From 2ad67141f1e47dc063b202993835361a06239aaa Mon Sep 17 00:00:00 2001 From: Tushar Dave Date: Tue, 11 Jul 2017 14:34:47 -0700 Subject: SPARC64: Fix sun4v DMA panic 64bit DMA only supported on sun4v equipped with ATU IOMMU HW. 'Commit b02c2b0bfd7ae ("sparc: remove arch specific dma_supported implementations")' introduced a code that incorrectly allow dma_supported() to succeed for 64bit dma mask even if system doesn't have ATU IOMMU. This results into panic. Fix it. Reported-by: Meelis Roos Signed-off-by: Tushar Dave Reviewed-by: Christoph Hellwig Signed-off-by: David S. Miller --- arch/sparc/kernel/pci_sun4v.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'arch/sparc/kernel') diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index 24f21c726dfa..f10e2f712394 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -673,12 +673,14 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist, static int dma_4v_supported(struct device *dev, u64 device_mask) { struct iommu *iommu = dev->archdata.iommu; - u64 dma_addr_mask; + u64 dma_addr_mask = iommu->dma_addr_mask; - if (device_mask > DMA_BIT_MASK(32) && iommu->atu) - dma_addr_mask = iommu->atu->dma_addr_mask; - else - dma_addr_mask = iommu->dma_addr_mask; + if (device_mask > DMA_BIT_MASK(32)) { + if (iommu->atu) + dma_addr_mask = iommu->atu->dma_addr_mask; + else + return 0; + } if ((device_mask & dma_addr_mask) == dma_addr_mask) return 1; -- cgit From f2e0cff85ed111a3cf24d894c3fa11697dfae628 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 12 Jul 2017 14:35:43 -0700 Subject: kernel/watchdog: introduce arch_touch_nmi_watchdog() For architectures that define HAVE_NMI_WATCHDOG, instead of having them provide the complete touch_nmi_watchdog() function, just have them provide arch_touch_nmi_watchdog(). This gives the generic code more flexibility in implementing this function, and arch implementations don't miss out on touching the softlockup watchdog or other generic details. Link: http://lkml.kernel.org/r/20170616065715.18390-3-npiggin@gmail.com Signed-off-by: Nicholas Piggin Reviewed-by: Don Zickus Reviewed-by: Babu Moger Tested-by: Babu Moger [sparc] Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sparc/kernel/nmi.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'arch/sparc/kernel') diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index 95e73c63c99d..048ad783ea3f 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -51,7 +51,7 @@ static DEFINE_PER_CPU(unsigned int, last_irq_sum); static DEFINE_PER_CPU(long, alert_counter); static DEFINE_PER_CPU(int, nmi_touch); -void touch_nmi_watchdog(void) +void arch_touch_nmi_watchdog(void) { if (atomic_read(&nmi_active)) { int cpu; @@ -61,10 +61,8 @@ void touch_nmi_watchdog(void) per_cpu(nmi_touch, cpu) = 1; } } - - touch_softlockup_watchdog(); } -EXPORT_SYMBOL(touch_nmi_watchdog); +EXPORT_SYMBOL(arch_touch_nmi_watchdog); static void die_nmi(const char *str, struct pt_regs *regs, int do_panic) { -- cgit From dcda9b04713c3f6ff0875652924844fae28286ea Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 12 Jul 2017 14:36:45 -0700 Subject: mm, tree wide: replace __GFP_REPEAT by __GFP_RETRY_MAYFAIL with more useful semantic __GFP_REPEAT was designed to allow retry-but-eventually-fail semantic to the page allocator. This has been true but only for allocations requests larger than PAGE_ALLOC_COSTLY_ORDER. It has been always ignored for smaller sizes. This is a bit unfortunate because there is no way to express the same semantic for those requests and they are considered too important to fail so they might end up looping in the page allocator for ever, similarly to GFP_NOFAIL requests. Now that the whole tree