From c513867561eeb07d24a0bdda1a18a8f91921a301 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 14 Oct 2008 18:08:48 -0400 Subject: ftrace: do not enclose logic in WARN_ON In ftrace, logic is defined in the WARN_ON_ONCE, which can become a nop with some configs. This patch fixes it. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- arch/x86/kernel/ftrace.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index d073d981a73..8821ceabf51 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -62,6 +62,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, unsigned char *new_code) { unsigned char replaced[MCOUNT_INSN_SIZE]; + int ret; /* * Note: Due to modules and __init, code can @@ -77,8 +78,9 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0) return 2; - WARN_ON_ONCE(__copy_to_user_inatomic((char __user *)ip, new_code, - MCOUNT_INSN_SIZE)); + ret = __copy_to_user_inatomic((char __user *)ip, new_code, + MCOUNT_INSN_SIZE); + WARN_ON_ONCE(ret); sync_core(); -- cgit v1.2.3-18-g5258 From 606576ce816603d9fe1fb453a88bc6eea16ca709 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 6 Oct 2008 19:06:12 -0400 Subject: ftrace: rename FTRACE to FUNCTION_TRACER Due to confusion between the ftrace infrastructure and the gcc profiling tracer "ftrace", this patch renames the config options from FTRACE to FUNCTION_TRACER. The other two names that are offspring from FTRACE DYNAMIC_FTRACE and FTRACE_MCOUNT_RECORD will stay the same. This patch was generated mostly by script, and partially by hand. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- arch/x86/Kconfig | 2 +- arch/x86/kernel/Makefile | 2 +- arch/x86/kernel/entry_32.S | 4 ++-- arch/x86/kernel/entry_64.S | 4 ++-- arch/x86/kernel/i386_ksyms_32.c | 2 +- arch/x86/kernel/x8664_ksyms_64.c | 2 +- arch/x86/xen/Makefile | 2 +- 7 files changed, 9 insertions(+), 9 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 40ee8080956..290e21aa774 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -28,7 +28,7 @@ config X86 select HAVE_KRETPROBES select HAVE_FTRACE_MCOUNT_RECORD select HAVE_DYNAMIC_FTRACE - select HAVE_FTRACE + select HAVE_FUNCTION_TRACER select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64) select HAVE_ARCH_KGDB if !X86_VOYAGER select HAVE_ARCH_TRACEHOOK diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 0d41f0343dc..ec3d30136bf 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -6,7 +6,7 @@ extra-y := head_$(BITS).o head$(BITS).o head.o init_task.o vmlinu CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE) -ifdef CONFIG_FTRACE +ifdef CONFIG_FUNCTION_TRACER # Do not profile debug and lowlevel utilities CFLAGS_REMOVE_tsc.o = -pg CFLAGS_REMOVE_rtc.o = -pg diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 4e4269c73bb..9d49facc21f 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -1149,7 +1149,7 @@ ENDPROC(xen_failsafe_callback) #endif /* CONFIG_XEN */ -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER #ifdef CONFIG_DYNAMIC_FTRACE ENTRY(mcount) @@ -1204,7 +1204,7 @@ trace: jmp ftrace_stub END(mcount) #endif /* CONFIG_DYNAMIC_FTRACE */ -#endif /* CONFIG_FTRACE */ +#endif /* CONFIG_FUNCTION_TRACER */ .section .rodata,"a" #include "syscall_table_32.S" diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 09e7145484c..b86f332c96a 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -61,7 +61,7 @@ .code64 -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER #ifdef CONFIG_DYNAMIC_FTRACE ENTRY(mcount) retq @@ -138,7 +138,7 @@ trace: jmp ftrace_stub END(mcount) #endif /* CONFIG_DYNAMIC_FTRACE */ -#endif /* CONFIG_FTRACE */ +#endif /* CONFIG_FUNCTION_TRACER */ #ifndef CONFIG_PREEMPT #define retint_kernel retint_restore_args diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c index dd7ebee446a..43cec6bdda6 100644 --- a/arch/x86/kernel/i386_ksyms_32.c +++ b/arch/x86/kernel/i386_ksyms_32.c @@ -5,7 +5,7 @@ #include #include -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER /* mcount is defined in assembly */ EXPORT_SYMBOL(mcount); #endif diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index b545f371b5f..695e426aa35 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -12,7 +12,7 @@ #include #include -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER /* mcount is defined in assembly */ EXPORT_SYMBOL(mcount); #endif diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 313947940a1..6dcefba7836 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -1,4 +1,4 @@ -ifdef CONFIG_FTRACE +ifdef CONFIG_FUNCTION_TRACER # Do not profile debug and lowlevel utilities CFLAGS_REMOVE_spinlock.o = -pg CFLAGS_REMOVE_time.o = -pg -- cgit v1.2.3-18-g5258 From 593eb8a2d63e95772a5f22d746f18a997c5ee463 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 23 Oct 2008 09:32:59 -0400 Subject: ftrace: return error on failed modified text. Have the ftrace_modify_code return error values: -EFAULT on error of reading the address -EINVAL if what is read does not match what it expected -EPERM if the write fails to update after a successful match. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- arch/x86/kernel/ftrace.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 8821ceabf51..428291581cb 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -62,7 +62,6 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, unsigned char *new_code) { unsigned char replaced[MCOUNT_INSN_SIZE]; - int ret; /* * Note: Due to modules and __init, code can @@ -72,15 +71,16 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, * No real locking needed, this code is run through * kstop_machine, or before SMP starts. */ - if (__copy_from_user_inatomic(replaced, (char __user *)ip, MCOUNT_INSN_SIZE)) - return 1; + if (__copy_from_user_inatomic(replaced, (char __user *)ip, + MCOUNT_INSN_SIZE)) + return -EFAULT; if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0) - return 2; + return -EINVAL; - ret = __copy_to_user_inatomic((char __user *)ip, new_code, - MCOUNT_INSN_SIZE); - WARN_ON_ONCE(ret); + if (__copy_to_user_inatomic((char __user *)ip, new_code, + MCOUNT_INSN_SIZE)) + return -EPERM; sync_core(); -- cgit v1.2.3-18-g5258 From 76aefee57657428fb77cbd8624119c1a440bee44 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 23 Oct 2008 09:33:00 -0400 Subject: ftrace: comment arch ftrace code Add comments to explain what is happening in the x86 arch ftrace code. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- arch/x86/kernel/ftrace.