--- /dev/null
+From 0a0ab96ce86e837b140d282f882c86f79d96ca2a Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Fri, 19 Aug 2022 11:30:50 +0100
+Subject: arm64: errata: add detection for AMEVCNTR01 incrementing incorrectly
+
+From: Ionela Voinescu <ionela.voinescu@arm.com>
+
+[ Upstream commit e89d120c4b720e232cc6a94f0fcbd59c15d41489 ]
+
+The AMU counter AMEVCNTR01 (constant counter) should increment at the same
+rate as the system counter. On affected Cortex-A510 cores, AMEVCNTR01
+increments incorrectly giving a significantly higher output value. This
+results in inaccurate task scheduler utilization tracking and incorrect
+feedback on CPU frequency.
+
+Work around this problem by returning 0 when reading the affected counter
+in key locations that results in disabling all users of this counter from
+using it either for frequency invariance or as FFH reference counter. This
+effect is the same to firmware disabling affected counters.
+
+Details on how the two features are affected by this erratum:
+
+ - AMU counters will not be used for frequency invariance for affected
+ CPUs and CPUs in the same cpufreq policy. AMUs can still be used for
+ frequency invariance for unaffected CPUs in the system. Although
+ unlikely, if no alternative method can be found to support frequency
+ invariance for affected CPUs (cpufreq based or solution based on
+ platform counters) frequency invariance will be disabled. Please check
+ the chapter on frequency invariance at
+ Documentation/scheduler/sched-capacity.rst for details of its effect.
+
+ - Given that FFH can be used to fetch either the core or constant counter
+ values, restrictions are lifted regarding any of these counters
+ returning a valid (!0) value. Therefore FFH is considered supported
+ if there is a least one CPU that support AMUs, independent of any
+ counters being disabled or affected by this erratum. Clarifying
+ comments are now added to the cpc_ffh_supported(), cpu_read_constcnt()
+ and cpu_read_corecnt() functions.
+
+The above is achieved through adding a new erratum: ARM64_ERRATUM_2457168.
+
+Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com>
+Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
+Cc: Catalin Marinas <catalin.marinas@arm.com>
+Cc: Will Deacon <will@kernel.org>
+Cc: James Morse <james.morse@arm.com>
+Link: https://lore.kernel.org/r/20220819103050.24211-1-ionela.voinescu@arm.com
+Signed-off-by: Will Deacon <will@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ Documentation/arm64/silicon-errata.rst | 2 ++
+ arch/arm64/Kconfig | 17 ++++++++++++++
+ arch/arm64/kernel/cpu_errata.c | 10 ++++++++
+ arch/arm64/kernel/cpufeature.c | 5 +++-
+ arch/arm64/kernel/topology.c | 32 ++++++++++++++++++++++++--
+ arch/arm64/tools/cpucaps | 1 +
+ 6 files changed, 64 insertions(+), 3 deletions(-)
+
+diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst
+index 33b04db8408f9..fda97b3fcf018 100644
+--- a/Documentation/arm64/silicon-errata.rst
++++ b/Documentation/arm64/silicon-errata.rst
+@@ -52,6 +52,8 @@ stable kernels.
+ | Allwinner | A64/R18 | UNKNOWN1 | SUN50I_ERRATUM_UNKNOWN1 |
+ +----------------+-----------------+-----------------+-----------------------------+
+ +----------------+-----------------+-----------------+-----------------------------+
++| ARM | Cortex-A510 | #2457168 | ARM64_ERRATUM_2457168 |
+++----------------+-----------------+-----------------+-----------------------------+
+ | ARM | Cortex-A510 | #2064142 | ARM64_ERRATUM_2064142 |
+ +----------------+-----------------+-----------------+-----------------------------+
+ | ARM | Cortex-A510 | #2038923 | ARM64_ERRATUM_2038923 |
+diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
+index 001eaba5a6b4b..21f33d8d66685 100644
+--- a/arch/arm64/Kconfig
++++ b/arch/arm64/Kconfig
+@@ -914,6 +914,23 @@ config ARM64_ERRATUM_1902691
+
+ If unsure, say Y.
+
++config ARM64_ERRATUM_2457168
++ bool "Cortex-A510: 2457168: workaround for AMEVCNTR01 incrementing incorrectly"
++ depends on ARM64_AMU_EXTN
++ default y
++ help
++ This option adds the workaround for ARM Cortex-A510 erratum 2457168.
++
++ The AMU counter AMEVCNTR01 (constant counter) should increment at the same rate
++ as the system counter. On affected Cortex-A510 cores AMEVCNTR01 increments
++ incorrectly giving a significantly higher output value.
++
++ Work around this problem by returning 0 when reading the affected counter in
++ key locations that results in disabling all users of this counter. This effect
++ is the same to firmware disabling affected counters.
++
++ If unsure, say Y.
++
+ config CAVIUM_ERRATUM_22375
+ bool "Cavium erratum 22375, 24313"
+ default y
+diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
+index 5f4117dae8888..af137f91607da 100644
+--- a/arch/arm64/kernel/cpu_errata.c
++++ b/arch/arm64/kernel/cpu_errata.c
+@@ -656,6 +656,16 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
+ ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A510, 0, 0, 2)
+ },
+ #endif
++#ifdef CONFIG_ARM64_ERRATUM_2457168
++ {
++ .desc = "ARM erratum 2457168",
++ .capability = ARM64_WORKAROUND_2457168,
++ .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
++
++ /* Cortex-A510 r0p0-r1p1 */
++ CAP_MIDR_RANGE(MIDR_CORTEX_A510, 0, 0, 1, 1)
++ },
++#endif
+ #ifdef CONFIG_ARM64_ERRATUM_2038923
+ {
+ .desc = "ARM erratum 2038923",
+diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
+index ebdfbd1cf207b..f34c9f8b9ee0a 100644
+--- a/arch/arm64/kernel/cpufeature.c
++++ b/arch/arm64/kernel/cpufeature.c
+@@ -1798,7 +1798,10 @@ static void cpu_amu_enable(struct arm64_cpu_capabilities const *cap)
+ pr_info("detected CPU%d: Activity Monitors Unit (AMU)\n",
+ smp_processor_id());
+ cpumask_set_cpu(smp_processor_id(), &amu_cpus);
+- update_freq_counters_refs();
++
++ /* 0 reference values signal broken/disabled counters */
++ if (!this_cpu_has_cap(ARM64_WORKAROUND_2457168))
++ update_freq_counters_refs();
+ }
+ }
+
+diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
+index 9ab78ad826e2a..707b5451929d4 100644
+--- a/arch/arm64/kernel/topology.c
++++ b/arch/arm64/kernel/topology.c
+@@ -310,12 +310,25 @@ core_initcall(init_amu_fie);
+
+ static void cpu_read_corecnt(void *val)
+ {
++ /*
++ * A value of 0 can be returned if the current CPU does not support AMUs
++ * or if the counter is disabled for this CPU. A return value of 0 at
++ * counter read is properly handled as an error case by the users of the
++ * counter.
++ */
+ *(u64 *)val = read_corecnt();
+ }
+
+ static void cpu_read_constcnt(void *val)
+ {
+- *(u64 *)val = read_constcnt();
++ /*
++ * Return 0 if the current CPU is affected by erratum 2457168. A value
++ * of 0 is also returned if the current CPU does not support AMUs or if
++ * the counter is disabled. A return value of 0 at counter read is
++ * properly handled as an error case by the users of the counter.
++ */
++ *(u64 *)val = this_cpu_has_cap(ARM64_WORKAROUND_2457168) ?
++ 0UL : read_constcnt();
+ }
+
+ static inline
+@@ -342,7 +355,22 @@ int counters_read_on_cpu(int cpu, smp_call_func_t func, u64 *val)
+ */
+ bool cpc_ffh_supported(void)
+ {
+- return freq_counters_valid(get_cpu_with_amu_feat());
++ int cpu = get_cpu_with_amu_feat();
++
++ /*
++ * FFH is considered supported if there is at least one present CPU that
++ * supports AMUs. Using FFH to read core and reference counters for CPUs
++ * that do not support AMUs, have counters disabled or that are affected
++ * by errata, will result in a return value of 0.
++ *
++ * This is done to allow any enabled and valid counters to be read
++ * through FFH, knowing that potentially returning 0 as counter value is
++ * properly handled by the users of these counters.
++ */
++ if ((cpu >= nr_cpu_ids) || !cpumask_test_cpu(cpu, cpu_present_mask))
++ return false;
++
++ return true;
+ }
+
+ int cpc_read_ffh(int cpu, struct cpc_reg *reg, u64 *val)
+diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
+index 8809e14cf86a2..18999f46df19f 100644
+--- a/arch/arm64/tools/cpucaps
++++ b/arch/arm64/tools/cpucaps
+@@ -66,6 +66,7 @@ WORKAROUND_1902691
+ WORKAROUND_2038923
+ WORKAROUND_2064142
+ WORKAROUND_2077057
++WORKAROUND_2457168
+ WORKAROUND_TRBE_OVERWRITE_FILL_MODE
+ WORKAROUND_TSB_FLUSH_FAILURE
+ WORKAROUND_TRBE_WRITE_OUT_OF_RANGE
+--
+2.35.1
+
--- /dev/null
+From c8a1c0e8a9b689271a181d7ddbce1bf5cbd17f3f Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Wed, 17 Aug 2022 19:23:21 +0100
+Subject: arm64/signal: Raise limit on stack frames
+
+From: Mark Brown <broonie@kernel.org>
+
+[ Upstream commit 7ddcaf78e93c9282b4d92184f511b4d5bee75355 ]
+
+The signal code has a limit of 64K on the size of a stack frame that it
+will generate, if this limit is exceeded then a process will be killed if
+it receives a signal. Unfortunately with the advent of SME this limit is
+too small - the maximum possible size of the ZA register alone is 64K. This
+is not an issue for practical systems at present but is easily seen using
+virtual platforms.