has been cleaned up and accidental or misled usage of __GFP_REPEAT flag has been removed for !costly requests we can give the original flag a better name and more importantly a more useful semantic. Let's rename it to __GFP_RETRY_MAYFAIL which tells the user that the allocator would try really hard but there is no promise of a success. This will work independent of the order and overrides the default allocator behavior. Page allocator users have several levels of guarantee vs. cost options (take GFP_KERNEL as an example) - GFP_KERNEL & ~__GFP_RECLAIM - optimistic allocation without _any_ attempt to free memory at all. The most light weight mode which even doesn't kick the background reclaim. Should be used carefully because it might deplete the memory and the next user might hit the more aggressive reclaim - GFP_KERNEL & ~__GFP_DIRECT_RECLAIM (or GFP_NOWAIT)- optimistic allocation without any attempt to free memory from the current context but can wake kswapd to reclaim memory if the zone is below the low watermark. Can be used from either atomic contexts or when the request is a performance optimization and there is another fallback for a slow path. - (GFP_KERNEL|__GFP_HIGH) & ~__GFP_DIRECT_RECLAIM (aka GFP_ATOMIC) - non sleeping allocation with an expensive fallback so it can access some portion of memory reserves. Usually used from interrupt/bh context with an expensive slow path fallback. - GFP_KERNEL - both background and direct reclaim are allowed and the _default_ page allocator behavior is used. That means that !costly allocation requests are basically nofail but there is no guarantee of that behavior so failures have to be checked properly by callers (e.g. OOM killer victim is allowed to fail currently). - GFP_KERNEL | __GFP_NORETRY - overrides the default allocator behavior and all allocation requests fail early rather than cause disruptive reclaim (one round of reclaim in this implementation). The OOM killer is not invoked. - GFP_KERNEL | __GFP_RETRY_MAYFAIL - overrides the default allocator behavior and all allocation requests try really hard. The request will fail if the reclaim cannot make any progress. The OOM killer won't be triggered. - GFP_KERNEL | __GFP_NOFAIL - overrides the default allocator behavior and all allocation requests will loop endlessly until they succeed. This might be really dangerous especially for larger orders. Existing users of __GFP_REPEAT are changed to __GFP_RETRY_MAYFAIL because they already had their semantic. No new users are added. __alloc_pages_slowpath is changed to bail out for __GFP_RETRY_MAYFAIL if there is no progress and we have already passed the OOM point. This means that all the reclaim opportunities have been exhausted except the most disruptive one (the OOM killer) and a user defined fallback behavior is more sensible than keep retrying in the page allocator. [akpm@linux-foundation.org: fix arch/sparc/kernel/mdesc.c] [mhocko@suse.com: semantic fix] Link: http://lkml.kernel.org/r/20170626123847.GM11534@dhcp22.suse.cz [mhocko@kernel.org: address other thing spotted by Vlastimil] Link: http://lkml.kernel.org/r/20170626124233.GN11534@dhcp22.suse.cz Link: http://lkml.kernel.org/r/20170623085345.11304-3-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Alex Belits Cc: Chris Wilson Cc: Christoph Hellwig Cc: Darrick J. Wong Cc: David Daney Cc: Johannes Weiner Cc: Mel Gorman Cc: NeilBrown Cc: Ralf Baechle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sparc/kernel/mdesc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/sparc/kernel') diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c index e4b4e790bf89..fa466ce45bc9 100644 --- a/arch/sparc/kernel/mdesc.c +++ b/arch/sparc/kernel/mdesc.c @@ -205,7 +205,7 @@ static struct mdesc_handle *mdesc_kmalloc(unsigned int mdesc_size) handle_size = (sizeof(struct mdesc_handle) - sizeof(struct mdesc_hdr) + mdesc_size); - base = kmalloc(handle_size + 15, GFP_KERNEL | __GFP_REPEAT); + base = kmalloc(handle_size + 15, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!base) return NULL; -- cgit From 9d53caec84c7c5700e7c1ed744ea584fff55f9ac Mon Sep 17 00:00:00 2001 From: Jane Chu Date: Tue, 11 Jul 2017 12:00:54 -0600 Subject: sparc64: Measure receiver forward progress to avoid send mondo timeout A large sun4v SPARC system may have moments of intensive xcall activities, usually caused by unmapping many pages on many CPUs concurrently. This can flood receivers with CPU mondo interrupts for an extended period, causing some unlucky senders to hit send-mondo timeout. This problem gets worse as cpu count increases because sometimes mappings must be invalidated on all CPUs, and sometimes all CPUs may gang up on a single CPU. But a busy system is not a broken system. In the above scenario, as long as the receiver is making forward progress processing mondo interrupts, the sender should continue to retry. This patch implements the receiver's forward progress meter by introducing a per cpu counter 'cpu_mondo_counter[cpu]' where 'cpu' is in the range of 0..NR_CPUS. The receiver increments its counter as soon as it receives a mondo and the sender tracks the receiver's counter. If the receiver has stopped making forward progress when the retry limit is reached, the sender declares send-mondo-timeout and panic; otherwise, the receiver is allowed to keep making forward progress. In addition, it's been observed that PCIe hotplug events generate Correctable Errors that are handled by hypervisor and then OS. Hypervisor 'borrows' a guest cpu strand briefly to provide the service. If the cpu strand is simultaneously the only cpu targeted by a mondo, it may not be available for the mondo in 20msec, causing SUN4V mondo timeout. It appears that 1 second is the agreed wait time between hypervisor and guest OS, this patch makes the adjustment. Orabug: 25476541 Orabug: 26417466 Signed-off-by: Jane Chu Reviewed-by: Steve Sistare Reviewed-by: Anthony Yznaga Reviewed-by: Rob Gardner Reviewed-by: Thomas Tai Signed-off-by: David S. Miller --- arch/sparc/kernel/smp_64.c | 185 +++++++++++++++++++++++++---------------- arch/sparc/kernel/sun4v_ivec.S | 15 ++++ arch/sparc/kernel/traps_64.c | 1 + 3 files changed, 131 insertions(+), 70 deletions(-) (limited to 'arch/sparc/kernel') diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index fdf31040a7dc..3218bc43302e 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -622,22 +622,48 @@ retry: } } -/* Multi-cpu list version. */ +#define CPU_MONDO_COUNTER(cpuid) (cpu_mondo_counter[cpuid]) +#define MONDO_USEC_WAIT_MIN 2 +#define MONDO_USEC_WAIT_MAX 100 +#define MONDO_RETRY_LIMIT 500000 + +/* Multi-cpu list version. + * + * Deliver xcalls to 'cnt' number of cpus in 'cpu_list'. + * Sometimes not all cpus receive the mondo, requiring us to re-send + * the mondo until all cpus have received, or cpus are truly stuck + * unable to receive mondo, and we timeout. + * Occasionally a target cpu strand is borrowed briefly by hypervisor to + * perform guest service, such as PCIe error handling. Consider the + * service time, 1 second overall wait is reasonable for 1 cpu. + * Here two in-between mondo check wait time are defined: 2 usec for + * single cpu quick turn around and up to 100usec for large cpu count. + * Deliver mondo to large number of cpus could take longer, we adjusts + * the retry count as long as target