public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Greg Kroah-Hartman <greg@kroah.com>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	stable@vger.kernel.org,
	Matthew Garrett <matthew.garrett@nebula.com>,
	Matt Fleming <matt.fleming@intel.com>,
	"Lee, Chun-Y" <jlee@suse.com>
Subject: [ 39/48] Modify UEFI anti-bricking code
Date: Tue, 18 Jun 2013 09:18:05 -0700	[thread overview]
Message-ID: <20130618161731.565472700@linuxfoundation.org> (raw)
In-Reply-To: <20130618161725.912524266@linuxfoundation.org>

From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3.9-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Matthew Garrett <matthew.garrett@nebula.com>

commit f8b8404337de4e2466e2e1139ea68b1f8295974f upstream.

This patch reworks the UEFI anti-bricking code, including an effective
reversion of cc5a080c and 31ff2f20. It turns out that calling
QueryVariableInfo() from boot services results in some firmware
implementations jumping to physical addresses even after entering virtual
mode, so until we have 1:1 mappings for UEFI runtime space this isn't
going to work so well.

Reverting these gets us back to the situation where we'd refuse to create
variables on some systems because they classify deleted variables as "used"
until the firmware triggers a garbage collection run, which they won't do
until they reach a lower threshold. This results in it being impossible to
install a bootloader, which is unhelpful.

Feedback from Samsung indicates that the firmware doesn't need more than
5KB of storage space for its own purposes, so that seems like a reasonable
threshold. However, there's still no guarantee that a platform will attempt
garbage collection merely because it drops below this threshold. It seems
that this is often only triggered if an attempt to write generates a
genuine EFI_OUT_OF_RESOURCES error. We can force that by attempting to
create a variable larger than the remaining space. This should fail, but if
it somehow succeeds we can then immediately delete it.

I've tested this on the UEFI machines I have available, but I don't have
a Samsung and so can't verify that it avoids the bricking problem.

Signed-off-by: Matthew Garrett <matthew.garrett@nebula.com>
Signed-off-by: Lee, Chun-Y <jlee@suse.com> [ dummy variable cleanup ]
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 arch/x86/boot/compressed/eboot.c      |   47 --------
 arch/x86/include/asm/efi.h            |    7 -
 arch/x86/include/uapi/asm/bootparam.h |    1 
 arch/x86/platform/efi/efi.c           |  190 +++++++++++-----------------------
 4 files changed, 66 insertions(+), 179 deletions(-)

--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -251,51 +251,6 @@ static void find_bits(unsigned long mask
 	*size = len;
 }
 
-static efi_status_t setup_efi_vars(struct boot_params *params)
-{
-	struct setup_data *data;
-	struct efi_var_bootdata *efidata;
-	u64 store_size, remaining_size, var_size;
-	efi_status_t status;
-
-	if (sys_table->runtime->hdr.revision < EFI_2_00_SYSTEM_TABLE_REVISION)
-		return EFI_UNSUPPORTED;
-
-	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
-
-	while (data && data->next)
-		data = (struct setup_data *)(unsigned long)data->next;
-
-	status = efi_call_phys4((void *)sys_table->runtime->query_variable_info,
-				EFI_VARIABLE_NON_VOLATILE |
-				EFI_VARIABLE_BOOTSERVICE_ACCESS |
-				EFI_VARIABLE_RUNTIME_ACCESS, &store_size,
-				&remaining_size, &var_size);
-
-	if (status != EFI_SUCCESS)
-		return status;
-
-	status = efi_call_phys3(sys_table->boottime->allocate_pool,
-				EFI_LOADER_DATA, sizeof(*efidata), &efidata);
-
-	if (status != EFI_SUCCESS)
-		return status;
-
-	efidata->data.type = SETUP_EFI_VARS;
-	efidata->data.len = sizeof(struct efi_var_bootdata) -
-		sizeof(struct setup_data);
-	efidata->data.next = 0;
-	efidata->store_size = store_size;
-	efidata->remaining_size = remaining_size;
-	efidata->max_var_size = var_size;
-
-	if (data)
-		data->next = (unsigned long)efidata;
-	else
-		params->hdr.setup_data = (unsigned long)efidata;
-
-}
-
 static efi_status_t setup_efi_pci(struct boot_params *params)
 {
 	efi_pci_io_protocol *pci;
@@ -1202,8 +1157,6 @@ struct boot_params *efi_main(void *handl
 
 	setup_graphics(boot_params);
 
