Now are able to use mmap_prepare, complete callbacks for procfs
implementations, update the vmcore implementation accordingly.
As part of this change, we must also update remap_vmalloc_range_partial()
to optionally not update VMA flags. Other than then remap_vmalloc_range()
wrapper, vmcore is the only user of this function so we can simply go ahead
and add a parameter.
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
---
arch/s390/kernel/crash_dump.c | 6 ++--
fs/proc/vmcore.c | 53 +++++++++++++++++++++++++----------
include/linux/vmalloc.h | 10 +++----
mm/vmalloc.c | 16 +++++++++--
4 files changed, 59 insertions(+), 26 deletions(-)
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index d4839de8ce9d..44d7902f7e41 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -186,7 +186,7 @@ static int remap_oldmem_pfn_range_kdump(struct vm_area_struct *vma,
if (pfn < oldmem_data.size >> PAGE_SHIFT) {
size_old = min(size, oldmem_data.size - (pfn << PAGE_SHIFT));
- rc = remap_pfn_range(vma, from,
+ rc = remap_pfn_range_complete(vma, from,
pfn + (oldmem_data.start >> PAGE_SHIFT),
size_old, prot);
if (rc || size == size_old)
@@ -195,7 +195,7 @@ static int remap_oldmem_pfn_range_kdump(struct vm_area_struct *vma,
from += size_old;
pfn += size_old >> PAGE_SHIFT;
}
- return remap_pfn_range(vma, from, pfn, size, prot);
+ return remap_pfn_range_complete(vma, from, pfn, size, prot);
}
/*
@@ -220,7 +220,7 @@ static int remap_oldmem_pfn_range_zfcpdump(struct vm_area_struct *vma,
from += size_hsa;
pfn += size_hsa >> PAGE_SHIFT;
}
- return remap_pfn_range(vma, from, pfn, size, prot);
+ return remap_pfn_range_complete(vma, from, pfn, size, prot);
}
/*
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index f188bd900eb2..5e4e19c38d5e 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -254,7 +254,7 @@ int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma,
unsigned long size, pgprot_t prot)
{
prot = pgprot_encrypted(prot);
- return remap_pfn_range(vma, from, pfn, size, prot);
+ return remap_pfn_range_complete(vma, from, pfn, size, prot);
}
/*
@@ -308,7 +308,7 @@ static int vmcoredd_mmap_dumps(struct vm_area_struct *vma, unsigned long dst,
tsz = min(offset + (u64)dump->size - start, (u64)size);
buf = dump->buf + start - offset;
if (remap_vmalloc_range_partial(vma, dst, buf, 0,
- tsz))
+ tsz, /* set_vma= */false))
return -EFAULT;
size -= tsz;
@@ -588,24 +588,40 @@ static int vmcore_remap_oldmem_pfn(struct vm_area_struct *vma,
return ret;
}
-static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
+static int mmap_prepare_vmcore(struct vm_area_desc *desc)
{
- size_t size = vma->vm_end - vma->vm_start;
- u64 start, end, len, tsz;
- struct vmcore_range *m;
+ size_t size = vma_desc_size(desc);
+ u64 start, end;
- start = (u64)vma->vm_pgoff << PAGE_SHIFT;
+ start = (u64)desc->pgoff << PAGE_SHIFT;
end = start + size;
if (size > vmcore_size || end > vmcore_size)
return -EINVAL;
- if (vma->vm_flags & (VM_WRITE | VM_EXEC))
+ if (desc->vm_flags & (VM_WRITE | VM_EXEC))
return -EPERM;
- vm_flags_mod(vma, VM_MIXEDMAP, VM_MAYWRITE | VM_MAYEXEC);
- vma->vm_ops = &vmcore_mmap_ops;
+ desc->vm_flags |= VM_MIXEDMAP | VM_REMAP_FLAGS;
+ desc->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC);
+ desc->vm_ops = &vmcore_mmap_ops;
+
+ /*
+ * No need for remap_pfn_range_prepare() as we ensure non-CoW by
+ * clearing VM_MAYWRITE.
