This is a note to let you know that I've just added the patch titled
software node: implement software_node_unregister()
to my driver-core git tree which can be found at
git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
in the driver-core-next 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 also be merged in the next major kernel release
during the merge window.
If you have any questions about this process, please let me know.
>From 46d26819a5056f4831649c5887ad5c71a16d86f7 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Date: Sun, 24 May 2020 17:30:40 +0200
Subject: software node: implement software_node_unregister()
Sometimes it is better to unregister individual nodes instead of trying
to do them all at once with software_node_unregister_nodes(), so create
software_node_unregister() so that you can unregister them one at a
time.
This is especially important when creating nodes in a hierarchy, with
parent -> children representations. Children always need to be removed
before a parent is, as the swnode logic assumes this is going to be the
case.
Fix up the lib/test_printf.c fwnode_pointer() test which to use this new
function as it had the problem of tearing things down in the backwards
order.
Fixes: f1ce39df508d ("lib/test_printf: Add tests for %pfw printk modifier")
Cc: stable <stable(a)vger.kernel.org>
Cc: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com>
Cc: Brendan Higgins <brendanhiggins(a)google.com>
Cc: Dmitry Torokhov <dmitry.torokhov(a)gmail.com>
Cc: Petr Mladek <pmladek(a)suse.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com>
Cc: Rasmus Villemoes <linux(a)rasmusvillemoes.dk>
Cc: Sakari Ailus <sakari.ailus(a)linux.intel.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky(a)gmail.com>
Cc: Steven Rostedt <rostedt(a)goodmis.org>
Reported-by: Naresh Kamboju <naresh.kamboju(a)linaro.org>
Reported-by: kernel test robot <rong.a.chen(a)intel.com>
Reported-by: Randy Dunlap <rdunlap(a)infradead.org>
Tested-by: Petr Mladek <pmladek(a)suse.com>
Tested-by: Randy Dunlap <rdunlap(a)infradead.org>
Tested-by: Guenter Roeck <linux(a)roeck-us.net>
Reviewed-by: Heikki Krogerus <heikki.krogerus(a)linux.intel.com>
Acked-by: Randy Dunlap <rdunlap(a)infradead.org>
Link: https://lore.kernel.org/r/20200524153041.2361-1-gregkh@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
drivers/base/swnode.c | 27 +++++++++++++++++++++------
include/linux/property.h | 1 +
lib/test_printf.c | 4 +++-
3 files changed, 25 insertions(+), 7 deletions(-)
diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c
index de8d3543e8fe..770b1f47a625 100644
--- a/drivers/base/swnode.c
+++ b/drivers/base/swnode.c
@@ -712,17 +712,18 @@ EXPORT_SYMBOL_GPL(software_node_register_nodes);
* @nodes: Zero terminated array of software nodes to be unregistered
*
* Unregister multiple software nodes at once.
+ *
+ * NOTE: Be careful using this call if the nodes had parent pointers set up in
+ * them before registering. If so, it is wiser to remove the nodes
+ * individually, in the correct order (child before parent) instead of relying
+ * on the sequential order of the list of nodes in the array.
