[PATCH v2 2/4] mm: Move ioremap page table mapping function to mm/

From: Nicholas Piggin
Date: Mon Apr 13 2020 - 09:00:02 EST

Next message: Huang\, Ying: "Re: [PATCH v2] mm: swap: use fixed-size readahead during swapoff"
Previous message: Nicholas Piggin: "[PATCH v2 1/4] mm/vmalloc: fix vmalloc_to_page for huge vmap mappings"
In reply to: Nicholas Piggin: "Re: [PATCH v2 1/4] mm/vmalloc: fix vmalloc_to_page for huge vmap mappings"
Next in thread: Nicholas Piggin: "[PATCH v2 4/4] mm/vmalloc: Hugepage vmalloc mappings"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

ioremap_page_range is a generic function to create a kernel virtual
mapping, move it to mm/vmalloc.c and rename it vmap_range.

For clarity with this move, also:
- Rename vunmap_page_range (vmap_range's inverse) to vunmap_range.
- Rename vmap_pages_range (which takes a page array) to vmap_pages.

Signed-off-by: Nicholas Piggin <npiggin@xxxxxxxxx>
---
include/linux/vmalloc.h | 3 +
lib/ioremap.c | 182 +++---------------------------
mm/vmalloc.c | 239 ++++++++++++++++++++++++++++++++++++----
3 files changed, 239 insertions(+), 185 deletions(-)

diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 0507a162ccd0..eb8a5080e472 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -173,6 +173,9 @@ extern struct vm_struct *find_vm_area(const void *addr);
extern int map_vm_area(struct vm_struct *area, pgprot_t prot,
struct page **pages);
#ifdef CONFIG_MMU
+int vmap_range(unsigned long addr,
+ unsigned long end, phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift);
extern int map_kernel_range_noflush(unsigned long start, unsigned long size,
pgprot_t prot, struct page **pages);
extern void unmap_kernel_range_noflush(unsigned long addr, unsigned long size);
diff --git a/lib/ioremap.c b/lib/ioremap.c
index 3f0e18543de8..7e383bdc51ad 100644
--- a/lib/ioremap.c
+++ b/lib/ioremap.c
@@ -60,176 +60,26 @@ static inline int ioremap_pud_enabled(void) { return 0; }
static inline int ioremap_pmd_enabled(void) { return 0; }
#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */

-static int ioremap_pte_range(pmd_t *pmd, unsigned long addr,
- unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
-{
- pte_t *pte;
- u64 pfn;
-
- pfn = phys_addr >> PAGE_SHIFT;
- pte = pte_alloc_kernel(pmd, addr);
- if (!pte)
- return -ENOMEM;
- do {
- BUG_ON(!pte_none(*pte));
- set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot));
- pfn++;
- } while (pte++, addr += PAGE_SIZE, addr != end);
- return 0;
-}
-
-static int ioremap_try_huge_pmd(pmd_t *pmd, unsigned long addr,
- unsigned long end, phys_addr_t phys_addr,
- pgprot_t prot)
-{
- if (!ioremap_pmd_enabled())
- return 0;
-
- if ((end - addr) != PMD_SIZE)
- return 0;
-
- if (!IS_ALIGNED(addr, PMD_SIZE))
- return 0;
-
- if (!IS_ALIGNED(phys_addr, PMD_SIZE))
- return 0;
-
- if (pmd_present(*pmd) && !pmd_free_pte_page(pmd, addr))
- return 0;
-
- return pmd_set_huge(pmd, phys_addr, prot);
-}
-
-static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
- unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
-{
- pmd_t *pmd;
- unsigned long next;
-
- pmd = pmd_alloc(&init_mm, pud, addr);
- if (!pmd)
- return -ENOMEM;
- do {
- next = pmd_addr_end(addr, end);
-
- if (ioremap_try_huge_pmd(pmd, addr, next, phys_addr, prot))
- continue;
-
- if (ioremap_pte_range(pmd, addr, next, phys_addr, prot))
- return -ENOMEM;
- } while (pmd++, phys_addr += (next - addr), addr = next, addr != end);
- return 0;
-}
-
-static int ioremap_try_huge_pud(pud_t *pud, unsigned long addr,
- unsigned long end, phys_addr_t phys_addr,
- pgprot_t prot)
-{
- if (!ioremap_pud_enabled())
- return 0;
-
- if ((end - addr) != PUD_SIZE)
- return 0;
-
- if (!IS_ALIGNED(addr, PUD_SIZE))
- return 0;
-
- if (!IS_ALIGNED(phys_addr, PUD_SIZE))
- return 0;
-
- if (pud_present(*pud) && !pud_free_pmd_page(pud, addr))
- return 0;
-
- return pud_set_huge(pud, phys_addr, prot);
-}
-
-static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
- unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
-{
- pud_t *pud;
- unsigned long next;
-
- pud = pud_alloc(&init_mm, p4d, addr);
- if (!pud)
- return -ENOMEM;
- do {
- next = pud_addr_end(addr, end);
-
- if (ioremap_try_huge_pud(pud, addr, next, phys_addr, prot))
- continue;
-
- if (ioremap_pmd_range(pud, addr, next, phys_addr, prot))
- return -ENOMEM;
- } while (pud++, phys_addr += (next - addr), addr = next, addr != end);
- return 0;
-}
-
-static int ioremap_try_huge_p4d(p4d_t *p4d, unsigned long addr,
- unsigned long end, phys_addr_t phys_addr,
- pgprot_t prot)
-{
- if (!ioremap_p4d_enabled())
- return 0;
-
- if ((end - addr) != P4D_SIZE)
- return 0;
-
- if (!IS_ALIGNED(addr, P4D_SIZE))
- return 0;
-
- if (!IS_ALIGNED(phys_addr, P4D_SIZE))
- return 0;
-
- if (p4d_present(*p4d) && !p4d_free_pud_page(p4d, addr))
- return 0;
-
- return p4d_set_huge(p4d, phys_addr, prot);
-}
-
-static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr,
- unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
-{
- p4d_t *p4d;
- unsigned long next;
-
- p4d = p4d_alloc(&init_mm, pgd, addr);
- if (!p4d)
- return -ENOMEM;
- do {
- next = p4d_addr_end(addr, end);
-
- if (ioremap_try_huge_p4d(p4d, addr, next, phys_addr, prot))
- continue;
-
- if (ioremap_pud_range(p4d, addr, next, phys_addr, prot))
- return -ENOMEM;
- } while (p4d++, phys_addr += (next - addr), addr = next, addr != end);
- return 0;
-}
-
int ioremap_page_range(unsigned long addr,
unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
{
- pgd_t *pgd;
- unsigned long start;
- unsigned long next;
- int err;
-
- might_sleep();
- BUG_ON(addr >= end);
-
- start = addr;
- pgd = pgd_offset_k(addr);
- do {
- next = pgd_addr_end(addr, end);
- err = ioremap_p4d_range(pgd, addr, next, phys_addr, prot);
- if (err)
- break;
- } while (pgd++, phys_addr += (next - addr), addr = next, addr != end);
-
- flush_cache_vmap(start, end);
+ unsigned int max_page_shift = PAGE_SHIFT;
+
+ /*
+ * Due to the max_page_shift parameter to vmap_range, platforms must
+ * enable all smaller sizes to take advantage of a given size,
+ * otherwise fall back to small pages.
+ */
+ if (ioremap_pmd_enabled()) {
+ max_page_shift = PMD_SHIFT;
+ if (ioremap_pud_enabled()) {
+ max_page_shift = PUD_SHIFT;
+ if (ioremap_p4d_enabled())
+ max_page_shift = P4D_SHIFT;
+ }
+ }

- return err;
+ return vmap_range(addr, end, phys_addr, prot, max_page_shift);
}

#ifdef CONFIG_GENERIC_IOREMAP
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 1afec7def23f..b1bc2fcae4e0 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -128,7 +128,7 @@ static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end)
} while (p4d++, addr = next, addr != end);
}

