From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932315Ab0LSPa7 (ORCPT ); Sun, 19 Dec 2010 10:30:59 -0500 Received: from mx3.mail.elte.hu ([157.181.1.138]:40645 "EHLO mx3.mail.elte.hu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932256Ab0LSPa5 (ORCPT ); Sun, 19 Dec 2010 10:30:57 -0500 Date: Sun, 19 Dec 2010 16:30:48 +0100 From: Ingo Molnar To: Linus Torvalds Cc: linux-kernel@vger.kernel.org, Thomas Gleixner , "H. Peter Anvin" , Andrew Morton Subject: [GIT PULL] x86 fixes Message-ID: <20101219153048.GA20533@elte.hu> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.5.20 (2009-08-17) X-ELTE-SpamScore: -2.0 X-ELTE-SpamLevel: X-ELTE-SpamCheck: no X-ELTE-SpamVersion: ELTE 2.0 X-ELTE-SpamCheck-Details: score=-2.0 required=5.9 tests=BAYES_00 autolearn=no SpamAssassin version=3.2.5 -2.0 BAYES_00 BODY: Bayesian spam probability is 0 to 1% [score: 0.0000] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Linus, Please pull the latest x86-fixes-for-linus git tree from: git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git x86-fixes-for-linus out-of-topic modifications in x86-fixes-for-linus: -------------------------------------------------- drivers/pci/dmar.c # 7f99d94: x86, vt-d: Handle previous faults drivers/pci/quirks.c # 254e420: x86, vt-d: Quirk for masking vtd include/linux/bootmem.h # 53dde5f: bootmem: Add alloc_bootmem_align( Thanks, Ingo ------------------> H. Peter Anvin (2): x86, gcc-4.6: Use gcc -m options when building vdso x86-32: Make sure we can map all of lowmem if we need to Kenji Kaneshige (2): x86, vt-d: Fix the vt-d fault handling irq migration in the x2apic mode x86: Enable the intr-remap fault handling after local APIC setup Suresh Siddha (4): bootmem: Add alloc_bootmem_align() x86, xsave: Use alloc_bootmem_align() instead of alloc_bootmem() x86, vt-d: Quirk for masking vtd spec errors to platform error handling logic x86, vt-d: Handle previous faults after enabling fault handling Thomas Gleixner (2): x86: io_apic: Avoid unused variable warning when CONFIG_GENERIC_PENDING_IRQ=n x86: HPET: Chose a paranoid safe value for the ETIME check arch/x86/boot/compressed/misc.c | 2 +- arch/x86/kernel/apic/apic.c | 8 ++++++++ arch/x86/kernel/apic/io_apic.c | 4 ++-- arch/x86/kernel/apic/probe_64.c | 7 ------- arch/x86/kernel/head_32.S | 12 +++++++----- arch/x86/kernel/hpet.c | 26 ++++++++++++++++---------- arch/x86/kernel/xsave.c | 3 ++- arch/x86/vdso/Makefile | 4 ++-- drivers/pci/dmar.c | 5 +++++ drivers/pci/quirks.c | 23 +++++++++++++++++++++++ include/linux/bootmem.h | 2 ++ 11 files changed, 68 insertions(+), 28 deletions(-) diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 23f315c..325c052 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -355,7 +355,7 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, if (heap > 0x3fffffffffffUL) error("Destination address too large"); #else - if (heap > ((-__PAGE_OFFSET-(512<<20)-1) & 0x7fffffff)) + if (heap > ((-__PAGE_OFFSET-(128<<20)-1) & 0x7fffffff)) error("Destination address too large"); #endif #ifndef CONFIG_RELOCATABLE diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 3f838d5..7821813 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1389,6 +1389,14 @@ void __cpuinit end_local_APIC_setup(void) setup_apic_nmi_watchdog(NULL); apic_pm_activate(); + + /* + * Now that local APIC setup is completed for BP, configure the fault + * handling for interrupt remapping. + */ + if (!smp_processor_id() && intr_remapping_enabled) + enable_drhd_fault_handling(); + } #ifdef CONFIG_X86_X2APIC diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 7cc0a72..fadcd74 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2430,13 +2430,12 @@ static void ack_apic_level(struct irq_data *data) { struct irq_cfg *cfg = data->chip_data; int i, do_unmask_irq = 0, irq = data->irq; - struct irq_desc *desc = irq_to_desc(irq); unsigned long v; irq_complete_move(cfg); #ifdef CONFIG_GENERIC_PENDING_IRQ /* If we are moving the irq we need to mask it */ - if (unlikely(desc->status & IRQ_MOVE_PENDING)) { + if (unlikely(irq_to_desc(irq)->status & IRQ_MOVE_PENDING)) { do_unmask_irq = 1; mask_ioapic(cfg); } @@ -3413,6 +3412,7 @@ dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, msg.data |= MSI_DATA_VECTOR(cfg->vector); msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; msg.address_lo |= MSI_ADDR_DEST_ID(dest); + msg.address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(dest); dmar_msi_write(irq, &msg); diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c index f9e4e6a..d8c4a6f 100644 --- a/arch/x86/kernel/apic/probe_64.c +++ b/arch/x86/kernel/apic/probe_64.c @@ -79,13 +79,6 @@ void __init default_setup_apic_routing(void) /* need to update phys_pkg_id */ apic->phys_pkg_id = apicid_phys_pkg_id; } - - /* - * Now that apic routing model is selected, configure the - * fault handling for intr remapping. - */ - if (intr_remapping_enabled) - enable_drhd_fault_handling(); } /* Same for both flat and physical. */ diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index bcece91..d7cdf5b 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -60,16 +60,18 @@ #define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD) #endif +/* Number of possible pages in the lowmem region */ +LOWMEM_PAGES = (((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT) + /* Enough space to fit pagetables for the low memory linear map */ -MAPPING_BEYOND_END = \ - PAGE_TABLE_SIZE(((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT) << PAGE_SHIFT +MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT /* * Worst-case size of the kernel mapping we need to make: - * the worst-case size of the kernel itself, plus the extra we need - * to map for the linear map. + * a relocatable kernel can live anywhere in lowmem, so we need to be able + * to map all of lowmem. */ -KERNEL_PAGES = (KERNEL_IMAGE_SIZE + MAPPING_BEYOND_END)>>PAGE_SHIFT +KERNEL_PAGES = LOWMEM_PAGES INIT_MAP_SIZE = PAGE_TABLE_SIZE(KERNEL_PAGES) * PAGE_SIZE_asm RESERVE_BRK(pagetables, INIT_MAP_SIZE) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index ae03cab..4ff5968 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -27,6 +27,9 @@ #define HPET_DEV_FSB_CAP 0x1000 #define HPET_DEV_PERI_CAP 0x2000 +#define HPET_MIN_CYCLES 128 +#define HPET_MIN_PROG_DELTA (HPET_MIN_CYCLES + (HPET_MIN_CYCLES >> 1)) + #define EVT_TO_HPET_DEV(evt) container_of(evt, struct hpet_dev, evt) /* @@ -299,8 +302,9 @@ static void hpet_legacy_clockevent_register(void) /* Calculate the min / max delta */ hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF, &hpet_clockevent); - /* 5 usec minimum reprogramming delta. */ - hpet_clockevent.min_delta_ns = 5000; + /* Setup minimum reprogramming delta. */ + hpet_clockevent.min_delta_ns = clockevent_delta2ns(HPET_MIN_PROG_DELTA, + &hpet_clockevent); /* * Start hpet with the boot cpu mask and make it @@ -393,22 +397,24 @@ static int hpet_next_event(unsigned long delta, * the wraparound into account) nor a simple count down event * mode. Further the write to the comparator register is * delayed internally up to two HPET clock cycles in certain - * chipsets (ATI, ICH9,10). We worked around that by reading - * back the compare register, but that required another - * workaround for ICH9,10 chips where the first readout after - * write can return the old stale value. We already have a - * minimum delta of 5us enforced, but a NMI or SMI hitting + * chipsets (ATI, ICH9,10). Some newer AMD chipsets have even + * longer delays. We worked around that by reading back the + * compare register, but that required another workaround for + * ICH9,10 chips where the first readout after write can + * return the old stale value. We already had a minimum + * programming delta of 5us enforced, but a NMI or SMI hitting * between the counter readout and the comparator write can * move us behind that point easily. Now instead of reading * the compare register back several times, we make the ETIME * decision based on the following: Return ETIME if the - * counter value after the write is less than 8 HPET cycles + * counter value after the write is less than