From 6ffac1e90a17ea0aded5c581204397421eec91b6 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Thu, 24 Jul 2008 18:07:56 -0700 Subject: x64, fpu: fix possible FPU leakage in error conditions On Thu, Jul 24, 2008 at 03:43:44PM -0700, Linus Torvalds wrote: > So how about this patch as a starting point? This is the RightThing(tm) to > do regardless, and if it then makes it easier to do some other cleanups, > we should do it first. What do you think? restore_fpu_checking() calls init_fpu() in error conditions. While this is wrong(as our main intention is to clear the fpu state of the thread), this was benign before commit 92d140e21f1 ("x86: fix taking DNA during 64bit sigreturn"). Post commit 92d140e21f1, live FPU registers may not belong to this process at this error scenario. In the error condition for restore_fpu_checking() (especially during the 64bit signal return), we are doing init_fpu(), which saves the live FPU register state (possibly belonging to some other process context) into the thread struct (through unlazy_fpu() in init_fpu()). This is wrong and can leak the FPU data. For the signal handler restore error condition in restore_i387(), clear the fpu state present in the thread struct(before ultimately sending a SIGSEGV for badframe). For the paranoid error condition check in math_state_restore(), send a SIGSEGV, if we fail to restore the state. Signed-off-by: Suresh Siddha Cc: Cc: Linus Torvalds Signed-off-by: Ingo Molnar --- include/asm-x86/i387.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/asm-x86') diff --git a/include/asm-x86/i387.h b/include/asm-x86/i387.h index 96fa844..0048fb7 100644 --- a/include/asm-x86/i387.h +++ b/include/asm-x86/i387.h @@ -62,8 +62,6 @@ static inline int restore_fpu_checking(struct i387_fxsave_struct *fx) #else : [fx] "cdaSDb" (fx), "m" (*fx), "0" (0)); #endif - if (unlikely(err)) - init_fpu(current); return err; } -- cgit v1.1 From 0ed89b06e49c326bff81d81f24b9ba955eb912d5 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 13 Aug 2008 10:17:24 +0200 Subject: x86: propagate new nonpanic bootmem macros to CONFIG_HAVE_ARCH_BOOTMEM_NODE Commit 74768ed833344b "page allocator: use no-panic variant of alloc_bootmem() in alloc_large_system_hash()" introduced two new _nopanic macros which are undefined for CONFIG_HAVE_ARCH_BOOTMEM_NODE. Signed-off-by: Johannes Weiner Acked-by: "Jan Beulich" Signed-off-by: Ingo Molnar --- include/asm-x86/mmzone_32.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/asm-x86') diff --git a/include/asm-x86/mmzone_32.h b/include/asm-x86/mmzone_32.h index b2298a2..5862e64 100644 --- a/include/asm-x86/mmzone_32.h +++ b/include/asm-x86/mmzone_32.h @@ -97,10 +97,16 @@ static inline int pfn_valid(int pfn) reserve_bootmem_node(NODE_DATA(0), (addr), (size), (flags)) #define alloc_bootmem(x) \ __alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) +#define alloc_bootmem_nopanic(x) \ + __alloc_bootmem_node_nopanic(NODE_DATA(0), (x), SMP_CACHE_BYTES, \ + __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_low(x) \ __alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, 0) #define alloc_bootmem_pages(x) \ __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS)) +#define alloc_bootmem_pages_nopanic(x) \ + __alloc_bootmem_node_nopanic(NODE_DATA(0), (x), PAGE_SIZE, \ + __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_low_pages(x) \ __alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0) #define alloc_bootmem_node(pgdat, x) \ -- cgit v1.1 From 519c31bacf78a969efa8d2e55ed8862848f28590 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 14 Aug 2008 19:55:15 +0200 Subject: x86, AMD IOMMU: use status bit instead of memory write-back for completion wait Signed-off-by: Joerg Roedel Signed-off-by: Ingo Molnar --- include/asm-x86/amd_iommu_types.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/asm-x86') diff --git a/include/asm-x86/amd_iommu_types.h b/include/asm-x86/amd_iommu_types.h index 22aa58c..3254322 100644 --- a/include/asm-x86/amd_iommu_types.h +++ b/include/asm-x86/amd_iommu_types.h @@ -69,6 +69,9 @@ #define MMIO_EVT_TAIL_OFFSET 0x2018 #define MMIO_STATUS_OFFSET 0x2020 +/* MMIO status bits */ +#define MMIO_STATUS_COM_WAIT_INT_MASK 0x04 + /* feature control bits */ #define CONTROL_IOMMU_EN 0x00ULL #define CONTROL_HT_TUN_EN 0x01ULL @@ -89,6 +92,7 @@ #define CMD_INV_IOMMU_PAGES 0x03 #define CMD_COMPL_WAIT_STORE_MASK 0x01 +#define CMD_COMPL_WAIT_INT_MASK 0x02 #define CMD_INV_IOMMU_PAGES_SIZE_MASK 0x01 #define CMD_INV_IOMMU_PAGES_PDE_MASK 0x02 -- cgit v1.1 From 9f5f5fb35d2934fe7dc0cb019854a030efd10cd7 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 14 Aug 2008 19:55:16 +0200 Subject: x86, AMD IOMMU: initialize device table properly This patch adds device table initializations which forbids memory accesses for devices per default and disables all page faults. Signed-off-by: Joerg Roedel Signed-off-by: Ingo Molnar --- include/asm-x86/amd_iommu_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/asm-x86') diff --git a/include/asm-x86/amd_iommu_types.h b/include/asm-x86/amd_iommu_types.h index 3254322..f0beca7 100644 --- a/include/asm-x86/amd_iommu_types.h +++ b/include/asm-x86/amd_iommu_types.h @@ -103,6 +103,7 @@ #define DEV_ENTRY_TRANSLATION 0x01 #define DEV_ENTRY_IR 0x3d #define DEV_ENTRY_IW 0x3e +#define DEV_ENTRY_NO_PAGE_FAULT 0x62 #define DEV_ENTRY_EX 0x67 #define DEV_ENTRY_SYSMGT1 0x68 #define DEV_ENTRY_SYSMGT2 0x69 -- cgit v1.1 From 8a456695c5020d6317f9c7af190999e9414b0d3e Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 14 Aug 2008 19:55:17 +0200 Subject: x86m AMD IOMMU: cleanup: replace LOW_U32 macro with generic lower_32_bits Signed-off-by: Joerg Roedel Signed-off-by: Ingo Molnar --- include/asm-x86/amd_iommu_types.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/asm-x86') diff --git a/include/asm-x86/amd_iommu_types.h b/include/asm-x86/amd_iommu_types.h index f0beca7..dcc8120 100644 --- a/include/asm-x86/amd_iommu_types.h +++ b/include/asm-x86/amd_iommu_types.h @@ -31,9 +31,6 @@ #define ALIAS_TABLE_ENTRY_SIZE 2 #define RLOOKUP_TABLE_ENTRY_SIZE (sizeof(void *)) -/* helper macros */ -#define LOW_U32(x) ((x) & ((1ULL << 32)-1)) - /* Length of the MMIO region for the AMD IOMMU */ #define MMIO_REGION_LENGTH 0x4000 -- cgit v1.1 From 394a15051c33f2b18e72f42283b36a9388fa414b Mon Sep 17 00:00:00 2001 From: Mark Langsdorf Date: Thu, 14 Aug 2008 09:11:26 -0500 Subject: x86: invalidate caches before going into suspend MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When a CPU core is shut down, all of its caches need to be flushed to prevent stale data from causing errors if the core is resumed. Current Linux suspend code performs an assignment after the flush, which can add dirty data back to the cache.  On some AMD platforms, additional speculative reads have caused crashes on resume because of this dirty data. Relocate the cache flush to be the very last thing done before halting.  Tie into an assembly line so the compile will not reorder it.  Add some documentation explaining what is going on and why we're doing this. Signed-off-by: Mark Langsdorf Acked-by: Mark Borden Acked-by: Michael Hohmuth Signed-off-by: Ingo Molnar --- include/asm-x86/processor.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/asm-x86') diff --git a/include/asm-x86/processor.h b/include/asm-x86/processor.h index 5f58da4..4df3e2f 100644 --- a/include/asm-x86/processor.h +++ b/include/asm-x86/processor.h @@ -728,6 +728,29 @@ extern unsigned long boot_option_idle_override; extern unsigned long idle_halt; extern unsigned long idle_nomwait; +/* + * on systems with caches, caches must be flashed as the absolute + * last instruction before going into a suspended halt. Otherwise, + * dirty data can linger in the cache and become stale on resume, + * leading to strange errors. + * + * perform a variety of operations to guarantee that the compiler + * will not reorder instructions. wbinvd itself is serializing + * so the processor will not reorder. + * + * Systems without cache can just go into halt. + */ +static inline void wbinvd_halt(void) +{ + mb(); + /* check for clflush to determine if wbinvd is legal */ + if (cpu_has_clflush) + asm volatile("cli; wbinvd; 1: hlt; jmp 1b" : : : "memory"); + else + while (1) + halt(); +} + extern void enable_sep_cpu(void); extern int sysenter_setup(void); -- cgit v1.1 From 1c5b0eb66d74683e2be5da0c53e33c1f4ca982fd Mon Sep 17 00:00:00 2001 From: Mikael Pettersson Date: Wed, 13 Aug 2008 21:07:07 +0200 Subject: x86: fix readb() et al compile error with gcc-3.2.3 Building 2.6.27-rc1 on x86 with gcc-3.2.3 fails with: In file included from include/asm/dma.h:12, from include/linux/bootmem.h:8, from init/main.c:26: include/asm/io.h: In function `readb': include/asm/io.h:32: syntax error before string constant include/asm/io.h: In function `readw': include/asm/io.h:33: syntax error before string constant include/asm/io.h: In function `readl': include/asm/io.h:34: syntax error before string constant include/asm/io.h: In function `__readb': include/asm/io.h:36: syntax error before string constant include/asm/io.h: In function `__readw': include/asm/io.h:37: syntax error before string constant include/asm/io.h: In function `__readl': include/asm/io.h:38: syntax error before string constant make[1]: *** [init/main.o] Error 1 make: *** [init] Error 2 Starting with 2.6.27-rc1 readb() et al are generated by a build_mmio_read() macro, which generates asm() statements with output register constraints like "=" "q", i.e. as two adjacent string literals. This doesn't work with gcc-3.2.3. Fixed by moving the "=" part into the callers' reg parameter (as suggested by Ingo). Build and boot-tested with gcc-3.2.3 on 32 and 64-bit x86. Fixes . Signed-off-by: Mikael Pettersson Signed-off-by: Ingo Molnar --- include/asm-x86/io.