From ca589ea8d1b64938329c016a5c07fc2eea985712 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 8 Sep 2020 15:30:31 +0200 Subject: [PATCH 1/6] s390/idle: fix suspicious RCU usage After commit eb1f00237aca ("lockdep,trace: Expose tracepoints") the lock tracepoints are visible to lockdep and RCU-lockdep is finding a bunch more RCU violations that were previously hidden. Switch the idle->seqcount over to using raw_write_*() to avoid the lockdep annotation and thus the lock tracepoints. Reported-by: Guenter Roeck Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/idle.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index c73f50649e7e..f7f1e64e0d98 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -39,14 +39,13 @@ void enabled_wait(void) local_irq_restore(flags); /* Account time spent with enabled wait psw loaded as idle time. */ - /* XXX seqcount has tracepoints that require RCU */ - write_seqcount_begin(&idle->seqcount); + raw_write_seqcount_begin(&idle->seqcount); idle_time = idle->clock_idle_exit - idle->clock_idle_enter; idle->clock_idle_enter = idle->clock_idle_exit = 0ULL; idle->idle_time += idle_time; idle->idle_count++; account_idle_time(cputime_to_nsecs(idle_time)); - write_seqcount_end(&idle->seqcount); + raw_write_seqcount_end(&idle->seqcount); } NOKPROBE_SYMBOL(enabled_wait); From b6186d7fb53349efd274263a45f0b08749ccaa2d Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Wed, 9 Sep 2020 11:59:43 +0200 Subject: [PATCH 2/6] s390/zcrypt: fix kmalloc 256k failure Tests showed that under stress conditions the kernel may temporary fail to allocate 256k with kmalloc. However, this fix reworks the related code in the cca_findcard2() function to use kvmalloc instead. Signed-off-by: Harald Freudenberger Reviewed-by: Ingo Franzki Cc: Stable Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/zcrypt_ccamisc.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c index 3f5b61351cde..c793dcabd551 100644 --- a/drivers/s390/crypto/zcrypt_ccamisc.c +++ b/drivers/s390/crypto/zcrypt_ccamisc.c @@ -1692,9 +1692,9 @@ int cca_findcard2(u32 **apqns, u32 *nr_apqns, u16 cardnr, u16 domain, *nr_apqns = 0; /* fetch status of all crypto cards */ - device_status = kmalloc_array(MAX_ZDEV_ENTRIES_EXT, - sizeof(struct zcrypt_device_status_ext), - GFP_KERNEL); + device_status = kvmalloc_array(MAX_ZDEV_ENTRIES_EXT, + sizeof(struct zcrypt_device_status_ext), + GFP_KERNEL); if (!device_status) return -ENOMEM; zcrypt_device_status_mask_ext(device_status); @@ -1762,7 +1762,7 @@ int cca_findcard2(u32 **apqns, u32 *nr_apqns, u16 cardnr, u16 domain, verify = 0; } - kfree(device_status); + kvfree(device_status); return rc; } EXPORT_SYMBOL(cca_findcard2); From fcb2b70cdb194157678fb1a75f9ff499aeba3d2a Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Wed, 9 Sep 2020 14:27:25 +0200 Subject: [PATCH 3/6] s390/init: add missing __init annotations Add __init to reserve_memory_end, reserve_oldmem and remove_oldmem. Sometimes these functions are not inlined, and then the build complains about section mismatch. Signed-off-by: Ilya Leoshkevich Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/setup.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index e600f6953d7c..c2c1b4e723ea 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -619,7 +619,7 @@ static struct notifier_block kdump_mem_nb = { /* * Make sure that the area behind memory_end is protected */ -static void reserve_memory_end(void) +static void __init reserve_memory_end(void) { if (memory_end_set) memblock_reserve(memory_end, ULONG_MAX); @@ -628,7 +628,7 @@ static void reserve_memory_end(void) /* * Make sure that oldmem, where the dump is stored, is protected */ -static void reserve_oldmem(void) +static void __init reserve_oldmem(void) { #ifdef CONFIG_CRASH_DUMP if (OLDMEM_BASE) @@ -640,7 +640,7 @@ static void reserve_oldmem(void) /* * Make sure that oldmem, where the dump is stored, is protected */ -static void remove_oldmem(void) +static void __init remove_oldmem(void) { #ifdef CONFIG_CRASH_DUMP if (OLDMEM_BASE) From afdf9550e54627fcf4dd609bdc1153059378cdf5 Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Thu, 3 Sep 2020 13:42:57 +0200 Subject: [PATCH 4/6] s390/pci: fix leak of DMA tables on hard unplug commit f606b3ef47c9 ("s390/pci: adapt events for zbus") removed the zpci_disable_device() call for a zPCI event with PEC 0x0304 because the device is already deconfigured by the platform. This however skips the Linux side of the disable in particular it leads to leaking the DMA tables and bitmaps because zpci_dma_exit_device() is never called on the device. If the device transitions to the Reserved state we call zpci_zdev_put() but zpci_release_device() will not call zpci_disable_device() because the state of the zPCI function is already ZPCI_FN_STATE_STANDBY. If the device is put into the Standby state, zpci_disable_device() is not called and the device is assumed to have been put in Standby through platform action. At this point the device may be removed by a subsequent event with PEC 0x0308 or 0x0306 which calls zpci_zdev_put() with the same problem as above or the device may be configured again in which case zpci_disable_device() is also not called. Fix this by calling zpci_disable_device() explicitly for PEC 0x0304 as before. To make it more clear that zpci_disable_device() may