This reverts commit f22e9b67f19ccc73de1ae04375d4b30684e261f8.
The regression reported in
https://lore.kernel.org/all/ZF4bMptC3Lf2Hnee@gerhold.net/ is being
fixed in
commit 7d7863db7cc0 ("usb: gadget: udc: core: Offload usb_udc_vbus_handler processing").
Hence reverting the revert.
Signed-off-by: Badhri Jagan Sridharan <badhri(a)google.com>
---
drivers/usb/gadget/udc/core.c | 148 ++++++++++++++++++++++++----------
1 file changed, 104 insertions(+), 44 deletions(-)
diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c
index 52e6d2e84e35..583c339876ab 100644
--- a/drivers/usb/gadget/udc/core.c
+++ b/drivers/usb/gadget/udc/core.c
@@ -37,6 +37,10 @@ static const struct bus_type gadget_bus_type;
* @vbus: for udcs who care about vbus status, this value is real vbus status;
* for udcs who do not care about vbus status, this value is always true
* @started: the UDC's started state. True if the UDC had started.
+ * @connect_lock: protects udc->vbus, udc->started, gadget->connect, gadget->deactivate related
+ * functions. usb_gadget_connect_locked, usb_gadget_disconnect_locked,
+ * usb_udc_connect_control_locked, usb_gadget_udc_start_locked, usb_gadget_udc_stop_locked are
+ * called with this lock held.
*
* This represents the internal data structure which is used by the UDC-class
* to hold information about udc driver and gadget together.
@@ -48,6 +52,7 @@ struct usb_udc {
struct list_head list;
bool vbus;
bool started;
+ struct mutex connect_lock;
};
static struct class *udc_class;
@@ -687,17 +692,9 @@ int usb_gadget_vbus_disconnect(struct usb_gadget *gadget)
}
EXPORT_SYMBOL_GPL(usb_gadget_vbus_disconnect);
-/**
- * usb_gadget_connect - software-controlled connect to USB host
- * @gadget:the peripheral being connected
- *
- * Enables the D+ (or potentially D-) pullup. The host will start
- * enumerating this gadget when the pullup is active and a VBUS session
- * is active (the link is powered).
- *
- * Returns zero on success, else negative errno.
- */
-int usb_gadget_connect(struct usb_gadget *gadget)
+/* Internal version of usb_gadget_connect needs to be called with connect_lock held. */
+static int usb_gadget_connect_locked(struct usb_gadget *gadget)
+ __must_hold(&gadget->udc->connect_lock)
{
int ret = 0;
@@ -706,10 +703,12 @@ int usb_gadget_connect(struct usb_gadget *gadget)
goto out;
}
- if (gadget->deactivated) {
+ if (gadget->deactivated || !gadget->udc->started) {
/*
* If gadget is deactivated we only save new state.
* Gadget will be connected automatically after activation.
+ *
+ * udc first needs to be started before gadget can be pulled up.
*/
gadget->connected = true;
goto out;
@@ -724,22 +723,32 @@ int usb_gadget_connect(struct usb_gadget *gadget)
return ret;
}
-EXPORT_SYMBOL_GPL(usb_gadget_connect);
/**
- * usb_gadget_disconnect - software-controlled disconnect from USB host
- * @gadget:the peripheral being disconnected
- *
- * Disables the D+ (or potentially D-) pullup, which the host may see
- * as a disconnect (when a VBUS session is active). Not all systems
- * support software pullup controls.
+ * usb_gadget_connect - software-controlled connect to USB host
+ * @gadget:the peripheral being connected
*
- * Following a successful disconnect, invoke the ->disconnect() callback
- * for the current gadget driver so that UDC drivers don't need to.
+ * Enables the D+ (or potentially D-) pullup. The host will start
+ * enumerating this gadget when the pullup is active and a VBUS session
+ * is active (the link is powered).
*
* Returns zero on success, else negative errno.
