From c8399943bdb70fef78798b97f975506ecc99e039 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 12 Jan 2009 23:01:15 +0100 Subject: x86, generic: mark complex bitops.h inlines as __always_inline Impact: reduce kernel image size Hugh Dickins noticed that older gcc versions when the kernel is built for code size didn't inline some of the bitops. Mark all complex x86 bitops that have more than a single asm statement or two as always inline to avoid this problem. Probably should be done for other architectures too. Ingo then found a better fix that only requires a single line change, but it unfortunately only works on gcc 4.3. On older gccs the original patch still makes a ~0.3% defconfig difference with CONFIG_OPTIMIZE_INLINING=y. With gcc 4.1 and a defconfig like build: 6116998 1138540 883788 8139326 7c323e vmlinux-oi-with-patch 6137043 1138540 883788 8159371 7c808b vmlinux-optimize-inlining ~20k / 0.3% difference. Signed-off-by: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar --- arch/x86/include/asm/bitops.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index e02a359d2aa..02b47a603fc 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -3,6 +3,9 @@ /* * Copyright 1992, Linus Torvalds. + * + * Note: inlines with more than a single statement should be marked + * __always_inline to avoid problems with older gcc's inlining heuristics. */ #ifndef _LINUX_BITOPS_H @@ -53,7 +56,8 @@ * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ -static inline void set_bit(unsigned int nr, volatile unsigned long *addr) +static __always_inline void +set_bit(unsigned int nr, volatile unsigned long *addr) { if (IS_IMMEDIATE(nr)) { asm volatile(LOCK_PREFIX "orb %1,%0" @@ -90,7 +94,8 @@ static inline void __set_bit(int nr, volatile unsigned long *addr) * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit() * in order to ensure changes are visible on other processors. */ -static inline void clear_bit(int nr, volatile unsigned long *addr) +static __always_inline void +clear_bit(int nr, volatile unsigned long *addr) { if (IS_IMMEDIATE(nr)) { asm volatile(LOCK_PREFIX "andb %1,%0" @@ -204,7 +209,8 @@ static inline int test_and_set_bit(int nr, volatile unsigned long *addr) * * This is the same as test_and_set_bit on x86. */ -static inline int test_and_set_bit_lock(int nr, volatile unsigned long *addr) +static __always_inline int +test_and_set_bit_lock(int nr, volatile unsigned long *addr) { return test_and_set_bit(nr, addr); } @@ -300,7 +306,7 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr) return oldbit; } -static inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr) +static __always_inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr) { return ((1UL << (nr % BITS_PER_LONG)) & (((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0; -- cgit v1.2.3-70-g09d2 From a3c6018e565dc07cf3738ace6bbe412f97b1bba8 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Fri, 16 Jan 2009 11:59:33 +0000 Subject: x86: fix assumed to be contiguous leaf page tables for kmap_atomic region (take 2) Debugging and original patch from Nick Piggin The early fixmap pmd entry inserted at the very top of the KVA is causing the subsequent fixmap mapping code to not provide physically linear pte pages over the kmap atomic portion of the fixmap (which relies on said property to calculate pte addresses). This has caused weird boot failures in kmap_atomic much later in the boot process (initial userspace faults) on a 32-bit PAE system with a larger number of CPUs (smaller CPU counts tend not to run over into the next page so don't show up the problem). Solve this by attempting to clear out the page table, and copy any of its entries to the new one. Also, add a bug if a nonlinear condition is encountered and can't be resolved, which might save some hours of debugging if this fragile scheme ever breaks again... Once we have such logic, we can also use it to eliminate the early ioremap trickery around the page table setup for the fixmap area. This also fixes potential issues with FIX_* entries sharing the leaf page table with the early ioremap ones getting discarded by early_ioremap_clear() and not restored by early_ioremap_reset(). It at once eliminates the temporary (and configuration, namely NR_CPUS, dependent) unavailability of early fixed mappings during the time the fixmap area page tables get constructed. Finally, also replace the hard coded calculation of the initial table space needed for the fixmap area with a proper one, allowing kernels configured for large CPU counts to actually boot. Based-on: Nick Piggin Signed-off-by: Jan Beulich Signed-off-by: Ingo Molnar --- arch/x86/include/asm/io.h | 1 - arch/x86/mm/init_32.c | 48 ++++++++++++++++++++++++++++++++++++++++++++--- arch/x86/mm/ioremap.c | 25 ------------------------ 3 files changed, 45 insertions(+), 29 deletions(-) (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 05cfed4485f..1dbbdf4be9b 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -99,7 +99,6 @@ extern void __iomem *ioremap_wc(unsigned long offset, unsigned long size); * A boot-time mapping is currently limited to at most 16 pages. */ extern void early_ioremap_init(void); -extern void early_ioremap_clear(void); extern void early_ioremap_reset(void); extern void __iomem *early_ioremap(unsigned long offset, unsigned long size); extern void __iomem *early_memremap(unsigned long offset, unsigned long size); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 88f1b10de3b..2cef0507441 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -138,6 +138,47 @@ static pte_t * __init one_page_table_init(pmd_t *pmd) return pte_offset_kernel(pmd, 0); } +static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd, + unsigned long vaddr, pte_t *lastpte) +{ +#ifdef CONFIG_HIGHMEM + /* + * Something (early fixmap) may already have put a pte + * page here, which causes the page table allocation + * to become nonlinear. Attempt to fix it, and if it + * is still nonlinear then we have to bug. + */ + int pmd_idx_kmap_begin = fix_to_virt(FIX_KMAP_END) >> PMD_SHIFT; + int pmd_idx_kmap_end = fix_to_virt(FIX_KMAP_BEGIN) >> PMD_SHIFT; + + if (pmd_idx_kmap_begin != pmd_idx_kmap_end + && (vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin + && (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end + && ((__pa(pte) >> PAGE_SHIFT) < table_start + || (__pa(pte) >> PAGE_SHIFT) >= table_end)) { + pte_t *newpte; + int i; + + BUG_ON(after_init_bootmem); + newpte = alloc_low_page(); + for (i = 0; i < PTRS_PER_PTE; i++) + set_pte(newpte + i, pte[i]); + + paravirt_alloc_pte(&init_mm, __pa(newpte) >> PAGE_SHIFT); + set_pmd(pmd, __pmd(__pa(newpte)|_PAGE_TABLE)); + BUG_ON(newpte != pte_offset_kernel(pmd, 0)); + __flush_tlb_all(); + + paravirt_release_pte(__pa(pte) >> PAGE_SHIFT); + pte = newpte; + } + BUG_ON(vaddr < fix_to_virt(FIX_KMAP_BEGIN - 1) + && vaddr > fix_to_virt(FIX_KMAP_END) + && lastpte && lastpte + PTRS_PER_PTE != pte); +#endif + return pte; +} + /* * This function initializes a certain range of kernel virtual memory * with new bootmem page tables, everywhere page tables are missing in @@ -154,6 +195,7 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base) unsigned long vaddr; pgd_t *pgd; pmd_t *pmd; + pte_t *pte = NULL; vaddr = start; pgd_idx = pgd_index(vaddr); @@ -165,7 +207,8 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base) pmd = pmd + pmd_index(vaddr); for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end); pmd++, pmd_idx++) { - one_page_table_init(pmd); + pte = page_table_kmap_check(one_page_table_init(pmd), + pmd, vaddr, pte); vaddr += PMD_SIZE; } @@ -508,7 +551,6 @@ static void __init early_ioremap_page_table_range_init(pgd_t *pgd_base) * Fixed mappings, only the page table structure has to be * created - mappings will be set by set_fixmap(): */ - early_ioremap_clear(); vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK; end = (FIXADDR_TOP + PMD_SIZE - 1) & PMD_MASK; page_table_range_init(vaddr, end, pgd_base); @@ -801,7 +843,7 @@ static void __init find_early_table_space(unsigned long end, int use_pse) tables += PAGE_ALIGN(ptes * sizeof(pte_t)); /* for fixmap */ - tables += PAGE_SIZE * 2; + tables += PAGE_ALIGN(__end_of_fixed_addresses * sizeof(pte_t)); /* * RED-PEN putting page tables only on node 0 could diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index bd85d42819e..af750ab973b 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -557,34 +557,9 @@ void __init early_ioremap_init(void) } } -void __init early_ioremap_clear(void) -{ - pmd_t *pmd; - - if (early_ioremap_debug) - printk(KERN_INFO "early_ioremap_clear()\n"); - - pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)); - pmd_clear(pmd); - paravirt_release_pte(__pa(bm_pte) >> PAGE_SHIFT); - __flush_tlb_all(); -} - void __init early_ioremap_reset(void) { - enum fixed_addresses idx; - unsigned long addr, phys; - pte_t *pte; - after_paging_init = 1; - for (idx = FIX_BTMAP_BEGIN; idx >= FIX_BTMAP_END; idx--) { - addr = fix_to_virt(idx); - pte = early_ioremap_pte(addr); - if (pte_present(*pte)) { - phys = pte_val(*pte) & PAGE_MASK; - set_fixmap(idx, phys); - } - } } static void __init __early_set_fixmap(enum fixed_addresses idx, -- cgit v1.2.3-70-g09d2 From 552b8aa4d1edcc1c764ff6f61a7686347a2d1827 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 