+
+Raise the limit to 256K, this is substantially more than could be used by
+any current architecture extension.
+
+Signed-off-by: Mark Brown <broonie@kernel.org>
+Acked-by: Catalin Marinas <catalin.marinas@arm.com>
+Link: https://lore.kernel.org/r/20220817182324.638214-2-broonie@kernel.org
+Signed-off-by: Will Deacon <will@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/arm64/kernel/signal.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
+index 8bb631bf9464c..e8e1f46d383da 100644
+--- a/arch/arm64/kernel/signal.c
++++ b/arch/arm64/kernel/signal.c
+@@ -91,7 +91,7 @@ static size_t sigframe_size(struct rt_sigframe_user_layout const *user)
+ * not taken into account. This limit is not a guarantee and is
+ * NOT ABI.
+ */
+-#define SIGFRAME_MAXSZ SZ_64K
++#define SIGFRAME_MAXSZ SZ_256K
+
+ static int __sigframe_alloc(struct rt_sigframe_user_layout *user,
+ unsigned long *offset, size_t size, bool extend)
+--
+2.35.1
+
--- /dev/null
+From f5cb110121e25faddb2f0f4a6bfcae0901e0ebc4 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 16 Aug 2022 13:01:57 +0100
+Subject: cpufreq: check only freq_table in __resolve_freq()
+
+From: Lukasz Luba <lukasz.luba@arm.com>
+
+[ Upstream commit 6ca7076fbfaeccce173aeab832d76b9e49e1034b ]
+
+There is no need to check if the cpufreq driver implements callback
+cpufreq_driver::target_index. The logic in the __resolve_freq uses
+the frequency table available in the policy. It doesn't matter if the
+driver provides 'target_index' or 'target' callback. It just has to
+populate the 'policy->freq_table'.
+
+Thus, check only frequency table during the frequency resolving call.
+
+Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
+Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
+Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/cpufreq/cpufreq.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
+index 2cad427741647..f9fd1b6c15d42 100644
+--- a/drivers/cpufreq/cpufreq.c
++++ b/drivers/cpufreq/cpufreq.c
+@@ -532,7 +532,7 @@ static unsigned int __resolve_freq(struct cpufreq_policy *policy,
+
+ target_freq = clamp_val(target_freq, policy->min, policy->max);
+
+- if (!cpufreq_driver->target_index)
++ if (!policy->freq_table)
+ return target_freq;
+
+ idx = cpufreq_frequency_table_target(policy, target_freq, relation);
+--
+2.35.1
+
--- /dev/null
+From a0835a3395f97e48e4da5c2f6fdaa2e6984c7f97 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Mon, 22 Aug 2022 13:30:44 +0800
+Subject: drm/amdgpu: add sdma instance check for gfx11 CGCG
+
+From: Tim Huang <tim.huang@amd.com>
+
+[ Upstream commit 00047c3d967d7ef8adf8bac3c3579294a3bc0bb1 ]
+
+For some ASICs, like GFX IP v11.0.1, only have one SDMA instance,
+so not need to configure SDMA1_RLC_CGCG_CTRL for this case.
+
+Signed-off-by: Tim Huang <tim.huang@amd.com>
+Reviewed-by: Yifan Zhang <yifan1.zhang@amd.com>
+Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 18 ++++++++++++------
+ 1 file changed, 12 insertions(+), 6 deletions(-)
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+index a4a6751b1e449..30998ac47707c 100644
+--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
++++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+@@ -5090,9 +5090,12 @@ static void gfx_v11_0_update_coarse_grain_clock_gating(struct amdgpu_device *ade
+ data = REG_SET_FIELD(data, SDMA0_RLC_CGCG_CTRL, CGCG_INT_ENABLE, 1);
+ WREG32_SOC15(GC, 0, regSDMA0_RLC_CGCG_CTRL, data);
+
+- data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL);
+- data = REG_SET_FIELD(data, SDMA1_RLC_CGCG_CTRL, CGCG_INT_ENABLE, 1);
+- WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data);
++ /* Some ASICs only have one SDMA instance, not need to configure SDMA1 */
++ if (adev->sdma.num_instances > 1) {
++ data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL);
++ data = REG_SET_FIELD(data, SDMA1_RLC_CGCG_CTRL, CGCG_INT_ENABLE, 1);
++ WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data);
++ }
+ } else {
+ /* Program RLC_CGCG_CGLS_CTRL */
+ def = data = RREG32_SOC15(GC, 0, regRLC_CGCG_CGLS_CTRL);
+@@ -5121,9 +5124,12 @@ static void gfx_v11_0_update_coarse_grain_clock_gating(struct amdgpu_device *ade
+ data &= ~SDMA0_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK;
+ WREG32_SOC15(GC, 0, regSDMA0_RLC_CGCG_CTRL, data);
+
+- data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL);
+- data &= ~SDMA1_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK;
+- WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data);
++ /* Some ASICs only have one SDMA instance, not need to configure SDMA1 */
++ if (adev->sdma.num_instances > 1) {
++ data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL);
++ data &= ~SDMA1_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK;
++ WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data);
++ }
+ }
+ }
+
+--
+2.35.1
+
--- /dev/null
+From 757c9c9663a13918459691cd60f9fce38d3792b3 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 18 Aug 2022 10:47:09 +0800
+Subject: drm/amdgpu: Check num_gfx_rings for gfx v9_0 rb setup.
+
+From: Candice Li <candice.li@amd.com>
+
+[ Upstream commit c351938350ab9b5e978dede2c321da43de7eb70c ]
+
+No need to set up rb when no gfx rings.
+
+Signed-off-by: Candice Li <candice.li@amd.com>
+Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
+Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 3 ++-
+ 1 file changed, 2 insertions(+), 1 deletion(-)
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+index 5349ca4d19e38..6d8ff3b099422 100644
+--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
++++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+@@ -2587,7 +2587,8 @@ static void gfx_v9_0_constants_init(struct amdgpu_device *adev)
+
+ gfx_v9_0_tiling_mode_table_init(adev);
+
+- gfx_v9_0_setup_rb(adev);
++ if (adev->gfx.num_gfx_rings)
++ gfx_v9_0_setup_rb(adev);
+ gfx_v9_0_get_cu_info(adev, &adev->gfx.cu_info);
+ adev->gfx.config.db_debug2 = RREG32_SOC15(GC, 0, mmDB_DEBUG2);
+
+--
+2.35.1
+
--- /dev/null
+From cdd6e80a35ee40ac531fda9cf9d96e01e1c613ef Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Fri, 12 Aug 2022 14:34:35 +0800
+Subject: drm/amdgpu: fix hive reference leak when adding xgmi device
+
+From: YiPeng Chai <YiPeng.Chai@amd.com>
+
+[ Upstream commit f5994da72ba124a3d0463672fdfbec073e3bb72f ]
+
+Only amdgpu_get_xgmi_hive but no amdgpu_put_xgmi_hive
+which will leak the hive reference.
+
+Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
+Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
+Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 ++
+ 1 file changed, 2 insertions(+)
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+index 3adebb63680e0..ea2b74c0fd229 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+@@ -2482,12 +2482,14 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
+ if (!hive->reset_domain ||
+ !amdgpu_reset_get_reset_domain(hive->reset_domain)) {
+ r = -ENOENT;
++ amdgpu_put_xgmi_hive(hive);
+ goto init_failed;
+ }
+
+ /* Drop the early temporary reset domain we created for device */
+ amdgpu_reset_put_reset_domain(adev->reset_domain);
+ adev->reset_domain = hive->reset_domain;
++ amdgpu_put_xgmi_hive(hive);
+ }
+ }
+
+--
+2.35.1
+
--- /dev/null
+From 608b83deb55457627ffaeb6557d8652df74068b5 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 23 Aug 2022 14:44:06 +0800
+Subject: drm/amdgpu: mmVM_L2_CNTL3 register not initialized correctly
+
+From: Qu Huang <jinsdb@126.com>
+
+[ Upstream commit b8983d42524f10ac6bf35bbce6a7cc8e45f61e04 ]
+
+The mmVM_L2_CNTL3 register is not assigned an initial value
+
+Signed-off-by: Qu Huang <jinsdb@126.com>
+Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+index 3f44a099c52a4..3e51e773f92be 100644
+--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
++++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+@@ -176,6 +176,7 @@ static void mmhub_v1_0_init_cache_regs(struct amdgpu_device *adev)
+ tmp = REG_SET_FIELD(tmp, VM_L2_CNTL2, INVALIDATE_L2_CACHE, 1);
+ WREG32_SOC15(MMHUB, 0, mmVM_L2_CNTL2, tmp);
+
++ tmp = mmVM_L2_CNTL3_DEFAULT;
+ if (adev->gmc.translate_further) {
+ tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, 12);
+ tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3,
+--
+2.35.1
+
--- /dev/null
+From a4376ebbf2799fe677bcae02ed6d9713dab91d82 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Fri, 12 Aug 2022 13:38:34 +0800
+Subject: drm/amdgpu: Move psp_xgmi_terminate call from
+ amdgpu_xgmi_remove_device to psp_hw_fini
+
+From: YiPeng Chai <YiPeng.Chai@amd.com>
+
+[ Upstream commit 9d705d7741ae70764f3d6d87e67fad3b5c30ffd0 ]
+
+V1:
+The amdgpu_xgmi_remove_device function will send unload command
+to psp through psp ring to terminate xgmi, but psp ring has been
+destroyed in psp_hw_fini.