*/
-int usb_gadget_disconnect(struct usb_gadget *gadget)
+int usb_gadget_connect(struct usb_gadget *gadget)
+{
+ int ret;
+
+ mutex_lock(&gadget->udc->connect_lock);
+ ret = usb_gadget_connect_locked(gadget);
+ mutex_unlock(&gadget->udc->connect_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(usb_gadget_connect);
+
+/* Internal version of usb_gadget_disconnect needs to be called with connect_lock held. */
+static int usb_gadget_disconnect_locked(struct usb_gadget *gadget)
+ __must_hold(&gadget->udc->connect_lock)
{
int ret = 0;
@@ -751,10 +760,12 @@ int usb_gadget_disconnect(struct usb_gadget *gadget)
if (!gadget->connected)
goto out;
- if (gadget->deactivated) {
+ if (gadget->deactivated || !gadget->udc->started) {
/*
* If gadget is deactivated we only save new state.
* Gadget will stay disconnected after activation.
+ *
+ * udc should have been started before gadget being pulled down.
*/
gadget->connected = false;
goto out;
@@ -774,6 +785,30 @@ int usb_gadget_disconnect(struct usb_gadget *gadget)
return ret;
}
+
+/**
+ * usb_gadget_disconnect - software-controlled disconnect from USB host
+ * @gadget:the peripheral being disconnected
+ *
+ * Disables the D+ (or potentially D-) pullup, which the host may see
+ * as a disconnect (when a VBUS session is active). Not all systems
+ * support software pullup controls.
+ *
+ * Following a successful disconnect, invoke the ->disconnect() callback
+ * for the current gadget driver so that UDC drivers don't need to.
+ *
+ * Returns zero on success, else negative errno.
+ */
+int usb_gadget_disconnect(struct usb_gadget *gadget)
+{
+ int ret;
+
+ mutex_lock(&gadget->udc->connect_lock);
+ ret = usb_gadget_disconnect_locked(gadget);
+ mutex_unlock(&gadget->udc->connect_lock);
+
+ return ret;
+}
EXPORT_SYMBOL_GPL(usb_gadget_disconnect);
/**
@@ -794,10 +829,11 @@ int usb_gadget_deactivate(struct usb_gadget *gadget)
if (gadget->deactivated)
goto out;
+ mutex_lock(&gadget->udc->connect_lock);
if (gadget->connected) {
- ret = usb_gadget_disconnect(gadget);
+ ret = usb_gadget_disconnect_locked(gadget);
if (ret)
- goto out;
+ goto unlock;
/*
* If gadget was being connected before deactivation, we want
@@ -807,6 +843,8 @@ int usb_gadget_deactivate(struct usb_gadget *gadget)
}
gadget->deactivated = true;
+unlock:
+ mutex_unlock(&gadget->udc->connect_lock);
out:
trace_usb_gadget_deactivate(gadget, ret);
@@ -830,6 +868,7 @@ int usb_gadget_activate(struct usb_gadget *gadget)
if (!gadget->deactivated)
goto out;
+ mutex_lock(&gadget->udc->connect_lock);
gadget->deactivated = false;
/*
@@ -837,7 +876,8 @@ int usb_gadget_activate(struct usb_gadget *gadget)
* while it was being deactivated, we call usb_gadget_connect().