+ */
+
+ return 0;
+}
+
+static int mmap_complete_vmcore(struct file *file, struct vm_area_struct *vma,
+ const void *context)
+{
+ size_t size = vma->vm_end - vma->vm_start;
+ u64 start, len, tsz;
+ struct vmcore_range *m;
+ start = (u64)vma->vm_pgoff << PAGE_SHIFT;
len = 0;
if (start < elfcorebuf_sz) {
@@ -613,8 +629,8 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
tsz = min(elfcorebuf_sz - (size_t)start, size);
pfn = __pa(elfcorebuf + start) >> PAGE_SHIFT;
- if (remap_pfn_range(vma, vma->vm_start, pfn, tsz,
- vma->vm_page_prot))
+ if (remap_pfn_range_complete(vma, vma->vm_start, pfn, tsz,
+ vma->vm_page_prot))
return -EAGAIN;
size -= tsz;
start += tsz;
@@ -664,7 +680,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)start, size);
kaddr = elfnotes_buf + start - elfcorebuf_sz - vmcoredd_orig_sz;
if (remap_vmalloc_range_partial(vma, vma->vm_start + len,
- kaddr, 0, tsz))
+ kaddr, 0, tsz, /* set_vma =*/false))
goto fail;
size -= tsz;
@@ -701,7 +717,13 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
return -EAGAIN;
}
#else
-static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
+static int mmap_prepare_vmcore(struct vm_area_desc *desc)
+{
+ return -ENOSYS;
+}
+
+static int mmap_complete_vmcore(struct file *file, struct vm_area_struct *vma,
+ const void *context)
{
return -ENOSYS;
}
@@ -712,7 +734,8 @@ static const struct proc_ops vmcore_proc_ops = {
.proc_release = release_vmcore,
.proc_read_iter = read_vmcore,
.proc_lseek = default_llseek,
- .proc_mmap = mmap_vmcore,
+ .proc_mmap_prepare = mmap_prepare_vmcore,
+ .proc_mmap_complete = mmap_complete_vmcore,
};
static u64 get_vmcore_size(size_t elfsz, size_t elfnotesegsz,
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index eb54b7b3202f..588810e571aa 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -215,12 +215,12 @@ extern void *vmap(struct page **pages, unsigned int count,
void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot);
extern void vunmap(const void *addr);
-extern int remap_vmalloc_range_partial(struct vm_area_struct *vma,
- unsigned long uaddr, void *kaddr,
- unsigned long pgoff, unsigned long size);
+int remap_vmalloc_range_partial(struct vm_area_struct *vma,
+ unsigned long uaddr, void *kaddr, unsigned long pgoff,
+ unsigned long size, bool set_vma);
-extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
- unsigned long pgoff);
+int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
+ unsigned long pgoff);
int vmap_pages_range(unsigned long addr, unsigned long end, pgprot_t prot,
struct page **pages, unsigned int page_shift);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 4249e1e01947..877b557b2482 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -4528,6 +4528,7 @@ long vread_iter(struct iov_iter *iter, const char *addr, size_t count)
* @kaddr: virtual address of vmalloc kernel memory
* @pgoff: offset from @kaddr to start at
* @size: size of map area
+ * @set_vma: If true, update VMA flags
*
* Returns: 0 for success, -Exxx on failure
*
@@ -4540,7 +4541,7 @@ long vread_iter(struct iov_iter *iter, const char *addr, size_t count)
*/
int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr,
void *kaddr, unsigned long pgoff,
- unsigned long size)
+ unsigned long size, bool set_vma)
{
struct vm_struct *area;
unsigned long off;
@@ -4566,6 +4567,10 @@ int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr,
return -EINVAL;
kaddr += off;
+ /* If we shouldn't modify VMA flags, vm_insert_page() mustn't. */
+ if (!set_vma && !(vma->vm_flags & VM_MIXEDMAP))
+ return -EINVAL;
+
do {
struct page *page = vmalloc_to_page(kaddr);
int ret;
@@ -4579,7 +4584,11 @@ int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr,
size -= PAGE_SIZE;
} while (size > 0);
- vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP);
+ if (set_vma)
+ vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP);
+ else
+ VM_WARN_ON_ONCE((vma->vm_flags & (VM_DONTEXPAND | VM_DONTDUMP)) !=
+ (VM_DONTEXPAND | VM_DONTDUMP));
return 0;
}
@@ -4603,7 +4612,8 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
{
return remap_vmalloc_range_partial(vma, vma->vm_start,
addr, pgoff,
- vma->vm_end - vma->vm_start);
+ vma->vm_end - vma->vm_start,
+ /* set_vma= */ true);
}
EXPORT_SYMBOL(remap_vmalloc_range);
--
2.51.0