*/
void software_node_unregister_nodes(const struct software_node *nodes)
{
- struct swnode *swnode;
int i;
- for (i = 0; nodes[i].name; i++) {
- swnode = software_node_to_swnode(&nodes[i]);
- if (swnode)
- fwnode_remove_software_node(&swnode->fwnode);
- }
+ for (i = 0; nodes[i].name; i++)
+ software_node_unregister(&nodes[i]);
}
EXPORT_SYMBOL_GPL(software_node_unregister_nodes);
@@ -741,6 +742,20 @@ int software_node_register(const struct software_node *node)
}
EXPORT_SYMBOL_GPL(software_node_register);
+/**
+ * software_node_unregister - Unregister static software node
+ * @node: The software node to be unregistered
+ */
+void software_node_unregister(const struct software_node *node)
+{
+ struct swnode *swnode;
+
+ swnode = software_node_to_swnode(node);
+ if (swnode)
+ fwnode_remove_software_node(&swnode->fwnode);
+}
+EXPORT_SYMBOL_GPL(software_node_unregister);
+
struct fwnode_handle *
fwnode_create_software_node(const struct property_entry *properties,
const struct fwnode_handle *parent)
diff --git a/include/linux/property.h b/include/linux/property.h
index d86de017c689..0d4099b4ce1f 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -441,6 +441,7 @@ int software_node_register_nodes(const struct software_node *nodes);
void software_node_unregister_nodes(const struct software_node *nodes);
int software_node_register(const struct software_node *node);
+void software_node_unregister(const struct software_node *node);
int software_node_notify(struct device *dev, unsigned long action);
diff --git a/lib/test_printf.c b/lib/test_printf.c
index 6b1622f4d7c2..fc63b8959d42 100644
--- a/lib/test_printf.c
+++ b/lib/test_printf.c
@@ -637,7 +637,9 @@ static void __init fwnode_pointer(void)
test(second_name, "%pfwP", software_node_fwnode(&softnodes[1]));
test(third_name, "%pfwP", software_node_fwnode(&softnodes[2]));
- software_node_unregister_nodes(softnodes);
+ software_node_unregister(&softnodes[2]);
+ software_node_unregister(&softnodes[1]);
+ software_node_unregister(&softnodes[0]);
}
static void __init
--
2.26.2
******************************************
* WARNING: Boot tests are now deprecated *
******************************************
As kernelci.org is expanding its functional testing capabilities, the concept
of boot testing is now deprecated. Boot results are scheduled to be dropped on
*5th June 2020*. The full schedule for boot tests deprecation is available on
this GitHub issue: https://github.com/kernelci/kernelci-backend/issues/238
The new equivalent is the *baseline* test suite which also runs sanity checks
using dmesg and bootrr: https://github.com/kernelci/bootrr
See the *baseline results for this kernel revision* on this page:
https://kernelci.org/test/job/stable-rc/branch/linux-4.14.y/kernel/v4.14.18…
-------------------------------------------------------------------------------
stable-rc/linux-4.14.y boot: 91 boots: 4 failed, 81 passed with 5 offline, 1 untried/unknown (v4.14.181-60-gce8b534d70e2)
Full Boot Summary: https://kernelci.org/boot/all/job/stable-rc/branch/linux-4.14.y/kernel/v4.1…
Full Build Summary: https://kernelci.org/build/stable-rc/branch/linux-4.14.y/kernel/v4.14.181-6…
Tree: stable-rc
Branch: linux-4.14.y
Git Describe: v4.14.181-60-gce8b534d70e2
Git Commit: ce8b534d70e21cb589da3731a1f61fabda583756
Git URL: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git
Tested: 58 unique boards, 18 SoC families, 13 builds out of 165
Boot Regressions Detected:
arm:
qcom_defconfig:
gcc-8:
qcom-apq8064-cm-qs600:
lab-baylibre-seattle: failing since 13 days (last pass: v4.14.180 - first fail: v4.14.180-37-gad4fc99d1989)
sama5_defconfig:
gcc-8:
at91-sama5d4_xplained:
lab-baylibre: failing since 96 days (last pass: v4.14.170-141-g00a0113414f7 - first fail: v4.14.171-29-g9cfe30e85240)
arm64:
defconfig:
gcc-8:
meson-gxl-s905x-khadas-vim:
lab-baylibre: new failure (last pass: v4.14.181-59-g2c9e54b6ad6a)
x86_64:
x86_64_defconfig:
gcc-8:
qemu_x86_64:
lab-baylibre: new failure (last pass: v4.14.181-59-g2c9e54b6ad6a)
Boot Failures Detected:
x86_64:
x86_64_defconfig:
gcc-8:
qemu_x86_64: 1 failed lab
arm:
sama5_defconfig:
gcc-8:
