From ae9b9403644f3ecc76867af042e7e1cfd5c099d0 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 30 Oct 2008 17:43:57 +0100 Subject: AMD IOMMU: fix detection of NP capable IOMMUs This patch changes the code to use IOMMU_CAP_NPCACHE as a shift and not as a mask. Signed-off-by: Joerg Roedel --- arch/x86/kernel/amd_iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index 3b346c6f551..38e88d40ab1 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -50,7 +50,7 @@ static int dma_ops_unity_map(struct dma_ops_domain *dma_dom, /* returns !0 if the IOMMU is caching non-present entries in its TLB */ static int iommu_has_npcache(struct amd_iommu *iommu) { - return iommu->cap & IOMMU_CAP_NPCACHE; + return iommu->cap & (1UL << IOMMU_CAP_NPCACHE); } /**************************************************************************** -- cgit v1.2.3 From 73557af5bf32c3db973050de1fb73423e8fc873e Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Fri, 31 Oct 2008 13:59:49 -0400 Subject: x86, voyager: fix smp_intr_init() compile breakage Impact: fix x86/Voyager build Looks like this became static on the rest of x86. Fix it up by adding an external definition to mach-voyager/setup.c Signed-off-by: Ingo Molnar --- arch/x86/include/asm/voyager.h | 1 + arch/x86/mach-voyager/setup.c | 2 +- arch/x86/mach-voyager/voyager_smp.c | 2 +- 3 files changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/voyager.h b/arch/x86/include/asm/voyager.h index 9c811d2e6f9..b3e64730762 100644 --- a/arch/x86/include/asm/voyager.h +++ b/arch/x86/include/asm/voyager.h @@ -520,6 +520,7 @@ extern void voyager_restart(void); extern void voyager_cat_power_off(void); extern void voyager_cat_do_common_interrupt(void); extern void voyager_handle_nmi(void); +extern void voyager_smp_intr_init(void); /* Commands for the following are */ #define VOYAGER_PSI_READ 0 #define VOYAGER_PSI_WRITE 1 diff --git a/arch/x86/mach-voyager/setup.c b/arch/x86/mach-voyager/setup.c index 6bbdd633864..a580b9562e7 100644 --- a/arch/x86/mach-voyager/setup.c +++ b/arch/x86/mach-voyager/setup.c @@ -27,7 +27,7 @@ static struct irqaction irq2 = { void __init intr_init_hook(void) { #ifdef CONFIG_SMP - smp_intr_init(); + voyager_smp_intr_init(); #endif setup_irq(2, &irq2); diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c index 7f4c6af1435..0e331652681 100644 --- a/arch/x86/mach-voyager/voyager_smp.c +++ b/arch/x86/mach-voyager/voyager_smp.c @@ -1258,7 +1258,7 @@ static void handle_vic_irq(unsigned int irq, struct irq_desc *desc) #define QIC_SET_GATE(cpi, vector) \ set_intr_gate((cpi) + QIC_DEFAULT_CPI_BASE, (vector)) -void __init smp_intr_init(void) +void __init voyager_smp_intr_init(void) { int i; -- cgit v1.2.3 From 70de9a97049e0ba79dc040868564408d5ce697f9 Mon Sep 17 00:00:00 2001 From: Alok Kataria Date: Mon, 3 Nov 2008 11:18:47 -0800 Subject: x86: don't use tsc_khz to calculate lpj if notsc is passed Impact: fix udelay when "notsc" boot parameter is passed With notsc passed on commandline, tsc may not be used for udelays, make sure that we do not use tsc_khz to calculate the lpj value in such cases. Reported-by: Bartlomiej Zolnierkiewicz Signed-off-by: Alok N Kataria Cc: Signed-off-by: Ingo Molnar --- arch/x86/kernel/tsc.