-	setup_efi_vars(boot_params);
-
 	setup_efi_pci(boot_params);
 
 	status = efi_call_phys3(sys_table->boottime->allocate_pool,
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -102,13 +102,6 @@ extern void efi_call_phys_epilog(void);
 extern void efi_unmap_memmap(void);
 extern void efi_memory_uc(u64 addr, unsigned long size);
 
-struct efi_var_bootdata {
-	struct setup_data data;
-	u64 store_size;
-	u64 remaining_size;
-	u64 max_var_size;
-};
-
 #ifdef CONFIG_EFI
 
 static inline bool efi_is_native(void)
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -6,7 +6,6 @@
 #define SETUP_E820_EXT			1
 #define SETUP_DTB			2
 #define SETUP_PCI			3
-#define SETUP_EFI_VARS			4
 
 /* ram_size flags */
 #define RAMDISK_IMAGE_START_MASK	0x07FF
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -41,7 +41,6 @@
 #include <linux/io.h>
 #include <linux/reboot.h>
 #include <linux/bcd.h>
-#include <linux/ucs2_string.h>
 
 #include <asm/setup.h>
 #include <asm/efi.h>
@@ -52,12 +51,12 @@
 
 #define EFI_DEBUG	1
 
-/*
- * There's some additional metadata associated with each
- * variable. Intel's reference implementation is 60 bytes - bump that
- * to account for potential alignment constraints
- */
-#define VAR_METADATA_SIZE 64
+#define EFI_MIN_RESERVE 5120
+
+#define EFI_DUMMY_GUID \
+	EFI_GUID(0x4424ac57, 0xbe4b, 0x47dd, 0x9e, 0x97, 0xed, 0x50, 0xf0, 0x9f, 0x92, 0xa9)
+
+static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 };
 
 struct efi __read_mostly efi = {
 	.mps        = EFI_INVALID_TABLE_ADDR,
@@ -77,13 +76,6 @@ struct efi_memory_map memmap;
 static struct efi efi_phys __initdata;
 static efi_system_table_t efi_systab __initdata;
 
-static u64 efi_var_store_size;
-static u64 efi_var_remaining_size;
-static u64 efi_var_max_var_size;
-static u64 boot_used_size;
-static u64 boot_var_size;
-static u64 active_size;
-
 unsigned long x86_efi_facility;
 
 /*
@@ -186,53 +178,8 @@ static efi_status_t virt_efi_get_next_va
 					       efi_char16_t *name,
 					       efi_guid_t *vendor)
 {
-	efi_status_t status;
-	static bool finished = false;
-	static u64 var_size;
-
-	status = efi_call_virt3(get_next_variable,
-				name_size, name, vendor);
-
-	if (status == EFI_NOT_FOUND) {
-		finished = true;
-		if (var_size < boot_used_size) {
-			boot_var_size = boot_used_size - var_size;
-			active_size += boot_var_size;
-		} else {
-			printk(KERN_WARNING FW_BUG  "efi: Inconsistent initial sizes\n");
-		}
-	}
-
-	if (boot_used_size && !finished) {
-		unsigned long size;
-		u32 attr;
-		efi_status_t s;
-		void *tmp;
-
-		s = virt_efi_get_variable(name, vendor, &attr, &size, NULL);
-
-		if (s != EFI_BUFFER_TOO_SMALL || !size)
-			return status;
-
-		tmp = kmalloc(size, GFP_ATOMIC);
-
-		if (!tmp)
-			return status;
-
-		s = virt_efi_get_variable(name, vendor, &attr, &size, tmp);
-
-		if (s == EFI_SUCCESS && (attr & EFI_VARIABLE_NON_VOLATILE)) {
-			var_size += size;
-			var_size += ucs2_strsize(name, 1024);
-			active_size += size;
-			active_size += VAR_METADATA_SIZE;
-			active_size += ucs2_strsize(name, 1024);
-		}
-
-		kfree(tmp);
-	}
-
-	return status;
+	return efi_call_virt3(get_next_variable,
+			      name_size, name, vendor);
 }
 
 static efi_status_t virt_efi_set_variable(efi_char16_t *name,
@@ -241,34 +188,9 @@ static efi_status_t virt_efi_set_variabl
 					  unsigned long data_size,
 					  void *data)
 {
-	efi_status_t status;
-	u32 orig_attr = 0;
-	unsigned long orig_size = 0;
-
-	status = virt_efi_get_variable(name, vendor, &orig_attr, &orig_size,
-				       NULL);
-
-	if (status != EFI_BUFFER_TOO_SMALL)
-		orig_size = 0;
-
-	status = efi_call_virt5(set_variable,
-				name, vendor, attr,
-				data_size, data);
-
-	if (status == EFI_SUCCESS) {
-		if (orig_size) {
-			active_size -= orig_size;
-			active_size -= ucs2_strsize(name, 1024);
-			active_size -= VAR_METADATA_SIZE;
-		}
-		if (data_size) {
-			active_size += data_size;
-			active_size += ucs2_strsize(name, 1024);
-			active_size += VAR_METADATA_SIZE;
-		}
-	}
-
-	return status;
+	return efi_call_virt5(set_variable,
+			      name, vendor, attr,
+			      data_size, data);
 }
 