-static void vunmap_page_range(unsigned long addr, unsigned long end)
+static void vunmap_range(unsigned long addr, unsigned long end)
{
pgd_t *pgd;
unsigned long next;
@@ -143,7 +143,208 @@ static void vunmap_page_range(unsigned long addr, unsigned long end)
} while (pgd++, addr = next, addr != end);
}

-static int vmap_pte_range(pmd_t *pmd, unsigned long addr,
+static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot)
+{
+ pte_t *pte;
+ u64 pfn;
+
+ pfn = phys_addr >> PAGE_SHIFT;
+ pte = pte_alloc_kernel(pmd, addr);
+ if (!pte)
+ return -ENOMEM;
+ do {
+ BUG_ON(!pte_none(*pte));
+ set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot));
+ pfn++;
+ } while (pte++, addr += PAGE_SIZE, addr != end);
+ return 0;
+}
+
+static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift)
+{
+ if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP))
+ return 0;
+
+ if (max_page_shift < PMD_SHIFT)
+ return 0;
+
+ if ((end - addr) != PMD_SIZE)
+ return 0;
+
+ if (!IS_ALIGNED(addr, PMD_SIZE))
+ return 0;
+
+ if (!IS_ALIGNED(phys_addr, PMD_SIZE))
+ return 0;
+
+ if (pmd_present(*pmd) && !pmd_free_pte_page(pmd, addr))
+ return 0;
+
+ return pmd_set_huge(pmd, phys_addr, prot);
+}
+
+static inline int vmap_pmd_range(pud_t *pud, unsigned long addr,
+ unsigned long end, phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift)
+{
+ pmd_t *pmd;
+ unsigned long next;
+
+ pmd = pmd_alloc(&init_mm, pud, addr);
+ if (!pmd)
+ return -ENOMEM;
+ do {
+ next = pmd_addr_end(addr, end);
+
+ if (vmap_try_huge_pmd(pmd, addr, next, phys_addr, prot,
+ max_page_shift))
+ continue;
+
+ if (vmap_pte_range(pmd, addr, next, phys_addr, prot))
+ return -ENOMEM;
+ } while (pmd++, phys_addr += (next - addr), addr = next, addr != end);
+ return 0;
+}
+
+static int vmap_try_huge_pud(pud_t *pud, unsigned long addr,
+ unsigned long end, phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift)
+{
+ if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP))
+ return 0;
+
+ if (max_page_shift < PUD_SHIFT)
+ return 0;
+
+ if ((end - addr) != PUD_SIZE)
+ return 0;
+
+ if (!IS_ALIGNED(addr, PUD_SIZE))
+ return 0;
+
+ if (!IS_ALIGNED(phys_addr, PUD_SIZE))
+ return 0;
+
+ if (pud_present(*pud) && !pud_free_pmd_page(pud, addr))
+ return 0;
+
+ return pud_set_huge(pud, phys_addr, prot);
+}
+
+static inline int vmap_pud_range(p4d_t *p4d, unsigned long addr,
+ unsigned long end, phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift)
+{
+ pud_t *pud;
+ unsigned long next;
+
+ pud = pud_alloc(&init_mm, p4d, addr);
+ if (!pud)
+ return -ENOMEM;
+ do {
+ next = pud_addr_end(addr, end);
+
+ if (vmap_try_huge_pud(pud, addr, next, phys_addr, prot,
+ max_page_shift))
+ continue;
+
+ if (vmap_pmd_range(pud, addr, next, phys_addr, prot,
+ max_page_shift))
+ return -ENOMEM;
+ } while (pud++, phys_addr += (next - addr), addr = next, addr != end);
+ return 0;
+}
+
+static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr,
+ unsigned long end, phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift)
+{
+ if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP))
+ return 0;
+
+ if (max_page_shift < P4D_SHIFT)
+ return 0;
+
+ if ((end - addr) != P4D_SIZE)
+ return 0;
+
+ if (!IS_ALIGNED(addr, P4D_SIZE))
+ return 0;
+
+ if (!IS_ALIGNED(phys_addr, P4D_SIZE))
+ return 0;
+
+ if (p4d_present(*p4d) && !p4d_free_pud_page(p4d, addr))
+ return 0;
+
+ return p4d_set_huge(p4d, phys_addr, prot);
+}
+
+static inline int vmap_p4d_range(pgd_t *pgd, unsigned long addr,
+ unsigned long end, phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift)
+{
+ p4d_t *p4d;
+ unsigned long next;
+
+ p4d = p4d_alloc(&init_mm, pgd, addr);
+ if (!p4d)
+ return -ENOMEM;
+ do {
+ next = p4d_addr_end(addr, end);
+
+ if (vmap_try_huge_p4d(p4d, addr, next, phys_addr, prot,
+ max_page_shift))
+ continue;
+
+ if (vmap_pud_range(p4d, addr, next, phys_addr, prot,
+ max_page_shift))
+ return -ENOMEM;
+ } while (p4d++, phys_addr += (next - addr), addr = next, addr != end);
+ return 0;
+}
+
+static int vmap_range_noflush(unsigned long addr,
+ unsigned long end, phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift)
+{
+ pgd_t *pgd;
+ unsigned long start;
+ unsigned long next;
+ int err;
+
+ might_sleep();
+ BUG_ON(addr >= end);
+
+ start = addr;
+ pgd = pgd_offset_k(addr);
+ do {
+ next = pgd_addr_end(addr, end);
+ err = vmap_p4d_range(pgd, addr, next, phys_addr, prot,
+ max_page_shift);
+ if (err)
+ break;
+ } while (pgd++, phys_addr += (next - addr), addr = next, addr != end);
+
+ return err;
+}
+
+int vmap_range(unsigned long addr,
+ unsigned long end, phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift)
+{
+ int ret;
+
+ ret = vmap_range_noflush(addr, end, phys_addr, prot, max_page_shift);
+ flush_cache_vmap(addr, end);
+
+ return ret;
+}
+
+static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr)
{
pte_t *pte;
@@ -169,7 +370,7 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr,
return 0;
}