cpus are making forward progress. + */ static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt) { - int retries, this_cpu, prev_sent, i, saw_cpu_error; + int this_cpu, tot_cpus, prev_sent, i, rem; + int usec_wait, retries, tot_retries; + u16 first_cpu = 0xffff; + unsigned long xc_rcvd = 0; unsigned long status; + int ecpuerror_id = 0; + int enocpu_id = 0; u16 *cpu_list; + u16 cpu; this_cpu = smp_processor_id(); - cpu_list = __va(tb->cpu_list_pa); - - saw_cpu_error = 0; - retries = 0; + usec_wait = cnt * MONDO_USEC_WAIT_MIN; + if (usec_wait > MONDO_USEC_WAIT_MAX) + usec_wait = MONDO_USEC_WAIT_MAX; + retries = tot_retries = 0; + tot_cpus = cnt; prev_sent = 0; + do { - int forward_progress, n_sent; + int n_sent, mondo_delivered, target_cpu_busy; status = sun4v_cpu_mondo_send(cnt, tb->cpu_list_pa, @@ -645,94 +671,113 @@ static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt) /* HV_EOK means all cpus received the xcall, we're done. */ if (likely(status == HV_EOK)) - break; + goto xcall_done; + + /* If not these non-fatal errors, panic */ + if (unlikely((status != HV_EWOULDBLOCK) && + (status != HV_ECPUERROR) && + (status != HV_ENOCPU))) + goto fatal_errors; /* First, see if we made any forward progress. + * + * Go through the cpu_list, count the target cpus that have + * received our mondo (n_sent), and those that did not (rem). + * Re-pack cpu_list with the cpus remain to be retried in the + * front - this simplifies tracking the truly stalled cpus. * * The hypervisor indicates successful sends by setting * cpu list entries to the value 0xffff. + * + * EWOULDBLOCK means some target cpus did not receive the + * mondo and retry usually helps. + * + * ECPUERROR means at least one target cpu is in error state, + * it's usually safe to skip the faulty cpu and retry. + * + * ENOCPU means one of the target cpu doesn't belong to the + * domain, perhaps offlined which is unexpected, but not + * fatal and it's okay to skip the offlined cpu. */ + rem = 0; n_sent = 0; for (i = 0; i < cnt; i++) { - if (likely(cpu_list[i] == 0xffff)) + cpu = cpu_list[i]; + if (likely(cpu == 0xffff)) { n_sent++; + } else if ((status == HV_ECPUERROR) && + (sun4v_cpu_state(cpu) == HV_CPU_STATE_ERROR)) { + ecpuerror_id = cpu + 1; + } else if (status == HV_ENOCPU && !cpu_online(cpu)) { + enocpu_id = cpu + 1; + } else { + cpu_list[rem++] = cpu; + } } - forward_progress = 0; - if (n_sent > prev_sent) - forward_progress = 1; + /* No cpu remained, we're done. */ + if (rem == 0) + break; - prev_sent = n_sent; + /* Otherwise, update the cpu count for retry. */ + cnt = rem; - /* If we get a HV_ECPUERROR, then one or more of the cpus - * in the list are in error state. Use the cpu_state() - * hypervisor call to find out which cpus are in error state. + /* Record the overall number of mondos received by the + * first of the remaining cpus. */ - if (unlikely(status == HV_ECPUERROR)) { - for (i = 0; i < cnt; i++) { - long err; - u16 cpu; + if (first_cpu != cpu_list[0]) { + first_cpu = cpu_list[0]; + xc_rcvd = CPU_MONDO_COUNTER(first_cpu); + } - cpu = cpu_list[i]; - if (cpu == 0xffff) - continue; + /* Was any mondo delivered successfully? */ + mondo_delivered = (n_sent > prev_sent); + prev_sent = n_sent; - err = sun4v_cpu_state(cpu); - if (err == HV_CPU_STATE_ERROR) { - saw_cpu_error = (cpu + 1); - cpu_list[i] = 0xffff; - } - } - } else if (unlikely(status != HV_EWOULDBLOCK)) - goto fatal_mondo_error; + /* or, was any target cpu busy processing other mondos? */ + target_cpu_busy = (xc_rcvd < CPU_MONDO_COUNTER(first_cpu)); + xc_rcvd = CPU_MONDO_COUNTER(first_cpu); - /* Don't bother rewriting the CPU list, just leave the - * 0xffff and non-0xffff entries