proc/vmcore: convert oldmem_pfn_is_ram callback to more generic vmcore callbacks

Let's support multiple registered callbacks, making sure that
registering vmcore callbacks cannot fail.  Make the callback return a
bool instead of an int, handling how to deal with errors internally.
Drop unused HAVE_OLDMEM_PFN_IS_RAM.

We soon want to make use of this infrastructure from other drivers:
virtio-mem, registering one callback for each virtio-mem device, to
prevent reading unplugged virtio-mem memory.

Handle it via a generic vmcore_cb structure, prepared for future
extensions: for example, once we support virtio-mem on s390x where the
vmcore is completely constructed in the second kernel, we want to detect
and add plugged virtio-mem memory ranges to the vmcore in order for them
to get dumped properly.

Handle corner cases that are unexpected and shouldn't happen in sane
setups: registering a callback after the vmcore has already been opened
(warn only) and unregistering a callback after the vmcore has already been
opened (warn and essentially read only zeroes from that point on).

Link: https://lkml.kernel.org/r/20211005121430.30136-6-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 69 insertions, 30 deletions

diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index a9bd80ab670e..7a04b2eca287 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -62,46 +62,75 @@ core_param(novmcoredd, vmcoredd_disabled, bool, 0);
 /* Device Dump Size */
 static size_t vmcoredd_orig_sz;
 
-/*
- * Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error
- * The called function has to take care of module refcounting.
- */
-static int (*oldmem_pfn_is_ram)(unsigned long pfn);
-
-int register_oldmem_pfn_is_ram(int (*fn)(unsigned long pfn))
+static DECLARE_RWSEM(vmcore_cb_rwsem);
+/* List of registered vmcore callbacks. */
+static LIST_HEAD(vmcore_cb_list);
+/* Whether we had a surprise unregistration of a callback. */
+static bool vmcore_cb_unstable;
+/* Whether the vmcore has been opened once. */
+static bool vmcore_opened;
+
+void register_vmcore_cb(struct vmcore_cb *cb)
 {
-	if (oldmem_pfn_is_ram)
-		return -EBUSY;
-	oldmem_pfn_is_ram = fn;
-	return 0;
+	down_write(&vmcore_cb_rwsem);
+	INIT_LIST_HEAD(&cb->next);
+	list_add_tail(&cb->next, &vmcore_cb_list);
+	/*
+	 * Registering a vmcore callback after the vmcore was opened is
+	 * very unusual (e.g., manual driver loading).
+	 */
+	if (vmcore_opened)
+		pr_warn_once("Unexpected vmcore callback registration\n");
+	up_write(&vmcore_cb_rwsem);
 }
-EXPORT_SYMBOL_GPL(register_oldmem_pfn_is_ram);
+EXPORT_SYMBOL_GPL(register_vmcore_cb);
 
-void unregister_oldmem_pfn_is_ram(void)
+void unregister_vmcore_cb(struct vmcore_cb *cb)
 {
-	oldmem_pfn_is_ram = NULL;
-	wmb();
+	down_write(&vmcore_cb_rwsem);
+	list_del(&cb->next);
+	/*
+	 * Unregistering a vmcore callback after the vmcore was opened is
+	 * very unusual (e.g., forced driver removal), but we cannot stop
+	 * unregistering.
+	 */
+	if (vmcore_opened) {
+		pr_warn_once("Unexpected vmcore callback unregistration\n");
+		vmcore_cb_unstable = true;
+	}
+	up_write(&vmcore_cb_rwsem);
 }
-EXPORT_SYMBOL_GPL(unregister_oldmem_pfn_is_ram);
+EXPORT_SYMBOL_GPL(unregister_vmcore_cb);
 
 static bool pfn_is_ram(unsigned long pfn)
 {
-	int (*fn)(unsigned long pfn);
-	/* pfn is ram unless fn() checks pagetype */
+	struct vmcore_cb *cb;
 	bool ret = true;
 
-	/*
-	 * Ask hypervisor if the pfn is really ram.
-	 * A ballooned page contains no data and reading from such a page
-	 * will cause high load in the hypervisor.
-	 */
-	fn = oldmem_pfn_is_ram;
-	if (fn)
-		ret = !!fn(pfn);
+	lockdep_assert_held_read(&vmcore_cb_rwsem);
+	if (unlikely(vmcore_cb_unstable))
+		return false;
+
+	list_for_each_entry(cb, &vmcore_cb_list, next) {
+		if (unlikely(!cb->pfn_is_ram))
+			continue;
+		ret = cb->pfn_is_ram(cb, pfn);
+		if (!ret)
+			break;
+	}
 
 	return ret;
 }
 
+static int open_vmcore(struct inode *inode, struct file *file)
+{
+	down_read(&vmcore_cb_rwsem);
+	vmcore_opened = true;
+	up_read(&vmcore_cb_rwsem);
+
+	return 0;
+}
+
 /* Reads a page from the oldmem device from given offset. */
 ssize_t read_from_oldmem(char *buf, size_t count,
 			 u64 *ppos, int userbuf,
@@ -117,6 +146,7 @@ ssize_t read_from_oldmem(char *buf, size_t count,
 	offset = (unsigned long)(*ppos % PAGE_SIZE);
 	pfn = (unsigned long)(*ppos / PAGE_SIZE);
 
+	down_read(&vmcore_cb_rwsem);
 	do {
 		if (count > (PAGE_SIZE - offset))
 			nr_bytes = PAGE_SIZE - offset;
@@ -136,8 +166,10 @@ ssize_t read_from_oldmem(char *buf, size_t count,
 				tmp = copy_oldmem_page(pfn, buf, nr_bytes,
 						       offset, userbuf);
 
-			if (tmp < 0)
+			if (tmp < 0) {
+				up_read(&vmcore_cb_rwsem);
 				return tmp;
+			}
 		}
 		*ppos += nr_bytes;
 		count -= nr_bytes;
@@ -147,6 +179,7 @@ ssize_t read_from_oldmem(char *buf, size_t count,
 		offset = 0;
 	} while (count);
 
+	up_read(&vmcore_cb_rwsem);
 	return read;
 }
 
@@ -537,14 +570,19 @@ static int vmcore_remap_oldmem_pfn(struct vm_area_struct *vma,
 			    unsigned long from, unsigned long pfn,
 			    unsigned long size, pgprot_t prot)
 {
+	int ret;
+
 	/*
 	 * Check if oldmem_pfn_is_ram was registered to avoid
 	 * looping over all pages without a reason.
 	 */
-	if (oldmem_pfn_is_ram)
-		return remap_oldmem_pfn_checked(vma, from, pfn, size, prot);
+	down_read(&vmcore_cb_rwsem);
+	if (!list_empty(&vmcore_cb_list) || vmcore_cb_unstable)
+		ret = remap_oldmem_pfn_checked(vma, from, pfn, size, prot);
 	else
-		return remap_oldmem_pfn_range(vma, from, pfn, size, prot);
+		ret = remap_oldmem_pfn_range(vma, from, pfn, size, prot);
+	up_read(&vmcore_cb_rwsem);
+	return ret;
 }
 
 static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
@@ -668,6 +706,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 #endif
 
 static const struct proc_ops vmcore_proc_ops = {
+	.proc_open	= open_vmcore,
 	.proc_read	= read_vmcore,
 	.proc_lseek	= default_llseek,
 	.proc_mmap	= mmap_vmcore,