+
+V2:
+1. Change the commit title.
+2. Restore amdgpu_xgmi_remove_device to its original calling location.
+ Move psp_xgmi_terminate call from amdgpu_xgmi_remove_device to
+ psp_hw_fini.
+
+Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
+Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
+Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 3 +++
+ drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c | 2 +-
+ 2 files changed, 4 insertions(+), 1 deletion(-)
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+index e9411c28d88ba..2b00f8fe15a89 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+@@ -2612,6 +2612,9 @@ static int psp_hw_fini(void *handle)
+ psp_rap_terminate(psp);
+ psp_dtm_terminate(psp);
+ psp_hdcp_terminate(psp);
++
++ if (adev->gmc.xgmi.num_physical_nodes > 1)
++ psp_xgmi_terminate(psp);
+ }
+
+ psp_asd_terminate(psp);
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+index 1b108d03e7859..f2aebbf3fbe38 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+@@ -742,7 +742,7 @@ int amdgpu_xgmi_remove_device(struct amdgpu_device *adev)
+ amdgpu_put_xgmi_hive(hive);
+ }
+
+- return psp_xgmi_terminate(&adev->psp);
++ return 0;
+ }
+
+ static int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block)
+--
+2.35.1
+
--- /dev/null
+From e936b2c23a2a2183ce1f3188fd9e3da01772fcc8 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 18 Aug 2022 14:13:52 -0400
+Subject: drm/amdgpu: Remove the additional kfd pre reset call for sriov
+
+From: shaoyunl <shaoyun.liu@amd.com>
+
+[ Upstream commit 06671734881af2bcf7f453661b5f8616e32bb3fc ]
+
+The additional call is caused by merge conflict
+
+Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
+Signed-off-by: shaoyunl <shaoyun.liu@amd.com>
+Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 --
+ 1 file changed, 2 deletions(-)
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+index ea2b74c0fd229..67d4a3c13ed19 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+@@ -4475,8 +4475,6 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
+ retry:
+ amdgpu_amdkfd_pre_reset(adev);
+
+- amdgpu_amdkfd_pre_reset(adev);
+-
+ if (from_hypervisor)
+ r = amdgpu_virt_request_full_gpu(adev, true);
+ else
+--
+2.35.1
+
--- /dev/null
+From 178c824c3e84750a033b390d8facc9abfb1029ae Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Fri, 19 Aug 2022 15:28:34 +0800
+Subject: drm/gem: Fix GEM handle release errors
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+From: Jeffy Chen <jeffy.chen@rock-chips.com>
+
+[ Upstream commit ea2aa97ca37a9044ade001aef71dbc06318e8d44 ]
+
+Currently we are assuming a one to one mapping between dmabuf and
+GEM handle when releasing GEM handles.
+
+But that is not always true, since we would create extra handles for the
+GEM obj in cases like gem_open() and getfb{,2}().
+
+A similar issue was reported at:
+https://lore.kernel.org/all/20211105083308.392156-1-jay.xu@rock-chips.com/
+
+Another problem is that the imported dmabuf might not always have
+gem_obj->dma_buf set, which would cause leaks in
+drm_gem_remove_prime_handles().
+
+Let's fix these for now by using handle to find the exact map to remove.
+
+Signed-off-by: Jeffy Chen <jeffy.chen@rock-chips.com>
+Reviewed-by: Christian König <christian.koenig@amd.com>
+Signed-off-by: Christian König <christian.koenig@amd.com>
+Link: https://patchwork.freedesktop.org/patch/msgid/20220819072834.17888-1-jeffy.chen@rock-chips.com
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/gpu/drm/drm_gem.c | 17 +----------------
+ drivers/gpu/drm/drm_internal.h | 4 ++--
+ drivers/gpu/drm/drm_prime.c | 20 ++++++++++++--------
+ 3 files changed, 15 insertions(+), 26 deletions(-)
+
+diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
+index 86d670c712867..ad068865ba206 100644
+--- a/drivers/gpu/drm/drm_gem.c
++++ b/drivers/gpu/drm/drm_gem.c
+@@ -168,21 +168,6 @@ void drm_gem_private_object_init(struct drm_device *dev,
+ }
+ EXPORT_SYMBOL(drm_gem_private_object_init);
+
+-static void
+-drm_gem_remove_prime_handles(struct drm_gem_object *obj, struct drm_file *filp)
+-{
+- /*
+- * Note: obj->dma_buf can't disappear as long as we still hold a
+- * handle reference in obj->handle_count.
+- */
+- mutex_lock(&filp->prime.lock);
+- if (obj->dma_buf) {
+- drm_prime_remove_buf_handle_locked(&filp->prime,
+- obj->dma_buf);
+- }
+- mutex_unlock(&filp->prime.lock);
+-}
+-
+ /**
+ * drm_gem_object_handle_free - release resources bound to userspace handles
+ * @obj: GEM object to clean up.
+@@ -253,7 +238,7 @@ drm_gem_object_release_handle(int id, void *ptr, void *data)
+ if (obj->funcs->close)
+ obj->funcs->close(obj, file_priv);
+
+- drm_gem_remove_prime_handles(obj, file_priv);
++ drm_prime_remove_buf_handle(&file_priv->prime, id);
+ drm_vma_node_revoke(&obj->vma_node, file_priv);
+
+ drm_gem_object_handle_put_unlocked(obj);
+diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
+index 1fbbc19f1ac09..7bb98e6a446d0 100644
+--- a/drivers/gpu/drm/drm_internal.h
++++ b/drivers/gpu/drm/drm_internal.h
+@@ -74,8 +74,8 @@ int drm_prime_fd_to_handle_ioctl(struct drm_device *dev, void *data,
+
+ void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv);
+ void drm_prime_destroy_file_private(struct drm_prime_file_private *prime_fpriv);
+-void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpriv,
+- struct dma_buf *dma_buf);
++void drm_prime_remove_buf_handle(struct drm_prime_file_private *prime_fpriv,
++ uint32_t handle);
+
+ /* drm_drv.c */
+ struct drm_minor *drm_minor_acquire(unsigned int minor_id);
+diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
+index e3f09f18110c7..bd5366b16381b 100644
+--- a/drivers/gpu/drm/drm_prime.c
++++ b/drivers/gpu/drm/drm_prime.c
+@@ -190,29 +190,33 @@ static int drm_prime_lookup_buf_handle(struct drm_prime_file_private *prime_fpri
+ return -ENOENT;
+ }
+
+-void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpriv,
+- struct dma_buf *dma_buf)
++void drm_prime_remove_buf_handle(struct drm_prime_file_private *prime_fpriv,
++ uint32_t handle)
+ {
+ struct rb_node *rb;
+
+- rb = prime_fpriv->dmabufs.rb_node;
++ mutex_lock(&prime_fpriv->lock);
++
++ rb = prime_fpriv->handles.rb_node;
+ while (rb) {
+ struct drm_prime_member *member;
+
+- member = rb_entry(rb, struct drm_prime_member, dmabuf_rb);
+- if (member->dma_buf == dma_buf) {
++ member = rb_entry(rb, struct drm_prime_member, handle_rb);
++ if (member->handle == handle) {
+ rb_erase(&member->handle_rb, &prime_fpriv->handles);
+ rb_erase(&member->dmabuf_rb, &prime_fpriv->dmabufs);
+
+- dma_buf_put(dma_buf);
++ dma_buf_put(member->dma_buf);
+ kfree(member);
+- return;
+- } else if (member->dma_buf < dma_buf) {
++ break;
++ } else if (member->handle < handle) {
+ rb = rb->rb_right;
+ } else {
+ rb = rb->rb_left;
+ }
+ }
++
++ mutex_unlock(&prime_fpriv->lock);
+ }
+
+ void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv)
+--
+2.35.1
+
--- /dev/null
+From b0cd3e162020cc1c4964859ad1ce9e7574883d1e Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 11 Aug 2022 15:25:40 +0800
+Subject: drm/radeon: add a force flush to delay work when radeon
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+From: Zhenneng Li <lizhenneng@kylinos.cn>
+
+[ Upstream commit f461950fdc374a3ada5a63c669d997de4600dffe ]
+
+Although radeon card fence and wait for gpu to finish processing current batch rings,
+there is still a corner case that radeon lockup work queue may not be fully flushed,
+and meanwhile the radeon_suspend_kms() function has called pci_set_power_state() to
+put device in D3hot state.
+Per PCI spec rev 4.0 on 5.3.1.4.1 D3hot State.
+> Configuration and Message requests are the only TLPs accepted by a Function in
+> the D3hot state. All other received Requests must be handled as Unsupported Requests,
+> and all received Completions may optionally be handled as Unexpected Completions.