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/asm-x86') diff --git a/include/asm-x86/io.h b/include/asm-x86/io.h index bf5d629..0f954dc 100644 --- a/include/asm-x86/io.h +++ b/include/asm-x86/io.h @@ -21,7 +21,7 @@ extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys); #define build_mmio_read(name, size, type, reg, barrier) \ static inline type name(const volatile void __iomem *addr) \ -{ type ret; asm volatile("mov" size " %1,%0":"=" reg (ret) \ +{ type ret; asm volatile("mov" size " %1,%0":reg (ret) \ :"m" (*(volatile type __force *)addr) barrier); return ret; } #define build_mmio_write(name, size, type, reg, barrier) \ @@ -29,13 +29,13 @@ static inline void name(type val, volatile void __iomem *addr) \ { asm volatile("mov" size " %0,%1": :reg (val), \ "m" (*(volatile type __force *)addr) barrier); } -build_mmio_read(readb, "b", unsigned char, "q", :"memory") -build_mmio_read(readw, "w", unsigned short, "r", :"memory") -build_mmio_read(readl, "l", unsigned int, "r", :"memory") +build_mmio_read(readb, "b", unsigned char, "=q", :"memory") +build_mmio_read(readw, "w", unsigned short, "=r", :"memory") +build_mmio_read(readl, "l", unsigned int, "=r", :"memory") -build_mmio_read(__readb, "b", unsigned char, "q", ) -build_mmio_read(__readw, "w", unsigned short, "r", ) -build_mmio_read(__readl, "l", unsigned int, "r", ) +build_mmio_read(__readb, "b", unsigned char, "=q", ) +build_mmio_read(__readw, "w", unsigned short, "=r", ) +build_mmio_read(__readl, "l", unsigned int, "=r", ) build_mmio_write(writeb, "b", unsigned char, "q", :"memory") build_mmio_write(writew, "w", unsigned short, "r", :"memory") @@ -59,8 +59,8 @@ build_mmio_write(__writel, "l", unsigned int, "r", ) #define mmiowb() barrier() #ifdef CONFIG_X86_64 -build_mmio_read(readq, "q", unsigned long, "r", :"memory") -build_mmio_read(__readq, "q", unsigned long, "r", ) +build_mmio_read(readq, "q", unsigned long, "=r", :"memory") +build_mmio_read(__readq, "q", unsigned long, "=r", ) build_mmio_write(writeq, "q", unsigned long, "r", :"memory") build_mmio_write(__writeq, "q", unsigned long, "r", ) -- cgit v1.1 From 7bc069c6bc4ede519a7116be1b9e149a1dbf787a Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Mon, 4 Aug 2008 14:38:54 +0100 Subject: x86: fix spin_is_contended() The masked difference is what needs to be compared against 1, rather than the difference of masked values (which can be negative). Signed-off-by: Jan Beulich Acked-by: Nick Piggin Cc: Signed-off-by: Ingo Molnar --- include/asm-x86/spinlock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/asm-x86') diff --git a/include/asm-x86/spinlock.h b/include/asm-x86/spinlock.h index 4f9a986..e39c790 100644 --- a/include/asm-x86/spinlock.h +++ b/include/asm-x86/spinlock.h @@ -65,7 +65,7 @@ static inline int __ticket_spin_is_contended(raw_spinlock_t *lock) { int tmp = ACCESS_ONCE(lock->slock); - return (((tmp >> 8) & 0xff) - (tmp & 0xff)) > 1; + return (((tmp >> 8) - tmp) & 0xff) > 1; } static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock) @@ -127,7 +127,7 @@ static inline int __ticket_spin_is_contended(raw_spinlock_t *lock) { int tmp = ACCESS_ONCE(lock->slock); - return (((tmp >> 16) & 0xffff) - (tmp & 0xffff)) > 1; + return (((tmp >> 16) - tmp) & 0xffff) > 1; } static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock) -- cgit v1.1 From 0d5cdc97e242a5589e5dca23277675f4b4482490 Mon Sep 17 00:00:00 2001 From: Jens Rottmann Date: Mon, 4 Aug 2008 14:40:16 +0200 Subject: x86, geode-mfgpt: check IRQ before using MFGPT as clocksource Adds a simple IRQ autodetection to the AMD Geode MFGPT driver, and more importantly, adds some checks, if IRQs can actually be received on the chosen line. This fixes cases where MFGPT is selected as clocksource though not producing any ticks, so the kernel simply starves during boot. Signed-off-by: Jens Rottmann Cc: Andres Salomon Cc: linux-geode@bombadil.infradead.org Cc: Jordan Crouse Signed-off-by: Ingo Molnar --- include/asm-x86/geode.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/asm-x86') diff --git a/include/asm-x86/geode.h b/include/asm-x86/geode.h index bb06027..2c1cda0 100644 --- a/include/asm-x86/geode.h +++ b/include/asm-x86/geode.h @@ -50,6 +50,7 @@ extern int geode_get_dev_base(unsigned int dev); #define MSR_PIC_YSEL_HIGH 0x51400021 #define MSR_PIC_ZSEL_LOW 0x51400022 #define MSR_PIC_ZSEL_HIGH 0x51400023 +#define MSR_PIC_IRQM_LPC 0x51400025 #define MSR_MFGPT_IRQ 0x51400028 #define MSR_MFGPT_NR 0x51400029 @@ -237,7 +238,7 @@ static inline u16 geode_mfgpt_read(int timer, u16 reg) } extern int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable); -extern int geode_mfgpt_set_irq(int timer, int cmp, int irq, int enable); +extern int geode_mfgpt_set_irq(int timer, int cmp, int *irq, int enable); extern int geode_mfgpt_alloc_timer(int timer, int domain); #define geode_mfgpt_setup_irq(t, c, i) geode_mfgpt_set_irq((t), (c), (i), 1) -- cgit v1.1 From 66d4bdf22b8652cda215e2653c8bbec7a767ed57 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Thu, 31 Jul 2008 16:48:31 +0100 Subject: x86-64: fix overlap of modules and fixmap areas Plus add a build time check so this doesn't go unnoticed again. Signed-off-by: Jan Beulich Signed-off-by: Ingo Molnar --- include/asm-x86/pgtable_64.