*/
if (gadget->connected)
- ret = usb_gadget_connect(gadget);
+ ret = usb_gadget_connect_locked(gadget);
+ mutex_unlock(&gadget->udc->connect_lock);
out:
trace_usb_gadget_activate(gadget, ret);
@@ -1078,12 +1118,13 @@ EXPORT_SYMBOL_GPL(usb_gadget_set_state);
/* ------------------------------------------------------------------------- */
-static void usb_udc_connect_control(struct usb_udc *udc)
+/* Acquire connect_lock before calling this function. */
+static void usb_udc_connect_control_locked(struct usb_udc *udc) __must_hold(&udc->connect_lock)
{
- if (udc->vbus)
- usb_gadget_connect(udc->gadget);
+ if (udc->vbus && udc->started)
+ usb_gadget_connect_locked(udc->gadget);
else
- usb_gadget_disconnect(udc->gadget);
+ usb_gadget_disconnect_locked(udc->gadget);
}
/**
@@ -1099,10 +1140,12 @@ void usb_udc_vbus_handler(struct usb_gadget *gadget, bool status)
{
struct usb_udc *udc = gadget->udc;
+ mutex_lock(&udc->connect_lock);
if (udc) {
udc->vbus = status;
- usb_udc_connect_control(udc);
+ usb_udc_connect_control_locked(udc);
}
+ mutex_unlock(&udc->connect_lock);
}
EXPORT_SYMBOL_GPL(usb_udc_vbus_handler);
@@ -1124,7 +1167,7 @@ void usb_gadget_udc_reset(struct usb_gadget *gadget,
EXPORT_SYMBOL_GPL(usb_gadget_udc_reset);
/**
- * usb_gadget_udc_start - tells usb device controller to start up
+ * usb_gadget_udc_start_locked - tells usb device controller to start up
* @udc: The UDC to be started
*
* This call is issued by the UDC Class driver when it's about
@@ -1135,8 +1178,11 @@ EXPORT_SYMBOL_GPL(usb_gadget_udc_reset);
* necessary to have it powered on.
*
* Returns zero on success, else negative errno.
+ *
+ * Caller should acquire connect_lock before invoking this function.
*/
-static inline int usb_gadget_udc_start(struct usb_udc *udc)
+static inline int usb_gadget_udc_start_locked(struct usb_udc *udc)
+ __must_hold(&udc->connect_lock)
{
int ret;
@@ -1153,7 +1199,7 @@ static inline int usb_gadget_udc_start(struct usb_udc *udc)
}
/**
- * usb_gadget_udc_stop - tells usb device controller we don't need it anymore
+ * usb_gadget_udc_stop_locked - tells usb device controller we don't need it anymore
* @udc: The UDC to be stopped
*
* This call is issued by the UDC Class driver after calling
@@ -1162,8 +1208,11 @@ static inline int usb_gadget_udc_start(struct usb_udc *udc)
* The details are implementation specific, but it can go as
* far as powering off UDC completely and disable its data
* line pullups.
+ *
+ * Caller should acquire connect lock before invoking this function.
*/
-static inline void usb_gadget_udc_stop(struct usb_udc *udc)
+static inline void usb_gadget_udc_stop_locked(struct usb_udc *udc)
+ __must_hold(&udc->connect_lock)
{
if (!udc->started) {
dev_err(&udc->dev, "UDC had already stopped\n");
@@ -1322,6 +1371,7 @@ int usb_add_gadget(struct usb_gadget *gadget)
udc->gadget = gadget;
gadget->udc = udc;
+ mutex_init(&udc->connect_lock);
udc->started = false;
@@ -1523,11 +1573,15 @@ static int gadget_bind_driver(struct device *dev)
if (ret)
goto err_bind;
- ret = usb_gadget_udc_start(udc);
- if (ret)
+ mutex_lock(&udc->connect_lock);
+ ret = usb_gadget_udc_start_locked(udc);
+ if (ret) {
