From 83fd5cc6481c6b7fa8b45f8a7e0aa7120213430b Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 16 Dec 2008 19:17:11 +0100 Subject: AMD IOMMU: allocate rlookup_table with __GFP_ZERO Impact: fix bug which can lead to panic in prealloc_protection_domains() Signed-off-by: Joerg Roedel --- arch/x86/kernel/amd_iommu_init.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index 30ae2701b3df..c90a15eba5c5 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -1074,7 +1074,8 @@ int __init amd_iommu_init(void) goto free; /* IOMMU rlookup table - find the IOMMU for a specific device */ - amd_iommu_rlookup_table = (void *)__get_free_pages(GFP_KERNEL, + amd_iommu_rlookup_table = (void *)__get_free_pages( + GFP_KERNEL | __GFP_ZERO, get_order(rlookup_table_size)); if (amd_iommu_rlookup_table == NULL) goto free; -- cgit v1.2.3-55-g7522 From cf9b303e55da810255638c0b616b1a3f7eda9320 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 15 Dec 2008 23:33:10 +0100 Subject: x86: re-enable MCE on secondary CPUS after suspend/resume Impact: fix disabled MCE after resume Don't prevent multiple initialization of MCEs. Back from early prehistory mcheck_init() has a reentry check. Presumably that was needed in very old kernels to prevent it entering twice. But as Andreas points out this prevents CPU hotplug (and therefore resume) to correctly reinitialize MCEs when a AP boots again after being offlined. Just drop the check. Reported-by: Andreas Herrmann Signed-off-by: Andi Kleen Tested-by: Andreas Herrmann Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/mcheck/mce_64.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c index 4b031a4ac856..1c838032fd37 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_64.c @@ -510,12 +510,9 @@ static void __cpuinit mce_cpu_features(struct cpuinfo_x86 *c) */ void __cpuinit mcheck_init(struct cpuinfo_x86 *c) { - static cpumask_t mce_cpus = CPU_MASK_NONE; - mce_cpu_quirks(c); if (mce_dont_init || - cpu_test_and_set(smp_processor_id(), mce_cpus) || !mce_available(c)) return; -- cgit v1.2.3-55-g7522 From cf558d25e5c9f70fa0279c9b7b8b4aed7cae9bd4 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 17 Dec 2008 15:06:01 +0100 Subject: AMD IOMMU: set cmd buffer pointers to zero manually Impact: set cmd buffer head and tail pointers to zero in case nobody else did Signed-off-by: Joerg Roedel --- arch/x86/kernel/amd_iommu_init.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index c90a15eba5c5..c6cc22815d35 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -427,6 +427,10 @@ static u8 * __init alloc_command_buffer(struct amd_iommu *iommu) memcpy_toio(iommu->mmio_base + MMIO_CMD_BUF_OFFSET, &entry, sizeof(entry)); + /* set head and tail to zero manually */ + writel(0x00, iommu->mmio_base + MMIO_CMD_HEAD_OFFSET); + writel(0x00, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET); + iommu_feature_enable(iommu, CONTROL_CMDBUF_EN); return cmd_buf; -- cgit v1.2.3-55-g7522 From 84df81759590ad16b0024cf46b3423cca76b2e07 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 17 Dec 2008 16:36:44 +0100 Subject: AMD IOMMU: panic if completion wait loop fails Impact: prevents data corruption after a failed completion wait loop Signed-off-by: Joerg Roedel --- arch/x86/kernel/amd_iommu.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index a7b6dec6fc3f..0a60d60ed036 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -235,8 +235,9 @@ static int iommu_completion_wait(struct amd_iommu *iommu) status &= ~MMIO_STATUS_COM_WAIT_INT_MASK; writel(status, iommu->mmio_base + MMIO_STATUS_OFFSET); - if (unlikely((i == EXIT_LOOP_COUNT) && printk_ratelimit())) - printk(KERN_WARNING "AMD IOMMU: Completion wait loop failed\n"); + if (unlikely(i == EXIT_LOOP_COUNT)) + panic("AMD IOMMU: Completion wait loop failed\n"); + out: spin_unlock_irqrestore(&iommu->lock, flags); -- cgit v1.2.3-55-g7522 From 55aab5f49e384a361668d112eefdb33e90779af9 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 17 Dec 2008 12:52:34 -0700 Subject: x86 gart: don't complain if no AMD GART found Impact: remove annoying bootup printk It's perfectly normal for no AMD GART to be present, e.g., if you have Intel CPUs. None of the other iommu_init() functions makes noise when it finds nothing. Signed-off-by: Bjorn Helgaas Acked-by: Joerg Roedel Signed-off-by: Ingo Molnar --- arch/x86/kernel/pci-gart_64.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index ba7ad83e20a8..a35eaa379ff6 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -745,10 +745,8 @@ void __init gart_iommu_init(void) unsigned long scratch; long i; - if (cache_k8_northbridges() < 0 || num_k8_northbridges == 0) { - printk(KERN_INFO "PCI-GART: No AMD GART found.