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/asm-x86') diff --git a/include/asm-x86/pgtable_64.h b/include/asm-x86/pgtable_64.h index ac5fff4..549144d 100644 --- a/include/asm-x86/pgtable_64.h +++ b/include/asm-x86/pgtable_64.h @@ -151,7 +151,7 @@ static inline void native_pgd_clear(pgd_t *pgd) #define VMALLOC_END _AC(0xffffe1ffffffffff, UL) #define VMEMMAP_START _AC(0xffffe20000000000, UL) #define MODULES_VADDR _AC(0xffffffffa0000000, UL) -#define MODULES_END _AC(0xfffffffffff00000, UL) +#define MODULES_END _AC(0xffffffffff000000, UL) #define MODULES_LEN (MODULES_END - MODULES_VADDR) #ifndef __ASSEMBLY__ -- cgit v1.1 From 163f6876f5c3ff8215e900b93779e960a56b3694 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Fri, 15 Aug 2008 00:40:22 -0700 Subject: kexec jump: rename KEXEC_CONTROL_CODE_SIZE to KEXEC_CONTROL_PAGE_SIZE Rename KEXEC_CONTROL_CODE_SIZE to KEXEC_CONTROL_PAGE_SIZE, because control page is used for not only code on some platform. For example in kexec jump, it is used for data and stack too. [akpm@linux-foundation.org: unbreak powerpc and arm, finish conversion] Signed-off-by: Huang Ying Cc: Pavel Machek Cc: "Rafael J. Wysocki" Cc: "Eric W. Biederman" Cc: Vivek Goyal Cc: Ingo Molnar Cc: Russell King Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-x86/kexec.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/asm-x86') diff --git a/include/asm-x86/kexec.h b/include/asm-x86/kexec.h index c0e52a1..f6fb3d2 100644 --- a/include/asm-x86/kexec.h +++ b/include/asm-x86/kexec.h @@ -63,7 +63,7 @@ /* Maximum address we can use for the control code buffer */ # define KEXEC_CONTROL_MEMORY_LIMIT TASK_SIZE -# define KEXEC_CONTROL_CODE_SIZE 4096 +# define KEXEC_CONTROL_PAGE_SIZE 4096 /* The native architecture */ # define KEXEC_ARCH KEXEC_ARCH_386 @@ -79,7 +79,7 @@ # define KEXEC_CONTROL_MEMORY_LIMIT (0xFFFFFFFFFFUL) /* Allocate one page for the pdp and the second for the code */ -# define KEXEC_CONTROL_CODE_SIZE (4096UL + 4096UL) +# define KEXEC_CONTROL_PAGE_SIZE (4096UL + 4096UL) /* The native architecture */ # define KEXEC_ARCH KEXEC_ARCH_X86_64 -- cgit v1.1 From fb45daa69d287b394eca1619b3fadff7c0215c71 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Fri, 15 Aug 2008 00:40:23 -0700 Subject: kexec jump: check code size in control page Kexec/Kexec-jump require code size in control page is less than PAGE_SIZE/2. This patch add link-time checking for this. ASSERT() of ld link script is used as the link-time checking mechanism. [akpm@linux-foundation.org: build fix] Signed-off-by: Huang Ying Cc: Pavel Machek Cc: "Rafael J. Wysocki" Cc: "Eric W. Biederman" Acked-by: Vivek Goyal Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-x86/kexec.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/asm-x86') diff --git a/include/asm-x86/kexec.h b/include/asm-x86/kexec.h index f6fb3d2..4246ab7 100644 --- a/include/asm-x86/kexec.h +++ b/include/asm-x86/kexec.h @@ -41,6 +41,10 @@ # define PAGES_NR 17 #endif +#ifdef CONFIG_X86_32 +# define KEXEC_CONTROL_CODE_MAX_SIZE 2048 +#endif + #ifndef __ASSEMBLY__ #include -- cgit v1.1 From 2fdc86901d2ab30a12402b46238951d2a7891590 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 13 Aug 2008 18:02:18 +0200 Subject: x86: add MAP_STACK mmap flag as per this discussion: http://lkml.org/lkml/2008/8/12/423 Pardo reported that 64-bit threaded apps, if their stacks exceed the combined size of ~4GB, slow down drastically in pthread_create() - because glibc uses MAP_32BIT to allocate the stacks. The use of MAP_32BIT is a legacy hack - to speed up context switching on certain early model 64-bit P4 CPUs. So introduce a new flag to be used by glibc instead, to not constrain 64-bit apps like this. glibc can switch to this new flag straight away - it will be ignored by the kernel. If those old CPUs ever matter to anyone, support for it can be implemented. Signed-off-by: Ingo Molnar Acked-by: Ulrich Drepper --- include/asm-x86/mman.