diff mbox series

[RESEND,v4,1/9] mm: Introduce new vm_map_pages() and vm_map_pages_zero() API

Message ID 751cb8a0f4c3e67e95c58a3b072937617f338eea.1552921225.git.jrdr.linux@gmail.com (mailing list archive)
State Accepted
Commit a667d7456f189e3422725dddcd067537feac49c0
Headers show
Series mm: Use vm_map_pages() and vm_map_pages_zero() API | expand

Commit Message

Souptick Joarder March 19, 2019, 2:23 a.m. UTC
Previouly drivers have their own way of mapping range of
kernel pages/memory into user vma and this was done by
invoking vm_insert_page() within a loop.

As this pattern is common across different drivers, it can
be generalized by creating new functions and use it across
the drivers.

vm_map_pages() is the API which could be used to mapped
kernel memory/pages in drivers which has considered vm_pgoff

vm_map_pages_zero() is the API which could be used to map
range of kernel memory/pages in drivers which has not considered
vm_pgoff. vm_pgoff is passed default as 0 for those drivers.

We _could_ then at a later "fix" these drivers which are using
vm_map_pages_zero() to behave according to the normal vm_pgoff
offsetting simply by removing the _zero suffix on the function
name and if that causes regressions, it gives us an easy way to revert.

Tested on Rockchip hardware and display is working, including talking
to Lima via prime.

Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Suggested-by: Russell King <linux@armlinux.org.uk>
Suggested-by: Matthew Wilcox <willy@infradead.org>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Tested-by: Heiko Stuebner <heiko@sntech.de>
---
 include/linux/mm.h |  4 +++
 mm/memory.c        | 81 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 mm/nommu.c         | 14 ++++++++++
 3 files changed, 99 insertions(+)
diff mbox series

Patch

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 80bb640..e0aaa73 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2565,6 +2565,10 @@  unsigned long change_prot_numa(struct vm_area_struct *vma,
 int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
 			unsigned long pfn, unsigned long size, pgprot_t);
 int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
+int vm_map_pages(struct vm_area_struct *vma, struct page **pages,
+				unsigned long num);
+int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages,
+				unsigned long num);
 vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn);
 vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
diff --git a/mm/memory.c b/mm/memory.c
index e11ca9d..cad3e27 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1520,6 +1520,87 @@  int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
 }
 EXPORT_SYMBOL(vm_insert_page);
 
+/*
+ * __vm_map_pages - maps range of kernel pages into user vma
+ * @vma: user vma to map to
+ * @pages: pointer to array of source kernel pages
+ * @num: number of pages in page array
+ * @offset: user's requested vm_pgoff
+ *
+ * This allows drivers to map range of kernel pages into a user vma.
+ *
+ * Return: 0 on success and error code otherwise.
+ */
+static int __vm_map_pages(struct vm_area_struct *vma, struct page **pages,
+				unsigned long num, unsigned long offset)
+{
+	unsigned long count = vma_pages(vma);
+	unsigned long uaddr = vma->vm_start;
+	int ret, i;
+
+	/* Fail if the user requested offset is beyond the end of the object */
+	if (offset > num)
+		return -ENXIO;
+
+	/* Fail if the user requested size exceeds available object size */
+	if (count > num - offset)
+		return -ENXIO;
+
+	for (i = 0; i < count; i++) {
+		ret = vm_insert_page(vma, uaddr, pages[offset + i]);
+		if (ret < 0)
+			return ret;
+		uaddr += PAGE_SIZE;
+	}
+
+	return 0;
+}
+
+/**
+ * vm_map_pages - maps range of kernel pages starts with non zero offset
+ * @vma: user vma to map to
+ * @pages: pointer to array of source kernel pages
+ * @num: number of pages in page array
+ *
+ * Maps an object consisting of @num pages, catering for the user's
+ * requested vm_pgoff
+ *
+ * If we fail to insert any page into the vma, the function will return
+ * immediately leaving any previously inserted pages present.  Callers
+ * from the mmap handler may immediately return the error as their caller
+ * will destroy the vma, removing any successfully inserted pages. Other
+ * callers should make their own arrangements for calling unmap_region().
+ *
+ * Context: Process context. Called by mmap handlers.
+ * Return: 0 on success and error code otherwise.
+ */
+int vm_map_pages(struct vm_area_struct *vma, struct page **pages,
+				unsigned long num)
+{
+	return __vm_map_pages(vma, pages, num, vma->vm_pgoff);
+}
+EXPORT_SYMBOL(vm_map_pages);
+
+/**
+ * vm_map_pages_zero - map range of kernel pages starts with zero offset
+ * @vma: user vma to map to
+ * @pages: pointer to array of source kernel pages
+ * @num: number of pages in page array
+ *
+ * Similar to vm_map_pages(), except that it explicitly sets the offset
+ * to 0. This function is intended for the drivers that did not consider
+ * vm_pgoff.
+ *
+ * Context: Process context. Called by mmap handlers.
+ * Return: 0 on success and error code otherwise.
+ */
+int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages,
+				unsigned long num)
+{
+	return __vm_map_pages(vma, pages, num, 0);
+}
+EXPORT_SYMBOL(vm_map_pages_zero);
+
 static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			pfn_t pfn, pgprot_t prot, bool mkwrite)
 {
diff --git a/mm/nommu.c b/mm/nommu.c
index 749276b..b492fd1 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -473,6 +473,20 @@  int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
 }
 EXPORT_SYMBOL(vm_insert_page);
 
+int vm_map_pages(struct vm_area_struct *vma, struct page **pages,
+			unsigned long num)
+{
+	return -EINVAL;
+}
+EXPORT_SYMBOL(vm_map_pages);
+
+int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages,
+				unsigned long num)
+{
+	return -EINVAL;
+}
+EXPORT_SYMBOL(vm_map_pages_zero);
+
 /*
  *  sys_brk() for the most part doesn't need the global kernel
  *  lock, except when an application is doing something nasty