From 4720dd1b3858f0da2593188cb1e57eb0d3bc4af2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 9 Dec 2010 17:43:21 +0100 Subject: x86: io_apic: Avoid unused variable warning when CONFIG_GENERIC_PENDING_IRQ=n arch/x86/kernel/apic/io_apic.c: In function 'ack_apic_level': arch/x86/kernel/apic/io_apic.c:2433: warning: unused variable 'desc' Signed-off-by: Andrew Morton LKML-Reference: <201010272107.o9RL7rse018212@imap1.linux-foundation.org> Signed-off-by: Thomas Gleixner --- arch/x86/kernel/apic/io_apic.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 7cc0a721f62..226060eec34 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); } -- cgit v1.2.3-70-g09d2 From f1c18071ad70e2a78ab31fc26a18fcfa954a05c6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 13 Dec 2010 12:43:23 +0100 Subject: x86: HPET: Chose a paranoid safe value for the ETIME check commit 995bd3bb5 (x86: Hpet: Avoid the comparator readback penalty) chose 8 HPET cycles as a safe value for the ETIME check, as we had the confirmation that the posted write to the comparator register is delayed by two HPET clock cycles on Intel chipsets which showed readback problems. After that patch hit mainline we got reports from machines with newer AMD chipsets which seem to have an even longer delay. See http://thread.gmane.org/gmane.linux.kernel/1054283 and http://thread.gmane.org/gmane.linux.kernel/1069458 for further information. Boris tried to come up with an ACPI based selection of the minimum HPET cycles, but this failed on a couple of test machines. And of course we did not get any useful information from the hardware folks. For now our only option is to chose a paranoid high and safe value for the minimum HPET cycles used by the ETIME check. Adjust the minimum ns value for the HPET clockevent accordingly. Reported-Bistected-and-Tested-by: Markus Trippelsdorf Signed-off-by: Thomas Gleixner LKML-Reference: Cc: Simon Kirby Cc: Borislav Petkov Cc: Andreas Herrmann Cc: John Stultz --- arch/x86/kernel/hpet.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index ae03cab4352..4ff5968f12d 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, -- cgit v1.2.3-70-g09d2 From de2a8cf98ecdde25231d6c5e7901e2cffaf32af9 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Mon, 13 Dec 2010 16:01:38 -0800 Subject: x86, gcc-4.6: Use gcc -m options when building vdso The vdso Makefile passes linker-style -m options not to the linker but to gcc. This happens to work with earlier gcc, but fails with gcc 4.6. Pass gcc-style -m options, instead. Note: all currently supported versions of gcc supports -m32, so there is no reason to conditionalize it any more. Reported-by: H. J. Lu Signed-off-by: H. Peter Anvin LKML-Reference: Cc: --- arch/x86/vdso/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index 4a2afa1bac5..b6552b189bc 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. -- cgit v1.2.3-70-g09d2 From 10340ae130fb70352eae1ae8a00b7906d91bf166 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Tue, 16 Nov 2010 13:23:51 -0800 Subject: x86, xsave: Use alloc_bootmem_align() instead of alloc_bootmem() Alignment of alloc_bootmem() depends on the value of L1_CACHE_SHIFT. What we need here, however, is 64 byte alignment. Use alloc_bootmem_align() and explicitly specify the alignment instead. This fixes a kernel boot crash reported by Jody when the cpu in .config is set to MPENTIUMII but the kernel is booted on a xsave-capable CPU. Reported-by: Jody Bruchon Signed-off-by: Suresh Siddha LKML-Reference: <20101116212442.059967454@sbsiddha-MOBL3.sc.intel.com> Signed-off-by: H. Peter Anvin Cc: --- arch/x86/kernel/xsave.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 9c253bd65e2..547128546cc 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(); -- cgit v1.2.3-70-g09d2 From 086e8ced65d9bcc4a8e8f1cd39b09640f2883f90 Mon Sep 17 00:00:00 2001 From: Kenji Kaneshige Date: Wed, 1 Dec 2010 09:40:32 -0800 Subject: x86, vt-d: Fix the vt-d fault handling irq migration in the x2apic mode In x2apic mode, we need to set the upper address register of the fault handling interrupt register of the vt-d hardware. Without this irq migration of the vt-d fault handling interrupt is broken. Signed-off-by: Kenji Kaneshige LKML-Reference: <1291225233.2648.39.camel@sbsiddha-MOBL3> Signed-off-by: Suresh Siddha Cc: stable@kernel.org [v2.6.32+] Acked-by: Chris Wright Tested-by: Takao Indoh Signed-off-by: H. Peter Anvin --- arch/x86/kernel/apic/io_apic.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 226060eec34..fadcd743a74 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -3412,6 +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); -- cgit v1.2.3-70-g09d2 From 7f7fbf45c6b748074546f7f16b9488ca71de99c1 Mon Sep 17 00:00:00 2001 From: Kenji Kaneshige Date: Tue, 30 Nov 2010 22:22:28 -0800 Subject: x86: Enable the intr-remap fault handling after local APIC setup Interrupt-remapping gets enabled very early in the boot, as it determines the apic mode that the processor can use. And the current code enables the vt-d fault handling before the setup_local_APIC(). And hence the APIC LDR registers and data structure in the memory may not be initialized. So the vt-d fault handling in logical xapic/x2apic modes were broken. Fix this by enabling the vt-d fault handling in the end_local_APIC_setup() A cleaner fix of enabling fault handling while enabling intr-remapping will be addressed for v2.6.38. [ Enabling intr-remapping determines the usage of x2apic mode and the apic mode determines the fault-handling configuration. ] Signed-off-by: Kenji Kaneshige LKML-Reference: <20101201062244.541996375@intel.com> Signed-off-by: Suresh Siddha Cc: stable@kernel.org [v2.6.32+] Acked-by: Chris Wright Signed-off-by: H. Peter Anvin --- arch/x86/kernel/apic/apic.c | 8 ++++++++ arch/x86/kernel/apic/probe_64.c | 7 ------- 2 files changed, 8 insertions(+), 7 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 3f838d53739..78218135b48 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/probe_64.c b/arch/x86/kernel/apic/probe_64.c index f9e4e6a5407..d8c4a6feb28 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. */ -- cgit v1.2.3-70-g09d2 From 147dd5610c8d1bacb88a6c1dfdaceaf257946ed0 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Thu, 16 Dec 2010 19:11:09 -0800 Subject: x86-32: Make sure we can map all of lowmem if we need to A relocatable kernel can be anywhere in lowmem -- and in the case of a kdump kernel, is likely to be fairly high. Since the early page tables map everything from address zero up we need to make sure we allocate enough brk that we can map all of lowmem if we need to. Reported-by: Stanislaw Gruszka Signed-off-by: H. Peter Anvin Tested-by: Yinghai Lu LKML-Reference: <4D0AD3ED.8070607@kernel.org> --- arch/x86/boot/compressed/misc.c | 2 +- arch/x86/kernel/head_32.S | 12 +++++++----- 2 files changed, 8 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 23f315c9f21..325c05294fc 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/head_32.S b/arch/x86/kernel/head_32.S index bcece91dd31..d7cdf5bc1e6 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) -- cgit v1.2.3-70-g09d2