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/asm-x86') diff --git a/include/asm-x86/mman.h b/include/asm-x86/mman.h index c1682b5..90bc410 100644 --- a/include/asm-x86/mman.h +++ b/include/asm-x86/mman.h @@ -12,6 +12,7 @@ #define MAP_NORESERVE 0x4000 /* don't check for reservations */ #define MAP_POPULATE 0x8000 /* populate (prefault) pagetables */ #define MAP_NONBLOCK 0x10000 /* do not block on IO */ +#define MAP_STACK 0x20000 /* give out an address that is best suited for process/thread stacks */ #define MCL_CURRENT 1 /* lock all current mappings */ #define MCL_FUTURE 2 /* lock all future mappings */ -- cgit v1.1 From cd98a04a59e2f94fa64d5bf1e26498d27427d5e7 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 13 Aug 2008 18:02:18 +0200 Subject: x86: add MAP_STACK mmap flag as per this discussion: http://lkml.org/lkml/2008/8/12/423 Pardo reported that 64-bit threaded apps, if their stacks exceed the combined size of ~4GB, slow down drastically in pthread_create() - because glibc uses MAP_32BIT to allocate the stacks. The use of MAP_32BIT is a legacy hack - to speed up context switching on certain early model 64-bit P4 CPUs. So introduce a new flag to be used by glibc instead, to not constrain 64-bit apps like this. glibc can switch to this new flag straight away - it will be ignored by the kernel. If those old CPUs ever matter to anyone, support for it can be implemented. Signed-off-by: Ingo Molnar Acked-by: Ulrich Drepper Signed-off-by: Linus Torvalds --- include/asm-x86/mman.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/asm-x86') diff --git a/include/asm-x86/mman.h b/include/asm-x86/mman.h index c1682b5..90bc410 100644 --- a/include/asm-x86/mman.h +++ b/include/asm-x86/mman.h @@ -12,6 +12,7 @@ #define MAP_NORESERVE 0x4000 /* don't check for reservations */ #define MAP_POPULATE 0x8000 /* populate (prefault) pagetables */ #define MAP_NONBLOCK 0x10000 /* do not block on IO */ +#define MAP_STACK 0x20000 /* give out an address that is best suited for process/thread stacks */ #define MCL_CURRENT 1 /* lock all current mappings */ #define MCL_FUTURE 2 /* lock all future mappings */ -- cgit v1.1 From 3c3b5c3b0bf798316a410e27e3d7e6f015663602 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Sat, 16 Aug 2008 03:39:26 -0400 Subject: x86: correct register constraints for 64-bit atomic operations x86_64 add/sub atomic ops does not seems to accept integer values bigger than 32 bits as immediates. Intel's add/sub documentation specifies they have to be passed as registers. The only operations in the x86-64 architecture which accept arbitrary 64-bit immediates is "movq" to any register; similarly, the only operation which accept arbitrary 64-bit displacement is "movabs" to or from al/ax/eax/rax. http://gcc.gnu.org/onlinedocs/gcc-4.3.0/gcc/Machine-Constraints.html states : e 32-bit signed integer constant, or a symbolic reference known to fit that range (for immediate operands in sign-extending x86-64 instructions). Z 32-bit unsigned integer constant, or a symbolic reference known to fit that range (for immediate operands in zero-extending x86-64 instructions). Since add/sub does sign extension, using the "e" constraint seems appropriate. It applies to 2.6.27-rc, 2.6.26, 2.6.25... Signed-off-by: Mathieu Desnoyers Signed-off-by: H. Peter Anvin Signed-off-by: Ingo Molnar --- include/asm-x86/atomic_64.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/asm-x86') diff --git a/include/asm-x86/atomic_64.h b/include/asm-x86/atomic_64.h index a009519..91c7d03 100644 --- a/include/asm-x86/atomic_64.h +++ b/include/asm-x86/atomic_64.h @@ -228,7 +228,7 @@ static inline void atomic64_add(long i, atomic64_t *v) { asm volatile(LOCK_PREFIX "addq %1,%0" : "=m" (v->counter) - : "ir" (i), "m" (v->counter)); + : "er" (i), "m" (v->counter)); } /** @@ -242,7 +242,7 @@ static inline void atomic64_sub(long i, atomic64_t *v) { asm volatile(LOCK_PREFIX "subq %1,%0" : "=m" (v->counter) - : "ir" (i), "m" (v->counter)); + : "er" (i), "m" (v->counter)); } /** @@ -260,7 +260,7 @@ static inline int atomic64_sub_and_test(long i, atomic64_t *v) asm volatile(LOCK_PREFIX "subq %2,%0; sete %1" : "=m" (v->counter), "=qm" (c) - : "ir" (i), "m" (v->counter) : "memory"); + : "er" (i), "m" (v->counter) : "memory"); return c; } @@ -341,7 +341,7 @@ static inline int atomic64_add_negative(long i, atomic64_t *v) asm volatile(LOCK_PREFIX "addq %2,%0; sets %1" : "=m" (v->counter), "=qm" (c) - : "ir" (i), "m" (v->counter) : "memory"); + : "er" (i), "m" (v->counter) : "memory"); return c; } -- cgit v1.1 From c72a5efec1193faa2ef34c0bd48d7251a70ec934 Mon Sep 17 00:00:00 2001 From: Marcin Slusarz Date: Mon, 11 Aug 2008 00:11:13 +0200 Subject: x86: mmconf: fix section mismatch warning WARNING: arch/x86/kernel/built-in.o(.cpuinit.text+0x1591): Section mismatch in reference from the function init_amd() to the function .init.text:check_enable_amd_mmconf_dmi() The function __cpuinit init_amd() references a function __init check_enable_amd_mmconf_dmi(). If check_enable_amd_mmconf_dmi is only used by init_amd then annotate check_enable_amd_mmconf_dmi with a matching annotation. check_enable_amd_mmconf_dmi is only called from init_amd which is __cpuinit Signed-off-by: Marcin Slusarz Signed-off-by: H. Peter Anvin Signed-off-by: Ingo Molnar --- include/asm-x86/mmconfig.