in there and the - * hypervisor will do the right thing. - * - * Only advance timeout state if we didn't make any - * forward progress. + /* Retry count is for no progress. If we're making progress, + * reset the retry count. */ - if (unlikely(!forward_progress)) { - if (unlikely(++retries > 10000)) - goto fatal_mondo_timeout; - - /* Delay a little bit to let other cpus catch up - * on their cpu mondo queue work. - */ - udelay(2 * cnt); + if (likely(mondo_delivered || target_cpu_busy)) { + tot_retries += retries; + retries = 0; + } else if (unlikely(retries > MONDO_RETRY_LIMIT)) { + goto fatal_mondo_timeout; } - } while (1); - if (unlikely(saw_cpu_error)) - goto fatal_mondo_cpu_error; + /* Delay a little bit to let other cpus catch up on + * their cpu mondo queue work. + */ + if (!mondo_delivered) + udelay(usec_wait); - return; + retries++; + } while (1); -fatal_mondo_cpu_error: - printk(KERN_CRIT "CPU[%d]: SUN4V mondo cpu error, some target cpus " - "(including %d) were in error state\n", - this_cpu, saw_cpu_error - 1); +xcall_done: + if (unlikely(ecpuerror_id > 0)) { + pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) was in error state\n", + this_cpu, ecpuerror_id - 1); + } else if (unlikely(enocpu_id > 0)) { + pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) does not belong to the domain\n", + this_cpu, enocpu_id - 1); + } return; +fatal_errors: + /* fatal errors include bad alignment, etc */ + pr_crit("CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) mondo_block_pa(%lx)\n", + this_cpu, tot_cpus, tb->cpu_list_pa, tb->cpu_mondo_block_pa); + panic("Unexpected SUN4V mondo error %lu\n", status); + fatal_mondo_timeout: - printk(KERN_CRIT "CPU[%d]: SUN4V mondo timeout, no forward " - " progress after %d retries.\n", - this_cpu, retries); - goto dump_cpu_list_and_out; - -fatal_mondo_error: - printk(KERN_CRIT "CPU[%d]: Unexpected SUN4V mondo error %lu\n", - this_cpu, status); - printk(KERN_CRIT "CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) " - "mondo_block_pa(%lx)\n", - this_cpu, cnt, tb->cpu_list_pa, tb->cpu_mondo_block_pa); - -dump_cpu_list_and_out: - printk(KERN_CRIT "CPU[%d]: CPU list [ ", this_cpu); - for (i = 0; i < cnt; i++) - printk("%u ", cpu_list[i]); - printk("]\n"); + /* some cpus being non-responsive to the cpu mondo */ + pr_crit("CPU[%d]: SUN4V mondo timeout, cpu(%d) made no forward progress after %d retries. Total target cpus(%d).\n", + this_cpu, first_cpu, (tot_retries + retries), tot_cpus); + panic("SUN4V mondo timeout panic\n"); } static void (*xcall_deliver_impl)(struct trap_per_cpu *, int); diff --git a/arch/sparc/kernel/sun4v_ivec.S b/arch/sparc/kernel/sun4v_ivec.S index 559bc5e9c199..34631995859a 100644 --- a/arch/sparc/kernel/sun4v_ivec.S +++ b/arch/sparc/kernel/sun4v_ivec.S @@ -26,6 +26,21 @@ sun4v_cpu_mondo: ldxa [%g0] ASI_SCRATCHPAD, %g4 sub %g4, TRAP_PER_CPU_FAULT_INFO, %g4 + /* Get smp_processor_id() into %g3 */ + sethi %hi(trap_block), %g5 + or %g5, %lo(trap_block), %g5 + sub %g4, %g5, %g3 + srlx %g3, TRAP_BLOCK_SZ_SHIFT, %g3 + + /* Increment cpu_mondo_counter[smp_processor_id()] */ + sethi %hi(cpu_mondo_counter), %g5 + or %g5, %lo(cpu_mondo_counter), %g5 + sllx %g3, 3, %g3 + add %g5, %g3, %g5 + ldx [%g5], %g3 + add %g3, 1, %g3 + stx %g3, [%g5] + /* Get CPU mondo queue base phys address into %g7. */ ldx [%g4 + TRAP_PER_CPU_CPU_MONDO_PA], %g7 diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index 196ee5eb4d48..ad31af1dd726 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -2733,6 +2733,7 @@ void do_getpsr(struct pt_regs *regs) } } +u64 cpu_mondo_counter[NR_CPUS] = {0}; struct trap_per_cpu trap_block[NR_CPUS]; EXPORT_SYMBOL(trap_block); -- cgit