December 2024 - Linux-stable-mirror

Re: Patch "rtla/utils: Add idle state disabling via libcpupower" has been added to the 6.12-stable tree

by Tomas Glozar

út 10. 12. 2024 v 21:44 odesílatel Sasha Levin <sashal(a)kernel.org> napsal: > > This is a note to let you know that I've just added the patch titled > > rtla/utils: Add idle state disabling via libcpupower > > to the 6.12-stable tree which can be found at: > http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… > > The filename of the patch is: > rtla-utils-add-idle-state-disabling-via-libcpupower.patch > and it can be found in the queue-6.12 subdirectory. > > If you, or anyone else, feels it should not be added to the stable tree, > please let <stable(a)vger.kernel.org> know about it. This is a part of a patchset implementing a new feature, rtla idle state disabling, see [1]. It seems it was included in this stable queue and also the one for 6.6 by mistake. Also, the patch by itself does not do anything, because it depends on preceding commits from the patchset to enable HAVE_LIBCPUPOWER_SUPPORT and on following commits to actually implement the functionality in the rtla command line interface. Perhaps AUTOSEL picked it due to some merge conflicts with other patches? I don't know of any though. [1] - https://lore.kernel.org/linux-trace-kernel/20241017140914.3200454-1-tglozar… > > > > commit 354bcd3b3efd600f4d23cee6898a6968659bb3a9 > Author: Tomas Glozar <tglozar(a)redhat.com> > Date: Thu Oct 17 16:09:11 2024 +0200 > > rtla/utils: Add idle state disabling via libcpupower > > [ Upstream commit 083d29d3784319e9e9fab3ac02683a7b26ae3480 ] > > Add functions to utils.c to disable idle states through functions of > libcpupower. This will serve as the basis for disabling idle states > per cpu when running timerlat. > > Link: https://lore.kernel.org/20241017140914.3200454-4-tglozar@redhat.com > Signed-off-by: Tomas Glozar <tglozar(a)redhat.com> > Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > > diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c > index 0735fcb827ed7..230f9fc7502dd 100644 > --- a/tools/tracing/rtla/src/utils.c > +++ b/tools/tracing/rtla/src/utils.c > @@ -4,6 +4,9 @@ > */ > > #define _GNU_SOURCE > +#ifdef HAVE_LIBCPUPOWER_SUPPORT > +#include <cpuidle.h> > +#endif /* HAVE_LIBCPUPOWER_SUPPORT */ > #include <dirent.h> > #include <stdarg.h> > #include <stdlib.h> > @@ -519,6 +522,153 @@ int set_cpu_dma_latency(int32_t latency) > return fd; > } > > +#ifdef HAVE_LIBCPUPOWER_SUPPORT > +static unsigned int **saved_cpu_idle_disable_state; > +static size_t saved_cpu_idle_disable_state_alloc_ctr; > + > +/* > + * save_cpu_idle_state_disable - save disable for all idle states of a cpu > + * > + * Saves the current disable of all idle states of a cpu, to be subsequently > + * restored via restore_cpu_idle_disable_state. > + * > + * Return: idle state count on success, negative on error > + */ > +int save_cpu_idle_disable_state(unsigned int cpu) > +{ > + unsigned int nr_states; > + unsigned int state; > + int disabled; > + int nr_cpus; > + > + nr_states = cpuidle_state_count(cpu); > + > + if (nr_states == 0) > + return 0; > + > + if (saved_cpu_idle_disable_state == NULL) { > + nr_cpus = sysconf(_SC_NPROCESSORS_CONF); > + saved_cpu_idle_disable_state = calloc(nr_cpus, sizeof(unsigned int *)); > + if (!saved_cpu_idle_disable_state) > + return -1; > + } > + > + saved_cpu_idle_disable_state[cpu] = calloc(nr_states, sizeof(unsigned int)); > + if (!saved_cpu_idle_disable_state[cpu]) > + return -1; > + saved_cpu_idle_disable_state_alloc_ctr++; > + > + for (state = 0; state < nr_states; state++) { > + disabled = cpuidle_is_state_disabled(cpu, state); > + if (disabled < 0) > + return disabled; > + saved_cpu_idle_disable_state[cpu][state] = disabled; > + } > + > + return nr_states; > +} > + > +/* > + * restore_cpu_idle_disable_state - restore disable for all idle states of a cpu > + * > + * Restores the current disable state of all idle states of a cpu that was > + * previously