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/asm-x86') diff --git a/include/asm-x86/mmconfig.h b/include/asm-x86/mmconfig.h index 95beda0..e293ab8 100644 --- a/include/asm-x86/mmconfig.h +++ b/include/asm-x86/mmconfig.h @@ -3,7 +3,7 @@ #ifdef CONFIG_PCI_MMCONFIG extern void __cpuinit fam10h_check_enable_mmcfg(void); -extern void __init check_enable_amd_mmconf_dmi(void); +extern void __cpuinit check_enable_amd_mmconf_dmi(void); #else static inline void fam10h_check_enable_mmcfg(void) { } static inline void check_enable_amd_mmconf_dmi(void) { } -- cgit v1.1 From c6a92a2501b35880d2e357dbd7f2cbc9a06f1058 Mon Sep 17 00:00:00 2001 From: Marcin Slusarz Date: Sun, 17 Aug 2008 17:50:50 +0200 Subject: x86, percpu: silence section mismatch warnings related to EARLY_PER_CPU variables Quoting Mike Travis in "x86: cleanup early per cpu variables/accesses v4" (23ca4bba3e20c6c3cb11c1bb0ab4770b724d39ac): The DEFINE macro defines the per_cpu variable as well as the early map and pointer. It also initializes the per_cpu variable and map elements to "_initvalue". The early_* macros provide access to the initial map (usually setup during system init) and the early pointer. This pointer is initialized to point to the early map but is then NULL'ed when the actual per_cpu areas are setup. After that the per_cpu variable is the correct access to the variable. As these variables are NULL'ed before __init sections are dropped (in setup_per_cpu_maps), they can be safely annotated as __ref. This change silences following section mismatch warnings: WARNING: vmlinux.o(.data+0x46c0): Section mismatch in reference from the variable x86_cpu_to_apicid_early_ptr to the variable .init.data:x86_cpu_to_apicid_early_map The variable x86_cpu_to_apicid_early_ptr references the variable __initdata x86_cpu_to_apicid_early_map If the reference is valid then annotate the variable with __init* (see linux/init.h) or name the variable: *driver, *_template, *_timer, *_sht, *_ops, *_probe, *_probe_one, *_console, WARNING: vmlinux.o(.data+0x46c8): Section mismatch in reference from the variable x86_bios_cpu_apicid_early_ptr to the variable .init.data:x86_bios_cpu_apicid_early_map The variable x86_bios_cpu_apicid_early_ptr references the variable __initdata x86_bios_cpu_apicid_early_map If the reference is valid then annotate the variable with __init* (see linux/init.h) or name the variable: *driver, *_template, *_timer, *_sht, *_ops, *_probe, *_probe_one, *_console, WARNING: vmlinux.o(.data+0x46d0): Section mismatch in reference from the variable x86_cpu_to_node_map_early_ptr to the variable .init.data:x86_cpu_to_node_map_early_map The variable x86_cpu_to_node_map_early_ptr references the variable __initdata x86_cpu_to_node_map_early_map If the reference is valid then annotate the variable with __init* (see linux/init.h) or name the variable: *driver, *_template, *_timer, *_sht, *_ops, *_probe, *_probe_one, *_console, Signed-off-by: Marcin Slusarz Cc: Mike Travis Signed-off-by: Ingo Molnar --- include/asm-x86/percpu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/asm-x86') diff --git a/include/asm-x86/percpu.h b/include/asm-x86/percpu.h index 4e91ee1..f643a3a 100644 --- a/include/asm-x86/percpu.h +++ b/include/asm-x86/percpu.h @@ -182,7 +182,7 @@ do { \ DEFINE_PER_CPU(_type, _name) = _initvalue; \ __typeof__(_type) _name##_early_map[NR_CPUS] __initdata = \ { [0 ... NR_CPUS-1] = _initvalue }; \ - __typeof__(_type) *_name##_early_ptr = _name##_early_map + __typeof__(_type) *_name##_early_ptr __refdata = _name##_early_map #define EXPORT_EARLY_PER_CPU_SYMBOL(_name) \ EXPORT_PER_CPU_SYMBOL(_name) -- cgit v1.1 From 99dd8713306a89f3e106143581244e550e00a644 Mon Sep 17 00:00:00 2001 From: Cliff Wickman Date: Tue, 19 Aug 2008 12:51:59 -0500 Subject: x86, SGI UV: hardcode the TLB flush interrupt system vector The UV TLB shootdown mechanism needs a system interrupt vector. Its vector had been hardcoded as 200, but needs to moved to the reserved system vector range so that it does not collide with some device vector. This is still temporary until dynamic system IRQ allocation is provided. But it will be needed when real UV hardware becomes available and runs 2.6.27. Signed-off-by: Cliff Wickman Signed-off-by: Ingo Molnar --- include/asm-x86/irq_vectors.h | 1 + include/asm-x86/uv/uv_bau.h | 5 ----- 2 files changed, 1 insertion(+), 5 deletions(-) (limited to 'include/asm-x86') diff --git a/include/asm-x86/irq_vectors.h b/include/asm-x86/irq_vectors.h index b95d167..a48c7f2 100644 --- a/include/asm-x86/irq_vectors.h +++ b/include/asm-x86/irq_vectors.h @@ -76,6 +76,7 @@ #define CALL_FUNCTION_SINGLE_VECTOR 0xfb #define THERMAL_APIC_VECTOR 0xfa #define THRESHOLD_APIC_VECTOR 0xf9 +#define UV_BAU_MESSAGE 0xf8 #define INVALIDATE_TLB_VECTOR_END 0xf7 #define INVALIDATE_TLB_VECTOR_START 0xf0 /* f0-f7 used for TLB flush */ diff --git a/include/asm-x86/uv/uv_bau.h b/include/asm-x86/uv/uv_bau.h index 91ac0df..610b6b3 100644 --- a/include/asm-x86/uv/uv_bau.h +++ b/include/asm-x86/uv/uv_bau.h @@ -40,11 +40,6 @@ #define