {
ptep_clear_flush(vma, addr, ptep);
+ return;
}
+
+ ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
+ clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
}
static __init int setup_hugepagesz(char *opt)
{
unsigned long ps = memparse(opt, &opt);
- if (ps == PMD_SIZE) {
- hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
- } else if (ps == PUD_SIZE) {
- hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
- } else {
- hugetlb_bad_size();
- pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
- return 0;
+ switch (ps) {
+#ifdef CONFIG_ARM64_4K_PAGES
+ case PUD_SIZE:
+#endif
+ case PMD_SIZE * CONT_PMDS:
+ case PMD_SIZE:
+ case PAGE_SIZE * CONT_PTES:
+ hugetlb_add_hstate(ilog2(ps) - PAGE_SHIFT);
+ return 1;
}
- return 1;
+
+ hugetlb_bad_size();
+ pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
+ return 0;
}
__setup("hugepagesz=", setup_hugepagesz);
+
+#ifdef CONFIG_ARM64_64K_PAGES
+static __init int add_default_hugepagesz(void)
+{
+ if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL)
+ hugetlb_add_hstate(CONT_PTE_SHIFT);
+ return 0;
+}
+arch_initcall(add_default_hugepagesz);
+#endif
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 23c2d89a362e..f1eb15e0e864 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -496,7 +496,7 @@ void mark_rodata_ro(void)
static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
pgprot_t prot, struct vm_struct *vma,
- int flags)
+ int flags, unsigned long vm_flags)
{
phys_addr_t pa_start = __pa_symbol(va_start);
unsigned long size = va_end - va_start;
@@ -507,10 +507,13 @@ static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
__create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot,
early_pgtable_alloc, flags);
+ if (!(vm_flags & VM_NO_GUARD))
+ size += PAGE_SIZE;
+
vma->addr = va_start;
vma->phys_addr = pa_start;
vma->size = size;
- vma->flags = VM_MAP;
+ vma->flags = VM_MAP | vm_flags;
vma->caller = __builtin_return_address(0);
vm_area_add_early(vma);
@@ -541,14 +544,15 @@ static void __init map_kernel(pgd_t *pgd)
* Only rodata will be remapped with different permissions later on,
* all other segments are allowed to use contiguous mappings.
*/
- map_kernel_segment(pgd, _text, _etext, text_prot, &vmlinux_text, 0);
+ map_kernel_segment(pgd, _text, _etext, text_prot, &vmlinux_text, 0,
+ VM_NO_GUARD);
map_kernel_segment(pgd, __start_rodata, __inittext_begin, PAGE_KERNEL,
- &vmlinux_rodata, NO_CONT_MAPPINGS);
+ &vmlinux_rodata, NO_CONT_MAPPINGS, VM_NO_GUARD);
map_kernel_segment(pgd, __inittext_begin, __inittext_end, text_prot,
- &vmlinux_inittext, 0);
+ &vmlinux_inittext, 0, VM_NO_GUARD);
map_kernel_segment(pgd, __initdata_begin, __initdata_end, PAGE_KERNEL,
- &vmlinux_initdata, 0);
- map_kernel_segment(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data, 0);
+ &vmlinux_initdata, 0, VM_NO_GUARD);
+ map_kernel_segment(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data, 0, 0);
if (!pgd_val(*pgd_offset_raw(pgd, FIXADDR_START))) {
/*
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index b388a99fea7b..dad128ba98bf 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -208,8 +208,6 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
}
node_set(nid, numa_nodes_parsed);
- pr_info("Adding memblock [0x%llx - 0x%llx] on node %d\n",
- start, (end - 1), nid);
return ret;
}
@@ -223,10 +221,7 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
void *nd;
int tnid;
- if (start_pfn < end_pfn)
- pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n", nid,
- start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
- else
+ if (start_pfn >= end_pfn)
pr_info("Initmem setup node %d [<memory-less node>]\n", nid);
nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);