20 Jan 2009 09:31:49 +0100 Subject: Revert "x86: signal: change type of paramter for sys_rt_sigreturn()" This reverts commit 4217458dafaa57d8e26a46f5d05ab8c53cf64191. Justin Madru bisected this commit, it was causing weird Firefox crashes. The reason is that GCC mis-optimizes (re-uses) the on-stack parameters of the calling frame, which corrupts the syscall return pt_regs state and thus corrupts user-space register state. So we go back to the slightly less clean but more optimization-safe method of getting to pt_regs. Also add a comment to explain this. Resolves: http://bugzilla.kernel.org/show_bug.cgi?id=12505 Reported-and-bisected-by: Justin Madru Tested-by: Justin Madru Signed-off-by: Ingo Molnar --- arch/x86/include/asm/syscalls.h | 2 +- arch/x86/kernel/signal.c | 11 +++++++++-- 2 files changed, 10 insertions(+), 3 deletions(-) (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index 9c6797c3e56..c0b0bda754e 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -40,7 +40,7 @@ asmlinkage int sys_sigaction(int, const struct old_sigaction __user *, struct old_sigaction __user *); asmlinkage int sys_sigaltstack(unsigned long); asmlinkage unsigned long sys_sigreturn(unsigned long); -asmlinkage int sys_rt_sigreturn(struct pt_regs); +asmlinkage int sys_rt_sigreturn(unsigned long); /* kernel/ioport.c */ asmlinkage long sys_iopl(unsigned long); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 89bb7668041..df0587f24c5 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -632,9 +632,16 @@ badframe: } #ifdef CONFIG_X86_32 -asmlinkage int sys_rt_sigreturn(struct pt_regs regs) +/* + * Note: do not pass in pt_regs directly as with tail-call optimization + * GCC will incorrectly stomp on the caller's frame and corrupt user-space + * register state: + */ +asmlinkage int sys_rt_sigreturn(unsigned long __unused) { - return do_rt_sigreturn(®s); + struct pt_regs *regs = (struct pt_regs *)&__unused; + + return do_rt_sigreturn(regs); } #else /* !CONFIG_X86_32 */ asmlinkage long sys_rt_sigreturn(struct pt_regs *regs) -- cgit v1.2.3-70-g09d2 From bdf21a49bab28f0d9613e8d8724ef9c9168b61b9 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Wed, 21 Jan 2009 15:01:56 -0800 Subject: x86: add MSR_IA32_MISC_ENABLE bits to Impact: None (new bit definitions currently unused) Add bit definitions for the MSR_IA32_MISC_ENABLE MSRs to . Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/msr-index.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index cb58643947b..358acc59ae0 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -202,6 +202,35 @@ #define MSR_IA32_THERM_STATUS 0x0000019c #define MSR_IA32_MISC_ENABLE 0x000001a0 +/* MISC_ENABLE bits: architectural */ +#define MSR_IA32_MISC_ENABLE_FAST_STRING (1ULL << 0) +#define MSR_IA32_MISC_ENABLE_TCC (1ULL << 1) +#define MSR_IA32_MISC_ENABLE_EMON (1ULL << 7) +#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL (1ULL << 11) +#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL (1ULL << 12) +#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP (1ULL << 16) +#define MSR_IA32_MISC_ENABLE_MWAIT (1ULL << 18) +#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID (1ULL << 22) +#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE (1ULL << 23) +#define MSR_IA32_MISC_ENABLE_XD_DISABLE (1ULL << 34) + +/* MISC_ENABLE bits: model-specific, meaning may vary from core to core */ +#define MSR_IA32_MISC_ENABLE_X87_COMPAT (1ULL << 2) +#define MSR_IA32_MISC_ENABLE_TM1 (1ULL << 3) +#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE (1ULL << 4) +#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE (1ULL << 6) +#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK (1ULL << 8) +#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE (1ULL << 9) +#define MSR_IA32_MISC_ENABLE_FERR (1ULL << 10) +#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX (1ULL << 10) +#define MSR_IA32_MISC_ENABLE_TM2 (1ULL << 13) +#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE (1ULL << 19) +#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK (1ULL << 20) +#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT (1ULL << 24) +#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE (1ULL << 37) +#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE (1ULL << 38) +#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE (1ULL << 39) + /* Intel Model 6 */ #define MSR_P6_EVNTSEL0 0x00000186 #define MSR_P6_EVNTSEL1 0x00000187 -- cgit v1.2.3-70-g09d2 From 42ef73fe134732b2e91c0326df5fd568da17c4b2 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 23 Jan 2009 17:37:49 +0100 Subject: x86, mm: fix pte_free() On -rt we were seeing spurious bad page states