+ mutex_unlock(&udc->connect_lock);
goto err_start;
+ }
usb_gadget_enable_async_callbacks(udc);
- usb_udc_connect_control(udc);
+ usb_udc_connect_control_locked(udc);
+ mutex_unlock(&udc->connect_lock);
kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE);
return 0;
@@ -1558,12 +1612,14 @@ static void gadget_unbind_driver(struct device *dev)
kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE);
- usb_gadget_disconnect(gadget);
+ mutex_lock(&udc->connect_lock);
+ usb_gadget_disconnect_locked(gadget);
usb_gadget_disable_async_callbacks(udc);
if (gadget->irq)
synchronize_irq(gadget->irq);
udc->driver->unbind(gadget);
- usb_gadget_udc_stop(udc);
+ usb_gadget_udc_stop_locked(udc);
+ mutex_unlock(&udc->connect_lock);
mutex_lock(&udc_lock);
driver->is_bound = false;
@@ -1649,11 +1705,15 @@ static ssize_t soft_connect_store(struct device *dev,
}
if (sysfs_streq(buf, "connect")) {
- usb_gadget_udc_start(udc);
- usb_gadget_connect(udc->gadget);
+ mutex_lock(&udc->connect_lock);
+ usb_gadget_udc_start_locked(udc);
+ usb_gadget_connect_locked(udc->gadget);
+ mutex_unlock(&udc->connect_lock);
} else if (sysfs_streq(buf, "disconnect")) {
- usb_gadget_disconnect(udc->gadget);
- usb_gadget_udc_stop(udc);
+ mutex_lock(&udc->connect_lock);
+ usb_gadget_disconnect_locked(udc->gadget);
+ usb_gadget_udc_stop_locked(udc);
+ mutex_unlock(&udc->connect_lock);
} else {
dev_err(dev, "unsupported command '%s'\n", buf);
ret = -EINVAL;
base-commit: b4a4be8471846d96b0ac52a0e9e7d48005cc97e2
--
2.41.0.rc0.172.g3f132b7071-goog
--
Irodánk elérhetősége: 2554 Road Of Kpalime Face Pharmacy Bet, Gulf Lome Togo
Én vagyok a bank igazgatója, értesítem, hogy IMF-kompenzációnk 850
000,00 dollárt tesz ki, mert az Ön e-mail címét megtalálták a csalás
áldozatainak listáján. Hajlandó vagy venni ezt az alapot vagy sem?
Megállapodtunk, hogy megkezdjük az 5 000 USD átutalását naponta, amíg
a teljes 850 000 USD összeget teljesen át nem utaljuk Önnek.
nem tudjuk egyedül az Ön e-mail címével elküldeni a fizetést, ezért
szükségünk van az Ön információira, hogy hova küldjük az összeget, pl.
A fogadott név, a fogadó ország, a telefonszám, az útlevélmásolat, a
Whatsapp szám
Tisztelettel
Tony Albert
bankigazgató
Whatsapp, +22870248258
This patch reverts commit 2c3fa6ae4d52 ("dlm: check required context
while close"). The function dlm_midcomms_close(), which will call later
dlm_lowcomms_close(), is called when the cluster manager tells the node
got fenced which means on midcomms/lowcomms layer to disconnect the node
from the cluster communication. The node can rejoin the cluster later.
This patch was ensuring no new message were able to be triggered when we
are in the close() function context. This was done by checking if the
lockspace has been stopped. However there is a missing check that we
only need to check specific lockspaces where the fenced node is member
of. This is currently complicated because there is no way to easily
check if a node is part of a specific lockspace without stopping the
recovery. For now we just revert this commit as it is just a check to
finding possible leaks of stopping lockspaces before close() is called.