saved by save_cpu_idle_disable_state. > + * > + * Return: idle state count on success, negative on error > + */ > +int restore_cpu_idle_disable_state(unsigned int cpu) > +{ > + unsigned int nr_states; > + unsigned int state; > + int disabled; > + int result; > + > + nr_states = cpuidle_state_count(cpu); > + > + if (nr_states == 0) > + return 0; > + > + if (!saved_cpu_idle_disable_state) > + return -1; > + > + for (state = 0; state < nr_states; state++) { > + if (!saved_cpu_idle_disable_state[cpu]) > + return -1; > + disabled = saved_cpu_idle_disable_state[cpu][state]; > + result = cpuidle_state_disable(cpu, state, disabled); > + if (result < 0) > + return result; > + } > + > + free(saved_cpu_idle_disable_state[cpu]); > + saved_cpu_idle_disable_state[cpu] = NULL; > + saved_cpu_idle_disable_state_alloc_ctr--; > + if (saved_cpu_idle_disable_state_alloc_ctr == 0) { > + free(saved_cpu_idle_disable_state); > + saved_cpu_idle_disable_state = NULL; > + } > + > + return nr_states; > +} > + > +/* > + * free_cpu_idle_disable_states - free saved idle state disable for all cpus > + * > + * Frees the memory used for storing cpu idle state disable for all cpus > + * and states. > + * > + * Normally, the memory is freed automatically in > + * restore_cpu_idle_disable_state; this is mostly for cleaning up after an > + * error. > + */ > +void free_cpu_idle_disable_states(void) > +{ > + int cpu; > + int nr_cpus; > + > + if (!saved_cpu_idle_disable_state) > + return; > + > + nr_cpus = sysconf(_SC_NPROCESSORS_CONF); > + > + for (cpu = 0; cpu < nr_cpus; cpu++) { > + free(saved_cpu_idle_disable_state[cpu]); > + saved_cpu_idle_disable_state[cpu] = NULL; > + } > + > + free(saved_cpu_idle_disable_state); > + saved_cpu_idle_disable_state = NULL; > +} > + > +/* > + * set_deepest_cpu_idle_state - limit idle state of cpu > + * > + * Disables all idle states deeper than the one given in > + * deepest_state (assuming states with higher number are deeper). > + * > + * This is used to reduce the exit from idle latency. Unlike > + * set_cpu_dma_latency, it can disable idle states per cpu. > + * > + * Return: idle state count on success, negative on error > + */ > +int set_deepest_cpu_idle_state(unsigned int cpu, unsigned int deepest_state) > +{ > + unsigned int nr_states; > + unsigned int state; > + int result; > + > + nr_states = cpuidle_state_count(cpu); > + > + for (state = deepest_state + 1; state < nr_states; state++) { > + result = cpuidle_state_disable(cpu, state, 1); > + if (result < 0) > + return result; > + } > + > + return nr_states; > +} > +#endif /* HAVE_LIBCPUPOWER_SUPPORT */ > + > #define _STR(x) #x > #define STR(x) _STR(x) > > diff --git a/tools/tracing/rtla/src/utils.h b/tools/tracing/rtla/src/utils.h > index 99c9cf81bcd02..101d4799a0090 100644 > --- a/tools/tracing/rtla/src/utils.h > +++ b/tools/tracing/rtla/src/utils.h > @@ -66,6 +66,19 @@ int set_comm_sched_attr(const char *comm_prefix, struct sched_attr *attr); > int set_comm_cgroup(const char *comm_prefix, const char *cgroup); > int set_pid_cgroup(pid_t pid, const char *cgroup); > int set_cpu_dma_latency(int32_t latency); > +#ifdef HAVE_LIBCPUPOWER_SUPPORT > +int save_cpu_idle_disable_state(unsigned int cpu); > +int restore_cpu_idle_disable_state(unsigned int cpu); > +void free_cpu_idle_disable_states(void); > +int set_deepest_cpu_idle_state(unsigned int cpu, unsigned int state); > +static inline int have_libcpupower_support(void) { return 1; } > +#else > +static inline int save_cpu_idle_disable_state(unsigned int cpu) { return -1; } > +static inline int restore_cpu_idle_disable_state(unsigned int cpu) { return -1; } > +static inline void free_cpu_idle_disable_states(void) { } > +static inline int set_deepest_cpu_idle_state(unsigned int cpu, unsigned int state) { return -1; } > +static inline int have_libcpupower_support(void) { return 0; } > +#endif /* HAVE_LIBCPUPOWER_SUPPORT */ > int auto_house_keeping(cpu_set_t *monitored_cpus); > > #define ns_to_usf(x) (((double)x/1000)) > Tomas

