efi: Allow disabling PCI busmastering on bridges during boot

Add an option to disable the busmaster bit in the control register on
all PCI bridges before calling ExitBootServices() and passing control
to the runtime kernel. System firmware may configure the IOMMU to prevent
malicious PCI devices from being able to attack the OS via DMA. However,
since firmware can't guarantee that the OS is IOMMU-aware, it will tear
down IOMMU configuration when ExitBootServices() is called. This leaves
a window between where a hostile device could still cause damage before
Linux configures the IOMMU again.

If CONFIG_EFI_DISABLE_PCI_DMA is enabled or "efi=disable_early_pci_dma"
is passed on the command line, the EFI stub will clear the busmaster bit
on all PCI bridges before ExitBootServices() is called. This will
prevent any malicious PCI devices from being able to perform DMA until
the kernel reenables busmastering after configuring the IOMMU.

This option may cause failures with some poorly behaved hardware and
should not be enabled without testing. The kernel commandline options
"efi=disable_early_pci_dma" or "efi=no_disable_early_pci_dma" may be
used to override the default. Note that PCI devices downstream from PCI
bridges are disconnected from their drivers first, using the UEFI
driver model API, so that DMA can be disabled safely at the bridge
level.

[ardb: disconnect PCI I/O handles first, as suggested by Arvind]

Co-developed-by: Matthew Garrett <[e-mail]>
Signed-off-by: Matthew Garrett <[e-mail]>
Signed-off-by: Ard Biesheuvel <[e-mail]>
Cc: Andy Lutomirski <[e-mail]>
Cc: Ard Biesheuvel <[e-mail]>
Cc: Arvind Sankar <[e-mail]>
Cc: Matthew Garrett <[e-mail]>
Cc: [e-mail]
Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: Ingo Molnar <[e-mail]>

Documentation/admin-guide/kernel-parameters.txt

···
 
 	efi=		[EFI]
 			Format: { "old_map", "nochunk", "noruntime", "debug",
-				  "nosoftreserve" }
+				  "nosoftreserve", "disable_early_pci_dma",
+				  "no_disable_early_pci_dma" }
 			old_map [X86-64]: switch to the old ioremap-based EFI
 			runtime services mapping. 32-bit still uses this one by
 			default.
···
 			claim. Specify efi=nosoftreserve to disable this
 			reservation and treat the memory by its base type
 			(i.e. EFI_CONVENTIONAL_MEMORY / "System RAM").
+			disable_early_pci_dma: Disable the busmaster bit on all
+			PCI bridges while in the EFI boot stub
+			no_disable_early_pci_dma: Leave the busmaster bit set
+			on all PCI bridges while in the EFI boot stub
 
 	efi_no_storage_paranoia [EFI; X86]
 			Using this parameter you can use more than 50% of

arch/x86/include/asm/efi.h

···
 #define __efi64_argmap_locate_protocol(protocol, reg, interface)	\
 	((protocol), (reg), efi64_zero_upper(interface))
 
+/* PCI I/O */
+#define __efi64_argmap_get_location(protocol, seg, bus, dev, func)	\
+	((protocol), efi64_zero_upper(seg), efi64_zero_upper(bus),	\
+	 efi64_zero_upper(dev), efi64_zero_upper(func))
+
 /*
  * The macros below handle the plumbing for the argument mapping. To add a
  * mapping for a specific EFI method, simply define a macro

drivers/firmware/efi/Kconfig

···
 
 	  Say Y here for Dell EMC PowerEdge systems.
 
+config EFI_DISABLE_PCI_DMA
+       bool "Clear Busmaster bit on PCI bridges during ExitBootServices()"
+       help
+	  Disable the busmaster bit in the control register on all PCI bridges
+	  while calling ExitBootServices() and passing control to the runtime
+	  kernel. System firmware may configure the IOMMU to prevent malicious
+	  PCI devices from being able to attack the OS via DMA. However, since
+	  firmware can't guarantee that the OS is IOMMU-aware, it will tear
+	  down IOMMU configuration when ExitBootServices() is called. This
+	  leaves a window between where a hostile device could still cause
+	  damage before Linux configures the IOMMU again.
+
+	  If you say Y here, the EFI stub will clear the busmaster bit on all
+	  PCI bridges before ExitBootServices() is called. This will prevent
+	  any malicious PCI devices from being able to perform DMA until the
+	  kernel reenables busmastering after configuring the IOMMU.
+
+	  This option will cause failures with some poorly behaved hardware
+	  and should not be enabled without testing. The kernel commandline
+	  options "efi=disable_early_pci_dma" or "efi=no_disable_early_pci_dma"
+	  may be used to override this option.
+
 endmenu
 
 config UEFI_CPER

drivers/firmware/efi/libstub/Makefile

···
 KCOV_INSTRUMENT			:= n
 
 lib-y				:= efi-stub-helper.o gop.o secureboot.o tpm.o \
-				   random.o
+				   random.o pci.o
 