Cc: stable(a)vger.kernel.org
Fixes: 2c3fa6ae4d52 ("dlm: check required context while close")
Signed-off-by: Alexander Aring <aahringo(a)redhat.com>
---
fs/dlm/lockspace.c | 12 ------------
fs/dlm/lockspace.h | 1 -
fs/dlm/midcomms.c | 3 ---
3 files changed, 16 deletions(-)
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index 67261b7b1f0e..0455dddb0797 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -935,15 +935,3 @@ void dlm_stop_lockspaces(void)
log_print("dlm user daemon left %d lockspaces", count);
}
-void dlm_stop_lockspaces_check(void)
-{
- struct dlm_ls *ls;
-
- spin_lock(&lslist_lock);
- list_for_each_entry(ls, &lslist, ls_list) {
- if (WARN_ON(!rwsem_is_locked(&ls->ls_in_recovery) ||
- !dlm_locking_stopped(ls)))
- break;
- }
- spin_unlock(&lslist_lock);
-}
diff --git a/fs/dlm/lockspace.h b/fs/dlm/lockspace.h
index 03f4a4a3a871..47ebd4411926 100644
--- a/fs/dlm/lockspace.h
+++ b/fs/dlm/lockspace.h
@@ -27,7 +27,6 @@ struct dlm_ls *dlm_find_lockspace_local(void *id);
struct dlm_ls *dlm_find_lockspace_device(int minor);
void dlm_put_lockspace(struct dlm_ls *ls);
void dlm_stop_lockspaces(void);
-void dlm_stop_lockspaces_check(void);
int dlm_new_user_lockspace(const char *name, const char *cluster,
uint32_t flags, int lvblen,
const struct dlm_lockspace_ops *ops,
diff --git a/fs/dlm/midcomms.c b/fs/dlm/midcomms.c
index c02c43e4980a..3df916a568ba 100644
--- a/fs/dlm/midcomms.c
+++ b/fs/dlm/midcomms.c
@@ -136,7 +136,6 @@
#include <net/tcp.h>
#include "dlm_internal.h"
-#include "lockspace.h"
#include "lowcomms.h"
#include "config.h"
#include "memory.h"
@@ -1491,8 +1490,6 @@ int dlm_midcomms_close(int nodeid)
if (nodeid == dlm_our_nodeid())
return 0;
- dlm_stop_lockspaces_check();
-
idx = srcu_read_lock(&nodes_srcu);
/* Abort pending close/remove operation */
node = nodeid2node(nodeid, 0);
--
2.31.1
From: Frank Wunderlich <frank-w(a)public-files.de>
To store uncompressed bl2 more space is required than partition is
actually defined.
There is currently no known usage of this reserved partition.
Openwrt uses same partition layout.
We added same change to u-boot with commit d7bb1099 [1].
[1] https://source.denx.de/u-boot/u-boot/-/commit/d7bb109900c1ca754a0198b9afb50…
Cc: stable(a)vger.kernel.org
Fixes: 8e01fb15b815 ("arm64: dts: mt7986: add Bananapi R3")
Signed-off-by: Frank Wunderlich <frank-w(a)public-files.de>
---
If the bl2 does not fit into the bl2-partition (cut off), board does
not boot, thats why i want to increase it now. My current bl2 is 197K
for nor and i ran into this problem.
Openwrt uses also the first reserved partition to give bl2 more
space:
https://git.openwrt.org/?p=openwrt/openwrt.git;a=blob;f=target/linux/mediat…
so imho it should be same in mainline to not require complex bl2
compression.
have now sent the board-specific dts to uboot too:
https://source.denx.de/u-boot/u-boot/-/commit/d7bb109900c1ca754a0198b9afb50…
---
.../boot/dts/mediatek/mt7986a-bananapi-bpi-r3-nor.dtso | 7 +------
1 file changed, 1 insertion(+), 6 deletions(-)
diff --git a/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3-nor.dtso b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3-nor.dtso
index 84aa229e80f3..e48881be4ed6 100644
--- a/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3-nor.dtso
+++ b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3-nor.dtso
@@ -27,15 +27,10 @@ partitions {
partition@0 {
label = "bl2";
- reg = <0x0 0x20000>;
+ reg = <0x0 0x40000>;
read-only;
};
- partition@20000 {
- label = "reserved";
- reg = <0x20000 0x20000>;
- };
-
partition@40000 {
label = "u-boot-env";
reg = <0x40000 0x40000>;
--
2.34.1
This is a note to let you know that I've just added the patch titled
mm: page_table_check: Ensure user pages are not slab pages
to my usb git tree which can be found at
git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb.git
in the usb-linus branch.