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 428291581cb..783455454d7 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -66,18 +66,23 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, /* * Note: Due to modules and __init, code can * disappear and change, we need to protect against faulting - * as well as code changing. + * as well as code changing. We do this by using the + * __copy_*_user functions. * * No real locking needed, this code is run through * kstop_machine, or before SMP starts. */ + + /* read the text we want to modify */ if (__copy_from_user_inatomic(replaced, (char __user *)ip, MCOUNT_INSN_SIZE)) return -EFAULT; + /* Make sure it is what we expect it to be */ if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0) return -EINVAL; + /* replace the text with the new text */ if (__copy_to_user_inatomic((char __user *)ip, new_code, MCOUNT_INSN_SIZE)) return -EPERM; -- cgit v1.2.3-18-g5258 From ab9a0918cbf0fa8883301838df8dbc8fc085ff50 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 23 Oct 2008 09:33:01 -0400 Subject: ftrace: use probe_kernel Andrew Morton suggested using the proper API for reading and writing kernel areas that might fault. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- arch/x86/kernel/ftrace.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 783455454d7..da4fb0deecf 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -67,15 +67,14 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, * Note: Due to modules and __init, code can * disappear and change, we need to protect against faulting * as well as code changing. We do this by using the - * __copy_*_user functions. + * probe_kernel_* functions. * * No real locking needed, this code is run through * kstop_machine, or before SMP starts. */ /* read the text we want to modify */ - if (__copy_from_user_inatomic(replaced, (char __user *)ip, - MCOUNT_INSN_SIZE)) + if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) return -EFAULT; /* Make sure it is what we expect it to be */ @@ -83,8 +82,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, return -EINVAL; /* replace the text with the new text */ - if (__copy_to_user_inatomic((char __user *)ip, new_code, - MCOUNT_INSN_SIZE)) + if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE)) return -EPERM; sync_core(); -- cgit v1.2.3-18-g5258 From 4d296c24326783bff1282ac72f310d8bac8df413 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 23 Oct 2008 09:33:06 -0400 Subject: ftrace: remove mcount set The arch dependent function ftrace_mcount_set was only used by the daemon start up code. This patch removes it. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- arch/x86/kernel/ftrace.c | 7 ------- 1 file changed, 7 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index da4fb0deecf..b399eed2353 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -103,13 +103,6 @@ notrace int ftrace_update_ftrace_func(ftrace_func_t func) return ret; } -notrace int ftrace_mcount_set(unsigned long *data) -{ - /* mcount is initialized as a nop */ - *data = 0; - return 0; -} - int __init ftrace_dyn_arch_init(void *data) { extern const unsigned char ftrace_test_p6nop[]; -- cgit v1.2.3-18-g5258 From 15adc048986f6b54b6044f2b6fc4b48f49413e2f Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 23 Oct 2008 09:33:08 -0400 Subject: ftrace, powerpc, sparc64, x86: remove notrace from arch ftrace file The entire file of ftrace.c in the arch code needs to be marked as notrace. It is much cleaner to do this from the Makefile with CFLAGS_REMOVE_ftrace.o. [ powerpc already had this in its Makefile. ] Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- arch/x86/kernel/Makefile | 1 + arch/x86/kernel/ftrace.c | 10 +++++----- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index f1283fe6072..e489ff9cb3e 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -11,6 +11,7 @@ ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_tsc.o = -pg CFLAGS_REMOVE_rtc.o = -pg CFLAGS_REMOVE_paravirt-spinlocks.o = -pg +CFLAGS_REMOVE_ftrace.o = -pg endif # diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index b399eed2353..b1e5e2244ec 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -33,17 +33,17 @@ union ftrace_code_union { }; -static int notrace ftrace_calc_offset(long ip, long addr) +static int ftrace_calc_offset(long ip, long addr) { return (int)(addr - ip); } -notrace unsigned char *ftrace_nop_replace(void) +unsigned char *ftrace_nop_replace(void) { return (char *)ftrace_nop; } -notrace unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) +unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) { static union ftrace_code_union calc; @@ -57,7 +57,7 @@ notrace unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) return calc.code; } -notrace int +int ftrace_modify_code(unsigned long ip, unsigned char *old_code, unsigned char *new_code) { @@ -90,7 +90,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, return 0; } -notrace int ftrace_update_ftrace_func(ftrace_func_t func) +int ftrace_update_ftrace_func(ftrace_func_t func) { unsigned long ip = (unsigned long)(&ftrace_call); unsigned char old[MCOUNT_INSN_SIZE], *new; -- cgit v1.2.3-18-g5258 From 75bebb7f0c2a709812cccb4d3151a21b012c5cad Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Thu, 23 Oct 2008 20:46:55 +0900 Subject: x86: use GFP_DMA for 24bit coherent_dma_mask dma_alloc_coherent (include/asm-x86/dma-mapping.h) avoids GFP_DMA allocation first and if the allocated address is not fit for the device's coherent_dma_mask, then dma_alloc_coherent does GFP_DMA allocation. This is because dma_alloc_coherent avoids precious GFP_DMA zone if possible. This is also how the old dma_alloc_coherent (arch/x86/kernel/pci-dma.c) works. However, if the coherent_dma_mask of a device is 24bit, there is no point to go into the above GFP_DMA retry mechanism. We had better use GFP_DMA in the first place. Signed-off-by: FUJITA Tomonori Tested-by: Takashi Iwai Signed-off-by: Ingo Molnar --- arch/x86/include/asm/dma-mapping.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 4a5397bfce2..7f225a4b2a2 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -255,9 +255,11 @@ static inline unsigned long dma_alloc_coherent_mask(struct device *dev, static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp) { -#ifdef CONFIG_X86_64 unsigned long dma_mask = dma_alloc_coherent_mask(dev, gfp); + if (dma_mask <= DMA_24BIT_MASK) + gfp |= GFP_DMA; +#ifdef CONFIG_X86_64 if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA)) gfp |= GFP_DMA32; #endif -- cgit v1.2.3-18-g5258 From 03967c5267b0e7312d1d55dc814d94cf190ca573 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Thu, 23 Oct 2008 23:14:29 +0900 Subject: x86: restore the old swiotlb alloc_coherent behavior This restores the old swiotlb alloc_coherent behavior (before the alloc_coherent rewrite): http://lkml.org/lkml/2008/8/12/200 The old alloc_coherent avoids GFP_DMA allocation first and if the allocated address is not fit for the device's coherent_dma_mask, then dma_alloc_coherent does GFP_DMA allocation. If it fails, alloc_coherent calls swiotlb_alloc_coherent (in short, we rarely used swiotlb_alloc_coherent). After the alloc_coherent rewrite, dma_alloc_coherent (include/asm-x86/dma-mapping.h) directly calls swiotlb_alloc_coherent. It means that we possibly can't handle a device having dma_masks > 24bit < 32bits since swiotlb_alloc_coherent doesn't have the above GFP_DMA retry mechanism. This patch fixes x86's swiotlb alloc_coherent to use the GFP_DMA retry mechanism, which dma_generic_alloc_coherent() provides now (pci-nommu.c and GART IOMMU driver also use dma_generic_alloc_coherent). Signed-off-by: FUJITA Tomonori Signed-off-by: Ingo Molnar --- arch/x86/kernel/pci-swiotlb_64.