 # include the stub's generic dependencies from lib/ when building for ARM/arm64
 arm-deps-y := fdt_rw.c fdt_ro.c fdt_wip.c fdt.c fdt_empty_tree.c fdt_sw.c

drivers/firmware/efi/libstub/efi-stub-helper.c

···
 static bool __efistub_global efi_quiet;
 static bool __efistub_global efi_novamap;
 static bool __efistub_global efi_nosoftreserve;
+static bool __efistub_global efi_disable_pci_dma =
+					IS_ENABLED(CONFIG_EFI_DISABLE_PCI_DMA);
 
 bool __pure nokaslr(void)
 {
···
 			efi_nosoftreserve = true;
 		}
 
+		if (!strncmp(str, "disable_early_pci_dma", 21)) {
+			str += strlen("disable_early_pci_dma");
+			efi_disable_pci_dma = true;
+		}
+
+		if (!strncmp(str, "no_disable_early_pci_dma", 24)) {
+			str += strlen("no_disable_early_pci_dma");
+			efi_disable_pci_dma = false;
+		}
+
 		/* Group words together, delimited by "," */
 		while (*str && *str != ' ' && *str != ',')
 			str++;
···
 	status = priv_func(map, priv);
 	if (status != EFI_SUCCESS)
 		goto free_map;
+
+	if (efi_disable_pci_dma)
+		efi_pci_disable_bridge_busmaster();
 
 	status = efi_bs_call(exit_boot_services, handle, *map->key_ptr);
 

drivers/firmware/efi/libstub/pci.c

···
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * PCI-related functions used by the EFI stub on multiple
+ * architectures.
+ *
+ * Copyright 2019 Google, LLC
+ */
+
+#include <linux/efi.h>
+#include <linux/pci.h>
+
+#include <asm/efi.h>
+
+#include "efistub.h"
+
+void efi_pci_disable_bridge_busmaster(void)
+{
+	efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
+	unsigned long pci_handle_size = 0;
+	efi_handle_t *pci_handle = NULL;
+	efi_handle_t handle;
+	efi_status_t status;
+	u16 class, command;
+	int i;
+
+	status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, &pci_proto,
+			     NULL, &pci_handle_size, NULL);
+
+	if (status != EFI_BUFFER_TOO_SMALL) {
+		if (status != EFI_SUCCESS && status != EFI_NOT_FOUND)
+			pr_efi_err("Failed to locate PCI I/O handles'\n");
+		return;
+	}
+
+	status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, pci_handle_size,
+			     (void **)&pci_handle);
+	if (status != EFI_SUCCESS) {
+		pr_efi_err("Failed to allocate memory for 'pci_handle'\n");
+		return;
+	}
+
+	status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, &pci_proto,
+			     NULL, &pci_handle_size, pci_handle);
+	if (status != EFI_SUCCESS) {
+		pr_efi_err("Failed to locate PCI I/O handles'\n");
+		goto free_handle;
+	}
+
+	for_each_efi_handle(handle, pci_handle, pci_handle_size, i) {
+		efi_pci_io_protocol_t *pci;
+		unsigned long segment_nr, bus_nr, device_nr, func_nr;
+
+		status = efi_bs_call(handle_protocol, handle, &pci_proto,
+				     (void **)&pci);
+		if (status != EFI_SUCCESS)
+			continue;
+
+		/*
+		 * Disregard devices living on bus 0 - these are not behind a
+		 * bridge so no point in disconnecting them from their drivers.
+		 */
+		status = efi_call_proto(pci, get_location, &segment_nr, &bus_nr,
+					&device_nr, &func_nr);
+		if (status != EFI_SUCCESS || bus_nr == 0)
+			continue;
+
+		/*
+		 * Don't disconnect VGA controllers so we don't risk losing
+		 * access to the framebuffer. Drivers for true PCIe graphics
+		 * controllers that are behind a PCIe root port do not use
+		 * DMA to implement the GOP framebuffer anyway [although they
+		 * may use it in their implentation of Gop->Blt()], and so
+		 * disabling DMA in the PCI bridge should not interfere with
+		 * normal operation of the device.
+		 */
+		status = efi_call_proto(pci, pci.read, EfiPciIoWidthUint16,
+					PCI_CLASS_DEVICE, 1, &class);
+		if (status != EFI_SUCCESS || class == PCI_CLASS_DISPLAY_VGA)
+			continue;
+
+		/* Disconnect this handle from all its drivers */
+		efi_bs_call(disconnect_controller, handle, NULL, NULL);
+	}
+
+	for_each_efi_handle(handle, pci_handle, pci_handle_size, i) {
+		efi_pci_io_protocol_t *pci;
+
+		status = efi_bs_call(handle_protocol, handle, &pci_proto,
+				     (void **)&pci);
+		if (status != EFI_SUCCESS || !pci)
+			continue;
+
+		status = efi_call_proto(pci, pci.read, EfiPciIoWidthUint16,
+					PCI_CLASS_DEVICE, 1, &class);
+
+		if (status != EFI_SUCCESS || class != PCI_CLASS_BRIDGE_PCI)
+			continue;
+
+		/* Disable busmastering */
+		status = efi_call_proto(pci, pci.read, EfiPciIoWidthUint16,
+					PCI_COMMAND, 1, &command);
+		if (status != EFI_SUCCESS || !(command & PCI_COMMAND_MASTER))
+			continue;
+
+		command &= ~PCI_COMMAND_MASTER;
+		status = efi_call_proto(pci, pci.write, EfiPciIoWidthUint16,
+					PCI_COMMAND, 1, &command);
+		if (status != EFI_SUCCESS)
+			pr_efi_err("Failed to disable PCI busmastering\n");
+	}
+
+free_handle:
+	efi_bs_call(free_pool, pci_handle);
+}

include/linux/efi.h

···
 		void *stall;
 		void *set_watchdog_timer;
 		void *connect_controller;
-		void *disconnect_controller;
+		efi_status_t (__efiapi *disconnect_controller)(efi_handle_t,
+							       efi_handle_t,
+							       efi_handle_t);
 		void *open_protocol;
 		void *close_protocol;
 		void *open_protocol_information;
···
 
 #define EFI_MEMRESERVE_COUNT(size) (((size) - sizeof(struct linux_efi_memreserve)) \
 	/ sizeof(((struct linux_efi_memreserve *)0)->entry[0]))
+
+void efi_pci_disable_bridge_busmaster(void);
 
 #endif /* _LINUX_EFI_H */