-static int vmap_pmd_range(pud_t *pud, unsigned long addr,
+static int vmap_pages_pmd_range(pud_t *pud, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr)
{
pmd_t *pmd;
@@ -180,13 +381,13 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr,
return -ENOMEM;
do {
next = pmd_addr_end(addr, end);
- if (vmap_pte_range(pmd, addr, next, prot, pages, nr))
+ if (vmap_pages_pte_range(pmd, addr, next, prot, pages, nr))
return -ENOMEM;
} while (pmd++, addr = next, addr != end);
return 0;
}

-static int vmap_pud_range(p4d_t *p4d, unsigned long addr,
+static int vmap_pages_pud_range(p4d_t *p4d, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr)
{
pud_t *pud;
@@ -197,13 +398,13 @@ static int vmap_pud_range(p4d_t *p4d, unsigned long addr,
return -ENOMEM;
do {
next = pud_addr_end(addr, end);
- if (vmap_pmd_range(pud, addr, next, prot, pages, nr))
+ if (vmap_pages_pmd_range(pud, addr, next, prot, pages, nr))
return -ENOMEM;
} while (pud++, addr = next, addr != end);
return 0;
}

-static int vmap_p4d_range(pgd_t *pgd, unsigned long addr,
+static int vmap_pages_p4d_range(pgd_t *pgd, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr)
{
p4d_t *p4d;
@@ -214,7 +415,7 @@ static int vmap_p4d_range(pgd_t *pgd, unsigned long addr,
return -ENOMEM;
do {
next = p4d_addr_end(addr, end);
- if (vmap_pud_range(p4d, addr, next, prot, pages, nr))
+ if (vmap_pages_pud_range(p4d, addr, next, prot, pages, nr))
return -ENOMEM;
} while (p4d++, addr = next, addr != end);
return 0;
@@ -226,7 +427,7 @@ static int vmap_p4d_range(pgd_t *pgd, unsigned long addr,
*
* Ie. pte at addr+N*PAGE_SIZE shall point to pfn corresponding to pages[N]
*/
-static int vmap_page_range_noflush(unsigned long start, unsigned long end,
+static int vmap_pages_range_noflush(unsigned long start, unsigned long end,
pgprot_t prot, struct page **pages)
{
pgd_t *pgd;
@@ -239,7 +440,7 @@ static int vmap_page_range_noflush(unsigned long start, unsigned long end,
pgd = pgd_offset_k(addr);
do {
next = pgd_addr_end(addr, end);
- err = vmap_p4d_range(pgd, addr, next, prot, pages, &nr);
+ err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr);
if (err)
return err;
} while (pgd++, addr = next, addr != end);
@@ -247,12 +448,12 @@ static int vmap_page_range_noflush(unsigned long start, unsigned long end,
return nr;
}

-static int vmap_page_range(unsigned long start, unsigned long end,
+static int vmap_pages_range(unsigned long start, unsigned long end,
pgprot_t prot, struct page **pages)
{
int ret;

- ret = vmap_page_range_noflush(start, end, prot, pages);
+ ret = vmap_pages_range_noflush(start, end, prot, pages);
flush_cache_vmap(start, end);
return ret;
}
@@ -1238,7 +1439,7 @@ EXPORT_SYMBOL_GPL(unregister_vmap_purge_notifier);
*/
static void unmap_vmap_area(struct vmap_area *va)
{
- vunmap_page_range(va->va_start, va->va_end);
+ vunmap_range(va->va_start, va->va_end);
}

/*
@@ -1699,7 +1900,7 @@ static void vb_free(const void *addr, unsigned long size)
rcu_read_unlock();
BUG_ON(!vb);

- vunmap_page_range((unsigned long)addr, (unsigned long)addr + size);
+ vunmap_range((unsigned long)addr, (unsigned long)addr + size);

if (debug_pagealloc_enabled_static())
flush_tlb_kernel_range((unsigned long)addr,
@@ -1854,7 +2055,7 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t pro

kasan_unpoison_vmalloc(mem, size);

- if (vmap_page_range(addr, addr + size, prot, pages) < 0) {
+ if (vmap_pages_range(addr, addr + size, prot, pages) < 0) {
vm_unmap_ram(mem, count);
return NULL;
}
@@ -2020,7 +2221,7 @@ void __init vmalloc_init(void)
int map_kernel_range_noflush(unsigned long addr, unsigned long size,
pgprot_t prot, struct page **pages)
{
- return vmap_page_range_noflush(addr, addr + size, prot, pages);
+ return vmap_pages_range_noflush(addr, addr + size, prot, pages);
}

/**
@@ -2039,7 +2240,7 @@ int map_kernel_range_noflush(unsigned long addr, unsigned long size,
*/
void unmap_kernel_range_noflush(unsigned long addr, unsigned long size)
{
- vunmap_page_range(addr, addr + size);
+ vunmap_range(addr, addr + size);
}
EXPORT_SYMBOL_GPL(unmap_kernel_range_noflush);

@@ -2056,7 +2257,7 @@ void unmap_kernel_range(unsigned long addr, unsigned long size)
unsigned long end = addr + size;

flush_cache_vunmap(addr, end);
- vunmap_page_range(addr, end);
+ vunmap_range(addr, end);
flush_tlb_kernel_range(addr, end);
}
EXPORT_SYMBOL_GPL(unmap_kernel_range);
@@ -2067,7 +2268,7 @@ int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page **pages)
unsigned long end = addr + get_vm_area_size(area);
int err;

- err = vmap_page_range(addr, end, prot, pages);
+ err = vmap_pages_range(addr, end, prot, pages);

return err > 0 ? 0 : err;
}
--
2.23.0

Next message: Huang\, Ying: "Re: [PATCH v2] mm: swap: use fixed-size readahead during swapoff"
Previous message: Nicholas Piggin: "[PATCH v2 1/4] mm/vmalloc: fix vmalloc_to_page for huge vmap mappings"
In reply to: Nicholas Piggin: "Re: [PATCH v2 1/4] mm/vmalloc: fix vmalloc_to_page for huge vmap mappings"
Next in thread: Nicholas Piggin: "[PATCH v2 4/4] mm/vmalloc: Hugepage vmalloc mappings"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]