\n"); + if (cache_k8_northbridges() < 0 || num_k8_northbridges == 0) return; - } #ifndef CONFIG_AGP_AMD64 no_agp = 1; -- cgit v1.2.3-55-g7522 From 280a9ca5d0663b185ddc4443052076c29652a328 Mon Sep 17 00:00:00 2001 From: Dmitry Adamushko Date: Sat, 20 Dec 2008 00:15:24 +0100 Subject: x86: fix resume (S2R) broken by Intel microcode module, on A110L Impact: fix deadlock This is in response to the following bug report: Bug-Entry : http://bugzilla.kernel.org/show_bug.cgi?id=12100 Subject : resume (S2R) broken by Intel microcode module, on A110L Submitter : Andreas Mohr Date : 2008-11-25 08:48 (19 days old) Handled-By : Dmitry Adamushko [ The deadlock scenario has been discovered by Andreas Mohr ] I think I might have a logical explanation why the system: (http://bugzilla.kernel.org/show_bug.cgi?id=12100) might hang upon resuming, OTOH it should have likely hanged each and every time. (1) possible deadlock in microcode_resume_cpu() if either 'if' section is taken; (2) now, I don't see it in spec. and can't experimentally verify it (newer ucodes don't seem to be available for my Core2duo)... but logically-wise, I'd think that when read upon resuming, the 'microcode revision' (MSR 0x8B) should be back to its original one (we need to reload ucode anyway so it doesn't seem logical if a cpu doesn't drop the version)... if so, the comparison with memcmp() for the full 'struct cpu_signature' is wrong... and that's how one of the aforementioned 'if' sections might have been triggered - leading to a deadlock. Obviously, in my tests I simulated loading/resuming with the ucode of the same version (just to see that the file is loaded/re-loaded upon resuming) so this issue has never popped up. I'd appreciate if someone with an appropriate system might give a try to the 2nd patch (titled "fix a comparison && deadlock..."). In any case, the deadlock situation is a must-have fix. Reported-by: Andreas Mohr Signed-off-by: Dmitry Adamushko Tested-by: Andreas Mohr Signed-off-by: Ingo Molnar Cc: Signed-off-by: Ingo Molnar --- arch/x86/kernel/microcode_core.c | 19 ++++++++++++++----- arch/x86/kernel/microcode_intel.c | 6 ++++++ 2 files changed, 20 insertions(+), 5 deletions(-) diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index 82fb2809ce32..c4b5b24e0217 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -272,13 +272,18 @@ static struct attribute_group mc_attr_group = { .name = "microcode", }; -static void microcode_fini_cpu(int cpu) +static void __microcode_fini_cpu(int cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - mutex_lock(µcode_mutex); microcode_ops->microcode_fini_cpu(cpu); uci->valid = 0; +} + +static void microcode_fini_cpu(int cpu) +{ + mutex_lock(µcode_mutex); + __microcode_fini_cpu(cpu); mutex_unlock(µcode_mutex); } @@ -306,12 +311,16 @@ static int microcode_resume_cpu(int cpu) * to this cpu (a bit of paranoia): */ if (microcode_ops->collect_cpu_info(cpu, &nsig)) { - microcode_fini_cpu(cpu); + __microcode_fini_cpu(cpu); + printk(KERN_ERR "failed to collect_cpu_info for resuming cpu #%d\n", + cpu); return -1; } - if (memcmp(&nsig, &uci->cpu_sig, sizeof(nsig))) { - microcode_fini_cpu(cpu); + if ((nsig.sig != uci->cpu_sig.sig) || (nsig.pf != uci->cpu_sig.pf)) { + __microcode_fini_cpu(cpu); + printk(KERN_ERR "cached ucode doesn't match the resuming cpu #%d\n", + cpu); /* Should we look for a new ucode here? */ return 1; } diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c index 622dc4a21784..a8e62792d171 100644 --- a/arch/x86/kernel/microcode_intel.c +++ b/arch/x86/kernel/microcode_intel.c @@ -155,6 +155,7 @@ static DEFINE_SPINLOCK(microcode_update_lock); static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) { struct cpuinfo_x86 *c = &cpu_data(cpu_num); + unsigned long flags; unsigned int val[2]; memset(csig, 0, sizeof(*csig)); @@ -174,11 +175,16 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) csig->pf = 1 << ((val[1] >> 18) & 7); } + /* serialize access to the physical write to MSR 0x79 */ + spin_lock_irqsave(µcode_update_lock, flags); + wrmsr(MSR_IA32_UCODE_REV, 0, 0); /* see notes above for revision 1.07. Apparent chip bug */ sync_core(); /* get the current revision from MSR 0x8B */ rdmsr(MSR_IA32_UCODE_REV, val[0], csig->rev); + spin_unlock_irqrestore(µcode_update_lock, flags); + pr_debug("microcode: collect_cpu_info : sig=0x%x, pf=0x%x, rev=0x%x\n", csig->sig, csig->pf, csig->rev); -- cgit v1.2.3-55-g7522