10 months, 3 weeks

2
1
0 0

[PATCHv2] drm: zynqmp_dp: Fix integer overflow in zynqmp_dp_rate_get()

by Karol Przybylski

This patch fixes a potential integer overflow in the zynqmp_dp_rate_get() The issue comes up when the expression drm_dp_bw_code_to_link_rate(dp->test.bw_code) * 10000 is evaluated using 32-bit Now the constant is a compatible 64-bit type. Resolves coverity issues: CID 1636340 and CID 1635811 Signed-off-by: Karol Przybylski <karprzy7(a)gmail.com> Fixes: 28edaacb821c6 ("drm: zynqmp_dp: Add debugfs interface for compliance testing") --- drivers/gpu/drm/xlnx/zynqmp_dp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xlnx/zynqmp_dp.c b/drivers/gpu/drm/xlnx/zynqmp_dp.c index 25c5dc61e..56a261a40 100644 --- a/drivers/gpu/drm/xlnx/zynqmp_dp.c +++ b/drivers/gpu/drm/xlnx/zynqmp_dp.c @@ -2190,7 +2190,7 @@ static int zynqmp_dp_rate_get(void *data, u64 *val) struct zynqmp_dp *dp = data; mutex_lock(&dp->lock); - *val = drm_dp_bw_code_to_link_rate(dp->test.bw_code) * 10000; + *val = drm_dp_bw_code_to_link_rate(dp->test.bw_code) * 10000ULL; mutex_unlock(&dp->lock); return 0; } -- 2.34.1

10 months, 3 weeks

2
1
0 0

[REGRESSION] ThinkPad L15 Gen 4 touchpad no longer works

by Ulrich Müller

After upgrading from 6.6.52 to 6.6.58, tapping on the touchpad stopped working. The problem is still present in 6.6.59. I see the following in dmesg output; the first line was not there previously: [ 2.129282] hid-multitouch 0018:27C6:01E0.0001: The byte is not expected for fixing the report descriptor. It's possible that the touchpad firmware is not suitable for applying the fix. got: 9 [ 2.137479] input: GXTP5140:00 27C6:01E0 as /devices/platform/AMDI0010:00/i2c-0/i2c-GXTP5140:00/0018:27C6:01E0.0001/input/input10 [ 2.137680] input: GXTP5140:00 27C6:01E0 as /devices/platform/AMDI0010:00/i2c-0/i2c-GXTP5140:00/0018:27C6:01E0.0001/input/input11 [ 2.137921] hid-multitouch 0018:27C6:01E0.0001: input,hidraw0: I2C HID v1.00 Mouse [GXTP5140:00 27C6:01E0] on i2c-GXTP5140:00 Hardware is a Lenovo ThinkPad L15 Gen 4. The problem goes away when reverting this commit: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/d… See also Gentoo bug report: https://bugs.gentoo.org/942797

10 months, 3 weeks

6
13
0 0

Stable inclusion

by Jens Axboe

Hi, Can you add the below to 6.1-stable? Thanks! commit 3181e22fb79910c7071e84a43af93ac89e8a7106 Author: Pavel Begunkov <asml.silence(a)gmail.com> Date: Mon Jan 9 14:46:10 2023 +0000 io_uring: wake up optimisations Commit 3181e22fb79910c7071e84a43af93ac89e8a7106 upstream. Flush completions is done either from the submit syscall or by the task_work, both are in the context of the submitter task, and when it goes for a single threaded rings like implied by ->task_complete, there won't be any waiters on ->cq_wait but the master task. That means that there can be no tasks sleeping on cq_wait while we run __io_submit_flush_completions() and so waking up can be skipped. Signed-off-by: Pavel Begunkov <asml.silence(a)gmail.com> Link: https://lore.kernel.org/r/60ad9768ec74435a0ddaa6eec0ffa7729474f69f.16732742… Signed-off-by: Jens Axboe <axboe(a)kernel.dk> diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 4f0ae938b146..0b1361663267 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -582,6 +582,16 @@ static inline void __io_cq_unlock_post(struct io_ring_ctx *ctx) io_cqring_ev_posted(ctx); } +static inline void __io_cq_unlock_post_flush(struct io_ring_ctx *ctx) + __releases(ctx->completion_lock) +{ + io_commit_cqring(ctx); + spin_unlock(&ctx->completion_lock); + io_commit_cqring_flush(ctx); + if (!(ctx->flags & IORING_SETUP_DEFER_TASKRUN)) + __io_cqring_wake(ctx); +} + void io_cq_unlock_post(struct io_ring_ctx *ctx) { __io_cq_unlock_post(ctx); @@ -1339,7 +1349,7 @@ static void __io_submit_flush_completions(struct io_ring_ctx *ctx) if (!(req->flags & REQ_F_CQE_SKIP)) __io_fill_cqe_req(ctx, req); } - __io_cq_unlock_post(ctx); + __io_cq_unlock_post_flush(ctx); io_free_batch_list(ctx, state->compl_reqs.first); INIT_WQ_LIST(&state->compl_reqs); -- Jens Axboe

10 months, 3 weeks

2
1
0 0

[PATCH v3 3/6] arm64/kvm: Configure HYP TCR.PS/DS based on host stage1

by Ard Biesheuvel

From: Ard Biesheuvel <ardb(a)kernel.org> When the host stage1 is configured for LPA2, the value currently being programmed into TCR_EL2.T0SZ may be invalid unless LPA2 is configured at HYP as well. This means kvm_lpa2_is_enabled() is not the right condition to test when setting TCR_EL2.DS, as it will return false if LPA2 is only available for stage 1 but not for stage 2. Similary, programming TCR_EL2.PS based on a limited IPA range due to lack of stage2 LPA2 support could potentially result in problems. So use lpa2_is_enabled() instead, and set the PS field according to the host's IPS, which is capped at 48 bits if LPA2 support is absent or disabled. Whether or not we can make meaningful use of such a configuration is a different question. Cc: <stable(a)vger.kernel.org> Signed-off-by: Ard Biesheuvel <ardb(a)kernel.org> --- arch/arm64/kvm/arm.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index a102c3aebdbc..7b2735ad32e9 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1990,8 +1990,7 @@ static int kvm_init_vector_slots(void) static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits) { struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu); - u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); - unsigned long tcr; + unsigned long tcr, ips; /* * Calculate the raw per-cpu offset without a translation from the @@ -2005,6 +2004,7 @@ static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits) params->mair_el2 = read_sysreg(mair_el1); tcr = read_sysreg(tcr_el1); + ips = FIELD_GET(TCR_IPS_MASK, tcr); if (cpus_have_final_cap(ARM64_KVM_HVHE)) { tcr |= TCR_EPD1_MASK; } else { @@ -2014,8 +2014,8 @@ static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits) tcr &= ~TCR_T0SZ_MASK; tcr |= TCR_T0SZ(hyp_va_bits); tcr &= ~TCR_EL2_PS_MASK; - tcr |= FIELD_PREP(TCR_EL2_PS_MASK, kvm_get_parange(mmfr0)); - if (kvm_lpa2_is_enabled()) + tcr |= FIELD_PREP(TCR_EL2_PS_MASK, ips); + if (lpa2_is_enabled()) tcr |= TCR_EL2_DS; params->tcr_el2 = tcr; -- 2.47.1.613.gc27f4b7a9f-goog