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 62348e4fd8d..2ef80e30192 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -813,10 +813,6 @@ void __init tsc_init(void) cpu_khz = calibrate_cpu(); #endif - lpj = ((u64)tsc_khz * 1000); - do_div(lpj, HZ); - lpj_fine = lpj; - printk("Detected %lu.%03lu MHz processor.\n", (unsigned long)cpu_khz / 1000, (unsigned long)cpu_khz % 1000); @@ -836,6 +832,10 @@ void __init tsc_init(void) /* now allow native_sched_clock() to use rdtsc */ tsc_disabled = 0; + lpj = ((u64)tsc_khz * 1000); + do_div(lpj, HZ); + lpj_fine = lpj; + use_tsc_delay(); /* Check and install the TSC clocksource */ dmi_check_system(bad_tsc_dmi_table); -- cgit v1.2.3 From e4ab1b3cbb8042f1653471c6333931134105d455 Mon Sep 17 00:00:00 2001 From: Mark McLoughlin Date: Tue, 4 Nov 2008 12:46:03 +0000 Subject: x86/docs: remove noirqbalance param docs Impact: documentation fix irqbalance was removed by: commit 8b8e8c1bf7275eca859fe551dfa484134eaf013b Author: Yinghai Lu Date: Tue Aug 19 20:50:23 2008 -0700 Remove the associated documentation for noirqbalance. Signed-off-by: Mark McLoughlin Signed-off-by: Ingo Molnar --- Documentation/kernel-parameters.txt | 2 -- 1 file changed, 2 deletions(-) diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 1bbcaa8982b..de4de3e7bc1 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1470,8 +1470,6 @@ and is between 256 and 4096 characters. It is defined in the file Valid arguments: on, off Default: on - noirqbalance [X86-32,SMP,KNL] Disable kernel irq balancing - noirqdebug [X86-32] Disables the code which attempts to detect and disable unhandled interrupt sources. -- cgit v1.2.3 From c78d0cf2925bffae8a6f00e7d9b8e971b0392edd Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Wed, 5 Nov 2008 12:04:46 +0000 Subject: x86: don't allow nr_irqs > NR_IRQS Impact: fix boot hang on 32-bit systems with more than 224 IO-APIC pins On some 32-bit systems with a lot of IO-APICs probe_nr_irqs() can return a value larger than NR_IRQS. This will lead to probe_irq_on() overrunning the irq_desc array. I hit this when running net-next-2.6 (close to 2.6.28-rc3) on a Supermicro dual Xeon system. NR_IRQS is 224 but probe_nr_irqs() detects 5 IOAPICs and returns 240. Here are the log messages: Tue Nov 4 16:53:47 2008 ACPI: IOAPIC (id[0x01] address[0xfec00000] gsi_base[0]) Tue Nov 4 16:53:47 2008 IOAPIC[0]: apic_id 1, version 32, address 0xfec00000, GSI 0-23 Tue Nov 4 16:53:47 2008 ACPI: IOAPIC (id[0x02] address[0xfec81000] gsi_base[24]) Tue Nov 4 16:53:47 2008 IOAPIC[1]: apic_id 2, version 32, address 0xfec81000, GSI 24-47 Tue Nov 4 16:53:47 2008 ACPI: IOAPIC (id[0x03] address[0xfec81400] gsi_base[48]) Tue Nov 4 16:53:47 2008 IOAPIC[2]: apic_id 3, version 32, address 0xfec81400, GSI 48-71 Tue Nov 4 16:53:47 2008 ACPI: IOAPIC (id[0x04] address[0xfec82000] gsi_base[72]) Tue Nov 4 16:53:47 2008 IOAPIC[3]: apic_id 4, version 32, address 0xfec82000, GSI 72-95 Tue Nov 4 16:53:47 2008 ACPI: IOAPIC (id[0x05] address[0xfec82400] gsi_base[96]) Tue Nov 4 16:53:47 2008 IOAPIC[4]: apic_id 5, version 32, address 0xfec82400, GSI 96-119 Tue Nov 4 16:53:47 2008 ACPI: INT_SRC_OVR (bus 0 bus_irq 0 global_irq 2 high edge) Tue Nov 4 16:53:47 2008 ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 9 high level) Tue Nov 4 16:53:47 2008 Enabling APIC mode: Flat. Using 5 I/O APICs Signed-off-by: Ben Hutchings Acked-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/io_apic.