+This issue will happen in following logs:
+Unable to handle kernel paging request at virtual address 00008800e0008010
+CPU 0 kworker/0:3(131): Oops 0
+pc = [<ffffffff811bea5c>] ra = [<ffffffff81240844>] ps = 0000 Tainted: G W
+pc is at si_gpu_check_soft_reset+0x3c/0x240
+ra is at si_dma_is_lockup+0x34/0xd0
+v0 = 0000000000000000 t0 = fff08800e0008010 t1 = 0000000000010000
+t2 = 0000000000008010 t3 = fff00007e3c00000 t4 = fff00007e3c00258
+t5 = 000000000000ffff t6 = 0000000000000001 t7 = fff00007ef078000
+s0 = fff00007e3c016e8 s1 = fff00007e3c00000 s2 = fff00007e3c00018
+s3 = fff00007e3c00000 s4 = fff00007fff59d80 s5 = 0000000000000000
+s6 = fff00007ef07bd98
+a0 = fff00007e3c00000 a1 = fff00007e3c016e8 a2 = 0000000000000008
+a3 = 0000000000000001 a4 = 8f5c28f5c28f5c29 a5 = ffffffff810f4338
+t8 = 0000000000000275 t9 = ffffffff809b66f8 t10 = ff6769c5d964b800
+t11= 000000000000b886 pv = ffffffff811bea20 at = 0000000000000000
+gp = ffffffff81d89690 sp = 00000000aa814126
+Disabling lock debugging due to kernel taint
+Trace:
+[<ffffffff81240844>] si_dma_is_lockup+0x34/0xd0
+[<ffffffff81119610>] radeon_fence_check_lockup+0xd0/0x290
+[<ffffffff80977010>] process_one_work+0x280/0x550
+[<ffffffff80977350>] worker_thread+0x70/0x7c0
+[<ffffffff80977410>] worker_thread+0x130/0x7c0
+[<ffffffff80982040>] kthread+0x200/0x210
+[<ffffffff809772e0>] worker_thread+0x0/0x7c0
+[<ffffffff80981f8c>] kthread+0x14c/0x210
+[<ffffffff80911658>] ret_from_kernel_thread+0x18/0x20
+[<ffffffff80981e40>] kthread+0x0/0x210
+ Code: ad3e0008 43f0074a ad7e0018 ad9e0020 8c3001e8 40230101
+ <88210000> 4821ed21
+So force lockup work queue flush to fix this problem.
+
+Acked-by: Christian König <christian.koenig@amd.com>
+Signed-off-by: Zhenneng Li <lizhenneng@kylinos.cn>
+Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/gpu/drm/radeon/radeon_device.c | 3 +++
+ 1 file changed, 3 insertions(+)
+
+diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
+index 429644d5ddc69..9fba16cb3f1e7 100644
+--- a/drivers/gpu/drm/radeon/radeon_device.c
++++ b/drivers/gpu/drm/radeon/radeon_device.c
+@@ -1604,6 +1604,9 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend,
+ if (r) {
+ /* delay GPU reset to resume */
+ radeon_fence_driver_force_completion(rdev, i);
++ } else {
++ /* finish executing delayed work */
++ flush_delayed_work(&rdev->fence_drv[i].lockup_work);
+ }
+ }
+
+--
+2.35.1
+
--- /dev/null
+From 6cd33465e68c48a3cab0e5ef7275205028bb20e5 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Fri, 19 Aug 2022 16:57:52 +0800
+Subject: fbdev: chipsfb: Add missing pci_disable_device() in
+ chipsfb_pci_init()
+
+From: Yang Yingliang <yangyingliang@huawei.com>
+
+[ Upstream commit 07c55c9803dea748d17a054000cbf1913ce06399 ]
+
+Add missing pci_disable_device() in error path in chipsfb_pci_init().
+
+Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
+Signed-off-by: Helge Deller <deller@gmx.de>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/video/fbdev/chipsfb.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+diff --git a/drivers/video/fbdev/chipsfb.c b/drivers/video/fbdev/chipsfb.c
+index 393894af26f84..2b00a9d554fc0 100644
+--- a/drivers/video/fbdev/chipsfb.c
++++ b/drivers/video/fbdev/chipsfb.c
+@@ -430,6 +430,7 @@ static int chipsfb_pci_init(struct pci_dev *dp, const struct pci_device_id *ent)
+ err_release_fb:
+ framebuffer_release(p);
+ err_disable:
++ pci_disable_device(dp);
+ err_out:
+ return rc;
+ }
+--
+2.35.1
+
--- /dev/null
+From 9f8ed2b41bf789ea4aba760267189760515b50e5 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Sun, 21 Aug 2022 20:17:31 +0900
+Subject: fbdev: fbcon: Destroy mutex on freeing struct fb_info
+
+From: Shigeru Yoshida <syoshida@redhat.com>
+
+[ Upstream commit 58559dfc1ebba2ae0c7627dc8f8991ae1984c6e3 ]
+
+It's needed to destroy bl_curve_mutex on freeing struct fb_info since
+the mutex is embedded in the structure and initialized when it's
+allocated.
+
+Signed-off-by: Shigeru Yoshida <syoshida@redhat.com>
+Signed-off-by: Helge Deller <deller@gmx.de>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/video/fbdev/core/fbsysfs.c | 4 ++++
+ 1 file changed, 4 insertions(+)
+
+diff --git a/drivers/video/fbdev/core/fbsysfs.c b/drivers/video/fbdev/core/fbsysfs.c
+index c2a60b187467e..4d7f63892dcc4 100644
+--- a/drivers/video/fbdev/core/fbsysfs.c
++++ b/drivers/video/fbdev/core/fbsysfs.c
+@@ -84,6 +84,10 @@ void framebuffer_release(struct fb_info *info)
+ if (WARN_ON(refcount_read(&info->count)))
+ return;
+
++#if IS_ENABLED(CONFIG_FB_BACKLIGHT)
++ mutex_destroy(&info->bl_curve_mutex);
++#endif
++
+ kfree(info->apertures);
+ kfree(info);
+ }
+--
+2.35.1
+
--- /dev/null
+From 8039bb036f9c55168903c38d4221d5e0492b7f40 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Fri, 12 Aug 2022 14:52:23 +0800
+Subject: fbdev: omapfb: Fix tests for platform_get_irq() failure
+
+From: Yu Zhe <yuzhe@nfschina.com>
+
+[ Upstream commit acf4c6205e862304681234a6a4375b478af12552 ]
+
+The platform_get_irq() returns negative error codes. It can't actually
+return zero.
+
+Signed-off-by: Yu Zhe <yuzhe@nfschina.com>
+Signed-off-by: Helge Deller <deller@gmx.de>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/video/fbdev/omap/omapfb_main.c | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+diff --git a/drivers/video/fbdev/omap/omapfb_main.c b/drivers/video/fbdev/omap/omapfb_main.c
+index 292fcb0a24fc9..6ff237cee7f87 100644
+--- a/drivers/video/fbdev/omap/omapfb_main.c
++++ b/drivers/video/fbdev/omap/omapfb_main.c
+@@ -1643,14 +1643,14 @@ static int omapfb_do_probe(struct platform_device *pdev,
+ goto cleanup;
+ }
+ fbdev->int_irq = platform_get_irq(pdev, 0);
+- if (!fbdev->int_irq) {
++ if (fbdev->int_irq < 0) {
+ dev_err(&pdev->dev, "unable to get irq\n");
+ r = ENXIO;
+ goto cleanup;
+ }
+
+ fbdev->ext_irq = platform_get_irq(pdev, 1);
+- if (!fbdev->ext_irq) {
++ if (fbdev->ext_irq < 0) {
+ dev_err(&pdev->dev, "unable to get irq\n");
+ r = ENXIO;
+ goto cleanup;
+--
+2.35.1
+
--- /dev/null
+From 50ac70eb75205acea496b504855ae4342d00b5b5 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 11 Aug 2022 11:14:13 -0600
+Subject: md: Flush workqueue md_rdev_misc_wq in md_alloc()
+
+From: David Sloan <david.sloan@eideticom.com>
+
+[ Upstream commit 5e8daf906f890560df430d30617c692a794acb73 ]
+
+A race condition still exists when removing and re-creating md devices
+in test cases. However, it is only seen on some setups.
+
+The race condition was tracked down to a reference still being held
+to the kobject by the rdev in the md_rdev_misc_wq which will be released
+in rdev_delayed_delete().
+
+md_alloc() waits for previous deletions by waiting on the md_misc_wq,
+but the md_rdev_misc_wq may still be holding a reference to a recently
+removed device.
+
+To fix this, also flush the md_rdev_misc_wq in md_alloc().
+
+Signed-off-by: David Sloan <david.sloan@eideticom.com>
+[logang@deltatee.com: rewrote commit message]
+Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
+Signed-off-by: Song Liu <song@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/md/md.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+diff --git a/drivers/md/md.c b/drivers/md/md.c
+index 91e7e80fce489..25d18b67a1620 100644
+--- a/drivers/md/md.c
++++ b/drivers/md/md.c
+@@ -5647,6 +5647,7 @@ static int md_alloc(dev_t dev, char *name)
+ * removed (mddev_delayed_delete).
+ */
+ flush_workqueue(md_misc_wq);
++ flush_workqueue(md_rdev_misc_wq);
+
+ mutex_lock(&disks_mutex);
+ mddev = mddev_alloc(dev);
+--
+2.35.1
+
--- /dev/null
+From 5bcab1a3803d0c8c2b84284842f2ed9f6ef82434 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Mon, 22 Aug 2022 22:44:11 -0700
+Subject: net/core/skbuff: Check the return value of skb_copy_bits()
+
+From: lily <floridsleeves@gmail.com>
+
+[ Upstream commit c624c58e08b15105662b9ab9be23d14a6b945a49 ]
+
+skb_copy_bits() could fail, which requires a check on the return
+value.
+
+Signed-off-by: Li Zhong <floridsleeves@gmail.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/core/skbuff.c | 5 ++---
+ 1 file changed, 2 insertions(+), 3 deletions(-)
+
+diff --git a/net/core/skbuff.c b/net/core/skbuff.c
+index bebf58464d667..4b2b07a9422cf 100644
+--- a/net/core/skbuff.c
++++ b/net/core/skbuff.c
+@@ -4179,9 +4179,8 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
+ SKB_GSO_CB(nskb)->csum_start =
+ skb_headroom(nskb) + doffset;
+ } else {
+- skb_copy_bits(head_skb, offset,
+- skb_put(nskb, len),
+- len);
++ if (skb_copy_bits(head_skb, offset, skb_put(nskb, len), len))
++ goto err;
+ }
+ continue;
+ }
+--
+2.35.1
+
--- /dev/null
+From 7f159f1844280cfb41183684d22553ea428aba81 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Fri, 19 Aug 2022 00:42:31 +0200
+Subject: netfilter: conntrack: work around exceeded receive window
+
+From: Florian Westphal <fw@strlen.de>
+
+[ Upstream commit cf97769c761abfeac8931b35fe0e1a8d5fabc9d8 ]
+
+When a TCP sends more bytes than allowed by the receive window, all future
+packets can be marked as invalid.
+This can clog up the conntrack table because of 5-day default timeout.
+
+Sequence of packets:
+ 01 initiator > responder: [S], seq 171, win 5840, options [mss 1330,sackOK,TS val 63 ecr 0,nop,wscale 1]
+ 02 responder > initiator: [S.], seq 33211, ack 172, win 65535, options [mss 1460,sackOK,TS val 010 ecr 63,nop,wscale 8]
+ 03 initiator > responder: [.], ack 33212, win 2920, options [nop,nop,TS val 068 ecr 010], length 0
+ 04 initiator > responder: [P.], seq 172:240, ack 33212, win 2920, options [nop,nop,TS val 279 ecr 010], length 68
+
+Window is 5840 starting from 33212 -> 39052.
+
+ 05 responder > initiator: [.], ack 240, win 256, options [nop,nop,TS val 872 ecr 279], length 0
+ 06 responder > initiator: [.], seq 33212:34530, ack 240, win 256, options [nop,nop,TS val 892 ecr 279], length 1318
+
+This is fine, conntrack will flag the connection as having outstanding
+data (UNACKED), which lowers the conntrack timeout to 300s.
+
+ 07 responder > initiator: [.], seq 34530:35848, ack 240, win 256, options [nop,nop,TS val 892 ecr 279], length 1318
+ 08 responder > initiator: [.], seq 35848:37166, ack 240, win 256, options [nop,nop,TS val 892 ecr 279], length 1318
+ 09 responder > initiator: [.], seq 37166:38484, ack 240, win 256, options [nop,nop,TS val 892 ecr 279], length 1318
+ 10 responder > initiator: [.], seq 38484:39802, ack 240, win 256, options [nop,nop,TS val 892 ecr 279], length 1318
+
+Packet 10 is already sending more than permitted, but conntrack doesn't
+validate this (only seq is tested vs. maxend, not 'seq+len').
+
+38484 is acceptable, but only up to 39052, so this packet should
+not have been sent (or only 568 bytes, not 1318).
+
+At this point, connection is still in '300s' mode.
+
+Next packet however will get flagged:
+ 11 responder > initiator: [P.], seq 39802:40128, ack 240, win 256, options [nop,nop,TS val 892 ecr 279], length 326
+
+nf_ct_proto_6: SEQ is over the upper bound (over the window of the receiver) .. LEN=378 .. SEQ=39802 ACK=240 ACK PSH ..
+
+Now, a couple of replies/acks comes in:
+
+ 12 initiator > responder: [.], ack 34530, win 4368,
+[.. irrelevant acks removed ]
+ 16 initiator > responder: [.], ack 39802, win 8712, options [nop,nop,TS val 296201291 ecr 2982371892], length 0
+
+This ack is significant -- this acks the last packet send by the
+responder that conntrack considered valid.
+
+This means that ack == td_end. This will withdraw the
+'unacked data' flag, the connection moves back to the 5-day timeout
+of established conntracks.
+
+ 17 initiator > responder: ack 40128, win 10030, ...
+
+This packet is also flagged as invalid.
+
+Because conntrack only updates state based on packets that are
+considered valid, packet 11 'did not exist' and that gets us:
+
+nf_ct_proto_6: ACK is over upper bound 39803 (ACKed data not seen yet) .. SEQ=240 ACK=40128 WINDOW=10030 RES=0x00 ACK URG
+
+Because this received and processed by the endpoints, the conntrack entry
+remains in a bad state, no packets will ever be considered valid again:
+
+ 30 responder > initiator: [F.], seq 40432, ack 2045, win 391, ..
+ 31 initiator > responder: [.], ack 40433, win 11348, ..
+ 32 initiator > responder: [F.], seq 2045, ack 40433, win 11348 ..
+
+... all trigger 'ACK is over bound' test and we end up with
+non-early-evictable 5-day default timeout.
+
+NB: This patch triggers a bunch of checkpatch warnings because of silly
+indent. I will resend the cleanup series linked below to reduce the
+indent level once this change has propagated to net-next.
+
+I could route the cleanup via nf but that causes extra backport work for
+stable maintainers.
+
+Link: https://lore.kernel.org/netfilter-devel/20220720175228.17880-1-fw@strlen.de/T/#mb1d7147d36294573cc4f81d00f9f8dadfdd06cd8
+Signed-off-by: Florian Westphal <fw@strlen.de>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/netfilter/nf_conntrack_proto_tcp.c | 31 ++++++++++++++++++++++++++
+ 1 file changed, 31 insertions(+)
+
+diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
+index a63b51dceaf2c..a634c72b1ffcf 100644
+--- a/net/netfilter/nf_conntrack_proto_tcp.c
++++ b/net/netfilter/nf_conntrack_proto_tcp.c
+@@ -655,6 +655,37 @@ static bool tcp_in_window(struct nf_conn *ct,
+ tn->tcp_be_liberal)
+ res = true;
+ if (!res) {
++ bool seq_ok = before(seq, sender->td_maxend + 1);
++
++ if (!seq_ok) {
++ u32 overshot = end - sender->td_maxend + 1;
++ bool ack_ok;
++
++ ack_ok = after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1);
++
++ if (in_recv_win &&
++ ack_ok &&
++ overshot <= receiver->td_maxwin &&
++ before(sack, receiver->td_end + 1)) {
++ /* Work around TCPs that send more bytes than allowed by
++ * the receive window.
++ *
++ * If the (marked as invalid) packet is allowed to pass by
++ * the ruleset and the peer acks this data, then its possible
++ * all future packets will trigger 'ACK is over upper bound' check.
++ *
++ * Thus if only the sequence check fails then do update td_end so
++ * possible ACK for this data can update internal state.
++ */
++ sender->td_end = end;
++ sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED;
++
++ nf_ct_l4proto_log_invalid(skb, ct, hook_state,
++ "%u bytes more than expected", overshot);
++ return res;
++ }
++ }
++
+ nf_ct_l4proto_log_invalid(skb, ct, hook_state,
+ "%s",
+ before(seq, sender->td_maxend + 1) ?
+--
+2.35.1
+
--- /dev/null
+From f463f79a910ac7628552550a58268a0dd88d8112 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Sun, 21 Aug 2022 14:49:58 +0200
+Subject: parisc: Add runtime check to prevent PA2.0 kernels on PA1.x machines
+
+From: Helge Deller <deller@gmx.de>
+
+[ Upstream commit 591d2108f3abc4db9f9073cae37cf3591fd250d6 ]
+
+If a 32-bit kernel was compiled for PA2.0 CPUs, it won't be able to run
+on machines with PA1.x CPUs. Add a check and bail out early if a PA1.x
+machine is detected.
+
+Signed-off-by: Helge Deller <deller@gmx.de>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/parisc/kernel/head.S | 43 ++++++++++++++++++++++++++++++++++++++-
+ 1 file changed, 42 insertions(+), 1 deletion(-)
+
+diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S
+index e0a9e96576221..fd15fd4bbb61b 100644
+--- a/arch/parisc/kernel/head.S
++++ b/arch/parisc/kernel/head.S
+@@ -22,7 +22,7 @@
+ #include <linux/init.h>
+ #include <linux/pgtable.h>
+
+- .level PA_ASM_LEVEL
++ .level 1.1
+
+ __INITDATA
+ ENTRY(boot_args)
+@@ -70,6 +70,47 @@ $bss_loop:
+ stw,ma %arg2,4(%r1)
+ stw,ma %arg3,4(%r1)
+
++#if !defined(CONFIG_64BIT) && defined(CONFIG_PA20)
++ /* This 32-bit kernel was compiled for PA2.0 CPUs. Check current CPU
++ * and halt kernel if we detect a PA1.x CPU. */
++ ldi 32,%r10
++ mtctl %r10,%cr11
++ .level 2.0
++ mfctl,w %cr11,%r10
++ .level 1.1
++ comib,<>,n 0,%r10,$cpu_ok
++
++ load32 PA(msg1),%arg0
++ ldi msg1_end-msg1,%arg1
++$iodc_panic:
++ copy %arg0, %r10
++ copy %arg1, %r11
++ load32 PA(init_stack),%sp
++#define MEM_CONS 0x3A0
++ ldw MEM_CONS+32(%r0),%arg0 // HPA
++ ldi ENTRY_IO_COUT,%arg1
++ ldw MEM_CONS+36(%r0),%arg2 // SPA
++ ldw MEM_CONS+8(%r0),%arg3 // layers
++ load32 PA(__bss_start),%r1
++ stw %r1,-52(%sp) // arg4
++ stw %r0,-56(%sp) // arg5
++ stw %r10,-60(%sp) // arg6 = ptr to text
++ stw %r11,-64(%sp) // arg7 = len
++ stw %r0,-68(%sp) // arg8
++ load32 PA(.iodc_panic_ret), %rp
++ ldw MEM_CONS+40(%r0),%r1 // ENTRY_IODC
++ bv,n (%r1)
++.iodc_panic_ret:
++ b . /* wait endless with ... */
++ or %r10,%r10,%r10 /* qemu idle sleep */
++msg1: .ascii "Can't boot kernel which was built for PA8x00 CPUs on this machine.\r\n"
++msg1_end:
++
++$cpu_ok:
++#endif
++
++ .level PA_ASM_LEVEL
++
+ /* Initialize startup VM. Just map first 16/32 MB of memory */
+ load32 PA(swapper_pg_dir),%r4
+ mtctl %r4,%cr24 /* Initialize kernel root pointer */
+--
+2.35.1
+
--- /dev/null
+From d992bcc02a5eb26ace85453472b17d0f074f61db Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Fri, 19 Aug 2022 12:15:10 +0800
+Subject: parisc: ccio-dma: Handle kmalloc failure in ccio_init_resources()
+
+From: Li Qiong <liqiong@nfschina.com>
+
+[ Upstream commit d46c742f827fa2326ab1f4faa1cccadb56912341 ]
+
+As the possible failure of the kmalloc(), it should be better
+to fix this error path, check and return '-ENOMEM' error code.
+
+Signed-off-by: Li Qiong <liqiong@nfschina.com>
+Signed-off-by: Helge Deller <deller@gmx.de>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/parisc/ccio-dma.c | 11 ++++++++---
+ 1 file changed, 8 insertions(+), 3 deletions(-)
+
+diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c
+index 9be007c9420f9..f69ab90b5e22d 100644
+--- a/drivers/parisc/ccio-dma.c
++++ b/drivers/parisc/ccio-dma.c
+@@ -1380,15 +1380,17 @@ ccio_init_resource(struct resource *res, char *name, void __iomem *ioaddr)
+ }
+ }
+
+-static void __init ccio_init_resources(struct ioc *ioc)
++static int __init ccio_init_resources(struct ioc *ioc)
+ {
+ struct resource *res = ioc->mmio_region;
+ char *name = kmalloc(14, GFP_KERNEL);
+-
++ if (unlikely(!name))
++ return -ENOMEM;
+ snprintf(name, 14, "GSC Bus [%d/]", ioc->hw_path);
+
+ ccio_init_resource(res, name, &ioc->ioc_regs->io_io_low);
+ ccio_init_resource(res + 1, name, &ioc->ioc_regs->io_io_low_hv);
++ return 0;
+ }
+
+ static int new_ioc_area(struct resource *res, unsigned long size,
+@@ -1543,7 +1545,10 @@ static int __init ccio_probe(struct parisc_device *dev)
+ return -ENOMEM;
+ }
+ ccio_ioc_init(ioc);
+- ccio_init_resources(ioc);
++ if (ccio_init_resources(ioc)) {
++ kfree(ioc);
++ return -ENOMEM;
++ }
+ hppa_dma_ops = &ccio_ops;
+
+ hba = kzalloc(sizeof(*hba), GFP_KERNEL);
+--
+2.35.1
+
--- /dev/null
+From 8ec4bbce9edfafa45b8c969ed42252ae20093b6e Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Sun, 21 Aug 2022 08:12:19 +0200
+Subject: Revert "parisc: Show error if wrong 32/64-bit compiler is being used"
+
+From: Helge Deller <deller@gmx.de>
+
+[ Upstream commit b4b18f47f4f9682fbf5827682645da7c8dde8f80 ]
+
+This reverts commit b160628e9ebcdc85d0db9d7f423c26b3c7c179d0.
+
+There is no need any longer to have this sanity check, because the
+previous commit ("parisc: Make CONFIG_64BIT available for ARCH=parisc64
+only") prevents that CONFIG_64BIT is set if ARCH==parisc.
+
+Signed-off-by: Helge Deller <deller@gmx.de>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/parisc/include/asm/bitops.h | 8 --------
+ 1 file changed, 8 deletions(-)
+
+diff --git a/arch/parisc/include/asm/bitops.h b/arch/parisc/include/asm/bitops.h
+index 56ffd260c669b..0ec9cfc5131fc 100644
+--- a/arch/parisc/include/asm/bitops.h
++++ b/arch/parisc/include/asm/bitops.h
+@@ -12,14 +12,6 @@
+ #include <asm/barrier.h>
+ #include <linux/atomic.h>
+
+-/* compiler build environment sanity checks: */
+-#if !defined(CONFIG_64BIT) && defined(__LP64__)
+-#error "Please use 'ARCH=parisc' to build the 32-bit kernel."
+-#endif
+-#if defined(CONFIG_64BIT) && !defined(__LP64__)
+-#error "Please use 'ARCH=parisc64' to build the 64-bit kernel."
+-#endif
+-
+ /* See http://marc.theaimsgroup.com/?t=108826637900003 for discussion
+ * on use of volatile and __*_bit() (set/clear/change):
+ * *_bit() want use of volatile.
+--
+2.35.1
+
--- /dev/null
+From ead5774450145690402e686e8cadd909f3249734 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Fri, 29 Jul 2022 14:41:10 -0700
+Subject: scsi: core: Allow the ALUA transitioning state enough time
+
+From: Brian Bunker <brian@purestorage.com>
+
+[ Upstream commit 54249306e2776774ccb827969e62d34570f991db ]
+
+The error path for the SCSI check condition of not ready, target in ALUA
+state transition, will result in the failure of that path after the retries
+are exhausted. In most cases that is well ahead of the transition timeout
+established in the SCSI ALUA device handler.
+
+Instead, reprep the command and re-add it to the queue after a 1 second
+delay. This will allow the handler to take care of the timeout and only
+fail the path if the target has exceeded the transition expiry timeout
+(default 60 seconds). If the expiry timeout is exceeded, the handler will
+change the path state from transitioning to standby leading to a path
+failure eliminating the potential of this re-prep to continue endlessly. In
+most cases the target will exit the transitioning state well before the
+expiry timeout but after the retries are exhausted as mentioned.
+
+Additionally remove the scsi_io_completion_reprep() function which provides
+little value.
+
+Link: https://lore.kernel.org/r/20220729214110.58576-1-brian@purestorage.com
+Reviewed-by: Martin Wilck <mwilck@suse.com>
+Acked-by: Krishna Kant <krishna.kant@purestorage.com>
+Acked-by: Seamus Connor <sconnor@purestorage.com>
+Signed-off-by: Brian Bunker <brian@purestorage.com>
+Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/scsi/scsi_lib.c | 44 +++++++++++++++++++++++------------------
+ 1 file changed, 25 insertions(+), 19 deletions(-)
+
+diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
+index 78edb1ea4748d..f5c876d03c1ad 100644
+--- a/drivers/scsi/scsi_lib.c
++++ b/drivers/scsi/scsi_lib.c
+@@ -118,7 +118,7 @@ scsi_set_blocked(struct scsi_cmnd *cmd, int reason)
+ }
+ }
+
+-static void scsi_mq_requeue_cmd(struct scsi_cmnd *cmd)
++static void scsi_mq_requeue_cmd(struct scsi_cmnd *cmd, unsigned long msecs)
+ {
+ struct request *rq = scsi_cmd_to_rq(cmd);
+
+@@ -128,7 +128,12 @@ static void scsi_mq_requeue_cmd(struct scsi_cmnd *cmd)
+ } else {
+ WARN_ON_ONCE(true);
+ }
+- blk_mq_requeue_request(rq, true);
++
++ if (msecs) {
++ blk_mq_requeue_request(rq, false);
++ blk_mq_delay_kick_requeue_list(rq->q, msecs);
++ } else
++ blk_mq_requeue_request(rq, true);
+ }
+
+ /**
+@@ -658,14 +663,6 @@ static unsigned int scsi_rq_err_bytes(const struct request *rq)
+ return bytes;
+ }
+
+-/* Helper for scsi_io_completion() when "reprep" action required. */
+-static void scsi_io_completion_reprep(struct scsi_cmnd *cmd,
+- struct request_queue *q)
+-{
+- /* A new command will be prepared and issued. */
+- scsi_mq_requeue_cmd(cmd);
+-}
+-
+ static bool scsi_cmd_runtime_exceeced(struct scsi_cmnd *cmd)
+ {
+ struct request *req = scsi_cmd_to_rq(cmd);
+@@ -683,14 +680,21 @@ static bool scsi_cmd_runtime_exceeced(struct scsi_cmnd *cmd)
+ return false;
+ }
+
++/*
++ * When ALUA transition state is returned, reprep the cmd to
++ * use the ALUA handler's transition timeout. Delay the reprep
++ * 1 sec to avoid aggressive retries of the target in that
++ * state.