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb_64.c index c4ce0332759..3c539d111ab 100644 --- a/arch/x86/kernel/pci-swiotlb_64.c +++ b/arch/x86/kernel/pci-swiotlb_64.c @@ -18,9 +18,21 @@ swiotlb_map_single_phys(struct device *hwdev, phys_addr_t paddr, size_t size, return swiotlb_map_single(hwdev, phys_to_virt(paddr), size, direction); } +static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, + dma_addr_t *dma_handle, gfp_t flags) +{ + void *vaddr; + + vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags); + if (vaddr) + return vaddr; + + return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags); +} + struct dma_mapping_ops swiotlb_dma_ops = { .mapping_error = swiotlb_dma_mapping_error, - .alloc_coherent = swiotlb_alloc_coherent, + .alloc_coherent = x86_swiotlb_alloc_coherent, .free_coherent = swiotlb_free_coherent, .map_single = swiotlb_map_single_phys, .unmap_single = swiotlb_unmap_single, -- cgit v1.2.3-18-g5258 From 3b15e581981b3ad35809f56d8131d5c19b6da1bd Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Thu, 23 Oct 2008 16:51:00 -0700 Subject: x86/PCI: build failure at x86/kernel/pci-dma.c with !CONFIG_PCI On Thu, Oct 23, 2008 at 04:09:52PM -0700, Alexander Beregalov wrote: > arch/x86/kernel/built-in.o: In function `iommu_setup': > pci-dma.c:(.init.text+0x36ad): undefined reference to `forbid_dac' > pci-dma.c:(.init.text+0x36cc): undefined reference to `forbid_dac' > pci-dma.c:(.init.text+0x3711): undefined reference to `forbid_dac This patch partially reverts a patch to add IOMMU support to ia64. The forbid_dac variable was incorrectly moved to quirks.c, which isn't built when PCI is disabled. Tested-by: "Alexander Beregalov" Acked-by: FUJITA Tomonori Signed-off-by: Fenghua Yu Signed-off-by: Jesse Barnes --- arch/x86/include/asm/iommu.h | 1 - arch/x86/kernel/pci-dma.c | 16 ++++++++++++++++ 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h index 98e28ea8cd1..e4a552d4446 100644 --- a/arch/x86/include/asm/iommu.h +++ b/arch/x86/include/asm/iommu.h @@ -7,7 +7,6 @@ extern struct dma_mapping_ops nommu_dma_ops; extern int force_iommu, no_iommu; extern int iommu_detected; extern int dmar_disabled; -extern int forbid_dac; extern unsigned long iommu_nr_pages(unsigned long addr, unsigned long len); diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 1972266e8ba..19262482021 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -9,6 +9,8 @@ #include #include +static int forbid_dac __read_mostly; + struct dma_mapping_ops *dma_ops; EXPORT_SYMBOL(dma_ops); @@ -291,3 +293,17 @@ void pci_iommu_shutdown(void) } /* Must execute after PCI subsystem */ fs_initcall(pci_iommu_init); + +#ifdef CONFIG_PCI +/* Many VIA bridges seem to corrupt data for DAC. Disable it here */ + +static __devinit void via_no_dac(struct pci_dev *dev) +{ + if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && forbid_dac == 0) { + printk(KERN_INFO "PCI: VIA PCI bridge detected." + "Disabling DAC.\n"); + forbid_dac = 1; + } +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID, via_no_dac); +#endif -- cgit v1.2.3-18-g5258 From 9f32d21c981bb638d0991ce5675a20337312066b Mon Sep 17 00:00:00 2001 From: Chris Lalancette Date: Thu, 23 Oct 2008 17:40:25 -0700 Subject: xen: fix Xen domU boot with batched mprotect Impact: fix guest kernel boot crash on certain configs Recent i686 2.6.27 kernels with a certain amount of memory (between 736 and 855MB) have a problem booting under a hypervisor that supports batched mprotect (this includes the RHEL-5 Xen hypervisor as well as any 3.3 or later Xen hypervisor). The problem ends up being that xen_ptep_modify_prot_commit() is using virt_to_machine to calculate which pfn to update. However, this only works for pages that are in the p2m list, and the pages coming from change_pte_range() in mm/mprotect.c are kmap_atomic pages. Because of this, we can run into the situation where the lookup in the p2m table returns an INVALID_MFN, which we then try to pass to the hypervisor, which then (correctly) denies the request to a totally bogus pfn. The right thing to do is to use arbitrary_virt_to_machine, so that we can be sure we are modifying the right pfn. This unfortunately introduces a performance penalty because of a full page-table-walk, but we can avoid that penalty for pages in the p2m list by checking if virt_addr_valid is true, and if so, just doing the lookup in the p2m table. The attached patch implements this, and allows my 2.6.27 i686 based guest with 768MB of memory to boot on a RHEL-5 hypervisor again. Thanks to Jeremy for the suggestions about how to fix this particular issue. Signed-off-by: Chris Lalancette Signed-off-by: Jeremy Fitzhardinge Cc: Chris Lalancette Signed-off-by: Ingo Molnar --- arch/x86/xen/mmu.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index d4d52f5a1cf..aba77b2b7d1 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -246,11 +246,21 @@ xmaddr_t arbitrary_virt_to_machine(void *vaddr) { unsigned long address = (unsigned long)vaddr; unsigned int level; - pte_t *pte = lookup_address(address, &level); - unsigned offset = address & ~PAGE_MASK; + pte_t *pte; + unsigned offset; - BUG_ON(pte == NULL); + /* + * if the PFN is in the linear mapped vaddr range, we can just use + * the (quick) virt_to_machine() p2m lookup + */ + if (virt_addr_valid(vaddr)) + return virt_to_machine(vaddr); + /* otherwise we have to do a (slower) full page-table walk */ + + pte = lookup_address(address, &level); + BUG_ON(pte == NULL); + offset = address & ~PAGE_MASK; return XMADDR(((phys_addr_t)pte_mfn(*pte) << PAGE_SHIFT) + offset); } @@ -410,7 +420,7 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, xen_mc_batch(); - u.ptr = virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD; + u.ptr = arbitrary_virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD; u.val = pte_val_ma(pte); xen_extend_mmu_update(&u); -- cgit v1.2.3-18-g5258 From ef020ab0109aa5cd6eac2e93519b7641c9862828 Mon Sep 17 00:00:00 2001 From: Cliff Wickman Date: Thu, 23 Oct 2008 17:54:05 -0500 Subject: x86/uv: memory allocation at initialization Impact: on SGI UV platforms, fix boot crash UV initialization is currently called too late to call alloc_bootmem_pages(). The current sequence is: start_kernel() mem_init() free_all_bootmem() <--- discard of bootmem rest_init() kernel_init() smp_prepare_cpus() native_smp_prepare_cpus() uv_system_init() <--- uses alloc_bootmem_pages() It should be calling kmalloc(). Signed-off-by: Cliff Wickman Signed-off-by: Ingo Molnar --- arch/x86/kernel/genx2apic_uv_x.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c index 680a06557c5..2c7dbdb9827 100644 --- a/arch/x86/kernel/genx2apic_uv_x.c +++ b/arch/x86/kernel/genx2apic_uv_x.