be called, even if the lower level device has already been disabled by the platform, add a comment to zpci_disable_device(). Cc: # 5.8 Fixes: f606b3ef47c9 ("s390/pci: adapt events for zbus") Signed-off-by: Niklas Schnelle Signed-off-by: Vasily Gorbik --- arch/s390/pci/pci.c | 4 ++++ arch/s390/pci/pci_event.c | 2 ++ 2 files changed, 6 insertions(+) diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 4b62d6b55024..1804230dd8d8 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -668,6 +668,10 @@ EXPORT_SYMBOL_GPL(zpci_enable_device); int zpci_disable_device(struct zpci_dev *zdev) { zpci_dma_exit_device(zdev); + /* + * The zPCI function may already be disabled by the platform, this is + * detected in clp_disable_fh() which becomes a no-op. + */ return clp_disable_fh(zdev); } EXPORT_SYMBOL_GPL(zpci_disable_device); diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index 9a3a291cad43..d9ae7456dd4c 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -143,6 +143,8 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) zpci_remove_device(zdev); } + zdev->fh = ccdf->fh; + zpci_disable_device(zdev); zdev->state = ZPCI_FN_STATE_STANDBY; if (!clp_get_state(ccdf->fid, &state) && state == ZPCI_FN_STATE_RESERVED) { From 73ac74c7d489756d2313219a108809921dbfaea1 Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Thu, 10 Sep 2020 12:24:53 +0200 Subject: [PATCH 5/6] lockdep: fix order in trace_hardirqs_off_caller() Switch order so that locking state is consistent even if the IRQ tracer calls into lockdep again. Acked-by: Peter Zijlstra Signed-off-by: Sven Schnelle Signed-off-by: Vasily Gorbik --- kernel/trace/trace_preemptirq.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c index f10073e62603..f4938040c228 100644 --- a/kernel/trace/trace_preemptirq.c +++ b/kernel/trace/trace_preemptirq.c @@ -102,14 +102,14 @@ NOKPROBE_SYMBOL(trace_hardirqs_on_caller); __visible void trace_hardirqs_off_caller(unsigned long caller_addr) { + lockdep_hardirqs_off(CALLER_ADDR0); + if (!this_cpu_read(tracing_irq_cpu)) { this_cpu_write(tracing_irq_cpu, 1); tracer_hardirqs_off(CALLER_ADDR0, caller_addr); if (!in_nmi()) trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr); } - - lockdep_hardirqs_off(CALLER_ADDR0); } EXPORT_SYMBOL(trace_hardirqs_off_caller); NOKPROBE_SYMBOL(trace_hardirqs_off_caller); From cd4d3d5f21ddbfae3f686ac0ff405f21f7847ad3 Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Tue, 8 Sep 2020 09:05:04 -0400 Subject: [PATCH 6/6] s390: add 3f program exception handler Program exception 3f (secure storage violation) can only be detected when the CPU is running in SIE with a format 4 state description, e.g. running a protected guest. Because of this and because user space partly controls the guest memory mapping and can trigger this exception, we want to send a SIGSEGV to the process running the guest and not panic the kernel. Signed-off-by: Janosch Frank Cc: # 5.7 Fixes: 084ea4d611a3 ("s390/mm: add (non)secure page access exceptions handlers") Reviewed-by: Claudio Imbrenda Reviewed-by: Cornelia Huck Acked-by: Christian Borntraeger Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/entry.h | 1 + arch/s390/kernel/pgm_check.S | 2 +- arch/s390/mm/fault.c | 20 ++++++++++++++++++++ 3 files changed, 22 insertions(+), 1 deletion(-) diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index faca269d5f27..a44ddc2f2dec 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -26,6 +26,7 @@ void do_protection_exception(struct pt_regs *regs); void do_dat_exception(struct pt_regs *regs); void do_secure_storage_access(struct pt_regs *regs); void do_non_secure_storage_access(struct pt_regs *regs); +void do_secure_storage_violation(struct pt_regs *regs); void addressing_exception(struct pt_regs *regs); void data_exception(struct pt_regs *regs); diff --git a/arch/s390/kernel/pgm_check.S b/arch/s390/kernel/pgm_check.S index 2c27907a5ffc..9a92638360ee 100644 --- a/arch/s390/kernel/pgm_check.S +++ b/arch/s390/kernel/pgm_check.S @@ -80,7 +80,7 @@ PGM_CHECK(do_dat_exception) /* 3b */ PGM_CHECK_DEFAULT /* 3c */ PGM_CHECK(do_secure_storage_access) /* 3d */ PGM_CHECK(do_non_secure_storage_access) /* 3e */ -PGM_CHECK_DEFAULT /* 3f */ +PGM_CHECK(do_secure_storage_violation) /* 3f */ PGM_CHECK(monitor_event_exception) /* 40 */ PGM_CHECK_DEFAULT /* 41 */ PGM_CHECK_DEFAULT /* 42 */ diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 4c8c063bce5b..996884dcc9fd 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -859,6 +859,21 @@ void do_non_secure_storage_access(struct pt_regs *regs) } NOKPROBE_SYMBOL(do_non_secure_storage_access); +void do_secure_storage_violation(struct pt_regs *regs) +{ + /* + * Either KVM messed up the secure guest mapping or the same + * page is mapped into multiple secure guests. + * + * This exception is only triggered when a guest 2 is running + * and can therefore never occur in kernel context. + */ + printk_ratelimited(KERN_WARNING + "Secure storage violation in task: %s, pid %d\n", + current->comm, current->pid); + send_sig(SIGSEGV, current, 0); +} + #else void do_secure_storage_access(struct pt_regs *regs) { @@ -869,4 +884,9 @@ void do_non_secure_storage_access(struct pt_regs *regs) { default_trap_handler(regs); } + +void do_secure_storage_violation(struct pt_regs *regs) +{ + default_trap_handler(regs); +} #endif