UV_ACTIVATION_DESCRIPTOR_SIZE 32 #define UV_DISTRIBUTION_SIZE 256 #define UV_SW_ACK_NPENDING 8 -#define UV_BAU_MESSAGE 200 -/* - * Messaging irq; see irq_64.h and include/asm-x86/hw_irq_64.h - * To be dynamically allocated in the future - */ #define UV_NET_ENDPOINT_INTD 0x38 #define UV_DESC_BASE_PNODE_SHIFT 49 #define UV_PAYLOADQ_PNODE_SHIFT 49 -- cgit v1.1 From c4bd1fdab0deec0f69aeabab22075cb22ac8ad44 Mon Sep 17 00:00:00 2001 From: Marcin Slusarz Date: Thu, 21 Aug 2008 20:49:05 +0200 Subject: x86: fix section mismatch warning - uv_cpu_init WARNING: vmlinux.o(.cpuinit.text+0x3cc4): Section mismatch in reference from the function uv_cpu_init() to the function .init.text:uv_system_init() The function __cpuinit uv_cpu_init() references a function __init uv_system_init(). If uv_system_init is only used by uv_cpu_init then annotate uv_system_init with a matching annotation. uv_system_init was ment to be called only once, so do it from codepath (native_smp_prepare_cpus) which is called once, right before activation of other cpus (smp_init). Note: old code relied on uv_node_to_blade being initialized to 0, but it'a not initialized from anywhere. Signed-off-by: Marcin Slusarz Acked-by: Jack Steiner Signed-off-by: Ingo Molnar --- include/asm-x86/genapic_32.h | 1 + include/asm-x86/genapic_64.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/asm-x86') diff --git a/include/asm-x86/genapic_32.h b/include/asm-x86/genapic_32.h index b02ea6e..754d635 100644 --- a/include/asm-x86/genapic_32.h +++ b/include/asm-x86/genapic_32.h @@ -118,6 +118,7 @@ enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC}; #define get_uv_system_type() UV_NONE #define is_uv_system() 0 #define uv_wakeup_secondary(a, b) 1 +#define uv_system_init() do {} while (0) #endif diff --git a/include/asm-x86/genapic_64.h b/include/asm-x86/genapic_64.h index 0f85046..a47d631 100644 --- a/include/asm-x86/genapic_64.h +++ b/include/asm-x86/genapic_64.h @@ -42,6 +42,7 @@ extern int is_uv_system(void); extern struct genapic apic_x2apic_uv_x; DECLARE_PER_CPU(int, x2apic_extra_bits); extern void uv_cpu_init(void); +extern void uv_system_init(void); extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip); extern void setup_apic_routing(void); -- cgit v1.1 From 8735728ef8dc935c4fb351f913758fdbb62c308d Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 22 Aug 2008 22:23:09 +0200 Subject: x86 MCE: Fix CPU hotplug problem with multiple multicore AMD CPUs During CPU hot-remove the sysfs directory created by threshold_create_bank(), defined in arch/x86/kernel/cpu/mcheck/mce_amd_64.c, has to be removed before its parent directory, created by mce_create_device(), defined in arch/x86/kernel/cpu/mcheck/mce_64.c . Moreover, when the CPU in question is hotplugged again, obviously the latter has to be created before the former. At present, the right ordering is not enforced, because all of these operations are carried out by CPU hotplug notifiers which are not appropriately ordered with respect to each other. This leads to serious problems on systems with two or more multicore AMD CPUs, among other things during suspend and hibernation. Fix the problem by placing threshold bank CPU hotplug callbacks in mce_cpu_callback(), so that they are invoked at the right places, if defined. Additionally, use kobject_del() to remove the sysfs directory associated with the kobject created by kobject_create_and_add() in threshold_create_bank(), to prevent the kernel from crashing during CPU hotplug operations on systems with two or more multicore AMD CPUs. This patch fixes bug #11337. Signed-off-by: Rafael J. Wysocki Acked-by: Andi Kleen Tested-by: Mark Langsdorf Signed-off-by: Ingo Molnar --- include/asm-x86/mce.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/asm-x86') diff --git a/include/asm-x86/mce.h b/include/asm-x86/mce.h index 94f1fd7..531eaa5 100644 --- a/include/asm-x86/mce.h +++ b/include/asm-x86/mce.h @@ -92,6 +92,7 @@ extern int mce_disabled; void mce_log(struct mce *m); DECLARE_PER_CPU(struct sys_device, device_mce); +extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu); #ifdef CONFIG_X86_MCE_INTEL void mce_intel_feature_init(struct cpuinfo_x86 *c); -- cgit v1.1 From 7a8fc9b248e77a4eab0613acf30a6811799786b3 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Sun, 17 Aug 2008 17:36:59 +0300 Subject: removed unused #include 's This patch lets the files using linux/version.h match the files that #include it. Signed-off-by: Adrian Bunk Signed-off-by: Linus Torvalds --- include/asm-x86/xen/hypervisor.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/asm-x86') diff --git a/include/asm-x86/xen/hypervisor.h b/include/asm-x86/xen/hypervisor.h index 8e15dd2..04ee061 100644 --- a/include/asm-x86/xen/hypervisor.h +++ b/include/asm-x86/xen/hypervisor.h @@ -35,7 +35,6 @@ #include #include -#include #include #include -- cgit v1.1 From 2a61812af2e564cba2c8170cf96e1c823210f619 Mon Sep 17 00:00:00 2001 From: Austin Zhang Date: Mon, 25 Aug 2008 11:14:51 -0400 Subject: x86: add X86_FEATURE_XMM4_2 definitions Added Intel processor SSE4.2 feature flag. No in-tree user at the moment, but makes the tree-merging life easier for the crypto tree. Signed-off-by: Austin Zhang Signed-off-by: Ingo Molnar --- include/asm-x86/cpufeature.