like: Bad page state in process 'firefox' page:c1bc2380 flags:0x40000000 mapping:c1bc2390 mapcount:0 count:0 Trying to fix it up, but a reboot is needed Backtrace: Pid: 503, comm: firefox Not tainted 2.6.26.8-rt13 #3 [] ? printk+0x14/0x19 [] bad_page+0x4e/0x79 [] free_hot_cold_page+0x5b/0x1d3 [] free_hot_page+0xf/0x11 [] __free_pages+0x20/0x2b [] __pte_alloc+0x87/0x91 [] handle_mm_fault+0xe4/0x733 [] ? rt_mutex_down_read_trylock+0x57/0x63 [] ? rt_mutex_down_read_trylock+0x57/0x63 [] do_page_fault+0x36f/0x88a This is the case where a concurrent fault already installed the PTE and we get to free the newly allocated one. This is due to pgtable_page_ctor() doing the spin_lock_init(&page->ptl) which is overlaid with the {private, mapping} struct. union { struct { unsigned long private; struct address_space *mapping; }; spinlock_t ptl; struct kmem_cache *slab; struct page *first_page; }; Normally the spinlock is small enough to not stomp on page->mapping, but PREEMPT_RT=y has huge 'spin'locks. But lockdep kernels should also be able to trigger this splat, as the lock tracking code grows the spinlock to cover page->mapping. The obvious fix is calling pgtable_page_dtor() like the regular pte free path __pte_free_tlb() does. It seems all architectures except x86 and nm10300 already do this, and nm10300 doesn't seem to use pgtable_page_ctor(), which suggests it doesn't do SMP or simply doesnt do MMU at all or something. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar Cc: --- arch/x86/include/asm/pgalloc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index cb7c151a8bf..dd14c54ac71 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -42,6 +42,7 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) static inline void pte_free(struct mm_struct *mm, struct page *pte) { + pgtable_page_dtor(pte); __free_page(pte); } -- cgit v1.2.3-70-g09d2 From e1b4d1143651fb3838be1117785b6e0386fa151f Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 25 Jan 2009 16:57:00 +0100 Subject: x86: use standard PIT frequency the RDC and ELAN platforms use slighly different PIT clocks, resulting in a timex.h hack that changes PIT_TICK_RATE during build time. But if a tester enables any of these platform support .config options, the PIT will be miscalibrated on standard PC platforms. So use one frequency - in a subsequent patch we'll add a quirk to allow x86 platforms to define different PIT frequencies. Signed-off-by: Ingo Molnar --- arch/x86/include/asm/timex.h | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/timex.h b/arch/x86/include/asm/timex.h index 1287dc1347d..b5c9d45c981 100644 --- a/arch/x86/include/asm/timex.h +++ b/arch/x86/include/asm/timex.h @@ -1,18 +1,13 @@ -/* x86 architecture timex specifications */ #ifndef _ASM_X86_TIMEX_H #define _ASM_X86_TIMEX_H #include #include -#ifdef CONFIG_X86_ELAN -# define PIT_TICK_RATE 1189200 /* AMD Elan has different frequency! */ -#elif defined(CONFIG_X86_RDC321X) -# define PIT_TICK_RATE 1041667 /* Underlying HZ for R8610 */ -#else -# define PIT_TICK_RATE 1193182 /* Underlying HZ */ -#endif -#define CLOCK_TICK_RATE PIT_TICK_RATE +/* The PIT ticks at this frequency (in HZ): */ +#define PIT_TICK_RATE 1193182 + +#define CLOCK_TICK_RATE PIT_TICK_RATE #define ARCH_HAS_READ_CURRENT_TIMER -- cgit v1.2.3-70-g09d2 From 5872fb94f85d2e4fdef94657bd14e1a492df9825 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 29 Jan 2009 16:28:02 -0800 Subject: Documentation: move DMA-mapping.txt to Doc/PCI/ Move DMA-mapping.txt to Documentation/PCI/. DMA-mapping.txt was supposed to be moved from Documentation/ to Documentation/PCI/. The 00-INDEX files in those two directories were updated, along with a few other text files, but the file itself somehow escaped being moved, so move it and update more text files and source files with its new location. Signed-off-by: Randy Dunlap Acked-by: Greg Kroah-Hartman cc: Jesse Barnes Signed-off-by: Linus Torvalds --- Documentation/DMA-API.txt | 2 +- Documentation/IO-mapping.txt | 4 ++-- Documentation/block/biodoc.txt | 5 +++-- Documentation/usb/dma.txt | 11 ++++++----- arch/ia64/hp/common/sba_iommu.c | 12 ++++++------ arch/parisc/include/asm/dma-mapping.h | 2 +- arch/parisc/kernel/pci-dma.c | 2 +- arch/x86/include/asm/dma-mapping.h | 4 ++-- arch/x86/kernel/pci-gart_64.c | 2 +- drivers/parisc/sba_iommu.c | 18 +++++++++--------- drivers/staging/altpciechdma/altpciechdma.c | 4 ++-- include/media/videobuf-dma-sg.h | 2 +- 12 files changed, 35 insertions(+), 33 deletions(-) (limited to 'arch/x86/include/asm') diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt index 52441694fe0..2a3fcc55e98 100644 --- a/Documentation/DMA-API.txt +++ b/Documentation/DMA-API.txt @@ -5,7 +5,7 @@ This document describes the DMA API. For a more gentle introduction phrased in terms of the pci_ equivalents (and actual examples) see -DMA-mapping.txt +Documentation/PCI/PCI-DMA-mapping.txt. This API is split into two pieces. Part I describes the API and the corresponding pci_ API. Part II describes the extensions to the API diff --git a/Documentation/IO-mapping.txt b/Documentation/IO-mapping.txt index 86edb61bdee..78a440695e1 100644 --- a/Documentation/IO-mapping.txt +++ b/Documentation/IO-mapping.txt @@ -1,6 +1,6 @@ [ NOTE: The virt_to_bus() and bus_to_virt() functions have been - superseded by the functionality provided by the PCI DMA - interface (see Documentation/DMA-mapping.txt). They continue + superseded by the functionality provided by the PCI DMA interface + (see Documentation/PCI/PCI-DMA-mapping.txt). They continue to be documented below for historical purposes, but new code must not use them. --davidm 00/12/12 ] diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt index 3c5434c83da..5d2480d33b4 100644 --- a/Documentation/block/biodoc.txt +++ b/Documentation/block/biodoc.txt @@ -186,8 +186,9 @@ a virtual address mapping (unlike the earlier scheme of virtual address do not have a corresponding kernel virtual address space mapping) and low-memory pages. -Note: Please refer to DMA-mapping.txt for a discussion on PCI high mem DMA -aspects and mapping of scatter gather lists, and support for 64 bit PCI. +Note: Please refer to Documentation/PCI/PCI-DMA-mapping.txt for a discussion +on PCI high mem DMA aspects and mapping of scatter gather lists, and support +for 64 bit PCI. Special handling is required only for cases where i/o needs to happen on pages at physical memory addresses beyond what the device can support. In these diff --git a/Documentation/usb/dma.txt b/Documentation/usb/dma.txt index e8b50b7de9d..cfdcd16e3ab 100644 --- a/Documentation/usb/dma.txt +++ b/Documentation/usb/dma.txt @@ -6,8 +6,9 @@ in the kernel usb programming guide (kerneldoc, from the source code). API OVERVIEW The big picture is that USB drivers can continue to ignore most DMA issues, -though they still must provide DMA-ready buffers (see DMA-mapping.txt). -That's how they've worked through the 2.4 (and earlier) kernels. +though they still must provide DMA-ready buffers (see +Documentation/PCI/PCI-DMA-mapping.txt). That's how they've worked through +the 2.4 (and earlier) kernels. OR: they can now be DMA-aware. @@ -62,8 +63,8 @@ and effects like cache-trashing can impose subtle penalties. force a consistent memory access ordering by using memory barriers. It's not using a streaming DMA mapping, so it's good for small transfers on systems where the I/O would otherwise thrash an IOMMU mapping. (See - Documentation/DMA-mapping.txt for definitions of "coherent" and "streaming" - DMA mappings.) + Documentation/PCI/PCI-DMA-mapping.txt for definitions of "coherent" and + "streaming" DMA mappings.) Asking for 1/Nth of a page (as well as asking for N pages) is reasonably space-efficient. @@ -93,7 +94,7 @@ WORKING WITH EXISTING BUFFERS Existing buffers aren't usable for DMA without first being mapped into the DMA address space of the device. However, most buffers passed to your driver can safely be used with such DMA mapping. (See the first section -of DMA-mapping.txt, titled "What memory is DMA-able?") +of Documentation/PCI/PCI-DMA-mapping.txt, titled "What memory is DMA-able?") - When you're using scatterlists, you can map everything at once. On some systems, this kicks in an IOMMU and turns the scatterlists into single diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c index d98f0f4ff83..6d5e6c5630e 100644 --- a/arch/ia64/hp/common/sba_iommu.c +++ b/arch/ia64/hp/common/sba_iommu.c @@ -906,7 +906,7 @@ sba_mark_invalid(struct ioc *ioc, dma_addr_t iova, size_t byte_cnt) * @dir: R/W or both. * @attrs: optional dma attributes * - * See Documentation/DMA-mapping.txt + * See Documentation/PCI/PCI-DMA-mapping.txt */ dma_addr_t sba_map_single_attrs(struct device *dev, void *addr, size_t size, int dir, @@ -1024,7 +1024,7 @@ sba_mark_clean(struct ioc *ioc, dma_addr_t iova, size_t size) * @dir: R/W or both. * @attrs: optional dma attributes * - * See Documentation/DMA-mapping.txt + * See Documentation/PCI/PCI-DMA-mapping.txt */ void sba_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size, int dir, struct dma_attrs *attrs) @@ -1102,7 +1102,7 @@ EXPORT_SYMBOL(sba_unmap_single_attrs); * @size: number of bytes mapped in driver buffer. * @dma_handle: IOVA of new buffer. * - * See Documentation/DMA-mapping.txt + * See Documentation/PCI/PCI-DMA-mapping.txt */ void * sba_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags) @@ -1165,7 +1165,7 @@ sba_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp * @vaddr: virtual address IOVA of "consistent" buffer. * @dma_handler: IO virtual address of "consistent" buffer. * - * See Documentation/DMA-mapping.txt + * See Documentation/PCI/PCI-DMA-mapping.txt */ void sba_free_coherent (struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle) { @@ -1420,7 +1420,7 @@ sba_coalesce_chunks(struct ioc *ioc, struct device *dev, * @dir: R/W or both. * @attrs: optional dma attributes * - * See Documentation/DMA-mapping.txt + * See Documentation/PCI/PCI-DMA-mapping.txt */ int sba_map_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents, int dir, struct dma_attrs *attrs) @@ -1512,7 +1512,7 @@ EXPORT_SYMBOL(sba_map_sg_attrs); * @dir: R/W or both. * @attrs: optional dma attributes * - * See Documentation/DMA-mapping.txt + * See Documentation/PCI/PCI-DMA-mapping.txt */ void sba_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents, int dir, struct dma_attrs *attrs) diff --git a/arch/parisc/include/asm/dma-mapping.h b/arch/parisc/include/asm/dma-mapping.h index 53af696f23d..da694338090 100644 --- a/arch/parisc/include/asm/dma-mapping.h +++ b/arch/parisc/include/asm/dma-mapping.h @@ -5,7 +5,7 @@ #include #include -/* See Documentation/DMA-mapping.txt */ +/* See Documentation/PCI/PCI-DMA-mapping.txt */ struct hppa_dma_ops { int (*dma_supported)(struct device *dev, u64 mask); void *(*alloc_consistent)(struct device *dev, size_t size, dma_addr_t *iova, gfp_t flag); diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c index ccd61b9567a..df47895db82 100644 --- a/arch/parisc/kernel/pci-dma.c +++ b/arch/parisc/kernel/pci-dma.c @@ -2,7 +2,7 @@ ** PARISC 1.1 Dynamic DMA mapping support. ** This implementation is for PA-RISC platforms that do not support ** I/O TLBs (aka DMA address translation hardware). -** See Documentation/DMA-mapping.txt for interface definitions. +** See Documentation/PCI/PCI-DMA-mapping.txt for interface definitions. ** ** (c) Copyright 1999,2000 Hewlett-Packard Company ** (c) Copyright 2000 Grant Grundler diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 4035357f5b9..132a134d12f 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -2,8 +2,8 @@ #define _ASM_X86_DMA_MAPPING_H /* - * IOMMU interface. See Documentation/DMA-mapping.txt and DMA-API.txt for - * documentation. + * IOMMU interface. See Documentation/PCI/PCI-DMA-mapping.txt and + * Documentation/DMA-API.txt for documentation. */ #include diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index 00c2bcd4146..d5768b1af08 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -5,7 +5,7 @@ * This allows to use PCI devices that only support 32bit addresses on systems * with more than 4GB. * - * See Documentation/DMA-mapping.txt for the interface specification. + * See Documentation/PCI/PCI-DMA-mapping.txt for the interface specification. * * Copyright 2002 Andi Kleen, SuSE Labs. * Subject to the GNU General Public License v2 only. diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c index 3fac8f81d59..a70cf16ee1a 100644 --- a/drivers/parisc/sba_iommu.c +++ b/drivers/parisc/sba_iommu.c @@ -668,7 +668,7 @@ sba_mark_invalid(struct ioc *ioc, dma_addr_t iova, size_t byte_cnt) * @dev: instance of PCI owned by the driver that's asking * @mask: number of address bits this PCI device can handle * - * See Documentation/DMA-mapping.txt + * See Documentation/PCI/PCI-DMA-mapping.txt */ static int sba_dma_supported( struct device *dev, u64 mask) { @@ -680,8 +680,8 @@ static int sba_dma_supported( struct device *dev, u64 mask) return(0); } - /* Documentation/DMA-mapping.txt tells drivers to try 64-bit first, - * then fall back to 32-bit if that fails. + /* Documentation/PCI/PCI-DMA-mapping.txt tells drivers to try 64-bit + * first, then fall back to 32-bit if that fails. * We are just "encouraging" 32-bit DMA masks here since we can * never allow IOMMU bypass unless we add special support for ZX1. */ @@ -706,7 +706,7 @@ static int sba_dma_supported( struct device *dev, u64 mask) * @size: number of bytes to map in driver buffer. * @direction: R/W or both. * - * See Documentation/DMA-mapping.txt + * See Documentation/PCI/PCI-DMA-mapping.txt */ static dma_addr_t sba_map_single(struct device *dev, void *addr, size_t size, @@ -785,7 +785,7 @@ sba_map_single(struct device *dev, void *addr, size_t size, * @size: number of bytes mapped in driver buffer. * @direction: R/W or both. * - * See Documentation/DMA-mapping.txt + * See Documentation/PCI/PCI-DMA-mapping.txt */ static void sba_unmap_single(struct device *dev, dma_addr_t iova, size_t size, @@ -861,7 +861,7 @@ sba_unmap_single(struct device *dev, dma_addr_t iova, size_t size, * @size: number of bytes mapped in driver buffer. * @dma_handle: IOVA of new buffer. * - * See Documentation/DMA-mapping.txt + * See Documentation/PCI/PCI-DMA-mapping.txt */ static void *sba_alloc_consistent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) @@ -892,7 +892,7 @@ static void *sba_alloc_consistent(struct device *hwdev, size_t size, * @vaddr: virtual address IOVA of "consistent" buffer. * @dma_handler: IO virtual address of "consistent" buffer. * - * See Documentation/DMA-mapping.txt + * See Documentation/PCI/PCI-DMA-mapping.txt */ static void sba_free_consistent(struct device *hwdev, size_t size, void *vaddr, @@ -927,7 +927,7 @@ int dump_run_sg = 0; * @nents: number of entries in list * @direction: R/W or both. * - * See Documentation/DMA-mapping.txt + * See Documentation/PCI/PCI-DMA-mapping.txt */ static int sba_map_sg(struct device *dev, struct scatterlist *sglist, int nents, @@ -1011,7 +1011,7 @@ sba_map_sg(struct device *dev, struct scatterlist *sglist, int nents, * @nents: number of entries in list * @direction: R/W or both. * - * See Documentation/DMA-mapping.txt + * See Documentation/PCI/PCI-DMA-mapping.txt */ static void sba_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents, diff --git a/drivers/staging/altpciechdma/altpciechdma.c b/drivers/staging/altpciechdma/altpciechdma.c index 8e2b4ca0651..f516140ca97 100644 --- a/drivers/staging/altpciechdma/altpciechdma.c +++ b/drivers/staging/altpciechdma/altpciechdma.c @@ -531,7 +531,7 @@ static int __devinit dma_test(struct ape_dev *ape, struct pci_dev *dev) goto fail; /* allocate and map coherently-cached memory for a DMA-able buffer */ - /* @see 2.6.26.2/Documentation/DMA-mapping.txt line 318 */ + /* @see Documentation/PCI/PCI-DMA-mapping.txt, near line 318 */ buffer_virt = (u8 *)pci_alloc_consistent(dev, PAGE_SIZE * 4, &buffer_bus); if (!buffer_virt) { printk(KERN_DEBUG "Could not allocate coherent DMA buffer.\n"); @@ -846,7 +846,7 @@ static int __devinit probe(struct pci_dev *dev, const struct pci_device_id *id) #if 1 // @todo For now, disable 64-bit, because I do not understand the implications (DAC!) /* query for DMA transfer */ - /* @see Documentation/DMA-mapping.txt */ + /* @see Documentation/PCI/PCI-DMA-mapping.txt */ if (!pci_set_dma_mask(dev, DMA_64BIT_MASK)) { pci_set_consistent_dma_mask(dev, DMA_64BIT_MASK); /* use 64-bit DMA */ diff --git a/include/media/videobuf-dma-sg.h b/include/media/videobuf-dma-sg.h index 90edd22d343..dda47f0082e 100644 --- a/include/media/videobuf-dma-sg.h +++ b/include/media/videobuf-dma-sg.h @@ -49,7 +49,7 @@ struct scatterlist* videobuf_pages_to_sg(struct page **pages, int nr_pages, * does memory allocation too using vmalloc_32(). * * videobuf_dma_*() - * see Documentation/DMA-mapping.txt, these functions to + * see Documentation/PCI/PCI-DMA-mapping.txt, these functions to * basically the same. The map function does also build a * scatterlist for the buffer (and unmap frees it ...) * -- cgit v1.2.3-70-g09d2 From 999721ca6d0c2540341acb73ac9048cbd6b05d3a Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Fri, 30 Jan 2009 22:44:58 +0530 Subject: headers_check fix: x86, e820.h fix the following 'make headers_check' warning: usr/include/asm/e820.h:44: found __[us]{8,16,32,64} type without #include Signed-off-by: Jaswinder Singh Rajput --- arch/x86/include/asm/e820.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index 3d8ceddbd40..00d41ce4c84 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -49,6 +49,7 @@ #define E820_RESERVED_KERN 128 #ifndef __ASSEMBLY__ +#include struct e820entry { __u64 addr; /* start of memory segment */ __u64 size; /* size of memory segment */ -- cgit v1.2.3-70-g09d2 From cef3767852a9b1a7ff4a8dfe0969e2d32eb728df Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Fri, 30 Jan 2009 22:46:08 +0530 Subject: headers_check fix: x86, kvm.h fix the following 'make headers_check' warnings: usr/include/asm/kvm.h:9: include of is preferred over usr/include/asm/kvm.h:16: found __[us]{8,16,32,64} type without #include Signed-off-by: Jaswinder Singh Rajput --- arch/x86/include/asm/kvm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index b95162af0bf..d2e3bf3608a 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -6,7 +6,7 @@ * */ -#include +#include #include /* Architectural interrupt line count. */ -- cgit v1.2.3-70-g09d2 From 999b697b9d8b15756e65da72c816ef4363a945a5 Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Fri, 30 Jan 2009 22:47:27 +0530 Subject: headers_check fix: x86, mce.h fix the following 'make headers_check' warnings: usr/include/asm/mce.h:7: include of is preferred over usr/include/asm/mce.h:29: found __[us]{8,16,32,64} type without #include Signed-off-by: Jaswinder Singh Rajput --- arch/x86/include/asm/mce.