HPET_MIN_CYCLES * away from the event or if the counter is already ahead of - * the event. + * the event. The minimum programming delta for the generic + * clockevents code is set to 1.5 * HPET_MIN_CYCLES. */ res = (s32)(cnt - hpet_readl(HPET_COUNTER)); - return res < 8 ? -ETIME : 0; + return res < HPET_MIN_CYCLES ? -ETIME : 0; } static void hpet_legacy_set_mode(enum clock_event_mode mode, diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 9c253bd..5471285 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -394,7 +394,8 @@ static void __init setup_xstate_init(void) * Setup init_xstate_buf to represent the init state of * all the features managed by the xsave */ - init_xstate_buf = alloc_bootmem(xstate_size); + init_xstate_buf = alloc_bootmem_align(xstate_size, + __alignof__(struct xsave_struct)); init_xstate_buf->i387.mxcsr = MXCSR_DEFAULT; clts(); diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index 4a2afa1..b6552b1 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -25,7 +25,7 @@ targets += vdso.so vdso.so.dbg vdso.lds $(vobjs-y) export CPPFLAGS_vdso.lds += -P -C -VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -Wl,-soname=linux-vdso.so.1 \ +VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \ -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 $(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so @@ -69,7 +69,7 @@ vdso32.so-$(VDSO32-y) += sysenter vdso32-images = $(vdso32.so-y:%=vdso32-%.so) CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds) -VDSO_LDFLAGS_vdso32.lds = -m elf_i386 -Wl,-soname=linux-gate.so.1 +VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-soname=linux-gate.so.1 # This makes sure the $(obj) subdirectory exists even though vdso32/ # is not a kbuild sub-make subdirectory. diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c index 0157708..09933eb 100644 --- a/drivers/pci/dmar.c +++ b/drivers/pci/dmar.c @@ -1417,6 +1417,11 @@ int __init enable_drhd_fault_handling(void) (unsigned long long)drhd->reg_base_addr, ret); return -1; } + + /* + * Clear any previous faults. + */ + dmar_fault(iommu->irq, iommu); } return 0; diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 6f9350c..36191ed 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -2764,6 +2764,29 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5C832, ricoh_m DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5C832, ricoh_mmc_fixup_r5c832); #endif /*CONFIG_MMC_RICOH_MMC*/ +#if defined(CONFIG_DMAR) || defined(CONFIG_INTR_REMAP) +#define VTUNCERRMSK_REG 0x1ac +#define VTD_MSK_SPEC_ERRORS (1 << 31) +/* + * This is a quirk for masking vt-d spec defined errors to platform error + * handling logic. With out this, platforms using Intel 7500, 5500 chipsets + * (and the derivative chipsets like X58 etc) seem to generate NMI/SMI (based + * on the RAS config settings of the platform) when a vt-d fault happens. + * The resulting SMI caused the system to hang. + * + * VT-d spec related errors are already handled by the VT-d OS code, so no + * need to report the same error through other channels. + */ +static void vtd_mask_spec_errors(struct pci_dev *dev) +{ + u32 word; + + pci_read_config_dword(dev, VTUNCERRMSK_REG, &word); + pci_write_config_dword(dev, VTUNCERRMSK_REG, word | VTD_MSK_SPEC_ERRORS); +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x342e, vtd_mask_spec_errors); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x3c28, vtd_mask_spec_errors); +#endif static void pci_do_fixups(struct pci_dev *dev, struct pci_fixup *f, struct pci_fixup *end) diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 266ab92..499dfe9 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -105,6 +105,8 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, #define alloc_bootmem(x) \ __alloc_bootmem(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) +#define alloc_bootmem_align(x, align) \ + __alloc_bootmem(x, align, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_nopanic(x) \ __alloc_bootmem_nopanic(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_pages(x) \