at91-sama5d4_xplained: 1 failed lab
arm64:
defconfig:
gcc-8:
meson-gxbb-p200: 1 failed lab
meson-gxm-q200: 1 failed lab
Offline Platforms:
arm:
qcom_defconfig:
gcc-8
qcom-apq8064-cm-qs600: 1 offline lab
multi_v7_defconfig:
gcc-8
exynos5800-peach-pi: 1 offline lab
qcom-apq8064-cm-qs600: 1 offline lab
stih410-b2120: 1 offline lab
exynos_defconfig:
gcc-8
exynos5800-peach-pi: 1 offline lab
---
For more info write to <info(a)kernelci.org>
******************************************
* WARNING: Boot tests are now deprecated *
******************************************
As kernelci.org is expanding its functional testing capabilities, the concept
of boot testing is now deprecated. Boot results are scheduled to be dropped on
*5th June 2020*. The full schedule for boot tests deprecation is available on
this GitHub issue: https://github.com/kernelci/kernelci-backend/issues/238
The new equivalent is the *baseline* test suite which also runs sanity checks
using dmesg and bootrr: https://github.com/kernelci/bootrr
See the *baseline results for this kernel revision* on this page:
https://kernelci.org/test/job/stable-rc/branch/linux-4.4.y/kernel/v4.4.224-…
-------------------------------------------------------------------------------
stable-rc/linux-4.4.y boot: 60 boots: 3 failed, 52 passed with 3 offline, 2 untried/unknown (v4.4.224-66-g147ece171c0d)
Full Boot Summary: https://kernelci.org/boot/all/job/stable-rc/branch/linux-4.4.y/kernel/v4.4.…
Full Build Summary: https://kernelci.org/build/stable-rc/branch/linux-4.4.y/kernel/v4.4.224-66-…
Tree: stable-rc
Branch: linux-4.4.y
Git Describe: v4.4.224-66-g147ece171c0d
Git Commit: 147ece171c0dc02b417f35088182a61e6dac368a
Git URL: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git
Tested: 42 unique boards, 16 SoC families, 12 builds out of 159
Boot Regressions Detected:
arm:
qcom_defconfig:
gcc-8:
qcom-apq8064-cm-qs600:
lab-baylibre-seattle: failing since 13 days (last pass: v4.4.223 - first fail: v4.4.223-36-g32f5ec9b096d)
x86_64:
x86_64_defconfig:
gcc-8:
qemu_x86_64:
lab-baylibre: new failure (last pass: v4.4.224-38-g1f47601a4296)
Boot Failures Detected:
x86_64:
x86_64_defconfig:
gcc-8:
qemu_x86_64: 1 failed lab
arm:
imx_v4_v5_defconfig:
gcc-8:
imx27-phytec-phycard-s-rdk: 1 failed lab
multi_v5_defconfig:
gcc-8:
imx27-phytec-phycard-s-rdk: 1 failed lab
Offline Platforms:
arm:
qcom_defconfig:
gcc-8
qcom-apq8064-cm-qs600: 1 offline lab
multi_v7_defconfig:
gcc-8
exynos5800-peach-pi: 1 offline lab
qcom-apq8064-cm-qs600: 1 offline lab
---
For more info write to <info(a)kernelci.org>
From: Can Guo <cang(a)codeaurora.org>
commit 17c7d35f141ef6158076adf3338f115f64fcf760 upstream.
[Please apply to 5.4-stable and earlier.]
In queuecommand path, if DMA map fails, it bails out with clock held. In
this case, release the clock to keep its usage paired.
[mkp: applied by hand]
Link: https://lore.kernel.org/r/0101016ed3d66395-1b7e7fce-b74d-42ca-a88a-4db78b79…
Reviewed-by: Bean Huo <beanhuo(a)micron.com>
Signed-off-by: Can Guo <cang(a)codeaurora.org>
Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com>
[EB: resolved cherry-pick conflict caused by newer kernels not having
the clear_bit_unlock() line]
Signed-off-by: Eric Biggers <ebiggers(a)google.com>
---
drivers/scsi/ufs/ufshcd.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 13ab1494c384..bc73181b0405 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -2480,6 +2480,7 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
err = ufshcd_map_sg(hba, lrbp);
if (err) {
+ ufshcd_release(hba);
lrbp->cmd = NULL;
clear_bit_unlock(tag, &hba->lrb_in_use);
goto out;
--
2.27.0.rc0.183.gde8f92d652-goog
This is a note to let you know that I've just added the patch titled
software node: implement software_node_unregister()
to my driver-core git tree which can be found at
git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
in the driver-core-testing 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 be merged to the driver-core-next branch sometime soon,
after it passes testing, and the merge window is open.
If you have any questions about this process, please let me know.