 static efi_status_t virt_efi_query_variable_info(u32 attr,
@@ -776,9 +698,6 @@ void __init efi_init(void)
 	char vendor[100] = "unknown";
 	int i = 0;
 	void *tmp;
-	struct setup_data *data;
-	struct efi_var_bootdata *efi_var_data;
-	u64 pa_data;
 
 #ifdef CONFIG_X86_32
 	if (boot_params.efi_info.efi_systab_hi ||
@@ -796,22 +715,6 @@ void __init efi_init(void)
 	if (efi_systab_init(efi_phys.systab))
 		return;
 
-	pa_data = boot_params.hdr.setup_data;
-	while (pa_data) {
-		data = early_ioremap(pa_data, sizeof(*efi_var_data));
-		if (data->type == SETUP_EFI_VARS) {
-			efi_var_data = (struct efi_var_bootdata *)data;
-
-			efi_var_store_size = efi_var_data->store_size;
-			efi_var_remaining_size = efi_var_data->remaining_size;
-			efi_var_max_var_size = efi_var_data->max_var_size;
-		}
-		pa_data = data->next;
-		early_iounmap(data, sizeof(*efi_var_data));
-	}
-
-	boot_used_size = efi_var_store_size - efi_var_remaining_size;
-
 	set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility);
 
 	/*
@@ -1075,6 +978,13 @@ void __init efi_enter_virtual_mode(void)
 		runtime_code_page_mkexec();
 
 	kfree(new_memmap);
+
+	/* clean DUMMY object */
+	efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
+			 EFI_VARIABLE_NON_VOLATILE |
+			 EFI_VARIABLE_BOOTSERVICE_ACCESS |
+			 EFI_VARIABLE_RUNTIME_ACCESS,
+			 0, NULL);
 }
 
 /*
@@ -1126,33 +1036,65 @@ efi_status_t efi_query_variable_store(u3
 	efi_status_t status;
 	u64 storage_size, remaining_size, max_size;
 
+	if (!(attributes & EFI_VARIABLE_NON_VOLATILE))
+		return 0;
+
 	status = efi.query_variable_info(attributes, &storage_size,
 					 &remaining_size, &max_size);
 	if (status != EFI_SUCCESS)
 		return status;
 
-	if (!max_size && remaining_size > size)
-		printk_once(KERN_ERR FW_BUG "Broken EFI implementation"
-			    " is returning MaxVariableSize=0\n");
 	/*
 	 * Some firmware implementations refuse to boot if there's insufficient
 	 * space in the variable store. We account for that by refusing the
 	 * write if permitting it would reduce the available space to under
-	 * 50%. However, some firmware won't reclaim variable space until
-	 * after the used (not merely the actively used) space drops below
-	 * a threshold. We can approximate that case with the value calculated
-	 * above. If both the firmware and our calculations indicate that the
-	 * available space would drop below 50%, refuse the write.
+	 * 5KB. This figure was provided by Samsung, so should be safe.
 	 */
+	if ((remaining_size - size < EFI_MIN_RESERVE) &&
+		!efi_no_storage_paranoia) {
 
-	if (!storage_size || size > remaining_size ||
-	    (max_size && size > max_size))
-		return EFI_OUT_OF_RESOURCES;
-
-	if (!efi_no_storage_paranoia &&
-	    ((active_size + size + VAR_METADATA_SIZE > storage_size / 2) &&
-	     (remaining_size - size < storage_size / 2)))
-		return EFI_OUT_OF_RESOURCES;
+		/*
+		 * Triggering garbage collection may require that the firmware
+		 * generate a real EFI_OUT_OF_RESOURCES error. We can force
+		 * that by attempting to use more space than is available.
+		 */
+		unsigned long dummy_size = remaining_size + 1024;
+		void *dummy = kmalloc(dummy_size, GFP_ATOMIC);
+
+		status = efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
+					  EFI_VARIABLE_NON_VOLATILE |
+					  EFI_VARIABLE_BOOTSERVICE_ACCESS |
+					  EFI_VARIABLE_RUNTIME_ACCESS,
+					  dummy_size, dummy);
+
+		if (status == EFI_SUCCESS) {
+			/*
+			 * This should have failed, so if it didn't make sure
+			 * that we delete it...
+			 */
+			efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
+					 EFI_VARIABLE_NON_VOLATILE |
+					 EFI_VARIABLE_BOOTSERVICE_ACCESS |
+					 EFI_VARIABLE_RUNTIME_ACCESS,
+					 0, dummy);
+		}
+
+		/*
+		 * The runtime code may now have triggered a garbage collection
+		 * run, so check the variable info again
+		 */
+		status = efi.query_variable_info(attributes, &storage_size,
+						 &remaining_size, &max_size);
+
+		if (status != EFI_SUCCESS)
+			return status;
+
+		/*
+		 * There still isn't enough room, so return an error
+		 */
+		if (remaining_size - size < EFI_MIN_RESERVE)
+			return EFI_OUT_OF_RESOURCES;
+	}
 
