[PATCH v3 4/4] efi: Fix handling of multiple efi_fake_mem= entries

[Dan Williams]

Dave noticed that when specifying multiple efi_fake_mem= entries only
the last entry was successfully being reflected in the efi memory map.
This is due to the fact that the efi_memmap_insert() is being called
multiple times, but on successive invocations the insertion should be
applied to the last new memmap rather than the original map at
efi_fake_memmap() entry.

Rework efi_fake_memmap() to install the new memory map after each
efi_fake_mem= entry is parsed.

This also fixes an issue in efi_fake_memmap() that caused it to litter
emtpy entries into the end of the efi memory map. The empty entry causes
efi_memmap_insert() to attempt more memmap splits / copies than
efi_memmap_split_count() accounted for when sizing the new map.

    BUG: unable to handle page fault for address: ffffffffff281000
    [..]
    RIP: 0010:efi_memmap_insert+0x11d/0x191
    [..]
    Call Trace:
     ? bgrt_init+0xbe/0xbe
     ? efi_arch_mem_reserve+0x1cb/0x228
     ? acpi_parse_bgrt+0xa/0xd
     ? acpi_table_parse+0x86/0xb8
     ? acpi_boot_init+0x494/0x4e3
     ? acpi_parse_x2apic+0x87/0x87
     ? setup_acpi_sci+0xa2/0xa2
     ? setup_arch+0x8db/0x9e1
     ? start_kernel+0x6a/0x547
     ? secondary_startup_64+0xb6/0xc0

Commit af1648984828 "x86/efi: Update e820 with reserved EFI boot
services data to fix kexec breakage" is listed in Fixes: since it
introduces more occurrences where efi_memmap_insert() is invoked after
an efi_fake_mem= configuration has been parsed. Previously the side
effects of vestigial empty entries were benign, but with commit
af1648984828 that follow-on efi_memmap_insert() invocation triggers the
above crash signature.

Fixes: 0f96a99dab36 ("efi: Add 'efi_fake_mem' boot option")
Fixes: af1648984828 ("x86/efi: Update e820 with reserved EFI boot services...")
Link: https://lore.kernel.org/r/20191231014630.GA24942@xxxxxxxxxxxxxxxxxxxxxxxxxx
Reported-by: Dave Young <dyoung@xxxxxxxxxx>
Cc: Taku Izumi <izumi.taku@xxxxxxxxxxxxxx>
Cc: Michael Weiser <michael@xxxxxxxxxxxxxxxxxxx>
Cc: Ard Biesheuvel <ard.biesheuvel@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx>
---
 drivers/firmware/efi/fake_mem.c |   32 +++++++++++++++++---------------
 drivers/firmware/efi/memmap.c   |    2 +-
 include/linux/efi.h             |    2 ++
 3 files changed, 20 insertions(+), 16 deletions(-)

diff --git a/drivers/firmware/efi/fake_mem.c b/drivers/firmware/efi/fake_mem.c
index 7e53e5520548..68d752d8af21 100644
--- a/drivers/firmware/efi/fake_mem.c
+++ b/drivers/firmware/efi/fake_mem.c
@@ -34,26 +34,17 @@ static int __init cmp_fake_mem(const void *x1, const void *x2)
 	return 0;
 }
 
-void __init efi_fake_memmap(void)
+static void __init efi_fake_range(struct efi_mem_range *efi_range)
 {
 	int new_nr_map = efi.memmap.nr_map;
 	efi_memory_desc_t *md;
 	phys_addr_t new_memmap_phy;
 	unsigned long flags = 0;
 	void *new_memmap;
-	int i;
-
-	if (!efi_enabled(EFI_MEMMAP) || !nr_fake_mem)
-		return;
 
 	/* count up the number of EFI memory descriptor */
-	for (i = 0; i < nr_fake_mem; i++) {
-		for_each_efi_memory_desc(md) {
-			struct range *r = &efi_fake_mems[i].range;
-
-			new_nr_map += efi_memmap_split_count(md, r);
-		}
-	}
+	for_each_efi_memory_desc(md)
+		new_nr_map += efi_memmap_split_count(md, &efi_range->range);
 
 	/* allocate memory for new EFI memmap */
 	new_memmap_phy = efi_memmap_alloc(new_nr_map, &flags);
@@ -64,17 +55,28 @@ void __init efi_fake_memmap(void)
 	new_memmap = early_memremap(new_memmap_phy,
 				    efi.memmap.desc_size * new_nr_map);
 	if (!new_memmap) {
-		memblock_free(new_memmap_phy, efi.memmap.desc_size * new_nr_map);
+		__efi_memmap_free(new_memmap_phy,
+				efi.memmap.desc_size * new_nr_map, flags);
 		return;
 	}
 
-	for (i = 0; i < nr_fake_mem; i++)
-		efi_memmap_insert(&efi.memmap, new_memmap, &efi_fake_mems[i]);
+	efi_memmap_insert(&efi.memmap, new_memmap, efi_range);
 
 	/* swap into new EFI memmap */
 	early_memunmap(new_memmap, efi.memmap.desc_size * new_nr_map);
 
 	efi_memmap_install(new_memmap_phy, new_nr_map, flags);
+}
+
+void __init efi_fake_memmap(void)
+{
+	int i;
+
+	if (!efi_enabled(EFI_MEMMAP) || !nr_fake_mem)
+		return;
+
+	for (i = 0; i < nr_fake_mem; i++)
+		efi_fake_range(&efi_fake_mems[i]);
 
 	/* print new EFI memmap */
 	efi_print_memmap();
diff --git a/drivers/firmware/efi/memmap.c b/drivers/firmware/efi/memmap.c
index 46c8b4056cc1..157b7776caf5 100644
--- a/drivers/firmware/efi/memmap.c
+++ b/drivers/firmware/efi/memmap.c
@@ -29,7 +29,7 @@ static phys_addr_t __init __efi_memmap_alloc_late(unsigned long size)
 	return PFN_PHYS(page_to_pfn(p));
 }
 
-static void __init __efi_memmap_free(u64 phys, unsigned long size, unsigned long flags)
+void __init __efi_memmap_free(u64 phys, unsigned long size, unsigned long flags)
 {
 	if (flags & EFI_MEMMAP_MEMBLOCK) {
 		if (slab_is_available())
diff --git a/include/linux/efi.h b/include/linux/efi.h
index fa2668a992ae..6ae31e064321 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1061,6 +1061,8 @@ extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr);
 
 extern phys_addr_t __init efi_memmap_alloc(unsigned int num_entries,
 		unsigned long *flags);
+extern void __efi_memmap_free(u64 phys, unsigned long size,
+		unsigned long flags);
 extern int __init efi_memmap_init_early(struct efi_memory_map_data *data);
 extern int __init efi_memmap_init_late(phys_addr_t addr, unsigned long size);
 extern void __init efi_memmap_unmap(void);