>From 46d26819a5056f4831649c5887ad5c71a16d86f7 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Date: Sun, 24 May 2020 17:30:40 +0200
Subject: software node: implement software_node_unregister()
Sometimes it is better to unregister individual nodes instead of trying
to do them all at once with software_node_unregister_nodes(), so create
software_node_unregister() so that you can unregister them one at a
time.
This is especially important when creating nodes in a hierarchy, with
parent -> children representations. Children always need to be removed
before a parent is, as the swnode logic assumes this is going to be the
case.
Fix up the lib/test_printf.c fwnode_pointer() test which to use this new
function as it had the problem of tearing things down in the backwards
order.
Fixes: f1ce39df508d ("lib/test_printf: Add tests for %pfw printk modifier")
Cc: stable <stable(a)vger.kernel.org>
Cc: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com>
Cc: Brendan Higgins <brendanhiggins(a)google.com>
Cc: Dmitry Torokhov <dmitry.torokhov(a)gmail.com>
Cc: Petr Mladek <pmladek(a)suse.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com>
Cc: Rasmus Villemoes <linux(a)rasmusvillemoes.dk>
Cc: Sakari Ailus <sakari.ailus(a)linux.intel.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky(a)gmail.com>
Cc: Steven Rostedt <rostedt(a)goodmis.org>
Reported-by: Naresh Kamboju <naresh.kamboju(a)linaro.org>
Reported-by: kernel test robot <rong.a.chen(a)intel.com>
Reported-by: Randy Dunlap <rdunlap(a)infradead.org>
Tested-by: Petr Mladek <pmladek(a)suse.com>
Tested-by: Randy Dunlap <rdunlap(a)infradead.org>
Tested-by: Guenter Roeck <linux(a)roeck-us.net>
Reviewed-by: Heikki Krogerus <heikki.krogerus(a)linux.intel.com>
Acked-by: Randy Dunlap <rdunlap(a)infradead.org>
Link: https://lore.kernel.org/r/20200524153041.2361-1-gregkh@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
drivers/base/swnode.c | 27 +++++++++++++++++++++------
include/linux/property.h | 1 +
lib/test_printf.c | 4 +++-
3 files changed, 25 insertions(+), 7 deletions(-)
diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c
index de8d3543e8fe..770b1f47a625 100644
--- a/drivers/base/swnode.c
+++ b/drivers/base/swnode.c
@@ -712,17 +712,18 @@ EXPORT_SYMBOL_GPL(software_node_register_nodes);
* @nodes: Zero terminated array of software nodes to be unregistered
*
* Unregister multiple software nodes at once.
+ *
+ * NOTE: Be careful using this call if the nodes had parent pointers set up in
+ * them before registering. If so, it is wiser to remove the nodes
+ * individually, in the correct order (child before parent) instead of relying
+ * on the sequential order of the list of nodes in the array.
*/
void software_node_unregister_nodes(const struct software_node *nodes)
{
- struct swnode *swnode;
int i;
- for (i = 0; nodes[i].name; i++) {
- swnode = software_node_to_swnode(&nodes[i]);
- if (swnode)
- fwnode_remove_software_node(&swnode->fwnode);
- }
+ for (i = 0; nodes[i].name; i++)
+ software_node_unregister(&nodes[i]);
}
EXPORT_SYMBOL_GPL(software_node_unregister_nodes);
@@ -741,6 +742,20 @@ int software_node_register(const struct software_node *node)
}
EXPORT_SYMBOL_GPL(software_node_register);
+/**
+ * software_node_unregister - Unregister static software node
+ * @node: The software node to be unregistered
+ */
+void software_node_unregister(const struct software_node *node)
+{
+ struct swnode *swnode;
+
+ swnode = software_node_to_swnode(node);
+ if (swnode)
+ fwnode_remove_software_node(&swnode->fwnode);
+}
+EXPORT_SYMBOL_GPL(software_node_unregister);
+
struct fwnode_handle *
fwnode_create_software_node(const struct property_entry *properties,
const struct fwnode_handle *parent)
diff --git a/include/linux/property.h b/include/linux/property.h
index d86de017c689..0d4099b4ce1f 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -441,6 +441,7 @@ int software_node_register_nodes(const struct software_node *nodes);
void software_node_unregister_nodes(const struct software_node *nodes);