++ */
++#define ALUA_TRANSITION_REPREP_DELAY 1000
++
+ /* Helper for scsi_io_completion() when special action required. */
+ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result)
+ {
+- struct request_queue *q = cmd->device->request_queue;
+ struct request *req = scsi_cmd_to_rq(cmd);
+ int level = 0;
+- enum {ACTION_FAIL, ACTION_REPREP, ACTION_RETRY,
+- ACTION_DELAYED_RETRY} action;
++ enum {ACTION_FAIL, ACTION_REPREP, ACTION_DELAYED_REPREP,
++ ACTION_RETRY, ACTION_DELAYED_RETRY} action;
+ struct scsi_sense_hdr sshdr;
+ bool sense_valid;
+ bool sense_current = true; /* false implies "deferred sense" */
+@@ -779,8 +783,8 @@ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result)
+ action = ACTION_DELAYED_RETRY;
+ break;
+ case 0x0a: /* ALUA state transition */
+- blk_stat = BLK_STS_TRANSPORT;
+- fallthrough;
++ action = ACTION_DELAYED_REPREP;
++ break;
+ default:
+ action = ACTION_FAIL;
+ break;
+@@ -839,7 +843,10 @@ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result)
+ return;
+ fallthrough;
+ case ACTION_REPREP:
+- scsi_io_completion_reprep(cmd, q);
++ scsi_mq_requeue_cmd(cmd, 0);
++ break;
++ case ACTION_DELAYED_REPREP:
++ scsi_mq_requeue_cmd(cmd, ALUA_TRANSITION_REPREP_DELAY);
+ break;
+ case ACTION_RETRY:
+ /* Retry the same command immediately */
+@@ -933,7 +940,7 @@ static int scsi_io_completion_nz_result(struct scsi_cmnd *cmd, int result,
+ * command block will be released and the queue function will be goosed. If we
+ * are not done then we have to figure out what to do next:
+ *
+- * a) We can call scsi_io_completion_reprep(). The request will be
++ * a) We can call scsi_mq_requeue_cmd(). The request will be
+ * unprepared and put back on the queue. Then a new command will
+ * be created for it. This should be used if we made forward
+ * progress, or if we want to switch from READ(10) to READ(6) for
+@@ -949,7 +956,6 @@ static int scsi_io_completion_nz_result(struct scsi_cmnd *cmd, int result,
+ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
+ {
+ int result = cmd->result;
+- struct request_queue *q = cmd->device->request_queue;
+ struct request *req = scsi_cmd_to_rq(cmd);
+ blk_status_t blk_stat = BLK_STS_OK;
+
+@@ -986,7 +992,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
+ * request just queue the command up again.
+ */
+ if (likely(result == 0))
+- scsi_io_completion_reprep(cmd, q);
++ scsi_mq_requeue_cmd(cmd, 0);
+ else
+ scsi_io_completion_action(cmd, result);
+ }
+--
+2.35.1
+
--- /dev/null
+From 25aa86ee786fe9be54c8c90c8f3b995ac13b7955 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 2 Aug 2022 15:18:49 +0800
+Subject: scsi: megaraid_sas: Fix double kfree()
+
+From: Guixin Liu <kanie@linux.alibaba.com>
+
+[ Upstream commit 8c499e49240bd93628368c3588975cfb94169b8b ]
+
+When allocating log_to_span fails, kfree(instance->ctrl_context) is called
+twice. Remove redundant call.
+
+Link: https://lore.kernel.org/r/1659424729-46502-1-git-send-email-kanie@linux.alibaba.com
+Acked-by: Sumit Saxena <sumit.saxena@broadcom.com>
+Signed-off-by: Guixin Liu <kanie@linux.alibaba.com>
+Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/scsi/megaraid/megaraid_sas_fusion.c | 1 -
+ 1 file changed, 1 deletion(-)
+
+diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
+index 5b5885d9732b6..3e9b2b0099c7a 100644
+--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
++++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
+@@ -5311,7 +5311,6 @@ megasas_alloc_fusion_context(struct megasas_instance *instance)
+ if (!fusion->log_to_span) {
+ dev_err(&instance->pdev->dev, "Failed from %s %d\n",
+ __func__, __LINE__);
+- kfree(instance->ctrl_context);
+ return -ENOMEM;
+ }
+ }
+--
+2.35.1
+
--- /dev/null
+From 29db7a8736e25e199d647289c38d7f62585224a4 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 7 Jul 2022 15:08:01 -0400
+Subject: scsi: qla2xxx: Disable ATIO interrupt coalesce for quad port ISP27XX
+
+From: Tony Battersby <tonyb@cybernetics.com>
+
+[ Upstream commit 53661ded2460b414644532de6b99bd87f71987e9 ]
+
+This partially reverts commit d2b292c3f6fd ("scsi: qla2xxx: Enable ATIO
+interrupt handshake for ISP27XX")
+
+For some workloads where the host sends a batch of commands and then
+pauses, ATIO interrupt coalesce can cause some incoming ATIO entries to be
+ignored for extended periods of time, resulting in slow performance,
+timeouts, and aborted commands.
+
+Disable interrupt coalesce and re-enable the dedicated ATIO MSI-X
+interrupt.
+
+Link: https://lore.kernel.org/r/97dcf365-89ff-014d-a3e5-1404c6af511c@cybernetics.com
+Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
+Reviewed-by: Nilesh Javali <njavali@marvell.com>
+Signed-off-by: Tony Battersby <tonyb@cybernetics.com>
+Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/scsi/qla2xxx/qla_target.c | 10 ++--------
+ 1 file changed, 2 insertions(+), 8 deletions(-)
+
+diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
+index 2b2f682883752..62666df1a59eb 100644
+--- a/drivers/scsi/qla2xxx/qla_target.c
++++ b/drivers/scsi/qla2xxx/qla_target.c
+@@ -6935,14 +6935,8 @@ qlt_24xx_config_rings(struct scsi_qla_host *vha)
+
+ if (ha->flags.msix_enabled) {
+ if (IS_QLA83XX(ha) || IS_QLA27XX(ha) || IS_QLA28XX(ha)) {
+- if (IS_QLA2071(ha)) {
+- /* 4 ports Baker: Enable Interrupt Handshake */
+- icb->msix_atio = 0;
+- icb->firmware_options_2 |= cpu_to_le32(BIT_26);
+- } else {
+- icb->msix_atio = cpu_to_le16(msix->entry);
+- icb->firmware_options_2 &= cpu_to_le32(~BIT_26);
+- }
++ icb->msix_atio = cpu_to_le16(msix->entry);
++ icb->firmware_options_2 &= cpu_to_le32(~BIT_26);
+ ql_dbg(ql_dbg_init, vha, 0xf072,
+ "Registering ICB vector 0x%x for atio que.\n",
+ msix->entry);
+--
+2.35.1
+
--- /dev/null
+From 74e5fbf4cdeff6916bd9ed98b2cc2bcf3903cdf2 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 11 Aug 2022 16:43:49 -0700
+Subject: scsi: ufs: core: Reduce the power mode change timeout
+
+From: Bart Van Assche <bvanassche@acm.org>
+
+[ Upstream commit 8f2c96420c6ec3dcb18c8be923e24c6feaa5ccf6 ]
+
+The current power mode change timeout (180 s) is so large that it can cause
+a watchdog timer to fire. Reduce the power mode change timeout to 10
+seconds.
+
+Link: https://lore.kernel.org/r/20220811234401.1957911-1-bvanassche@acm.org
+Reviewed-by: Stanley Chu <stanley.chu@mediatek.com>
+Signed-off-by: Bart Van Assche <bvanassche@acm.org>
+Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/ufs/core/ufshcd.c | 9 ++++++++-
+ 1 file changed, 8 insertions(+), 1 deletion(-)
+
+diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
+index a51ca56a0ebe7..829da9cb14a86 100644
+--- a/drivers/ufs/core/ufshcd.c
++++ b/drivers/ufs/core/ufshcd.c
+@@ -8723,6 +8723,8 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,
+ struct scsi_device *sdp;
+ unsigned long flags;
+ int ret, retries;
++ unsigned long deadline;
++ int32_t remaining;
+
+ spin_lock_irqsave(hba->host->host_lock, flags);
+ sdp = hba->ufs_device_wlun;
+@@ -8755,9 +8757,14 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,
+ * callbacks hence set the RQF_PM flag so that it doesn't resume the
+ * already suspended childs.
+ */
++ deadline = jiffies + 10 * HZ;
+ for (retries = 3; retries > 0; --retries) {
++ ret = -ETIMEDOUT;
++ remaining = deadline - jiffies;
++ if (remaining <= 0)
++ break;
+ ret = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, &sshdr,
+- START_STOP_TIMEOUT, 0, 0, RQF_PM, NULL);
++ remaining / HZ, 0, 0, RQF_PM, NULL);
+ if (!scsi_status_is_check_condition(ret) ||
+ !scsi_sense_valid(&sshdr) ||
+ sshdr.sense_key != UNIT_ATTENTION)
+--
+2.35.1
+
fs-only-do-a-memory-barrier-for-the-first-set_buffer_uptodate.patch
soc-fsl-select-fsl_guts-driver-for-dpio.patch
revert-mm-kmemleak-take-a-full-lowmem-check-in-kmemleak_-_phys.patch
+scsi-qla2xxx-disable-atio-interrupt-coalesce-for-qua.patch
+scsi-core-allow-the-alua-transitioning-state-enough-.patch
+scsi-megaraid_sas-fix-double-kfree.patch
+drm-gem-fix-gem-handle-release-errors.patch
+drm-amdgpu-move-psp_xgmi_terminate-call-from-amdgpu_.patch
+drm-amdgpu-fix-hive-reference-leak-when-adding-xgmi-.patch
+drm-amdgpu-check-num_gfx_rings-for-gfx-v9_0-rb-setup.patch
+drm-amdgpu-remove-the-additional-kfd-pre-reset-call-.patch
+drm-radeon-add-a-force-flush-to-delay-work-when-rade.patch
+scsi-ufs-core-reduce-the-power-mode-change-timeout.patch
+revert-parisc-show-error-if-wrong-32-64-bit-compiler.patch
+parisc-ccio-dma-handle-kmalloc-failure-in-ccio_init_.patch
+parisc-add-runtime-check-to-prevent-pa2.0-kernels-on.patch
+arm64-errata-add-detection-for-amevcntr01-incrementi.patch
+arm64-signal-raise-limit-on-stack-frames.patch
+netfilter-conntrack-work-around-exceeded-receive-win.patch
+thermal-int340x_thermal-handle-data_vault-when-the-v.patch
+cpufreq-check-only-freq_table-in-__resolve_freq.patch
+net-core-skbuff-check-the-return-value-of-skb_copy_b.patch
+md-flush-workqueue-md_rdev_misc_wq-in-md_alloc.patch
+fbdev-omapfb-fix-tests-for-platform_get_irq-failure.patch
+fbdev-fbcon-destroy-mutex-on-freeing-struct-fb_info.patch
+fbdev-chipsfb-add-missing-pci_disable_device-in-chip.patch
+x86-sev-mark-snp_abort-noreturn.patch
+drm-amdgpu-add-sdma-instance-check-for-gfx11-cgcg.patch
+drm-amdgpu-mmvm_l2_cntl3-register-not-initialized-co.patch
--- /dev/null
+From 5fe215f96d924550a18545ee8b9bfca1da6d739d Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Mon, 8 Aug 2022 21:21:58 +0800
+Subject: thermal/int340x_thermal: handle data_vault when the value is
+ ZERO_SIZE_PTR
+
+From: Lee, Chun-Yi <joeyli.kernel@gmail.com>
+
+[ Upstream commit 7931e28098a4c1a2a6802510b0cbe57546d2049d ]
+
+In some case, the GDDV returns a package with a buffer which has
+zero length. It causes that kmemdup() returns ZERO_SIZE_PTR (0x10).
+
+Then the data_vault_read() got NULL point dereference problem when
+accessing the 0x10 value in data_vault.
+
+[ 71.024560] BUG: kernel NULL pointer dereference, address:
+0000000000000010
+
+This patch uses ZERO_OR_NULL_PTR() for checking ZERO_SIZE_PTR or
+NULL value in data_vault.
+
+Signed-off-by: "Lee, Chun-Yi" <jlee@suse.com>
+Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/thermal/intel/int340x_thermal/int3400_thermal.c | 9 +++++----
+ 1 file changed, 5 insertions(+), 4 deletions(-)
+
+diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
+index 80d4e0676083a..365489bf4b8c1 100644
+--- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
++++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
+@@ -527,7 +527,7 @@ static void int3400_setup_gddv(struct int3400_thermal_priv *priv)
+ priv->data_vault = kmemdup(obj->package.elements[0].buffer.pointer,
+ obj->package.elements[0].buffer.length,
+ GFP_KERNEL);
+- if (!priv->data_vault)
++ if (ZERO_OR_NULL_PTR(priv->data_vault))
+ goto out_free;
+
+ bin_attr_data_vault.private = priv->data_vault;
+@@ -597,7 +597,7 @@ static int int3400_thermal_probe(struct platform_device *pdev)
+ goto free_imok;
+ }
+
+- if (priv->data_vault) {
++ if (!ZERO_OR_NULL_PTR(priv->data_vault)) {
+ result = sysfs_create_group(&pdev->dev.kobj,
+ &data_attribute_group);
+ if (result)
+@@ -615,7 +615,8 @@ static int int3400_thermal_probe(struct platform_device *pdev)
+ free_sysfs:
+ cleanup_odvp(priv);
+ if (priv->data_vault) {
+- sysfs_remove_group(&pdev->dev.kobj, &data_attribute_group);
++ if (!ZERO_OR_NULL_PTR(priv->data_vault))
++ sysfs_remove_group(&pdev->dev.kobj, &data_attribute_group);
+ kfree(priv->data_vault);
+ }
+ free_uuid:
+@@ -647,7 +648,7 @@ static int int3400_thermal_remove(struct platform_device *pdev)
+ if (!priv->rel_misc_dev_res)
+ acpi_thermal_rel_misc_device_remove(priv->adev->handle);
+
+- if (priv->data_vault)
++ if (!ZERO_OR_NULL_PTR(priv->data_vault))
+ sysfs_remove_group(&pdev->dev.kobj, &data_attribute_group);
+ sysfs_remove_group(&pdev->dev.kobj, &uuid_attribute_group);
+ sysfs_remove_group(&pdev->dev.kobj, &imok_attribute_group);
+--
+2.35.1
+
--- /dev/null
+From 0e152e92c52968cf66980a419b818c78fddabc19 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Wed, 24 Aug 2022 17:13:26 +0200
+Subject: x86/sev: Mark snp_abort() noreturn
+
+From: Borislav Petkov <bp@suse.de>
+
+[ Upstream commit c93c296fff6b369a7115916145047c8a3db6e27f ]
+
+Mark both the function prototype and definition as noreturn in order to
+prevent the compiler from doing transformations which confuse objtool
+like so:
+
+ vmlinux.o: warning: objtool: sme_enable+0x71: unreachable instruction
+
+This triggers with gcc-12.
+
+Add it and sev_es_terminate() to the objtool noreturn tracking array
+too. Sort it while at it.
+
+Suggested-by: Michael Matz <matz@suse.de>
+Signed-off-by: Borislav Petkov <bp@suse.de>
+Acked-by: Peter Zijlstra <peterz@infradead.org>
+Link: https://lore.kernel.org/r/20220824152420.20547-1-bp@alien8.de
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/x86/include/asm/sev.h | 2 +-
+ arch/x86/kernel/sev.c | 2 +-
+ tools/objtool/check.c | 34 ++++++++++++++++++----------------
+ 3 files changed, 20 insertions(+), 18 deletions(-)
+
+diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
+index 4a23e52fe0ee1..ebc271bb6d8ed 100644
+--- a/arch/x86/include/asm/sev.h
++++ b/arch/x86/include/asm/sev.h
+@@ -195,7 +195,7 @@ void snp_set_memory_shared(unsigned long vaddr, unsigned int npages);
+ void snp_set_memory_private(unsigned long vaddr, unsigned int npages);
+ void snp_set_wakeup_secondary_cpu(void);
+ bool snp_init(struct boot_params *bp);
+-void snp_abort(void);
++void __init __noreturn snp_abort(void);
+ int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned long *fw_err);
+ #else
+ static inline void sev_es_ist_enter(struct pt_regs *regs) { }
+diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
+index 4f84c3f11af5b..a428c62330d37 100644
+--- a/arch/x86/kernel/sev.c
++++ b/arch/x86/kernel/sev.c
+@@ -2112,7 +2112,7 @@ bool __init snp_init(struct boot_params *bp)
+ return true;
+ }
+
+-void __init snp_abort(void)
++void __init __noreturn snp_abort(void)
+ {
+ sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
+ }
+diff --git a/tools/objtool/check.c b/tools/objtool/check.c
+index 31c719f99f66e..5d87e0b0d85f9 100644
+--- a/tools/objtool/check.c
++++ b/tools/objtool/check.c
+@@ -162,32 +162,34 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func,
+
+ /*
+ * Unfortunately these have to be hard coded because the noreturn
+- * attribute isn't provided in ELF data.
++ * attribute isn't provided in ELF data. Keep 'em sorted.
+ */
+ static const char * const global_noreturns[] = {
++ "__invalid_creds",
++ "__module_put_and_kthread_exit",
++ "__reiserfs_panic",
+ "__stack_chk_fail",
+- "panic",
++ "__ubsan_handle_builtin_unreachable",
++ "cpu_bringup_and_idle",
++ "cpu_startup_entry",
+ "do_exit",
++ "do_group_exit",
+ "do_task_dead",
+- "kthread_exit",
+- "make_task_dead",
+- "__module_put_and_kthread_exit",
++ "ex_handler_msr_mce",
++ "fortify_panic",
+ "kthread_complete_and_exit",
+- "__reiserfs_panic",
++ "kthread_exit",
++ "kunit_try_catch_throw",
+ "lbug_with_loc",
+- "fortify_panic",
+- "usercopy_abort",
+ "machine_real_restart",
++ "make_task_dead",
++ "panic",
+ "rewind_stack_and_make_dead",
+- "kunit_try_catch_throw",
+- "xen_start_kernel",
+- "cpu_bringup_and_idle",
+- "do_group_exit",
++ "sev_es_terminate",
++ "snp_abort",
+ "stop_this_cpu",
+- "__invalid_creds",
+- "cpu_startup_entry",
+- "__ubsan_handle_builtin_unreachable",
+- "ex_handler_msr_mce",
++ "usercopy_abort",
++ "xen_start_kernel",
+ };
+
+ if (!func)
+--
+2.35.1
+
projects / thirdparty / kernel / stable-queue.git / commitdiff