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c index b764d7429c6..7a3f2028e2e 100644 --- a/arch/x86/kernel/io_apic.c +++ b/arch/x86/kernel/io_apic.c @@ -3611,6 +3611,8 @@ int __init probe_nr_irqs(void) /* something wrong ? */ if (nr < nr_min) nr = nr_min; + if (WARN_ON(nr > NR_IRQS)) + nr = NR_IRQS; return nr; } -- cgit v1.2.3 From 1b4897688011cd05e07f00dcfe6af3331eb36a3c Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 4 Nov 2008 14:10:13 -0800 Subject: x86: size NR_IRQS on 32-bit systems the same way as 64-bit Impact: make NR_IRQS big enough for system with lots of apic/pins If lots of IO_APIC's are there (or can be there), size the same way as 64-bit, depending on MAX_IO_APICS and NR_CPUS. This fixes the boot problem reported by Ben Hutchings on a 32-bit server with 5 IO-APICs and 240 IO-APIC pins. Signed-off-by: Yinghai Tested-by: Ben Hutchings Signed-off-by: Ingo Molnar --- arch/x86/include/asm/irq_vectors.h | 20 ++++++-------------- 1 file changed, 6 insertions(+), 14 deletions(-) diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index d843ed0e9b2..503aadc4ad3 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -101,30 +101,22 @@ #define LAST_VM86_IRQ 15 #define invalid_vm86_irq(irq) ((irq) < 3 || (irq) > 15) -#ifdef CONFIG_X86_64 +#if defined(CONFIG_X86_IO_APIC) && !defined(CONFIG_PARAVIRT) && !defined(CONFIG_X86_VISWS) && !defined(CONFIG_X86_VOYAGER) # if NR_CPUS < MAX_IO_APICS # define NR_IRQS (NR_VECTORS + (32 * NR_CPUS)) # else # define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS)) # endif -#elif !defined(CONFIG_X86_VOYAGER) +#elif defined(CONFIG_PARAVIRT) || defined(CONFIG_X86_VISWS) || defined(CONFIG_X86_VOYAGER) -# if defined(CONFIG_X86_IO_APIC) || defined(CONFIG_PARAVIRT) || defined(CONFIG_X86_VISWS) - -# define NR_IRQS 224 - -# else /* IO_APIC || PARAVIRT */ - -# define NR_IRQS 16 - -# endif +# define NR_IRQS 224 -#else /* !VISWS && !VOYAGER */ +#else /* IO_APIC || PARAVIRT */ -# define NR_IRQS 224 +# define NR_IRQS 16 -#endif /* VISWS */ +#endif /* Voyager specific defines */ /* These define the CPIs we use in linux */ -- cgit v1.2.3 From da85f865b1dcec0853c48b763ed312441ce0c7df Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 5 Nov 2008 13:37:27 -0600 Subject: x86: mention ACPI in top-level Kconfig menu Impact: clarify menuconfig text Mention ACPI in the top-level menu to give a clue as to where it lives. This matches what ia64 does. Signed-off-by: Bjorn Helgaas Signed-off-by: Ingo Molnar --- arch/x86/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 6f20718d315..5d6aa4013dc 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1494,7 +1494,7 @@ config HAVE_ARCH_EARLY_PFN_TO_NID def_bool X86_64 depends on NUMA -menu "Power management options" +menu "Power management and ACPI options" depends on !X86_VOYAGER config ARCH_HIBERNATION_HEADER -- cgit v1.2.3 From 7db282fa67b58daff8a57f9e1c93d4474b5908ff Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 5 Nov 2008 23:36:48 -0800 Subject: x86: remove VISWS and PARAVIRT around NR_IRQS puzzle Impact: fix warning message when PARAVIRT is set in config Remove stale #ifdef components from our IRQ sizing logic. x86/Voyager is the only holdout. Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/include/asm/irq_vectors.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 503aadc4ad3..0005adb0f94 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -101,18 +101,18 @@ #define LAST_VM86_IRQ 15 #define invalid_vm86_irq(irq) ((irq) < 3 || (irq) > 15) -#if defined(CONFIG_X86_IO_APIC) && !defined(CONFIG_PARAVIRT) && !defined(CONFIG_X86_VISWS) && !defined(CONFIG_X86_VOYAGER) +#if defined(CONFIG_X86_IO_APIC) && !defined(CONFIG_X86_VOYAGER) # if NR_CPUS < MAX_IO_APICS # define NR_IRQS (NR_VECTORS + (32 * NR_CPUS)) # else # define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS)) # endif -#elif defined(CONFIG_PARAVIRT) || defined(CONFIG_X86_VISWS) || defined(CONFIG_X86_VOYAGER) +#elif defined(CONFIG_X86_VOYAGER) # define NR_IRQS 224 -#else /* IO_APIC || PARAVIRT */ +#else /* IO_APIC || VOYAGER */ # define NR_IRQS 16 -- cgit v1.2.3 From d6f0f39b7d05e62b347c4352d070e4afb3ade4b5 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Tue, 4 Nov 2008 13:53:04 -0800 Subject: x86: add smp_mb() before sending INVALIDATE_TLB_VECTOR Impact: fix rare x2apic hang On x86, x2apic mode accesses for sending IPI's don't have serializing semantics. If the IPI receivner refers(in lock-free fashion) to some memory setup by the sender, the need for smp_mb() before sending the IPI becomes critical in x2apic mode. Add the smp_mb() in native_flush_tlb_others() before sending the IPI. Signed-off-by: Suresh Siddha Signed-off-by: Ingo Molnar --- arch/x86/kernel/tlb_32.c | 6 ++++++ arch/x86/kernel/tlb_64.c | 5 +++++ 2 files changed, 11 insertions(+) diff --git a/arch/x86/kernel/tlb_32.c b/arch/x86/kernel/tlb_32.c index e00534b3353..f4049f3513b 100644 --- a/arch/x86/kernel/tlb_32.c +++ b/arch/x86/kernel/tlb_32.c @@ -154,6 +154,12 @@ void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm, flush_mm = mm; flush_va = va; cpus_or(flush_cpumask, cpumask, flush_cpumask); + + /* + * Make the above memory operations globally visible before + * sending the IPI. + */ + smp_mb(); /* * We have to send the IPI only to * CPUs affected. diff --git a/arch/x86/kernel/tlb_64.c b/arch/x86/kernel/tlb_64.c index dcbf7a1159e..8f919ca6949 100644 --- a/arch/x86/kernel/tlb_64.c +++ b/arch/x86/kernel/tlb_64.c @@ -182,6 +182,11 @@ void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm, f->flush_va = va; cpus_or(f->flush_cpumask, cpumask, f->flush_cpumask); + /* + * Make the above memory operations globally visible before + * sending the IPI. + */ + smp_mb(); /* * We have to send the IPI only to * CPUs affected. -- cgit v1.2.3 From 80be308dfa3798c7bad0fc81760b2faf83870e91 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 6 Nov 2008 14:59:05 +0100 Subject: AMD IOMMU: fix lazy IO/TLB flushing in unmap path Lazy flushing needs to take care of the unmap path too which is not yet implemented and leads to stale IO/TLB entries. This is fixed by this patch. Signed-off-by: Joerg Roedel --- arch/x86/kernel/amd_iommu.