The patch will show up in the next release of the linux-next tree
(usually sometime within the next 24 hours during the week.)
The patch will hopefully also be merged in Linus's tree for the
next -rc kernel release.
If you have any questions about this process, please let me know.
From 44d0fb387b53e56c8a050bac5c7d460e21eb226f Mon Sep 17 00:00:00 2001
From: Ruihan Li <lrh2000(a)pku.edu.cn>
Date: Mon, 15 May 2023 21:09:58 +0800
Subject: mm: page_table_check: Ensure user pages are not slab pages
The current uses of PageAnon in page table check functions can lead to
type confusion bugs between struct page and slab [1], if slab pages are
accidentally mapped into the user space. This is because slab reuses the
bits in struct page to store its internal states, which renders PageAnon
ineffective on slab pages.
Since slab pages are not expected to be mapped into the user space, this
patch adds BUG_ON(PageSlab(page)) checks to make sure that slab pages
are not inadvertently mapped. Otherwise, there must be some bugs in the
kernel.
Reported-by: syzbot+fcf1a817ceb50935ce99(a)syzkaller.appspotmail.com
Closes: https://lore.kernel.org/lkml/000000000000258e5e05fae79fc1@google.com/ [1]
Fixes: df4e817b7108 ("mm: page table check")
Cc: <stable(a)vger.kernel.org> # 5.17
Signed-off-by: Ruihan Li <lrh2000(a)pku.edu.cn>
Acked-by: Pasha Tatashin <pasha.tatashin(a)soleen.com>
Link: https://lore.kernel.org/r/20230515130958.32471-5-lrh2000@pku.edu.cn
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
include/linux/page-flags.h | 6 ++++++
mm/page_table_check.c | 6 ++++++
2 files changed, 12 insertions(+)
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 1c68d67b832f..92a2063a0a23 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -617,6 +617,12 @@ PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted)
* Please note that, confusingly, "page_mapping" refers to the inode
* address_space which maps the page from disk; whereas "page_mapped"
* refers to user virtual address space into which the page is mapped.
+ *
+ * For slab pages, since slab reuses the bits in struct page to store its
+ * internal states, the page->mapping does not exist as such, nor do these
+ * flags below. So in order to avoid testing non-existent bits, please
+ * make sure that PageSlab(page) actually evaluates to false before calling
+ * the following functions (e.g., PageAnon). See mm/slab.h.
*/
#define PAGE_MAPPING_ANON 0x1
#define PAGE_MAPPING_MOVABLE 0x2
diff --git a/mm/page_table_check.c b/mm/page_table_check.c
index 25d8610c0042..f2baf97d5f38 100644
--- a/mm/page_table_check.c
+++ b/mm/page_table_check.c
@@ -71,6 +71,8 @@ static void page_table_check_clear(struct mm_struct *mm, unsigned long addr,
page = pfn_to_page(pfn);
page_ext = page_ext_get(page);
+
+ BUG_ON(PageSlab(page));
anon = PageAnon(page);
for (i = 0; i < pgcnt; i++) {
@@ -107,6 +109,8 @@ static void page_table_check_set(struct mm_struct *mm, unsigned long addr,
page = pfn_to_page(pfn);
page_ext = page_ext_get(page);
+
+ BUG_ON(PageSlab(page));
anon = PageAnon(page);
for (i = 0; i < pgcnt; i++) {
@@ -133,6 +137,8 @@ void __page_table_check_zero(struct page *page, unsigned int order)
struct page_ext *page_ext;
unsigned long i;
+ BUG_ON(PageSlab(page));
+
page_ext = page_ext_get(page);
BUG_ON(!page_ext);
for (i = 0; i < (1ul << order); i++) {
--
2.40.1
This is a note to let you know that I've just added the patch titled
mm: page_table_check: Make it dependent on EXCLUSIVE_SYSTEM_RAM
to my usb git tree which can be found at
git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb.git
in the usb-linus branch.