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include @@ -398,16 +397,16 @@ void __init uv_system_init(void) printk(KERN_DEBUG "UV: Found %d blades\n", uv_num_possible_blades()); bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades(); - uv_blade_info = alloc_bootmem_pages(bytes); + uv_blade_info = kmalloc(bytes, GFP_KERNEL); get_lowmem_redirect(&lowmem_redir_base, &lowmem_redir_size); bytes = sizeof(uv_node_to_blade[0]) * num_possible_nodes(); - uv_node_to_blade = alloc_bootmem_pages(bytes); + uv_node_to_blade = kmalloc(bytes, GFP_KERNEL); memset(uv_node_to_blade, 255, bytes); bytes = sizeof(uv_cpu_to_blade[0]) * num_possible_cpus(); - uv_cpu_to_blade = alloc_bootmem_pages(bytes); + uv_cpu_to_blade = kmalloc(bytes, GFP_KERNEL); memset(uv_cpu_to_blade, 255, bytes); blade = 0; -- cgit v1.2.3-18-g5258 From 8115f3f0c939c5db0fe3c6c6c58911fd3a205b1e Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 24 Oct 2008 09:12:17 -0400 Subject: ftrace: use a real variable for ftrace_nop in x86 Impact: avoid section mismatch warning, clean up The dynamic ftrace determines which nop is safe to use at start up. When it finds a safe nop for patching, it sets a pointer called ftrace_nop to point to the code. All call sites are then patched to this nop. Later, when tracing is turned on, this ftrace_nop variable is again used to compare the location to make sure it is a nop before we update it to an mcount call. If this fails just once, a warning is printed and ftrace is disabled. Rakib Mullick noted that the code that sets up the nop is a .init section where as the nop itself is in the .text section. This is needed because the nop is used later on after boot up. The problem is that the test of the nop jumps back to the setup code and causes a "section mismatch" warning. Rakib first recommended to convert the nop to .init.text, but as stated above, this would fail since that text is used later. The real solution is to extend Rabik's patch, and to make the ftrace_nop into an array, and just save the code from the assembly to this array. Now the section can stay as an init section, and we have a nop to use later on. Reported-by: Rakib Mullick Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- arch/x86/kernel/ftrace.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index b1e5e2244ec..50ea0ac8c9b 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -21,8 +21,7 @@ #include -/* Long is fine, even if it is only 4 bytes ;-) */ -static unsigned long *ftrace_nop; +static unsigned char ftrace_nop[MCOUNT_INSN_SIZE]; union ftrace_code_union { char code[MCOUNT_INSN_SIZE]; @@ -40,7 +39,7 @@ static int ftrace_calc_offset(long ip, long addr) unsigned char *ftrace_nop_replace(void) { - return (char *)ftrace_nop; + return ftrace_nop; } unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) @@ -125,9 +124,6 @@ int __init ftrace_dyn_arch_init(void *data) * TODO: check the cpuid to determine the best nop. */ asm volatile ( - "jmp ftrace_test_jmp\n" - /* This code needs to stay around */ - ".section .text, \"ax\"\n" "ftrace_test_jmp:" "jmp ftrace_test_p6nop\n" "nop\n" @@ -138,8 +134,6 @@ int __init ftrace_dyn_arch_init(void *data) "jmp 1f\n" "ftrace_test_nop5:" ".byte 0x66,0x66,0x66,0x66,0x90\n" - "jmp 1f\n" - ".previous\n" "1:" ".section .fixup, \"ax\"\n" "2: movl $1, %0\n" @@ -154,15 +148,15 @@ int __init ftrace_dyn_arch_init(void *data) switch (faulted) { case 0: pr_info("ftrace: converting mcount calls to 0f 1f 44 00 00\n"); - ftrace_nop = (unsigned long *)ftrace_test_p6nop; + memcpy(ftrace_nop, ftrace_test_p6nop, MCOUNT_INSN_SIZE); break; case 1: pr_info("ftrace: converting mcount calls to 66 66 66 66 90\n"); - ftrace_nop = (unsigned long *)ftrace_test_nop5; + memcpy(ftrace_nop, ftrace_test_nop5, MCOUNT_INSN_SIZE); break; case 2: pr_info("ftrace: converting mcount calls to jmp . + 5\n"); - ftrace_nop = (unsigned long *)ftrace_test_jmp; + memcpy(ftrace_nop, ftrace_test_jmp, MCOUNT_INSN_SIZE); break; } -- cgit v1.2.3-18-g5258 From 3afa39493de510c33c56ddc76e6e1af7f87c5392 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sat, 25 Oct 2008 22:58:21 -0700 Subject: x86: keep the /proc/meminfo page count correct Impact: get correct page count in /proc/meminfo found page count in /proc/meminfo is nor correct on 1G system in VirtualBox 2.0.4 # cat /proc/meminfo MemTotal: 1017508 kB MemFree: 822700 kB Buffers: 1456 kB Cached: 26632 kB SwapCached: 0 kB ... Hugepagesize: 2048 kB DirectMap4k: 4032 kB DirectMap2M: 18446744073709549568 kB with this patch get: ... DirectMap4k: 4032 kB DirectMap2M: 1044480 kB which is consistent to kernel_page_tables ---[ Low Kernel Mapping ]--- 0xffff880000000000-0xffff880000001000 4K RW PCD GLB x pte 0xffff880000001000-0xffff88000009f000 632K RW GLB x pte 0xffff88000009f000-0xffff8800000a0000 4K RW PCD GLB x pte 0xffff8800000a0000-0xffff880000200000 1408K RW GLB x pte 0xffff880000200000-0xffff88003fe00000 1020M RW PSE GLB x pmd 0xffff88003fe00000-0xffff88003fff0000 1984K RW GLB NX pte 0xffff88003fff0000-0xffff880040000000 64K pte 0xffff880040000000-0xffff888000000000 511G pud 0xffff888000000000-0xffffc20000000000 58880G pgd Signed-off-by: Yinghai Lu Acked-by: Suresh Siddha Signed-off-by: Ingo Molnar --- arch/x86/mm/init_64.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index b8e461d4941..c7a4c5a9a21 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -350,8 +350,10 @@ phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end, * pagetable pages as RO. So assume someone who pre-setup * these mappings are more intelligent. */ - if (pte_val(*pte)) + if (pte_val(*pte)) { + pages++; continue; + } if (0) printk(" pte=%p addr=%lx pte=%016lx\n", @@ -418,8 +420,10 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end, * not differ with respect to page frame and * attributes. */ - if (page_size_mask & (1 << PG_LEVEL_2M)) + if (page_size_mask & (1 << PG_LEVEL_2M)) { + pages++; continue; + } new_prot = pte_pgprot(pte_clrhuge(*(pte_t *)pmd)); } @@ -499,8 +503,10 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end, * not differ with respect to page frame and * attributes. */ - if (page_size_mask & (1 << PG_LEVEL_1G)) + if (page_size_mask & (1 << PG_LEVEL_1G)) { + pages++; continue; + } prot = pte_pgprot(pte_clrhuge(*(pte_t *)pud)); } -- cgit v1.2.3-18-g5258 From 60817c9b31ef7897d60bca2f384cbc316a3fdd8b Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Mon, 27 Oct 2008 13:03:18 -0700 Subject: x86, memory hotplug: remove wrong -1 in calling init_memory_mapping() Impact: fix crash with memory hotplug Shuahua Li found: | I just did some experiments on a desktop for memory hotplug and this bug | triggered a crash in my test. | | Yinghai's suggestion also fixed the bug. We don't need to round it, just remove that extra -1 Signed-off-by: Yinghai Signed-off-by: Ingo Molnar --- arch/x86/mm/init_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index c7a4c5a9a21..f79a02f64d1 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -837,7 +837,7 @@ int arch_add_memory(int nid, u64 start, u64 size) unsigned long nr_pages = size >> PAGE_SHIFT; int ret; - last_mapped_pfn = init_memory_mapping(start, start + size-1); + last_mapped_pfn = init_memory_mapping(start, start + size); if (last_mapped_pfn > max_pfn_mapped) max_pfn_mapped = last_mapped_pfn; -- cgit v1.2.3-18-g5258 From 6ad9f15c94822c3f067a7d443f3b414e08b34460 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Wed, 15 Oct 2008 07:45:08 -0200 Subject: KVM: MMU: sync root on paravirt TLB flush The pvmmu TLB flush handler should request a root sync, similarly to a native read-write CR3. Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- arch/x86/kvm/mmu.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86') diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 99c239c5c0a..2a5e64881d9 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2634,6 +2634,7 @@ static int kvm_pv_mmu_write(struct kvm_vcpu *vcpu, static int kvm_pv_mmu_flush_tlb(struct kvm_vcpu *vcpu) { kvm_x86_ops->tlb_flush(vcpu); + set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests); return 1; } -- cgit v1.2.3-18-g5258 From 5550af4df179e52753d3a43a788a113ad8cd95cd Mon Sep 17 00:00:00 2001 From: Sheng Yang Date: Wed, 15 Oct 2008 20:15:06 +0800 Subject: KVM: Fix guest shared interrupt with in-kernel irqchip Every call of kvm_set_irq() should offer an irq_source_id, which is allocated by kvm_request_irq_source_id(). Based on irq_source_id, we identify the irq source and implement logical OR for shared level interrupts. The allocated irq_source_id can be freed by kvm_free_irq_source_id(). Currently, we support at most sizeof(unsigned long) different irq sources. [Amit: - rebase to kvm.git HEAD - move definition of KVM_USERSPACE_IRQ_SOURCE_ID to common file - move kvm_request_irq_source_id to the update_irq ioctl] [Xiantao: - Add kvm/ia64 stuff and make it work for kvm/ia64 guests] Signed-off-by: Sheng Yang Signed-off-by: Amit Shah Signed-off-by: Xiantao Zhang Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 3 +++ arch/x86/kvm/i8254.c | 11 +++++++++-- arch/x86/kvm/i8254.h | 1 + arch/x86/kvm/x86.c | 6 +++++- 4 files changed, 18 insertions(+), 3 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 65679d00633..8346be87cfa 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -364,6 +364,9 @@ struct kvm_arch{ struct page *ept_identity_pagetable; bool ept_identity_pagetable_done; + + unsigned long irq_sources_bitmap; + unsigned long irq_states[KVM_IOAPIC_NUM_PINS]; }; struct kvm_vm_stat { diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 11c6725fb79..8772dc94682 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -545,6 +545,12 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm) if (!pit) return NULL; + mutex_lock(&kvm->lock); + pit->irq_source_id = kvm_request_irq_source_id(kvm); + mutex_unlock(&kvm->lock); + if (pit->irq_source_id < 0) + return NULL; + mutex_init(&pit->pit_state.lock); mutex_lock(&pit->pit_state.lock); spin_lock_init(&pit->pit_state.inject_lock); @@ -587,6 +593,7 @@ void kvm_free_pit(struct kvm *kvm) mutex_lock(&kvm->arch.vpit->pit_state.lock); timer = &kvm->arch.vpit->pit_state.pit_timer.timer; hrtimer_cancel(timer); + kvm_free_irq_source_id(kvm, kvm->arch.vpit->irq_source_id); mutex_unlock(&kvm->arch.vpit->pit_state.lock); kfree(kvm->arch.vpit); } @@ -595,8 +602,8 @@ void kvm_free_pit(struct kvm *kvm) static void __inject_pit_timer_intr(struct kvm *kvm) { mutex_lock(&kvm->lock); - kvm_set_irq(kvm, 0, 1); - kvm_set_irq(kvm, 0, 0); + kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1); + kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0); mutex_unlock(&kvm->lock); } diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h index e436d4983aa..4178022b97a 100644 --- a/arch/x86/kvm/i8254.h +++ b/arch/x86/kvm/i8254.h @@ -44,6 +44,7 @@ struct kvm_pit { struct kvm_io_device speaker_dev; struct kvm *kvm; struct kvm_kpit_state pit_state; + int irq_source_id; }; #define KVM_PIT_BASE_ADDRESS 0x40 diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4f0677d1eae..f1f8ff2f1fa 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1742,7 +1742,8 @@ long kvm_arch_vm_ioctl(struct file *filp, goto out; if (irqchip_in_kernel(kvm)) { mutex_lock(&kvm->lock); - kvm_set_irq(kvm, irq_event.irq, irq_event.level); + kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, + irq_event.irq, irq_event.level); mutex_unlock(&kvm->lock); r = 0; } @@ -4013,6 +4014,9 @@ struct kvm *kvm_arch_create_vm(void) INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); + /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */ + set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap); + return kvm; } -- cgit v1.2.3-18-g5258 From 531f6ed7de911e975352fbb2b228367121da630a Mon Sep 17 00:00:00 2001 From: Markus Metzger Date: Fri, 17 Oct 2008 09:09:27 +0200 Subject: x86, bts: improve help text for BTS config Improve the help text of the X86_PTRACE_BTS config. Make X86_DS invisible and depend on X86_PTRACE_BTS. Reported-by: Roland Dreier Signed-off-by: Markus Metzger Signed-off-by: Ingo Molnar --- arch/x86/Kconfig.cpu | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 0b7c4a3f065..b815664fe37 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -513,19 +513,19 @@ config CPU_SUP_UMC_32 If unsure, say N. config X86_DS - bool "Debug Store support" - default y - help - Add support for Debug Store. - This allows the kernel to provide a memory buffer to the hardware - to store various profiling and tracing events. + def_bool X86_PTRACE_BTS + depends on X86_DEBUGCTLMSR config X86_PTRACE_BTS - bool "ptrace interface to Branch Trace Store" + bool "Branch Trace Store" default y - depends on (X86_DS && X86_DEBUGCTLMSR) + depends on X86_DEBUGCTLMSR help - Add a ptrace interface to allow collecting an execution trace - of the traced task. - This collects control flow changes in a (cyclic) buffer and allows - debuggers to fill in the gaps and show an execution trace of the debuggee. + This adds a ptrace interface to the hardware's branch trace store. + + Debuggers may use it to collect an execution trace of the debugged + application in order to answer the question 'how did I get here?'