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 1d6e17c2f23..32c6e17b960 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -3,8 +3,8 @@ #ifdef __x86_64__ +#include #include -#include /* * Machine Check support for x86 @@ -115,8 +115,6 @@ extern int mce_notify_user(void); #endif /* !CONFIG_X86_32 */ - - #ifdef CONFIG_X86_MCE extern void mcheck_init(struct cpuinfo_x86 *c); #else @@ -126,5 +124,4 @@ extern void stop_mce(void); extern void restart_mce(void); #endif /* __KERNEL__ */ - #endif /* _ASM_X86_MCE_H */ -- cgit v1.2.3-70-g09d2 From d122072cc079d299e5191c9cbb6162ba8791624c Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Fri, 30 Jan 2009 22:48:17 +0530 Subject: headers_check fix: x86, mtrr.h fix the following 'make headers_check' warning: usr/include/asm/mtrr.h:61: found __[us]{8,16,32,64} type without #include Signed-off-by: Jaswinder Singh Rajput --- arch/x86/include/asm/mtrr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h index 14080d22edb..a51ada8467d 100644 --- a/arch/x86/include/asm/mtrr.h +++ b/arch/x86/include/asm/mtrr.h @@ -23,6 +23,7 @@ #ifndef _ASM_X86_MTRR_H #define _ASM_X86_MTRR_H +#include #include #include -- cgit v1.2.3-70-g09d2 From 420ab35eef206d147973d26db14b5618868726be Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Fri, 30 Jan 2009 22:52:16 +0530 Subject: headers_check fix: x86, ptrace-abi.h fix the following 'make headers_check' warnings: usr/include/asm/ptrace-abi.h:86: include of is preferred over usr/include/asm/ptrace-abi.h:93: found __[us]{8,16,32,64} type without #include Signed-off-by: Jaswinder Singh Rajput --- arch/x86/include/asm/ptrace-abi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/ptrace-abi.h b/arch/x86/include/asm/ptrace-abi.h index 25f1bb8fc62..8e0f8d199e0 100644 --- a/arch/x86/include/asm/ptrace-abi.h +++ b/arch/x86/include/asm/ptrace-abi.h @@ -83,7 +83,7 @@ #ifdef CONFIG_X86_PTRACE_BTS #ifndef __ASSEMBLY__ -#include +#include /* configuration/status structure used in PTRACE_BTS_CONFIG and PTRACE_BTS_STATUS commands. -- cgit v1.2.3-70-g09d2 From e59afe6a21dce7bb3c63ba4f894a3195ae3d5529 Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Fri, 30 Jan 2009 22:53:49 +0530 Subject: headers_check fix: x86, sigcontext.h fix the following 'make headers_check' warnings: usr/include/asm/sigcontext.h:5: include of is preferred over usr/include/asm/sigcontext.h:24: found __[us]{8,16,32,64} type without #include Signed-off-by: Jaswinder Singh Rajput --- arch/x86/include/asm/sigcontext.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h index 0afcb5e58ac..ec666491aaa 100644 --- a/arch/x86/include/asm/sigcontext.h +++ b/arch/x86/include/asm/sigcontext.h @@ -2,7 +2,7 @@ #define _ASM_X86_SIGCONTEXT_H #include -#include +#include #define FP_XSTATE_MAGIC1 0x46505853U #define FP_XSTATE_MAGIC2 0x46505845U -- cgit v1.2.3-70-g09d2 From 2de548faa78c650bb20c4680ee3a225cca33a45d Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Fri, 30 Jan 2009 22:55:20 +0530 Subject: headers_check fix: x86, sigcontext32.h fix the following 'make headers_check' warning: usr/include/asm/sigcontext32.h:20: found __[us]{8,16,32,64} type without #include Signed-off-by: Jaswinder Singh Rajput --- arch/x86/include/asm/sigcontext32.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/sigcontext32.h b/arch/x86/include/asm/sigcontext32.h index 6126188cf3a..ad1478c4ae1 100644 --- a/arch/x86/include/asm/sigcontext32.h +++ b/arch/x86/include/asm/sigcontext32.h @@ -1,6 +1,8 @@ #ifndef _ASM_X86_SIGCONTEXT32_H #define _ASM_X86_SIGCONTEXT32_H +#include + /* signal context for 32bit programs. */ #define X86_FXSR_MAGIC 0x0000 -- cgit v1.2.3-70-g09d2 From 7cff3608d2553a045b676fa81b0cf54e4f2cc5ce Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Rajput Date: Fri, 30 Jan 2009 22:57:38 +0530 Subject: headers_check fix: x86, swab.h fix the following 'make headers_check' warnings: usr/include/asm/swab.h:4: include of is preferred over usr/include/asm/swab.h:7: found __[us]{8,16,32,64} type without #include Signed-off-by: Jaswinder Singh Rajput --- arch/x86/include/asm/swab.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/swab.h b/arch/x86/include/asm/swab.h index 306d4178ffc..557cd9f0066 100644 --- a/arch/x86/include/asm/swab.h +++ b/arch/x86/include/asm/swab.h @@ -1,7 +1,7 @@ #ifndef _ASM_X86_SWAB_H #define _ASM_X86_SWAB_H -#include +#include #include static inline __attribute_const__ __u32 __arch_swab32(__u32 val) -- cgit v1.2.3-70-g09d2