The patch will show up in the next release of the linux-next tree
(usually sometime within the next 24 hours during the week.)
The patch will hopefully also be merged in Linus's tree for the
next -rc kernel release.
If you have any questions about this process, please let me know.
From 81a31a860bb61d54eb688af2568d9332ed9b8942 Mon Sep 17 00:00:00 2001
From: Ruihan Li <lrh2000(a)pku.edu.cn>
Date: Mon, 15 May 2023 21:09:57 +0800
Subject: mm: page_table_check: Make it dependent on EXCLUSIVE_SYSTEM_RAM
Without EXCLUSIVE_SYSTEM_RAM, users are allowed to map arbitrary
physical memory regions into the userspace via /dev/mem. At the same
time, pages may change their properties (e.g., from anonymous pages to
named pages) while they are still being mapped in the userspace, leading
to "corruption" detected by the page table check.
To avoid these false positives, this patch makes PAGE_TABLE_CHECK
depends on EXCLUSIVE_SYSTEM_RAM. This dependency is understandable
because PAGE_TABLE_CHECK is a hardening technique but /dev/mem without
STRICT_DEVMEM (i.e., !EXCLUSIVE_SYSTEM_RAM) is itself a security
problem.
Even with EXCLUSIVE_SYSTEM_RAM, I/O pages may be still allowed to be
mapped via /dev/mem. However, these pages are always considered as named
pages, so they won't break the logic used in the page table check.
Cc: <stable(a)vger.kernel.org> # 5.17
Signed-off-by: Ruihan Li <lrh2000(a)pku.edu.cn>
Acked-by: David Hildenbrand <david(a)redhat.com>
Acked-by: Pasha Tatashin <pasha.tatashin(a)soleen.com>
Link: https://lore.kernel.org/r/20230515130958.32471-4-lrh2000@pku.edu.cn
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
Documentation/mm/page_table_check.rst | 19 +++++++++++++++++++
mm/Kconfig.debug | 1 +
2 files changed, 20 insertions(+)
diff --git a/Documentation/mm/page_table_check.rst b/Documentation/mm/page_table_check.rst
index cfd8f4117cf3..c12838ce6b8d 100644
--- a/Documentation/mm/page_table_check.rst
+++ b/Documentation/mm/page_table_check.rst
@@ -52,3 +52,22 @@ Build kernel with:
Optionally, build kernel with PAGE_TABLE_CHECK_ENFORCED in order to have page
table support without extra kernel parameter.
+
+Implementation notes
+====================
+
+We specifically decided not to use VMA information in order to avoid relying on
+MM states (except for limited "struct page" info). The page table check is a
+separate from Linux-MM state machine that verifies that the user accessible
+pages are not falsely shared.
+
+PAGE_TABLE_CHECK depends on EXCLUSIVE_SYSTEM_RAM. The reason is that without
+EXCLUSIVE_SYSTEM_RAM, users are allowed to map arbitrary physical memory
+regions into the userspace via /dev/mem. At the same time, pages may change
+their properties (e.g., from anonymous pages to named pages) while they are
+still being mapped in the userspace, leading to "corruption" detected by the
+page table check.
+
+Even with EXCLUSIVE_SYSTEM_RAM, I/O pages may be still allowed to be mapped via
+/dev/mem. However, these pages are always considered as named pages, so they
+won't break the logic used in the page table check.
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index a925415b4d10..018a5bd2f576 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -98,6 +98,7 @@ config PAGE_OWNER
config PAGE_TABLE_CHECK
bool "Check for invalid mappings in user page tables"
depends on ARCH_SUPPORTS_PAGE_TABLE_CHECK
+ depends on EXCLUSIVE_SYSTEM_RAM
select PAGE_EXTENSION
help
Check that anonymous page is not being mapped twice with read write
--
2.40.1