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/asm-x86') diff --git a/include/asm-x86/cpufeature.h b/include/asm-x86/cpufeature.h index 2f5a792..762f6a6 100644 --- a/include/asm-x86/cpufeature.h +++ b/include/asm-x86/cpufeature.h @@ -91,6 +91,7 @@ #define X86_FEATURE_CX16 (4*32+13) /* CMPXCHG16B */ #define X86_FEATURE_XTPR (4*32+14) /* Send Task Priority Messages */ #define X86_FEATURE_DCA (4*32+18) /* Direct Cache Access */ +#define X86_FEATURE_XMM4_2 (4*32+20) /* Streaming SIMD Extensions-4.2 */ /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */ #define X86_FEATURE_XSTORE (5*32+ 2) /* on-CPU RNG present (xstore insn) */ @@ -189,6 +190,7 @@ extern const char * const x86_power_flags[32]; #define cpu_has_gbpages boot_cpu_has(X86_FEATURE_GBPAGES) #define cpu_has_arch_perfmon boot_cpu_has(X86_FEATURE_ARCH_PERFMON) #define cpu_has_pat boot_cpu_has(X86_FEATURE_PAT) +#define cpu_has_xmm4_2 boot_cpu_has(X86_FEATURE_XMM4_2) #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64) # define cpu_has_invlpg 1 -- cgit v1.1 From c6f31932d0a1d2b13952f506ebc92675e2d8df80 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Mon, 25 Aug 2008 17:27:21 -0700 Subject: x86: msr: propagate errors from smp_call_function_single() Propagate error (-ENXIO) from smp_call_function_single(). These errors can happen when a CPU is unplugged while the MSR driver is open. Signed-off-by: H. Peter Anvin --- include/asm-x86/msr.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/asm-x86') diff --git a/include/asm-x86/msr.h b/include/asm-x86/msr.h index ca110ee..ad5f2de 100644 --- a/include/asm-x86/msr.h +++ b/include/asm-x86/msr.h @@ -192,19 +192,20 @@ do { \ #define write_rdtscp_aux(val) wrmsr(0xc0000103, (val), 0) #ifdef CONFIG_SMP -void rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); -void wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); +int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); +int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); - int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); #else /* CONFIG_SMP */ -static inline void rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) +static inline int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) { rdmsr(msr_no, *l, *h); + return 0; } -static inline void wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) +static inline int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) { wrmsr(msr_no, l, h); + return 0; } static inline int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) -- cgit v1.1 From 08970fc4e0385790a7b093adfaa4165a189f9eb0 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Mon, 25 Aug 2008 22:39:15 -0700 Subject: x86: msr: fix bogus return values from rdmsr_safe/wrmsr_safe Impact: bogus error codes (+other?) on x86-64 The rdmsr_safe/wrmsr_safe routines have macros for the handling of the edx:eax arguments. Those macros take a variable number of assembly arguments. This is rather inherently incompatible with using %digit-style escapes in the inline assembly; replace those with %[name]-style escapes. This fixes miscompilation on x86-64, which at the very least caused bogus return values. It is possible that this could also corrupt the return value; I am not sure. Signed-off-by: H. Peter Anvin --- include/asm-x86/msr.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/asm-x86') diff --git a/include/asm-x86/msr.h b/include/asm-x86/msr.h index ad5f2de..2362cfd 100644 --- a/include/asm-x86/msr.h +++ b/include/asm-x86/msr.h @@ -52,14 +52,14 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr, { DECLARE_ARGS(val, low, high); - asm volatile("2: rdmsr ; xor %0,%0\n" + asm volatile("2: rdmsr ; xor %[err],%[err]\n" "1:\n\t" ".section .fixup,\"ax\"\n\t" - "3: mov %3,%0 ; jmp 1b\n\t" + "3: mov %[fault],%[err] ; jmp 1b\n\t" ".previous\n\t" _ASM_EXTABLE(2b, 3b) - : "=r" (*err), EAX_EDX_RET(val, low, high) - : "c" (msr), "i" (-EFAULT)); + : [err] "=r" (*err), EAX_EDX_RET(val, low, high) + : "c" (msr), [fault] "i" (-EFAULT)); return EAX_EDX_VAL(val, low, high); } @@ -73,15 +73,15 @@ static inline int native_write_msr_safe(unsigned int msr, unsigned low, unsigned high) { int err; - asm volatile("2: wrmsr ; xor %0,%0\n" + asm volatile("2: wrmsr ; xor %[err],%[err]\n" "1:\n\t" ".section .fixup,\"ax\"\n\t" - "3: mov %4,%0 ; jmp 1b\n\t" + "3: mov %[fault],%[err] ; jmp 1b\n\t" ".previous\n\t" _ASM_EXTABLE(2b, 3b) - : "=a" (err) + : [err] "=a" (err) : "c" (msr), "0" (low), "d" (high), - "i" (-EFAULT) + [fault] "i" (-EFAULT) : "memory"); return err; } -- cgit v1.1