int software_node_register(const struct software_node *node);
+void software_node_unregister(const struct software_node *node);
int software_node_notify(struct device *dev, unsigned long action);
diff --git a/lib/test_printf.c b/lib/test_printf.c
index 6b1622f4d7c2..fc63b8959d42 100644
--- a/lib/test_printf.c
+++ b/lib/test_printf.c
@@ -637,7 +637,9 @@ static void __init fwnode_pointer(void)
test(second_name, "%pfwP", software_node_fwnode(&softnodes[1]));
test(third_name, "%pfwP", software_node_fwnode(&softnodes[2]));
- software_node_unregister_nodes(softnodes);
+ software_node_unregister(&softnodes[2]);
+ software_node_unregister(&softnodes[1]);
+ software_node_unregister(&softnodes[0]);
}
static void __init
--
2.26.2
The following commit has been merged into the ras/core branch of tip:
Commit-ID: be69f6c5cd38c457c22f6e718077f6524437369d
Gitweb: https://git.kernel.org/tip/be69f6c5cd38c457c22f6e718077f6524437369d
Author: Tony Luck <tony.luck(a)intel.com>
AuthorDate: Wed, 20 May 2020 09:35:46 -07:00
Committer: Borislav Petkov <bp(a)suse.de>
CommitterDate: Mon, 25 May 2020 22:37:41 +02:00
x86/{mce,mm}: Unmap the entire page if the whole page is affected and poisoned
An interesting thing happened when a guest Linux instance took a machine
check. The VMM unmapped the bad page from guest physical space and
passed the machine check to the guest.
Linux took all the normal actions to offline the page from the process
that was using it. But then guest Linux crashed because it said there
was a second machine check inside the kernel with this stack trace:
do_memory_failure
set_mce_nospec
set_memory_uc
_set_memory_uc
change_page_attr_set_clr
cpa_flush
clflush_cache_range_opt
This was odd, because a CLFLUSH instruction shouldn't raise a machine
check (it isn't consuming the data). Further investigation showed that
the VMM had passed in another machine check because is appeared that the
guest was accessing the bad page.
Fix is to check the scope of the poison by checking the MCi_MISC register.
If the entire page is affected, then unmap the page. If only part of the
page is affected, then mark the page as uncacheable.
This assumes that VMMs will do the logical thing and pass in the "whole
page scope" via the MCi_MISC register (since they unmapped the entire
page).
[ bp: Adjust to x86/entry changes. ]
Fixes: 284ce4011ba6 ("x86/memory_failure: Introduce {set, clear}_mce_nospec()")
Reported-by: Jue Wang <juew(a)google.com>
Signed-off-by: Tony Luck <tony.luck(a)intel.com>
Signed-off-by: Borislav Petkov <bp(a)suse.de>
Tested-by: Jue Wang <juew(a)google.com>
Cc: <stable(a)vger.kernel.org>
Link: https://lkml.kernel.org/r/20200520163546.GA7977@agluck-desk2.amr.corp.intel…
---
arch/x86/include/asm/set_memory.h | 19 +++++++++++++------
arch/x86/kernel/cpu/mce/core.c | 18 ++++++++++++++----
include/linux/sched.h | 4 +++-
include/linux/set_memory.h | 2 +-
4 files changed, 31 insertions(+), 12 deletions(-)
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index ec2c0a0..5948218 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -86,28 +86,35 @@ int set_direct_map_default_noflush(struct page *page);
extern int kernel_set_to_readonly;
#ifdef CONFIG_X86_64
-static inline int set_mce_nospec(unsigned long pfn)
+/*
+ * Prevent speculative access to the page by either unmapping
+ * it (if we do not require access to any part of the page) or
+ * marking it uncacheable (if we want to try to retrieve data
+ * from non-poisoned lines in the page).
+ */
+static inline int set_mce_nospec(unsigned long pfn, bool unmap)
{
unsigned long decoy_addr;
int rc;
/*
- * Mark the linear address as UC to make sure we don't log more
- * errors because of speculative access to the page.
* We would like to just call:
- * set_memory_uc((unsigned long)pfn_to_kaddr(pfn), 1);
+ * set_memory_XX((unsigned long)pfn_to_kaddr(pfn), 1);
* but doing that would radically increase the odds of a
* speculative access to the poison page because we'd have
* the virtual address of the kernel 1:1 mapping sitting
* around in registers.