 	return EFI_SUCCESS;
 }



  parent reply	other threads:[~2013-06-18 16:24 UTC|newest]

Thread overview: 67+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-06-18 16:17 [ 00/48] 3.9.7-stable review Greg Kroah-Hartman
2013-06-18 16:17 ` [ 01/48] audit: wait_for_auditd() should use TASK_UNINTERRUPTIBLE Greg Kroah-Hartman
2013-06-18 16:17 ` [ 02/48] b43: stop format string leaking into error msgs Greg Kroah-Hartman
2013-06-18 16:17 ` [ 03/48] ACPI / video: Do not bind to device objects with a scan handler Greg Kroah-Hartman
2013-06-18 16:17 ` [ 04/48] libceph: must hold mutex for reset_changed_osds() Greg Kroah-Hartman
2013-06-18 16:17 ` [ 05/48] ceph: add cpu_to_le32() calls when encoding a reconnect capability Greg Kroah-Hartman
2013-06-18 16:17 ` [ 06/48] ceph: ceph_pagelist_append might sleep while atomic Greg Kroah-Hartman
2013-06-18 16:17 ` [ 07/48] rbd: dont destroy ceph_opts in rbd_add() Greg Kroah-Hartman
2013-06-18 16:17 ` [ 08/48] drivers/rtc/rtc-twl.c: fix missing device_init_wakeup() when booted with device tree Greg Kroah-Hartman
2013-06-18 16:17 ` [ 09/48] drm/gma500/psb: Unpin framebuffer on crtc disable Greg Kroah-Hartman
2013-06-18 16:17 ` [ 10/48] drm/gma500/cdv: " Greg Kroah-Hartman
2013-06-18 16:17 ` [ 11/48] Bluetooth: Fix missing length checks for L2CAP signalling PDUs Greg Kroah-Hartman
2013-06-18 16:17 ` [ 12/48] Bluetooth: Fix mgmt handling of power on failures Greg Kroah-Hartman
2013-06-18 16:17 ` [ 13/48] s390/pci: Implement IRQ functions if !PCI Greg Kroah-Hartman
2013-06-18 17:35   ` Ben Hutchings
2013-06-18 17:42     ` Greg Kroah-Hartman
2013-06-18 21:35       ` Ben Hutchings
2013-06-19  7:09     ` Martin Schwidefsky
2013-06-20 19:21     ` Greg Kroah-Hartman
2013-06-18 16:17 ` [ 14/48] ath9k: Disable PowerSave by default Greg Kroah-Hartman
2013-06-18 16:17 ` [ 15/48] Revert "ath9k_hw: Update rx gain initval to improve rx sensitivity" Greg Kroah-Hartman
2013-06-18 16:17 ` [ 16/48] ath9k: Use minstrel rate control by default Greg Kroah-Hartman
2013-06-18 16:17 ` [ 17/48] CPU hotplug: provide a generic helper to disable/enable CPU hotplug Greg Kroah-Hartman
2013-06-18 16:17 ` [ 18/48] reboot: rigrate shutdown/reboot to boot cpu Greg Kroah-Hartman
2013-06-18 16:17 ` [ 19/48] kmsg: honor dmesg_restrict sysctl on /dev/kmsg Greg Kroah-Hartman
2013-06-18 16:17 ` [ 20/48] cciss: fix broken mutex usage in ioctl Greg Kroah-Hartman
2013-06-18 16:17 ` [ 21/48] memcg: dont initialize kmem-cache destroying work for root caches Greg Kroah-Hartman
2013-06-18 16:17 ` [ 22/48] wl12xx: fix minimum required firmware version for wl127x multirole Greg Kroah-Hartman
2013-06-18 16:17 ` [ 23/48] drm/i915: prefer VBT modes for SVDO-LVDS over EDID Greg Kroah-Hartman
2013-06-18 16:17 ` [ 24/48] swap: avoid read_swap_cache_async() race to deadlock while waiting on discard I/O completion Greg Kroah-Hartman
2013-06-18 16:17 ` [ 25/48] md/raid1: consider WRITE as successful only if at least one non-Faulty and non-rebuilding drive completed it Greg Kroah-Hartman