. + Debuggers may trace user mode as well as kernel mode. + + Say Y unless there is no application development on this machine + and you want to save a small amount of code size. -- cgit v1.2.3-18-g5258 From 36b75da27bb51dc34e358d0b7487406132806c46 Mon Sep 17 00:00:00 2001 From: Peter Oruba Date: Fri, 17 Oct 2008 15:30:37 +0200 Subject: x86: microcode patch loader author update Removed one author's email address from module init message. Signed-off-by: Peter Oruba Signed-off-by: Ingo Molnar --- arch/x86/kernel/microcode_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index 936d8d55f23..82fb2809ce3 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -480,8 +480,8 @@ static int __init microcode_init(void) printk(KERN_INFO "Microcode Update Driver: v" MICROCODE_VERSION - " " - " \n"); + " ," + " Peter Oruba\n"); return 0; } -- cgit v1.2.3-18-g5258 From 3c52204bb90834bca8e9e78a3628d886ad6d4db5 Mon Sep 17 00:00:00 2001 From: Peter Oruba Date: Fri, 17 Oct 2008 15:30:38 +0200 Subject: x86: AMD microcode patch loader author update Removed author's email address from MODULE_AUTHOR. Signed-off-by: Peter Oruba Signed-off-by: Ingo Molnar --- arch/x86/kernel/microcode_amd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index 7a1f8eeac2c..5f8e5d75a25 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -39,7 +39,7 @@ #include MODULE_DESCRIPTION("AMD Microcode Update Driver"); -MODULE_AUTHOR("Peter Oruba "); +MODULE_AUTHOR("Peter Oruba"); MODULE_LICENSE("GPL v2"); #define UCODE_MAGIC 0x00414d44 -- cgit v1.2.3-18-g5258 From 1281675e9c0d4d42d993697f4daab45ef22d49da Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 14 Oct 2008 18:59:17 -0700 Subject: x86: fix APIC_DEBUG with inquire_remote_apic APIC_DEBUG is always 2. need to update inquire_remote_apic to check apic_verbosity with it instead. Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/include/asm/es7000/wakecpu.h | 9 ++++----- arch/x86/include/asm/mach-default/mach_wakecpu.h | 9 ++++----- 2 files changed, 8 insertions(+), 10 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/es7000/wakecpu.h b/arch/x86/include/asm/es7000/wakecpu.h index 3ffc5a7bf66..39849346191 100644 --- a/arch/x86/include/asm/es7000/wakecpu.h +++ b/arch/x86/include/asm/es7000/wakecpu.h @@ -50,10 +50,9 @@ static inline void restore_NMI_vector(unsigned short *high, unsigned short *low) { } -#if APIC_DEBUG - #define inquire_remote_apic(apicid) __inquire_remote_apic(apicid) -#else - #define inquire_remote_apic(apicid) {} -#endif +#define inquire_remote_apic(apicid) do { \ + if (apic_verbosity >= APIC_DEBUG) \ + __inquire_remote_apic(apicid); \ + } while (0) #endif /* __ASM_MACH_WAKECPU_H */ diff --git a/arch/x86/include/asm/mach-default/mach_wakecpu.h b/arch/x86/include/asm/mach-default/mach_wakecpu.h index d5c0b826a4f..9d80db91e99 100644 --- a/arch/x86/include/asm/mach-default/mach_wakecpu.h +++ b/arch/x86/include/asm/mach-default/mach_wakecpu.h @@ -33,10 +33,9 @@ static inline void restore_NMI_vector(unsigned short *high, unsigned short *low) { } -#if APIC_DEBUG - #define inquire_remote_apic(apicid) __inquire_remote_apic(apicid) -#else - #define inquire_remote_apic(apicid) {} -#endif +#define inquire_remote_apic(apicid) do { \ + if (apic_verbosity >= APIC_DEBUG) \ + __inquire_remote_apic(apicid); \ + } while (0) #endif /* _ASM_X86_MACH_DEFAULT_MACH_WAKECPU_H */ -- cgit v1.2.3-18-g5258 From e7706fc691513b0f06adb3de3d6ac04293180146 Mon Sep 17 00:00:00 2001 From: Ken'ichi Ohmichi Date: Mon, 20 Oct 2008 13:51:52 +0900 Subject: x86, kdump: fix invalid access on i386 sparsemem Impact: fix kdump crash on 32-bit sparsemem kernels Since linux-2.6.27, kdump has failed on i386 sparsemem kernel. 1st-kernel gets a panic just before switching to 2nd-kernel. The cause is that a kernel accesses invalid mem_section by page_to_pfn(image->swap_page) at machine_kexec(). image->swap_page is allocated if kexec for hibernation, but it is not allocated if kdump. So if kdump, a kernel should not access the mem_section corresponding to image->swap_page. The attached patch fixes this invalid access. Signed-off-by: Ken'ichi Ohmichi Cc: kexec-ml Cc: Andrew Morton Signed-off-by: Ingo Molnar --- arch/x86/kernel/machine_kexec_32.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 0732adba05c..7a385746509 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -162,7 +162,10 @@ void machine_kexec(struct kimage *image) page_list[VA_PTE_0] = (unsigned long)kexec_pte0; page_list[PA_PTE_1] = __pa(kexec_pte1); page_list[VA_PTE_1] = (unsigned long)kexec_pte1; - page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page) << PAGE_SHIFT); + + if (image->type == KEXEC_TYPE_DEFAULT) + page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page) + << PAGE_SHIFT); /* The segment registers are funny things, they have both a * visible and an invisible part. Whenever the visible part is -- cgit v1.2.3-18-g5258 From 11a6b0c933b55654a58afd84f63a5dde1607d78f Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 14 Oct 2008 18:59:18 -0700 Subject: x86: 64 bit print out absent pages num too so users are not confused with memhole causing big total ram we don't need to worry about 32 bit, because memhole is always above max_low_pfn. Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/mm/init_64.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index f79a02f64d1..ad38648bddb 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -884,6 +884,7 @@ static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel, void __init mem_init(void) { long codesize, reservedpages, datasize, initsize; + unsigned long absent_pages; start_periodic_check_for_corruption(); @@ -899,8 +900,9 @@ void __init mem_init(void) #else totalram_pages = free_all_bootmem(); #endif - reservedpages = max_pfn - totalram_pages - - absent_pages_in_range(0, max_pfn); + + absent_pages = absent_pages_in_range(0, max_pfn); + reservedpages = max_pfn - totalram_pages - absent_pages; after_bootmem = 1; codesize = (unsigned long) &_etext - (unsigned long) &_text; @@ -917,10 +919,11 @@ void __init mem_init(void) VSYSCALL_END - VSYSCALL_START); printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, " - "%ldk reserved, %ldk data, %ldk init)\n", + "%ldk absent, %ldk reserved, %ldk data, %ldk init)\n", (unsigned long) nr_free_pages() << (PAGE_SHIFT-10), max_pfn << (PAGE_SHIFT-10), codesize >> 10, + absent_pages << (PAGE_SHIFT-10), reservedpages << (PAGE_SHIFT-10), datasize >> 10, initsize >> 10); -- cgit v1.2.3-18-g5258 From 87c6f40128f92621698f97a62d2ead5184d1dd97 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 28 Oct 2008 16:13:54 +0100 Subject: x86, gart: fix gart detection for Fam11h CPUs Impact: fix AMD Family 11h boot hangs / USB device problems The AMD Fam11h CPUs have a K8 northbridge. This northbridge is different from other family's because it lacks GART support (as I just learned). But the kernel implicitly expects a GART if it finds an AMD northbridge. Fix this by removing the Fam11h northbridge id from the scan list of K8 northbridges. This patch also changes the message in the GART driver about missing K8 northbridges to tell that the GART is missing which is the correct information in this case. Reported-by: Jouni Malinen Signed-off-by: Joerg Roedel Signed-off-by: Ingo Molnar --- arch/x86/kernel/k8.c | 1 - arch/x86/kernel/pci-gart_64.c | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/k8.c b/arch/x86/kernel/k8.c index 304d8bad655..cbc4332a77b 100644 --- a/arch/x86/kernel/k8.c +++ b/arch/x86/kernel/k8.c @@ -18,7 +18,6 @@ static u32 *flush_words; struct pci_device_id k8_nb_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_11H_NB_MISC) }, {} }; EXPORT_SYMBOL(k8_nb_ids); diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index e3f75bbcede..a42b02b4df6 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -744,7 +744,7 @@ void __init gart_iommu_init(void) long i; if (cache_k8_northbridges() < 0 || num_k8_northbridges == 0) { - printk(KERN_INFO "PCI-GART: No AMD northbridge found.\n"); + printk(KERN_INFO "PCI-GART: No AMD GART found.\n"); return; } -- cgit v1.2.3-18-g5258 From f96f57d91c2df75011d1e260c23edca429f37361 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 28 Oct 2008 12:39:23 -0700 Subject: x86: fix init_memory_mapping for [dc000000 - e0000000) - v2 Impact: change over-mapping to precise mapping, fix /proc/meminfo output v2: fix less than 1G ram system handling when gart aperture is 0xdc000000 - 0xe0000000 it return 0xc0000000 - 0xe0000000 that is not right. this patch fix that will get exact mapping on 256g sytem with that aperture after patch LBSuse:~ # cat /proc/meminfo MemTotal: 264742432 kB MemFree: 263920628 kB Buffers: 1416 kB Cached: 24468 kB ... DirectMap4k: 5760 kB DirectMap2M: 3205120 kB DirectMap1G: 265289728 kB it is consistent to LBSuse:~ # cat /sys/kernel/debug/kernel_page_tables .. ---[ Low Kernel Mapping ]--- 0xffff880000000000-0xffff880000200000 2M RW GLB x pte 0xffff880000200000-0xffff880040000000 1022M RW PSE GLB x pmd 0xffff880040000000-0xffff8800c0000000 2G RW PSE GLB NX pud 0xffff8800c0000000-0xffff8800d7e00000 382M RW PSE GLB NX pmd 0xffff8800d7e00000-0xffff8800d7fa0000 1664K RW GLB NX pte 0xffff8800d7fa0000-0xffff8800d8000000 384K pte 0xffff8800d8000000-0xffff8800dc000000 64M pmd 0xffff8800dc000000-0xffff8800e0000000 64M RW PSE GLB NX pmd 0xffff8800e0000000-0xffff880100000000 512M pmd 0xffff880100000000-0xffff880800000000 28G RW PSE GLB NX pud 0xffff880800000000-0xffff880824600000 582M RW PSE GLB NX pmd 0xffff880824600000-0xffff8808247f0000 1984K RW GLB NX pte 0xffff8808247f0000-0xffff880824800000 64K RW PCD GLB NX pte 0xffff880824800000-0xffff880840000000 440M RW PSE GLB NX pmd 0xffff880840000000-0xffff884000000000 223G RW PSE GLB NX pud 0xffff884000000000-0xffff884028000000 640M RW PSE GLB NX pmd 0xffff884028000000-0xffff884040000000 384M pmd 0xffff884040000000-0xffff888000000000 255G pud 0xffff888000000000-0xffffc20000000000 58880G pgd Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/mm/init_64.c | 50 +++++++++++++++++++++++++++++++++----------------- 1 file changed, 33 insertions(+), 17 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index ad38648bddb..ebe1811e5b1 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -671,12 +671,13 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, unsigned long last_map_addr = 0; unsigned long page_size_mask = 0; unsigned long start_pfn, end_pfn; + unsigned long pos; struct map_range mr[NR_RANGE_MR]; int nr_range, i; int use_pse, use_gbpages; - printk(KERN_INFO "init_memory_mapping\n"); + printk(KERN_INFO "init_memory_mapping: %016lx-%016lx\n", start, end); /* * Find space for the kernel direct mapping tables. @@ -710,35 +711,50 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, /* head if not big page alignment ?*/ start_pfn = start >> PAGE_SHIFT; - end_pfn = ((start + (PMD_SIZE - 1)) >> PMD_SHIFT) + pos = start_pfn << PAGE_SHIFT; + end_pfn = ((pos + (PMD_SIZE - 1)) >> PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT); - nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); + if (start_pfn < end_pfn) { + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); + pos = end_pfn << PAGE_SHIFT; + } /* big page (2M) range*/ - start_pfn = ((start + (PMD_SIZE - 1))>>PMD_SHIFT) + start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT); - end_pfn = ((start + (PUD_SIZE - 1))>>PUD_SHIFT) + end_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT); - if (end_pfn > ((end>>PUD_SHIFT)<<(PUD_SHIFT - PAGE_SHIFT))) - end_pfn = ((end>>PUD_SHIFT)<<(PUD_SHIFT - PAGE_SHIFT)); - nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, - page_size_mask & (1< ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT))) + end_pfn = ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT)); + if (start_pfn < end_pfn) { + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, + page_size_mask & (1<>PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT); - nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, + start_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT) + << (PUD_SHIFT - PAGE_SHIFT); + end_pfn = (end >> PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT); + if (start_pfn < end_pfn) { + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, page_size_mask & ((1<>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT); - nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, - page_size_mask & (1<>PMD_SHIFT) + << (PMD_SHIFT - PAGE_SHIFT); + end_pfn = (end >> PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT); + if (start_pfn < end_pfn) { + nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, + page_size_mask & (1<>PAGE_SHIFT; end_pfn = end>>PAGE_SHIFT; nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); -- cgit v1.2.3-18-g5258 From 9352f5698db2c6d7f2789f6cd37e3996d49ac4b5 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Tue, 28 Oct 2008 23:05:22 -0700 Subject: x86: two trivial sparse annotations Impact: fewer sparse warnings, no functional changes arch/x86/kernel/vsmp_64.c:87:14: warning: incorrect type in argument 1 (different address spaces) arch/x86/kernel/vsmp_64.c:87:14: expected void const volatile [noderef] *addr arch/x86/kernel/vsmp_64.c:87:14: got void *[assigned] address arch/x86/kernel/vsmp_64.c:88:22: warning: incorrect type in argument 1 (different address spaces) arch/x86/kernel/vsmp_64.c:88:22: expected void const volatile [noderef] *addr arch/x86/kernel/vsmp_64.c:88:22: got void * arch/x86/kernel/vsmp_64.c:100:23: warning: incorrect type in argument 2 (different address spaces) arch/x86/kernel/vsmp_64.c:100:23: expected void volatile [noderef] *addr arch/x86/kernel/vsmp_64.c:100:23: got void * arch/x86/kernel/vsmp_64.c:101:23: warning: incorrect type in argument 1 (different address spaces) arch/x86/kernel/vsmp_64.c:101:23: expected void const volatile [noderef] *addr arch/x86/kernel/vsmp_64.c:101:23: got void * arch/x86/mm/gup.c:235:6: warning: incorrect type in argument 1 (different base types) arch/x86/mm/gup.c:235:6: expected void const volatile [noderef] * arch/x86/mm/gup.c:235:6: got unsigned long [unsigned] [assigned] start Signed-off-by: Harvey Harrison Signed-off-by: Ingo Molnar --- arch/x86/kernel/vsmp_64.c | 2 +- arch/x86/mm/gup.