From: Aaron Lewis aaronlewis@google.com

[ Upstream commit df11f7dd5834146defa448acba097e8d7703cc42 ]

Fix the layout of 'struct desc64' to match the layout described in the SDM Vol 3, Chapter 3 "Protected-Mode Memory Management", section 3.4.5 "Segment Descriptors", Figure 3-8 "Segment Descriptor". The test added later in this series relies on this and crashes if this layout is not correct.

Signed-off-by: Aaron Lewis aaronlewis@google.com Reviewed-by: Alexander Graf graf@amazon.com Message-Id: 20201012194716.3950330-2-aaronlewis@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/kvm/include/x86_64/processor.h | 2 +- tools/testing/selftests/kvm/lib/x86_64/processor.c | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index ff234018219cf..aead07c24afcf 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -57,7 +57,7 @@ enum x86_register { struct desc64 { uint16_t limit0; uint16_t base0; - unsigned base1:8, s:1, type:4, dpl:2, p:1; + unsigned base1:8, type:4, s:1, dpl:2, p:1; unsigned limit1:4, avl:1, l:1, db:1, g:1, base2:8; uint32_t base3; uint32_t zero1; diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 6698cb741e10a..7d8f7fc736467 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -446,11 +446,12 @@ static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp) desc->limit0 = segp->limit & 0xFFFF; desc->base0 = segp->base & 0xFFFF; desc->base1 = segp->base >> 16; - desc->s = segp->s; desc->type = segp->type; + desc->s = segp->s; desc->dpl = segp->dpl; desc->p = segp->present; desc->limit1 = segp->limit >> 16; + desc->avl = segp->avl; desc->l = segp->l; desc->db = segp->db; desc->g = segp->g;

From: Will Deacon will@kernel.org

[ Upstream commit f969f03888b9438fdb227b6460d99ede5737326d ]

In a surprising turn of events, it transpires that CPU capabilities configured as ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE are never set as the result of late-onlining. Therefore our handling of erratum 1418040 does not get activated if it is not required by any of the boot CPUs, even though we allow late-onlining of an affected CPU.

In order to get things working again, replace the cpus_have_const_cap() invocation with an explicit check for the current CPU using this_cpu_has_cap().

Cc: Sai Prakash Ranjan saiprakash.ranjan@codeaurora.org Cc: Stephen Boyd swboyd@chromium.org Cc: Catalin Marinas catalin.marinas@arm.com Cc: Mark Rutland mark.rutland@arm.com Reviewed-by: Suzuki K Poulose suzuki.poulose@arm.com Acked-by: Marc Zyngier maz@kernel.org Link: https://lore.kernel.org/r/20201106114952.10032-1-will@kernel.org Signed-off-by: Will Deacon will@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/include/asm/cpufeature.h | 2 ++ arch/arm64/kernel/process.c | 5 ++--- 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 10d3048dec7c2..ccae05da98a7f 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -262,6 +262,8 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0; /* * CPU feature detected at boot time based on feature of one or more CPUs. * All possible conflicts for a late CPU are ignored. + * NOTE: this means that a late CPU with the feature will *not* cause the + * capability to be advertised by cpus_have_*cap()! */ #define ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE \ (ARM64_CPUCAP_SCOPE_LOCAL_CPU | \ diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 10190c4b16dc4..7d7cfa128b71b 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -511,14 +511,13 @@ static void erratum_1418040_thread_switch(struct task_struct *prev, bool prev32, next32; u64 val;

- if (!(IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) && - cpus_have_const_cap(ARM64_WORKAROUND_1418040))) + if (!IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040)) return;

prev32 = is_compat_thread(task_thread_info(prev)); next32 = is_compat_thread(task_thread_info(next));

- if (prev32 == next32) + if (prev32 == next32 || !this_cpu_has_cap(ARM64_WORKAROUND_1418040)) return;

val = read_sysreg(cntkctl_el1);

From: Will Deacon will@kernel.org

[ Upstream commit 04e613ded8c26489b3e0f9101b44462f780d1a35 ]

Commit ce3d31ad3cac ("arm64/smp: Move rcu_cpu_starting() earlier") ensured that RCU is informed early about incoming CPUs that might end up calling into printk() before they are online. However, if such a CPU fails the early CPU feature compatibility checks in check_local_cpu_capabilities(), then it will be powered off or parked without informing RCU, leading to an endless stream of stalls:

| rcu: INFO: rcu_preempt detected stalls on CPUs/tasks: | rcu: 2-O...: (0 ticks this GP) idle=002/1/0x4000000000000000 softirq=0/0 fqs=2593 | (detected by 0, t=5252 jiffies, g=9317, q=136) | Task dump for CPU 2: | task:swapper/2 state:R running task stack: 0 pid: 0 ppid: 1 flags:0x00000028 | Call trace: | ret_from_fork+0x0/0x30

Ensure that the dying CPU invokes rcu_report_dead() prior to being powered off or parked.

Cc: Qian Cai cai@redhat.com Cc: "Paul E. McKenney" paulmck@kernel.org Reviewed-by: Paul E. McKenney paulmck@kernel.org Suggested-by: Qian Cai cai@redhat.com Link: https://lore.kernel.org/r/20201105222242.GA8842@willie-the-truck Link: https://lore.kernel.org/r/20201106103602.9849-3-will@kernel.org Signed-off-by: Will Deacon will@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/kernel/smp.c | 1 + kernel/rcu/tree.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 426409e0d0713..987220ac4cfef 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -388,6 +388,7 @@ void cpu_die_early(void)

/* Mark this CPU absent */ set_cpu_present(cpu, 0); + rcu_report_dead(cpu);

#ifdef CONFIG_HOTPLUG_CPU update_cpu_boot_status(CPU_KILL_ME); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 62e59596a30a0..1b1d2b09efa9b 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3157,7 +3157,6 @@ void rcu_cpu_starting(unsigned int cpu) smp_mb(); /* Ensure RCU read-side usage follows above initialization. */ }

-#ifdef CONFIG_HOTPLUG_CPU /* * The outgoing function has no further need of RCU, so remove it from * the rcu_node tree's ->qsmaskinitnext bit masks. @@ -3197,6 +3196,7 @@ void rcu_report_dead(unsigned int cpu) per_cpu(rcu_cpu_started, cpu) = 0; }

+#ifdef CONFIG_HOTPLUG_CPU /* * The outgoing CPU has just passed through the dying-idle state, and we * are being invoked from the CPU that was IPIed to continue the offline

From: "Darrick J. Wong" darrick.wong@oracle.com

[ Upstream commit 22843291efc986ce7722610073fcf85a39b4cb13 ]

__sb_start_write has some weird looking lockdep code that claims to exist to handle nested freeze locking requests from xfs. The code as written seems broken -- if we think we hold a read lock on any of the higher freeze levels (e.g. we hold SB_FREEZE_WRITE and are trying to lock SB_FREEZE_PAGEFAULT), it converts a blocking lock attempt into a trylock.

However, it's not correct to downgrade a blocking lock attempt to a trylock unless the downgrading code or the callers are prepared to deal with that situation. Neither __sb_start_write nor its callers handle this at all. For example:

sb_start_pagefault ignores the return value completely, with the result that if xfs_filemap_fault loses a race with a different thread trying to fsfreeze, it will proceed without pagefault freeze protection (thereby breaking locking rules) and then unlocks the pagefault freeze lock that it doesn't own on its way out (thereby corrupting the lock state), which leads to a system hang shortly afterwards.

Normally, this won't happen because our ownership of a read lock on a higher freeze protection level blocks fsfreeze from grabbing a write lock on that higher level. *However*, if lockdep is offline, lock_is_held_type unconditionally returns 1, which means that percpu_rwsem_is_held returns 1, which means that __sb_start_write unconditionally converts blocking freeze lock attempts into trylocks, even when we *don't* hold anything that would block a fsfreeze.

Apparently this all held together until 5.10-rc1, when bugs in lockdep caused lockdep to shut itself off early in an fstests run, and once fstests gets to the "race writes with freezer" tests, kaboom. This might explain the long trail of vanishingly infrequent livelocks in fstests after lockdep goes offline that I've never been able to diagnose.

We could fix it by spinning on the trylock if wait==true, but AFAICT the locking works fine if lockdep is not built at all (and I didn't see any complaints running fstests overnight), so remove this snippet entirely.

NOTE: Commit f4b554af9931 in 2015 created the current weird logic (which used to exist in a different form in commit 5accdf82ba25c from 2012) in __sb_start_write. XFS solved this whole problem in the late 2.6 era by creating a variant of transactions (XFS_TRANS_NO_WRITECOUNT) that don't grab intwrite freeze protection, thus making lockdep's solution unnecessary. The commit claims that Dave Chinner explained that the trylock hack + comment could be removed, but nobody ever did.

Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: Jan Kara jack@suse.cz Signed-off-by: Sasha Levin sashal@kernel.org --- fs/super.c | 33 ++++----------------------------- 1 file changed, 4 insertions(+), 29 deletions(-)

diff --git a/fs/super.c b/fs/super.c index a288cd60d2aed..877532baf513d 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1647,36 +1647,11 @@ EXPORT_SYMBOL(__sb_end_write); */ int __sb_start_write(struct super_block *sb, int level, bool wait) { - bool force_trylock = false; - int ret = 1; + if (!wait) + return percpu_down_read_trylock(sb->s_writers.rw_sem + level-1);

-#ifdef CONFIG_LOCKDEP - /* - * We want lockdep to tell us about possible deadlocks with freezing - * but it's it bit tricky to properly instrument it. Getting a freeze - * protection works as getting a read lock but there are subtle - * problems. XFS for example gets freeze protection on internal level - * twice in some cases, which is OK only because we already hold a - * freeze protection also on higher level. Due to these cases we have - * to use wait == F (trylock mode) which must not fail. - */ - if (wait) { - int i; - - for (i = 0; i < level - 1; i++) - if (percpu_rwsem_is_held(sb->s_writers.rw_sem + i)) { - force_trylock = true; - break; - } - } -#endif - if (wait && !force_trylock) - percpu_down_read(sb->s_writers.rw_sem + level-1); - else - ret = percpu_down_read_trylock(sb->s_writers.rw_sem + level-1); - - WARN_ON(force_trylock && !ret); - return ret; + percpu_down_read(sb->s_writers.rw_sem + level-1); + return 1; } EXPORT_SYMBOL(__sb_start_write);

From: Paul Barker pbarker@konsulko.com

[ Upstream commit fd8feec665fef840277515a5c2b9b7c3e3970fad ]

To convert the number of pulses counted into an RPM estimation, we need to divide by the width of our measurement interval instead of multiplying by it. If the width of the measurement interval is zero we don't update the RPM value to avoid dividing by zero.

We also don't need to do 64-bit division, with 32-bits we can handle a fan running at over 4 million RPM.

Signed-off-by: Paul Barker pbarker@konsulko.com Link: https://lore.kernel.org/r/20201111164643.7087-1-pbarker@konsulko.com Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/pwm-fan.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c index 42ffd2e5182d5..c88ce77fe6763 100644 --- a/drivers/hwmon/pwm-fan.c +++ b/drivers/hwmon/pwm-fan.c @@ -54,16 +54,18 @@ static irqreturn_t pulse_handler(int irq, void *dev_id) static void sample_timer(struct timer_list *t) { struct pwm_fan_ctx *ctx = from_timer(ctx, t, rpm_timer); + unsigned int delta = ktime_ms_delta(ktime_get(), ctx->sample_start); int pulses; - u64 tmp;

- pulses = atomic_read(&ctx->pulses); - atomic_sub(pulses, &ctx->pulses); - tmp = (u64)pulses * ktime_ms_delta(ktime_get(), ctx->sample_start) * 60; - do_div(tmp, ctx->pulses_per_revolution * 1000); - ctx->rpm = tmp; + if (delta) { + pulses = atomic_read(&ctx->pulses); + atomic_sub(pulses, &ctx->pulses); + ctx->rpm = (unsigned int)(pulses * 1000 * 60) / + (ctx->pulses_per_revolution * delta); + + ctx->sample_start = ktime_get(); + }

- ctx->sample_start = ktime_get(); mod_timer(&ctx->rpm_timer, jiffies + HZ); }