The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From ce33c845b030c9cf768370c951bc699470b09fa7 Mon Sep 17 00:00:00 2001
From: Daniel Bristot de Oliveira <bristot(a)kernel.org>
Date: Sun, 20 Feb 2022 23:49:57 +0100
Subject: [PATCH] tracing: Dump stacktrace trigger to the corresponding
instance
The stacktrace event trigger is not dumping the stacktrace to the instance
where it was enabled, but to the global "instance."
Use the private_data, pointing to the trigger file, to figure out the
corresponding trace instance, and use it in the trigger action, like
snapshot_trigger does.
Link: https://lkml.kernel.org/r/afbb0b4f18ba92c276865bc97204d438473f4ebc.16453962…
Cc: stable(a)vger.kernel.org
Fixes: ae63b31e4d0e2 ("tracing: Separate out trace events from global variables")
Reviewed-by: Tom Zanussi <zanussi(a)kernel.org>
Tested-by: Tom Zanussi <zanussi(a)kernel.org>
Signed-off-by: Daniel Bristot de Oliveira <bristot(a)kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org>
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index d00fee705f9c..e0d50c9577f3 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -1540,7 +1540,12 @@ stacktrace_trigger(struct event_trigger_data *data,
struct trace_buffer *buffer, void *rec,
struct ring_buffer_event *event)
{
- trace_dump_stack(STACK_SKIP);
+ struct trace_event_file *file = data->private_data;
+
+ if (file)
+ __trace_stack(file->tr, tracing_gen_ctx(), STACK_SKIP);
+ else
+ trace_dump_stack(STACK_SKIP);
}
static void
--
Dear friend,
My name is Madi Zongo, a banker in one of the banks in my country here
called Burkina Faso. I have the sum of $27,2 Million for transfer
which i need your help. If you are interested, please reply me
urgently for more details. Contact me via Email: zmadizongo(a)gmail.com
Thanks and best Regards.
The patch below does not apply to the 4.9-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 302e9edd54985f584cfc180098f3554774126969 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt(a)goodmis.org>
Date: Wed, 23 Feb 2022 22:38:37 -0500
Subject: [PATCH] tracing: Have traceon and traceoff trigger honor the instance
If a trigger is set on an event to disable or enable tracing within an
instance, then tracing should be disabled or enabled in the instance and
not at the top level, which is confusing to users.
Link: https://lkml.kernel.org/r/20220223223837.14f94ec3@rorschach.local.home
Cc: stable(a)vger.kernel.org
Fixes: ae63b31e4d0e2 ("tracing: Separate out trace events from global variables")
Tested-by: Daniel Bristot de Oliveira <bristot(a)kernel.org>
Reviewed-by: Tom Zanussi <zanussi(a)kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org>
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index e0d50c9577f3..efe563140f27 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -1295,6 +1295,16 @@ traceon_trigger(struct event_trigger_data *data,
struct trace_buffer *buffer, void *rec,
struct ring_buffer_event *event)
{
+ struct trace_event_file *file = data->private_data;
+
+ if (file) {
+ if (tracer_tracing_is_on(file->tr))
+ return;
+
+ tracer_tracing_on(file->tr);
+ return;
+ }
+
if (tracing_is_on())
return;
@@ -1306,8 +1316,15 @@ traceon_count_trigger(struct event_trigger_data *data,
struct trace_buffer *buffer, void *rec,
struct ring_buffer_event *event)
{
- if (tracing_is_on())
- return;
+ struct trace_event_file *file = data->private_data;
+
+ if (file) {
+ if (tracer_tracing_is_on(file->tr))
+ return;
+ } else {
+ if (tracing_is_on())
+ return;
+ }
if (!data->count)
return;
@@ -1315,7 +1332,10 @@ traceon_count_trigger(struct event_trigger_data *data,
if (data->count != -1)
(data->count)--;
- tracing_on();
+ if (file)
+ tracer_tracing_on(file->tr);
+ else
+ tracing_on();
}
static void
@@ -1323,6 +1343,16 @@ traceoff_trigger(struct event_trigger_data *data,
struct trace_buffer *buffer, void *rec,
struct ring_buffer_event *event)
{
+ struct trace_event_file *file = data->private_data;
+
+ if (file) {
+ if (!tracer_tracing_is_on(file->tr))
+ return;
+
+ tracer_tracing_off(file->tr);
+ return;
+ }
+
if (!tracing_is_on())
return;
@@ -1334,8 +1364,15 @@ traceoff_count_trigger(struct event_trigger_data *data,
struct trace_buffer *buffer, void *rec,
struct ring_buffer_event *event)
{
- if (!tracing_is_on())
- return;
+ struct trace_event_file *file = data->private_data;
+
+ if (file) {
+ if (!tracer_tracing_is_on(file->tr))
+ return;
+ } else {
+ if (!tracing_is_on())
+ return;
+ }
if (!data->count)
return;
@@ -1343,7 +1380,10 @@ traceoff_count_trigger(struct event_trigger_data *data,
if (data->count != -1)
(data->count)--;
- tracing_off();
+ if (file)
+ tracer_tracing_off(file->tr);
+ else
+ tracing_off();
}
static int
From: Xiaomeng Tong <xiam0nd.tong(a)gmail.com>
The bug is here:
ret = i40e_add_macvlan_filter(hw, ch->seid, vdev->dev_addr, &aq_err);
The list iterator 'ch' will point to a bogus position containing
HEAD if the list is empty or no element is found. This case must
be checked before any use of the iterator, otherwise it will
lead to a invalid memory access.
To fix this bug, use a new variable 'iter' as the list iterator,
while use the origin variable 'ch' as a dedicated pointer to
point to the found element.
Cc: stable(a)vger.kernel.org
Fixes: 1d8d80b4e4ff6 ("i40e: Add macvlan support on i40e")
Signed-off-by: Xiaomeng Tong <xiam0nd.tong(a)gmail.com>
Tested-by: Gurucharan <gurucharanx.g(a)intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen(a)intel.com>
---
drivers/net/ethernet/intel/i40e/i40e_main.c | 27 +++++++++++----------
1 file changed, 14 insertions(+), 13 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 6778df2177a1..98871f014994 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -7549,42 +7549,43 @@ static void i40e_free_macvlan_channels(struct i40e_vsi *vsi)
static int i40e_fwd_ring_up(struct i40e_vsi *vsi, struct net_device *vdev,
struct i40e_fwd_adapter *fwd)
{
+ struct i40e_channel *ch = NULL, *ch_tmp, *iter;
int ret = 0, num_tc = 1, i, aq_err;
- struct i40e_channel *ch, *ch_tmp;
struct i40e_pf *pf = vsi->back;
struct i40e_hw *hw = &pf->hw;
- if (list_empty(&vsi->macvlan_list))
- return -EINVAL;
-
/* Go through the list and find an available channel */
- list_for_each_entry_safe(ch, ch_tmp, &vsi->macvlan_list, list) {
- if (!i40e_is_channel_macvlan(ch)) {
- ch->fwd = fwd;
+ list_for_each_entry_safe(iter, ch_tmp, &vsi->macvlan_list, list) {
+ if (!i40e_is_channel_macvlan(iter)) {
+ iter->fwd = fwd;
/* record configuration for macvlan interface in vdev */
for (i = 0; i < num_tc; i++)
netdev_bind_sb_channel_queue(vsi->netdev, vdev,
i,
- ch->num_queue_pairs,
- ch->base_queue);
- for (i = 0; i < ch->num_queue_pairs; i++) {
+ iter->num_queue_pairs,
+ iter->base_queue);
+ for (i = 0; i < iter->num_queue_pairs; i++) {
struct i40e_ring *tx_ring, *rx_ring;
u16 pf_q;
- pf_q = ch->base_queue + i;
+ pf_q = iter->base_queue + i;
/* Get to TX ring ptr */
tx_ring = vsi->tx_rings[pf_q];
- tx_ring->ch = ch;
+ tx_ring->ch = iter;
/* Get the RX ring ptr */
rx_ring = vsi->rx_rings[pf_q];
- rx_ring->ch = ch;
+ rx_ring->ch = iter;
}
+ ch = iter;
break;
}
}
+ if (!ch)
+ return -EINVAL;
+
/* Guarantee all rings are updated before we update the
* MAC address filter.
*/
--
2.31.1
This is a note to let you know that I've just added the patch titled
topology: make core_mask include at least cluster_siblings
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-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 db1e59483dfd8d4e956575302520bb8f7e20c79b Mon Sep 17 00:00:00 2001
From: Darren Hart <darren(a)os.amperecomputing.com>
Date: Mon, 11 Apr 2022 13:53:34 -0700
Subject: topology: make core_mask include at least cluster_siblings
Ampere Altra defines CPU clusters in the ACPI PPTT. They share a Snoop
Control Unit, but have no shared CPU-side last level cache.
cpu_coregroup_mask() will return a cpumask with weight 1, while
cpu_clustergroup_mask() will return a cpumask with weight 2.
As a result, build_sched_domain() will BUG() once per CPU with:
BUG: arch topology borken
the CLS domain not a subset of the MC domain
The MC level cpumask is then extended to that of the CLS child, and is
later removed entirely as redundant. This sched domain topology is an
improvement over previous topologies, or those built without
SCHED_CLUSTER, particularly for certain latency sensitive workloads.
With the current scheduler model and heuristics, this is a desirable
default topology for Ampere Altra and Altra Max system.
Rather than create a custom sched domains topology structure and
introduce new logic in arch/arm64 to detect these systems, update the
core_mask so coregroup is never a subset of clustergroup, extending it
to cluster_siblings if necessary. Only do this if CONFIG_SCHED_CLUSTER
is enabled to avoid also changing the topology (MC) when
CONFIG_SCHED_CLUSTER is disabled.
This has the added benefit over a custom topology of working for both
symmetric and asymmetric topologies. It does not address systems where
the CLUSTER topology is above a populated MC topology, but these are not
considered today and can be addressed separately if and when they
appear.
The final sched domain topology for a 2 socket Ampere Altra system is
unchanged with or without CONFIG_SCHED_CLUSTER, and the BUG is avoided:
For CPU0:
CONFIG_SCHED_CLUSTER=y
CLS [0-1]
DIE [0-79]
NUMA [0-159]
CONFIG_SCHED_CLUSTER is not set
DIE [0-79]
NUMA [0-159]
Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael(a)kernel.org>
Cc: Catalin Marinas <catalin.marinas(a)arm.com>
Cc: Will Deacon <will(a)kernel.org>
Cc: Peter Zijlstra <peterz(a)infradead.org>
Cc: Vincent Guittot <vincent.guittot(a)linaro.org>
Cc: D. Scott Phillips <scott(a)os.amperecomputing.com>
Cc: Ilkka Koskinen <ilkka(a)os.amperecomputing.com>
Cc: <stable(a)vger.kernel.org> # 5.16.x
Suggested-by: Barry Song <song.bao.hua(a)hisilicon.com>
Reviewed-by: Barry Song <song.bao.hua(a)hisilicon.com>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann(a)arm.com>
Acked-by: Sudeep Holla <sudeep.holla(a)arm.com>
Signed-off-by: Darren Hart <darren(a)os.amperecomputing.com>
Link: https://lore.kernel.org/r/c8fe9fce7c86ed56b4c455b8c902982dc2303868.16496969…
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
drivers/base/arch_topology.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 1d6636ebaac5..5497c5ab7318 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -667,6 +667,15 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
core_mask = &cpu_topology[cpu].llc_sibling;
}
+ /*
+ * For systems with no shared cpu-side LLC but with clusters defined,
+ * extend core_mask to cluster_siblings. The sched domain builder will
+ * then remove MC as redundant with CLS if SCHED_CLUSTER is enabled.
+ */
+ if (IS_ENABLED(CONFIG_SCHED_CLUSTER) &&
+ cpumask_subset(core_mask, &cpu_topology[cpu].cluster_sibling))
+ core_mask = &cpu_topology[cpu].cluster_sibling;
+
return core_mask;
}
--
2.35.3
This is a note to let you know that I've just added the patch titled
arch_topology: Do not set llc_sibling if llc_id is invalid
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-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 1dc9f1a66e1718479e1c4f95514e1750602a3cb9 Mon Sep 17 00:00:00 2001
From: Wang Qing <wangqing(a)vivo.com>
Date: Sun, 10 Apr 2022 19:36:19 -0700
Subject: arch_topology: Do not set llc_sibling if llc_id is invalid
When ACPI is not enabled, cpuid_topo->llc_id = cpu_topo->llc_id = -1, which
will set llc_sibling 0xff(...), this is misleading.
Don't set llc_sibling(default 0) if we don't know the cache topology.
Reviewed-by: Sudeep Holla <sudeep.holla(a)arm.com>
Signed-off-by: Wang Qing <wangqing(a)vivo.com>
Fixes: 37c3ec2d810f ("arm64: topology: divorce MC scheduling domain from core_siblings")
Cc: stable <stable(a)vger.kernel.org>
Link: https://lore.kernel.org/r/1649644580-54626-1-git-send-email-wangqing@vivo.c…
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
drivers/base/arch_topology.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 5497c5ab7318..f73b836047cf 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -693,7 +693,7 @@ void update_siblings_masks(unsigned int cpuid)
for_each_online_cpu(cpu) {
cpu_topo = &cpu_topology[cpu];
- if (cpuid_topo->llc_id == cpu_topo->llc_id) {
+ if (cpu_topo->llc_id != -1 && cpuid_topo->llc_id == cpu_topo->llc_id) {
cpumask_set_cpu(cpu, &cpuid_topo->llc_sibling);
cpumask_set_cpu(cpuid, &cpu_topo->llc_sibling);
}
--
2.35.3
I noticed that our autobot recently backported parts of a series which
fixed XFS syncfs error handling [1]. Unfortunately - due to missing
requirements - it only managed to merge those patches which do not
actually fix anything.
This can be repaired by applying the prerequisites and then the missing
parts of the original series, namely in order:
9a208ba5c9af fs: remove __sync_filesystem
70164eb6ccb7 block: remove __sync_blockdev
1e03a36bdff4 block: simplify the block device syncing code
5679897eb104 vfs: make sync_filesystem return errors from ->sync_fs
2d86293c7075 xfs: return errors in xfs_fs_sync_fs
With all that we could also put a cherry on top and merge:
b97cca3ba909 xfs: only bother with sync_filesystem during readonly remount
but that's just a touchup and not a real bugfix, so probably optional.
thanks,
Holger
[1] https://lore.kernel.org/linux-xfs/164316348940.2600168.17153575889519271710…
From: Niklas Cassel <niklas.cassel(a)wdc.com>
The sparse annotation ordering inside the function call is swapped.
Fix the ordering so that we silence the following sparse warnings:
fs/binfmt_flat.c:816:39: warning: incorrect type in argument 1 (different address spaces)
fs/binfmt_flat.c:816:39: expected unsigned int [noderef] [usertype] __user *rp
fs/binfmt_flat.c:816:39: got unsigned int [usertype] *[noderef] __user
No functional change as sparse annotations are ignored by the compiler.
Fixes: a767e6fd68d2 ("binfmt_flat: do not stop relocating GOT entries prematurely on riscv")
Reported-by: kernel test robot <lkp(a)intel.com>
Signed-off-by: Niklas Cassel <niklas.cassel(a)wdc.com>
Cc: <stable(a)vger.kernel.org>
---
Hello Kees,
Sorry about this.
Feel free to squash it with the existing patch if you so like.
fs/binfmt_flat.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index e5e2a03b39c1..dca0b6875f9c 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -813,7 +813,7 @@ static int load_flat_file(struct linux_binprm *bprm,
* image.
*/
if (flags & FLAT_FLAG_GOTPIC) {
- rp = skip_got_header((u32 * __user) datapos);
+ rp = skip_got_header((u32 __user *) datapos);
for (; ; rp++) {
u32 addr, rp_val;
if (get_user(rp_val, rp))
--
2.35.1
The arm_smmu_mm_invalidate_range function is designed to be called
by mm core for Shared Virtual Addressing purpose between IOMMU and
CPU MMU. However, the ways of two subsystems defining their "end"
addresses are slightly different. IOMMU defines its "end" address
using the last address of an address range, while mm core defines
that using the following address of an address range:
include/linux/mm_types.h:
unsigned long vm_end;
/* The first byte after our end address ...
This mismatch resulted in an incorrect calculation for size so it
failed to be page-size aligned. Further, it caused a dead loop at
"while (iova < end)" check in __arm_smmu_tlb_inv_range function.
This patch fixes the issue by doing the calculation correctly.
Fixes: 2f7e8c553e98d ("iommu/arm-smmu-v3: Hook up ATC invalidation to mm ops")
Cc: stable(a)vger.kernel.org
Signed-off-by: Nicolin Chen <nicolinc(a)nvidia.com>
---
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
index 22ddd05bbdcd..c623dae1e115 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
@@ -183,7 +183,14 @@ static void arm_smmu_mm_invalidate_range(struct mmu_notifier *mn,
{
struct arm_smmu_mmu_notifier *smmu_mn = mn_to_smmu(mn);
struct arm_smmu_domain *smmu_domain = smmu_mn->domain;
- size_t size = end - start + 1;
+ size_t size;
+
+ /*
+ * The mm_types defines vm_end as the first byte after the end address,
+ * different from IOMMU subsystem using the last address of an address
+ * range. So do a simple translation here by calculating size correctly.
+ */
+ size = end - start;
if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_BTM))
arm_smmu_tlb_inv_range_asid(start, size, smmu_mn->cd->asid,
--
2.17.1
> -----Original Message-----
> From: Fabio Estevam <festevam(a)gmail.com>
> Sent: Tuesday, April 19, 2022 5:15 PM
> To: herbert(a)gondor.apana.org.au
> Cc: Horia Geanta <horia.geanta(a)nxp.com>; Gaurav Jain
> <gaurav.jain(a)nxp.com>; Varun Sethi <V.Sethi(a)nxp.com>; linux-
> crypto(a)vger.kernel.org; Fabio Estevam <festevam(a)denx.de>;
> stable(a)vger.kernel.org
> Subject: [EXT] [PATCH v4] crypto: caam - fix i.MX6SX entropy delay value
>
> Caution: EXT Email
>
> From: Fabio Estevam <festevam(a)denx.de>
>
> Since commit 358ba762d9f1 ("crypto: caam - enable prediction resistance in
> HRWNG") the following CAAM errors can be seen on i.MX6SX:
>
> caam_jr 2101000.jr: 20003c5b: CCB: desc idx 60: RNG: Hardware error
> hwrng: no data available
>
> This error is due to an incorrect entropy delay for i.MX6SX.
>
> Fix it by increasing the minimum entropy delay for i.MX6SX as done in U-Boot:
> https://eur01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fpatch
> work.ozlabs.org%2Fproject%2Fuboot%2Fpatch%2F20220415111049.2565744-
> 1-
> gaurav.jain%40nxp.com%2F&data=05%7C01%7Cgaurav.jain%40nxp.co
> m%7C9016fe4b6bb8402de08f08da21fa0703%7C686ea1d3bc2b4c6fa92cd99c5c
> 301635%7C0%7C0%7C637859655100732358%7CUnknown%7CTWFpbGZsb3d8
> eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3
> D%7C3000%7C%7C%7C&sdata=wglpvZBmQUKn7sLRx5xpdwdgFMOc6LE
> qIMqUU0h4UZE%3D&reserved=0
>
> Cc: <stable(a)vger.kernel.org>
> Fixes: 358ba762d9f1 ("crypto: caam - enable prediction resistance in HRWNG")
> Signed-off-by: Fabio Estevam <festevam(a)denx.de>
> ---
> Changes since v3:
> - Add a needs_extended_entropy_delay() function
> - Assign the 'ent_delay' inside the the RNG initialization area. (Horia)
> - Change the terminology as per Horia's explanation.
>
> drivers/crypto/caam/ctrl.c | 18 ++++++++++++++++++
> 1 file changed, 18 insertions(+)
>
> diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c index
> ca0361b2dbb0..5b989a842ee9 100644
> --- a/drivers/crypto/caam/ctrl.c
> +++ b/drivers/crypto/caam/ctrl.c
> @@ -609,6 +609,13 @@ static bool check_version(struct fsl_mc_version
> *mc_version, u32 major, } #endif
>
> +static bool needs_extended_entropy_delay(void)
> +{
> + if (of_machine_is_compatible("fsl,imx6sx"))
> + return true;
> + return false;
> +}
> +
> /* Probe routine for CAAM top (controller) level */ static int
> caam_probe(struct platform_device *pdev) { @@ -855,6 +862,8 @@ static
> int caam_probe(struct platform_device *pdev)
> * Also, if a handle was instantiated, do not change
> * the TRNG parameters.
> */
> + if (needs_extended_entropy_delay())
> + ent_delay = 12000;
> if (!(ctrlpriv->rng4_sh_init || inst_handles)) {
Please note if TRNG state handles are already instantiated e.g. by U-Boot bootloader, It is assumed that entropy is set correctly and kick_trng() will be skipped
Kindly pick the U-Boot changes as detailed in commit message.
> dev_info(dev,
> "Entropy delay = %u\n", @@ -871,6 +880,15 @@ static
> int caam_probe(struct platform_device *pdev)
> */
> ret = instantiate_rng(dev, inst_handles,
> gen_sk);
> + /*
> + * Entropy delay is determined via TRNG characterization.
> + * TRNG characterization is run across different voltages
> + * and temperatures.
> + * If worst case value for ent_dly is identified,
> + * the loop can be skipped for that platform.
> + */
> + if (needs_extended_entropy_delay())
There is nothing like extended entropy delay and function name seems to be incorrect, The software test were run offline across ranges of temperature, voltage and process to determine the correct entropy delay.
However, value of 12000 is determined by running said test across voltage and temperature only for iMX6SX.
> + break;
> if (ret == -EAGAIN)
> /*
> * if here, the loop will rerun,
> --
> 2.25.1
Issue description:
When an OTG port has been switched to device role and then switch back
to host role again, the USB 3.0 Host (XHCI) will not be able to detect
"plug in event of a connected USB 2.0/1.0 ((Highspeed and Fullspeed)
devices until system reboot.
Root cause and Solution:
There is a condition checking flag "ssusb->otg_switch.is_u3_drd" in
toggle_opstate(). At the end of role switch procedure, toggle_opstate()
will be called to set DC_SESSION and SOFT_CONN bit. If "is_u3_drd" was
set and switched the role to USB host 3.0, bit DC_SESSION and SOFT_CONN
will be skipped hence caused the port cannot detect connected USB 2.0
(Highspeed and Fullspeed) devices. Simply remove the condition check to
solve this issue.
Fixes: d0ed062a8b75 ("usb: mtu3: dual-role mode support")
Signed-off-by: Macpaul Lin <macpaul.lin(a)mediatek.com>
Signed-off-by: Tainping Fang <tianping.fang(a)mediatek.com>
Tested-by: Fabien Parent <fparent(a)baylibre.com>
Cc: stable(a)vger.kernel.org
---
drivers/usb/mtu3/mtu3_dr.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/drivers/usb/mtu3/mtu3_dr.c b/drivers/usb/mtu3/mtu3_dr.c
index ec6ec621838b..b820724c56e4 100644
--- a/drivers/usb/mtu3/mtu3_dr.c
+++ b/drivers/usb/mtu3/mtu3_dr.c
@@ -21,10 +21,8 @@ static inline struct ssusb_mtk *otg_sx_to_ssusb(struct otg_switch_mtk *otg_sx)
static void toggle_opstate(struct ssusb_mtk *ssusb)
{
- if (!ssusb->otg_switch.is_u3_drd) {
- mtu3_setbits(ssusb->mac_base, U3D_DEVICE_CONTROL, DC_SESSION);
- mtu3_setbits(ssusb->mac_base, U3D_POWER_MANAGEMENT, SOFT_CONN);
- }
+ mtu3_setbits(ssusb->mac_base, U3D_DEVICE_CONTROL, DC_SESSION);
+ mtu3_setbits(ssusb->mac_base, U3D_POWER_MANAGEMENT, SOFT_CONN);
}
/* only port0 supports dual-role mode */
--
2.18.0
From: Guo Ren <guoren(a)linux.alibaba.com>
These patch_text implementations are using stop_machine_cpuslocked
infrastructure with atomic cpu_count. The original idea: When the
master CPU patch_text, the others should wait for it. But current
implementation is using the first CPU as master, which couldn't
guarantee the remaining CPUs are waiting. This patch changes the
last CPU as the master to solve the potential risk.
Fixes: 64711f9a47d4 ("xtensa: implement jump_label support")
Signed-off-by: Guo Ren <guoren(a)linux.alibaba.com>
Signed-off-by: Guo Ren <guoren(a)kernel.org>
Reviewed-by: Max Filippov <jcmvbkbc(a)gmail.com>
Reviewed-by: Masami Hiramatsu <mhiramat(a)kernel.org>
Cc: <stable(a)vger.kernel.org>
Message-Id: <20220407073323.743224-4-guoren(a)kernel.org>
Signed-off-by: Max Filippov <jcmvbkbc(a)gmail.com>
---
arch/xtensa/kernel/jump_label.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/xtensa/kernel/jump_label.c b/arch/xtensa/kernel/jump_label.c
index 0dde21e0d3de..ad1841cecdfb 100644
--- a/arch/xtensa/kernel/jump_label.c
+++ b/arch/xtensa/kernel/jump_label.c
@@ -40,7 +40,7 @@ static int patch_text_stop_machine(void *data)
{
struct patch *patch = data;
- if (atomic_inc_return(&patch->cpu_count) == 1) {
+ if (atomic_inc_return(&patch->cpu_count) == num_online_cpus()) {
local_patch_text(patch->addr, patch->data, patch->sz);
atomic_inc(&patch->cpu_count);
} else {
--
2.30.2
During the uvcg_video_pump() process, if an error occurs and
uvcg_queue_cancel() is called, the buffer queue will be cleared out, but
the current marker (queue->buf_used) of the active buffer (no longer
active) is not reset. On the next iteration of uvcg_video_pump() the
stale buf_used count will be used and the logic of min((unsigned
int)len, buf->bytesused - queue->buf_used) may incorrectly calculate a
nbytes size, causing an invalid memory access.
[80802.185460][ T315] configfs-gadget gadget: uvc: VS request completed
with status -18.
[80802.185519][ T315] configfs-gadget gadget: uvc: VS request completed
with status -18.
...
uvcg_queue_cancel() is called and the queue is cleared out, but the
marker queue->buf_used is not reset.
...
[80802.262328][ T8682] Unable to handle kernel paging request at virtual
address ffffffc03af9f000
...
...
[80802.263138][ T8682] Call trace:
[80802.263146][ T8682] __memcpy+0x12c/0x180
[80802.263155][ T8682] uvcg_video_pump+0xcc/0x1e0
[80802.263165][ T8682] process_one_work+0x2cc/0x568
[80802.263173][ T8682] worker_thread+0x28c/0x518
[80802.263181][ T8682] kthread+0x160/0x170
[80802.263188][ T8682] ret_from_fork+0x10/0x18
[80802.263198][ T8682] Code: a8c12829 a88130cb a8c130
Fixes: d692522577c0 ("usb: gadget/uvc: Port UVC webcam gadget to use videobuf2 framework")
Signed-off-by: Dan Vacura <w36195(a)motorola.com>
---
Changes in v2:
- Add Fixes tag
drivers/usb/gadget/function/uvc_queue.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/usb/gadget/function/uvc_queue.c b/drivers/usb/gadget/function/uvc_queue.c
index d852ac9e47e7..2cda982f3765 100644
--- a/drivers/usb/gadget/function/uvc_queue.c
+++ b/drivers/usb/gadget/function/uvc_queue.c
@@ -264,6 +264,8 @@ void uvcg_queue_cancel(struct uvc_video_queue *queue, int disconnect)
buf->state = UVC_BUF_STATE_ERROR;
vb2_buffer_done(&buf->buf.vb2_buf, VB2_BUF_STATE_ERROR);
}
+ queue->buf_used = 0;
+
/* This must be protected by the irqlock spinlock to avoid race
* conditions between uvc_queue_buffer and the disconnection event that
* could result in an interruptible wait in uvc_dequeue_buffer. Do not
--
2.32.0
From: Fabio Estevam <festevam(a)denx.de>
Since commit 358ba762d9f1 ("crypto: caam - enable prediction resistance
in HRWNG") the following CAAM errors can be seen on i.MX6SX:
caam_jr 2101000.jr: 20003c5b: CCB: desc idx 60: RNG: Hardware error
hwrng: no data available
This error is due to an incorrect entropy delay for i.MX6SX.
Fix it by increasing the minimum entropy delay for i.MX6SX
as done in U-Boot:
https://patchwork.ozlabs.org/project/uboot/patch/20220415111049.2565744-1-g…
Cc: <stable(a)vger.kernel.org>
Fixes: 358ba762d9f1 ("crypto: caam - enable prediction resistance in HRWNG")
Signed-off-by: Fabio Estevam <festevam(a)denx.de>
---
Changes since v3:
- Add a needs_extended_entropy_delay() function
- Assign the 'ent_delay' inside the the RNG initialization area. (Horia)
- Change the terminology as per Horia's explanation.
drivers/crypto/caam/ctrl.c | 18 ++++++++++++++++++
1 file changed, 18 insertions(+)
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index ca0361b2dbb0..5b989a842ee9 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -609,6 +609,13 @@ static bool check_version(struct fsl_mc_version *mc_version, u32 major,
}
#endif
+static bool needs_extended_entropy_delay(void)
+{
+ if (of_machine_is_compatible("fsl,imx6sx"))
+ return true;
+ return false;
+}
+
/* Probe routine for CAAM top (controller) level */
static int caam_probe(struct platform_device *pdev)
{
@@ -855,6 +862,8 @@ static int caam_probe(struct platform_device *pdev)
* Also, if a handle was instantiated, do not change
* the TRNG parameters.
*/
+ if (needs_extended_entropy_delay())
+ ent_delay = 12000;
if (!(ctrlpriv->rng4_sh_init || inst_handles)) {
dev_info(dev,
"Entropy delay = %u\n",
@@ -871,6 +880,15 @@ static int caam_probe(struct platform_device *pdev)
*/
ret = instantiate_rng(dev, inst_handles,
gen_sk);
+ /*
+ * Entropy delay is determined via TRNG characterization.
+ * TRNG characterization is run across different voltages
+ * and temperatures.
+ * If worst case value for ent_dly is identified,
+ * the loop can be skipped for that platform.
+ */
+ if (needs_extended_entropy_delay())
+ break;
if (ret == -EAGAIN)
/*
* if here, the loop will rerun,
--
2.25.1
This is a fix for commit f6795053dac8 ("mm: mmap: Allow for "high"
userspace addresses") for hugetlb.
This patch adds support for "high" userspace addresses that are
optionally supported on the system and have to be requested via a hint
mechanism ("high" addr parameter to mmap).
Architectures such as powerpc and x86 achieve this by making changes to
their architectural versions of hugetlb_get_unmapped_area() function.
However, arm64 uses the generic version of that function.
So take into account arch_get_mmap_base() and arch_get_mmap_end() in
hugetlb_get_unmapped_area(). To allow that, move those two macros
out of mm/mmap.c into include/linux/sched/mm.h
If these macros are not defined in architectural code then they default
to (TASK_SIZE) and (base) so should not introduce any behavioural
changes to architectures that do not define them.
For the time being, only ARM64 is affected by this change.
From Catalin (ARM64):
We should have fixed hugetlb_get_unmapped_area() as well when we
added support for 52-bit VA. The reason for commit f6795053dac8 was to
prevent normal mmap() from returning addresses above 48-bit by default
as some user-space had hard assumptions about this.
It's a slight ABI change if you do this for hugetlb_get_unmapped_area()
but I doubt anyone would notice. It's more likely that the current
behaviour would cause issues, so I'd rather have them consistent.
Signed-off-by: Christophe Leroy <christophe.leroy(a)csgroup.eu>
Cc: Steve Capper <steve.capper(a)arm.com>
Cc: Will Deacon <will.deacon(a)arm.com>
Cc: Catalin Marinas <catalin.marinas(a)arm.com>
Fixes: f6795053dac8 ("mm: mmap: Allow for "high" userspace addresses")
Cc: <stable(a)vger.kernel.org> # 5.0.x
Reviewed-by: Catalin Marinas <catalin.marinas(a)arm.com>
Acked-by: Andrew Morton <akpm(a)linux-foundation.org>
---
Resending the patch as standalone so that is can be merged via mm tree in 5.18 and stable.
v10:
- Moved as first patch of the series so that it can be applied
separately as a flag and be easily applied back on stable.
- Added text from Catalin explaining why it is a fixup.
---
fs/hugetlbfs/inode.c | 9 +++++----
include/linux/sched/mm.h | 8 ++++++++
mm/mmap.c | 8 --------
3 files changed, 13 insertions(+), 12 deletions(-)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 99c7477cee5c..dd3a088db11d 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -206,7 +206,7 @@ hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr,
info.flags = 0;
info.length = len;
info.low_limit = current->mm->mmap_base;
- info.high_limit = TASK_SIZE;
+ info.high_limit = arch_get_mmap_end(addr);
info.align_mask = PAGE_MASK & ~huge_page_mask(h);
info.align_offset = 0;
return vm_unmapped_area(&info);
@@ -222,7 +222,7 @@ hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr,
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
info.length = len;
info.low_limit = max(PAGE_SIZE, mmap_min_addr);
- info.high_limit = current->mm->mmap_base;
+ info.high_limit = arch_get_mmap_base(addr, current->mm->mmap_base);
info.align_mask = PAGE_MASK & ~huge_page_mask(h);
info.align_offset = 0;
addr = vm_unmapped_area(&info);
@@ -237,7 +237,7 @@ hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr,
VM_BUG_ON(addr != -ENOMEM);
info.flags = 0;
info.low_limit = current->mm->mmap_base;
- info.high_limit = TASK_SIZE;
+ info.high_limit = arch_get_mmap_end(addr);
addr = vm_unmapped_area(&info);
}
@@ -251,6 +251,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
struct hstate *h = hstate_file(file);
+ const unsigned long mmap_end = arch_get_mmap_end(addr);
if (len & ~huge_page_mask(h))
return -EINVAL;
@@ -266,7 +267,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
if (addr) {
addr = ALIGN(addr, huge_page_size(h));
vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr &&
+ if (mmap_end - len >= addr &&
(!vma || addr + len <= vm_start_gap(vma)))
return addr;
}
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index a80356e9dc69..1ad1f4bfa025 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -136,6 +136,14 @@ static inline void mm_update_next_owner(struct mm_struct *mm)
#endif /* CONFIG_MEMCG */
#ifdef CONFIG_MMU
+#ifndef arch_get_mmap_end
+#define arch_get_mmap_end(addr) (TASK_SIZE)
+#endif
+
+#ifndef arch_get_mmap_base
+#define arch_get_mmap_base(addr, base) (base)
+#endif
+
extern void arch_pick_mmap_layout(struct mm_struct *mm,
struct rlimit *rlim_stack);
extern unsigned long
diff --git a/mm/mmap.c b/mm/mmap.c
index 3aa839f81e63..313b57d55a63 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2117,14 +2117,6 @@ unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info)
return addr;
}
-#ifndef arch_get_mmap_end
-#define arch_get_mmap_end(addr) (TASK_SIZE)
-#endif
-
-#ifndef arch_get_mmap_base
-#define arch_get_mmap_base(addr, base) (base)
-#endif
-
/* Get an address range which is currently unmapped.
* For shmat() with addr=0.
*
--
2.35.1
This is a note to let you know that I've just added the patch titled
usb: gadget: uvc: Fix crash when encoding data for usb request
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 71d471e3faf90c9674cadc7605ac719e82cb7fac Mon Sep 17 00:00:00 2001
From: Dan Vacura <w36195(a)motorola.com>
Date: Thu, 31 Mar 2022 13:40:23 -0500
Subject: usb: gadget: uvc: Fix crash when encoding data for usb request
During the uvcg_video_pump() process, if an error occurs and
uvcg_queue_cancel() is called, the buffer queue will be cleared out, but
the current marker (queue->buf_used) of the active buffer (no longer
active) is not reset. On the next iteration of uvcg_video_pump() the
stale buf_used count will be used and the logic of min((unsigned
int)len, buf->bytesused - queue->buf_used) may incorrectly calculate a
nbytes size, causing an invalid memory access.
[80802.185460][ T315] configfs-gadget gadget: uvc: VS request completed
with status -18.
[80802.185519][ T315] configfs-gadget gadget: uvc: VS request completed
with status -18.
...
uvcg_queue_cancel() is called and the queue is cleared out, but the
marker queue->buf_used is not reset.
...
[80802.262328][ T8682] Unable to handle kernel paging request at virtual
address ffffffc03af9f000
...
...
[80802.263138][ T8682] Call trace:
[80802.263146][ T8682] __memcpy+0x12c/0x180
[80802.263155][ T8682] uvcg_video_pump+0xcc/0x1e0
[80802.263165][ T8682] process_one_work+0x2cc/0x568
[80802.263173][ T8682] worker_thread+0x28c/0x518
[80802.263181][ T8682] kthread+0x160/0x170
[80802.263188][ T8682] ret_from_fork+0x10/0x18
[80802.263198][ T8682] Code: a8c12829 a88130cb a8c130
Fixes: d692522577c0 ("usb: gadget/uvc: Port UVC webcam gadget to use videobuf2 framework")
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Dan Vacura <w36195(a)motorola.com>
Link: https://lore.kernel.org/r/20220331184024.23918-1-w36195@motorola.com
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
drivers/usb/gadget/function/uvc_queue.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/usb/gadget/function/uvc_queue.c b/drivers/usb/gadget/function/uvc_queue.c
index d852ac9e47e7..2cda982f3765 100644
--- a/drivers/usb/gadget/function/uvc_queue.c
+++ b/drivers/usb/gadget/function/uvc_queue.c
@@ -264,6 +264,8 @@ void uvcg_queue_cancel(struct uvc_video_queue *queue, int disconnect)
buf->state = UVC_BUF_STATE_ERROR;
vb2_buffer_done(&buf->buf.vb2_buf, VB2_BUF_STATE_ERROR);
}
+ queue->buf_used = 0;
+
/* This must be protected by the irqlock spinlock to avoid race
* conditions between uvc_queue_buffer and the disconnection event that
* could result in an interruptible wait in uvc_dequeue_buffer. Do not
--
2.35.3
From: Nicholas Piggin <npiggin(a)gmail.com>
[ Upstream commit c7fa848ff01dad9ed3146a6b1a7d3622131bcedd ]
When new work is created that requires attention from the hypervisor
(e.g., to inject an interrupt into the guest), fast_vcpu_kick is used to
pull the target vcpu out of the guest if it may have been running.
Therefore the work creation side looks like this:
vcpu->arch.doorbell_request = 1;
kvmppc_fast_vcpu_kick_hv(vcpu) {
smp_mb();
cpu = vcpu->cpu;
if (cpu != -1)
send_ipi(cpu);
}
And the guest entry side *should* look like this:
vcpu->cpu = smp_processor_id();
smp_mb();
if (vcpu->arch.doorbell_request) {
// do something (abort entry or inject doorbell etc)
}
But currently the store and load are flipped, so it is possible for the
entry to see no doorbell pending, and the doorbell creation misses the
store to set cpu, resulting lost work (or at least delayed until the
next guest exit).
Fix this by reordering the entry operations and adding a smp_mb
between them. The P8 path appears to have a similar race which is
commented but not addressed yet.
Signed-off-by: Nicholas Piggin <npiggin(a)gmail.com>
Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au>
Link: https://lore.kernel.org/r/20220303053315.1056880-2-npiggin@gmail.com
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
---
arch/powerpc/kvm/book3s_hv.c | 41 +++++++++++++++++++++++++++++-------
1 file changed, 33 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 791db769080d..316f61a4cb59 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -225,6 +225,13 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
int cpu;
struct rcuwait *waitp;
+ /*
+ * rcuwait_wake_up contains smp_mb() which orders prior stores that
+ * create pending work vs below loads of cpu fields. The other side
+ * is the barrier in vcpu run that orders setting the cpu fields vs
+ * testing for pending work.
+ */
+
waitp = kvm_arch_vcpu_get_wait(vcpu);
if (rcuwait_wake_up(waitp))
++vcpu->stat.generic.halt_wakeup;
@@ -1089,7 +1096,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
break;
}
tvcpu->arch.prodded = 1;
- smp_mb();
+ smp_mb(); /* This orders prodded store vs ceded load */
if (tvcpu->arch.ceded)
kvmppc_fast_vcpu_kick_hv(tvcpu);
break;
@@ -3771,6 +3778,14 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
pvc = core_info.vc[sub];
pvc->pcpu = pcpu + thr;
for_each_runnable_thread(i, vcpu, pvc) {
+ /*
+ * XXX: is kvmppc_start_thread called too late here?
+ * It updates vcpu->cpu and vcpu->arch.thread_cpu
+ * which are used by kvmppc_fast_vcpu_kick_hv(), but
+ * kick is called after new exceptions become available
+ * and exceptions are checked earlier than here, by
+ * kvmppc_core_prepare_to_enter.
+ */
kvmppc_start_thread(vcpu, pvc);
kvmppc_create_dtl_entry(vcpu, pvc);
trace_kvm_guest_enter(vcpu);
@@ -4492,6 +4507,21 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
if (need_resched() || !kvm->arch.mmu_ready)
goto out;
+ vcpu->cpu = pcpu;
+ vcpu->arch.thread_cpu = pcpu;
+ vc->pcpu = pcpu;
+ local_paca->kvm_hstate.kvm_vcpu = vcpu;
+ local_paca->kvm_hstate.ptid = 0;
+ local_paca->kvm_hstate.fake_suspend = 0;
+
+ /*
+ * Orders set cpu/thread_cpu vs testing for pending interrupts and
+ * doorbells below. The other side is when these fields are set vs
+ * kvmppc_fast_vcpu_kick_hv reading the cpu/thread_cpu fields to
+ * kick a vCPU to notice the pending interrupt.
+ */
+ smp_mb();
+
if (!nested) {
kvmppc_core_prepare_to_enter(vcpu);
if (test_bit(BOOK3S_IRQPRIO_EXTERNAL,
@@ -4511,13 +4541,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
tb = mftb();
- vcpu->cpu = pcpu;
- vcpu->arch.thread_cpu = pcpu;
- vc->pcpu = pcpu;
- local_paca->kvm_hstate.kvm_vcpu = vcpu;
- local_paca->kvm_hstate.ptid = 0;
- local_paca->kvm_hstate.fake_suspend = 0;
-
__kvmppc_create_dtl_entry(vcpu, pcpu, tb + vc->tb_offset, 0);
trace_kvm_guest_enter(vcpu);
@@ -4619,6 +4642,8 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
run->exit_reason = KVM_EXIT_INTR;
vcpu->arch.ret = -EINTR;
out:
+ vcpu->cpu = -1;
+ vcpu->arch.thread_cpu = -1;
powerpc_local_irq_pmu_restore(flags);
preempt_enable();
goto done;
--
2.35.1
Last cycle we extended the idmapped mounts infrastructure to support idmapped
mounts of idmapped filesystems (No such filesystem yet exist.).
Since then, the meaning of an idmapped mount is a mount whose idmapping is
different from the filesystems idmapping.
While doing that work we missed to adapt the acl translation helpers. They
still assume that checking for the identity mapping is enough. But they need to
use the no_idmapping() helper instead.
Note, POSIX ACLs are always translated right at the userspace-kernel boundary
using the caller's current idmapping and the initial idmapping. The order
depends on whether we're coming from or going to userspace. The filesystem's
idmapping doesn't matter at the border.
Consequently, if a non-idmapped mount is passed we need to make sure to always
pass the initial idmapping as the mount's idmapping and not the filesystem
idmapping. Since it's irrelevant here it would yield invalid ids and prevent
setting acls for filesystems that are mountable in a userns and support posix
acls (tmpfs and fuse).
I verified the regression reported in [1] and verified that this patch fixes
it. A regression test will be added to xfstests in parallel.
Link: https://bugzilla.kernel.org/show_bug.cgi?id=215849 [1]
Fixes: bd303368b776 ("fs: support mapped mounts of mapped filesystems")
Cc: Seth Forshee <sforshee(a)digitalocean.com>
Cc: Christoph Hellwig <hch(a)lst.de>
Cc: <stable(a)vger.kernel.org> # 5.17
Cc: <regressions(a)lists.linux.dev>
Signed-off-by: Christian Brauner (Microsoft) <brauner(a)kernel.org>
---
Hey Linus,
Last cycle we introduced a regression that got reported to me right over Easter
on Bugzilla. It is only relevant for 5.17 and current mainline. Could you
please apply this regression fix?
Thanks!
Christian
---
fs/posix_acl.c | 10 ++++++++++
fs/xattr.c | 6 ++++--
include/linux/posix_acl_xattr.h | 4 ++++
3 files changed, 18 insertions(+), 2 deletions(-)
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 80acb6885cf9..962d32468eb4 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -759,9 +759,14 @@ static void posix_acl_fix_xattr_userns(
}
void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns,
+ struct inode *inode,
void *value, size_t size)
{
struct user_namespace *user_ns = current_user_ns();
+
+ /* Leave ids untouched on non-idmapped mounts. */
+ if (no_idmapping(mnt_userns, i_user_ns(inode)))
+ mnt_userns = &init_user_ns;
if ((user_ns == &init_user_ns) && (mnt_userns == &init_user_ns))
return;
posix_acl_fix_xattr_userns(&init_user_ns, user_ns, mnt_userns, value,
@@ -769,9 +774,14 @@ void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns,
}
void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns,
+ struct inode *inode,
void *value, size_t size)
{
struct user_namespace *user_ns = current_user_ns();
+
+ /* Leave ids untouched on non-idmapped mounts. */
+ if (no_idmapping(mnt_userns, i_user_ns(inode)))
+ mnt_userns = &init_user_ns;
if ((user_ns == &init_user_ns) && (mnt_userns == &init_user_ns))
return;
posix_acl_fix_xattr_userns(user_ns, &init_user_ns, mnt_userns, value,
diff --git a/fs/xattr.c b/fs/xattr.c
index 5c8c5175b385..998045165916 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -569,7 +569,8 @@ setxattr(struct user_namespace *mnt_userns, struct dentry *d,
}
if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
(strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0))
- posix_acl_fix_xattr_from_user(mnt_userns, kvalue, size);
+ posix_acl_fix_xattr_from_user(mnt_userns, d_inode(d),
+ kvalue, size);
}
error = vfs_setxattr(mnt_userns, d, kname, kvalue, size, flags);
@@ -667,7 +668,8 @@ getxattr(struct user_namespace *mnt_userns, struct dentry *d,
if (error > 0) {
if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
(strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0))
- posix_acl_fix_xattr_to_user(mnt_userns, kvalue, error);
+ posix_acl_fix_xattr_to_user(mnt_userns, d_inode(d),
+ kvalue, error);
if (size && copy_to_user(value, kvalue, error))
error = -EFAULT;
} else if (error == -ERANGE && size >= XATTR_SIZE_MAX) {
diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h
index 060e8d203181..1766e1de6956 100644
--- a/include/linux/posix_acl_xattr.h
+++ b/include/linux/posix_acl_xattr.h
@@ -34,15 +34,19 @@ posix_acl_xattr_count(size_t size)
#ifdef CONFIG_FS_POSIX_ACL
void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns,
+ struct inode *inode,
void *value, size_t size);
void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns,
+ struct inode *inode,
void *value, size_t size);
#else
static inline void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns,
+ struct inode *inode,
void *value, size_t size)
{
}
static inline void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns,
+ struct inode *inode,
void *value, size_t size)
{
}
base-commit: b2d229d4ddb17db541098b83524d901257e93845
--
2.32.0
This is the start of the stable review cycle for the 4.19.239 release.
There are 32 patches in this series, all will be posted as a response
to this one. If anyone has any issues with these being applied, please
let me know.
Responses should be made by Wed, 20 Apr 2022 12:11:14 +0000.
Anything received after that time might be too late.
The whole patch series can be found in one patch at:
https://www.kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.19.239-r…
or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.19.y
and the diffstat can be found below.
thanks,
greg k-h
-------------
Pseudo-Shortlog of commits:
Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Linux 4.19.239-rc1
Martin Povišer <povik+lin(a)cutebit.org>
i2c: pasemi: Wait for write xfers to finish
Nadav Amit <namit(a)vmware.com>
smp: Fix offline cpu check in flush_smp_call_function_queue()
Nathan Chancellor <nathan(a)kernel.org>
ARM: davinci: da850-evm: Avoid NULL pointer dereference
Nicolas Dichtel <nicolas.dichtel(a)6wind.com>
ipv6: fix panic when forwarding a pkt with no in6 dev
Fabio M. De Francesco <fmdefrancesco(a)gmail.com>
ALSA: pcm: Test for "silence" field in struct "pcm_format_data"
Tim Crawford <tcrawford(a)system76.com>
ALSA: hda/realtek: Add quirk for Clevo PD50PNT
Jason A. Donenfeld <Jason(a)zx2c4.com>
gcc-plugins: latent_entropy: use /dev/urandom
Oliver Upton <oupton(a)google.com>
KVM: Don't create VM debugfs files outside of the VM directory
Patrick Wang <patrick.wang.shcn(a)gmail.com>
mm: kmemleak: take a full lowmem check in kmemleak_*_phys()
Juergen Gross <jgross(a)suse.com>
mm, page_alloc: fix build_zonerefs_node()
Duoming Zhou <duoming(a)zju.edu.cn>
drivers: net: slip: fix NPD bug in sl_tx_timeout()
Alexey Galakhov <agalakhov(a)gmail.com>
scsi: mvsas: Add PCI ID of RocketRaid 2640
Roman Li <Roman.Li(a)amd.com>
drm/amd/display: Fix allocate_mst_payload assert on resume
Joey Gouly <joey.gouly(a)arm.com>
arm64: alternatives: mark patch_alternative() as `noinstr`
Leo Ruan <tingquan.ruan(a)cn.bosch.com>
gpu: ipu-v3: Fix dev_dbg frequency output
Christian Lamparter <chunkeey(a)gmail.com>
ata: libata-core: Disable READ LOG DMA EXT for Samsung 840 EVOs
Randy Dunlap <rdunlap(a)infradead.org>
net: micrel: fix KS8851_MLL Kconfig
Tyrel Datwyler <tyreld(a)linux.ibm.com>
scsi: ibmvscsis: Increase INITIAL_SRP_LIMIT to 1024
Xiaoguang Wang <xiaoguang.wang(a)linux.alibaba.com>
scsi: target: tcmu: Fix possible page UAF
Michael Kelley <mikelley(a)microsoft.com>
Drivers: hv: vmbus: Prevent load re-ordering when reading ring buffer
QintaoShen <unSimple1993(a)163.com>
drm/amdkfd: Check for potential null return of kmalloc_array()
Aurabindo Pillai <aurabindo.pillai(a)amd.com>
drm/amd: Add USBC connector ID
Harshit Mogalapalli <harshit.m.mogalapalli(a)oracle.com>
cifs: potential buffer overflow in handling symlinks
Lin Ma <linma(a)zju.edu.cn>
nfc: nci: add flush_workqueue to prevent uaf
Athira Rajeev <atrajeev(a)linux.vnet.ibm.com>
testing/selftests/mqueue: Fix mq_perf_tests to free the allocated cpu set
Petr Malat <oss(a)malat.biz>
sctp: Initialize daddr on peeled off socket
Dinh Nguyen <dinguyen(a)kernel.org>
net: ethernet: stmmac: fix altr_tse_pcs function when using a fixed-link
Vadim Pasternak <vadimp(a)nvidia.com>
mlxsw: i2c: Fix initialization error flow
Linus Torvalds <torvalds(a)linux-foundation.org>
gpiolib: acpi: use correct format characters
Guillaume Nault <gnault(a)redhat.com>
veth: Ensure eth header is in skb's linear part
Vlad Buslov <vladbu(a)nvidia.com>
net/sched: flower: fix parsing of ethertype following VLAN header
Miaoqian Lin <linmq006(a)gmail.com>
memory: atmel-ebi: Fix missing of_node_put in atmel_ebi_probe
-------------
Diffstat:
Makefile | 4 +-
arch/arm/mach-davinci/board-da850-evm.c | 4 +-
arch/arm64/kernel/alternative.c | 6 +--
drivers/ata/libata-core.c | 3 ++
drivers/gpio/gpiolib-acpi.c | 4 +-
drivers/gpu/drm/amd/amdgpu/ObjectID.h | 1 +
drivers/gpu/drm/amd/amdkfd/kfd_events.c | 2 +
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 3 +-
drivers/gpu/ipu-v3/ipu-di.c | 5 ++-
drivers/hv/ring_buffer.c | 11 +++++-
drivers/i2c/busses/i2c-pasemi.c | 6 +++
drivers/memory/atmel-ebi.c | 23 ++++++++---
drivers/net/ethernet/mellanox/mlxsw/i2c.c | 1 +
drivers/net/ethernet/micrel/Kconfig | 1 +
drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c | 8 ----
drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.h | 4 ++
.../net/ethernet/stmicro/stmmac/dwmac-socfpga.c | 13 +++----
drivers/net/slip/slip.c | 2 +-
drivers/net/veth.c | 2 +-
drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c | 2 +-
drivers/scsi/mvsas/mv_init.c | 1 +
drivers/target/target_core_user.c | 3 +-
fs/cifs/link.c | 3 ++
include/net/flow_dissector.h | 2 +
kernel/smp.c | 2 +-
mm/kmemleak.c | 8 ++--
mm/page_alloc.c | 2 +-
net/core/flow_dissector.c | 1 +
net/ipv6/ip6_output.c | 2 +-
net/nfc/nci/core.c | 4 ++
net/sched/cls_flower.c | 18 ++++++---
net/sctp/socket.c | 2 +-
scripts/gcc-plugins/latent_entropy_plugin.c | 44 +++++++++++++---------
sound/core/pcm_misc.c | 2 +-
sound/pci/hda/patch_realtek.c | 1 +
tools/testing/selftests/mqueue/mq_perf_tests.c | 25 ++++++++----
virt/kvm/kvm_main.c | 8 +++-
37 files changed, 155 insertions(+), 78 deletions(-)
When writing out a stereo control we discard the change notification from
the first channel, meaning that events are only generated based on changes
to the second channel. Ensure that we report a change if either channel
has changed.
Signed-off-by: Mark Brown <broonie(a)kernel.org>
Cc: stable(a)vger.kernel.org
---
sound/soc/soc-ops.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c
index 73c9d53de25b..f0d1aeb38346 100644
--- a/sound/soc/soc-ops.c
+++ b/sound/soc/soc-ops.c
@@ -413,6 +413,7 @@ int snd_soc_put_volsw_sx(struct snd_kcontrol *kcontrol,
int min = mc->min;
unsigned int mask = (1U << (fls(min + max) - 1)) - 1;
int err = 0;
+ int ret;
unsigned int val, val_mask;
val_mask = mask << shift;
@@ -422,6 +423,7 @@ int snd_soc_put_volsw_sx(struct snd_kcontrol *kcontrol,
err = snd_soc_component_update_bits(component, reg, val_mask, val);
if (err < 0)
return err;
+ ret = err;
if (snd_soc_volsw_is_stereo(mc)) {
unsigned int val2;
@@ -432,6 +434,11 @@ int snd_soc_put_volsw_sx(struct snd_kcontrol *kcontrol,
err = snd_soc_component_update_bits(component, reg2, val_mask,
val2);
+
+ /* Don't discard any error code or drop change flag */
+ if (ret == 0 || err < 0) {
+ ret = err;
+ }
}
return err;
}
--
2.30.2
The patch titled
Subject: revert "fs/binfmt_elf: use PT_LOAD p_align values for static PIE"
has been removed from the -mm tree. Its filename was
revert-fs-binfmt_elf-use-pt_load-p_align-values-for-static-pie.patch
This patch was dropped because it was merged into mainline or a subsystem tree
------------------------------------------------------
From: Andrew Morton <akpm(a)linux-foundation.org>
Subject: revert "fs/binfmt_elf: use PT_LOAD p_align values for static PIE"
Despite Mike's attempted fix (925346c129da117122), regressions reports
continue:
https://lore.kernel.org/lkml/cb5b81bd-9882-e5dc-cd22-54bdbaaefbbc@leemhuis.…https://bugzilla.kernel.org/show_bug.cgi?id=215720https://lkml.kernel.org/r/b685f3d0-da34-531d-1aa9-479accd3e21b@leemhuis.info
So revert this patch.
Fixes: 9630f0d60fec ("fs/binfmt_elf: use PT_LOAD p_align values for static PIE")
Cc: Alexey Dobriyan <adobriyan(a)gmail.com>
Cc: Al Viro <viro(a)zeniv.linux.org.uk>
Cc: Chris Kennelly <ckennelly(a)google.com>
Cc: David Rientjes <rientjes(a)google.com>
Cc: Fangrui Song <maskray(a)google.com>
Cc: H.J. Lu <hjl.tools(a)gmail.com>
Cc: Hugh Dickins <hughd(a)google.com>
Cc: Ian Rogers <irogers(a)google.com>
Cc: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com>
Cc: Mike Kravetz <mike.kravetz(a)oracle.com>
Cc: Mike Rapoport <rppt(a)kernel.org>
Cc: Nick Desaulniers <ndesaulniers(a)google.com>
Cc: Sandeep Patil <sspatil(a)google.com>
Cc: Shuah Khan <shuah(a)kernel.org>
Cc: Song Liu <songliubraving(a)fb.com>
Cc: Suren Baghdasaryan <surenb(a)google.com>
Cc: Thorsten Leemhuis <regressions(a)leemhuis.info>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
fs/binfmt_elf.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
--- a/fs/binfmt_elf.c~revert-fs-binfmt_elf-use-pt_load-p_align-values-for-static-pie
+++ a/fs/binfmt_elf.c
@@ -1117,11 +1117,11 @@ out_free_interp:
* independently randomized mmap region (0 load_bias
* without MAP_FIXED nor MAP_FIXED_NOREPLACE).
*/
- alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum);
- if (alignment > ELF_MIN_ALIGN) {
+ if (interpreter) {
load_bias = ELF_ET_DYN_BASE;
if (current->flags & PF_RANDOMIZE)
load_bias += arch_mmap_rnd();
+ alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum);
if (alignment)
load_bias &= ~(alignment - 1);
elf_flags |= MAP_FIXED_NOREPLACE;
_
Patches currently in -mm which might be from akpm(a)linux-foundation.org are
mm.patch
kasan-fix-sleeping-function-called-from-invalid-context-on-rt-kernel-fix.patch
mm-create-new-mm-swaph-header-file-fix.patch
mm-shmem-make-shmem_init-return-void-fix.patch
mm-khugepaged-introduce-khugepaged_enter_vma-helper-vs-maple-tree.patch
mm-check-against-orig_pte-for-finish_fault-fix-checkpatch-fixes.patch
mglru-vs-maple-tree.patch
mm-vmscan-fix-comment-for-current_may_throttle-fix.patch
ksm-count-ksm-merging-pages-for-each-process-fix.patch
mm-memory_hotplug-refactor-hotadd_init_pgdat-and-try_online_node-checkpatch-fixes.patch
proc-fix-dentry-inode-overinstantiating-under-proc-pid-net-checkpatch-fixes.patch
fs-proc-kcorec-remove-check-of-list-iterator-against-head-past-the-loop-body-fix.patch
add-fat-messages-to-printk-index-checkpatch-fixes.patch
linux-next-rejects.patch
linux-next-git-rejects.patch
mm-oom_killc-fix-vm_oom_kill_table-ifdeffery.patch
The patch titled
Subject: revert "fs/binfmt_elf: fix PT_LOAD p_align values for loaders"
has been removed from the -mm tree. Its filename was
revert-fs-binfmt_elf-fix-pt_load-p_align-values-for-loaders.patch
This patch was dropped because it was merged into mainline or a subsystem tree
------------------------------------------------------
From: Andrew Morton <akpm(a)linux-foundation.org>
Subject: revert "fs/binfmt_elf: fix PT_LOAD p_align values for loaders"
925346c129da11 ("fs/binfmt_elf: fix PT_LOAD p_align values for loaders")
is an attempt to fix regressions due to 9630f0d60fec5f ("fs/binfmt_elf:
use PT_LOAD p_align values for static PIE").
But regressionss continue to be reported:
https://lore.kernel.org/lkml/cb5b81bd-9882-e5dc-cd22-54bdbaaefbbc@leemhuis.…https://bugzilla.kernel.org/show_bug.cgi?id=215720https://lkml.kernel.org/r/b685f3d0-da34-531d-1aa9-479accd3e21b@leemhuis.info
This patch reverts the fix, so the original can also be reverted.
Fixes: 925346c129da11 ("fs/binfmt_elf: fix PT_LOAD p_align values for loaders")
Cc: H.J. Lu <hjl.tools(a)gmail.com>
Cc: Chris Kennelly <ckennelly(a)google.com>
Cc: Al Viro <viro(a)zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan(a)gmail.com>
Cc: Song Liu <songliubraving(a)fb.com>
Cc: David Rientjes <rientjes(a)google.com>
Cc: Ian Rogers <irogers(a)google.com>
Cc: Hugh Dickins <hughd(a)google.com>
Cc: Suren Baghdasaryan <surenb(a)google.com>
Cc: Sandeep Patil <sspatil(a)google.com>
Cc: Fangrui Song <maskray(a)google.com>
Cc: Nick Desaulniers <ndesaulniers(a)google.com>
Cc: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com>
Cc: Mike Kravetz <mike.kravetz(a)oracle.com>
Cc: Shuah Khan <shuah(a)kernel.org>
Cc: Thorsten Leemhuis <regressions(a)leemhuis.info>
Cc: Mike Rapoport <rppt(a)kernel.org>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
fs/binfmt_elf.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/fs/binfmt_elf.c~revert-fs-binfmt_elf-fix-pt_load-p_align-values-for-loaders
+++ a/fs/binfmt_elf.c
@@ -1118,7 +1118,7 @@ out_free_interp:
* without MAP_FIXED nor MAP_FIXED_NOREPLACE).
*/
alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum);
- if (interpreter || alignment > ELF_MIN_ALIGN) {
+ if (alignment > ELF_MIN_ALIGN) {
load_bias = ELF_ET_DYN_BASE;
if (current->flags & PF_RANDOMIZE)
load_bias += arch_mmap_rnd();
_
Patches currently in -mm which might be from akpm(a)linux-foundation.org are
mm.patch
kasan-fix-sleeping-function-called-from-invalid-context-on-rt-kernel-fix.patch
mm-create-new-mm-swaph-header-file-fix.patch
mm-shmem-make-shmem_init-return-void-fix.patch
mm-khugepaged-introduce-khugepaged_enter_vma-helper-vs-maple-tree.patch
mm-check-against-orig_pte-for-finish_fault-fix-checkpatch-fixes.patch
mglru-vs-maple-tree.patch
mm-vmscan-fix-comment-for-current_may_throttle-fix.patch
ksm-count-ksm-merging-pages-for-each-process-fix.patch
mm-memory_hotplug-refactor-hotadd_init_pgdat-and-try_online_node-checkpatch-fixes.patch
proc-fix-dentry-inode-overinstantiating-under-proc-pid-net-checkpatch-fixes.patch
fs-proc-kcorec-remove-check-of-list-iterator-against-head-past-the-loop-body-fix.patch
add-fat-messages-to-printk-index-checkpatch-fixes.patch
linux-next-rejects.patch
linux-next-git-rejects.patch
mm-oom_killc-fix-vm_oom_kill_table-ifdeffery.patch
The patch titled
Subject: hugetlb: do not demote poisoned hugetlb pages
has been removed from the -mm tree. Its filename was
hugetlb-do-not-demote-poisoned-hugetlb-pages.patch
This patch was dropped because it was merged into mainline or a subsystem tree
------------------------------------------------------
From: Mike Kravetz <mike.kravetz(a)oracle.com>
Subject: hugetlb: do not demote poisoned hugetlb pages
It is possible for poisoned hugetlb pages to reside on the free lists.
The huge page allocation routines which dequeue entries from the free
lists make a point of avoiding poisoned pages. There is no such check and
avoidance in the demote code path.
If a hugetlb page on the is on a free list, poison will only be set in the
head page rather then the page with the actual error. If such a page is
demoted, then the poison flag may follow the wrong page. A page without
error could have poison set, and a page with poison could not have the
flag set.
Check for poison before attempting to demote a hugetlb page. Also, return
-EBUSY to the caller if only poisoned pages are on the free list.
Link: https://lkml.kernel.org/r/20220307215707.50916-1-mike.kravetz@oracle.com
Fixes: 8531fc6f52f5 ("hugetlb: add hugetlb demote page support")
Signed-off-by: Mike Kravetz <mike.kravetz(a)oracle.com>
Reviewed-by: Naoya Horiguchi <naoya.horiguchi(a)nec.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/hugetlb.c | 17 ++++++++++-------
1 file changed, 10 insertions(+), 7 deletions(-)
--- a/mm/hugetlb.c~hugetlb-do-not-demote-poisoned-hugetlb-pages
+++ a/mm/hugetlb.c
@@ -3475,7 +3475,6 @@ static int demote_pool_huge_page(struct
{
int nr_nodes, node;
struct page *page;
- int rc = 0;
lockdep_assert_held(&hugetlb_lock);
@@ -3486,15 +3485,19 @@ static int demote_pool_huge_page(struct
}
for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) {
- if (!list_empty(&h->hugepage_freelists[node])) {
- page = list_entry(h->hugepage_freelists[node].next,
- struct page, lru);
- rc = demote_free_huge_page(h, page);
- break;
+ list_for_each_entry(page, &h->hugepage_freelists[node], lru) {
+ if (PageHWPoison(page))
+ continue;
+
+ return demote_free_huge_page(h, page);
}
}
- return rc;
+ /*
+ * Only way to get here is if all pages on free lists are poisoned.
+ * Return -EBUSY so that caller will not retry.
+ */
+ return -EBUSY;
}
#define HSTATE_ATTR_RO(_name) \
_
Patches currently in -mm which might be from mike.kravetz(a)oracle.com are
The patch titled
Subject: mm: fix unexpected zeroed page mapping with zram swap
has been removed from the -mm tree. Its filename was
mm-fix-unexpected-zeroed-page-mapping-with-zram-swap.patch
This patch was dropped because it was merged into mainline or a subsystem tree
------------------------------------------------------
From: Minchan Kim <minchan(a)kernel.org>
Subject: mm: fix unexpected zeroed page mapping with zram swap
Two processes under CLONE_VM cloning, user process can be corrupted by
seeing zeroed page unexpectedly.
CPU A CPU B
do_swap_page do_swap_page
SWP_SYNCHRONOUS_IO path SWP_SYNCHRONOUS_IO path
swap_readpage valid data
swap_slot_free_notify
delete zram entry
swap_readpage zeroed(invalid) data
pte_lock
map the *zero data* to userspace
pte_unlock
pte_lock
if (!pte_same)
goto out_nomap;
pte_unlock
return and next refault will
read zeroed data
The swap_slot_free_notify is bogus for CLONE_VM case since it doesn't
increase the refcount of swap slot at copy_mm so it couldn't catch up
whether it's safe or not to discard data from backing device. In the
case, only the lock it could rely on to synchronize swap slot freeing is
page table lock. Thus, this patch gets rid of the swap_slot_free_notify
function. With this patch, CPU A will see correct data.
CPU A CPU B
do_swap_page do_swap_page
SWP_SYNCHRONOUS_IO path SWP_SYNCHRONOUS_IO path
swap_readpage original data
pte_lock
map the original data
swap_free
swap_range_free
bd_disk->fops->swap_slot_free_notify
swap_readpage read zeroed data
pte_unlock
pte_lock
if (!pte_same)
goto out_nomap;
pte_unlock
return
on next refault will see mapped data by CPU B
The concern of the patch would increase memory consumption since it could
keep wasted memory with compressed form in zram as well as uncompressed
form in address space. However, most of cases of zram uses no readahead
and do_swap_page is followed by swap_free so it will free the compressed
form from in zram quickly.
Link: https://lkml.kernel.org/r/YjTVVxIAsnKAXjTd@google.com
Fixes: 0bcac06f27d7 ("mm, swap: skip swapcache for swapin of synchronous device")
Reported-by: Ivan Babrou <ivan(a)cloudflare.com>
Tested-by: Ivan Babrou <ivan(a)cloudflare.com>
Signed-off-by: Minchan Kim <minchan(a)kernel.org>
Cc: Nitin Gupta <ngupta(a)vflare.org>
Cc: Sergey Senozhatsky <senozhatsky(a)chromium.org>
Cc: Jens Axboe <axboe(a)kernel.dk>
Cc: David Hildenbrand <david(a)redhat.com>
Cc: <stable(a)vger.kernel.org> [4.14+]
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/page_io.c | 54 -------------------------------------------------
1 file changed, 54 deletions(-)
--- a/mm/page_io.c~mm-fix-unexpected-zeroed-page-mapping-with-zram-swap
+++ a/mm/page_io.c
@@ -51,54 +51,6 @@ void end_swap_bio_write(struct bio *bio)
bio_put(bio);
}
-static void swap_slot_free_notify(struct page *page)
-{
- struct swap_info_struct *sis;
- struct gendisk *disk;
- swp_entry_t entry;
-
- /*
- * There is no guarantee that the page is in swap cache - the software
- * suspend code (at least) uses end_swap_bio_read() against a non-
- * swapcache page. So we must check PG_swapcache before proceeding with
- * this optimization.
- */
- if (unlikely(!PageSwapCache(page)))
- return;
-
- sis = page_swap_info(page);
- if (data_race(!(sis->flags & SWP_BLKDEV)))
- return;
-
- /*
- * The swap subsystem performs lazy swap slot freeing,
- * expecting that the page will be swapped out again.
- * So we can avoid an unnecessary write if the page
- * isn't redirtied.
- * This is good for real swap storage because we can
- * reduce unnecessary I/O and enhance wear-leveling
- * if an SSD is used as the as swap device.
- * But if in-memory swap device (eg zram) is used,
- * this causes a duplicated copy between uncompressed
- * data in VM-owned memory and compressed data in
- * zram-owned memory. So let's free zram-owned memory
- * and make the VM-owned decompressed page *dirty*,
- * so the page should be swapped out somewhere again if
- * we again wish to reclaim it.
- */
- disk = sis->bdev->bd_disk;
- entry.val = page_private(page);
- if (disk->fops->swap_slot_free_notify && __swap_count(entry) == 1) {
- unsigned long offset;
-
- offset = swp_offset(entry);
-
- SetPageDirty(page);
- disk->fops->swap_slot_free_notify(sis->bdev,
- offset);
- }
-}
-
static void end_swap_bio_read(struct bio *bio)
{
struct page *page = bio_first_page_all(bio);
@@ -114,7 +66,6 @@ static void end_swap_bio_read(struct bio
}
SetPageUptodate(page);
- swap_slot_free_notify(page);
out:
unlock_page(page);
WRITE_ONCE(bio->bi_private, NULL);
@@ -394,11 +345,6 @@ int swap_readpage(struct page *page, boo
if (sis->flags & SWP_SYNCHRONOUS_IO) {
ret = bdev_read_page(sis->bdev, swap_page_sector(page), page);
if (!ret) {
- if (trylock_page(page)) {
- swap_slot_free_notify(page);
- unlock_page(page);
- }
-
count_vm_event(PSWPIN);
goto out;
}
_
Patches currently in -mm which might be from minchan(a)kernel.org are
The patch titled
Subject: mm, page_alloc: fix build_zonerefs_node()
has been removed from the -mm tree. Its filename was
mm-page_alloc-fix-build_zonerefs_node.patch
This patch was dropped because it was merged into mainline or a subsystem tree
------------------------------------------------------
From: Juergen Gross <jgross(a)suse.com>
Subject: mm, page_alloc: fix build_zonerefs_node()
Since commit 6aa303defb74 ("mm, vmscan: only allocate and reclaim from
zones with pages managed by the buddy allocator") only zones with free
memory are included in a built zonelist. This is problematic when e.g.
all memory of a zone has been ballooned out when zonelists are being
rebuilt.
The decision whether to rebuild the zonelists when onlining new memory is
done based on populated_zone() returning 0 for the zone the memory will be
added to. The new zone is added to the zonelists only, if it has free
memory pages (managed_zone() returns a non-zero value) after the memory
has been onlined. This implies, that onlining memory will always free the
added pages to the allocator immediately, but this is not true in all
cases: when e.g. running as a Xen guest the onlined new memory will be
added only to the ballooned memory list, it will be freed only when the
guest is being ballooned up afterwards.
Another problem with using managed_zone() for the decision whether a zone
is being added to the zonelists is, that a zone with all memory used will
in fact be removed from all zonelists in case the zonelists happen to be
rebuilt.
Use populated_zone() when building a zonelist as it has been done before
that commit.
There was a report that QubesOS (based on Xen) is hitting this problem.
Xen has switched to use the zone device functionality in kernel 5.9
and QubesOS wants to use memory hotplugging for guests in order to be
able to start a guest with minimal memory and expand it as needed.
This was the report leading to the patch.
Link: https://lkml.kernel.org/r/20220407120637.9035-1-jgross@suse.com
Fixes: 6aa303defb74 ("mm, vmscan: only allocate and reclaim from zones with pages managed by the buddy allocator")
Signed-off-by: Juergen Gross <jgross(a)suse.com>
Reported-by: Marek Marczykowski-G��recki <marmarek(a)invisiblethingslab.com>
Acked-by: Michal Hocko <mhocko(a)suse.com>
Acked-by: David Hildenbrand <david(a)redhat.com>
Cc: Marek Marczykowski-G��recki <marmarek(a)invisiblethingslab.com>
Reviewed-by: Wei Yang <richard.weiyang(a)gmail.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/page_alloc.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/mm/page_alloc.c~mm-page_alloc-fix-build_zonerefs_node
+++ a/mm/page_alloc.c
@@ -6131,7 +6131,7 @@ static int build_zonerefs_node(pg_data_t
do {
zone_type--;
zone = pgdat->node_zones + zone_type;
- if (managed_zone(zone)) {
+ if (populated_zone(zone)) {
zoneref_set_zone(zone, &zonerefs[nr_zones++]);
check_highest_zone(zone_type);
}
_
Patches currently in -mm which might be from jgross(a)suse.com are
Sticky MCR bits are lost in console restoration if console suspending
has been disabled. This currently affects the AFE bit, which works in
combination with RTS which we set, so we want to make sure the UART
retains control of its FIFO where previously requested. Also specific
drivers may need other bits in the future.
Signed-off-by: Maciej W. Rozycki <macro(a)orcam.me.uk>
Fixes: 4516d50aabed ("serial: 8250: Use canary to restart console after suspend")
Cc: stable(a)vger.kernel.org # v4.0+
---
New change in v4, factored out from 5/5.
---
drivers/tty/serial/8250/8250_port.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
linux-serial-8250-mcr-restore.diff
Index: linux-macro/drivers/tty/serial/8250/8250_port.c
===================================================================
--- linux-macro.orig/drivers/tty/serial/8250/8250_port.c
+++ linux-macro/drivers/tty/serial/8250/8250_port.c
@@ -3308,7 +3308,7 @@ static void serial8250_console_restore(s
serial8250_set_divisor(port, baud, quot, frac);
serial_port_out(port, UART_LCR, up->lcr);
- serial8250_out_MCR(up, UART_MCR_DTR | UART_MCR_RTS);
+ serial8250_out_MCR(up, up->mcr | UART_MCR_DTR | UART_MCR_RTS);
}
/*
Sticky MCR bits are lost in console restoration if console suspending
has been disabled. This currently affects the AFE bit, which works in
combination with RTS which we set, so we want to make sure the UART
retains control of its FIFO where previously requested. Also specific
drivers may need other bits in the future.
Signed-off-by: Maciej W. Rozycki <macro(a)orcam.me.uk>
Fixes: 4516d50aabed ("serial: 8250: Use canary to restart console after suspend")
Cc: stable(a)vger.kernel.org # v4.0+
Reviewed-by: Andy Shevchenko <andy.shevchenko(a)gmail.com>
---
Changes from v4:
- Reorder as 1/5 (from 4/5).
New change in v4, factored out from 5/5.
---
drivers/tty/serial/8250/8250_port.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
linux-serial-8250-mcr-restore.diff
Index: linux-macro/drivers/tty/serial/8250/8250_port.c
===================================================================
--- linux-macro.orig/drivers/tty/serial/8250/8250_port.c
+++ linux-macro/drivers/tty/serial/8250/8250_port.c
@@ -3308,7 +3308,7 @@ static void serial8250_console_restore(s
serial8250_set_divisor(port, baud, quot, frac);
serial_port_out(port, UART_LCR, up->lcr);
- serial8250_out_MCR(up, UART_MCR_DTR | UART_MCR_RTS);
+ serial8250_out_MCR(up, up->mcr | UART_MCR_DTR | UART_MCR_RTS);
}
/*
The patch below does not apply to the 5.17-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From e941976659f1f6834077a1596bf53e6bdb10e90b Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence(a)gmail.com>
Date: Wed, 13 Apr 2022 16:10:33 +0100
Subject: [PATCH] io_uring: use right issue_flags for splice/tee
Pass right issue_flags into into io_file_get_fixed() instead of
IO_URING_F_UNLOCKED. It's probably not a problem at the moment but let's
do it safer.
Fixes: 6bf9c47a3989 ("io_uring: defer file assignment")
Signed-off-by: Pavel Begunkov <asml.silence(a)gmail.com>
Link: https://lore.kernel.org/r/7d242daa9df5d776907686977cd29fbceb4a2d8d.16498625…
Signed-off-by: Jens Axboe <axboe(a)kernel.dk>
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 6b1a98697dcf..3d6cbf77c89d 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -4358,7 +4358,7 @@ static int io_tee(struct io_kiocb *req, unsigned int issue_flags)
return -EAGAIN;
if (sp->flags & SPLICE_F_FD_IN_FIXED)
- in = io_file_get_fixed(req, sp->splice_fd_in, IO_URING_F_UNLOCKED);
+ in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags);
else
in = io_file_get_normal(req, sp->splice_fd_in);
if (!in) {
@@ -4400,7 +4400,7 @@ static int io_splice(struct io_kiocb *req, unsigned int issue_flags)
return -EAGAIN;
if (sp->flags & SPLICE_F_FD_IN_FIXED)
- in = io_file_get_fixed(req, sp->splice_fd_in, IO_URING_F_UNLOCKED);
+ in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags);
else
in = io_file_get_normal(req, sp->splice_fd_in);
if (!in) {
From: Duoming Zhou <duoming(a)zju.edu.cn>
commit 82e31755e55fbcea6a9dfaae5fe4860ade17cbc0 upstream.
There are race conditions that may lead to UAF bugs in
ax25_heartbeat_expiry(), ax25_t1timer_expiry(), ax25_t2timer_expiry(),
ax25_t3timer_expiry() and ax25_idletimer_expiry(), when we call
ax25_release() to deallocate ax25_dev.
One of the UAF bugs caused by ax25_release() is shown below:
(Thread 1) | (Thread 2)
ax25_dev_device_up() //(1) |
... | ax25_kill_by_device()
ax25_bind() //(2) |
ax25_connect() | ...
ax25_std_establish_data_link() |
ax25_start_t1timer() | ax25_dev_device_down() //(3)
mod_timer(&ax25->t1timer,..) |
| ax25_release()
(wait a time) | ...
| ax25_dev_put(ax25_dev) //(4)FREE
ax25_t1timer_expiry() |
ax25->ax25_dev->values[..] //USE| ...
... |
We increase the refcount of ax25_dev in position (1) and (2), and
decrease the refcount of ax25_dev in position (3) and (4).
The ax25_dev will be freed in position (4) and be used in
ax25_t1timer_expiry().
The fail log is shown below:
==============================================================
[ 106.116942] BUG: KASAN: use-after-free in ax25_t1timer_expiry+0x1c/0x60
[ 106.116942] Read of size 8 at addr ffff88800bda9028 by task swapper/0/0
[ 106.116942] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.17.0-06123-g0905eec574
[ 106.116942] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-14
[ 106.116942] Call Trace:
...
[ 106.116942] ax25_t1timer_expiry+0x1c/0x60
[ 106.116942] call_timer_fn+0x122/0x3d0
[ 106.116942] __run_timers.part.0+0x3f6/0x520
[ 106.116942] run_timer_softirq+0x4f/0xb0
[ 106.116942] __do_softirq+0x1c2/0x651
...
This patch adds del_timer_sync() in ax25_release(), which could ensure
that all timers stop before we deallocate ax25_dev.
Signed-off-by: Duoming Zhou <duoming(a)zju.edu.cn>
Signed-off-by: Paolo Abeni <pabeni(a)redhat.com>
Signed-off-by: Ovidiu Panait <ovidiu.panait(a)windriver.com>
---
net/ax25/af_ax25.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index f5686c463bc0..363d47f94532 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1053,6 +1053,11 @@ static int ax25_release(struct socket *sock)
ax25_destroy_socket(ax25);
}
if (ax25_dev) {
+ del_timer_sync(&ax25->timer);
+ del_timer_sync(&ax25->t1timer);
+ del_timer_sync(&ax25->t2timer);
+ del_timer_sync(&ax25->t3timer);
+ del_timer_sync(&ax25->idletimer);
dev_put_track(ax25_dev->dev, &ax25_dev->dev_tracker);
ax25_dev_put(ax25_dev);
}
--
2.25.1
From: Srinivas Pandruvada <srinivas.pandruvada(a)linux.intel.com>
commit 03c83982a0278207709143ba78c5a470179febee upstream.
On systems with overclocking enabled, CPPC Highest Performance can be
hard coded to 0xff. In this case even if we have cores with different
highest performance, ITMT can't be enabled as the current implementation
depends on CPPC Highest Performance.
On such systems we can use MSR_HWP_CAPABILITIES maximum performance field
when CPPC.Highest Performance is 0xff.
Due to legacy reasons, we can't solely depend on MSR_HWP_CAPABILITIES as
in some older systems CPPC Highest Performance is the only way to identify
different performing cores.
Reported-by: Michael Larabel <Michael(a)MichaelLarabel.com>
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada(a)linux.intel.com>
Tested-by: Michael Larabel <Michael(a)MichaelLarabel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com>
Signed-off-by: Dimitri John Ledkov <dimitri.ledkov(a)canonical.com>
---
drivers/cpufreq/intel_pstate.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index e15c3bc17a55..8a2c6b58b652 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -335,6 +335,8 @@ static void intel_pstste_sched_itmt_work_fn(struct work_struct *work)
static DECLARE_WORK(sched_itmt_work, intel_pstste_sched_itmt_work_fn);
+#define CPPC_MAX_PERF U8_MAX
+
static void intel_pstate_set_itmt_prio(int cpu)
{
struct cppc_perf_caps cppc_perf;
@@ -345,6 +347,14 @@ static void intel_pstate_set_itmt_prio(int cpu)
if (ret)
return;
+ /*
+ * On some systems with overclocking enabled, CPPC.highest_perf is hardcoded to 0xff.
+ * In this case we can't use CPPC.highest_perf to enable ITMT.
+ * In this case we can look at MSR_HWP_CAPABILITIES bits [8:0] to decide.
+ */
+ if (cppc_perf.highest_perf == CPPC_MAX_PERF)
+ cppc_perf.highest_perf = HWP_HIGHEST_PERF(READ_ONCE(all_cpu_data[cpu]->hwp_cap_cached));
+
/*
* The priorities can be set regardless of whether or not
* sched_set_itmt_support(true) has been called and it is valid to
--
2.32.0
commit c40160f2998c897231f8454bf797558d30a20375 upstream.
While the latent entropy plugin mostly doesn't derive entropy from
get_random_const() for measuring the call graph, when __latent_entropy is
applied to a constant, then it's initialized statically to output from
get_random_const(). In that case, this data is derived from a 64-bit
seed, which means a buffer of 512 bits doesn't really have that amount
of compile-time entropy.
This patch fixes that shortcoming by just buffering chunks of
/dev/urandom output and doling it out as requested.
At the same time, it's important that we don't break the use of
-frandom-seed, for people who want the runtime benefits of the latent
entropy plugin, while still having compile-time determinism. In that
case, we detect whether gcc's set_random_seed() has been called by
making a call to get_random_seed(noinit=true) in the plugin init
function, which is called after set_random_seed() is called but before
anything that calls get_random_seed(noinit=false), and seeing if it's
zero or not. If it's not zero, we're in deterministic mode, and so we
just generate numbers with a basic xorshift prng.
Note that we don't detect if -frandom-seed is being used using the
documented local_tick variable, because it's assigned via:
local_tick = (unsigned) tv.tv_sec * 1000 + tv.tv_usec / 1000;
which may well overflow and become -1 on its own, and so isn't
reliable: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105171
[kees: The 256 byte rnd_buf size was chosen based on average (250),
median (64), and std deviation (575) bytes of used entropy for a
defconfig x86_64 build]
Fixes: 38addce8b600 ("gcc-plugins: Add latent_entropy plugin")
Cc: stable(a)vger.kernel.org
Cc: PaX Team <pageexec(a)freemail.hu>
Signed-off-by: Jason A. Donenfeld <Jason(a)zx2c4.com>
Signed-off-by: Kees Cook <keescook(a)chromium.org>
Link: https://lore.kernel.org/r/20220405222815.21155-1-Jason@zx2c4.com
Signed-off-by: Jason A. Donenfeld <Jason(a)zx2c4.com>
---
scripts/gcc-plugins/latent_entropy_plugin.c | 44 +++++++++++++--------
1 file changed, 27 insertions(+), 17 deletions(-)
diff --git a/scripts/gcc-plugins/latent_entropy_plugin.c b/scripts/gcc-plugins/latent_entropy_plugin.c
index dff390f692a2..4435263766ac 100644
--- a/scripts/gcc-plugins/latent_entropy_plugin.c
+++ b/scripts/gcc-plugins/latent_entropy_plugin.c
@@ -86,25 +86,31 @@ static struct plugin_info latent_entropy_plugin_info = {
.help = "disable\tturn off latent entropy instrumentation\n",
};
-static unsigned HOST_WIDE_INT seed;
-/*
- * get_random_seed() (this is a GCC function) generates the seed.
- * This is a simple random generator without any cryptographic security because
- * the entropy doesn't come from here.
- */
+static unsigned HOST_WIDE_INT deterministic_seed;
+static unsigned HOST_WIDE_INT rnd_buf[32];
+static size_t rnd_idx = ARRAY_SIZE(rnd_buf);
+static int urandom_fd = -1;
+
static unsigned HOST_WIDE_INT get_random_const(void)
{
- unsigned int i;
- unsigned HOST_WIDE_INT ret = 0;
-
- for (i = 0; i < 8 * sizeof(ret); i++) {
- ret = (ret << 1) | (seed & 1);
- seed >>= 1;
- if (ret & 1)
- seed ^= 0xD800000000000000ULL;
+ if (deterministic_seed) {
+ unsigned HOST_WIDE_INT w = deterministic_seed;
+ w ^= w << 13;
+ w ^= w >> 7;
+ w ^= w << 17;
+ deterministic_seed = w;
+ return deterministic_seed;
}
- return ret;
+ if (urandom_fd < 0) {
+ urandom_fd = open("/dev/urandom", O_RDONLY);
+ gcc_assert(urandom_fd >= 0);
+ }
+ if (rnd_idx >= ARRAY_SIZE(rnd_buf)) {
+ gcc_assert(read(urandom_fd, rnd_buf, sizeof(rnd_buf)) == sizeof(rnd_buf));
+ rnd_idx = 0;
+ }
+ return rnd_buf[rnd_idx++];
}
static tree tree_get_random_const(tree type)
@@ -556,8 +562,6 @@ static void latent_entropy_start_unit(void *gcc_data __unused,
tree type, id;
int quals;
- seed = get_random_seed(false);
-
if (in_lto_p)
return;
@@ -594,6 +598,12 @@ __visible int plugin_init(struct plugin_name_args *plugin_info,
struct register_pass_info latent_entropy_pass_info;
+ /*
+ * Call get_random_seed() with noinit=true, so that this returns
+ * 0 in the case where no seed has been passed via -frandom-seed.
+ */
+ deterministic_seed = get_random_seed(true);
+
latent_entropy_pass_info.pass = make_latent_entropy_pass();
latent_entropy_pass_info.reference_pass_name = "optimized";
latent_entropy_pass_info.ref_pass_instance_number = 1;
--
2.35.1
The patch below does not apply to the 5.17-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 7179c3ce3dbff646c55f7cd664a895f462f049e5 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence(a)gmail.com>
Date: Wed, 13 Apr 2022 16:10:35 +0100
Subject: [PATCH] io_uring: fix poll error reporting
We should not return an error code in req->result in
io_poll_check_events(), because it may get mangled and returned as
success. Just return the error code directly, the callers will fail the
request or proceed accordingly.
Fixes: 6bf9c47a3989 ("io_uring: defer file assignment")
Signed-off-by: Pavel Begunkov <asml.silence(a)gmail.com>
Link: https://lore.kernel.org/r/5f03514ee33324dc811fb93df84aee0f695fb044.16498625…
Signed-off-by: Jens Axboe <axboe(a)kernel.dk>
diff --git a/fs/io_uring.c b/fs/io_uring.c
index d06f1952fdfa..ab674a0d269b 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -5861,9 +5861,8 @@ static int io_poll_check_events(struct io_kiocb *req, bool locked)
unsigned flags = locked ? 0 : IO_URING_F_UNLOCKED;
if (unlikely(!io_assign_file(req, flags)))
- req->result = -EBADF;
- else
- req->result = vfs_poll(req->file, &pt) & req->apoll_events;
+ return -EBADF;
+ req->result = vfs_poll(req->file, &pt) & req->apoll_events;
}
/* multishot, just fill an CQE and proceed */
The patch below does not apply to the 5.17-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From cce64ef01308b677a687d90927fc2b2e0e1cba67 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence(a)gmail.com>
Date: Wed, 13 Apr 2022 16:10:34 +0100
Subject: [PATCH] io_uring: fix poll file assign deadlock
We pass "unlocked" into io_assign_file() in io_poll_check_events(),
which can lead to double locking.
Fixes: 6bf9c47a3989 ("io_uring: defer file assignment")
Signed-off-by: Pavel Begunkov <asml.silence(a)gmail.com>
Link: https://lore.kernel.org/r/2476d4ae46554324b599ee4055447b105f20a75a.16498625…
Signed-off-by: Jens Axboe <axboe(a)kernel.dk>
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 3d6cbf77c89d..d06f1952fdfa 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -5858,8 +5858,9 @@ static int io_poll_check_events(struct io_kiocb *req, bool locked)
if (!req->result) {
struct poll_table_struct pt = { ._key = req->apoll_events };
+ unsigned flags = locked ? 0 : IO_URING_F_UNLOCKED;
- if (unlikely(!io_assign_file(req, IO_URING_F_UNLOCKED)))
+ if (unlikely(!io_assign_file(req, flags)))
req->result = -EBADF;
else
req->result = vfs_poll(req->file, &pt) & req->apoll_events;
The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From a668cc07f990d2ed19424d5c1a529521a9d1cee1 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter(a)intel.com>
Date: Wed, 13 Apr 2022 14:42:32 +0300
Subject: [PATCH] perf tools: Fix segfault accessing sample_id xyarray
perf_evsel::sample_id is an xyarray which can cause a segfault when
accessed beyond its size. e.g.
# perf record -e intel_pt// -C 1 sleep 1
Segmentation fault (core dumped)
#
That is happening because a dummy event is opened to capture text poke
events accross all CPUs, however the mmap logic is allocating according
to the number of user_requested_cpus.
In general, perf sometimes uses the evsel cpus to open events, and
sometimes the evlist user_requested_cpus. However, it is not necessary
to determine which case is which because the opened event file
descriptors are also in an xyarray, the size of whch can be used
to correctly allocate the size of the sample_id xyarray, because there
is one ID per file descriptor.
Note, in the affected code path, perf_evsel fd array is subsequently
used to get the file descriptor for the mmap, so it makes sense for the
xyarrays to be the same size there.
Fixes: d1a177595b3a824c ("libperf: Adopt perf_evlist__mmap()/munmap() from tools/perf")
Fixes: 246eba8e9041c477 ("perf tools: Add support for PERF_RECORD_TEXT_POKE")
Signed-off-by: Adrian Hunter <adrian.hunter(a)intel.com>
Acked-by: Ian Rogers <irogers(a)google.com>
Cc: Adrian Hunter <adrian.hunter(a)intel.com>
Cc: Jiri Olsa <jolsa(a)kernel.org>
Cc: stable(a)vger.kernel.org # 5.5+
Link: https://lore.kernel.org/r/20220413114232.26914-1-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com>
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 1b15ba13c477..a09315538a30 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -577,7 +577,6 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
{
struct perf_evsel *evsel;
const struct perf_cpu_map *cpus = evlist->user_requested_cpus;
- const struct perf_thread_map *threads = evlist->threads;
if (!ops || !ops->get || !ops->mmap)
return -EINVAL;
@@ -589,7 +588,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
perf_evlist__for_each_entry(evlist, evsel) {
if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
evsel->sample_id == NULL &&
- perf_evsel__alloc_id(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0)
+ perf_evsel__alloc_id(evsel, evsel->fd->max_x, evsel->fd->max_y) < 0)
return -ENOMEM;
}
The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From a668cc07f990d2ed19424d5c1a529521a9d1cee1 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter(a)intel.com>
Date: Wed, 13 Apr 2022 14:42:32 +0300
Subject: [PATCH] perf tools: Fix segfault accessing sample_id xyarray
perf_evsel::sample_id is an xyarray which can cause a segfault when
accessed beyond its size. e.g.
# perf record -e intel_pt// -C 1 sleep 1
Segmentation fault (core dumped)
#
That is happening because a dummy event is opened to capture text poke
events accross all CPUs, however the mmap logic is allocating according
to the number of user_requested_cpus.
In general, perf sometimes uses the evsel cpus to open events, and
sometimes the evlist user_requested_cpus. However, it is not necessary
to determine which case is which because the opened event file
descriptors are also in an xyarray, the size of whch can be used
to correctly allocate the size of the sample_id xyarray, because there
is one ID per file descriptor.
Note, in the affected code path, perf_evsel fd array is subsequently
used to get the file descriptor for the mmap, so it makes sense for the
xyarrays to be the same size there.
Fixes: d1a177595b3a824c ("libperf: Adopt perf_evlist__mmap()/munmap() from tools/perf")
Fixes: 246eba8e9041c477 ("perf tools: Add support for PERF_RECORD_TEXT_POKE")
Signed-off-by: Adrian Hunter <adrian.hunter(a)intel.com>
Acked-by: Ian Rogers <irogers(a)google.com>
Cc: Adrian Hunter <adrian.hunter(a)intel.com>
Cc: Jiri Olsa <jolsa(a)kernel.org>
Cc: stable(a)vger.kernel.org # 5.5+
Link: https://lore.kernel.org/r/20220413114232.26914-1-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com>
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 1b15ba13c477..a09315538a30 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -577,7 +577,6 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
{
struct perf_evsel *evsel;
const struct perf_cpu_map *cpus = evlist->user_requested_cpus;
- const struct perf_thread_map *threads = evlist->threads;
if (!ops || !ops->get || !ops->mmap)
return -EINVAL;
@@ -589,7 +588,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
perf_evlist__for_each_entry(evlist, evsel) {
if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
evsel->sample_id == NULL &&
- perf_evsel__alloc_id(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0)
+ perf_evsel__alloc_id(evsel, evsel->fd->max_x, evsel->fd->max_y) < 0)
return -ENOMEM;
}
The patch below does not apply to the 5.17-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From a668cc07f990d2ed19424d5c1a529521a9d1cee1 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter(a)intel.com>
Date: Wed, 13 Apr 2022 14:42:32 +0300
Subject: [PATCH] perf tools: Fix segfault accessing sample_id xyarray
perf_evsel::sample_id is an xyarray which can cause a segfault when
accessed beyond its size. e.g.
# perf record -e intel_pt// -C 1 sleep 1
Segmentation fault (core dumped)
#
That is happening because a dummy event is opened to capture text poke
events accross all CPUs, however the mmap logic is allocating according
to the number of user_requested_cpus.
In general, perf sometimes uses the evsel cpus to open events, and
sometimes the evlist user_requested_cpus. However, it is not necessary
to determine which case is which because the opened event file
descriptors are also in an xyarray, the size of whch can be used
to correctly allocate the size of the sample_id xyarray, because there
is one ID per file descriptor.
Note, in the affected code path, perf_evsel fd array is subsequently
used to get the file descriptor for the mmap, so it makes sense for the
xyarrays to be the same size there.
Fixes: d1a177595b3a824c ("libperf: Adopt perf_evlist__mmap()/munmap() from tools/perf")
Fixes: 246eba8e9041c477 ("perf tools: Add support for PERF_RECORD_TEXT_POKE")
Signed-off-by: Adrian Hunter <adrian.hunter(a)intel.com>
Acked-by: Ian Rogers <irogers(a)google.com>
Cc: Adrian Hunter <adrian.hunter(a)intel.com>
Cc: Jiri Olsa <jolsa(a)kernel.org>
Cc: stable(a)vger.kernel.org # 5.5+
Link: https://lore.kernel.org/r/20220413114232.26914-1-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com>
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 1b15ba13c477..a09315538a30 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -577,7 +577,6 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
{
struct perf_evsel *evsel;
const struct perf_cpu_map *cpus = evlist->user_requested_cpus;
- const struct perf_thread_map *threads = evlist->threads;
if (!ops || !ops->get || !ops->mmap)
return -EINVAL;
@@ -589,7 +588,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
perf_evlist__for_each_entry(evlist, evsel) {
if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
evsel->sample_id == NULL &&
- perf_evsel__alloc_id(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0)
+ perf_evsel__alloc_id(evsel, evsel->fd->max_x, evsel->fd->max_y) < 0)
return -ENOMEM;
}
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 993eb48fa199b5f476df8204e652eff63dd19361 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com>
Date: Mon, 11 Apr 2022 21:07:51 +0300
Subject: [PATCH] i2c: dev: check return value when calling dev_set_name()
If dev_set_name() fails, the dev_name() is null, check the return
value of dev_set_name() to avoid the null-ptr-deref.
Fixes: 1413ef638aba ("i2c: dev: Fix the race between the release of i2c_dev and cdev")
Signed-off-by: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com>
Signed-off-by: Wolfram Sang <wsa(a)kernel.org>
diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c
index cf5d049342ea..6fd2b6718b08 100644
--- a/drivers/i2c/i2c-dev.c
+++ b/drivers/i2c/i2c-dev.c
@@ -668,16 +668,21 @@ static int i2cdev_attach_adapter(struct device *dev, void *dummy)
i2c_dev->dev.class = i2c_dev_class;
i2c_dev->dev.parent = &adap->dev;
i2c_dev->dev.release = i2cdev_dev_release;
- dev_set_name(&i2c_dev->dev, "i2c-%d", adap->nr);
+
+ res = dev_set_name(&i2c_dev->dev, "i2c-%d", adap->nr);
+ if (res)
+ goto err_put_i2c_dev;
res = cdev_device_add(&i2c_dev->cdev, &i2c_dev->dev);
- if (res) {
- put_i2c_dev(i2c_dev, false);
- return res;
- }
+ if (res)
+ goto err_put_i2c_dev;
pr_debug("adapter [%s] registered as minor %d\n", adap->name, adap->nr);
return 0;
+
+err_put_i2c_dev:
+ put_i2c_dev(i2c_dev, false);
+ return res;
}
static int i2cdev_detach_adapter(struct device *dev, void *dummy)
The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 993eb48fa199b5f476df8204e652eff63dd19361 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com>
Date: Mon, 11 Apr 2022 21:07:51 +0300
Subject: [PATCH] i2c: dev: check return value when calling dev_set_name()
If dev_set_name() fails, the dev_name() is null, check the return
value of dev_set_name() to avoid the null-ptr-deref.
Fixes: 1413ef638aba ("i2c: dev: Fix the race between the release of i2c_dev and cdev")
Signed-off-by: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com>
Signed-off-by: Wolfram Sang <wsa(a)kernel.org>
diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c
index cf5d049342ea..6fd2b6718b08 100644
--- a/drivers/i2c/i2c-dev.c
+++ b/drivers/i2c/i2c-dev.c
@@ -668,16 +668,21 @@ static int i2cdev_attach_adapter(struct device *dev, void *dummy)
i2c_dev->dev.class = i2c_dev_class;
i2c_dev->dev.parent = &adap->dev;
i2c_dev->dev.release = i2cdev_dev_release;
- dev_set_name(&i2c_dev->dev, "i2c-%d", adap->nr);
+
+ res = dev_set_name(&i2c_dev->dev, "i2c-%d", adap->nr);
+ if (res)
+ goto err_put_i2c_dev;
res = cdev_device_add(&i2c_dev->cdev, &i2c_dev->dev);
- if (res) {
- put_i2c_dev(i2c_dev, false);
- return res;
- }
+ if (res)
+ goto err_put_i2c_dev;
pr_debug("adapter [%s] registered as minor %d\n", adap->name, adap->nr);
return 0;
+
+err_put_i2c_dev:
+ put_i2c_dev(i2c_dev, false);
+ return res;
}
static int i2cdev_detach_adapter(struct device *dev, void *dummy)
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 993eb48fa199b5f476df8204e652eff63dd19361 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com>
Date: Mon, 11 Apr 2022 21:07:51 +0300
Subject: [PATCH] i2c: dev: check return value when calling dev_set_name()
If dev_set_name() fails, the dev_name() is null, check the return
value of dev_set_name() to avoid the null-ptr-deref.
Fixes: 1413ef638aba ("i2c: dev: Fix the race between the release of i2c_dev and cdev")
Signed-off-by: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com>
Signed-off-by: Wolfram Sang <wsa(a)kernel.org>
diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c
index cf5d049342ea..6fd2b6718b08 100644
--- a/drivers/i2c/i2c-dev.c
+++ b/drivers/i2c/i2c-dev.c
@@ -668,16 +668,21 @@ static int i2cdev_attach_adapter(struct device *dev, void *dummy)
i2c_dev->dev.class = i2c_dev_class;
i2c_dev->dev.parent = &adap->dev;
i2c_dev->dev.release = i2cdev_dev_release;
- dev_set_name(&i2c_dev->dev, "i2c-%d", adap->nr);
+
+ res = dev_set_name(&i2c_dev->dev, "i2c-%d", adap->nr);
+ if (res)
+ goto err_put_i2c_dev;
res = cdev_device_add(&i2c_dev->cdev, &i2c_dev->dev);
- if (res) {
- put_i2c_dev(i2c_dev, false);
- return res;
- }
+ if (res)
+ goto err_put_i2c_dev;
pr_debug("adapter [%s] registered as minor %d\n", adap->name, adap->nr);
return 0;
+
+err_put_i2c_dev:
+ put_i2c_dev(i2c_dev, false);
+ return res;
}
static int i2cdev_detach_adapter(struct device *dev, void *dummy)
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 993eb48fa199b5f476df8204e652eff63dd19361 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com>
Date: Mon, 11 Apr 2022 21:07:51 +0300
Subject: [PATCH] i2c: dev: check return value when calling dev_set_name()
If dev_set_name() fails, the dev_name() is null, check the return
value of dev_set_name() to avoid the null-ptr-deref.
Fixes: 1413ef638aba ("i2c: dev: Fix the race between the release of i2c_dev and cdev")
Signed-off-by: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com>
Signed-off-by: Wolfram Sang <wsa(a)kernel.org>
diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c
index cf5d049342ea..6fd2b6718b08 100644
--- a/drivers/i2c/i2c-dev.c
+++ b/drivers/i2c/i2c-dev.c
@@ -668,16 +668,21 @@ static int i2cdev_attach_adapter(struct device *dev, void *dummy)
i2c_dev->dev.class = i2c_dev_class;
i2c_dev->dev.parent = &adap->dev;
i2c_dev->dev.release = i2cdev_dev_release;
- dev_set_name(&i2c_dev->dev, "i2c-%d", adap->nr);
+
+ res = dev_set_name(&i2c_dev->dev, "i2c-%d", adap->nr);
+ if (res)
+ goto err_put_i2c_dev;
res = cdev_device_add(&i2c_dev->cdev, &i2c_dev->dev);
- if (res) {
- put_i2c_dev(i2c_dev, false);
- return res;
- }
+ if (res)
+ goto err_put_i2c_dev;
pr_debug("adapter [%s] registered as minor %d\n", adap->name, adap->nr);
return 0;
+
+err_put_i2c_dev:
+ put_i2c_dev(i2c_dev, false);
+ return res;
}
static int i2cdev_detach_adapter(struct device *dev, void *dummy)
The patch below does not apply to the 4.9-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 993eb48fa199b5f476df8204e652eff63dd19361 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com>
Date: Mon, 11 Apr 2022 21:07:51 +0300
Subject: [PATCH] i2c: dev: check return value when calling dev_set_name()
If dev_set_name() fails, the dev_name() is null, check the return
value of dev_set_name() to avoid the null-ptr-deref.
Fixes: 1413ef638aba ("i2c: dev: Fix the race between the release of i2c_dev and cdev")
Signed-off-by: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com>
Signed-off-by: Wolfram Sang <wsa(a)kernel.org>
diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c
index cf5d049342ea..6fd2b6718b08 100644
--- a/drivers/i2c/i2c-dev.c
+++ b/drivers/i2c/i2c-dev.c
@@ -668,16 +668,21 @@ static int i2cdev_attach_adapter(struct device *dev, void *dummy)
i2c_dev->dev.class = i2c_dev_class;
i2c_dev->dev.parent = &adap->dev;
i2c_dev->dev.release = i2cdev_dev_release;
- dev_set_name(&i2c_dev->dev, "i2c-%d", adap->nr);
+
+ res = dev_set_name(&i2c_dev->dev, "i2c-%d", adap->nr);
+ if (res)
+ goto err_put_i2c_dev;
res = cdev_device_add(&i2c_dev->cdev, &i2c_dev->dev);
- if (res) {
- put_i2c_dev(i2c_dev, false);
- return res;
- }
+ if (res)
+ goto err_put_i2c_dev;
pr_debug("adapter [%s] registered as minor %d\n", adap->name, adap->nr);
return 0;
+
+err_put_i2c_dev:
+ put_i2c_dev(i2c_dev, false);
+ return res;
}
static int i2cdev_detach_adapter(struct device *dev, void *dummy)
The patch below does not apply to the 4.9-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From c40160f2998c897231f8454bf797558d30a20375 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason(a)zx2c4.com>
Date: Wed, 6 Apr 2022 00:28:15 +0200
Subject: [PATCH] gcc-plugins: latent_entropy: use /dev/urandom
While the latent entropy plugin mostly doesn't derive entropy from
get_random_const() for measuring the call graph, when __latent_entropy is
applied to a constant, then it's initialized statically to output from
get_random_const(). In that case, this data is derived from a 64-bit
seed, which means a buffer of 512 bits doesn't really have that amount
of compile-time entropy.
This patch fixes that shortcoming by just buffering chunks of
/dev/urandom output and doling it out as requested.
At the same time, it's important that we don't break the use of
-frandom-seed, for people who want the runtime benefits of the latent
entropy plugin, while still having compile-time determinism. In that
case, we detect whether gcc's set_random_seed() has been called by
making a call to get_random_seed(noinit=true) in the plugin init
function, which is called after set_random_seed() is called but before
anything that calls get_random_seed(noinit=false), and seeing if it's
zero or not. If it's not zero, we're in deterministic mode, and so we
just generate numbers with a basic xorshift prng.
Note that we don't detect if -frandom-seed is being used using the
documented local_tick variable, because it's assigned via:
local_tick = (unsigned) tv.tv_sec * 1000 + tv.tv_usec / 1000;
which may well overflow and become -1 on its own, and so isn't
reliable: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105171
[kees: The 256 byte rnd_buf size was chosen based on average (250),
median (64), and std deviation (575) bytes of used entropy for a
defconfig x86_64 build]
Fixes: 38addce8b600 ("gcc-plugins: Add latent_entropy plugin")
Cc: stable(a)vger.kernel.org
Cc: PaX Team <pageexec(a)freemail.hu>
Signed-off-by: Jason A. Donenfeld <Jason(a)zx2c4.com>
Signed-off-by: Kees Cook <keescook(a)chromium.org>
Link: https://lore.kernel.org/r/20220405222815.21155-1-Jason@zx2c4.com
diff --git a/scripts/gcc-plugins/latent_entropy_plugin.c b/scripts/gcc-plugins/latent_entropy_plugin.c
index 589454bce930..8425da41de0d 100644
--- a/scripts/gcc-plugins/latent_entropy_plugin.c
+++ b/scripts/gcc-plugins/latent_entropy_plugin.c
@@ -86,25 +86,31 @@ static struct plugin_info latent_entropy_plugin_info = {
.help = "disable\tturn off latent entropy instrumentation\n",
};
-static unsigned HOST_WIDE_INT seed;
-/*
- * get_random_seed() (this is a GCC function) generates the seed.
- * This is a simple random generator without any cryptographic security because
- * the entropy doesn't come from here.
- */
+static unsigned HOST_WIDE_INT deterministic_seed;
+static unsigned HOST_WIDE_INT rnd_buf[32];
+static size_t rnd_idx = ARRAY_SIZE(rnd_buf);
+static int urandom_fd = -1;
+
static unsigned HOST_WIDE_INT get_random_const(void)
{
- unsigned int i;
- unsigned HOST_WIDE_INT ret = 0;
-
- for (i = 0; i < 8 * sizeof(ret); i++) {
- ret = (ret << 1) | (seed & 1);
- seed >>= 1;
- if (ret & 1)
- seed ^= 0xD800000000000000ULL;
+ if (deterministic_seed) {
+ unsigned HOST_WIDE_INT w = deterministic_seed;
+ w ^= w << 13;
+ w ^= w >> 7;
+ w ^= w << 17;
+ deterministic_seed = w;
+ return deterministic_seed;
}
- return ret;
+ if (urandom_fd < 0) {
+ urandom_fd = open("/dev/urandom", O_RDONLY);
+ gcc_assert(urandom_fd >= 0);
+ }
+ if (rnd_idx >= ARRAY_SIZE(rnd_buf)) {
+ gcc_assert(read(urandom_fd, rnd_buf, sizeof(rnd_buf)) == sizeof(rnd_buf));
+ rnd_idx = 0;
+ }
+ return rnd_buf[rnd_idx++];
}
static tree tree_get_random_const(tree type)
@@ -537,8 +543,6 @@ static void latent_entropy_start_unit(void *gcc_data __unused,
tree type, id;
int quals;
- seed = get_random_seed(false);
-
if (in_lto_p)
return;
@@ -573,6 +577,12 @@ __visible int plugin_init(struct plugin_name_args *plugin_info,
const struct plugin_argument * const argv = plugin_info->argv;
int i;
+ /*
+ * Call get_random_seed() with noinit=true, so that this returns
+ * 0 in the case where no seed has been passed via -frandom-seed.
+ */
+ deterministic_seed = get_random_seed(true);
+
static const struct ggc_root_tab gt_ggc_r_gt_latent_entropy[] = {
{
.base = &latent_entropy_decl,
The patch below does not apply to the 4.9-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 6624bb34b4eb19f715db9908cca00122748765d7 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg(a)intel.com>
Date: Mon, 11 Apr 2022 11:42:03 +0200
Subject: [PATCH] nl80211: correctly check NL80211_ATTR_REG_ALPHA2 size
We need this to be at least two bytes, so we can access
alpha2[0] and alpha2[1]. It may be three in case some
userspace used NUL-termination since it was NLA_STRING
(and we also push it out with NUL-termination).
Cc: stable(a)vger.kernel.org
Reported-by: Lee Jones <lee.jones(a)linaro.org>
Link: https://lore.kernel.org/r/20220411114201.fd4a31f06541.Ie7ff4be2cf348d8cc28e…
Signed-off-by: Johannes Berg <johannes.berg(a)intel.com>
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index ee1c2b6b6971..21e808fcb676 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -528,7 +528,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
.len = IEEE80211_MAX_MESH_ID_LEN },
[NL80211_ATTR_MPATH_NEXT_HOP] = NLA_POLICY_ETH_ADDR_COMPAT,
- [NL80211_ATTR_REG_ALPHA2] = { .type = NLA_STRING, .len = 2 },
+ /* allow 3 for NUL-termination, we used to declare this NLA_STRING */
+ [NL80211_ATTR_REG_ALPHA2] = NLA_POLICY_RANGE(NLA_BINARY, 2, 3),
[NL80211_ATTR_REG_RULES] = { .type = NLA_NESTED },
[NL80211_ATTR_BSS_CTS_PROT] = { .type = NLA_U8 },
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 6624bb34b4eb19f715db9908cca00122748765d7 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg(a)intel.com>
Date: Mon, 11 Apr 2022 11:42:03 +0200
Subject: [PATCH] nl80211: correctly check NL80211_ATTR_REG_ALPHA2 size
We need this to be at least two bytes, so we can access
alpha2[0] and alpha2[1]. It may be three in case some
userspace used NUL-termination since it was NLA_STRING
(and we also push it out with NUL-termination).
Cc: stable(a)vger.kernel.org
Reported-by: Lee Jones <lee.jones(a)linaro.org>
Link: https://lore.kernel.org/r/20220411114201.fd4a31f06541.Ie7ff4be2cf348d8cc28e…
Signed-off-by: Johannes Berg <johannes.berg(a)intel.com>
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index ee1c2b6b6971..21e808fcb676 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -528,7 +528,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
.len = IEEE80211_MAX_MESH_ID_LEN },
[NL80211_ATTR_MPATH_NEXT_HOP] = NLA_POLICY_ETH_ADDR_COMPAT,
- [NL80211_ATTR_REG_ALPHA2] = { .type = NLA_STRING, .len = 2 },
+ /* allow 3 for NUL-termination, we used to declare this NLA_STRING */
+ [NL80211_ATTR_REG_ALPHA2] = NLA_POLICY_RANGE(NLA_BINARY, 2, 3),
[NL80211_ATTR_REG_RULES] = { .type = NLA_NESTED },
[NL80211_ATTR_BSS_CTS_PROT] = { .type = NLA_U8 },
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 6624bb34b4eb19f715db9908cca00122748765d7 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg(a)intel.com>
Date: Mon, 11 Apr 2022 11:42:03 +0200
Subject: [PATCH] nl80211: correctly check NL80211_ATTR_REG_ALPHA2 size
We need this to be at least two bytes, so we can access
alpha2[0] and alpha2[1]. It may be three in case some
userspace used NUL-termination since it was NLA_STRING
(and we also push it out with NUL-termination).
Cc: stable(a)vger.kernel.org
Reported-by: Lee Jones <lee.jones(a)linaro.org>
Link: https://lore.kernel.org/r/20220411114201.fd4a31f06541.Ie7ff4be2cf348d8cc28e…
Signed-off-by: Johannes Berg <johannes.berg(a)intel.com>
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index ee1c2b6b6971..21e808fcb676 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -528,7 +528,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
.len = IEEE80211_MAX_MESH_ID_LEN },
[NL80211_ATTR_MPATH_NEXT_HOP] = NLA_POLICY_ETH_ADDR_COMPAT,
- [NL80211_ATTR_REG_ALPHA2] = { .type = NLA_STRING, .len = 2 },
+ /* allow 3 for NUL-termination, we used to declare this NLA_STRING */
+ [NL80211_ATTR_REG_ALPHA2] = NLA_POLICY_RANGE(NLA_BINARY, 2, 3),
[NL80211_ATTR_REG_RULES] = { .type = NLA_NESTED },
[NL80211_ATTR_BSS_CTS_PROT] = { .type = NLA_U8 },
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 6624bb34b4eb19f715db9908cca00122748765d7 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg(a)intel.com>
Date: Mon, 11 Apr 2022 11:42:03 +0200
Subject: [PATCH] nl80211: correctly check NL80211_ATTR_REG_ALPHA2 size
We need this to be at least two bytes, so we can access
alpha2[0] and alpha2[1]. It may be three in case some
userspace used NUL-termination since it was NLA_STRING
(and we also push it out with NUL-termination).
Cc: stable(a)vger.kernel.org
Reported-by: Lee Jones <lee.jones(a)linaro.org>
Link: https://lore.kernel.org/r/20220411114201.fd4a31f06541.Ie7ff4be2cf348d8cc28e…
Signed-off-by: Johannes Berg <johannes.berg(a)intel.com>
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index ee1c2b6b6971..21e808fcb676 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -528,7 +528,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
.len = IEEE80211_MAX_MESH_ID_LEN },
[NL80211_ATTR_MPATH_NEXT_HOP] = NLA_POLICY_ETH_ADDR_COMPAT,
- [NL80211_ATTR_REG_ALPHA2] = { .type = NLA_STRING, .len = 2 },
+ /* allow 3 for NUL-termination, we used to declare this NLA_STRING */
+ [NL80211_ATTR_REG_ALPHA2] = NLA_POLICY_RANGE(NLA_BINARY, 2, 3),
[NL80211_ATTR_REG_RULES] = { .type = NLA_NESTED },
[NL80211_ATTR_BSS_CTS_PROT] = { .type = NLA_U8 },
The patch below does not apply to the 5.10-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From a668cc07f990d2ed19424d5c1a529521a9d1cee1 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter(a)intel.com>
Date: Wed, 13 Apr 2022 14:42:32 +0300
Subject: [PATCH] perf tools: Fix segfault accessing sample_id xyarray
perf_evsel::sample_id is an xyarray which can cause a segfault when
accessed beyond its size. e.g.
# perf record -e intel_pt// -C 1 sleep 1
Segmentation fault (core dumped)
#
That is happening because a dummy event is opened to capture text poke
events accross all CPUs, however the mmap logic is allocating according
to the number of user_requested_cpus.
In general, perf sometimes uses the evsel cpus to open events, and
sometimes the evlist user_requested_cpus. However, it is not necessary
to determine which case is which because the opened event file
descriptors are also in an xyarray, the size of whch can be used
to correctly allocate the size of the sample_id xyarray, because there
is one ID per file descriptor.
Note, in the affected code path, perf_evsel fd array is subsequently
used to get the file descriptor for the mmap, so it makes sense for the
xyarrays to be the same size there.
Fixes: d1a177595b3a824c ("libperf: Adopt perf_evlist__mmap()/munmap() from tools/perf")
Fixes: 246eba8e9041c477 ("perf tools: Add support for PERF_RECORD_TEXT_POKE")
Signed-off-by: Adrian Hunter <adrian.hunter(a)intel.com>
Acked-by: Ian Rogers <irogers(a)google.com>
Cc: Adrian Hunter <adrian.hunter(a)intel.com>
Cc: Jiri Olsa <jolsa(a)kernel.org>
Cc: stable(a)vger.kernel.org # 5.5+
Link: https://lore.kernel.org/r/20220413114232.26914-1-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com>
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 1b15ba13c477..a09315538a30 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -577,7 +577,6 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
{
struct perf_evsel *evsel;
const struct perf_cpu_map *cpus = evlist->user_requested_cpus;
- const struct perf_thread_map *threads = evlist->threads;
if (!ops || !ops->get || !ops->mmap)
return -EINVAL;
@@ -589,7 +588,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
perf_evlist__for_each_entry(evlist, evsel) {
if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
evsel->sample_id == NULL &&
- perf_evsel__alloc_id(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0)
+ perf_evsel__alloc_id(evsel, evsel->fd->max_x, evsel->fd->max_y) < 0)
return -ENOMEM;
}
The patch below does not apply to the 5.17-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From a668cc07f990d2ed19424d5c1a529521a9d1cee1 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter(a)intel.com>
Date: Wed, 13 Apr 2022 14:42:32 +0300
Subject: [PATCH] perf tools: Fix segfault accessing sample_id xyarray
perf_evsel::sample_id is an xyarray which can cause a segfault when
accessed beyond its size. e.g.
# perf record -e intel_pt// -C 1 sleep 1
Segmentation fault (core dumped)
#
That is happening because a dummy event is opened to capture text poke
events accross all CPUs, however the mmap logic is allocating according
to the number of user_requested_cpus.
In general, perf sometimes uses the evsel cpus to open events, and
sometimes the evlist user_requested_cpus. However, it is not necessary
to determine which case is which because the opened event file
descriptors are also in an xyarray, the size of whch can be used
to correctly allocate the size of the sample_id xyarray, because there
is one ID per file descriptor.
Note, in the affected code path, perf_evsel fd array is subsequently
used to get the file descriptor for the mmap, so it makes sense for the
xyarrays to be the same size there.
Fixes: d1a177595b3a824c ("libperf: Adopt perf_evlist__mmap()/munmap() from tools/perf")
Fixes: 246eba8e9041c477 ("perf tools: Add support for PERF_RECORD_TEXT_POKE")
Signed-off-by: Adrian Hunter <adrian.hunter(a)intel.com>
Acked-by: Ian Rogers <irogers(a)google.com>
Cc: Adrian Hunter <adrian.hunter(a)intel.com>
Cc: Jiri Olsa <jolsa(a)kernel.org>
Cc: stable(a)vger.kernel.org # 5.5+
Link: https://lore.kernel.org/r/20220413114232.26914-1-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com>
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 1b15ba13c477..a09315538a30 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -577,7 +577,6 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
{
struct perf_evsel *evsel;
const struct perf_cpu_map *cpus = evlist->user_requested_cpus;
- const struct perf_thread_map *threads = evlist->threads;
if (!ops || !ops->get || !ops->mmap)
return -EINVAL;
@@ -589,7 +588,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
perf_evlist__for_each_entry(evlist, evsel) {
if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
evsel->sample_id == NULL &&
- perf_evsel__alloc_id(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0)
+ perf_evsel__alloc_id(evsel, evsel->fd->max_x, evsel->fd->max_y) < 0)
return -ENOMEM;
}
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 08d835dff916bfe8f45acc7b92c7af6c4081c8a7 Mon Sep 17 00:00:00 2001
From: Rei Yamamoto <yamamoto.rei(a)jp.fujitsu.com>
Date: Thu, 31 Mar 2022 09:33:09 +0900
Subject: [PATCH] genirq/affinity: Consider that CPUs on nodes can be
unbalanced
If CPUs on a node are offline at boot time, the number of nodes is
different when building affinity masks for present cpus and when building
affinity masks for possible cpus. This causes the following problem:
In the case that the number of vectors is less than the number of nodes
there are cases where bits of masks for present cpus are overwritten when
building masks for possible cpus.
Fix this by excluding CPUs, which are not part of the current build mask
(present/possible).
[ tglx: Massaged changelog and added comment ]
Fixes: b82592199032 ("genirq/affinity: Spread IRQs to all available NUMA nodes")
Signed-off-by: Rei Yamamoto <yamamoto.rei(a)jp.fujitsu.com>
Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de>
Reviewed-by: Ming Lei <ming.lei(a)redhat.com>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20220331003309.10891-1-yamamoto.rei@jp.fujitsu.com
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index f7ff8919dc9b..fdf170404650 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -269,8 +269,9 @@ static int __irq_build_affinity_masks(unsigned int startvec,
*/
if (numvecs <= nodes) {
for_each_node_mask(n, nodemsk) {
- cpumask_or(&masks[curvec].mask, &masks[curvec].mask,
- node_to_cpumask[n]);
+ /* Ensure that only CPUs which are in both masks are set */
+ cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]);
+ cpumask_or(&masks[curvec].mask, &masks[curvec].mask, nmsk);
if (++curvec == last_affv)
curvec = firstvec;
}
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From a690e5f2db4d1dca742ce734aaff9f3112d63764 Mon Sep 17 00:00:00 2001
From: Naohiro Aota <naohiro.aota(a)wdc.com>
Date: Tue, 29 Mar 2022 15:55:58 +0900
Subject: [PATCH] btrfs: mark resumed async balance as writing
When btrfs balance is interrupted with umount, the background balance
resumes on the next mount. There is a potential deadlock with FS freezing
here like as described in commit 26559780b953 ("btrfs: zoned: mark
relocation as writing"). Mark the process as sb_writing to avoid it.
Reviewed-by: Filipe Manana <fdmanana(a)suse.com>
CC: stable(a)vger.kernel.org # 4.9+
Signed-off-by: Naohiro Aota <naohiro.aota(a)wdc.com>
Reviewed-by: David Sterba <dsterba(a)suse.com>
Signed-off-by: David Sterba <dsterba(a)suse.com>
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 2cfbc74a3b4e..a8cc736731fd 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4430,10 +4430,12 @@ static int balance_kthread(void *data)
struct btrfs_fs_info *fs_info = data;
int ret = 0;
+ sb_start_write(fs_info->sb);
mutex_lock(&fs_info->balance_mutex);
if (fs_info->balance_ctl)
ret = btrfs_balance(fs_info, fs_info->balance_ctl, NULL);
mutex_unlock(&fs_info->balance_mutex);
+ sb_end_write(fs_info->sb);
return ret;
}
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From a690e5f2db4d1dca742ce734aaff9f3112d63764 Mon Sep 17 00:00:00 2001
From: Naohiro Aota <naohiro.aota(a)wdc.com>
Date: Tue, 29 Mar 2022 15:55:58 +0900
Subject: [PATCH] btrfs: mark resumed async balance as writing
When btrfs balance is interrupted with umount, the background balance
resumes on the next mount. There is a potential deadlock with FS freezing
here like as described in commit 26559780b953 ("btrfs: zoned: mark
relocation as writing"). Mark the process as sb_writing to avoid it.
Reviewed-by: Filipe Manana <fdmanana(a)suse.com>
CC: stable(a)vger.kernel.org # 4.9+
Signed-off-by: Naohiro Aota <naohiro.aota(a)wdc.com>
Reviewed-by: David Sterba <dsterba(a)suse.com>
Signed-off-by: David Sterba <dsterba(a)suse.com>
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 2cfbc74a3b4e..a8cc736731fd 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4430,10 +4430,12 @@ static int balance_kthread(void *data)
struct btrfs_fs_info *fs_info = data;
int ret = 0;
+ sb_start_write(fs_info->sb);
mutex_lock(&fs_info->balance_mutex);
if (fs_info->balance_ctl)
ret = btrfs_balance(fs_info, fs_info->balance_ctl, NULL);
mutex_unlock(&fs_info->balance_mutex);
+ sb_end_write(fs_info->sb);
return ret;
}
The patch below does not apply to the 4.9-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From a690e5f2db4d1dca742ce734aaff9f3112d63764 Mon Sep 17 00:00:00 2001
From: Naohiro Aota <naohiro.aota(a)wdc.com>
Date: Tue, 29 Mar 2022 15:55:58 +0900
Subject: [PATCH] btrfs: mark resumed async balance as writing
When btrfs balance is interrupted with umount, the background balance
resumes on the next mount. There is a potential deadlock with FS freezing
here like as described in commit 26559780b953 ("btrfs: zoned: mark
relocation as writing"). Mark the process as sb_writing to avoid it.
Reviewed-by: Filipe Manana <fdmanana(a)suse.com>
CC: stable(a)vger.kernel.org # 4.9+
Signed-off-by: Naohiro Aota <naohiro.aota(a)wdc.com>
Reviewed-by: David Sterba <dsterba(a)suse.com>
Signed-off-by: David Sterba <dsterba(a)suse.com>
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 2cfbc74a3b4e..a8cc736731fd 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4430,10 +4430,12 @@ static int balance_kthread(void *data)
struct btrfs_fs_info *fs_info = data;
int ret = 0;
+ sb_start_write(fs_info->sb);
mutex_lock(&fs_info->balance_mutex);
if (fs_info->balance_ctl)
ret = btrfs_balance(fs_info, fs_info->balance_ctl, NULL);
mutex_unlock(&fs_info->balance_mutex);
+ sb_end_write(fs_info->sb);
return ret;
}
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 1d0e84806047f38027d7572adb4702ef7c09b317 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc(a)google.com>
Date: Thu, 31 Mar 2022 22:13:59 +0000
Subject: [PATCH] KVM: x86/mmu: Resolve nx_huge_pages when kvm.ko is loaded
Resolve nx_huge_pages to true/false when kvm.ko is loaded, leaving it as
-1 is technically undefined behavior when its value is read out by
param_get_bool(), as boolean values are supposed to be '0' or '1'.
Alternatively, KVM could define a custom getter for the param, but the
auto value doesn't depend on the vendor module in any way, and printing
"auto" would be unnecessarily unfriendly to the user.
In addition to fixing the undefined behavior, resolving the auto value
also fixes the scenario where the auto value resolves to N and no vendor
module is loaded. Previously, -1 would result in Y being printed even
though KVM would ultimately disable the mitigation.
Rename the existing MMU module init/exit helpers to clarify that they're
invoked with respect to the vendor module, and add comments to document
why KVM has two separate "module init" flows.
=========================================================================
UBSAN: invalid-load in kernel/params.c:320:33
load of value 255 is not a valid value for type '_Bool'
CPU: 6 PID: 892 Comm: tail Not tainted 5.17.0-rc3+ #799
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
Call Trace:
<TASK>
dump_stack_lvl+0x34/0x44
ubsan_epilogue+0x5/0x40
__ubsan_handle_load_invalid_value.cold+0x43/0x48
param_get_bool.cold+0xf/0x14
param_attr_show+0x55/0x80
module_attr_show+0x1c/0x30
sysfs_kf_seq_show+0x93/0xc0
seq_read_iter+0x11c/0x450
new_sync_read+0x11b/0x1a0
vfs_read+0xf0/0x190
ksys_read+0x5f/0xe0
do_syscall_64+0x3b/0xc0
entry_SYSCALL_64_after_hwframe+0x44/0xae
</TASK>
=========================================================================
Fixes: b8e8c8303ff2 ("kvm: mmu: ITLB_MULTIHIT mitigation")
Cc: stable(a)vger.kernel.org
Reported-by: Bruno Goncalves <bgoncalv(a)redhat.com>
Reported-by: Jan Stancek <jstancek(a)redhat.com>
Signed-off-by: Sean Christopherson <seanjc(a)google.com>
Message-Id: <20220331221359.3912754-1-seanjc(a)google.com>
Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com>
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d23e80a56eb8..0d37ba442de3 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1585,8 +1585,9 @@ static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm)
#define kvm_arch_pmi_in_guest(vcpu) \
((vcpu) && (vcpu)->arch.handling_intr_from_guest)
-int kvm_mmu_module_init(void);
-void kvm_mmu_module_exit(void);
+void kvm_mmu_x86_module_init(void);
+int kvm_mmu_vendor_module_init(void);
+void kvm_mmu_vendor_module_exit(void);
void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
int kvm_mmu_create(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 8f19ea752704..f9080ee50ffa 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6237,12 +6237,24 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
return 0;
}
-int kvm_mmu_module_init(void)
+/*
+ * nx_huge_pages needs to be resolved to true/false when kvm.ko is loaded, as
+ * its default value of -1 is technically undefined behavior for a boolean.
+ */
+void kvm_mmu_x86_module_init(void)
{
- int ret = -ENOMEM;
-
if (nx_huge_pages == -1)
__set_nx_huge_pages(get_nx_auto_mode());
+}
+
+/*
+ * The bulk of the MMU initialization is deferred until the vendor module is
+ * loaded as many of the masks/values may be modified by VMX or SVM, i.e. need
+ * to be reset when a potentially different vendor module is loaded.
+ */
+int kvm_mmu_vendor_module_init(void)
+{
+ int ret = -ENOMEM;
/*
* MMU roles use union aliasing which is, generally speaking, an
@@ -6290,7 +6302,7 @@ void kvm_mmu_destroy(struct kvm_vcpu *vcpu)
mmu_free_memory_caches(vcpu);
}
-void kvm_mmu_module_exit(void)
+void kvm_mmu_vendor_module_exit(void)
{
mmu_destroy_caches();
percpu_counter_destroy(&kvm_total_used_mmu_pages);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0c0ca599a353..de49a88df1c2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8926,7 +8926,7 @@ int kvm_arch_init(void *opaque)
}
kvm_nr_uret_msrs = 0;
- r = kvm_mmu_module_init();
+ r = kvm_mmu_vendor_module_init();
if (r)
goto out_free_percpu;
@@ -8974,7 +8974,7 @@ void kvm_arch_exit(void)
cancel_work_sync(&pvclock_gtod_work);
#endif
kvm_x86_ops.hardware_enable = NULL;
- kvm_mmu_module_exit();
+ kvm_mmu_vendor_module_exit();
free_percpu(user_return_msrs);
kmem_cache_destroy(x86_emulator_cache);
#ifdef CONFIG_KVM_XEN
@@ -12986,3 +12986,19 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit);
+
+static int __init kvm_x86_init(void)
+{
+ kvm_mmu_x86_module_init();
+ return 0;
+}
+module_init(kvm_x86_init);
+
+static void __exit kvm_x86_exit(void)
+{
+ /*
+ * If module_init() is implemented, module_exit() must also be
+ * implemented to allow module unload.
+ */
+}
+module_exit(kvm_x86_exit);
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 1d0e84806047f38027d7572adb4702ef7c09b317 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc(a)google.com>
Date: Thu, 31 Mar 2022 22:13:59 +0000
Subject: [PATCH] KVM: x86/mmu: Resolve nx_huge_pages when kvm.ko is loaded
Resolve nx_huge_pages to true/false when kvm.ko is loaded, leaving it as
-1 is technically undefined behavior when its value is read out by
param_get_bool(), as boolean values are supposed to be '0' or '1'.
Alternatively, KVM could define a custom getter for the param, but the
auto value doesn't depend on the vendor module in any way, and printing
"auto" would be unnecessarily unfriendly to the user.
In addition to fixing the undefined behavior, resolving the auto value
also fixes the scenario where the auto value resolves to N and no vendor
module is loaded. Previously, -1 would result in Y being printed even
though KVM would ultimately disable the mitigation.
Rename the existing MMU module init/exit helpers to clarify that they're
invoked with respect to the vendor module, and add comments to document
why KVM has two separate "module init" flows.
=========================================================================
UBSAN: invalid-load in kernel/params.c:320:33
load of value 255 is not a valid value for type '_Bool'
CPU: 6 PID: 892 Comm: tail Not tainted 5.17.0-rc3+ #799
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
Call Trace:
<TASK>
dump_stack_lvl+0x34/0x44
ubsan_epilogue+0x5/0x40
__ubsan_handle_load_invalid_value.cold+0x43/0x48
param_get_bool.cold+0xf/0x14
param_attr_show+0x55/0x80
module_attr_show+0x1c/0x30
sysfs_kf_seq_show+0x93/0xc0
seq_read_iter+0x11c/0x450
new_sync_read+0x11b/0x1a0
vfs_read+0xf0/0x190
ksys_read+0x5f/0xe0
do_syscall_64+0x3b/0xc0
entry_SYSCALL_64_after_hwframe+0x44/0xae
</TASK>
=========================================================================
Fixes: b8e8c8303ff2 ("kvm: mmu: ITLB_MULTIHIT mitigation")
Cc: stable(a)vger.kernel.org
Reported-by: Bruno Goncalves <bgoncalv(a)redhat.com>
Reported-by: Jan Stancek <jstancek(a)redhat.com>
Signed-off-by: Sean Christopherson <seanjc(a)google.com>
Message-Id: <20220331221359.3912754-1-seanjc(a)google.com>
Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com>
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d23e80a56eb8..0d37ba442de3 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1585,8 +1585,9 @@ static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm)
#define kvm_arch_pmi_in_guest(vcpu) \
((vcpu) && (vcpu)->arch.handling_intr_from_guest)
-int kvm_mmu_module_init(void);
-void kvm_mmu_module_exit(void);
+void kvm_mmu_x86_module_init(void);
+int kvm_mmu_vendor_module_init(void);
+void kvm_mmu_vendor_module_exit(void);
void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
int kvm_mmu_create(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 8f19ea752704..f9080ee50ffa 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6237,12 +6237,24 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
return 0;
}
-int kvm_mmu_module_init(void)
+/*
+ * nx_huge_pages needs to be resolved to true/false when kvm.ko is loaded, as
+ * its default value of -1 is technically undefined behavior for a boolean.
+ */
+void kvm_mmu_x86_module_init(void)
{
- int ret = -ENOMEM;
-
if (nx_huge_pages == -1)
__set_nx_huge_pages(get_nx_auto_mode());
+}
+
+/*
+ * The bulk of the MMU initialization is deferred until the vendor module is
+ * loaded as many of the masks/values may be modified by VMX or SVM, i.e. need
+ * to be reset when a potentially different vendor module is loaded.
+ */
+int kvm_mmu_vendor_module_init(void)
+{
+ int ret = -ENOMEM;
/*
* MMU roles use union aliasing which is, generally speaking, an
@@ -6290,7 +6302,7 @@ void kvm_mmu_destroy(struct kvm_vcpu *vcpu)
mmu_free_memory_caches(vcpu);
}
-void kvm_mmu_module_exit(void)
+void kvm_mmu_vendor_module_exit(void)
{
mmu_destroy_caches();
percpu_counter_destroy(&kvm_total_used_mmu_pages);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0c0ca599a353..de49a88df1c2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8926,7 +8926,7 @@ int kvm_arch_init(void *opaque)
}
kvm_nr_uret_msrs = 0;
- r = kvm_mmu_module_init();
+ r = kvm_mmu_vendor_module_init();
if (r)
goto out_free_percpu;
@@ -8974,7 +8974,7 @@ void kvm_arch_exit(void)
cancel_work_sync(&pvclock_gtod_work);
#endif
kvm_x86_ops.hardware_enable = NULL;
- kvm_mmu_module_exit();
+ kvm_mmu_vendor_module_exit();
free_percpu(user_return_msrs);
kmem_cache_destroy(x86_emulator_cache);
#ifdef CONFIG_KVM_XEN
@@ -12986,3 +12986,19 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit);
+
+static int __init kvm_x86_init(void)
+{
+ kvm_mmu_x86_module_init();
+ return 0;
+}
+module_init(kvm_x86_init);
+
+static void __exit kvm_x86_exit(void)
+{
+ /*
+ * If module_init() is implemented, module_exit() must also be
+ * implemented to allow module unload.
+ */
+}
+module_exit(kvm_x86_exit);
The patch below does not apply to the 4.9-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 1d0e84806047f38027d7572adb4702ef7c09b317 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc(a)google.com>
Date: Thu, 31 Mar 2022 22:13:59 +0000
Subject: [PATCH] KVM: x86/mmu: Resolve nx_huge_pages when kvm.ko is loaded
Resolve nx_huge_pages to true/false when kvm.ko is loaded, leaving it as
-1 is technically undefined behavior when its value is read out by
param_get_bool(), as boolean values are supposed to be '0' or '1'.
Alternatively, KVM could define a custom getter for the param, but the
auto value doesn't depend on the vendor module in any way, and printing
"auto" would be unnecessarily unfriendly to the user.
In addition to fixing the undefined behavior, resolving the auto value
also fixes the scenario where the auto value resolves to N and no vendor
module is loaded. Previously, -1 would result in Y being printed even
though KVM would ultimately disable the mitigation.
Rename the existing MMU module init/exit helpers to clarify that they're
invoked with respect to the vendor module, and add comments to document
why KVM has two separate "module init" flows.
=========================================================================
UBSAN: invalid-load in kernel/params.c:320:33
load of value 255 is not a valid value for type '_Bool'
CPU: 6 PID: 892 Comm: tail Not tainted 5.17.0-rc3+ #799
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
Call Trace:
<TASK>
dump_stack_lvl+0x34/0x44
ubsan_epilogue+0x5/0x40
__ubsan_handle_load_invalid_value.cold+0x43/0x48
param_get_bool.cold+0xf/0x14
param_attr_show+0x55/0x80
module_attr_show+0x1c/0x30
sysfs_kf_seq_show+0x93/0xc0
seq_read_iter+0x11c/0x450
new_sync_read+0x11b/0x1a0
vfs_read+0xf0/0x190
ksys_read+0x5f/0xe0
do_syscall_64+0x3b/0xc0
entry_SYSCALL_64_after_hwframe+0x44/0xae
</TASK>
=========================================================================
Fixes: b8e8c8303ff2 ("kvm: mmu: ITLB_MULTIHIT mitigation")
Cc: stable(a)vger.kernel.org
Reported-by: Bruno Goncalves <bgoncalv(a)redhat.com>
Reported-by: Jan Stancek <jstancek(a)redhat.com>
Signed-off-by: Sean Christopherson <seanjc(a)google.com>
Message-Id: <20220331221359.3912754-1-seanjc(a)google.com>
Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com>
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d23e80a56eb8..0d37ba442de3 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1585,8 +1585,9 @@ static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm)
#define kvm_arch_pmi_in_guest(vcpu) \
((vcpu) && (vcpu)->arch.handling_intr_from_guest)
-int kvm_mmu_module_init(void);
-void kvm_mmu_module_exit(void);
+void kvm_mmu_x86_module_init(void);
+int kvm_mmu_vendor_module_init(void);
+void kvm_mmu_vendor_module_exit(void);
void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
int kvm_mmu_create(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 8f19ea752704..f9080ee50ffa 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6237,12 +6237,24 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
return 0;
}
-int kvm_mmu_module_init(void)
+/*
+ * nx_huge_pages needs to be resolved to true/false when kvm.ko is loaded, as
+ * its default value of -1 is technically undefined behavior for a boolean.
+ */
+void kvm_mmu_x86_module_init(void)
{
- int ret = -ENOMEM;
-
if (nx_huge_pages == -1)
__set_nx_huge_pages(get_nx_auto_mode());
+}
+
+/*
+ * The bulk of the MMU initialization is deferred until the vendor module is
+ * loaded as many of the masks/values may be modified by VMX or SVM, i.e. need
+ * to be reset when a potentially different vendor module is loaded.
+ */
+int kvm_mmu_vendor_module_init(void)
+{
+ int ret = -ENOMEM;
/*
* MMU roles use union aliasing which is, generally speaking, an
@@ -6290,7 +6302,7 @@ void kvm_mmu_destroy(struct kvm_vcpu *vcpu)
mmu_free_memory_caches(vcpu);
}
-void kvm_mmu_module_exit(void)
+void kvm_mmu_vendor_module_exit(void)
{
mmu_destroy_caches();
percpu_counter_destroy(&kvm_total_used_mmu_pages);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0c0ca599a353..de49a88df1c2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8926,7 +8926,7 @@ int kvm_arch_init(void *opaque)
}
kvm_nr_uret_msrs = 0;
- r = kvm_mmu_module_init();
+ r = kvm_mmu_vendor_module_init();
if (r)
goto out_free_percpu;
@@ -8974,7 +8974,7 @@ void kvm_arch_exit(void)
cancel_work_sync(&pvclock_gtod_work);
#endif
kvm_x86_ops.hardware_enable = NULL;
- kvm_mmu_module_exit();
+ kvm_mmu_vendor_module_exit();
free_percpu(user_return_msrs);
kmem_cache_destroy(x86_emulator_cache);
#ifdef CONFIG_KVM_XEN
@@ -12986,3 +12986,19 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit);
+
+static int __init kvm_x86_init(void)
+{
+ kvm_mmu_x86_module_init();
+ return 0;
+}
+module_init(kvm_x86_init);
+
+static void __exit kvm_x86_exit(void)
+{
+ /*
+ * If module_init() is implemented, module_exit() must also be
+ * implemented to allow module unload.
+ */
+}
+module_exit(kvm_x86_exit);
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 1d0e84806047f38027d7572adb4702ef7c09b317 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc(a)google.com>
Date: Thu, 31 Mar 2022 22:13:59 +0000
Subject: [PATCH] KVM: x86/mmu: Resolve nx_huge_pages when kvm.ko is loaded
Resolve nx_huge_pages to true/false when kvm.ko is loaded, leaving it as
-1 is technically undefined behavior when its value is read out by
param_get_bool(), as boolean values are supposed to be '0' or '1'.
Alternatively, KVM could define a custom getter for the param, but the
auto value doesn't depend on the vendor module in any way, and printing
"auto" would be unnecessarily unfriendly to the user.
In addition to fixing the undefined behavior, resolving the auto value
also fixes the scenario where the auto value resolves to N and no vendor
module is loaded. Previously, -1 would result in Y being printed even
though KVM would ultimately disable the mitigation.
Rename the existing MMU module init/exit helpers to clarify that they're
invoked with respect to the vendor module, and add comments to document
why KVM has two separate "module init" flows.
=========================================================================
UBSAN: invalid-load in kernel/params.c:320:33
load of value 255 is not a valid value for type '_Bool'
CPU: 6 PID: 892 Comm: tail Not tainted 5.17.0-rc3+ #799
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
Call Trace:
<TASK>
dump_stack_lvl+0x34/0x44
ubsan_epilogue+0x5/0x40
__ubsan_handle_load_invalid_value.cold+0x43/0x48
param_get_bool.cold+0xf/0x14
param_attr_show+0x55/0x80
module_attr_show+0x1c/0x30
sysfs_kf_seq_show+0x93/0xc0
seq_read_iter+0x11c/0x450
new_sync_read+0x11b/0x1a0
vfs_read+0xf0/0x190
ksys_read+0x5f/0xe0
do_syscall_64+0x3b/0xc0
entry_SYSCALL_64_after_hwframe+0x44/0xae
</TASK>
=========================================================================
Fixes: b8e8c8303ff2 ("kvm: mmu: ITLB_MULTIHIT mitigation")
Cc: stable(a)vger.kernel.org
Reported-by: Bruno Goncalves <bgoncalv(a)redhat.com>
Reported-by: Jan Stancek <jstancek(a)redhat.com>
Signed-off-by: Sean Christopherson <seanjc(a)google.com>
Message-Id: <20220331221359.3912754-1-seanjc(a)google.com>
Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com>
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d23e80a56eb8..0d37ba442de3 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1585,8 +1585,9 @@ static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm)
#define kvm_arch_pmi_in_guest(vcpu) \
((vcpu) && (vcpu)->arch.handling_intr_from_guest)
-int kvm_mmu_module_init(void);
-void kvm_mmu_module_exit(void);
+void kvm_mmu_x86_module_init(void);
+int kvm_mmu_vendor_module_init(void);
+void kvm_mmu_vendor_module_exit(void);
void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
int kvm_mmu_create(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 8f19ea752704..f9080ee50ffa 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6237,12 +6237,24 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
return 0;
}
-int kvm_mmu_module_init(void)
+/*
+ * nx_huge_pages needs to be resolved to true/false when kvm.ko is loaded, as
+ * its default value of -1 is technically undefined behavior for a boolean.
+ */
+void kvm_mmu_x86_module_init(void)
{
- int ret = -ENOMEM;
-
if (nx_huge_pages == -1)
__set_nx_huge_pages(get_nx_auto_mode());
+}
+
+/*
+ * The bulk of the MMU initialization is deferred until the vendor module is
+ * loaded as many of the masks/values may be modified by VMX or SVM, i.e. need
+ * to be reset when a potentially different vendor module is loaded.
+ */
+int kvm_mmu_vendor_module_init(void)
+{
+ int ret = -ENOMEM;
/*
* MMU roles use union aliasing which is, generally speaking, an
@@ -6290,7 +6302,7 @@ void kvm_mmu_destroy(struct kvm_vcpu *vcpu)
mmu_free_memory_caches(vcpu);
}
-void kvm_mmu_module_exit(void)
+void kvm_mmu_vendor_module_exit(void)
{
mmu_destroy_caches();
percpu_counter_destroy(&kvm_total_used_mmu_pages);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0c0ca599a353..de49a88df1c2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8926,7 +8926,7 @@ int kvm_arch_init(void *opaque)
}
kvm_nr_uret_msrs = 0;
- r = kvm_mmu_module_init();
+ r = kvm_mmu_vendor_module_init();
if (r)
goto out_free_percpu;
@@ -8974,7 +8974,7 @@ void kvm_arch_exit(void)
cancel_work_sync(&pvclock_gtod_work);
#endif
kvm_x86_ops.hardware_enable = NULL;
- kvm_mmu_module_exit();
+ kvm_mmu_vendor_module_exit();
free_percpu(user_return_msrs);
kmem_cache_destroy(x86_emulator_cache);
#ifdef CONFIG_KVM_XEN
@@ -12986,3 +12986,19 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit);
+
+static int __init kvm_x86_init(void)
+{
+ kvm_mmu_x86_module_init();
+ return 0;
+}
+module_init(kvm_x86_init);
+
+static void __exit kvm_x86_exit(void)
+{
+ /*
+ * If module_init() is implemented, module_exit() must also be
+ * implemented to allow module unload.
+ */
+}
+module_exit(kvm_x86_exit);
This patch fixes a memory corruption that occurred in the
nand_scan() path for Hynix nand device.
On boot, for Hynix nand device will panic at a weird place:
| Unable to handle kernel NULL pointer dereference at virtual
address 00000070
| [00000070] *pgd=00000000
| Internal error: Oops: 5 [#1] PREEMPT SMP ARM
| Modules linked in:
| CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.17.0-01473-g13ae1769cfb0
#38
| Hardware name: Generic DT based system
| PC is at nandc_set_reg+0x8/0x1c
| LR is at qcom_nandc_command+0x20c/0x5d0
| pc : [<c088b74c>] lr : [<c088d9c8>] psr: 00000113
| sp : c14adc50 ip : c14ee208 fp : c0cc970c
| r10: 000000a3 r9 : 00000000 r8 : 00000040
| r7 : c16f6a00 r6 : 00000090 r5 : 00000004 r4 :c14ee040
| r3 : 00000000 r2 : 0000000b r1 : 00000000 r0 :c14ee040
| Flags: nzcv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none
| Control: 10c5387d Table: 8020406a DAC: 00000051
| Register r0 information: slab kmalloc-2k start c14ee000 pointer offset
64 size 2048
| Process swapper/0 (pid: 1, stack limit = 0x(ptrval))
| nandc_set_reg from qcom_nandc_command+0x20c/0x5d0
| qcom_nandc_command from nand_readid_op+0x198/0x1e8
| nand_readid_op from hynix_nand_has_valid_jedecid+0x30/0x78
| hynix_nand_has_valid_jedecid from hynix_nand_init+0xb8/0x454
| hynix_nand_init from nand_scan_with_ids+0xa30/0x14a8
| nand_scan_with_ids from qcom_nandc_probe+0x648/0x7b0
| qcom_nandc_probe from platform_probe+0x58/0xac
The problem is that the nand_scan()'s qcom_nand_attach_chip callback
is updating the nandc->max_cwperpage from 1 to 4 or 8 based on page size.
This causes the sg_init_table of clear_bam_transaction() in the driver's
qcom_nandc_command() to memset much more than what was initially
allocated by alloc_bam_transaction().
This patch will update nandc->max_cwperpage 1 to 4 or 8 based on page
size in qcom_nand_attach_chip call back after freeing the previously
allocated memory for bam txn as per nandc->max_cwperpage = 1 and then
again allocating bam txn as per nandc->max_cwperpage = 4 or 8 based on
page size in qcom_nand_attach_chip call back itself.
Cc: stable(a)vger.kernel.org
Fixes: 6a3cec64f18c ("mtd: rawnand: qcom: convert driver to nand_scan()")
Reported-by: Konrad Dybcio <konrad.dybcio(a)somainline.org>
Signed-off-by: Md Sadre Alam <quic_mdalam(a)quicinc.com>
Signed-off-by: Sricharan R <quic_srichara(a)quicinc.com>
---
Changes in V4:
* Incorporated "commit log wrong" comment from Mani
* Updated commit log
Changes in V3:
* Incorporated "Fixes tags are missing" comment from Miquèl
* Added Fixes tag Fixes:6a3cec64f18c ("mtd: rawnand: qcom: convert driver to nand_scan()")
* Incorporated "stable tag missing" comment from Miquèl
* Added stable tag Cc: stable(a)vger.kernel.org
* Incorporated "Reported-by tag missing" comment from Mani
* Added Reported-by tag Reported-by: Konrad Dybcio <konrad.dybcio(a)somainline.org>
Changes in V2:
* Incorporated "alloc_bam_transaction inside qcom_nand_attach_chip" suggestion from Mani
* Freed previously alloacted memory for bam txn before updating max_cwperpage inside
qcom_nand_attach_chip().
* Moved alloc_bam_transaction() inside qcom_nand_attach_chip(). after upding max_cwperpage
4 or 8 based on page size.
drivers/mtd/nand/raw/qcom_nandc.c | 24 +++++++++++++-----------
1 file changed, 13 insertions(+), 11 deletions(-)
diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index 1a77542..048b255 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -2651,10 +2651,23 @@ static int qcom_nand_attach_chip(struct nand_chip *chip)
ecc->engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
mtd_set_ooblayout(mtd, &qcom_nand_ooblayout_ops);
+ /* Free the initially allocated BAM transaction for reading the ONFI params */
+ if (nandc->props->is_bam)
+ free_bam_transaction(nandc);
nandc->max_cwperpage = max_t(unsigned int, nandc->max_cwperpage,
cwperpage);
+ /* Now allocate the BAM transaction based on updated max_cwperpage */
+ if (nandc->props->is_bam) {
+ nandc->bam_txn = alloc_bam_transaction(nandc);
+ if (!nandc->bam_txn) {
+ dev_err(nandc->dev,
+ "failed to allocate bam transaction\n");
+ return -ENOMEM;
+ }
+ }
+
/*
* DATA_UD_BYTES varies based on whether the read/write command protects
* spare data with ECC too. We protect spare data by default, so we set
@@ -2955,17 +2968,6 @@ static int qcom_nand_host_init_and_register(struct qcom_nand_controller *nandc,
if (ret)
return ret;
- if (nandc->props->is_bam) {
- free_bam_transaction(nandc);
- nandc->bam_txn = alloc_bam_transaction(nandc);
- if (!nandc->bam_txn) {
- dev_err(nandc->dev,
- "failed to allocate bam transaction\n");
- nand_cleanup(chip);
- return -ENOMEM;
- }
- }
-
ret = mtd_device_parse_register(mtd, probes, NULL, NULL, 0);
if (ret)
nand_cleanup(chip);
--
2.7.4
This patch fixes a memory corruption that occurred in the
nand_scan() path for Hynix nand device.
On boot, for Hynix nand device will panic at a weird place:
| Unable to handle kernel NULL pointer dereference at virtual
address 00000070
| [00000070] *pgd=00000000
| Internal error: Oops: 5 [#1] PREEMPT SMP ARM
| Modules linked in:
| CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.17.0-01473-g13ae1769cfb0
#38
| Hardware name: Generic DT based system
| PC is at nandc_set_reg+0x8/0x1c
| LR is at qcom_nandc_command+0x20c/0x5d0
| pc : [<c088b74c>] lr : [<c088d9c8>] psr: 00000113
| sp : c14adc50 ip : c14ee208 fp : c0cc970c
| r10: 000000a3 r9 : 00000000 r8 : 00000040
| r7 : c16f6a00 r6 : 00000090 r5 : 00000004 r4 :c14ee040
| r3 : 00000000 r2 : 0000000b r1 : 00000000 r0 :c14ee040
| Flags: nzcv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none
| Control: 10c5387d Table: 8020406a DAC: 00000051
| Register r0 information: slab kmalloc-2k start c14ee000 pointer offset
64 size 2048
| Process swapper/0 (pid: 1, stack limit = 0x(ptrval))
| nandc_set_reg from qcom_nandc_command+0x20c/0x5d0
| qcom_nandc_command from nand_readid_op+0x198/0x1e8
| nand_readid_op from hynix_nand_has_valid_jedecid+0x30/0x78
| hynix_nand_has_valid_jedecid from hynix_nand_init+0xb8/0x454
| hynix_nand_init from nand_scan_with_ids+0xa30/0x14a8
| nand_scan_with_ids from qcom_nandc_probe+0x648/0x7b0
| qcom_nandc_probe from platform_probe+0x58/0xac
The problem is that the nand_scan()'s qcom_nand_attach_chip callback
is updating the nandc->max_cwperpage from 1 to 4.This causes the
sg_init_table of clear_bam_transaction() in the driver's
qcom_nandc_command() to memset much more than what was initially
allocated by alloc_bam_transaction().
This patch will update nandc->max_cwperpage 1 to 4 after nand_scan()
returns, and remove updating nandc->max_cwperpage from
qcom_nand_attach_chip call back.
Cc: stable(a)vger.kernel.org
Fixes: 6a3cec64f18c ("mtd: rawnand: qcom: convert driver to nand_scan()")
Reported-by: Konrad Dybcio <konrad.dybcio(a)somainline.org>
Signed-off-by: Md Sadre Alam <quic_mdalam(a)quicinc.com>
Signed-off-by: Sricharan R <quic_srichara(a)quicinc.com>
---
[V3]
* Updated commit message Fixes, Cc, Reported-by
drivers/mtd/nand/raw/qcom_nandc.c | 24 +++++++++++++-----------
1 file changed, 13 insertions(+), 11 deletions(-)
diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index 1a77542..048b255 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -2651,10 +2651,23 @@ static int qcom_nand_attach_chip(struct nand_chip *chip)
ecc->engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
mtd_set_ooblayout(mtd, &qcom_nand_ooblayout_ops);
+ /* Free the initially allocated BAM transaction for reading the ONFI params */
+ if (nandc->props->is_bam)
+ free_bam_transaction(nandc);
nandc->max_cwperpage = max_t(unsigned int, nandc->max_cwperpage,
cwperpage);
+ /* Now allocate the BAM transaction based on updated max_cwperpage */
+ if (nandc->props->is_bam) {
+ nandc->bam_txn = alloc_bam_transaction(nandc);
+ if (!nandc->bam_txn) {
+ dev_err(nandc->dev,
+ "failed to allocate bam transaction\n");
+ return -ENOMEM;
+ }
+ }
+
/*
* DATA_UD_BYTES varies based on whether the read/write command protects
* spare data with ECC too. We protect spare data by default, so we set
@@ -2955,17 +2968,6 @@ static int qcom_nand_host_init_and_register(struct qcom_nand_controller *nandc,
if (ret)
return ret;
- if (nandc->props->is_bam) {
- free_bam_transaction(nandc);
- nandc->bam_txn = alloc_bam_transaction(nandc);
- if (!nandc->bam_txn) {
- dev_err(nandc->dev,
- "failed to allocate bam transaction\n");
- nand_cleanup(chip);
- return -ENOMEM;
- }
- }
-
ret = mtd_device_parse_register(mtd, probes, NULL, NULL, 0);
if (ret)
nand_cleanup(chip);
--
2.7.4
Good day,
I am Mr. Richard Wahl, you have a Donation of €1,200,000.00 . I won a fortune in the Power-ball lottery and i am donating part of it to Ten Lucky people and Ten Charity organization. Your email came out victorious so Reply me urgently for more information via email richardwahl01011(a)gmail.com
Sincerely,
Mr. Richard Wahl
...............................................................
Ich bin Herr Richard Wahl, Sie haben eine Spende in Höhe von 1.200.000,00 €. Ich habe ein Vermögen in der Power-Ball-Lotterie gewonnen und spende einen Teil davon an Ten Lucky People und die Ten Charity-Organisation. Ihre E-Mail war erfolgreich, also antworten Sie mir dringend für weitere Informationen per E-Mail richardwahl01011(a)gmail.com
Aufrichtig,
Herr Richard Wahl
--
This email has been checked for viruses by Avast antivirus software.
https://www.avast.com/antivirus