From a2bd4097b3ec242f4de4924db463a9c94530e03a Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Thu, 26 Nov 2020 18:00:37 +0100 Subject: [PATCH 1/2] s390/pci: fix CPU address in MSI for directed IRQ The directed MSIs are delivered to CPUs whose address is written to the MSI message address. The current code assumes that a CPU logical number (as it is seen by the kernel) is also the CPU address. The above assumption is not correct, as the CPU address is rather the value returned by STAP instruction. That value does not necessarily match the kernel logical CPU number. Fixes: e979ce7bced2 ("s390/pci: provide support for CPU directed interrupts") Cc: # v5.2+ Signed-off-by: Alexander Gordeev Reviewed-by: Halil Pasic Reviewed-by: Niklas Schnelle Signed-off-by: Niklas Schnelle Signed-off-by: Heiko Carstens --- arch/s390/pci/pci_irq.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c index 743f257cf2cb..75217fb63d7b 100644 --- a/arch/s390/pci/pci_irq.c +++ b/arch/s390/pci/pci_irq.c @@ -103,9 +103,10 @@ static int zpci_set_irq_affinity(struct irq_data *data, const struct cpumask *de { struct msi_desc *entry = irq_get_msi_desc(data->irq); struct msi_msg msg = entry->msg; + int cpu_addr = smp_cpu_get_cpu_address(cpumask_first(dest)); msg.address_lo &= 0xff0000ff; - msg.address_lo |= (cpumask_first(dest) << 8); + msg.address_lo |= (cpu_addr << 8); pci_write_msi_msg(data->irq, &msg); return IRQ_SET_MASK_OK; @@ -238,6 +239,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) unsigned long bit; struct msi_desc *msi; struct msi_msg msg; + int cpu_addr; int rc, irq; zdev->aisb = -1UL; @@ -287,9 +289,15 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) handle_percpu_irq); msg.data = hwirq - bit; if (irq_delivery == DIRECTED) { + if (msi->affinity) + cpu = cpumask_first(&msi->affinity->mask); + else + cpu = 0; + cpu_addr = smp_cpu_get_cpu_address(cpu); + msg.address_lo = zdev->msi_addr & 0xff0000ff; - msg.address_lo |= msi->affinity ? - (cpumask_first(&msi->affinity->mask) << 8) : 0; + msg.address_lo |= (cpu_addr << 8); + for_each_possible_cpu(cpu) { airq_iv_set_data(zpci_ibv[cpu], hwirq, irq); } From b1cae1f84a0f609a34ebcaa087fbecef32f69882 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 2 Dec 2020 11:46:01 +0100 Subject: [PATCH 2/2] s390: fix irq state tracing With commit 58c644ba512c ("sched/idle: Fix arch_cpu_idle() vs tracing") common code calls arch_cpu_idle() with a lockdep state that tells irqs are on. This doesn't work very well for s390: psw_idle() will enable interrupts to wait for an interrupt. As soon as an interrupt occurs the interrupt handler will verify if the old context was psw_idle(). If that is the case the interrupt enablement bits in the old program status word will be cleared. A subsequent test in both the external as well as the io interrupt handler checks if in the old context interrupts were enabled. Due to the above patching of the old program status word it is assumed the old context had interrupts disabled, and therefore a call to TRACE_IRQS_OFF (aka trace_hardirqs_off_caller) is skipped. Which in turn makes lockdep incorrectly "think" that interrupts are enabled within the interrupt handler. Fix this by unconditionally calling TRACE_IRQS_OFF when entering interrupt handlers. Also call unconditionally TRACE_IRQS_ON when leaving interrupts handlers. This leaves the special psw_idle() case, which now returns with interrupts disabled, but has an "irqs on" lockdep state. So callers of psw_idle() must adjust the state on their own, if required. This is currently only __udelay_disabled(). Fixes: 58c644ba512c ("sched/idle: Fix arch_cpu_idle() vs tracing") Acked-by: Peter Zijlstra (Intel) Signed-off-by: Heiko Carstens --- arch/s390/kernel/entry.S | 15 --------------- arch/s390/lib/delay.c | 5 ++--- 2 files changed, 2 insertions(+), 18 deletions(-) diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 26bb0603c5a1..92beb1444644 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -763,12 +763,7 @@ ENTRY(io_int_handler) xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) TSTMSK __LC_CPU_FLAGS,_CIF_IGNORE_IRQ jo .Lio_restore -#if IS_ENABLED(CONFIG_TRACE_IRQFLAGS) - tmhh %r8,0x300 - jz 1f TRACE_IRQS_OFF -1: -#endif xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) .Lio_loop: lgr %r2,%r11 # pass pointer to pt_regs @@ -791,12 +786,7 @@ ENTRY(io_int_handler) TSTMSK __LC_CPU_FLAGS,_CIF_WORK jnz .Lio_work .Lio_restore: -#if IS_ENABLED(CONFIG_TRACE_IRQFLAGS) - tm __PT_PSW(%r11),3 - jno 0f TRACE_IRQS_ON -0: -#endif mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) tm __PT_PSW+1(%r11),0x01 # returning to user ? jno .Lio_exit_kernel @@ -976,12 +966,7 @@ ENTRY(ext_int_handler) xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) TSTMSK __LC_CPU_FLAGS,_CIF_IGNORE_IRQ jo .Lio_restore -#if IS_ENABLED(CONFIG_TRACE_IRQFLAGS) - tmhh %r8,0x300 - jz 1f TRACE_IRQS_OFF -1: -#endif xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) lgr %r2,%r11 # pass pointer to pt_regs lghi %r3,EXT_INTERRUPT diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c index daca7bad66de..8c0c68e7770e 100644 --- a/arch/s390/lib/delay.c +++ b/arch/s390/lib/delay.c @@ -33,7 +33,7 @@ EXPORT_SYMBOL(__delay); static void __udelay_disabled(unsigned long long usecs) { - unsigned long cr0, cr0_new, psw_mask, flags; + unsigned long cr0, cr0_new, psw_mask; struct s390_idle_data idle; u64 end; @@ -45,9 +45,8 @@ static void __udelay_disabled(unsigned long long usecs) psw_mask = __extract_psw() | PSW_MASK_EXT | PSW_MASK_WAIT; set_clock_comparator(end); set_cpu_flag(CIF_IGNORE_IRQ); - local_irq_save(flags); psw_idle(&idle, psw_mask); - local_irq_restore(flags); + trace_hardirqs_off(); clear_cpu_flag(CIF_IGNORE_IRQ); set_clock_comparator(S390_lowcore.clock_comparator); __ctl_load(cr0, 0, 0);