2013-06-18 16:17 ` [ 26/48] md/raid1,5,10: Disable WRITE SAME until a recovery strategy is in place Greg Kroah-Hartman
2013-06-18 16:17 ` [ 27/48] md/raid1,raid10: use freeze_array in place of raise_barrier in various places Greg Kroah-Hartman
2013-06-18 16:17 ` [ 28/48] mm/page_alloc.c: fix watermark check in __zone_watermark_ok() Greg Kroah-Hartman
2013-06-18 16:17 ` [ 29/48] mm: migration: add migrate_entry_wait_huge() Greg Kroah-Hartman
2013-06-20  9:52   ` Satoru Takeuchi
2013-06-20 17:02     ` Greg Kroah-Hartman
2013-06-21 11:42       ` Satoru Takeuchi
2013-06-21 12:47     ` Michal Hocko
2013-06-21 22:56       ` Satoru Takeuchi
2013-06-22 12:28         ` Satoru Takeuchi
2013-06-27 18:48     ` Naoya Horiguchi
2013-06-18 16:17 ` [ 30/48] x86: Fix adjust_range_size_mask calling position Greg Kroah-Hartman
2013-06-18 16:17 ` [ 31/48] x86: Fix typo in kexec register clearing Greg Kroah-Hartman
2013-06-18 16:17 ` [ 32/48] drm/nv50/disp: force dac power state during load detect Greg Kroah-Hartman
2013-06-18 16:17 ` [ 33/48] drm/nv50/kms: use dac loadval from vbios, where its available Greg Kroah-Hartman
2013-06-18 16:18 ` [ 34/48] libceph: clear messenger auth_retry flag when we authenticate Greg Kroah-Hartman
2013-06-18 16:18 ` [ 35/48] libceph: fix authorizer invalidation Greg Kroah-Hartman
2013-06-18 16:18 ` [ 36/48] libceph: add update_authorizer auth method Greg Kroah-Hartman
2013-06-18 16:18 ` [ 37/48] libceph: wrap auth ops in wrapper functions Greg Kroah-Hartman
2013-06-18 16:18 ` [ 38/48] libceph: wrap auth methods in a mutex Greg Kroah-Hartman
2013-06-18 16:18 ` Greg Kroah-Hartman [this message]
2013-06-18 16:18 ` [ 40/48] powerpc: Fix stack overflow crash in resume_kernel when ftracing Greg Kroah-Hartman
2013-06-18 16:18 ` [ 41/48] powerpc: Fix emulation of illegal instructions on PowerNV platform Greg Kroah-Hartman
2013-06-18 16:18 ` [ 42/48] powerpc: Fix missing/delayed calls to irq_work Greg Kroah-Hartman
2013-06-18 16:18 ` [ 43/48] usb: chipidea: fix id change handling Greg Kroah-Hartman
2013-06-18 16:18 ` [ 44/48] USB: pl2303: fix device initialisation at open Greg Kroah-Hartman
2013-06-18 16:18 ` [ 45/48] USB: f81232: " Greg Kroah-Hartman
2013-06-18 16:18 ` [ 46/48] USB: spcp8x5: " Greg Kroah-Hartman
2013-06-18 16:18 ` [ 47/48] tg3: Wait for boot code to finish after power on Greg Kroah-Hartman
2013-06-18 16:18 ` [ 48/48] ARM: Kirkwood: handle mv88f6282 cpu in __kirkwood_variant() Greg Kroah-Hartman
2013-06-18 21:55 ` [ 00/48] 3.9.7-stable review Shuah Khan
2013-06-18 22:11   ` Greg Kroah-Hartman
2013-06-18 22:58 ` Guenter Roeck
2013-06-18 23:26   ` Greg Kroah-Hartman
2013-06-20 10:02 ` Satoru Takeuchi
2013-06-20 17:01   ` Greg Kroah-Hartman

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20130618161731.565472700@linuxfoundation.org \
    --to=greg@kroah.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=jlee@suse.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=matt.fleming@intel.com \
    --cc=matthew.garrett@nebula.com \
    --cc=stable@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox