[RFC 1/3] lib: copy_{from,to}_user using gup & kmap_atomic()

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



copy_{from,to}_user() uaccess helpers are implemented by user page
pinning, followed by temporary kernel mapping & then memcpy(). This
helps to achieve user page copy when current virtual address mapping
of the CPU excludes user pages.

Performance wise, results are not encouraging, 'dd' on tmpfs results,

ARM Cortex-A8, BeagleBone White (256MiB RAM):
w/o series - ~29.5 MB/s
w/ series - ~20.5 MB/s
w/ series & highmem disabled - ~21.2 MB/s

On Cortex-A15(2GiB RAM) in QEMU:
w/o series - ~4 MB/s
w/ series - ~2.6 MB/s

Roughly a one-third drop in performance. Disabling highmem improves
performance only slightly.

'hackbench' also showed a similar pattern.

uaccess routines using page pinning & temporary kernel mapping is not
something new, it has been done long long ago by Ingo [1] as part of
4G/4G user/kernel mapping implementation on x86, though not merged in
mainline.

[1] https://lore.kernel.org/lkml/Pine.LNX.4.44.0307082332450.17252-100000@localhost.localdomain/

Signed-off-by: afzal mohammed <afzal.mohd.ma@xxxxxxxxx>
---
 lib/Kconfig                   |   4 +
 lib/Makefile                  |   3 +
 lib/uaccess_gup_kmap_memcpy.c | 162 ++++++++++++++++++++++++++++++++++
 3 files changed, 169 insertions(+)
 create mode 100644 lib/uaccess_gup_kmap_memcpy.c

diff --git a/lib/Kconfig b/lib/Kconfig
index 5d53f9609c252..dadf4f6cc391d 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -622,6 +622,10 @@ config ARCH_HAS_MEMREMAP_COMPAT_ALIGN
 config UACCESS_MEMCPY
 	bool
 
+# pin page + kmap_atomic + memcpy for user copies, intended for vmsplit 4g/4g
+config UACCESS_GUP_KMAP_MEMCPY
+	bool
+
 config ARCH_HAS_UACCESS_FLUSHCACHE
 	bool
 
diff --git a/lib/Makefile b/lib/Makefile
index 685aee60de1d5..bc457f85e391a 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -309,3 +309,6 @@ obj-$(CONFIG_OBJAGG) += objagg.o
 
 # KUnit tests
 obj-$(CONFIG_LIST_KUNIT_TEST) += list-test.o
+
+# uaccess
+obj-$(CONFIG_UACCESS_GUP_KMAP_MEMCPY) += uaccess_gup_kmap_memcpy.o
diff --git a/lib/uaccess_gup_kmap_memcpy.c b/lib/uaccess_gup_kmap_memcpy.c
new file mode 100644
index 0000000000000..1536762df1fd5
--- /dev/null
+++ b/lib/uaccess_gup_kmap_memcpy.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0
+// Started from arch/um/kernel/skas/uaccess.c
+
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/highmem.h>
+#include <linux/mm.h>
+
+#include <asm/page.h>
+#include <asm/pgtable.h>
+
+static int do_op_one_page(unsigned long addr, int len,
+		 int (*op)(unsigned long addr, int len, void *arg), void *arg,
+		 struct page *page)
+{
+	int n;
+
+	addr = (unsigned long) kmap_atomic(page) + (addr & ~PAGE_MASK);
+	n = (*op)(addr, len, arg);
+	kunmap_atomic((void *)addr);
+
+	return n;
+}
+
+static long buffer_op(unsigned long addr, int len,
+		      int (*op)(unsigned long, int, void *), void *arg,
+		      struct page **pages)
+{
+	long size, remain, n;
+
+	size = min(PAGE_ALIGN(addr) - addr, (unsigned long) len);
+	remain = len;
+	if (size == 0)
+		goto page_boundary;
+
+	n = do_op_one_page(addr, size, op, arg, *pages);
+	if (n != 0) {
+		remain = (n < 0 ? remain : 0);
+		goto out;
+	}
+
+	pages++;
+	addr += size;
+	remain -= size;
+
+page_boundary:
+	if (remain == 0)
+		goto out;
+	while (addr < ((addr + remain) & PAGE_MASK)) {
+		n = do_op_one_page(addr, PAGE_SIZE, op, arg, *pages);
+		if (n != 0) {
+			remain = (n < 0 ? remain : 0);
+			goto out;
+		}
+
+		pages++;
+		addr += PAGE_SIZE;
+		remain -= PAGE_SIZE;
+	}
+	if (remain == 0)
+		goto out;
+
+	n = do_op_one_page(addr, remain, op, arg, *pages);
+	if (n != 0) {
+		remain = (n < 0 ? remain : 0);
+		goto out;
+	}
+
+	return 0;
+out:
+	return remain;
+}
+
+static int copy_chunk_from_user(unsigned long from, int len, void *arg)
+{
+	unsigned long *to_ptr = arg, to = *to_ptr;
+
+	memcpy((void *) to, (void *) from, len);
+	*to_ptr += len;
+	return 0;
+}
+
+static int copy_chunk_to_user(unsigned long to, int len, void *arg)
+{
+	unsigned long *from_ptr = arg, from = *from_ptr;
+
+	memcpy((void *) to, (void *) from, len);
+	*from_ptr += len;
+	return 0;
+}
+
+unsigned long gup_kmap_copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	struct page **pages;
+	int num_pages, ret, i;
+
+	if (uaccess_kernel()) {
+		memcpy(to, (__force void *)from, n);
+		return 0;
+	}
+
+	num_pages = DIV_ROUND_UP((unsigned long)from + n, PAGE_SIZE) -
+				 (unsigned long)from / PAGE_SIZE;
+	pages = kmalloc_array(num_pages, sizeof(*pages), GFP_KERNEL | __GFP_ZERO);
+	if (!pages)
+		goto end;
+
+	ret = get_user_pages_fast((unsigned long)from, num_pages, 0, pages);
+	if (ret < 0)
+		goto free_pages;
+
+	if (ret != num_pages) {
+		num_pages = ret;
+		goto put_pages;
+	}
+
+	n = buffer_op((unsigned long) from, n, copy_chunk_from_user, &to, pages);
+
+put_pages:
+	for (i = 0; i < num_pages; i++)
+		put_page(pages[i]);
+free_pages:
+	kfree(pages);
+end:
+	return n;
+}
+
+unsigned long gup_kmap_copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	struct page **pages;
+	int num_pages, ret, i;
+
+	if (uaccess_kernel()) {
+		memcpy((__force void *) to, from, n);
+		return 0;
+	}
+
+	num_pages = DIV_ROUND_UP((unsigned long)to + n, PAGE_SIZE) - (unsigned long)to / PAGE_SIZE;
+	pages = kmalloc_array(num_pages, sizeof(*pages), GFP_KERNEL | __GFP_ZERO);
+	if (!pages)
+		goto end;
+
+	ret = get_user_pages_fast((unsigned long)to, num_pages, FOLL_WRITE, pages);
+	if (ret < 0)
+		goto free_pages;
+
+	if (ret != num_pages) {
+		num_pages = ret;
+		goto put_pages;
+	}
+
+
+	n = buffer_op((unsigned long) to, n, copy_chunk_to_user, &from, pages);
+
+put_pages:
+	for (i = 0; i < num_pages; i++)
+		put_page(pages[i]);
+free_pages:
+	kfree(pages);
+end:
+	return n;
+}
-- 
2.26.2





[Index of Archives]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Bugtraq]     [Linux OMAP]     [Linux MIPS]     [eCos]     [Asterisk Internet PBX]     [Linux API]

  Powered by Linux