* Instead we get tricky. We create a non-canonical address
* that looks just like the one we want, but has bit 63 flipped.
- * This relies on set_memory_uc() properly sanitizing any __pa()
+ * This relies on set_memory_XX() properly sanitizing any __pa()
* results with __PHYSICAL_MASK or PTE_PFN_MASK.
*/
decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63));
- rc = set_memory_uc(decoy_addr, 1);
+ if (unmap)
+ rc = set_memory_np(decoy_addr, 1);
+ else
+ rc = set_memory_uc(decoy_addr, 1);
if (rc)
pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
return rc;
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index ffee8a2..753bc77 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -520,6 +520,14 @@ bool mce_is_memory_error(struct mce *m)
}
EXPORT_SYMBOL_GPL(mce_is_memory_error);
+static bool whole_page(struct mce *m)
+{
+ if (!mca_cfg.ser || !(m->status & MCI_STATUS_MISCV))
+ return true;
+
+ return MCI_MISC_ADDR_LSB(m->misc) >= PAGE_SHIFT;
+}
+
bool mce_is_correctable(struct mce *m)
{
if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED)
@@ -573,7 +581,7 @@ static int uc_decode_notifier(struct notifier_block *nb, unsigned long val,
pfn = mce->addr >> PAGE_SHIFT;
if (!memory_failure(pfn, 0)) {
- set_mce_nospec(pfn);
+ set_mce_nospec(pfn, whole_page(mce));
mce->kflags |= MCE_HANDLED_UC;
}
@@ -1173,11 +1181,12 @@ static void kill_me_maybe(struct callback_head *cb)
int flags = MF_ACTION_REQUIRED;
pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr);
- if (!(p->mce_status & MCG_STATUS_RIPV))
+
+ if (!p->mce_ripv)
flags |= MF_MUST_KILL;
if (!memory_failure(p->mce_addr >> PAGE_SHIFT, flags)) {
- set_mce_nospec(p->mce_addr >> PAGE_SHIFT);
+ set_mce_nospec(p->mce_addr >> PAGE_SHIFT, p->mce_whole_page);
return;
}
@@ -1331,7 +1340,8 @@ void noinstr do_machine_check(struct pt_regs *regs)
BUG_ON(!on_thread_stack() || !user_mode(regs));
current->mce_addr = m.addr;
- current->mce_status = m.mcgstatus;
+ current->mce_ripv = !!(m.mcgstatus & MCG_STATUS_RIPV);
+ current->mce_whole_page = whole_page(&m);
current->mce_kill_me.func = kill_me_maybe;
if (kill_it)
current->mce_kill_me.func = kill_me_now;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1d68ee3..6293fc2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1304,7 +1304,9 @@ struct task_struct {
#ifdef CONFIG_X86_MCE
u64 mce_addr;
- u64 mce_status;
+ __u64 mce_ripv : 1,
+ mce_whole_page : 1,
+ __mce_reserved : 62;
struct callback_head mce_kill_me;
#endif
diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h
index 86281ac..860e0f8 100644
--- a/include/linux/set_memory.h
+++ b/include/linux/set_memory.h
@@ -26,7 +26,7 @@ static inline int set_direct_map_default_noflush(struct page *page)
#endif
#ifndef set_mce_nospec
-static inline int set_mce_nospec(unsigned long pfn)
+static inline int set_mce_nospec(unsigned long pfn, bool unmap)
{
return 0;
}
On Tue, May 26, 2020 at 11:44:18AM -0700, Jue Wang wrote:
> On Tue, May 26, 2020 at 11:03 AM Jue Wang <juew(a)google.com> wrote:
>
> > I tried to test this but my guest image build setup was not able to build
> > from kernel/git/bp/bp.git tip-ras-core branch. It appeared there was some
> > bindeb-pkg issue.
> >
> The bindeb-pkg issue is resolved and I tested the following branch in KVM
> guest and the injected MCE is recovered.
> https://git.kernel.org/pub/scm/linux/kernel/git/bp/bp.git/log/?h=tip-ras-co…
Thanks to both of you!
--
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquette