The set value of `fast_switch_enabled` indicates that fast_switch
callback is set. For some drivers such as amd_pstate and intel_pstate,
the adjust_perf callback is used but it still sets
`fast_switch_possible` flag. This is because this flag also decides
whether schedutil governor selects adjust_perf function for frequency
update. This condition in the schedutil governor forces the scaling
driver to set the `fast_switch_possible` flag.
Remove `fast_switch_enabled` check when schedutil decides to select
adjust_perf function for frequency update. Thus removing this drivers
are now free to remove `fast_switch_possible` flag if they don't use
fast_switch callback.
This issue becomes apparent when aperf/mperf overflow occurs. When this
happens, kernel disables frequency invariance calculation which causes
schedutil to fallback to sugov_update_single_freq which currently relies
on the fast_switch callback.
Normal flow:
sugov_update_single_perf
cpufreq_driver_adjust_perf
cpufreq_driver->adjust_perf
Error case flow:
sugov_update_single_perf
sugov_update_single_freq <-- This is chosen because the freq invariant is disabled due to aperf/mperf overflow
cpufreq_driver_fast_switch
cpufreq_driver->fast_switch <-- Here NULL pointer dereference is happening, because fast_switch is not set
This change fixes this NULL pointer dereference issue.
Fixes: a61dec744745 ("cpufreq: schedutil: Avoid missing updates for one-CPU policies")
Signed-off-by: Wyes Karny <wyes.karny(a)amd.com>
Cc: "Rafael J. Wysocki" <rafael(a)kernel.org>
Cc: stable(a)vger.kernel.org
---
drivers/cpufreq/amd-pstate.c | 10 +++++++---
drivers/cpufreq/cpufreq.c | 20 +++++++++++++++++++-
drivers/cpufreq/intel_pstate.c | 3 +--
include/linux/cpufreq.h | 1 +
kernel/sched/cpufreq_schedutil.c | 2 +-
5 files changed, 29 insertions(+), 7 deletions(-)
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 5a3d4aa0f45a..007bfe724a6a 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -671,8 +671,14 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
/* It will be updated by governor */
policy->cur = policy->cpuinfo.min_freq;
+ /**
+ * For shared memory system frequency update takes time that's why
+ * do this in deferred kthread context.
+ */
if (boot_cpu_has(X86_FEATURE_CPPC))
- policy->fast_switch_possible = true;
+ current_pstate_driver->adjust_perf = amd_pstate_adjust_perf;
+ else
+ current_pstate_driver->adjust_perf = NULL;
ret = freq_qos_add_request(&policy->constraints, &cpudata->req[0],
FREQ_QOS_MIN, policy->cpuinfo.min_freq);
@@ -697,8 +703,6 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
policy->driver_data = cpudata;
amd_pstate_boost_init(cpudata);
- if (!current_pstate_driver->adjust_perf)
- current_pstate_driver->adjust_perf = amd_pstate_adjust_perf;
return 0;
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 6b52ebe5a890..366747012104 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -501,6 +501,13 @@ void cpufreq_enable_fast_switch(struct cpufreq_policy *policy)
if (!policy->fast_switch_possible)
return;
+ /**
+ * It's not expected driver's fast_switch callback is not set
+ * even fast_switch_possible is true.
+ */
+ if (WARN_ON(!cpufreq_driver_has_fast_switch()))
+ return;
+
mutex_lock(&cpufreq_fast_switch_lock);
if (cpufreq_fast_switch_count >= 0) {
cpufreq_fast_switch_count++;
@@ -2143,6 +2150,17 @@ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
}
EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch);
+/**
+ * cpufreq_driver_has_fast_switch - Check "fast switch" callback.
+ *
+ * Return 'true' if the ->fast_switch callback is present for the
+ * current driver or 'false' otherwise.
+ */
+bool cpufreq_driver_has_fast_switch(void)
+{
+ return !!cpufreq_driver->fast_switch;
+}
+
/**
* cpufreq_driver_adjust_perf - Adjust CPU performance level in one go.
* @cpu: Target CPU.
@@ -2157,7 +2175,7 @@ EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch);
* and it is expected to select a suitable performance level equal to or above
* @min_perf and preferably equal to or below @target_perf.
*
- * This function must not be called if policy->fast_switch_enabled is unset.
+ * By default this function takes the fast frequency update path.
*
* Governors calling this function must guarantee that it will never be invoked
* twice in parallel for the same CPU and that it will never be called in
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 2548ec92faa2..007893514c87 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2698,8 +2698,6 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy)
intel_pstate_init_acpi_perf_limits(policy);
- policy->fast_switch_possible = true;
-
return 0;
}
@@ -2955,6 +2953,7 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
if (ret)
return ret;
+ policy->fast_switch_possible = true;
policy->cpuinfo.transition_latency = INTEL_CPUFREQ_TRANSITION_LATENCY;
/* This reflects the intel_pstate_get_cpu_pstates() setting. */
policy->cur = policy->cpuinfo.min_freq;
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 26e2eb399484..7a32cfca26c9 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -604,6 +604,7 @@ struct cpufreq_governor {
/* Pass a target to the cpufreq driver */
unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
unsigned int target_freq);
+bool cpufreq_driver_has_fast_switch(void);
void cpufreq_driver_adjust_perf(unsigned int cpu,
unsigned long min_perf,
unsigned long target_perf,
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index e3211455b203..f993ecf731a9 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -776,7 +776,7 @@ static int sugov_start(struct cpufreq_policy *policy)
if (policy_is_shared(policy))
uu = sugov_update_shared;
- else if (policy->fast_switch_enabled && cpufreq_driver_has_adjust_perf())
+ else if (cpufreq_driver_has_adjust_perf())
uu = sugov_update_single_perf;
else
uu = sugov_update_single_freq;
--
2.34.1
On Fri, May 12, 2023 at 08:28:26AM +0000, zhangqiumiao wrote:
> Hello,
>
> We found the following issue using syzkaller on Linux v5.10.0.
5.10.0 is very old and obsolete and over 20 thousand patches old.
Please, if you are testing LTS kernels, use the latest one.
> A similar issue was found in function `paste_selection` before and
> I believe they are the same.
> (https://lore.kernel.org/all/000000000000fe769905d315a1b7@google.com/)
>
> Unfortunately, no one seems to be paying attention to this issue.
Do you have a proposed patch for this fix now that you have a way to
reproduce this? Do you see this in real situations or only in
fault-injection systems running syzbot?
And can you reproduce this on 6.4-rc1? Do you have a reproducer?
thanks,
greg k-h
This is a backport of the CR0.WP KVM series[1] to Linux v6.2. All
commits applied either clean or with only minor changes needed to
account for missing prerequisite patches, e.g. the lack of a
kvm_is_cr0_bit_set() helper for patch 5 or the slightly different
surrounding context in patch 4 (__always_inline vs. plain inline for
to_kvm_vmx()).
I used 'ssdd 10 50000' from rt-tests[2] as a micro-benchmark, running on
a grsecurity L1 VM. Below table shows the results (runtime in seconds,
lower is better):
legacy TDP shadow
Linux v6.2.10 7.61s 7.98s 68.6s
+ patches 3.37s 3.41s 70.2s
The KVM unit test suite showed no regressions.
Please consider applying.
Thanks,
Mathias
[1] https://lore.kernel.org/kvm/20230322013731.102955-1-minipli@grsecurity.net/
[2] https://git.kernel.org/pub/scm/utils/rt-tests/rt-tests.git
Mathias Krause (3):
KVM: x86: Do not unload MMU roots when only toggling CR0.WP with TDP
enabled
KVM: x86: Make use of kvm_read_cr*_bits() when testing bits
KVM: VMX: Make CR0.WP a guest owned bit
Paolo Bonzini (1):
KVM: x86/mmu: Avoid indirect call for get_cr3
Sean Christopherson (1):
KVM: x86/mmu: Refresh CR0.WP prior to checking for emulated permission
faults
arch/x86/kvm/kvm_cache_regs.h | 2 +-
arch/x86/kvm/mmu.h | 26 ++++++++++++++++++-
arch/x86/kvm/mmu/mmu.c | 46 ++++++++++++++++++++++++++--------
arch/x86/kvm/mmu/paging_tmpl.h | 2 +-
arch/x86/kvm/pmu.c | 4 +--
arch/x86/kvm/vmx/nested.c | 4 +--
arch/x86/kvm/vmx/vmx.c | 6 ++---
arch/x86/kvm/vmx/vmx.h | 18 +++++++++++++
arch/x86/kvm/x86.c | 12 +++++++++
9 files changed, 99 insertions(+), 21 deletions(-)
--
2.39.2
From: Conor Dooley <conor.dooley(a)microchip.com>
Guenter reported a lockdep splat that appears to have been present for a
while in v6.1.y & the backports of the riscv_patch_in_stop_machine dance
did nothing to help here, as the lock is not being taken when
patch_text_nosync() is called in riscv_cpufeature_patch_func().
Add the lock/unlock; elide the splat.
Fixes: c15ac4fd60d5 ("riscv/ftrace: Add dynamic function tracer support")
Reported-by: Guenter Roeck <linux(a)roeck-us.net>
cc: stable(a)vger.kernel.org
Signed-off-by: Conor Dooley <conor.dooley(a)microchip.com>
---
arch/riscv/kernel/cpufeature.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 694267d1fe81..fd1238df6149 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -9,6 +9,7 @@
#include <linux/bitmap.h>
#include <linux/ctype.h>
#include <linux/libfdt.h>
+#include <linux/memory.h>
#include <linux/module.h>
#include <linux/of.h>
#include <asm/alternative.h>
@@ -316,8 +317,11 @@ void __init_or_module riscv_cpufeature_patch_func(struct alt_entry *begin,
}
tmp = (1U << alt->errata_id);
- if (cpu_req_feature & tmp)
+ if (cpu_req_feature & tmp) {
+ mutex_lock(&text_mutex);
patch_text_nosync(alt->old_ptr, alt->alt_ptr, alt->alt_len);
+ mutex_unlock(&text_mutex);
+ }
}
}
#endif
--
2.39.2
[ Upstream commit 19b5e6659eaf537ebeac90ae30c7df0296fe5ab9 ]
Existing code is causing a race condition where dirt_needed value is
already set by the host and gets overwritten with default value. Remove
this default setting of dirt_needed, to avoid overwriting the value
received in the channel callback set by vmbus_open. Removing this
setting also means the default value for dirt_needed is changed to false
as it's allocated by kzalloc which is similar to legacy hyperv_fb driver.
Signed-off-by: Saurabh Sengar <ssengar(a)linux.microsoft.com>
Reviewed-by: Michael Kelley <mikelley(a)microsoft.com>
Reviewed-by: Dexuan Cui <decui(a)microsoft.com>
---
drivers/gpu/drm/hyperv/hyperv_drm_drv.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c
index 00e53de4812b..584d3a73db96 100644
--- a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c
+++ b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c
@@ -198,8 +198,6 @@ static int hyperv_vmbus_probe(struct hv_device *hdev,
if (ret)
drm_warn(dev, "Failed to update vram location.\n");
- hv->dirt_needed = true;
-
ret = hyperv_mode_config_init(hv);
if (ret)
goto err_vmbus_close;
--
2.34.1
A commit went into 6.3 that helps adjust the timing for resume of some
monitors behind MST hubs.
This commit was done on top of a restructuring that happened in 6.3, but
the existing old function names work as well for this issue.
Hand modify the code to use the old function names in 6.2.y and 6.1.y
to help this issue.
Ryan Lin (1):
drm/amd/display: Ext displays with dock can't recognized after resume
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 9 +++++++++
1 file changed, 9 insertions(+)
--
2.34.1
This is a partial backport of the CR0.WP KVM series[1] to Linux v5.4. It
limits itself to avoid TDP MMU unloading as making CR0.WP a guest owned
bit turned out to be too much of an effort and the partial backport
already being quite effective.
I used 'ssdd 10 50000' from rt-tests[2] as a micro-benchmark, running on
a grsecurity L1 VM. Below table shows the results (runtime in seconds,
lower is better):
TDP shadow
Linux v5.4.240 8.87s 56.8s
+ patches 5.84s 55.4s
This kernel version had no module parameter to control the TDP MMU
setting, it's always enabled when EPT / NPT is. Therefore its meaning is
likely what became "legacy" in newer kernels.
Please consider applying.
Thanks,
Mathias
[1] https://lore.kernel.org/kvm/20230322013731.102955-1-minipli@grsecurity.net/
[2] https://git.kernel.org/pub/scm/utils/rt-tests/rt-tests.git
Mathias Krause (2):
KVM: x86: Do not unload MMU roots when only toggling CR0.WP with TDP
enabled
KVM: x86: Make use of kvm_read_cr*_bits() when testing bits
Paolo Bonzini (1):
KVM: x86/mmu: Avoid indirect call for get_cr3
arch/x86/kvm/mmu.c | 14 +++++++-------
arch/x86/kvm/mmu.h | 11 +++++++++++
arch/x86/kvm/paging_tmpl.h | 2 +-
arch/x86/kvm/vmx/vmx.c | 4 ++--
arch/x86/kvm/x86.c | 14 +++++++++++++-
5 files changed, 34 insertions(+), 11 deletions(-)
--
2.39.2
This is a backport of the CR0.WP KVM series[1] to Linux v5.10. It
further extends the v5.15 backport by two patches, namely patch 5 (which
is the prerequisite for Lai's patches) and patch 8 which was already
part of the v5.15.27 stable update but didn't made it to v5.10.
I used 'ssdd 10 50000' from rt-tests[2] as a micro-benchmark, running on
a grsecurity L1 VM. Below table shows the results (runtime in seconds,
lower is better):
legacy TDP shadow
Linux v5.10.177 10.37s 88.7s 69.7s
+ patches 4.88s 4.92s 70.1s
TDP MMU is, as for v5.15, slower than shadow paging on a vanilla kernel.
Fortunately it's disabled by default.
The KVM unit test suite showed no regressions.
Please consider applying.
Thanks,
Mathias
[1] https://lore.kernel.org/kvm/20230322013731.102955-1-minipli@grsecurity.net/
[2] https://git.kernel.org/pub/scm/utils/rt-tests/rt-tests.git
Lai Jiangshan (4):
KVM: X86: Don't reset mmu context when X86_CR4_PCIDE 1->0
KVM: X86: Don't reset mmu context when toggling X86_CR4_PGE
KVM: X86: Ensure that dirty PDPTRs are loaded
KVM: x86/mmu: Reconstruct shadow page root if the guest PDPTEs is
changed
Mathias Krause (3):
KVM: x86: Do not unload MMU roots when only toggling CR0.WP with TDP
enabled
KVM: x86: Make use of kvm_read_cr*_bits() when testing bits
KVM: VMX: Make CR0.WP a guest owned bit
Paolo Bonzini (1):
KVM: x86/mmu: Avoid indirect call for get_cr3
Sean Christopherson (2):
KVM: x86: Read and pass all CR0/CR4 role bits to shadow MMU helper
KVM: x86/mmu: Refresh CR0.WP prior to checking for emulated permission
faults
arch/x86/kvm/kvm_cache_regs.h | 2 +-
arch/x86/kvm/mmu.h | 42 +++++++++++++++++++++++++++++++++-
arch/x86/kvm/mmu/mmu.c | 32 +++++++++++++++++++-------
arch/x86/kvm/mmu/paging_tmpl.h | 2 +-
arch/x86/kvm/pmu.c | 4 ++--
arch/x86/kvm/vmx/nested.c | 4 ++--
arch/x86/kvm/vmx/vmx.c | 6 ++---
arch/x86/kvm/vmx/vmx.h | 18 +++++++++++++++
arch/x86/kvm/x86.c | 32 +++++++++++++++++++++-----
9 files changed, 118 insertions(+), 24 deletions(-)
--
2.39.2
This is a backport of the CR0.WP KVM series[1] to Linux v6.1, pretty
much the same as for v6.2.
I used 'ssdd 10 50000' from rt-tests[2] as a micro-benchmark, running on
a grsecurity L1 VM. Below table shows the results (runtime in seconds,
lower is better):
legacy TDP shadow
Linux v6.1.23 7.65s 8.23s 68.7s
+ patches 3.36s 3.36s 69.1s
The KVM unit test suite showed no regressions.
Please consider applying.
Thanks,
Mathias
[1] https://lore.kernel.org/kvm/20230322013731.102955-1-minipli@grsecurity.net/
[2] https://git.kernel.org/pub/scm/utils/rt-tests/rt-tests.git
Mathias Krause (3):
KVM: x86: Do not unload MMU roots when only toggling CR0.WP with TDP
enabled
KVM: x86: Make use of kvm_read_cr*_bits() when testing bits
KVM: VMX: Make CR0.WP a guest owned bit
Paolo Bonzini (1):
KVM: x86/mmu: Avoid indirect call for get_cr3
Sean Christopherson (1):
KVM: x86/mmu: Refresh CR0.WP prior to checking for emulated permission
faults
arch/x86/kvm/kvm_cache_regs.h | 2 +-
arch/x86/kvm/mmu.h | 26 ++++++++++++++++++-
arch/x86/kvm/mmu/mmu.c | 46 ++++++++++++++++++++++++++--------
arch/x86/kvm/mmu/paging_tmpl.h | 2 +-
arch/x86/kvm/pmu.c | 4 +--
arch/x86/kvm/vmx/nested.c | 4 +--
arch/x86/kvm/vmx/vmx.c | 6 ++---
arch/x86/kvm/vmx/vmx.h | 18 +++++++++++++
arch/x86/kvm/x86.c | 12 +++++++++
9 files changed, 99 insertions(+), 21 deletions(-)
--
2.39.2
The special device /dev/mem enables users to map arbitrary physical
memory regions into the user space, which can conflict with the double
mapping detection logic used by the page table check. For instance,
pages may change their properties (e.g., from anonymous pages to named
pages) while they are still being mapped in the user space via /dev/mem,
leading to "corruption" detected by the page table check.
To address this issue, the PAGE_TABLE_CHECK config option is now
dependent on !DEVMM. This ensures that the page table check cannot be
enabled when /dev/mem is used. It should be noted that /dev/mem itself
is a significant security issue, and its conflict with a hardening
technique is understandable.
Cc: <stable(a)vger.kernel.org> # 5.17
Signed-off-by: Ruihan Li <lrh2000(a)pku.edu.cn>
---
Documentation/mm/page_table_check.rst | 18 ++++++++++++++++++
mm/Kconfig.debug | 2 +-
2 files changed, 19 insertions(+), 1 deletion(-)
diff --git a/Documentation/mm/page_table_check.rst b/Documentation/mm/page_table_check.rst
index cfd8f4117..b04f29230 100644
--- a/Documentation/mm/page_table_check.rst
+++ b/Documentation/mm/page_table_check.rst
@@ -52,3 +52,21 @@ Build kernel with:
Optionally, build kernel with PAGE_TABLE_CHECK_ENFORCED in order to have page
table support without extra kernel parameter.
+
+Implementation notes
+====================
+
+We specifically decided not to use VMA information in order to avoid relying on
+MM states (except for limited "struct page" info). The page table check is a
+separate from Linux-MM state machine that verifies that the user accessible
+pages are not falsely shared.
+
+As a result, special devices that violate the model cannot live with
+PAGE_TABLE_CHECK. Currently, /dev/mem is the only known example. Given it
+allows users to map arbitrary physical memory regions into the userspace, any
+pages may change their properties (e.g., from anonymous pages to named pages)
+while they are still being mapped in the userspace via /dev/mem, leading to
+"corruption" detected by the page table check. Therefore, the PAGE_TABLE_CHECK
+config option is now dependent on !DEVMEM. It's worth noting that /dev/mem
+itself is a significant security issue, and its conflict with a hardening
+technique is understandable.
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index a925415b4..37f3d5b20 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -97,7 +97,7 @@ config PAGE_OWNER
config PAGE_TABLE_CHECK
bool "Check for invalid mappings in user page tables"
- depends on ARCH_SUPPORTS_PAGE_TABLE_CHECK
+ depends on ARCH_SUPPORTS_PAGE_TABLE_CHECK && !DEVMEM
select PAGE_EXTENSION
help
Check that anonymous page is not being mapped twice with read write
--
2.40.1
When mgag200 switched from simple KMS to regular atomic helpers,
the initialization of the gamma settings was lost.
This leads to a black screen, if the bios/uefi doesn't use the same
pixel color depth.
v2: rebase on top of drm-misc-fixes, and add Cc stable tag.
Link: https://bugzilla.redhat.com/show_bug.cgi?id=2171155
Fixes: 1baf9127c482 ("drm/mgag200: Replace simple-KMS with regular atomic helpers")
Cc: <stable(a)vger.kernel.org>
Tested-by: Phil Oester <kernel(a)linuxace.com>
Reviewed-by: Thomas Zimmermann <tzimmermann(a)suse.de>
Signed-off-by: Jocelyn Falempe <jfalempe(a)redhat.com>
---
drivers/gpu/drm/mgag200/mgag200_mode.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 0a5aaf78172a..576c4c838a33 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -640,6 +640,11 @@ void mgag200_crtc_helper_atomic_enable(struct drm_crtc *crtc, struct drm_atomic_
if (funcs->pixpllc_atomic_update)
funcs->pixpllc_atomic_update(crtc, old_state);
+ if (crtc_state->gamma_lut)
+ mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data);
+ else
+ mgag200_crtc_set_gamma_linear(mdev, format);
+
mgag200_enable_display(mdev);
if (funcs->enable_vidrst)
base-commit: a26cc2934331b57b5a7164bff344f0a2ec245fc0
--
2.39.2
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>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x 146a37e05d620cef4ad430e5d1c9c077fe6fa76f
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023050627-kept-container-b02a@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 146a37e05d620cef4ad430e5d1c9c077fe6fa76f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen(a)linux.intel.com>
Date: Fri, 17 Mar 2023 13:33:18 +0200
Subject: [PATCH] serial: 8250: Fix serial8250_tx_empty() race with DMA Tx
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
There's a potential race before THRE/TEMT deasserts when DMA Tx is
starting up (or the next batch of continuous Tx is being submitted).
This can lead to misdetecting Tx empty condition.
It is entirely normal for THRE/TEMT to be set for some time after the
DMA Tx had been setup in serial8250_tx_dma(). As Tx side is definitely
not empty at that point, it seems incorrect for serial8250_tx_empty()
claim Tx is empty.
Fix the race by also checking in serial8250_tx_empty() whether there's
DMA Tx active.
Note: This fix only addresses in-kernel race mainly to make using
TCSADRAIN/FLUSH robust. Userspace can still cause other races but they
seem userspace concurrency control problems.
Fixes: 9ee4b83e51f74 ("serial: 8250: Add support for dmaengine")
Cc: stable(a)vger.kernel.org
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com>
Link: https://lore.kernel.org/r/20230317113318.31327-3-ilpo.jarvinen@linux.intel.…
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h
index 287153d32536..1e8fe44a7099 100644
--- a/drivers/tty/serial/8250/8250.h
+++ b/drivers/tty/serial/8250/8250.h
@@ -365,6 +365,13 @@ static inline void serial8250_do_prepare_rx_dma(struct uart_8250_port *p)
if (dma->prepare_rx_dma)
dma->prepare_rx_dma(p);
}
+
+static inline bool serial8250_tx_dma_running(struct uart_8250_port *p)
+{
+ struct uart_8250_dma *dma = p->dma;
+
+ return dma && dma->tx_running;
+}
#else
static inline int serial8250_tx_dma(struct uart_8250_port *p)
{
@@ -380,6 +387,11 @@ static inline int serial8250_request_dma(struct uart_8250_port *p)
return -1;
}
static inline void serial8250_release_dma(struct uart_8250_port *p) { }
+
+static inline bool serial8250_tx_dma_running(struct uart_8250_port *p)
+{
+ return false;
+}
#endif
static inline int ns16550a_goto_highspeed(struct uart_8250_port *up)
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index fa43df05342b..107bcdfb119c 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -2005,18 +2005,19 @@ static int serial8250_tx_threshold_handle_irq(struct uart_port *port)
static unsigned int serial8250_tx_empty(struct uart_port *port)
{
struct uart_8250_port *up = up_to_u8250p(port);
+ unsigned int result = 0;
unsigned long flags;
- u16 lsr;
serial8250_rpm_get(up);
spin_lock_irqsave(&port->lock, flags);
- lsr = serial_lsr_in(up);
+ if (!serial8250_tx_dma_running(up) && uart_lsr_tx_empty(serial_lsr_in(up)))
+ result = TIOCSER_TEMT;
spin_unlock_irqrestore(&port->lock, flags);
serial8250_rpm_put(up);
- return uart_lsr_tx_empty(lsr) ? TIOCSER_TEMT : 0;
+ return result;
}
unsigned int serial8250_do_get_mctrl(struct uart_port *port)
From: Pierre-Louis Bossart <pierre-louis.bossart(a)linux.intel.com>
[ Upstream commit 3aa1e96a2b95e2ece198f8dd01e96818971b84df ]
A BE connected to more than one FE, e.g. in a mixer case, can go
through the following transitions.
play FE1 -> BE state is START
pause FE1 -> BE state is PAUSED
play FE2 -> BE state is START
stop FE2 -> BE state is STOP (see note [1] below)
release FE1 -> BE state is START
stop FE1 -> BE state is STOP
play FE1 -> BE state is START
pause FE1 -> BE state is PAUSED
play FE2 -> BE state is START
release FE1 -> BE state is START
stop FE2 -> BE state is START
stop FE1 -> BE state is STOP
play FE1 -> BE state is START
play FE2 -> BE state is START (no change)
pause FE1 -> BE state is START (no change)
pause FE2 -> BE state is PAUSED
release FE1 -> BE state is START
release FE2 -> BE state is START (no change)
stop FE1 -> BE state is START (no change)
stop FE2 -> BE state is STOP
The existing code for PAUSE_RELEASE only allows for the case where the
BE is paused, which clearly would not work in the sequences above.
Extend the allowed states to restart the BE when PAUSE_RELEASE is
received, and increase the refcount if the BE is already in START.
[1] the existing logic does not move the BE state back to PAUSED when
the FE2 is stopped. This patch does not change the logic; it would be
painful to keep a history of changes on the FE side, the state machine
is already rather complicated with transitions based on the last BE
state and the trigger type.
Reported-by: Bard Liao <bard.liao(a)intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart(a)linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen(a)linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao(a)linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan(a)linux.intel.com>
Link: https://lore.kernel.org/r/20211207173745.15850-7-pierre-louis.bossart@linux…
Signed-off-by: Mark Brown <broonie(a)kernel.org>
Fixes: aa9ff6a4955f ("ASoC: soc-compress: Reposition and add pcm_mutex")
Signed-off-by: Yixuan Jiang <yixuanjiang(a)google.com>
Cc: stable(a)vger.kernel.org # 5.15+
---
sound/soc/soc-pcm.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index b6099d36518f5..6e589708b9338 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -2151,7 +2151,10 @@ int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream,
be->dpcm[stream].state = SND_SOC_DPCM_STATE_START;
break;
case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
- if ((be->dpcm[stream].state != SND_SOC_DPCM_STATE_PAUSED))
+ if (!be->dpcm[stream].be_start &&
+ (be->dpcm[stream].state != SND_SOC_DPCM_STATE_START) &&
+ (be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP) &&
+ (be->dpcm[stream].state != SND_SOC_DPCM_STATE_PAUSED))
goto next;
be->dpcm[stream].be_start++;
--
2.40.1.521.gf1e218fcd8-goog
From: Pierre-Louis Bossart <pierre-louis.bossart(a)linux.intel.com>
[ Upstream commit 848aedfdc6ba25ad5652797db9266007773e44dd ]
On start/pause_release/resume, when more than one FE is connected to
the same BE, it's possible that the trigger is sent more than
once. This is not desirable, we only want to trigger a BE once, which
is straightforward to implement with a refcount.
For stop/pause/suspend, the problem is more complicated: the check
implemented in snd_soc_dpcm_can_be_free_stop() may fail due to a
conceptual deadlock when we trigger the BE before the FE. In this
case, the FE states have not yet changed, so there are corner cases
where the TRIGGER_STOP is never sent - the dual case of start where
multiple triggers might be sent.
This patch suggests an unconditional trigger in all cases, without
checking the FE states, using a refcount protected by the BE PCM
stream lock.
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart(a)linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen(a)linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao(a)linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan(a)linux.intel.com>
Link: https://lore.kernel.org/r/20211207173745.15850-6-pierre-louis.bossart@linux…
Signed-off-by: Mark Brown <broonie(a)kernel.org>
Fixes: aa9ff6a4955f ("ASoC: soc-compress: Reposition and add pcm_mutex")
Signed-off-by: Yixuan Jiang <yixuanjiang(a)google.com>
Cc: stable(a)vger.kernel.org # 5.15+
---
include/sound/soc-dpcm.h | 2 ++
sound/soc/soc-pcm.c | 53 +++++++++++++++++++++++++++++++---------
2 files changed, 44 insertions(+), 11 deletions(-)
diff --git a/include/sound/soc-dpcm.h b/include/sound/soc-dpcm.h
index e296a3949b18b..d963f3b608489 100644
--- a/include/sound/soc-dpcm.h
+++ b/include/sound/soc-dpcm.h
@@ -101,6 +101,8 @@ struct snd_soc_dpcm_runtime {
enum snd_soc_dpcm_state state;
int trigger_pending; /* trigger cmd + 1 if pending, 0 if not */
+
+ int be_start; /* refcount protected by BE stream pcm lock */
};
#define for_each_dpcm_fe(be, stream, _dpcm) \
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 7903516c89a6a..b6099d36518f5 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1630,7 +1630,7 @@ int dpcm_be_dai_startup(struct snd_soc_pcm_runtime *fe, int stream)
be->dpcm[stream].state = SND_SOC_DPCM_STATE_CLOSE;
goto unwind;
}
-
+ be->dpcm[stream].be_start = 0;
be->dpcm[stream].state = SND_SOC_DPCM_STATE_OPEN;
count++;
}
@@ -2116,14 +2116,21 @@ int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream,
switch (cmd) {
case SNDRV_PCM_TRIGGER_START:
- if ((be->dpcm[stream].state != SND_SOC_DPCM_STATE_PREPARE) &&
+ if (!be->dpcm[stream].be_start &&
+ (be->dpcm[stream].state != SND_SOC_DPCM_STATE_PREPARE) &&
(be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP) &&
(be->dpcm[stream].state != SND_SOC_DPCM_STATE_PAUSED))
goto next;
+ be->dpcm[stream].be_start++;
+ if (be->dpcm[stream].be_start != 1)
+ goto next;
+
ret = soc_pcm_trigger(be_substream, cmd);
- if (ret)
+ if (ret) {
+ be->dpcm[stream].be_start--;
goto next;
+ }
be->dpcm[stream].state = SND_SOC_DPCM_STATE_START;
break;
@@ -2131,9 +2138,15 @@ int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream,
if ((be->dpcm[stream].state != SND_SOC_DPCM_STATE_SUSPEND))
goto next;
+ be->dpcm[stream].be_start++;
+ if (be->dpcm[stream].be_start != 1)
+ goto next;
+
ret = soc_pcm_trigger(be_substream, cmd);
- if (ret)
+ if (ret) {
+ be->dpcm[stream].be_start--;
goto next;
+ }
be->dpcm[stream].state = SND_SOC_DPCM_STATE_START;
break;
@@ -2141,9 +2154,15 @@ int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream,
if ((be->dpcm[stream].state != SND_SOC_DPCM_STATE_PAUSED))
goto next;
+ be->dpcm[stream].be_start++;
+ if (be->dpcm[stream].be_start != 1)
+ goto next;
+
ret = soc_pcm_trigger(be_substream, cmd);
- if (ret)
+ if (ret) {
+ be->dpcm[stream].be_start--;
goto next;
+ }
be->dpcm[stream].state = SND_SOC_DPCM_STATE_START;
break;
@@ -2152,12 +2171,18 @@ int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream,
(be->dpcm[stream].state != SND_SOC_DPCM_STATE_PAUSED))
goto next;
- if (!snd_soc_dpcm_can_be_free_stop(fe, be, stream))
+ if (be->dpcm[stream].state == SND_SOC_DPCM_STATE_START)
+ be->dpcm[stream].be_start--;
+
+ if (be->dpcm[stream].be_start != 0)
goto next;
ret = soc_pcm_trigger(be_substream, cmd);
- if (ret)
+ if (ret) {
+ if (be->dpcm[stream].state == SND_SOC_DPCM_STATE_START)
+ be->dpcm[stream].be_start++;
goto next;
+ }
be->dpcm[stream].state = SND_SOC_DPCM_STATE_STOP;
break;
@@ -2165,12 +2190,15 @@ int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream,
if (be->dpcm[stream].state != SND_SOC_DPCM_STATE_START)
goto next;
- if (!snd_soc_dpcm_can_be_free_stop(fe, be, stream))
+ be->dpcm[stream].be_start--;
+ if (be->dpcm[stream].be_start != 0)
goto next;
ret = soc_pcm_trigger(be_substream, cmd);
- if (ret)
+ if (ret) {
+ be->dpcm[stream].be_start++;
goto next;
+ }
be->dpcm[stream].state = SND_SOC_DPCM_STATE_SUSPEND;
break;
@@ -2178,12 +2206,15 @@ int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream,
if (be->dpcm[stream].state != SND_SOC_DPCM_STATE_START)
goto next;
- if (!snd_soc_dpcm_can_be_free_stop(fe, be, stream))
+ be->dpcm[stream].be_start--;
+ if (be->dpcm[stream].be_start != 0)
goto next;
ret = soc_pcm_trigger(be_substream, cmd);
- if (ret)
+ if (ret) {
+ be->dpcm[stream].be_start++;
goto next;
+ }
be->dpcm[stream].state = SND_SOC_DPCM_STATE_PAUSED;
break;
--
2.40.1.521.gf1e218fcd8-goog
From: Takashi Iwai <tiwai(a)suse.de>
[ Upstream commit b2ae80663008a7662febe7d13f14ea1b2eb0cd51 ]
When more than one FE is connected to a BE, e.g. in a mixing use case,
the BE can be triggered multiple times when the FE are opened/started
concurrently. This race condition is problematic in the case of
SoundWire BE dailinks, and this is not desirable in a general
case.
This patch relies on the existing BE PCM lock, which takes atomicity into
account. The locking model assumes that all interactions start with
the FE, so that there is no deadlock between FE and BE locks.
Signed-off-by: Takashi Iwai <tiwai(a)suse.de>
[test, checkpatch fix and clarification of commit message by plbossart]
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart(a)linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen(a)linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao(a)linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan(a)linux.intel.com>
Link: https://lore.kernel.org/r/20211207173745.15850-5-pierre-louis.bossart@linux…
Signed-off-by: Mark Brown <broonie(a)kernel.org>
Fixes: aa9ff6a4955f ("ASoC: soc-compress: Reposition and add pcm_mutex")
Signed-off-by: Yixuan Jiang <yixuanjiang(a)google.com>
Cc: stable(a)vger.kernel.org # 5.15+
---
sound/soc/soc-pcm.c | 46 ++++++++++++++++++++++++++++-----------------
1 file changed, 29 insertions(+), 17 deletions(-)
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index a9869203804e7..7903516c89a6a 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -46,12 +46,18 @@ static inline void snd_soc_dpcm_stream_lock_irq(struct snd_soc_pcm_runtime *rtd,
snd_pcm_stream_lock_irq(snd_soc_dpcm_get_substream(rtd, stream));
}
+#define snd_soc_dpcm_stream_lock_irqsave(rtd, stream, flags) \
+ snd_pcm_stream_lock_irqsave(snd_soc_dpcm_get_substream(rtd, stream), flags)
+
static inline void snd_soc_dpcm_stream_unlock_irq(struct snd_soc_pcm_runtime *rtd,
int stream)
{
snd_pcm_stream_unlock_irq(snd_soc_dpcm_get_substream(rtd, stream));
}
+#define snd_soc_dpcm_stream_unlock_irqrestore(rtd, stream, flags) \
+ snd_pcm_stream_unlock_irqrestore(snd_soc_dpcm_get_substream(rtd, stream), flags)
+
#define DPCM_MAX_BE_USERS 8
static inline const char *soc_cpu_dai_name(struct snd_soc_pcm_runtime *rtd)
@@ -2090,6 +2096,7 @@ int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream,
{
struct snd_soc_pcm_runtime *be;
struct snd_soc_dpcm *dpcm;
+ unsigned long flags;
int ret = 0;
for_each_dpcm_be(fe, stream, dpcm) {
@@ -2098,9 +2105,11 @@ int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream,
be = dpcm->be;
be_substream = snd_soc_dpcm_get_substream(be, stream);
+ snd_soc_dpcm_stream_lock_irqsave(be, stream, flags);
+
/* is this op for this BE ? */
if (!snd_soc_dpcm_be_can_update(fe, be, stream))
- continue;
+ goto next;
dev_dbg(be->dev, "ASoC: trigger BE %s cmd %d\n",
be->dai_link->name, cmd);
@@ -2110,77 +2119,80 @@ int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream,
if ((be->dpcm[stream].state != SND_SOC_DPCM_STATE_PREPARE) &&
(be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP) &&
(be->dpcm[stream].state != SND_SOC_DPCM_STATE_PAUSED))
- continue;
+ goto next;
ret = soc_pcm_trigger(be_substream, cmd);
if (ret)
- goto end;
+ goto next;
be->dpcm[stream].state = SND_SOC_DPCM_STATE_START;
break;
case SNDRV_PCM_TRIGGER_RESUME:
if ((be->dpcm[stream].state != SND_SOC_DPCM_STATE_SUSPEND))
- continue;
+ goto next;
ret = soc_pcm_trigger(be_substream, cmd);
if (ret)
- goto end;
+ goto next;
be->dpcm[stream].state = SND_SOC_DPCM_STATE_START;
break;
case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
if ((be->dpcm[stream].state != SND_SOC_DPCM_STATE_PAUSED))
- continue;
+ goto next;
ret = soc_pcm_trigger(be_substream, cmd);
if (ret)
- goto end;
+ goto next;
be->dpcm[stream].state = SND_SOC_DPCM_STATE_START;
break;
case SNDRV_PCM_TRIGGER_STOP:
if ((be->dpcm[stream].state != SND_SOC_DPCM_STATE_START) &&
(be->dpcm[stream].state != SND_SOC_DPCM_STATE_PAUSED))
- continue;
+ goto next;
if (!snd_soc_dpcm_can_be_free_stop(fe, be, stream))
- continue;
+ goto next;
ret = soc_pcm_trigger(be_substream, cmd);
if (ret)
- goto end;
+ goto next;
be->dpcm[stream].state = SND_SOC_DPCM_STATE_STOP;
break;
case SNDRV_PCM_TRIGGER_SUSPEND:
if (be->dpcm[stream].state != SND_SOC_DPCM_STATE_START)
- continue;
+ goto next;
if (!snd_soc_dpcm_can_be_free_stop(fe, be, stream))
- continue;
+ goto next;
ret = soc_pcm_trigger(be_substream, cmd);
if (ret)
- goto end;
+ goto next;
be->dpcm[stream].state = SND_SOC_DPCM_STATE_SUSPEND;
break;
case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
if (be->dpcm[stream].state != SND_SOC_DPCM_STATE_START)
- continue;
+ goto next;
if (!snd_soc_dpcm_can_be_free_stop(fe, be, stream))
- continue;
+ goto next;
ret = soc_pcm_trigger(be_substream, cmd);
if (ret)
- goto end;
+ goto next;
be->dpcm[stream].state = SND_SOC_DPCM_STATE_PAUSED;
break;
}
+next:
+ snd_soc_dpcm_stream_unlock_irqrestore(be, stream, flags);
+ if (ret)
+ break;
}
-end:
if (ret < 0)
dev_err(fe->dev, "ASoC: %s() failed at %s (%d)\n",
__func__, be->dai_link->name, ret);
--
2.40.1.521.gf1e218fcd8-goog
From: Pierre-Louis Bossart <pierre-louis.bossart(a)linux.intel.com>
[ Upstream commit bbf7d3b1c4f40eb02dd1dffb500ba00b0bff0303 ]
Since the flow for DPCM is based on taking a lock for the FE first, we
need to make sure during the connection between a BE and an FE that
they both use the same 'atomicity', otherwise we may sleep in atomic
context.
If the FE is nonatomic, this patch forces the BE to be nonatomic as
well. That should have no negative impact since the BE 'inherits' the
FE properties.
However, if the FE is atomic and the BE is not, then the configuration
is flagged as invalid.
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart(a)linux.intel.com>
[ removed FE stream lock by tiwai ]
Signed-off-by: Takashi Iwai <tiwai(a)suse.de>
Reviewed-by: Kai Vehmanen <kai.vehmanen(a)linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao(a)linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan(a)linux.intel.com>
Link: https://lore.kernel.org/r/20211207173745.15850-3-pierre-louis.bossart@linux…
Signed-off-by: Mark Brown <broonie(a)kernel.org>
Fixes: aa9ff6a4955f ("ASoC: soc-compress: Reposition and add pcm_mutex")
Signed-off-by: Yixuan Jiang <yixuanjiang(a)google.com>
Cc: stable(a)vger.kernel.org # 5.15+
---
sound/soc/soc-pcm.c | 16 ++++++++++++++++
1 file changed, 16 insertions(+)
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index cffae9b7c2548..373f20bd14301 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1123,6 +1123,8 @@ static snd_pcm_uframes_t soc_pcm_pointer(struct snd_pcm_substream *substream)
static int dpcm_be_connect(struct snd_soc_pcm_runtime *fe,
struct snd_soc_pcm_runtime *be, int stream)
{
+ struct snd_pcm_substream *fe_substream;
+ struct snd_pcm_substream *be_substream;
struct snd_soc_dpcm *dpcm;
unsigned long flags;
@@ -1132,6 +1134,20 @@ static int dpcm_be_connect(struct snd_soc_pcm_runtime *fe,
return 0;
}
+ fe_substream = snd_soc_dpcm_get_substream(fe, stream);
+ be_substream = snd_soc_dpcm_get_substream(be, stream);
+
+ if (!fe_substream->pcm->nonatomic && be_substream->pcm->nonatomic) {
+ dev_err(be->dev, "%s: FE is atomic but BE is nonatomic, invalid configuration\n",
+ __func__);
+ return -EINVAL;
+ }
+ if (fe_substream->pcm->nonatomic && !be_substream->pcm->nonatomic) {
+ dev_warn(be->dev, "%s: FE is nonatomic but BE is not, forcing BE as nonatomic\n",
+ __func__);
+ be_substream->pcm->nonatomic = 1;
+ }
+
dpcm = kzalloc(sizeof(struct snd_soc_dpcm), GFP_ATOMIC);
if (!dpcm)
return -ENOMEM;
--
2.40.1.521.gf1e218fcd8-goog
Дорогой любимый,
Пожалуйста, прочитайте это медленно и внимательно, так как это может
быть одно из самых важных электронных писем, которые вы когда-либо
получали. Я миссис Кристина Кэмпбелл, я была замужем за покойным
Эдвардом Кэмпбеллом. опытный подрядчик в регионе Восточной Азии. Он
умер в четверг, 31 июля 2003 г., в Париже. Мы были женаты семь лет без
ребенка.