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index 38e88d40ab1..4755bbc7ae5 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -526,6 +526,9 @@ static void dma_ops_free_addresses(struct dma_ops_domain *dom, { address >>= PAGE_SHIFT; iommu_area_free(dom->bitmap, address, pages); + + if (address + pages >= dom->next_bit) + dom->need_flush = true; } /**************************************************************************** @@ -981,8 +984,10 @@ static void __unmap_single(struct amd_iommu *iommu, dma_ops_free_addresses(dma_dom, dma_addr, pages); - if (amd_iommu_unmap_flush) + if (amd_iommu_unmap_flush || dma_dom->need_flush) { iommu_flush_pages(iommu, dma_dom->domain.id, dma_addr, size); + dma_dom->need_flush = false; + } } /* -- cgit v1.2.3 From b9c3bfc24e1088d260de4091b2b41808c7398355 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 6 Nov 2008 12:05:40 +0000 Subject: x86: align DirectMap in /proc/meminfo Impact: right-align /proc/meminfo consistent with other fields When the split-LRU patches added Inactive(anon) and Inactive(file) lines to /proc/meminfo, all counts were moved two columns rightwards to fit in. Now move x86's DirectMap lines two columns rightwards to line up. Signed-off-by: Hugh Dickins Signed-off-by: Ingo Molnar --- arch/x86/mm/pageattr.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index f1dc1b75d16..e89d24815f2 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -67,18 +67,18 @@ static void split_page_count(int level) void arch_report_meminfo(struct seq_file *m) { - seq_printf(m, "DirectMap4k: %8lu kB\n", + seq_printf(m, "DirectMap4k: %8lu kB\n", direct_pages_count[PG_LEVEL_4K] << 2); #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) - seq_printf(m, "DirectMap2M: %8lu kB\n", + seq_printf(m, "DirectMap2M: %8lu kB\n", direct_pages_count[PG_LEVEL_2M] << 11); #else - seq_printf(m, "DirectMap4M: %8lu kB\n", + seq_printf(m, "DirectMap4M: %8lu kB\n", direct_pages_count[PG_LEVEL_2M] << 12); #endif #ifdef CONFIG_X86_64 if (direct_gbpages) - seq_printf(m, "DirectMap1G: %8lu kB\n", + seq_printf(m, "DirectMap1G: %8lu kB\n", direct_pages_count[PG_LEVEL_1G] << 20); #endif } -- cgit v1.2.3 From 8d00450d296dedec9ada38d43b83e79cca6fd5a3 Mon Sep 17 00:00:00 2001 From: Eduardo Habkost Date: Tue, 4 Nov 2008 12:52:44 -0200 Subject: Revert "x86: default to reboot via ACPI" This reverts commit c7ffa6c26277b403920e2255d10df849bd613380. the assumptio of this change was that this would not break any existing machine. Andrey Borzenkov reported troubles with the ACPI reboot method: the system would hang on reboot, necessiating a power cycle. Probably more systems are affected as well. Also, there are patches queued up for v2.6.29 to disable virtualization on emergency_restart() - which was the original motivation of this change. Reported-by: Andrey Borzenkov Bisected-by: Andrey Borzenkov Signed-off-by: Eduardo Habkost Acked-by: Avi Kivity Signed-off-by: Ingo Molnar --- arch/x86/kernel/reboot.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index f4c93f1cfc1..724adfc63cb 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -29,11 +29,7 @@ EXPORT_SYMBOL(pm_power_off); static const struct desc_ptr no_idt = {}; static int reboot_mode; -/* - * Keyboard reset and triple fault may result in INIT, not RESET, which - * doesn't work when we're in vmx root mode. Try ACPI first. - */ -enum reboot_type reboot_type = BOOT_ACPI; +enum reboot_type reboot_type = BOOT_KBD; int reboot_force; #if defined(CONFIG_X86_32) && defined(CONFIG_SMP) -- cgit v1.2.3