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index 7766d36983f..a688f3bfaec 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -78,7 +78,7 @@ static unsigned __init_or_module vsmp_patch(u8 type, u16 clobbers, void *ibuf, static void __init set_vsmp_pv_ops(void) { - void *address; + void __iomem *address; unsigned int cap, ctl, cfg; /* set vSMP magic bits to indicate vSMP capable kernel */ diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index 4ba373c5b8c..be54176e9eb 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -233,7 +233,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write, len = (unsigned long) nr_pages << PAGE_SHIFT; end = start + len; if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ, - start, len))) + (void __user *)start, len))) goto slow_irqon; /* -- cgit v1.2.3-18-g5258 From 1d6cf1feb854c53c6d59e0d879603692b379e208 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Tue, 28 Oct 2008 22:46:04 -0700 Subject: x86: start annotating early ioremap pointers with __iomem Impact: some new sparse warnings in e820.c etc, but no functional change. As with regular ioremap, iounmap etc, annotate with __iomem. Fixes the following sparse warnings, will produce some new ones elsewhere in arch/x86 that will get worked out over time. arch/x86/mm/ioremap.c:402:9: warning: cast removes address space of expression arch/x86/mm/ioremap.c:406:10: warning: cast adds address space to expression () arch/x86/mm/ioremap.c:782:19: warning: Using plain integer as NULL pointer Signed-off-by: Harvey Harrison Signed-off-by: Ingo Molnar --- arch/x86/include/asm/io.h | 6 +++--- arch/x86/mm/ioremap.c | 22 +++++++++++----------- 2 files changed, 14 insertions(+), 14 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 5618a103f39..ac2abc88cd9 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -82,9 +82,9 @@ extern void __iomem *ioremap_wc(unsigned long offset, unsigned long size); extern void early_ioremap_init(void); extern void early_ioremap_clear(void); extern void early_ioremap_reset(void); -extern void *early_ioremap(unsigned long offset, unsigned long size); -extern void *early_memremap(unsigned long offset, unsigned long size); -extern void early_iounmap(void *addr, unsigned long size); +extern void __iomem *early_ioremap(unsigned long offset, unsigned long size); +extern void __iomem *early_memremap(unsigned long offset, unsigned long size); +extern void early_iounmap(void __iomem *addr, unsigned long size); extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys); diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index ae71e11eb3e..d4c4307ff3e 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -387,7 +387,7 @@ static void __iomem *ioremap_default(resource_size_t phys_addr, unsigned long size) { unsigned long flags; - void *ret; + void __iomem *ret; int err; /* @@ -399,11 +399,11 @@ static void __iomem *ioremap_default(resource_size_t phys_addr, if (err < 0) return NULL; - ret = (void *) __ioremap_caller(phys_addr, size, flags, - __builtin_return_address(0)); + ret = __ioremap_caller(phys_addr, size, flags, + __builtin_return_address(0)); free_memtype(phys_addr, phys_addr + size); - return (void __iomem *)ret; + return ret; } void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size, @@ -622,7 +622,7 @@ static inline void __init early_clear_fixmap(enum fixed_addresses idx) __early_set_fixmap(idx, 0, __pgprot(0)); } -static void *prev_map[FIX_BTMAPS_SLOTS] __initdata; +static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata; static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata; static int __init check_early_ioremap_leak(void) { @@ -645,7 +645,7 @@ static int __init check_early_ioremap_leak(void) } late_initcall(check_early_ioremap_leak); -static void __init *__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot) +static void __init __iomem *__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot) { unsigned long offset, last_addr; unsigned int nrpages; @@ -713,23 +713,23 @@ static void __init *__early_ioremap(unsigned long phys_addr, unsigned long size, if (early_ioremap_debug) printk(KERN_CONT "%08lx + %08lx\n", offset, fix_to_virt(idx0)); - prev_map[slot] = (void *) (offset + fix_to_virt(idx0)); + prev_map[slot] = (void __iomem *)(offset + fix_to_virt(idx0)); return prev_map[slot]; } /* Remap an IO device */ -void __init *early_ioremap(unsigned long phys_addr, unsigned long size) +void __init __iomem *early_ioremap(unsigned long phys_addr, unsigned long size) { return __early_ioremap(phys_addr, size, PAGE_KERNEL_IO); } /* Remap memory */ -void __init *early_memremap(unsigned long phys_addr, unsigned long size) +void __init __iomem *early_memremap(unsigned long phys_addr, unsigned long size) { return __early_ioremap(phys_addr, size, PAGE_KERNEL); } -void __init early_iounmap(void *addr, unsigned long size) +void __init early_iounmap(void __iomem *addr, unsigned long size) { unsigned long virt_addr; unsigned long offset; @@ -779,7 +779,7 @@ void __init early_iounmap(void *addr, unsigned long size) --idx; --nrpages; } - prev_map[slot] = 0; + prev_map[slot] = NULL; } void __this_fixmap_does_not_exist(void) -- cgit v1.2.3-18-g5258 From fe8b868eccb9f85a0e231e35f0abac5b39bac801 Mon Sep 17 00:00:00 2001 From: Gary Hade Date: Tue, 28 Oct 2008 16:43:14 -0700 Subject: x86: remove debug code from arch_add_memory() Impact: remove incorrect WARN_ON(1) Gets rid of dmesg spam created during physical memory hot-add which will very likely confuse users. The change removes what appears to be debugging code which I assume was unintentionally included in: x86: arch/x86/mm/init_64.c printk fixes commit 10f22dde556d1ed41d55355d1fb8ad495f9810c8 Signed-off-by: Gary Hade Signed-off-by: Ingo Molnar --- arch/x86/mm/init_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index ebe1811e5b1..9db01db6e3c 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -858,7 +858,7 @@ int arch_add_memory(int nid, u64 start, u64 size) max_pfn_mapped = last_mapped_pfn; ret = __add_pages(zone, start_pfn, nr_pages); - WARN_ON(1); + WARN_ON_ONCE(ret); return ret; } -- cgit v1.2.3-18-g5258 From ab00fee30cddf975200b3c97aef25bea144a0d89 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Thu, 30 Oct 2008 10:37:21 +0000 Subject: i386/PAE: fix pud_page() Impact: cleanup To the unsuspecting user it is quite annoying that this broken and inconsistent with x86-64 definition still exists. Signed-off-by: Jan Beulich Signed-off-by: Ingo Molnar --- arch/x86/include/asm/pgtable-3level.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index fb16cec702e..52597aeadff 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -120,13 +120,13 @@ static inline void pud_clear(pud_t *pudp) write_cr3(pgd); } -#define pud_page(pud) ((struct page *) __va(pud_val(pud) & PTE_PFN_MASK)) +#define pud_page(pud) pfn_to_page(pud_val(pud) >> PAGE_SHIFT) #define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & PTE_PFN_MASK)) /* Find an entry in the second-level page table.. */ -#define pmd_offset(pud, address) ((pmd_t *)pud_page(*(pud)) + \ +#define pmd_offset(pud, address) ((pmd_t *)pud_page_vaddr(*(pud)) + \ pmd_index(address)) #ifdef CONFIG_SMP -- cgit v1.2.3-18-g5258 From ae9b9403644f3ecc76867af042e7e1cfd5c099d0 Mon Sep 17 00:00:00 2001 From: Joerg Roed