Пока вы читаете это, я не хочу, чтобы вы жалели меня, потому что я
верю, что все когда-нибудь умрут. У меня был диагностирован рак
пищевода, и мой врач сказал мне, что я не протяну долго из-за моих
сложных проблем со здоровьем.
Я хочу, чтобы Бог был милостив ко мне и принял мою душу, поэтому я
решил подавать милостыню благотворительным организациям / церквям /
буддийским храмам / мечети / сиротам / малообеспеченным и вдовам, так
как я хочу, чтобы это было одним из последних добрых дел. Я делаю на
земле, прежде чем я умру. На данный момент я раздал деньги некоторым
благотворительным организациям в Шотландии, Уэльсе, Израиле, Финляндии
и Армении. Теперь, когда мое здоровье так сильно ухудшилось, я больше
не могу заниматься этим сама.
Однажды я попросил членов моей семьи закрыть один из моих счетов и
раздать деньги, которые у меня там есть, благотворительным
организациям в Беларуси, Украине, Латвии, России и Эстонии, они
отказались и оставили деньги себе. Следовательно, я не доверяю их
больше, так как они, кажется, не борются с тем, что я оставил для них.
Последние из моих денег, о которых никто не знает, — это огромный
денежный депозит в размере шести миллионов долларов США в размере 6
000 000 долларов США, который у меня есть в банке в Таиланде, где я
разместил этот фонд. Я хочу, чтобы вы использовали этот фонд для
благотворительных программ и поддерживали человечество в своей стране,
если только вы будете искренними.
Я принял это решение, потому что у меня нет ребенка, который
унаследует эти деньги, я не боюсь смерти, поэтому я знаю, куда я иду.
Я знаю, что я буду в лоне Господа. Как только я получу ваш ответ, я
дам вам контакты Банка и вышлю вам письмо-разрешение, которое даст вам
право как первоначальному бенефициару этого фонда немедленно начать
эту благотворительную программу в вашей стране.
Только жизнь, прожитая для других, имеет смысл. Я хочу, чтобы вы
всегда молились за меня. Любая задержка с вашим ответом даст мне
возможность найти другого человека для той же цели. Если вы не
заинтересованы, пожалуйста, извините меня за то, что связался с вами.
Вы можете связаться со мной или ответить мне на мою личную электронную
почту: (cristiinacampbell(a)hotmail.com).
Спасибо,
Искренне Ваш,
миссис Кристина Кэмпбелл
Электронная почта; cristiinacampbell(a)hotmail.com
From: Xiubo Li <xiubli(a)redhat.com>
Blindly expanding the readahead windows will cause unneccessary
pagecache thrashing and also will introdue the network workload.
We should disable expanding the windows if the readahead is disabled
and also shouldn't expand the windows too much.
Expanding forward firstly instead of expanding backward for possible
sequential reads.
Bound `rreq->len` to the actual file size to restore the previous page
cache usage.
The posix_fadvise may change the maximum size of a file readahead.
Cc: stable(a)vger.kernel.org
Fixes: 49870056005c ("ceph: convert ceph_readpages to ceph_readahead")
URL: https://lore.kernel.org/ceph-devel/20230504082510.247-1-sehuww@mail.scut.ed…
URL: https://www.spinics.net/lists/ceph-users/msg76183.html
Cc: Hu Weiwen <sehuww(a)mail.scut.edu.cn>
Signed-off-by: Xiubo Li <xiubli(a)redhat.com>
---
fs/ceph/addr.c | 40 +++++++++++++++++++++++++++++++++-------
1 file changed, 33 insertions(+), 7 deletions(-)
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index db55fce13324..e1bf90059112 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -188,16 +188,42 @@ static void ceph_netfs_expand_readahead(struct netfs_io_request *rreq)
struct inode *inode = rreq->inode;
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_file_layout *lo = &ci->i_layout;
+ unsigned long max_pages = inode->i_sb->s_bdi->ra_pages;
+ loff_t end = rreq->start + rreq->len, new_end;
+ struct ceph_netfs_request_data *priv = rreq->netfs_priv;
+ unsigned long max_len;
u32 blockoff;
- u64 blockno;
- /* Expand the start downward */
- blockno = div_u64_rem(rreq->start, lo->stripe_unit, &blockoff);
- rreq->start = blockno * lo->stripe_unit;
- rreq->len += blockoff;
+ if (priv) {
+ /* Readahead is disabled by posix_fadvise POSIX_FADV_RANDOM */
+ if (priv->file_ra_disabled)
+ max_pages = 0;
+ else
+ max_pages = priv->file_ra_pages;
+
+ }
+
+ /* Readahead is disabled */
+ if (!max_pages)
+ return;
- /* Now, round up the length to the next block */
- rreq->len = roundup(rreq->len, lo->stripe_unit);
+ max_len = max_pages << PAGE_SHIFT;
+
+ /*
+ * Try to expand the length forward by rounding up it to the next
+ * block, but do not exceed the file size, unless the original
+ * request already exceeds it.
+ */
+ new_end = min(round_up(end, lo->stripe_unit), rreq->i_size);
+ if (new_end > end && new_end <= rreq->start + max_len)
+ rreq->len = new_end - rreq->start;
+
+ /* Try to expand the start downward */
+ div_u64_rem(rreq->start, lo->stripe_unit, &blockoff);
+ if (rreq->len + blockoff <= max_len) {
+ rreq->start -= blockoff;
+ rreq->len += blockoff;
+ }
}
static bool ceph_netfs_clamp_length(struct netfs_io_subrequest *subreq)
--
2.40.0