10 months, 3 weeks

1
0
0 0

[PATCH v3 2/6] arm64/mm: Override PARange for !LPA2 and use it consistently

by Ard Biesheuvel

From: Ard Biesheuvel <ardb(a)kernel.org> When FEAT_LPA{,2} are not implemented, the ID_AA64MMFR0_EL1.PARange and TCR.IPS values corresponding with 52-bit physical addressing are reserved. Setting the TCR.IPS field to 0b110 (52-bit physical addressing) has side effects, such as how the TTBRn_ELx.BADDR fields are interpreted, and so it is important that disabling FEAT_LPA2 (by overriding the ID_AA64MMFR0.TGran fields) also presents a PARange field consistent with that. So limit the field to 48 bits unless LPA2 is enabled, and update existing references to use the override consistently. Fixes: 352b0395b505 ("arm64: Enable 52-bit virtual addressing for 4k and 16k granule configs") Cc: <stable(a)vger.kernel.org> Signed-off-by: Ard Biesheuvel <ardb(a)kernel.org> --- arch/arm64/include/asm/assembler.h | 5 +++++ arch/arm64/kernel/cpufeature.c | 2 +- arch/arm64/kernel/pi/idreg-override.c | 9 +++++++++ arch/arm64/kernel/pi/map_kernel.c | 6 ++++++ arch/arm64/mm/init.c | 7 ++++++- 5 files changed, 27 insertions(+), 2 deletions(-) diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 3d8d534a7a77..ad63457a05c5 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -343,6 +343,11 @@ alternative_cb_end // Narrow PARange to fit the PS field in TCR_ELx ubfx \tmp0, \tmp0, #ID_AA64MMFR0_EL1_PARANGE_SHIFT, #3 mov \tmp1, #ID_AA64MMFR0_EL1_PARANGE_MAX +#ifdef CONFIG_ARM64_LPA2 +alternative_if_not ARM64_HAS_VA52 + mov \tmp1, #ID_AA64MMFR0_EL1_PARANGE_48 +alternative_else_nop_endif +#endif cmp \tmp0, \tmp1 csel \tmp0, \tmp1, \tmp0, hi bfi \tcr, \tmp0, \pos, #3 diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 6ce71f444ed8..f8cb8a6ab98a 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -3478,7 +3478,7 @@ static void verify_hyp_capabilities(void) return; safe_mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); - mmfr0 = read_cpuid(ID_AA64MMFR0_EL1); + mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); /* Verify VMID bits */ diff --git a/arch/arm64/kernel/pi/idreg-override.c b/arch/arm64/kernel/pi/idreg-override.c index 22159251eb3a..c6b185b885f7 100644 --- a/arch/arm64/kernel/pi/idreg-override.c +++ b/arch/arm64/kernel/pi/idreg-override.c @@ -83,6 +83,15 @@ static bool __init mmfr2_varange_filter(u64 val) id_aa64mmfr0_override.val |= (ID_AA64MMFR0_EL1_TGRAN_LPA2 - 1) << ID_AA64MMFR0_EL1_TGRAN_SHIFT; id_aa64mmfr0_override.mask |= 0xfU << ID_AA64MMFR0_EL1_TGRAN_SHIFT; + + /* + * Override PARange to 48 bits - the override will just be + * ignored if the actual PARange is smaller, but this is + * unlikely to be the case for LPA2 capable silicon. + */ + id_aa64mmfr0_override.val |= + ID_AA64MMFR0_EL1_PARANGE_48 << ID_AA64MMFR0_EL1_PARANGE_SHIFT; + id_aa64mmfr0_override.mask |= 0xfU << ID_AA64MMFR0_EL1_PARANGE_SHIFT; } #endif return true; diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c index f374a3e5a5fe..e57b043f324b 100644 --- a/arch/arm64/kernel/pi/map_kernel.c +++ b/arch/arm64/kernel/pi/map_kernel.c @@ -136,6 +136,12 @@ static void noinline __section(".idmap.text") set_ttbr0_for_lpa2(u64 ttbr) { u64 sctlr = read_sysreg(sctlr_el1); u64 tcr = read_sysreg(tcr_el1) | TCR_DS; + u64 mmfr0 = read_sysreg(id_aa64mmfr0_el1); + u64 parange = cpuid_feature_extract_unsigned_field(mmfr0, + ID_AA64MMFR0_EL1_PARANGE_SHIFT); + + tcr &= ~TCR_IPS_MASK; + tcr |= parange << TCR_IPS_SHIFT; asm(" msr sctlr_el1, %0 ;" " isb ;" diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index d21f67d67cf5..2b2289d55eaa 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -280,7 +280,12 @@ void __init arm64_memblock_init(void) if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { extern u16 memstart_offset_seed; - u64 mmfr0 = read_cpuid(ID_AA64MMFR0_EL1); + + /* + * Use the sanitised version of id_aa64mmfr0_el1 so that linear + * map randomization can be enabled by shrinking the IPA space. + */ + u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); int parange = cpuid_feature_extract_unsigned_field( mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT); s64 range = linear_region_size - -- 2.47.1.613.gc27f4b7a9f-goog

10 months, 3 weeks

1
0
0 0

[PATCH v3 1/6] arm64/mm: Reduce PA space to 48 bits when LPA2 is not enabled

by Ard Biesheuvel

From: Ard Biesheuvel <ardb(a)kernel.org> Currently, LPA2 kernel support implies support for up to 52 bits of physical addressing, and this is reflected in global definitions such as PHYS_MASK_SHIFT and MAX_PHYSMEM_BITS. This is potentially problematic, given that LPA2 hardware support is modeled as a CPU feature which can be overridden, and with LPA2 hardware support turned off, attempting to map physical regions with address bits [51:48] set (which may exist on LPA2 capable systems booting with arm64.nolva) will result in corrupted mappings with a truncated output address and bogus shareability attributes. This means that the accepted physical address range in the mapping routines should be at most 48 bits wide when LPA2 support is configured but not enabled at runtime. Fixes: 352b0395b505 ("arm64: Enable 52-bit virtual addressing for 4k and 16k granule configs") Cc: <stable(a)vger.kernel.org> Reviewed-by: Anshuman Khandual <anshuman.khandual(a)arm.com> Signed-off-by: Ard Biesheuvel <ardb(a)kernel.org> --- arch/arm64/include/asm/pgtable-hwdef.h | 6 ------ arch/arm64/include/asm/pgtable-prot.h | 7 +++++++ arch/arm64/include/asm/sparsemem.h | 5 ++++- 3 files changed, 11 insertions(+), 7 deletions(-) diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index c78a988cca93..a9136cc551cc 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -222,12 +222,6 @@ */ #define S1_TABLE_AP (_AT(pmdval_t, 3) << 61) -/* - * Highest possible physical address supported. - */ -#define PHYS_MASK_SHIFT (CONFIG_ARM64_PA_BITS) -#define PHYS_MASK ((UL(1) << PHYS_MASK_SHIFT) - 1) - #define TTBR_CNP_BIT (UL(1) << 0) /* diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 9f9cf13bbd95..a95f1f77bb39 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -81,6 +81,7 @@ extern unsigned long prot_ns_shared; #define lpa2_is_enabled() false #define PTE_MAYBE_SHARED PTE_SHARED #define PMD_MAYBE_SHARED PMD_SECT_S +#define PHYS_MASK_SHIFT (CONFIG_ARM64_PA_BITS) #else static inline bool __pure lpa2_is_enabled(void) { @@ -89,8 +90,14 @@ static inline bool __pure lpa2_is_enabled(void) #define PTE_MAYBE_SHARED (lpa2_is_enabled() ? 0 : PTE_SHARED) #define PMD_MAYBE_SHARED (lpa2_is_enabled() ? 0 : PMD_SECT_S) +#define PHYS_MASK_SHIFT (lpa2_is_enabled() ? CONFIG_ARM64_PA_BITS : 48) #endif +/* + * Highest possible physical address supported. + */ +#define PHYS_MASK ((UL(1) << PHYS_MASK_SHIFT) - 1) + /* * If we have userspace only BTI we don't want to mark kernel pages * guarded even if the system does support BTI. diff --git a/arch/arm64/include/asm/sparsemem.h b/arch/arm64/include/asm/sparsemem.h index 8a8acc220371..84783efdc9d1 100644 --- a/arch/arm64/include/asm/sparsemem.h +++ b/arch/arm64/include/asm/sparsemem.h @@ -5,7 +5,10 @@ #ifndef __ASM_SPARSEMEM_H #define __ASM_SPARSEMEM_H -#define MAX_PHYSMEM_BITS CONFIG_ARM64_PA_BITS +#include <asm/pgtable-prot.h> + +#define MAX_PHYSMEM_BITS PHYS_MASK_SHIFT +#define MAX_POSSIBLE_PHYSMEM_BITS (52) /* * Section size must be at least 512MB for 64K base -- 2.47.1.613.gc27f4b7a9f-goog

10 months, 3 weeks

1
0
0 0

[PATCH 1/2] ocfs2: Revert "ocfs2: fix the la space leak when unmounting an ocfs2 volume"

by Heming Zhao

This reverts commit dfe6c5692fb5 ("ocfs2: fix the la space leak when unmounting an ocfs2 volume"). In commit dfe6c5692fb5, the commit log stating "This bug has existed since the initial OCFS2 code." is incorrect. The correct introduction commit is 30dd3478c3cd ("ocfs2: correctly use ocfs2_find_next_zero_bit()"). Fixes: dfe6c5692fb5 ("ocfs2: fix the la space leak when unmounting an ocfs2 volume") Signed-off-by: Heming Zhao <heing.zhao(a)suse.com> Cc: <stable(a)vger.kernel.org> --- fs/ocfs2/localalloc.c | 19 ------------------- 1 file changed, 19 deletions(-) diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 8ac42ea81a17..5df34561c551 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -1002,25 +1002,6 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb, start = bit_off + 1; } - /* clear the contiguous bits until the end boundary */ - if (count) { - blkno = la_start_blk + - ocfs2_clusters_to_blocks(osb->sb, - start - count); - - trace_ocfs2_sync_local_to_main_free( - count, start - count, - (unsigned long long)la_start_blk, - (unsigned long long)blkno); - - status = ocfs2_release_clusters(handle, - main_bm_inode, - main_bm_bh, blkno, - count); - if (status < 0) - mlog_errno(status); - } - bail: if (status) mlog_errno(status); -- 2.43.0

10 months, 3 weeks

3
7
0 0

[PATCH v2] powerpc/pseries/eeh: Fix get PE state translation

by Narayana Murty N

The PE Reset State "0" obtained from RTAS calls ibm_read_slot_reset_[state|state2] indicates that the Reset is deactivated and the PE is not in the MMIO Stopped or DMA Stopped state. With PE Reset State "0", the MMIO and DMA is allowed for the PE. The function pseries_eeh_get_state() is currently not indicating that to the caller because of which the drivers are unable to resume the MMIO and DMA activity. The patch fixes that by reflecting what is actually allowed. Fixes: 00ba05a12b3c ("powerpc/pseries: Cleanup on pseries_eeh_get_state()") Signed-off-by: Narayana Murty N <nnmlinux(a)linux.ibm.com> --- Changelog: V1:https://lore.kernel.org/all/20241107042027.338065-1-nnmlinux@linux.ibm.c… --added Fixes tag for "powerpc/pseries: Cleanup on pseries_eeh_get_state()". --- arch/powerpc/platforms/pseries/eeh_pseries.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 1893f66371fa..b12ef382fec7 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -580,8 +580,10 @@ static int pseries_eeh_get_state(struct eeh_pe *pe, int *delay) switch(rets[0]) { case 0: - result = EEH_STATE_MMIO_ACTIVE | - EEH_STATE_DMA_ACTIVE; + result = EEH_STATE_MMIO_ACTIVE | + EEH_STATE_DMA_ACTIVE | + EEH_STATE_MMIO_ENABLED | + EEH_STATE_DMA_ENABLED; break; case 1: result = EEH_STATE_RESET_ACTIVE | -- 2.47.1

10 months, 3 weeks

2
1
0 0

[PATCH net v4 0/6] virtio_net: correct netdev_tx_reset_queue() invocation points

by Koichiro Den

When virtnet_close is followed by virtnet_open, some TX completions can possibly remain unconsumed, until they are finally processed during the first NAPI poll after the netdev_tx_reset_queue(), resulting in a crash [1]. Commit b96ed2c97c79 ("virtio_net: move netdev_tx_reset_queue() call before RX napi enable") was not sufficient to eliminate all BQL crash scenarios for virtio-net. This issue can be reproduced with the latest net-next master by running: `while :; do ip l set DEV down; ip l set DEV up; done` under heavy network TX load from inside the machine. This patch series resolves the issue and also addresses similar existing problems: (a). Drop netdev_tx_reset_queue() from open/close path. This eliminates the BQL crashes due to the problematic open/close path. (b). As a result of (a), netdev_tx_reset_queue() is now explicitly required in freeze/restore path. Add netdev_tx_reset_queue() immediately after free_unused_bufs() invocation. (c). Fix missing resetting in virtnet_tx_resize(). virtnet_tx_resize() has lacked proper resetting since commit c8bd1f7f3e61 ("virtio_net: add support for Byte Queue Limits"). (d). Fix missing resetting in the XDP_SETUP_XSK_POOL path. Similar to (c), this path lacked proper resetting. Call netdev_tx_reset_queue() when virtqueue_reset() has actually recycled unused buffers. This patch series consists of six commits: [1/6]: Resolves (a) and (b). # also -stable 6.11.y [2/6]: Minor fix to make [4/6] streamlined. [3/6]: Prerequisite for (c). # also -stable 6.11.y [4/6]: Resolves (c) (incl. Prerequisite for (d)) # also -stable 6.11.y [5/6]: Preresuisite for (d). [6/6]: Resolves (d). Changes for v4: - move netdev_tx_reset_queue() out of free_unused_bufs() - submit to net, not net-next Changes for v3: - replace 'flushed' argument with 'recycle_done' Changes for v2: - add tx queue resetting for (b) to (d) above v3: https://lore.kernel.org/all/20241204050724.307544-1-koichiro.den@canonical.… v2: https://lore.kernel.org/all/20241203073025.67065-1-koichiro.den@canonical.c… v1: https://lore.kernel.org/all/20241130181744.3772632-1-koichiro.den@canonical… [1]: ------------[ cut here ]------------ kernel BUG at lib/dynamic_queue_limits.c:99! Oops: invalid opcode: 0000 [#1] PREEMPT SMP NOPTI CPU: 7 UID: 0 PID: 1598 Comm: ip Tainted: G N 6.12.0net-next_main+ #2 Tainted: [N]=TEST Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), \ BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014 RIP: 0010:dql_completed+0x26b/0x290 Code: b7 c2 49 89 e9 44 89 da 89 c6 4c 89 d7 e8 ed 17 47 00 58 65 ff 0d 4d 27 90 7e 0f 85 fd fe ff ff e8 ea 53 8d ff e9 f3 fe ff ff <0f> 0b 01 d2 44 89 d1 29 d1 ba 00 00 00 00 0f 48 ca e9 28 ff ff ff RSP: 0018:ffffc900002b0d08 EFLAGS: 00010297 RAX: 0000000000000000 RBX: ffff888102398c80 RCX: 0000000080190009 RDX: 0000000000000000 RSI: 000000000000006a RDI: 0000000000000000 RBP: ffff888102398c00 R08: 0000000000000000 R09: 0000000000000000 R10: 00000000000000ca R11: 0000000000015681 R12: 0000000000000001 R13: ffffc900002b0d68 R14: ffff88811115e000 R15: ffff8881107aca40 FS: 00007f41ded69500(0000) GS:ffff888667dc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000556ccc2dc1a0 CR3: 0000000104fd8003 CR4: 0000000000772ef0 PKRU: 55555554 Call Trace: <IRQ> ? die+0x32/0x80 ? do_trap+0xd9/0x100 ? dql_completed+0x26b/0x290 ? dql_completed+0x26b/0x290 ? do_error_trap+0x6d/0xb0 ? dql_completed+0x26b/0x290 ? exc_invalid_op+0x4c/0x60 ? dql_completed+0x26b/0x290 ? asm_exc_invalid_op+0x16/0x20 ? dql_completed+0x26b/0x290 __free_old_xmit+0xff/0x170 [virtio_net] free_old_xmit+0x54/0xc0 [virtio_net] virtnet_poll+0xf4/0xe30 [virtio_net] ? __update_load_avg_cfs_rq+0x264/0x2d0 ? update_curr+0x35/0x260 ? reweight_entity+0x1be/0x260 __napi_poll.constprop.0+0x28/0x1c0 net_rx_action+0x329/0x420 ? enqueue_hrtimer+0x35/0x90 ? trace_hardirqs_on+0x1d/0x80 ? kvm_sched_clock_read+0xd/0x20 ? sched_clock+0xc/0x30 ? kvm_sched_clock_read+0xd/0x20 ? sched_clock+0xc/0x30 ? sched_clock_cpu+0xd/0x1a0 handle_softirqs+0x138/0x3e0 do_softirq.part.0+0x89/0xc0 </IRQ> <TASK> __local_bh_enable_ip+0xa7/0xb0 virtnet_open+0xc8/0x310 [virtio_net] __dev_open+0xfa/0x1b0 __dev_change_flags+0x1de/0x250 dev_change_flags+0x22/0x60 do_setlink.isra.0+0x2df/0x10b0 ? rtnetlink_rcv_msg+0x34f/0x3f0 ? netlink_rcv_skb+0x54/0x100 ? netlink_unicast+0x23e/0x390 ? netlink_sendmsg+0x21e/0x490 ? ____sys_sendmsg+0x31b/0x350 ? avc_has_perm_noaudit+0x67/0xf0 ? cred_has_capability.isra.0+0x75/0x110 ? __nla_validate_parse+0x5f/0xee0 ? __pfx___probestub_irq_enable+0x3/0x10 ? __create_object+0x5e/0x90 ? security_capable+0x3b/0x7[I0 rtnl_newlink+0x784/0xaf0 ? avc_has_perm_noaudit+0x67/0xf0 ? cred_has_capability.isra.0+0x75/0x110 ? stack_depot_save_flags+0x24/0x6d0 ? __pfx_rtnl_newlink+0x10/0x10 rtnetlink_rcv_msg+0x34f/0x3f0 ? do_syscall_64+0x6c/0x180 ? entry_SYSCALL_64_after_hwframe+0x76/0x7e ? __pfx_rtnetlink_rcv_msg+0x10/0x10 netlink_rcv_skb+0x54/0x100 netlink_unicast+0x23e/0x390 netlink_sendmsg+0x21e/0x490 ____sys_sendmsg+0x31b/0x350 ? copy_msghdr_from_user+0x6d/0xa0 ___sys_sendmsg+0x86/0xd0 ? __pte_offset_map+0x17/0x160 ? preempt_count_add+0x69/0xa0 ? __call_rcu_common.constprop.0+0x147/0x610 ? preempt_count_add+0x69/0xa0 ? preempt_count_add+0x69/0xa0 ? _raw_spin_trylock+0x13/0x60 ? trace_hardirqs_on+0x1d/0x80 __sys_sendmsg+0x66/0xc0 do_syscall_64+0x6c/0x180 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f41defe5b34 Code: 15 e1 12 0f 00 f7 d8 64 89 02 b8 ff ff ff ff eb bf 0f 1f 44 00 00 f3 0f 1e fa 80 3d 35 95 0f 00 00 74 13 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 4c c3 0f 1f 00 55 48 89 e5 48 83 ec 20 89 55 RSP: 002b:00007ffe5336ecc8 EFLAGS: 00000202 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f41defe5b34 RDX: 0000000000000000 RSI: 00007ffe5336ed30 RDI: 0000000000000003 RBP: 00007ffe5336eda0 R08: 0000000000000010 R09: 0000000000000001 R10: 00007ffe5336f6f9 R11: 0000000000000202 R12: 0000000000000003 R13: 0000000067452259 R14: 0000556ccc28b040 R15: 0000000000000000 </TASK> [...] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]--- Koichiro Den (6): virtio_net: correct netdev_tx_reset_queue() invocation point virtio_net: replace vq2rxq with vq2txq where appropriate virtio_ring: add a func argument 'recycle_done' to virtqueue_resize() virtio_net: ensure netdev_tx_reset_queue is called on tx ring resize virtio_ring: add a func argument 'recycle_done' to virtqueue_reset() virtio_net: ensure netdev_tx_reset_queue is called on bind xsk for tx drivers/net/virtio_net.c | 31 +++++++++++++++++++++++++------ drivers/virtio/virtio_ring.c | 12 ++++++++++-- include/linux/virtio.h | 6 ++++-- 3 files changed, 39 insertions(+), 10 deletions(-) -- 2.43.0

10 months, 3 weeks

8
13
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror December 2024